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.

MED-MVS test				94.84 32	98.88 1	85.89 64	97.32 10	97.86 1	88.11 129	97.21 14	97.54 44		99.67 1	95.27 40	98.85 20	98.95 11

MED-MVS		95.74 3	96.04 3	94.84 32	98.88 1	85.89 64	97.32 10	97.86 1	89.01 94	97.21 14	97.54 44	92.42 4	99.67 1	95.27 40	98.85 20	98.95 11

TestfortrainingZip a		95.70 4	95.76 5	95.51 8	98.88 1	87.98 10	97.32 10	97.86 1	88.11 129	97.21 14	97.54 44	92.42 4	99.67 1	93.66 60	98.85 20	98.89 15

FOURS1					98.86 4	85.54 73	98.29 1	97.49 12	89.79 63	96.29 32

test_0728_SECOND				95.01 18	98.79 5	86.43 40	97.09 21	97.49 12					99.61 7	95.62 34	99.08 7	98.99 9

DVP-MVS		95.67 5	96.02 4	94.64 43	98.78 6	85.93 58	97.09 21	96.73 97	90.27 45	97.04 22	98.05 25	91.47 10	99.55 20	95.62 34	99.08 7	98.45 41
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
test0726					98.78 6	85.93 58	97.19 16	97.47 17	90.27 45	97.64 6	98.13 7	91.47 10

SED-MVS		95.91 2	96.28 2	94.80 37	98.77 8	85.99 55	97.13 19	97.44 21	90.31 41	97.71 2	98.07 20	92.31 6	99.58 14	95.66 30	99.13 3	98.84 19

IU-MVS					98.77 8	86.00 53		96.84 82	81.26 340	97.26 13				95.50 36	99.13 3	99.03 8

test_241102_ONE					98.77 8	85.99 55		97.44 21	90.26 47	97.71 2	97.96 31	92.31 6	99.38 35

region2R		94.43 36	94.27 47	94.92 21	98.65 11	86.67 31	96.92 29	97.23 43	88.60 111	93.58 79	97.27 58	85.22 63	99.54 24	92.21 94	98.74 35	98.56 30

ACMMPR		94.43 36	94.28 45	94.91 22	98.63 12	86.69 29	96.94 25	97.32 34	88.63 108	93.53 82	97.26 60	85.04 67	99.54 24	92.35 89	98.78 30	98.50 32

HFP-MVS		94.52 31	94.40 38	94.86 25	98.61 13	86.81 26	96.94 25	97.34 30	88.63 108	93.65 77	97.21 62	86.10 52	99.49 30	92.35 89	98.77 32	98.30 55

test_one_0601					98.58 14	85.83 67		97.44 21	91.05 23	96.78 27	98.06 22	91.45 13

test_part2					98.55 15	87.22 20				96.40 31

XVS		94.45 34	94.32 41	94.85 26	98.54 16	86.60 35	96.93 27	97.19 44	90.66 34	92.85 95	97.16 68	85.02 68	99.49 30	91.99 105	98.56 54	98.47 38

X-MVStestdata		88.31 233	86.13 282	94.85 26	98.54 16	86.60 35	96.93 27	97.19 44	90.66 34	92.85 95	23.41 493	85.02 68	99.49 30	91.99 105	98.56 54	98.47 38

ZNCC-MVS		94.47 33	94.28 45	95.03 17	98.52 18	86.96 21	96.85 33	97.32 34	88.24 121	93.15 87	97.04 73	86.17 51	99.62 5	92.40 86	98.81 27	98.52 31

mPP-MVS		93.99 56	93.78 66	94.63 44	98.50 19	85.90 63	96.87 31	96.91 75	88.70 106	91.83 133	97.17 67	83.96 84	99.55 20	91.44 119	98.64 49	98.43 43

MSP-MVS		95.42 8	95.56 8	94.98 20	98.49 20	86.52 37	96.91 30	97.47 17	91.73 14	96.10 36	96.69 87	89.90 14	99.30 48	94.70 47	98.04 80	99.13 2
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
MP-MVS		94.25 42	94.07 56	94.77 39	98.47 21	86.31 45	96.71 36	96.98 64	89.04 90	91.98 123	97.19 65	85.43 60	99.56 16	92.06 103	98.79 28	98.44 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		94.45 34	94.20 51	95.19 14	98.46 22	87.50 17	95.00 154	97.12 55	87.13 171	92.51 112	96.30 104	89.24 19	99.34 42	93.46 63	98.62 50	98.73 23

PGM-MVS		93.96 58	93.72 70	94.68 42	98.43 23	86.22 48	95.30 129	97.78 4	87.45 161	93.26 84	97.33 56	84.62 77	99.51 28	90.75 131	98.57 53	98.32 54

MTAPA		94.42 39	94.22 48	95.00 19	98.42 24	86.95 22	94.36 208	96.97 65	91.07 22	93.14 88	97.56 43	84.30 80	99.56 16	93.43 64	98.75 34	98.47 38

GST-MVS		94.21 45	93.97 60	94.90 24	98.41 25	86.82 25	96.54 41	97.19 44	88.24 121	93.26 84	96.83 82	85.48 59	99.59 11	91.43 120	98.40 58	98.30 55

NormalMVS		93.46 72	93.16 84	94.37 56	98.40 26	86.20 49	96.30 47	96.27 135	91.65 17	92.68 105	96.13 118	77.97 182	98.84 105	90.75 131	98.26 63	98.07 82

lecture		95.10 14	95.46 10	94.01 65	98.40 26	84.36 106	97.70 3	97.78 4	91.19 20	96.22 34	98.08 19	86.64 43	99.37 37	94.91 45	98.26 63	98.29 60

ME-MVS		95.17 12	95.29 14	94.81 35	98.39 28	85.89 64	95.91 88	97.55 9	89.01 94	95.86 42	97.54 44	89.24 19	99.59 11	95.27 40	98.85 20	98.95 11

HPM-MVS		94.02 54	93.88 61	94.43 51	98.39 28	85.78 69	97.25 15	97.07 60	86.90 181	92.62 109	96.80 86	84.85 74	99.17 56	92.43 84	98.65 48	98.33 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		94.34 40	94.21 50	94.74 41	98.39 28	86.64 33	97.60 5	97.24 41	88.53 113	92.73 103	97.23 61	85.20 64	99.32 46	92.15 97	98.83 26	98.25 68

DPE-MVS		95.57 6	95.67 6	95.25 12	98.36 31	87.28 19	95.56 119	97.51 11	89.13 87	97.14 18	97.91 32	91.64 9	99.62 5	94.61 49	99.17 2	98.86 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HPM-MVS_fast		93.40 80	93.22 82	93.94 69	98.36 31	84.83 86	97.15 18	96.80 88	85.77 209	92.47 113	97.13 69	82.38 106	99.07 64	90.51 136	98.40 58	97.92 104

DP-MVS Recon		91.95 109	91.28 128	93.96 68	98.33 33	85.92 60	94.66 179	96.66 104	82.69 301	90.03 181	95.82 143	82.30 110	99.03 69	84.57 233	96.48 129	96.91 186

APDe-MVS		95.46 7	95.64 7	94.91 22	98.26 34	86.29 47	97.46 7	97.40 26	89.03 92	96.20 35	98.10 14	89.39 18	99.34 42	95.88 29	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TSAR-MVS + MP.		94.85 19	94.94 24	94.58 46	98.25 35	86.33 43	96.11 67	96.62 107	88.14 126	96.10 36	96.96 76	89.09 21	98.94 91	94.48 50	98.68 41	98.48 35
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
HPM-MVS++		95.14 13	94.91 26	95.83 4	98.25 35	89.65 4	95.92 87	96.96 68	91.75 13	94.02 71	96.83 82	88.12 27	99.55 20	93.41 66	98.94 16	98.28 61

CPTT-MVS		91.99 108	91.80 108	92.55 143	98.24 37	81.98 190	96.76 35	96.49 118	81.89 322	90.24 172	96.44 102	78.59 174	98.61 134	89.68 151	97.85 89	97.06 171

SR-MVS		94.23 44	94.17 54	94.43 51	98.21 38	85.78 69	96.40 43	96.90 76	88.20 124	94.33 61	97.40 53	84.75 76	99.03 69	93.35 67	97.99 82	98.48 35

MP-MVS-pluss		94.21 45	94.00 59	94.85 26	98.17 39	86.65 32	94.82 167	97.17 49	86.26 197	92.83 97	97.87 34	85.57 58	99.56 16	94.37 52	98.92 17	98.34 48
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ZD-MVS					98.15 40	86.62 34		97.07 60	83.63 273	94.19 64	96.91 78	87.57 34	99.26 50	91.99 105	98.44 57

SMA-MVS		95.20 10	95.07 20	95.59 6	98.14 41	88.48 8	96.26 54	97.28 40	85.90 205	97.67 4	98.10 14	88.41 23	99.56 16	94.66 48	99.19 1	98.71 25
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
CNVR-MVS		95.40 9	95.37 11	95.50 9	98.11 42	88.51 7	95.29 131	96.96 68	92.09 10	95.32 49	97.08 70	89.49 17	99.33 45	95.10 43	98.85 20	98.66 26

114514_t		89.51 190	88.50 206	92.54 144	98.11 42	81.99 189	95.16 146	96.36 127	70.19 459	85.81 270	95.25 172	76.70 199	98.63 131	82.07 276	96.86 118	97.00 178

ACMMP		93.24 84	92.88 90	94.30 59	98.09 44	85.33 78	96.86 32	97.45 20	88.33 117	90.15 179	97.03 74	81.44 128	99.51 28	90.85 130	95.74 143	98.04 89
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
APD-MVS		94.24 43	94.07 56	94.75 40	98.06 45	86.90 24	95.88 90	96.94 71	85.68 212	95.05 55	97.18 66	87.31 38	99.07 64	91.90 111	98.61 52	98.28 61
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CSCG		93.23 85	93.05 86	93.76 77	98.04 46	84.07 112	96.22 56	97.37 27	84.15 260	90.05 180	95.66 153	87.77 29	99.15 60	89.91 145	98.27 62	98.07 82

ACMMP_NAP		94.74 25	94.56 33	95.28 11	98.02 47	87.70 12	95.68 107	97.34 30	88.28 120	95.30 50	97.67 41	85.90 54	99.54 24	93.91 56	98.95 15	98.60 28

OPU-MVS				96.21 3	98.00 48	90.85 3	97.13 19				97.08 70	92.59 2	98.94 91	92.25 92	98.99 14	98.84 19

reproduce_model		94.76 24	94.92 25	94.29 60	97.92 49	85.18 80	95.95 85	97.19 44	89.67 67	95.27 51	98.16 6	86.53 47	99.36 40	95.42 37	98.15 73	98.33 50

SR-MVS-dyc-post		93.82 62	93.82 63	93.82 73	97.92 49	84.57 93	96.28 51	96.76 92	87.46 159	93.75 75	97.43 51	84.24 81	99.01 74	92.73 76	97.80 92	97.88 108

RE-MVS-def			93.68 72		97.92 49	84.57 93	96.28 51	96.76 92	87.46 159	93.75 75	97.43 51	82.94 99		92.73 76	97.80 92	97.88 108

APD-MVS_3200maxsize		93.78 63	93.77 67	93.80 75	97.92 49	84.19 110	96.30 47	96.87 79	86.96 177	93.92 73	97.47 49	83.88 85	98.96 88	92.71 79	97.87 88	98.26 67

reproduce-ours		94.82 20	94.97 22	94.38 54	97.91 53	85.46 74	95.86 91	97.15 51	89.82 57	95.23 52	98.10 14	87.09 40	99.37 37	95.30 38	98.25 67	98.30 55

our_new_method		94.82 20	94.97 22	94.38 54	97.91 53	85.46 74	95.86 91	97.15 51	89.82 57	95.23 52	98.10 14	87.09 40	99.37 37	95.30 38	98.25 67	98.30 55

save fliter					97.85 55	85.63 72	95.21 141	96.82 85	89.44 73

SF-MVS		94.97 17	94.90 28	95.20 13	97.84 56	87.76 11	96.65 39	97.48 16	87.76 150	95.71 44	97.70 40	88.28 26	99.35 41	93.89 57	98.78 30	98.48 35

NCCC		94.81 22	94.69 32	95.17 15	97.83 57	87.46 18	95.66 110	96.93 72	92.34 7	93.94 72	96.58 97	87.74 30	99.44 33	92.83 75	98.40 58	98.62 27

9.14			94.47 35		97.79 58		96.08 69	97.44 21	86.13 203	95.10 54	97.40 53	88.34 25	99.22 52	93.25 68	98.70 38

CDPH-MVS		92.83 94	92.30 101	94.44 49	97.79 58	86.11 52	94.06 230	96.66 104	80.09 354	92.77 100	96.63 94	86.62 44	99.04 68	87.40 188	98.66 45	98.17 73

DVP-MVS++		95.98 1	96.36 1	94.82 34	97.78 60	86.00 53	98.29 1	97.49 12	90.75 29	97.62 8	98.06 22	92.59 2	99.61 7	95.64 32	99.02 12	98.86 16

MSC_two_6792asdad				96.52 1	97.78 60	90.86 1		96.85 80					99.61 7	96.03 27	99.06 9	99.07 5

No_MVS				96.52 1	97.78 60	90.86 1		96.85 80					99.61 7	96.03 27	99.06 9	99.07 5

dcpmvs_2		93.49 70	94.19 52	91.38 218	97.69 63	76.78 362	94.25 213	96.29 131	88.33 117	94.46 59	96.88 79	88.07 28	98.64 129	93.62 62	98.09 77	98.73 23

DP-MVS		87.25 274	85.36 313	92.90 115	97.65 64	83.24 140	94.81 168	92.00 376	74.99 422	81.92 369	95.00 186	72.66 267	99.05 66	66.92 436	92.33 244	96.40 209

PAPM_NR		91.22 136	90.78 141	92.52 146	97.60 65	81.46 208	94.37 206	96.24 142	86.39 194	87.41 233	94.80 198	82.06 118	98.48 142	82.80 261	95.37 154	97.61 130

patch_mono-2		93.74 65	94.32 41	92.01 180	97.54 66	78.37 319	93.40 272	97.19 44	88.02 135	94.99 56	97.21 62	88.35 24	98.44 152	94.07 54	98.09 77	99.23 1

TEST9					97.53 67	86.49 38	94.07 228	96.78 89	81.61 332	92.77 100	96.20 108	87.71 31	99.12 62

train_agg		93.44 75	93.08 85	94.52 48	97.53 67	86.49 38	94.07 228	96.78 89	81.86 323	92.77 100	96.20 108	87.63 32	99.12 62	92.14 98	98.69 39	97.94 96

test_8					97.49 69	86.30 46	94.02 234	96.76 92	81.86 323	92.70 104	96.20 108	87.63 32	99.02 72

DeepC-MVS_fast	89.43 2	94.04 53	93.79 65	94.80 37	97.48 70	86.78 27	95.65 112	96.89 77	89.40 75	92.81 98	96.97 75	85.37 61	99.24 51	90.87 129	98.69 39	98.38 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
AdaColmap		89.89 180	89.07 187	92.37 156	97.41 71	83.03 154	94.42 195	95.92 180	82.81 298	86.34 259	94.65 207	73.89 249	99.02 72	80.69 303	95.51 147	95.05 267

agg_prior					97.38 72	85.92 60		96.72 99		92.16 119			98.97 86

原ACMM1				92.01 180	97.34 73	81.05 224		96.81 87	78.89 370	90.45 168	95.92 133	82.65 103	98.84 105	80.68 304	98.26 63	96.14 222

MSLP-MVS++		93.72 66	94.08 55	92.65 137	97.31 74	83.43 133	95.79 98	97.33 32	90.03 50	93.58 79	96.96 76	84.87 73	97.76 227	92.19 96	98.66 45	96.76 195

新几何1				93.10 102	97.30 75	84.35 107		95.56 215	71.09 455	91.26 148	96.24 106	82.87 101	98.86 101	79.19 334	98.10 76	96.07 228

test_prior				93.82 73	97.29 76	84.49 97		96.88 78					98.87 99			98.11 81

PLC	84.53 7	89.06 210	88.03 219	92.15 178	97.27 77	82.69 168	94.29 211	95.44 228	79.71 359	84.01 331	94.18 229	76.68 200	98.75 115	77.28 352	93.41 213	95.02 268
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
SD-MVS		94.96 18	95.33 12	93.88 70	97.25 78	86.69 29	96.19 57	97.11 58	90.42 37	96.95 24	97.27 58	89.53 16	96.91 312	94.38 51	98.85 20	98.03 90
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
test12				94.34 57	97.13 79	86.15 51		96.29 131		91.04 160		85.08 66	99.01 74		98.13 75	97.86 110

MG-MVS		91.77 117	91.70 110	92.00 183	97.08 80	80.03 270	93.60 265	95.18 246	87.85 146	90.89 162	96.47 101	82.06 118	98.36 159	85.07 221	97.04 110	97.62 129

SteuartSystems-ACMMP		95.20 10	95.32 13	94.85 26	96.99 81	86.33 43	97.33 8	97.30 37	91.38 19	95.39 48	97.46 50	88.98 22	99.40 34	94.12 53	98.89 18	98.82 21
Skip Steuart: Steuart Systems R&D Blog.
MVS_111021_HR		93.45 74	93.31 79	93.84 72	96.99 81	84.84 85	93.24 285	97.24 41	88.76 103	91.60 139	95.85 140	86.07 53	98.66 124	91.91 109	98.16 71	98.03 90

CNLPA		89.07 209	87.98 221	92.34 160	96.87 83	84.78 88	94.08 227	93.24 339	81.41 336	84.46 315	95.13 182	75.57 221	96.62 329	77.21 353	93.84 197	95.61 251

PHI-MVS		93.89 60	93.65 74	94.62 45	96.84 84	86.43 40	96.69 37	97.49 12	85.15 236	93.56 81	96.28 105	85.60 57	99.31 47	92.45 83	98.79 28	98.12 80

旧先验1					96.79 85	81.81 195		95.67 206			96.81 84	86.69 42			97.66 98	96.97 180

LFMVS		90.08 170	89.13 184	92.95 113	96.71 86	82.32 182	96.08 69	89.91 432	86.79 182	92.15 120	96.81 84	62.60 385	98.34 162	87.18 192	93.90 194	98.19 71

SPE-MVS-test		94.02 54	94.29 44	93.24 92	96.69 87	83.24 140	97.49 6	96.92 73	92.14 9	92.90 93	95.77 148	85.02 68	98.33 164	93.03 72	98.62 50	98.13 77

Anonymous202405211		87.68 249	86.13 282	92.31 163	96.66 88	80.74 241	94.87 162	91.49 393	80.47 350	89.46 192	95.44 162	54.72 443	98.23 170	82.19 272	89.89 278	97.97 94

TAPA-MVS	84.62 6	88.16 237	87.01 247	91.62 207	96.64 89	80.65 242	94.39 202	96.21 147	76.38 406	86.19 263	95.44 162	79.75 154	98.08 189	62.75 454	95.29 156	96.13 223
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MAR-MVS		90.30 163	89.37 178	93.07 106	96.61 90	84.48 98	95.68 107	95.67 206	82.36 306	87.85 223	92.85 276	76.63 201	98.80 110	80.01 314	96.68 123	95.91 234
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
VNet		92.24 105	91.91 107	93.24 92	96.59 91	83.43 133	94.84 166	96.44 119	89.19 85	94.08 70	95.90 134	77.85 188	98.17 174	88.90 165	93.38 214	98.13 77

TSAR-MVS + GP.		93.66 67	93.41 78	94.41 53	96.59 91	86.78 27	94.40 200	93.93 315	89.77 64	94.21 63	95.59 156	87.35 37	98.61 134	92.72 78	96.15 136	97.83 115

MVSMamba_PlusPlus		93.44 75	93.54 76	93.14 100	96.58 93	83.05 153	96.06 73	96.50 117	84.42 257	94.09 67	95.56 158	85.01 71	98.69 123	94.96 44	98.66 45	97.67 127

CS-MVS		94.12 51	94.44 37	93.17 98	96.55 94	83.08 152	97.63 4	96.95 70	91.71 15	93.50 83	96.21 107	85.61 56	98.24 169	93.64 61	98.17 70	98.19 71

test222					96.55 94	81.70 200	92.22 330	95.01 254	68.36 463	90.20 174	96.14 117	80.26 143			97.80 92	96.05 231

Anonymous20240529		88.09 239	86.59 264	92.58 141	96.53 96	81.92 193	95.99 79	95.84 190	74.11 432	89.06 199	95.21 176	61.44 395	98.81 109	83.67 249	87.47 319	97.01 177

Anonymous20231211		86.59 304	85.13 319	90.98 241	96.52 97	81.50 204	96.14 64	96.16 157	73.78 435	83.65 340	92.15 301	63.26 381	97.37 276	82.82 260	81.74 384	94.06 316

DeepPCF-MVS	89.96 1	94.20 47	94.77 31	92.49 148	96.52 97	80.00 272	94.00 237	97.08 59	90.05 49	95.65 46	97.29 57	89.66 15	98.97 86	93.95 55	98.71 36	98.50 32

fmvsm_s_conf0.5_n_9		94.99 16	95.50 9	93.44 85	96.51 99	82.25 183	95.76 102	96.92 73	93.37 3	97.63 7	98.43 1	84.82 75	99.16 59	98.15 1	97.92 85	98.90 14

testdata				90.49 263	96.40 100	77.89 334		95.37 234	72.51 447	93.63 78	96.69 87	82.08 117	97.65 236	83.08 253	97.39 102	95.94 233

PVSNet_Blended_VisFu		91.38 132	90.91 137	92.80 121	96.39 101	83.17 144	94.87 162	96.66 104	83.29 284	89.27 195	94.46 218	80.29 141	99.17 56	87.57 185	95.37 154	96.05 231

API-MVS		90.66 154	90.07 156	92.45 151	96.36 102	84.57 93	96.06 73	95.22 245	82.39 304	89.13 196	94.27 226	80.32 140	98.46 146	80.16 312	96.71 122	94.33 304

F-COLMAP		87.95 242	86.80 253	91.40 217	96.35 103	80.88 233	94.73 174	95.45 226	79.65 360	82.04 367	94.61 208	71.13 285	98.50 140	76.24 365	91.05 259	94.80 282

VDD-MVS		90.74 148	89.92 162	93.20 94	96.27 104	83.02 155	95.73 104	93.86 319	88.42 116	92.53 110	96.84 81	62.09 387	98.64 129	90.95 127	92.62 239	97.93 103

OMC-MVS		91.23 135	90.62 145	93.08 104	96.27 104	84.07 112	93.52 267	95.93 179	86.95 178	89.51 189	96.13 118	78.50 176	98.35 161	85.84 213	92.90 228	96.83 194

DPM-MVS		92.58 99	91.74 109	95.08 16	96.19 106	89.31 5	92.66 311	96.56 112	83.44 279	91.68 138	95.04 184	86.60 46	98.99 81	85.60 215	97.92 85	96.93 184

SymmetryMVS		92.81 96	92.31 100	94.32 58	96.15 107	86.20 49	96.30 47	94.43 293	91.65 17	92.68 105	96.13 118	77.97 182	98.84 105	90.75 131	94.72 167	97.92 104

CHOSEN 1792x2688		88.84 216	87.69 229	92.30 166	96.14 108	81.42 210	90.01 397	95.86 189	74.52 427	87.41 233	93.94 239	75.46 222	98.36 159	80.36 308	95.53 146	97.12 167

balanced_conf03		93.98 57	94.22 48	93.26 91	96.13 109	83.29 139	96.27 53	96.52 115	89.82 57	95.56 47	95.51 159	84.50 78	98.79 112	94.83 46	98.86 19	97.72 124

thres100view900		87.63 254	86.71 256	90.38 271	96.12 110	78.55 312	95.03 153	91.58 389	87.15 169	88.06 219	92.29 297	68.91 326	98.10 179	70.13 414	91.10 254	94.48 299

PVSNet_BlendedMVS		89.98 174	89.70 167	90.82 247	96.12 110	81.25 214	93.92 243	96.83 83	83.49 278	89.10 197	92.26 298	81.04 134	98.85 103	86.72 200	87.86 314	92.35 400

PVSNet_Blended		90.73 149	90.32 148	91.98 184	96.12 110	81.25 214	92.55 315	96.83 83	82.04 315	89.10 197	92.56 288	81.04 134	98.85 103	86.72 200	95.91 139	95.84 239

testing3-2		86.72 299	86.71 256	86.74 400	96.11 113	65.92 461	93.39 273	89.65 439	89.46 72	87.84 224	92.79 282	59.17 417	97.60 241	81.31 291	90.72 263	96.70 199

UA-Net		92.83 94	92.54 97	93.68 81	96.10 114	84.71 89	95.66 110	96.39 124	91.92 11	93.22 86	96.49 100	83.16 94	98.87 99	84.47 235	95.47 150	97.45 140

MM		95.10 14	94.91 26	95.68 5	96.09 115	88.34 9	96.68 38	94.37 297	95.08 1	94.68 57	97.72 39	82.94 99	99.64 4	97.85 5	98.76 33	99.06 7

thres600view7		87.65 251	86.67 259	90.59 251	96.08 116	78.72 306	94.88 161	91.58 389	87.06 173	88.08 218	92.30 296	68.91 326	98.10 179	70.05 417	91.10 254	94.96 272

DeepC-MVS	88.79 3	93.31 81	92.99 88	94.26 61	96.07 117	85.83 67	94.89 160	96.99 63	89.02 93	89.56 188	97.37 55	82.51 105	99.38 35	92.20 95	98.30 61	97.57 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		87.89 243	86.32 275	92.59 140	96.07 117	82.92 159	95.23 136	94.92 267	75.66 414	82.89 355	95.98 128	72.48 271	99.21 54	68.43 424	95.23 159	95.64 248

fmvsm_s_conf0.5_n_11		94.60 28	95.23 16	92.69 134	96.05 119	82.00 188	96.31 46	96.71 100	92.27 8	96.68 30	98.39 2	85.32 62	98.92 94	97.20 14	98.16 71	97.17 158

h-mvs33		90.80 146	90.15 153	92.75 128	96.01 120	82.66 169	95.43 123	95.53 219	89.80 60	93.08 89	95.64 154	75.77 214	99.00 79	92.07 100	78.05 422	96.60 202

SDMVSNet		90.19 166	89.61 171	91.93 189	96.00 121	83.09 151	92.89 302	95.98 173	88.73 104	86.85 246	95.20 177	72.09 278	97.08 298	88.90 165	89.85 280	95.63 249

sd_testset		88.59 225	87.85 227	90.83 245	96.00 121	80.42 254	92.35 323	94.71 281	88.73 104	86.85 246	95.20 177	67.31 336	96.43 352	79.64 321	89.85 280	95.63 249

HyFIR lowres test		88.09 239	86.81 252	91.93 189	96.00 121	80.63 243	90.01 397	95.79 193	73.42 439	87.68 229	92.10 306	73.86 250	97.96 213	80.75 302	91.70 248	97.19 157

tfpn200view9		87.58 259	86.64 260	90.41 268	95.99 124	78.64 309	94.58 182	91.98 378	86.94 179	88.09 216	91.77 318	69.18 322	98.10 179	70.13 414	91.10 254	94.48 299

thres400		87.62 256	86.64 260	90.57 252	95.99 124	78.64 309	94.58 182	91.98 378	86.94 179	88.09 216	91.77 318	69.18 322	98.10 179	70.13 414	91.10 254	94.96 272

MVS_111021_LR		92.47 102	92.29 102	92.98 110	95.99 124	84.43 102	93.08 291	96.09 165	88.20 124	91.12 153	95.72 151	81.33 130	97.76 227	91.74 113	97.37 103	96.75 196

fmvsm_s_conf0.5_n_8		94.56 30	95.12 18	92.87 117	95.96 127	81.32 212	95.76 102	97.57 8	93.48 2	97.53 10	98.32 3	81.78 125	99.13 61	97.91 2	97.81 91	98.16 74

fmvsm_l_conf0.5_n_9		94.65 27	95.28 15	92.77 123	95.95 128	81.83 194	95.53 120	97.12 55	91.68 16	97.89 1	98.06 22	85.71 55	98.65 126	97.32 12	98.26 63	97.83 115

PatchMatch-RL		86.77 298	85.54 307	90.47 267	95.88 129	82.71 167	90.54 379	92.31 366	79.82 358	84.32 323	91.57 330	68.77 328	96.39 354	73.16 393	93.48 212	92.32 401

EPP-MVSNet		91.70 126	91.56 116	92.13 179	95.88 129	80.50 252	97.33 8	95.25 242	86.15 200	89.76 186	95.60 155	83.42 90	98.32 166	87.37 190	93.25 218	97.56 135

IS-MVSNet		91.43 131	91.09 133	92.46 149	95.87 131	81.38 211	96.95 24	93.69 332	89.72 66	89.50 191	95.98 128	78.57 175	97.77 226	83.02 255	96.50 128	98.22 70

test_fmvsm_n_1920		94.71 26	95.11 19	93.50 84	95.79 132	84.62 91	96.15 62	97.64 6	89.85 56	97.19 17	97.89 33	86.28 50	98.71 121	97.11 16	98.08 79	97.17 158

PAPR		90.02 173	89.27 183	92.29 168	95.78 133	80.95 229	92.68 310	96.22 144	81.91 319	86.66 250	93.75 251	82.23 112	98.44 152	79.40 333	94.79 166	97.48 138

Vis-MVSNet (Re-imp)		89.59 188	89.44 175	90.03 286	95.74 134	75.85 376	95.61 115	90.80 412	87.66 155	87.83 225	95.40 165	76.79 197	96.46 350	78.37 339	96.73 121	97.80 118

fmvsm_s_conf0.5_n_10		94.43 36	94.84 29	93.20 94	95.73 135	83.19 143	95.99 79	97.31 36	91.08 21	97.67 4	98.11 11	81.87 122	99.22 52	97.86 4	97.91 87	97.20 156

test_yl		90.69 151	90.02 160	92.71 131	95.72 136	82.41 179	94.11 222	95.12 248	85.63 213	91.49 142	94.70 200	74.75 229	98.42 155	86.13 208	92.53 241	97.31 144

DCV-MVSNet		90.69 151	90.02 160	92.71 131	95.72 136	82.41 179	94.11 222	95.12 248	85.63 213	91.49 142	94.70 200	74.75 229	98.42 155	86.13 208	92.53 241	97.31 144

sasdasda		93.27 82	92.75 92	94.85 26	95.70 138	87.66 13	96.33 44	96.41 122	90.00 51	94.09 67	94.60 209	82.33 108	98.62 132	92.40 86	92.86 229	98.27 63

canonicalmvs		93.27 82	92.75 92	94.85 26	95.70 138	87.66 13	96.33 44	96.41 122	90.00 51	94.09 67	94.60 209	82.33 108	98.62 132	92.40 86	92.86 229	98.27 63

CANet		93.54 69	93.20 83	94.55 47	95.65 140	85.73 71	94.94 157	96.69 103	91.89 12	90.69 164	95.88 136	81.99 120	99.54 24	93.14 70	97.95 84	98.39 45

fmvsm_l_conf0.5_n_3		94.80 23	95.01 21	94.15 63	95.64 141	85.08 81	96.09 68	97.36 28	90.98 24	97.09 20	98.12 10	84.98 72	98.94 91	97.07 17	97.80 92	98.43 43

3Dnovator+	87.14 4	92.42 103	91.37 125	95.55 7	95.63 142	88.73 6	97.07 23	96.77 91	90.84 26	84.02 330	96.62 95	75.95 212	99.34 42	87.77 181	97.68 97	98.59 29

MGCFI-Net		93.03 91	92.63 95	94.23 62	95.62 143	85.92 60	96.08 69	96.33 129	89.86 55	93.89 74	94.66 206	82.11 115	98.50 140	92.33 91	92.82 232	98.27 63

fmvsm_s_conf0.5_n		93.76 64	94.06 58	92.86 118	95.62 143	83.17 144	96.14 64	96.12 162	88.13 127	95.82 43	98.04 28	83.43 88	98.48 142	96.97 21	96.23 133	96.92 185

test2506		87.21 278	86.28 277	90.02 288	95.62 143	73.64 401	96.25 55	71.38 491	87.89 144	90.45 168	96.65 91	55.29 438	98.09 187	86.03 210	96.94 112	98.33 50

ECVR-MVS		89.09 208	88.53 204	90.77 249	95.62 143	75.89 375	96.16 60	84.22 468	87.89 144	90.20 174	96.65 91	63.19 382	98.10 179	85.90 211	96.94 112	98.33 50

alignmvs		93.08 90	92.50 98	94.81 35	95.62 143	87.61 16	95.99 79	96.07 167	89.77 64	94.12 66	94.87 193	80.56 138	98.66 124	92.42 85	93.10 225	98.15 75

test1111		89.10 206	88.64 201	90.48 264	95.53 148	74.97 385	96.08 69	84.89 466	88.13 127	90.16 178	96.65 91	63.29 380	98.10 179	86.14 206	96.90 115	98.39 45

fmvsm_s_conf0.5_n_3		94.49 32	95.13 17	92.56 142	95.49 149	81.10 222	95.93 86	97.16 50	92.96 4	97.39 12	98.13 7	83.63 87	98.80 110	97.89 3	97.61 99	97.78 120

WTY-MVS		89.60 187	88.92 194	91.67 206	95.47 150	81.15 219	92.38 320	94.78 278	83.11 288	89.06 199	94.32 221	78.67 173	96.61 332	81.57 288	90.89 261	97.24 152

DELS-MVS		93.43 79	93.25 81	93.97 67	95.42 151	85.04 82	93.06 294	97.13 54	90.74 31	91.84 131	95.09 183	86.32 49	99.21 54	91.22 121	98.45 56	97.65 128
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
balanced_ft_v1		92.23 106	92.05 105	92.77 123	95.40 152	81.78 198	95.80 96	95.69 205	87.94 139	91.92 128	95.04 184	75.91 213	98.71 121	93.83 58	96.94 112	97.82 117

fmvsm_s_conf0.5_n_2		93.47 71	93.83 62	92.39 155	95.36 153	81.19 218	95.20 143	96.56 112	90.37 39	97.13 19	98.03 29	77.47 191	98.96 88	97.79 6	96.58 125	97.03 174

thres200		87.21 278	86.24 279	90.12 280	95.36 153	78.53 313	93.26 283	92.10 372	86.42 193	88.00 221	91.11 343	69.24 321	98.00 205	69.58 418	91.04 260	93.83 330

Vis-MVSNet		91.75 119	91.23 129	93.29 89	95.32 155	83.78 122	96.14 64	95.98 173	89.89 53	90.45 168	96.58 97	75.09 225	98.31 167	84.75 227	96.90 115	97.78 120
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_l_conf0.5_n_a		94.20 47	94.40 38	93.60 82	95.29 156	84.98 83	95.61 115	96.28 134	86.31 195	96.75 28	97.86 35	87.40 36	98.74 118	97.07 17	97.02 111	97.07 170

fmvsm_l_conf0.5_n		94.29 41	94.46 36	93.79 76	95.28 157	85.43 76	95.68 107	96.43 120	86.56 189	96.84 26	97.81 37	87.56 35	98.77 114	97.14 15	96.82 119	97.16 165

BH-RMVSNet		88.37 231	87.48 234	91.02 236	95.28 157	79.45 288	92.89 302	93.07 345	85.45 223	86.91 242	94.84 197	70.35 300	97.76 227	73.97 387	94.59 174	95.85 238

COLMAP_ROB	80.39 16	83.96 358	82.04 367	89.74 302	95.28 157	79.75 281	94.25 213	92.28 367	75.17 420	78.02 421	93.77 249	58.60 421	97.84 223	65.06 445	85.92 332	91.63 413
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
PS-MVSNAJ		91.18 138	90.92 136	91.96 186	95.26 160	82.60 175	92.09 335	95.70 203	86.27 196	91.84 131	92.46 290	79.70 156	98.99 81	89.08 160	95.86 140	94.29 305

BH-untuned		88.60 224	88.13 218	90.01 289	95.24 161	78.50 315	93.29 281	94.15 308	84.75 249	84.46 315	93.40 257	75.76 216	97.40 272	77.59 349	94.52 177	94.12 311

EC-MVSNet		93.44 75	93.71 71	92.63 138	95.21 162	82.43 176	97.27 14	96.71 100	90.57 36	92.88 94	95.80 144	83.16 94	98.16 175	93.68 59	98.14 74	97.31 144

ETV-MVS		92.74 97	92.66 94	92.97 111	95.20 163	84.04 116	95.07 150	96.51 116	90.73 32	92.96 92	91.19 337	84.06 82	98.34 162	91.72 114	96.54 126	96.54 207

mvsmamba		90.33 162	89.69 168	92.25 173	95.17 164	81.64 201	95.27 134	93.36 337	84.88 243	89.51 189	94.27 226	69.29 320	97.42 264	89.34 156	96.12 137	97.68 126

GeoE		90.05 171	89.43 176	91.90 194	95.16 165	80.37 255	95.80 96	94.65 284	83.90 265	87.55 232	94.75 199	78.18 181	97.62 240	81.28 292	93.63 204	97.71 125

EIA-MVS		91.95 109	91.94 106	91.98 184	95.16 165	80.01 271	95.36 124	96.73 97	88.44 114	89.34 193	92.16 300	83.82 86	98.45 150	89.35 155	97.06 109	97.48 138

ab-mvs		89.41 197	88.35 210	92.60 139	95.15 167	82.65 173	92.20 331	95.60 213	83.97 264	88.55 209	93.70 253	74.16 244	98.21 173	82.46 266	89.37 288	96.94 183

fmvsm_s_conf0.5_n_4		93.86 61	94.37 40	92.33 161	95.13 168	80.95 229	95.64 113	96.97 65	89.60 69	96.85 25	97.77 38	83.08 97	98.92 94	97.49 8	96.78 120	97.13 166

VDDNet		89.56 189	88.49 208	92.76 126	95.07 169	82.09 186	96.30 47	93.19 342	81.05 345	91.88 129	96.86 80	61.16 403	98.33 164	88.43 172	92.49 243	97.84 114

fmvsm_s_conf0.5_n_a		93.57 68	93.76 68	93.00 109	95.02 170	83.67 125	96.19 57	96.10 164	87.27 165	95.98 40	98.05 25	83.07 98	98.45 150	96.68 23	95.51 147	96.88 188

AllTest		83.42 365	81.39 371	89.52 319	95.01 171	77.79 339	93.12 287	90.89 410	77.41 391	76.12 435	93.34 258	54.08 446	97.51 249	68.31 425	84.27 349	93.26 356

TestCases				89.52 319	95.01 171	77.79 339		90.89 410	77.41 391	76.12 435	93.34 258	54.08 446	97.51 249	68.31 425	84.27 349	93.26 356

EI-MVSNet-Vis-set		93.01 92	92.92 89	93.29 89	95.01 171	83.51 132	94.48 188	95.77 194	90.87 25	92.52 111	96.67 89	84.50 78	99.00 79	91.99 105	94.44 180	97.36 143

SSM_0404		90.73 149	90.08 155	92.69 134	95.00 174	83.13 146	94.32 209	95.00 258	85.41 224	89.84 182	95.35 167	76.13 204	97.98 209	85.46 218	94.18 189	96.95 181

fmvsm_s_conf0.5_n_6		94.11 52	94.56 33	92.76 126	94.98 175	81.96 192	95.79 98	97.29 39	89.31 79	97.52 11	97.61 42	83.25 93	98.88 98	97.05 19	98.22 69	97.43 142

xiu_mvs_v2_base		91.13 140	90.89 138	91.86 195	94.97 176	82.42 177	92.24 328	95.64 211	86.11 204	91.74 137	93.14 269	79.67 161	98.89 97	89.06 161	95.46 151	94.28 306

tttt0517		88.61 223	87.78 228	91.11 231	94.96 177	77.81 337	95.35 125	89.69 436	85.09 238	88.05 220	94.59 211	66.93 342	98.48 142	83.27 252	92.13 246	97.03 174

baseline1		88.10 238	87.28 240	90.57 252	94.96 177	80.07 266	94.27 212	91.29 398	86.74 184	87.41 233	94.00 236	76.77 198	96.20 363	80.77 301	79.31 418	95.44 253

Test_1112_low_res		87.65 251	86.51 268	91.08 232	94.94 179	79.28 299	91.77 343	94.30 300	76.04 412	83.51 344	92.37 293	77.86 187	97.73 232	78.69 338	89.13 294	96.22 217

1112_ss		88.42 228	87.33 238	91.72 204	94.92 180	80.98 227	92.97 299	94.54 288	78.16 387	83.82 334	93.88 244	78.78 171	97.91 219	79.45 329	89.41 287	96.26 216

QAPM		89.51 190	88.15 217	93.59 83	94.92 180	84.58 92	96.82 34	96.70 102	78.43 381	83.41 348	96.19 111	73.18 262	99.30 48	77.11 355	96.54 126	96.89 187

MGCNet		94.18 50	93.80 64	95.34 10	94.91 182	87.62 15	95.97 82	93.01 347	92.58 6	94.22 62	97.20 64	80.56 138	99.59 11	97.04 20	98.68 41	98.81 22

BH-w/o		87.57 260	87.05 245	89.12 329	94.90 183	77.90 333	92.41 318	93.51 334	82.89 297	83.70 338	91.34 331	75.75 217	97.07 300	75.49 370	93.49 210	92.39 398

thisisatest0530		88.67 221	87.61 231	91.86 195	94.87 184	80.07 266	94.63 180	89.90 433	84.00 263	88.46 211	93.78 248	66.88 344	98.46 146	83.30 251	92.65 234	97.06 171

EI-MVSNet-UG-set		92.74 97	92.62 96	93.12 101	94.86 185	83.20 142	94.40 200	95.74 197	90.71 33	92.05 121	96.60 96	84.00 83	98.99 81	91.55 117	93.63 204	97.17 158

HY-MVS	83.01 12	89.03 212	87.94 223	92.29 168	94.86 185	82.77 161	92.08 336	94.49 291	81.52 335	86.93 240	92.79 282	78.32 180	98.23 170	79.93 315	90.55 265	95.88 237

hse-mvs2		89.88 181	89.34 179	91.51 211	94.83 187	81.12 221	93.94 241	93.91 318	89.80 60	93.08 89	93.60 254	75.77 214	97.66 235	92.07 100	77.07 429	95.74 244

AUN-MVS		87.78 247	86.54 267	91.48 213	94.82 188	81.05 224	93.91 245	93.93 315	83.00 293	86.93 240	93.53 255	69.50 314	97.67 233	86.14 206	77.12 428	95.73 246

fmvsm_s_conf0.5_n_5		93.96 58	94.18 53	93.30 88	94.79 189	83.81 121	95.77 100	96.74 96	88.02 135	96.23 33	97.84 36	83.36 92	98.83 108	97.49 8	97.34 105	97.25 151

mamba_0408		89.06 210	87.92 224	92.50 147	94.76 190	82.66 169	79.84 480	94.64 285	85.18 229	88.96 201	95.00 186	76.00 209	97.98 209	83.74 246	93.15 222	96.85 190

SSM_04072		88.57 227	87.92 224	90.51 261	94.76 190	82.66 169	79.84 480	94.64 285	85.18 229	88.96 201	95.00 186	76.00 209	92.03 449	83.74 246	93.15 222	96.85 190

SSM_0407		90.47 161	89.80 165	92.46 149	94.76 190	82.66 169	93.98 239	95.00 258	85.41 224	88.96 201	95.35 167	76.13 204	97.88 222	85.46 218	93.15 222	96.85 190

Fast-Effi-MVS+		89.41 197	88.64 201	91.71 205	94.74 193	80.81 238	93.54 266	95.10 250	83.11 288	86.82 248	90.67 360	79.74 155	97.75 231	80.51 307	93.55 206	96.57 205

myMVS_eth3d28		85.80 323	85.26 317	87.42 378	94.73 194	69.92 446	90.60 377	90.95 407	87.21 168	86.06 266	90.04 379	59.47 412	96.02 370	74.89 379	93.35 217	96.33 211

ACMP	84.23 8	89.01 214	88.35 210	90.99 239	94.73 194	81.27 213	95.07 150	95.89 185	86.48 190	83.67 339	94.30 222	69.33 316	97.99 206	87.10 197	88.55 299	93.72 341
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
KinetiMVS		91.82 111	91.30 126	93.39 86	94.72 196	83.36 137	95.45 122	96.37 126	90.33 40	92.17 118	96.03 125	72.32 274	98.75 115	87.94 178	96.34 131	98.07 82

PVSNet	78.82 18	85.55 326	84.65 330	88.23 357	94.72 196	71.93 422	87.12 444	92.75 355	78.80 374	84.95 303	90.53 362	64.43 370	96.71 320	74.74 380	93.86 195	96.06 230

LCM-MVSNet-Re		88.30 234	88.32 213	88.27 354	94.71 198	72.41 421	93.15 286	90.98 405	87.77 149	79.25 407	91.96 313	78.35 179	95.75 386	83.04 254	95.62 145	96.65 201

HQP_MVS		90.60 158	90.19 151	91.82 199	94.70 199	82.73 165	95.85 93	96.22 144	90.81 27	86.91 242	94.86 194	74.23 240	98.12 177	88.15 173	89.99 274	94.63 285

plane_prior7					94.70 199	82.74 164

E3new		91.76 118	91.58 114	92.28 172	94.69 201	80.90 232	93.68 263	96.17 155	87.15 169	91.09 159	95.70 152	81.75 126	98.05 196	89.67 152	94.35 182	97.90 107

ACMH+	81.04 14	85.05 339	83.46 351	89.82 297	94.66 202	79.37 292	94.44 193	94.12 311	82.19 310	78.04 420	92.82 279	58.23 422	97.54 246	73.77 390	82.90 369	92.54 390

ACMM	84.12 9	89.14 205	88.48 209	91.12 228	94.65 203	81.22 216	95.31 127	96.12 162	85.31 228	85.92 268	94.34 219	70.19 303	98.06 192	85.65 214	88.86 297	94.08 315
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
viewcassd2359sk11		91.79 112	91.62 111	92.29 168	94.62 204	80.88 233	93.70 260	96.18 154	87.38 163	91.13 152	95.85 140	81.62 127	98.06 192	89.71 149	94.40 181	97.94 96

fmvsm_s_conf0.1_n_2		93.16 88	93.42 77	92.37 156	94.62 204	81.13 220	95.23 136	95.89 185	90.30 43	96.74 29	98.02 30	76.14 203	98.95 90	97.64 7	96.21 134	97.03 174

test_fmvsmconf_n		94.60 28	94.81 30	93.98 66	94.62 204	84.96 84	96.15 62	97.35 29	89.37 76	96.03 39	98.11 11	86.36 48	99.01 74	97.45 10	97.83 90	97.96 95

viewdifsd2359ckpt09		91.18 138	90.65 144	92.75 128	94.61 207	82.36 181	94.32 209	95.74 197	84.72 250	89.66 187	95.15 181	79.69 159	98.04 197	87.70 182	94.27 187	97.85 113

guyue		91.12 141	90.84 139	91.96 186	94.59 208	80.57 250	94.87 162	93.71 331	88.96 97	91.14 151	95.22 173	73.22 261	97.76 227	92.01 104	93.81 198	97.54 137

plane_prior1					94.59 208

casdiffmvs_mvg		92.96 93	92.83 91	93.35 87	94.59 208	83.40 135	95.00 154	96.34 128	90.30 43	92.05 121	96.05 122	83.43 88	98.15 176	92.07 100	95.67 144	98.49 34
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
3Dnovator	86.66 5	91.73 121	90.82 140	94.44 49	94.59 208	86.37 42	97.18 17	97.02 62	89.20 84	84.31 325	96.66 90	73.74 253	99.17 56	86.74 198	97.96 83	97.79 119

FA-MVS(test-final)		89.66 185	88.91 195	91.93 189	94.57 212	80.27 256	91.36 355	94.74 280	84.87 244	89.82 183	92.61 287	74.72 232	98.47 145	83.97 241	93.53 208	97.04 173

FE-MVS		87.40 267	86.02 288	91.57 209	94.56 213	79.69 283	90.27 384	93.72 330	80.57 348	88.80 205	91.62 326	65.32 360	98.59 136	74.97 378	94.33 184	96.44 208

GDP-MVS		92.04 107	91.46 122	93.75 78	94.55 214	84.69 90	95.60 118	96.56 112	87.83 147	93.07 91	95.89 135	73.44 257	98.65 126	90.22 139	96.03 138	97.91 106

plane_prior6					94.52 215	82.75 162						74.23 240

UGNet		89.95 177	88.95 193	92.95 113	94.51 216	83.31 138	95.70 106	95.23 243	89.37 76	87.58 230	93.94 239	64.00 375	98.78 113	83.92 242	96.31 132	96.74 197
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
BP-MVS1		92.48 101	92.07 104	93.72 79	94.50 217	84.39 105	95.90 89	94.30 300	90.39 38	92.67 107	95.94 131	74.46 236	98.65 126	93.14 70	97.35 104	98.13 77

E2		91.79 112	91.61 112	92.31 163	94.49 218	80.86 235	93.74 255	96.19 148	87.63 156	91.16 149	95.94 131	81.31 131	98.06 192	89.76 147	94.29 185	97.99 92

E3		91.78 115	91.61 112	92.30 166	94.48 219	80.86 235	93.73 256	96.19 148	87.63 156	91.16 149	95.95 130	81.30 132	98.06 192	89.76 147	94.29 185	97.99 92

LPG-MVS_test		89.45 193	88.90 196	91.12 228	94.47 220	81.49 206	95.30 129	96.14 158	86.73 185	85.45 285	95.16 179	69.89 307	98.10 179	87.70 182	89.23 292	93.77 336

LGP-MVS_train				91.12 228	94.47 220	81.49 206		96.14 158	86.73 185	85.45 285	95.16 179	69.89 307	98.10 179	87.70 182	89.23 292	93.77 336

baseline		92.39 104	92.29 102	92.69 134	94.46 222	81.77 199	94.14 219	96.27 135	89.22 83	91.88 129	96.00 126	82.35 107	97.99 206	91.05 123	95.27 158	98.30 55

ACMH	80.38 17	85.36 331	83.68 348	90.39 269	94.45 223	80.63 243	94.73 174	94.85 272	82.09 311	77.24 426	92.65 285	60.01 409	97.58 243	72.25 398	84.87 344	92.96 373
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
LTVRE_ROB	82.13 13	86.26 315	84.90 325	90.34 273	94.44 224	81.50 204	92.31 327	94.89 268	83.03 292	79.63 401	92.67 284	69.69 310	97.79 225	71.20 403	86.26 331	91.72 411
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
testing91		87.11 283	86.18 280	89.92 292	94.43 225	75.38 384	91.53 350	92.27 368	86.48 190	86.50 251	90.24 370	61.19 401	97.53 247	82.10 274	90.88 262	96.84 193

fmvsm_s_conf0.5_n_7		93.15 89	93.76 68	91.31 221	94.42 226	79.48 286	94.52 186	97.14 53	89.33 78	94.17 65	98.09 18	81.83 123	97.49 253	96.33 26	98.02 81	96.95 181

casdiffmvs		92.51 100	92.43 99	92.74 130	94.41 227	81.98 190	94.54 185	96.23 143	89.57 70	91.96 125	96.17 112	82.58 104	98.01 204	90.95 127	95.45 152	98.23 69
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETVMVS		84.43 352	82.92 361	88.97 335	94.37 228	74.67 388	91.23 362	88.35 448	83.37 282	86.06 266	89.04 398	55.38 436	95.67 390	67.12 432	91.34 252	96.58 204

MVS_Test		91.31 134	91.11 131	91.93 189	94.37 228	80.14 261	93.46 270	95.80 192	86.46 192	91.35 147	93.77 249	82.21 113	98.09 187	87.57 185	94.95 162	97.55 136

NP-MVS					94.37 228	82.42 177					93.98 237

TR-MVS		86.78 295	85.76 301	89.82 297	94.37 228	78.41 317	92.47 317	92.83 351	81.11 344	86.36 257	92.40 292	68.73 329	97.48 254	73.75 391	89.85 280	93.57 345

Effi-MVS+		91.59 129	91.11 131	93.01 108	94.35 232	83.39 136	94.60 181	95.10 250	87.10 172	90.57 167	93.10 271	81.43 129	98.07 191	89.29 157	94.48 178	97.59 133

E5new		91.71 122	91.55 117	92.20 174	94.33 233	80.62 245	94.41 196	96.19 148	88.06 131	91.11 154	96.16 113	79.92 147	98.03 200	90.00 140	93.80 199	97.94 96

E5		91.71 122	91.55 117	92.20 174	94.33 233	80.62 245	94.41 196	96.19 148	88.06 131	91.11 154	96.16 113	79.92 147	98.03 200	90.00 140	93.80 199	97.94 96

E6new		91.71 122	91.55 117	92.20 174	94.32 235	80.62 245	94.41 196	96.19 148	88.06 131	91.11 154	96.16 113	79.92 147	98.03 200	90.00 140	93.80 199	97.94 96

E6		91.71 122	91.55 117	92.20 174	94.32 235	80.62 245	94.41 196	96.19 148	88.06 131	91.11 154	96.16 113	79.92 147	98.03 200	90.00 140	93.80 199	97.94 96

viewmanbaseed2359cas		91.78 115	91.58 114	92.37 156	94.32 235	81.07 223	93.76 253	95.96 177	87.26 166	91.50 141	95.88 136	80.92 136	97.97 211	89.70 150	94.92 163	98.07 82

viewdifsd2359ckpt13		91.20 137	90.75 142	92.54 144	94.30 238	82.13 185	94.03 232	95.89 185	85.60 215	90.20 174	95.36 166	79.69 159	97.90 221	87.85 180	93.86 195	97.61 130

testing11		86.44 311	85.35 314	89.69 307	94.29 239	75.40 383	91.30 357	90.53 417	84.76 248	85.06 300	90.13 376	58.95 420	97.45 259	82.08 275	91.09 258	96.21 219

E4		91.74 120	91.55 117	92.31 163	94.27 240	80.80 239	93.81 250	96.17 155	87.97 137	91.11 154	96.05 122	80.75 137	98.08 189	89.78 146	94.02 191	98.06 87

RRT-MVS		90.85 145	90.70 143	91.30 222	94.25 241	76.83 361	94.85 165	96.13 161	89.04 90	90.23 173	94.88 192	70.15 304	98.72 119	91.86 112	94.88 164	98.34 48

testing99		86.72 299	85.73 304	89.69 307	94.23 242	74.91 387	91.35 356	90.97 406	86.14 201	86.36 257	90.22 371	59.41 414	97.48 254	82.24 271	90.66 264	96.69 200

CLD-MVS		89.47 192	88.90 196	91.18 227	94.22 243	82.07 187	92.13 333	96.09 165	87.90 142	85.37 294	92.45 291	74.38 238	97.56 245	87.15 193	90.43 267	93.93 320
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
viewdifsd2359ckpt07		91.11 142	91.02 134	91.41 216	94.21 244	78.37 319	92.91 301	95.71 202	87.50 158	90.32 171	95.88 136	80.27 142	97.99 206	88.78 168	93.55 206	97.86 110

UBG		85.51 327	84.57 334	88.35 350	94.21 244	71.78 426	90.07 395	89.66 438	82.28 308	85.91 269	89.01 399	61.30 396	97.06 301	76.58 361	92.06 247	96.22 217

HQP-NCC					94.17 246		94.39 202		88.81 100	85.43 288

ACMP_Plane					94.17 246		94.39 202		88.81 100	85.43 288

HQP-MVS		89.80 183	89.28 182	91.34 220	94.17 246	81.56 202	94.39 202	96.04 170	88.81 100	85.43 288	93.97 238	73.83 251	97.96 213	87.11 195	89.77 283	94.50 296

testing222		84.84 345	83.32 352	89.43 323	94.15 249	75.94 374	91.09 365	89.41 444	84.90 242	85.78 271	89.44 393	52.70 451	96.28 361	70.80 409	91.57 250	96.07 228

WBMVS		84.97 342	84.18 338	87.34 379	94.14 250	71.62 430	90.20 391	92.35 363	81.61 332	84.06 328	90.76 356	61.82 390	96.52 344	78.93 336	83.81 353	93.89 321

XVG-OURS		89.40 199	88.70 200	91.52 210	94.06 251	81.46 208	91.27 360	96.07 167	86.14 201	88.89 204	95.77 148	68.73 329	97.26 285	87.39 189	89.96 276	95.83 240

sss		88.93 215	88.26 216	90.94 243	94.05 252	80.78 240	91.71 345	95.38 232	81.55 334	88.63 208	93.91 243	75.04 226	95.47 399	82.47 265	91.61 249	96.57 205

PCF-MVS	84.11 10	87.74 248	86.08 286	92.70 133	94.02 253	84.43 102	89.27 410	95.87 188	73.62 437	84.43 317	94.33 220	78.48 178	98.86 101	70.27 410	94.45 179	94.81 281
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GBi-Net		87.26 272	85.98 290	91.08 232	94.01 254	83.10 148	95.14 147	94.94 262	83.57 274	84.37 318	91.64 322	66.59 349	96.34 358	78.23 343	85.36 338	93.79 331

test1		87.26 272	85.98 290	91.08 232	94.01 254	83.10 148	95.14 147	94.94 262	83.57 274	84.37 318	91.64 322	66.59 349	96.34 358	78.23 343	85.36 338	93.79 331

FMVSNet2		87.19 280	85.82 297	91.30 222	94.01 254	83.67 125	94.79 169	94.94 262	83.57 274	83.88 333	92.05 310	66.59 349	96.51 345	77.56 350	85.01 341	93.73 340

XVG-OURS-SEG-HR		89.95 177	89.45 174	91.47 214	94.00 257	81.21 217	91.87 340	96.06 169	85.78 208	88.55 209	95.73 150	74.67 233	97.27 283	88.71 169	89.64 285	95.91 234

FIs		90.51 160	90.35 147	90.99 239	93.99 258	80.98 227	95.73 104	97.54 10	89.15 86	86.72 249	94.68 202	81.83 123	97.24 287	85.18 220	88.31 307	94.76 283

xiu_mvs_v1_base_debu		90.64 155	90.05 157	92.40 152	93.97 259	84.46 99	93.32 276	95.46 223	85.17 231	92.25 115	94.03 231	70.59 295	98.57 137	90.97 124	94.67 169	94.18 307

xiu_mvs_v1_base		90.64 155	90.05 157	92.40 152	93.97 259	84.46 99	93.32 276	95.46 223	85.17 231	92.25 115	94.03 231	70.59 295	98.57 137	90.97 124	94.67 169	94.18 307

xiu_mvs_v1_base_debi		90.64 155	90.05 157	92.40 152	93.97 259	84.46 99	93.32 276	95.46 223	85.17 231	92.25 115	94.03 231	70.59 295	98.57 137	90.97 124	94.67 169	94.18 307

viewmacassd2359aftdt		91.67 128	91.43 124	92.37 156	93.95 262	81.00 226	93.90 247	95.97 176	87.75 151	91.45 144	96.04 124	79.92 147	97.97 211	89.26 158	94.67 169	98.14 76

VortexMVS		88.42 228	88.01 220	89.63 313	93.89 263	78.82 305	93.82 249	95.47 222	86.67 187	84.53 313	91.99 312	72.62 269	96.65 323	89.02 162	84.09 351	93.41 353

VPA-MVSNet		89.62 186	88.96 192	91.60 208	93.86 264	82.89 160	95.46 121	97.33 32	87.91 141	88.43 212	93.31 261	74.17 243	97.40 272	87.32 191	82.86 370	94.52 293

MVSFormer		91.68 127	91.30 126	92.80 121	93.86 264	83.88 119	95.96 83	95.90 183	84.66 253	91.76 135	94.91 190	77.92 185	97.30 279	89.64 153	97.11 107	97.24 152

lupinMVS		90.92 144	90.21 150	93.03 107	93.86 264	83.88 119	92.81 305	93.86 319	79.84 357	91.76 135	94.29 223	77.92 185	98.04 197	90.48 137	97.11 107	97.17 158

AstraMVS		90.69 151	90.30 149	91.84 198	93.81 267	79.85 277	94.76 172	92.39 362	88.96 97	91.01 161	95.87 139	70.69 293	97.94 216	92.49 82	92.70 233	97.73 123

IterMVS-LS		88.36 232	87.91 226	89.70 305	93.80 268	78.29 323	93.73 256	95.08 252	85.73 210	84.75 306	91.90 316	79.88 152	96.92 311	83.83 243	82.51 371	93.89 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MSDG		84.86 344	83.09 357	90.14 279	93.80 268	80.05 268	89.18 413	93.09 344	78.89 370	78.19 418	91.91 315	65.86 359	97.27 283	68.47 423	88.45 303	93.11 368

FMVSNet3		87.40 267	86.11 284	91.30 222	93.79 270	83.64 127	94.20 217	94.81 276	83.89 266	84.37 318	91.87 317	68.45 332	96.56 341	78.23 343	85.36 338	93.70 342

fmvsm_s_conf0.1_n		93.46 72	93.66 73	92.85 119	93.75 271	83.13 146	96.02 77	95.74 197	87.68 153	95.89 41	98.17 5	82.78 102	98.46 146	96.71 22	96.17 135	96.98 179

icg_test_0407_2		89.15 204	88.97 191	89.68 311	93.72 272	77.75 342	88.26 427	95.34 237	85.53 219	88.34 214	94.49 214	77.69 189	93.99 424	84.75 227	92.65 234	97.28 147

IMVS_0407		89.85 182	89.51 173	90.88 244	93.72 272	77.75 342	93.07 293	95.34 237	85.53 219	88.34 214	94.49 214	77.69 189	97.60 241	84.75 227	92.65 234	97.28 147

IMVS_0404		87.60 258	86.84 251	89.89 293	93.72 272	77.75 342	88.56 422	95.34 237	85.53 219	79.98 395	94.49 214	66.54 352	94.64 412	84.75 227	92.65 234	97.28 147

IMVS_0403		89.97 175	89.64 169	90.96 242	93.72 272	77.75 342	93.00 296	95.34 237	85.53 219	88.77 206	94.49 214	78.49 177	97.84 223	84.75 227	92.65 234	97.28 147

FC-MVSNet-test		90.27 164	90.18 152	90.53 256	93.71 276	79.85 277	95.77 100	97.59 7	89.31 79	86.27 260	94.67 205	81.93 121	97.01 305	84.26 237	88.09 310	94.71 284

TAMVS		89.21 203	88.29 214	91.96 186	93.71 276	82.62 174	93.30 280	94.19 305	82.22 309	87.78 227	93.94 239	78.83 169	96.95 309	77.70 348	92.98 227	96.32 212

ET-MVSNet_ETH3D		87.51 262	85.91 294	92.32 162	93.70 278	83.93 117	92.33 325	90.94 408	84.16 259	72.09 457	92.52 289	69.90 306	95.85 380	89.20 159	88.36 306	97.17 158

test_fmvsmvis_n_1920		93.44 75	93.55 75	93.10 102	93.67 279	84.26 108	95.83 95	96.14 158	89.00 96	92.43 114	97.50 48	83.37 91	98.72 119	96.61 24	97.44 101	96.32 212

reproduce_monomvs		86.37 313	85.87 295	87.87 366	93.66 280	73.71 399	93.44 271	95.02 253	88.61 110	82.64 359	91.94 314	57.88 424	96.68 321	89.96 144	79.71 414	93.22 360

CDS-MVSNet		89.45 193	88.51 205	92.29 168	93.62 281	83.61 130	93.01 295	94.68 283	81.95 317	87.82 226	93.24 265	78.69 172	96.99 306	80.34 309	93.23 219	96.28 215
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
UniMVSNet (Re)		89.80 183	89.07 187	92.01 180	93.60 282	84.52 96	94.78 170	97.47 17	89.26 82	86.44 256	92.32 295	82.10 116	97.39 275	84.81 226	80.84 399	94.12 311

VPNet		88.20 236	87.47 235	90.39 269	93.56 283	79.46 287	94.04 231	95.54 218	88.67 107	86.96 239	94.58 212	69.33 316	97.15 292	84.05 240	80.53 404	94.56 291

thisisatest0515		87.33 270	85.99 289	91.37 219	93.49 284	79.55 284	90.63 376	89.56 441	80.17 352	87.56 231	90.86 350	67.07 341	98.28 168	81.50 289	93.02 226	96.29 214

mvs_anonymous		89.37 201	89.32 180	89.51 321	93.47 285	74.22 394	91.65 348	94.83 274	82.91 296	85.45 285	93.79 247	81.23 133	96.36 357	86.47 202	94.09 190	97.94 96

CANet_DTU		90.26 165	89.41 177	92.81 120	93.46 286	83.01 156	93.48 268	94.47 292	89.43 74	87.76 228	94.23 228	70.54 299	99.03 69	84.97 222	96.39 130	96.38 210

testing3		80.46 403	79.59 397	83.06 437	93.44 287	64.64 468	93.33 275	85.47 463	84.34 258	79.93 397	90.84 352	44.35 472	92.39 446	57.06 471	87.56 318	92.16 405

UniMVSNet_NR-MVSNet		89.92 179	89.29 181	91.81 201	93.39 288	83.72 123	94.43 194	97.12 55	89.80 60	86.46 253	93.32 260	83.16 94	97.23 288	84.92 223	81.02 395	94.49 298

Effi-MVS+-dtu		88.65 222	88.35 210	89.54 316	93.33 289	76.39 369	94.47 191	94.36 298	87.70 152	85.43 288	89.56 392	73.45 256	97.26 285	85.57 216	91.28 253	94.97 269

WR-MVS		88.38 230	87.67 230	90.52 260	93.30 290	80.18 259	93.26 283	95.96 177	88.57 112	85.47 284	92.81 280	76.12 206	96.91 312	81.24 293	82.29 375	94.47 301

WR-MVS_H		87.80 246	87.37 237	89.10 330	93.23 291	78.12 326	95.61 115	97.30 37	87.90 142	83.72 337	92.01 311	79.65 162	96.01 372	76.36 362	80.54 403	93.16 364

test_0402		81.30 395	79.17 404	87.67 370	93.19 292	78.17 325	92.98 298	91.71 383	75.25 419	76.02 438	90.31 369	59.23 415	96.37 355	50.22 477	83.63 358	88.47 462

Elysia		90.12 167	89.10 185	93.18 96	93.16 293	84.05 114	95.22 138	96.27 135	85.16 234	90.59 165	94.68 202	64.64 367	98.37 157	86.38 204	95.77 141	97.12 167

StellarMVS		90.12 167	89.10 185	93.18 96	93.16 293	84.05 114	95.22 138	96.27 135	85.16 234	90.59 165	94.68 202	64.64 367	98.37 157	86.38 204	95.77 141	97.12 167

OPM-MVS		90.12 167	89.56 172	91.82 199	93.14 295	83.90 118	94.16 218	95.74 197	88.96 97	87.86 222	95.43 164	72.48 271	97.91 219	88.10 177	90.18 272	93.65 343
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
CP-MVSNet		87.63 254	87.26 242	88.74 341	93.12 296	76.59 366	95.29 131	96.58 110	88.43 115	83.49 347	92.98 274	75.28 223	95.83 381	78.97 335	81.15 391	93.79 331

mmtdpeth		85.04 341	84.15 340	87.72 369	93.11 297	75.74 378	94.37 206	92.83 351	84.98 240	89.31 194	86.41 437	61.61 393	97.14 295	92.63 81	62.11 474	90.29 440

diffmvs_AUTHOR		91.51 130	91.44 123	91.73 203	93.09 298	80.27 256	92.51 316	95.58 214	87.22 167	91.80 134	95.57 157	79.96 146	97.48 254	92.23 93	94.97 161	97.45 140

diffmvs		91.37 133	91.23 129	91.77 202	93.09 298	80.27 256	92.36 321	95.52 220	87.03 174	91.40 146	94.93 189	80.08 144	97.44 262	92.13 99	94.56 175	97.61 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
nrg030		91.08 143	90.39 146	93.17 98	93.07 300	86.91 23	96.41 42	96.26 139	88.30 119	88.37 213	94.85 196	82.19 114	97.64 238	91.09 122	82.95 365	94.96 272

UWE-MVS		83.69 364	83.09 357	85.48 415	93.06 301	65.27 466	90.92 370	86.14 458	79.90 356	86.26 261	90.72 359	57.17 428	95.81 383	71.03 408	92.62 239	95.35 258

PAPM		86.68 301	85.39 311	90.53 256	93.05 302	79.33 298	89.79 400	94.77 279	78.82 373	81.95 368	93.24 265	76.81 196	97.30 279	66.94 434	93.16 221	94.95 276

DU-MVS		89.34 202	88.50 206	91.85 197	93.04 303	83.72 123	94.47 191	96.59 109	89.50 71	86.46 253	93.29 263	77.25 193	97.23 288	84.92 223	81.02 395	94.59 288

NR-MVSNet		88.58 226	87.47 235	91.93 189	93.04 303	84.16 111	94.77 171	96.25 141	89.05 89	80.04 394	93.29 263	79.02 168	97.05 303	81.71 287	80.05 409	94.59 288

jason		90.80 146	90.10 154	92.90 115	93.04 303	83.53 131	93.08 291	94.15 308	80.22 351	91.41 145	94.91 190	76.87 195	97.93 217	90.28 138	96.90 115	97.24 152
jason: jason.
PS-CasMVS		87.32 271	86.88 248	88.63 344	92.99 306	76.33 371	95.33 126	96.61 108	88.22 123	83.30 352	93.07 272	73.03 264	95.79 385	78.36 340	81.00 397	93.75 338

test_vis1_n_1920		89.39 200	89.84 163	88.04 361	92.97 307	72.64 416	94.71 176	96.03 172	86.18 199	91.94 127	96.56 99	61.63 391	95.74 387	93.42 65	95.11 160	95.74 244

SD_0403		84.71 348	84.65 330	84.92 424	92.95 308	65.95 460	92.07 337	93.23 340	83.82 269	79.03 408	93.73 252	73.90 248	92.91 442	63.02 453	90.05 273	95.89 236

MVSTER		88.84 216	88.29 214	90.51 261	92.95 308	80.44 253	93.73 256	95.01 254	84.66 253	87.15 237	93.12 270	72.79 266	97.21 290	87.86 179	87.36 322	93.87 325

RPSCF		85.07 338	84.27 336	87.48 376	92.91 310	70.62 440	91.69 347	92.46 360	76.20 411	82.67 358	95.22 173	63.94 376	97.29 282	77.51 351	85.80 333	94.53 292

viewdifsd2359ckpt11		89.43 195	89.05 189	90.56 254	92.89 311	77.00 357	92.81 305	94.52 289	87.03 174	89.77 184	95.79 145	74.67 233	97.51 249	88.97 163	84.98 342	97.17 158

viewmsd2359difaftdt		89.43 195	89.05 189	90.56 254	92.89 311	77.00 357	92.81 305	94.52 289	87.03 174	89.77 184	95.79 145	74.67 233	97.51 249	88.97 163	84.98 342	97.17 158

viewmambaseed2359dif		90.04 172	89.78 166	90.83 245	92.85 313	77.92 331	92.23 329	95.01 254	81.90 320	90.20 174	95.45 161	79.64 163	97.34 277	87.52 187	93.17 220	97.23 155

FMVSNet1		85.85 321	84.11 341	91.08 232	92.81 314	83.10 148	95.14 147	94.94 262	81.64 330	82.68 357	91.64 322	59.01 419	96.34 358	75.37 372	83.78 354	93.79 331

tfpnnormal		84.72 347	83.23 355	89.20 327	92.79 315	80.05 268	94.48 188	95.81 191	82.38 305	81.08 378	91.21 336	69.01 325	96.95 309	61.69 456	80.59 402	90.58 439

LuminaMVS		90.55 159	89.81 164	92.77 123	92.78 316	84.21 109	94.09 226	94.17 307	85.82 206	91.54 140	94.14 230	69.93 305	97.92 218	91.62 116	94.21 188	96.18 220

SSC-MVS3.2		84.60 350	84.19 337	85.85 412	92.74 317	68.07 451	88.15 429	93.81 325	87.42 162	83.76 336	91.07 345	62.91 383	95.73 388	74.56 384	83.24 364	93.75 338

OpenMVS	83.78 11	88.74 220	87.29 239	93.08 104	92.70 318	85.39 77	96.57 40	96.43 120	78.74 376	80.85 380	96.07 121	69.64 311	99.01 74	78.01 346	96.65 124	94.83 280

TranMVSNet+NR-MVSNet		88.84 216	87.95 222	91.49 212	92.68 319	83.01 156	94.92 159	96.31 130	89.88 54	85.53 279	93.85 246	76.63 201	96.96 308	81.91 280	79.87 412	94.50 296

MVS		87.44 265	86.10 285	91.44 215	92.61 320	83.62 128	92.63 312	95.66 208	67.26 465	81.47 372	92.15 301	77.95 184	98.22 172	79.71 318	95.48 149	92.47 393

fmvsm_s_conf0.1_n_a		93.19 86	93.26 80	92.97 111	92.49 321	83.62 128	96.02 77	95.72 201	86.78 183	96.04 38	98.19 4	82.30 110	98.43 154	96.38 25	95.42 153	96.86 189

CHOSEN 280x420		85.15 337	83.99 344	88.65 343	92.47 322	78.40 318	79.68 482	92.76 354	74.90 424	81.41 374	89.59 390	69.85 309	95.51 395	79.92 316	95.29 156	92.03 406

test_fmvsmconf0.1_n		94.20 47	94.31 43	93.88 70	92.46 323	84.80 87	96.18 59	96.82 85	89.29 81	95.68 45	98.11 11	85.10 65	98.99 81	97.38 11	97.75 96	97.86 110

UniMVSNet_ETH3D		87.53 261	86.37 272	91.00 238	92.44 324	78.96 304	94.74 173	95.61 212	84.07 262	85.36 295	94.52 213	59.78 411	97.34 277	82.93 256	87.88 313	96.71 198

1314		87.51 262	86.57 265	90.34 273	92.42 325	79.74 282	92.63 312	95.35 236	78.35 382	80.14 391	91.62 326	74.05 245	97.15 292	81.05 294	93.53 208	94.12 311

cl22		86.78 295	85.98 290	89.18 328	92.34 326	77.62 348	90.84 372	94.13 310	81.33 338	83.97 332	90.15 375	73.96 247	96.60 336	84.19 238	82.94 366	93.33 354

PEN-MVS		86.80 294	86.27 278	88.40 348	92.32 327	75.71 379	95.18 144	96.38 125	87.97 137	82.82 356	93.15 268	73.39 259	95.92 376	76.15 366	79.03 420	93.59 344

tt0805		86.92 288	85.74 303	90.48 264	92.22 328	79.98 273	95.63 114	94.88 270	83.83 268	84.74 307	92.80 281	57.61 426	97.67 233	85.48 217	84.42 347	93.79 331

c3_l		87.14 282	86.50 269	89.04 332	92.20 329	77.26 353	91.22 363	94.70 282	82.01 316	84.34 322	90.43 365	78.81 170	96.61 332	83.70 248	81.09 392	93.25 358

SCA		86.32 314	85.18 318	89.73 304	92.15 330	76.60 365	91.12 364	91.69 385	83.53 277	85.50 282	88.81 403	66.79 345	96.48 347	76.65 358	90.35 269	96.12 224

XXY-MVS		87.65 251	86.85 250	90.03 286	92.14 331	80.60 249	93.76 253	95.23 243	82.94 295	84.60 309	94.02 234	74.27 239	95.49 398	81.04 295	83.68 357	94.01 319

miper_ehance_all_eth		87.22 277	86.62 263	89.02 333	92.13 332	77.40 351	90.91 371	94.81 276	81.28 339	84.32 323	90.08 378	79.26 165	96.62 329	83.81 244	82.94 366	93.04 371

IB-MVS	80.51 15	85.24 336	83.26 354	91.19 226	92.13 332	79.86 276	91.75 344	91.29 398	83.28 285	80.66 384	88.49 409	61.28 397	98.46 146	80.99 298	79.46 416	95.25 261
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
cascas		86.43 312	84.98 322	90.80 248	92.10 334	80.92 231	90.24 388	95.91 182	73.10 442	83.57 343	88.39 410	65.15 362	97.46 258	84.90 225	91.43 251	94.03 318

Fast-Effi-MVS+-dtu		87.44 265	86.72 255	89.63 313	92.04 335	77.68 347	94.03 232	93.94 314	85.81 207	82.42 360	91.32 334	70.33 301	97.06 301	80.33 310	90.23 271	94.14 310

cl____		86.52 307	85.78 298	88.75 339	92.03 336	76.46 367	90.74 373	94.30 300	81.83 325	83.34 350	90.78 355	75.74 219	96.57 339	81.74 285	81.54 386	93.22 360

DIV-MVS_self_test		86.53 306	85.78 298	88.75 339	92.02 337	76.45 368	90.74 373	94.30 300	81.83 325	83.34 350	90.82 353	75.75 217	96.57 339	81.73 286	81.52 387	93.24 359

eth_miper_zixun_eth		86.50 308	85.77 300	88.68 342	91.94 338	75.81 377	90.47 382	94.89 268	82.05 313	84.05 329	90.46 364	75.96 211	96.77 316	82.76 262	79.36 417	93.46 351

Syy-MVS		80.07 408	79.78 392	80.94 446	91.92 339	59.93 478	89.75 402	87.40 455	81.72 327	78.82 413	87.20 427	66.29 354	91.29 458	47.06 479	87.84 315	91.60 414

myMVS_eth3d		79.67 413	78.79 409	82.32 443	91.92 339	64.08 469	89.75 402	87.40 455	81.72 327	78.82 413	87.20 427	45.33 470	91.29 458	59.09 466	87.84 315	91.60 414

PS-MVSNAJss		89.97 175	89.62 170	91.02 236	91.90 341	80.85 237	95.26 135	95.98 173	86.26 197	86.21 262	94.29 223	79.70 156	97.65 236	88.87 167	88.10 308	94.57 290

ITE_SJBPF				88.24 356	91.88 342	77.05 356		92.92 348	85.54 217	80.13 392	93.30 262	57.29 427	96.20 363	72.46 397	84.71 345	91.49 419

EI-MVSNet		89.10 206	88.86 198	89.80 300	91.84 343	78.30 322	93.70 260	95.01 254	85.73 210	87.15 237	95.28 170	79.87 153	97.21 290	83.81 244	87.36 322	93.88 324

CVMVSNet		84.69 349	84.79 328	84.37 429	91.84 343	64.92 467	93.70 260	91.47 394	66.19 469	86.16 264	95.28 170	67.18 340	93.33 435	80.89 300	90.42 268	94.88 278

dmvs_re		84.20 355	83.22 356	87.14 390	91.83 345	77.81 337	90.04 396	90.19 423	84.70 252	81.49 371	89.17 396	64.37 371	91.13 460	71.58 401	85.65 335	92.46 394

MVS-HIRNet		73.70 435	72.20 437	78.18 454	91.81 346	56.42 486	82.94 471	82.58 472	55.24 480	68.88 466	66.48 483	55.32 437	95.13 405	58.12 468	88.42 304	83.01 471

PatchmatchNet		85.85 321	84.70 329	89.29 325	91.76 347	75.54 380	88.49 423	91.30 397	81.63 331	85.05 301	88.70 407	71.71 279	96.24 362	74.61 383	89.05 295	96.08 227
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TransMVSNet (Re)		84.43 352	83.06 359	88.54 345	91.72 348	78.44 316	95.18 144	92.82 353	82.73 300	79.67 400	92.12 303	73.49 255	95.96 374	71.10 407	68.73 462	91.21 426

IterMVS-SCA-FT		85.45 328	84.53 335	88.18 358	91.71 349	76.87 360	90.19 392	92.65 358	85.40 226	81.44 373	90.54 361	66.79 345	95.00 409	81.04 295	81.05 393	92.66 383

TinyColmap		79.76 412	77.69 415	85.97 408	91.71 349	73.12 407	89.55 404	90.36 420	75.03 421	72.03 458	90.19 373	46.22 469	96.19 365	63.11 451	81.03 394	88.59 461

MDTV_nov1_ep13			83.56 350		91.69 351	69.93 445	87.75 437	91.54 391	78.60 378	84.86 304	88.90 402	69.54 313	96.03 369	70.25 411	88.93 296

miper_enhance_ethall		86.90 289	86.18 280	89.06 331	91.66 352	77.58 349	90.22 390	94.82 275	79.16 366	84.48 314	89.10 397	79.19 167	96.66 322	84.06 239	82.94 366	92.94 374

DTE-MVSNet		86.11 316	85.48 309	87.98 362	91.65 353	74.92 386	94.93 158	95.75 196	87.36 164	82.26 362	93.04 273	72.85 265	95.82 382	74.04 386	77.46 426	93.20 362

MIMVSNet		82.59 373	80.53 376	88.76 338	91.51 354	78.32 321	86.57 449	90.13 425	79.32 362	80.70 383	88.69 408	52.98 450	93.07 440	66.03 440	88.86 297	94.90 277

WB-MVSnew		83.77 362	83.28 353	85.26 420	91.48 355	71.03 435	91.89 338	87.98 449	78.91 368	84.78 305	90.22 371	69.11 324	94.02 423	64.70 446	90.44 266	90.71 434

pm-mvs1		86.61 302	85.54 307	89.82 297	91.44 356	80.18 259	95.28 133	94.85 272	83.84 267	81.66 370	92.62 286	72.45 273	96.48 347	79.67 320	78.06 421	92.82 379

Baseline_NR-MVSNet		87.07 284	86.63 262	88.40 348	91.44 356	77.87 335	94.23 216	92.57 359	84.12 261	85.74 273	92.08 307	77.25 193	96.04 368	82.29 270	79.94 410	91.30 424

IterMVS		84.88 343	83.98 345	87.60 371	91.44 356	76.03 373	90.18 393	92.41 361	83.24 286	81.06 379	90.42 366	66.60 348	94.28 420	79.46 328	80.98 398	92.48 392
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MS-PatchMatch		85.05 339	84.16 339	87.73 368	91.42 359	78.51 314	91.25 361	93.53 333	77.50 390	80.15 390	91.58 328	61.99 388	95.51 395	75.69 369	94.35 182	89.16 454

tpm2		84.08 356	82.94 360	87.48 376	91.39 360	71.27 431	89.23 412	90.37 419	71.95 451	84.64 308	89.33 394	67.30 337	96.55 343	75.17 374	87.09 326	94.63 285

v8		87.50 264	86.71 256	89.89 293	91.37 361	79.40 291	94.50 187	95.38 232	84.81 247	83.60 342	91.33 332	76.05 207	97.42 264	82.84 259	80.51 406	92.84 378

ADS-MVSNet2		81.66 387	79.71 395	87.50 374	91.35 362	74.19 395	83.33 468	88.48 447	72.90 444	82.24 363	85.77 443	64.98 363	93.20 438	64.57 447	83.74 355	95.12 264

ADS-MVSNet		81.56 389	79.78 392	86.90 395	91.35 362	71.82 424	83.33 468	89.16 445	72.90 444	82.24 363	85.77 443	64.98 363	93.76 429	64.57 447	83.74 355	95.12 264

GA-MVS		86.61 302	85.27 316	90.66 250	91.33 364	78.71 308	90.40 383	93.81 325	85.34 227	85.12 298	89.57 391	61.25 398	97.11 297	80.99 298	89.59 286	96.15 221

miper_lstm_enhance		85.27 335	84.59 333	87.31 381	91.28 365	74.63 389	87.69 438	94.09 312	81.20 343	81.36 375	89.85 386	74.97 228	94.30 419	81.03 297	79.84 413	93.01 372

XVG-ACMP-BASELINE		86.00 317	84.84 327	89.45 322	91.20 366	78.00 329	91.70 346	95.55 216	85.05 239	82.97 354	92.25 299	54.49 444	97.48 254	82.93 256	87.45 321	92.89 376

v10		87.25 274	86.38 271	89.85 295	91.19 367	79.50 285	94.48 188	95.45 226	83.79 270	83.62 341	91.19 337	75.13 224	97.42 264	81.94 279	80.60 401	92.63 384

FMVSNet5		81.52 391	79.60 396	87.27 382	91.17 368	77.95 330	91.49 351	92.26 369	76.87 402	76.16 434	87.91 419	51.67 452	92.34 447	67.74 429	81.16 389	91.52 417

USDC		82.76 370	81.26 373	87.26 383	91.17 368	74.55 390	89.27 410	93.39 336	78.26 385	75.30 442	92.08 307	54.43 445	96.63 326	71.64 400	85.79 334	90.61 436

CostFormer		85.77 324	84.94 324	88.26 355	91.16 370	72.58 419	89.47 408	91.04 404	76.26 409	86.45 255	89.97 382	70.74 292	96.86 315	82.35 268	87.07 327	95.34 259

test_cas_vis1_n_1920		88.83 219	88.85 199	88.78 337	91.15 371	76.72 363	93.85 248	94.93 266	83.23 287	92.81 98	96.00 126	61.17 402	94.45 413	91.67 115	94.84 165	95.17 263

baseline2		86.50 308	85.39 311	89.84 296	91.12 372	76.70 364	91.88 339	88.58 446	82.35 307	79.95 396	90.95 348	73.42 258	97.63 239	80.27 311	89.95 277	95.19 262

tpm cat1		81.96 379	80.27 382	87.01 391	91.09 373	71.02 436	87.38 442	91.53 392	66.25 468	80.17 389	86.35 439	68.22 334	96.15 366	69.16 419	82.29 375	93.86 327

tpmvs		83.35 367	82.07 366	87.20 388	91.07 374	71.00 437	88.31 426	91.70 384	78.91 368	80.49 387	87.18 429	69.30 319	97.08 298	68.12 428	83.56 359	93.51 349

tt0320-xc		79.63 414	76.66 423	88.52 346	91.03 375	78.72 306	93.00 296	89.53 443	66.37 467	76.11 437	87.11 431	46.36 468	95.32 403	72.78 395	67.67 463	91.51 418

v1144		87.61 257	86.79 254	90.06 284	91.01 376	79.34 295	93.95 240	95.42 231	83.36 283	85.66 275	91.31 335	74.98 227	97.42 264	83.37 250	82.06 377	93.42 352

v2v482		87.84 244	87.06 244	90.17 276	90.99 377	79.23 302	94.00 237	95.13 247	84.87 244	85.53 279	92.07 309	74.45 237	97.45 259	84.71 232	81.75 383	93.85 328

SixPastTwentyTwo		83.91 360	82.90 362	86.92 394	90.99 377	70.67 439	93.48 268	91.99 377	85.54 217	77.62 425	92.11 305	60.59 405	96.87 314	76.05 367	77.75 423	93.20 362

test-LLR		85.87 320	85.41 310	87.25 384	90.95 379	71.67 428	89.55 404	89.88 434	83.41 280	84.54 311	87.95 417	67.25 338	95.11 406	81.82 282	93.37 215	94.97 269

test-mter		84.54 351	83.64 349	87.25 384	90.95 379	71.67 428	89.55 404	89.88 434	79.17 365	84.54 311	87.95 417	55.56 433	95.11 406	81.82 282	93.37 215	94.97 269

v148		87.04 285	86.32 275	89.21 326	90.94 381	77.26 353	93.71 259	94.43 293	84.84 246	84.36 321	90.80 354	76.04 208	97.05 303	82.12 273	79.60 415	93.31 355

mvs_tets		88.06 241	87.28 240	90.38 271	90.94 381	79.88 275	95.22 138	95.66 208	85.10 237	84.21 327	93.94 239	63.53 378	97.40 272	88.50 171	88.40 305	93.87 325

MVP-Stereo		85.97 318	84.86 326	89.32 324	90.92 383	82.19 184	92.11 334	94.19 305	78.76 375	78.77 416	91.63 325	68.38 333	96.56 341	75.01 377	93.95 193	89.20 453
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
Patchmatch-test		81.37 393	79.30 400	87.58 372	90.92 383	74.16 396	80.99 475	87.68 453	70.52 457	76.63 432	88.81 403	71.21 284	92.76 444	60.01 463	86.93 328	95.83 240

jajsoiax		88.24 235	87.50 233	90.48 264	90.89 385	80.14 261	95.31 127	95.65 210	84.97 241	84.24 326	94.02 234	65.31 361	97.42 264	88.56 170	88.52 301	93.89 321

tpmrst		85.35 332	84.99 321	86.43 404	90.88 386	67.88 454	88.71 419	91.43 395	80.13 353	86.08 265	88.80 405	73.05 263	96.02 370	82.48 264	83.40 363	95.40 255

gg-mvs-nofinetune		81.77 384	79.37 398	88.99 334	90.85 387	77.73 346	86.29 450	79.63 479	74.88 425	83.19 353	69.05 482	60.34 406	96.11 367	75.46 371	94.64 173	93.11 368

D2MVS		85.90 319	85.09 320	88.35 350	90.79 388	77.42 350	91.83 342	95.70 203	80.77 347	80.08 393	90.02 380	66.74 347	96.37 355	81.88 281	87.97 312	91.26 425

sc_t1		81.53 390	78.67 411	90.12 280	90.78 389	78.64 309	93.91 245	90.20 422	68.42 462	80.82 381	89.88 384	46.48 466	96.76 317	76.03 368	71.47 445	94.96 272

OurMVSNet-221017-0		85.35 332	84.64 332	87.49 375	90.77 390	72.59 418	94.01 235	94.40 296	84.72 250	79.62 402	93.17 267	61.91 389	96.72 318	81.99 278	81.16 389	93.16 364

v1192		87.25 274	86.33 274	90.00 290	90.76 391	79.04 303	93.80 251	95.48 221	82.57 302	85.48 283	91.18 339	73.38 260	97.42 264	82.30 269	82.06 377	93.53 346

test_djsdf		89.03 212	88.64 201	90.21 275	90.74 392	79.28 299	95.96 83	95.90 183	84.66 253	85.33 296	92.94 275	74.02 246	97.30 279	89.64 153	88.53 300	94.05 317

v7n		86.81 293	85.76 301	89.95 291	90.72 393	79.25 301	95.07 150	95.92 180	84.45 256	82.29 361	90.86 350	72.60 270	97.53 247	79.42 332	80.52 405	93.08 370

PVSNet_0	73.20 20	77.22 427	74.83 433	84.37 429	90.70 394	71.10 434	83.09 470	89.67 437	72.81 446	73.93 450	83.13 457	60.79 404	93.70 431	68.54 422	50.84 484	88.30 463

v144192		87.19 280	86.35 273	89.74 302	90.64 395	78.24 324	93.92 243	95.43 229	81.93 318	85.51 281	91.05 346	74.21 242	97.45 259	82.86 258	81.56 385	93.53 346

test_fmvs1		87.34 269	87.56 232	86.68 401	90.59 396	71.80 425	94.01 235	94.04 313	78.30 383	91.97 124	95.22 173	56.28 431	93.71 430	92.89 74	94.71 168	94.52 293

V42		87.68 249	86.86 249	90.15 278	90.58 397	80.14 261	94.24 215	95.28 241	83.66 272	85.67 274	91.33 332	74.73 231	97.41 270	84.43 236	81.83 381	92.89 376

CR-MVSNet		85.35 332	83.76 347	90.12 280	90.58 397	79.34 295	85.24 458	91.96 380	78.27 384	85.55 277	87.87 420	71.03 287	95.61 391	73.96 388	89.36 289	95.40 255

RPMNet		83.95 359	81.53 370	91.21 225	90.58 397	79.34 295	85.24 458	96.76 92	71.44 453	85.55 277	82.97 460	70.87 290	98.91 96	61.01 458	89.36 289	95.40 255

v1921920		86.97 287	86.06 287	89.69 307	90.53 400	78.11 327	93.80 251	95.43 229	81.90 320	85.33 296	91.05 346	72.66 267	97.41 270	82.05 277	81.80 382	93.53 346

usedtu_dtu_shiyan1		86.84 291	85.61 305	90.53 256	90.50 401	81.80 196	90.97 368	94.96 260	83.05 290	83.50 345	90.32 367	72.15 275	96.65 323	79.49 326	85.55 336	93.15 366

FE-MVSNET3		86.84 291	85.61 305	90.53 256	90.50 401	81.80 196	90.97 368	94.96 260	83.05 290	83.50 345	90.32 367	72.15 275	96.65 323	79.49 326	85.55 336	93.15 366

tt0320		80.13 407	77.41 416	88.29 353	90.50 401	78.02 328	93.10 290	90.71 415	66.06 470	76.75 430	86.97 432	49.56 458	95.40 400	71.65 399	71.41 446	91.46 421

v1240		86.78 295	85.85 296	89.56 315	90.45 404	77.79 339	93.61 264	95.37 234	81.65 329	85.43 288	91.15 341	71.50 282	97.43 263	81.47 290	82.05 379	93.47 350

tpm		84.73 346	84.02 343	86.87 397	90.33 405	68.90 449	89.06 415	89.94 431	80.85 346	85.75 272	89.86 385	68.54 331	95.97 373	77.76 347	84.05 352	95.75 243

EG-PatchMatch MVS		82.37 378	80.34 381	88.46 347	90.27 406	79.35 293	92.80 308	94.33 299	77.14 395	73.26 454	90.18 374	47.47 463	96.72 318	70.25 411	87.32 324	89.30 450

EPNet_dtu		86.49 310	85.94 293	88.14 359	90.24 407	72.82 411	94.11 222	92.20 370	86.66 188	79.42 403	92.36 294	73.52 254	95.81 383	71.26 402	93.66 203	95.80 242
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPMVS		83.90 361	82.70 365	87.51 373	90.23 408	72.67 414	88.62 421	81.96 474	81.37 337	85.01 302	88.34 411	66.31 353	94.45 413	75.30 373	87.12 325	95.43 254

EPNet		91.79 112	91.02 134	94.10 64	90.10 409	85.25 79	96.03 76	92.05 374	92.83 5	87.39 236	95.78 147	79.39 164	99.01 74	88.13 175	97.48 100	98.05 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PatchT		82.68 372	81.27 372	86.89 396	90.09 410	70.94 438	84.06 465	90.15 424	74.91 423	85.63 276	83.57 455	69.37 315	94.87 411	65.19 442	88.50 302	94.84 279

Patchmtry		82.71 371	80.93 375	88.06 360	90.05 411	76.37 370	84.74 463	91.96 380	72.28 450	81.32 376	87.87 420	71.03 287	95.50 397	68.97 420	80.15 408	92.32 401

pmmvs4		85.43 329	83.86 346	90.16 277	90.02 412	82.97 158	90.27 384	92.67 357	75.93 413	80.73 382	91.74 320	71.05 286	95.73 388	78.85 337	83.46 361	91.78 410

TESTMET0.1,1		83.74 363	82.85 363	86.42 405	89.96 413	71.21 433	89.55 404	87.88 450	77.41 391	83.37 349	87.31 425	56.71 429	93.65 432	80.62 305	92.85 231	94.40 302

dp		81.47 392	80.23 383	85.17 421	89.92 414	65.49 464	86.74 447	90.10 426	76.30 408	81.10 377	87.12 430	62.81 384	95.92 376	68.13 427	79.88 411	94.09 314

K. test v3		81.59 388	80.15 385	85.91 411	89.89 415	69.42 448	92.57 314	87.71 452	85.56 216	73.44 453	89.71 389	55.58 432	95.52 394	77.17 354	69.76 451	92.78 380

MDA-MVSNet-bldmvs		78.85 420	76.31 425	86.46 402	89.76 416	73.88 397	88.79 418	90.42 418	79.16 366	59.18 478	88.33 412	60.20 407	94.04 422	62.00 455	68.96 455	91.48 420

test_fmvs1_n		87.03 286	87.04 246	86.97 392	89.74 417	71.86 423	94.55 184	94.43 293	78.47 379	91.95 126	95.50 160	51.16 454	93.81 428	93.02 73	94.56 175	95.26 260

GG-mvs-BLEND				87.94 364	89.73 418	77.91 332	87.80 433	78.23 484		80.58 385	83.86 451	59.88 410	95.33 402	71.20 403	92.22 245	90.60 438

EGC-MVSNET		61.97 447	56.37 452	78.77 452	89.63 419	73.50 402	89.12 414	82.79 471	0.21 498	1.24 499	84.80 448	39.48 475	90.04 465	44.13 481	75.94 434	72.79 480

gm-plane-assit					89.60 420	68.00 452			77.28 394		88.99 400		97.57 244	79.44 330

MonoMVSNet		86.89 290	86.55 266	87.92 365	89.46 421	73.75 398	94.12 220	93.10 343	87.82 148	85.10 299	90.76 356	69.59 312	94.94 410	86.47 202	82.50 372	95.07 266

test_fmvsmconf0.01_n		93.19 86	93.02 87	93.71 80	89.25 422	84.42 104	96.06 73	96.29 131	89.06 88	94.68 57	98.13 7	79.22 166	98.98 85	97.22 13	97.24 106	97.74 122

anonymousdsp		87.84 244	87.09 243	90.12 280	89.13 423	80.54 251	94.67 178	95.55 216	82.05 313	83.82 334	92.12 303	71.47 283	97.15 292	87.15 193	87.80 317	92.67 382

N_pmnet		68.89 441	68.44 443	70.23 462	89.07 424	28.79 501	88.06 430	19.50 501	69.47 460	71.86 460	84.93 447	61.24 399	91.75 455	54.70 473	77.15 427	90.15 442

pmmvs5		84.21 354	82.84 364	88.34 352	88.95 425	76.94 359	92.41 318	91.91 382	75.63 415	80.28 388	91.18 339	64.59 369	95.57 392	77.09 356	83.47 360	92.53 391

PMMVS		85.71 325	84.96 323	87.95 363	88.90 426	77.09 355	88.68 420	90.06 427	72.32 449	86.47 252	90.76 356	72.15 275	94.40 416	81.78 284	93.49 210	92.36 399

JIA-IIPM		81.04 396	78.98 408	87.25 384	88.64 427	73.48 403	81.75 474	89.61 440	73.19 441	82.05 366	73.71 478	66.07 358	95.87 379	71.18 405	84.60 346	92.41 396

test_vis1_n		86.56 305	86.49 270	86.78 399	88.51 428	72.69 413	94.68 177	93.78 327	79.55 361	90.70 163	95.31 169	48.75 460	93.28 436	93.15 69	93.99 192	94.38 303

Gipuma		57.99 453	54.91 455	67.24 468	88.51 428	65.59 463	52.21 490	90.33 421	43.58 486	42.84 489	51.18 490	20.29 491	85.07 480	34.77 487	70.45 447	51.05 489
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
EU-MVSNet		81.32 394	80.95 374	82.42 442	88.50 430	63.67 471	93.32 276	91.33 396	64.02 473	80.57 386	92.83 278	61.21 400	92.27 448	76.34 363	80.38 407	91.32 423

our_test_3		81.93 381	80.46 380	86.33 406	88.46 431	73.48 403	88.46 424	91.11 400	76.46 404	76.69 431	88.25 413	66.89 343	94.36 417	68.75 421	79.08 419	91.14 428

ppachtmachnet_test		81.84 382	80.07 386	87.15 389	88.46 431	74.43 393	89.04 416	92.16 371	75.33 418	77.75 423	88.99 400	66.20 355	95.37 401	65.12 444	77.60 424	91.65 412

lessismore_v0				86.04 407	88.46 431	68.78 450		80.59 477		73.01 455	90.11 377	55.39 435	96.43 352	75.06 376	65.06 469	92.90 375

test0.0.03 1		82.41 376	81.69 368	84.59 427	88.23 434	72.89 410	90.24 388	87.83 451	83.41 280	79.86 398	89.78 387	67.25 338	88.99 472	65.18 443	83.42 362	91.90 409

MDA-MVSNet_test_wron		79.21 418	77.19 420	85.29 418	88.22 435	72.77 412	85.87 452	90.06 427	74.34 428	62.62 475	87.56 423	66.14 356	91.99 452	66.90 437	73.01 438	91.10 431

YYNet1		79.22 417	77.20 419	85.28 419	88.20 436	72.66 415	85.87 452	90.05 429	74.33 429	62.70 473	87.61 422	66.09 357	92.03 449	66.94 434	72.97 439	91.15 427

UWE-MVS-28		78.98 419	78.38 412	80.80 447	88.18 437	60.66 477	90.65 375	78.51 481	78.84 372	77.93 422	90.93 349	59.08 418	89.02 471	50.96 476	90.33 270	92.72 381

pmmvs6		83.42 365	81.60 369	88.87 336	88.01 438	77.87 335	94.96 156	94.24 304	74.67 426	78.80 415	91.09 344	60.17 408	96.49 346	77.06 357	75.40 435	92.23 403

testgi		80.94 400	80.20 384	83.18 435	87.96 439	66.29 459	91.28 359	90.70 416	83.70 271	78.12 419	92.84 277	51.37 453	90.82 462	63.34 450	82.46 373	92.43 395

mvsany_test1		85.42 330	85.30 315	85.77 413	87.95 440	75.41 382	87.61 441	80.97 476	76.82 403	88.68 207	95.83 142	77.44 192	90.82 462	85.90 211	86.51 329	91.08 432

Anonymous20231206		81.03 397	79.77 394	84.82 425	87.85 441	70.26 443	91.42 352	92.08 373	73.67 436	77.75 423	89.25 395	62.43 386	93.08 439	61.50 457	82.00 380	91.12 429

dmvs_testset		74.57 434	75.81 431	70.86 461	87.72 442	40.47 496	87.05 445	77.90 486	82.75 299	71.15 463	85.47 445	67.98 335	84.12 483	45.26 480	76.98 430	88.00 464

test_fmvs2		83.98 357	84.03 342	83.83 434	87.16 443	67.53 458	93.93 242	92.89 349	77.62 389	86.89 245	93.53 255	47.18 464	92.02 451	90.54 134	86.51 329	91.93 408

OpenMVS_ROB	74.94 19	79.51 415	77.03 422	86.93 393	87.00 444	76.23 372	92.33 325	90.74 414	68.93 461	74.52 447	88.23 414	49.58 457	96.62 329	57.64 469	84.29 348	87.94 465

LF4IMVS		80.37 405	79.07 407	84.27 431	86.64 445	69.87 447	89.39 409	91.05 403	76.38 406	74.97 444	90.00 381	47.85 462	94.25 421	74.55 385	80.82 400	88.69 460

MIMVSNet1		79.38 416	77.28 418	85.69 414	86.35 446	73.67 400	91.61 349	92.75 355	78.11 388	72.64 456	88.12 415	48.16 461	91.97 453	60.32 460	77.49 425	91.43 422

KD-MVS_2432*1600		78.50 421	76.02 429	85.93 409	86.22 447	74.47 391	84.80 461	92.33 364	79.29 363	76.98 428	85.92 441	53.81 448	93.97 425	67.39 430	57.42 479	89.36 448

miper_refine_blended		78.50 421	76.02 429	85.93 409	86.22 447	74.47 391	84.80 461	92.33 364	79.29 363	76.98 428	85.92 441	53.81 448	93.97 425	67.39 430	57.42 479	89.36 448

0.4-1-1-0.2		80.84 401	77.77 414	90.06 284	86.18 449	79.35 293	86.75 446	89.54 442	76.23 410	78.59 417	75.46 475	55.03 440	96.99 306	80.11 313	72.05 443	93.85 328

CL-MVSNet_self_test		81.74 385	80.53 376	85.36 417	85.96 450	72.45 420	90.25 386	93.07 345	81.24 341	79.85 399	87.29 426	70.93 289	92.52 445	66.95 433	69.23 453	91.11 430

test_vis1_rt		77.96 425	76.46 424	82.48 441	85.89 451	71.74 427	90.25 386	78.89 480	71.03 456	71.30 462	81.35 469	42.49 474	91.05 461	84.55 234	82.37 374	84.65 468

test20.03		79.95 410	79.08 406	82.55 439	85.79 452	67.74 456	91.09 365	91.08 401	81.23 342	74.48 448	89.96 383	61.63 391	90.15 464	60.08 461	76.38 431	89.76 445

Anonymous20240521		80.44 404	79.21 402	84.11 432	85.75 453	67.89 453	92.86 304	93.23 340	75.61 416	75.59 441	87.47 424	50.03 455	94.33 418	71.14 406	81.21 388	90.12 443

KD-MVS_self_test		80.20 406	79.24 401	83.07 436	85.64 454	65.29 465	91.01 367	93.93 315	78.71 377	76.32 433	86.40 438	59.20 416	92.93 441	72.59 396	69.35 452	91.00 433

blended_shiyan6		82.78 369	80.48 379	89.67 312	85.53 455	79.76 280	91.37 354	93.82 322	77.14 395	79.30 406	83.73 453	64.96 365	96.63 326	79.68 319	68.75 458	92.63 384

blend_shiyan4		81.94 380	79.35 399	89.70 305	85.52 456	80.08 264	91.29 358	93.82 322	77.12 398	79.31 405	82.94 461	54.81 441	96.60 336	79.60 322	69.78 450	92.41 396

blended_shiyan8		82.79 368	80.49 378	89.69 307	85.50 457	79.83 279	91.38 353	93.82 322	77.14 395	79.39 404	83.73 453	64.95 366	96.63 326	79.75 317	68.77 457	92.62 386

Patchmatch-RL test		81.67 386	79.96 390	86.81 398	85.42 458	71.23 432	82.17 473	87.50 454	78.47 379	77.19 427	82.50 466	70.81 291	93.48 433	82.66 263	72.89 440	95.71 247

UnsupCasMVSNet_eth		80.07 408	78.27 413	85.46 416	85.24 459	72.63 417	88.45 425	94.87 271	82.99 294	71.64 461	88.07 416	56.34 430	91.75 455	73.48 392	63.36 472	92.01 407

wanda-best-256-512		82.44 374	80.07 386	89.53 317	85.12 460	79.44 289	90.49 380	93.75 328	76.97 400	79.00 409	82.72 462	64.29 372	96.61 332	79.56 324	68.75 458	92.55 387

FE-blended-shiyan7		82.44 374	80.07 386	89.53 317	85.12 460	79.44 289	90.49 380	93.75 328	76.97 400	79.00 409	82.72 462	64.29 372	96.61 332	79.56 324	68.75 458	92.55 387

usedtu_blend_shiyan5		82.39 377	79.93 391	89.75 301	85.12 460	80.08 264	92.36 321	93.26 338	74.29 430	79.00 409	82.72 462	64.29 372	96.60 336	79.60 322	68.75 458	92.55 387

pmmvs-eth3d		80.97 399	78.72 410	87.74 367	84.99 463	79.97 274	90.11 394	91.65 387	75.36 417	73.51 452	86.03 440	59.45 413	93.96 427	75.17 374	72.21 441	89.29 452

FE-MVSNET2		81.82 383	79.99 389	87.34 379	84.74 464	77.36 352	92.72 309	94.55 287	82.09 311	73.79 451	86.46 434	57.80 425	94.45 413	74.65 381	73.10 437	90.20 441

mvs5depth		80.98 398	79.15 405	86.45 403	84.57 465	73.29 406	87.79 434	91.67 386	80.52 349	82.20 365	89.72 388	55.14 439	95.93 375	73.93 389	66.83 465	90.12 443

CMPMVS	59.16 21	80.52 402	79.20 403	84.48 428	83.98 466	67.63 457	89.95 399	93.84 321	64.79 472	66.81 470	91.14 342	57.93 423	95.17 404	76.25 364	88.10 308	90.65 435
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
UnsupCasMVSNet_bld		76.23 431	73.27 435	85.09 422	83.79 467	72.92 409	85.65 455	93.47 335	71.52 452	68.84 467	79.08 472	49.77 456	93.21 437	66.81 438	60.52 476	89.13 456

FE-MVSNET		78.19 423	76.03 428	84.69 426	83.70 468	73.31 405	90.58 378	90.00 430	77.11 399	71.91 459	85.47 445	55.53 434	91.94 454	59.69 464	70.24 448	88.83 458

PM-MVS		78.11 424	76.12 427	84.09 433	83.54 469	70.08 444	88.97 417	85.27 465	79.93 355	74.73 446	86.43 436	34.70 481	93.48 433	79.43 331	72.06 442	88.72 459

dongtai		58.82 452	58.24 450	60.56 470	83.13 470	45.09 494	82.32 472	48.22 500	67.61 464	61.70 477	69.15 481	38.75 476	76.05 489	32.01 488	41.31 488	60.55 485

DSMNet-mixed		76.94 428	76.29 426	78.89 451	83.10 471	56.11 487	87.78 435	79.77 478	60.65 477	75.64 440	88.71 406	61.56 394	88.34 473	60.07 462	89.29 291	92.21 404

new_pmnet		72.15 437	70.13 440	78.20 453	82.95 472	65.68 462	83.91 466	82.40 473	62.94 475	64.47 472	79.82 471	42.85 473	86.26 478	57.41 470	74.44 436	82.65 473

new-patchmatchnet		76.41 430	75.17 432	80.13 448	82.65 473	59.61 479	87.66 439	91.08 401	78.23 386	69.85 465	83.22 456	54.76 442	91.63 457	64.14 449	64.89 470	89.16 454

ttmdpeth		76.55 429	74.64 434	82.29 444	82.25 474	67.81 455	89.76 401	85.69 461	70.35 458	75.76 439	91.69 321	46.88 465	89.77 466	66.16 439	63.23 473	89.30 450

WB-MVS		67.92 442	67.49 444	69.21 465	81.09 475	41.17 495	88.03 431	78.00 485	73.50 438	62.63 474	83.11 459	63.94 376	86.52 476	25.66 491	51.45 483	79.94 476

SSC-MVS		67.06 443	66.56 445	68.56 467	80.54 476	40.06 497	87.77 436	77.37 488	72.38 448	61.75 476	82.66 465	63.37 379	86.45 477	24.48 492	48.69 486	79.16 478

APD_test1		69.04 440	66.26 446	77.36 456	80.51 477	62.79 474	85.46 457	83.51 470	54.11 482	59.14 479	84.79 449	23.40 488	89.61 467	55.22 472	70.24 448	79.68 477

ambc				83.06 437	79.99 478	63.51 472	77.47 483	92.86 350		74.34 449	84.45 450	28.74 482	95.06 408	73.06 394	68.89 456	90.61 436

test_fmvs3		77.67 426	77.16 421	79.22 450	79.52 479	61.14 475	92.34 324	91.64 388	73.98 433	78.86 412	86.59 433	27.38 485	87.03 474	88.12 176	75.97 433	89.50 447

TDRefinement		79.81 411	77.34 417	87.22 387	79.24 480	75.48 381	93.12 287	92.03 375	76.45 405	75.01 443	91.58 328	49.19 459	96.44 351	70.22 413	69.18 454	89.75 446

MVStest1		72.91 436	69.70 441	82.54 440	78.14 481	73.05 408	88.21 428	86.21 457	60.69 476	64.70 471	90.53 362	46.44 467	85.70 479	58.78 467	53.62 481	88.87 457

usedtu_dtu_shiyan2		74.72 433	71.30 438	84.98 423	77.78 482	70.58 441	91.85 341	90.76 413	67.24 466	68.06 469	82.17 467	37.13 478	92.78 443	60.69 459	66.03 466	91.59 416

kuosan		53.51 454	53.30 457	54.13 474	76.06 483	45.36 493	80.11 479	48.36 499	59.63 478	54.84 480	63.43 487	37.41 477	62.07 494	20.73 494	39.10 489	54.96 488

pmmvs3		71.81 439	68.71 442	81.11 445	75.86 484	70.42 442	86.74 447	83.66 469	58.95 479	68.64 468	80.89 470	36.93 479	89.52 468	63.10 452	63.59 471	83.39 469

mvsany_test3		74.95 432	73.26 436	80.02 449	74.61 485	63.16 473	85.53 456	78.42 482	74.16 431	74.89 445	86.46 434	36.02 480	89.09 470	82.39 267	66.91 464	87.82 466

DeepMVS_CX				56.31 473	74.23 486	51.81 489		56.67 497	44.85 485	48.54 485	75.16 476	27.87 484	58.74 495	40.92 485	52.22 482	58.39 487

test_f		71.95 438	70.87 439	75.21 457	74.21 487	59.37 480	85.07 460	85.82 460	65.25 471	70.42 464	83.13 457	23.62 486	82.93 485	78.32 341	71.94 444	83.33 470

test_vis3_rt		65.12 445	62.60 447	72.69 459	71.44 488	60.71 476	87.17 443	65.55 492	63.80 474	53.22 482	65.65 485	14.54 495	89.44 469	76.65 358	65.38 468	67.91 483

FPMVS		64.63 446	62.55 448	70.88 460	70.80 489	56.71 482	84.42 464	84.42 467	51.78 483	49.57 483	81.61 468	23.49 487	81.48 486	40.61 486	76.25 432	74.46 479

testf1		59.54 449	56.11 453	69.85 463	69.28 490	56.61 484	80.37 477	76.55 489	42.58 487	45.68 486	75.61 473	11.26 496	84.18 481	43.20 483	60.44 477	68.75 481

APD_test2		59.54 449	56.11 453	69.85 463	69.28 490	56.61 484	80.37 477	76.55 489	42.58 487	45.68 486	75.61 473	11.26 496	84.18 481	43.20 483	60.44 477	68.75 481

PMMVS2		59.60 448	56.40 451	69.21 465	68.83 492	46.58 491	73.02 487	77.48 487	55.07 481	49.21 484	72.95 480	17.43 493	80.04 487	49.32 478	44.33 487	80.99 475

wuyk23d		21.27 462	20.48 465	23.63 478	68.59 493	36.41 499	49.57 491	6.85 502	9.37 494	7.89 496	4.46 498	4.03 500	31.37 496	17.47 496	16.07 495	3.12 493

E-PMN		43.23 458	42.29 460	46.03 475	65.58 494	37.41 498	73.51 485	64.62 493	33.99 490	28.47 494	47.87 491	19.90 492	67.91 491	22.23 493	24.45 491	32.77 490

LCM-MVSNet		66.00 444	62.16 449	77.51 455	64.51 495	58.29 481	83.87 467	90.90 409	48.17 484	54.69 481	73.31 479	16.83 494	86.75 475	65.47 441	61.67 475	87.48 467

EMVS		42.07 459	41.12 461	44.92 476	63.45 496	35.56 500	73.65 484	63.48 494	33.05 491	26.88 495	45.45 492	21.27 490	67.14 492	19.80 495	23.02 493	32.06 491

MVE	39.65 23	43.39 457	38.59 463	57.77 471	56.52 497	48.77 490	55.38 489	58.64 496	29.33 492	28.96 493	52.65 489	4.68 499	64.62 493	28.11 490	33.07 490	59.93 486
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		58.88 451	54.22 456	72.86 458	56.50 498	56.67 483	80.75 476	86.00 459	73.09 443	37.39 490	64.63 486	22.17 489	79.49 488	43.51 482	23.96 492	82.43 474

test_method		50.52 456	48.47 458	56.66 472	52.26 499	18.98 503	41.51 492	81.40 475	10.10 493	44.59 488	75.01 477	28.51 483	68.16 490	53.54 474	49.31 485	82.83 472

PMVS	47.18 22	52.22 455	48.46 459	63.48 469	45.72 500	46.20 492	73.41 486	78.31 483	41.03 489	30.06 492	65.68 484	6.05 498	83.43 484	30.04 489	65.86 467	60.80 484
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		35.64 460	39.24 462	24.84 477	14.87 501	23.90 502	62.71 488	51.51 498	6.58 495	36.66 491	62.08 488	44.37 471	30.34 497	52.40 475	22.00 494	20.27 492

testmvs		8.92 463	11.52 466	1.12 480	1.06 502	0.46 505	86.02 451	0.65 503	0.62 496	2.74 497	9.52 496	0.31 502	0.45 499	2.38 497	0.39 496	2.46 495

test123		8.76 464	11.22 467	1.39 479	0.85 503	0.97 504	85.76 454	0.35 504	0.54 497	2.45 498	8.14 497	0.60 501	0.48 498	2.16 498	0.17 497	2.71 494

mmdepth		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

monomultidepth		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

test_blank		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

eth-test2					0.00 504

eth-test					0.00 504

uanet_test		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

DCPMVS		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

cdsmvs_eth3d_5k		22.14 461	29.52 464	0.00 481	0.00 504	0.00 506	0.00 493	95.76 195	0.00 499	0.00 500	94.29 223	75.66 220	0.00 500	0.00 499	0.00 498	0.00 496

pcd_1.5k_mvsjas		6.64 466	8.86 469	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	79.70 156	0.00 500	0.00 499	0.00 498	0.00 496

sosnet-low-res		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

sosnet		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uncertanet		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

Regformer		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

ab-mvs-re		7.82 465	10.43 468	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	93.88 244	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

uanet		0.00 467	0.00 470	0.00 481	0.00 504	0.00 506	0.00 493	0.00 505	0.00 499	0.00 500	0.00 499	0.00 503	0.00 500	0.00 499	0.00 498	0.00 496

TestfortrainingZip							97.32 10

WAC-MVS						64.08 469								59.14 465

PC_three_1452									82.47 303	97.09 20	97.07 72	92.72 1	98.04 197	92.70 80	99.02 12	98.86 16

test_241102_TWO								97.44 21	90.31 41	97.62 8	98.07 20	91.46 12	99.58 14	95.66 30	99.12 6	98.98 10

test_0728_THIRD									90.75 29	97.04 22	98.05 25	92.09 8	99.55 20	95.64 32	99.13 3	99.13 2

GSMVS																96.12 224

sam_mvs1												71.70 280				96.12 224

sam_mvs												70.60 294

MTGPA								96.97 65

test_post1							88.00 432				9.81 495	69.31 318	95.53 393	76.65 358

test_post											10.29 494	70.57 298	95.91 378

patchmatchnet-post											83.76 452	71.53 281	96.48 347

MTMP							96.16 60	60.64 495

test9_res														91.91 109	98.71 36	98.07 82

agg_prior2														90.54 134	98.68 41	98.27 63

test_prior4						85.96 57	94.11 222

test_prior2							94.12 220		87.67 154	92.63 108	96.39 103	86.62 44		91.50 118	98.67 44

旧先验2							93.36 274		71.25 454	94.37 60			97.13 296	86.74 198

新几何2							93.11 289

无先验							93.28 282	96.26 139	73.95 434				99.05 66	80.56 306		96.59 203

原ACMM2							92.94 300

testdata2													98.75 115	78.30 342

segment_acmp												87.16 39

testdata1							92.15 332		87.94 139

plane_prior5								96.22 144					98.12 177	88.15 173	89.99 274	94.63 285

plane_prior4											94.86 194

plane_prior3						82.75 162			90.26 47	86.91 242

plane_prior2							95.85 93		90.81 27

plane_prior						82.73 165	95.21 141		89.66 68						89.88 279

n2								0.00 505

nn								0.00 505

door-mid								85.49 462

test11								96.57 111

door								85.33 464

HQP5-MVS						81.56 202

BP-MVS														87.11 195

HQP4-MVS										85.43 288			97.96 213			94.51 295

HQP3-MVS								96.04 170							89.77 283

HQP2-MVS												73.83 251

MDTV_nov1_ep13_2view						55.91 488	87.62 440		73.32 440	84.59 310		70.33 301		74.65 381		95.50 252

ACMMP++_ref															87.47 319

ACMMP++															88.01 311

Test By Simon												80.02 145

High-resolution multi-view benchmark