High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

RA-MVS			97.90 5		99.58 1	95.25 22	98.70 11	98.56 29	94.47 81	98.94 21	98.86 39	94.67 13	99.88 4	97.61 42	99.68 4

aaatest				98.00 25	99.56 2	94.50 38	98.69 12	98.70 16	93.45 126	98.73 33	98.53 55		99.86 12	97.40 52	99.58 27	99.65 21

MED-MVS		98.08 1	98.08 2	98.06 21	99.56 2	94.50 38	98.69 12	98.70 16	95.63 26	98.73 33	98.95 21	95.46 7	99.86 12	97.40 52	99.63 18	99.82 1

TestfortrainingZip a		97.79 8	97.62 14	98.28 10	99.56 2	95.15 26	98.69 12	98.35 42	95.63 26	98.95 20	98.95 21	93.45 26	99.88 4	96.63 72	98.41 138	99.82 1

FOURS1					99.55 5	93.34 74	99.29 1	98.35 42	94.98 49	98.49 41

region2R		97.07 42	96.84 53	97.77 39	99.46 6	93.79 62	98.52 21	98.24 65	93.19 137	97.14 80	98.34 77	91.59 63	99.87 9	95.46 126	99.59 23	99.64 25

DVP-MVS		97.91 5	97.81 7	98.22 15	99.45 7	95.36 15	98.21 49	97.85 140	94.92 53	98.73 33	98.87 34	95.08 9	99.84 28	97.52 44	99.67 7	99.48 57
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.51 4	99.45 7	95.93 6	98.21 49	98.28 53					99.86 12	97.52 44	99.67 7	99.75 8

test0726					99.45 7	95.36 15	98.31 33	98.29 51	94.92 53	98.99 19	98.92 26	95.08 9

ACMMPR		97.07 42	96.84 53	97.79 35	99.44 10	93.88 60	98.52 21	98.31 48	93.21 134	97.15 79	98.33 80	91.35 68	99.86 12	95.63 117	99.59 23	99.62 27

SED-MVS		98.05 3	97.99 3	98.24 12	99.42 11	95.30 19	98.25 41	98.27 57	95.13 43	99.19 14	98.89 31	95.54 5	99.85 23	97.52 44	99.66 11	99.56 41

IU-MVS					99.42 11	95.39 13		97.94 127	90.40 277	98.94 21				97.41 51	99.66 11	99.74 10

test_241102_ONE					99.42 11	95.30 19		98.27 57	95.09 46	99.19 14	98.81 41	95.54 5	99.65 82

HFP-MVS		97.14 38	96.92 49	97.83 31	99.42 11	94.12 53	98.52 21	98.32 47	93.21 134	97.18 77	98.29 86	92.08 52	99.83 33	95.63 117	99.59 23	99.54 46

MSP-MVS		97.59 14	97.54 19	97.73 43	99.40 15	93.77 64	98.53 20	98.29 51	95.55 30	98.56 40	97.81 142	93.90 19	99.65 82	96.62 73	99.21 85	99.77 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
mPP-MVS		96.86 53	96.60 68	97.64 50	99.40 15	93.44 69	98.50 24	98.09 95	93.27 133	95.95 138	98.33 80	91.04 76	99.88 4	95.20 131	99.57 31	99.60 32

MP-MVS		96.77 61	96.45 79	97.72 44	99.39 17	93.80 61	98.41 29	98.06 104	93.37 129	95.54 158	98.34 77	90.59 86	99.88 4	94.83 149	99.54 34	99.49 55
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
XVS		97.18 35	96.96 47	97.81 33	99.38 18	94.03 57	98.59 18	98.20 71	94.85 56	96.59 104	98.29 86	91.70 59	99.80 42	95.66 112	99.40 63	99.62 27

X-MVStestdata		91.71 288	89.67 359	97.81 33	99.38 18	94.03 57	98.59 18	98.20 71	94.85 56	96.59 104	32.69 555	91.70 59	99.80 42	95.66 112	99.40 63	99.62 27

NormalMVS		96.36 83	96.11 88	97.12 78	99.37 20	92.90 91	97.99 70	97.63 169	95.92 17	96.57 107	97.93 116	85.34 196	99.50 124	94.99 138	99.21 85	98.97 117

lecture		97.58 16	97.63 13	97.43 60	99.37 20	92.93 90	98.86 7	98.85 5	95.27 37	98.65 38	98.90 28	91.97 55	99.80 42	97.63 39	99.21 85	99.57 37

ZNCC-MVS		96.96 47	96.67 66	97.85 30	99.37 20	94.12 53	98.49 25	98.18 79	92.64 171	96.39 118	98.18 93	91.61 61	99.88 4	95.59 122	99.55 32	99.57 37

MTAPA		97.08 40	96.78 61	97.97 28	99.37 20	94.42 43	97.24 197	98.08 96	95.07 47	96.11 129	98.59 50	90.88 82	99.90 2	96.18 95	99.50 42	99.58 36

GST-MVS		96.85 55	96.52 72	97.82 32	99.36 24	94.14 52	98.29 35	98.13 87	92.72 165	96.70 95	98.06 101	91.35 68	99.86 12	94.83 149	99.28 76	99.47 59

HPM-MVS		96.69 68	96.45 79	97.40 61	99.36 24	93.11 84	98.87 6	98.06 104	91.17 238	96.40 117	97.99 111	90.99 77	99.58 102	95.61 119	99.61 22	99.49 55
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PGM-MVS		96.81 59	96.53 71	97.65 48	99.35 26	93.53 68	97.65 133	98.98 2	92.22 188	97.14 80	98.44 66	91.17 74	99.85 23	94.35 173	99.46 48	99.57 37

CP-MVS		97.02 44	96.81 58	97.64 50	99.33 27	93.54 67	98.80 9	98.28 53	92.99 147	96.45 116	98.30 85	91.90 56	99.85 23	95.61 119	99.68 4	99.54 46

test_one_0601					99.32 28	95.20 23		98.25 63	95.13 43	98.48 42	98.87 34	95.16 8

HPM-MVS_fast		96.51 75	96.27 85	97.22 72	99.32 28	92.74 97	98.74 10	98.06 104	90.57 270	96.77 92	98.35 74	90.21 89	99.53 116	94.80 153	99.63 18	99.38 71

test-260524					99.31 30	95.74 9		98.19 76		97.99 54		93.53 24	99.87 9	98.08 29	99.63 18

MCST-MVS		97.18 35	96.84 53	98.20 16	99.30 31	95.35 17	97.12 211	98.07 101	93.54 120	96.08 131	97.69 157	93.86 20	99.71 70	96.50 77	99.39 65	99.55 44

test_part2					99.28 32	95.74 9				98.10 51

CPTT-MVS		95.57 111	95.19 117	96.70 94	99.27 33	91.48 150	98.33 32	98.11 92	87.79 365	95.17 173	98.03 105	87.09 153	99.61 94	93.51 192	99.42 58	99.02 107

TSAR-MVS + MP.		97.42 23	97.33 31	97.69 47	99.25 34	94.24 48	98.07 62	97.85 140	93.72 110	98.57 39	98.35 74	93.69 22	99.40 137	97.06 59	99.46 48	99.44 62
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CSCG		96.05 91	95.91 91	96.46 119	99.24 35	90.47 199	98.30 34	98.57 28	89.01 319	93.97 216	97.57 174	92.62 43	99.76 57	94.66 161	99.27 77	99.15 89

ACMMP		96.27 87	95.93 90	97.28 68	99.24 35	92.62 102	98.25 41	98.81 6	92.99 147	94.56 196	98.39 70	88.96 105	99.85 23	94.57 167	97.63 167	99.36 73
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MP-MVS-pluss		96.70 66	96.27 85	97.98 27	99.23 37	94.71 33	96.96 226	98.06 104	90.67 259	95.55 156	98.78 44	91.07 75	99.86 12	96.58 75	99.55 32	99.38 71
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
aaEdge-Enhanced		97.54 18	97.39 29	98.00 25	99.21 38	94.50 38	97.75 113	98.34 45	94.23 91	98.15 49	98.53 55	93.32 31	99.84 28	97.40 52	99.58 27	99.65 21

DP-MVS Recon		95.68 105	95.12 122	97.37 62	99.19 39	94.19 49	97.03 215	98.08 96	88.35 346	95.09 175	97.65 162	89.97 93	99.48 128	92.08 226	98.59 128	98.44 202

DPE-MVS		97.86 6	97.65 12	98.47 5	99.17 40	95.78 8	97.21 204	98.35 42	95.16 41	98.71 37	98.80 42	95.05 11	99.89 3	96.70 71	99.73 1	99.73 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		97.82 7	97.73 11	98.08 20	99.15 41	94.82 32	98.81 8	98.30 49	94.76 67	98.30 45	98.90 28	93.77 21	99.68 78	97.93 30	99.69 3	99.75 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SR-MVS		97.01 45	96.86 51	97.47 58	99.09 42	93.27 79	97.98 73	98.07 101	93.75 109	97.45 68	98.48 63	91.43 66	99.59 99	96.22 86	99.27 77	99.54 46

ACMMP_NAP		97.20 34	96.86 51	98.23 13	99.09 42	95.16 25	97.60 144	98.19 76	92.82 162	97.93 58	98.74 46	91.60 62	99.86 12	96.26 83	99.52 37	99.67 16

HPM-MVS++		97.34 27	96.97 45	98.47 5	99.08 44	96.16 5	97.55 154	97.97 124	95.59 28	96.61 102	97.89 124	92.57 44	99.84 28	95.95 102	99.51 40	99.40 67

114514_t		93.95 193	93.06 211	96.63 100	99.07 45	91.61 142	97.46 170	97.96 125	77.99 486	93.00 245	97.57 174	86.14 174	99.33 143	89.22 297	99.15 96	98.94 127

SMA-MVS		97.35 26	97.03 42	98.30 9	99.06 46	95.42 12	97.94 83	98.18 79	90.57 270	98.85 30	98.94 24	93.33 29	99.83 33	96.72 69	99.68 4	99.63 26
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
patch_mono-2		96.83 58	97.44 26	95.01 238	99.05 47	85.39 394	96.98 224	98.77 8	94.70 69	97.99 54	98.66 47	93.61 23	99.91 1	97.67 38	99.50 42	99.72 14

ZD-MVS					99.05 47	94.59 36		98.08 96	89.22 312	97.03 85	98.10 97	92.52 45	99.65 82	94.58 166	99.31 74

APD-MVS		96.95 48	96.60 68	98.01 23	99.03 49	94.93 31	97.72 121	98.10 94	91.50 218	98.01 53	98.32 82	92.33 48	99.58 102	94.85 146	99.51 40	99.53 49
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS-dyc-post		96.88 52	96.80 59	97.11 80	99.02 50	92.34 112	97.98 73	98.03 113	93.52 123	97.43 71	98.51 58	91.40 67	99.56 110	96.05 97	99.26 80	99.43 64

RE-MVS-def			96.72 64		99.02 50	92.34 112	97.98 73	98.03 113	93.52 123	97.43 71	98.51 58	90.71 84		96.05 97	99.26 80	99.43 64

SF-MVS		97.39 25	97.13 33	98.17 17	99.02 50	95.28 21	98.23 45	98.27 57	92.37 181	98.27 46	98.65 49	93.33 29	99.72 68	96.49 78	99.52 37	99.51 50

APD-MVS_3200maxsize		96.81 59	96.71 65	97.12 78	99.01 53	92.31 114	97.98 73	98.06 104	93.11 143	97.44 69	98.55 53	90.93 80	99.55 112	96.06 96	99.25 82	99.51 50

reproduce_model		97.51 21	97.51 22	97.50 56	98.99 54	93.01 86	97.79 109	98.21 69	95.73 25	97.99 54	99.03 16	92.63 42	99.82 35	97.80 32	99.42 58	99.67 16

reproduce-ours		97.53 19	97.51 22	97.60 52	98.97 55	93.31 77	97.71 124	98.20 71	95.80 22	97.88 59	98.98 19	92.91 34	99.81 37	97.68 34	99.43 55	99.67 16

our_new_method		97.53 19	97.51 22	97.60 52	98.97 55	93.31 77	97.71 124	98.20 71	95.80 22	97.88 59	98.98 19	92.91 34	99.81 37	97.68 34	99.43 55	99.67 16

dcpmvs_2		96.37 82	97.05 40	94.31 290	98.96 57	84.11 415	97.56 149	97.51 198	93.92 103	97.43 71	98.52 57	92.75 38	99.32 145	97.32 57	99.50 42	99.51 50

9.14			96.75 63		98.93 58		97.73 118	98.23 68	91.28 230	97.88 59	98.44 66	93.00 33	99.65 82	95.76 109	99.47 47

CDPH-MVS		95.97 95	95.38 110	97.77 39	98.93 58	94.44 42	96.35 297	97.88 133	86.98 385	96.65 99	97.89 124	91.99 54	99.47 129	92.26 215	99.46 48	99.39 69

save fliter					98.91 60	94.28 45	97.02 217	98.02 116	95.35 34

CNVR-MVS		97.68 9	97.44 26	98.37 7	98.90 61	95.86 7	97.27 195	98.08 96	95.81 21	97.87 62	98.31 83	94.26 16	99.68 78	97.02 60	99.49 45	99.57 37

PAPM_NR		95.01 142	94.59 150	96.26 138	98.89 62	90.68 194	97.24 197	97.73 155	91.80 205	92.93 250	96.62 247	89.13 103	99.14 171	89.21 298	97.78 164	98.97 117

OPU-MVS				98.55 3	98.82 63	96.86 3	98.25 41				98.26 89	96.04 2	99.24 154	95.36 128	99.59 23	99.56 41

NCCC		97.30 30	97.03 42	98.11 19	98.77 64	95.06 29	97.34 184	98.04 111	95.96 16	97.09 83	97.88 129	93.18 32	99.71 70	95.84 107	99.17 93	99.56 41

DP-MVS		92.76 249	91.51 274	96.52 109	98.77 64	90.99 175	97.38 181	96.08 357	82.38 460	89.29 349	97.87 130	83.77 228	99.69 76	81.37 433	96.69 215	98.89 142

MSLP-MVS++		96.94 49	97.06 37	96.59 104	98.72 66	91.86 132	97.67 129	98.49 32	94.66 72	97.24 76	98.41 69	92.31 50	98.94 199	96.61 74	99.46 48	98.96 120

TEST9					98.70 67	94.19 49	96.41 288	98.02 116	88.17 350	96.03 132	97.56 176	92.74 39	99.59 99

train_agg		96.30 86	95.83 94	97.72 44	98.70 67	94.19 49	96.41 288	98.02 116	88.58 337	96.03 132	97.56 176	92.73 40	99.59 99	95.04 135	99.37 69	99.39 69

DVP-MVS++		98.06 2	97.99 3	98.28 10	98.67 69	95.39 13	99.29 1	98.28 53	94.78 64	98.93 23	98.87 34	96.04 2	99.86 12	97.45 48	99.58 27	99.59 33

MSC_two_6792asdad				98.86 1	98.67 69	96.94 1		97.93 128					99.86 12	97.68 34	99.67 7	99.77 4

No_MVS				98.86 1	98.67 69	96.94 1		97.93 128					99.86 12	97.68 34	99.67 7	99.77 4

test_8					98.67 69	94.06 56	96.37 296	98.01 119	88.58 337	95.98 137	97.55 178	92.73 40	99.58 102

agg_prior					98.67 69	93.79 62		98.00 120		95.68 150			99.57 109

test_prior				97.23 71	98.67 69	92.99 87		98.00 120					99.41 136			99.29 76

DeepC-MVS_fast	93.89 2	96.93 50	96.64 67	97.78 37	98.64 75	94.30 44	97.41 174	98.04 111	94.81 62	96.59 104	98.37 72	91.24 71	99.64 90	95.16 133	99.52 37	99.42 66
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
新几何1				97.32 64	98.60 76	93.59 66		97.75 152	81.58 467	95.75 145	97.85 134	90.04 91	99.67 80	86.50 365	99.13 99	98.69 175

原ACMM1				96.38 127	98.59 77	91.09 173		97.89 131	87.41 377	95.22 172	97.68 158	90.25 88	99.54 114	87.95 322	99.12 101	98.49 194

AdaColmap		94.34 172	93.68 184	96.31 131	98.59 77	91.68 140	96.59 277	97.81 148	89.87 286	92.15 265	97.06 211	83.62 233	99.54 114	89.34 292	98.07 153	97.70 268

PLC	91.00 6	94.11 184	93.43 198	96.13 147	98.58 79	91.15 171	96.69 264	97.39 227	87.29 380	91.37 287	96.71 233	88.39 117	99.52 120	87.33 351	97.13 193	97.73 266
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SD-MVS		97.41 24	97.53 20	97.06 84	98.57 80	94.46 41	97.92 86	98.14 86	94.82 60	99.01 18	98.55 53	94.18 17	97.41 419	96.94 61	99.64 16	99.32 75
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
TestfortrainingZip				98.34 8	98.54 81	96.25 4	98.69 12	97.85 140	94.15 93	98.17 48	97.94 115	94.00 18	99.63 91		97.45 177	99.15 89

test12				97.65 48	98.46 82	94.26 46		97.66 163		95.52 159		90.89 81	99.46 130		99.25 82	99.22 83

MVS_111021_HR		96.68 70	96.58 70	96.99 86	98.46 82	92.31 114	96.20 315	98.90 3	94.30 90	95.86 141	97.74 151	92.33 48	99.38 140	96.04 99	99.42 58	99.28 78

OMC-MVS		95.09 135	94.70 145	96.25 141	98.46 82	91.28 158	96.43 284	97.57 182	92.04 200	94.77 191	97.96 114	87.01 154	99.09 179	91.31 243	96.77 208	98.36 209

fmvsm_s_conf0.5_n_9		97.33 28	97.57 17	96.62 103	98.43 85	90.32 211	97.80 107	98.53 30	97.24 5	99.62 3	99.14 3	88.65 112	99.80 42	99.54 1	99.15 96	99.74 10

fmvsm_s_conf0.5_n_11		97.30 30	97.59 16	96.43 121	98.42 86	91.37 155	98.04 65	98.00 120	97.30 3	99.45 5	99.21 2	89.28 100	99.80 42	99.27 10	99.35 71	98.12 233

MG-MVS		95.61 109	95.38 110	96.31 131	98.42 86	90.53 197	96.04 326	97.48 204	93.47 125	95.67 151	98.10 97	89.17 102	99.25 153	91.27 244	98.77 119	99.13 92

test_fmvsm_n_1920		97.55 17	97.89 6	96.53 107	98.41 88	91.73 134	98.01 68	99.02 1	96.37 14	99.30 8	98.92 26	92.39 47	99.79 48	99.16 15	99.46 48	98.08 241

PHI-MVS		96.77 61	96.46 78	97.71 46	98.40 89	94.07 55	98.21 49	98.45 37	89.86 287	97.11 82	98.01 108	92.52 45	99.69 76	96.03 100	99.53 35	99.36 73

F-COLMAP		93.58 208	92.98 215	95.37 217	98.40 89	88.98 276	97.18 206	97.29 243	87.75 368	90.49 307	97.10 209	85.21 200	99.50 124	86.70 362	96.72 213	97.63 270

SteuartSystems-ACMMP		97.62 13	97.53 20	97.87 29	98.39 91	94.25 47	98.43 28	98.27 57	95.34 35	98.11 50	98.56 51	94.53 14	99.71 70	96.57 76	99.62 21	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
旧先验1					98.38 92	93.38 71		97.75 152			98.09 99	92.30 51			99.01 109	99.16 87

CNLPA		94.28 173	93.53 190	96.52 109	98.38 92	92.55 106	96.59 277	96.88 302	90.13 283	91.91 273	97.24 198	85.21 200	99.09 179	87.64 340	97.83 162	97.92 251

TAPA-MVS	90.10 7	92.30 265	91.22 285	95.56 199	98.33 94	89.60 241	96.79 250	97.65 165	81.83 464	91.52 283	97.23 199	87.94 127	98.91 204	71.31 489	98.37 139	98.17 229
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		96.69 68	96.49 73	97.27 69	98.31 95	93.39 70	96.79 250	96.72 311	94.17 92	97.44 69	97.66 161	92.76 37	99.33 143	96.86 65	97.76 166	99.08 101

SPE-MVS-test		96.89 51	97.04 41	96.45 120	98.29 96	91.66 141	99.03 4	97.85 140	95.84 19	96.90 87	97.97 113	91.24 71	98.75 236	96.92 62	99.33 72	98.94 127

fmvsm_l_conf0.5_n_9		97.59 14	97.79 8	96.97 88	98.28 97	91.49 148	97.61 143	98.71 13	97.10 6	99.70 2	98.93 25	90.95 79	99.77 55	99.35 6	99.53 35	99.65 21

fmvsm_s_conf0.5_n_8		97.32 29	97.48 25	96.85 90	98.28 97	91.07 174	97.76 111	98.62 25	97.53 2	99.20 13	99.12 6	88.24 120	99.81 37	99.41 3	99.17 93	99.67 16

CHOSEN 1792x2688		94.15 180	93.51 193	96.06 152	98.27 99	89.38 255	95.18 385	98.48 34	85.60 409	93.76 221	97.11 207	83.15 243	99.61 94	91.33 242	98.72 121	99.19 84

PVSNet_BlendedMVS		94.06 186	93.92 177	94.47 278	98.27 99	89.46 252	96.73 258	98.36 39	90.17 280	94.36 201	95.24 321	88.02 124	99.58 102	93.44 194	90.72 348	94.36 433

PVSNet_Blended		94.87 153	94.56 152	95.81 177	98.27 99	89.46 252	95.47 364	98.36 39	88.84 328	94.36 201	96.09 278	88.02 124	99.58 102	93.44 194	98.18 148	98.40 205

fmvsm_l_conf0.5_n_a		97.63 12	97.76 9	97.26 70	98.25 102	92.59 104	97.81 106	98.68 18	94.93 51	99.24 11	98.87 34	93.52 25	99.79 48	99.32 7	99.21 85	99.40 67

fmvsm_s_conf0.5_n_10		97.29 32	97.40 28	96.97 88	98.24 103	91.96 130	97.89 90	98.72 12	96.77 8	99.46 4	99.06 13	87.78 131	99.84 28	99.40 4	99.27 77	99.12 95

Anonymous20231211		90.63 349	89.42 366	94.27 293	98.24 103	89.19 267	98.05 64	97.89 131	79.95 476	88.25 380	94.96 330	72.56 405	98.13 319	89.70 282	85.14 411	95.49 355

EI-MVSNet-Vis-set		96.51 75	96.47 75	96.63 100	98.24 103	91.20 164	96.89 235	97.73 155	94.74 68	96.49 111	98.49 60	90.88 82	99.58 102	96.44 79	98.32 141	99.13 92

test222					98.24 103	92.21 118	95.33 371	97.60 175	79.22 480	95.25 169	97.84 136	88.80 109			99.15 96	98.72 172

HyFIR lowres test		93.66 206	92.92 217	95.87 170	98.24 103	89.88 229	94.58 403	98.49 32	85.06 419	93.78 220	95.78 293	82.86 253	98.67 255	91.77 232	95.71 249	99.07 104

MVS_111021_LR		96.24 88	96.19 87	96.39 126	98.23 108	91.35 157	96.24 312	98.79 7	93.99 100	95.80 143	97.65 162	89.92 94	99.24 154	95.87 103	99.20 90	98.58 183

fmvsm_l_conf0.5_n		97.65 10	97.75 10	97.34 63	98.21 109	92.75 96	97.83 101	98.73 10	95.04 48	99.30 8	98.84 40	93.34 28	99.78 52	99.32 7	99.13 99	99.50 53

EI-MVSNet-UG-set		96.34 84	96.30 84	96.47 117	98.20 110	90.93 181	96.86 239	97.72 157	94.67 71	96.16 128	98.46 64	90.43 87	99.58 102	96.23 85	97.96 159	98.90 136

PVSNet_Blended_VisFu		95.27 121	94.91 132	96.38 127	98.20 110	90.86 184	97.27 195	98.25 63	90.21 279	94.18 209	97.27 196	87.48 144	99.73 64	93.53 191	97.77 165	98.55 186

Anonymous202405211		92.07 276	90.83 302	95.76 185	98.19 112	88.75 283	97.58 145	95.00 412	86.00 404	93.64 225	97.45 182	66.24 460	99.53 116	90.68 259	92.71 314	99.01 111

PatchMatch-RL		92.90 241	92.02 253	95.56 199	98.19 112	90.80 186	95.27 376	97.18 258	87.96 356	91.86 276	95.68 299	80.44 307	98.99 195	84.01 402	97.54 169	96.89 305

testdata				95.46 214	98.18 114	88.90 279		97.66 163	82.73 456	97.03 85	98.07 100	90.06 90	98.85 209	89.67 283	98.98 110	98.64 178

fmvsm_l_mol_unc0.5_1		97.99 4	98.12 1	97.58 54	98.16 115	93.34 74	96.88 237	98.28 53	97.29 4	99.72 1	99.45 1	94.43 15	99.79 48	99.20 12	99.66 11	99.62 27

CS-MVS		96.86 53	97.06 37	96.26 138	98.16 115	91.16 170	99.09 3	97.87 135	95.30 36	97.06 84	98.03 105	91.72 57	98.71 247	97.10 58	99.17 93	98.90 136

fmvsm_l_conf0.5_n_3		97.64 11	97.60 15	97.79 35	98.14 117	93.94 59	97.93 85	98.65 23	96.70 9	99.38 6	99.07 12	89.92 94	99.81 37	99.16 15	99.43 55	99.61 31

Anonymous20240529		91.98 279	90.73 308	95.73 190	98.14 117	89.40 254	97.99 70	97.72 157	79.63 478	93.54 229	97.41 186	69.94 429	99.56 110	91.04 249	91.11 341	98.22 223

LFMVS		93.60 207	92.63 231	96.52 109	98.13 119	91.27 159	97.94 83	93.39 464	90.57 270	96.29 122	98.31 83	69.00 438	99.16 166	94.18 175	95.87 244	99.12 95

SDMVSNet		94.17 177	93.61 186	95.86 173	98.09 120	91.37 155	97.35 183	98.20 71	93.18 139	91.79 277	97.28 194	79.13 331	98.93 200	94.61 164	92.84 311	97.28 290

sd_testset		93.10 230	92.45 241	95.05 234	98.09 120	89.21 264	96.89 235	97.64 167	93.18 139	91.79 277	97.28 194	75.35 379	98.65 260	88.99 304	92.84 311	97.28 290

DeepPCF-MVS	93.97 1	96.61 72	97.09 35	95.15 229	98.09 120	86.63 360	96.00 330	98.15 84	95.43 31	97.95 57	98.56 51	93.40 27	99.36 141	96.77 66	99.48 46	99.45 60

DPM-MVS		95.69 104	94.92 131	98.01 23	98.08 123	95.71 11	95.27 376	97.62 173	90.43 275	95.55 156	97.07 210	91.72 57	99.50 124	89.62 285	98.94 112	98.82 156

MVSMamba_PlusPlus		96.51 75	96.48 74	96.59 104	98.07 124	91.97 128	98.14 56	97.79 149	90.43 275	97.34 74	97.52 179	91.29 70	99.19 159	98.12 28	99.64 16	98.60 181

fmvsm_s_conf0.5_n		96.85 55	97.13 33	96.04 154	98.07 124	90.28 212	97.97 79	98.76 9	94.93 51	98.84 31	99.06 13	88.80 109	99.65 82	99.06 19	98.63 125	98.18 226

VNet		95.89 99	95.45 104	97.21 73	98.07 124	92.94 89	97.50 158	98.15 84	93.87 105	97.52 66	97.61 169	85.29 198	99.53 116	95.81 108	95.27 262	99.16 87

MM		97.29 32	96.98 44	98.23 13	98.01 127	95.03 30	98.07 62	95.76 369	97.78 1	97.52 66	98.80 42	88.09 122	99.86 12	99.44 2	99.37 69	99.80 3

MAR-MVS		94.22 175	93.46 195	96.51 113	98.00 128	92.19 121	97.67 129	97.47 208	88.13 354	93.00 245	95.84 286	84.86 210	99.51 121	87.99 321	98.17 150	97.83 261
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
fmvsm_s_conf0.5_n_3		97.15 37	97.36 30	96.52 109	97.98 129	91.19 165	97.84 98	98.65 23	97.08 7	99.25 10	99.10 7	87.88 129	99.79 48	99.32 7	99.18 92	98.59 182

fmvsm_s_conf0.5_n_2		96.62 71	96.82 57	96.02 157	97.98 129	90.43 202	97.50 158	98.59 26	96.59 11	99.31 7	99.08 9	84.47 215	99.75 61	99.37 5	98.45 135	97.88 254

DeepC-MVS	93.07 3	96.06 90	95.66 96	97.29 66	97.96 131	93.17 83	97.30 189	98.06 104	93.92 103	93.38 236	98.66 47	86.83 156	99.73 64	95.60 121	99.22 84	98.96 120
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
COLMAP_ROB	87.81 15	90.40 355	89.28 369	93.79 324	97.95 132	87.13 346	96.92 230	95.89 364	82.83 452	86.88 414	97.18 201	73.77 394	99.29 150	78.44 455	93.62 304	94.95 393
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AllTest		90.23 360	88.98 375	93.98 309	97.94 133	86.64 357	96.51 281	95.54 385	85.38 412	85.49 434	96.77 230	70.28 424	99.15 168	80.02 444	92.87 309	96.15 328

TestCases				93.98 309	97.94 133	86.64 357		95.54 385	85.38 412	85.49 434	96.77 230	70.28 424	99.15 168	80.02 444	92.87 309	96.15 328

thres100view900		92.43 257	91.58 269	94.98 242	97.92 135	89.37 256	97.71 124	94.66 428	92.20 191	93.31 238	94.90 334	78.06 354	99.08 181	81.40 430	94.08 292	96.48 317

thres600view7		92.49 255	91.60 268	95.18 228	97.91 136	89.47 250	97.65 133	94.66 428	92.18 195	93.33 237	94.91 333	78.06 354	99.10 176	81.61 426	94.06 296	96.98 299

API-MVS		94.84 155	94.49 158	95.90 168	97.90 137	92.00 127	97.80 107	97.48 204	89.19 313	94.81 188	96.71 233	88.84 108	99.17 164	88.91 307	98.76 120	96.53 314

VDD-MVS		93.82 200	93.08 210	96.02 157	97.88 138	89.96 227	97.72 121	95.85 365	92.43 179	95.86 141	98.44 66	68.42 445	99.39 138	96.31 82	94.85 269	98.71 174

SymmetryMVS		95.94 97	95.54 99	97.15 76	97.85 139	92.90 91	97.99 70	96.91 298	95.92 17	96.57 107	97.93 116	85.34 196	99.50 124	94.99 138	96.39 233	99.05 106

tfpn200view9		92.38 260	91.52 272	94.95 246	97.85 139	89.29 260	97.41 174	94.88 420	92.19 193	93.27 240	94.46 360	78.17 350	99.08 181	81.40 430	94.08 292	96.48 317

thres400		92.42 258	91.52 272	95.12 232	97.85 139	89.29 260	97.41 174	94.88 420	92.19 193	93.27 240	94.46 360	78.17 350	99.08 181	81.40 430	94.08 292	96.98 299

h-mvs33		94.15 180	93.52 192	96.04 154	97.81 142	90.22 214	97.62 142	97.58 179	95.19 39	96.74 93	97.45 182	83.67 231	99.61 94	95.85 105	79.73 455	98.29 218

DELS-MVS		96.61 72	96.38 82	97.30 65	97.79 143	93.19 82	95.96 332	98.18 79	95.23 38	95.87 140	97.65 162	91.45 64	99.70 75	95.87 103	99.44 54	99.00 114
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
PVSNet	86.66 18	92.24 269	91.74 265	93.73 326	97.77 144	83.69 422	92.88 461	96.72 311	87.91 358	93.00 245	94.86 336	78.51 345	99.05 190	86.53 363	97.45 177	98.47 197

testing915		94.92 149	94.46 160	96.28 136	97.76 145	91.12 172	97.88 92	95.70 372	92.69 166	95.50 160	96.74 232	83.71 229	98.70 249	94.04 178	96.15 237	99.02 107

fmvsm_s_conf0.5_n_4		96.75 63	97.07 36	95.79 181	97.76 145	89.57 243	97.66 132	98.66 21	95.36 33	99.03 17	98.90 28	88.39 117	99.73 64	99.17 14	98.66 123	98.08 241

test_yl		94.78 159	94.23 168	96.43 121	97.74 147	91.22 160	96.85 240	97.10 268	91.23 235	95.71 147	96.93 220	84.30 219	99.31 147	93.10 201	95.12 265	98.75 168

DCV-MVSNet		94.78 159	94.23 168	96.43 121	97.74 147	91.22 160	96.85 240	97.10 268	91.23 235	95.71 147	96.93 220	84.30 219	99.31 147	93.10 201	95.12 265	98.75 168

testing3-2		92.10 275	92.05 250	92.27 390	97.71 149	79.56 470	97.42 172	94.41 440	93.53 121	93.22 242	95.49 309	69.16 437	99.11 174	93.25 198	94.22 285	98.13 231

WTY-MVS		94.71 164	94.02 173	96.79 92	97.71 149	92.05 124	96.59 277	97.35 236	90.61 265	94.64 194	96.93 220	86.41 167	99.39 138	91.20 246	94.71 277	98.94 127

UA-Net		95.95 96	95.53 100	97.20 74	97.67 151	92.98 88	97.65 133	98.13 87	94.81 62	96.61 102	98.35 74	88.87 107	99.51 121	90.36 269	97.35 181	99.11 97

IS-MVSNet		94.90 150	94.52 156	96.05 153	97.67 151	90.56 196	98.44 27	96.22 349	93.21 134	93.99 214	97.74 151	85.55 192	98.45 286	89.98 274	97.86 161	99.14 91

test2506		91.60 297	90.78 303	94.04 305	97.66 153	83.81 418	98.27 38	75.53 522	93.43 127	95.23 170	98.21 90	67.21 451	99.07 185	93.01 208	98.49 131	99.25 81

ECVR-MVS		93.19 226	92.73 227	94.57 272	97.66 153	85.41 392	98.21 49	88.23 502	93.43 127	94.70 192	98.21 90	72.57 404	99.07 185	93.05 205	98.49 131	99.25 81

fmvsm_s_conf0.5_n_a		96.75 63	96.93 48	96.20 143	97.64 155	90.72 192	98.00 69	98.73 10	94.55 76	98.91 27	99.08 9	88.22 121	99.63 91	98.91 22	98.37 139	98.25 221

PAPR		94.18 176	93.42 200	96.48 116	97.64 155	91.42 154	95.55 359	97.71 161	88.99 321	92.34 261	95.82 288	89.19 101	99.11 174	86.14 371	97.38 179	98.90 136

BridgeMVS		96.84 57	96.89 50	96.68 95	97.63 157	92.22 117	98.17 55	97.82 147	94.44 83	98.23 47	97.36 189	90.97 78	99.22 156	97.74 33	99.66 11	98.61 180

CANet		96.39 81	96.02 89	97.50 56	97.62 158	93.38 71	97.02 217	97.96 125	95.42 32	94.86 185	97.81 142	87.38 147	99.82 35	96.88 63	99.20 90	99.29 76

thres200		92.23 270	91.39 275	94.75 259	97.61 159	89.03 271	96.60 276	95.09 409	92.08 198	93.28 239	94.00 388	78.39 348	99.04 193	81.26 436	94.18 288	96.19 324

Vis-MVSNet (Re-imp)		94.15 180	93.88 178	94.95 246	97.61 159	87.92 322	98.10 58	95.80 368	92.22 188	93.02 244	97.45 182	84.53 214	97.91 364	88.24 317	97.97 158	99.02 107

MGCFI-Net		95.94 97	95.40 108	97.56 55	97.59 161	94.62 35	98.21 49	97.57 182	94.41 85	96.17 127	96.16 271	87.54 139	99.17 164	96.19 93	94.73 276	98.91 133

sasdasda		96.02 92	95.45 104	97.75 41	97.59 161	95.15 26	98.28 36	97.60 175	94.52 78	96.27 123	96.12 273	87.65 134	99.18 162	96.20 91	94.82 271	98.91 133

canonicalmvs		96.02 92	95.45 104	97.75 41	97.59 161	95.15 26	98.28 36	97.60 175	94.52 78	96.27 123	96.12 273	87.65 134	99.18 162	96.20 91	94.82 271	98.91 133

LS3D		93.57 210	92.61 233	96.47 117	97.59 161	91.61 142	97.67 129	97.72 157	85.17 417	90.29 311	98.34 77	84.60 212	99.73 64	83.85 407	98.27 144	98.06 243

fmvsm_s_conf0.5_n_5		97.00 46	96.97 45	97.09 81	97.58 165	92.56 105	97.68 128	98.47 35	94.02 98	98.90 28	98.89 31	88.94 106	99.78 52	99.18 13	99.03 108	98.93 131

test1111		93.19 226	92.82 221	94.30 291	97.58 165	84.56 409	98.21 49	89.02 500	93.53 121	94.58 195	98.21 90	72.69 403	99.05 190	93.06 204	98.48 133	99.28 78

alignmvs		95.87 101	95.23 116	97.78 37	97.56 167	95.19 24	97.86 94	97.17 260	94.39 87	96.47 113	96.40 258	85.89 177	99.20 158	96.21 90	95.11 267	98.95 124

EPP-MVSNet		95.22 127	95.04 125	95.76 185	97.49 168	89.56 244	98.67 16	97.00 288	90.69 257	94.24 205	97.62 168	89.79 96	98.81 215	93.39 197	96.49 225	98.92 132

test_fmvsmconf_n		97.49 22	97.56 18	97.29 66	97.44 169	92.37 111	97.91 87	98.88 4	95.83 20	98.92 26	99.05 15	91.45 64	99.80 42	99.12 17	99.46 48	99.69 15

test_vis1_n_1920		94.17 177	94.58 151	92.91 369	97.42 170	82.02 442	97.83 101	97.85 140	94.68 70	98.10 51	98.49 60	70.15 427	99.32 145	97.91 31	98.82 115	97.40 284

PS-MVSNAJ		95.37 116	95.33 112	95.49 210	97.35 171	90.66 195	95.31 373	97.48 204	93.85 106	96.51 110	95.70 298	88.65 112	99.65 82	94.80 153	98.27 144	96.17 325

fmvsm_s_conf0.1_n_2		96.33 85	96.44 81	96.00 161	97.30 172	90.37 208	97.53 155	97.92 130	96.52 12	99.14 16	99.08 9	83.21 240	99.74 62	99.22 11	98.06 154	97.88 254

fmvsm_s_conf0.5_n_7		96.45 78	96.80 59	95.37 217	97.29 173	88.38 300	97.23 201	98.47 35	95.14 42	98.43 43	99.09 8	87.58 137	99.72 68	98.80 26	99.21 85	98.02 245

fmvsm_s_conf0.5_n_6		97.08 40	97.17 32	96.81 91	97.28 174	91.73 134	97.75 113	98.50 31	94.86 55	99.22 12	98.78 44	89.75 97	99.76 57	99.10 18	99.29 75	98.94 127

ab-mvs		93.57 210	92.55 235	96.64 96	97.28 174	91.96 130	95.40 367	97.45 215	89.81 291	93.22 242	96.28 264	79.62 325	99.46 130	90.74 257	93.11 308	98.50 192

xiu_mvs_v2_base		95.32 119	95.29 113	95.40 216	97.22 176	90.50 198	95.44 366	97.44 219	93.70 112	96.46 114	96.18 268	88.59 116	99.53 116	94.79 156	97.81 163	96.17 325

BH-untuned		92.94 239	92.62 232	93.92 319	97.22 176	86.16 375	96.40 292	96.25 348	90.06 284	89.79 330	96.17 270	83.19 241	98.35 297	87.19 355	97.27 187	97.24 292

baseline1		92.82 247	91.90 258	95.55 201	97.20 178	90.77 189	97.19 205	94.58 432	92.20 191	92.36 258	96.34 261	84.16 223	98.21 311	89.20 299	83.90 434	97.68 269

Vis-MVSNet		95.23 126	94.81 138	96.51 113	97.18 179	91.58 145	98.26 40	98.12 89	94.38 88	94.90 184	98.15 96	82.28 268	98.92 202	91.45 241	98.58 129	99.01 111
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ETV-MVS		96.02 92	95.89 92	96.40 124	97.16 180	92.44 109	97.47 168	97.77 151	94.55 76	96.48 112	94.51 355	91.23 73	98.92 202	95.65 115	98.19 147	97.82 262

balanced_ft_v1		95.56 112	95.40 108	96.07 151	97.16 180	90.36 209	98.23 45	97.31 241	92.89 159	96.36 119	97.11 207	83.28 238	99.26 152	97.40 52	98.80 117	98.58 183

BH-RMVSNet		92.72 251	91.97 255	94.97 244	97.16 180	87.99 320	96.15 319	95.60 380	90.62 264	91.87 275	97.15 204	78.41 347	98.57 275	83.16 409	97.60 168	98.36 209

MSDG		91.42 310	90.24 332	94.96 245	97.15 183	88.91 278	93.69 443	96.32 337	85.72 408	86.93 412	96.47 254	80.24 311	98.98 196	80.57 440	95.05 268	96.98 299

tttt0517		92.96 237	92.33 244	94.87 249	97.11 184	87.16 345	97.97 79	92.09 482	90.63 263	93.88 219	97.01 218	76.50 367	99.06 187	90.29 271	95.45 259	98.38 207

HY-MVS	89.66 9	93.87 198	92.95 216	96.63 100	97.10 185	92.49 108	95.64 355	96.64 319	89.05 318	93.00 245	95.79 292	85.77 182	99.45 132	89.16 301	94.35 280	97.96 248

thisisatest0530		93.03 234	92.21 247	95.49 210	97.07 186	89.11 269	97.49 166	92.19 481	90.16 281	94.09 212	96.41 257	76.43 370	99.05 190	90.38 268	95.68 250	98.31 217

XVG-OURS		93.72 204	93.35 201	94.80 255	97.07 186	88.61 289	94.79 398	97.46 210	91.97 203	93.99 214	97.86 132	81.74 281	98.88 206	92.64 212	92.67 316	96.92 304

sss		94.51 168	93.80 179	96.64 96	97.07 186	91.97 128	96.32 302	98.06 104	88.94 324	94.50 198	96.78 229	84.60 212	99.27 151	91.90 227	96.02 238	98.68 176

EIA-MVS		95.53 113	95.47 103	95.71 192	97.06 189	89.63 239	97.82 103	97.87 135	93.57 116	93.92 218	95.04 327	90.61 85	98.95 197	94.62 163	98.68 122	98.54 187

XVG-OURS-SEG-HR		93.86 199	93.55 188	94.81 252	97.06 189	88.53 295	95.28 374	97.45 215	91.68 210	94.08 213	97.68 158	82.41 266	98.90 205	93.84 185	92.47 317	96.98 299

SSM_0404		94.73 163	94.31 167	95.98 163	97.05 191	90.90 183	97.01 220	97.29 243	91.24 232	94.17 210	97.60 170	85.03 203	98.76 230	92.14 220	97.30 185	98.29 218

1112_ss		93.37 219	92.42 242	96.21 142	97.05 191	90.99 175	96.31 303	96.72 311	86.87 388	89.83 329	96.69 237	86.51 163	99.14 171	88.12 318	93.67 302	98.50 192

Test_1112_low_res		92.84 246	91.84 260	95.85 174	97.04 193	89.97 226	95.53 361	96.64 319	85.38 412	89.65 336	95.18 322	85.86 178	99.10 176	87.70 332	93.58 307	98.49 194

E3new		95.28 120	95.11 123	95.80 178	97.03 194	89.76 233	96.78 254	97.54 195	92.06 199	95.40 163	97.75 148	87.49 143	98.76 230	94.85 146	97.10 194	98.88 144

mvsmamba		94.57 165	94.14 170	95.87 170	97.03 194	89.93 228	97.84 98	95.85 365	91.34 226	94.79 189	96.80 228	80.67 301	98.81 215	94.85 146	98.12 152	98.85 149

hse-mvs2		93.45 217	92.99 212	94.81 252	97.02 196	88.59 290	96.69 264	96.47 329	95.19 39	96.74 93	96.16 271	83.67 231	98.48 284	95.85 105	79.13 459	97.35 287

EC-MVSNet		96.42 79	96.47 75	96.26 138	97.01 197	91.52 147	98.89 5	97.75 152	94.42 84	96.64 100	97.68 158	89.32 99	98.60 270	97.45 48	99.11 102	98.67 177

AUN-MVS		91.76 287	90.75 306	94.81 252	97.00 198	88.57 291	96.65 268	96.49 328	89.63 298	92.15 265	96.12 273	78.66 343	98.50 281	90.83 252	79.18 458	97.36 285

KinetiMVS		95.26 122	94.75 144	96.79 92	96.99 199	92.05 124	97.82 103	97.78 150	94.77 66	96.46 114	97.70 155	80.62 303	99.34 142	92.37 214	98.28 143	98.97 117

BH-w/o		92.14 274	91.75 263	93.31 354	96.99 199	85.73 385	95.67 350	95.69 375	88.73 335	89.26 351	94.82 339	82.97 250	98.07 333	85.26 387	96.32 234	96.13 330

guyue		95.17 133	94.96 130	95.82 176	96.97 201	89.65 238	97.56 149	95.58 382	94.82 60	95.72 146	97.42 185	82.90 252	98.84 211	96.71 70	96.93 199	98.96 120

GeoE		93.89 197	93.28 203	95.72 191	96.96 202	89.75 234	98.24 44	96.92 297	89.47 304	92.12 267	97.21 200	84.42 216	98.39 294	87.71 331	96.50 224	99.01 111

Casviewmamba		95.67 106	95.55 98	96.03 156	96.95 203	90.12 216	97.72 121	97.55 194	94.10 95	95.23 170	98.18 93	87.32 148	98.80 218	95.40 127	97.52 171	99.19 84

viewcassd2359sk11		95.26 122	95.09 124	95.80 178	96.95 203	89.72 235	96.80 249	97.56 190	92.21 190	95.37 165	97.80 144	87.17 152	98.77 224	94.82 151	97.10 194	98.90 136

viewdifsd2359ckpt09		94.81 158	94.37 164	96.12 148	96.91 205	90.75 191	96.94 227	97.31 241	90.51 273	94.31 203	97.38 187	85.70 183	98.71 247	93.54 190	96.75 210	98.90 136

myMVS_eth3d28		91.52 305	90.97 294	93.17 360	96.91 205	83.24 426	95.61 356	94.96 416	92.24 187	91.98 271	93.28 419	69.31 435	98.40 289	88.71 312	95.68 250	97.88 254

3Dnovator+	91.43 4	95.40 115	94.48 159	98.16 18	96.90 207	95.34 18	98.48 26	97.87 135	94.65 73	88.53 371	98.02 107	83.69 230	99.71 70	93.18 200	98.96 111	99.44 62

viewdifsd2359ckpt13		94.87 153	94.52 156	95.90 168	96.88 208	90.19 215	96.92 230	97.36 234	91.26 231	94.65 193	97.46 181	85.79 181	98.64 262	93.64 189	96.76 209	98.88 144

viewmanbaseed2359cas		95.24 125	95.02 126	95.91 166	96.87 209	89.98 224	96.82 245	97.49 201	92.26 186	95.47 161	97.82 140	86.47 164	98.69 250	94.80 153	97.20 190	99.06 105

MGCNet		96.74 65	96.31 83	98.02 22	96.87 209	94.65 34	97.58 145	94.39 441	96.47 13	97.16 78	98.39 70	87.53 140	99.87 9	98.97 21	99.41 61	99.55 44

casdiffmvs_mvg		95.81 102	95.57 97	96.51 113	96.87 209	91.49 148	97.50 158	97.56 190	93.99 100	95.13 174	97.92 119	87.89 128	98.78 220	95.97 101	97.33 182	99.26 80
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UGNet		94.04 188	93.28 203	96.31 131	96.85 212	91.19 165	97.88 92	97.68 162	94.40 86	93.00 245	96.18 268	73.39 399	99.61 94	91.72 233	98.46 134	98.13 231
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
FBQ-MVS		91.77 286	90.62 314	95.21 226	96.84 213	88.89 281	96.90 233	95.31 398	90.60 267	92.64 253	92.29 442	69.43 434	98.48 284	87.33 351	94.21 286	98.27 220

VDDNet		93.05 233	92.07 249	96.02 157	96.84 213	90.39 204	98.08 60	95.85 365	86.22 401	95.79 144	98.46 64	67.59 448	99.19 159	94.92 141	94.85 269	98.47 197

RPSCF		90.75 343	90.86 298	90.42 438	96.84 213	76.29 489	95.61 356	96.34 336	83.89 435	91.38 286	97.87 130	76.45 368	98.78 220	87.16 357	92.23 320	96.20 323

hybridcas		95.46 114	95.29 113	95.96 164	96.83 216	90.08 218	97.63 139	97.49 201	93.76 108	94.79 189	98.04 103	86.87 155	98.72 245	94.71 159	97.53 170	99.08 101

FE-MVS		92.05 277	91.05 291	95.08 233	96.83 216	87.93 321	93.91 434	95.70 372	86.30 398	94.15 211	94.97 329	76.59 366	99.21 157	84.10 400	96.86 203	98.09 240

MVS_Test		94.89 151	94.62 148	95.68 193	96.83 216	89.55 246	96.70 262	97.17 260	91.17 238	95.60 154	96.11 277	87.87 130	98.76 230	93.01 208	97.17 192	98.72 172

reproduce_monomvs		91.30 319	91.10 290	91.92 399	96.82 219	82.48 436	97.01 220	97.49 201	94.64 74	88.35 374	95.27 318	70.53 422	98.10 324	95.20 131	84.60 421	95.19 384

LCM-MVSNet-Re		92.50 253	92.52 238	92.44 382	96.82 219	81.89 443	96.92 230	93.71 461	92.41 180	84.30 446	94.60 350	85.08 202	97.03 434	91.51 238	97.36 180	98.40 205

ETVMVS		90.52 352	89.14 374	94.67 263	96.81 221	87.85 327	95.91 336	93.97 455	89.71 295	92.34 261	92.48 433	65.41 466	97.96 352	81.37 433	94.27 284	98.21 224

E2		95.20 128	95.00 128	95.79 181	96.79 222	89.66 236	96.82 245	97.58 179	92.35 182	95.28 167	97.83 138	86.68 159	98.76 230	94.79 156	96.92 200	98.95 124

mamba_0408		93.70 205	92.99 212	95.83 175	96.79 222	90.38 205	88.69 498	97.07 274	90.96 248	93.68 222	97.31 192	84.97 206	98.76 230	90.95 250	96.51 221	98.35 211

SSM_04072		93.51 213	92.99 212	95.05 234	96.79 222	90.38 205	88.69 498	97.07 274	90.96 248	93.68 222	97.31 192	84.97 206	96.42 451	90.95 250	96.51 221	98.35 211

SSM_0407		94.54 167	94.12 172	95.80 178	96.79 222	90.38 205	96.79 250	97.29 243	91.24 232	93.68 222	97.60 170	85.03 203	98.67 255	92.14 220	96.51 221	98.35 211

GDP-MVS		95.62 108	95.13 120	97.09 81	96.79 222	93.26 80	97.89 90	97.83 146	93.58 115	96.80 89	97.82 140	83.06 247	99.16 166	94.40 170	97.95 160	98.87 147

test_cas_vis1_n_1920		94.48 170	94.55 155	94.28 292	96.78 227	86.45 366	97.63 139	97.64 167	93.32 132	97.68 64	98.36 73	73.75 395	99.08 181	96.73 68	99.05 105	97.31 289

baseline		95.58 110	95.42 107	96.08 149	96.78 227	90.41 203	97.16 208	97.45 215	93.69 113	95.65 152	97.85 134	87.29 149	98.68 252	95.66 112	97.25 188	99.13 92

E3		95.20 128	95.00 128	95.79 181	96.77 229	89.66 236	96.82 245	97.58 179	92.35 182	95.28 167	97.83 138	86.69 158	98.76 230	94.79 156	96.92 200	98.95 124

FA-MVS(test-final)		93.52 212	92.92 217	95.31 221	96.77 229	88.54 293	94.82 397	96.21 351	89.61 299	94.20 207	95.25 320	83.24 239	99.14 171	90.01 273	96.16 236	98.25 221

Fast-Effi-MVS+		93.46 214	92.75 225	95.59 198	96.77 229	90.03 219	96.81 248	97.13 262	88.19 349	91.30 292	94.27 373	86.21 171	98.63 265	87.66 339	96.46 227	98.12 233

QAPM		93.45 217	92.27 245	96.98 87	96.77 229	92.62 102	98.39 30	98.12 89	84.50 427	88.27 379	97.77 147	82.39 267	99.81 37	85.40 384	98.81 116	98.51 191

viewdifsd2359ckpt07		94.76 161	94.68 146	95.01 238	96.76 233	87.41 335	96.38 294	97.43 222	92.65 169	94.52 197	97.75 148	85.55 192	98.81 215	94.36 172	96.69 215	98.82 156

casdiffmvs		95.64 107	95.49 101	96.08 149	96.76 233	90.45 200	97.29 190	97.44 219	94.00 99	95.46 162	97.98 112	87.52 142	98.73 240	95.64 116	97.33 182	99.08 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CHOSEN 280x420		93.12 229	92.72 228	94.34 286	96.71 235	87.27 339	90.29 488	97.72 157	86.61 393	91.34 289	95.29 315	84.29 221	98.41 288	93.25 198	98.94 112	97.35 287

PRO-TEST		95.74 103	95.69 95	95.91 166	96.68 236	90.34 210	97.49 166	97.61 174	93.99 100	96.64 100	97.00 219	88.00 126	98.54 277	95.58 123	98.18 148	98.84 153

BP-MVS1		95.89 99	95.49 101	97.08 83	96.67 237	93.20 81	98.08 60	96.32 337	94.56 75	96.32 120	97.84 136	84.07 225	99.15 168	96.75 67	98.78 118	98.90 136

fmvsm_s_conf0.1_n		96.58 74	96.77 62	96.01 160	96.67 237	90.25 213	97.91 87	98.38 38	94.48 80	98.84 31	99.14 3	88.06 123	99.62 93	98.82 24	98.60 127	98.15 230

E5new		95.04 138	94.88 133	95.52 203	96.62 239	89.02 272	97.29 190	97.57 182	92.54 172	95.04 176	97.89 124	85.65 186	98.77 224	94.92 141	96.44 228	98.78 160

E5		95.04 138	94.88 133	95.52 203	96.62 239	89.02 272	97.29 190	97.57 182	92.54 172	95.04 176	97.89 124	85.65 186	98.77 224	94.92 141	96.44 228	98.78 160

test_fmvsmvis_n_1920		96.70 66	96.84 53	96.31 131	96.62 239	91.73 134	97.98 73	98.30 49	96.19 15	96.10 130	98.95 21	89.42 98	99.76 57	98.90 23	99.08 103	97.43 282

casdiffseed414692147		94.55 166	94.02 173	96.15 146	96.61 242	90.79 187	97.42 172	97.39 227	92.18 195	93.95 217	97.64 165	84.37 218	98.66 258	90.68 259	95.91 242	99.00 114

Effi-MVS+		94.93 147	94.45 161	96.36 129	96.61 242	91.47 151	96.41 288	97.41 225	91.02 246	94.50 198	95.92 282	87.53 140	98.78 220	93.89 183	96.81 207	98.84 153

E6new		95.04 138	94.88 133	95.52 203	96.60 244	89.02 272	97.29 190	97.57 182	92.54 172	95.04 176	97.90 122	85.66 184	98.77 224	94.92 141	96.44 228	98.78 160

E6		95.04 138	94.88 133	95.52 203	96.60 244	89.02 272	97.29 190	97.57 182	92.54 172	95.04 176	97.90 122	85.66 184	98.77 224	94.92 141	96.44 228	98.78 160

thisisatest0515		92.29 266	91.30 280	95.25 225	96.60 244	88.90 279	94.36 416	92.32 479	87.92 357	93.43 235	94.57 351	77.28 361	99.00 194	89.42 290	95.86 245	97.86 258

PCF-MVS	89.48 11	91.56 301	89.95 347	96.36 129	96.60 244	92.52 107	92.51 471	97.26 249	79.41 479	88.90 359	96.56 250	84.04 226	99.55 112	77.01 464	97.30 185	97.01 298
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
E4		95.09 135	94.86 137	95.77 184	96.58 248	89.56 244	96.85 240	97.56 190	92.50 176	95.03 180	97.86 132	86.03 175	98.78 220	94.71 159	96.65 218	98.96 120

VortexMVS		92.88 243	92.64 230	93.58 341	96.58 248	87.53 334	96.93 229	97.28 246	92.78 164	89.75 331	94.99 328	82.73 257	97.76 379	94.60 165	88.16 377	95.46 359

xiu_mvs_v1_base_debu		95.01 142	94.76 141	95.75 187	96.58 248	91.71 137	96.25 309	97.35 236	92.99 147	96.70 95	96.63 244	82.67 258	99.44 133	96.22 86	97.46 173	96.11 331

xiu_mvs_v1_base		95.01 142	94.76 141	95.75 187	96.58 248	91.71 137	96.25 309	97.35 236	92.99 147	96.70 95	96.63 244	82.67 258	99.44 133	96.22 86	97.46 173	96.11 331

xiu_mvs_v1_base_debi		95.01 142	94.76 141	95.75 187	96.58 248	91.71 137	96.25 309	97.35 236	92.99 147	96.70 95	96.63 244	82.67 258	99.44 133	96.22 86	97.46 173	96.11 331

MVSTER		93.20 225	92.81 222	94.37 283	96.56 253	89.59 242	97.06 214	97.12 263	91.24 232	91.30 292	95.96 280	82.02 274	98.05 336	93.48 193	90.55 350	95.47 358

3Dnovator	91.36 5	95.19 131	94.44 162	97.44 59	96.56 253	93.36 73	98.65 17	98.36 39	94.12 94	89.25 352	98.06 101	82.20 270	99.77 55	93.41 196	99.32 73	99.18 86

test_fmvs1		93.21 224	93.53 190	92.25 392	96.55 255	81.20 449	97.40 178	96.96 290	90.68 258	96.80 89	98.04 103	69.25 436	98.40 289	97.58 43	98.50 130	97.16 296

testing91		91.90 282	91.02 292	94.53 275	96.54 256	86.55 363	95.86 338	95.64 379	91.77 207	91.89 274	93.47 412	69.94 429	98.86 207	90.23 272	93.86 299	98.18 226

testing222		90.31 356	88.96 376	94.35 284	96.54 256	87.29 337	95.50 362	93.84 459	90.97 247	91.75 279	92.96 423	62.18 481	98.00 343	82.86 412	94.08 292	97.76 265

viewmacassd2359aftdt		95.07 137	94.80 139	95.87 170	96.53 258	89.84 230	96.90 233	97.48 204	92.44 178	95.36 166	97.89 124	85.23 199	98.68 252	94.40 170	97.00 198	99.09 99

testing11		91.68 291	90.75 306	94.47 278	96.53 258	86.56 362	95.76 346	94.51 436	91.10 244	91.24 297	93.59 407	68.59 442	98.86 207	91.10 247	94.29 283	98.00 247

FMVSNet3		91.78 285	90.69 311	95.03 237	96.53 258	92.27 116	97.02 217	96.93 293	89.79 293	89.35 346	94.65 348	77.01 362	97.47 413	86.12 372	88.82 369	95.35 370

UBG		91.55 302	90.76 304	93.94 315	96.52 261	85.06 401	95.22 380	94.54 434	90.47 274	91.98 271	92.71 426	72.02 408	98.74 238	88.10 319	95.26 263	98.01 246

GBi-Net		91.35 315	90.27 330	94.59 267	96.51 262	91.18 167	97.50 158	96.93 293	88.82 330	89.35 346	94.51 355	73.87 391	97.29 426	86.12 372	88.82 369	95.31 373

test1		91.35 315	90.27 330	94.59 267	96.51 262	91.18 167	97.50 158	96.93 293	88.82 330	89.35 346	94.51 355	73.87 391	97.29 426	86.12 372	88.82 369	95.31 373

FMVSNet2		91.31 318	90.08 339	94.99 240	96.51 262	92.21 118	97.41 174	96.95 291	88.82 330	88.62 368	94.75 342	73.87 391	97.42 418	85.20 388	88.55 374	95.35 370

WBMVS		90.69 348	89.99 346	92.81 374	96.48 265	85.00 402	95.21 382	96.30 339	89.46 305	89.04 358	94.05 386	72.45 406	97.82 371	89.46 288	87.41 387	95.61 353

testing99		91.62 296	90.72 309	94.32 288	96.48 265	86.11 380	95.81 342	94.76 425	91.55 212	91.75 279	93.44 414	68.55 443	98.82 213	90.43 266	93.69 301	98.04 244

ACMH+	87.92 14	90.20 362	89.18 372	93.25 356	96.48 265	86.45 366	96.99 223	96.68 316	88.83 329	84.79 442	96.22 267	70.16 426	98.53 279	84.42 397	88.04 378	94.77 420

CANet_DTU		94.37 171	93.65 185	96.55 106	96.46 268	92.13 122	96.21 313	96.67 318	94.38 88	93.53 230	97.03 217	79.34 328	99.71 70	90.76 256	98.45 135	97.82 262

mvs_anonymous		93.82 200	93.74 182	94.06 303	96.44 269	85.41 392	95.81 342	97.05 281	89.85 289	90.09 322	96.36 260	87.44 145	97.75 381	93.97 179	96.69 215	99.02 107

diffmvs		95.25 124	95.13 120	95.63 195	96.43 270	89.34 257	95.99 331	97.35 236	92.83 161	96.31 121	97.37 188	86.44 166	98.67 255	96.26 83	97.19 191	98.87 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ET-MVSNet_ETH3D		91.49 307	90.11 338	95.63 195	96.40 271	91.57 146	95.34 370	93.48 463	90.60 267	75.58 492	95.49 309	80.08 314	96.79 445	94.25 174	89.76 358	98.52 189

RRT-MVS		94.51 168	94.35 165	94.98 242	96.40 271	86.55 363	97.56 149	97.41 225	93.19 137	94.93 183	97.04 212	79.12 332	99.30 149	96.19 93	97.32 184	99.09 99

TR-MVS		91.48 308	90.59 318	94.16 299	96.40 271	87.33 336	95.67 350	95.34 397	87.68 371	91.46 285	95.52 308	76.77 365	98.35 297	82.85 414	93.61 305	96.79 308

ACMP	89.59 10	92.62 252	92.14 248	94.05 304	96.40 271	88.20 312	97.36 182	97.25 252	91.52 217	88.30 377	96.64 240	78.46 346	98.72 245	91.86 230	91.48 334	95.23 380
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
onestephybrid01		95.12 134	95.01 127	95.46 214	96.39 275	88.92 277	96.28 307	97.27 247	92.67 167	96.00 136	97.73 154	86.28 168	98.66 258	95.58 123	96.85 204	98.79 159

diffmvs_AUTHOR		95.33 118	95.27 115	95.50 209	96.37 276	89.08 270	96.08 323	97.38 231	93.09 145	96.53 109	97.74 151	86.45 165	98.68 252	96.32 81	97.48 172	98.75 168

AstraMVS		94.82 157	94.64 147	95.34 220	96.36 277	88.09 317	97.58 145	94.56 433	94.98 49	95.70 149	97.92 119	81.93 278	98.93 200	96.87 64	95.88 243	98.99 116

MVSFormer		95.37 116	95.16 118	95.99 162	96.34 278	91.21 162	98.22 47	97.57 182	91.42 222	96.22 125	97.32 190	86.20 172	97.92 361	94.07 176	99.05 105	98.85 149

lupinMVS		94.99 146	94.56 152	96.29 135	96.34 278	91.21 162	95.83 340	96.27 344	88.93 325	96.22 125	96.88 225	86.20 172	98.85 209	95.27 129	99.05 105	98.82 156

viewmamba		95.18 132	95.15 119	95.26 224	96.31 280	88.25 307	96.29 305	97.27 247	93.61 114	95.65 152	97.91 121	86.79 157	98.64 262	95.69 111	96.82 206	98.88 144

ACMM	89.79 8	92.96 237	92.50 239	94.35 284	96.30 281	88.71 284	97.58 145	97.36 234	91.40 224	90.53 306	96.65 239	79.77 320	98.75 236	91.24 245	91.64 330	95.59 354
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
hybridnocas07		94.93 147	94.78 140	95.37 217	96.27 282	88.62 288	96.10 321	97.26 249	92.35 182	95.58 155	97.48 180	85.60 191	98.65 260	95.47 125	96.90 202	98.85 149

IterMVS-LS		92.29 266	91.94 256	93.34 353	96.25 283	86.97 349	96.57 280	97.05 281	90.67 259	89.50 343	94.80 340	86.59 160	97.64 391	89.91 276	86.11 399	95.40 366
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
hybrid		94.76 161	94.60 149	95.27 222	96.24 284	88.36 301	96.05 325	97.25 252	91.40 224	95.40 163	97.59 172	85.48 194	98.63 265	95.23 130	96.71 214	98.83 155

viewmambaseed2359dif		94.28 173	94.14 170	94.71 260	96.21 285	86.97 349	95.93 334	97.11 267	89.00 320	95.00 182	97.70 155	86.02 176	98.59 274	93.71 188	96.59 220	98.57 185

HQP_MVS		93.78 202	93.43 198	94.82 250	96.21 285	89.99 222	97.74 116	97.51 198	94.85 56	91.34 289	96.64 240	81.32 287	98.60 270	93.02 206	92.23 320	95.86 336

plane_prior7					96.21 285	89.98 224

ACMH	87.59 16	90.53 351	89.42 366	93.87 320	96.21 285	87.92 322	97.24 197	96.94 292	88.45 343	83.91 454	96.27 265	71.92 409	98.62 268	84.43 396	89.43 361	95.05 391
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
icg_test_0407_2		93.58 208	93.46 195	93.94 315	96.19 289	86.16 375	93.73 440	97.24 254	91.54 213	93.50 231	97.04 212	85.64 189	96.91 440	90.68 259	95.59 253	98.76 164

IMVS_0407		93.94 194	93.75 181	94.49 277	96.19 289	86.16 375	96.35 297	97.24 254	91.54 213	93.50 231	97.04 212	85.64 189	98.54 277	90.68 259	95.59 253	98.76 164

IMVS_0404		92.44 256	91.92 257	94.00 307	96.19 289	86.16 375	93.84 437	97.24 254	91.54 213	88.17 383	97.04 212	76.96 364	97.09 431	90.68 259	95.59 253	98.76 164

IMVS_0403		93.98 192	93.79 180	94.55 273	96.19 289	86.16 375	96.35 297	97.24 254	91.54 213	93.59 226	97.04 212	85.86 178	98.73 240	90.68 259	95.59 253	98.76 164

dtuplus		94.16 179	93.98 175	94.70 261	96.18 293	86.85 352	96.04 326	97.07 274	89.75 294	95.02 181	97.79 146	84.94 208	98.62 268	92.62 213	96.43 232	98.62 179

CDS-MVSNet		94.14 183	93.54 189	95.93 165	96.18 293	91.46 152	96.33 301	97.04 283	88.97 323	93.56 227	96.51 252	87.55 138	97.89 365	89.80 279	95.95 240	98.44 202
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
LTVRE_ROB	88.41 13	90.99 333	89.92 349	94.19 295	96.18 293	89.55 246	96.31 303	97.09 270	87.88 359	85.67 432	95.91 283	78.79 342	98.57 275	81.50 427	89.98 355	94.44 431
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
LPG-MVS_test		92.94 239	92.56 234	94.10 301	96.16 296	88.26 305	97.65 133	97.46 210	91.29 227	90.12 319	97.16 202	79.05 334	98.73 240	92.25 217	91.89 328	95.31 373

LGP-MVS_train				94.10 301	96.16 296	88.26 305		97.46 210	91.29 227	90.12 319	97.16 202	79.05 334	98.73 240	92.25 217	91.89 328	95.31 373

TAMVS		94.01 189	93.46 195	95.64 194	96.16 296	90.45 200	96.71 261	96.89 301	89.27 311	93.46 234	96.92 223	87.29 149	97.94 358	88.70 313	95.74 247	98.53 188

testing3		87.67 399	86.88 401	90.05 443	96.14 299	80.71 452	97.10 212	92.85 471	90.15 282	87.54 394	94.55 352	55.70 491	94.10 485	73.77 480	94.10 291	95.35 370

plane_prior1					96.14 299

viewmsd2359difaftdt		93.46 214	93.23 205	94.17 296	96.12 301	85.42 390	96.43 284	97.08 271	92.91 155	94.21 206	98.00 109	80.82 299	98.74 238	94.41 169	89.05 366	98.34 215

CLD-MVS		92.98 236	92.53 237	94.32 288	96.12 301	89.20 265	95.28 374	97.47 208	92.66 168	89.90 326	95.62 302	80.58 304	98.40 289	92.73 211	92.40 318	95.38 368
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewdifsd2359ckpt11		93.46 214	93.22 206	94.17 296	96.11 303	85.42 390	96.43 284	97.07 274	92.91 155	94.20 207	98.00 109	80.82 299	98.73 240	94.42 168	89.04 368	98.34 215

plane_prior6					96.10 304	90.00 220						81.32 287

cl22		91.21 323	90.56 320	93.14 362	96.09 305	86.80 353	94.41 414	96.58 325	87.80 364	88.58 370	93.99 389	80.85 298	97.62 394	89.87 278	86.93 390	94.99 392

Elysia		94.00 190	93.12 208	96.64 96	96.08 306	92.72 99	97.50 158	97.63 169	91.15 240	94.82 186	97.12 205	74.98 382	99.06 187	90.78 254	98.02 155	98.12 233

StellarMVS		94.00 190	93.12 208	96.64 96	96.08 306	92.72 99	97.50 158	97.63 169	91.15 240	94.82 186	97.12 205	74.98 382	99.06 187	90.78 254	98.02 155	98.12 233

test_fmvs1_n		92.73 250	92.88 219	92.29 389	96.08 306	81.05 450	97.98 73	97.08 271	90.72 256	96.79 91	98.18 93	63.07 475	98.45 286	97.62 41	98.42 137	97.36 285

nomal-1		91.63 294	90.62 314	94.66 264	96.07 309	87.86 325	95.58 358	94.63 431	89.80 292	89.61 337	92.66 427	72.05 407	98.29 304	90.61 265	94.55 279	97.82 262

Effi-MVS+-dtu		93.08 231	93.21 207	92.68 380	96.02 310	83.25 425	97.14 210	96.72 311	93.85 106	91.20 299	93.44 414	83.08 245	98.30 303	91.69 236	95.73 248	96.50 316

NP-MVS					95.99 311	89.81 232					95.87 284

UWE-MVS		89.91 368	89.48 365	91.21 421	95.88 312	78.23 482	94.91 394	90.26 496	89.11 315	92.35 260	94.52 354	68.76 440	97.96 352	83.95 404	95.59 253	97.42 283

ADS-MVSNet2		89.45 379	88.59 382	92.03 397	95.86 313	82.26 440	90.93 484	94.32 446	83.23 449	91.28 295	91.81 450	79.01 338	95.99 457	79.52 447	91.39 336	97.84 259

ADS-MVSNet		89.89 370	88.68 381	93.53 344	95.86 313	84.89 406	90.93 484	95.07 410	83.23 449	91.28 295	91.81 450	79.01 338	97.85 367	79.52 447	91.39 336	97.84 259

HQP-NCC					95.86 313		96.65 268		93.55 117	90.14 313

ACMP_Plane					95.86 313		96.65 268		93.55 117	90.14 313

HQP-MVS		93.19 226	92.74 226	94.54 274	95.86 313	89.33 258	96.65 268	97.39 227	93.55 117	90.14 313	95.87 284	80.95 293	98.50 281	92.13 223	92.10 325	95.78 344

mmtdpeth		89.70 377	88.96 376	91.90 401	95.84 318	84.42 410	97.46 170	95.53 389	90.27 278	94.46 200	90.50 460	69.74 433	98.95 197	97.39 56	69.48 498	92.34 471

EI-MVSNet		93.03 234	92.88 219	93.48 348	95.77 319	86.98 348	96.44 282	97.12 263	90.66 261	91.30 292	97.64 165	86.56 161	98.05 336	89.91 276	90.55 350	95.41 363

CVMVSNet		91.23 322	91.75 263	89.67 448	95.77 319	74.69 493	96.44 282	94.88 420	85.81 406	92.18 264	97.64 165	79.07 333	95.58 468	88.06 320	95.86 245	98.74 171

FIs		94.09 185	93.70 183	95.27 222	95.70 321	92.03 126	98.10 58	98.68 18	93.36 131	90.39 309	96.70 235	87.63 136	97.94 358	92.25 217	90.50 352	95.84 339

VPA-MVSNet		93.24 223	92.48 240	95.51 207	95.70 321	92.39 110	97.86 94	98.66 21	92.30 185	92.09 269	95.37 313	80.49 306	98.40 289	93.95 180	85.86 400	95.75 348

test_fmvsmconf0.1_n		97.09 39	97.06 37	97.19 75	95.67 323	92.21 118	97.95 82	98.27 57	95.78 24	98.40 44	99.00 17	89.99 92	99.78 52	99.06 19	99.41 61	99.59 33

SD_0403		90.01 366	90.02 345	89.96 445	95.65 324	76.76 485	95.76 346	96.46 330	90.58 269	86.59 416	96.29 263	82.12 272	94.78 478	73.00 484	93.76 300	98.35 211

tt0805		91.09 328	90.07 342	94.16 299	95.61 325	88.31 302	97.56 149	96.51 327	89.56 300	89.17 355	95.64 301	67.08 455	98.38 295	91.07 248	88.44 375	95.80 342

SCA		91.84 284	91.18 287	93.83 321	95.59 326	84.95 405	94.72 399	95.58 382	90.82 251	92.25 263	93.69 399	75.80 374	98.10 324	86.20 369	95.98 239	98.45 199

c3_l		91.38 312	90.89 296	92.88 371	95.58 327	86.30 369	94.68 400	96.84 306	88.17 350	88.83 365	94.23 376	85.65 186	97.47 413	89.36 291	84.63 419	94.89 401

VPNet		92.23 270	91.31 279	94.99 240	95.56 328	90.96 177	97.22 203	97.86 139	92.96 153	90.96 300	96.62 247	75.06 380	98.20 312	91.90 227	83.65 436	95.80 342

miper_ehance_all_eth		91.59 298	91.13 288	92.97 367	95.55 329	86.57 361	94.47 410	96.88 302	87.77 366	88.88 361	94.01 387	86.22 170	97.54 406	89.49 287	86.93 390	94.79 417

IterMVS-SCA-FT		90.31 356	89.81 353	91.82 405	95.52 330	84.20 414	94.30 420	96.15 355	90.61 265	87.39 398	94.27 373	75.80 374	96.44 450	87.34 350	86.88 394	94.82 412

jason		94.84 155	94.39 163	96.18 144	95.52 330	90.93 181	96.09 322	96.52 326	89.28 310	96.01 135	97.32 190	84.70 211	98.77 224	95.15 134	98.91 114	98.85 149
jason: jason.
LuminaMVS		94.89 151	94.35 165	96.53 107	95.48 332	92.80 95	96.88 237	96.18 354	92.85 160	95.92 139	96.87 227	81.44 285	98.83 212	96.43 80	97.10 194	97.94 250

fmvsm_s_conf0.1_n_a		96.40 80	96.47 75	96.16 145	95.48 332	90.69 193	97.91 87	98.33 46	94.07 96	98.93 23	99.14 3	87.44 145	99.61 94	98.63 27	98.32 141	98.18 226

FC-MVSNet-test		93.94 194	93.57 187	95.04 236	95.48 332	91.45 153	98.12 57	98.71 13	93.37 129	90.23 312	96.70 235	87.66 133	97.85 367	91.49 239	90.39 353	95.83 340

IterMVS		90.15 364	89.67 359	91.61 412	95.48 332	83.72 420	94.33 418	96.12 356	89.99 285	87.31 401	94.15 381	75.78 376	96.27 455	86.97 360	86.89 393	94.83 407
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
dmvs_re		90.21 361	89.50 364	92.35 385	95.47 336	85.15 398	95.70 349	94.37 443	90.94 250	88.42 372	93.57 408	74.63 386	95.67 465	82.80 415	89.57 360	96.22 322

FMVSNet1		89.88 371	88.31 385	94.59 267	95.41 337	91.18 167	97.50 158	96.93 293	86.62 392	87.41 397	94.51 355	65.94 463	97.29 426	83.04 411	87.43 385	95.31 373

UniMVSNet (Re)		93.31 221	92.55 235	95.61 197	95.39 338	93.34 74	97.39 179	98.71 13	93.14 142	90.10 321	94.83 338	87.71 132	98.03 340	91.67 237	83.99 430	95.46 359

MVS-HIRNet		82.47 453	81.21 457	86.26 473	95.38 339	69.21 504	88.96 497	89.49 498	66.28 505	80.79 473	74.08 521	68.48 444	97.39 421	71.93 487	95.47 258	92.18 476

PatchmatchNet		91.91 281	91.35 276	93.59 340	95.38 339	84.11 415	93.15 456	95.39 391	89.54 301	92.10 268	93.68 401	82.82 255	98.13 319	84.81 391	95.32 261	98.52 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
cl____		90.96 336	90.32 326	92.89 370	95.37 341	86.21 372	94.46 412	96.64 319	87.82 362	88.15 384	94.18 379	82.98 249	97.54 406	87.70 332	85.59 402	94.92 399

DIV-MVS_self_test		90.97 335	90.33 325	92.88 371	95.36 342	86.19 374	94.46 412	96.63 322	87.82 362	88.18 382	94.23 376	82.99 248	97.53 408	87.72 329	85.57 403	94.93 397

miper_enhance_ethall		91.54 304	91.01 293	93.15 361	95.35 343	87.07 347	93.97 429	96.90 299	86.79 389	89.17 355	93.43 417	86.55 162	97.64 391	89.97 275	86.93 390	94.74 422

UniMVSNet_NR-MVSNet		93.37 219	92.67 229	95.47 213	95.34 344	92.83 93	97.17 207	98.58 27	92.98 152	90.13 317	95.80 289	88.37 119	97.85 367	91.71 234	83.93 431	95.73 350

ITE_SJBPF				92.43 383	95.34 344	85.37 395		95.92 360	91.47 219	87.75 391	96.39 259	71.00 418	97.96 352	82.36 421	89.86 357	93.97 444

OpenMVS	89.19 12	92.86 244	91.68 266	96.40 124	95.34 344	92.73 98	98.27 38	98.12 89	84.86 422	85.78 431	97.75 148	78.89 341	99.74 62	87.50 346	98.65 124	96.73 309

eth_miper_zixun_eth		91.02 332	90.59 318	92.34 387	95.33 347	84.35 411	94.10 426	96.90 299	88.56 339	88.84 364	94.33 368	84.08 224	97.60 396	88.77 311	84.37 427	95.06 390

miper_lstm_enhance		90.50 354	90.06 343	91.83 404	95.33 347	83.74 419	93.86 435	96.70 315	87.56 374	87.79 389	93.81 395	83.45 236	96.92 439	87.39 349	84.62 420	94.82 412

1314		92.81 248	92.03 252	95.14 230	95.33 347	89.52 249	96.04 326	97.44 219	87.72 369	86.25 420	95.33 314	83.84 227	98.79 219	89.26 295	97.05 197	97.11 297

PAPM		91.52 305	90.30 328	95.20 227	95.30 350	89.83 231	93.38 452	96.85 305	86.26 400	88.59 369	95.80 289	84.88 209	98.15 317	75.67 470	95.93 241	97.63 270

Fast-Effi-MVS+-dtu		92.29 266	91.99 254	93.21 359	95.27 351	85.52 388	97.03 215	96.63 322	92.09 197	89.11 357	95.14 324	80.33 310	98.08 329	87.54 343	94.74 275	96.03 334

Patchmatch-test		89.42 380	87.99 388	93.70 329	95.27 351	85.11 399	88.98 496	94.37 443	81.11 468	87.10 406	93.69 399	82.28 268	97.50 411	74.37 476	94.76 273	98.48 196

PVSNet_0	82.17 19	85.46 437	83.64 439	90.92 427	95.27 351	79.49 473	90.55 487	95.60 380	83.76 439	83.00 461	89.95 466	71.09 417	97.97 348	82.75 417	60.79 512	95.31 373

IB-MVS	87.33 17	89.91 368	88.28 386	94.79 256	95.26 354	87.70 330	95.12 389	93.95 456	89.35 309	87.03 407	92.49 432	70.74 421	99.19 159	89.18 300	81.37 448	97.49 279
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
nrg030		94.05 187	93.31 202	96.27 137	95.22 355	94.59 36	98.34 31	97.46 210	92.93 154	91.21 298	96.64 240	87.23 151	98.22 310	94.99 138	85.80 401	95.98 335

MDTV_nov1_ep13			90.76 304		95.22 355	80.33 459	93.03 459	95.28 399	88.14 353	92.84 251	93.83 392	81.34 286	98.08 329	82.86 412	94.34 281

MVS		91.71 288	90.44 322	95.51 207	95.20 357	91.59 144	96.04 326	97.45 215	73.44 496	87.36 399	95.60 303	85.42 195	99.10 176	85.97 376	97.46 173	95.83 340

SSC-MVS3.2		89.74 376	89.26 370	91.19 424	95.16 358	80.29 461	94.53 405	97.03 285	91.79 206	88.86 362	94.10 382	69.94 429	97.82 371	85.29 385	86.66 395	95.45 361

Syy-MVS		87.13 409	87.02 400	87.47 464	95.16 358	73.21 498	95.00 391	93.93 457	88.55 340	86.96 409	91.99 446	75.90 372	94.00 487	61.59 508	94.11 289	95.20 381

myMVS_eth3d		87.18 408	86.38 405	89.58 449	95.16 358	79.53 471	95.00 391	93.93 457	88.55 340	86.96 409	91.99 446	56.23 490	94.00 487	75.47 472	94.11 289	95.20 381

tfpnnormal		89.70 377	88.40 384	93.60 339	95.15 361	90.10 217	97.56 149	98.16 83	87.28 381	86.16 422	94.63 349	77.57 359	98.05 336	74.48 474	84.59 422	92.65 464

tpmrst		91.44 309	91.32 278	91.79 407	95.15 361	79.20 476	93.42 451	95.37 393	88.55 340	93.49 233	93.67 402	82.49 264	98.27 307	90.41 267	89.34 362	97.90 252

WR-MVS		92.34 262	91.53 271	94.77 257	95.13 363	90.83 185	96.40 292	97.98 123	91.88 204	89.29 349	95.54 307	82.50 263	97.80 374	89.79 280	85.27 409	95.69 351

tpm cat1		88.36 392	87.21 396	91.81 406	95.13 363	80.55 456	92.58 470	95.70 372	74.97 492	87.45 395	91.96 448	78.01 356	98.17 316	80.39 442	88.74 372	96.72 310

WR-MVS_H		92.00 278	91.35 276	93.95 313	95.09 365	89.47 250	98.04 65	98.68 18	91.46 220	88.34 375	94.68 345	85.86 178	97.56 399	85.77 379	84.24 428	94.82 412

CP-MVSNet		91.89 283	91.24 283	93.82 322	95.05 366	88.57 291	97.82 103	98.19 76	91.70 209	88.21 381	95.76 294	81.96 275	97.52 410	87.86 323	84.65 418	95.37 369

test_0402		86.46 420	84.79 428	91.45 415	95.02 367	85.55 387	96.29 305	94.89 419	80.90 469	82.21 465	93.97 390	68.21 446	97.29 426	62.98 506	88.68 373	91.51 483

cascas		91.20 324	90.08 339	94.58 271	94.97 368	89.16 268	93.65 446	97.59 178	79.90 477	89.40 344	92.92 424	75.36 378	98.36 296	92.14 220	94.75 274	96.23 321

PS-CasMVS		91.55 302	90.84 301	93.69 330	94.96 369	88.28 304	97.84 98	98.24 65	91.46 220	88.04 386	95.80 289	79.67 322	97.48 412	87.02 359	84.54 424	95.31 373

DU-MVS		92.90 241	92.04 251	95.49 210	94.95 370	92.83 93	97.16 208	98.24 65	93.02 146	90.13 317	95.71 296	83.47 234	97.85 367	91.71 234	83.93 431	95.78 344

NR-MVSNet		92.34 262	91.27 282	95.53 202	94.95 370	93.05 85	97.39 179	98.07 101	92.65 169	84.46 443	95.71 296	85.00 205	97.77 378	89.71 281	83.52 437	95.78 344

mvsany_test1		93.93 196	93.98 175	93.78 325	94.94 372	86.80 353	94.62 401	92.55 476	88.77 334	96.85 88	98.49 60	88.98 104	98.08 329	95.03 136	95.62 252	96.46 319

tpmvs		89.83 374	89.15 373	91.89 402	94.92 373	80.30 460	93.11 457	95.46 390	86.28 399	88.08 385	92.65 428	80.44 307	98.52 280	81.47 429	89.92 356	96.84 306

PMMVS		92.86 244	92.34 243	94.42 282	94.92 373	86.73 356	94.53 405	96.38 335	84.78 424	94.27 204	95.12 326	83.13 244	98.40 289	91.47 240	96.49 225	98.12 233

tpm2		89.96 367	89.21 371	92.23 393	94.91 375	81.25 447	93.78 438	94.42 439	80.62 474	91.56 282	93.44 414	76.44 369	97.94 358	85.60 381	92.08 327	97.49 279

TinyColmap		86.82 415	85.35 418	91.21 421	94.91 375	82.99 430	93.94 431	94.02 454	83.58 442	81.56 469	94.68 345	62.34 480	98.13 319	75.78 468	87.35 389	92.52 468

UniMVSNet_ETH3D		91.34 317	90.22 335	94.68 262	94.86 377	87.86 325	97.23 201	97.46 210	87.99 355	89.90 326	96.92 223	66.35 458	98.23 309	90.30 270	90.99 344	97.96 248

CostFormer		91.18 327	90.70 310	92.62 381	94.84 378	81.76 444	94.09 427	94.43 438	84.15 431	92.72 252	93.77 396	79.43 327	98.20 312	90.70 258	92.18 323	97.90 252

MIMVSNet		88.50 391	86.76 402	93.72 328	94.84 378	87.77 329	91.39 478	94.05 452	86.41 396	87.99 387	92.59 431	63.27 474	95.82 462	77.44 458	92.84 311	97.57 277

FMVSNet5		87.29 405	85.79 410	91.78 408	94.80 380	87.28 338	95.49 363	95.28 399	84.09 432	83.85 455	91.82 449	62.95 476	94.17 484	78.48 454	85.34 408	93.91 445

TranMVSNet+NR-MVSNet		92.50 253	91.63 267	95.14 230	94.76 381	92.07 123	97.53 155	98.11 92	92.90 158	89.56 340	96.12 273	83.16 242	97.60 396	89.30 293	83.20 440	95.75 348

test_vis1_n		92.37 261	92.26 246	92.72 377	94.75 382	82.64 432	98.02 67	96.80 308	91.18 237	97.77 63	97.93 116	58.02 486	98.29 304	97.63 39	98.21 146	97.23 293

XXY-MVS		92.16 272	91.23 284	94.95 246	94.75 382	90.94 180	97.47 168	97.43 222	89.14 314	88.90 359	96.43 256	79.71 321	98.24 308	89.56 286	87.68 382	95.67 352

EPMVS		90.70 346	89.81 353	93.37 352	94.73 384	84.21 413	93.67 444	88.02 503	89.50 303	92.38 257	93.49 410	77.82 358	97.78 376	86.03 375	92.68 315	98.11 239

D2MVS		91.30 319	90.95 295	92.35 385	94.71 385	85.52 388	96.18 317	98.21 69	88.89 326	86.60 415	93.82 394	79.92 318	97.95 356	89.29 294	90.95 345	93.56 449

USDC		88.94 384	87.83 390	92.27 390	94.66 386	84.96 404	93.86 435	95.90 362	87.34 379	83.40 456	95.56 305	67.43 449	98.19 314	82.64 419	89.67 359	93.66 448

GA-MVS		91.38 312	90.31 327	94.59 267	94.65 387	87.62 332	94.34 417	96.19 353	90.73 255	90.35 310	93.83 392	71.84 410	97.96 352	87.22 354	93.61 305	98.21 224

OPM-MVS		93.28 222	92.76 223	94.82 250	94.63 388	90.77 189	96.65 268	97.18 258	93.72 110	91.68 281	97.26 197	79.33 329	98.63 265	92.13 223	92.28 319	95.07 389
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
test-LLR		91.42 310	91.19 286	92.12 395	94.59 389	80.66 453	94.29 421	92.98 469	91.11 242	90.76 304	92.37 435	79.02 336	98.07 333	88.81 309	96.74 211	97.63 270

test-mter		90.19 363	89.54 363	92.12 395	94.59 389	80.66 453	94.29 421	92.98 469	87.68 371	90.76 304	92.37 435	67.67 447	98.07 333	88.81 309	96.74 211	97.63 270

dp		88.90 386	88.26 387	90.81 431	94.58 391	76.62 487	92.85 463	94.93 417	85.12 418	90.07 324	93.07 421	75.81 373	98.12 322	80.53 441	87.42 386	97.71 267

WB-MVSnew		89.88 371	89.56 362	90.82 430	94.57 392	83.06 429	95.65 354	92.85 471	87.86 361	90.83 303	94.10 382	79.66 323	96.88 441	76.34 465	94.19 287	92.54 467

PEN-MVS		91.20 324	90.44 322	93.48 348	94.49 393	87.91 324	97.76 111	98.18 79	91.29 227	87.78 390	95.74 295	80.35 309	97.33 424	85.46 383	82.96 441	95.19 384

gg-mvs-nofinetune		87.82 397	85.61 412	94.44 280	94.46 394	89.27 263	91.21 482	84.61 513	80.88 470	89.89 328	74.98 519	71.50 413	97.53 408	85.75 380	97.21 189	96.51 315

CR-MVSNet		90.82 341	89.77 355	93.95 313	94.45 395	87.19 343	90.23 489	95.68 377	86.89 387	92.40 255	92.36 438	80.91 295	97.05 433	81.09 437	93.95 297	97.60 275

RPMNet		88.98 383	87.05 398	94.77 257	94.45 395	87.19 343	90.23 489	98.03 113	77.87 488	92.40 255	87.55 489	80.17 313	99.51 121	68.84 496	93.95 297	97.60 275

TESTMET0.1,1		90.06 365	89.42 366	91.97 398	94.41 397	80.62 455	94.29 421	91.97 484	87.28 381	90.44 308	92.47 434	68.79 439	97.67 386	88.50 316	96.60 219	97.61 274

TransMVSNet (Re)		88.94 384	87.56 391	93.08 364	94.35 398	88.45 299	97.73 118	95.23 403	87.47 375	84.26 447	95.29 315	79.86 319	97.33 424	79.44 451	74.44 478	93.45 453

MS-PatchMatch		90.27 358	89.77 355	91.78 408	94.33 399	84.72 408	95.55 359	96.73 310	86.17 402	86.36 419	95.28 317	71.28 415	97.80 374	84.09 401	98.14 151	92.81 460

baseline2		91.63 294	90.86 298	93.94 315	94.33 399	86.32 368	95.92 335	91.64 486	89.37 308	86.94 411	94.69 344	81.62 283	98.69 250	88.64 314	94.57 278	96.81 307

XVG-ACMP-BASELINE		90.93 337	90.21 336	93.09 363	94.31 401	85.89 381	95.33 371	97.26 249	91.06 245	89.38 345	95.44 312	68.61 441	98.60 270	89.46 288	91.05 342	94.79 417

pm-mvs1		90.72 345	89.65 361	93.96 312	94.29 402	89.63 239	97.79 109	96.82 307	89.07 316	86.12 425	95.48 311	78.61 344	97.78 376	86.97 360	81.67 446	94.46 429

v8		91.29 321	90.53 321	93.57 343	94.15 403	88.12 316	97.34 184	97.06 280	88.99 321	88.32 376	94.26 375	83.08 245	98.01 342	87.62 341	83.92 433	94.57 427

v10		91.04 331	90.23 333	93.49 347	94.12 404	88.16 315	97.32 187	97.08 271	88.26 348	88.29 378	94.22 378	82.17 271	97.97 348	86.45 366	84.12 429	94.33 434

Patchmtry		88.64 390	87.25 394	92.78 376	94.09 405	86.64 357	89.82 493	95.68 377	80.81 472	87.63 393	92.36 438	80.91 295	97.03 434	78.86 453	85.12 412	94.67 424

PatchT		88.87 387	87.42 392	93.22 358	94.08 406	85.10 400	89.51 494	94.64 430	81.92 463	92.36 258	88.15 482	80.05 315	97.01 436	72.43 485	93.65 303	97.54 278

V42		91.58 300	90.87 297	93.73 326	94.05 407	88.50 296	97.32 187	96.97 289	88.80 333	89.71 332	94.33 368	82.54 262	98.05 336	89.01 303	85.07 413	94.64 426

DTE-MVSNet		90.56 350	89.75 357	93.01 365	93.95 408	87.25 340	97.64 137	97.65 165	90.74 254	87.12 403	95.68 299	79.97 317	97.00 437	83.33 408	81.66 447	94.78 419

tpm		90.25 359	89.74 358	91.76 410	93.92 409	79.73 468	93.98 428	93.54 462	88.28 347	91.99 270	93.25 420	77.51 360	97.44 416	87.30 353	87.94 379	98.12 233

PS-MVSNAJss		93.74 203	93.51 193	94.44 280	93.91 410	89.28 262	97.75 113	97.56 190	92.50 176	89.94 325	96.54 251	88.65 112	98.18 315	93.83 186	90.90 346	95.86 336

v1144		91.37 314	90.60 317	93.68 333	93.89 411	88.23 308	96.84 243	97.03 285	88.37 345	89.69 334	94.39 362	82.04 273	97.98 345	87.80 326	85.37 406	94.84 406

v2v482		91.59 298	90.85 300	93.80 323	93.87 412	88.17 314	96.94 227	96.88 302	89.54 301	89.53 341	94.90 334	81.70 282	98.02 341	89.25 296	85.04 415	95.20 381

v148		90.99 333	90.38 324	92.81 374	93.83 413	85.80 382	96.78 254	96.68 316	89.45 306	88.75 367	93.93 391	82.96 251	97.82 371	87.83 324	83.25 438	94.80 415

Baseline_NR-MVSNet		91.20 324	90.62 314	92.95 368	93.83 413	88.03 318	97.01 220	95.12 408	88.42 344	89.70 333	95.13 325	83.47 234	97.44 416	89.66 284	83.24 439	93.37 454

EPNet_dtu		91.71 288	91.28 281	92.99 366	93.76 415	83.71 421	96.69 264	95.28 399	93.15 141	87.02 408	95.95 281	83.37 237	97.38 422	79.46 450	96.84 205	97.88 254
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
v1192		91.07 329	90.23 333	93.58 341	93.70 416	87.82 328	96.73 258	97.07 274	87.77 366	89.58 338	94.32 370	80.90 297	97.97 348	86.52 364	85.48 404	94.95 393

GG-mvs-BLEND				93.62 338	93.69 417	89.20 265	92.39 473	83.33 516		87.98 388	89.84 468	71.00 418	96.87 442	82.08 423	95.40 260	94.80 415

test_fmvs2		89.77 375	89.93 348	89.31 455	93.68 418	76.37 488	97.64 137	95.90 362	89.84 290	91.49 284	96.26 266	58.77 484	97.10 430	94.65 162	91.13 340	94.46 429

tt0320-xc		84.83 441	82.33 450	92.31 388	93.66 419	86.20 373	96.17 318	94.06 451	71.26 499	82.04 467	92.22 443	55.07 493	96.72 447	81.49 428	75.04 475	94.02 442

v144192		91.06 330	90.28 329	93.39 351	93.66 419	87.23 342	96.83 244	97.07 274	87.43 376	89.69 334	94.28 372	81.48 284	98.00 343	87.18 356	84.92 417	94.93 397

usedtu_dtu_shiyan1		91.65 292	90.67 312	94.60 265	93.65 421	90.95 178	94.86 395	97.12 263	89.69 296	89.21 353	93.62 404	81.17 290	97.67 386	87.54 343	89.14 364	95.17 386

FE-MVSNET3		91.65 292	90.67 312	94.60 265	93.65 421	90.95 178	94.86 395	97.12 263	89.69 296	89.21 353	93.62 404	81.17 290	97.67 386	87.54 343	89.14 364	95.17 386

v1921920		90.85 340	90.03 344	93.29 355	93.55 423	86.96 351	96.74 257	97.04 283	87.36 378	89.52 342	94.34 367	80.23 312	97.97 348	86.27 367	85.21 410	94.94 395

v7n		90.76 342	89.86 350	93.45 350	93.54 424	87.60 333	97.70 127	97.37 232	88.85 327	87.65 392	94.08 385	81.08 292	98.10 324	84.68 393	83.79 435	94.66 425

JIA-IIPM		88.26 394	87.04 399	91.91 400	93.52 425	81.42 446	89.38 495	94.38 442	80.84 471	90.93 301	80.74 513	79.22 330	97.92 361	82.76 416	91.62 331	96.38 320

v1240		90.70 346	89.85 351	93.23 357	93.51 426	86.80 353	96.61 274	97.02 287	87.16 383	89.58 338	94.31 371	79.55 326	97.98 345	85.52 382	85.44 405	94.90 400

test_djsdf		93.07 232	92.76 223	94.00 307	93.49 427	88.70 285	98.22 47	97.57 182	91.42 222	90.08 323	95.55 306	82.85 254	97.92 361	94.07 176	91.58 332	95.40 366

SixPastTwentyTwo		89.15 382	88.54 383	90.98 426	93.49 427	80.28 462	96.70 262	94.70 427	90.78 252	84.15 449	95.57 304	71.78 411	97.71 384	84.63 394	85.07 413	94.94 395

test_vis1_rt		86.16 427	85.06 424	89.46 451	93.47 429	80.46 457	96.41 288	86.61 510	85.22 415	79.15 483	88.64 477	52.41 496	97.06 432	93.08 203	90.57 349	90.87 489

sc_t1		86.48 419	84.10 438	93.63 337	93.45 430	85.76 384	96.79 250	94.71 426	73.06 497	86.45 418	94.35 365	55.13 492	97.95 356	84.38 398	78.55 462	97.18 295

tt0320		85.39 438	83.12 442	92.19 394	93.44 431	85.79 383	96.19 316	94.87 423	71.19 500	82.92 462	91.76 452	58.43 485	96.81 444	81.03 438	78.26 463	93.98 443

mvs_tets		92.31 264	91.76 262	93.94 315	93.41 432	88.29 303	97.63 139	97.53 196	92.04 200	88.76 366	96.45 255	74.62 387	98.09 328	93.91 182	91.48 334	95.45 361

OurMVSNet-221017-0		90.51 353	90.19 337	91.44 416	93.41 432	81.25 447	96.98 224	96.28 343	91.68 210	86.55 417	96.30 262	74.20 390	97.98 345	88.96 306	87.40 388	95.09 388

pmmvs4		90.93 337	89.85 351	94.17 296	93.34 434	90.79 187	94.60 402	96.02 358	84.62 425	87.45 395	95.15 323	81.88 279	97.45 415	87.70 332	87.87 380	94.27 438

jajsoiax		92.42 258	91.89 259	94.03 306	93.33 435	88.50 296	97.73 118	97.53 196	92.00 202	88.85 363	96.50 253	75.62 377	98.11 323	93.88 184	91.56 333	95.48 356

gm-plane-assit					93.22 436	78.89 480			84.82 423		93.52 409		98.64 262	87.72 329

MVP-Stereo		90.74 344	90.08 339	92.71 378	93.19 437	88.20 312	95.86 338	96.27 344	86.07 403	84.86 441	94.76 341	77.84 357	97.75 381	83.88 406	98.01 157	92.17 477
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EU-MVSNet		88.72 389	88.90 378	88.20 460	93.15 438	74.21 495	96.63 273	94.22 448	85.18 416	87.32 400	95.97 279	76.16 371	94.98 476	85.27 386	86.17 397	95.41 363

MDA-MVSNet-bldmvs		85.00 439	82.95 445	91.17 425	93.13 439	83.33 424	94.56 404	95.00 412	84.57 426	65.13 507	92.65 428	70.45 423	95.85 460	73.57 481	77.49 464	94.33 434

K. test v3		87.64 400	86.75 403	90.32 439	93.02 440	79.48 474	96.61 274	92.08 483	90.66 261	80.25 478	94.09 384	67.21 451	96.65 448	85.96 377	80.83 450	94.83 407

dtuonly		90.88 339	91.13 288	90.13 442	92.98 441	75.01 492	92.74 467	95.54 385	87.69 370	91.37 287	96.61 249	79.65 324	98.15 317	87.44 348	96.21 235	97.23 293

MonoMVSNet		91.92 280	91.77 261	92.37 384	92.94 442	83.11 428	97.09 213	95.55 384	92.91 155	90.85 302	94.55 352	81.27 289	96.52 449	93.01 208	87.76 381	97.47 281

UWE-MVS-28		86.81 416	86.41 404	88.02 462	92.87 443	74.60 494	95.38 369	86.70 509	88.17 350	87.28 402	94.67 347	70.83 420	93.30 495	67.45 497	94.31 282	96.17 325

pmmvs5		89.86 373	88.87 379	92.82 373	92.86 444	86.23 371	96.26 308	95.39 391	84.24 430	87.12 403	94.51 355	74.27 389	97.36 423	87.61 342	87.57 383	94.86 402

testgi		87.97 395	87.21 396	90.24 440	92.86 444	80.76 451	96.67 267	94.97 414	91.74 208	85.52 433	95.83 287	62.66 479	94.47 481	76.25 466	88.36 376	95.48 356

EPNet		95.20 128	94.56 152	97.14 77	92.80 446	92.68 101	97.85 97	94.87 423	96.64 10	92.46 254	97.80 144	86.23 169	99.65 82	93.72 187	98.62 126	99.10 98
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
N_pmnet		78.73 461	78.71 462	78.79 486	92.80 446	46.50 537	94.14 425	43.71 539	78.61 483	80.83 472	91.66 453	74.94 384	96.36 452	67.24 498	84.45 425	93.50 451

EG-PatchMatch MVS		87.02 412	85.44 415	91.76 410	92.67 448	85.00 402	96.08 323	96.45 331	83.41 448	79.52 480	93.49 410	57.10 488	97.72 383	79.34 452	90.87 347	92.56 466

test_fmvsmconf0.01_n		96.15 89	95.85 93	97.03 85	92.66 449	91.83 133	97.97 79	97.84 145	95.57 29	97.53 65	99.00 17	84.20 222	99.76 57	98.82 24	99.08 103	99.48 57

Gipuma		67.86 477	65.41 479	75.18 495	92.66 449	73.45 497	66.50 531	94.52 435	53.33 521	57.80 517	66.07 527	30.81 511	89.20 507	48.15 522	78.88 461	62.90 529
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		92.16 272	91.55 270	93.97 311	92.58 451	89.55 246	97.51 157	97.42 224	89.42 307	88.40 373	94.84 337	80.66 302	97.88 366	91.87 229	91.28 338	94.48 428

EGC-MVSNET		68.77 475	63.01 484	86.07 474	92.49 452	82.24 441	93.96 430	90.96 493	0.71 561	2.62 563	90.89 458	53.66 494	93.46 492	57.25 515	84.55 423	82.51 511

test0.0.03 1		89.37 381	88.70 380	91.41 417	92.47 453	85.63 386	95.22 380	92.70 474	91.11 242	86.91 413	93.65 403	79.02 336	93.19 498	78.00 457	89.18 363	95.41 363

our_test_3		88.78 388	87.98 389	91.20 423	92.45 454	82.53 434	93.61 448	95.69 375	85.77 407	84.88 440	93.71 397	79.99 316	96.78 446	79.47 449	86.24 396	94.28 437

ppachtmachnet_test		88.35 393	87.29 393	91.53 413	92.45 454	83.57 423	93.75 439	95.97 359	84.28 428	85.32 437	94.18 379	79.00 340	96.93 438	75.71 469	84.99 416	94.10 439

dtuonlycased		85.91 432	85.69 411	86.60 471	92.42 456	76.96 484	93.66 445	94.49 437	86.68 390	80.87 471	92.00 445	71.52 412	93.23 497	79.58 446	79.97 453	89.60 495

YYNet1		85.87 434	84.23 436	90.78 434	92.38 457	82.46 438	93.17 454	95.14 407	82.12 462	67.69 501	92.36 438	78.16 352	95.50 472	77.31 460	79.73 455	94.39 432

MDA-MVSNet_test_wron		85.87 434	84.23 436	90.80 433	92.38 457	82.57 433	93.17 454	95.15 406	82.15 461	67.65 503	92.33 441	78.20 349	95.51 471	77.33 459	79.74 454	94.31 436

LF4IMVS		87.94 396	87.25 394	89.98 444	92.38 457	80.05 466	94.38 415	95.25 402	87.59 373	84.34 445	94.74 343	64.31 472	97.66 390	84.83 390	87.45 384	92.23 474

lessismore_v0				90.45 437	91.96 460	79.09 478		87.19 507		80.32 477	94.39 362	66.31 459	97.55 401	84.00 403	76.84 467	94.70 423

dmvs_testset		81.38 456	82.60 448	77.73 487	91.74 461	51.49 528	93.03 459	84.21 515	89.07 316	78.28 487	91.25 457	76.97 363	88.53 510	56.57 516	82.24 445	93.16 455

ArgMatch-Sym		83.08 451	81.73 455	87.11 467	91.53 462	76.72 486	92.86 462	91.54 487	83.66 441	82.34 464	93.45 413	44.99 503	92.15 501	81.78 425	73.46 483	92.47 470

ArgMatch-SfM		83.09 450	81.67 456	87.34 466	91.48 463	76.29 489	92.76 465	91.31 490	84.26 429	81.99 468	93.35 418	45.52 502	92.98 499	81.83 424	72.49 486	92.76 461

0.4-1-1-0.1		86.83 414	84.27 435	94.50 276	91.39 464	88.23 308	92.62 469	92.27 480	84.04 433	86.01 427	83.30 506	65.29 468	98.31 301	89.08 302	74.45 477	96.96 303

pmmvs6		87.81 398	86.19 407	92.69 379	91.32 465	86.30 369	97.34 184	96.41 333	80.59 475	84.05 453	94.37 364	67.37 450	97.67 386	84.75 392	79.51 457	94.09 441

Anonymous20231206		87.09 410	86.14 408	89.93 446	91.22 466	80.35 458	96.11 320	95.35 394	83.57 443	84.16 448	93.02 422	73.54 398	95.61 466	72.16 486	86.14 398	93.84 446

KD-MVS_2432*1600		84.81 442	82.64 446	91.31 419	91.07 467	85.34 396	91.22 480	95.75 370	85.56 410	83.09 459	90.21 464	67.21 451	95.89 458	77.18 462	62.48 510	92.69 462

miper_refine_blended		84.81 442	82.64 446	91.31 419	91.07 467	85.34 396	91.22 480	95.75 370	85.56 410	83.09 459	90.21 464	67.21 451	95.89 458	77.18 462	62.48 510	92.69 462

DeepMVS_CX				74.68 497	90.84 469	64.34 515		81.61 518	65.34 507	67.47 504	88.01 484	48.60 500	80.13 525	62.33 507	73.68 482	79.58 514

0.3-1-1-0.015		86.11 429	83.37 441	94.34 286	90.58 470	88.02 319	91.64 477	92.45 478	83.56 444	84.46 443	81.84 509	62.73 478	98.31 301	88.98 305	74.09 480	96.70 311

0.4-1-1-0.2		86.27 425	83.62 440	94.20 294	90.38 471	87.69 331	91.04 483	92.52 477	83.43 447	85.22 438	81.49 511	65.31 467	98.29 304	88.90 308	74.30 479	96.64 312

Anonymous20240521		86.42 421	85.44 415	89.34 454	90.33 472	79.79 467	96.73 258	95.92 360	83.71 440	83.25 458	91.36 456	63.92 473	96.01 456	78.39 456	85.36 407	92.22 475

test20.03		86.14 428	85.40 417	88.35 458	90.12 473	80.06 465	95.90 337	95.20 404	88.59 336	81.29 470	93.62 404	71.43 414	92.65 500	71.26 490	81.17 449	92.34 471

OpenMVS_ROB	81.14 20	84.42 444	82.28 451	90.83 429	90.06 474	84.05 417	95.73 348	94.04 453	73.89 495	80.17 479	91.53 454	59.15 483	97.64 391	66.92 500	89.05 366	90.80 490

UnsupCasMVSNet_eth		85.99 430	84.45 433	90.62 435	89.97 475	82.40 439	93.62 447	97.37 232	89.86 287	78.59 486	92.37 435	65.25 470	95.35 474	82.27 422	70.75 495	94.10 439

DSMNet-mixed		86.34 423	86.12 409	87.00 470	89.88 476	70.43 501	94.93 393	90.08 497	77.97 487	85.42 436	92.78 425	74.44 388	93.96 489	74.43 475	95.14 264	96.62 313

new_pmnet		82.89 452	81.12 458	88.18 461	89.63 477	80.18 464	91.77 476	92.57 475	76.79 490	75.56 493	88.23 481	61.22 482	94.48 480	71.43 488	82.92 442	89.87 493

MIMVSNet1		84.93 440	83.05 443	90.56 436	89.56 478	84.84 407	95.40 367	95.35 394	83.91 434	80.38 476	92.21 444	57.23 487	93.34 494	70.69 492	82.75 444	93.50 451

KD-MVS_self_test		85.95 431	84.95 425	88.96 457	89.55 479	79.11 477	95.13 388	96.42 332	85.91 405	84.07 452	90.48 461	70.03 428	94.82 477	80.04 443	72.94 484	92.94 458

ttmdpeth		85.91 432	84.76 429	89.36 453	89.14 480	80.25 463	95.66 353	93.16 468	83.77 438	83.39 457	95.26 319	66.24 460	95.26 475	80.65 439	75.57 472	92.57 465

CMPMVS	62.92 21	85.62 436	84.92 426	87.74 463	89.14 480	73.12 499	94.17 424	96.80 308	73.98 493	73.65 496	94.93 332	66.36 457	97.61 395	83.95 404	91.28 338	92.48 469
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		79.31 460	77.70 463	84.14 475	89.11 482	69.07 505	92.36 474	91.50 488	69.07 502	73.87 495	92.63 430	39.93 507	94.32 482	70.54 494	80.25 452	89.02 497

blend_shiyan4		86.87 413	84.61 432	93.67 334	88.87 483	88.70 285	95.17 386	96.30 339	82.80 454	86.16 422	87.11 492	65.12 471	97.55 401	87.73 327	72.21 487	94.75 421

CL-MVSNet_self_test		86.31 424	85.15 422	89.80 447	88.83 484	81.74 445	93.93 432	96.22 349	86.67 391	85.03 439	90.80 459	78.09 353	94.50 479	74.92 473	71.86 488	93.15 456

blended_shiyan6		87.55 402	85.52 414	93.64 336	88.78 485	88.50 296	95.23 379	96.30 339	82.80 454	86.09 426	87.70 487	73.69 397	97.56 399	87.70 332	71.36 491	94.86 402

dongtai		69.99 472	69.33 472	71.98 500	88.78 485	61.64 518	89.86 492	59.93 531	75.67 491	74.96 494	85.45 501	50.19 498	81.66 522	43.86 524	55.27 516	72.63 520

blended_shiyan8		87.58 401	85.55 413	93.66 335	88.76 487	88.54 293	95.21 382	96.29 342	82.81 453	86.25 420	87.73 486	73.70 396	97.58 398	87.81 325	71.42 490	94.85 405

mvs5depth		86.53 417	85.08 423	90.87 428	88.74 488	82.52 435	91.91 475	94.23 447	86.35 397	87.11 405	93.70 398	66.52 456	97.76 379	81.37 433	75.80 471	92.31 473

Patchmatch-RL test		87.38 403	86.24 406	90.81 431	88.74 488	78.40 481	88.12 505	93.17 466	87.11 384	82.17 466	89.29 472	81.95 276	95.60 467	88.64 314	77.02 466	98.41 204

gbinet_0.2-2-1-0.02		87.30 404	85.16 421	93.69 330	88.70 490	88.81 282	95.14 387	96.20 352	83.03 451	86.14 424	87.06 493	71.26 416	97.40 420	87.46 347	71.49 489	94.86 402

wanda-best-256-512		87.29 405	85.21 419	93.53 344	88.54 491	88.21 310	94.51 408	96.27 344	82.69 457	85.92 428	86.89 495	73.04 400	97.55 401	87.68 336	71.36 491	94.83 407

FE-blended-shiyan7		87.29 405	85.21 419	93.53 344	88.54 491	88.21 310	94.51 408	96.27 344	82.69 457	85.92 428	86.89 495	73.03 401	97.55 401	87.68 336	71.36 491	94.83 407

usedtu_blend_shiyan5		87.06 411	84.84 427	93.69 330	88.54 491	88.70 285	95.83 340	95.54 385	78.74 482	85.92 428	86.89 495	73.03 401	97.55 401	87.73 327	71.36 491	94.83 407

pmmvs-eth3d		86.22 426	84.45 433	91.53 413	88.34 494	87.25 340	94.47 410	95.01 411	83.47 445	79.51 481	89.61 470	69.75 432	95.71 463	83.13 410	76.73 469	91.64 480

UnsupCasMVSNet_bld		82.13 455	79.46 461	90.14 441	88.00 495	82.47 437	90.89 486	96.62 324	78.94 481	75.61 491	84.40 504	56.63 489	96.31 454	77.30 461	66.77 504	91.63 481

PM-MVS		83.48 447	81.86 454	88.31 459	87.83 496	77.59 483	93.43 450	91.75 485	86.91 386	80.63 474	89.91 467	44.42 505	95.84 461	85.17 389	76.73 469	91.50 485

FE-MVSNET2		86.36 422	84.68 431	91.39 418	87.67 497	86.47 365	96.21 313	96.41 333	87.87 360	79.31 482	89.64 469	65.29 468	95.58 468	82.42 420	77.28 465	92.14 478

MVStest1		82.38 454	80.04 459	89.37 452	87.63 498	82.83 431	95.03 390	93.37 465	73.90 494	73.50 497	94.35 365	62.89 477	93.25 496	73.80 479	65.92 506	92.04 479

DenseAffine		72.53 466	69.17 473	82.59 479	87.49 499	70.91 500	88.38 502	81.13 519	67.58 504	64.27 509	87.44 491	23.61 521	88.47 512	66.10 501	56.56 514	88.38 498

FE-MVSNET		83.85 445	81.97 452	89.51 450	87.19 500	83.19 427	95.21 382	93.17 466	83.45 446	78.90 484	89.05 474	65.46 465	93.84 491	69.71 495	75.56 473	91.51 483

new-patchmatchnet		83.18 449	81.87 453	87.11 467	86.88 501	75.99 491	93.70 441	95.18 405	85.02 420	77.30 489	88.40 479	65.99 462	93.88 490	74.19 478	70.18 496	91.47 486

test_fmvs3		83.21 448	83.02 444	83.78 476	86.77 502	68.34 506	96.76 256	94.91 418	86.49 394	84.14 450	89.48 471	36.04 509	91.73 503	91.86 230	80.77 451	91.26 488

LoFTR		72.43 467	68.71 474	83.60 477	85.67 503	65.61 512	88.04 506	87.40 506	66.11 506	55.94 520	85.54 500	25.43 516	95.55 470	60.87 509	63.38 509	89.63 494

WB-MVS		76.77 462	76.63 466	77.18 488	85.32 504	56.82 525	94.53 405	89.39 499	82.66 459	71.35 499	89.18 473	75.03 381	88.88 508	35.42 529	66.79 503	85.84 503

SSC-MVS		76.05 463	75.83 467	76.72 492	84.77 505	56.22 526	94.32 419	88.96 501	81.82 465	70.52 500	88.91 475	74.79 385	88.71 509	33.69 531	64.71 507	85.23 506

RoMa-SfM		70.64 470	67.48 475	80.09 481	84.70 506	66.61 509	88.62 500	73.09 526	65.10 508	64.98 508	88.91 475	22.38 522	87.00 513	63.51 505	56.06 515	86.67 501

kuosan		65.27 480	64.66 481	67.11 506	83.80 507	61.32 519	88.53 501	60.77 530	68.22 503	67.67 502	80.52 514	49.12 499	70.76 532	29.67 533	53.64 518	69.26 522

mvsany_test3		83.59 446	82.44 449	87.03 469	83.80 507	73.82 496	93.70 441	90.92 494	86.42 395	82.51 463	90.26 463	46.76 501	95.71 463	90.82 253	76.76 468	91.57 482

ambc				86.56 472	83.60 509	70.00 503	85.69 510	94.97 414		80.60 475	88.45 478	37.42 508	96.84 443	82.69 418	75.44 474	92.86 459

DKM		67.96 476	64.19 482	79.27 484	83.41 510	64.35 514	86.88 508	68.11 528	63.15 511	59.36 513	86.08 499	16.45 534	86.15 515	64.54 503	49.73 519	87.32 500

test_f		80.57 457	79.62 460	83.41 478	83.38 511	67.80 508	93.57 449	93.72 460	80.80 473	77.91 488	87.63 488	33.40 510	92.08 502	87.14 358	79.04 460	90.34 492

MatchFormer		67.84 478	63.81 483	79.93 483	83.26 512	60.99 520	87.61 507	84.49 514	54.89 519	51.76 521	81.06 512	22.08 523	94.10 485	50.36 521	58.82 513	84.72 507

pmmvs3		79.97 459	77.50 464	87.39 465	82.80 513	79.38 475	92.70 468	90.75 495	70.69 501	78.66 485	87.47 490	51.34 497	93.40 493	73.39 482	69.65 497	89.38 496

TDRefinement		86.53 417	84.76 429	91.85 403	82.23 514	84.25 412	96.38 294	95.35 394	84.97 421	84.09 451	94.94 331	65.76 464	98.34 300	84.60 395	74.52 476	92.97 457

usedtu_dtu_shiyan2		80.00 458	76.91 465	89.27 456	82.13 515	79.69 469	95.45 365	94.20 449	72.95 498	75.80 490	87.75 485	44.44 504	94.30 483	70.64 493	68.81 501	93.84 446

ALIKED-LG		47.63 493	45.22 497	54.88 510	81.48 516	48.47 533	71.83 524	45.44 538	32.66 529	37.07 533	63.26 530	19.21 528	63.71 533	15.49 543	40.53 530	52.46 530

ALIKED-MNN		45.42 496	42.62 500	53.80 512	80.52 517	47.58 535	70.83 527	43.05 541	27.21 531	34.32 537	61.10 532	14.85 538	62.94 534	14.90 544	36.82 533	50.89 531

ALIKED-NN		46.19 495	43.87 498	53.16 513	80.39 518	47.77 534	69.82 530	43.65 540	27.89 530	36.60 534	63.35 529	17.30 530	61.29 535	15.84 542	39.98 531	50.41 532

test_vis3_rt		72.73 464	70.55 468	79.27 484	80.02 519	68.13 507	93.92 433	74.30 525	76.90 489	58.99 515	73.58 522	20.29 524	95.37 473	84.16 399	72.80 485	74.31 517

DKM-HiRes		64.02 482	59.97 486	76.17 493	79.46 520	59.20 521	84.48 513	58.37 534	58.52 515	56.03 519	83.71 505	13.19 542	83.72 519	60.49 510	45.50 523	85.59 504

RoMa-HiRes		64.40 481	60.91 485	74.89 496	78.66 521	58.85 523	85.22 512	58.46 533	58.65 514	59.29 514	86.60 498	16.97 531	83.91 518	59.14 511	45.20 524	81.91 513

testf1		69.31 473	66.76 477	76.94 490	78.61 522	61.93 516	88.27 503	86.11 511	55.62 516	59.69 511	85.31 502	20.19 525	89.32 505	57.62 513	69.44 499	79.58 514

APD_test2		69.31 473	66.76 477	76.94 490	78.61 522	61.93 516	88.27 503	86.11 511	55.62 516	59.69 511	85.31 502	20.19 525	89.32 505	57.62 513	69.44 499	79.58 514

PMMVS2		70.19 471	66.92 476	80.01 482	76.35 524	65.67 511	86.22 509	87.58 505	64.83 509	62.38 510	80.29 515	26.78 515	88.49 511	63.79 504	54.07 517	85.88 502

PDCNetPlus		61.05 484	58.26 488	69.44 503	75.52 525	55.68 527	81.49 517	51.76 536	62.45 512	51.54 522	82.02 508	23.69 520	78.90 526	65.91 502	29.91 541	73.74 518

FPMVS		71.27 468	69.85 470	75.50 494	74.64 526	59.03 522	91.30 479	91.50 488	58.80 513	57.92 516	88.28 480	29.98 513	85.53 516	53.43 519	82.84 443	81.95 512

MASt3R-SfM		71.17 469	70.37 469	73.55 498	74.50 527	51.20 529	82.17 516	80.88 520	64.49 510	72.54 498	91.37 455	25.17 518	81.85 521	75.86 467	66.37 505	87.59 499

E-PMN		53.28 488	52.56 492	55.43 509	74.43 528	47.13 536	83.63 515	76.30 521	42.23 525	42.59 529	62.22 531	28.57 514	74.40 529	31.53 532	31.51 536	44.78 533

SP-LightGlue		43.37 498	42.49 502	46.03 515	74.26 529	31.37 546	71.24 526	40.98 544	23.86 534	33.18 539	56.34 537	16.78 532	39.73 541	21.09 539	44.68 525	66.97 524

wuyk23d		25.11 512	24.57 517	26.74 527	73.98 530	39.89 541	57.88 535	9.80 566	12.27 554	10.39 557	6.97 561	7.03 547	36.44 545	25.43 535	17.39 555	3.89 558

SP-SuperGlue		43.33 499	42.50 501	45.81 516	73.95 531	31.24 547	71.34 525	41.17 543	23.96 533	33.42 538	56.47 535	16.72 533	39.64 542	21.11 538	44.32 526	66.57 525

SP-MNN		42.11 501	40.98 506	45.49 518	72.87 532	30.19 551	70.72 528	39.96 545	20.98 536	30.21 543	55.72 539	15.26 537	40.07 540	19.70 541	43.42 528	66.21 526

SP-NN		42.37 500	41.40 504	45.29 519	72.86 533	30.45 549	70.32 529	39.16 547	22.21 535	31.32 540	56.73 534	15.45 536	39.53 543	20.27 540	44.25 527	65.88 527

test_method		66.11 479	64.89 480	69.79 502	72.62 534	35.23 543	65.19 532	92.83 473	20.35 538	65.20 506	88.08 483	43.14 506	82.70 520	73.12 483	63.46 508	91.45 487

EMVS		52.08 491	51.31 494	54.39 511	72.62 534	45.39 538	83.84 514	75.51 523	41.13 526	40.77 531	59.65 533	30.08 512	73.60 530	28.31 534	29.90 542	44.18 534

LCM-MVSNet		72.55 465	69.39 471	82.03 480	70.81 536	65.42 513	90.12 491	94.36 445	55.02 518	65.88 505	81.72 510	24.16 519	89.96 504	74.32 477	68.10 502	90.71 491

PMatch-SfM		57.38 487	52.53 493	71.95 501	68.62 537	49.38 530	77.61 520	45.82 537	52.41 522	46.59 525	82.04 507	4.86 559	81.03 523	58.34 512	36.49 534	85.43 505

ELoFTR		60.03 485	55.86 489	72.52 499	67.65 538	48.49 532	76.21 521	75.14 524	53.94 520	45.93 526	79.98 517	9.14 544	85.06 517	55.39 517	39.36 532	84.02 509

MVE	50.73 23	53.25 489	48.81 495	66.58 507	65.34 539	57.50 524	72.49 522	70.94 527	40.15 527	39.28 532	63.51 528	6.89 548	73.48 531	38.29 527	42.38 529	68.76 523
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SIFT-NN		28.47 506	28.54 511	28.27 523	64.38 540	31.62 545	48.50 538	24.78 550	14.32 542	19.55 546	40.46 542	7.22 546	31.96 546	6.20 549	31.47 537	21.24 541

PMatch-Up-SfM		52.53 490	47.58 496	67.36 505	63.24 541	43.29 540	72.10 523	34.71 549	47.03 523	43.51 527	79.07 518	3.90 562	75.83 527	54.68 518	30.02 540	82.95 510

SIFT-MNN		27.50 507	27.40 512	27.80 524	61.71 542	30.57 548	46.59 540	24.66 551	14.04 543	17.35 547	39.90 543	6.52 549	31.80 547	6.13 550	29.65 543	21.04 542

ANet_high		63.94 483	59.58 487	77.02 489	61.24 543	66.06 510	85.66 511	87.93 504	78.53 484	42.94 528	71.04 523	25.42 517	80.71 524	52.60 520	30.83 538	84.28 508

SIFT-NCM-Cal		25.87 509	25.57 514	26.75 526	60.60 544	29.37 552	44.96 543	22.64 554	13.57 548	11.67 555	37.90 549	5.81 554	31.26 549	5.32 557	27.70 546	19.63 547

SIFT-NN-NCMNet		27.16 508	27.05 513	27.51 525	59.97 545	30.42 550	46.49 541	24.52 552	13.94 545	17.23 548	39.47 544	6.39 550	31.40 548	5.94 551	29.49 544	20.72 544

SIFT-ConvMatch		24.62 513	24.14 518	26.03 530	58.66 546	29.15 553	40.80 548	21.31 556	13.69 547	13.51 551	38.52 547	5.65 555	30.22 552	5.51 556	19.65 552	18.73 549

SIFT-CM-Cal		23.18 517	22.70 521	24.60 533	57.42 547	26.79 556	37.63 550	18.36 559	13.35 550	12.57 553	37.37 552	5.54 556	28.79 554	5.17 559	16.92 557	18.23 550

SIFT-UMatch		24.03 514	23.67 520	25.10 532	57.10 548	26.49 557	42.43 546	20.05 558	13.49 549	12.40 554	38.51 548	5.45 557	30.07 553	5.56 554	18.08 554	18.74 548

SIFT-NN-CMatch		25.59 510	25.23 515	26.67 529	56.47 549	28.89 554	42.75 545	22.52 555	13.89 546	16.98 549	39.39 546	6.26 552	30.38 550	5.77 553	22.99 549	20.75 543

SIFT-UM-Cal		22.52 518	22.27 522	23.27 535	56.41 550	23.87 560	39.94 549	16.81 561	13.33 551	10.54 556	37.90 549	5.16 558	28.36 556	5.23 558	15.12 558	17.57 551

SIFT-NN-UMatch		25.24 511	25.01 516	25.92 531	54.55 551	27.33 555	44.97 542	22.85 553	13.97 544	13.40 552	39.41 545	6.28 551	30.23 551	5.83 552	23.82 548	20.21 545

SIFT-NN-PointCN		23.81 515	23.84 519	23.73 534	52.41 552	22.80 562	42.30 547	20.98 557	13.02 552	15.14 550	37.74 551	6.20 553	28.40 555	5.52 555	21.24 550	19.98 546

MVS_clip		37.19 503	40.69 507	26.70 528	52.35 553	23.34 561	43.13 544	10.51 564	12.50 553	56.71 518	80.13 516	19.51 527	16.50 560	43.87 523	47.47 520	40.26 537

GLUNet-SfM		46.44 494	41.21 505	62.14 508	51.92 554	38.44 542	58.72 534	57.51 535	34.08 528	34.61 536	67.84 525	11.40 543	74.90 528	35.48 528	19.30 553	73.08 519

SIFT-PCN-Cal		20.26 521	20.34 525	20.01 537	51.70 555	17.74 565	35.64 552	16.15 562	11.90 556	10.28 558	33.69 553	4.55 560	25.68 557	4.57 560	14.59 559	16.60 554

SIFT-PointCN		20.70 520	20.89 524	20.14 536	51.62 556	18.11 564	37.52 551	17.71 560	12.03 555	10.05 559	33.23 554	4.33 561	25.40 558	4.55 561	16.94 556	16.90 552

PMVS	53.92 22	58.58 486	55.40 490	68.12 504	51.00 557	48.64 531	78.86 518	87.10 508	46.77 524	35.84 535	74.28 520	8.76 545	86.34 514	42.07 526	73.91 481	69.38 521
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SIFT-NCMNet		17.70 522	17.74 526	17.60 538	49.47 558	16.50 566	30.22 553	10.39 565	11.77 557	8.79 560	29.74 556	3.61 564	22.42 559	3.97 562	11.69 560	13.89 555

SP-DiffGlue		43.94 497	43.32 499	45.79 517	47.79 559	33.03 544	63.37 533	42.65 542	25.71 532	41.26 530	69.27 524	18.83 529	38.88 544	34.96 530	46.05 521	65.47 528

XFeat-MNN		35.01 504	34.34 508	37.02 520	42.54 560	25.71 558	54.01 536	39.41 546	20.70 537	30.13 544	55.85 538	14.08 540	44.62 538	22.90 536	29.45 545	40.75 535

XFeat-NN		33.93 505	33.70 509	34.60 522	41.69 561	24.48 559	51.85 537	36.02 548	19.55 539	31.20 541	56.38 536	13.46 541	40.91 539	22.51 537	30.65 539	38.42 538

VLMVS_CLIP		39.93 502	41.64 503	34.80 521	33.81 562	19.16 563	46.81 539	59.30 532	16.50 541	47.57 524	67.74 526	14.11 539	49.88 537	42.98 525	45.94 522	35.36 539

tmp_tt		51.94 492	53.82 491	46.29 514	33.73 563	45.30 539	78.32 519	67.24 529	18.02 540	50.93 523	87.05 494	52.99 495	53.11 536	70.76 491	25.29 547	40.46 536

VLMVS		20.83 519	22.16 523	16.83 539	23.35 564	13.77 567	21.05 554	12.13 563	1.76 560	31.04 542	45.78 541	15.59 535	13.56 561	13.60 545	35.16 535	23.18 540

MVS_baseline		12.31 525	14.46 529	5.86 540	16.09 565	0.78 570	6.53 555	1.85 568	0.36 562	23.99 545	49.92 540	2.55 565	0.00 564	8.94 546	19.86 551	16.82 553

testmvs		13.36 523	16.33 527	4.48 542	5.04 566	2.26 569	93.18 453	3.28 567	2.70 558	8.24 561	21.66 557	2.29 566	2.19 562	7.58 547	2.96 561	9.00 557

test123		13.04 524	15.66 528	5.18 541	4.51 567	3.45 568	92.50 472	1.81 569	2.50 559	7.58 562	20.15 558	3.67 563	2.18 563	7.13 548	1.07 562	9.90 556

PatchmatchNet2					0.00 568	79.04 479	92.75 466	94.19 450	78.18 485
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmdepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

monomultidepth		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

test_blank		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

eth-test2					0.00 568

eth-test					0.00 568

uanet_test		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

DCPMVS		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

cdsmvs_eth3d_5k		23.24 516	30.99 510	0.00 543	0.00 568	0.00 571	0.00 556	97.63 169	0.00 563	0.00 564	96.88 225	84.38 217	0.00 564	0.00 563	0.00 563	0.00 559

pcd_1.5k_mvsjas		7.39 527	9.85 531	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	88.65 112	0.00 564	0.00 563	0.00 563	0.00 559

sosnet-low-res		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

sosnet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uncertanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Regformer		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

ab-mvs-re		8.06 526	10.74 530	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	96.69 237	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

uanet		0.00 528	0.00 532	0.00 543	0.00 568	0.00 571	0.00 556	0.00 570	0.00 563	0.00 564	0.00 562	0.00 567	0.00 564	0.00 563	0.00 563	0.00 559

Meshroom													0.00 564
: In preparation.
AliceVision / Meshro													0.00 564
: In preparation.
AliceVision_Meshroom													0.00 564
: In preparation.
PatchmatchNet1														67.11 499	84.43 426	93.53 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													96.32 453
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
WAC-MVS						79.53 471								75.56 471

PC_three_1452									90.77 253	98.89 29	98.28 88	96.24 1	98.35 297	95.76 109	99.58 27	99.59 33

test_241102_TWO								98.27 57	95.13 43	98.93 23	98.89 31	94.99 12	99.85 23	97.52 44	99.65 15	99.74 10

test_0728_THIRD									94.78 64	98.73 33	98.87 34	95.87 4	99.84 28	97.45 48	99.72 2	99.77 4

GSMVS																98.45 199

sam_mvs1												82.76 256				98.45 199

sam_mvs												81.94 277

MTGPA								98.08 96

test_post1							92.81 464				16.58 560	80.53 305	97.68 385	86.20 369

test_post											17.58 559	81.76 280	98.08 329

patchmatchnet-post											90.45 462	82.65 261	98.10 324

MTMP							97.86 94	82.03 517

test9_res														94.81 152	99.38 66	99.45 60

agg_prior2														93.94 181	99.38 66	99.50 53

test_prior4						93.66 65	96.42 287

test_prior2							96.35 297		92.80 163	96.03 132	97.59 172	92.01 53		95.01 137	99.38 66

旧先验2							95.94 333		81.66 466	97.34 74			98.82 213	92.26 215

新几何2							95.79 344

无先验							95.79 344	97.87 135	83.87 437				99.65 82	87.68 336		98.89 142

原ACMM2							95.67 350

testdata2													99.67 80	85.96 377

segment_acmp												92.89 36

testdata1							95.26 378		93.10 144

plane_prior5								97.51 198					98.60 270	93.02 206	92.23 320	95.86 336

plane_prior4											96.64 240

plane_prior3						90.00 220			94.46 82	91.34 289

plane_prior2							97.74 116		94.85 56

plane_prior						89.99 222	97.24 197		94.06 97						92.16 324

n2								0.00 570

nn								0.00 570

door-mid								91.06 492

test11								97.88 133

door								91.13 491

HQP5-MVS						89.33 258

BP-MVS														92.13 223

HQP4-MVS										90.14 313			98.50 281			95.78 344

HQP3-MVS								97.39 227							92.10 325

HQP2-MVS												80.95 293

MDTV_nov1_ep13_2view						70.35 502	93.10 458		83.88 436	93.55 228		82.47 265		86.25 368		98.38 207

ACMMP++_ref															90.30 354

ACMMP++															91.02 343

Test By Simon												88.73 111

High-resolution multi-view benchmark