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.

PC_three_1452									82.47 314	97.09 19	97.07 72	92.72 1	98.04 202	92.70 81	99.02 12	98.86 16

DVP-MVS++		95.98 1	96.36 1	94.82 35	97.78 61	86.00 55	98.29 1	97.49 11	90.75 31	97.62 8	98.06 24	92.59 2	99.61 7	95.64 33	99.02 12	98.86 16

OPU-MVS				96.21 3	98.00 49	90.85 3	97.13 19				97.08 70	92.59 2	98.94 93	92.25 94	98.99 14	98.84 19

MED-MVS		95.95 2	96.31 2	94.90 25	98.88 1	85.89 66	97.32 10	97.86 1	90.76 29	97.21 14	98.09 18	92.42 4	99.67 1	95.27 41	98.95 15	99.14 2

SED-MVS		95.91 3	96.28 3	94.80 38	98.77 8	85.99 57	97.13 19	97.44 20	90.31 44	97.71 2	98.07 22	92.31 5	99.58 14	95.66 31	99.13 3	98.84 19

test_241102_ONE					98.77 8	85.99 57		97.44 20	90.26 50	97.71 2	97.96 33	92.31 5	99.38 36

test_0728_THIRD									90.75 31	97.04 21	98.05 27	92.09 7	99.55 21	95.64 33	99.13 3	99.13 4

DPE-MVS		95.57 5	95.67 5	95.25 12	98.36 32	87.28 19	95.56 119	97.51 10	89.13 91	97.14 17	97.91 34	91.64 8	99.62 5	94.61 50	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
DVP-MVS		95.67 4	96.02 4	94.64 44	98.78 6	85.93 60	97.09 21	96.73 99	90.27 48	97.04 21	98.05 27	91.47 9	99.55 21	95.62 35	99.08 7	98.45 42
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 60	97.19 16	97.47 16	90.27 48	97.64 6	98.13 7	91.47 9

test_241102_TWO								97.44 20	90.31 44	97.62 8	98.07 22	91.46 11	99.58 14	95.66 31	99.12 6	98.98 12

test_one_0601					98.58 14	85.83 69		97.44 20	91.05 23	96.78 27	98.06 24	91.45 12

MSP-MVS		95.42 7	95.56 7	94.98 21	98.49 20	86.52 38	96.91 30	97.47 16	91.73 14	96.10 36	96.69 87	89.90 13	99.30 49	94.70 48	98.04 80	99.13 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
DeepPCF-MVS	89.96 1	94.20 47	94.77 31	92.49 152	96.52 99	80.00 280	94.00 241	97.08 60	90.05 52	95.65 48	97.29 57	89.66 14	98.97 88	93.95 56	98.71 36	98.50 32

test-260524					98.47 21	86.91 23		97.38 27		95.81 44		89.60 15	99.63 4	95.95 29	98.95 15

SD-MVS		94.96 18	95.33 12	93.88 71	97.25 80	86.69 30	96.19 57	97.11 59	90.42 40	96.95 23	97.27 58	89.53 16	96.91 326	94.38 52	98.85 22	98.03 92
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
CNVR-MVS		95.40 8	95.37 11	95.50 8	98.11 43	88.51 8	95.29 132	96.96 69	92.09 10	95.32 51	97.08 70	89.49 17	99.33 46	95.10 44	98.85 22	98.66 26

APDe-MVS		95.46 6	95.64 6	94.91 23	98.26 35	86.29 48	97.46 7	97.40 26	89.03 97	96.20 35	98.10 14	89.39 18	99.34 43	95.88 30	99.03 11	99.10 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
TestfortrainingZip				95.40 9	97.32 75	88.97 6	97.32 10	96.82 86	89.07 92	95.69 46	96.49 100	89.27 19	99.29 51		95.80 144	97.95 98

aaEdge-Enhanced		95.17 12	95.29 14	94.81 36	98.39 29	85.89 66	95.91 88	97.55 8	89.01 99	95.86 42	97.54 46	89.24 20	99.59 11	95.27 41	98.85 22	98.95 13

MCST-MVS		94.45 34	94.20 51	95.19 14	98.46 23	87.50 17	95.00 156	97.12 56	87.13 177	92.51 114	96.30 106	89.24 20	99.34 43	93.46 64	98.62 50	98.73 23

TSAR-MVS + MP.		94.85 19	94.94 24	94.58 47	98.25 36	86.33 44	96.11 67	96.62 109	88.14 132	96.10 36	96.96 76	89.09 22	98.94 93	94.48 51	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
TestfortrainingZip a		95.33 9	95.44 10	94.99 20	98.88 1	86.26 49	97.32 10	97.43 25	90.76 29	96.80 26	98.09 18	89.00 23	99.58 14	93.66 61	96.99 113	99.14 2

SteuartSystems-ACMMP		95.20 10	95.32 13	94.85 28	96.99 83	86.33 44	97.33 8	97.30 38	91.38 19	95.39 50	97.46 50	88.98 24	99.40 35	94.12 54	98.89 20	98.82 21
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 10	95.07 20	95.59 6	98.14 42	88.48 9	96.26 54	97.28 41	85.90 213	97.67 4	98.10 14	88.41 25	99.56 17	94.66 49	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
patch_mono-2		93.74 65	94.32 41	92.01 184	97.54 67	78.37 333	93.40 277	97.19 45	88.02 140	94.99 58	97.21 62	88.35 26	98.44 155	94.07 55	98.09 77	99.23 1

9.14			94.47 35		97.79 59		96.08 69	97.44 20	86.13 211	95.10 56	97.40 53	88.34 27	99.22 54	93.25 69	98.70 38

SF-MVS		94.97 17	94.90 28	95.20 13	97.84 57	87.76 11	96.65 39	97.48 15	87.76 156	95.71 45	97.70 42	88.28 28	99.35 42	93.89 58	98.78 30	98.48 35

HPM-MVS++		95.14 13	94.91 26	95.83 4	98.25 36	89.65 4	95.92 87	96.96 69	91.75 13	94.02 73	96.83 82	88.12 29	99.55 21	93.41 67	98.94 18	98.28 62

dcpmvs_2		93.49 70	94.19 52	91.38 227	97.69 64	76.78 377	94.25 216	96.29 133	88.33 122	94.46 61	96.88 79	88.07 30	98.64 131	93.62 63	98.09 77	98.73 23

CSCG		93.23 85	93.05 86	93.76 78	98.04 47	84.07 114	96.22 56	97.37 28	84.15 270	90.05 190	95.66 157	87.77 31	99.15 62	89.91 153	98.27 62	98.07 84

NCCC		94.81 22	94.69 32	95.17 15	97.83 58	87.46 18	95.66 110	96.93 73	92.34 7	93.94 74	96.58 97	87.74 32	99.44 34	92.83 76	98.40 58	98.62 27

TEST9					97.53 68	86.49 39	94.07 232	96.78 91	81.61 344	92.77 102	96.20 110	87.71 33	99.12 64

train_agg		93.44 75	93.08 85	94.52 49	97.53 68	86.49 39	94.07 232	96.78 91	81.86 335	92.77 102	96.20 110	87.63 34	99.12 64	92.14 100	98.69 39	97.94 99

test_8					97.49 70	86.30 47	94.02 238	96.76 94	81.86 335	92.70 106	96.20 110	87.63 34	99.02 74

ZD-MVS					98.15 41	86.62 35		97.07 61	83.63 283	94.19 66	96.91 78	87.57 36	99.26 52	91.99 107	98.44 57

fmvsm_l_conf0.5_n		94.29 41	94.46 36	93.79 77	95.28 160	85.43 78	95.68 107	96.43 122	86.56 196	96.84 25	97.81 39	87.56 37	98.77 116	97.14 15	96.82 121	97.16 175

fmvsm_l_conf0.5_n_a		94.20 47	94.40 38	93.60 83	95.29 159	84.98 85	95.61 115	96.28 136	86.31 203	96.75 28	97.86 37	87.40 38	98.74 120	97.07 17	97.02 112	97.07 180

TSAR-MVS + GP.		93.66 67	93.41 78	94.41 54	96.59 93	86.78 28	94.40 203	93.93 326	89.77 67	94.21 65	95.59 161	87.35 39	98.61 137	92.72 79	96.15 138	97.83 119

APD-MVS		94.24 43	94.07 56	94.75 41	98.06 46	86.90 25	95.88 90	96.94 72	85.68 220	95.05 57	97.18 66	87.31 40	99.07 66	91.90 113	98.61 52	98.28 62
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 41

reproduce-ours		94.82 20	94.97 22	94.38 55	97.91 54	85.46 76	95.86 91	97.15 52	89.82 60	95.23 54	98.10 14	87.09 42	99.37 38	95.30 39	98.25 67	98.30 56

our_new_method		94.82 20	94.97 22	94.38 55	97.91 54	85.46 76	95.86 91	97.15 52	89.82 60	95.23 54	98.10 14	87.09 42	99.37 38	95.30 39	98.25 67	98.30 56

旧先验1					96.79 87	81.81 200		95.67 211			96.81 84	86.69 44			97.66 98	96.97 190

lecture		95.10 14	95.46 9	94.01 66	98.40 27	84.36 108	97.70 3	97.78 3	91.19 20	96.22 34	98.08 21	86.64 45	99.37 38	94.91 46	98.26 63	98.29 61

test_prior2							94.12 224		87.67 160	92.63 110	96.39 105	86.62 46		91.50 121	98.67 44

CDPH-MVS		92.83 94	92.30 103	94.44 50	97.79 59	86.11 54	94.06 234	96.66 106	80.09 366	92.77 102	96.63 94	86.62 46	99.04 70	87.40 196	98.66 45	98.17 75

DPM-MVS		92.58 100	91.74 111	95.08 16	96.19 108	89.31 5	92.66 318	96.56 114	83.44 289	91.68 141	95.04 193	86.60 48	98.99 83	85.60 223	97.92 85	96.93 194

reproduce_model		94.76 24	94.92 25	94.29 61	97.92 50	85.18 82	95.95 85	97.19 45	89.67 70	95.27 53	98.16 6	86.53 49	99.36 41	95.42 38	98.15 73	98.33 51

test_fmvsmconf_n		94.60 28	94.81 30	93.98 67	94.62 209	84.96 86	96.15 62	97.35 30	89.37 80	96.03 39	98.11 11	86.36 50	99.01 76	97.45 10	97.83 90	97.96 97

DELS-MVS		93.43 79	93.25 81	93.97 68	95.42 154	85.04 84	93.06 299	97.13 55	90.74 33	91.84 133	95.09 192	86.32 51	99.21 56	91.22 125	98.45 56	97.65 133
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
test_fmvsm_n_1920		94.71 26	95.11 19	93.50 85	95.79 134	84.62 93	96.15 62	97.64 5	89.85 59	97.19 16	97.89 35	86.28 52	98.71 123	97.11 16	98.08 79	97.17 168

ZNCC-MVS		94.47 33	94.28 45	95.03 17	98.52 18	86.96 21	96.85 33	97.32 35	88.24 127	93.15 89	97.04 73	86.17 53	99.62 5	92.40 88	98.81 27	98.52 31

HFP-MVS		94.52 31	94.40 38	94.86 27	98.61 13	86.81 27	96.94 25	97.34 31	88.63 112	93.65 79	97.21 62	86.10 54	99.49 31	92.35 91	98.77 32	98.30 56

MVS_111021_HR		93.45 74	93.31 79	93.84 73	96.99 83	84.84 87	93.24 290	97.24 42	88.76 107	91.60 142	95.85 143	86.07 55	98.66 126	91.91 111	98.16 71	98.03 92

ACMMP_NAP		94.74 25	94.56 33	95.28 11	98.02 48	87.70 12	95.68 107	97.34 31	88.28 126	95.30 52	97.67 43	85.90 56	99.54 25	93.91 57	98.95 15	98.60 28

fmvsm_l_conf0.5_n_9		94.65 27	95.28 15	92.77 126	95.95 130	81.83 199	95.53 120	97.12 56	91.68 16	97.89 1	98.06 24	85.71 57	98.65 128	97.32 12	98.26 63	97.83 119

CS-MVS		94.12 51	94.44 37	93.17 99	96.55 96	83.08 154	97.63 4	96.95 71	91.71 15	93.50 85	96.21 109	85.61 58	98.24 172	93.64 62	98.17 70	98.19 73

PHI-MVS		93.89 60	93.65 74	94.62 46	96.84 86	86.43 41	96.69 37	97.49 11	85.15 244	93.56 83	96.28 107	85.60 59	99.31 48	92.45 85	98.79 28	98.12 82

MP-MVS-pluss		94.21 45	94.00 59	94.85 28	98.17 40	86.65 33	94.82 169	97.17 50	86.26 205	92.83 99	97.87 36	85.57 60	99.56 17	94.37 53	98.92 19	98.34 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 45	93.97 60	94.90 25	98.41 26	86.82 26	96.54 41	97.19 45	88.24 127	93.26 86	96.83 82	85.48 61	99.59 11	91.43 123	98.40 58	98.30 56

MP-MVS		94.25 42	94.07 56	94.77 40	98.47 21	86.31 46	96.71 36	96.98 65	89.04 95	91.98 125	97.19 65	85.43 62	99.56 17	92.06 105	98.79 28	98.44 43
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	89.43 2	94.04 53	93.79 65	94.80 38	97.48 71	86.78 28	95.65 112	96.89 78	89.40 79	92.81 100	96.97 75	85.37 63	99.24 53	90.87 134	98.69 39	98.38 48
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_11		94.60 28	95.23 16	92.69 138	96.05 121	82.00 192	96.31 46	96.71 102	92.27 8	96.68 30	98.39 2	85.32 64	98.92 96	97.20 14	98.16 71	97.17 168

region2R		94.43 36	94.27 47	94.92 22	98.65 11	86.67 32	96.92 29	97.23 44	88.60 115	93.58 81	97.27 58	85.22 65	99.54 25	92.21 96	98.74 35	98.56 30

CP-MVS		94.34 40	94.21 50	94.74 42	98.39 29	86.64 34	97.60 5	97.24 42	88.53 117	92.73 105	97.23 61	85.20 66	99.32 47	92.15 99	98.83 26	98.25 70

test_fmvsmconf0.1_n		94.20 47	94.31 43	93.88 71	92.46 336	84.80 89	96.18 59	96.82 86	89.29 85	95.68 47	98.11 11	85.10 67	98.99 83	97.38 11	97.75 96	97.86 114

test12				94.34 58	97.13 81	86.15 53		96.29 133		91.04 164		85.08 68	99.01 76		98.13 75	97.86 114

ACMMPR		94.43 36	94.28 45	94.91 23	98.63 12	86.69 30	96.94 25	97.32 35	88.63 112	93.53 84	97.26 60	85.04 69	99.54 25	92.35 91	98.78 30	98.50 32

SPE-MVS-test		94.02 54	94.29 44	93.24 93	96.69 89	83.24 142	97.49 6	96.92 74	92.14 9	92.90 95	95.77 152	85.02 70	98.33 167	93.03 73	98.62 50	98.13 79

XVS		94.45 34	94.32 41	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 36	92.85 97	97.16 68	85.02 70	99.49 31	91.99 107	98.56 54	98.47 38

X-MVStestdata		88.31 242	86.13 291	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 36	92.85 97	23.41 539	85.02 70	99.49 31	91.99 107	98.56 54	98.47 38

MVSMamba_PlusPlus		93.44 75	93.54 76	93.14 101	96.58 95	83.05 155	96.06 73	96.50 119	84.42 266	94.09 69	95.56 163	85.01 73	98.69 125	94.96 45	98.66 45	97.67 132

fmvsm_l_conf0.5_n_3		94.80 23	95.01 21	94.15 64	95.64 143	85.08 83	96.09 68	97.36 29	90.98 24	97.09 19	98.12 10	84.98 74	98.94 93	97.07 17	97.80 92	98.43 44

MSLP-MVS++		93.72 66	94.08 55	92.65 141	97.31 76	83.43 135	95.79 98	97.33 33	90.03 53	93.58 81	96.96 76	84.87 75	97.76 233	92.19 98	98.66 45	96.76 205

HPM-MVS		94.02 54	93.88 61	94.43 52	98.39 29	85.78 71	97.25 15	97.07 61	86.90 188	92.62 111	96.80 86	84.85 76	99.17 58	92.43 86	98.65 48	98.33 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_9		94.99 16	95.50 8	93.44 86	96.51 101	82.25 187	95.76 102	96.92 74	93.37 3	97.63 7	98.43 1	84.82 77	99.16 61	98.15 1	97.92 85	98.90 15

SR-MVS		94.23 44	94.17 54	94.43 52	98.21 39	85.78 71	96.40 43	96.90 77	88.20 130	94.33 63	97.40 53	84.75 78	99.03 71	93.35 68	97.99 82	98.48 35

PGM-MVS		93.96 58	93.72 70	94.68 43	98.43 24	86.22 50	95.30 130	97.78 3	87.45 167	93.26 86	97.33 56	84.62 79	99.51 29	90.75 137	98.57 53	98.32 55

BridgeMVS		93.98 57	94.22 48	93.26 92	96.13 111	83.29 141	96.27 53	96.52 117	89.82 60	95.56 49	95.51 166	84.50 80	98.79 114	94.83 47	98.86 21	97.72 129

EI-MVSNet-Vis-set		93.01 92	92.92 89	93.29 90	95.01 174	83.51 134	94.48 191	95.77 199	90.87 25	92.52 113	96.67 89	84.50 80	99.00 81	91.99 107	94.44 185	97.36 152

MTAPA		94.42 39	94.22 48	95.00 19	98.42 25	86.95 22	94.36 211	96.97 66	91.07 22	93.14 90	97.56 45	84.30 82	99.56 17	93.43 65	98.75 34	98.47 38

SR-MVS-dyc-post		93.82 62	93.82 63	93.82 74	97.92 50	84.57 95	96.28 51	96.76 94	87.46 165	93.75 77	97.43 51	84.24 83	99.01 76	92.73 77	97.80 92	97.88 112

ETV-MVS		92.74 98	92.66 95	92.97 113	95.20 166	84.04 118	95.07 151	96.51 118	90.73 34	92.96 94	91.19 348	84.06 84	98.34 165	91.72 116	96.54 128	96.54 218

EI-MVSNet-UG-set		92.74 98	92.62 97	93.12 102	94.86 188	83.20 144	94.40 203	95.74 202	90.71 35	92.05 123	96.60 96	84.00 85	98.99 83	91.55 119	93.63 213	97.17 168

mPP-MVS		93.99 56	93.78 66	94.63 45	98.50 19	85.90 65	96.87 31	96.91 76	88.70 110	91.83 135	97.17 67	83.96 86	99.55 21	91.44 122	98.64 49	98.43 44

APD-MVS_3200maxsize		93.78 63	93.77 67	93.80 76	97.92 50	84.19 112	96.30 47	96.87 80	86.96 184	93.92 75	97.47 49	83.88 87	98.96 90	92.71 80	97.87 88	98.26 69

EIA-MVS		91.95 111	91.94 108	91.98 188	95.16 168	80.01 279	95.36 125	96.73 99	88.44 118	89.34 203	92.16 311	83.82 88	98.45 153	89.35 163	97.06 110	97.48 147

fmvsm_s_conf0.5_n_3		94.49 32	95.13 17	92.56 146	95.49 152	81.10 227	95.93 86	97.16 51	92.96 4	97.39 12	98.13 7	83.63 89	98.80 112	97.89 3	97.61 99	97.78 125

fmvsm_s_conf0.5_n		93.76 64	94.06 58	92.86 120	95.62 145	83.17 146	96.14 64	96.12 166	88.13 133	95.82 43	98.04 30	83.43 90	98.48 145	96.97 21	96.23 135	96.92 195

casdiffmvs_mvg		92.96 93	92.83 91	93.35 88	94.59 213	83.40 137	95.00 156	96.34 130	90.30 46	92.05 123	96.05 125	83.43 90	98.15 180	92.07 102	95.67 148	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
EPP-MVSNet		91.70 128	91.56 118	92.13 183	95.88 131	80.50 259	97.33 8	95.25 250	86.15 208	89.76 196	95.60 160	83.42 92	98.32 169	87.37 198	93.25 228	97.56 141

test_fmvsmvis_n_1920		93.44 75	93.55 75	93.10 103	93.67 286	84.26 110	95.83 95	96.14 162	89.00 100	92.43 116	97.50 48	83.37 93	98.72 121	96.61 24	97.44 102	96.32 223

fmvsm_s_conf0.5_n_5		93.96 58	94.18 53	93.30 89	94.79 192	83.81 123	95.77 100	96.74 98	88.02 140	96.23 33	97.84 38	83.36 94	98.83 110	97.49 8	97.34 106	97.25 160

fmvsm_s_conf0.5_n_6		94.11 52	94.56 33	92.76 129	94.98 178	81.96 196	95.79 98	97.29 40	89.31 83	97.52 11	97.61 44	83.25 95	98.88 100	97.05 19	98.22 69	97.43 151

UA-Net		92.83 94	92.54 98	93.68 82	96.10 116	84.71 91	95.66 110	96.39 126	91.92 11	93.22 88	96.49 100	83.16 96	98.87 101	84.47 244	95.47 155	97.45 149

UniMVSNet_NR-MVSNet		89.92 187	89.29 190	91.81 205	93.39 295	83.72 125	94.43 197	97.12 56	89.80 63	86.46 265	93.32 271	83.16 96	97.23 300	84.92 232	81.02 409	94.49 310

EC-MVSNet		93.44 75	93.71 71	92.63 142	95.21 165	82.43 180	97.27 14	96.71 102	90.57 39	92.88 96	95.80 148	83.16 96	98.16 179	93.68 60	98.14 74	97.31 153

fmvsm_s_conf0.5_n_4		93.86 61	94.37 40	92.33 165	95.13 171	80.95 234	95.64 113	96.97 66	89.60 72	96.85 24	97.77 40	83.08 99	98.92 96	97.49 8	96.78 122	97.13 176

fmvsm_s_conf0.5_n_a		93.57 68	93.76 68	93.00 111	95.02 173	83.67 127	96.19 57	96.10 168	87.27 171	95.98 40	98.05 27	83.07 100	98.45 153	96.68 23	95.51 152	96.88 198

MM		95.10 14	94.91 26	95.68 5	96.09 117	88.34 10	96.68 38	94.37 308	95.08 1	94.68 59	97.72 41	82.94 101	99.64 3	97.85 5	98.76 33	99.06 9

RE-MVS-def			93.68 72		97.92 50	84.57 95	96.28 51	96.76 94	87.46 165	93.75 77	97.43 51	82.94 101		92.73 77	97.80 92	97.88 112

新几何1				93.10 103	97.30 77	84.35 109		95.56 221	71.09 472	91.26 152	96.24 108	82.87 103	98.86 103	79.19 347	98.10 76	96.07 239

fmvsm_s_conf0.1_n		93.46 72	93.66 73	92.85 121	93.75 278	83.13 148	96.02 77	95.74 202	87.68 159	95.89 41	98.17 5	82.78 104	98.46 149	96.71 22	96.17 137	96.98 189

Casviewmamba		92.82 96	92.75 92	93.03 108	94.79 192	82.44 179	95.39 124	96.24 144	90.58 38	91.79 137	96.43 104	82.73 105	98.19 177	91.31 124	95.54 150	98.46 41

原ACMM1				92.01 184	97.34 74	81.05 229		96.81 89	78.89 382	90.45 174	95.92 136	82.65 106	98.84 107	80.68 315	98.26 63	96.14 233

casdiffmvs		92.51 101	92.43 100	92.74 133	94.41 233	81.98 194	94.54 188	96.23 146	89.57 74	91.96 127	96.17 115	82.58 107	98.01 209	90.95 132	95.45 157	98.23 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepC-MVS	88.79 3	93.31 81	92.99 88	94.26 62	96.07 119	85.83 69	94.89 162	96.99 64	89.02 98	89.56 198	97.37 55	82.51 108	99.38 36	92.20 97	98.30 61	97.57 140
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HPM-MVS_fast		93.40 80	93.22 82	93.94 70	98.36 32	84.83 88	97.15 18	96.80 90	85.77 217	92.47 115	97.13 69	82.38 109	99.07 66	90.51 142	98.40 58	97.92 108

baseline		92.39 106	92.29 104	92.69 138	94.46 228	81.77 204	94.14 223	96.27 137	89.22 87	91.88 131	96.00 129	82.35 110	97.99 211	91.05 127	95.27 163	98.30 56

sasdasda		93.27 82	92.75 92	94.85 28	95.70 140	87.66 13	96.33 44	96.41 124	90.00 54	94.09 69	94.60 219	82.33 111	98.62 134	92.40 88	92.86 240	98.27 65

canonicalmvs		93.27 82	92.75 92	94.85 28	95.70 140	87.66 13	96.33 44	96.41 124	90.00 54	94.09 69	94.60 219	82.33 111	98.62 134	92.40 88	92.86 240	98.27 65

fmvsm_s_conf0.1_n_a		93.19 86	93.26 80	92.97 113	92.49 334	83.62 130	96.02 77	95.72 206	86.78 190	96.04 38	98.19 4	82.30 113	98.43 157	96.38 25	95.42 158	96.86 199

DP-MVS Recon		91.95 111	91.28 132	93.96 69	98.33 34	85.92 62	94.66 182	96.66 106	82.69 312	90.03 191	95.82 146	82.30 113	99.03 71	84.57 242	96.48 131	96.91 196

hybridcas		92.43 104	92.33 101	92.74 133	94.51 221	81.84 198	95.05 154	96.16 160	89.60 72	91.40 149	96.20 110	82.23 115	98.09 191	89.95 152	95.87 142	98.28 62

PAPR		90.02 181	89.27 192	92.29 172	95.78 135	80.95 234	92.68 317	96.22 147	81.91 331	86.66 262	93.75 261	82.23 115	98.44 155	79.40 346	94.79 171	97.48 147

MVS_Test		91.31 137	91.11 135	91.93 193	94.37 234	80.14 268	93.46 275	95.80 197	86.46 199	91.35 151	93.77 259	82.21 117	98.09 191	87.57 193	94.95 167	97.55 143

nrg030		91.08 148	90.39 154	93.17 99	93.07 307	86.91 23	96.41 42	96.26 141	88.30 124	88.37 223	94.85 206	82.19 118	97.64 244	91.09 126	82.95 379	94.96 284

MGCFI-Net		93.03 91	92.63 96	94.23 63	95.62 145	85.92 62	96.08 69	96.33 131	89.86 58	93.89 76	94.66 216	82.11 119	98.50 143	92.33 93	92.82 243	98.27 65

UniMVSNet (Re)		89.80 191	89.07 196	92.01 184	93.60 289	84.52 98	94.78 173	97.47 16	89.26 86	86.44 268	92.32 306	82.10 120	97.39 283	84.81 235	80.84 413	94.12 324

testdata				90.49 273	96.40 102	77.89 349		95.37 241	72.51 464	93.63 80	96.69 87	82.08 121	97.65 242	83.08 263	97.39 103	95.94 244

PAPM_NR		91.22 140	90.78 146	92.52 150	97.60 66	81.46 213	94.37 209	96.24 144	86.39 202	87.41 245	94.80 208	82.06 122	98.48 145	82.80 271	95.37 159	97.61 136

MG-MVS		91.77 119	91.70 112	92.00 187	97.08 82	80.03 278	93.60 270	95.18 256	87.85 152	90.89 167	96.47 102	82.06 122	98.36 162	85.07 230	97.04 111	97.62 134

CANet		93.54 69	93.20 83	94.55 48	95.65 142	85.73 73	94.94 159	96.69 105	91.89 12	90.69 169	95.88 139	81.99 124	99.54 25	93.14 71	97.95 84	98.39 46

FC-MVSNet-test		90.27 172	90.18 160	90.53 266	93.71 283	79.85 287	95.77 100	97.59 6	89.31 83	86.27 272	94.67 215	81.93 125	97.01 319	84.26 246	88.09 324	94.71 296

fmvsm_s_conf0.5_n_10		94.43 36	94.84 29	93.20 95	95.73 137	83.19 145	95.99 79	97.31 37	91.08 21	97.67 4	98.11 11	81.87 126	99.22 54	97.86 4	97.91 87	97.20 166

fmvsm_s_conf0.5_n_7		93.15 89	93.76 68	91.31 230	94.42 232	79.48 299	94.52 189	97.14 54	89.33 82	94.17 67	98.09 18	81.83 127	97.49 260	96.33 26	98.02 81	96.95 191

FIs		90.51 168	90.35 155	90.99 248	93.99 265	80.98 232	95.73 104	97.54 9	89.15 90	86.72 261	94.68 212	81.83 127	97.24 299	85.18 228	88.31 321	94.76 295

fmvsm_s_conf0.5_n_8		94.56 30	95.12 18	92.87 119	95.96 129	81.32 217	95.76 102	97.57 7	93.48 2	97.53 10	98.32 3	81.78 129	99.13 63	97.91 2	97.81 91	98.16 76

E3new		91.76 120	91.58 116	92.28 176	94.69 206	80.90 237	93.68 268	96.17 158	87.15 175	91.09 163	95.70 156	81.75 130	98.05 201	89.67 160	94.35 187	97.90 111

viewcassd2359sk11		91.79 114	91.62 113	92.29 172	94.62 209	80.88 238	93.70 265	96.18 157	87.38 169	91.13 156	95.85 143	81.62 131	98.06 197	89.71 157	94.40 186	97.94 99

ACMMP		93.24 84	92.88 90	94.30 60	98.09 45	85.33 80	96.86 32	97.45 19	88.33 122	90.15 189	97.03 74	81.44 132	99.51 29	90.85 135	95.74 147	98.04 91
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
Effi-MVS+		91.59 131	91.11 135	93.01 110	94.35 238	83.39 138	94.60 184	95.10 260	87.10 178	90.57 173	93.10 282	81.43 133	98.07 196	89.29 165	94.48 183	97.59 139

MVS_111021_LR		92.47 103	92.29 104	92.98 112	95.99 126	84.43 104	93.08 296	96.09 169	88.20 130	91.12 157	95.72 155	81.33 134	97.76 233	91.74 115	97.37 104	96.75 206

E2		91.79 114	91.61 114	92.31 167	94.49 224	80.86 241	93.74 260	96.19 151	87.63 162	91.16 153	95.94 134	81.31 135	98.06 197	89.76 155	94.29 190	97.99 94

E3		91.78 117	91.61 114	92.30 170	94.48 225	80.86 241	93.73 261	96.19 151	87.63 162	91.16 153	95.95 133	81.30 136	98.06 197	89.76 155	94.29 190	97.99 94

mvs_anonymous		89.37 210	89.32 189	89.51 335	93.47 292	74.22 409	91.65 358	94.83 285	82.91 307	85.45 297	93.79 257	81.23 137	96.36 372	86.47 210	94.09 195	97.94 99

PVSNet_BlendedMVS		89.98 182	89.70 175	90.82 257	96.12 112	81.25 219	93.92 247	96.83 84	83.49 288	89.10 207	92.26 309	81.04 138	98.85 105	86.72 208	87.86 328	92.35 416

PVSNet_Blended		90.73 156	90.32 156	91.98 188	96.12 112	81.25 219	92.55 322	96.83 84	82.04 327	89.10 207	92.56 299	81.04 138	98.85 105	86.72 208	95.91 141	95.84 250

viewmanbaseed2359cas		91.78 117	91.58 116	92.37 160	94.32 241	81.07 228	93.76 258	95.96 182	87.26 172	91.50 144	95.88 139	80.92 140	97.97 216	89.70 158	94.92 168	98.07 84

E4		91.74 122	91.55 119	92.31 167	94.27 246	80.80 245	93.81 255	96.17 158	87.97 142	91.11 158	96.05 125	80.75 141	98.08 194	89.78 154	94.02 197	98.06 89

viewmamba		91.38 134	91.32 129	91.58 214	93.02 314	79.63 296	92.83 310	95.38 238	88.29 125	90.66 170	95.81 147	80.63 142	97.50 259	91.52 120	93.71 211	97.62 134

MGCNet		94.18 50	93.80 64	95.34 10	94.91 185	87.62 15	95.97 82	93.01 359	92.58 6	94.22 64	97.20 64	80.56 143	99.59 11	97.04 20	98.68 41	98.81 22

alignmvs		93.08 90	92.50 99	94.81 36	95.62 145	87.61 16	95.99 79	96.07 171	89.77 67	94.12 68	94.87 203	80.56 143	98.66 126	92.42 87	93.10 235	98.15 77

API-MVS		90.66 162	90.07 164	92.45 155	96.36 104	84.57 95	96.06 73	95.22 253	82.39 315	89.13 206	94.27 236	80.32 145	98.46 149	80.16 325	96.71 124	94.33 316

PVSNet_Blended_VisFu		91.38 134	90.91 142	92.80 124	96.39 103	83.17 146	94.87 164	96.66 106	83.29 294	89.27 205	94.46 228	80.29 146	99.17 58	87.57 193	95.37 159	96.05 242

viewdifsd2359ckpt07		91.11 146	91.02 139	91.41 225	94.21 251	78.37 333	92.91 306	95.71 207	87.50 164	90.32 179	95.88 139	80.27 147	97.99 211	88.78 176	93.55 215	97.86 114

test222					96.55 96	81.70 205	92.22 340	95.01 264	68.36 481	90.20 182	96.14 120	80.26 148			97.80 92	96.05 242

diffmvs		91.37 136	91.23 133	91.77 206	93.09 305	80.27 263	92.36 328	95.52 226	87.03 181	91.40 149	94.93 199	80.08 149	97.44 269	92.13 101	94.56 180	97.61 136
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Test By Simon												80.02 150

onestephybrid01		91.23 138	91.10 137	91.61 212	93.07 307	79.86 285	92.83 310	95.34 244	87.07 179	91.04 164	95.53 164	80.01 151	97.43 270	90.96 131	94.08 196	97.56 141

diffmvs_AUTHOR		91.51 132	91.44 125	91.73 207	93.09 305	80.27 263	92.51 323	95.58 220	87.22 173	91.80 136	95.57 162	79.96 152	97.48 261	92.23 95	94.97 166	97.45 149

E5new		91.71 124	91.55 119	92.20 178	94.33 239	80.62 251	94.41 199	96.19 151	88.06 136	91.11 158	96.16 116	79.92 153	98.03 205	90.00 147	93.80 206	97.94 99

E6new		91.71 124	91.55 119	92.20 178	94.32 241	80.62 251	94.41 199	96.19 151	88.06 136	91.11 158	96.16 116	79.92 153	98.03 205	90.00 147	93.80 206	97.94 99

E6		91.71 124	91.55 119	92.20 178	94.32 241	80.62 251	94.41 199	96.19 151	88.06 136	91.11 158	96.16 116	79.92 153	98.03 205	90.00 147	93.80 206	97.94 99

E5		91.71 124	91.55 119	92.20 178	94.33 239	80.62 251	94.41 199	96.19 151	88.06 136	91.11 158	96.16 116	79.92 153	98.03 205	90.00 147	93.80 206	97.94 99

viewmacassd2359aftdt		91.67 130	91.43 126	92.37 160	93.95 269	81.00 231	93.90 252	95.97 181	87.75 157	91.45 147	96.04 127	79.92 153	97.97 216	89.26 166	94.67 174	98.14 78

IterMVS-LS		88.36 241	87.91 235	89.70 319	93.80 275	78.29 337	93.73 261	95.08 262	85.73 218	84.75 318	91.90 327	79.88 158	96.92 325	83.83 253	82.51 385	93.89 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 215	88.86 207	89.80 313	91.84 356	78.30 336	93.70 265	95.01 264	85.73 218	87.15 249	95.28 179	79.87 159	97.21 302	83.81 254	87.36 336	93.88 339

TAPA-MVS	84.62 6	88.16 246	87.01 256	91.62 211	96.64 91	80.65 248	94.39 205	96.21 150	76.38 423	86.19 275	95.44 169	79.75 160	98.08 194	62.75 473	95.29 161	96.13 234
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 206	88.64 210	91.71 209	94.74 197	80.81 244	93.54 271	95.10 260	83.11 298	86.82 260	90.67 371	79.74 161	97.75 237	80.51 318	93.55 215	96.57 216

pcd_1.5k_mvsjas		6.64 525	8.86 526	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	79.70 162	0.00 561	0.00 560	0.00 560	0.00 557

PS-MVSNAJss		89.97 183	89.62 178	91.02 245	91.90 354	80.85 243	95.26 136	95.98 178	86.26 205	86.21 274	94.29 233	79.70 162	97.65 242	88.87 175	88.10 322	94.57 302

PS-MVSNAJ		91.18 142	90.92 141	91.96 190	95.26 163	82.60 177	92.09 345	95.70 208	86.27 204	91.84 133	92.46 301	79.70 162	98.99 83	89.08 168	95.86 143	94.29 317

viewdifsd2359ckpt09		91.18 142	90.65 150	92.75 131	94.61 212	82.36 185	94.32 212	95.74 202	84.72 259	89.66 197	95.15 190	79.69 165	98.04 202	87.70 190	94.27 192	97.85 117

viewdifsd2359ckpt13		91.20 141	90.75 147	92.54 148	94.30 244	82.13 189	94.03 236	95.89 190	85.60 223	90.20 182	95.36 175	79.69 165	97.90 226	87.85 188	93.86 202	97.61 136

xiu_mvs_v2_base		91.13 144	90.89 143	91.86 199	94.97 179	82.42 181	92.24 338	95.64 216	86.11 212	91.74 140	93.14 280	79.67 167	98.89 99	89.06 169	95.46 156	94.28 318

WR-MVS_H		87.80 255	87.37 246	89.10 344	93.23 298	78.12 340	95.61 115	97.30 38	87.90 148	83.72 349	92.01 322	79.65 168	96.01 387	76.36 378	80.54 417	93.16 379

viewmambaseed2359dif		90.04 180	89.78 174	90.83 255	92.85 322	77.92 345	92.23 339	95.01 264	81.90 332	90.20 182	95.45 168	79.64 169	97.34 287	87.52 195	93.17 230	97.23 165

EPNet		91.79 114	91.02 139	94.10 65	90.10 422	85.25 81	96.03 76	92.05 387	92.83 5	87.39 248	95.78 151	79.39 170	99.01 76	88.13 183	97.48 101	98.05 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 286	86.62 272	89.02 348	92.13 345	77.40 366	90.91 382	94.81 287	81.28 351	84.32 335	90.08 389	79.26 171	96.62 343	83.81 254	82.94 380	93.04 386

test_fmvsmconf0.01_n		93.19 86	93.02 87	93.71 81	89.25 435	84.42 106	96.06 73	96.29 133	89.06 93	94.68 59	98.13 7	79.22 172	98.98 87	97.22 13	97.24 107	97.74 127

miper_enhance_ethall		86.90 299	86.18 289	89.06 346	91.66 365	77.58 364	90.22 401	94.82 286	79.16 378	84.48 326	89.10 408	79.19 173	96.66 336	84.06 249	82.94 380	92.94 389

hybridnocas07		90.93 149	90.72 148	91.54 216	92.75 327	79.72 293	92.35 330	95.21 254	86.41 201	90.44 177	95.40 172	79.17 174	97.39 283	90.83 136	93.94 200	97.50 146

NR-MVSNet		88.58 235	87.47 244	91.93 193	93.04 311	84.16 113	94.77 174	96.25 143	89.05 94	80.04 408	93.29 274	79.02 175	97.05 316	81.71 297	80.05 423	94.59 300

hybrid		90.69 158	90.45 153	91.43 224	92.67 332	79.42 304	92.28 337	95.21 254	85.15 244	90.39 178	95.37 174	78.93 176	97.32 289	90.27 145	93.74 210	97.55 143

TAMVS		89.21 212	88.29 223	91.96 190	93.71 283	82.62 176	93.30 285	94.19 316	82.22 321	87.78 238	93.94 249	78.83 177	96.95 323	77.70 364	92.98 237	96.32 223

c3_l		87.14 292	86.50 278	89.04 347	92.20 342	77.26 368	91.22 374	94.70 293	82.01 328	84.34 334	90.43 376	78.81 178	96.61 346	83.70 258	81.09 406	93.25 373

1112_ss		88.42 237	87.33 247	91.72 208	94.92 183	80.98 232	92.97 304	94.54 299	78.16 400	83.82 346	93.88 254	78.78 179	97.91 224	79.45 342	89.41 301	96.26 227

CDS-MVSNet		89.45 202	88.51 214	92.29 172	93.62 288	83.61 132	93.01 300	94.68 294	81.95 329	87.82 237	93.24 276	78.69 180	96.99 320	80.34 321	93.23 229	96.28 226
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 196	88.92 203	91.67 210	95.47 153	81.15 224	92.38 327	94.78 289	83.11 298	89.06 209	94.32 231	78.67 181	96.61 346	81.57 298	90.89 275	97.24 161

CPTT-MVS		91.99 110	91.80 110	92.55 147	98.24 38	81.98 194	96.76 35	96.49 120	81.89 334	90.24 180	96.44 103	78.59 182	98.61 137	89.68 159	97.85 89	97.06 181

IS-MVSNet		91.43 133	91.09 138	92.46 153	95.87 133	81.38 216	96.95 24	93.69 343	89.72 69	89.50 201	95.98 131	78.57 183	97.77 232	83.02 265	96.50 130	98.22 72

dtuplus		89.78 193	89.43 184	90.85 254	92.83 323	77.91 346	92.32 335	94.97 270	82.33 319	90.20 182	95.53 164	78.56 184	97.38 285	85.15 229	92.95 238	97.24 161

casdiffseed414692147		91.11 146	90.55 152	92.81 122	94.27 246	82.58 178	94.81 170	96.03 176	87.93 146	90.17 187	95.62 159	78.51 185	97.90 226	84.18 248	93.45 222	97.94 99

OMC-MVS		91.23 138	90.62 151	93.08 105	96.27 106	84.07 114	93.52 272	95.93 184	86.95 185	89.51 199	96.13 121	78.50 186	98.35 164	85.84 221	92.90 239	96.83 204

IMVS_0403		89.97 183	89.64 177	90.96 251	93.72 279	77.75 357	93.00 301	95.34 244	85.53 227	88.77 216	94.49 224	78.49 187	97.84 229	84.75 236	92.65 245	97.28 156

PCF-MVS	84.11 10	87.74 257	86.08 295	92.70 137	94.02 260	84.43 104	89.27 422	95.87 193	73.62 454	84.43 329	94.33 230	78.48 188	98.86 103	70.27 429	94.45 184	94.81 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 243	88.32 222	88.27 369	94.71 203	72.41 436	93.15 291	90.98 420	87.77 155	79.25 423	91.96 324	78.35 189	95.75 401	83.04 264	95.62 149	96.65 211

HY-MVS	83.01 12	89.03 221	87.94 232	92.29 172	94.86 188	82.77 163	92.08 346	94.49 302	81.52 347	86.93 252	92.79 293	78.32 190	98.23 173	79.93 328	90.55 279	95.88 248

GeoE		90.05 179	89.43 184	91.90 198	95.16 168	80.37 262	95.80 96	94.65 295	83.90 275	87.55 244	94.75 209	78.18 191	97.62 246	81.28 303	93.63 213	97.71 130

NormalMVS		93.46 72	93.16 84	94.37 57	98.40 27	86.20 51	96.30 47	96.27 137	91.65 17	92.68 107	96.13 121	77.97 192	98.84 107	90.75 137	98.26 63	98.07 84

SymmetryMVS		92.81 97	92.31 102	94.32 59	96.15 109	86.20 51	96.30 47	94.43 304	91.65 17	92.68 107	96.13 121	77.97 192	98.84 107	90.75 137	94.72 172	97.92 108

MVS		87.44 274	86.10 294	91.44 223	92.61 333	83.62 130	92.63 319	95.66 213	67.26 484	81.47 386	92.15 312	77.95 194	98.22 175	79.71 331	95.48 154	92.47 409

MVSFormer		91.68 129	91.30 130	92.80 124	93.86 271	83.88 121	95.96 83	95.90 188	84.66 262	91.76 138	94.91 200	77.92 195	97.30 290	89.64 161	97.11 108	97.24 161

lupinMVS		90.92 150	90.21 158	93.03 108	93.86 271	83.88 121	92.81 312	93.86 330	79.84 369	91.76 138	94.29 233	77.92 195	98.04 202	90.48 143	97.11 108	97.17 168

Test_1112_low_res		87.65 260	86.51 277	91.08 241	94.94 182	79.28 313	91.77 353	94.30 311	76.04 429	83.51 356	92.37 304	77.86 197	97.73 238	78.69 353	89.13 308	96.22 228

VNet		92.24 107	91.91 109	93.24 93	96.59 93	83.43 135	94.84 168	96.44 121	89.19 89	94.08 72	95.90 137	77.85 198	98.17 178	88.90 173	93.38 224	98.13 79

icg_test_0407_2		89.15 213	88.97 200	89.68 325	93.72 279	77.75 357	88.26 441	95.34 244	85.53 227	88.34 224	94.49 224	77.69 199	93.99 441	84.75 236	92.65 245	97.28 156

IMVS_0407		89.85 190	89.51 181	90.88 253	93.72 279	77.75 357	93.07 298	95.34 244	85.53 227	88.34 224	94.49 224	77.69 199	97.60 247	84.75 236	92.65 245	97.28 156

fmvsm_s_conf0.5_n_2		93.47 71	93.83 62	92.39 159	95.36 156	81.19 223	95.20 144	96.56 114	90.37 42	97.13 18	98.03 31	77.47 201	98.96 90	97.79 6	96.58 127	97.03 184

mvsany_test1		85.42 341	85.30 325	85.77 428	87.95 454	75.41 397	87.61 455	80.97 495	76.82 419	88.68 217	95.83 145	77.44 202	90.82 481	85.90 219	86.51 343	91.08 448

DU-MVS		89.34 211	88.50 215	91.85 201	93.04 311	83.72 125	94.47 194	96.59 111	89.50 75	86.46 265	93.29 274	77.25 203	97.23 300	84.92 232	81.02 409	94.59 300

Baseline_NR-MVSNet		87.07 294	86.63 271	88.40 363	91.44 369	77.87 350	94.23 219	92.57 371	84.12 271	85.74 285	92.08 318	77.25 203	96.04 383	82.29 280	79.94 424	91.30 440

jason		90.80 152	90.10 162	92.90 117	93.04 311	83.53 133	93.08 296	94.15 319	80.22 363	91.41 148	94.91 200	76.87 205	97.93 222	90.28 144	96.90 117	97.24 161
jason: jason.
PAPM		86.68 311	85.39 321	90.53 266	93.05 310	79.33 312	89.79 411	94.77 290	78.82 385	81.95 382	93.24 276	76.81 206	97.30 290	66.94 453	93.16 231	94.95 288

Vis-MVSNet (Re-imp)		89.59 197	89.44 183	90.03 299	95.74 136	75.85 391	95.61 115	90.80 427	87.66 161	87.83 236	95.40 172	76.79 207	96.46 364	78.37 354	96.73 123	97.80 123

baseline1		88.10 247	87.28 249	90.57 262	94.96 180	80.07 273	94.27 215	91.29 412	86.74 191	87.41 245	94.00 246	76.77 208	96.20 378	80.77 312	79.31 432	95.44 264

114514_t		89.51 199	88.50 215	92.54 148	98.11 43	81.99 193	95.16 147	96.36 129	70.19 476	85.81 282	95.25 181	76.70 209	98.63 133	82.07 286	96.86 120	97.00 188

PLC	84.53 7	89.06 219	88.03 228	92.15 182	97.27 79	82.69 170	94.29 214	95.44 234	79.71 371	84.01 343	94.18 239	76.68 210	98.75 117	77.28 368	93.41 223	95.02 280
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 225	87.95 231	91.49 220	92.68 331	83.01 158	94.92 161	96.31 132	89.88 57	85.53 291	93.85 256	76.63 211	96.96 322	81.91 290	79.87 426	94.50 308

MAR-MVS		90.30 171	89.37 187	93.07 107	96.61 92	84.48 100	95.68 107	95.67 211	82.36 317	87.85 234	92.85 287	76.63 211	98.80 112	80.01 327	96.68 125	95.91 245
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
fmvsm_s_conf0.1_n_2		93.16 88	93.42 77	92.37 160	94.62 209	81.13 225	95.23 137	95.89 190	90.30 46	96.74 29	98.02 32	76.14 213	98.95 92	97.64 7	96.21 136	97.03 184

SSM_0407		90.47 169	89.80 173	92.46 153	94.76 194	82.66 171	93.98 243	95.00 268	85.41 232	88.96 211	95.35 176	76.13 214	97.88 228	85.46 226	93.15 232	96.85 200

SSM_0404		90.73 156	90.08 163	92.69 138	95.00 177	83.13 148	94.32 212	95.00 268	85.41 232	89.84 192	95.35 176	76.13 214	97.98 214	85.46 226	94.18 194	96.95 191

WR-MVS		88.38 239	87.67 239	90.52 270	93.30 297	80.18 266	93.26 288	95.96 182	88.57 116	85.47 296	92.81 291	76.12 216	96.91 326	81.24 304	82.29 389	94.47 313

v8		87.50 273	86.71 265	89.89 306	91.37 374	79.40 305	94.50 190	95.38 238	84.81 256	83.60 354	91.33 343	76.05 217	97.42 272	82.84 269	80.51 420	92.84 393

v148		87.04 295	86.32 284	89.21 340	90.94 394	77.26 368	93.71 264	94.43 304	84.84 255	84.36 333	90.80 365	76.04 218	97.05 316	82.12 283	79.60 429	93.31 370

mamba_0408		89.06 219	87.92 233	92.50 151	94.76 194	82.66 171	79.84 499	94.64 296	85.18 237	88.96 211	95.00 195	76.00 219	97.98 214	83.74 256	93.15 232	96.85 200

SSM_04072		88.57 236	87.92 233	90.51 271	94.76 194	82.66 171	79.84 499	94.64 296	85.18 237	88.96 211	95.00 195	76.00 219	92.03 466	83.74 256	93.15 232	96.85 200

eth_miper_zixun_eth		86.50 318	85.77 309	88.68 357	91.94 351	75.81 392	90.47 393	94.89 279	82.05 325	84.05 341	90.46 375	75.96 221	96.77 330	82.76 272	79.36 431	93.46 366

3Dnovator+	87.14 4	92.42 105	91.37 127	95.55 7	95.63 144	88.73 7	97.07 23	96.77 93	90.84 26	84.02 342	96.62 95	75.95 222	99.34 43	87.77 189	97.68 97	98.59 29

balanced_ft_v1		92.23 108	92.05 107	92.77 126	95.40 155	81.78 203	95.80 96	95.69 210	87.94 144	91.92 130	95.04 193	75.91 223	98.71 123	93.83 59	96.94 114	97.82 121

h-mvs33		90.80 152	90.15 161	92.75 131	96.01 122	82.66 171	95.43 123	95.53 225	89.80 63	93.08 91	95.64 158	75.77 224	99.00 81	92.07 102	78.05 436	96.60 213

hse-mvs2		89.88 189	89.34 188	91.51 219	94.83 190	81.12 226	93.94 245	93.91 329	89.80 63	93.08 91	93.60 264	75.77 224	97.66 241	92.07 102	77.07 444	95.74 255

BH-untuned		88.60 233	88.13 227	90.01 302	95.24 164	78.50 329	93.29 286	94.15 319	84.75 258	84.46 327	93.40 268	75.76 226	97.40 280	77.59 365	94.52 182	94.12 324

DIV-MVS_self_test		86.53 316	85.78 307	88.75 354	92.02 350	76.45 383	90.74 384	94.30 311	81.83 337	83.34 363	90.82 364	75.75 227	96.57 353	81.73 296	81.52 401	93.24 374

BH-w/o		87.57 269	87.05 254	89.12 343	94.90 186	77.90 348	92.41 325	93.51 346	82.89 308	83.70 350	91.34 342	75.75 227	97.07 313	75.49 386	93.49 219	92.39 414

cl____		86.52 317	85.78 307	88.75 354	92.03 349	76.46 382	90.74 384	94.30 311	81.83 337	83.34 363	90.78 366	75.74 229	96.57 353	81.74 295	81.54 400	93.22 375

cdsmvs_eth3d_5k		22.14 497	29.52 493	0.00 541	0.00 565	0.00 568	0.00 553	95.76 200	0.00 560	0.00 561	94.29 233	75.66 230	0.00 561	0.00 560	0.00 560	0.00 557

CNLPA		89.07 218	87.98 230	92.34 164	96.87 85	84.78 90	94.08 231	93.24 351	81.41 348	84.46 327	95.13 191	75.57 231	96.62 343	77.21 369	93.84 204	95.61 262

CHOSEN 1792x2688		88.84 225	87.69 238	92.30 170	96.14 110	81.42 215	90.01 408	95.86 194	74.52 444	87.41 245	93.94 249	75.46 232	98.36 162	80.36 320	95.53 151	97.12 177

CP-MVSNet		87.63 263	87.26 251	88.74 356	93.12 303	76.59 381	95.29 132	96.58 112	88.43 119	83.49 359	92.98 285	75.28 233	95.83 396	78.97 349	81.15 405	93.79 346

v10		87.25 283	86.38 280	89.85 308	91.19 380	79.50 298	94.48 191	95.45 232	83.79 280	83.62 353	91.19 348	75.13 234	97.42 272	81.94 289	80.60 415	92.63 400

Vis-MVSNet		91.75 121	91.23 133	93.29 90	95.32 158	83.78 124	96.14 64	95.98 178	89.89 56	90.45 174	96.58 97	75.09 235	98.31 170	84.75 236	96.90 117	97.78 125
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PRO-TEST		90.79 154	91.35 128	89.09 345	95.56 150	70.84 454	94.18 221	95.64 216	88.41 121	88.10 226	94.99 198	75.04 236	98.62 134	92.70 81	97.56 100	97.81 122

sss		88.93 224	88.26 225	90.94 252	94.05 259	80.78 246	91.71 355	95.38 238	81.55 346	88.63 218	93.91 253	75.04 236	95.47 414	82.47 275	91.61 261	96.57 216

v1144		87.61 266	86.79 263	90.06 297	91.01 389	79.34 309	93.95 244	95.42 237	83.36 293	85.66 287	91.31 346	74.98 238	97.42 272	83.37 260	82.06 391	93.42 367

miper_lstm_enhance		85.27 346	84.59 344	87.31 396	91.28 378	74.63 404	87.69 452	94.09 323	81.20 355	81.36 389	89.85 397	74.97 239	94.30 435	81.03 308	79.84 427	93.01 387

test_yl		90.69 158	90.02 168	92.71 135	95.72 138	82.41 183	94.11 226	95.12 258	85.63 221	91.49 145	94.70 210	74.75 240	98.42 158	86.13 216	92.53 252	97.31 153

DCV-MVSNet		90.69 158	90.02 168	92.71 135	95.72 138	82.41 183	94.11 226	95.12 258	85.63 221	91.49 145	94.70 210	74.75 240	98.42 158	86.13 216	92.53 252	97.31 153

V42		87.68 258	86.86 258	90.15 290	90.58 410	80.14 268	94.24 218	95.28 249	83.66 282	85.67 286	91.33 343	74.73 242	97.41 278	84.43 245	81.83 395	92.89 391

FA-MVS(test-final)		89.66 194	88.91 204	91.93 193	94.57 217	80.27 263	91.36 366	94.74 291	84.87 253	89.82 193	92.61 298	74.72 243	98.47 148	83.97 251	93.53 217	97.04 183

viewdifsd2359ckpt11		89.43 204	89.05 198	90.56 264	92.89 320	77.00 372	92.81 312	94.52 300	87.03 181	89.77 194	95.79 149	74.67 244	97.51 255	88.97 171	84.98 356	97.17 168

viewmsd2359difaftdt		89.43 204	89.05 198	90.56 264	92.89 320	77.00 372	92.81 312	94.52 300	87.03 181	89.77 194	95.79 149	74.67 244	97.51 255	88.97 171	84.98 356	97.17 168

XVG-OURS-SEG-HR		89.95 185	89.45 182	91.47 222	94.00 264	81.21 222	91.87 350	96.06 173	85.78 216	88.55 219	95.73 154	74.67 244	97.27 295	88.71 177	89.64 299	95.91 245

BP-MVS1		92.48 102	92.07 106	93.72 80	94.50 223	84.39 107	95.90 89	94.30 311	90.39 41	92.67 109	95.94 134	74.46 247	98.65 128	93.14 71	97.35 105	98.13 79

v2v482		87.84 253	87.06 253	90.17 288	90.99 390	79.23 316	94.00 241	95.13 257	84.87 253	85.53 291	92.07 320	74.45 248	97.45 266	84.71 241	81.75 397	93.85 343

CLD-MVS		89.47 201	88.90 205	91.18 236	94.22 250	82.07 191	92.13 343	96.09 169	87.90 148	85.37 306	92.45 302	74.38 249	97.56 251	87.15 201	90.43 281	93.93 335
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 260	86.85 259	90.03 299	92.14 344	80.60 256	93.76 258	95.23 251	82.94 306	84.60 321	94.02 244	74.27 250	95.49 413	81.04 306	83.68 371	94.01 332

HQP_MVS		90.60 166	90.19 159	91.82 203	94.70 204	82.73 167	95.85 93	96.22 147	90.81 27	86.91 254	94.86 204	74.23 251	98.12 181	88.15 181	89.99 288	94.63 297

plane_prior6					94.52 220	82.75 164						74.23 251

v144192		87.19 289	86.35 282	89.74 316	90.64 408	78.24 338	93.92 247	95.43 235	81.93 330	85.51 293	91.05 357	74.21 253	97.45 266	82.86 268	81.56 399	93.53 361

VPA-MVSNet		89.62 195	88.96 201	91.60 213	93.86 271	82.89 162	95.46 121	97.33 33	87.91 147	88.43 222	93.31 272	74.17 254	97.40 280	87.32 199	82.86 384	94.52 305

ab-mvs		89.41 206	88.35 219	92.60 143	95.15 170	82.65 175	92.20 341	95.60 219	83.97 274	88.55 219	93.70 263	74.16 255	98.21 176	82.46 276	89.37 302	96.94 193

1314		87.51 271	86.57 274	90.34 284	92.42 338	79.74 292	92.63 319	95.35 243	78.35 395	80.14 405	91.62 337	74.05 256	97.15 304	81.05 305	93.53 217	94.12 324

test_djsdf		89.03 221	88.64 210	90.21 287	90.74 405	79.28 313	95.96 83	95.90 188	84.66 262	85.33 308	92.94 286	74.02 257	97.30 290	89.64 161	88.53 314	94.05 330

cl22		86.78 305	85.98 299	89.18 342	92.34 339	77.62 363	90.84 383	94.13 321	81.33 350	83.97 344	90.15 386	73.96 258	96.60 350	84.19 247	82.94 380	93.33 369

SD_0403		84.71 359	84.65 341	84.92 439	92.95 317	65.95 477	92.07 347	93.23 352	83.82 279	79.03 424	93.73 262	73.90 259	92.91 459	63.02 472	90.05 287	95.89 247

AdaColmap		89.89 188	89.07 196	92.37 160	97.41 72	83.03 156	94.42 198	95.92 185	82.81 309	86.34 271	94.65 217	73.89 260	99.02 74	80.69 314	95.51 152	95.05 279

HyFIR lowres test		88.09 248	86.81 261	91.93 193	96.00 123	80.63 249	90.01 408	95.79 198	73.42 456	87.68 240	92.10 317	73.86 261	97.96 218	80.75 313	91.70 260	97.19 167

HQP2-MVS												73.83 262

HQP-MVS		89.80 191	89.28 191	91.34 229	94.17 253	81.56 207	94.39 205	96.04 174	88.81 104	85.43 300	93.97 248	73.83 262	97.96 218	87.11 203	89.77 297	94.50 308

3Dnovator	86.66 5	91.73 123	90.82 145	94.44 50	94.59 213	86.37 43	97.18 17	97.02 63	89.20 88	84.31 337	96.66 90	73.74 264	99.17 58	86.74 206	97.96 83	97.79 124

EPNet_dtu		86.49 320	85.94 302	88.14 374	90.24 420	72.82 426	94.11 226	92.20 382	86.66 195	79.42 419	92.36 305	73.52 265	95.81 398	71.26 419	93.66 212	95.80 253
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 363	83.06 371	88.54 360	91.72 361	78.44 330	95.18 145	92.82 365	82.73 311	79.67 416	92.12 314	73.49 266	95.96 389	71.10 424	68.73 481	91.21 442

Effi-MVS+-dtu		88.65 231	88.35 219	89.54 330	93.33 296	76.39 384	94.47 194	94.36 309	87.70 158	85.43 300	89.56 403	73.45 267	97.26 297	85.57 224	91.28 265	94.97 281

GDP-MVS		92.04 109	91.46 124	93.75 79	94.55 219	84.69 92	95.60 118	96.56 114	87.83 153	93.07 93	95.89 138	73.44 268	98.65 128	90.22 146	96.03 140	97.91 110

baseline2		86.50 318	85.39 321	89.84 309	91.12 385	76.70 379	91.88 349	88.58 464	82.35 318	79.95 410	90.95 359	73.42 269	97.63 245	80.27 323	89.95 291	95.19 273

PEN-MVS		86.80 304	86.27 287	88.40 363	92.32 340	75.71 394	95.18 145	96.38 127	87.97 142	82.82 370	93.15 279	73.39 270	95.92 391	76.15 382	79.03 434	93.59 359

v1192		87.25 283	86.33 283	90.00 303	90.76 404	79.04 317	93.80 256	95.48 227	82.57 313	85.48 295	91.18 350	73.38 271	97.42 272	82.30 279	82.06 391	93.53 361

guyue		91.12 145	90.84 144	91.96 190	94.59 213	80.57 257	94.87 164	93.71 342	88.96 101	91.14 155	95.22 182	73.22 272	97.76 233	92.01 106	93.81 205	97.54 145

QAPM		89.51 199	88.15 226	93.59 84	94.92 183	84.58 94	96.82 34	96.70 104	78.43 394	83.41 361	96.19 114	73.18 273	99.30 49	77.11 371	96.54 128	96.89 197

tpmrst		85.35 343	84.99 331	86.43 419	90.88 399	67.88 471	88.71 432	91.43 409	80.13 365	86.08 277	88.80 417	73.05 274	96.02 385	82.48 274	83.40 377	95.40 266

PS-CasMVS		87.32 280	86.88 257	88.63 359	92.99 315	76.33 386	95.33 127	96.61 110	88.22 129	83.30 365	93.07 283	73.03 275	95.79 400	78.36 355	81.00 411	93.75 353

DTE-MVSNet		86.11 327	85.48 319	87.98 377	91.65 366	74.92 401	94.93 160	95.75 201	87.36 170	82.26 376	93.04 284	72.85 276	95.82 397	74.04 402	77.46 440	93.20 377

MVSTER		88.84 225	88.29 223	90.51 271	92.95 317	80.44 260	93.73 261	95.01 264	84.66 262	87.15 249	93.12 281	72.79 277	97.21 302	87.86 187	87.36 336	93.87 340

v1921920		86.97 297	86.06 296	89.69 321	90.53 413	78.11 341	93.80 256	95.43 235	81.90 332	85.33 308	91.05 357	72.66 278	97.41 278	82.05 287	81.80 396	93.53 361

DP-MVS		87.25 283	85.36 323	92.90 117	97.65 65	83.24 142	94.81 170	92.00 389	74.99 439	81.92 383	95.00 195	72.66 278	99.05 68	66.92 455	92.33 255	96.40 220

VortexMVS		88.42 237	88.01 229	89.63 327	93.89 270	78.82 319	93.82 254	95.47 228	86.67 194	84.53 325	91.99 323	72.62 280	96.65 337	89.02 170	84.09 365	93.41 368

v7n		86.81 303	85.76 310	89.95 304	90.72 406	79.25 315	95.07 151	95.92 185	84.45 265	82.29 375	90.86 361	72.60 281	97.53 253	79.42 345	80.52 419	93.08 385

OPM-MVS		90.12 175	89.56 180	91.82 203	93.14 302	83.90 120	94.16 222	95.74 202	88.96 101	87.86 233	95.43 171	72.48 282	97.91 224	88.10 185	90.18 286	93.65 358
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 252	86.32 284	92.59 144	96.07 119	82.92 161	95.23 137	94.92 278	75.66 431	82.89 369	95.98 131	72.48 282	99.21 56	68.43 443	95.23 164	95.64 259

pm-mvs1		86.61 312	85.54 317	89.82 310	91.44 369	80.18 266	95.28 134	94.85 283	83.84 277	81.66 384	92.62 297	72.45 284	96.48 361	79.67 333	78.06 435	92.82 394

KinetiMVS		91.82 113	91.30 130	93.39 87	94.72 201	83.36 139	95.45 122	96.37 128	90.33 43	92.17 120	96.03 128	72.32 285	98.75 117	87.94 186	96.34 133	98.07 84

usedtu_dtu_shiyan1		86.84 301	85.61 315	90.53 266	90.50 414	81.80 201	90.97 379	94.96 271	83.05 300	83.50 357	90.32 378	72.15 286	96.65 337	79.49 339	85.55 350	93.15 381

FE-MVSNET3		86.84 301	85.61 315	90.53 266	90.50 414	81.80 201	90.97 379	94.96 271	83.05 300	83.50 357	90.32 378	72.15 286	96.65 337	79.49 339	85.55 350	93.15 381

PMMVS		85.71 336	84.96 333	87.95 378	88.90 439	77.09 370	88.68 433	90.06 443	72.32 466	86.47 264	90.76 367	72.15 286	94.40 431	81.78 294	93.49 219	92.36 415

SDMVSNet		90.19 174	89.61 179	91.93 193	96.00 123	83.09 153	92.89 307	95.98 178	88.73 108	86.85 258	95.20 186	72.09 289	97.08 311	88.90 173	89.85 294	95.63 260

PatchmatchNet		85.85 332	84.70 340	89.29 339	91.76 360	75.54 395	88.49 437	91.30 411	81.63 343	85.05 313	88.70 420	71.71 290	96.24 377	74.61 399	89.05 309	96.08 238
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 291				96.12 235

patchmatchnet-post											83.76 468	71.53 292	96.48 361

v1240		86.78 305	85.85 305	89.56 329	90.45 417	77.79 354	93.61 269	95.37 241	81.65 341	85.43 300	91.15 352	71.50 293	97.43 270	81.47 300	82.05 393	93.47 365

anonymousdsp		87.84 253	87.09 252	90.12 292	89.13 436	80.54 258	94.67 181	95.55 222	82.05 325	83.82 346	92.12 314	71.47 294	97.15 304	87.15 201	87.80 331	92.67 398

Patchmatch-test		81.37 407	79.30 413	87.58 387	90.92 396	74.16 411	80.99 494	87.68 471	70.52 474	76.63 449	88.81 415	71.21 295	92.76 461	60.01 482	86.93 342	95.83 251

F-COLMAP		87.95 251	86.80 262	91.40 226	96.35 105	80.88 238	94.73 177	95.45 232	79.65 372	82.04 381	94.61 218	71.13 296	98.50 143	76.24 381	91.05 271	94.80 294

pmmvs4		85.43 340	83.86 358	90.16 289	90.02 425	82.97 160	90.27 395	92.67 369	75.93 430	80.73 396	91.74 331	71.05 297	95.73 403	78.85 352	83.46 375	91.78 426

CR-MVSNet		85.35 343	83.76 359	90.12 292	90.58 410	79.34 309	85.24 475	91.96 393	78.27 397	85.55 289	87.87 433	71.03 298	95.61 406	73.96 404	89.36 303	95.40 266

Patchmtry		82.71 383	80.93 387	88.06 375	90.05 424	76.37 385	84.74 481	91.96 393	72.28 467	81.32 390	87.87 433	71.03 298	95.50 412	68.97 439	80.15 422	92.32 417

CL-MVSNet_self_test		81.74 398	80.53 388	85.36 432	85.96 467	72.45 435	90.25 397	93.07 357	81.24 353	79.85 413	87.29 439	70.93 300	92.52 462	66.95 452	69.23 471	91.11 446

RPMNet		83.95 371	81.53 382	91.21 234	90.58 410	79.34 309	85.24 475	96.76 94	71.44 470	85.55 289	82.97 476	70.87 301	98.91 98	61.01 477	89.36 303	95.40 266

Patchmatch-RL test		81.67 399	79.96 403	86.81 413	85.42 475	71.23 447	82.17 492	87.50 473	78.47 392	77.19 444	82.50 483	70.81 302	93.48 450	82.66 273	72.89 455	95.71 258

CostFormer		85.77 335	84.94 334	88.26 370	91.16 383	72.58 434	89.47 420	91.04 418	76.26 426	86.45 267	89.97 393	70.74 303	96.86 329	82.35 278	87.07 341	95.34 270

AstraMVS		90.69 158	90.30 157	91.84 202	93.81 274	79.85 287	94.76 175	92.39 374	88.96 101	91.01 166	95.87 142	70.69 304	97.94 221	92.49 84	92.70 244	97.73 128

sam_mvs												70.60 305

xiu_mvs_v1_base_debu		90.64 163	90.05 165	92.40 156	93.97 266	84.46 101	93.32 281	95.46 229	85.17 239	92.25 117	94.03 241	70.59 306	98.57 140	90.97 128	94.67 174	94.18 320

xiu_mvs_v1_base		90.64 163	90.05 165	92.40 156	93.97 266	84.46 101	93.32 281	95.46 229	85.17 239	92.25 117	94.03 241	70.59 306	98.57 140	90.97 128	94.67 174	94.18 320

xiu_mvs_v1_base_debi		90.64 163	90.05 165	92.40 156	93.97 266	84.46 101	93.32 281	95.46 229	85.17 239	92.25 117	94.03 241	70.59 306	98.57 140	90.97 128	94.67 174	94.18 320

test_post											10.29 554	70.57 309	95.91 393

CANet_DTU		90.26 173	89.41 186	92.81 122	93.46 293	83.01 158	93.48 273	94.47 303	89.43 78	87.76 239	94.23 238	70.54 310	99.03 71	84.97 231	96.39 132	96.38 221

BH-RMVSNet		88.37 240	87.48 243	91.02 245	95.28 160	79.45 301	92.89 307	93.07 357	85.45 231	86.91 254	94.84 207	70.35 311	97.76 233	73.97 403	94.59 179	95.85 249

Fast-Effi-MVS+-dtu		87.44 274	86.72 264	89.63 327	92.04 348	77.68 362	94.03 236	93.94 325	85.81 215	82.42 374	91.32 345	70.33 312	97.06 314	80.33 322	90.23 285	94.14 323

MDTV_nov1_ep13_2view						55.91 509	87.62 454		73.32 457	84.59 322		70.33 312		74.65 397		95.50 263

ACMM	84.12 9	89.14 214	88.48 218	91.12 237	94.65 208	81.22 221	95.31 128	96.12 166	85.31 236	85.92 280	94.34 229	70.19 314	98.06 197	85.65 222	88.86 311	94.08 328
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RRT-MVS		90.85 151	90.70 149	91.30 231	94.25 248	76.83 376	94.85 167	96.13 165	89.04 95	90.23 181	94.88 202	70.15 315	98.72 121	91.86 114	94.88 169	98.34 49

LuminaMVS		90.55 167	89.81 172	92.77 126	92.78 326	84.21 111	94.09 230	94.17 318	85.82 214	91.54 143	94.14 240	69.93 316	97.92 223	91.62 118	94.21 193	96.18 231

ET-MVSNet_ETH3D		87.51 271	85.91 303	92.32 166	93.70 285	83.93 119	92.33 333	90.94 423	84.16 269	72.09 475	92.52 300	69.90 317	95.85 395	89.20 167	88.36 320	97.17 168

LPG-MVS_test		89.45 202	88.90 205	91.12 237	94.47 226	81.49 211	95.30 130	96.14 162	86.73 192	85.45 297	95.16 188	69.89 318	98.10 183	87.70 190	89.23 306	93.77 351

LGP-MVS_train				91.12 237	94.47 226	81.49 211		96.14 162	86.73 192	85.45 297	95.16 188	69.89 318	98.10 183	87.70 190	89.23 306	93.77 351

CHOSEN 280x420		85.15 348	83.99 356	88.65 358	92.47 335	78.40 332	79.68 501	92.76 366	74.90 441	81.41 388	89.59 401	69.85 320	95.51 410	79.92 329	95.29 161	92.03 422

LTVRE_ROB	82.13 13	86.26 325	84.90 335	90.34 284	94.44 230	81.50 209	92.31 336	94.89 279	83.03 302	79.63 417	92.67 295	69.69 321	97.79 231	71.20 420	86.26 345	91.72 427
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
OpenMVS	83.78 11	88.74 229	87.29 248	93.08 105	92.70 330	85.39 79	96.57 40	96.43 122	78.74 388	80.85 394	96.07 124	69.64 322	99.01 76	78.01 361	96.65 126	94.83 292

MonoMVSNet		86.89 300	86.55 275	87.92 380	89.46 434	73.75 413	94.12 224	93.10 355	87.82 154	85.10 311	90.76 367	69.59 323	94.94 425	86.47 210	82.50 386	95.07 277

MDTV_nov1_ep13			83.56 362		91.69 364	69.93 461	87.75 451	91.54 404	78.60 390	84.86 316	88.90 413	69.54 324	96.03 384	70.25 430	88.93 310

dtuonly		84.33 365	84.48 347	83.87 449	86.63 461	63.54 489	86.79 461	91.48 407	78.02 402	83.20 366	93.56 265	69.53 325	94.11 438	79.08 348	92.02 259	93.97 334

AUN-MVS		87.78 256	86.54 276	91.48 221	94.82 191	81.05 229	93.91 249	93.93 326	83.00 303	86.93 252	93.53 266	69.50 326	97.67 239	86.14 214	77.12 443	95.73 257

PatchT		82.68 384	81.27 384	86.89 411	90.09 423	70.94 453	84.06 484	90.15 440	74.91 440	85.63 288	83.57 471	69.37 327	94.87 426	65.19 461	88.50 316	94.84 291

VPNet		88.20 245	87.47 244	90.39 280	93.56 290	79.46 300	94.04 235	95.54 224	88.67 111	86.96 251	94.58 222	69.33 328	97.15 304	84.05 250	80.53 418	94.56 303

ACMP	84.23 8	89.01 223	88.35 219	90.99 248	94.73 199	81.27 218	95.07 151	95.89 190	86.48 197	83.67 351	94.30 232	69.33 328	97.99 211	87.10 205	88.55 313	93.72 356
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 446				9.81 555	69.31 330	95.53 408	76.65 374

tpmvs		83.35 379	82.07 378	87.20 403	91.07 387	71.00 452	88.31 440	91.70 397	78.91 380	80.49 401	87.18 442	69.30 331	97.08 311	68.12 447	83.56 373	93.51 364

mvsmamba		90.33 170	89.69 176	92.25 177	95.17 167	81.64 206	95.27 135	93.36 349	84.88 252	89.51 199	94.27 236	69.29 332	97.42 272	89.34 164	96.12 139	97.68 131

thres200		87.21 287	86.24 288	90.12 292	95.36 156	78.53 327	93.26 288	92.10 385	86.42 200	88.00 232	91.11 354	69.24 333	98.00 210	69.58 437	91.04 273	93.83 345

tfpn200view9		87.58 268	86.64 269	90.41 279	95.99 126	78.64 323	94.58 185	91.98 391	86.94 186	88.09 227	91.77 329	69.18 334	98.10 183	70.13 433	91.10 266	94.48 311

thres400		87.62 265	86.64 269	90.57 262	95.99 126	78.64 323	94.58 185	91.98 391	86.94 186	88.09 227	91.77 329	69.18 334	98.10 183	70.13 433	91.10 266	94.96 284

WB-MVSnew		83.77 374	83.28 365	85.26 435	91.48 368	71.03 450	91.89 348	87.98 467	78.91 380	84.78 317	90.22 382	69.11 336	94.02 440	64.70 465	90.44 280	90.71 450

tfpnnormal		84.72 358	83.23 367	89.20 341	92.79 325	80.05 275	94.48 191	95.81 196	82.38 316	81.08 392	91.21 347	69.01 337	96.95 323	61.69 475	80.59 416	90.58 455

thres100view900		87.63 263	86.71 265	90.38 282	96.12 112	78.55 326	95.03 155	91.58 402	87.15 175	88.06 230	92.29 308	68.91 338	98.10 183	70.13 433	91.10 266	94.48 311

thres600view7		87.65 260	86.67 268	90.59 261	96.08 118	78.72 320	94.88 163	91.58 402	87.06 180	88.08 229	92.30 307	68.91 338	98.10 183	70.05 436	91.10 266	94.96 284

PatchMatch-RL		86.77 308	85.54 317	90.47 277	95.88 131	82.71 169	90.54 390	92.31 378	79.82 370	84.32 335	91.57 341	68.77 340	96.39 369	73.16 409	93.48 221	92.32 417

XVG-OURS		89.40 208	88.70 209	91.52 217	94.06 258	81.46 213	91.27 371	96.07 171	86.14 209	88.89 214	95.77 152	68.73 341	97.26 297	87.39 197	89.96 290	95.83 251

TR-MVS		86.78 305	85.76 310	89.82 310	94.37 234	78.41 331	92.47 324	92.83 363	81.11 356	86.36 269	92.40 303	68.73 341	97.48 261	73.75 407	89.85 294	93.57 360

tpm		84.73 357	84.02 355	86.87 412	90.33 418	68.90 465	89.06 427	89.94 447	80.85 358	85.75 284	89.86 396	68.54 343	95.97 388	77.76 363	84.05 366	95.75 254

FMVSNet3		87.40 276	86.11 293	91.30 231	93.79 277	83.64 129	94.20 220	94.81 287	83.89 276	84.37 330	91.87 328	68.45 344	96.56 355	78.23 358	85.36 352	93.70 357

MVP-Stereo		85.97 329	84.86 337	89.32 338	90.92 396	82.19 188	92.11 344	94.19 316	78.76 387	78.77 432	91.63 336	68.38 345	96.56 355	75.01 393	93.95 199	89.20 470
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 392	80.27 394	87.01 406	91.09 386	71.02 451	87.38 457	91.53 405	66.25 488	80.17 403	86.35 454	68.22 346	96.15 381	69.16 438	82.29 389	93.86 342

dmvs_testset		74.57 450	75.81 447	70.86 481	87.72 456	40.47 523	87.05 460	77.90 505	82.75 310	71.15 481	85.47 461	67.98 347	84.12 504	45.26 505	76.98 445	88.00 482

sd_testset		88.59 234	87.85 236	90.83 255	96.00 123	80.42 261	92.35 330	94.71 292	88.73 108	86.85 258	95.20 186	67.31 348	96.43 367	79.64 334	89.85 294	95.63 260

tpm2		84.08 368	82.94 372	87.48 391	91.39 373	71.27 446	89.23 424	90.37 435	71.95 468	84.64 320	89.33 405	67.30 349	96.55 357	75.17 390	87.09 340	94.63 297

test-LLR		85.87 331	85.41 320	87.25 399	90.95 392	71.67 443	89.55 416	89.88 450	83.41 290	84.54 323	87.95 430	67.25 350	95.11 421	81.82 292	93.37 225	94.97 281

test0.0.03 1		82.41 389	81.69 380	84.59 442	88.23 448	72.89 425	90.24 399	87.83 469	83.41 290	79.86 412	89.78 398	67.25 350	88.99 491	65.18 462	83.42 376	91.90 425

CVMVSNet		84.69 360	84.79 339	84.37 444	91.84 356	64.92 484	93.70 265	91.47 408	66.19 489	86.16 276	95.28 179	67.18 352	93.33 452	80.89 311	90.42 282	94.88 290

thisisatest0515		87.33 279	85.99 298	91.37 228	93.49 291	79.55 297	90.63 387	89.56 457	80.17 364	87.56 243	90.86 361	67.07 353	98.28 171	81.50 299	93.02 236	96.29 225

tttt0517		88.61 232	87.78 237	91.11 240	94.96 180	77.81 352	95.35 126	89.69 452	85.09 247	88.05 231	94.59 221	66.93 354	98.48 145	83.27 262	92.13 257	97.03 184

our_test_3		81.93 394	80.46 392	86.33 421	88.46 444	73.48 418	88.46 438	91.11 414	76.46 420	76.69 448	88.25 426	66.89 355	94.36 433	68.75 440	79.08 433	91.14 444

thisisatest0530		88.67 230	87.61 240	91.86 199	94.87 187	80.07 273	94.63 183	89.90 449	84.00 273	88.46 221	93.78 258	66.88 356	98.46 149	83.30 261	92.65 245	97.06 181

IterMVS-SCA-FT		85.45 339	84.53 346	88.18 373	91.71 362	76.87 375	90.19 403	92.65 370	85.40 234	81.44 387	90.54 372	66.79 357	95.00 424	81.04 306	81.05 407	92.66 399

SCA		86.32 324	85.18 328	89.73 318	92.15 343	76.60 380	91.12 375	91.69 398	83.53 287	85.50 294	88.81 415	66.79 357	96.48 361	76.65 374	90.35 283	96.12 235

D2MVS		85.90 330	85.09 330	88.35 365	90.79 401	77.42 365	91.83 352	95.70 208	80.77 359	80.08 407	90.02 391	66.74 359	96.37 370	81.88 291	87.97 326	91.26 441

IterMVS		84.88 354	83.98 357	87.60 386	91.44 369	76.03 388	90.18 404	92.41 373	83.24 296	81.06 393	90.42 377	66.60 360	94.28 436	79.46 341	80.98 412	92.48 408
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 281	85.98 299	91.08 241	94.01 261	83.10 150	95.14 148	94.94 273	83.57 284	84.37 330	91.64 333	66.59 361	96.34 373	78.23 358	85.36 352	93.79 346

test1		87.26 281	85.98 299	91.08 241	94.01 261	83.10 150	95.14 148	94.94 273	83.57 284	84.37 330	91.64 333	66.59 361	96.34 373	78.23 358	85.36 352	93.79 346

FMVSNet2		87.19 289	85.82 306	91.30 231	94.01 261	83.67 127	94.79 172	94.94 273	83.57 284	83.88 345	92.05 321	66.59 361	96.51 359	77.56 366	85.01 355	93.73 355

IMVS_0404		87.60 267	86.84 260	89.89 306	93.72 279	77.75 357	88.56 435	95.34 244	85.53 227	79.98 409	94.49 224	66.54 364	94.64 427	84.75 236	92.65 245	97.28 156

EPMVS		83.90 373	82.70 377	87.51 388	90.23 421	72.67 429	88.62 434	81.96 493	81.37 349	85.01 314	88.34 424	66.31 365	94.45 428	75.30 389	87.12 339	95.43 265

Syy-MVS		80.07 423	79.78 405	80.94 463	91.92 352	59.93 499	89.75 414	87.40 474	81.72 339	78.82 429	87.20 440	66.29 366	91.29 476	47.06 504	87.84 329	91.60 430

ppachtmachnet_test		81.84 395	80.07 399	87.15 404	88.46 444	74.43 408	89.04 428	92.16 384	75.33 435	77.75 440	88.99 411	66.20 367	95.37 416	65.12 463	77.60 438	91.65 428

MDA-MVSNet_test_wron		79.21 434	77.19 436	85.29 433	88.22 449	72.77 427	85.87 469	90.06 443	74.34 445	62.62 495	87.56 436	66.14 368	91.99 469	66.90 456	73.01 453	91.10 447

YYNet1		79.22 433	77.20 435	85.28 434	88.20 450	72.66 430	85.87 469	90.05 445	74.33 446	62.70 493	87.61 435	66.09 369	92.03 466	66.94 453	72.97 454	91.15 443

JIA-IIPM		81.04 410	78.98 422	87.25 399	88.64 440	73.48 418	81.75 493	89.61 456	73.19 458	82.05 380	73.71 503	66.07 370	95.87 394	71.18 422	84.60 360	92.41 412

MSDG		84.86 355	83.09 369	90.14 291	93.80 275	80.05 275	89.18 425	93.09 356	78.89 382	78.19 434	91.91 326	65.86 371	97.27 295	68.47 442	88.45 317	93.11 383

FE-MVS		87.40 276	86.02 297	91.57 215	94.56 218	79.69 295	90.27 395	93.72 341	80.57 360	88.80 215	91.62 337	65.32 372	98.59 139	74.97 394	94.33 189	96.44 219

jajsoiax		88.24 244	87.50 242	90.48 274	90.89 398	80.14 268	95.31 128	95.65 215	84.97 250	84.24 338	94.02 244	65.31 373	97.42 272	88.56 178	88.52 315	93.89 336

cascas		86.43 322	84.98 332	90.80 258	92.10 347	80.92 236	90.24 399	95.91 187	73.10 459	83.57 355	88.39 423	65.15 374	97.46 265	84.90 234	91.43 263	94.03 331

ADS-MVSNet2		81.66 400	79.71 408	87.50 389	91.35 375	74.19 410	83.33 487	88.48 465	72.90 461	82.24 377	85.77 459	64.98 375	93.20 455	64.57 466	83.74 369	95.12 275

ADS-MVSNet		81.56 402	79.78 405	86.90 410	91.35 375	71.82 439	83.33 487	89.16 463	72.90 461	82.24 377	85.77 459	64.98 375	93.76 446	64.57 466	83.74 369	95.12 275

blended_shiyan6		82.78 381	80.48 391	89.67 326	85.53 472	79.76 290	91.37 365	93.82 333	77.14 410	79.30 422	83.73 469	64.96 377	96.63 340	79.68 332	68.75 477	92.63 400

blended_shiyan8		82.79 380	80.49 390	89.69 321	85.50 474	79.83 289	91.38 364	93.82 333	77.14 410	79.39 420	83.73 469	64.95 378	96.63 340	79.75 330	68.77 476	92.62 402

Elysia		90.12 175	89.10 194	93.18 97	93.16 300	84.05 116	95.22 139	96.27 137	85.16 242	90.59 171	94.68 212	64.64 379	98.37 160	86.38 212	95.77 145	97.12 177

StellarMVS		90.12 175	89.10 194	93.18 97	93.16 300	84.05 116	95.22 139	96.27 137	85.16 242	90.59 171	94.68 212	64.64 379	98.37 160	86.38 212	95.77 145	97.12 177

pmmvs5		84.21 366	82.84 376	88.34 367	88.95 438	76.94 374	92.41 325	91.91 395	75.63 432	80.28 402	91.18 350	64.59 381	95.57 407	77.09 372	83.47 374	92.53 407

PVSNet	78.82 18	85.55 337	84.65 341	88.23 372	94.72 201	71.93 437	87.12 459	92.75 367	78.80 386	84.95 315	90.53 373	64.43 382	96.71 334	74.74 396	93.86 202	96.06 241

dmvs_re		84.20 367	83.22 368	87.14 405	91.83 358	77.81 352	90.04 407	90.19 439	84.70 261	81.49 385	89.17 407	64.37 383	91.13 478	71.58 417	85.65 349	92.46 410

wanda-best-256-512		82.44 387	80.07 399	89.53 331	85.12 478	79.44 302	90.49 391	93.75 339	76.97 416	79.00 425	82.72 479	64.29 384	96.61 346	79.56 337	68.75 477	92.55 403

FE-blended-shiyan7		82.44 387	80.07 399	89.53 331	85.12 478	79.44 302	90.49 391	93.75 339	76.97 416	79.00 425	82.72 479	64.29 384	96.61 346	79.56 337	68.75 477	92.55 403

usedtu_blend_shiyan5		82.39 390	79.93 404	89.75 315	85.12 478	80.08 271	92.36 328	93.26 350	74.29 447	79.00 425	82.72 479	64.29 384	96.60 350	79.60 335	68.75 477	92.55 403

UGNet		89.95 185	88.95 202	92.95 115	94.51 221	83.31 140	95.70 106	95.23 251	89.37 80	87.58 242	93.94 249	64.00 387	98.78 115	83.92 252	96.31 134	96.74 207
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
WB-MVS		67.92 460	67.49 461	69.21 486	81.09 495	41.17 522	88.03 445	78.00 504	73.50 455	62.63 494	83.11 475	63.94 388	86.52 495	25.66 524	51.45 504	79.94 497

RPSCF		85.07 349	84.27 348	87.48 391	92.91 319	70.62 456	91.69 357	92.46 372	76.20 428	82.67 372	95.22 182	63.94 388	97.29 293	77.51 367	85.80 347	94.53 304

mvs_tets		88.06 250	87.28 249	90.38 282	90.94 394	79.88 284	95.22 139	95.66 213	85.10 246	84.21 339	93.94 249	63.53 390	97.40 280	88.50 179	88.40 319	93.87 340

SSC-MVS		67.06 461	66.56 463	68.56 488	80.54 496	40.06 524	87.77 450	77.37 507	72.38 465	61.75 496	82.66 482	63.37 391	86.45 496	24.48 526	48.69 507	79.16 500

test1111		89.10 215	88.64 210	90.48 274	95.53 151	74.97 400	96.08 69	84.89 485	88.13 133	90.16 188	96.65 91	63.29 392	98.10 183	86.14 214	96.90 117	98.39 46

gbinet_0.2-2-1-0.02		82.59 385	80.19 397	89.77 314	85.23 477	80.05 275	91.59 360	93.52 345	77.60 404	79.78 414	82.87 478	63.26 393	96.45 365	78.93 350	68.97 473	92.81 395

Anonymous20231211		86.59 314	85.13 329	90.98 250	96.52 99	81.50 209	96.14 64	96.16 160	73.78 452	83.65 352	92.15 312	63.26 393	97.37 286	82.82 270	81.74 398	94.06 329

ECVR-MVS		89.09 217	88.53 213	90.77 259	95.62 145	75.89 390	96.16 60	84.22 487	87.89 150	90.20 182	96.65 91	63.19 395	98.10 183	85.90 219	96.94 114	98.33 51

dtuonlycased		79.67 428	79.05 421	81.54 461	88.34 447	68.44 467	88.96 430	90.65 432	78.48 391	73.21 472	85.88 458	63.18 396	91.00 480	70.40 428	72.32 456	85.19 487

SSC-MVS3.2		84.60 361	84.19 349	85.85 427	92.74 328	68.07 468	88.15 443	93.81 336	87.42 168	83.76 348	91.07 356	62.91 397	95.73 403	74.56 400	83.24 378	93.75 353

nomal-1		86.20 326	84.90 335	90.11 296	92.72 329	80.88 238	89.79 411	91.03 419	82.96 305	83.49 359	88.82 414	62.88 398	94.38 432	81.35 301	91.05 271	95.07 277

dp		81.47 406	80.23 395	85.17 436	89.92 427	65.49 481	86.74 463	90.10 442	76.30 425	81.10 391	87.12 443	62.81 399	95.92 391	68.13 446	79.88 425	94.09 327

LFMVS		90.08 178	89.13 193	92.95 115	96.71 88	82.32 186	96.08 69	89.91 448	86.79 189	92.15 122	96.81 84	62.60 400	98.34 165	87.18 200	93.90 201	98.19 73

Anonymous20231206		81.03 411	79.77 407	84.82 440	87.85 455	70.26 459	91.42 363	92.08 386	73.67 453	77.75 440	89.25 406	62.43 401	93.08 456	61.50 476	82.00 394	91.12 445

VDD-MVS		90.74 155	89.92 170	93.20 95	96.27 106	83.02 157	95.73 104	93.86 330	88.42 120	92.53 112	96.84 81	62.09 402	98.64 131	90.95 132	92.62 250	97.93 107

MS-PatchMatch		85.05 350	84.16 351	87.73 383	91.42 372	78.51 328	91.25 372	93.53 344	77.50 405	80.15 404	91.58 339	61.99 403	95.51 410	75.69 385	94.35 187	89.16 471

OurMVSNet-221017-0		85.35 343	84.64 343	87.49 390	90.77 403	72.59 433	94.01 239	94.40 307	84.72 259	79.62 418	93.17 278	61.91 404	96.72 332	81.99 288	81.16 403	93.16 379

WBMVS		84.97 353	84.18 350	87.34 394	94.14 257	71.62 445	90.20 402	92.35 375	81.61 344	84.06 340	90.76 367	61.82 405	96.52 358	78.93 350	83.81 367	93.89 336

test_vis1_n_1920		89.39 209	89.84 171	88.04 376	92.97 316	72.64 431	94.71 179	96.03 176	86.18 207	91.94 129	96.56 99	61.63 406	95.74 402	93.42 66	95.11 165	95.74 255

test20.03		79.95 425	79.08 419	82.55 455	85.79 469	67.74 473	91.09 376	91.08 415	81.23 354	74.48 465	89.96 394	61.63 406	90.15 483	60.08 480	76.38 446	89.76 462

mmtdpeth		85.04 352	84.15 352	87.72 384	93.11 304	75.74 393	94.37 209	92.83 363	84.98 249	89.31 204	86.41 452	61.61 408	97.14 307	92.63 83	62.11 493	90.29 456

DSMNet-mixed		76.94 444	76.29 442	78.89 468	83.10 489	56.11 508	87.78 449	79.77 497	60.65 497	75.64 457	88.71 419	61.56 409	88.34 492	60.07 481	89.29 305	92.21 420

Anonymous20240529		88.09 248	86.59 273	92.58 145	96.53 98	81.92 197	95.99 79	95.84 195	74.11 449	89.06 209	95.21 185	61.44 410	98.81 111	83.67 259	87.47 333	97.01 187

UBG		85.51 338	84.57 345	88.35 365	94.21 251	71.78 441	90.07 406	89.66 454	82.28 320	85.91 281	89.01 410	61.30 411	97.06 314	76.58 377	92.06 258	96.22 228

IB-MVS	80.51 15	85.24 347	83.26 366	91.19 235	92.13 345	79.86 285	91.75 354	91.29 412	83.28 295	80.66 398	88.49 422	61.28 412	98.46 149	80.99 309	79.46 430	95.25 272
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
GA-MVS		86.61 312	85.27 326	90.66 260	91.33 377	78.71 322	90.40 394	93.81 336	85.34 235	85.12 310	89.57 402	61.25 413	97.11 309	80.99 309	89.59 300	96.15 232

N_pmnet		68.89 459	68.44 459	70.23 483	89.07 437	28.79 534	88.06 444	19.50 535	69.47 477	71.86 478	84.93 463	61.24 414	91.75 472	54.70 492	77.15 442	90.15 459

EU-MVSNet		81.32 408	80.95 386	82.42 458	88.50 443	63.67 488	93.32 281	91.33 410	64.02 493	80.57 400	92.83 289	61.21 415	92.27 465	76.34 379	80.38 421	91.32 439

testing91		87.11 293	86.18 289	89.92 305	94.43 231	75.38 399	91.53 361	92.27 380	86.48 197	86.50 263	90.24 381	61.19 416	97.53 253	82.10 284	90.88 276	96.84 203

FBQ-MVS		87.19 289	85.74 312	91.52 217	94.74 197	80.62 251	93.91 249	92.20 382	84.27 268	87.61 241	88.77 418	61.17 417	97.29 293	78.01 361	91.03 274	96.64 212

test_cas_vis1_n_1920		88.83 228	88.85 208	88.78 352	91.15 384	76.72 378	93.85 253	94.93 277	83.23 297	92.81 100	96.00 129	61.17 417	94.45 428	91.67 117	94.84 170	95.17 274

VDDNet		89.56 198	88.49 217	92.76 129	95.07 172	82.09 190	96.30 47	93.19 354	81.05 357	91.88 131	96.86 80	61.16 419	98.33 167	88.43 180	92.49 254	97.84 118

PVSNet_0	73.20 20	77.22 443	74.83 449	84.37 444	90.70 407	71.10 449	83.09 489	89.67 453	72.81 463	73.93 467	83.13 473	60.79 420	93.70 448	68.54 441	50.84 505	88.30 481

SixPastTwentyTwo		83.91 372	82.90 374	86.92 409	90.99 390	70.67 455	93.48 273	91.99 390	85.54 225	77.62 442	92.11 316	60.59 421	96.87 328	76.05 383	77.75 437	93.20 377

gg-mvs-nofinetune		81.77 397	79.37 411	88.99 349	90.85 400	77.73 361	86.29 466	79.63 498	74.88 442	83.19 367	69.05 510	60.34 422	96.11 382	75.46 387	94.64 178	93.11 383

MDA-MVSNet-bldmvs		78.85 436	76.31 441	86.46 417	89.76 429	73.88 412	88.79 431	90.42 434	79.16 378	59.18 498	88.33 425	60.20 423	94.04 439	62.00 474	68.96 474	91.48 436

pmmvs6		83.42 377	81.60 381	88.87 351	88.01 452	77.87 350	94.96 158	94.24 315	74.67 443	78.80 431	91.09 355	60.17 424	96.49 360	77.06 373	75.40 450	92.23 419

ACMH	80.38 17	85.36 342	83.68 360	90.39 280	94.45 229	80.63 249	94.73 177	94.85 283	82.09 323	77.24 443	92.65 296	60.01 425	97.58 249	72.25 414	84.87 358	92.96 388
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 379	89.73 431	77.91 346	87.80 447	78.23 503		80.58 399	83.86 467	59.88 426	95.33 417	71.20 420	92.22 256	90.60 454

UniMVSNet_ETH3D		87.53 270	86.37 281	91.00 247	92.44 337	78.96 318	94.74 176	95.61 218	84.07 272	85.36 307	94.52 223	59.78 427	97.34 287	82.93 266	87.88 327	96.71 208

myMVS_eth3d28		85.80 334	85.26 327	87.42 393	94.73 199	69.92 462	90.60 388	90.95 422	87.21 174	86.06 278	90.04 390	59.47 428	96.02 385	74.89 395	93.35 227	96.33 222

pmmvs-eth3d		80.97 413	78.72 424	87.74 382	84.99 481	79.97 282	90.11 405	91.65 400	75.36 434	73.51 469	86.03 455	59.45 429	93.96 444	75.17 390	72.21 457	89.29 469

testing99		86.72 309	85.73 314	89.69 321	94.23 249	74.91 402	91.35 367	90.97 421	86.14 209	86.36 269	90.22 382	59.41 430	97.48 261	82.24 281	90.66 278	96.69 210

test_0402		81.30 409	79.17 417	87.67 385	93.19 299	78.17 339	92.98 303	91.71 396	75.25 436	76.02 455	90.31 380	59.23 431	96.37 370	50.22 499	83.63 372	88.47 480

KD-MVS_self_test		80.20 421	79.24 414	83.07 452	85.64 471	65.29 482	91.01 378	93.93 326	78.71 389	76.32 450	86.40 453	59.20 432	92.93 458	72.59 412	69.35 470	91.00 449

testing3-2		86.72 309	86.71 265	86.74 415	96.11 115	65.92 478	93.39 278	89.65 455	89.46 76	87.84 235	92.79 293	59.17 433	97.60 247	81.31 302	90.72 277	96.70 209

UWE-MVS-28		78.98 435	78.38 427	80.80 464	88.18 451	60.66 498	90.65 386	78.51 500	78.84 384	77.93 438	90.93 360	59.08 434	89.02 490	50.96 497	90.33 284	92.72 397

FMVSNet1		85.85 332	84.11 353	91.08 241	92.81 324	83.10 150	95.14 148	94.94 273	81.64 342	82.68 371	91.64 333	59.01 435	96.34 373	75.37 388	83.78 368	93.79 346

testing11		86.44 321	85.35 324	89.69 321	94.29 245	75.40 398	91.30 368	90.53 433	84.76 257	85.06 312	90.13 387	58.95 436	97.45 266	82.08 285	91.09 270	96.21 230

COLMAP_ROB	80.39 16	83.96 370	82.04 379	89.74 316	95.28 160	79.75 291	94.25 216	92.28 379	75.17 437	78.02 437	93.77 259	58.60 437	97.84 229	65.06 464	85.92 346	91.63 429
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMH+	81.04 14	85.05 350	83.46 363	89.82 310	94.66 207	79.37 306	94.44 196	94.12 322	82.19 322	78.04 436	92.82 290	58.23 438	97.54 252	73.77 406	82.90 383	92.54 406

CMPMVS	59.16 21	80.52 417	79.20 416	84.48 443	83.98 484	67.63 474	89.95 410	93.84 332	64.79 492	66.81 489	91.14 353	57.93 439	95.17 419	76.25 380	88.10 322	90.65 451
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
reproduce_monomvs		86.37 323	85.87 304	87.87 381	93.66 287	73.71 414	93.44 276	95.02 263	88.61 114	82.64 373	91.94 325	57.88 440	96.68 335	89.96 151	79.71 428	93.22 375

FE-MVSNET2		81.82 396	79.99 402	87.34 394	84.74 482	77.36 367	92.72 316	94.55 298	82.09 323	73.79 468	86.46 449	57.80 441	94.45 428	74.65 397	73.10 452	90.20 457

tt0805		86.92 298	85.74 312	90.48 274	92.22 341	79.98 281	95.63 114	94.88 281	83.83 278	84.74 319	92.80 292	57.61 442	97.67 239	85.48 225	84.42 361	93.79 346

ITE_SJBPF				88.24 371	91.88 355	77.05 371		92.92 360	85.54 225	80.13 406	93.30 273	57.29 443	96.20 378	72.46 413	84.71 359	91.49 435

UWE-MVS		83.69 376	83.09 369	85.48 430	93.06 309	65.27 483	90.92 381	86.14 477	79.90 368	86.26 273	90.72 370	57.17 444	95.81 398	71.03 425	92.62 250	95.35 269

TESTMET0.1,1		83.74 375	82.85 375	86.42 420	89.96 426	71.21 448	89.55 416	87.88 468	77.41 406	83.37 362	87.31 438	56.71 445	93.65 449	80.62 316	92.85 242	94.40 314

UnsupCasMVSNet_eth		80.07 423	78.27 428	85.46 431	85.24 476	72.63 432	88.45 439	94.87 282	82.99 304	71.64 479	88.07 429	56.34 446	91.75 472	73.48 408	63.36 491	92.01 423

test_fmvs1		87.34 278	87.56 241	86.68 416	90.59 409	71.80 440	94.01 239	94.04 324	78.30 396	91.97 126	95.22 182	56.28 447	93.71 447	92.89 75	94.71 173	94.52 305

K. test v3		81.59 401	80.15 398	85.91 426	89.89 428	69.42 464	92.57 321	87.71 470	85.56 224	73.44 470	89.71 400	55.58 448	95.52 409	77.17 370	69.76 469	92.78 396

test-mter		84.54 362	83.64 361	87.25 399	90.95 392	71.67 443	89.55 416	89.88 450	79.17 377	84.54 323	87.95 430	55.56 449	95.11 421	81.82 292	93.37 225	94.97 281

FE-MVSNET		78.19 439	76.03 444	84.69 441	83.70 486	73.31 420	90.58 389	90.00 446	77.11 414	71.91 477	85.47 461	55.53 450	91.94 471	59.69 483	70.24 466	88.83 475

lessismore_v0				86.04 422	88.46 444	68.78 466		80.59 496		73.01 473	90.11 388	55.39 451	96.43 367	75.06 392	65.06 488	92.90 390

ETVMVS		84.43 363	82.92 373	88.97 350	94.37 234	74.67 403	91.23 373	88.35 466	83.37 292	86.06 278	89.04 409	55.38 452	95.67 405	67.12 451	91.34 264	96.58 215

MVS-HIRNet		73.70 451	72.20 453	78.18 472	91.81 359	56.42 507	82.94 490	82.58 491	55.24 500	68.88 484	66.48 512	55.32 453	95.13 420	58.12 487	88.42 318	83.01 491

test2506		87.21 287	86.28 286	90.02 301	95.62 145	73.64 416	96.25 55	71.38 512	87.89 150	90.45 174	96.65 91	55.29 454	98.09 191	86.03 218	96.94 114	98.33 51

mvs5depth		80.98 412	79.15 418	86.45 418	84.57 483	73.29 421	87.79 448	91.67 399	80.52 361	82.20 379	89.72 399	55.14 455	95.93 390	73.93 405	66.83 484	90.12 460

0.4-1-1-0.2		80.84 415	77.77 429	90.06 297	86.18 466	79.35 307	86.75 462	89.54 458	76.23 427	78.59 433	75.46 498	55.03 456	96.99 320	80.11 326	72.05 460	93.85 343

0.4-1-1-0.1		81.55 403	78.59 426	90.42 278	87.55 457	79.90 283	88.56 435	89.19 462	77.01 415	79.72 415	77.71 492	54.84 457	97.11 309	80.50 319	72.20 458	94.26 319

blend_shiyan4		81.94 393	79.35 412	89.70 319	85.52 473	80.08 271	91.29 369	93.82 333	77.12 413	79.31 421	82.94 477	54.81 458	96.60 350	79.60 335	69.78 468	92.41 412

new-patchmatchnet		76.41 446	75.17 448	80.13 465	82.65 491	59.61 500	87.66 453	91.08 415	78.23 399	69.85 483	83.22 472	54.76 459	91.63 475	64.14 468	64.89 489	89.16 471

Anonymous202405211		87.68 258	86.13 291	92.31 167	96.66 90	80.74 247	94.87 164	91.49 406	80.47 362	89.46 202	95.44 169	54.72 460	98.23 173	82.19 282	89.89 292	97.97 96

XVG-ACMP-BASELINE		86.00 328	84.84 338	89.45 336	91.20 379	78.00 343	91.70 356	95.55 222	85.05 248	82.97 368	92.25 310	54.49 461	97.48 261	82.93 266	87.45 335	92.89 391

USDC		82.76 382	81.26 385	87.26 398	91.17 381	74.55 405	89.27 422	93.39 348	78.26 398	75.30 459	92.08 318	54.43 462	96.63 340	71.64 416	85.79 348	90.61 452

AllTest		83.42 377	81.39 383	89.52 333	95.01 174	77.79 354	93.12 292	90.89 425	77.41 406	76.12 452	93.34 269	54.08 463	97.51 255	68.31 444	84.27 363	93.26 371

TestCases				89.52 333	95.01 174	77.79 354		90.89 425	77.41 406	76.12 452	93.34 269	54.08 463	97.51 255	68.31 444	84.27 363	93.26 371

KD-MVS_2432*1600		78.50 437	76.02 445	85.93 424	86.22 464	74.47 406	84.80 479	92.33 376	79.29 375	76.98 445	85.92 456	53.81 465	93.97 442	67.39 449	57.42 498	89.36 465

miper_refine_blended		78.50 437	76.02 445	85.93 424	86.22 464	74.47 406	84.80 479	92.33 376	79.29 375	76.98 445	85.92 456	53.81 465	93.97 442	67.39 449	57.42 498	89.36 465

MIMVSNet		82.59 385	80.53 388	88.76 353	91.51 367	78.32 335	86.57 465	90.13 441	79.32 374	80.70 397	88.69 421	52.98 467	93.07 457	66.03 459	88.86 311	94.90 289

testing222		84.84 356	83.32 364	89.43 337	94.15 256	75.94 389	91.09 376	89.41 461	84.90 251	85.78 283	89.44 404	52.70 468	96.28 376	70.80 427	91.57 262	96.07 239

0.3-1-1-0.015		80.75 416	77.58 431	90.25 286	86.55 462	79.72 293	87.46 456	89.48 460	76.43 422	77.93 438	75.94 495	52.31 469	97.05 316	80.25 324	71.85 462	93.99 333

FMVSNet5		81.52 405	79.60 409	87.27 397	91.17 381	77.95 344	91.49 362	92.26 381	76.87 418	76.16 451	87.91 432	51.67 470	92.34 464	67.74 448	81.16 403	91.52 433

testgi		80.94 414	80.20 396	83.18 451	87.96 453	66.29 476	91.28 370	90.70 431	83.70 281	78.12 435	92.84 288	51.37 471	90.82 481	63.34 469	82.46 387	92.43 411

test_fmvs1_n		87.03 296	87.04 255	86.97 407	89.74 430	71.86 438	94.55 187	94.43 304	78.47 392	91.95 128	95.50 167	51.16 472	93.81 445	93.02 74	94.56 180	95.26 271

Anonymous20240521		80.44 419	79.21 415	84.11 447	85.75 470	67.89 470	92.86 309	93.23 352	75.61 433	75.59 458	87.47 437	50.03 473	94.33 434	71.14 423	81.21 402	90.12 460

UnsupCasMVSNet_bld		76.23 447	73.27 451	85.09 437	83.79 485	72.92 424	85.65 472	93.47 347	71.52 469	68.84 485	79.08 490	49.77 474	93.21 454	66.81 457	60.52 495	89.13 473

OpenMVS_ROB	74.94 19	79.51 431	77.03 438	86.93 408	87.00 459	76.23 387	92.33 333	90.74 429	68.93 478	74.52 464	88.23 427	49.58 475	96.62 343	57.64 488	84.29 362	87.94 483

tt0320		80.13 422	77.41 432	88.29 368	90.50 414	78.02 342	93.10 295	90.71 430	66.06 490	76.75 447	86.97 445	49.56 476	95.40 415	71.65 415	71.41 464	91.46 437

TDRefinement		79.81 426	77.34 433	87.22 402	79.24 500	75.48 396	93.12 292	92.03 388	76.45 421	75.01 460	91.58 339	49.19 477	96.44 366	70.22 432	69.18 472	89.75 463

test_vis1_n		86.56 315	86.49 279	86.78 414	88.51 441	72.69 428	94.68 180	93.78 338	79.55 373	90.70 168	95.31 178	48.75 478	93.28 453	93.15 70	93.99 198	94.38 315

MIMVSNet1		79.38 432	77.28 434	85.69 429	86.35 463	73.67 415	91.61 359	92.75 367	78.11 401	72.64 474	88.12 428	48.16 479	91.97 470	60.32 479	77.49 439	91.43 438

LF4IMVS		80.37 420	79.07 420	84.27 446	86.64 460	69.87 463	89.39 421	91.05 417	76.38 423	74.97 461	90.00 392	47.85 480	94.25 437	74.55 401	80.82 414	88.69 477

EG-PatchMatch MVS		82.37 391	80.34 393	88.46 362	90.27 419	79.35 307	92.80 315	94.33 310	77.14 410	73.26 471	90.18 385	47.47 481	96.72 332	70.25 430	87.32 338	89.30 467

test_fmvs2		83.98 369	84.03 354	83.83 450	87.16 458	67.53 475	93.93 246	92.89 361	77.62 403	86.89 257	93.53 266	47.18 482	92.02 468	90.54 140	86.51 343	91.93 424

ttmdpeth		76.55 445	74.64 450	82.29 460	82.25 492	67.81 472	89.76 413	85.69 480	70.35 475	75.76 456	91.69 332	46.88 483	89.77 485	66.16 458	63.23 492	89.30 467

sc_t1		81.53 404	78.67 425	90.12 292	90.78 402	78.64 323	93.91 249	90.20 438	68.42 480	80.82 395	89.88 395	46.48 484	96.76 331	76.03 384	71.47 463	94.96 284

MVStest1		72.91 452	69.70 457	82.54 456	78.14 501	73.05 423	88.21 442	86.21 476	60.69 496	64.70 491	90.53 373	46.44 485	85.70 499	58.78 486	53.62 501	88.87 474

tt0320-xc		79.63 430	76.66 439	88.52 361	91.03 388	78.72 320	93.00 301	89.53 459	66.37 487	76.11 454	87.11 444	46.36 486	95.32 418	72.78 411	67.67 482	91.51 434

TinyColmap		79.76 427	77.69 430	85.97 423	91.71 362	73.12 422	89.55 416	90.36 436	75.03 438	72.03 476	90.19 384	46.22 487	96.19 380	63.11 470	81.03 408	88.59 479

myMVS_eth3d		79.67 428	78.79 423	82.32 459	91.92 352	64.08 486	89.75 414	87.40 474	81.72 339	78.82 429	87.20 440	45.33 488	91.29 476	59.09 485	87.84 329	91.60 430

tmp_tt		35.64 489	39.24 489	24.84 512	14.87 560	23.90 538	62.71 515	51.51 521	6.58 539	36.66 521	62.08 520	44.37 489	30.34 535	52.40 496	22.00 529	20.27 535

testing3		80.46 418	79.59 410	83.06 453	93.44 294	64.64 485	93.33 280	85.47 482	84.34 267	79.93 411	90.84 363	44.35 490	92.39 463	57.06 490	87.56 332	92.16 421

new_pmnet		72.15 453	70.13 456	78.20 471	82.95 490	65.68 479	83.91 485	82.40 492	62.94 495	64.47 492	79.82 489	42.85 491	86.26 497	57.41 489	74.44 451	82.65 493

test_vis1_rt		77.96 441	76.46 440	82.48 457	85.89 468	71.74 442	90.25 397	78.89 499	71.03 473	71.30 480	81.35 486	42.49 492	91.05 479	84.55 243	82.37 388	84.65 488

EGC-MVSNET		61.97 465	56.37 470	78.77 469	89.63 432	73.50 417	89.12 426	82.79 490	0.21 558	1.24 560	84.80 464	39.48 493	90.04 484	44.13 506	75.94 449	72.79 504

dongtai		58.82 470	58.24 468	60.56 494	83.13 488	45.09 519	82.32 491	48.22 524	67.61 483	61.70 497	69.15 509	38.75 494	76.05 514	32.01 519	41.31 510	60.55 517

kuosan		53.51 475	53.30 475	54.13 502	76.06 503	45.36 518	80.11 498	48.36 523	59.63 498	54.84 500	63.43 518	37.41 495	62.07 524	20.73 528	39.10 512	54.96 521

usedtu_dtu_shiyan2		74.72 449	71.30 454	84.98 438	77.78 502	70.58 457	91.85 351	90.76 428	67.24 485	68.06 487	82.17 484	37.13 496	92.78 460	60.69 478	66.03 485	91.59 432

pmmvs3		71.81 455	68.71 458	81.11 462	75.86 504	70.42 458	86.74 463	83.66 488	58.95 499	68.64 486	80.89 488	36.93 497	89.52 487	63.10 471	63.59 490	83.39 489

mvsany_test3		74.95 448	73.26 452	80.02 466	74.61 505	63.16 491	85.53 473	78.42 501	74.16 448	74.89 462	86.46 449	36.02 498	89.09 489	82.39 277	66.91 483	87.82 484

PM-MVS		78.11 440	76.12 443	84.09 448	83.54 487	70.08 460	88.97 429	85.27 484	79.93 367	74.73 463	86.43 451	34.70 499	93.48 450	79.43 344	72.06 459	88.72 476

ambc				83.06 453	79.99 498	63.51 490	77.47 502	92.86 362		74.34 466	84.45 466	28.74 500	95.06 423	73.06 410	68.89 475	90.61 452

test_method		50.52 479	48.47 479	56.66 499	52.26 530	18.98 540	41.51 526	81.40 494	10.10 529	44.59 511	75.01 501	28.51 501	68.16 517	53.54 494	49.31 506	82.83 492

DeepMVS_CX				56.31 500	74.23 507	51.81 511		56.67 520	44.85 509	48.54 505	75.16 500	27.87 502	58.74 525	40.92 513	52.22 503	58.39 520

test_fmvs3		77.67 442	77.16 437	79.22 467	79.52 499	61.14 495	92.34 332	91.64 401	73.98 450	78.86 428	86.59 448	27.38 503	87.03 493	88.12 184	75.97 448	89.50 464

test_f		71.95 454	70.87 455	75.21 476	74.21 508	59.37 501	85.07 477	85.82 479	65.25 491	70.42 482	83.13 473	23.62 504	82.93 506	78.32 356	71.94 461	83.33 490

FPMVS		64.63 464	62.55 466	70.88 480	70.80 511	56.71 503	84.42 483	84.42 486	51.78 503	49.57 503	81.61 485	23.49 505	81.48 508	40.61 514	76.25 447	74.46 503

APD_test1		69.04 458	66.26 464	77.36 475	80.51 497	62.79 492	85.46 474	83.51 489	54.11 502	59.14 499	84.79 465	23.40 506	89.61 486	55.22 491	70.24 466	79.68 498

ANet_high		58.88 469	54.22 474	72.86 477	56.50 527	56.67 504	80.75 495	86.00 478	73.09 460	37.39 519	64.63 516	22.17 507	79.49 510	43.51 508	23.96 524	82.43 494

EMVS		42.07 486	41.12 488	44.92 508	63.45 521	35.56 529	73.65 505	63.48 517	33.05 519	26.88 529	45.45 526	21.27 508	67.14 519	19.80 529	23.02 526	32.06 529

ArgMatch-SfM		70.39 456	67.69 460	78.49 470	81.44 494	60.73 496	84.71 482	75.65 510	68.09 482	66.71 490	86.79 446	20.42 509	86.05 498	71.50 418	53.87 500	88.67 478

Gipuma		57.99 471	54.91 473	67.24 489	88.51 441	65.59 480	52.21 519	90.33 437	43.58 511	42.84 512	51.18 523	20.29 510	85.07 500	34.77 516	70.45 465	51.05 522
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 485	42.29 485	46.03 506	65.58 519	37.41 527	73.51 506	64.62 515	33.99 517	28.47 527	47.87 525	19.90 511	67.91 518	22.23 527	24.45 522	32.77 528

ArgMatch-Sym		69.79 457	67.05 462	77.99 473	81.59 493	61.16 494	84.99 478	71.84 511	67.17 486	67.90 488	86.60 447	19.89 512	85.00 501	70.93 426	52.57 502	87.82 484

PMMVS2		59.60 466	56.40 469	69.21 486	68.83 514	46.58 515	73.02 509	77.48 506	55.07 501	49.21 504	72.95 505	17.43 513	80.04 509	49.32 501	44.33 509	80.99 496

LCM-MVSNet		66.00 462	62.16 467	77.51 474	64.51 520	58.29 502	83.87 486	90.90 424	48.17 505	54.69 501	73.31 504	16.83 514	86.75 494	65.47 460	61.67 494	87.48 486

test_vis3_rt		65.12 463	62.60 465	72.69 478	71.44 510	60.71 497	87.17 458	65.55 514	63.80 494	53.22 502	65.65 515	14.54 515	89.44 488	76.65 374	65.38 487	67.91 513

testf1		59.54 467	56.11 471	69.85 484	69.28 512	56.61 505	80.37 496	76.55 508	42.58 512	45.68 509	75.61 496	11.26 516	84.18 502	43.20 510	60.44 496	68.75 510

APD_test2		59.54 467	56.11 471	69.85 484	69.28 512	56.61 505	80.37 496	76.55 508	42.58 512	45.68 509	75.61 496	11.26 516	84.18 502	43.20 510	60.44 496	68.75 510

MVS_clip		24.79 496	27.71 496	16.02 522	35.36 542	15.85 542	27.38 534	5.39 558	6.70 538	40.04 516	63.09 519	10.55 518	8.72 556	27.86 523	33.03 518	23.49 533

PDCNetPlus		48.34 480	45.15 483	57.91 497	61.43 522	41.85 521	65.98 514	38.30 528	47.59 506	37.96 518	71.85 506	10.18 519	66.85 521	52.94 495	20.14 535	65.03 515

VLMVS		10.93 512	11.73 512	8.51 534	11.99 561	6.47 564	9.10 551	5.11 559	0.73 555	17.62 534	25.59 538	9.61 520	6.56 558	6.19 539	19.64 536	12.50 538

VLMVS_CLIP		27.58 493	28.97 494	23.41 514	23.47 556	13.17 548	30.64 532	40.90 526	9.21 531	36.34 522	50.75 524	8.75 521	38.05 530	25.18 525	35.53 514	19.03 537

LoFTR		57.22 472	52.62 476	71.00 479	72.03 509	48.57 514	72.00 510	70.08 513	44.40 510	40.92 515	76.42 494	8.12 522	82.76 507	42.28 512	47.33 508	81.66 495

DenseAffine		56.77 473	52.17 477	70.54 482	74.27 506	53.25 510	77.23 503	50.43 522	49.87 504	47.26 508	77.37 493	7.99 523	79.10 511	50.35 498	34.79 515	79.28 499

RoMa-SfM		53.80 474	49.39 478	67.06 490	67.87 516	48.86 512	75.04 504	38.06 529	47.23 507	47.40 507	78.96 491	7.40 524	76.66 513	48.89 502	33.62 516	75.64 502

MASt3R-SfM		45.78 483	43.96 484	51.24 504	45.04 532	29.83 533	57.88 516	38.83 527	31.88 520	47.48 506	81.30 487	7.16 525	51.15 528	49.56 500	36.51 513	72.74 505

ALIKED-LG		28.00 492	26.54 497	32.41 509	58.12 524	31.80 530	47.26 522	21.21 534	14.15 526	19.16 532	41.93 528	6.72 526	35.73 531	5.96 540	24.32 523	29.69 530

MatchFormer		51.11 477	46.66 481	64.46 492	67.11 517	43.39 520	70.54 511	63.67 516	33.19 518	37.22 520	70.30 508	6.67 527	78.17 512	30.29 520	40.94 511	71.81 507

PMVS	47.18 22	52.22 476	48.46 480	63.48 493	45.72 531	46.20 516	73.41 507	78.31 502	41.03 514	30.06 525	65.68 514	6.05 528	83.43 505	30.04 521	65.86 486	60.80 516
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SP-DiffGlue		20.02 501	19.96 504	20.21 517	19.64 557	13.14 549	30.51 533	15.49 540	8.39 532	19.98 531	43.75 527	5.48 529	13.72 542	13.75 532	22.65 527	33.78 526

RoMa-HiRes		46.47 481	42.20 486	59.28 496	57.74 525	39.86 526	66.76 513	24.64 532	39.96 515	41.50 514	75.37 499	5.40 530	69.26 516	43.35 509	25.09 520	68.71 512

ALIKED-NN		26.07 495	24.75 499	30.02 511	55.08 529	30.61 532	44.20 525	19.22 536	10.98 528	17.98 533	40.71 529	5.39 531	32.83 533	5.59 541	23.63 525	26.63 532

ALIKED-MNN		26.28 494	24.57 500	31.39 510	56.22 528	31.73 531	45.54 523	19.13 537	11.12 527	17.11 535	39.35 530	5.01 532	34.53 532	5.54 542	22.12 528	27.92 531

DKM		50.92 478	46.13 482	65.30 491	66.27 518	45.98 517	73.05 508	31.91 531	45.08 508	42.04 513	75.01 501	4.95 533	73.81 515	47.90 503	28.96 519	76.09 501

SP-LightGlue		20.24 499	20.15 503	20.49 515	43.51 534	12.27 550	38.68 528	14.56 542	7.54 535	12.90 540	30.07 535	4.75 534	14.38 539	7.60 535	21.75 530	34.82 523

SP-SuperGlue		20.22 500	20.18 502	20.36 516	43.26 535	12.27 550	38.71 527	14.77 541	7.64 534	13.04 539	30.21 534	4.73 535	14.21 541	7.59 536	21.65 531	34.59 524

MVE	39.65 23	43.39 484	38.59 490	57.77 498	56.52 526	48.77 513	55.38 517	58.64 519	29.33 522	28.96 526	52.65 522	4.68 536	64.62 523	28.11 522	33.07 517	59.93 518
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SP-NN		19.44 503	19.37 506	19.67 519	41.70 537	11.48 555	37.75 530	13.72 545	6.86 536	11.86 541	29.97 536	4.23 537	14.25 540	7.13 537	21.07 532	33.30 527

SP-MNN		19.61 502	19.42 505	20.19 518	42.15 536	11.42 556	38.15 529	14.24 543	6.55 540	11.64 542	29.88 537	4.16 538	14.56 538	7.09 538	20.92 533	34.58 525

XFeat-MNN		17.43 504	16.95 507	18.86 520	16.90 558	11.28 557	27.31 535	17.08 538	8.08 533	15.61 537	35.73 531	4.06 539	22.95 536	10.20 533	17.59 539	22.35 534

wuyk23d		21.27 498	20.48 501	23.63 513	68.59 515	36.41 528	49.57 520	6.85 552	9.37 530	7.89 543	4.46 558	4.03 540	31.37 534	17.47 531	16.07 540	3.12 554

GLUNet-SfM		31.36 491	26.25 498	46.70 505	35.51 541	24.89 537	33.71 531	36.36 530	19.08 525	23.78 530	52.69 521	3.82 541	56.26 527	19.75 530	11.56 549	58.95 519

DKM-HiRes		45.90 482	41.41 487	59.36 495	59.55 523	39.90 525	67.13 512	23.25 533	39.95 516	38.74 517	71.81 507	3.67 542	66.42 522	43.82 507	24.82 521	71.77 508

XFeat-NN		15.96 505	15.86 508	16.25 521	15.78 559	9.87 560	25.17 536	13.83 544	6.76 537	15.68 536	34.83 532	3.61 543	19.28 537	9.22 534	17.90 537	19.58 536

ELoFTR		40.15 487	35.08 491	55.36 501	41.27 538	28.17 536	47.70 521	43.76 525	29.15 523	30.35 524	65.97 513	2.17 544	66.90 520	34.51 517	20.83 534	71.00 509

SIFT-NN		12.98 506	13.18 509	12.37 523	36.49 540	16.03 541	22.41 537	7.69 548	4.89 541	7.41 544	20.48 540	1.69 545	11.46 544	1.88 546	15.70 541	9.61 540

SIFT-MNN		12.44 507	12.55 510	12.11 524	34.55 543	15.21 543	20.91 538	7.74 547	4.86 542	6.54 546	20.09 541	1.51 546	11.47 543	1.88 546	14.87 543	9.64 539

SIFT-NN-NCMNet		12.12 508	12.25 511	11.75 525	32.82 545	14.83 544	20.73 539	7.58 549	4.72 544	6.60 545	19.53 542	1.49 547	11.15 546	1.74 548	15.02 542	9.28 541

SIFT-NN-UMatch		11.06 511	11.19 517	10.66 529	28.66 551	12.16 552	19.79 540	6.86 551	4.73 543	5.21 549	19.47 544	1.46 548	10.70 549	1.71 549	12.79 547	9.13 543

SIFT-NN-CMatch		11.26 510	11.31 515	11.13 527	30.21 549	13.40 547	18.43 542	6.79 553	4.71 545	6.47 547	19.53 542	1.43 549	10.72 548	1.71 549	12.49 548	9.26 542

SIFT-NN-PointCN		10.26 515	10.46 520	9.65 532	27.18 552	9.89 559	17.89 544	6.17 555	4.40 551	5.65 548	18.29 548	1.43 549	10.09 552	1.61 553	11.55 550	8.99 545

SIFT-NCM-Cal		11.58 509	11.64 513	11.40 526	33.45 544	14.10 545	19.75 541	6.89 550	4.68 547	4.55 553	18.60 547	1.34 551	11.28 545	1.53 554	13.95 544	8.82 546

SIFT-ConvMatch		10.91 513	10.94 518	10.84 528	32.07 546	13.57 546	17.23 545	6.35 554	4.71 545	5.18 550	18.94 545	1.30 552	10.76 547	1.65 552	11.02 551	8.19 547

SIFT-CM-Cal		10.08 516	10.13 522	9.92 531	30.71 548	11.88 553	15.35 547	5.44 557	4.59 549	4.72 551	18.04 550	1.26 553	10.19 551	1.46 556	9.60 553	7.69 549

SIFT-UMatch		10.58 514	10.73 519	10.15 530	31.05 547	11.65 554	18.01 543	5.92 556	4.65 548	4.72 551	18.93 546	1.25 554	10.62 550	1.66 551	10.39 552	8.16 548

SIFT-UM-Cal		9.80 517	10.00 523	9.22 533	30.05 550	10.15 558	16.31 546	4.85 561	4.54 550	4.19 554	18.23 549	1.19 555	9.95 553	1.52 555	9.11 555	7.57 550

MVS_baseline		7.30 524	8.69 527	3.12 538	8.45 562	0.31 567	3.27 552	0.80 564	0.16 559	14.50 538	32.51 533	1.15 556	0.00 561	4.24 543	13.11 546	9.06 544

PMatch-SfM		38.18 488	33.34 492	52.72 503	43.67 533	28.18 535	52.96 518	16.29 539	29.70 521	31.24 523	68.56 511	1.08 557	57.70 526	38.73 515	17.80 538	72.30 506

SIFT-PCN-Cal		8.65 521	8.88 525	7.98 535	26.74 553	7.47 562	13.90 549	4.61 562	4.09 553	3.82 555	15.86 551	1.01 558	8.94 554	1.34 557	8.52 556	7.53 551

SIFT-PointCN		8.76 519	9.03 524	7.96 536	26.50 554	7.60 561	14.94 548	5.08 560	4.10 552	3.74 556	15.46 552	0.94 559	8.92 555	1.33 558	9.14 554	7.37 552

SIFT-NCMNet		7.46 523	7.71 528	6.72 537	25.03 555	6.86 563	11.42 550	2.98 563	4.05 554	3.38 557	13.68 553	0.84 560	7.65 557	1.13 559	6.87 557	5.66 553

PMatch-Up-SfM		32.59 490	28.46 495	44.98 507	37.19 539	22.27 539	44.73 524	10.63 546	23.85 524	27.52 528	64.10 517	0.78 561	47.14 529	34.15 518	13.22 545	65.53 514

test123		8.76 519	11.22 516	1.39 539	0.85 564	0.97 565	85.76 471	0.35 566	0.54 557	2.45 559	8.14 557	0.60 562	0.48 559	2.16 545	0.17 559	2.71 555

testmvs		8.92 518	11.52 514	1.12 540	1.06 563	0.46 566	86.02 467	0.65 565	0.62 556	2.74 558	9.52 556	0.31 563	0.45 560	2.38 544	0.39 558	2.46 556

mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

ab-mvs-re		7.82 522	10.43 521	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	93.88 254	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 559	0.00 564	0.00 561	0.00 560	0.00 560	0.00 557

PatchmatchNet2					0.00 565	62.07 493	85.98 468	87.63 472	68.79 479
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														54.59 493	77.20 441	90.17 458
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.68 474
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				94.84 34	98.88 1	85.89 66	97.32 10	97.86 1	88.11 135	97.21 14	97.54 46		99.67 1	95.27 41	98.85 22	98.95 13

WAC-MVS						64.08 486								59.14 484

FOURS1					98.86 4	85.54 75	98.29 1	97.49 11	89.79 66	96.29 32

MSC_two_6792asdad				96.52 1	97.78 61	90.86 1		96.85 81					99.61 7	96.03 27	99.06 9	99.07 7

No_MVS				96.52 1	97.78 61	90.86 1		96.85 81					99.61 7	96.03 27	99.06 9	99.07 7

eth-test2					0.00 565

eth-test					0.00 565

IU-MVS					98.77 8	86.00 55		96.84 83	81.26 352	97.26 13				95.50 37	99.13 3	99.03 10

save fliter					97.85 56	85.63 74	95.21 142	96.82 86	89.44 77

test_0728_SECOND				95.01 18	98.79 5	86.43 41	97.09 21	97.49 11					99.61 7	95.62 35	99.08 7	98.99 11

GSMVS																96.12 235

test_part2					98.55 15	87.22 20				96.40 31

MTGPA								96.97 66

MTMP							96.16 60	60.64 518

gm-plane-assit					89.60 433	68.00 469			77.28 409		88.99 411		97.57 250	79.44 343

test9_res														91.91 111	98.71 36	98.07 84

agg_prior2														90.54 140	98.68 41	98.27 65

agg_prior					97.38 73	85.92 62		96.72 101		92.16 121			98.97 88

test_prior4						85.96 59	94.11 226

test_prior				93.82 74	97.29 78	84.49 99		96.88 79					98.87 101			98.11 83

旧先验2							93.36 279		71.25 471	94.37 62			97.13 308	86.74 206

新几何2							93.11 294

无先验							93.28 287	96.26 141	73.95 451				99.05 68	80.56 317		96.59 214

原ACMM2							92.94 305

testdata2													98.75 117	78.30 357

testdata1							92.15 342		87.94 144

plane_prior7					94.70 204	82.74 166

plane_prior5								96.22 147					98.12 181	88.15 181	89.99 288	94.63 297

plane_prior4											94.86 204

plane_prior3						82.75 164			90.26 50	86.91 254

plane_prior2							95.85 93		90.81 27

plane_prior1					94.59 213

plane_prior						82.73 167	95.21 142		89.66 71						89.88 293

n2								0.00 567

nn								0.00 567

door-mid								85.49 481

test11								96.57 113

door								85.33 483

HQP5-MVS						81.56 207

HQP-NCC					94.17 253		94.39 205		88.81 104	85.43 300

ACMP_Plane					94.17 253		94.39 205		88.81 104	85.43 300

BP-MVS														87.11 203

HQP4-MVS										85.43 300			97.96 218			94.51 307

HQP3-MVS								96.04 174							89.77 297

NP-MVS					94.37 234	82.42 181					93.98 247

ACMMP++_ref															87.47 333

ACMMP++															88.01 325

High-resolution multi-view benchmark