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									82.47 315	97.09 20	97.07 73	92.72 1	98.04 202	92.70 82	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 32	97.62 9	98.06 25	92.59 2	99.61 7	95.64 34	99.02 12	98.86 16

OPU-MVS				96.21 3	98.00 49	90.85 3	97.13 19				97.08 71	92.59 2	98.94 93	92.25 94	98.99 14	98.84 19

MED-MVS		95.95 2	96.31 2	94.90 25	98.88 1	85.89 66	97.32 10	97.86 1	90.76 30	97.21 15	98.09 19	92.42 4	99.67 1	95.27 42	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 45	97.71 3	98.07 23	92.31 5	99.58 14	95.66 32	99.13 3	98.84 19

test_241102_ONE					98.77 8	85.99 57		97.44 20	90.26 51	97.71 3	97.96 34	92.31 5	99.38 36

test_0728_THIRD									90.75 32	97.04 22	98.05 28	92.09 7	99.55 21	95.64 34	99.13 3	99.13 4

DPE-MVS		95.57 5	95.67 6	95.25 12	98.36 32	87.28 19	95.56 119	97.51 10	89.13 92	97.14 18	97.91 35	91.64 8	99.62 5	94.61 51	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 49	97.04 22	98.05 28	91.47 9	99.55 21	95.62 36	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 49	97.64 7	98.13 8	91.47 9

test_241102_TWO								97.44 20	90.31 45	97.62 9	98.07 23	91.46 11	99.58 14	95.66 32	99.12 6	98.98 12

test_one_0601					98.58 14	85.83 69		97.44 20	91.05 24	96.78 28	98.06 25	91.45 12

fmvsm_l_mol_unc0.5_1		95.04 16	95.73 5	92.96 115	95.59 150	82.16 189	94.15 223	96.64 109	91.92 11	98.69 1	98.92 1	90.35 13	98.76 117	96.75 22	98.57 53	97.98 97

MSP-MVS		95.42 7	95.56 8	94.98 21	98.49 20	86.52 38	96.91 30	97.47 16	91.73 15	96.10 37	96.69 88	89.90 14	99.30 49	94.70 49	98.04 81	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 48	94.77 32	92.49 153	96.52 99	80.00 282	94.00 242	97.08 60	90.05 53	95.65 49	97.29 58	89.66 15	98.97 88	93.95 57	98.71 36	98.50 32

test-260524					98.47 21	86.91 23		97.38 27		95.81 45		89.60 16	99.63 4	95.95 30	98.95 15

SD-MVS		94.96 19	95.33 13	93.88 71	97.25 80	86.69 30	96.19 57	97.11 59	90.42 41	96.95 24	97.27 59	89.53 17	96.91 327	94.38 53	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 12	95.50 8	98.11 43	88.51 8	95.29 132	96.96 69	92.09 10	95.32 52	97.08 71	89.49 18	99.33 46	95.10 45	98.85 22	98.66 26

APDe-MVS		95.46 6	95.64 7	94.91 23	98.26 35	86.29 48	97.46 7	97.40 26	89.03 98	96.20 36	98.10 15	89.39 19	99.34 43	95.88 31	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 93	95.69 47	96.49 101	89.27 20	99.29 51		95.80 145	97.95 100

aaEdge-Enhanced		95.17 12	95.29 15	94.81 36	98.39 29	85.89 66	95.91 88	97.55 8	89.01 100	95.86 43	97.54 47	89.24 21	99.59 11	95.27 42	98.85 22	98.95 13

MCST-MVS		94.45 35	94.20 52	95.19 14	98.46 23	87.50 17	95.00 156	97.12 56	87.13 178	92.51 115	96.30 107	89.24 21	99.34 43	93.46 65	98.62 50	98.73 23

TSAR-MVS + MP.		94.85 20	94.94 25	94.58 47	98.25 36	86.33 44	96.11 67	96.62 110	88.14 132	96.10 37	96.96 77	89.09 23	98.94 93	94.48 52	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 11	94.99 20	98.88 1	86.26 49	97.32 10	97.43 25	90.76 30	96.80 27	98.09 19	89.00 24	99.58 14	93.66 62	96.99 113	99.14 2

SteuartSystems-ACMMP		95.20 10	95.32 14	94.85 28	96.99 83	86.33 44	97.33 8	97.30 38	91.38 20	95.39 51	97.46 51	88.98 25	99.40 35	94.12 55	98.89 20	98.82 21
Skip Steuart: Steuart Systems R&D Blog.
SMA-MVS		95.20 10	95.07 21	95.59 6	98.14 42	88.48 9	96.26 54	97.28 41	85.90 214	97.67 5	98.10 15	88.41 26	99.56 17	94.66 50	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 66	94.32 42	92.01 186	97.54 67	78.37 335	93.40 278	97.19 45	88.02 141	94.99 59	97.21 63	88.35 27	98.44 155	94.07 56	98.09 78	99.23 1

9.14			94.47 36		97.79 59		96.08 69	97.44 20	86.13 212	95.10 57	97.40 54	88.34 28	99.22 54	93.25 70	98.70 38

SF-MVS		94.97 18	94.90 29	95.20 13	97.84 57	87.76 11	96.65 39	97.48 15	87.76 157	95.71 46	97.70 43	88.28 29	99.35 42	93.89 59	98.78 30	98.48 35

HPM-MVS++		95.14 13	94.91 27	95.83 4	98.25 36	89.65 4	95.92 87	96.96 69	91.75 14	94.02 74	96.83 83	88.12 30	99.55 21	93.41 68	98.94 18	98.28 62

dcpmvs_2		93.49 71	94.19 53	91.38 229	97.69 64	76.78 379	94.25 217	96.29 134	88.33 122	94.46 62	96.88 80	88.07 31	98.64 132	93.62 64	98.09 78	98.73 23

CSCG		93.23 86	93.05 87	93.76 78	98.04 47	84.07 114	96.22 56	97.37 28	84.15 271	90.05 192	95.66 158	87.77 32	99.15 62	89.91 154	98.27 63	98.07 84

NCCC		94.81 23	94.69 33	95.17 15	97.83 58	87.46 18	95.66 110	96.93 73	92.34 7	93.94 75	96.58 98	87.74 33	99.44 34	92.83 77	98.40 59	98.62 27

TEST9					97.53 68	86.49 39	94.07 233	96.78 91	81.61 345	92.77 103	96.20 111	87.71 34	99.12 64

train_agg		93.44 76	93.08 86	94.52 49	97.53 68	86.49 39	94.07 233	96.78 91	81.86 336	92.77 103	96.20 111	87.63 35	99.12 64	92.14 100	98.69 39	97.94 101

test_8					97.49 70	86.30 47	94.02 239	96.76 94	81.86 336	92.70 107	96.20 111	87.63 35	99.02 74

ZD-MVS					98.15 41	86.62 35		97.07 61	83.63 284	94.19 67	96.91 79	87.57 37	99.26 52	91.99 107	98.44 58

fmvsm_l_conf0.5_n		94.29 42	94.46 37	93.79 77	95.28 160	85.43 78	95.68 107	96.43 123	86.56 197	96.84 26	97.81 40	87.56 38	98.77 116	97.14 15	96.82 121	97.16 176

fmvsm_l_conf0.5_n_a		94.20 48	94.40 39	93.60 83	95.29 159	84.98 85	95.61 115	96.28 137	86.31 204	96.75 29	97.86 38	87.40 39	98.74 121	97.07 17	97.02 112	97.07 181

TSAR-MVS + GP.		93.66 68	93.41 79	94.41 54	96.59 93	86.78 28	94.40 204	93.93 327	89.77 68	94.21 66	95.59 162	87.35 40	98.61 137	92.72 80	96.15 138	97.83 121

APD-MVS		94.24 44	94.07 57	94.75 41	98.06 46	86.90 25	95.88 90	96.94 72	85.68 221	95.05 58	97.18 67	87.31 41	99.07 66	91.90 113	98.61 52	98.28 62
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												87.16 42

reproduce-ours		94.82 21	94.97 23	94.38 55	97.91 54	85.46 76	95.86 91	97.15 52	89.82 61	95.23 55	98.10 15	87.09 43	99.37 38	95.30 40	98.25 68	98.30 56

our_new_method		94.82 21	94.97 23	94.38 55	97.91 54	85.46 76	95.86 91	97.15 52	89.82 61	95.23 55	98.10 15	87.09 43	99.37 38	95.30 40	98.25 68	98.30 56

旧先验1					96.79 87	81.81 201		95.67 213			96.81 85	86.69 45			97.66 99	96.97 191

lecture		95.10 14	95.46 10	94.01 66	98.40 27	84.36 108	97.70 3	97.78 3	91.19 21	96.22 35	98.08 22	86.64 46	99.37 38	94.91 47	98.26 64	98.29 61

test_prior2							94.12 225		87.67 161	92.63 111	96.39 106	86.62 47		91.50 121	98.67 44

CDPH-MVS		92.83 95	92.30 104	94.44 50	97.79 59	86.11 54	94.06 235	96.66 106	80.09 367	92.77 103	96.63 95	86.62 47	99.04 70	87.40 197	98.66 45	98.17 75

DPM-MVS		92.58 101	91.74 113	95.08 16	96.19 108	89.31 5	92.66 319	96.56 115	83.44 290	91.68 143	95.04 194	86.60 49	98.99 83	85.60 224	97.92 86	96.93 195

reproduce_model		94.76 25	94.92 26	94.29 61	97.92 50	85.18 82	95.95 85	97.19 45	89.67 71	95.27 54	98.16 7	86.53 50	99.36 41	95.42 39	98.15 74	98.33 51

test_fmvsmconf_n		94.60 29	94.81 31	93.98 67	94.62 209	84.96 86	96.15 62	97.35 30	89.37 81	96.03 40	98.11 12	86.36 51	99.01 76	97.45 10	97.83 91	97.96 99

DELS-MVS		93.43 80	93.25 82	93.97 68	95.42 154	85.04 84	93.06 300	97.13 55	90.74 34	91.84 135	95.09 193	86.32 52	99.21 56	91.22 125	98.45 57	97.65 134
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 27	95.11 20	93.50 85	95.79 134	84.62 93	96.15 62	97.64 5	89.85 60	97.19 17	97.89 36	86.28 53	98.71 124	97.11 16	98.08 80	97.17 169

ZNCC-MVS		94.47 34	94.28 46	95.03 17	98.52 18	86.96 21	96.85 33	97.32 35	88.24 127	93.15 90	97.04 74	86.17 54	99.62 5	92.40 88	98.81 27	98.52 31

HFP-MVS		94.52 32	94.40 39	94.86 27	98.61 13	86.81 27	96.94 25	97.34 31	88.63 113	93.65 80	97.21 63	86.10 55	99.49 31	92.35 91	98.77 32	98.30 56

MVS_111021_HR		93.45 75	93.31 80	93.84 73	96.99 83	84.84 87	93.24 291	97.24 42	88.76 108	91.60 144	95.85 144	86.07 56	98.66 127	91.91 111	98.16 72	98.03 92

ACMMP_NAP		94.74 26	94.56 34	95.28 11	98.02 48	87.70 12	95.68 107	97.34 31	88.28 126	95.30 53	97.67 44	85.90 57	99.54 25	93.91 58	98.95 15	98.60 28

fmvsm_l_conf0.5_n_9		94.65 28	95.28 16	92.77 127	95.95 130	81.83 200	95.53 120	97.12 56	91.68 17	97.89 2	98.06 25	85.71 58	98.65 129	97.32 12	98.26 64	97.83 121

CS-MVS		94.12 52	94.44 38	93.17 99	96.55 96	83.08 154	97.63 4	96.95 71	91.71 16	93.50 86	96.21 110	85.61 59	98.24 172	93.64 63	98.17 71	98.19 73

PHI-MVS		93.89 61	93.65 75	94.62 46	96.84 86	86.43 41	96.69 37	97.49 11	85.15 245	93.56 84	96.28 108	85.60 60	99.31 48	92.45 85	98.79 28	98.12 82

MP-MVS-pluss		94.21 46	94.00 60	94.85 28	98.17 40	86.65 33	94.82 169	97.17 50	86.26 206	92.83 100	97.87 37	85.57 61	99.56 17	94.37 54	98.92 19	98.34 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
GST-MVS		94.21 46	93.97 61	94.90 25	98.41 26	86.82 26	96.54 41	97.19 45	88.24 127	93.26 87	96.83 83	85.48 62	99.59 11	91.43 123	98.40 59	98.30 56

MP-MVS		94.25 43	94.07 57	94.77 40	98.47 21	86.31 46	96.71 36	96.98 65	89.04 96	91.98 127	97.19 66	85.43 63	99.56 17	92.06 105	98.79 28	98.44 43
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
DeepC-MVS_fast	89.43 2	94.04 54	93.79 66	94.80 38	97.48 71	86.78 28	95.65 112	96.89 78	89.40 80	92.81 101	96.97 76	85.37 64	99.24 53	90.87 134	98.69 39	98.38 48
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.5_n_11		94.60 29	95.23 17	92.69 139	96.05 121	82.00 193	96.31 46	96.71 102	92.27 8	96.68 31	98.39 3	85.32 65	98.92 96	97.20 14	98.16 72	97.17 169

region2R		94.43 37	94.27 48	94.92 22	98.65 11	86.67 32	96.92 29	97.23 44	88.60 116	93.58 82	97.27 59	85.22 66	99.54 25	92.21 96	98.74 35	98.56 30

CP-MVS		94.34 41	94.21 51	94.74 42	98.39 29	86.64 34	97.60 5	97.24 42	88.53 118	92.73 106	97.23 62	85.20 67	99.32 47	92.15 99	98.83 26	98.25 70

test_fmvsmconf0.1_n		94.20 48	94.31 44	93.88 71	92.46 337	84.80 89	96.18 59	96.82 86	89.29 86	95.68 48	98.11 12	85.10 68	98.99 83	97.38 11	97.75 97	97.86 116

test12				94.34 58	97.13 81	86.15 53		96.29 134		91.04 166		85.08 69	99.01 76		98.13 76	97.86 116

ACMMPR		94.43 37	94.28 46	94.91 23	98.63 12	86.69 30	96.94 25	97.32 35	88.63 113	93.53 85	97.26 61	85.04 70	99.54 25	92.35 91	98.78 30	98.50 32

SPE-MVS-test		94.02 55	94.29 45	93.24 93	96.69 89	83.24 142	97.49 6	96.92 74	92.14 9	92.90 96	95.77 153	85.02 71	98.33 167	93.03 74	98.62 50	98.13 79

XVS		94.45 35	94.32 42	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 37	92.85 98	97.16 69	85.02 71	99.49 31	91.99 107	98.56 55	98.47 38

X-MVStestdata		88.31 243	86.13 292	94.85 28	98.54 16	86.60 36	96.93 27	97.19 45	90.66 37	92.85 98	23.41 540	85.02 71	99.49 31	91.99 107	98.56 55	98.47 38

MVSMamba_PlusPlus		93.44 76	93.54 77	93.14 101	96.58 95	83.05 155	96.06 73	96.50 120	84.42 267	94.09 70	95.56 164	85.01 74	98.69 126	94.96 46	98.66 45	97.67 133

fmvsm_l_conf0.5_n_3		94.80 24	95.01 22	94.15 64	95.64 143	85.08 83	96.09 68	97.36 29	90.98 25	97.09 20	98.12 11	84.98 75	98.94 93	97.07 17	97.80 93	98.43 44

MSLP-MVS++		93.72 67	94.08 56	92.65 142	97.31 76	83.43 135	95.79 98	97.33 33	90.03 54	93.58 82	96.96 77	84.87 76	97.76 234	92.19 98	98.66 45	96.76 206

HPM-MVS		94.02 55	93.88 62	94.43 52	98.39 29	85.78 71	97.25 15	97.07 61	86.90 189	92.62 112	96.80 87	84.85 77	99.17 58	92.43 86	98.65 48	98.33 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
fmvsm_s_conf0.5_n_9		94.99 17	95.50 9	93.44 86	96.51 101	82.25 187	95.76 102	96.92 74	93.37 3	97.63 8	98.43 2	84.82 78	99.16 61	98.15 1	97.92 86	98.90 15

SR-MVS		94.23 45	94.17 55	94.43 52	98.21 39	85.78 71	96.40 43	96.90 77	88.20 130	94.33 64	97.40 54	84.75 79	99.03 71	93.35 69	97.99 83	98.48 35

PGM-MVS		93.96 59	93.72 71	94.68 43	98.43 24	86.22 50	95.30 130	97.78 3	87.45 168	93.26 87	97.33 57	84.62 80	99.51 29	90.75 138	98.57 53	98.32 55

BridgeMVS		93.98 58	94.22 49	93.26 92	96.13 111	83.29 141	96.27 53	96.52 118	89.82 61	95.56 50	95.51 167	84.50 81	98.79 114	94.83 48	98.86 21	97.72 130

EI-MVSNet-Vis-set		93.01 93	92.92 90	93.29 90	95.01 174	83.51 134	94.48 192	95.77 201	90.87 26	92.52 114	96.67 90	84.50 81	99.00 81	91.99 107	94.44 186	97.36 153

MTAPA		94.42 40	94.22 49	95.00 19	98.42 25	86.95 22	94.36 212	96.97 66	91.07 23	93.14 91	97.56 46	84.30 83	99.56 17	93.43 66	98.75 34	98.47 38

SR-MVS-dyc-post		93.82 63	93.82 64	93.82 74	97.92 50	84.57 95	96.28 51	96.76 94	87.46 166	93.75 78	97.43 52	84.24 84	99.01 76	92.73 78	97.80 93	97.88 114

ETV-MVS		92.74 99	92.66 96	92.97 113	95.20 166	84.04 118	95.07 151	96.51 119	90.73 35	92.96 95	91.19 349	84.06 85	98.34 165	91.72 116	96.54 128	96.54 219

EI-MVSNet-UG-set		92.74 99	92.62 98	93.12 102	94.86 188	83.20 144	94.40 204	95.74 204	90.71 36	92.05 125	96.60 97	84.00 86	98.99 83	91.55 119	93.63 214	97.17 169

mPP-MVS		93.99 57	93.78 67	94.63 45	98.50 19	85.90 65	96.87 31	96.91 76	88.70 111	91.83 137	97.17 68	83.96 87	99.55 21	91.44 122	98.64 49	98.43 44

APD-MVS_3200maxsize		93.78 64	93.77 68	93.80 76	97.92 50	84.19 112	96.30 47	96.87 80	86.96 185	93.92 76	97.47 50	83.88 88	98.96 90	92.71 81	97.87 89	98.26 69

EIA-MVS		91.95 113	91.94 110	91.98 190	95.16 168	80.01 281	95.36 125	96.73 99	88.44 119	89.34 205	92.16 312	83.82 89	98.45 153	89.35 164	97.06 110	97.48 148

fmvsm_s_conf0.5_n_3		94.49 33	95.13 18	92.56 147	95.49 152	81.10 229	95.93 86	97.16 51	92.96 4	97.39 13	98.13 8	83.63 90	98.80 112	97.89 3	97.61 100	97.78 126

fmvsm_s_conf0.5_n		93.76 65	94.06 59	92.86 121	95.62 145	83.17 146	96.14 64	96.12 168	88.13 133	95.82 44	98.04 31	83.43 91	98.48 145	96.97 21	96.23 135	96.92 196

casdiffmvs_mvg		92.96 94	92.83 92	93.35 88	94.59 213	83.40 137	95.00 156	96.34 131	90.30 47	92.05 125	96.05 126	83.43 91	98.15 180	92.07 102	95.67 149	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		91.70 130	91.56 120	92.13 185	95.88 131	80.50 261	97.33 8	95.25 251	86.15 209	89.76 198	95.60 161	83.42 93	98.32 169	87.37 199	93.25 229	97.56 142

test_fmvsmvis_n_1920		93.44 76	93.55 76	93.10 103	93.67 287	84.26 110	95.83 95	96.14 164	89.00 101	92.43 117	97.50 49	83.37 94	98.72 122	96.61 25	97.44 102	96.32 224

fmvsm_s_conf0.5_n_5		93.96 59	94.18 54	93.30 89	94.79 192	83.81 123	95.77 100	96.74 98	88.02 141	96.23 34	97.84 39	83.36 95	98.83 110	97.49 8	97.34 106	97.25 161

fmvsm_s_conf0.5_n_6		94.11 53	94.56 34	92.76 130	94.98 178	81.96 197	95.79 98	97.29 40	89.31 84	97.52 12	97.61 45	83.25 96	98.88 100	97.05 19	98.22 70	97.43 152

UA-Net		92.83 95	92.54 99	93.68 82	96.10 116	84.71 91	95.66 110	96.39 127	91.92 11	93.22 89	96.49 101	83.16 97	98.87 101	84.47 245	95.47 156	97.45 150

UniMVSNet_NR-MVSNet		89.92 188	89.29 191	91.81 207	93.39 296	83.72 125	94.43 198	97.12 56	89.80 64	86.46 266	93.32 272	83.16 97	97.23 301	84.92 233	81.02 410	94.49 311

EC-MVSNet		93.44 76	93.71 72	92.63 143	95.21 165	82.43 180	97.27 14	96.71 102	90.57 40	92.88 97	95.80 149	83.16 97	98.16 179	93.68 61	98.14 75	97.31 154

fmvsm_s_conf0.5_n_4		93.86 62	94.37 41	92.33 167	95.13 171	80.95 236	95.64 113	96.97 66	89.60 73	96.85 25	97.77 41	83.08 100	98.92 96	97.49 8	96.78 122	97.13 177

fmvsm_s_conf0.5_n_a		93.57 69	93.76 69	93.00 111	95.02 173	83.67 127	96.19 57	96.10 170	87.27 172	95.98 41	98.05 28	83.07 101	98.45 153	96.68 24	95.51 153	96.88 199

MM		95.10 14	94.91 27	95.68 5	96.09 117	88.34 10	96.68 38	94.37 309	95.08 1	94.68 60	97.72 42	82.94 102	99.64 3	97.85 5	98.76 33	99.06 9

RE-MVS-def			93.68 73		97.92 50	84.57 95	96.28 51	96.76 94	87.46 166	93.75 78	97.43 52	82.94 102		92.73 78	97.80 93	97.88 114

新几何1				93.10 103	97.30 77	84.35 109		95.56 222	71.09 473	91.26 154	96.24 109	82.87 104	98.86 103	79.19 348	98.10 77	96.07 240

fmvsm_s_conf0.1_n		93.46 73	93.66 74	92.85 122	93.75 279	83.13 148	96.02 77	95.74 204	87.68 160	95.89 42	98.17 6	82.78 105	98.46 149	96.71 23	96.17 137	96.98 190

Casviewmamba		92.82 97	92.75 93	93.03 108	94.79 192	82.44 179	95.39 124	96.24 145	90.58 39	91.79 139	96.43 105	82.73 106	98.19 177	91.31 124	95.54 151	98.46 41

原ACMM1				92.01 186	97.34 74	81.05 231		96.81 89	78.89 383	90.45 176	95.92 137	82.65 107	98.84 107	80.68 316	98.26 64	96.14 234

casdiffmvs		92.51 102	92.43 101	92.74 134	94.41 234	81.98 195	94.54 189	96.23 147	89.57 75	91.96 129	96.17 116	82.58 108	98.01 209	90.95 132	95.45 158	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 82	92.99 89	94.26 62	96.07 119	85.83 69	94.89 162	96.99 64	89.02 99	89.56 200	97.37 56	82.51 109	99.38 36	92.20 97	98.30 62	97.57 141
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 81	93.22 83	93.94 70	98.36 32	84.83 88	97.15 18	96.80 90	85.77 218	92.47 116	97.13 70	82.38 110	99.07 66	90.51 143	98.40 59	97.92 110

baseline		92.39 107	92.29 105	92.69 139	94.46 229	81.77 205	94.14 224	96.27 138	89.22 88	91.88 133	96.00 130	82.35 111	97.99 211	91.05 127	95.27 164	98.30 56

sasdasda		93.27 83	92.75 93	94.85 28	95.70 140	87.66 13	96.33 44	96.41 125	90.00 55	94.09 70	94.60 220	82.33 112	98.62 135	92.40 88	92.86 241	98.27 65

canonicalmvs		93.27 83	92.75 93	94.85 28	95.70 140	87.66 13	96.33 44	96.41 125	90.00 55	94.09 70	94.60 220	82.33 112	98.62 135	92.40 88	92.86 241	98.27 65

fmvsm_s_conf0.1_n_a		93.19 87	93.26 81	92.97 113	92.49 335	83.62 130	96.02 77	95.72 208	86.78 191	96.04 39	98.19 5	82.30 114	98.43 157	96.38 26	95.42 159	96.86 200

DP-MVS Recon		91.95 113	91.28 133	93.96 69	98.33 34	85.92 62	94.66 183	96.66 106	82.69 313	90.03 193	95.82 147	82.30 114	99.03 71	84.57 243	96.48 131	96.91 197

hybridcas		92.43 105	92.33 102	92.74 134	94.51 221	81.84 199	95.05 154	96.16 162	89.60 73	91.40 151	96.20 111	82.23 116	98.09 191	89.95 153	95.87 143	98.28 62

PAPR		90.02 182	89.27 193	92.29 174	95.78 135	80.95 236	92.68 318	96.22 148	81.91 332	86.66 263	93.75 262	82.23 116	98.44 155	79.40 347	94.79 172	97.48 148

MVS_Test		91.31 139	91.11 136	91.93 195	94.37 235	80.14 270	93.46 276	95.80 199	86.46 200	91.35 153	93.77 260	82.21 118	98.09 191	87.57 194	94.95 168	97.55 144

nrg030		91.08 150	90.39 155	93.17 99	93.07 308	86.91 23	96.41 42	96.26 142	88.30 124	88.37 225	94.85 206	82.19 119	97.64 245	91.09 126	82.95 380	94.96 285

MGCFI-Net		93.03 92	92.63 97	94.23 63	95.62 145	85.92 62	96.08 69	96.33 132	89.86 59	93.89 77	94.66 216	82.11 120	98.50 143	92.33 93	92.82 244	98.27 65

UniMVSNet (Re)		89.80 192	89.07 197	92.01 186	93.60 290	84.52 98	94.78 173	97.47 16	89.26 87	86.44 269	92.32 307	82.10 121	97.39 284	84.81 236	80.84 414	94.12 325

testdata				90.49 275	96.40 102	77.89 351		95.37 242	72.51 465	93.63 81	96.69 88	82.08 122	97.65 243	83.08 264	97.39 103	95.94 245

PAPM_NR		91.22 142	90.78 147	92.52 151	97.60 66	81.46 215	94.37 210	96.24 145	86.39 203	87.41 246	94.80 208	82.06 123	98.48 145	82.80 272	95.37 160	97.61 137

MG-MVS		91.77 121	91.70 114	92.00 189	97.08 82	80.03 280	93.60 271	95.18 257	87.85 153	90.89 169	96.47 103	82.06 123	98.36 162	85.07 231	97.04 111	97.62 135

CANet		93.54 70	93.20 84	94.55 48	95.65 142	85.73 73	94.94 159	96.69 105	91.89 13	90.69 171	95.88 140	81.99 125	99.54 25	93.14 72	97.95 85	98.39 46

FC-MVSNet-test		90.27 173	90.18 161	90.53 268	93.71 284	79.85 289	95.77 100	97.59 6	89.31 84	86.27 273	94.67 215	81.93 126	97.01 320	84.26 247	88.09 325	94.71 297

fmvsm_s_conf0.5_n_10		94.43 37	94.84 30	93.20 95	95.73 137	83.19 145	95.99 79	97.31 37	91.08 22	97.67 5	98.11 12	81.87 127	99.22 54	97.86 4	97.91 88	97.20 167

fmvsm_s_conf0.5_n_7		93.15 90	93.76 69	91.31 232	94.42 233	79.48 301	94.52 190	97.14 54	89.33 83	94.17 68	98.09 19	81.83 128	97.49 261	96.33 27	98.02 82	96.95 192

FIs		90.51 169	90.35 156	90.99 250	93.99 266	80.98 234	95.73 104	97.54 9	89.15 91	86.72 262	94.68 212	81.83 128	97.24 300	85.18 229	88.31 322	94.76 296

fmvsm_s_conf0.5_n_8		94.56 31	95.12 19	92.87 120	95.96 129	81.32 219	95.76 102	97.57 7	93.48 2	97.53 11	98.32 4	81.78 130	99.13 63	97.91 2	97.81 92	98.16 76

E3new		91.76 122	91.58 118	92.28 178	94.69 206	80.90 239	93.68 269	96.17 160	87.15 176	91.09 165	95.70 157	81.75 131	98.05 201	89.67 161	94.35 188	97.90 113

viewcassd2359sk11		91.79 116	91.62 115	92.29 174	94.62 209	80.88 240	93.70 266	96.18 159	87.38 170	91.13 158	95.85 144	81.62 132	98.06 197	89.71 158	94.40 187	97.94 101

ACMMP		93.24 85	92.88 91	94.30 60	98.09 45	85.33 80	96.86 32	97.45 19	88.33 122	90.15 191	97.03 75	81.44 133	99.51 29	90.85 135	95.74 148	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+		91.59 133	91.11 136	93.01 110	94.35 239	83.39 138	94.60 185	95.10 261	87.10 179	90.57 175	93.10 283	81.43 134	98.07 196	89.29 166	94.48 184	97.59 140

MVS_111021_LR		92.47 104	92.29 105	92.98 112	95.99 126	84.43 104	93.08 297	96.09 171	88.20 130	91.12 159	95.72 156	81.33 135	97.76 234	91.74 115	97.37 104	96.75 207

E2		91.79 116	91.61 116	92.31 169	94.49 225	80.86 243	93.74 261	96.19 152	87.63 163	91.16 155	95.94 135	81.31 136	98.06 197	89.76 156	94.29 191	97.99 95

E3		91.78 119	91.61 116	92.30 172	94.48 226	80.86 243	93.73 262	96.19 152	87.63 163	91.16 155	95.95 134	81.30 137	98.06 197	89.76 156	94.29 191	97.99 95

mvs_anonymous		89.37 211	89.32 190	89.51 337	93.47 293	74.22 411	91.65 359	94.83 286	82.91 308	85.45 298	93.79 258	81.23 138	96.36 373	86.47 211	94.09 196	97.94 101

PVSNet_BlendedMVS		89.98 183	89.70 176	90.82 259	96.12 112	81.25 221	93.92 248	96.83 84	83.49 289	89.10 209	92.26 310	81.04 139	98.85 105	86.72 209	87.86 329	92.35 417

PVSNet_Blended		90.73 157	90.32 157	91.98 190	96.12 112	81.25 221	92.55 323	96.83 84	82.04 328	89.10 209	92.56 300	81.04 139	98.85 105	86.72 209	95.91 142	95.84 251

viewmanbaseed2359cas		91.78 119	91.58 118	92.37 162	94.32 242	81.07 230	93.76 259	95.96 184	87.26 173	91.50 146	95.88 140	80.92 141	97.97 216	89.70 159	94.92 169	98.07 84

PRO-TEST		92.11 110	92.00 109	92.44 157	94.50 223	81.48 214	94.67 181	96.19 152	88.04 140	92.23 121	94.64 218	80.86 142	97.82 231	90.78 137	96.11 140	98.02 94

E4		91.74 124	91.55 121	92.31 169	94.27 247	80.80 247	93.81 256	96.17 160	87.97 143	91.11 160	96.05 126	80.75 143	98.08 194	89.78 155	94.02 198	98.06 89

viewmamba		91.38 136	91.32 130	91.58 216	93.02 315	79.63 298	92.83 311	95.38 239	88.29 125	90.66 172	95.81 148	80.63 144	97.50 260	91.52 120	93.71 212	97.62 135

MGCNet		94.18 51	93.80 65	95.34 10	94.91 185	87.62 15	95.97 82	93.01 360	92.58 6	94.22 65	97.20 65	80.56 145	99.59 11	97.04 20	98.68 41	98.81 22

alignmvs		93.08 91	92.50 100	94.81 36	95.62 145	87.61 16	95.99 79	96.07 173	89.77 68	94.12 69	94.87 203	80.56 145	98.66 127	92.42 87	93.10 236	98.15 77

API-MVS		90.66 163	90.07 165	92.45 156	96.36 104	84.57 95	96.06 73	95.22 254	82.39 316	89.13 208	94.27 237	80.32 147	98.46 149	80.16 326	96.71 124	94.33 317

PVSNet_Blended_VisFu		91.38 136	90.91 143	92.80 125	96.39 103	83.17 146	94.87 164	96.66 106	83.29 295	89.27 207	94.46 229	80.29 148	99.17 58	87.57 194	95.37 160	96.05 243

viewdifsd2359ckpt07		91.11 148	91.02 140	91.41 227	94.21 252	78.37 335	92.91 307	95.71 209	87.50 165	90.32 181	95.88 140	80.27 149	97.99 211	88.78 177	93.55 216	97.86 116

test222					96.55 96	81.70 206	92.22 341	95.01 265	68.36 482	90.20 184	96.14 121	80.26 150			97.80 93	96.05 243

diffmvs		91.37 138	91.23 134	91.77 208	93.09 306	80.27 265	92.36 329	95.52 227	87.03 182	91.40 151	94.93 199	80.08 151	97.44 270	92.13 101	94.56 181	97.61 137
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												80.02 152

onestephybrid01		91.23 140	91.10 138	91.61 214	93.07 308	79.86 287	92.83 311	95.34 245	87.07 180	91.04 166	95.53 165	80.01 153	97.43 271	90.96 131	94.08 197	97.56 142

diffmvs_AUTHOR		91.51 134	91.44 127	91.73 209	93.09 306	80.27 265	92.51 324	95.58 221	87.22 174	91.80 138	95.57 163	79.96 154	97.48 262	92.23 95	94.97 167	97.45 150

E5new		91.71 126	91.55 121	92.20 180	94.33 240	80.62 253	94.41 200	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 207	97.94 101

E6new		91.71 126	91.55 121	92.20 180	94.32 242	80.62 253	94.41 200	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 207	97.94 101

E6		91.71 126	91.55 121	92.20 180	94.32 242	80.62 253	94.41 200	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 207	97.94 101

E5		91.71 126	91.55 121	92.20 180	94.33 240	80.62 253	94.41 200	96.19 152	88.06 136	91.11 160	96.16 117	79.92 155	98.03 205	90.00 148	93.80 207	97.94 101

viewmacassd2359aftdt		91.67 132	91.43 128	92.37 162	93.95 270	81.00 233	93.90 253	95.97 183	87.75 158	91.45 149	96.04 128	79.92 155	97.97 216	89.26 167	94.67 175	98.14 78

IterMVS-LS		88.36 242	87.91 236	89.70 321	93.80 276	78.29 339	93.73 262	95.08 263	85.73 219	84.75 319	91.90 328	79.88 160	96.92 326	83.83 254	82.51 386	93.89 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.10 216	88.86 208	89.80 315	91.84 357	78.30 338	93.70 266	95.01 265	85.73 219	87.15 250	95.28 180	79.87 161	97.21 303	83.81 255	87.36 337	93.88 340

TAPA-MVS	84.62 6	88.16 247	87.01 257	91.62 213	96.64 91	80.65 250	94.39 206	96.21 151	76.38 424	86.19 276	95.44 170	79.75 162	98.08 194	62.75 474	95.29 162	96.13 235
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
Fast-Effi-MVS+		89.41 207	88.64 211	91.71 211	94.74 197	80.81 246	93.54 272	95.10 261	83.11 299	86.82 261	90.67 372	79.74 163	97.75 238	80.51 319	93.55 216	96.57 217

pcd_1.5k_mvsjas		6.64 526	8.86 527	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	79.70 164	0.00 562	0.00 561	0.00 561	0.00 558

PS-MVSNAJss		89.97 184	89.62 179	91.02 247	91.90 355	80.85 245	95.26 136	95.98 180	86.26 206	86.21 275	94.29 234	79.70 164	97.65 243	88.87 176	88.10 323	94.57 303

PS-MVSNAJ		91.18 144	90.92 142	91.96 192	95.26 163	82.60 177	92.09 346	95.70 210	86.27 205	91.84 135	92.46 302	79.70 164	98.99 83	89.08 169	95.86 144	94.29 318

viewdifsd2359ckpt09		91.18 144	90.65 151	92.75 132	94.61 212	82.36 185	94.32 213	95.74 204	84.72 260	89.66 199	95.15 191	79.69 167	98.04 202	87.70 191	94.27 193	97.85 119

viewdifsd2359ckpt13		91.20 143	90.75 148	92.54 149	94.30 245	82.13 190	94.03 237	95.89 192	85.60 224	90.20 184	95.36 176	79.69 167	97.90 226	87.85 189	93.86 203	97.61 137

xiu_mvs_v2_base		91.13 146	90.89 144	91.86 201	94.97 179	82.42 181	92.24 339	95.64 218	86.11 213	91.74 142	93.14 281	79.67 169	98.89 99	89.06 170	95.46 157	94.28 319

WR-MVS_H		87.80 256	87.37 247	89.10 346	93.23 299	78.12 342	95.61 115	97.30 38	87.90 149	83.72 350	92.01 323	79.65 170	96.01 388	76.36 379	80.54 418	93.16 380

viewmambaseed2359dif		90.04 181	89.78 175	90.83 257	92.85 323	77.92 347	92.23 340	95.01 265	81.90 333	90.20 184	95.45 169	79.64 171	97.34 288	87.52 196	93.17 231	97.23 166

EPNet		91.79 116	91.02 140	94.10 65	90.10 423	85.25 81	96.03 76	92.05 388	92.83 5	87.39 249	95.78 152	79.39 172	99.01 76	88.13 184	97.48 101	98.05 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
miper_ehance_all_eth		87.22 287	86.62 273	89.02 349	92.13 346	77.40 368	90.91 383	94.81 288	81.28 352	84.32 336	90.08 390	79.26 173	96.62 344	83.81 255	82.94 381	93.04 387

test_fmvsmconf0.01_n		93.19 87	93.02 88	93.71 81	89.25 436	84.42 106	96.06 73	96.29 134	89.06 94	94.68 60	98.13 8	79.22 174	98.98 87	97.22 13	97.24 107	97.74 128

miper_enhance_ethall		86.90 300	86.18 290	89.06 347	91.66 366	77.58 366	90.22 402	94.82 287	79.16 379	84.48 327	89.10 409	79.19 175	96.66 337	84.06 250	82.94 381	92.94 390

hybridnocas07		90.93 151	90.72 149	91.54 218	92.75 328	79.72 295	92.35 331	95.21 255	86.41 202	90.44 179	95.40 173	79.17 176	97.39 284	90.83 136	93.94 201	97.50 147

NR-MVSNet		88.58 236	87.47 245	91.93 195	93.04 312	84.16 113	94.77 174	96.25 144	89.05 95	80.04 409	93.29 275	79.02 177	97.05 317	81.71 298	80.05 424	94.59 301

hybrid		90.69 159	90.45 154	91.43 226	92.67 333	79.42 306	92.28 338	95.21 255	85.15 245	90.39 180	95.37 175	78.93 178	97.32 290	90.27 146	93.74 211	97.55 144

TAMVS		89.21 213	88.29 224	91.96 192	93.71 284	82.62 176	93.30 286	94.19 317	82.22 322	87.78 239	93.94 250	78.83 179	96.95 324	77.70 365	92.98 238	96.32 224

c3_l		87.14 293	86.50 279	89.04 348	92.20 343	77.26 370	91.22 375	94.70 294	82.01 329	84.34 335	90.43 377	78.81 180	96.61 347	83.70 259	81.09 407	93.25 374

1112_ss		88.42 238	87.33 248	91.72 210	94.92 183	80.98 234	92.97 305	94.54 300	78.16 401	83.82 347	93.88 255	78.78 181	97.91 224	79.45 343	89.41 302	96.26 228

CDS-MVSNet		89.45 203	88.51 215	92.29 174	93.62 289	83.61 132	93.01 301	94.68 295	81.95 330	87.82 238	93.24 277	78.69 182	96.99 321	80.34 322	93.23 230	96.28 227
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WTY-MVS		89.60 197	88.92 204	91.67 212	95.47 153	81.15 226	92.38 328	94.78 290	83.11 299	89.06 211	94.32 232	78.67 183	96.61 347	81.57 299	90.89 276	97.24 162

CPTT-MVS		91.99 112	91.80 112	92.55 148	98.24 38	81.98 195	96.76 35	96.49 121	81.89 335	90.24 182	96.44 104	78.59 184	98.61 137	89.68 160	97.85 90	97.06 182

IS-MVSNet		91.43 135	91.09 139	92.46 154	95.87 133	81.38 218	96.95 24	93.69 344	89.72 70	89.50 203	95.98 132	78.57 185	97.77 233	83.02 266	96.50 130	98.22 72

dtuplus		89.78 194	89.43 185	90.85 256	92.83 324	77.91 348	92.32 336	94.97 271	82.33 320	90.20 184	95.53 165	78.56 186	97.38 286	85.15 230	92.95 239	97.24 162

casdiffseed414692147		91.11 148	90.55 153	92.81 123	94.27 247	82.58 178	94.81 170	96.03 178	87.93 147	90.17 189	95.62 160	78.51 187	97.90 226	84.18 249	93.45 223	97.94 101

OMC-MVS		91.23 140	90.62 152	93.08 105	96.27 106	84.07 114	93.52 273	95.93 186	86.95 186	89.51 201	96.13 122	78.50 188	98.35 164	85.84 222	92.90 240	96.83 205

IMVS_0403		89.97 184	89.64 178	90.96 253	93.72 280	77.75 359	93.00 302	95.34 245	85.53 228	88.77 218	94.49 225	78.49 189	97.84 229	84.75 237	92.65 246	97.28 157

PCF-MVS	84.11 10	87.74 258	86.08 296	92.70 138	94.02 261	84.43 104	89.27 423	95.87 195	73.62 455	84.43 330	94.33 231	78.48 190	98.86 103	70.27 430	94.45 185	94.81 294
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
LCM-MVSNet-Re		88.30 244	88.32 223	88.27 370	94.71 203	72.41 438	93.15 292	90.98 421	87.77 156	79.25 424	91.96 325	78.35 191	95.75 402	83.04 265	95.62 150	96.65 212

HY-MVS	83.01 12	89.03 222	87.94 233	92.29 174	94.86 188	82.77 163	92.08 347	94.49 303	81.52 348	86.93 253	92.79 294	78.32 192	98.23 173	79.93 329	90.55 280	95.88 249

GeoE		90.05 180	89.43 185	91.90 200	95.16 168	80.37 264	95.80 96	94.65 296	83.90 276	87.55 245	94.75 209	78.18 193	97.62 247	81.28 304	93.63 214	97.71 131

NormalMVS		93.46 73	93.16 85	94.37 57	98.40 27	86.20 51	96.30 47	96.27 138	91.65 18	92.68 108	96.13 122	77.97 194	98.84 107	90.75 138	98.26 64	98.07 84

SymmetryMVS		92.81 98	92.31 103	94.32 59	96.15 109	86.20 51	96.30 47	94.43 305	91.65 18	92.68 108	96.13 122	77.97 194	98.84 107	90.75 138	94.72 173	97.92 110

MVS		87.44 275	86.10 295	91.44 225	92.61 334	83.62 130	92.63 320	95.66 215	67.26 485	81.47 387	92.15 313	77.95 196	98.22 175	79.71 332	95.48 155	92.47 410

MVSFormer		91.68 131	91.30 131	92.80 125	93.86 272	83.88 121	95.96 83	95.90 190	84.66 263	91.76 140	94.91 200	77.92 197	97.30 291	89.64 162	97.11 108	97.24 162

lupinMVS		90.92 152	90.21 159	93.03 108	93.86 272	83.88 121	92.81 313	93.86 331	79.84 370	91.76 140	94.29 234	77.92 197	98.04 202	90.48 144	97.11 108	97.17 169

Test_1112_low_res		87.65 261	86.51 278	91.08 243	94.94 182	79.28 315	91.77 354	94.30 312	76.04 430	83.51 357	92.37 305	77.86 199	97.73 239	78.69 354	89.13 309	96.22 229

VNet		92.24 108	91.91 111	93.24 93	96.59 93	83.43 135	94.84 168	96.44 122	89.19 90	94.08 73	95.90 138	77.85 200	98.17 178	88.90 174	93.38 225	98.13 79

icg_test_0407_2		89.15 214	88.97 201	89.68 327	93.72 280	77.75 359	88.26 442	95.34 245	85.53 228	88.34 226	94.49 225	77.69 201	93.99 442	84.75 237	92.65 246	97.28 157

IMVS_0407		89.85 191	89.51 182	90.88 255	93.72 280	77.75 359	93.07 299	95.34 245	85.53 228	88.34 226	94.49 225	77.69 201	97.60 248	84.75 237	92.65 246	97.28 157

fmvsm_s_conf0.5_n_2		93.47 72	93.83 63	92.39 161	95.36 156	81.19 225	95.20 144	96.56 115	90.37 43	97.13 19	98.03 32	77.47 203	98.96 90	97.79 6	96.58 127	97.03 185

mvsany_test1		85.42 342	85.30 326	85.77 429	87.95 455	75.41 399	87.61 456	80.97 496	76.82 420	88.68 219	95.83 146	77.44 204	90.82 482	85.90 220	86.51 344	91.08 449

DU-MVS		89.34 212	88.50 216	91.85 203	93.04 312	83.72 125	94.47 195	96.59 112	89.50 76	86.46 266	93.29 275	77.25 205	97.23 301	84.92 233	81.02 410	94.59 301

Baseline_NR-MVSNet		87.07 295	86.63 272	88.40 364	91.44 370	77.87 352	94.23 220	92.57 372	84.12 272	85.74 286	92.08 319	77.25 205	96.04 384	82.29 281	79.94 425	91.30 441

jason		90.80 154	90.10 163	92.90 118	93.04 312	83.53 133	93.08 297	94.15 320	80.22 364	91.41 150	94.91 200	76.87 207	97.93 222	90.28 145	96.90 117	97.24 162
jason: jason.
PAPM		86.68 312	85.39 322	90.53 268	93.05 311	79.33 314	89.79 412	94.77 291	78.82 386	81.95 383	93.24 277	76.81 208	97.30 291	66.94 454	93.16 232	94.95 289

Vis-MVSNet (Re-imp)		89.59 198	89.44 184	90.03 301	95.74 136	75.85 393	95.61 115	90.80 428	87.66 162	87.83 237	95.40 173	76.79 209	96.46 365	78.37 355	96.73 123	97.80 124

baseline1		88.10 248	87.28 250	90.57 264	94.96 180	80.07 275	94.27 216	91.29 413	86.74 192	87.41 246	94.00 247	76.77 210	96.20 379	80.77 313	79.31 433	95.44 265

114514_t		89.51 200	88.50 216	92.54 149	98.11 43	81.99 194	95.16 147	96.36 130	70.19 477	85.81 283	95.25 182	76.70 211	98.63 134	82.07 287	96.86 120	97.00 189

PLC	84.53 7	89.06 220	88.03 229	92.15 184	97.27 79	82.69 170	94.29 215	95.44 235	79.71 372	84.01 344	94.18 240	76.68 212	98.75 118	77.28 369	93.41 224	95.02 281
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TranMVSNet+NR-MVSNet		88.84 226	87.95 232	91.49 222	92.68 332	83.01 158	94.92 161	96.31 133	89.88 58	85.53 292	93.85 257	76.63 213	96.96 323	81.91 291	79.87 427	94.50 309

MAR-MVS		90.30 172	89.37 188	93.07 107	96.61 92	84.48 100	95.68 107	95.67 213	82.36 318	87.85 235	92.85 288	76.63 213	98.80 112	80.01 328	96.68 125	95.91 246
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 89	93.42 78	92.37 162	94.62 209	81.13 227	95.23 137	95.89 192	90.30 47	96.74 30	98.02 33	76.14 215	98.95 92	97.64 7	96.21 136	97.03 185

SSM_0407		90.47 170	89.80 174	92.46 154	94.76 194	82.66 171	93.98 244	95.00 269	85.41 233	88.96 213	95.35 177	76.13 216	97.88 228	85.46 227	93.15 233	96.85 201

SSM_0404		90.73 157	90.08 164	92.69 139	95.00 177	83.13 148	94.32 213	95.00 269	85.41 233	89.84 194	95.35 177	76.13 216	97.98 214	85.46 227	94.18 195	96.95 192

WR-MVS		88.38 240	87.67 240	90.52 272	93.30 298	80.18 268	93.26 289	95.96 184	88.57 117	85.47 297	92.81 292	76.12 218	96.91 327	81.24 305	82.29 390	94.47 314

v8		87.50 274	86.71 266	89.89 308	91.37 375	79.40 307	94.50 191	95.38 239	84.81 257	83.60 355	91.33 344	76.05 219	97.42 273	82.84 270	80.51 421	92.84 394

v148		87.04 296	86.32 285	89.21 342	90.94 395	77.26 370	93.71 265	94.43 305	84.84 256	84.36 334	90.80 366	76.04 220	97.05 317	82.12 284	79.60 430	93.31 371

mamba_0408		89.06 220	87.92 234	92.50 152	94.76 194	82.66 171	79.84 500	94.64 297	85.18 238	88.96 213	95.00 196	76.00 221	97.98 214	83.74 257	93.15 233	96.85 201

SSM_04072		88.57 237	87.92 234	90.51 273	94.76 194	82.66 171	79.84 500	94.64 297	85.18 238	88.96 213	95.00 196	76.00 221	92.03 467	83.74 257	93.15 233	96.85 201

eth_miper_zixun_eth		86.50 319	85.77 310	88.68 358	91.94 352	75.81 394	90.47 394	94.89 280	82.05 326	84.05 342	90.46 376	75.96 223	96.77 331	82.76 273	79.36 432	93.46 367

3Dnovator+	87.14 4	92.42 106	91.37 129	95.55 7	95.63 144	88.73 7	97.07 23	96.77 93	90.84 27	84.02 343	96.62 96	75.95 224	99.34 43	87.77 190	97.68 98	98.59 29

balanced_ft_v1		92.23 109	92.05 108	92.77 127	95.40 155	81.78 204	95.80 96	95.69 212	87.94 145	91.92 132	95.04 194	75.91 225	98.71 124	93.83 60	96.94 114	97.82 123

h-mvs33		90.80 154	90.15 162	92.75 132	96.01 122	82.66 171	95.43 123	95.53 226	89.80 64	93.08 92	95.64 159	75.77 226	99.00 81	92.07 102	78.05 437	96.60 214

hse-mvs2		89.88 190	89.34 189	91.51 221	94.83 190	81.12 228	93.94 246	93.91 330	89.80 64	93.08 92	93.60 265	75.77 226	97.66 242	92.07 102	77.07 445	95.74 256

BH-untuned		88.60 234	88.13 228	90.01 304	95.24 164	78.50 331	93.29 287	94.15 320	84.75 259	84.46 328	93.40 269	75.76 228	97.40 281	77.59 366	94.52 183	94.12 325

DIV-MVS_self_test		86.53 317	85.78 308	88.75 355	92.02 351	76.45 385	90.74 385	94.30 312	81.83 338	83.34 364	90.82 365	75.75 229	96.57 354	81.73 297	81.52 402	93.24 375

BH-w/o		87.57 270	87.05 255	89.12 345	94.90 186	77.90 350	92.41 326	93.51 347	82.89 309	83.70 351	91.34 343	75.75 229	97.07 314	75.49 387	93.49 220	92.39 415

cl____		86.52 318	85.78 308	88.75 355	92.03 350	76.46 384	90.74 385	94.30 312	81.83 338	83.34 364	90.78 367	75.74 231	96.57 354	81.74 296	81.54 401	93.22 376

cdsmvs_eth3d_5k		22.14 498	29.52 494	0.00 542	0.00 566	0.00 569	0.00 554	95.76 202	0.00 561	0.00 562	94.29 234	75.66 232	0.00 562	0.00 561	0.00 561	0.00 558

CNLPA		89.07 219	87.98 231	92.34 166	96.87 85	84.78 90	94.08 232	93.24 352	81.41 349	84.46 328	95.13 192	75.57 233	96.62 344	77.21 370	93.84 205	95.61 263

CHOSEN 1792x2688		88.84 226	87.69 239	92.30 172	96.14 110	81.42 217	90.01 409	95.86 196	74.52 445	87.41 246	93.94 250	75.46 234	98.36 162	80.36 321	95.53 152	97.12 178

CP-MVSNet		87.63 264	87.26 252	88.74 357	93.12 304	76.59 383	95.29 132	96.58 113	88.43 120	83.49 360	92.98 286	75.28 235	95.83 397	78.97 350	81.15 406	93.79 347

v10		87.25 284	86.38 281	89.85 310	91.19 381	79.50 300	94.48 192	95.45 233	83.79 281	83.62 354	91.19 349	75.13 236	97.42 273	81.94 290	80.60 416	92.63 401

Vis-MVSNet		91.75 123	91.23 134	93.29 90	95.32 158	83.78 124	96.14 64	95.98 180	89.89 57	90.45 176	96.58 98	75.09 237	98.31 170	84.75 237	96.90 117	97.78 126
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sss		88.93 225	88.26 226	90.94 254	94.05 260	80.78 248	91.71 356	95.38 239	81.55 347	88.63 220	93.91 254	75.04 238	95.47 415	82.47 276	91.61 262	96.57 217

v1144		87.61 267	86.79 264	90.06 299	91.01 390	79.34 311	93.95 245	95.42 238	83.36 294	85.66 288	91.31 347	74.98 239	97.42 273	83.37 261	82.06 392	93.42 368

miper_lstm_enhance		85.27 347	84.59 345	87.31 397	91.28 379	74.63 406	87.69 453	94.09 324	81.20 356	81.36 390	89.85 398	74.97 240	94.30 436	81.03 309	79.84 428	93.01 388

test_yl		90.69 159	90.02 169	92.71 136	95.72 138	82.41 183	94.11 227	95.12 259	85.63 222	91.49 147	94.70 210	74.75 241	98.42 158	86.13 217	92.53 253	97.31 154

DCV-MVSNet		90.69 159	90.02 169	92.71 136	95.72 138	82.41 183	94.11 227	95.12 259	85.63 222	91.49 147	94.70 210	74.75 241	98.42 158	86.13 217	92.53 253	97.31 154

V42		87.68 259	86.86 259	90.15 292	90.58 411	80.14 270	94.24 219	95.28 250	83.66 283	85.67 287	91.33 344	74.73 243	97.41 279	84.43 246	81.83 396	92.89 392

FA-MVS(test-final)		89.66 195	88.91 205	91.93 195	94.57 217	80.27 265	91.36 367	94.74 292	84.87 254	89.82 195	92.61 299	74.72 244	98.47 148	83.97 252	93.53 218	97.04 184

viewdifsd2359ckpt11		89.43 205	89.05 199	90.56 266	92.89 321	77.00 374	92.81 313	94.52 301	87.03 182	89.77 196	95.79 150	74.67 245	97.51 256	88.97 172	84.98 357	97.17 169

viewmsd2359difaftdt		89.43 205	89.05 199	90.56 266	92.89 321	77.00 374	92.81 313	94.52 301	87.03 182	89.77 196	95.79 150	74.67 245	97.51 256	88.97 172	84.98 357	97.17 169

XVG-OURS-SEG-HR		89.95 186	89.45 183	91.47 224	94.00 265	81.21 224	91.87 351	96.06 175	85.78 217	88.55 221	95.73 155	74.67 245	97.27 296	88.71 178	89.64 300	95.91 246

BP-MVS1		92.48 103	92.07 107	93.72 80	94.50 223	84.39 107	95.90 89	94.30 312	90.39 42	92.67 110	95.94 135	74.46 248	98.65 129	93.14 72	97.35 105	98.13 79

v2v482		87.84 254	87.06 254	90.17 290	90.99 391	79.23 318	94.00 242	95.13 258	84.87 254	85.53 292	92.07 321	74.45 249	97.45 267	84.71 242	81.75 398	93.85 344

CLD-MVS		89.47 202	88.90 206	91.18 238	94.22 251	82.07 192	92.13 344	96.09 171	87.90 149	85.37 307	92.45 303	74.38 250	97.56 252	87.15 202	90.43 282	93.93 336
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XXY-MVS		87.65 261	86.85 260	90.03 301	92.14 345	80.60 258	93.76 259	95.23 252	82.94 307	84.60 322	94.02 245	74.27 251	95.49 414	81.04 307	83.68 372	94.01 333

HQP_MVS		90.60 167	90.19 160	91.82 205	94.70 204	82.73 167	95.85 93	96.22 148	90.81 28	86.91 255	94.86 204	74.23 252	98.12 181	88.15 182	89.99 289	94.63 298

plane_prior6					94.52 220	82.75 164						74.23 252

v144192		87.19 290	86.35 283	89.74 318	90.64 409	78.24 340	93.92 248	95.43 236	81.93 331	85.51 294	91.05 358	74.21 254	97.45 267	82.86 269	81.56 400	93.53 362

VPA-MVSNet		89.62 196	88.96 202	91.60 215	93.86 272	82.89 162	95.46 121	97.33 33	87.91 148	88.43 224	93.31 273	74.17 255	97.40 281	87.32 200	82.86 385	94.52 306

ab-mvs		89.41 207	88.35 220	92.60 144	95.15 170	82.65 175	92.20 342	95.60 220	83.97 275	88.55 221	93.70 264	74.16 256	98.21 176	82.46 277	89.37 303	96.94 194

1314		87.51 272	86.57 275	90.34 286	92.42 339	79.74 294	92.63 320	95.35 244	78.35 396	80.14 406	91.62 338	74.05 257	97.15 305	81.05 306	93.53 218	94.12 325

test_djsdf		89.03 222	88.64 211	90.21 289	90.74 406	79.28 315	95.96 83	95.90 190	84.66 263	85.33 309	92.94 287	74.02 258	97.30 291	89.64 162	88.53 315	94.05 331

cl22		86.78 306	85.98 300	89.18 344	92.34 340	77.62 365	90.84 384	94.13 322	81.33 351	83.97 345	90.15 387	73.96 259	96.60 351	84.19 248	82.94 381	93.33 370

SD_0403		84.71 360	84.65 342	84.92 440	92.95 318	65.95 478	92.07 348	93.23 353	83.82 280	79.03 425	93.73 263	73.90 260	92.91 460	63.02 473	90.05 288	95.89 248

AdaColmap		89.89 189	89.07 197	92.37 162	97.41 72	83.03 156	94.42 199	95.92 187	82.81 310	86.34 272	94.65 217	73.89 261	99.02 74	80.69 315	95.51 153	95.05 280

HyFIR lowres test		88.09 249	86.81 262	91.93 195	96.00 123	80.63 251	90.01 409	95.79 200	73.42 457	87.68 241	92.10 318	73.86 262	97.96 218	80.75 314	91.70 261	97.19 168

HQP2-MVS												73.83 263

HQP-MVS		89.80 192	89.28 192	91.34 231	94.17 254	81.56 208	94.39 206	96.04 176	88.81 105	85.43 301	93.97 249	73.83 263	97.96 218	87.11 204	89.77 298	94.50 309

3Dnovator	86.66 5	91.73 125	90.82 146	94.44 50	94.59 213	86.37 43	97.18 17	97.02 63	89.20 89	84.31 338	96.66 91	73.74 265	99.17 58	86.74 207	97.96 84	97.79 125

EPNet_dtu		86.49 321	85.94 303	88.14 375	90.24 421	72.82 428	94.11 227	92.20 383	86.66 196	79.42 420	92.36 306	73.52 266	95.81 399	71.26 420	93.66 213	95.80 254
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		84.43 364	83.06 372	88.54 361	91.72 362	78.44 332	95.18 145	92.82 366	82.73 312	79.67 417	92.12 315	73.49 267	95.96 390	71.10 425	68.73 482	91.21 443

Effi-MVS+-dtu		88.65 232	88.35 220	89.54 332	93.33 297	76.39 386	94.47 195	94.36 310	87.70 159	85.43 301	89.56 404	73.45 268	97.26 298	85.57 225	91.28 266	94.97 282

GDP-MVS		92.04 111	91.46 126	93.75 79	94.55 219	84.69 92	95.60 118	96.56 115	87.83 154	93.07 94	95.89 139	73.44 269	98.65 129	90.22 147	96.03 141	97.91 112

baseline2		86.50 319	85.39 322	89.84 311	91.12 386	76.70 381	91.88 350	88.58 465	82.35 319	79.95 411	90.95 360	73.42 270	97.63 246	80.27 324	89.95 292	95.19 274

PEN-MVS		86.80 305	86.27 288	88.40 364	92.32 341	75.71 396	95.18 145	96.38 128	87.97 143	82.82 371	93.15 280	73.39 271	95.92 392	76.15 383	79.03 435	93.59 360

v1192		87.25 284	86.33 284	90.00 305	90.76 405	79.04 319	93.80 257	95.48 228	82.57 314	85.48 296	91.18 351	73.38 272	97.42 273	82.30 280	82.06 392	93.53 362

guyue		91.12 147	90.84 145	91.96 192	94.59 213	80.57 259	94.87 164	93.71 343	88.96 102	91.14 157	95.22 183	73.22 273	97.76 234	92.01 106	93.81 206	97.54 146

QAPM		89.51 200	88.15 227	93.59 84	94.92 183	84.58 94	96.82 34	96.70 104	78.43 395	83.41 362	96.19 115	73.18 274	99.30 49	77.11 372	96.54 128	96.89 198

tpmrst		85.35 344	84.99 332	86.43 420	90.88 400	67.88 472	88.71 433	91.43 410	80.13 366	86.08 278	88.80 418	73.05 275	96.02 386	82.48 275	83.40 378	95.40 267

PS-CasMVS		87.32 281	86.88 258	88.63 360	92.99 316	76.33 388	95.33 127	96.61 111	88.22 129	83.30 366	93.07 284	73.03 276	95.79 401	78.36 356	81.00 412	93.75 354

DTE-MVSNet		86.11 328	85.48 320	87.98 378	91.65 367	74.92 403	94.93 160	95.75 203	87.36 171	82.26 377	93.04 285	72.85 277	95.82 398	74.04 403	77.46 441	93.20 378

MVSTER		88.84 226	88.29 224	90.51 273	92.95 318	80.44 262	93.73 262	95.01 265	84.66 263	87.15 250	93.12 282	72.79 278	97.21 303	87.86 188	87.36 337	93.87 341

v1921920		86.97 298	86.06 297	89.69 323	90.53 414	78.11 343	93.80 257	95.43 236	81.90 333	85.33 309	91.05 358	72.66 279	97.41 279	82.05 288	81.80 397	93.53 362

DP-MVS		87.25 284	85.36 324	92.90 118	97.65 65	83.24 142	94.81 170	92.00 390	74.99 440	81.92 384	95.00 196	72.66 279	99.05 68	66.92 456	92.33 256	96.40 221

VortexMVS		88.42 238	88.01 230	89.63 329	93.89 271	78.82 321	93.82 255	95.47 229	86.67 195	84.53 326	91.99 324	72.62 281	96.65 338	89.02 171	84.09 366	93.41 369

v7n		86.81 304	85.76 311	89.95 306	90.72 407	79.25 317	95.07 151	95.92 187	84.45 266	82.29 376	90.86 362	72.60 282	97.53 254	79.42 346	80.52 420	93.08 386

OPM-MVS		90.12 176	89.56 181	91.82 205	93.14 303	83.90 120	94.16 222	95.74 204	88.96 102	87.86 234	95.43 172	72.48 283	97.91 224	88.10 186	90.18 287	93.65 359
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
LS3D		87.89 253	86.32 285	92.59 145	96.07 119	82.92 161	95.23 137	94.92 279	75.66 432	82.89 370	95.98 132	72.48 283	99.21 56	68.43 444	95.23 165	95.64 260

pm-mvs1		86.61 313	85.54 318	89.82 312	91.44 370	80.18 268	95.28 134	94.85 284	83.84 278	81.66 385	92.62 298	72.45 285	96.48 362	79.67 334	78.06 436	92.82 395

KinetiMVS		91.82 115	91.30 131	93.39 87	94.72 201	83.36 139	95.45 122	96.37 129	90.33 44	92.17 122	96.03 129	72.32 286	98.75 118	87.94 187	96.34 133	98.07 84

usedtu_dtu_shiyan1		86.84 302	85.61 316	90.53 268	90.50 415	81.80 202	90.97 380	94.96 272	83.05 301	83.50 358	90.32 379	72.15 287	96.65 338	79.49 340	85.55 351	93.15 382

FE-MVSNET3		86.84 302	85.61 316	90.53 268	90.50 415	81.80 202	90.97 380	94.96 272	83.05 301	83.50 358	90.32 379	72.15 287	96.65 338	79.49 340	85.55 351	93.15 382

PMMVS		85.71 337	84.96 334	87.95 379	88.90 440	77.09 372	88.68 434	90.06 444	72.32 467	86.47 265	90.76 368	72.15 287	94.40 432	81.78 295	93.49 220	92.36 416

SDMVSNet		90.19 175	89.61 180	91.93 195	96.00 123	83.09 153	92.89 308	95.98 180	88.73 109	86.85 259	95.20 187	72.09 290	97.08 312	88.90 174	89.85 295	95.63 261

PatchmatchNet		85.85 333	84.70 341	89.29 341	91.76 361	75.54 397	88.49 438	91.30 412	81.63 344	85.05 314	88.70 421	71.71 291	96.24 378	74.61 400	89.05 310	96.08 239
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												71.70 292				96.12 236

patchmatchnet-post											83.76 469	71.53 293	96.48 362

v1240		86.78 306	85.85 306	89.56 331	90.45 418	77.79 356	93.61 270	95.37 242	81.65 342	85.43 301	91.15 353	71.50 294	97.43 271	81.47 301	82.05 394	93.47 366

anonymousdsp		87.84 254	87.09 253	90.12 294	89.13 437	80.54 260	94.67 181	95.55 223	82.05 326	83.82 347	92.12 315	71.47 295	97.15 305	87.15 202	87.80 332	92.67 399

Patchmatch-test		81.37 408	79.30 414	87.58 388	90.92 397	74.16 413	80.99 495	87.68 472	70.52 475	76.63 450	88.81 416	71.21 296	92.76 462	60.01 483	86.93 343	95.83 252

F-COLMAP		87.95 252	86.80 263	91.40 228	96.35 105	80.88 240	94.73 177	95.45 233	79.65 373	82.04 382	94.61 219	71.13 297	98.50 143	76.24 382	91.05 272	94.80 295

pmmvs4		85.43 341	83.86 359	90.16 291	90.02 426	82.97 160	90.27 396	92.67 370	75.93 431	80.73 397	91.74 332	71.05 298	95.73 404	78.85 353	83.46 376	91.78 427

CR-MVSNet		85.35 344	83.76 360	90.12 294	90.58 411	79.34 311	85.24 476	91.96 394	78.27 398	85.55 290	87.87 434	71.03 299	95.61 407	73.96 405	89.36 304	95.40 267

Patchmtry		82.71 384	80.93 388	88.06 376	90.05 425	76.37 387	84.74 482	91.96 394	72.28 468	81.32 391	87.87 434	71.03 299	95.50 413	68.97 440	80.15 423	92.32 418

CL-MVSNet_self_test		81.74 399	80.53 389	85.36 433	85.96 468	72.45 437	90.25 398	93.07 358	81.24 354	79.85 414	87.29 440	70.93 301	92.52 463	66.95 453	69.23 472	91.11 447

RPMNet		83.95 372	81.53 383	91.21 236	90.58 411	79.34 311	85.24 476	96.76 94	71.44 471	85.55 290	82.97 477	70.87 302	98.91 98	61.01 478	89.36 304	95.40 267

Patchmatch-RL test		81.67 400	79.96 404	86.81 414	85.42 476	71.23 449	82.17 493	87.50 474	78.47 393	77.19 445	82.50 484	70.81 303	93.48 451	82.66 274	72.89 456	95.71 259

CostFormer		85.77 336	84.94 335	88.26 371	91.16 384	72.58 436	89.47 421	91.04 419	76.26 427	86.45 268	89.97 394	70.74 304	96.86 330	82.35 279	87.07 342	95.34 271

AstraMVS		90.69 159	90.30 158	91.84 204	93.81 275	79.85 289	94.76 175	92.39 375	88.96 102	91.01 168	95.87 143	70.69 305	97.94 221	92.49 84	92.70 245	97.73 129

sam_mvs												70.60 306

xiu_mvs_v1_base_debu		90.64 164	90.05 166	92.40 158	93.97 267	84.46 101	93.32 282	95.46 230	85.17 240	92.25 118	94.03 242	70.59 307	98.57 140	90.97 128	94.67 175	94.18 321

xiu_mvs_v1_base		90.64 164	90.05 166	92.40 158	93.97 267	84.46 101	93.32 282	95.46 230	85.17 240	92.25 118	94.03 242	70.59 307	98.57 140	90.97 128	94.67 175	94.18 321

xiu_mvs_v1_base_debi		90.64 164	90.05 166	92.40 158	93.97 267	84.46 101	93.32 282	95.46 230	85.17 240	92.25 118	94.03 242	70.59 307	98.57 140	90.97 128	94.67 175	94.18 321

test_post											10.29 555	70.57 310	95.91 394

CANet_DTU		90.26 174	89.41 187	92.81 123	93.46 294	83.01 158	93.48 274	94.47 304	89.43 79	87.76 240	94.23 239	70.54 311	99.03 71	84.97 232	96.39 132	96.38 222

BH-RMVSNet		88.37 241	87.48 244	91.02 247	95.28 160	79.45 303	92.89 308	93.07 358	85.45 232	86.91 255	94.84 207	70.35 312	97.76 234	73.97 404	94.59 180	95.85 250

Fast-Effi-MVS+-dtu		87.44 275	86.72 265	89.63 329	92.04 349	77.68 364	94.03 237	93.94 326	85.81 216	82.42 375	91.32 346	70.33 313	97.06 315	80.33 323	90.23 286	94.14 324

MDTV_nov1_ep13_2view						55.91 510	87.62 455		73.32 458	84.59 323		70.33 313		74.65 398		95.50 264

ACMM	84.12 9	89.14 215	88.48 219	91.12 239	94.65 208	81.22 223	95.31 128	96.12 168	85.31 237	85.92 281	94.34 230	70.19 315	98.06 197	85.65 223	88.86 312	94.08 329
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
RRT-MVS		90.85 153	90.70 150	91.30 233	94.25 249	76.83 378	94.85 167	96.13 167	89.04 96	90.23 183	94.88 202	70.15 316	98.72 122	91.86 114	94.88 170	98.34 49

LuminaMVS		90.55 168	89.81 173	92.77 127	92.78 327	84.21 111	94.09 231	94.17 319	85.82 215	91.54 145	94.14 241	69.93 317	97.92 223	91.62 118	94.21 194	96.18 232

ET-MVSNet_ETH3D		87.51 272	85.91 304	92.32 168	93.70 286	83.93 119	92.33 334	90.94 424	84.16 270	72.09 476	92.52 301	69.90 318	95.85 396	89.20 168	88.36 321	97.17 169

LPG-MVS_test		89.45 203	88.90 206	91.12 239	94.47 227	81.49 212	95.30 130	96.14 164	86.73 193	85.45 298	95.16 189	69.89 319	98.10 183	87.70 191	89.23 307	93.77 352

LGP-MVS_train				91.12 239	94.47 227	81.49 212		96.14 164	86.73 193	85.45 298	95.16 189	69.89 319	98.10 183	87.70 191	89.23 307	93.77 352

CHOSEN 280x420		85.15 349	83.99 357	88.65 359	92.47 336	78.40 334	79.68 502	92.76 367	74.90 442	81.41 389	89.59 402	69.85 321	95.51 411	79.92 330	95.29 162	92.03 423

LTVRE_ROB	82.13 13	86.26 326	84.90 336	90.34 286	94.44 231	81.50 210	92.31 337	94.89 280	83.03 303	79.63 418	92.67 296	69.69 322	97.79 232	71.20 421	86.26 346	91.72 428
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	88.74 230	87.29 249	93.08 105	92.70 331	85.39 79	96.57 40	96.43 123	78.74 389	80.85 395	96.07 125	69.64 323	99.01 76	78.01 362	96.65 126	94.83 293

MonoMVSNet		86.89 301	86.55 276	87.92 381	89.46 435	73.75 415	94.12 225	93.10 356	87.82 155	85.10 312	90.76 368	69.59 324	94.94 426	86.47 211	82.50 387	95.07 278

MDTV_nov1_ep13			83.56 363		91.69 365	69.93 462	87.75 452	91.54 405	78.60 391	84.86 317	88.90 414	69.54 325	96.03 385	70.25 431	88.93 311

dtuonly		84.33 366	84.48 348	83.87 450	86.63 462	63.54 490	86.79 462	91.48 408	78.02 403	83.20 367	93.56 266	69.53 326	94.11 439	79.08 349	92.02 260	93.97 335

AUN-MVS		87.78 257	86.54 277	91.48 223	94.82 191	81.05 231	93.91 250	93.93 327	83.00 304	86.93 253	93.53 267	69.50 327	97.67 240	86.14 215	77.12 444	95.73 258

PatchT		82.68 385	81.27 385	86.89 412	90.09 424	70.94 455	84.06 485	90.15 441	74.91 441	85.63 289	83.57 472	69.37 328	94.87 427	65.19 462	88.50 317	94.84 292

VPNet		88.20 246	87.47 245	90.39 282	93.56 291	79.46 302	94.04 236	95.54 225	88.67 112	86.96 252	94.58 223	69.33 329	97.15 305	84.05 251	80.53 419	94.56 304

ACMP	84.23 8	89.01 224	88.35 220	90.99 250	94.73 199	81.27 220	95.07 151	95.89 192	86.48 198	83.67 352	94.30 233	69.33 329	97.99 211	87.10 206	88.55 314	93.72 357
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_post1							88.00 447				9.81 556	69.31 331	95.53 409	76.65 375

tpmvs		83.35 380	82.07 379	87.20 404	91.07 388	71.00 454	88.31 441	91.70 398	78.91 381	80.49 402	87.18 443	69.30 332	97.08 312	68.12 448	83.56 374	93.51 365

mvsmamba		90.33 171	89.69 177	92.25 179	95.17 167	81.64 207	95.27 135	93.36 350	84.88 253	89.51 201	94.27 237	69.29 333	97.42 273	89.34 165	96.12 139	97.68 132

thres200		87.21 288	86.24 289	90.12 294	95.36 156	78.53 329	93.26 289	92.10 386	86.42 201	88.00 233	91.11 355	69.24 334	98.00 210	69.58 438	91.04 274	93.83 346

tfpn200view9		87.58 269	86.64 270	90.41 281	95.99 126	78.64 325	94.58 186	91.98 392	86.94 187	88.09 228	91.77 330	69.18 335	98.10 183	70.13 434	91.10 267	94.48 312

thres400		87.62 266	86.64 270	90.57 264	95.99 126	78.64 325	94.58 186	91.98 392	86.94 187	88.09 228	91.77 330	69.18 335	98.10 183	70.13 434	91.10 267	94.96 285

WB-MVSnew		83.77 375	83.28 366	85.26 436	91.48 369	71.03 452	91.89 349	87.98 468	78.91 381	84.78 318	90.22 383	69.11 337	94.02 441	64.70 466	90.44 281	90.71 451

tfpnnormal		84.72 359	83.23 368	89.20 343	92.79 326	80.05 277	94.48 192	95.81 198	82.38 317	81.08 393	91.21 348	69.01 338	96.95 324	61.69 476	80.59 417	90.58 456

thres100view900		87.63 264	86.71 266	90.38 284	96.12 112	78.55 328	95.03 155	91.58 403	87.15 176	88.06 231	92.29 309	68.91 339	98.10 183	70.13 434	91.10 267	94.48 312

thres600view7		87.65 261	86.67 269	90.59 263	96.08 118	78.72 322	94.88 163	91.58 403	87.06 181	88.08 230	92.30 308	68.91 339	98.10 183	70.05 437	91.10 267	94.96 285

PatchMatch-RL		86.77 309	85.54 318	90.47 279	95.88 131	82.71 169	90.54 391	92.31 379	79.82 371	84.32 336	91.57 342	68.77 341	96.39 370	73.16 410	93.48 222	92.32 418

XVG-OURS		89.40 209	88.70 210	91.52 219	94.06 259	81.46 215	91.27 372	96.07 173	86.14 210	88.89 216	95.77 153	68.73 342	97.26 298	87.39 198	89.96 291	95.83 252

TR-MVS		86.78 306	85.76 311	89.82 312	94.37 235	78.41 333	92.47 325	92.83 364	81.11 357	86.36 270	92.40 304	68.73 342	97.48 262	73.75 408	89.85 295	93.57 361

tpm		84.73 358	84.02 356	86.87 413	90.33 419	68.90 466	89.06 428	89.94 448	80.85 359	85.75 285	89.86 397	68.54 344	95.97 389	77.76 364	84.05 367	95.75 255

FMVSNet3		87.40 277	86.11 294	91.30 233	93.79 278	83.64 129	94.20 221	94.81 288	83.89 277	84.37 331	91.87 329	68.45 345	96.56 356	78.23 359	85.36 353	93.70 358

MVP-Stereo		85.97 330	84.86 338	89.32 340	90.92 397	82.19 188	92.11 345	94.19 317	78.76 388	78.77 433	91.63 337	68.38 346	96.56 356	75.01 394	93.95 200	89.20 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		81.96 393	80.27 395	87.01 407	91.09 387	71.02 453	87.38 458	91.53 406	66.25 489	80.17 404	86.35 455	68.22 347	96.15 382	69.16 439	82.29 390	93.86 343

dmvs_testset		74.57 451	75.81 448	70.86 482	87.72 457	40.47 524	87.05 461	77.90 506	82.75 311	71.15 482	85.47 462	67.98 348	84.12 505	45.26 506	76.98 446	88.00 483

sd_testset		88.59 235	87.85 237	90.83 257	96.00 123	80.42 263	92.35 331	94.71 293	88.73 109	86.85 259	95.20 187	67.31 349	96.43 368	79.64 335	89.85 295	95.63 261

tpm2		84.08 369	82.94 373	87.48 392	91.39 374	71.27 448	89.23 425	90.37 436	71.95 469	84.64 321	89.33 406	67.30 350	96.55 358	75.17 391	87.09 341	94.63 298

test-LLR		85.87 332	85.41 321	87.25 400	90.95 393	71.67 445	89.55 417	89.88 451	83.41 291	84.54 324	87.95 431	67.25 351	95.11 422	81.82 293	93.37 226	94.97 282

test0.0.03 1		82.41 390	81.69 381	84.59 443	88.23 449	72.89 427	90.24 400	87.83 470	83.41 291	79.86 413	89.78 399	67.25 351	88.99 492	65.18 463	83.42 377	91.90 426

CVMVSNet		84.69 361	84.79 340	84.37 445	91.84 357	64.92 485	93.70 266	91.47 409	66.19 490	86.16 277	95.28 180	67.18 353	93.33 453	80.89 312	90.42 283	94.88 291

thisisatest0515		87.33 280	85.99 299	91.37 230	93.49 292	79.55 299	90.63 388	89.56 458	80.17 365	87.56 244	90.86 362	67.07 354	98.28 171	81.50 300	93.02 237	96.29 226

tttt0517		88.61 233	87.78 238	91.11 242	94.96 180	77.81 354	95.35 126	89.69 453	85.09 248	88.05 232	94.59 222	66.93 355	98.48 145	83.27 263	92.13 258	97.03 185

our_test_3		81.93 395	80.46 393	86.33 422	88.46 445	73.48 420	88.46 439	91.11 415	76.46 421	76.69 449	88.25 427	66.89 356	94.36 434	68.75 441	79.08 434	91.14 445

thisisatest0530		88.67 231	87.61 241	91.86 201	94.87 187	80.07 275	94.63 184	89.90 450	84.00 274	88.46 223	93.78 259	66.88 357	98.46 149	83.30 262	92.65 246	97.06 182

IterMVS-SCA-FT		85.45 340	84.53 347	88.18 374	91.71 363	76.87 377	90.19 404	92.65 371	85.40 235	81.44 388	90.54 373	66.79 358	95.00 425	81.04 307	81.05 408	92.66 400

SCA		86.32 325	85.18 329	89.73 320	92.15 344	76.60 382	91.12 376	91.69 399	83.53 288	85.50 295	88.81 416	66.79 358	96.48 362	76.65 375	90.35 284	96.12 236

D2MVS		85.90 331	85.09 331	88.35 366	90.79 402	77.42 367	91.83 353	95.70 210	80.77 360	80.08 408	90.02 392	66.74 360	96.37 371	81.88 292	87.97 327	91.26 442

IterMVS		84.88 355	83.98 358	87.60 387	91.44 370	76.03 390	90.18 405	92.41 374	83.24 297	81.06 394	90.42 378	66.60 361	94.28 437	79.46 342	80.98 413	92.48 409
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
GBi-Net		87.26 282	85.98 300	91.08 243	94.01 262	83.10 150	95.14 148	94.94 274	83.57 285	84.37 331	91.64 334	66.59 362	96.34 374	78.23 359	85.36 353	93.79 347

test1		87.26 282	85.98 300	91.08 243	94.01 262	83.10 150	95.14 148	94.94 274	83.57 285	84.37 331	91.64 334	66.59 362	96.34 374	78.23 359	85.36 353	93.79 347

FMVSNet2		87.19 290	85.82 307	91.30 233	94.01 262	83.67 127	94.79 172	94.94 274	83.57 285	83.88 346	92.05 322	66.59 362	96.51 360	77.56 367	85.01 356	93.73 356

IMVS_0404		87.60 268	86.84 261	89.89 308	93.72 280	77.75 359	88.56 436	95.34 245	85.53 228	79.98 410	94.49 225	66.54 365	94.64 428	84.75 237	92.65 246	97.28 157

EPMVS		83.90 374	82.70 378	87.51 389	90.23 422	72.67 431	88.62 435	81.96 494	81.37 350	85.01 315	88.34 425	66.31 366	94.45 429	75.30 390	87.12 340	95.43 266

Syy-MVS		80.07 424	79.78 406	80.94 464	91.92 353	59.93 500	89.75 415	87.40 475	81.72 340	78.82 430	87.20 441	66.29 367	91.29 477	47.06 505	87.84 330	91.60 431

ppachtmachnet_test		81.84 396	80.07 400	87.15 405	88.46 445	74.43 410	89.04 429	92.16 385	75.33 436	77.75 441	88.99 412	66.20 368	95.37 417	65.12 464	77.60 439	91.65 429

MDA-MVSNet_test_wron		79.21 435	77.19 437	85.29 434	88.22 450	72.77 429	85.87 470	90.06 444	74.34 446	62.62 496	87.56 437	66.14 369	91.99 470	66.90 457	73.01 454	91.10 448

YYNet1		79.22 434	77.20 436	85.28 435	88.20 451	72.66 432	85.87 470	90.05 446	74.33 447	62.70 494	87.61 436	66.09 370	92.03 467	66.94 454	72.97 455	91.15 444

JIA-IIPM		81.04 411	78.98 423	87.25 400	88.64 441	73.48 420	81.75 494	89.61 457	73.19 459	82.05 381	73.71 504	66.07 371	95.87 395	71.18 423	84.60 361	92.41 413

MSDG		84.86 356	83.09 370	90.14 293	93.80 276	80.05 277	89.18 426	93.09 357	78.89 383	78.19 435	91.91 327	65.86 372	97.27 296	68.47 443	88.45 318	93.11 384

FE-MVS		87.40 277	86.02 298	91.57 217	94.56 218	79.69 297	90.27 396	93.72 342	80.57 361	88.80 217	91.62 338	65.32 373	98.59 139	74.97 395	94.33 190	96.44 220

jajsoiax		88.24 245	87.50 243	90.48 276	90.89 399	80.14 270	95.31 128	95.65 217	84.97 251	84.24 339	94.02 245	65.31 374	97.42 273	88.56 179	88.52 316	93.89 337

cascas		86.43 323	84.98 333	90.80 260	92.10 348	80.92 238	90.24 400	95.91 189	73.10 460	83.57 356	88.39 424	65.15 375	97.46 266	84.90 235	91.43 264	94.03 332

ADS-MVSNet2		81.66 401	79.71 409	87.50 390	91.35 376	74.19 412	83.33 488	88.48 466	72.90 462	82.24 378	85.77 460	64.98 376	93.20 456	64.57 467	83.74 370	95.12 276

ADS-MVSNet		81.56 403	79.78 406	86.90 411	91.35 376	71.82 441	83.33 488	89.16 464	72.90 462	82.24 378	85.77 460	64.98 376	93.76 447	64.57 467	83.74 370	95.12 276

blended_shiyan6		82.78 382	80.48 392	89.67 328	85.53 473	79.76 292	91.37 366	93.82 334	77.14 411	79.30 423	83.73 470	64.96 378	96.63 341	79.68 333	68.75 478	92.63 401

blended_shiyan8		82.79 381	80.49 391	89.69 323	85.50 475	79.83 291	91.38 365	93.82 334	77.14 411	79.39 421	83.73 470	64.95 379	96.63 341	79.75 331	68.77 477	92.62 403

Elysia		90.12 176	89.10 195	93.18 97	93.16 301	84.05 116	95.22 139	96.27 138	85.16 243	90.59 173	94.68 212	64.64 380	98.37 160	86.38 213	95.77 146	97.12 178

StellarMVS		90.12 176	89.10 195	93.18 97	93.16 301	84.05 116	95.22 139	96.27 138	85.16 243	90.59 173	94.68 212	64.64 380	98.37 160	86.38 213	95.77 146	97.12 178

pmmvs5		84.21 367	82.84 377	88.34 368	88.95 439	76.94 376	92.41 326	91.91 396	75.63 433	80.28 403	91.18 351	64.59 382	95.57 408	77.09 373	83.47 375	92.53 408

PVSNet	78.82 18	85.55 338	84.65 342	88.23 373	94.72 201	71.93 439	87.12 460	92.75 368	78.80 387	84.95 316	90.53 374	64.43 383	96.71 335	74.74 397	93.86 203	96.06 242

dmvs_re		84.20 368	83.22 369	87.14 406	91.83 359	77.81 354	90.04 408	90.19 440	84.70 262	81.49 386	89.17 408	64.37 384	91.13 479	71.58 418	85.65 350	92.46 411

wanda-best-256-512		82.44 388	80.07 400	89.53 333	85.12 479	79.44 304	90.49 392	93.75 340	76.97 417	79.00 426	82.72 480	64.29 385	96.61 347	79.56 338	68.75 478	92.55 404

FE-blended-shiyan7		82.44 388	80.07 400	89.53 333	85.12 479	79.44 304	90.49 392	93.75 340	76.97 417	79.00 426	82.72 480	64.29 385	96.61 347	79.56 338	68.75 478	92.55 404

usedtu_blend_shiyan5		82.39 391	79.93 405	89.75 317	85.12 479	80.08 273	92.36 329	93.26 351	74.29 448	79.00 426	82.72 480	64.29 385	96.60 351	79.60 336	68.75 478	92.55 404

UGNet		89.95 186	88.95 203	92.95 116	94.51 221	83.31 140	95.70 106	95.23 252	89.37 81	87.58 243	93.94 250	64.00 388	98.78 115	83.92 253	96.31 134	96.74 208
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		67.92 461	67.49 462	69.21 487	81.09 496	41.17 523	88.03 446	78.00 505	73.50 456	62.63 495	83.11 476	63.94 389	86.52 496	25.66 525	51.45 505	79.94 498

RPSCF		85.07 350	84.27 349	87.48 392	92.91 320	70.62 457	91.69 358	92.46 373	76.20 429	82.67 373	95.22 183	63.94 389	97.29 294	77.51 368	85.80 348	94.53 305

mvs_tets		88.06 251	87.28 250	90.38 284	90.94 395	79.88 286	95.22 139	95.66 215	85.10 247	84.21 340	93.94 250	63.53 391	97.40 281	88.50 180	88.40 320	93.87 341

SSC-MVS		67.06 462	66.56 464	68.56 489	80.54 497	40.06 525	87.77 451	77.37 508	72.38 466	61.75 497	82.66 483	63.37 392	86.45 497	24.48 527	48.69 508	79.16 501

test1111		89.10 216	88.64 211	90.48 276	95.53 151	74.97 402	96.08 69	84.89 486	88.13 133	90.16 190	96.65 92	63.29 393	98.10 183	86.14 215	96.90 117	98.39 46

gbinet_0.2-2-1-0.02		82.59 386	80.19 398	89.77 316	85.23 478	80.05 277	91.59 361	93.52 346	77.60 405	79.78 415	82.87 479	63.26 394	96.45 366	78.93 351	68.97 474	92.81 396

Anonymous20231211		86.59 315	85.13 330	90.98 252	96.52 99	81.50 210	96.14 64	96.16 162	73.78 453	83.65 353	92.15 313	63.26 394	97.37 287	82.82 271	81.74 399	94.06 330

ECVR-MVS		89.09 218	88.53 214	90.77 261	95.62 145	75.89 392	96.16 60	84.22 488	87.89 151	90.20 184	96.65 92	63.19 396	98.10 183	85.90 220	96.94 114	98.33 51

dtuonlycased		79.67 429	79.05 422	81.54 462	88.34 448	68.44 468	88.96 431	90.65 433	78.48 392	73.21 473	85.88 459	63.18 397	91.00 481	70.40 429	72.32 457	85.19 488

SSC-MVS3.2		84.60 362	84.19 350	85.85 428	92.74 329	68.07 469	88.15 444	93.81 337	87.42 169	83.76 349	91.07 357	62.91 398	95.73 404	74.56 401	83.24 379	93.75 354

nomal-1		86.20 327	84.90 336	90.11 298	92.72 330	80.88 240	89.79 412	91.03 420	82.96 306	83.49 360	88.82 415	62.88 399	94.38 433	81.35 302	91.05 272	95.07 278

dp		81.47 407	80.23 396	85.17 437	89.92 428	65.49 482	86.74 464	90.10 443	76.30 426	81.10 392	87.12 444	62.81 400	95.92 392	68.13 447	79.88 426	94.09 328

LFMVS		90.08 179	89.13 194	92.95 116	96.71 88	82.32 186	96.08 69	89.91 449	86.79 190	92.15 124	96.81 85	62.60 401	98.34 165	87.18 201	93.90 202	98.19 73

Anonymous20231206		81.03 412	79.77 408	84.82 441	87.85 456	70.26 460	91.42 364	92.08 387	73.67 454	77.75 441	89.25 407	62.43 402	93.08 457	61.50 477	82.00 395	91.12 446

VDD-MVS		90.74 156	89.92 171	93.20 95	96.27 106	83.02 157	95.73 104	93.86 331	88.42 121	92.53 113	96.84 82	62.09 403	98.64 132	90.95 132	92.62 251	97.93 109

MS-PatchMatch		85.05 351	84.16 352	87.73 384	91.42 373	78.51 330	91.25 373	93.53 345	77.50 406	80.15 405	91.58 340	61.99 404	95.51 411	75.69 386	94.35 188	89.16 472

OurMVSNet-221017-0		85.35 344	84.64 344	87.49 391	90.77 404	72.59 435	94.01 240	94.40 308	84.72 260	79.62 419	93.17 279	61.91 405	96.72 333	81.99 289	81.16 404	93.16 380

WBMVS		84.97 354	84.18 351	87.34 395	94.14 258	71.62 447	90.20 403	92.35 376	81.61 345	84.06 341	90.76 368	61.82 406	96.52 359	78.93 351	83.81 368	93.89 337

test_vis1_n_1920		89.39 210	89.84 172	88.04 377	92.97 317	72.64 433	94.71 179	96.03 178	86.18 208	91.94 131	96.56 100	61.63 407	95.74 403	93.42 67	95.11 166	95.74 256

test20.03		79.95 426	79.08 420	82.55 456	85.79 470	67.74 474	91.09 377	91.08 416	81.23 355	74.48 466	89.96 395	61.63 407	90.15 484	60.08 481	76.38 447	89.76 463

mmtdpeth		85.04 353	84.15 353	87.72 385	93.11 305	75.74 395	94.37 210	92.83 364	84.98 250	89.31 206	86.41 453	61.61 409	97.14 308	92.63 83	62.11 494	90.29 457

DSMNet-mixed		76.94 445	76.29 443	78.89 469	83.10 490	56.11 509	87.78 450	79.77 498	60.65 498	75.64 458	88.71 420	61.56 410	88.34 493	60.07 482	89.29 306	92.21 421

Anonymous20240529		88.09 249	86.59 274	92.58 146	96.53 98	81.92 198	95.99 79	95.84 197	74.11 450	89.06 211	95.21 186	61.44 411	98.81 111	83.67 260	87.47 334	97.01 188

UBG		85.51 339	84.57 346	88.35 366	94.21 252	71.78 443	90.07 407	89.66 455	82.28 321	85.91 282	89.01 411	61.30 412	97.06 315	76.58 378	92.06 259	96.22 229

IB-MVS	80.51 15	85.24 348	83.26 367	91.19 237	92.13 346	79.86 287	91.75 355	91.29 413	83.28 296	80.66 399	88.49 423	61.28 413	98.46 149	80.99 310	79.46 431	95.25 273
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		86.61 313	85.27 327	90.66 262	91.33 378	78.71 324	90.40 395	93.81 337	85.34 236	85.12 311	89.57 403	61.25 414	97.11 310	80.99 310	89.59 301	96.15 233

N_pmnet		68.89 460	68.44 460	70.23 484	89.07 438	28.79 535	88.06 445	19.50 536	69.47 478	71.86 479	84.93 464	61.24 415	91.75 473	54.70 493	77.15 443	90.15 460

EU-MVSNet		81.32 409	80.95 387	82.42 459	88.50 444	63.67 489	93.32 282	91.33 411	64.02 494	80.57 401	92.83 290	61.21 416	92.27 466	76.34 380	80.38 422	91.32 440

testing91		87.11 294	86.18 290	89.92 307	94.43 232	75.38 401	91.53 362	92.27 381	86.48 198	86.50 264	90.24 382	61.19 417	97.53 254	82.10 285	90.88 277	96.84 204

FBQ-MVS		87.19 290	85.74 313	91.52 219	94.74 197	80.62 253	93.91 250	92.20 383	84.27 269	87.61 242	88.77 419	61.17 418	97.29 294	78.01 362	91.03 275	96.64 213

test_cas_vis1_n_1920		88.83 229	88.85 209	88.78 353	91.15 385	76.72 380	93.85 254	94.93 278	83.23 298	92.81 101	96.00 130	61.17 418	94.45 429	91.67 117	94.84 171	95.17 275

VDDNet		89.56 199	88.49 218	92.76 130	95.07 172	82.09 191	96.30 47	93.19 355	81.05 358	91.88 133	96.86 81	61.16 420	98.33 167	88.43 181	92.49 255	97.84 120

PVSNet_0	73.20 20	77.22 444	74.83 450	84.37 445	90.70 408	71.10 451	83.09 490	89.67 454	72.81 464	73.93 468	83.13 474	60.79 421	93.70 449	68.54 442	50.84 506	88.30 482

SixPastTwentyTwo		83.91 373	82.90 375	86.92 410	90.99 391	70.67 456	93.48 274	91.99 391	85.54 226	77.62 443	92.11 317	60.59 422	96.87 329	76.05 384	77.75 438	93.20 378

gg-mvs-nofinetune		81.77 398	79.37 412	88.99 350	90.85 401	77.73 363	86.29 467	79.63 499	74.88 443	83.19 368	69.05 511	60.34 423	96.11 383	75.46 388	94.64 179	93.11 384

MDA-MVSNet-bldmvs		78.85 437	76.31 442	86.46 418	89.76 430	73.88 414	88.79 432	90.42 435	79.16 379	59.18 499	88.33 426	60.20 424	94.04 440	62.00 475	68.96 475	91.48 437

pmmvs6		83.42 378	81.60 382	88.87 352	88.01 453	77.87 352	94.96 158	94.24 316	74.67 444	78.80 432	91.09 356	60.17 425	96.49 361	77.06 374	75.40 451	92.23 420

ACMH	80.38 17	85.36 343	83.68 361	90.39 282	94.45 230	80.63 251	94.73 177	94.85 284	82.09 324	77.24 444	92.65 297	60.01 426	97.58 250	72.25 415	84.87 359	92.96 389
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GG-mvs-BLEND				87.94 380	89.73 432	77.91 348	87.80 448	78.23 504		80.58 400	83.86 468	59.88 427	95.33 418	71.20 421	92.22 257	90.60 455

UniMVSNet_ETH3D		87.53 271	86.37 282	91.00 249	92.44 338	78.96 320	94.74 176	95.61 219	84.07 273	85.36 308	94.52 224	59.78 428	97.34 288	82.93 267	87.88 328	96.71 209

myMVS_eth3d28		85.80 335	85.26 328	87.42 394	94.73 199	69.92 463	90.60 389	90.95 423	87.21 175	86.06 279	90.04 391	59.47 429	96.02 386	74.89 396	93.35 228	96.33 223

pmmvs-eth3d		80.97 414	78.72 425	87.74 383	84.99 482	79.97 284	90.11 406	91.65 401	75.36 435	73.51 470	86.03 456	59.45 430	93.96 445	75.17 391	72.21 458	89.29 470

testing99		86.72 310	85.73 315	89.69 323	94.23 250	74.91 404	91.35 368	90.97 422	86.14 210	86.36 270	90.22 383	59.41 431	97.48 262	82.24 282	90.66 279	96.69 211

test_0402		81.30 410	79.17 418	87.67 386	93.19 300	78.17 341	92.98 304	91.71 397	75.25 437	76.02 456	90.31 381	59.23 432	96.37 371	50.22 500	83.63 373	88.47 481

KD-MVS_self_test		80.20 422	79.24 415	83.07 453	85.64 472	65.29 483	91.01 379	93.93 327	78.71 390	76.32 451	86.40 454	59.20 433	92.93 459	72.59 413	69.35 471	91.00 450

testing3-2		86.72 310	86.71 266	86.74 416	96.11 115	65.92 479	93.39 279	89.65 456	89.46 77	87.84 236	92.79 294	59.17 434	97.60 248	81.31 303	90.72 278	96.70 210

UWE-MVS-28		78.98 436	78.38 428	80.80 465	88.18 452	60.66 499	90.65 387	78.51 501	78.84 385	77.93 439	90.93 361	59.08 435	89.02 491	50.96 498	90.33 285	92.72 398

FMVSNet1		85.85 333	84.11 354	91.08 243	92.81 325	83.10 150	95.14 148	94.94 274	81.64 343	82.68 372	91.64 334	59.01 436	96.34 374	75.37 389	83.78 369	93.79 347

testing11		86.44 322	85.35 325	89.69 323	94.29 246	75.40 400	91.30 369	90.53 434	84.76 258	85.06 313	90.13 388	58.95 437	97.45 267	82.08 286	91.09 271	96.21 231

COLMAP_ROB	80.39 16	83.96 371	82.04 380	89.74 318	95.28 160	79.75 293	94.25 217	92.28 380	75.17 438	78.02 438	93.77 260	58.60 438	97.84 229	65.06 465	85.92 347	91.63 430
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	85.05 351	83.46 364	89.82 312	94.66 207	79.37 308	94.44 197	94.12 323	82.19 323	78.04 437	92.82 291	58.23 439	97.54 253	73.77 407	82.90 384	92.54 407

CMPMVS	59.16 21	80.52 418	79.20 417	84.48 444	83.98 485	67.63 475	89.95 411	93.84 333	64.79 493	66.81 490	91.14 354	57.93 440	95.17 420	76.25 381	88.10 323	90.65 452
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
reproduce_monomvs		86.37 324	85.87 305	87.87 382	93.66 288	73.71 416	93.44 277	95.02 264	88.61 115	82.64 374	91.94 326	57.88 441	96.68 336	89.96 152	79.71 429	93.22 376

FE-MVSNET2		81.82 397	79.99 403	87.34 395	84.74 483	77.36 369	92.72 317	94.55 299	82.09 324	73.79 469	86.46 450	57.80 442	94.45 429	74.65 398	73.10 453	90.20 458

tt0805		86.92 299	85.74 313	90.48 276	92.22 342	79.98 283	95.63 114	94.88 282	83.83 279	84.74 320	92.80 293	57.61 443	97.67 240	85.48 226	84.42 362	93.79 347

ITE_SJBPF				88.24 372	91.88 356	77.05 373		92.92 361	85.54 226	80.13 407	93.30 274	57.29 444	96.20 379	72.46 414	84.71 360	91.49 436

UWE-MVS		83.69 377	83.09 370	85.48 431	93.06 310	65.27 484	90.92 382	86.14 478	79.90 369	86.26 274	90.72 371	57.17 445	95.81 399	71.03 426	92.62 251	95.35 270

TESTMET0.1,1		83.74 376	82.85 376	86.42 421	89.96 427	71.21 450	89.55 417	87.88 469	77.41 407	83.37 363	87.31 439	56.71 446	93.65 450	80.62 317	92.85 243	94.40 315

UnsupCasMVSNet_eth		80.07 424	78.27 429	85.46 432	85.24 477	72.63 434	88.45 440	94.87 283	82.99 305	71.64 480	88.07 430	56.34 447	91.75 473	73.48 409	63.36 492	92.01 424

test_fmvs1		87.34 279	87.56 242	86.68 417	90.59 410	71.80 442	94.01 240	94.04 325	78.30 397	91.97 128	95.22 183	56.28 448	93.71 448	92.89 76	94.71 174	94.52 306

K. test v3		81.59 402	80.15 399	85.91 427	89.89 429	69.42 465	92.57 322	87.71 471	85.56 225	73.44 471	89.71 401	55.58 449	95.52 410	77.17 371	69.76 470	92.78 397

test-mter		84.54 363	83.64 362	87.25 400	90.95 393	71.67 445	89.55 417	89.88 451	79.17 378	84.54 324	87.95 431	55.56 450	95.11 422	81.82 293	93.37 226	94.97 282

FE-MVSNET		78.19 440	76.03 445	84.69 442	83.70 487	73.31 422	90.58 390	90.00 447	77.11 415	71.91 478	85.47 462	55.53 451	91.94 472	59.69 484	70.24 467	88.83 476

lessismore_v0				86.04 423	88.46 445	68.78 467		80.59 497		73.01 474	90.11 389	55.39 452	96.43 368	75.06 393	65.06 489	92.90 391

ETVMVS		84.43 364	82.92 374	88.97 351	94.37 235	74.67 405	91.23 374	88.35 467	83.37 293	86.06 279	89.04 410	55.38 453	95.67 406	67.12 452	91.34 265	96.58 216

MVS-HIRNet		73.70 452	72.20 454	78.18 473	91.81 360	56.42 508	82.94 491	82.58 492	55.24 501	68.88 485	66.48 513	55.32 454	95.13 421	58.12 488	88.42 319	83.01 492

test2506		87.21 288	86.28 287	90.02 303	95.62 145	73.64 418	96.25 55	71.38 513	87.89 151	90.45 176	96.65 92	55.29 455	98.09 191	86.03 219	96.94 114	98.33 51

mvs5depth		80.98 413	79.15 419	86.45 419	84.57 484	73.29 423	87.79 449	91.67 400	80.52 362	82.20 380	89.72 400	55.14 456	95.93 391	73.93 406	66.83 485	90.12 461

0.4-1-1-0.2		80.84 416	77.77 430	90.06 299	86.18 467	79.35 309	86.75 463	89.54 459	76.23 428	78.59 434	75.46 499	55.03 457	96.99 321	80.11 327	72.05 461	93.85 344

0.4-1-1-0.1		81.55 404	78.59 427	90.42 280	87.55 458	79.90 285	88.56 436	89.19 463	77.01 416	79.72 416	77.71 493	54.84 458	97.11 310	80.50 320	72.20 459	94.26 320

blend_shiyan4		81.94 394	79.35 413	89.70 321	85.52 474	80.08 273	91.29 370	93.82 334	77.12 414	79.31 422	82.94 478	54.81 459	96.60 351	79.60 336	69.78 469	92.41 413

new-patchmatchnet		76.41 447	75.17 449	80.13 466	82.65 492	59.61 501	87.66 454	91.08 416	78.23 400	69.85 484	83.22 473	54.76 460	91.63 476	64.14 469	64.89 490	89.16 472

Anonymous202405211		87.68 259	86.13 292	92.31 169	96.66 90	80.74 249	94.87 164	91.49 407	80.47 363	89.46 204	95.44 170	54.72 461	98.23 173	82.19 283	89.89 293	97.97 98

XVG-ACMP-BASELINE		86.00 329	84.84 339	89.45 338	91.20 380	78.00 345	91.70 357	95.55 223	85.05 249	82.97 369	92.25 311	54.49 462	97.48 262	82.93 267	87.45 336	92.89 392

USDC		82.76 383	81.26 386	87.26 399	91.17 382	74.55 407	89.27 423	93.39 349	78.26 399	75.30 460	92.08 319	54.43 463	96.63 341	71.64 417	85.79 349	90.61 453

AllTest		83.42 378	81.39 384	89.52 335	95.01 174	77.79 356	93.12 293	90.89 426	77.41 407	76.12 453	93.34 270	54.08 464	97.51 256	68.31 445	84.27 364	93.26 372

TestCases				89.52 335	95.01 174	77.79 356		90.89 426	77.41 407	76.12 453	93.34 270	54.08 464	97.51 256	68.31 445	84.27 364	93.26 372

KD-MVS_2432*1600		78.50 438	76.02 446	85.93 425	86.22 465	74.47 408	84.80 480	92.33 377	79.29 376	76.98 446	85.92 457	53.81 466	93.97 443	67.39 450	57.42 499	89.36 466

miper_refine_blended		78.50 438	76.02 446	85.93 425	86.22 465	74.47 408	84.80 480	92.33 377	79.29 376	76.98 446	85.92 457	53.81 466	93.97 443	67.39 450	57.42 499	89.36 466

MIMVSNet		82.59 386	80.53 389	88.76 354	91.51 368	78.32 337	86.57 466	90.13 442	79.32 375	80.70 398	88.69 422	52.98 468	93.07 458	66.03 460	88.86 312	94.90 290

testing222		84.84 357	83.32 365	89.43 339	94.15 257	75.94 391	91.09 377	89.41 462	84.90 252	85.78 284	89.44 405	52.70 469	96.28 377	70.80 428	91.57 263	96.07 240

0.3-1-1-0.015		80.75 417	77.58 432	90.25 288	86.55 463	79.72 295	87.46 457	89.48 461	76.43 423	77.93 439	75.94 496	52.31 470	97.05 317	80.25 325	71.85 463	93.99 334

FMVSNet5		81.52 406	79.60 410	87.27 398	91.17 382	77.95 346	91.49 363	92.26 382	76.87 419	76.16 452	87.91 433	51.67 471	92.34 465	67.74 449	81.16 404	91.52 434

testgi		80.94 415	80.20 397	83.18 452	87.96 454	66.29 477	91.28 371	90.70 432	83.70 282	78.12 436	92.84 289	51.37 472	90.82 482	63.34 470	82.46 388	92.43 412

test_fmvs1_n		87.03 297	87.04 256	86.97 408	89.74 431	71.86 440	94.55 188	94.43 305	78.47 393	91.95 130	95.50 168	51.16 473	93.81 446	93.02 75	94.56 181	95.26 272

Anonymous20240521		80.44 420	79.21 416	84.11 448	85.75 471	67.89 471	92.86 310	93.23 353	75.61 434	75.59 459	87.47 438	50.03 474	94.33 435	71.14 424	81.21 403	90.12 461

UnsupCasMVSNet_bld		76.23 448	73.27 452	85.09 438	83.79 486	72.92 426	85.65 473	93.47 348	71.52 470	68.84 486	79.08 491	49.77 475	93.21 455	66.81 458	60.52 496	89.13 474

OpenMVS_ROB	74.94 19	79.51 432	77.03 439	86.93 409	87.00 460	76.23 389	92.33 334	90.74 430	68.93 479	74.52 465	88.23 428	49.58 476	96.62 344	57.64 489	84.29 363	87.94 484

tt0320		80.13 423	77.41 433	88.29 369	90.50 415	78.02 344	93.10 296	90.71 431	66.06 491	76.75 448	86.97 446	49.56 477	95.40 416	71.65 416	71.41 465	91.46 438

TDRefinement		79.81 427	77.34 434	87.22 403	79.24 501	75.48 398	93.12 293	92.03 389	76.45 422	75.01 461	91.58 340	49.19 478	96.44 367	70.22 433	69.18 473	89.75 464

test_vis1_n		86.56 316	86.49 280	86.78 415	88.51 442	72.69 430	94.68 180	93.78 339	79.55 374	90.70 170	95.31 179	48.75 479	93.28 454	93.15 71	93.99 199	94.38 316

MIMVSNet1		79.38 433	77.28 435	85.69 430	86.35 464	73.67 417	91.61 360	92.75 368	78.11 402	72.64 475	88.12 429	48.16 480	91.97 471	60.32 480	77.49 440	91.43 439

LF4IMVS		80.37 421	79.07 421	84.27 447	86.64 461	69.87 464	89.39 422	91.05 418	76.38 424	74.97 462	90.00 393	47.85 481	94.25 438	74.55 402	80.82 415	88.69 478

EG-PatchMatch MVS		82.37 392	80.34 394	88.46 363	90.27 420	79.35 309	92.80 316	94.33 311	77.14 411	73.26 472	90.18 386	47.47 482	96.72 333	70.25 431	87.32 339	89.30 468

test_fmvs2		83.98 370	84.03 355	83.83 451	87.16 459	67.53 476	93.93 247	92.89 362	77.62 404	86.89 258	93.53 267	47.18 483	92.02 469	90.54 141	86.51 344	91.93 425

ttmdpeth		76.55 446	74.64 451	82.29 461	82.25 493	67.81 473	89.76 414	85.69 481	70.35 476	75.76 457	91.69 333	46.88 484	89.77 486	66.16 459	63.23 493	89.30 468

sc_t1		81.53 405	78.67 426	90.12 294	90.78 403	78.64 325	93.91 250	90.20 439	68.42 481	80.82 396	89.88 396	46.48 485	96.76 332	76.03 385	71.47 464	94.96 285

MVStest1		72.91 453	69.70 458	82.54 457	78.14 502	73.05 425	88.21 443	86.21 477	60.69 497	64.70 492	90.53 374	46.44 486	85.70 500	58.78 487	53.62 502	88.87 475

tt0320-xc		79.63 431	76.66 440	88.52 362	91.03 389	78.72 322	93.00 302	89.53 460	66.37 488	76.11 455	87.11 445	46.36 487	95.32 419	72.78 412	67.67 483	91.51 435

TinyColmap		79.76 428	77.69 431	85.97 424	91.71 363	73.12 424	89.55 417	90.36 437	75.03 439	72.03 477	90.19 385	46.22 488	96.19 381	63.11 471	81.03 409	88.59 480

myMVS_eth3d		79.67 429	78.79 424	82.32 460	91.92 353	64.08 487	89.75 415	87.40 475	81.72 340	78.82 430	87.20 441	45.33 489	91.29 477	59.09 486	87.84 330	91.60 431

tmp_tt		35.64 490	39.24 490	24.84 513	14.87 561	23.90 539	62.71 516	51.51 522	6.58 540	36.66 522	62.08 521	44.37 490	30.34 536	52.40 497	22.00 530	20.27 536

testing3		80.46 419	79.59 411	83.06 454	93.44 295	64.64 486	93.33 281	85.47 483	84.34 268	79.93 412	90.84 364	44.35 491	92.39 464	57.06 491	87.56 333	92.16 422

new_pmnet		72.15 454	70.13 457	78.20 472	82.95 491	65.68 480	83.91 486	82.40 493	62.94 496	64.47 493	79.82 490	42.85 492	86.26 498	57.41 490	74.44 452	82.65 494

test_vis1_rt		77.96 442	76.46 441	82.48 458	85.89 469	71.74 444	90.25 398	78.89 500	71.03 474	71.30 481	81.35 487	42.49 493	91.05 480	84.55 244	82.37 389	84.65 489

EGC-MVSNET		61.97 466	56.37 471	78.77 470	89.63 433	73.50 419	89.12 427	82.79 491	0.21 559	1.24 561	84.80 465	39.48 494	90.04 485	44.13 507	75.94 450	72.79 505

dongtai		58.82 471	58.24 469	60.56 495	83.13 489	45.09 520	82.32 492	48.22 525	67.61 484	61.70 498	69.15 510	38.75 495	76.05 515	32.01 520	41.31 511	60.55 518

kuosan		53.51 476	53.30 476	54.13 503	76.06 504	45.36 519	80.11 499	48.36 524	59.63 499	54.84 501	63.43 519	37.41 496	62.07 525	20.73 529	39.10 513	54.96 522

usedtu_dtu_shiyan2		74.72 450	71.30 455	84.98 439	77.78 503	70.58 458	91.85 352	90.76 429	67.24 486	68.06 488	82.17 485	37.13 497	92.78 461	60.69 479	66.03 486	91.59 433

pmmvs3		71.81 456	68.71 459	81.11 463	75.86 505	70.42 459	86.74 464	83.66 489	58.95 500	68.64 487	80.89 489	36.93 498	89.52 488	63.10 472	63.59 491	83.39 490

mvsany_test3		74.95 449	73.26 453	80.02 467	74.61 506	63.16 492	85.53 474	78.42 502	74.16 449	74.89 463	86.46 450	36.02 499	89.09 490	82.39 278	66.91 484	87.82 485

PM-MVS		78.11 441	76.12 444	84.09 449	83.54 488	70.08 461	88.97 430	85.27 485	79.93 368	74.73 464	86.43 452	34.70 500	93.48 451	79.43 345	72.06 460	88.72 477

ambc				83.06 454	79.99 499	63.51 491	77.47 503	92.86 363		74.34 467	84.45 467	28.74 501	95.06 424	73.06 411	68.89 476	90.61 453

test_method		50.52 480	48.47 480	56.66 500	52.26 531	18.98 541	41.51 527	81.40 495	10.10 530	44.59 512	75.01 502	28.51 502	68.16 518	53.54 495	49.31 507	82.83 493

DeepMVS_CX				56.31 501	74.23 508	51.81 512		56.67 521	44.85 510	48.54 506	75.16 501	27.87 503	58.74 526	40.92 514	52.22 504	58.39 521

test_fmvs3		77.67 443	77.16 438	79.22 468	79.52 500	61.14 496	92.34 333	91.64 402	73.98 451	78.86 429	86.59 449	27.38 504	87.03 494	88.12 185	75.97 449	89.50 465

test_f		71.95 455	70.87 456	75.21 477	74.21 509	59.37 502	85.07 478	85.82 480	65.25 492	70.42 483	83.13 474	23.62 505	82.93 507	78.32 357	71.94 462	83.33 491

FPMVS		64.63 465	62.55 467	70.88 481	70.80 512	56.71 504	84.42 484	84.42 487	51.78 504	49.57 504	81.61 486	23.49 506	81.48 509	40.61 515	76.25 448	74.46 504

APD_test1		69.04 459	66.26 465	77.36 476	80.51 498	62.79 493	85.46 475	83.51 490	54.11 503	59.14 500	84.79 466	23.40 507	89.61 487	55.22 492	70.24 467	79.68 499

ANet_high		58.88 470	54.22 475	72.86 478	56.50 528	56.67 505	80.75 496	86.00 479	73.09 461	37.39 520	64.63 517	22.17 508	79.49 511	43.51 509	23.96 525	82.43 495

EMVS		42.07 487	41.12 489	44.92 509	63.45 522	35.56 530	73.65 506	63.48 518	33.05 520	26.88 530	45.45 527	21.27 509	67.14 520	19.80 530	23.02 527	32.06 530

ArgMatch-SfM		70.39 457	67.69 461	78.49 471	81.44 495	60.73 497	84.71 483	75.65 511	68.09 483	66.71 491	86.79 447	20.42 510	86.05 499	71.50 419	53.87 501	88.67 479

Gipuma		57.99 472	54.91 474	67.24 490	88.51 442	65.59 481	52.21 520	90.33 438	43.58 512	42.84 513	51.18 524	20.29 511	85.07 501	34.77 517	70.45 466	51.05 523
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
E-PMN		43.23 486	42.29 486	46.03 507	65.58 520	37.41 528	73.51 507	64.62 516	33.99 518	28.47 528	47.87 526	19.90 512	67.91 519	22.23 528	24.45 523	32.77 529

ArgMatch-Sym		69.79 458	67.05 463	77.99 474	81.59 494	61.16 495	84.99 479	71.84 512	67.17 487	67.90 489	86.60 448	19.89 513	85.00 502	70.93 427	52.57 503	87.82 485

PMMVS2		59.60 467	56.40 470	69.21 487	68.83 515	46.58 516	73.02 510	77.48 507	55.07 502	49.21 505	72.95 506	17.43 514	80.04 510	49.32 502	44.33 510	80.99 497

LCM-MVSNet		66.00 463	62.16 468	77.51 475	64.51 521	58.29 503	83.87 487	90.90 425	48.17 506	54.69 502	73.31 505	16.83 515	86.75 495	65.47 461	61.67 495	87.48 487

test_vis3_rt		65.12 464	62.60 466	72.69 479	71.44 511	60.71 498	87.17 459	65.55 515	63.80 495	53.22 503	65.65 516	14.54 516	89.44 489	76.65 375	65.38 488	67.91 514

testf1		59.54 468	56.11 472	69.85 485	69.28 513	56.61 506	80.37 497	76.55 509	42.58 513	45.68 510	75.61 497	11.26 517	84.18 503	43.20 511	60.44 497	68.75 511

APD_test2		59.54 468	56.11 472	69.85 485	69.28 513	56.61 506	80.37 497	76.55 509	42.58 513	45.68 510	75.61 497	11.26 517	84.18 503	43.20 511	60.44 497	68.75 511

MVS_clip		24.79 497	27.71 497	16.02 523	35.36 543	15.85 543	27.38 535	5.39 559	6.70 539	40.04 517	63.09 520	10.55 519	8.72 557	27.86 524	33.03 519	23.49 534

PDCNetPlus		48.34 481	45.15 484	57.91 498	61.43 523	41.85 522	65.98 515	38.30 529	47.59 507	37.96 519	71.85 507	10.18 520	66.85 522	52.94 496	20.14 536	65.03 516

VLMVS		10.93 513	11.73 513	8.51 535	11.99 562	6.47 565	9.10 552	5.11 560	0.73 556	17.62 535	25.59 539	9.61 521	6.56 559	6.19 540	19.64 537	12.50 539

VLMVS_CLIP		27.58 494	28.97 495	23.41 515	23.47 557	13.17 549	30.64 533	40.90 527	9.21 532	36.34 523	50.75 525	8.75 522	38.05 531	25.18 526	35.53 515	19.03 538

LoFTR		57.22 473	52.62 477	71.00 480	72.03 510	48.57 515	72.00 511	70.08 514	44.40 511	40.92 516	76.42 495	8.12 523	82.76 508	42.28 513	47.33 509	81.66 496

DenseAffine		56.77 474	52.17 478	70.54 483	74.27 507	53.25 511	77.23 504	50.43 523	49.87 505	47.26 509	77.37 494	7.99 524	79.10 512	50.35 499	34.79 516	79.28 500

RoMa-SfM		53.80 475	49.39 479	67.06 491	67.87 517	48.86 513	75.04 505	38.06 530	47.23 508	47.40 508	78.96 492	7.40 525	76.66 514	48.89 503	33.62 517	75.64 503

MASt3R-SfM		45.78 484	43.96 485	51.24 505	45.04 533	29.83 534	57.88 517	38.83 528	31.88 521	47.48 507	81.30 488	7.16 526	51.15 529	49.56 501	36.51 514	72.74 506

ALIKED-LG		28.00 493	26.54 498	32.41 510	58.12 525	31.80 531	47.26 523	21.21 535	14.15 527	19.16 533	41.93 529	6.72 527	35.73 532	5.96 541	24.32 524	29.69 531

MatchFormer		51.11 478	46.66 482	64.46 493	67.11 518	43.39 521	70.54 512	63.67 517	33.19 519	37.22 521	70.30 509	6.67 528	78.17 513	30.29 521	40.94 512	71.81 508

PMVS	47.18 22	52.22 477	48.46 481	63.48 494	45.72 532	46.20 517	73.41 508	78.31 503	41.03 515	30.06 526	65.68 515	6.05 529	83.43 506	30.04 522	65.86 487	60.80 517
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
SP-DiffGlue		20.02 502	19.96 505	20.21 518	19.64 558	13.14 550	30.51 534	15.49 541	8.39 533	19.98 532	43.75 528	5.48 530	13.72 543	13.75 533	22.65 528	33.78 527

RoMa-HiRes		46.47 482	42.20 487	59.28 497	57.74 526	39.86 527	66.76 514	24.64 533	39.96 516	41.50 515	75.37 500	5.40 531	69.26 517	43.35 510	25.09 521	68.71 513

ALIKED-NN		26.07 496	24.75 500	30.02 512	55.08 530	30.61 533	44.20 526	19.22 537	10.98 529	17.98 534	40.71 530	5.39 532	32.83 534	5.59 542	23.63 526	26.63 533

ALIKED-MNN		26.28 495	24.57 501	31.39 511	56.22 529	31.73 532	45.54 524	19.13 538	11.12 528	17.11 536	39.35 531	5.01 533	34.53 533	5.54 543	22.12 529	27.92 532

DKM		50.92 479	46.13 483	65.30 492	66.27 519	45.98 518	73.05 509	31.91 532	45.08 509	42.04 514	75.01 502	4.95 534	73.81 516	47.90 504	28.96 520	76.09 502

SP-LightGlue		20.24 500	20.15 504	20.49 516	43.51 535	12.27 551	38.68 529	14.56 543	7.54 536	12.90 541	30.07 536	4.75 535	14.38 540	7.60 536	21.75 531	34.82 524

SP-SuperGlue		20.22 501	20.18 503	20.36 517	43.26 536	12.27 551	38.71 528	14.77 542	7.64 535	13.04 540	30.21 535	4.73 536	14.21 542	7.59 537	21.65 532	34.59 525

MVE	39.65 23	43.39 485	38.59 491	57.77 499	56.52 527	48.77 514	55.38 518	58.64 520	29.33 523	28.96 527	52.65 523	4.68 537	64.62 524	28.11 523	33.07 518	59.93 519
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
SP-NN		19.44 504	19.37 507	19.67 520	41.70 538	11.48 556	37.75 531	13.72 546	6.86 537	11.86 542	29.97 537	4.23 538	14.25 541	7.13 538	21.07 533	33.30 528

SP-MNN		19.61 503	19.42 506	20.19 519	42.15 537	11.42 557	38.15 530	14.24 544	6.55 541	11.64 543	29.88 538	4.16 539	14.56 539	7.09 539	20.92 534	34.58 526

XFeat-MNN		17.43 505	16.95 508	18.86 521	16.90 559	11.28 558	27.31 536	17.08 539	8.08 534	15.61 538	35.73 532	4.06 540	22.95 537	10.20 534	17.59 540	22.35 535

wuyk23d		21.27 499	20.48 502	23.63 514	68.59 516	36.41 529	49.57 521	6.85 553	9.37 531	7.89 544	4.46 559	4.03 541	31.37 535	17.47 532	16.07 541	3.12 555

GLUNet-SfM		31.36 492	26.25 499	46.70 506	35.51 542	24.89 538	33.71 532	36.36 531	19.08 526	23.78 531	52.69 522	3.82 542	56.26 528	19.75 531	11.56 550	58.95 520

DKM-HiRes		45.90 483	41.41 488	59.36 496	59.55 524	39.90 526	67.13 513	23.25 534	39.95 517	38.74 518	71.81 508	3.67 543	66.42 523	43.82 508	24.82 522	71.77 509

XFeat-NN		15.96 506	15.86 509	16.25 522	15.78 560	9.87 561	25.17 537	13.83 545	6.76 538	15.68 537	34.83 533	3.61 544	19.28 538	9.22 535	17.90 538	19.58 537

ELoFTR		40.15 488	35.08 492	55.36 502	41.27 539	28.17 537	47.70 522	43.76 526	29.15 524	30.35 525	65.97 514	2.17 545	66.90 521	34.51 518	20.83 535	71.00 510

SIFT-NN		12.98 507	13.18 510	12.37 524	36.49 541	16.03 542	22.41 538	7.69 549	4.89 542	7.41 545	20.48 541	1.69 546	11.46 545	1.88 547	15.70 542	9.61 541

SIFT-MNN		12.44 508	12.55 511	12.11 525	34.55 544	15.21 544	20.91 539	7.74 548	4.86 543	6.54 547	20.09 542	1.51 547	11.47 544	1.88 547	14.87 544	9.64 540

SIFT-NN-NCMNet		12.12 509	12.25 512	11.75 526	32.82 546	14.83 545	20.73 540	7.58 550	4.72 545	6.60 546	19.53 543	1.49 548	11.15 547	1.74 549	15.02 543	9.28 542

SIFT-NN-UMatch		11.06 512	11.19 518	10.66 530	28.66 552	12.16 553	19.79 541	6.86 552	4.73 544	5.21 550	19.47 545	1.46 549	10.70 550	1.71 550	12.79 548	9.13 544

SIFT-NN-CMatch		11.26 511	11.31 516	11.13 528	30.21 550	13.40 548	18.43 543	6.79 554	4.71 546	6.47 548	19.53 543	1.43 550	10.72 549	1.71 550	12.49 549	9.26 543

SIFT-NN-PointCN		10.26 516	10.46 521	9.65 533	27.18 553	9.89 560	17.89 545	6.17 556	4.40 552	5.65 549	18.29 549	1.43 550	10.09 553	1.61 554	11.55 551	8.99 546

SIFT-NCM-Cal		11.58 510	11.64 514	11.40 527	33.45 545	14.10 546	19.75 542	6.89 551	4.68 548	4.55 554	18.60 548	1.34 552	11.28 546	1.53 555	13.95 545	8.82 547

SIFT-ConvMatch		10.91 514	10.94 519	10.84 529	32.07 547	13.57 547	17.23 546	6.35 555	4.71 546	5.18 551	18.94 546	1.30 553	10.76 548	1.65 553	11.02 552	8.19 548

SIFT-CM-Cal		10.08 517	10.13 523	9.92 532	30.71 549	11.88 554	15.35 548	5.44 558	4.59 550	4.72 552	18.04 551	1.26 554	10.19 552	1.46 557	9.60 554	7.69 550

SIFT-UMatch		10.58 515	10.73 520	10.15 531	31.05 548	11.65 555	18.01 544	5.92 557	4.65 549	4.72 552	18.93 547	1.25 555	10.62 551	1.66 552	10.39 553	8.16 549

SIFT-UM-Cal		9.80 518	10.00 524	9.22 534	30.05 551	10.15 559	16.31 547	4.85 562	4.54 551	4.19 555	18.23 550	1.19 556	9.95 554	1.52 556	9.11 556	7.57 551

MVS_baseline		7.30 525	8.69 528	3.12 539	8.45 563	0.31 568	3.27 553	0.80 565	0.16 560	14.50 539	32.51 534	1.15 557	0.00 562	4.24 544	13.11 547	9.06 545

PMatch-SfM		38.18 489	33.34 493	52.72 504	43.67 534	28.18 536	52.96 519	16.29 540	29.70 522	31.24 524	68.56 512	1.08 558	57.70 527	38.73 516	17.80 539	72.30 507

SIFT-PCN-Cal		8.65 522	8.88 526	7.98 536	26.74 554	7.47 563	13.90 550	4.61 563	4.09 554	3.82 556	15.86 552	1.01 559	8.94 555	1.34 558	8.52 557	7.53 552

SIFT-PointCN		8.76 520	9.03 525	7.96 537	26.50 555	7.60 562	14.94 549	5.08 561	4.10 553	3.74 557	15.46 553	0.94 560	8.92 556	1.33 559	9.14 555	7.37 553

SIFT-NCMNet		7.46 524	7.71 529	6.72 538	25.03 556	6.86 564	11.42 551	2.98 564	4.05 555	3.38 558	13.68 554	0.84 561	7.65 558	1.13 560	6.87 558	5.66 554

PMatch-Up-SfM		32.59 491	28.46 496	44.98 508	37.19 540	22.27 540	44.73 525	10.63 547	23.85 525	27.52 529	64.10 518	0.78 562	47.14 530	34.15 519	13.22 546	65.53 515

test123		8.76 520	11.22 517	1.39 540	0.85 565	0.97 566	85.76 472	0.35 567	0.54 558	2.45 560	8.14 558	0.60 563	0.48 560	2.16 546	0.17 560	2.71 556

testmvs		8.92 519	11.52 515	1.12 541	1.06 564	0.46 567	86.02 468	0.65 566	0.62 557	2.74 559	9.52 557	0.31 564	0.45 561	2.38 545	0.39 559	2.46 557

mmdepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

monomultidepth		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

test_blank		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet_test		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

DCPMVS		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

sosnet-low-res		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

sosnet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uncertanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Regformer		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

ab-mvs-re		7.82 523	10.43 522	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	93.88 255	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

uanet		0.00 527	0.00 530	0.00 542	0.00 566	0.00 569	0.00 554	0.00 568	0.00 561	0.00 562	0.00 560	0.00 565	0.00 562	0.00 561	0.00 561	0.00 558

Meshroom													0.00 562
: In preparation.
AliceVision / Meshro													0.00 562
: In preparation.
AliceVision_Meshroom													0.00 562
: In preparation.
PatchmatchNet2					0.00 566	62.07 494	85.98 469	87.63 473	68.79 480
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet1														54.59 494	77.20 442	90.17 459
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													91.68 475
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
aaatest				94.84 34	98.88 1	85.89 66	97.32 10	97.86 1	88.11 135	97.21 15	97.54 47		99.67 1	95.27 42	98.85 22	98.95 13

WAC-MVS						64.08 487								59.14 485

FOURS1					98.86 4	85.54 75	98.29 1	97.49 11	89.79 67	96.29 33

MSC_two_6792asdad				96.52 1	97.78 61	90.86 1		96.85 81					99.61 7	96.03 28	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 28	99.06 9	99.07 7

eth-test2					0.00 566

eth-test					0.00 566

IU-MVS					98.77 8	86.00 55		96.84 83	81.26 353	97.26 14				95.50 38	99.13 3	99.03 10

save fliter					97.85 56	85.63 74	95.21 142	96.82 86	89.44 78

test_0728_SECOND				95.01 18	98.79 5	86.43 41	97.09 21	97.49 11					99.61 7	95.62 36	99.08 7	98.99 11

GSMVS																96.12 236

test_part2					98.55 15	87.22 20				96.40 32

MTGPA								96.97 66

MTMP							96.16 60	60.64 519

gm-plane-assit					89.60 434	68.00 470			77.28 410		88.99 412		97.57 251	79.44 344

test9_res														91.91 111	98.71 36	98.07 84

agg_prior2														90.54 141	98.68 41	98.27 65

agg_prior					97.38 73	85.92 62		96.72 101		92.16 123			98.97 88

test_prior4						85.96 59	94.11 227

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

旧先验2							93.36 280		71.25 472	94.37 63			97.13 309	86.74 207

新几何2							93.11 295

无先验							93.28 288	96.26 142	73.95 452				99.05 68	80.56 318		96.59 215

原ACMM2							92.94 306

testdata2													98.75 118	78.30 358

testdata1							92.15 343		87.94 145

plane_prior7					94.70 204	82.74 166

plane_prior5								96.22 148					98.12 181	88.15 182	89.99 289	94.63 298

plane_prior4											94.86 204

plane_prior3						82.75 164			90.26 51	86.91 255

plane_prior2							95.85 93		90.81 28

plane_prior1					94.59 213

plane_prior						82.73 167	95.21 142		89.66 72						89.88 294

n2								0.00 568

nn								0.00 568

door-mid								85.49 482

test11								96.57 114

door								85.33 484

HQP5-MVS						81.56 208

HQP-NCC					94.17 254		94.39 206		88.81 105	85.43 301

ACMP_Plane					94.17 254		94.39 206		88.81 105	85.43 301

BP-MVS														87.11 204

HQP4-MVS										85.43 301			97.96 218			94.51 308

HQP3-MVS								96.04 176							89.77 298

NP-MVS					94.37 235	82.42 181					93.98 248

ACMMP++_ref															87.47 334

ACMMP++															88.01 326

High-resolution multi-view benchmark