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.

AdaColmap		93.82 124	93.06 132	96.10 116	99.88 1	89.07 170	98.33 200	97.55 123	86.81 239	90.39 192	98.65 100	75.09 237	99.98 9	93.32 146	97.53 125	99.26 102

DP-MVS Recon		95.85 62	95.15 77	97.95 31	99.87 2	94.38 53	99.60 39	97.48 139	86.58 243	94.42 127	99.13 46	87.36 90	99.98 9	93.64 138	98.33 108	99.48 80

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 27	97.98 53	97.18 3	95.96 95	99.33 19	92.62 25	100.00 1	98.99 25	99.93 1	99.98 6

CNVR-MVS		98.46 1	98.38 1	98.72 9	99.80 4	96.19 15	99.80 16	97.99 52	97.05 6	99.41 4	99.59 2	92.89 24	100.00 1	98.99 25	99.90 7	99.96 10

MG-MVS		97.24 20	96.83 31	98.47 15	99.79 5	95.71 19	99.07 114	99.06 10	94.45 42	96.42 89	98.70 97	88.81 64	99.74 88	95.35 104	99.86 12	99.97 7

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 49	99.81 12	97.88 57	96.54 13	98.84 25	99.46 10	92.55 26	99.98 9	98.25 46	99.93 1	99.94 18

region2R		96.30 46	96.17 48	96.70 82	99.70 7	90.31 137	99.46 60	97.66 95	90.55 127	97.07 72	99.07 53	86.85 102	99.97 21	95.43 102	99.74 29	99.81 33

HFP-MVS		96.42 42	96.26 42	96.90 70	99.69 8	90.96 123	99.47 56	97.81 68	90.54 128	96.88 74	99.05 56	87.57 82	99.96 28	95.65 95	99.72 31	99.78 38

ACMMPR		96.28 47	96.14 52	96.73 79	99.68 9	90.47 135	99.47 56	97.80 70	90.54 128	96.83 79	99.03 58	86.51 113	99.95 31	95.65 95	99.72 31	99.75 46

ZD-MVS					99.67 10	93.28 72		97.61 110	87.78 215	97.41 61	99.16 38	90.15 52	99.56 105	98.35 41	99.70 35

CP-MVS		96.22 48	96.15 51	96.42 99	99.67 10	89.62 161	99.70 27	97.61 110	90.07 143	96.00 94	99.16 38	87.43 85	99.92 40	96.03 91	99.72 31	99.70 52

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 31	99.72 24	97.47 141	93.95 50	99.07 16	99.46 10	93.18 21	99.97 21	99.64 7	99.82 19	99.69 55
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				98.77 8	99.66 12	96.37 14	99.72 24	97.68 90					99.98 9	99.64 7	99.82 19	99.96 10

test0726					99.66 12	95.20 31	99.77 18	97.70 86	93.95 50	99.35 7	99.54 3	93.18 21

CPTT-MVS		94.60 102	94.43 91	95.09 154	99.66 12	86.85 226	99.44 63	97.47 141	83.22 299	94.34 130	98.96 68	82.50 179	99.55 106	94.81 117	99.50 54	98.88 136

MSLP-MVS++		97.50 17	97.45 17	97.63 39	99.65 16	93.21 73	99.70 27	98.13 42	94.61 37	97.78 56	99.46 10	89.85 54	99.81 79	97.97 52	99.91 6	99.88 26

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 18				99.19 32	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 26	99.77 18	97.72 81	94.17 45	99.30 9	99.54 3	93.32 18	99.98 9	99.70 4	99.81 23	99.99 1

IU-MVS					99.63 18	95.38 23		97.73 80	95.54 28	99.54 3				99.69 6	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 26		97.72 81	94.16 47	99.30 9	99.49 9	93.32 18	99.98 9

PAPR		96.35 43	95.82 58	97.94 32	99.63 18	94.19 57	99.42 68	97.55 123	92.43 84	93.82 140	99.12 48	87.30 92	99.91 45	94.02 130	99.06 76	99.74 47

XVS		96.47 41	96.37 40	96.77 75	99.62 22	90.66 131	99.43 66	97.58 118	92.41 87	96.86 75	98.96 68	87.37 87	99.87 58	95.65 95	99.43 60	99.78 38

X-MVStestdata		90.69 197	88.66 220	96.77 75	99.62 22	90.66 131	99.43 66	97.58 118	92.41 87	96.86 75	29.59 408	87.37 87	99.87 58	95.65 95	99.43 60	99.78 38

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 23	99.55 45	97.68 90	93.01 72	99.23 11	99.45 14	95.12 8	99.98 9	99.25 18	99.92 3	99.97 7

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 88					99.98 9	99.55 12	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 88					99.98 9	99.55 12	99.83 15	99.96 10

DeepC-MVS_fast	93.52 2	97.16 24	96.84 29	98.13 25	99.61 24	94.45 50	98.85 136	97.64 103	96.51 16	95.88 98	99.39 18	87.35 91	99.99 5	96.61 79	99.69 36	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_one_0601					99.59 28	94.89 35		97.64 103	93.14 71	98.93 22	99.45 14	93.45 17

CDPH-MVS		96.56 39	96.18 45	97.70 37	99.59 28	93.92 61	99.13 109	97.44 147	89.02 172	97.90 54	99.22 27	88.90 63	99.49 112	94.63 123	99.79 27	99.68 56

test_prior				97.01 61	99.58 30	91.77 100		97.57 121					99.49 112			99.79 36

APDe-MVS		97.53 14	97.47 15	97.70 37	99.58 30	93.63 65	99.56 44	97.52 131	93.59 65	98.01 51	99.12 48	90.80 40	99.55 106	99.26 17	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
mPP-MVS		95.90 61	95.75 63	96.38 102	99.58 30	89.41 165	99.26 86	97.41 151	90.66 121	94.82 119	98.95 71	86.15 121	99.98 9	95.24 108	99.64 40	99.74 47

TEST9					99.57 33	93.17 74	99.38 72	97.66 95	89.57 157	98.39 36	99.18 35	90.88 38	99.66 94

train_agg		97.20 23	97.08 23	97.57 43	99.57 33	93.17 74	99.38 72	97.66 95	90.18 137	98.39 36	99.18 35	90.94 35	99.66 94	98.58 36	99.85 13	99.88 26

test_8					99.55 35	93.07 77	99.37 75	97.64 103	90.18 137	98.36 38	99.19 32	90.94 35	99.64 100

test_part2					99.54 36	95.42 21				98.13 43

MSP-MVS		97.77 9	98.18 2	96.53 93	99.54 36	90.14 143	99.41 69	97.70 86	95.46 30	98.60 30	99.19 32	95.71 4	99.49 112	98.15 48	99.85 13	99.95 15
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
agg_prior					99.54 36	92.66 87		97.64 103		97.98 52			99.61 102

CSCG		94.87 91	94.71 85	95.36 143	99.54 36	86.49 231	99.34 78	98.15 40	82.71 310	90.15 195	99.25 23	89.48 57	99.86 63	94.97 115	98.82 91	99.72 50

HPM-MVS++		97.72 11	97.59 13	98.14 24	99.53 40	94.76 43	99.19 91	97.75 76	95.66 24	98.21 41	99.29 20	91.10 32	99.99 5	97.68 57	99.87 9	99.68 56

APD-MVS		96.95 29	96.72 32	97.63 39	99.51 41	93.58 66	99.16 97	97.44 147	90.08 142	98.59 31	99.07 53	89.06 60	99.42 123	97.92 53	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
FOURS1					99.50 42	88.94 177	99.55 45	97.47 141	91.32 110	98.12 45

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 22	99.29 82	97.72 81	94.50 39	98.64 29	99.54 3	93.32 18	99.97 21	99.58 10	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PGM-MVS		95.85 62	95.65 68	96.45 97	99.50 42	89.77 158	98.22 208	98.90 13	89.19 167	96.74 82	98.95 71	85.91 125	99.92 40	93.94 131	99.46 56	99.66 60

GST-MVS		95.97 56	95.66 66	96.90 70	99.49 45	91.22 110	99.45 62	97.48 139	89.69 151	95.89 97	98.72 93	86.37 116	99.95 31	94.62 124	99.22 71	99.52 76

MP-MVS		96.00 53	95.82 58	96.54 92	99.47 46	90.13 145	99.36 76	97.41 151	90.64 124	95.49 109	98.95 71	85.51 130	99.98 9	96.00 92	99.59 50	99.52 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.09 51	95.81 60	96.95 69	99.42 47	91.19 112	99.55 45	97.53 127	89.72 150	95.86 100	98.94 74	86.59 109	99.97 21	95.13 109	99.56 51	99.68 56

SR-MVS		96.13 50	96.16 50	96.07 117	99.42 47	89.04 171	98.59 169	97.33 158	90.44 131	96.84 77	99.12 48	86.75 104	99.41 126	97.47 60	99.44 59	99.76 45

PAPM_NR		95.43 74	95.05 81	96.57 91	99.42 47	90.14 143	98.58 171	97.51 133	90.65 123	92.44 157	98.90 78	87.77 81	99.90 50	90.88 171	99.32 65	99.68 56

9.14			96.87 27		99.34 50		99.50 52	97.49 138	89.41 163	98.59 31	99.43 16	89.78 55	99.69 91	98.69 30	99.62 45

save fliter					99.34 50	93.85 63	99.65 36	97.63 107	95.69 22

PHI-MVS		96.65 37	96.46 38	97.21 55	99.34 50	91.77 100	99.70 27	98.05 46	86.48 248	98.05 48	99.20 30	89.33 58	99.96 28	98.38 39	99.62 45	99.90 22

test12				97.83 34	99.33 53	94.45 50		97.55 123		97.56 57		88.60 66	99.50 111		99.71 34	99.55 73

SMA-MVS		97.24 20	96.99 24	98.00 30	99.30 54	94.20 56	99.16 97	97.65 102	89.55 159	99.22 13	99.52 8	90.34 49	99.99 5	98.32 43	99.83 15	99.82 32
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
MTAPA		96.09 51	95.80 61	96.96 68	99.29 55	91.19 112	97.23 268	97.45 144	92.58 81	94.39 129	99.24 25	86.43 115	99.99 5	96.22 85	99.40 63	99.71 51

HPM-MVS		95.41 76	95.22 75	95.99 122	99.29 55	89.14 168	99.17 96	97.09 183	87.28 228	95.40 110	98.48 115	84.93 140	99.38 128	95.64 99	99.65 38	99.47 81
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		94.67 100	94.30 92	95.79 129	99.25 57	88.13 195	98.41 189	98.67 22	90.38 133	91.43 173	98.72 93	82.22 188	99.95 31	93.83 135	95.76 158	99.29 99
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_3200maxsize		95.64 71	95.65 68	95.62 136	99.24 58	87.80 201	98.42 187	97.22 166	88.93 177	96.64 87	98.98 63	85.49 131	99.36 130	96.68 76	99.27 69	99.70 52

SR-MVS-dyc-post		95.75 68	95.86 57	95.41 142	99.22 59	87.26 221	98.40 192	97.21 167	89.63 153	96.67 85	98.97 64	86.73 106	99.36 130	96.62 77	99.31 66	99.60 68

RE-MVS-def			95.70 64		99.22 59	87.26 221	98.40 192	97.21 167	89.63 153	96.67 85	98.97 64	85.24 137		96.62 77	99.31 66	99.60 68

patch_mono-2		97.10 26	97.97 8	94.49 176	99.21 61	83.73 291	99.62 38	98.25 32	95.28 32	99.38 6	98.91 77	92.28 27	99.94 34	99.61 9	99.22 71	99.78 38

API-MVS		94.78 94	94.18 98	96.59 88	99.21 61	90.06 150	98.80 142	97.78 73	83.59 294	93.85 138	99.21 29	83.79 153	99.97 21	92.37 158	99.00 80	99.74 47

PLC	91.07 3	94.23 111	94.01 102	94.87 162	99.17 63	87.49 210	99.25 87	96.55 213	88.43 192	91.26 177	98.21 127	85.92 123	99.86 63	89.77 187	97.57 122	97.24 208
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
EI-MVSNet-Vis-set		95.76 67	95.63 70	96.17 113	99.14 64	90.33 136	98.49 180	97.82 65	91.92 96	94.75 121	98.88 82	87.06 97	99.48 116	95.40 103	97.17 135	98.70 153

TSAR-MVS + MP.		97.44 18	97.46 16	97.39 49	99.12 65	93.49 70	98.52 174	97.50 136	94.46 40	98.99 18	98.64 101	91.58 29	99.08 148	98.49 37	99.83 15	99.60 68
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		97.22 22	96.92 25	98.12 27	99.11 66	94.88 36	99.44 63	97.45 144	89.60 155	98.70 27	99.42 17	90.42 46	99.72 89	98.47 38	99.65 38	99.77 43

HPM-MVS_fast		94.89 88	94.62 86	95.70 132	99.11 66	88.44 191	99.14 106	97.11 179	85.82 256	95.69 105	98.47 116	83.46 158	99.32 135	93.16 148	99.63 44	99.35 93

MAR-MVS		94.43 108	94.09 100	95.45 140	99.10 68	87.47 211	98.39 196	97.79 72	88.37 194	94.02 135	99.17 37	78.64 222	99.91 45	92.48 157	98.85 90	98.96 126
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
114514_t		94.06 114	93.05 133	97.06 59	99.08 69	92.26 95	98.97 128	97.01 191	82.58 312	92.57 155	98.22 125	80.68 204	99.30 136	89.34 193	99.02 79	99.63 65

EI-MVSNet-UG-set		95.43 74	95.29 73	95.86 127	99.07 70	89.87 155	98.43 186	97.80 70	91.78 98	94.11 133	98.77 87	86.25 119	99.48 116	94.95 116	96.45 144	98.22 180

原ACMM1				96.18 111	99.03 71	90.08 146		97.63 107	88.98 173	97.00 73	98.97 64	88.14 75	99.71 90	88.23 204	99.62 45	98.76 150

SD-MVS		97.51 16	97.40 18	97.81 35	99.01 72	93.79 64	99.33 79	97.38 154	93.73 61	98.83 26	99.02 60	90.87 39	99.88 54	98.69 30	99.74 29	99.77 43
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
旧先验1					98.97 73	92.90 85		97.74 77			99.15 41	91.05 34			99.33 64	99.60 68

LS3D		90.19 206	88.72 218	94.59 175	98.97 73	86.33 239	96.90 280	96.60 207	74.96 362	84.06 252	98.74 90	75.78 234	99.83 73	74.93 325	97.57 122	97.62 198

CNLPA		93.64 131	92.74 140	96.36 104	98.96 75	90.01 153	99.19 91	95.89 268	86.22 251	89.40 203	98.85 83	80.66 205	99.84 69	88.57 200	96.92 138	99.24 103

MP-MVS-pluss		95.80 64	95.30 72	97.29 51	98.95 76	92.66 87	98.59 169	97.14 175	88.95 175	93.12 149	99.25 23	85.62 127	99.94 34	96.56 81	99.48 55	99.28 100
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
新几何1				97.40 48	98.92 77	92.51 92		97.77 75	85.52 261	96.69 84	99.06 55	88.08 76	99.89 53	84.88 242	99.62 45	99.79 36

DP-MVS		88.75 236	86.56 255	95.34 144	98.92 77	87.45 212	97.64 253	93.52 350	70.55 374	81.49 293	97.25 164	74.43 243	99.88 54	71.14 348	94.09 174	98.67 155

TSAR-MVS + GP.		96.95 29	96.91 26	97.07 58	98.88 79	91.62 103	99.58 42	96.54 214	95.09 34	96.84 77	98.63 103	91.16 30	99.77 85	99.04 24	96.42 145	99.81 33

CANet		97.00 28	96.49 36	98.55 12	98.86 80	96.10 16	99.83 10	97.52 131	95.90 19	97.21 67	98.90 78	82.66 178	99.93 38	98.71 29	98.80 92	99.63 65

dcpmvs_2		95.67 70	96.18 45	94.12 193	98.82 81	84.22 284	97.37 261	95.45 294	90.70 120	95.77 103	98.63 103	90.47 44	98.68 165	99.20 20	99.22 71	99.45 84

ACMMP_NAP		96.59 38	96.18 45	97.81 35	98.82 81	93.55 67	98.88 135	97.59 116	90.66 121	97.98 52	99.14 44	86.59 109	100.00 1	96.47 83	99.46 56	99.89 25

PVSNet_BlendedMVS		93.36 139	93.20 129	93.84 204	98.77 83	91.61 104	99.47 56	98.04 48	91.44 106	94.21 131	92.63 279	83.50 156	99.87 58	97.41 61	83.37 276	90.05 338

PVSNet_Blended		95.94 59	95.66 66	96.75 77	98.77 83	91.61 104	99.88 4	98.04 48	93.64 64	94.21 131	97.76 138	83.50 156	99.87 58	97.41 61	97.75 120	98.79 146

DeepPCF-MVS	93.56 1	96.55 40	97.84 10	92.68 227	98.71 85	78.11 349	99.70 27	97.71 85	98.18 1	97.36 63	99.76 1	90.37 48	99.94 34	99.27 16	99.54 53	99.99 1

EPNet		96.82 32	96.68 34	97.25 54	98.65 86	93.10 76	99.48 54	98.76 15	96.54 13	97.84 55	98.22 125	87.49 84	99.66 94	95.35 104	97.78 119	99.00 122
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
OMC-MVS		93.90 121	93.62 117	94.73 169	98.63 87	87.00 224	98.04 228	96.56 212	92.19 92	92.46 156	98.73 91	79.49 214	99.14 145	92.16 160	94.34 173	98.03 187

MVS_111021_HR		96.69 35	96.69 33	96.72 81	98.58 88	91.00 122	99.14 106	99.45 1	93.86 56	95.15 115	98.73 91	88.48 67	99.76 86	97.23 65	99.56 51	99.40 88

test_yl		95.27 80	94.60 87	97.28 52	98.53 89	92.98 80	99.05 118	98.70 19	86.76 240	94.65 124	97.74 140	87.78 79	99.44 119	95.57 100	92.61 189	99.44 85

DCV-MVSNet		95.27 80	94.60 87	97.28 52	98.53 89	92.98 80	99.05 118	98.70 19	86.76 240	94.65 124	97.74 140	87.78 79	99.44 119	95.57 100	92.61 189	99.44 85

TAPA-MVS	87.50 9	90.35 201	89.05 211	94.25 188	98.48 91	85.17 271	98.42 187	96.58 211	82.44 317	87.24 221	98.53 107	82.77 173	98.84 156	59.09 383	97.88 115	98.72 151
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.32 92	91.21 111	98.08 225	97.58 118	83.74 290	95.87 99	99.02 60	86.74 105			99.64 40	99.81 33

MM		97.76 10	97.39 19	98.86 5	98.30 93	96.83 7	99.81 12	99.13 9	97.66 2	98.29 40	98.96 68	85.84 126	99.90 50	99.72 3	98.80 92	99.85 30

DPM-MVS		97.86 8	97.25 21	99.68 1	98.25 94	99.10 1	99.76 21	97.78 73	96.61 12	98.15 42	99.53 7	93.62 16	100.00 1	91.79 163	99.80 26	99.94 18

LFMVS		92.23 167	90.84 180	96.42 99	98.24 95	91.08 119	98.24 207	96.22 233	83.39 297	94.74 122	98.31 121	61.12 336	98.85 155	94.45 126	92.82 185	99.32 96

testdata				95.26 149	98.20 96	87.28 218		97.60 112	85.21 265	98.48 34	99.15 41	88.15 74	98.72 163	90.29 180	99.45 58	99.78 38

PatchMatch-RL		91.47 178	90.54 187	94.26 187	98.20 96	86.36 237	96.94 278	97.14 175	87.75 217	88.98 206	95.75 221	71.80 270	99.40 127	80.92 284	97.39 129	97.02 216

MVS_111021_LR		95.78 65	95.94 54	95.28 148	98.19 98	87.69 202	98.80 142	99.26 7	93.39 67	95.04 117	98.69 98	84.09 150	99.76 86	96.96 71	99.06 76	98.38 169

F-COLMAP		92.07 171	91.75 162	93.02 217	98.16 99	82.89 303	98.79 146	95.97 251	86.54 245	87.92 213	97.80 135	78.69 221	99.65 98	85.97 228	95.93 157	96.53 230

Anonymous202405211		88.84 230	87.03 249	94.27 186	98.14 100	84.18 285	98.44 185	95.58 287	76.79 356	89.34 204	96.88 188	53.42 365	99.54 108	87.53 212	87.12 242	99.09 117

VNet		95.08 85	94.26 93	97.55 44	98.07 101	93.88 62	98.68 155	98.73 18	90.33 134	97.16 71	97.43 156	79.19 216	99.53 109	96.91 73	91.85 205	99.24 103

CS-MVS-test		95.98 55	96.34 41	94.90 161	98.06 102	87.66 205	99.69 34	96.10 243	93.66 62	98.35 39	99.05 56	86.28 117	97.66 221	96.96 71	98.90 88	99.37 91

DELS-MVS		97.12 25	96.60 35	98.68 10	98.03 103	96.57 11	99.84 9	97.84 61	96.36 18	95.20 114	98.24 124	88.17 72	99.83 73	96.11 89	99.60 49	99.64 63
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	87.13 12	93.69 127	92.83 139	96.28 107	97.99 104	90.22 141	99.38 72	98.93 12	91.42 108	93.66 142	97.68 143	71.29 275	99.64 100	87.94 208	97.20 132	98.98 124

test_fmvsm_n_1920		97.08 27	97.55 14	95.67 134	97.94 105	89.61 162	99.93 2	98.48 24	97.08 5	99.08 15	99.13 46	88.17 72	99.93 38	99.11 23	99.06 76	97.47 201

cl22		89.57 218	88.79 217	91.91 241	97.94 105	87.62 206	97.98 231	96.51 215	85.03 270	82.37 276	91.79 291	83.65 154	96.50 276	85.96 229	77.89 303	91.61 291

CS-MVS		95.75 68	96.19 43	94.40 180	97.88 107	86.22 242	99.66 35	96.12 242	92.69 80	98.07 47	98.89 80	87.09 95	97.59 227	96.71 74	98.62 100	99.39 90

CHOSEN 280x420		96.80 33	96.85 28	96.66 85	97.85 108	94.42 52	94.76 329	98.36 29	92.50 83	95.62 107	97.52 151	97.92 1	97.38 239	98.31 44	98.80 92	98.20 182

thres200		93.69 127	92.59 144	96.97 67	97.76 109	94.74 44	99.35 77	99.36 2	89.23 165	91.21 179	96.97 181	83.42 159	98.77 158	85.08 238	90.96 223	97.39 203

HY-MVS	88.56 7	95.29 79	94.23 94	98.48 14	97.72 110	96.41 13	94.03 337	98.74 16	92.42 86	95.65 106	94.76 239	86.52 112	99.49 112	95.29 106	92.97 184	99.53 75

Anonymous20231211		84.72 298	82.65 309	90.91 263	97.71 111	84.55 280	97.28 264	96.67 202	66.88 387	79.18 319	90.87 309	58.47 344	96.60 267	82.61 271	74.20 330	91.59 293

tfpn200view9		93.43 136	92.27 149	96.90 70	97.68 112	94.84 39	99.18 93	99.36 2	88.45 189	90.79 182	96.90 185	83.31 160	98.75 160	84.11 254	90.69 225	97.12 210

thres400		93.39 138	92.27 149	96.73 79	97.68 112	94.84 39	99.18 93	99.36 2	88.45 189	90.79 182	96.90 185	83.31 160	98.75 160	84.11 254	90.69 225	96.61 225

thres100view900		93.34 140	92.15 152	96.90 70	97.62 114	94.84 39	99.06 117	99.36 2	87.96 210	90.47 190	96.78 193	83.29 162	98.75 160	84.11 254	90.69 225	97.12 210

thres600view7		93.18 145	92.00 155	96.75 77	97.62 114	94.92 34	99.07 114	99.36 2	87.96 210	90.47 190	96.78 193	83.29 162	98.71 164	82.93 268	90.47 229	96.61 225

WTY-MVS		95.97 56	95.11 79	98.54 13	97.62 114	96.65 9	99.44 63	98.74 16	92.25 91	95.21 113	98.46 118	86.56 111	99.46 118	95.00 114	92.69 188	99.50 79

fmvsm_l_conf0.5_n_a		97.70 12	97.80 11	97.42 46	97.59 117	92.91 84	99.86 5	98.04 48	96.70 10	99.58 2	99.26 21	90.90 37	99.94 34	99.57 11	98.66 99	99.40 88

Anonymous20240529		87.66 256	85.58 269	93.92 201	97.59 117	85.01 274	98.13 216	97.13 177	66.69 388	88.47 210	96.01 217	55.09 359	99.51 110	87.00 215	84.12 267	97.23 209

HyFIR lowres test		93.68 129	93.29 127	94.87 162	97.57 119	88.04 197	98.18 212	98.47 25	87.57 223	91.24 178	95.05 233	85.49 131	97.46 234	93.22 147	92.82 185	99.10 116

sasdasda		95.02 86	93.96 107	98.20 21	97.53 120	95.92 17	98.71 150	96.19 236	91.78 98	95.86 100	98.49 112	79.53 212	99.03 149	96.12 87	91.42 219	99.66 60

canonicalmvs		95.02 86	93.96 107	98.20 21	97.53 120	95.92 17	98.71 150	96.19 236	91.78 98	95.86 100	98.49 112	79.53 212	99.03 149	96.12 87	91.42 219	99.66 60

fmvsm_l_conf0.5_n		97.65 13	97.72 12	97.41 47	97.51 122	92.78 86	99.85 8	98.05 46	96.78 8	99.60 1	99.23 26	90.42 46	99.92 40	99.55 12	98.50 104	99.55 73

iter_conf05_11		94.23 111	93.49 120	96.46 95	97.51 122	91.32 109	99.96 1	94.31 336	95.62 26	99.32 8	99.22 27	57.79 346	98.59 171	98.00 50	99.64 40	99.46 82

bld_raw_dy_0_64		91.37 182	89.75 196	96.23 108	97.51 122	90.58 133	99.16 97	88.98 388	95.64 25	87.18 223	99.20 30	57.19 350	98.66 166	98.00 50	84.86 259	99.46 82

ETVMVS		94.50 106	93.90 111	96.31 106	97.48 125	92.98 80	99.07 114	97.86 59	88.09 205	94.40 128	96.90 185	88.35 69	97.28 243	90.72 176	92.25 199	98.66 158

CHOSEN 1792x2688		94.35 109	93.82 113	95.95 124	97.40 126	88.74 185	98.41 189	98.27 31	92.18 93	91.43 173	96.40 204	78.88 217	99.81 79	93.59 139	97.81 116	99.30 98

SteuartSystems-ACMMP		97.25 19	97.34 20	97.01 61	97.38 127	91.46 107	99.75 22	97.66 95	94.14 49	98.13 43	99.26 21	92.16 28	99.66 94	97.91 54	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
fmvsm_s_conf0.5_n		96.19 49	96.49 36	95.30 147	97.37 128	89.16 167	99.86 5	98.47 25	95.68 23	98.87 23	99.15 41	82.44 185	99.92 40	99.14 21	97.43 128	96.83 221

alignmvs		95.77 66	95.00 82	98.06 29	97.35 129	95.68 20	99.71 26	97.50 136	91.50 104	96.16 93	98.61 105	86.28 117	99.00 151	96.19 86	91.74 207	99.51 78

PS-MVSNAJ		96.87 31	96.40 39	98.29 19	97.35 129	97.29 5	99.03 120	97.11 179	95.83 20	98.97 20	99.14 44	82.48 181	99.60 103	98.60 33	99.08 74	98.00 188

testing222		94.48 107	94.00 103	95.95 124	97.30 131	92.27 94	98.82 139	97.92 55	89.20 166	94.82 119	97.26 162	87.13 94	97.32 242	91.95 161	91.56 211	98.25 176

MVS_0304		97.53 14	97.15 22	98.67 11	97.30 131	96.52 12	99.60 39	98.88 14	97.14 4	97.21 67	98.94 74	86.89 101	99.91 45	99.43 15	98.91 87	99.59 72

EPNet_dtu		92.28 165	92.15 152	92.70 226	97.29 133	84.84 276	98.64 161	97.82 65	92.91 77	93.02 151	97.02 179	85.48 133	95.70 321	72.25 345	94.89 168	97.55 200
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVSTER		92.71 153	92.32 147	93.86 203	97.29 133	92.95 83	99.01 123	96.59 208	90.09 141	85.51 238	94.00 249	94.61 15	96.56 271	90.77 175	83.03 278	92.08 279

EPMVS		92.59 158	91.59 164	95.59 138	97.22 135	90.03 151	91.78 357	98.04 48	90.42 132	91.66 167	90.65 317	86.49 114	97.46 234	81.78 279	96.31 148	99.28 100

testing11		95.33 78	94.98 83	96.37 103	97.20 136	92.31 93	99.29 82	97.68 90	90.59 125	94.43 126	97.20 167	90.79 41	98.60 169	95.25 107	92.38 193	98.18 183

testing99		94.88 89	94.45 89	96.17 113	97.20 136	91.91 98	99.20 90	97.66 95	89.95 145	93.68 141	97.06 176	90.28 50	98.50 172	93.52 140	91.54 213	98.12 185

testing91		94.88 89	94.44 90	96.21 109	97.19 138	91.90 99	99.23 88	97.66 95	89.91 146	93.66 142	97.05 178	90.21 51	98.50 172	93.52 140	91.53 216	98.25 176

test_fmvs1		92.35 162	92.94 137	90.57 273	97.19 138	75.43 358	99.55 45	94.97 314	95.20 33	96.82 80	97.57 150	59.59 341	99.84 69	97.30 63	98.29 111	96.46 232

tpmvs		89.16 222	87.76 236	93.35 211	97.19 138	84.75 278	90.58 372	97.36 156	81.99 322	84.56 245	89.31 345	83.98 152	98.17 186	74.85 327	90.00 232	97.12 210

DeepC-MVS	91.02 4	94.56 105	93.92 110	96.46 95	97.16 141	90.76 127	98.39 196	97.11 179	93.92 52	88.66 208	98.33 120	78.14 224	99.85 67	95.02 112	98.57 102	98.78 148
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
iter_conf05		93.48 133	93.18 130	94.39 183	97.15 142	94.17 58	99.30 81	92.97 354	92.38 90	86.70 230	95.42 227	95.67 5	96.59 268	94.67 122	84.32 265	92.39 262

PVSNet_Blended_VisFu		94.67 100	94.11 99	96.34 105	97.14 143	91.10 117	99.32 80	97.43 149	92.10 95	91.53 172	96.38 207	83.29 162	99.68 92	93.42 145	96.37 146	98.25 176

h-mvs33		92.47 161	91.95 157	94.05 197	97.13 144	85.01 274	98.36 198	98.08 44	93.85 57	96.27 91	96.73 195	83.19 165	99.43 122	95.81 93	68.09 362	97.70 194

miper_enhance_ethall		90.33 202	89.70 197	92.22 233	97.12 145	88.93 179	98.35 199	95.96 253	88.60 184	83.14 261	92.33 281	87.38 86	96.18 299	86.49 223	77.89 303	91.55 294

xiu_mvs_v2_base		96.66 36	96.17 48	98.11 28	97.11 146	96.96 6	99.01 123	97.04 186	95.51 29	98.86 24	99.11 52	82.19 189	99.36 130	98.59 35	98.14 112	98.00 188

VDD-MVS		91.24 186	90.18 191	94.45 179	97.08 147	85.84 258	98.40 192	96.10 243	86.99 231	93.36 146	98.16 128	54.27 362	99.20 138	96.59 80	90.63 228	98.31 175

UGNet		91.91 173	90.85 179	95.10 153	97.06 148	88.69 186	98.01 229	98.24 34	92.41 87	92.39 158	93.61 260	60.52 338	99.68 92	88.14 205	97.25 131	96.92 219
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
baseline1		92.61 157	91.28 170	96.58 89	97.05 149	94.63 47	97.72 247	96.20 234	89.82 148	88.56 209	96.85 189	86.85 102	97.82 207	88.42 201	80.10 294	97.30 205

CANet_DTU		94.31 110	93.35 124	97.20 56	97.03 150	94.71 45	98.62 163	95.54 289	95.61 27	97.21 67	98.47 116	71.88 268	99.84 69	88.38 202	97.46 127	97.04 215

MSDG		88.29 245	86.37 257	94.04 198	96.90 151	86.15 246	96.52 293	94.36 335	77.89 352	79.22 318	96.95 182	69.72 282	99.59 104	73.20 340	92.58 191	96.37 235

BH-w/o		92.32 163	91.79 160	93.91 202	96.85 152	86.18 244	99.11 111	95.74 277	88.13 203	84.81 242	97.00 180	77.26 229	97.91 200	89.16 198	98.03 113	97.64 195

AllTest		84.97 296	83.12 301	90.52 276	96.82 153	78.84 341	95.89 313	92.17 365	77.96 350	75.94 337	95.50 224	55.48 355	99.18 139	71.15 346	87.14 240	93.55 252

TestCases				90.52 276	96.82 153	78.84 341		92.17 365	77.96 350	75.94 337	95.50 224	55.48 355	99.18 139	71.15 346	87.14 240	93.55 252

SDMVSNet		91.09 187	89.91 194	94.65 171	96.80 155	90.54 134	97.78 241	97.81 68	88.34 196	85.73 234	95.26 230	66.44 310	98.26 183	94.25 129	86.75 243	95.14 243

sd_testset		89.23 221	88.05 235	92.74 225	96.80 155	85.33 267	95.85 318	97.03 188	88.34 196	85.73 234	95.26 230	61.12 336	97.76 216	85.61 234	86.75 243	95.14 243

PMMVS		93.62 132	93.90 111	92.79 222	96.79 157	81.40 320	98.85 136	96.81 198	91.25 111	96.82 80	98.15 129	77.02 230	98.13 188	93.15 149	96.30 149	98.83 142

BH-RMVSNet		91.25 185	89.99 193	95.03 158	96.75 158	88.55 188	98.65 159	94.95 315	87.74 218	87.74 215	97.80 135	68.27 292	98.14 187	80.53 289	97.49 126	98.41 166

MVS_Test		93.67 130	92.67 142	96.69 83	96.72 159	92.66 87	97.22 269	96.03 248	87.69 221	95.12 116	94.03 247	81.55 195	98.28 182	89.17 197	96.46 143	99.14 111

COLMAP_ROB	82.69 18	84.54 302	82.82 303	89.70 300	96.72 159	78.85 340	95.89 313	92.83 357	71.55 371	77.54 332	95.89 219	59.40 342	99.14 145	67.26 362	88.26 236	91.11 311
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
mvs_anonymous		92.50 160	91.65 163	95.06 155	96.60 161	89.64 160	97.06 274	96.44 220	86.64 242	84.14 250	93.93 251	82.49 180	96.17 300	91.47 164	96.08 154	99.35 93

UWE-MVS		93.18 145	93.40 123	92.50 230	96.56 162	83.55 293	98.09 224	97.84 61	89.50 160	91.72 165	96.23 210	91.08 33	96.70 264	86.28 225	93.33 180	97.26 207

ETV-MVS		96.00 53	96.00 53	96.00 121	96.56 162	91.05 120	99.63 37	96.61 206	93.26 70	97.39 62	98.30 122	86.62 108	98.13 188	98.07 49	97.57 122	98.82 143

GG-mvs-BLEND				96.98 66	96.53 164	94.81 42	87.20 377	97.74 77		93.91 137	96.40 204	96.56 2	96.94 255	95.08 110	98.95 85	99.20 107

FMVSNet3		88.81 234	87.08 248	93.99 200	96.52 165	94.59 48	98.08 225	96.20 234	85.85 255	82.12 280	91.60 295	74.05 248	95.40 330	79.04 296	80.24 291	91.99 282

fmvsm_s_conf0.5_n_a		95.97 56	96.19 43	95.31 146	96.51 166	89.01 173	99.81 12	98.39 27	95.46 30	99.19 14	99.16 38	81.44 199	99.91 45	98.83 28	96.97 137	97.01 217

BH-untuned		91.46 179	90.84 180	93.33 212	96.51 166	84.83 277	98.84 138	95.50 291	86.44 250	83.50 254	96.70 196	75.49 236	97.77 211	86.78 221	97.81 116	97.40 202

FE-MVS		91.38 181	90.16 192	95.05 157	96.46 168	87.53 209	89.69 374	97.84 61	82.97 304	92.18 160	92.00 288	84.07 151	98.93 154	80.71 286	95.52 162	98.68 154

sss		94.85 92	93.94 109	97.58 41	96.43 169	94.09 60	98.93 130	99.16 8	89.50 160	95.27 112	97.85 132	81.50 196	99.65 98	92.79 155	94.02 175	98.99 123

test2506		94.80 93	94.21 95	96.58 89	96.41 170	92.18 96	98.01 229	98.96 11	90.82 118	93.46 145	97.28 160	85.92 123	98.45 175	89.82 185	97.19 133	99.12 114

ECVR-MVS		92.29 164	91.33 169	95.15 152	96.41 170	87.84 200	98.10 221	94.84 318	90.82 118	91.42 175	97.28 160	65.61 315	98.49 174	90.33 179	97.19 133	99.12 114

ET-MVSNet_ETH3D		92.56 159	91.45 167	95.88 126	96.39 172	94.13 59	99.46 60	96.97 194	92.18 93	66.94 377	98.29 123	94.65 14	94.28 350	94.34 127	83.82 272	99.24 103

dp		90.16 208	88.83 216	94.14 192	96.38 173	86.42 233	91.57 361	97.06 185	84.76 276	88.81 207	90.19 335	84.29 148	97.43 237	75.05 324	91.35 222	98.56 160

EIA-MVS		95.11 83	95.27 74	94.64 173	96.34 174	86.51 230	99.59 41	96.62 205	92.51 82	94.08 134	98.64 101	86.05 122	98.24 185	95.07 111	98.50 104	99.18 108

test_vis1_n_1920		93.08 149	93.42 122	92.04 240	96.31 175	79.36 337	99.83 10	96.06 247	96.72 9	98.53 33	98.10 130	58.57 343	99.91 45	97.86 55	98.79 95	96.85 220

TR-MVS		90.77 194	89.44 202	94.76 166	96.31 175	88.02 198	97.92 233	95.96 253	85.52 261	88.22 212	97.23 165	66.80 306	98.09 191	84.58 246	92.38 193	98.17 184

UA-Net		93.30 141	92.62 143	95.34 144	96.27 177	88.53 190	95.88 315	96.97 194	90.90 116	95.37 111	97.07 175	82.38 186	99.10 147	83.91 258	94.86 169	98.38 169

tpmrst		92.78 152	92.16 151	94.65 171	96.27 177	87.45 212	91.83 356	97.10 182	89.10 171	94.68 123	90.69 314	88.22 71	97.73 219	89.78 186	91.80 206	98.77 149

hse-mvs2		91.67 176	91.51 166	92.15 237	96.22 179	82.61 309	97.74 246	97.53 127	93.85 57	96.27 91	96.15 211	83.19 165	97.44 236	95.81 93	66.86 369	96.40 234

AUN-MVS		90.17 207	89.50 200	92.19 235	96.21 180	82.67 307	97.76 245	97.53 127	88.05 206	91.67 166	96.15 211	83.10 167	97.47 233	88.11 206	66.91 368	96.43 233

ADS-MVSNet2		87.62 257	86.88 251	89.86 294	96.21 180	79.14 339	87.15 378	92.99 353	83.01 302	89.91 198	87.27 358	78.87 218	92.80 363	74.20 332	92.27 197	97.64 195

ADS-MVSNet		88.99 224	87.30 244	94.07 195	96.21 180	87.56 208	87.15 378	96.78 200	83.01 302	89.91 198	87.27 358	78.87 218	97.01 252	74.20 332	92.27 197	97.64 195

PatchmatchNet		92.05 172	91.04 175	95.06 155	96.17 183	89.04 171	91.26 365	97.26 160	89.56 158	90.64 186	90.56 323	88.35 69	97.11 247	79.53 292	96.07 155	99.03 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test1111		92.12 169	91.19 172	94.94 160	96.15 184	87.36 215	98.12 218	94.84 318	90.85 117	90.97 180	97.26 162	65.60 316	98.37 177	89.74 188	97.14 136	99.07 120

gg-mvs-nofinetune		90.00 211	87.71 238	96.89 74	96.15 184	94.69 46	85.15 383	97.74 77	68.32 383	92.97 152	60.16 396	96.10 3	96.84 258	93.89 132	98.87 89	99.14 111

MDTV_nov1_ep13			90.47 189		96.14 186	88.55 188	91.34 364	97.51 133	89.58 156	92.24 159	90.50 327	86.99 100	97.61 226	77.64 307	92.34 195

IS-MVSNet		93.00 150	92.51 145	94.49 176	96.14 186	87.36 215	98.31 203	95.70 279	88.58 185	90.17 194	97.50 152	83.02 169	97.22 244	87.06 213	96.07 155	98.90 135

Vis-MVSNet (Re-imp)		93.26 144	93.00 136	94.06 196	96.14 186	86.71 229	98.68 155	96.70 201	88.30 198	89.71 202	97.64 146	85.43 134	96.39 283	88.06 207	96.32 147	99.08 118

thisisatest0515		94.75 95	94.19 96	96.43 98	96.13 189	92.64 90	99.47 56	97.60 112	87.55 224	93.17 148	97.59 148	94.71 12	98.42 176	88.28 203	93.20 181	98.24 179

FA-MVS(test-final)		92.22 168	91.08 174	95.64 135	96.05 190	88.98 174	91.60 360	97.25 161	86.99 231	91.84 162	92.12 282	83.03 168	99.00 151	86.91 218	93.91 176	98.93 132

test_fmvsmconf_n		96.78 34	96.84 29	96.61 86	95.99 191	90.25 138	99.90 3	98.13 42	96.68 11	98.42 35	98.92 76	85.34 136	99.88 54	99.12 22	99.08 74	99.70 52

ab-mvs		91.05 190	89.17 208	96.69 83	95.96 192	91.72 102	92.62 351	97.23 165	85.61 260	89.74 200	93.89 253	68.55 289	99.42 123	91.09 167	87.84 238	98.92 134

Fast-Effi-MVS+		91.72 175	90.79 183	94.49 176	95.89 193	87.40 214	99.54 50	95.70 279	85.01 272	89.28 205	95.68 222	77.75 226	97.57 231	83.22 263	95.06 167	98.51 162

EPP-MVSNet		93.75 126	93.67 116	94.01 199	95.86 194	85.70 260	98.67 157	97.66 95	84.46 279	91.36 176	97.18 170	91.16 30	97.79 209	92.93 151	93.75 177	98.53 161

mvsany_test1		94.57 104	95.09 80	92.98 218	95.84 195	82.07 313	98.76 148	95.24 307	92.87 79	96.45 88	98.71 96	84.81 143	99.15 141	97.68 57	95.49 163	97.73 193

Effi-MVS+		93.87 122	93.15 131	96.02 120	95.79 196	90.76 127	96.70 290	95.78 274	86.98 234	95.71 104	97.17 171	79.58 210	98.01 198	94.57 125	96.09 153	99.31 97

tpm cat1		88.89 228	87.27 245	93.76 206	95.79 196	85.32 268	90.76 370	97.09 183	76.14 358	85.72 236	88.59 348	82.92 170	98.04 196	76.96 311	91.43 218	97.90 191

thisisatest0530		94.00 116	93.52 118	95.43 141	95.76 198	90.02 152	98.99 125	97.60 112	86.58 243	91.74 164	97.36 159	94.78 11	98.34 178	86.37 224	92.48 192	97.94 190

3Dnovator+	87.72 8	93.43 136	91.84 159	98.17 23	95.73 199	95.08 33	98.92 132	97.04 186	91.42 108	81.48 294	97.60 147	74.60 240	99.79 82	90.84 172	98.97 82	99.64 63

MVS		93.92 119	92.28 148	98.83 7	95.69 200	96.82 8	96.22 305	98.17 37	84.89 274	84.34 249	98.61 105	79.32 215	99.83 73	93.88 133	99.43 60	99.86 29

cascas		90.93 192	89.33 206	95.76 130	95.69 200	93.03 79	98.99 125	96.59 208	80.49 337	86.79 229	94.45 242	65.23 319	98.60 169	93.52 140	92.18 200	95.66 242

QAPM		91.41 180	89.49 201	97.17 57	95.66 202	93.42 71	98.60 167	97.51 133	80.92 335	81.39 295	97.41 157	72.89 260	99.87 58	82.33 273	98.68 97	98.21 181

tttt0517		93.30 141	93.01 135	94.17 191	95.57 203	86.47 232	98.51 177	97.60 112	85.99 254	90.55 187	97.19 169	94.80 10	98.31 179	85.06 239	91.86 204	97.74 192

1112_ss		92.71 153	91.55 165	96.20 110	95.56 204	91.12 115	98.48 182	94.69 325	88.29 199	86.89 227	98.50 110	87.02 98	98.66 166	84.75 243	89.77 233	98.81 144

diffmvs		94.59 103	94.19 96	95.81 128	95.54 205	90.69 129	98.70 153	95.68 281	91.61 101	95.96 95	97.81 134	80.11 206	98.06 193	96.52 82	95.76 158	98.67 155
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LCM-MVSNet-Re		88.59 241	88.61 221	88.51 320	95.53 206	72.68 370	96.85 282	88.43 389	88.45 189	73.14 354	90.63 318	75.82 233	94.38 349	92.95 150	95.71 160	98.48 164

Test_1112_low_res		92.27 166	90.97 176	96.18 111	95.53 206	91.10 117	98.47 184	94.66 326	88.28 200	86.83 228	93.50 264	87.00 99	98.65 168	84.69 244	89.74 234	98.80 145

PCF-MVS	89.78 5	91.26 183	89.63 198	96.16 115	95.44 208	91.58 106	95.29 325	96.10 243	85.07 269	82.75 263	97.45 155	78.28 223	99.78 84	80.60 288	95.65 161	97.12 210
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EC-MVSNet		95.09 84	95.17 76	94.84 164	95.42 209	88.17 193	99.48 54	95.92 260	91.47 105	97.34 64	98.36 119	82.77 173	97.41 238	97.24 64	98.58 101	98.94 131

3Dnovator	87.35 11	93.17 147	91.77 161	97.37 50	95.41 210	93.07 77	98.82 139	97.85 60	91.53 103	82.56 269	97.58 149	71.97 267	99.82 76	91.01 169	99.23 70	99.22 106

IB-MVS	89.43 6	92.12 169	90.83 182	95.98 123	95.40 211	90.78 126	99.81 12	98.06 45	91.23 112	85.63 237	93.66 259	90.63 42	98.78 157	91.22 166	71.85 352	98.36 172
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
test_cas_vis1_n_1920		93.86 123	93.74 115	94.22 189	95.39 212	86.08 248	99.73 23	96.07 246	96.38 17	97.19 70	97.78 137	65.46 318	99.86 63	96.71 74	98.92 86	96.73 222

miper_ehance_all_eth		88.94 226	88.12 233	91.40 253	95.32 213	86.93 225	97.85 238	95.55 288	84.19 282	81.97 285	91.50 297	84.16 149	95.91 314	84.69 244	77.89 303	91.36 302

1314		93.44 135	91.98 156	97.84 33	95.24 214	94.38 53	96.22 305	97.92 55	90.18 137	82.28 277	97.71 142	77.63 227	99.80 81	91.94 162	98.67 98	99.34 95

XVG-OURS		90.83 193	90.49 188	91.86 242	95.23 215	81.25 324	95.79 320	95.92 260	88.96 174	90.02 197	98.03 131	71.60 272	99.35 133	91.06 168	87.78 239	94.98 246

casdiffmvs_mvg		94.00 116	93.33 125	96.03 119	95.22 216	90.90 125	99.09 112	95.99 249	90.58 126	91.55 171	97.37 158	79.91 208	98.06 193	95.01 113	95.22 165	99.13 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TESTMET0.1,1		93.82 124	93.26 128	95.49 139	95.21 217	90.25 138	99.15 103	97.54 126	89.18 168	91.79 163	94.87 236	89.13 59	97.63 224	86.21 226	96.29 150	98.60 159

xiu_mvs_v1_base_debu		94.73 96	93.98 104	96.99 63	95.19 218	95.24 26	98.62 163	96.50 216	92.99 74	97.52 58	98.83 84	72.37 263	99.15 141	97.03 67	96.74 140	96.58 227

xiu_mvs_v1_base		94.73 96	93.98 104	96.99 63	95.19 218	95.24 26	98.62 163	96.50 216	92.99 74	97.52 58	98.83 84	72.37 263	99.15 141	97.03 67	96.74 140	96.58 227

xiu_mvs_v1_base_debi		94.73 96	93.98 104	96.99 63	95.19 218	95.24 26	98.62 163	96.50 216	92.99 74	97.52 58	98.83 84	72.37 263	99.15 141	97.03 67	96.74 140	96.58 227

XVG-OURS-SEG-HR		90.95 191	90.66 186	91.83 243	95.18 221	81.14 327	95.92 312	95.92 260	88.40 193	90.33 193	97.85 132	70.66 278	99.38 128	92.83 153	88.83 235	94.98 246

Effi-MVS+-dtu		89.97 213	90.68 185	87.81 325	95.15 222	71.98 372	97.87 237	95.40 298	91.92 96	87.57 216	91.44 298	74.27 246	96.84 258	89.45 190	93.10 183	94.60 248

Syy-MVS		84.10 310	84.53 289	82.83 356	95.14 223	65.71 384	97.68 250	96.66 203	86.52 246	82.63 266	96.84 190	68.15 293	89.89 380	45.62 394	91.54 213	92.87 255

myMVS_eth3d		88.68 240	89.07 210	87.50 328	95.14 223	79.74 335	97.68 250	96.66 203	86.52 246	82.63 266	96.84 190	85.22 138	89.89 380	69.43 354	91.54 213	92.87 255

Vis-MVSNet		92.64 155	91.85 158	95.03 158	95.12 225	88.23 192	98.48 182	96.81 198	91.61 101	92.16 161	97.22 166	71.58 273	98.00 199	85.85 233	97.81 116	98.88 136
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
GBi-Net		86.67 269	84.96 277	91.80 245	95.11 226	88.81 182	96.77 284	95.25 304	82.94 305	82.12 280	90.25 330	62.89 328	94.97 337	79.04 296	80.24 291	91.62 288

test1		86.67 269	84.96 277	91.80 245	95.11 226	88.81 182	96.77 284	95.25 304	82.94 305	82.12 280	90.25 330	62.89 328	94.97 337	79.04 296	80.24 291	91.62 288

FMVSNet2		86.90 264	84.79 283	93.24 213	95.11 226	92.54 91	97.67 252	95.86 272	82.94 305	80.55 301	91.17 304	62.89 328	95.29 332	77.23 308	79.71 297	91.90 283

GeoE		90.60 199	89.56 199	93.72 208	95.10 229	85.43 264	99.41 69	94.94 316	83.96 287	87.21 222	96.83 192	74.37 244	97.05 251	80.50 290	93.73 178	98.67 155

baseline		93.91 120	93.30 126	95.72 131	95.10 229	90.07 147	97.48 257	95.91 265	91.03 113	93.54 144	97.68 143	79.58 210	98.02 197	94.27 128	95.14 166	99.08 118

casdiffmvs		93.98 118	93.43 121	95.61 137	95.07 231	89.86 156	98.80 142	95.84 273	90.98 115	92.74 154	97.66 145	79.71 209	98.10 190	94.72 120	95.37 164	98.87 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVSFormer		94.71 99	94.08 101	96.61 86	95.05 232	94.87 37	97.77 243	96.17 239	86.84 237	98.04 49	98.52 108	85.52 128	95.99 307	89.83 183	98.97 82	98.96 126

lupinMVS		96.32 45	95.94 54	97.44 45	95.05 232	94.87 37	99.86 5	96.50 216	93.82 59	98.04 49	98.77 87	85.52 128	98.09 191	96.98 70	98.97 82	99.37 91

CostFormer		92.89 151	92.48 146	94.12 193	94.99 234	85.89 255	92.89 347	97.00 192	86.98 234	95.00 118	90.78 310	90.05 53	97.51 232	92.92 152	91.73 208	98.96 126

c3_l		88.19 247	87.23 246	91.06 259	94.97 235	86.17 245	97.72 247	95.38 299	83.43 296	81.68 292	91.37 299	82.81 172	95.72 320	84.04 257	73.70 334	91.29 306

SCA		90.64 198	89.25 207	94.83 165	94.95 236	88.83 181	96.26 302	97.21 167	90.06 144	90.03 196	90.62 319	66.61 307	96.81 260	83.16 264	94.36 172	98.84 139

test-LLR		93.11 148	92.68 141	94.40 180	94.94 237	87.27 219	99.15 103	97.25 161	90.21 135	91.57 168	94.04 245	84.89 141	97.58 228	85.94 230	96.13 151	98.36 172

test-mter		93.27 143	92.89 138	94.40 180	94.94 237	87.27 219	99.15 103	97.25 161	88.95 175	91.57 168	94.04 245	88.03 77	97.58 228	85.94 230	96.13 151	98.36 172

cl____		87.82 249	86.79 253	90.89 265	94.88 239	85.43 264	97.81 239	95.24 307	82.91 309	80.71 300	91.22 302	81.97 192	95.84 316	81.34 281	75.06 318	91.40 301

DIV-MVS_self_test		87.82 249	86.81 252	90.87 266	94.87 240	85.39 266	97.81 239	95.22 312	82.92 308	80.76 299	91.31 301	81.99 190	95.81 318	81.36 280	75.04 319	91.42 300

tpm2		91.77 174	91.09 173	93.82 205	94.83 241	85.56 263	92.51 352	97.16 174	84.00 285	93.83 139	90.66 316	87.54 83	97.17 245	87.73 210	91.55 212	98.72 151

PVSNet_0	83.28 16	87.31 260	85.16 275	93.74 207	94.78 242	84.59 279	98.91 133	98.69 21	89.81 149	78.59 325	93.23 269	61.95 332	99.34 134	94.75 118	55.72 389	97.30 205

CDS-MVSNet		93.47 134	93.04 134	94.76 166	94.75 243	89.45 164	98.82 139	97.03 188	87.91 212	90.97 180	96.48 202	89.06 60	96.36 285	89.50 189	92.81 187	98.49 163
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
gm-plane-assit					94.69 244	88.14 194			88.22 201		97.20 167		98.29 181	90.79 174

eth_miper_zixun_eth		87.76 251	87.00 250	90.06 287	94.67 245	82.65 308	97.02 277	95.37 300	84.19 282	81.86 290	91.58 296	81.47 197	95.90 315	83.24 262	73.61 335	91.61 291

testing3		87.75 252	88.22 231	86.36 336	94.66 246	77.41 352	99.52 51	97.95 54	86.05 253	81.12 296	96.69 197	86.18 120	89.31 384	61.65 378	90.12 231	92.35 267

RPSCF		85.33 292	85.55 270	84.67 348	94.63 247	62.28 387	93.73 339	93.76 344	74.38 365	85.23 241	97.06 176	64.09 322	98.31 179	80.98 282	86.08 251	93.41 254

miper_lstm_enhance		86.90 264	86.20 260	89.00 315	94.53 248	81.19 325	96.74 288	95.24 307	82.33 318	80.15 306	90.51 326	81.99 190	94.68 346	80.71 286	73.58 336	91.12 310

Patchmatch-test		86.25 278	84.06 295	92.82 221	94.42 249	82.88 304	82.88 392	94.23 338	71.58 370	79.39 316	90.62 319	89.00 62	96.42 282	63.03 374	91.37 221	99.16 109

VDDNet		90.08 210	88.54 226	94.69 170	94.41 250	87.68 203	98.21 210	96.40 221	76.21 357	93.33 147	97.75 139	54.93 360	98.77 158	94.71 121	90.96 223	97.61 199

fmvsm_s_conf0.1_n		95.56 72	95.68 65	95.20 150	94.35 251	89.10 169	99.50 52	97.67 94	94.76 36	98.68 28	99.03 58	81.13 202	99.86 63	98.63 32	97.36 130	96.63 224

test_fmvsmvis_n_1920		95.47 73	95.40 71	95.70 132	94.33 252	90.22 141	99.70 27	96.98 193	96.80 7	92.75 153	98.89 80	82.46 184	99.92 40	98.36 40	98.33 108	96.97 218

KD-MVS_2432*1600		82.98 315	80.52 323	90.38 280	94.32 253	88.98 174	92.87 348	95.87 270	80.46 338	73.79 349	87.49 355	82.76 175	93.29 357	70.56 350	46.53 398	88.87 355

miper_refine_blended		82.98 315	80.52 323	90.38 280	94.32 253	88.98 174	92.87 348	95.87 270	80.46 338	73.79 349	87.49 355	82.76 175	93.29 357	70.56 350	46.53 398	88.87 355

EI-MVSNet		89.87 214	89.38 205	91.36 255	94.32 253	85.87 256	97.61 254	96.59 208	85.10 267	85.51 238	97.10 173	81.30 201	96.56 271	83.85 260	83.03 278	91.64 286

CVMVSNet		90.30 203	90.91 178	88.46 321	94.32 253	73.58 366	97.61 254	97.59 116	90.16 140	88.43 211	97.10 173	76.83 231	92.86 360	82.64 270	93.54 179	98.93 132

WB-MVSnew		88.69 238	88.34 228	89.77 298	94.30 257	85.99 253	98.14 215	97.31 159	87.15 230	87.85 214	96.07 215	69.91 279	95.52 325	72.83 343	91.47 217	87.80 362

test_fmvs1_n		91.07 188	91.41 168	90.06 287	94.10 258	74.31 362	99.18 93	94.84 318	94.81 35	96.37 90	97.46 154	50.86 373	99.82 76	97.14 66	97.90 114	96.04 239

IterMVS-LS		88.34 243	87.44 241	91.04 260	94.10 258	85.85 257	98.10 221	95.48 292	85.12 266	82.03 284	91.21 303	81.35 200	95.63 323	83.86 259	75.73 315	91.63 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TAMVS		92.62 156	92.09 154	94.20 190	94.10 258	87.68 203	98.41 189	96.97 194	87.53 225	89.74 200	96.04 216	84.77 145	96.49 278	88.97 199	92.31 196	98.42 165

PAPM		96.35 43	95.94 54	97.58 41	94.10 258	95.25 25	98.93 130	98.17 37	94.26 44	93.94 136	98.72 93	89.68 56	97.88 203	96.36 84	99.29 68	99.62 67

CLD-MVS		91.06 189	90.71 184	92.10 238	94.05 262	86.10 247	99.55 45	96.29 230	94.16 47	84.70 244	97.17 171	69.62 284	97.82 207	94.74 119	86.08 251	92.39 262
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP-NCC					93.95 263		99.16 97		93.92 52	87.57 216

ACMP_Plane					93.95 263		99.16 97		93.92 52	87.57 216

HQP-MVS		91.50 177	91.23 171	92.29 232	93.95 263	86.39 235	99.16 97	96.37 223	93.92 52	87.57 216	96.67 198	73.34 252	97.77 211	93.82 136	86.29 246	92.72 257

NP-MVS					93.94 266	86.22 242					96.67 198

plane_prior6					93.92 267	86.02 252						72.92 258

ACMP	87.39 10	88.71 237	88.24 230	90.12 286	93.91 268	81.06 328	98.50 178	95.67 282	89.43 162	80.37 303	95.55 223	65.67 313	97.83 206	90.55 177	84.51 261	91.47 296
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
plane_prior1					93.90 269

HQP_MVS		91.26 183	90.95 177	92.16 236	93.84 270	86.07 250	99.02 121	96.30 227	93.38 68	86.99 224	96.52 200	72.92 258	97.75 217	93.46 143	86.17 249	92.67 259

plane_prior7					93.84 270	85.73 259

dmvs_re		88.69 238	88.06 234	90.59 272	93.83 272	78.68 343	95.75 321	96.18 238	87.99 209	84.48 248	96.32 208	67.52 300	96.94 255	84.98 241	85.49 255	96.14 237

MVS-HIRNet		79.01 334	75.13 346	90.66 271	93.82 273	81.69 316	85.16 382	93.75 345	54.54 392	74.17 347	59.15 398	57.46 348	96.58 270	63.74 371	94.38 171	93.72 251

FMVSNet5		82.29 318	80.54 322	87.52 327	93.79 274	84.01 287	93.73 339	92.47 361	76.92 355	74.27 346	86.15 366	63.69 326	89.24 385	69.07 355	74.79 322	89.29 350

ACMH+	83.78 15	84.21 306	82.56 311	89.15 312	93.73 275	79.16 338	96.43 295	94.28 337	81.09 332	74.00 348	94.03 247	54.58 361	97.67 220	76.10 318	78.81 299	90.63 326

ACMM	86.95 13	88.77 235	88.22 231	90.43 278	93.61 276	81.34 322	98.50 178	95.92 260	87.88 213	83.85 253	95.20 232	67.20 303	97.89 202	86.90 219	84.90 258	92.06 280
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS	85.28 14	90.75 195	88.84 215	96.48 94	93.58 277	93.51 69	98.80 142	97.41 151	82.59 311	78.62 323	97.49 153	68.00 296	99.82 76	84.52 248	98.55 103	96.11 238

IterMVS		85.81 285	84.67 286	89.22 310	93.51 278	83.67 292	96.32 299	94.80 321	85.09 268	78.69 321	90.17 336	66.57 309	93.17 359	79.48 294	77.42 309	90.81 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CR-MVSNet		88.83 232	87.38 243	93.16 215	93.47 279	86.24 240	84.97 385	94.20 339	88.92 178	90.76 184	86.88 362	84.43 146	94.82 342	70.64 349	92.17 201	98.41 166

RPMNet		85.07 295	81.88 312	94.64 173	93.47 279	86.24 240	84.97 385	97.21 167	64.85 390	90.76 184	78.80 387	80.95 203	99.27 137	53.76 389	92.17 201	98.41 166

IterMVS-SCA-FT		85.73 288	84.64 287	89.00 315	93.46 281	82.90 302	96.27 300	94.70 324	85.02 271	78.62 323	90.35 328	66.61 307	93.33 356	79.38 295	77.36 310	90.76 321

Fast-Effi-MVS+-dtu		88.84 230	88.59 223	89.58 303	93.44 282	78.18 347	98.65 159	94.62 327	88.46 188	84.12 251	95.37 229	68.91 286	96.52 274	82.06 276	91.70 209	94.06 249

Patchmtry		83.61 314	81.64 314	89.50 305	93.36 283	82.84 305	84.10 388	94.20 339	69.47 380	79.57 314	86.88 362	84.43 146	94.78 343	68.48 358	74.30 328	90.88 316

LPG-MVS_test		88.86 229	88.47 227	90.06 287	93.35 284	80.95 329	98.22 208	95.94 256	87.73 219	83.17 259	96.11 213	66.28 311	97.77 211	90.19 181	85.19 256	91.46 297

LGP-MVS_train				90.06 287	93.35 284	80.95 329		95.94 256	87.73 219	83.17 259	96.11 213	66.28 311	97.77 211	90.19 181	85.19 256	91.46 297

JIA-IIPM		85.97 281	84.85 281	89.33 309	93.23 286	73.68 365	85.05 384	97.13 177	69.62 379	91.56 170	68.03 394	88.03 77	96.96 253	77.89 306	93.12 182	97.34 204

ACMH	83.09 17	84.60 300	82.61 310	90.57 273	93.18 287	82.94 300	96.27 300	94.92 317	81.01 333	72.61 360	93.61 260	56.54 351	97.79 209	74.31 330	81.07 289	90.99 313
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PatchT		85.44 291	83.19 300	92.22 233	93.13 288	83.00 299	83.80 391	96.37 223	70.62 373	90.55 187	79.63 386	84.81 143	94.87 340	58.18 385	91.59 210	98.79 146

baseline2		94.04 115	93.80 114	94.74 168	93.07 289	90.25 138	98.12 218	98.16 39	89.86 147	86.53 231	96.95 182	95.56 6	98.05 195	91.44 165	94.53 170	95.93 240

jason		95.40 77	94.86 84	97.03 60	92.91 290	94.23 55	99.70 27	96.30 227	93.56 66	96.73 83	98.52 108	81.46 198	97.91 200	96.08 90	98.47 106	98.96 126
jason: jason.
LTVRE_ROB	81.71 19	84.59 301	82.72 308	90.18 284	92.89 291	83.18 298	93.15 344	94.74 322	78.99 343	75.14 344	92.69 277	65.64 314	97.63 224	69.46 353	81.82 287	89.74 343
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
VPA-MVSNet		89.10 223	87.66 239	93.45 210	92.56 292	91.02 121	97.97 232	98.32 30	86.92 236	86.03 233	92.01 286	68.84 288	97.10 249	90.92 170	75.34 316	92.23 270

tpm		89.67 216	88.95 213	91.82 244	92.54 293	81.43 319	92.95 346	95.92 260	87.81 214	90.50 189	89.44 342	84.99 139	95.65 322	83.67 261	82.71 281	98.38 169

GA-MVS		90.10 209	88.69 219	94.33 184	92.44 294	87.97 199	99.08 113	96.26 231	89.65 152	86.92 226	93.11 272	68.09 294	96.96 253	82.54 272	90.15 230	98.05 186

test_fmvsmconf0.1_n		95.94 59	95.79 62	96.40 101	92.42 295	89.92 154	99.79 17	96.85 197	96.53 15	97.22 66	98.67 99	82.71 177	99.84 69	98.92 27	98.98 81	99.43 87

FIs		90.70 196	89.87 195	93.18 214	92.29 296	91.12 115	98.17 214	98.25 32	89.11 170	83.44 255	94.82 238	82.26 187	96.17 300	87.76 209	82.76 280	92.25 268

ITE_SJBPF				87.93 323	92.26 297	76.44 355		93.47 351	87.67 222	79.95 309	95.49 226	56.50 352	97.38 239	75.24 323	82.33 284	89.98 340

UniMVSNet (Re)		89.50 220	88.32 229	93.03 216	92.21 298	90.96 123	98.90 134	98.39 27	89.13 169	83.22 256	92.03 284	81.69 194	96.34 291	86.79 220	72.53 345	91.81 284

UniMVSNet_NR-MVSNet		89.60 217	88.55 225	92.75 224	92.17 299	90.07 147	98.74 149	98.15 40	88.37 194	83.21 257	93.98 250	82.86 171	95.93 311	86.95 216	72.47 346	92.25 268

TinyColmap		80.42 328	77.94 333	87.85 324	92.09 300	78.58 344	93.74 338	89.94 382	74.99 361	69.77 365	91.78 292	46.09 380	97.58 228	65.17 370	77.89 303	87.38 364

fmvsm_s_conf0.1_n_a		95.16 82	95.15 77	95.18 151	92.06 301	88.94 177	99.29 82	97.53 127	94.46 40	98.98 19	98.99 62	79.99 207	99.85 67	98.24 47	96.86 139	96.73 222

tt0805		86.50 274	84.79 283	91.63 251	91.97 302	81.49 318	96.49 294	97.38 154	82.24 319	82.44 271	95.82 220	51.22 370	98.25 184	84.55 247	80.96 290	95.13 245

MS-PatchMatch		86.75 267	85.92 264	89.22 310	91.97 302	82.47 310	96.91 279	96.14 241	83.74 290	77.73 330	93.53 263	58.19 345	97.37 241	76.75 314	98.35 107	87.84 360

VPNet		88.30 244	86.57 254	93.49 209	91.95 304	91.35 108	98.18 212	97.20 171	88.61 183	84.52 247	94.89 235	62.21 331	96.76 263	89.34 193	72.26 349	92.36 264

FMVSNet1		83.94 311	81.32 319	91.80 245	91.94 305	88.81 182	96.77 284	95.25 304	77.98 348	78.25 328	90.25 330	50.37 374	94.97 337	73.27 339	77.81 307	91.62 288

WR-MVS		88.54 242	87.22 247	92.52 229	91.93 306	89.50 163	98.56 172	97.84 61	86.99 231	81.87 288	93.81 254	74.25 247	95.92 313	85.29 236	74.43 326	92.12 277

D2MVS		87.96 248	87.39 242	89.70 300	91.84 307	83.40 295	98.31 203	98.49 23	88.04 207	78.23 329	90.26 329	73.57 250	96.79 262	84.21 251	83.53 274	88.90 354

FC-MVSNet-test		90.22 205	89.40 204	92.67 228	91.78 308	89.86 156	97.89 234	98.22 35	88.81 180	82.96 262	94.66 240	81.90 193	95.96 309	85.89 232	82.52 283	92.20 274

MIMVSNet		84.48 303	81.83 313	92.42 231	91.73 309	87.36 215	85.52 381	94.42 333	81.40 328	81.91 286	87.58 352	51.92 368	92.81 362	73.84 335	88.15 237	97.08 214

USDC		84.74 297	82.93 302	90.16 285	91.73 309	83.54 294	95.00 327	93.30 352	88.77 181	73.19 353	93.30 267	53.62 364	97.65 223	75.88 320	81.54 288	89.30 349

test_vis1_n		90.40 200	90.27 190	90.79 268	91.55 311	76.48 354	99.12 110	94.44 330	94.31 43	97.34 64	96.95 182	43.60 384	99.42 123	97.57 59	97.60 121	96.47 231

nrg030		90.23 204	88.87 214	94.32 185	91.53 312	93.54 68	98.79 146	95.89 268	88.12 204	84.55 246	94.61 241	78.80 220	96.88 257	92.35 159	75.21 317	92.53 261

DU-MVS		88.83 232	87.51 240	92.79 222	91.46 313	90.07 147	98.71 150	97.62 109	88.87 179	83.21 257	93.68 257	74.63 238	95.93 311	86.95 216	72.47 346	92.36 264

NR-MVSNet		87.74 255	86.00 263	92.96 219	91.46 313	90.68 130	96.65 291	97.42 150	88.02 208	73.42 351	93.68 257	77.31 228	95.83 317	84.26 250	71.82 353	92.36 264

tfpnnormal		83.65 312	81.35 318	90.56 275	91.37 315	88.06 196	97.29 263	97.87 58	78.51 347	76.20 334	90.91 307	64.78 320	96.47 279	61.71 377	73.50 337	87.13 369

test_vis1_rt		81.31 324	80.05 327	85.11 343	91.29 316	70.66 376	98.98 127	77.39 404	85.76 258	68.80 368	82.40 375	36.56 391	99.44 119	92.67 156	86.55 245	85.24 379

test_0402		78.81 336	76.33 341	86.26 337	91.18 317	78.44 346	95.88 315	91.34 376	68.55 381	70.51 364	89.91 337	52.65 367	94.99 336	47.14 393	79.78 296	85.34 378

test0.0.03 1		88.96 225	88.61 221	90.03 291	91.09 318	84.43 281	98.97 128	97.02 190	90.21 135	80.29 304	96.31 209	84.89 141	91.93 374	72.98 341	85.70 254	93.73 250

WR-MVS_H		86.53 273	85.49 271	89.66 302	91.04 319	83.31 297	97.53 256	98.20 36	84.95 273	79.64 312	90.90 308	78.01 225	95.33 331	76.29 317	72.81 342	90.35 330

CP-MVSNet		86.54 272	85.45 272	89.79 297	91.02 320	82.78 306	97.38 260	97.56 122	85.37 263	79.53 315	93.03 273	71.86 269	95.25 333	79.92 291	73.43 340	91.34 303

TranMVSNet+NR-MVSNet		87.75 252	86.31 258	92.07 239	90.81 321	88.56 187	98.33 200	97.18 172	87.76 216	81.87 288	93.90 252	72.45 262	95.43 328	83.13 266	71.30 356	92.23 270

PS-CasMVS		85.81 285	84.58 288	89.49 307	90.77 322	82.11 312	97.20 270	97.36 156	84.83 275	79.12 320	92.84 276	67.42 302	95.16 335	78.39 304	73.25 341	91.21 308

DeepMVS_CX				76.08 367	90.74 323	51.65 400		90.84 378	86.47 249	57.89 388	87.98 349	35.88 392	92.60 364	65.77 368	65.06 373	83.97 383

mvsmamba		89.99 212	89.42 203	91.69 250	90.64 324	86.34 238	98.40 192	92.27 363	91.01 114	84.80 243	94.93 234	76.12 232	96.51 275	92.81 154	83.84 269	92.21 272

OPM-MVS		89.76 215	89.15 209	91.57 252	90.53 325	85.58 262	98.11 220	95.93 259	92.88 78	86.05 232	96.47 203	67.06 305	97.87 204	89.29 196	86.08 251	91.26 307
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XXY-MVS		87.75 252	86.02 262	92.95 220	90.46 326	89.70 159	97.71 249	95.90 266	84.02 284	80.95 297	94.05 244	67.51 301	97.10 249	85.16 237	78.41 300	92.04 281

UniMVSNet_ETH3D		85.65 290	83.79 298	91.21 256	90.41 327	80.75 331	95.36 324	95.78 274	78.76 346	81.83 291	94.33 243	49.86 375	96.66 265	84.30 249	83.52 275	96.22 236

RRT_MVS		88.91 227	88.56 224	89.93 292	90.31 328	81.61 317	98.08 225	96.38 222	89.30 164	82.41 274	94.84 237	73.15 256	96.04 306	90.38 178	82.23 285	92.15 275

v10		85.73 288	84.01 296	90.87 266	90.03 329	86.73 228	97.20 270	95.22 312	81.25 330	79.85 311	89.75 339	73.30 254	96.28 297	76.87 312	72.64 344	89.61 346

v8		86.11 279	84.45 290	91.10 258	89.99 330	86.85 226	97.24 267	95.36 301	81.99 322	79.89 310	89.86 338	74.53 242	96.39 283	78.83 300	72.32 348	90.05 338

V42		87.00 263	85.68 268	90.98 262	89.91 331	86.08 248	98.32 202	95.61 285	83.67 293	82.72 264	90.67 315	74.00 249	96.53 273	81.94 278	74.28 329	90.32 331

XVG-ACMP-BASELINE		85.86 283	84.95 279	88.57 319	89.90 332	77.12 353	94.30 333	95.60 286	87.40 227	82.12 280	92.99 275	53.42 365	97.66 221	85.02 240	83.83 270	90.92 315

PEN-MVS		85.21 293	83.93 297	89.07 314	89.89 333	81.31 323	97.09 273	97.24 164	84.45 280	78.66 322	92.68 278	68.44 291	94.87 340	75.98 319	70.92 357	91.04 312

test_fmvs2		85.10 294	85.45 272	84.02 351	89.85 334	65.63 385	98.49 180	92.59 359	90.45 130	85.43 240	93.32 265	43.94 382	96.59 268	90.81 173	84.19 266	89.85 342

v1144		86.83 266	85.31 274	91.40 253	89.75 335	87.21 223	98.31 203	95.45 294	83.22 299	82.70 265	90.78 310	73.36 251	96.36 285	79.49 293	74.69 323	90.63 326

TransMVSNet (Re)		81.97 320	79.61 329	89.08 313	89.70 336	84.01 287	97.26 265	91.85 371	78.84 344	73.07 357	91.62 294	67.17 304	95.21 334	67.50 361	59.46 383	88.02 359

v2v482		87.27 261	85.76 266	91.78 249	89.59 337	87.58 207	98.56 172	95.54 289	84.53 278	82.51 270	91.78 292	73.11 257	96.47 279	82.07 275	74.14 332	91.30 305

pm-mvs1		84.68 299	82.78 306	90.40 279	89.58 338	85.18 270	97.31 262	94.73 323	81.93 324	76.05 336	92.01 286	65.48 317	96.11 303	78.75 301	69.14 359	89.91 341

pmmvs4		87.58 258	86.17 261	91.80 245	89.58 338	88.92 180	97.25 266	95.28 303	82.54 313	80.49 302	93.17 271	75.62 235	96.05 305	82.75 269	78.90 298	90.42 329

v1192		86.32 277	84.71 285	91.17 257	89.53 340	86.40 234	98.13 216	95.44 296	82.52 314	82.42 273	90.62 319	71.58 273	96.33 292	77.23 308	74.88 320	90.79 319

v144192		86.40 275	84.89 280	90.91 263	89.48 341	85.59 261	98.21 210	95.43 297	82.45 316	82.62 268	90.58 322	72.79 261	96.36 285	78.45 303	74.04 333	90.79 319

v148		86.38 276	85.06 276	90.37 282	89.47 342	84.10 286	98.52 174	95.48 292	83.80 289	80.93 298	90.22 333	74.60 240	96.31 293	80.92 284	71.55 354	90.69 324

v1921920		86.02 280	84.44 291	90.77 269	89.32 343	85.20 269	98.10 221	95.35 302	82.19 320	82.25 278	90.71 312	70.73 276	96.30 296	76.85 313	74.49 325	90.80 318

v1240		85.77 287	84.11 294	90.73 270	89.26 344	85.15 272	97.88 236	95.23 311	81.89 325	82.16 279	90.55 324	69.60 285	96.31 293	75.59 322	74.87 321	90.72 323

our_test_3		84.47 304	82.80 304	89.50 305	89.01 345	83.90 289	97.03 275	94.56 328	81.33 329	75.36 343	90.52 325	71.69 271	94.54 348	68.81 356	76.84 311	90.07 336

ppachtmachnet_test		83.63 313	81.57 316	89.80 296	89.01 345	85.09 273	97.13 272	94.50 329	78.84 344	76.14 335	91.00 306	69.78 281	94.61 347	63.40 372	74.36 327	89.71 345

DTE-MVSNet		84.14 308	82.80 304	88.14 322	88.95 347	79.87 334	96.81 283	96.24 232	83.50 295	77.60 331	92.52 280	67.89 298	94.24 351	72.64 344	69.05 360	90.32 331

PS-MVSNAJss		89.54 219	89.05 211	91.00 261	88.77 348	84.36 282	97.39 258	95.97 251	88.47 186	81.88 287	93.80 255	82.48 181	96.50 276	89.34 193	83.34 277	92.15 275

Baseline_NR-MVSNet		85.83 284	84.82 282	88.87 318	88.73 349	83.34 296	98.63 162	91.66 372	80.41 340	82.44 271	91.35 300	74.63 238	95.42 329	84.13 253	71.39 355	87.84 360

MVP-Stereo		86.61 271	85.83 265	88.93 317	88.70 350	83.85 290	96.07 309	94.41 334	82.15 321	75.64 341	91.96 289	67.65 299	96.45 281	77.20 310	98.72 96	86.51 372
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
EU-MVSNet		84.19 307	84.42 292	83.52 354	88.64 351	67.37 383	96.04 310	95.76 276	85.29 264	78.44 326	93.18 270	70.67 277	91.48 376	75.79 321	75.98 313	91.70 285

pmmvs5		85.87 282	84.40 293	90.30 283	88.53 352	84.23 283	98.60 167	93.71 346	81.53 327	80.29 304	92.02 285	64.51 321	95.52 325	82.04 277	78.34 301	91.15 309

MDA-MVSNet-bldmvs		77.82 342	74.75 348	87.03 332	88.33 353	78.52 345	96.34 298	92.85 356	75.57 359	48.87 394	87.89 350	57.32 349	92.49 368	60.79 379	64.80 374	90.08 335

N_pmnet		70.19 354	69.87 356	71.12 374	88.24 354	30.63 413	95.85 318	28.70 412	70.18 376	68.73 369	86.55 364	64.04 323	93.81 352	53.12 390	73.46 338	88.94 353

v7n		84.42 305	82.75 307	89.43 308	88.15 355	81.86 314	96.75 287	95.67 282	80.53 336	78.38 327	89.43 343	69.89 280	96.35 290	73.83 336	72.13 350	90.07 336

SixPastTwentyTwo		82.63 317	81.58 315	85.79 340	88.12 356	71.01 375	95.17 326	92.54 360	84.33 281	72.93 358	92.08 283	60.41 339	95.61 324	74.47 329	74.15 331	90.75 322

test_djsdf		88.26 246	87.73 237	89.84 295	88.05 357	82.21 311	97.77 243	96.17 239	86.84 237	82.41 274	91.95 290	72.07 266	95.99 307	89.83 183	84.50 262	91.32 304

mvs_tets		87.09 262	86.22 259	89.71 299	87.87 358	81.39 321	96.73 289	95.90 266	88.19 202	79.99 308	93.61 260	59.96 340	96.31 293	89.40 192	84.34 264	91.43 299

OurMVSNet-221017-0		84.13 309	83.59 299	85.77 341	87.81 359	70.24 377	94.89 328	93.65 348	86.08 252	76.53 333	93.28 268	61.41 334	96.14 302	80.95 283	77.69 308	90.93 314

YYNet1		79.64 333	77.04 338	87.43 330	87.80 360	79.98 333	96.23 304	94.44 330	73.83 367	51.83 391	87.53 353	67.96 297	92.07 373	66.00 367	67.75 366	90.23 333

MDA-MVSNet_test_wron		79.65 332	77.05 337	87.45 329	87.79 361	80.13 332	96.25 303	94.44 330	73.87 366	51.80 392	87.47 357	68.04 295	92.12 372	66.02 366	67.79 365	90.09 334

jajsoiax		87.35 259	86.51 256	89.87 293	87.75 362	81.74 315	97.03 275	95.98 250	88.47 186	80.15 306	93.80 255	61.47 333	96.36 285	89.44 191	84.47 263	91.50 295

K. test v3		81.04 325	79.77 328	84.83 346	87.41 363	70.23 378	95.60 323	93.93 343	83.70 292	67.51 375	89.35 344	55.76 353	93.58 355	76.67 315	68.03 363	90.67 325

dmvs_testset		77.17 344	78.99 331	71.71 372	87.25 364	38.55 409	91.44 362	81.76 400	85.77 257	69.49 366	95.94 218	69.71 283	84.37 392	52.71 391	76.82 312	92.21 272

testgi		82.29 318	81.00 321	86.17 338	87.24 365	74.84 361	97.39 258	91.62 373	88.63 182	75.85 340	95.42 227	46.07 381	91.55 375	66.87 365	79.94 295	92.12 277

LF4IMVS		81.94 321	81.17 320	84.25 350	87.23 366	68.87 382	93.35 343	91.93 370	83.35 298	75.40 342	93.00 274	49.25 378	96.65 266	78.88 299	78.11 302	87.22 368

EG-PatchMatch MVS		79.92 329	77.59 334	86.90 333	87.06 367	77.90 351	96.20 307	94.06 341	74.61 363	66.53 379	88.76 347	40.40 389	96.20 298	67.02 363	83.66 273	86.61 370

test_fmvsmconf0.01_n		94.14 113	93.51 119	96.04 118	86.79 368	89.19 166	99.28 85	95.94 256	95.70 21	95.50 108	98.49 112	73.27 255	99.79 82	98.28 45	98.32 110	99.15 110

Gipuma		54.77 366	52.22 370	62.40 383	86.50 369	59.37 391	50.20 401	90.35 381	36.52 399	41.20 400	49.49 401	18.33 402	81.29 394	32.10 400	65.34 372	46.54 401
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
anonymousdsp		86.69 268	85.75 267	89.53 304	86.46 370	82.94 300	96.39 296	95.71 278	83.97 286	79.63 313	90.70 313	68.85 287	95.94 310	86.01 227	84.02 268	89.72 344

EGC-MVSNET		60.70 361	55.37 365	76.72 366	86.35 371	71.08 373	89.96 373	84.44 397	0.38 409	1.50 410	84.09 371	37.30 390	88.10 388	40.85 398	73.44 339	70.97 394

test_method		70.10 355	68.66 358	74.41 371	86.30 372	55.84 393	94.47 330	89.82 383	35.18 400	66.15 380	84.75 370	30.54 394	77.96 401	70.40 352	60.33 381	89.44 348

lessismore_v0				85.08 344	85.59 373	69.28 380		90.56 380		67.68 374	90.21 334	54.21 363	95.46 327	73.88 334	62.64 377	90.50 328

CMPMVS	58.40 21	80.48 327	80.11 326	81.59 362	85.10 374	59.56 390	94.14 336	95.95 255	68.54 382	60.71 386	93.31 266	55.35 358	97.87 204	83.06 267	84.85 260	87.33 366
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20231206		80.76 326	79.42 330	84.79 347	84.78 375	72.98 367	96.53 292	92.97 354	79.56 341	74.33 345	88.83 346	61.27 335	92.15 371	60.59 380	75.92 314	89.24 351

DSMNet-mixed		81.60 323	81.43 317	82.10 359	84.36 376	60.79 388	93.63 341	86.74 392	79.00 342	79.32 317	87.15 360	63.87 324	89.78 382	66.89 364	91.92 203	95.73 241

pmmvs6		79.90 330	77.31 336	87.67 326	84.17 377	78.13 348	95.86 317	93.68 347	67.94 384	72.67 359	89.62 341	50.98 372	95.75 319	74.80 328	66.04 370	89.14 352

new_pmnet		76.02 345	73.71 350	82.95 355	83.88 378	72.85 369	91.26 365	92.26 364	70.44 375	62.60 384	81.37 379	47.64 379	92.32 369	61.85 376	72.10 351	83.68 384

OpenMVS_ROB	73.86 20	77.99 341	75.06 347	86.77 334	83.81 379	77.94 350	96.38 297	91.53 375	67.54 385	68.38 370	87.13 361	43.94 382	96.08 304	55.03 388	81.83 286	86.29 373

test20.03		78.51 339	77.48 335	81.62 361	83.07 380	71.03 374	96.11 308	92.83 357	81.66 326	69.31 367	89.68 340	57.53 347	87.29 390	58.65 384	68.47 361	86.53 371

Anonymous20240521		78.63 338	76.90 339	83.82 352	82.82 381	72.86 368	95.72 322	93.57 349	73.55 368	72.17 361	84.79 369	49.69 376	92.51 367	65.29 369	74.50 324	86.09 374

UnsupCasMVSNet_eth		78.90 335	76.67 340	85.58 342	82.81 382	74.94 360	91.98 355	96.31 226	84.64 277	65.84 381	87.71 351	51.33 369	92.23 370	72.89 342	56.50 388	89.56 347

KD-MVS_self_test		77.47 343	75.88 343	82.24 357	81.59 383	68.93 381	92.83 350	94.02 342	77.03 354	73.14 354	83.39 372	55.44 357	90.42 377	67.95 359	57.53 386	87.38 364

CL-MVSNet_self_test		79.89 331	78.34 332	84.54 349	81.56 384	75.01 359	96.88 281	95.62 284	81.10 331	75.86 339	85.81 367	68.49 290	90.26 378	63.21 373	56.51 387	88.35 357

MIMVSNet1		75.92 346	73.30 351	83.81 353	81.29 385	75.57 357	92.26 353	92.05 368	73.09 369	67.48 376	86.18 365	40.87 388	87.64 389	55.78 387	70.68 358	88.21 358

Patchmatch-RL test		81.90 322	80.13 325	87.23 331	80.71 386	70.12 379	84.07 389	88.19 390	83.16 301	70.57 362	82.18 377	87.18 93	92.59 365	82.28 274	62.78 376	98.98 124

APD_test1		68.93 356	66.98 359	74.77 370	80.62 387	53.15 397	87.97 376	85.01 395	53.76 393	59.26 387	87.52 354	25.19 396	89.95 379	56.20 386	67.33 367	81.19 388

pmmvs-eth3d		78.71 337	76.16 342	86.38 335	80.25 388	81.19 325	94.17 335	92.13 367	77.97 349	66.90 378	82.31 376	55.76 353	92.56 366	73.63 338	62.31 379	85.38 376

UnsupCasMVSNet_bld		73.85 351	70.14 355	84.99 345	79.44 389	75.73 356	88.53 375	95.24 307	70.12 377	61.94 385	74.81 391	41.41 387	93.62 354	68.65 357	51.13 395	85.62 375

PM-MVS		74.88 349	72.85 352	80.98 363	78.98 390	64.75 386	90.81 369	85.77 393	80.95 334	68.23 372	82.81 373	29.08 395	92.84 361	76.54 316	62.46 378	85.36 377

new-patchmatchnet		74.80 350	72.40 353	81.99 360	78.36 391	72.20 371	94.44 331	92.36 362	77.06 353	63.47 383	79.98 385	51.04 371	88.85 386	60.53 381	54.35 390	84.92 381

test_fmvs3		75.09 348	75.19 345	74.81 369	77.45 392	54.08 395	95.93 311	90.64 379	82.51 315	73.29 352	81.19 380	22.29 398	86.29 391	85.50 235	67.89 364	84.06 382

WB-MVS		66.44 357	66.29 360	66.89 377	74.84 393	44.93 404	93.00 345	84.09 398	71.15 372	55.82 389	81.63 378	63.79 325	80.31 399	21.85 403	50.47 396	75.43 390

SSC-MVS		65.42 358	65.20 361	66.06 378	73.96 394	43.83 405	92.08 354	83.54 399	69.77 378	54.73 390	80.92 382	63.30 327	79.92 400	20.48 404	48.02 397	74.44 391

pmmvs3		72.86 352	69.76 357	82.17 358	73.86 395	74.19 363	94.20 334	89.01 387	64.23 391	67.72 373	80.91 383	41.48 386	88.65 387	62.40 375	54.02 391	83.68 384

mvsany_test3		75.85 347	74.52 349	79.83 364	73.53 396	60.64 389	91.73 358	87.87 391	83.91 288	70.55 363	82.52 374	31.12 393	93.66 353	86.66 222	62.83 375	85.19 380

test_f		71.94 353	70.82 354	75.30 368	72.77 397	53.28 396	91.62 359	89.66 385	75.44 360	64.47 382	78.31 388	20.48 399	89.56 383	78.63 302	66.02 371	83.05 387

ambc				79.60 365	72.76 398	56.61 392	76.20 396	92.01 369		68.25 371	80.23 384	23.34 397	94.73 344	73.78 337	60.81 380	87.48 363

TDRefinement		78.01 340	75.31 344	86.10 339	70.06 399	73.84 364	93.59 342	91.58 374	74.51 364	73.08 356	91.04 305	49.63 377	97.12 246	74.88 326	59.47 382	87.33 366

test_vis3_rt		61.29 360	58.75 363	68.92 376	67.41 400	52.84 398	91.18 367	59.23 411	66.96 386	41.96 399	58.44 399	11.37 407	94.72 345	74.25 331	57.97 385	59.20 398

testf1		56.38 364	53.73 367	64.31 381	64.84 401	45.11 402	80.50 394	75.94 406	38.87 396	42.74 396	75.07 389	11.26 408	81.19 395	41.11 396	53.27 392	66.63 395

APD_test2		56.38 364	53.73 367	64.31 381	64.84 401	45.11 402	80.50 394	75.94 406	38.87 396	42.74 396	75.07 389	11.26 408	81.19 395	41.11 396	53.27 392	66.63 395

PMMVS2		58.97 363	55.07 366	70.69 375	62.72 403	55.37 394	85.97 380	80.52 401	49.48 394	45.94 395	68.31 393	15.73 404	80.78 397	49.79 392	37.12 400	75.91 389

E-PMN		41.02 371	40.93 373	41.29 387	61.97 404	33.83 410	84.00 390	65.17 409	27.17 402	27.56 402	46.72 403	17.63 403	60.41 406	19.32 405	18.82 402	29.61 402

wuyk23d		16.71 375	16.73 379	16.65 389	60.15 405	25.22 414	41.24 402	5.17 413	6.56 406	5.48 409	3.61 409	3.64 411	22.72 408	15.20 407	9.52 406	1.99 406

FPMVS		61.57 359	60.32 362	65.34 379	60.14 406	42.44 407	91.02 368	89.72 384	44.15 395	42.63 398	80.93 381	19.02 400	80.59 398	42.50 395	72.76 343	73.00 392

EMVS		39.96 372	39.88 374	40.18 388	59.57 407	32.12 412	84.79 387	64.57 410	26.27 403	26.14 404	44.18 406	18.73 401	59.29 407	17.03 406	17.67 404	29.12 403

LCM-MVSNet		60.07 362	56.37 364	71.18 373	54.81 408	48.67 401	82.17 393	89.48 386	37.95 398	49.13 393	69.12 392	13.75 406	81.76 393	59.28 382	51.63 394	83.10 386

MVE	44.00 22	41.70 370	37.64 375	53.90 386	49.46 409	43.37 406	65.09 400	66.66 408	26.19 404	25.77 405	48.53 402	3.58 412	63.35 405	26.15 402	27.28 401	54.97 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		50.71 368	46.17 371	64.33 380	44.27 410	52.30 399	76.13 397	78.73 402	64.95 389	27.37 403	55.23 400	14.61 405	67.74 403	36.01 399	18.23 403	72.95 393

PMVS	41.42 23	45.67 369	42.50 372	55.17 385	34.28 411	32.37 411	66.24 399	78.71 403	30.72 401	22.04 406	59.59 397	4.59 410	77.85 402	27.49 401	58.84 384	55.29 399
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
tmp_tt		53.66 367	52.86 369	56.05 384	32.75 412	41.97 408	73.42 398	76.12 405	21.91 405	39.68 401	96.39 206	42.59 385	65.10 404	78.00 305	14.92 405	61.08 397

testmvs		18.81 374	23.05 377	6.10 391	4.48 413	2.29 416	97.78 241	3.00 414	3.27 407	18.60 407	62.71 395	1.53 414	2.49 410	14.26 408	1.80 407	13.50 405

test123		16.58 376	19.47 378	7.91 390	3.59 414	5.37 415	94.32 332	1.39 415	2.49 408	13.98 408	44.60 405	2.91 413	2.65 409	11.35 409	0.57 408	15.70 404

test_blank		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

eth-test2					0.00 415

eth-test					0.00 415

uanet_test		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

DCPMVS		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

cdsmvs_eth3d_5k		22.52 373	30.03 376	0.00 392	0.00 415	0.00 417	0.00 403	97.17 173	0.00 410	0.00 411	98.77 87	74.35 245	0.00 411	0.00 410	0.00 409	0.00 407

pcd_1.5k_mvsjas		6.87 378	9.16 381	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	82.48 181	0.00 411	0.00 410	0.00 409	0.00 407

sosnet-low-res		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

sosnet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uncertanet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

Regformer		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

ab-mvs-re		8.21 377	10.94 380	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	98.50 110	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

uanet		0.00 379	0.00 382	0.00 392	0.00 415	0.00 417	0.00 403	0.00 416	0.00 410	0.00 411	0.00 410	0.00 415	0.00 411	0.00 410	0.00 409	0.00 407

WAC-MVS						79.74 335								67.75 360

PC_three_1452									94.60 38	99.41 4	99.12 48	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

test_241102_TWO								97.72 81	94.17 45	99.23 11	99.54 3	93.14 23	99.98 9	99.70 4	99.82 19	99.99 1

test_0728_THIRD									93.01 72	99.07 16	99.46 10	94.66 13	99.97 21	99.25 18	99.82 19	99.95 15

GSMVS																98.84 139

sam_mvs1												88.39 68				98.84 139

sam_mvs												87.08 96

MTGPA								97.45 144

test_post1							90.74 371				41.37 407	85.38 135	96.36 285	83.16 264

test_post											46.00 404	87.37 87	97.11 247

patchmatchnet-post											84.86 368	88.73 65	96.81 260

MTMP							99.21 89	91.09 377

test9_res														98.60 33	99.87 9	99.90 22

agg_prior2														97.84 56	99.87 9	99.91 21

test_prior4						92.00 97	99.41 69

test_prior2							99.57 43		91.43 107	98.12 45	98.97 64	90.43 45		98.33 42	99.81 23

旧先验2							98.67 157		85.75 259	98.96 21			98.97 153	93.84 134

新几何2							98.26 206

无先验							98.52 174	97.82 65	87.20 229				99.90 50	87.64 211		99.85 30

原ACMM2							98.69 154

testdata2													99.88 54	84.16 252

segment_acmp												90.56 43

testdata1							97.89 234		92.43 84

plane_prior5								96.30 227					97.75 217	93.46 143	86.17 249	92.67 259

plane_prior4											96.52 200

plane_prior3						85.91 254			93.65 63	86.99 224

plane_prior2							99.02 121		93.38 68

plane_prior						86.07 250	99.14 106		93.81 60						86.26 248

n2								0.00 416

nn								0.00 416

door-mid								84.90 396

test11								97.68 90

door								85.30 394

HQP5-MVS						86.39 235

BP-MVS														93.82 136

HQP4-MVS										87.57 216			97.77 211			92.72 257

HQP3-MVS								96.37 223							86.29 246

HQP2-MVS												73.34 252

MDTV_nov1_ep13_2view						91.17 114	91.38 363		87.45 226	93.08 150		86.67 107		87.02 214		98.95 130

ACMMP++_ref															82.64 282

ACMMP++															83.83 270

Test By Simon												83.62 155

High-resolution multi-view benchmark