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									82.47 311	97.09 19	97.07 72	92.72 1	98.04 201	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 93	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	80.00 278	94.00 240	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	96.91 324	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		95.80 143	97.95 98

ME-MVS		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	87.13 176	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	88.14 131	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	96.99 112	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	85.90 212	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	78.37 331	93.40 275	97.19 45	88.02 139	94.99 58	97.21 62	88.35 26	98.44 154	94.07 55	98.09 77	99.23 1

9.14			94.47 35		97.79 59		96.08 69	97.44 20	86.13 210	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	87.76 155	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	91.38 226	97.69 64	76.78 375	94.25 216	96.29 133	88.33 121	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	84.15 268	90.05 190	95.66 157	87.77 31	99.15 62	89.91 152	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	94.07 231	96.78 91	81.61 341	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	94.07 231	96.78 91	81.86 332	92.77 102	96.20 110	87.63 34	99.12 64	92.14 99	98.69 39	97.94 99

test_8					97.49 70	86.30 47	94.02 237	96.76 94	81.86 332	92.70 106	96.20 110	87.63 34	99.02 74

ZD-MVS					98.15 41	86.62 35		97.07 61	83.63 281	94.19 66	96.91 78	87.57 36	99.26 52	91.99 106	98.44 57

fmvsm_l_conf0.5_n		94.29 41	94.46 36	93.79 77	95.28 159	85.43 78	95.68 107	96.43 122	86.56 195	96.84 25	97.81 39	87.56 37	98.77 116	97.14 15	96.82 120	97.16 174

fmvsm_l_conf0.5_n_a		94.20 47	94.40 38	93.60 83	95.29 158	84.98 85	95.61 115	96.28 136	86.31 202	96.75 28	97.86 37	87.40 38	98.74 120	97.07 17	97.02 111	97.07 179

TSAR-MVS + GP.		93.66 67	93.41 78	94.41 54	96.59 93	86.78 28	94.40 203	93.93 325	89.77 67	94.21 65	95.59 161	87.35 39	98.61 136	92.72 79	96.15 137	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	85.68 219	95.05 57	97.18 66	87.31 40	99.07 66	91.90 112	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	96.97 189

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							94.12 223		87.67 159	92.63 110	96.39 105	86.62 46		91.50 120	98.67 44

CDPH-MVS		92.83 94	92.30 103	94.44 50	97.79 59	86.11 54	94.06 233	96.66 106	80.09 363	92.77 102	96.63 94	86.62 46	99.04 70	87.40 195	98.66 45	98.17 75

DPM-MVS		92.58 100	91.74 111	95.08 16	96.19 108	89.31 5	92.66 316	96.56 114	83.44 287	91.68 141	95.04 193	86.60 48	98.99 83	85.60 222	97.92 85	96.93 193

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	94.62 207	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	95.42 153	85.04 84	93.06 297	97.13 55	90.74 33	91.84 133	95.09 192	86.32 51	99.21 56	91.22 124	98.45 56	97.65 132
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	97.17 167

ZNCC-MVS		94.47 33	94.28 45	95.03 17	98.52 18	86.96 21	96.85 33	97.32 35	88.24 126	93.15 89	97.04 73	86.17 53	99.62 5	92.40 87	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 90	98.77 32	98.30 56

MVS_111021_HR		93.45 74	93.31 79	93.84 73	96.99 83	84.84 87	93.24 288	97.24 42	88.76 107	91.60 142	95.85 143	86.07 55	98.66 126	91.91 110	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	88.28 125	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	98.24 171	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	85.15 243	93.56 83	96.28 107	85.60 59	99.31 48	92.45 84	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	86.26 204	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	88.24 126	93.26 86	96.83 82	85.48 61	99.59 11	91.43 122	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	92.06 104	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	90.87 133	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	97.17 167

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 95	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 98	98.83 26	98.25 70

test_fmvsmconf0.1_n		94.20 47	94.31 43	93.88 71	92.46 333	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 90	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	98.33 166	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	91.99 106	98.56 54	98.47 38

X-MVStestdata		88.31 241	86.13 290	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 36	92.85 97	23.41 532	85.02 70	99.49 31	91.99 106	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	84.42 265	94.09 69	95.56 163	85.01 73	98.69 125	94.96 45	98.66 45	97.67 131

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	97.76 232	92.19 97	98.66 45	96.76 204

HPM-MVS		94.02 54	93.88 61	94.43 52	98.39 29	85.78 71	97.25 15	97.07 61	86.90 187	92.62 111	96.80 86	84.85 76	99.17 58	92.43 85	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	88.20 129	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	87.45 166	93.26 86	97.33 56	84.62 79	99.51 29	90.75 136	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	97.72 128

EI-MVSNet-Vis-set		93.01 92	92.92 89	93.29 90	95.01 173	83.51 134	94.48 191	95.77 199	90.87 25	92.52 113	96.67 89	84.50 80	99.00 81	91.99 106	94.44 184	97.36 151

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	87.46 164	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	95.20 165	84.04 118	95.07 151	96.51 118	90.73 34	92.96 94	91.19 347	84.06 84	98.34 164	91.72 115	96.54 127	96.54 216

EI-MVSNet-UG-set		92.74 98	92.62 97	93.12 102	94.86 187	83.20 144	94.40 203	95.74 202	90.71 35	92.05 123	96.60 96	84.00 85	98.99 83	91.55 118	93.63 212	97.17 167

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	91.44 121	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	86.96 183	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	95.16 167	80.01 277	95.36 125	96.73 99	88.44 118	89.34 203	92.16 310	83.82 88	98.45 152	89.35 162	97.06 109	97.48 146

fmvsm_s_conf0.5_n_3		94.49 32	95.13 17	92.56 146	95.49 151	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	97.78 124

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	88.13 132	95.82 43	98.04 30	83.43 90	98.48 144	96.97 21	96.23 134	96.92 194

casdiffmvs_mvg		92.96 93	92.83 91	93.35 88	94.59 211	83.40 137	95.00 156	96.34 130	90.30 46	92.05 123	96.05 125	83.43 90	98.15 179	92.07 101	95.67 147	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	80.50 257	97.33 8	95.25 249	86.15 207	89.76 196	95.60 160	83.42 92	98.32 168	87.37 197	93.25 227	97.56 140

test_fmvsmvis_n_1920		93.44 75	93.55 75	93.10 103	93.67 284	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	97.44 101	96.32 221

fmvsm_s_conf0.5_n_5		93.96 58	94.18 53	93.30 89	94.79 191	83.81 123	95.77 100	96.74 98	88.02 139	96.23 33	97.84 38	83.36 94	98.83 110	97.49 8	97.34 105	97.25 159

fmvsm_s_conf0.5_n_6		94.11 52	94.56 33	92.76 129	94.98 177	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	97.43 150

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	84.47 243	95.47 154	97.45 148

UniMVSNet_NR-MVSNet		89.92 186	89.29 189	91.81 205	93.39 293	83.72 125	94.43 197	97.12 56	89.80 63	86.46 263	93.32 270	83.16 96	97.23 298	84.92 231	81.02 406	94.49 307

EC-MVSNet		93.44 75	93.71 71	92.63 142	95.21 164	82.43 180	97.27 14	96.71 102	90.57 39	92.88 96	95.80 148	83.16 96	98.16 178	93.68 60	98.14 74	97.31 152

fmvsm_s_conf0.5_n_4		93.86 61	94.37 40	92.33 165	95.13 170	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	96.78 121	97.13 175

fmvsm_s_conf0.5_n_a		93.57 68	93.76 68	93.00 111	95.02 172	83.67 127	96.19 57	96.10 168	87.27 170	95.98 40	98.05 27	83.07 100	98.45 152	96.68 23	95.51 151	96.88 197

MM		95.10 14	94.91 26	95.68 5	96.09 117	88.34 10	96.68 38	94.37 307	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	87.46 164	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		95.56 220	71.09 469	91.26 152	96.24 108	82.87 103	98.86 103	79.19 345	98.10 76	96.07 237

fmvsm_s_conf0.1_n		93.46 72	93.66 73	92.85 121	93.75 276	83.13 148	96.02 77	95.74 202	87.68 158	95.89 41	98.17 5	82.78 104	98.46 148	96.71 22	96.17 136	96.98 188

Casviewmamba		92.82 96	92.75 92	93.03 108	94.79 191	82.44 179	95.39 124	96.24 144	90.58 38	91.79 137	96.43 104	82.73 105	98.19 176	91.31 123	95.54 149	98.46 41

原ACMM1				92.01 184	97.34 74	81.05 229		96.81 89	78.89 379	90.45 174	95.92 136	82.65 106	98.84 107	80.68 313	98.26 63	96.14 231

casdiffmvs		92.51 101	92.43 100	92.74 133	94.41 231	81.98 194	94.54 188	96.23 146	89.57 74	91.96 127	96.17 115	82.58 107	98.01 208	90.95 131	95.45 156	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 96	98.30 61	97.57 139
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	85.77 216	92.47 115	97.13 69	82.38 109	99.07 66	90.51 141	98.40 58	97.92 108

baseline		92.39 106	92.29 104	92.69 138	94.46 226	81.77 204	94.14 222	96.27 137	89.22 87	91.88 131	96.00 129	82.35 110	97.99 210	91.05 126	95.27 162	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	94.60 218	82.33 111	98.62 134	92.40 87	92.86 239	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	94.60 218	82.33 111	98.62 134	92.40 87	92.86 239	98.27 65

fmvsm_s_conf0.1_n_a		93.19 86	93.26 80	92.97 113	92.49 331	83.62 130	96.02 77	95.72 206	86.78 189	96.04 38	98.19 4	82.30 113	98.43 156	96.38 25	95.42 157	96.86 198

DP-MVS Recon		91.95 111	91.28 131	93.96 69	98.33 34	85.92 62	94.66 182	96.66 106	82.69 309	90.03 191	95.82 146	82.30 113	99.03 71	84.57 241	96.48 130	96.91 195

hybridcas		92.43 104	92.33 101	92.74 133	94.51 219	81.84 198	95.05 154	96.16 160	89.60 72	91.40 149	96.20 110	82.23 115	98.09 190	89.95 151	95.87 141	98.28 62

PAPR		90.02 180	89.27 191	92.29 172	95.78 135	80.95 234	92.68 315	96.22 147	81.91 328	86.66 260	93.75 260	82.23 115	98.44 154	79.40 344	94.79 170	97.48 146

MVS_Test		91.31 137	91.11 134	91.93 193	94.37 232	80.14 266	93.46 273	95.80 197	86.46 198	91.35 151	93.77 258	82.21 117	98.09 190	87.57 192	94.95 166	97.55 142

nrg030		91.08 148	90.39 153	93.17 99	93.07 305	86.91 23	96.41 42	96.26 141	88.30 123	88.37 223	94.85 205	82.19 118	97.64 243	91.09 125	82.95 376	94.96 281

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	94.66 215	82.11 119	98.50 142	92.33 92	92.82 242	98.27 65

UniMVSNet (Re)		89.80 190	89.07 195	92.01 184	93.60 287	84.52 98	94.78 173	97.47 16	89.26 86	86.44 266	92.32 305	82.10 120	97.39 282	84.81 234	80.84 410	94.12 321

testdata				90.49 272	96.40 102	77.89 347		95.37 240	72.51 461	93.63 80	96.69 87	82.08 121	97.65 241	83.08 262	97.39 102	95.94 242

PAPM_NR		91.22 140	90.78 145	92.52 150	97.60 66	81.46 213	94.37 209	96.24 144	86.39 201	87.41 243	94.80 207	82.06 122	98.48 144	82.80 270	95.37 158	97.61 135

MG-MVS		91.77 119	91.70 112	92.00 187	97.08 82	80.03 276	93.60 268	95.18 255	87.85 151	90.89 167	96.47 102	82.06 122	98.36 161	85.07 229	97.04 110	97.62 133

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		90.27 171	90.18 159	90.53 265	93.71 281	79.85 285	95.77 100	97.59 6	89.31 83	86.27 270	94.67 214	81.93 125	97.01 317	84.26 245	88.09 321	94.71 293

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	97.20 165

fmvsm_s_conf0.5_n_7		93.15 89	93.76 68	91.31 229	94.42 230	79.48 297	94.52 189	97.14 54	89.33 82	94.17 67	98.09 18	81.83 127	97.49 259	96.33 26	98.02 81	96.95 190

FIs		90.51 167	90.35 154	90.99 247	93.99 263	80.98 232	95.73 104	97.54 9	89.15 90	86.72 259	94.68 211	81.83 127	97.24 297	85.18 227	88.31 318	94.76 292

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	94.69 204	80.90 237	93.68 266	96.17 158	87.15 174	91.09 163	95.70 156	81.75 130	98.05 200	89.67 159	94.35 186	97.90 111

viewcassd2359sk11		91.79 114	91.62 113	92.29 172	94.62 207	80.88 238	93.70 263	96.18 157	87.38 168	91.13 156	95.85 143	81.62 131	98.06 196	89.71 156	94.40 185	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	88.33 121	90.15 189	97.03 74	81.44 132	99.51 29	90.85 134	95.74 146	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	91.11 134	93.01 110	94.35 236	83.39 138	94.60 184	95.10 259	87.10 177	90.57 173	93.10 281	81.43 133	98.07 195	89.29 164	94.48 182	97.59 138

MVS_111021_LR		92.47 103	92.29 104	92.98 112	95.99 126	84.43 104	93.08 294	96.09 169	88.20 129	91.12 157	95.72 155	81.33 134	97.76 232	91.74 114	97.37 103	96.75 205

E2		91.79 114	91.61 114	92.31 167	94.49 222	80.86 240	93.74 258	96.19 151	87.63 161	91.16 153	95.94 134	81.31 135	98.06 196	89.76 154	94.29 189	97.99 94

E3		91.78 117	91.61 114	92.30 170	94.48 223	80.86 240	93.73 259	96.19 151	87.63 161	91.16 153	95.95 133	81.30 136	98.06 196	89.76 154	94.29 189	97.99 94

mvs_anonymous		89.37 209	89.32 188	89.51 333	93.47 290	74.22 407	91.65 356	94.83 284	82.91 304	85.45 295	93.79 256	81.23 137	96.36 370	86.47 209	94.09 194	97.94 99

PVSNet_BlendedMVS		89.98 181	89.70 174	90.82 256	96.12 112	81.25 219	93.92 246	96.83 84	83.49 286	89.10 207	92.26 308	81.04 138	98.85 105	86.72 207	87.86 325	92.35 413

PVSNet_Blended		90.73 155	90.32 155	91.98 188	96.12 112	81.25 219	92.55 320	96.83 84	82.04 324	89.10 207	92.56 298	81.04 138	98.85 105	86.72 207	95.91 140	95.84 248

viewmanbaseed2359cas		91.78 117	91.58 116	92.37 160	94.32 239	81.07 228	93.76 256	95.96 182	87.26 171	91.50 144	95.88 139	80.92 140	97.97 215	89.70 157	94.92 167	98.07 84

E4		91.74 122	91.55 119	92.31 167	94.27 244	80.80 244	93.81 253	96.17 158	87.97 141	91.11 158	96.05 125	80.75 141	98.08 193	89.78 153	94.02 196	98.06 89

viewmamba		91.38 134	91.32 128	91.58 214	93.02 312	79.63 294	92.83 308	95.38 237	88.29 124	90.66 170	95.81 147	80.63 142	97.50 258	91.52 119	93.71 210	97.62 133

MGCNet		94.18 50	93.80 64	95.34 10	94.91 184	87.62 15	95.97 82	93.01 358	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	94.87 202	80.56 143	98.66 126	92.42 86	93.10 234	98.15 77

API-MVS		90.66 161	90.07 163	92.45 155	96.36 104	84.57 95	96.06 73	95.22 252	82.39 312	89.13 206	94.27 235	80.32 145	98.46 148	80.16 323	96.71 123	94.33 313

PVSNet_Blended_VisFu		91.38 134	90.91 141	92.80 124	96.39 103	83.17 146	94.87 164	96.66 106	83.29 292	89.27 205	94.46 227	80.29 146	99.17 58	87.57 192	95.37 158	96.05 240

viewdifsd2359ckpt07		91.11 146	91.02 138	91.41 224	94.21 249	78.37 331	92.91 304	95.71 207	87.50 163	90.32 179	95.88 139	80.27 147	97.99 210	88.78 175	93.55 214	97.86 114

test222					96.55 96	81.70 205	92.22 338	95.01 263	68.36 477	90.20 182	96.14 120	80.26 148			97.80 92	96.05 240

diffmvs		91.37 136	91.23 132	91.77 206	93.09 303	80.27 261	92.36 326	95.52 225	87.03 180	91.40 149	94.93 198	80.08 149	97.44 268	92.13 100	94.56 179	97.61 135
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	91.10 136	91.61 212	93.07 305	79.86 283	92.83 308	95.34 243	87.07 178	91.04 164	95.53 164	80.01 151	97.43 269	90.96 130	94.08 195	97.56 140

diffmvs_AUTHOR		91.51 132	91.44 125	91.73 207	93.09 303	80.27 261	92.51 321	95.58 219	87.22 172	91.80 136	95.57 162	79.96 152	97.48 260	92.23 94	94.97 165	97.45 148

E5new		91.71 124	91.55 119	92.20 178	94.33 237	80.62 250	94.41 199	96.19 151	88.06 135	91.11 158	96.16 116	79.92 153	98.03 204	90.00 146	93.80 205	97.94 99

E6new		91.71 124	91.55 119	92.20 178	94.32 239	80.62 250	94.41 199	96.19 151	88.06 135	91.11 158	96.16 116	79.92 153	98.03 204	90.00 146	93.80 205	97.94 99

E6		91.71 124	91.55 119	92.20 178	94.32 239	80.62 250	94.41 199	96.19 151	88.06 135	91.11 158	96.16 116	79.92 153	98.03 204	90.00 146	93.80 205	97.94 99

E5		91.71 124	91.55 119	92.20 178	94.33 237	80.62 250	94.41 199	96.19 151	88.06 135	91.11 158	96.16 116	79.92 153	98.03 204	90.00 146	93.80 205	97.94 99

viewmacassd2359aftdt		91.67 130	91.43 126	92.37 160	93.95 267	81.00 231	93.90 250	95.97 181	87.75 156	91.45 147	96.04 127	79.92 153	97.97 215	89.26 165	94.67 173	98.14 78

IterMVS-LS		88.36 240	87.91 234	89.70 317	93.80 273	78.29 335	93.73 259	95.08 261	85.73 217	84.75 316	91.90 326	79.88 158	96.92 323	83.83 252	82.51 382	93.89 333
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 214	88.86 206	89.80 311	91.84 353	78.30 334	93.70 263	95.01 263	85.73 217	87.15 247	95.28 179	79.87 159	97.21 300	83.81 253	87.36 333	93.88 336

TAPA-MVS	84.62 6	88.16 245	87.01 255	91.62 211	96.64 91	80.65 247	94.39 205	96.21 150	76.38 420	86.19 273	95.44 169	79.75 160	98.08 193	62.75 470	95.29 160	96.13 232
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 205	88.64 209	91.71 209	94.74 196	80.81 243	93.54 269	95.10 259	83.11 296	86.82 258	90.67 370	79.74 161	97.75 236	80.51 316	93.55 214	96.57 214

pcd_1.5k_mvsjas		6.64 518	8.86 520	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	79.70 162	0.00 554	0.00 552	0.00 552	0.00 549

PS-MVSNAJss		89.97 182	89.62 177	91.02 244	91.90 351	80.85 242	95.26 136	95.98 178	86.26 204	86.21 272	94.29 232	79.70 162	97.65 241	88.87 174	88.10 319	94.57 299

PS-MVSNAJ		91.18 142	90.92 140	91.96 190	95.26 162	82.60 177	92.09 343	95.70 208	86.27 203	91.84 133	92.46 300	79.70 162	98.99 83	89.08 167	95.86 142	94.29 314

viewdifsd2359ckpt09		91.18 142	90.65 149	92.75 131	94.61 210	82.36 185	94.32 212	95.74 202	84.72 258	89.66 197	95.15 190	79.69 165	98.04 201	87.70 189	94.27 191	97.85 117

viewdifsd2359ckpt13		91.20 141	90.75 146	92.54 148	94.30 242	82.13 189	94.03 235	95.89 190	85.60 222	90.20 182	95.36 175	79.69 165	97.90 225	87.85 187	93.86 201	97.61 135

xiu_mvs_v2_base		91.13 144	90.89 142	91.86 199	94.97 178	82.42 181	92.24 336	95.64 216	86.11 211	91.74 140	93.14 279	79.67 167	98.89 99	89.06 168	95.46 155	94.28 315

WR-MVS_H		87.80 254	87.37 245	89.10 342	93.23 296	78.12 338	95.61 115	97.30 38	87.90 147	83.72 347	92.01 321	79.65 168	96.01 385	76.36 375	80.54 414	93.16 376

viewmambaseed2359dif		90.04 179	89.78 173	90.83 254	92.85 320	77.92 343	92.23 337	95.01 263	81.90 329	90.20 182	95.45 168	79.64 169	97.34 286	87.52 194	93.17 229	97.23 164

EPNet		91.79 114	91.02 138	94.10 65	90.10 419	85.25 81	96.03 76	92.05 385	92.83 5	87.39 246	95.78 151	79.39 170	99.01 76	88.13 182	97.48 100	98.05 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 285	86.62 271	89.02 345	92.13 342	77.40 364	90.91 380	94.81 286	81.28 348	84.32 333	90.08 388	79.26 171	96.62 341	83.81 253	82.94 377	93.04 383

test_fmvsmconf0.01_n		93.19 86	93.02 87	93.71 81	89.25 432	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	97.24 106	97.74 126

miper_enhance_ethall		86.90 297	86.18 288	89.06 343	91.66 362	77.58 362	90.22 399	94.82 285	79.16 375	84.48 324	89.10 407	79.19 173	96.66 334	84.06 248	82.94 377	92.94 386

hybridnocas07		90.93 149	90.72 147	91.54 216	92.75 325	79.72 291	92.35 328	95.21 253	86.41 200	90.44 177	95.40 172	79.17 174	97.39 282	90.83 135	93.94 199	97.50 145

NR-MVSNet		88.58 234	87.47 243	91.93 193	93.04 309	84.16 113	94.77 174	96.25 143	89.05 94	80.04 405	93.29 273	79.02 175	97.05 314	81.71 296	80.05 420	94.59 297

hybrid		90.69 157	90.45 152	91.43 223	92.67 329	79.42 302	92.28 335	95.21 253	85.15 243	90.39 178	95.37 174	78.93 176	97.32 288	90.27 144	93.74 209	97.55 142

TAMVS		89.21 211	88.29 222	91.96 190	93.71 281	82.62 176	93.30 283	94.19 315	82.22 318	87.78 237	93.94 248	78.83 177	96.95 321	77.70 361	92.98 236	96.32 221

c3_l		87.14 290	86.50 277	89.04 344	92.20 339	77.26 366	91.22 372	94.70 292	82.01 325	84.34 332	90.43 375	78.81 178	96.61 344	83.70 257	81.09 403	93.25 370

1112_ss		88.42 236	87.33 246	91.72 208	94.92 182	80.98 232	92.97 302	94.54 298	78.16 397	83.82 344	93.88 253	78.78 179	97.91 223	79.45 340	89.41 298	96.26 225

CDS-MVSNet		89.45 201	88.51 213	92.29 172	93.62 286	83.61 132	93.01 298	94.68 293	81.95 326	87.82 236	93.24 275	78.69 180	96.99 318	80.34 319	93.23 228	96.28 224
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 195	88.92 202	91.67 210	95.47 152	81.15 224	92.38 325	94.78 288	83.11 296	89.06 209	94.32 230	78.67 181	96.61 344	81.57 297	90.89 272	97.24 160

CPTT-MVS		91.99 110	91.80 110	92.55 147	98.24 38	81.98 194	96.76 35	96.49 120	81.89 331	90.24 180	96.44 103	78.59 182	98.61 136	89.68 158	97.85 89	97.06 180

IS-MVSNet		91.43 133	91.09 137	92.46 153	95.87 133	81.38 216	96.95 24	93.69 342	89.72 69	89.50 201	95.98 131	78.57 183	97.77 231	83.02 264	96.50 129	98.22 72

dtuplus		89.78 192	89.43 183	90.85 253	92.83 321	77.91 344	92.32 333	94.97 269	82.33 316	90.20 182	95.53 164	78.56 184	97.38 284	85.15 228	92.95 237	97.24 160

casdiffseed414692147		91.11 146	90.55 151	92.81 122	94.27 244	82.58 178	94.81 170	96.03 176	87.93 145	90.17 187	95.62 159	78.51 185	97.90 225	84.18 247	93.45 221	97.94 99

OMC-MVS		91.23 138	90.62 150	93.08 105	96.27 106	84.07 114	93.52 270	95.93 184	86.95 184	89.51 199	96.13 121	78.50 186	98.35 163	85.84 220	92.90 238	96.83 203

IMVS_0403		89.97 182	89.64 176	90.96 250	93.72 277	77.75 355	93.00 299	95.34 243	85.53 226	88.77 216	94.49 223	78.49 187	97.84 228	84.75 235	92.65 244	97.28 155

PCF-MVS	84.11 10	87.74 256	86.08 294	92.70 137	94.02 258	84.43 104	89.27 419	95.87 193	73.62 451	84.43 327	94.33 229	78.48 188	98.86 103	70.27 426	94.45 183	94.81 290
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 242	88.32 221	88.27 366	94.71 201	72.41 434	93.15 289	90.98 417	87.77 154	79.25 420	91.96 323	78.35 189	95.75 399	83.04 263	95.62 148	96.65 210

HY-MVS	83.01 12	89.03 220	87.94 231	92.29 172	94.86 187	82.77 163	92.08 344	94.49 301	81.52 344	86.93 250	92.79 292	78.32 190	98.23 172	79.93 326	90.55 276	95.88 246

GeoE		90.05 178	89.43 183	91.90 198	95.16 167	80.37 260	95.80 96	94.65 294	83.90 273	87.55 242	94.75 208	78.18 191	97.62 245	81.28 301	93.63 212	97.71 129

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	90.75 136	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	94.43 303	91.65 17	92.68 107	96.13 121	77.97 192	98.84 107	90.75 136	94.72 171	97.92 108

MVS		87.44 273	86.10 293	91.44 222	92.61 330	83.62 130	92.63 317	95.66 213	67.26 480	81.47 383	92.15 311	77.95 194	98.22 174	79.71 329	95.48 153	92.47 406

MVSFormer		91.68 129	91.30 129	92.80 124	93.86 269	83.88 121	95.96 83	95.90 188	84.66 261	91.76 138	94.91 199	77.92 195	97.30 289	89.64 160	97.11 107	97.24 160

lupinMVS		90.92 150	90.21 157	93.03 108	93.86 269	83.88 121	92.81 310	93.86 329	79.84 366	91.76 138	94.29 232	77.92 195	98.04 201	90.48 142	97.11 107	97.17 167

Test_1112_low_res		87.65 259	86.51 276	91.08 240	94.94 181	79.28 311	91.77 351	94.30 310	76.04 426	83.51 354	92.37 303	77.86 197	97.73 237	78.69 351	89.13 305	96.22 226

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	98.17 177	88.90 172	93.38 223	98.13 79

icg_test_0407_2		89.15 212	88.97 199	89.68 323	93.72 277	77.75 355	88.26 438	95.34 243	85.53 226	88.34 224	94.49 223	77.69 199	93.99 438	84.75 235	92.65 244	97.28 155

IMVS_0407		89.85 189	89.51 180	90.88 252	93.72 277	77.75 355	93.07 296	95.34 243	85.53 226	88.34 224	94.49 223	77.69 199	97.60 246	84.75 235	92.65 244	97.28 155

fmvsm_s_conf0.5_n_2		93.47 71	93.83 62	92.39 159	95.36 155	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	96.58 126	97.03 183

mvsany_test1		85.42 338	85.30 323	85.77 425	87.95 451	75.41 395	87.61 452	80.97 491	76.82 416	88.68 217	95.83 145	77.44 202	90.82 477	85.90 218	86.51 340	91.08 445

DU-MVS		89.34 210	88.50 214	91.85 201	93.04 309	83.72 125	94.47 194	96.59 111	89.50 75	86.46 263	93.29 273	77.25 203	97.23 298	84.92 231	81.02 406	94.59 297

Baseline_NR-MVSNet		87.07 292	86.63 270	88.40 360	91.44 366	77.87 348	94.23 219	92.57 370	84.12 269	85.74 283	92.08 317	77.25 203	96.04 381	82.29 279	79.94 421	91.30 437

jason		90.80 152	90.10 161	92.90 117	93.04 309	83.53 133	93.08 294	94.15 318	80.22 360	91.41 148	94.91 199	76.87 205	97.93 221	90.28 143	96.90 116	97.24 160
jason: jason.
PAPM		86.68 309	85.39 319	90.53 265	93.05 308	79.33 310	89.79 409	94.77 289	78.82 382	81.95 379	93.24 275	76.81 206	97.30 289	66.94 450	93.16 230	94.95 285

Vis-MVSNet (Re-imp)		89.59 196	89.44 182	90.03 297	95.74 136	75.85 389	95.61 115	90.80 424	87.66 160	87.83 235	95.40 172	76.79 207	96.46 362	78.37 352	96.73 122	97.80 122

baseline1		88.10 246	87.28 248	90.57 261	94.96 179	80.07 271	94.27 215	91.29 410	86.74 190	87.41 243	94.00 245	76.77 208	96.20 376	80.77 310	79.31 429	95.44 262

114514_t		89.51 198	88.50 214	92.54 148	98.11 43	81.99 193	95.16 147	96.36 129	70.19 473	85.81 280	95.25 181	76.70 209	98.63 133	82.07 285	96.86 119	97.00 187

PLC	84.53 7	89.06 218	88.03 227	92.15 182	97.27 79	82.69 170	94.29 214	95.44 233	79.71 368	84.01 341	94.18 238	76.68 210	98.75 117	77.28 365	93.41 222	95.02 277
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 224	87.95 230	91.49 219	92.68 328	83.01 158	94.92 161	96.31 132	89.88 57	85.53 289	93.85 255	76.63 211	96.96 320	81.91 289	79.87 423	94.50 305

MAR-MVS		90.30 170	89.37 186	93.07 107	96.61 92	84.48 100	95.68 107	95.67 211	82.36 314	87.85 233	92.85 286	76.63 211	98.80 112	80.01 325	96.68 124	95.91 243
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	94.62 207	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	96.21 135	97.03 183

SSM_0407		90.47 168	89.80 172	92.46 153	94.76 193	82.66 171	93.98 242	95.00 267	85.41 231	88.96 211	95.35 176	76.13 214	97.88 227	85.46 225	93.15 231	96.85 199

SSM_0404		90.73 155	90.08 162	92.69 138	95.00 176	83.13 148	94.32 212	95.00 267	85.41 231	89.84 192	95.35 176	76.13 214	97.98 213	85.46 225	94.18 193	96.95 190

WR-MVS		88.38 238	87.67 238	90.52 269	93.30 295	80.18 264	93.26 286	95.96 182	88.57 116	85.47 294	92.81 290	76.12 216	96.91 324	81.24 302	82.29 386	94.47 310

v8		87.50 272	86.71 264	89.89 304	91.37 371	79.40 303	94.50 190	95.38 237	84.81 255	83.60 352	91.33 342	76.05 217	97.42 271	82.84 268	80.51 417	92.84 390

v148		87.04 293	86.32 283	89.21 338	90.94 391	77.26 366	93.71 262	94.43 303	84.84 254	84.36 331	90.80 364	76.04 218	97.05 314	82.12 282	79.60 426	93.31 367

mamba_0408		89.06 218	87.92 232	92.50 151	94.76 193	82.66 171	79.84 495	94.64 295	85.18 236	88.96 211	95.00 195	76.00 219	97.98 213	83.74 255	93.15 231	96.85 199

SSM_04072		88.57 235	87.92 232	90.51 270	94.76 193	82.66 171	79.84 495	94.64 295	85.18 236	88.96 211	95.00 195	76.00 219	92.03 463	83.74 255	93.15 231	96.85 199

eth_miper_zixun_eth		86.50 316	85.77 308	88.68 354	91.94 348	75.81 390	90.47 391	94.89 278	82.05 322	84.05 339	90.46 374	75.96 221	96.77 328	82.76 271	79.36 428	93.46 363

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	84.02 340	96.62 95	75.95 222	99.34 43	87.77 188	97.68 97	98.59 29

balanced_ft_v1		92.23 108	92.05 107	92.77 126	95.40 154	81.78 203	95.80 96	95.69 210	87.94 143	91.92 130	95.04 193	75.91 223	98.71 123	93.83 59	96.94 113	97.82 121

h-mvs33		90.80 152	90.15 160	92.75 131	96.01 122	82.66 171	95.43 123	95.53 224	89.80 63	93.08 91	95.64 158	75.77 224	99.00 81	92.07 101	78.05 433	96.60 211

hse-mvs2		89.88 188	89.34 187	91.51 218	94.83 189	81.12 226	93.94 244	93.91 328	89.80 63	93.08 91	93.60 263	75.77 224	97.66 240	92.07 101	77.07 440	95.74 253

BH-untuned		88.60 232	88.13 226	90.01 300	95.24 163	78.50 327	93.29 284	94.15 318	84.75 257	84.46 325	93.40 267	75.76 226	97.40 279	77.59 362	94.52 181	94.12 321

DIV-MVS_self_test		86.53 314	85.78 306	88.75 351	92.02 347	76.45 381	90.74 382	94.30 310	81.83 334	83.34 360	90.82 363	75.75 227	96.57 351	81.73 295	81.52 398	93.24 371

BH-w/o		87.57 268	87.05 253	89.12 341	94.90 185	77.90 346	92.41 323	93.51 345	82.89 305	83.70 348	91.34 341	75.75 227	97.07 311	75.49 383	93.49 218	92.39 411

cl____		86.52 315	85.78 306	88.75 351	92.03 346	76.46 380	90.74 382	94.30 310	81.83 334	83.34 360	90.78 365	75.74 229	96.57 351	81.74 294	81.54 397	93.22 372

cdsmvs_eth3d_5k		22.14 492	29.52 490	0.00 534	0.00 558	0.00 560	0.00 545	95.76 200	0.00 552	0.00 554	94.29 232	75.66 230	0.00 554	0.00 552	0.00 552	0.00 549

CNLPA		89.07 217	87.98 229	92.34 164	96.87 85	84.78 90	94.08 230	93.24 350	81.41 345	84.46 325	95.13 191	75.57 231	96.62 341	77.21 366	93.84 203	95.61 260

CHOSEN 1792x2688		88.84 224	87.69 237	92.30 170	96.14 110	81.42 215	90.01 406	95.86 194	74.52 441	87.41 243	93.94 248	75.46 232	98.36 161	80.36 318	95.53 150	97.12 176

CP-MVSNet		87.63 262	87.26 250	88.74 353	93.12 301	76.59 379	95.29 132	96.58 112	88.43 119	83.49 357	92.98 284	75.28 233	95.83 394	78.97 347	81.15 402	93.79 343

v10		87.25 282	86.38 279	89.85 306	91.19 377	79.50 296	94.48 191	95.45 231	83.79 278	83.62 351	91.19 347	75.13 234	97.42 271	81.94 288	80.60 412	92.63 397

Vis-MVSNet		91.75 121	91.23 132	93.29 90	95.32 157	83.78 124	96.14 64	95.98 178	89.89 56	90.45 174	96.58 97	75.09 235	98.31 169	84.75 235	96.90 116	97.78 124
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 223	88.26 224	90.94 251	94.05 257	80.78 245	91.71 353	95.38 237	81.55 343	88.63 218	93.91 252	75.04 236	95.47 412	82.47 274	91.61 260	96.57 214

v1144		87.61 265	86.79 262	90.06 295	91.01 386	79.34 307	93.95 243	95.42 236	83.36 291	85.66 285	91.31 345	74.98 237	97.42 271	83.37 259	82.06 388	93.42 364

miper_lstm_enhance		85.27 343	84.59 341	87.31 393	91.28 375	74.63 402	87.69 449	94.09 322	81.20 352	81.36 386	89.85 396	74.97 238	94.30 432	81.03 306	79.84 424	93.01 384

test_yl		90.69 157	90.02 167	92.71 135	95.72 138	82.41 183	94.11 225	95.12 257	85.63 220	91.49 145	94.70 209	74.75 239	98.42 157	86.13 215	92.53 251	97.31 152

DCV-MVSNet		90.69 157	90.02 167	92.71 135	95.72 138	82.41 183	94.11 225	95.12 257	85.63 220	91.49 145	94.70 209	74.75 239	98.42 157	86.13 215	92.53 251	97.31 152

V42		87.68 257	86.86 257	90.15 289	90.58 407	80.14 266	94.24 218	95.28 248	83.66 280	85.67 284	91.33 342	74.73 241	97.41 277	84.43 244	81.83 392	92.89 388

FA-MVS(test-final)		89.66 193	88.91 203	91.93 193	94.57 215	80.27 261	91.36 364	94.74 290	84.87 252	89.82 193	92.61 297	74.72 242	98.47 147	83.97 250	93.53 216	97.04 182

viewdifsd2359ckpt11		89.43 203	89.05 197	90.56 263	92.89 318	77.00 370	92.81 310	94.52 299	87.03 180	89.77 194	95.79 149	74.67 243	97.51 254	88.97 170	84.98 353	97.17 167

viewmsd2359difaftdt		89.43 203	89.05 197	90.56 263	92.89 318	77.00 370	92.81 310	94.52 299	87.03 180	89.77 194	95.79 149	74.67 243	97.51 254	88.97 170	84.98 353	97.17 167

XVG-OURS-SEG-HR		89.95 184	89.45 181	91.47 221	94.00 262	81.21 222	91.87 348	96.06 173	85.78 215	88.55 219	95.73 154	74.67 243	97.27 293	88.71 176	89.64 296	95.91 243

BP-MVS1		92.48 102	92.07 106	93.72 80	94.50 221	84.39 107	95.90 89	94.30 310	90.39 41	92.67 109	95.94 134	74.46 246	98.65 128	93.14 71	97.35 104	98.13 79

v2v482		87.84 252	87.06 252	90.17 287	90.99 387	79.23 314	94.00 240	95.13 256	84.87 252	85.53 289	92.07 319	74.45 247	97.45 265	84.71 240	81.75 394	93.85 340

CLD-MVS		89.47 200	88.90 204	91.18 235	94.22 248	82.07 191	92.13 341	96.09 169	87.90 147	85.37 304	92.45 301	74.38 248	97.56 250	87.15 200	90.43 278	93.93 332
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 259	86.85 258	90.03 297	92.14 341	80.60 254	93.76 256	95.23 250	82.94 303	84.60 319	94.02 243	74.27 249	95.49 411	81.04 304	83.68 368	94.01 329

HQP_MVS		90.60 165	90.19 158	91.82 203	94.70 202	82.73 167	95.85 93	96.22 147	90.81 27	86.91 252	94.86 203	74.23 250	98.12 180	88.15 180	89.99 285	94.63 294

plane_prior6					94.52 218	82.75 164						74.23 250

v144192		87.19 288	86.35 281	89.74 314	90.64 405	78.24 336	93.92 246	95.43 234	81.93 327	85.51 291	91.05 356	74.21 252	97.45 265	82.86 267	81.56 396	93.53 358

VPA-MVSNet		89.62 194	88.96 200	91.60 213	93.86 269	82.89 162	95.46 121	97.33 33	87.91 146	88.43 222	93.31 271	74.17 253	97.40 279	87.32 198	82.86 381	94.52 302

ab-mvs		89.41 205	88.35 218	92.60 143	95.15 169	82.65 175	92.20 339	95.60 218	83.97 272	88.55 219	93.70 262	74.16 254	98.21 175	82.46 275	89.37 299	96.94 192

1314		87.51 270	86.57 273	90.34 283	92.42 335	79.74 290	92.63 317	95.35 242	78.35 392	80.14 402	91.62 336	74.05 255	97.15 302	81.05 303	93.53 216	94.12 321

test_djsdf		89.03 220	88.64 209	90.21 286	90.74 402	79.28 311	95.96 83	95.90 188	84.66 261	85.33 306	92.94 285	74.02 256	97.30 289	89.64 160	88.53 311	94.05 327

cl22		86.78 303	85.98 298	89.18 340	92.34 336	77.62 361	90.84 381	94.13 320	81.33 347	83.97 342	90.15 385	73.96 257	96.60 348	84.19 246	82.94 377	93.33 366

SD_0403		84.71 356	84.65 338	84.92 436	92.95 315	65.95 474	92.07 345	93.23 351	83.82 277	79.03 421	93.73 261	73.90 258	92.91 456	63.02 469	90.05 284	95.89 245

AdaColmap		89.89 187	89.07 195	92.37 160	97.41 72	83.03 156	94.42 198	95.92 185	82.81 306	86.34 269	94.65 216	73.89 259	99.02 74	80.69 312	95.51 151	95.05 276

HyFIR lowres test		88.09 247	86.81 260	91.93 193	96.00 123	80.63 248	90.01 406	95.79 198	73.42 453	87.68 239	92.10 316	73.86 260	97.96 217	80.75 311	91.70 259	97.19 166

HQP2-MVS												73.83 261

HQP-MVS		89.80 190	89.28 190	91.34 228	94.17 251	81.56 207	94.39 205	96.04 174	88.81 104	85.43 298	93.97 247	73.83 261	97.96 217	87.11 202	89.77 294	94.50 305

3Dnovator	86.66 5	91.73 123	90.82 144	94.44 50	94.59 211	86.37 43	97.18 17	97.02 63	89.20 88	84.31 335	96.66 90	73.74 263	99.17 58	86.74 205	97.96 83	97.79 123

EPNet_dtu		86.49 318	85.94 301	88.14 371	90.24 417	72.82 424	94.11 225	92.20 381	86.66 194	79.42 416	92.36 304	73.52 264	95.81 396	71.26 416	93.66 211	95.80 251
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 360	83.06 368	88.54 357	91.72 358	78.44 328	95.18 145	92.82 364	82.73 308	79.67 413	92.12 313	73.49 265	95.96 387	71.10 421	68.73 477	91.21 439

Effi-MVS+-dtu		88.65 230	88.35 218	89.54 328	93.33 294	76.39 382	94.47 194	94.36 308	87.70 157	85.43 298	89.56 402	73.45 266	97.26 295	85.57 223	91.28 264	94.97 278

GDP-MVS		92.04 109	91.46 124	93.75 79	94.55 217	84.69 92	95.60 118	96.56 114	87.83 152	93.07 93	95.89 138	73.44 267	98.65 128	90.22 145	96.03 139	97.91 110

baseline2		86.50 316	85.39 319	89.84 307	91.12 382	76.70 377	91.88 347	88.58 461	82.35 315	79.95 407	90.95 358	73.42 268	97.63 244	80.27 321	89.95 288	95.19 271

PEN-MVS		86.80 302	86.27 286	88.40 360	92.32 337	75.71 392	95.18 145	96.38 127	87.97 141	82.82 367	93.15 278	73.39 269	95.92 389	76.15 379	79.03 431	93.59 356

v1192		87.25 282	86.33 282	90.00 301	90.76 401	79.04 315	93.80 254	95.48 226	82.57 310	85.48 293	91.18 349	73.38 270	97.42 271	82.30 278	82.06 388	93.53 358

guyue		91.12 145	90.84 143	91.96 190	94.59 211	80.57 255	94.87 164	93.71 341	88.96 101	91.14 155	95.22 182	73.22 271	97.76 232	92.01 105	93.81 204	97.54 144

QAPM		89.51 198	88.15 225	93.59 84	94.92 182	84.58 94	96.82 34	96.70 104	78.43 391	83.41 358	96.19 114	73.18 272	99.30 49	77.11 368	96.54 127	96.89 196

tpmrst		85.35 340	84.99 329	86.43 416	90.88 396	67.88 468	88.71 429	91.43 407	80.13 362	86.08 275	88.80 415	73.05 273	96.02 383	82.48 273	83.40 374	95.40 264

PS-CasMVS		87.32 279	86.88 256	88.63 356	92.99 313	76.33 384	95.33 127	96.61 110	88.22 128	83.30 362	93.07 282	73.03 274	95.79 398	78.36 353	81.00 408	93.75 350

DTE-MVSNet		86.11 324	85.48 317	87.98 374	91.65 363	74.92 399	94.93 160	95.75 201	87.36 169	82.26 373	93.04 283	72.85 275	95.82 395	74.04 399	77.46 437	93.20 374

MVSTER		88.84 224	88.29 222	90.51 270	92.95 315	80.44 258	93.73 259	95.01 263	84.66 261	87.15 247	93.12 280	72.79 276	97.21 300	87.86 186	87.36 333	93.87 337

v1921920		86.97 295	86.06 295	89.69 319	90.53 410	78.11 339	93.80 254	95.43 234	81.90 329	85.33 306	91.05 356	72.66 277	97.41 277	82.05 286	81.80 393	93.53 358

DP-MVS		87.25 282	85.36 321	92.90 117	97.65 65	83.24 142	94.81 170	92.00 387	74.99 436	81.92 380	95.00 195	72.66 277	99.05 68	66.92 452	92.33 254	96.40 218

VortexMVS		88.42 236	88.01 228	89.63 325	93.89 268	78.82 317	93.82 252	95.47 227	86.67 193	84.53 323	91.99 322	72.62 279	96.65 335	89.02 169	84.09 362	93.41 365

v7n		86.81 301	85.76 309	89.95 302	90.72 403	79.25 313	95.07 151	95.92 185	84.45 264	82.29 372	90.86 360	72.60 280	97.53 252	79.42 343	80.52 416	93.08 382

OPM-MVS		90.12 174	89.56 179	91.82 203	93.14 300	83.90 120	94.16 221	95.74 202	88.96 101	87.86 232	95.43 171	72.48 281	97.91 223	88.10 184	90.18 283	93.65 355
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 251	86.32 283	92.59 144	96.07 119	82.92 161	95.23 137	94.92 277	75.66 428	82.89 366	95.98 131	72.48 281	99.21 56	68.43 440	95.23 163	95.64 257

pm-mvs1		86.61 310	85.54 315	89.82 308	91.44 366	80.18 264	95.28 134	94.85 282	83.84 275	81.66 381	92.62 296	72.45 283	96.48 359	79.67 331	78.06 432	92.82 391

KinetiMVS		91.82 113	91.30 129	93.39 87	94.72 199	83.36 139	95.45 122	96.37 128	90.33 43	92.17 120	96.03 128	72.32 284	98.75 117	87.94 185	96.34 132	98.07 84

usedtu_dtu_shiyan1		86.84 299	85.61 313	90.53 265	90.50 411	81.80 201	90.97 377	94.96 270	83.05 298	83.50 355	90.32 377	72.15 285	96.65 335	79.49 337	85.55 347	93.15 378

FE-MVSNET3		86.84 299	85.61 313	90.53 265	90.50 411	81.80 201	90.97 377	94.96 270	83.05 298	83.50 355	90.32 377	72.15 285	96.65 335	79.49 337	85.55 347	93.15 378

PMMVS		85.71 333	84.96 331	87.95 375	88.90 436	77.09 368	88.68 430	90.06 440	72.32 463	86.47 262	90.76 366	72.15 285	94.40 429	81.78 293	93.49 218	92.36 412

SDMVSNet		90.19 173	89.61 178	91.93 193	96.00 123	83.09 153	92.89 305	95.98 178	88.73 108	86.85 256	95.20 186	72.09 288	97.08 309	88.90 172	89.85 291	95.63 258

PatchmatchNet		85.85 329	84.70 337	89.29 337	91.76 357	75.54 393	88.49 434	91.30 409	81.63 340	85.05 311	88.70 417	71.71 289	96.24 375	74.61 396	89.05 306	96.08 236
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 290				96.12 233

patchmatchnet-post											83.76 465	71.53 291	96.48 359

v1240		86.78 303	85.85 304	89.56 327	90.45 414	77.79 352	93.61 267	95.37 240	81.65 338	85.43 298	91.15 351	71.50 292	97.43 269	81.47 299	82.05 390	93.47 362

anonymousdsp		87.84 252	87.09 251	90.12 291	89.13 433	80.54 256	94.67 181	95.55 221	82.05 322	83.82 344	92.12 313	71.47 293	97.15 302	87.15 200	87.80 328	92.67 395

Patchmatch-test		81.37 404	79.30 410	87.58 384	90.92 393	74.16 409	80.99 490	87.68 468	70.52 471	76.63 446	88.81 413	71.21 294	92.76 458	60.01 479	86.93 339	95.83 249

F-COLMAP		87.95 250	86.80 261	91.40 225	96.35 105	80.88 238	94.73 177	95.45 231	79.65 369	82.04 378	94.61 217	71.13 295	98.50 142	76.24 378	91.05 270	94.80 291

pmmvs4		85.43 337	83.86 355	90.16 288	90.02 422	82.97 160	90.27 393	92.67 368	75.93 427	80.73 393	91.74 330	71.05 296	95.73 401	78.85 350	83.46 372	91.78 423

CR-MVSNet		85.35 340	83.76 356	90.12 291	90.58 407	79.34 307	85.24 471	91.96 391	78.27 394	85.55 287	87.87 430	71.03 297	95.61 404	73.96 401	89.36 300	95.40 264

Patchmtry		82.71 380	80.93 384	88.06 372	90.05 421	76.37 383	84.74 477	91.96 391	72.28 464	81.32 387	87.87 430	71.03 297	95.50 410	68.97 436	80.15 419	92.32 414

CL-MVSNet_self_test		81.74 395	80.53 385	85.36 429	85.96 464	72.45 433	90.25 395	93.07 356	81.24 350	79.85 410	87.29 436	70.93 299	92.52 459	66.95 449	69.23 467	91.11 443

RPMNet		83.95 368	81.53 379	91.21 233	90.58 407	79.34 307	85.24 471	96.76 94	71.44 467	85.55 287	82.97 473	70.87 300	98.91 98	61.01 474	89.36 300	95.40 264

Patchmatch-RL test		81.67 396	79.96 400	86.81 410	85.42 472	71.23 445	82.17 488	87.50 469	78.47 389	77.19 441	82.50 480	70.81 301	93.48 447	82.66 272	72.89 451	95.71 256

CostFormer		85.77 332	84.94 332	88.26 367	91.16 380	72.58 432	89.47 417	91.04 416	76.26 423	86.45 265	89.97 392	70.74 302	96.86 327	82.35 277	87.07 338	95.34 268

AstraMVS		90.69 157	90.30 156	91.84 202	93.81 272	79.85 285	94.76 175	92.39 373	88.96 101	91.01 166	95.87 142	70.69 303	97.94 220	92.49 83	92.70 243	97.73 127

sam_mvs												70.60 304

xiu_mvs_v1_base_debu		90.64 162	90.05 164	92.40 156	93.97 264	84.46 101	93.32 279	95.46 228	85.17 238	92.25 117	94.03 240	70.59 305	98.57 139	90.97 127	94.67 173	94.18 317

xiu_mvs_v1_base		90.64 162	90.05 164	92.40 156	93.97 264	84.46 101	93.32 279	95.46 228	85.17 238	92.25 117	94.03 240	70.59 305	98.57 139	90.97 127	94.67 173	94.18 317

xiu_mvs_v1_base_debi		90.64 162	90.05 164	92.40 156	93.97 264	84.46 101	93.32 279	95.46 228	85.17 238	92.25 117	94.03 240	70.59 305	98.57 139	90.97 127	94.67 173	94.18 317

test_post											10.29 547	70.57 308	95.91 391

CANet_DTU		90.26 172	89.41 185	92.81 122	93.46 291	83.01 158	93.48 271	94.47 302	89.43 78	87.76 238	94.23 237	70.54 309	99.03 71	84.97 230	96.39 131	96.38 219

BH-RMVSNet		88.37 239	87.48 242	91.02 244	95.28 159	79.45 299	92.89 305	93.07 356	85.45 230	86.91 252	94.84 206	70.35 310	97.76 232	73.97 400	94.59 178	95.85 247

Fast-Effi-MVS+-dtu		87.44 273	86.72 263	89.63 325	92.04 345	77.68 360	94.03 235	93.94 324	85.81 214	82.42 371	91.32 344	70.33 311	97.06 312	80.33 320	90.23 282	94.14 320

MDTV_nov1_ep13_2view						55.91 505	87.62 451		73.32 454	84.59 320		70.33 311		74.65 394		95.50 261

ACMM	84.12 9	89.14 213	88.48 217	91.12 236	94.65 206	81.22 221	95.31 128	96.12 166	85.31 235	85.92 278	94.34 228	70.19 313	98.06 196	85.65 221	88.86 308	94.08 325
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RRT-MVS		90.85 151	90.70 148	91.30 230	94.25 246	76.83 374	94.85 167	96.13 165	89.04 95	90.23 181	94.88 201	70.15 314	98.72 121	91.86 113	94.88 168	98.34 49

LuminaMVS		90.55 166	89.81 171	92.77 126	92.78 324	84.21 111	94.09 229	94.17 317	85.82 213	91.54 143	94.14 239	69.93 315	97.92 222	91.62 117	94.21 192	96.18 229

ET-MVSNet_ETH3D		87.51 270	85.91 302	92.32 166	93.70 283	83.93 119	92.33 331	90.94 420	84.16 267	72.09 472	92.52 299	69.90 316	95.85 393	89.20 166	88.36 317	97.17 167

LPG-MVS_test		89.45 201	88.90 204	91.12 236	94.47 224	81.49 211	95.30 130	96.14 162	86.73 191	85.45 295	95.16 188	69.89 317	98.10 182	87.70 189	89.23 303	93.77 348

LGP-MVS_train				91.12 236	94.47 224	81.49 211		96.14 162	86.73 191	85.45 295	95.16 188	69.89 317	98.10 182	87.70 189	89.23 303	93.77 348

CHOSEN 280x420		85.15 345	83.99 353	88.65 355	92.47 332	78.40 330	79.68 497	92.76 365	74.90 438	81.41 385	89.59 400	69.85 319	95.51 408	79.92 327	95.29 160	92.03 419

LTVRE_ROB	82.13 13	86.26 323	84.90 333	90.34 283	94.44 228	81.50 209	92.31 334	94.89 278	83.03 300	79.63 414	92.67 294	69.69 320	97.79 230	71.20 417	86.26 342	91.72 424
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	88.74 228	87.29 247	93.08 105	92.70 327	85.39 79	96.57 40	96.43 122	78.74 385	80.85 391	96.07 124	69.64 321	99.01 76	78.01 359	96.65 125	94.83 289

MonoMVSNet		86.89 298	86.55 274	87.92 377	89.46 431	73.75 411	94.12 223	93.10 354	87.82 153	85.10 309	90.76 366	69.59 322	94.94 423	86.47 209	82.50 383	95.07 275

MDTV_nov1_ep13			83.56 359		91.69 361	69.93 458	87.75 448	91.54 402	78.60 387	84.86 314	88.90 412	69.54 323	96.03 382	70.25 427	88.93 307

dtuonly		84.33 362	84.48 344	83.87 446	86.63 458	63.54 486	86.79 458	91.48 405	78.02 399	83.20 363	93.56 264	69.53 324	94.11 435	79.08 346	92.02 258	93.97 331

AUN-MVS		87.78 255	86.54 275	91.48 220	94.82 190	81.05 229	93.91 248	93.93 325	83.00 301	86.93 250	93.53 265	69.50 325	97.67 238	86.14 213	77.12 439	95.73 255

PatchT		82.68 381	81.27 381	86.89 408	90.09 420	70.94 451	84.06 480	90.15 437	74.91 437	85.63 286	83.57 468	69.37 326	94.87 424	65.19 458	88.50 313	94.84 288

VPNet		88.20 244	87.47 243	90.39 279	93.56 288	79.46 298	94.04 234	95.54 223	88.67 111	86.96 249	94.58 221	69.33 327	97.15 302	84.05 249	80.53 415	94.56 300

ACMP	84.23 8	89.01 222	88.35 218	90.99 247	94.73 197	81.27 218	95.07 151	95.89 190	86.48 196	83.67 349	94.30 231	69.33 327	97.99 210	87.10 204	88.55 310	93.72 353
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 443				9.81 548	69.31 329	95.53 406	76.65 371

tpmvs		83.35 376	82.07 375	87.20 400	91.07 384	71.00 450	88.31 437	91.70 395	78.91 377	80.49 398	87.18 439	69.30 330	97.08 309	68.12 444	83.56 370	93.51 361

mvsmamba		90.33 169	89.69 175	92.25 177	95.17 166	81.64 206	95.27 135	93.36 348	84.88 251	89.51 199	94.27 235	69.29 331	97.42 271	89.34 163	96.12 138	97.68 130

thres200		87.21 286	86.24 287	90.12 291	95.36 155	78.53 325	93.26 286	92.10 383	86.42 199	88.00 231	91.11 353	69.24 332	98.00 209	69.58 434	91.04 271	93.83 342

tfpn200view9		87.58 267	86.64 268	90.41 278	95.99 126	78.64 321	94.58 185	91.98 389	86.94 185	88.09 226	91.77 328	69.18 333	98.10 182	70.13 430	91.10 265	94.48 308

thres400		87.62 264	86.64 268	90.57 261	95.99 126	78.64 321	94.58 185	91.98 389	86.94 185	88.09 226	91.77 328	69.18 333	98.10 182	70.13 430	91.10 265	94.96 281

WB-MVSnew		83.77 371	83.28 362	85.26 432	91.48 365	71.03 448	91.89 346	87.98 464	78.91 377	84.78 315	90.22 381	69.11 335	94.02 437	64.70 462	90.44 277	90.71 447

tfpnnormal		84.72 355	83.23 364	89.20 339	92.79 323	80.05 273	94.48 191	95.81 196	82.38 313	81.08 389	91.21 346	69.01 336	96.95 321	61.69 472	80.59 413	90.58 452

thres100view900		87.63 262	86.71 264	90.38 281	96.12 112	78.55 324	95.03 155	91.58 400	87.15 174	88.06 229	92.29 307	68.91 337	98.10 182	70.13 430	91.10 265	94.48 308

thres600view7		87.65 259	86.67 267	90.59 260	96.08 118	78.72 318	94.88 163	91.58 400	87.06 179	88.08 228	92.30 306	68.91 337	98.10 182	70.05 433	91.10 265	94.96 281

PatchMatch-RL		86.77 306	85.54 315	90.47 276	95.88 131	82.71 169	90.54 388	92.31 377	79.82 367	84.32 333	91.57 340	68.77 339	96.39 367	73.16 406	93.48 220	92.32 414

XVG-OURS		89.40 207	88.70 208	91.52 217	94.06 256	81.46 213	91.27 369	96.07 171	86.14 208	88.89 214	95.77 152	68.73 340	97.26 295	87.39 196	89.96 287	95.83 249

TR-MVS		86.78 303	85.76 309	89.82 308	94.37 232	78.41 329	92.47 322	92.83 362	81.11 353	86.36 267	92.40 302	68.73 340	97.48 260	73.75 404	89.85 291	93.57 357

tpm		84.73 354	84.02 352	86.87 409	90.33 415	68.90 462	89.06 424	89.94 444	80.85 355	85.75 282	89.86 395	68.54 342	95.97 386	77.76 360	84.05 363	95.75 252

FMVSNet3		87.40 275	86.11 292	91.30 230	93.79 275	83.64 129	94.20 220	94.81 286	83.89 274	84.37 328	91.87 327	68.45 343	96.56 353	78.23 356	85.36 349	93.70 354

MVP-Stereo		85.97 326	84.86 334	89.32 336	90.92 393	82.19 188	92.11 342	94.19 315	78.76 384	78.77 429	91.63 335	68.38 344	96.56 353	75.01 390	93.95 198	89.20 466
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 389	80.27 391	87.01 403	91.09 383	71.02 449	87.38 454	91.53 403	66.25 484	80.17 400	86.35 451	68.22 345	96.15 379	69.16 435	82.29 386	93.86 339

dmvs_testset		74.57 447	75.81 444	70.86 478	87.72 453	40.47 519	87.05 457	77.90 501	82.75 307	71.15 478	85.47 458	67.98 346	84.12 500	45.26 501	76.98 441	88.00 478

sd_testset		88.59 233	87.85 235	90.83 254	96.00 123	80.42 259	92.35 328	94.71 291	88.73 108	86.85 256	95.20 186	67.31 347	96.43 365	79.64 332	89.85 291	95.63 258

tpm2		84.08 365	82.94 369	87.48 388	91.39 370	71.27 444	89.23 421	90.37 432	71.95 465	84.64 318	89.33 404	67.30 348	96.55 355	75.17 387	87.09 337	94.63 294

test-LLR		85.87 328	85.41 318	87.25 396	90.95 389	71.67 441	89.55 413	89.88 447	83.41 288	84.54 321	87.95 427	67.25 349	95.11 419	81.82 291	93.37 224	94.97 278

test0.0.03 1		82.41 386	81.69 377	84.59 439	88.23 445	72.89 423	90.24 397	87.83 466	83.41 288	79.86 409	89.78 397	67.25 349	88.99 487	65.18 459	83.42 373	91.90 422

CVMVSNet		84.69 357	84.79 336	84.37 441	91.84 353	64.92 481	93.70 263	91.47 406	66.19 485	86.16 274	95.28 179	67.18 351	93.33 449	80.89 309	90.42 279	94.88 287

thisisatest0515		87.33 278	85.99 297	91.37 227	93.49 289	79.55 295	90.63 385	89.56 454	80.17 361	87.56 241	90.86 360	67.07 352	98.28 170	81.50 298	93.02 235	96.29 223

tttt0517		88.61 231	87.78 236	91.11 239	94.96 179	77.81 350	95.35 126	89.69 449	85.09 246	88.05 230	94.59 220	66.93 353	98.48 144	83.27 261	92.13 256	97.03 183

our_test_3		81.93 391	80.46 389	86.33 418	88.46 441	73.48 416	88.46 435	91.11 412	76.46 417	76.69 445	88.25 423	66.89 354	94.36 430	68.75 437	79.08 430	91.14 441

thisisatest0530		88.67 229	87.61 239	91.86 199	94.87 186	80.07 271	94.63 183	89.90 446	84.00 271	88.46 221	93.78 257	66.88 355	98.46 148	83.30 260	92.65 244	97.06 180

IterMVS-SCA-FT		85.45 336	84.53 343	88.18 370	91.71 359	76.87 373	90.19 401	92.65 369	85.40 233	81.44 384	90.54 371	66.79 356	95.00 422	81.04 304	81.05 404	92.66 396

SCA		86.32 322	85.18 326	89.73 316	92.15 340	76.60 378	91.12 373	91.69 396	83.53 285	85.50 292	88.81 413	66.79 356	96.48 359	76.65 371	90.35 280	96.12 233

D2MVS		85.90 327	85.09 328	88.35 362	90.79 398	77.42 363	91.83 350	95.70 208	80.77 356	80.08 404	90.02 390	66.74 358	96.37 368	81.88 290	87.97 323	91.26 438

IterMVS		84.88 351	83.98 354	87.60 383	91.44 366	76.03 386	90.18 402	92.41 372	83.24 294	81.06 390	90.42 376	66.60 359	94.28 433	79.46 339	80.98 409	92.48 405
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 280	85.98 298	91.08 240	94.01 259	83.10 150	95.14 148	94.94 272	83.57 282	84.37 328	91.64 332	66.59 360	96.34 371	78.23 356	85.36 349	93.79 343

test1		87.26 280	85.98 298	91.08 240	94.01 259	83.10 150	95.14 148	94.94 272	83.57 282	84.37 328	91.64 332	66.59 360	96.34 371	78.23 356	85.36 349	93.79 343

FMVSNet2		87.19 288	85.82 305	91.30 230	94.01 259	83.67 127	94.79 172	94.94 272	83.57 282	83.88 343	92.05 320	66.59 360	96.51 357	77.56 363	85.01 352	93.73 352

IMVS_0404		87.60 266	86.84 259	89.89 304	93.72 277	77.75 355	88.56 432	95.34 243	85.53 226	79.98 406	94.49 223	66.54 363	94.64 425	84.75 235	92.65 244	97.28 155

EPMVS		83.90 370	82.70 374	87.51 385	90.23 418	72.67 427	88.62 431	81.96 489	81.37 346	85.01 312	88.34 421	66.31 364	94.45 426	75.30 386	87.12 336	95.43 263

Syy-MVS		80.07 420	79.78 402	80.94 460	91.92 349	59.93 495	89.75 411	87.40 470	81.72 336	78.82 426	87.20 437	66.29 365	91.29 472	47.06 500	87.84 326	91.60 427

ppachtmachnet_test		81.84 392	80.07 396	87.15 401	88.46 441	74.43 406	89.04 425	92.16 382	75.33 432	77.75 437	88.99 410	66.20 366	95.37 414	65.12 460	77.60 435	91.65 425

MDA-MVSNet_test_wron		79.21 431	77.19 433	85.29 430	88.22 446	72.77 425	85.87 465	90.06 440	74.34 442	62.62 492	87.56 433	66.14 367	91.99 466	66.90 453	73.01 449	91.10 444

YYNet1		79.22 430	77.20 432	85.28 431	88.20 447	72.66 428	85.87 465	90.05 442	74.33 443	62.70 490	87.61 432	66.09 368	92.03 463	66.94 450	72.97 450	91.15 440

JIA-IIPM		81.04 407	78.98 419	87.25 396	88.64 437	73.48 416	81.75 489	89.61 453	73.19 455	82.05 377	73.71 500	66.07 369	95.87 392	71.18 419	84.60 357	92.41 409

MSDG		84.86 352	83.09 366	90.14 290	93.80 273	80.05 273	89.18 422	93.09 355	78.89 379	78.19 431	91.91 325	65.86 370	97.27 293	68.47 439	88.45 314	93.11 380

FE-MVS		87.40 275	86.02 296	91.57 215	94.56 216	79.69 293	90.27 393	93.72 340	80.57 357	88.80 215	91.62 336	65.32 371	98.59 138	74.97 391	94.33 188	96.44 217

jajsoiax		88.24 243	87.50 241	90.48 273	90.89 395	80.14 266	95.31 128	95.65 215	84.97 249	84.24 336	94.02 243	65.31 372	97.42 271	88.56 177	88.52 312	93.89 333

cascas		86.43 320	84.98 330	90.80 257	92.10 344	80.92 236	90.24 397	95.91 187	73.10 456	83.57 353	88.39 420	65.15 373	97.46 264	84.90 233	91.43 262	94.03 328

ADS-MVSNet2		81.66 397	79.71 405	87.50 386	91.35 372	74.19 408	83.33 483	88.48 462	72.90 458	82.24 374	85.77 456	64.98 374	93.20 452	64.57 463	83.74 366	95.12 273

ADS-MVSNet		81.56 399	79.78 402	86.90 407	91.35 372	71.82 437	83.33 483	89.16 460	72.90 458	82.24 374	85.77 456	64.98 374	93.76 443	64.57 463	83.74 366	95.12 273

blended_shiyan6		82.78 378	80.48 388	89.67 324	85.53 469	79.76 288	91.37 363	93.82 332	77.14 407	79.30 419	83.73 466	64.96 376	96.63 338	79.68 330	68.75 473	92.63 397

blended_shiyan8		82.79 377	80.49 387	89.69 319	85.50 471	79.83 287	91.38 362	93.82 332	77.14 407	79.39 417	83.73 466	64.95 377	96.63 338	79.75 328	68.77 472	92.62 399

Elysia		90.12 174	89.10 193	93.18 97	93.16 298	84.05 116	95.22 139	96.27 137	85.16 241	90.59 171	94.68 211	64.64 378	98.37 159	86.38 211	95.77 144	97.12 176

StellarMVS		90.12 174	89.10 193	93.18 97	93.16 298	84.05 116	95.22 139	96.27 137	85.16 241	90.59 171	94.68 211	64.64 378	98.37 159	86.38 211	95.77 144	97.12 176

pmmvs5		84.21 363	82.84 373	88.34 364	88.95 435	76.94 372	92.41 323	91.91 393	75.63 429	80.28 399	91.18 349	64.59 380	95.57 405	77.09 369	83.47 371	92.53 404

PVSNet	78.82 18	85.55 334	84.65 338	88.23 369	94.72 199	71.93 435	87.12 456	92.75 366	78.80 383	84.95 313	90.53 372	64.43 381	96.71 332	74.74 393	93.86 201	96.06 239

dmvs_re		84.20 364	83.22 365	87.14 402	91.83 355	77.81 350	90.04 405	90.19 436	84.70 260	81.49 382	89.17 406	64.37 382	91.13 474	71.58 414	85.65 346	92.46 407

wanda-best-256-512		82.44 384	80.07 396	89.53 329	85.12 475	79.44 300	90.49 389	93.75 338	76.97 413	79.00 422	82.72 476	64.29 383	96.61 344	79.56 335	68.75 473	92.55 400

FE-blended-shiyan7		82.44 384	80.07 396	89.53 329	85.12 475	79.44 300	90.49 389	93.75 338	76.97 413	79.00 422	82.72 476	64.29 383	96.61 344	79.56 335	68.75 473	92.55 400

usedtu_blend_shiyan5		82.39 387	79.93 401	89.75 313	85.12 475	80.08 269	92.36 326	93.26 349	74.29 444	79.00 422	82.72 476	64.29 383	96.60 348	79.60 333	68.75 473	92.55 400

UGNet		89.95 184	88.95 201	92.95 115	94.51 219	83.31 140	95.70 106	95.23 250	89.37 80	87.58 240	93.94 248	64.00 386	98.78 115	83.92 251	96.31 133	96.74 206
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		67.92 457	67.49 458	69.21 483	81.09 492	41.17 518	88.03 442	78.00 500	73.50 452	62.63 491	83.11 472	63.94 387	86.52 491	25.66 519	51.45 500	79.94 493

RPSCF		85.07 346	84.27 345	87.48 388	92.91 317	70.62 453	91.69 355	92.46 371	76.20 425	82.67 369	95.22 182	63.94 387	97.29 292	77.51 364	85.80 344	94.53 301

mvs_tets		88.06 249	87.28 248	90.38 281	90.94 391	79.88 282	95.22 139	95.66 213	85.10 245	84.21 337	93.94 248	63.53 389	97.40 279	88.50 178	88.40 316	93.87 337

SSC-MVS		67.06 458	66.56 460	68.56 485	80.54 493	40.06 520	87.77 447	77.37 503	72.38 462	61.75 493	82.66 479	63.37 390	86.45 492	24.48 520	48.69 503	79.16 496

test1111		89.10 214	88.64 209	90.48 273	95.53 150	74.97 398	96.08 69	84.89 481	88.13 132	90.16 188	96.65 91	63.29 391	98.10 182	86.14 213	96.90 116	98.39 46

gbinet_0.2-2-1-0.02		82.59 382	80.19 394	89.77 312	85.23 474	80.05 273	91.59 358	93.52 344	77.60 401	79.78 411	82.87 475	63.26 392	96.45 363	78.93 348	68.97 469	92.81 392

Anonymous20231211		86.59 312	85.13 327	90.98 249	96.52 99	81.50 209	96.14 64	96.16 160	73.78 449	83.65 350	92.15 311	63.26 392	97.37 285	82.82 269	81.74 395	94.06 326

ECVR-MVS		89.09 216	88.53 212	90.77 258	95.62 145	75.89 388	96.16 60	84.22 483	87.89 149	90.20 182	96.65 91	63.19 394	98.10 182	85.90 218	96.94 113	98.33 51

dtuonlycased		79.67 425	79.05 418	81.54 458	88.34 444	68.44 464	88.96 427	90.65 429	78.48 388	73.21 469	85.88 455	63.18 395	91.00 476	70.40 425	72.32 452	85.19 483

SSC-MVS3.2		84.60 358	84.19 346	85.85 424	92.74 326	68.07 465	88.15 440	93.81 335	87.42 167	83.76 346	91.07 355	62.91 396	95.73 401	74.56 397	83.24 375	93.75 350

dp		81.47 403	80.23 392	85.17 433	89.92 424	65.49 478	86.74 460	90.10 439	76.30 422	81.10 388	87.12 440	62.81 397	95.92 389	68.13 443	79.88 422	94.09 324

LFMVS		90.08 177	89.13 192	92.95 115	96.71 88	82.32 186	96.08 69	89.91 445	86.79 188	92.15 122	96.81 84	62.60 398	98.34 164	87.18 199	93.90 200	98.19 73

Anonymous20231206		81.03 408	79.77 404	84.82 437	87.85 452	70.26 456	91.42 361	92.08 384	73.67 450	77.75 437	89.25 405	62.43 399	93.08 453	61.50 473	82.00 391	91.12 442

VDD-MVS		90.74 154	89.92 169	93.20 95	96.27 106	83.02 157	95.73 104	93.86 329	88.42 120	92.53 112	96.84 81	62.09 400	98.64 131	90.95 131	92.62 249	97.93 107

MS-PatchMatch		85.05 347	84.16 348	87.73 380	91.42 369	78.51 326	91.25 370	93.53 343	77.50 402	80.15 401	91.58 338	61.99 401	95.51 408	75.69 382	94.35 186	89.16 467

OurMVSNet-221017-0		85.35 340	84.64 340	87.49 387	90.77 400	72.59 431	94.01 238	94.40 306	84.72 258	79.62 415	93.17 277	61.91 402	96.72 330	81.99 287	81.16 400	93.16 376

WBMVS		84.97 350	84.18 347	87.34 391	94.14 255	71.62 443	90.20 400	92.35 374	81.61 341	84.06 338	90.76 366	61.82 403	96.52 356	78.93 348	83.81 364	93.89 333

test_vis1_n_1920		89.39 208	89.84 170	88.04 373	92.97 314	72.64 429	94.71 179	96.03 176	86.18 206	91.94 129	96.56 99	61.63 404	95.74 400	93.42 66	95.11 164	95.74 253

test20.03		79.95 422	79.08 416	82.55 452	85.79 466	67.74 470	91.09 374	91.08 413	81.23 351	74.48 462	89.96 393	61.63 404	90.15 479	60.08 477	76.38 442	89.76 458

mmtdpeth		85.04 349	84.15 349	87.72 381	93.11 302	75.74 391	94.37 209	92.83 362	84.98 248	89.31 204	86.41 449	61.61 406	97.14 305	92.63 82	62.11 489	90.29 453

DSMNet-mixed		76.94 441	76.29 439	78.89 465	83.10 486	56.11 504	87.78 446	79.77 493	60.65 493	75.64 454	88.71 416	61.56 407	88.34 488	60.07 478	89.29 302	92.21 417

Anonymous20240529		88.09 247	86.59 272	92.58 145	96.53 98	81.92 197	95.99 79	95.84 195	74.11 446	89.06 209	95.21 185	61.44 408	98.81 111	83.67 258	87.47 330	97.01 186

UBG		85.51 335	84.57 342	88.35 362	94.21 249	71.78 439	90.07 404	89.66 451	82.28 317	85.91 279	89.01 409	61.30 409	97.06 312	76.58 374	92.06 257	96.22 226

IB-MVS	80.51 15	85.24 344	83.26 363	91.19 234	92.13 342	79.86 283	91.75 352	91.29 410	83.28 293	80.66 395	88.49 419	61.28 410	98.46 148	80.99 307	79.46 427	95.25 270
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		86.61 310	85.27 324	90.66 259	91.33 374	78.71 320	90.40 392	93.81 335	85.34 234	85.12 308	89.57 401	61.25 411	97.11 307	80.99 307	89.59 297	96.15 230

N_pmnet		68.89 456	68.44 456	70.23 480	89.07 434	28.79 530	88.06 441	19.50 530	69.47 474	71.86 475	84.93 460	61.24 412	91.75 469	54.70 489	77.15 438	90.15 455

EU-MVSNet		81.32 405	80.95 383	82.42 455	88.50 440	63.67 485	93.32 279	91.33 408	64.02 489	80.57 397	92.83 288	61.21 413	92.27 462	76.34 376	80.38 418	91.32 436

testing91		87.11 291	86.18 288	89.92 303	94.43 229	75.38 397	91.53 359	92.27 379	86.48 196	86.50 261	90.24 380	61.19 414	97.53 252	82.10 283	90.88 273	96.84 202

test_cas_vis1_n_1920		88.83 227	88.85 207	88.78 349	91.15 381	76.72 376	93.85 251	94.93 276	83.23 295	92.81 100	96.00 129	61.17 415	94.45 426	91.67 116	94.84 169	95.17 272

VDDNet		89.56 197	88.49 216	92.76 129	95.07 171	82.09 190	96.30 47	93.19 353	81.05 354	91.88 131	96.86 80	61.16 416	98.33 166	88.43 179	92.49 253	97.84 118

PVSNet_0	73.20 20	77.22 440	74.83 446	84.37 441	90.70 404	71.10 447	83.09 485	89.67 450	72.81 460	73.93 464	83.13 470	60.79 417	93.70 445	68.54 438	50.84 501	88.30 477

SixPastTwentyTwo		83.91 369	82.90 371	86.92 406	90.99 387	70.67 452	93.48 271	91.99 388	85.54 224	77.62 439	92.11 315	60.59 418	96.87 326	76.05 380	77.75 434	93.20 374

gg-mvs-nofinetune		81.77 394	79.37 408	88.99 346	90.85 397	77.73 359	86.29 463	79.63 494	74.88 439	83.19 364	69.05 507	60.34 419	96.11 380	75.46 384	94.64 177	93.11 380

MDA-MVSNet-bldmvs		78.85 433	76.31 438	86.46 414	89.76 426	73.88 410	88.79 428	90.42 431	79.16 375	59.18 495	88.33 422	60.20 420	94.04 436	62.00 471	68.96 470	91.48 433

pmmvs6		83.42 374	81.60 378	88.87 348	88.01 449	77.87 348	94.96 158	94.24 314	74.67 440	78.80 428	91.09 354	60.17 421	96.49 358	77.06 370	75.40 446	92.23 416

ACMH	80.38 17	85.36 339	83.68 357	90.39 279	94.45 227	80.63 248	94.73 177	94.85 282	82.09 320	77.24 440	92.65 295	60.01 422	97.58 248	72.25 411	84.87 355	92.96 385
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 376	89.73 428	77.91 344	87.80 444	78.23 499		80.58 396	83.86 464	59.88 423	95.33 415	71.20 417	92.22 255	90.60 451

UniMVSNet_ETH3D		87.53 269	86.37 280	91.00 246	92.44 334	78.96 316	94.74 176	95.61 217	84.07 270	85.36 305	94.52 222	59.78 424	97.34 286	82.93 265	87.88 324	96.71 207

myMVS_eth3d28		85.80 331	85.26 325	87.42 390	94.73 197	69.92 459	90.60 386	90.95 419	87.21 173	86.06 276	90.04 389	59.47 425	96.02 383	74.89 392	93.35 226	96.33 220

pmmvs-eth3d		80.97 410	78.72 421	87.74 379	84.99 478	79.97 280	90.11 403	91.65 398	75.36 431	73.51 466	86.03 452	59.45 426	93.96 441	75.17 387	72.21 453	89.29 465

testing99		86.72 307	85.73 312	89.69 319	94.23 247	74.91 400	91.35 365	90.97 418	86.14 208	86.36 267	90.22 381	59.41 427	97.48 260	82.24 280	90.66 275	96.69 209

test_0402		81.30 406	79.17 414	87.67 382	93.19 297	78.17 337	92.98 301	91.71 394	75.25 433	76.02 452	90.31 379	59.23 428	96.37 368	50.22 495	83.63 369	88.47 476

KD-MVS_self_test		80.20 418	79.24 411	83.07 449	85.64 468	65.29 479	91.01 376	93.93 325	78.71 386	76.32 447	86.40 450	59.20 429	92.93 455	72.59 409	69.35 466	91.00 446

testing3-2		86.72 307	86.71 264	86.74 412	96.11 115	65.92 475	93.39 276	89.65 452	89.46 76	87.84 234	92.79 292	59.17 430	97.60 246	81.31 300	90.72 274	96.70 208

UWE-MVS-28		78.98 432	78.38 424	80.80 461	88.18 448	60.66 494	90.65 384	78.51 496	78.84 381	77.93 435	90.93 359	59.08 431	89.02 486	50.96 493	90.33 281	92.72 394

FMVSNet1		85.85 329	84.11 350	91.08 240	92.81 322	83.10 150	95.14 148	94.94 272	81.64 339	82.68 368	91.64 332	59.01 432	96.34 371	75.37 385	83.78 365	93.79 343

testing11		86.44 319	85.35 322	89.69 319	94.29 243	75.40 396	91.30 366	90.53 430	84.76 256	85.06 310	90.13 386	58.95 433	97.45 265	82.08 284	91.09 269	96.21 228

COLMAP_ROB	80.39 16	83.96 367	82.04 376	89.74 314	95.28 159	79.75 289	94.25 216	92.28 378	75.17 434	78.02 434	93.77 258	58.60 434	97.84 228	65.06 461	85.92 343	91.63 426
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	85.05 347	83.46 360	89.82 308	94.66 205	79.37 304	94.44 196	94.12 321	82.19 319	78.04 433	92.82 289	58.23 435	97.54 251	73.77 403	82.90 380	92.54 403

CMPMVS	59.16 21	80.52 414	79.20 413	84.48 440	83.98 481	67.63 471	89.95 408	93.84 331	64.79 488	66.81 486	91.14 352	57.93 436	95.17 417	76.25 377	88.10 319	90.65 448
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
reproduce_monomvs		86.37 321	85.87 303	87.87 378	93.66 285	73.71 412	93.44 274	95.02 262	88.61 114	82.64 370	91.94 324	57.88 437	96.68 333	89.96 150	79.71 425	93.22 372

FE-MVSNET2		81.82 393	79.99 399	87.34 391	84.74 479	77.36 365	92.72 314	94.55 297	82.09 320	73.79 465	86.46 446	57.80 438	94.45 426	74.65 394	73.10 448	90.20 454

tt0805		86.92 296	85.74 311	90.48 273	92.22 338	79.98 279	95.63 114	94.88 280	83.83 276	84.74 317	92.80 291	57.61 439	97.67 238	85.48 224	84.42 358	93.79 343

ITE_SJBPF				88.24 368	91.88 352	77.05 369		92.92 359	85.54 224	80.13 403	93.30 272	57.29 440	96.20 376	72.46 410	84.71 356	91.49 432

UWE-MVS		83.69 373	83.09 366	85.48 427	93.06 307	65.27 480	90.92 379	86.14 473	79.90 365	86.26 271	90.72 369	57.17 441	95.81 396	71.03 422	92.62 249	95.35 267

TESTMET0.1,1		83.74 372	82.85 372	86.42 417	89.96 423	71.21 446	89.55 413	87.88 465	77.41 403	83.37 359	87.31 435	56.71 442	93.65 446	80.62 314	92.85 241	94.40 311

UnsupCasMVSNet_eth		80.07 420	78.27 425	85.46 428	85.24 473	72.63 430	88.45 436	94.87 281	82.99 302	71.64 476	88.07 426	56.34 443	91.75 469	73.48 405	63.36 487	92.01 420

test_fmvs1		87.34 277	87.56 240	86.68 413	90.59 406	71.80 438	94.01 238	94.04 323	78.30 393	91.97 126	95.22 182	56.28 444	93.71 444	92.89 75	94.71 172	94.52 302

K. test v3		81.59 398	80.15 395	85.91 423	89.89 425	69.42 461	92.57 319	87.71 467	85.56 223	73.44 467	89.71 399	55.58 445	95.52 407	77.17 367	69.76 465	92.78 393

test-mter		84.54 359	83.64 358	87.25 396	90.95 389	71.67 441	89.55 413	89.88 447	79.17 374	84.54 321	87.95 427	55.56 446	95.11 419	81.82 291	93.37 224	94.97 278

FE-MVSNET		78.19 436	76.03 441	84.69 438	83.70 483	73.31 418	90.58 387	90.00 443	77.11 411	71.91 474	85.47 458	55.53 447	91.94 468	59.69 480	70.24 462	88.83 471

lessismore_v0				86.04 419	88.46 441	68.78 463		80.59 492		73.01 470	90.11 387	55.39 448	96.43 365	75.06 389	65.06 484	92.90 387

ETVMVS		84.43 360	82.92 370	88.97 347	94.37 232	74.67 401	91.23 371	88.35 463	83.37 290	86.06 276	89.04 408	55.38 449	95.67 403	67.12 448	91.34 263	96.58 213

MVS-HIRNet		73.70 448	72.20 450	78.18 469	91.81 356	56.42 503	82.94 486	82.58 487	55.24 496	68.88 481	66.48 509	55.32 450	95.13 418	58.12 484	88.42 315	83.01 487

test2506		87.21 286	86.28 285	90.02 299	95.62 145	73.64 414	96.25 55	71.38 508	87.89 149	90.45 174	96.65 91	55.29 451	98.09 190	86.03 217	96.94 113	98.33 51

mvs5depth		80.98 409	79.15 415	86.45 415	84.57 480	73.29 419	87.79 445	91.67 397	80.52 358	82.20 376	89.72 398	55.14 452	95.93 388	73.93 402	66.83 480	90.12 456

0.4-1-1-0.2		80.84 412	77.77 426	90.06 295	86.18 463	79.35 305	86.75 459	89.54 455	76.23 424	78.59 430	75.46 495	55.03 453	96.99 318	80.11 324	72.05 456	93.85 340

0.4-1-1-0.1		81.55 400	78.59 423	90.42 277	87.55 454	79.90 281	88.56 432	89.19 459	77.01 412	79.72 412	77.71 489	54.84 454	97.11 307	80.50 317	72.20 454	94.26 316

blend_shiyan4		81.94 390	79.35 409	89.70 317	85.52 470	80.08 269	91.29 367	93.82 332	77.12 410	79.31 418	82.94 474	54.81 455	96.60 348	79.60 333	69.78 464	92.41 409

new-patchmatchnet		76.41 443	75.17 445	80.13 462	82.65 488	59.61 496	87.66 450	91.08 413	78.23 396	69.85 480	83.22 469	54.76 456	91.63 471	64.14 465	64.89 485	89.16 467

Anonymous202405211		87.68 257	86.13 290	92.31 167	96.66 90	80.74 246	94.87 164	91.49 404	80.47 359	89.46 202	95.44 169	54.72 457	98.23 172	82.19 281	89.89 289	97.97 96

XVG-ACMP-BASELINE		86.00 325	84.84 335	89.45 334	91.20 376	78.00 341	91.70 354	95.55 221	85.05 247	82.97 365	92.25 309	54.49 458	97.48 260	82.93 265	87.45 332	92.89 388

USDC		82.76 379	81.26 382	87.26 395	91.17 378	74.55 403	89.27 419	93.39 347	78.26 395	75.30 456	92.08 317	54.43 459	96.63 338	71.64 413	85.79 345	90.61 449

AllTest		83.42 374	81.39 380	89.52 331	95.01 173	77.79 352	93.12 290	90.89 422	77.41 403	76.12 449	93.34 268	54.08 460	97.51 254	68.31 441	84.27 360	93.26 368

TestCases				89.52 331	95.01 173	77.79 352		90.89 422	77.41 403	76.12 449	93.34 268	54.08 460	97.51 254	68.31 441	84.27 360	93.26 368

KD-MVS_2432*1600		78.50 434	76.02 442	85.93 421	86.22 461	74.47 404	84.80 475	92.33 375	79.29 372	76.98 442	85.92 453	53.81 462	93.97 439	67.39 446	57.42 494	89.36 461

miper_refine_blended		78.50 434	76.02 442	85.93 421	86.22 461	74.47 404	84.80 475	92.33 375	79.29 372	76.98 442	85.92 453	53.81 462	93.97 439	67.39 446	57.42 494	89.36 461

MIMVSNet		82.59 382	80.53 385	88.76 350	91.51 364	78.32 333	86.57 462	90.13 438	79.32 371	80.70 394	88.69 418	52.98 464	93.07 454	66.03 456	88.86 308	94.90 286

testing222		84.84 353	83.32 361	89.43 335	94.15 254	75.94 387	91.09 374	89.41 458	84.90 250	85.78 281	89.44 403	52.70 465	96.28 374	70.80 424	91.57 261	96.07 237

0.3-1-1-0.015		80.75 413	77.58 428	90.25 285	86.55 459	79.72 291	87.46 453	89.48 457	76.43 419	77.93 435	75.94 492	52.31 466	97.05 314	80.25 322	71.85 458	93.99 330

FMVSNet5		81.52 402	79.60 406	87.27 394	91.17 378	77.95 342	91.49 360	92.26 380	76.87 415	76.16 448	87.91 429	51.67 467	92.34 461	67.74 445	81.16 400	91.52 430

testgi		80.94 411	80.20 393	83.18 448	87.96 450	66.29 473	91.28 368	90.70 428	83.70 279	78.12 432	92.84 287	51.37 468	90.82 477	63.34 466	82.46 384	92.43 408

test_fmvs1_n		87.03 294	87.04 254	86.97 404	89.74 427	71.86 436	94.55 187	94.43 303	78.47 389	91.95 128	95.50 167	51.16 469	93.81 442	93.02 74	94.56 179	95.26 269

Anonymous20240521		80.44 416	79.21 412	84.11 444	85.75 467	67.89 467	92.86 307	93.23 351	75.61 430	75.59 455	87.47 434	50.03 470	94.33 431	71.14 420	81.21 399	90.12 456

UnsupCasMVSNet_bld		76.23 444	73.27 448	85.09 434	83.79 482	72.92 422	85.65 468	93.47 346	71.52 466	68.84 482	79.08 487	49.77 471	93.21 451	66.81 454	60.52 491	89.13 469

OpenMVS_ROB	74.94 19	79.51 428	77.03 435	86.93 405	87.00 456	76.23 385	92.33 331	90.74 426	68.93 475	74.52 461	88.23 424	49.58 472	96.62 341	57.64 485	84.29 359	87.94 479

tt0320		80.13 419	77.41 429	88.29 365	90.50 411	78.02 340	93.10 293	90.71 427	66.06 486	76.75 444	86.97 442	49.56 473	95.40 413	71.65 412	71.41 460	91.46 434

TDRefinement		79.81 423	77.34 430	87.22 399	79.24 497	75.48 394	93.12 290	92.03 386	76.45 418	75.01 457	91.58 338	49.19 474	96.44 364	70.22 429	69.18 468	89.75 459

test_vis1_n		86.56 313	86.49 278	86.78 411	88.51 438	72.69 426	94.68 180	93.78 337	79.55 370	90.70 168	95.31 178	48.75 475	93.28 450	93.15 70	93.99 197	94.38 312

MIMVSNet1		79.38 429	77.28 431	85.69 426	86.35 460	73.67 413	91.61 357	92.75 366	78.11 398	72.64 471	88.12 425	48.16 476	91.97 467	60.32 476	77.49 436	91.43 435

LF4IMVS		80.37 417	79.07 417	84.27 443	86.64 457	69.87 460	89.39 418	91.05 415	76.38 420	74.97 458	90.00 391	47.85 477	94.25 434	74.55 398	80.82 411	88.69 473

EG-PatchMatch MVS		82.37 388	80.34 390	88.46 359	90.27 416	79.35 305	92.80 313	94.33 309	77.14 407	73.26 468	90.18 384	47.47 478	96.72 330	70.25 427	87.32 335	89.30 463

test_fmvs2		83.98 366	84.03 351	83.83 447	87.16 455	67.53 472	93.93 245	92.89 360	77.62 400	86.89 255	93.53 265	47.18 479	92.02 465	90.54 139	86.51 340	91.93 421

ttmdpeth		76.55 442	74.64 447	82.29 457	82.25 489	67.81 469	89.76 410	85.69 476	70.35 472	75.76 453	91.69 331	46.88 480	89.77 481	66.16 455	63.23 488	89.30 463

sc_t1		81.53 401	78.67 422	90.12 291	90.78 399	78.64 321	93.91 248	90.20 435	68.42 476	80.82 392	89.88 394	46.48 481	96.76 329	76.03 381	71.47 459	94.96 281

MVStest1		72.91 449	69.70 454	82.54 453	78.14 498	73.05 421	88.21 439	86.21 472	60.69 492	64.70 488	90.53 372	46.44 482	85.70 495	58.78 483	53.62 497	88.87 470

tt0320-xc		79.63 427	76.66 436	88.52 358	91.03 385	78.72 318	93.00 299	89.53 456	66.37 483	76.11 451	87.11 441	46.36 483	95.32 416	72.78 408	67.67 478	91.51 431

TinyColmap		79.76 424	77.69 427	85.97 420	91.71 359	73.12 420	89.55 413	90.36 433	75.03 435	72.03 473	90.19 383	46.22 484	96.19 378	63.11 467	81.03 405	88.59 475

myMVS_eth3d		79.67 425	78.79 420	82.32 456	91.92 349	64.08 483	89.75 411	87.40 470	81.72 336	78.82 426	87.20 437	45.33 485	91.29 472	59.09 482	87.84 326	91.60 427

tmp_tt		35.64 486	39.24 486	24.84 509	14.87 555	23.90 534	62.71 511	51.51 517	6.58 533	36.66 517	62.08 516	44.37 486	30.34 530	52.40 492	22.00 523	20.27 530

testing3		80.46 415	79.59 407	83.06 450	93.44 292	64.64 482	93.33 278	85.47 478	84.34 266	79.93 408	90.84 362	44.35 487	92.39 460	57.06 487	87.56 329	92.16 418

new_pmnet		72.15 450	70.13 453	78.20 468	82.95 487	65.68 476	83.91 481	82.40 488	62.94 491	64.47 489	79.82 486	42.85 488	86.26 493	57.41 486	74.44 447	82.65 489

test_vis1_rt		77.96 438	76.46 437	82.48 454	85.89 465	71.74 440	90.25 395	78.89 495	71.03 470	71.30 477	81.35 483	42.49 489	91.05 475	84.55 242	82.37 385	84.65 484

EGC-MVSNET		61.97 462	56.37 467	78.77 466	89.63 429	73.50 415	89.12 423	82.79 486	0.21 551	1.24 553	84.80 461	39.48 490	90.04 480	44.13 502	75.94 445	72.79 500

dongtai		58.82 467	58.24 465	60.56 491	83.13 485	45.09 515	82.32 487	48.22 520	67.61 479	61.70 494	69.15 506	38.75 491	76.05 510	32.01 515	41.31 506	60.55 513

kuosan		53.51 472	53.30 472	54.13 499	76.06 500	45.36 514	80.11 494	48.36 519	59.63 494	54.84 497	63.43 515	37.41 492	62.07 520	20.73 522	39.10 508	54.96 517

usedtu_dtu_shiyan2		74.72 446	71.30 451	84.98 435	77.78 499	70.58 454	91.85 349	90.76 425	67.24 481	68.06 484	82.17 481	37.13 493	92.78 457	60.69 475	66.03 481	91.59 429

pmmvs3		71.81 452	68.71 455	81.11 459	75.86 501	70.42 455	86.74 460	83.66 484	58.95 495	68.64 483	80.89 485	36.93 494	89.52 483	63.10 468	63.59 486	83.39 485

mvsany_test3		74.95 445	73.26 449	80.02 463	74.61 502	63.16 488	85.53 469	78.42 497	74.16 445	74.89 459	86.46 446	36.02 495	89.09 485	82.39 276	66.91 479	87.82 480

PM-MVS		78.11 437	76.12 440	84.09 445	83.54 484	70.08 457	88.97 426	85.27 480	79.93 364	74.73 460	86.43 448	34.70 496	93.48 447	79.43 342	72.06 455	88.72 472

ambc				83.06 450	79.99 495	63.51 487	77.47 498	92.86 361		74.34 463	84.45 463	28.74 497	95.06 421	73.06 407	68.89 471	90.61 449

test_method		50.52 476	48.47 476	56.66 496	52.26 527	18.98 536	41.51 522	81.40 490	10.10 525	44.59 508	75.01 498	28.51 498	68.16 513	53.54 490	49.31 502	82.83 488

DeepMVS_CX				56.31 497	74.23 504	51.81 507		56.67 516	44.85 505	48.54 502	75.16 497	27.87 499	58.74 521	40.92 509	52.22 499	58.39 516

test_fmvs3		77.67 439	77.16 434	79.22 464	79.52 496	61.14 491	92.34 330	91.64 399	73.98 447	78.86 425	86.59 445	27.38 500	87.03 489	88.12 183	75.97 444	89.50 460

test_f		71.95 451	70.87 452	75.21 473	74.21 505	59.37 497	85.07 473	85.82 475	65.25 487	70.42 479	83.13 470	23.62 501	82.93 502	78.32 354	71.94 457	83.33 486

FPMVS		64.63 461	62.55 463	70.88 477	70.80 508	56.71 499	84.42 479	84.42 482	51.78 499	49.57 500	81.61 482	23.49 502	81.48 504	40.61 510	76.25 443	74.46 499

APD_test1		69.04 455	66.26 461	77.36 472	80.51 494	62.79 489	85.46 470	83.51 485	54.11 498	59.14 496	84.79 462	23.40 503	89.61 482	55.22 488	70.24 462	79.68 494

ANet_high		58.88 466	54.22 471	72.86 474	56.50 524	56.67 500	80.75 491	86.00 474	73.09 457	37.39 515	64.63 513	22.17 504	79.49 506	43.51 504	23.96 518	82.43 490

EMVS		42.07 483	41.12 485	44.92 505	63.45 518	35.56 525	73.65 501	63.48 513	33.05 515	26.88 524	45.45 521	21.27 505	67.14 515	19.80 523	23.02 520	32.06 525

ArgMatch-SfM		70.39 453	67.69 457	78.49 467	81.44 491	60.73 492	84.71 478	75.65 506	68.09 478	66.71 487	86.79 443	20.42 506	86.05 494	71.50 415	53.87 496	88.67 474

Gipuma		57.99 468	54.91 470	67.24 486	88.51 438	65.59 477	52.21 515	90.33 434	43.58 507	42.84 509	51.18 519	20.29 507	85.07 496	34.77 512	70.45 461	51.05 518
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 482	42.29 482	46.03 503	65.58 516	37.41 523	73.51 502	64.62 511	33.99 513	28.47 522	47.87 520	19.90 508	67.91 514	22.23 521	24.45 516	32.77 524

ArgMatch-Sym		69.79 454	67.05 459	77.99 470	81.59 490	61.16 490	84.99 474	71.84 507	67.17 482	67.90 485	86.60 444	19.89 509	85.00 497	70.93 423	52.57 498	87.82 480

PMMVS2		59.60 463	56.40 466	69.21 483	68.83 511	46.58 511	73.02 505	77.48 502	55.07 497	49.21 501	72.95 502	17.43 510	80.04 505	49.32 497	44.33 505	80.99 492

LCM-MVSNet		66.00 459	62.16 464	77.51 471	64.51 517	58.29 498	83.87 482	90.90 421	48.17 501	54.69 498	73.31 501	16.83 511	86.75 490	65.47 457	61.67 490	87.48 482

test_vis3_rt		65.12 460	62.60 462	72.69 475	71.44 507	60.71 493	87.17 455	65.55 510	63.80 490	53.22 499	65.65 512	14.54 512	89.44 484	76.65 371	65.38 483	67.91 509

testf1		59.54 464	56.11 468	69.85 481	69.28 509	56.61 501	80.37 492	76.55 504	42.58 508	45.68 506	75.61 493	11.26 513	84.18 498	43.20 506	60.44 492	68.75 506

APD_test2		59.54 464	56.11 468	69.85 481	69.28 509	56.61 501	80.37 492	76.55 504	42.58 508	45.68 506	75.61 493	11.26 513	84.18 498	43.20 506	60.44 492	68.75 506

PDCNetPlus		48.34 477	45.15 480	57.91 494	61.43 519	41.85 517	65.98 510	38.30 523	47.59 502	37.96 514	71.85 503	10.18 515	66.85 517	52.94 491	20.14 529	65.03 511

LoFTR		57.22 469	52.62 473	71.00 476	72.03 506	48.57 510	72.00 506	70.08 509	44.40 506	40.92 512	76.42 491	8.12 516	82.76 503	42.28 508	47.33 504	81.66 491

DenseAffine		56.77 470	52.17 474	70.54 479	74.27 503	53.25 506	77.23 499	50.43 518	49.87 500	47.26 505	77.37 490	7.99 517	79.10 507	50.35 494	34.79 510	79.28 495

RoMa-SfM		53.80 471	49.39 475	67.06 487	67.87 513	48.86 508	75.04 500	38.06 524	47.23 503	47.40 504	78.96 488	7.40 518	76.66 509	48.89 498	33.62 511	75.64 498

MASt3R-SfM		45.78 480	43.96 481	51.24 501	45.04 529	29.83 529	57.88 512	38.83 522	31.88 516	47.48 503	81.30 484	7.16 519	51.15 524	49.56 496	36.51 509	72.74 501

ALIKED-LG		28.00 489	26.54 492	32.41 506	58.12 521	31.80 526	47.26 518	21.21 529	14.15 522	19.16 527	41.93 523	6.72 520	35.73 526	5.96 533	24.32 517	29.69 526

MatchFormer		51.11 474	46.66 478	64.46 489	67.11 514	43.39 516	70.54 507	63.67 512	33.19 514	37.22 516	70.30 505	6.67 521	78.17 508	30.29 516	40.94 507	71.81 503

PMVS	47.18 22	52.22 473	48.46 477	63.48 490	45.72 528	46.20 512	73.41 503	78.31 498	41.03 510	30.06 520	65.68 511	6.05 522	83.43 501	30.04 517	65.86 482	60.80 512
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SP-DiffGlue		20.02 496	19.96 499	20.21 513	19.64 552	13.14 543	30.51 528	15.49 535	8.39 527	19.98 526	43.75 522	5.48 523	13.72 537	13.75 526	22.65 521	33.78 522

RoMa-HiRes		46.47 478	42.20 483	59.28 493	57.74 522	39.86 522	66.76 509	24.64 527	39.96 511	41.50 511	75.37 496	5.40 524	69.26 512	43.35 505	25.09 514	68.71 508

ALIKED-NN		26.07 491	24.75 494	30.02 508	55.08 526	30.61 528	44.20 521	19.22 531	10.98 524	17.98 528	40.71 524	5.39 525	32.83 528	5.59 534	23.63 519	26.63 528

ALIKED-MNN		26.28 490	24.57 495	31.39 507	56.22 525	31.73 527	45.54 519	19.13 532	11.12 523	17.11 529	39.35 525	5.01 526	34.53 527	5.54 535	22.12 522	27.92 527

DKM		50.92 475	46.13 479	65.30 488	66.27 515	45.98 513	73.05 504	31.91 526	45.08 504	42.04 510	75.01 498	4.95 527	73.81 511	47.90 499	28.96 513	76.09 497

SP-LightGlue		20.24 494	20.15 498	20.49 511	43.51 531	12.27 544	38.68 524	14.56 537	7.54 530	12.90 533	30.07 529	4.75 528	14.38 534	7.60 529	21.75 524	34.82 519

SP-SuperGlue		20.22 495	20.18 497	20.36 512	43.26 532	12.27 544	38.71 523	14.77 536	7.64 529	13.04 532	30.21 528	4.73 529	14.21 536	7.59 530	21.65 525	34.59 520

MVE	39.65 23	43.39 481	38.59 487	57.77 495	56.52 523	48.77 509	55.38 513	58.64 515	29.33 518	28.96 521	52.65 518	4.68 530	64.62 519	28.11 518	33.07 512	59.93 514
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SP-NN		19.44 498	19.37 501	19.67 515	41.70 534	11.48 549	37.75 526	13.72 540	6.86 531	11.86 534	29.97 530	4.23 531	14.25 535	7.13 531	21.07 526	33.30 523

SP-MNN		19.61 497	19.42 500	20.19 514	42.15 533	11.42 550	38.15 525	14.24 538	6.55 534	11.64 535	29.88 531	4.16 532	14.56 533	7.09 532	20.92 527	34.58 521

XFeat-MNN		17.43 499	16.95 502	18.86 516	16.90 553	11.28 551	27.31 529	17.08 533	8.08 528	15.61 531	35.73 526	4.06 533	22.95 531	10.20 527	17.59 532	22.35 529

wuyk23d		21.27 493	20.48 496	23.63 510	68.59 512	36.41 524	49.57 516	6.85 547	9.37 526	7.89 536	4.46 551	4.03 534	31.37 529	17.47 525	16.07 533	3.12 546

GLUNet-SfM		31.36 488	26.25 493	46.70 502	35.51 538	24.89 533	33.71 527	36.36 525	19.08 521	23.78 525	52.69 517	3.82 535	56.26 523	19.75 524	11.56 541	58.95 515

DKM-HiRes		45.90 479	41.41 484	59.36 492	59.55 520	39.90 521	67.13 508	23.25 528	39.95 512	38.74 513	71.81 504	3.67 536	66.42 518	43.82 503	24.82 515	71.77 504

XFeat-NN		15.96 500	15.86 503	16.25 517	15.78 554	9.87 554	25.17 530	13.83 539	6.76 532	15.68 530	34.83 527	3.61 537	19.28 532	9.22 528	17.90 530	19.58 531

ELoFTR		40.15 484	35.08 488	55.36 498	41.27 535	28.17 532	47.70 517	43.76 521	29.15 519	30.35 519	65.97 510	2.17 538	66.90 516	34.51 513	20.83 528	71.00 505

SIFT-NN		12.98 501	13.18 504	12.37 518	36.49 537	16.03 537	22.41 531	7.69 543	4.89 535	7.41 537	20.48 533	1.69 539	11.46 539	1.88 538	15.70 534	9.61 533

SIFT-MNN		12.44 502	12.55 505	12.11 519	34.55 539	15.21 538	20.91 532	7.74 542	4.86 536	6.54 539	20.09 534	1.51 540	11.47 538	1.88 538	14.87 536	9.64 532

SIFT-NN-NCMNet		12.12 503	12.25 506	11.75 520	32.82 541	14.83 539	20.73 533	7.58 544	4.72 538	6.60 538	19.53 535	1.49 541	11.15 541	1.74 540	15.02 535	9.28 534

SIFT-NN-UMatch		11.06 506	11.19 511	10.66 524	28.66 547	12.16 546	19.79 534	6.86 546	4.73 537	5.21 542	19.47 537	1.46 542	10.70 544	1.71 541	12.79 539	9.13 536

SIFT-NN-CMatch		11.26 505	11.31 509	11.13 522	30.21 545	13.40 542	18.43 536	6.79 548	4.71 539	6.47 540	19.53 535	1.43 543	10.72 543	1.71 541	12.49 540	9.26 535

SIFT-NN-PointCN		10.26 509	10.46 514	9.65 527	27.18 548	9.89 553	17.89 538	6.17 550	4.40 545	5.65 541	18.29 541	1.43 543	10.09 547	1.61 545	11.55 542	8.99 537

SIFT-NCM-Cal		11.58 504	11.64 507	11.40 521	33.45 540	14.10 540	19.75 535	6.89 545	4.68 541	4.55 546	18.60 540	1.34 545	11.28 540	1.53 546	13.95 537	8.82 538

SIFT-ConvMatch		10.91 507	10.94 512	10.84 523	32.07 542	13.57 541	17.23 539	6.35 549	4.71 539	5.18 543	18.94 538	1.30 546	10.76 542	1.65 544	11.02 543	8.19 539

SIFT-CM-Cal		10.08 510	10.13 516	9.92 526	30.71 544	11.88 547	15.35 541	5.44 552	4.59 543	4.72 544	18.04 543	1.26 547	10.19 546	1.46 548	9.60 545	7.69 541

SIFT-UMatch		10.58 508	10.73 513	10.15 525	31.05 543	11.65 548	18.01 537	5.92 551	4.65 542	4.72 544	18.93 539	1.25 548	10.62 545	1.66 543	10.39 544	8.16 540

SIFT-UM-Cal		9.80 511	10.00 517	9.22 528	30.05 546	10.15 552	16.31 540	4.85 554	4.54 544	4.19 547	18.23 542	1.19 549	9.95 548	1.52 547	9.11 547	7.57 542

PMatch-SfM		38.18 485	33.34 489	52.72 500	43.67 530	28.18 531	52.96 514	16.29 534	29.70 517	31.24 518	68.56 508	1.08 550	57.70 522	38.73 511	17.80 531	72.30 502

SIFT-PCN-Cal		8.65 515	8.88 519	7.98 529	26.74 549	7.47 556	13.90 543	4.61 555	4.09 547	3.82 548	15.86 544	1.01 551	8.94 549	1.34 549	8.52 548	7.53 543

SIFT-PointCN		8.76 513	9.03 518	7.96 530	26.50 550	7.60 555	14.94 542	5.08 553	4.10 546	3.74 549	15.46 545	0.94 552	8.92 550	1.33 550	9.14 546	7.37 544

SIFT-NCMNet		7.46 517	7.71 521	6.72 531	25.03 551	6.86 557	11.42 544	2.98 556	4.05 548	3.38 550	13.68 546	0.84 553	7.65 551	1.13 551	6.87 549	5.66 545

PMatch-Up-SfM		32.59 487	28.46 491	44.98 504	37.19 536	22.27 535	44.73 520	10.63 541	23.85 520	27.52 523	64.10 514	0.78 554	47.14 525	34.15 514	13.22 538	65.53 510

test123		8.76 513	11.22 510	1.39 532	0.85 557	0.97 558	85.76 467	0.35 558	0.54 550	2.45 552	8.14 550	0.60 555	0.48 552	2.16 537	0.17 551	2.71 547

testmvs		8.92 512	11.52 508	1.12 533	1.06 556	0.46 559	86.02 464	0.65 557	0.62 549	2.74 551	9.52 549	0.31 556	0.45 553	2.38 536	0.39 550	2.46 548

mmdepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

ab-mvs-re		7.82 516	10.43 515	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	93.88 253	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

MED-MVS test				94.84 34	98.88 1	85.89 66	97.32 10	97.86 1	88.11 134	97.21 14	97.54 46		99.67 1	95.27 41	98.85 22	98.95 13

WAC-MVS						64.08 483								59.14 481

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					0.00 558

eth-test					0.00 558

IU-MVS					98.77 8	86.00 55		96.84 83	81.26 349	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																96.12 233

test_part2					98.55 15	87.22 20				96.40 31

MTGPA								96.97 66

MTMP							96.16 60	60.64 514

gm-plane-assit					89.60 430	68.00 466			77.28 406		88.99 410		97.57 249	79.44 341

test9_res														91.91 110	98.71 36	98.07 84

agg_prior2														90.54 139	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	94.11 225

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

旧先验2							93.36 277		71.25 468	94.37 62			97.13 306	86.74 205

新几何2							93.11 292

无先验							93.28 285	96.26 141	73.95 448				99.05 68	80.56 315		96.59 212

原ACMM2							92.94 303

testdata2													98.75 117	78.30 355

testdata1							92.15 340		87.94 143

plane_prior7					94.70 202	82.74 166

plane_prior5								96.22 147					98.12 180	88.15 180	89.99 285	94.63 294

plane_prior4											94.86 203

plane_prior3						82.75 164			90.26 50	86.91 252

plane_prior2							95.85 93		90.81 27

plane_prior1					94.59 211

plane_prior						82.73 167	95.21 142		89.66 71						89.88 290

n2								0.00 559

nn								0.00 559

door-mid								85.49 477

test11								96.57 113

door								85.33 479

HQP5-MVS						81.56 207

HQP-NCC					94.17 251		94.39 205		88.81 104	85.43 298

ACMP_Plane					94.17 251		94.39 205		88.81 104	85.43 298

BP-MVS														87.11 202

HQP4-MVS										85.43 298			97.96 217			94.51 304

HQP3-MVS								96.04 174							89.77 294

NP-MVS					94.37 232	82.42 181					93.98 246

ACMMP++_ref															87.47 330

ACMMP++															88.01 322

High-resolution multi-view benchmark