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.

DVP-MVS++		96.05 4	96.41 3	94.96 25	99.05 13	85.34 65	98.13 71	96.77 71	88.38 92	97.70 13	98.77 15	92.06 3	99.84 17	97.47 40	99.37 1	99.70 3

PC_three_1452									91.12 50	98.33 4	98.42 43	92.51 2	99.81 27	98.96 6	99.37 1	99.70 3

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 16				98.54 29	92.06 3	99.84 17	99.11 5	99.37 1	99.74 1

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 31	97.10 37	95.17 4	92.11 106	98.46 39	87.33 27	99.97 2	97.21 46	99.31 4	99.63 7

MSP-MVS		95.62 8	96.54 1	92.86 112	98.31 52	80.10 235	97.42 130	96.78 65	92.20 36	97.11 23	98.29 52	93.46 1	99.10 121	96.01 56	99.30 5	99.38 14
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
DPM-MVS		96.21 2	95.53 15	98.26 1	96.26 112	95.09 1	99.15 12	96.98 46	93.39 23	96.45 38	98.79 13	90.17 9	99.99 1	89.33 171	99.25 6	99.70 3

HPM-MVS++		95.32 13	95.48 16	94.85 27	98.62 38	86.04 44	97.81 94	96.93 53	92.45 30	95.69 47	98.50 34	85.38 36	99.85 15	94.75 76	99.18 7	98.65 55

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 5	87.69 25	99.06 23	97.12 35	94.66 10	96.79 30	98.78 14	86.42 32	99.95 6	97.59 39	99.18 7	99.00 32

NCCC		95.63 7	95.94 8	94.69 33	99.21 6	85.15 76	99.16 11	96.96 50	94.11 15	95.59 49	98.64 24	85.07 38	99.91 7	95.61 63	99.10 9	99.00 32

SMA-MVS		94.70 25	94.68 31	94.76 30	98.02 63	85.94 48	97.47 123	96.77 71	85.32 187	97.92 5	98.70 22	83.09 62	99.84 17	95.79 60	99.08 10	98.49 63
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
MSLP-MVS++		94.28 36	94.39 38	93.97 55	98.30 53	84.06 98	98.64 44	96.93 53	90.71 57	93.08 88	98.70 22	79.98 88	99.21 107	94.12 85	99.07 11	98.63 56

DPE-MVS		95.32 13	95.55 14	94.64 34	98.79 27	84.87 85	97.77 97	96.74 76	86.11 161	96.54 37	98.89 10	88.39 21	99.74 52	97.67 38	99.05 12	99.31 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TSAR-MVS + MP.		94.79 24	95.17 23	93.64 73	97.66 75	84.10 97	95.85 269	96.42 125	91.26 48	97.49 20	96.80 141	86.50 31	98.49 154	95.54 65	99.03 13	98.33 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test9_res														96.00 57	99.03 13	98.31 75

test_241102_TWO								96.78 65	88.72 84	97.70 13	98.91 2	87.86 24	99.82 23	98.15 22	99.00 15	99.47 9

agg_prior2														94.30 81	99.00 15	98.57 59

SED-MVS		95.88 5	96.22 4	94.87 26	99.03 19	85.03 80	99.12 16	96.78 65	88.72 84	97.79 10	98.91 2	88.48 19	99.82 23	98.15 22	98.97 17	99.74 1

IU-MVS					99.03 19	85.34 65		96.86 60	92.05 41	98.74 1				98.15 22	98.97 17	99.42 13

train_agg		94.28 36	94.45 36	93.74 64	98.64 35	83.71 104	97.82 92	96.65 90	84.50 217	95.16 54	98.09 66	84.33 46	99.36 97	95.91 59	98.96 19	98.16 87

MG-MVS		94.25 38	93.72 49	95.85 12	99.38 3	89.35 11	97.98 81	98.09 9	89.99 68	92.34 100	96.97 133	81.30 73	98.99 127	88.54 186	98.88 20	99.20 25

DVP-MVS		95.58 9	95.91 9	94.57 36	99.05 13	85.18 71	99.06 23	96.46 120	88.75 82	96.69 31	98.76 17	87.69 25	99.76 44	97.90 30	98.85 21	98.77 45
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				95.14 21	99.04 18	86.14 43	99.06 23	96.77 71					99.84 17	97.90 30	98.85 21	99.45 10

test_0728_THIRD									88.38 92	96.69 31	98.76 17	89.64 14	99.76 44	97.47 40	98.84 23	99.38 14

balanced_conf03		94.60 28	94.30 41	95.48 17	96.45 106	88.82 14	96.33 227	95.58 199	91.12 50	95.84 46	93.87 253	83.47 58	98.37 164	97.26 44	98.81 24	99.24 23

MSC_two_6792asdad				97.14 3	99.05 13	92.19 4		96.83 62					99.81 27	98.08 26	98.81 24	99.43 11

No_MVS				97.14 3	99.05 13	92.19 4		96.83 62					99.81 27	98.08 26	98.81 24	99.43 11

test_prior2							98.37 56		86.08 163	94.57 68	98.02 72	83.14 60		95.05 72	98.79 27

APDe-MVS		94.56 29	94.75 28	93.96 56	98.84 26	83.40 115	98.04 79	96.41 126	85.79 174	95.00 60	98.28 53	84.32 49	99.18 114	97.35 43	98.77 28	99.28 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DeepC-MVS_fast	89.06 2	94.48 32	94.30 41	95.02 23	98.86 25	85.68 55	98.06 77	96.64 93	93.64 21	91.74 113	98.54 29	80.17 84	99.90 8	92.28 114	98.75 29	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CDPH-MVS		93.12 59	92.91 70	93.74 64	98.65 34	83.88 99	97.67 105	96.26 145	83.00 266	93.22 85	98.24 54	81.31 72	99.21 107	89.12 172	98.74 30	98.14 89

DELS-MVS		94.98 16	94.49 35	96.44 6	96.42 107	90.59 7	99.21 8	97.02 43	94.40 14	91.46 115	97.08 128	83.32 59	99.69 64	92.83 107	98.70 31	99.04 30
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
DeepPCF-MVS	89.82 1	94.61 26	96.17 5	89.91 268	97.09 100	70.21 416	98.99 29	96.69 84	95.57 2	95.08 58	99.23 1	86.40 33	99.87 11	97.84 33	98.66 32	99.65 6

PHI-MVS		93.59 50	93.63 52	93.48 84	98.05 62	81.76 169	98.64 44	97.13 33	82.60 276	94.09 74	98.49 35	80.35 79	99.85 15	94.74 77	98.62 33	98.83 42

MED-MVS test				94.20 48	99.06 10	83.70 106	98.35 57	97.14 30	87.45 120	97.03 26	98.90 5		99.96 3	97.78 35	98.60 34	98.94 35

MED-MVS		95.43 12	95.84 10	94.20 48	99.06 10	83.70 106	98.35 57	97.14 30	85.79 174	97.03 26	98.90 5	89.87 12	99.96 3	97.78 35	98.60 34	98.94 35

TestfortrainingZip a		95.44 11	95.38 18	95.64 13	99.06 10	88.36 15	98.35 57	97.14 30	87.45 120	97.03 26	98.90 5	89.87 12	99.96 3	91.98 121	98.60 34	98.61 58

ME-MVS		94.82 22	95.04 24	94.17 50	99.17 8	83.70 106	97.66 106	97.22 24	85.79 174	95.34 51	98.90 5	84.89 39	99.86 13	97.78 35	98.60 34	98.94 35

ACMMP_NAP		93.46 54	93.23 63	94.17 50	97.16 98	84.28 95	96.82 184	96.65 90	86.24 158	94.27 71	97.99 73	77.94 120	99.83 21	93.39 93	98.57 38	98.39 70

MVSMamba_PlusPlus		92.37 93	91.55 105	94.83 28	95.37 146	87.69 25	95.60 283	95.42 215	74.65 397	93.95 76	92.81 273	83.11 61	97.70 199	94.49 80	98.53 39	99.11 28

SF-MVS		94.17 39	94.05 46	94.55 37	97.56 81	85.95 46	97.73 101	96.43 124	84.02 234	95.07 59	98.74 19	82.93 63	99.38 94	95.42 67	98.51 40	98.32 73

原ACMM1				91.22 221	97.77 71	78.10 303		96.61 96	81.05 300	91.28 121	97.42 110	77.92 122	98.98 128	79.85 279	98.51 40	96.59 223

SD-MVS		94.84 21	95.02 26	94.29 42	97.87 68	84.61 88	97.76 99	96.19 153	89.59 74	96.66 33	98.17 60	84.33 46	99.60 75	96.09 55	98.50 42	98.66 54
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
ZD-MVS					99.09 9	83.22 119		96.60 99	82.88 269	93.61 81	98.06 71	82.93 63	99.14 117	95.51 66	98.49 43

新几何1				93.12 99	97.44 87	81.60 178		96.71 81	74.54 398	91.22 122	97.57 101	79.13 99	99.51 87	77.40 311	98.46 44	98.26 80

SteuartSystems-ACMMP		94.13 42	94.44 37	93.20 95	95.41 144	81.35 182	99.02 27	96.59 100	89.50 76	94.18 73	98.36 49	83.68 57	99.45 91	94.77 75	98.45 45	98.81 44
Skip Steuart: Steuart Systems R&D Blog.
9.14			94.26 43		98.10 61		98.14 68	96.52 112	84.74 207	94.83 64	98.80 12	82.80 65	99.37 96	95.95 58	98.42 46

HFP-MVS		92.89 66	92.86 73	92.98 106	98.71 29	81.12 187	97.58 113	96.70 82	85.20 192	91.75 112	97.97 78	78.47 111	99.71 60	90.95 133	98.41 47	98.12 92

ACMMPR		92.69 80	92.67 76	92.75 119	98.66 32	80.57 213	97.58 113	96.69 84	85.20 192	91.57 114	97.92 79	77.01 142	99.67 68	90.95 133	98.41 47	98.00 103

MP-MVS-pluss		92.58 85	92.35 84	93.29 90	97.30 96	82.53 134	96.44 215	96.04 165	84.68 210	89.12 154	98.37 48	77.48 130	99.74 52	93.31 98	98.38 49	97.59 144
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		92.72 75	92.70 75	92.79 117	98.68 30	80.53 219	97.53 118	96.51 113	85.22 190	91.94 110	97.98 76	77.26 133	99.67 68	90.83 140	98.37 50	98.18 85

APD-MVS		93.61 49	93.59 53	93.69 70	98.76 28	83.26 118	97.21 142	96.09 159	82.41 280	94.65 67	98.21 55	81.96 70	98.81 139	94.65 78	98.36 51	99.01 31
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ZNCC-MVS		92.75 71	92.60 78	93.23 93	98.24 55	81.82 167	97.63 107	96.50 115	85.00 202	91.05 124	97.74 90	78.38 112	99.80 31	90.48 146	98.34 52	98.07 94

test12				94.25 43	98.34 50	85.55 61		96.35 138		92.36 99		80.84 74	99.22 106		98.31 53	97.98 105

MP-MVS		92.61 84	92.67 76	92.42 142	98.13 60	79.73 247	97.33 137	96.20 151	85.63 178	90.53 131	97.66 93	78.14 118	99.70 63	92.12 117	98.30 54	97.85 117
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test222					96.15 116	78.41 290	95.87 267	96.46 120	71.97 423	89.66 144	97.45 106	76.33 158			98.24 55	98.30 76

CP-MVS		92.54 86	92.60 78	92.34 147	98.50 44	79.90 240	98.40 55	96.40 128	84.75 206	90.48 133	98.09 66	77.40 131	99.21 107	91.15 130	98.23 56	97.92 110

MTAPA		92.45 89	92.31 87	92.86 112	97.90 65	80.85 203	92.88 375	96.33 139	87.92 106	90.20 137	98.18 57	76.71 150	99.76 44	92.57 111	98.09 57	97.96 109

XVS		92.69 80	92.71 74	92.63 128	98.52 41	80.29 224	97.37 134	96.44 122	87.04 138	91.38 116	97.83 87	77.24 135	99.59 76	90.46 148	98.07 58	98.02 97

X-MVStestdata		86.26 256	84.14 277	92.63 128	98.52 41	80.29 224	97.37 134	96.44 122	87.04 138	91.38 116	20.73 497	77.24 135	99.59 76	90.46 148	98.07 58	98.02 97

MVS		90.60 143	88.64 177	96.50 5	94.25 191	90.53 8	93.33 363	97.21 25	77.59 367	78.88 308	97.31 113	71.52 248	99.69 64	89.60 165	98.03 60	99.27 22

mPP-MVS		91.88 106	91.82 99	92.07 169	98.38 48	78.63 283	97.29 139	96.09 159	85.12 198	88.45 168	97.66 93	75.53 178	99.68 66	89.83 159	98.02 61	97.88 112

MM		95.85 6	95.74 11	96.15 8	96.34 109	89.50 9	99.18 9	98.10 8	95.68 1	96.64 34	97.92 79	80.72 75	99.80 31	99.16 2	97.96 62	99.15 27

HPM-MVS		91.62 113	91.53 106	91.89 179	97.88 67	79.22 260	96.99 166	95.73 192	82.07 286	89.50 149	97.19 122	75.59 176	98.93 134	90.91 135	97.94 63	97.54 148
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MVS_111021_HR		93.41 55	93.39 60	93.47 86	97.34 95	82.83 128	97.56 115	98.27 6	89.16 80	89.71 142	97.14 123	79.77 90	99.56 82	93.65 91	97.94 63	98.02 97

PGM-MVS		91.93 103	91.80 100	92.32 151	98.27 54	79.74 246	95.28 294	97.27 22	83.83 244	90.89 128	97.78 89	76.12 165	99.56 82	88.82 181	97.93 65	97.66 135

MGCNet		95.58 9	95.44 17	96.01 10	97.63 76	89.26 12	99.27 5	96.59 100	94.71 9	97.08 24	97.99 73	78.69 108	99.86 13	99.15 3	97.85 66	98.91 39

3Dnovator	82.32 10	89.33 178	87.64 202	94.42 39	93.73 210	85.70 53	97.73 101	96.75 75	86.73 149	76.21 345	95.93 159	62.17 329	99.68 66	81.67 259	97.81 67	97.88 112

SPE-MVS-test		92.98 62	93.67 51	90.90 232	96.52 105	76.87 336	98.68 41	94.73 252	90.36 65	94.84 63	97.89 83	77.94 120	97.15 261	94.28 84	97.80 68	98.70 53

fmvsm_l_conf0.5_n_9		94.91 17	95.60 12	92.84 115	95.20 153	80.55 214	99.45 1	96.36 137	95.17 4	98.48 3	98.55 27	80.53 78	99.78 38	98.87 7	97.79 69	98.19 84

GST-MVS		92.43 91	92.22 92	93.04 103	98.17 58	81.64 175	97.40 132	96.38 132	84.71 209	90.90 127	97.40 111	77.55 129	99.76 44	89.75 163	97.74 70	97.72 129

PAPM		92.87 69	92.40 83	94.30 41	92.25 281	87.85 22	96.40 220	96.38 132	91.07 52	88.72 164	96.90 134	82.11 68	97.37 244	90.05 158	97.70 71	97.67 134

test_fmvsm_n_1920		94.81 23	95.60 12	92.45 138	95.29 149	80.96 198	99.29 4	97.21 25	94.50 13	97.29 22	98.44 40	82.15 67	99.78 38	98.56 12	97.68 72	96.61 222

CANet		94.89 19	94.64 32	95.63 14	97.55 82	88.12 19	99.06 23	96.39 130	94.07 17	95.34 51	97.80 88	76.83 147	99.87 11	97.08 48	97.64 73	98.89 40

patch_mono-2		95.14 15	96.08 7	92.33 149	98.44 47	77.84 313	98.43 52	97.21 25	92.58 29	97.68 15	97.65 97	86.88 29	99.83 21	98.25 18	97.60 74	99.33 18

dcpmvs_2		93.10 60	93.46 59	92.02 173	97.77 71	79.73 247	94.82 320	93.86 328	86.91 141	91.33 119	96.76 142	85.20 37	98.06 177	96.90 50	97.60 74	98.27 79

testdata				90.13 258	95.92 126	74.17 374		96.49 118	73.49 407	94.82 65	97.99 73	78.80 106	97.93 185	83.53 242	97.52 76	98.29 77

MVSFormer		91.36 120	90.57 126	93.73 66	93.00 238	88.08 20	94.80 322	94.48 274	80.74 307	94.90 61	97.13 124	78.84 104	95.10 374	83.77 234	97.46 77	98.02 97

lupinMVS		93.87 47	93.58 54	94.75 31	93.00 238	88.08 20	99.15 12	95.50 206	91.03 53	94.90 61	97.66 93	78.84 104	97.56 211	94.64 79	97.46 77	98.62 57

HPM-MVS_fast		90.38 150	90.17 141	91.03 226	97.61 77	77.35 328	97.15 152	95.48 207	79.51 340	88.79 161	96.90 134	71.64 246	98.81 139	87.01 207	97.44 79	96.94 203

GG-mvs-BLEND				93.49 83	94.94 165	86.26 39	81.62 464	97.00 44		88.32 171	94.30 236	91.23 5	96.21 311	88.49 188	97.43 80	98.00 103

旧先验1					97.39 92	79.58 251		96.54 109			98.08 69	84.00 52			97.42 81	97.62 141

PS-MVSNAJ		94.17 39	93.52 56	96.10 9	95.65 136	92.35 2	98.21 66	95.79 188	92.42 31	96.24 40	98.18 57	71.04 253	99.17 115	96.77 51	97.39 82	96.79 213

fmvsm_s_conf0.5_n_11		94.41 33	95.19 22	92.09 167	95.65 136	80.91 201	99.23 7	94.85 245	94.92 7	97.68 15	98.82 11	79.31 94	99.78 38	98.83 9	97.38 83	95.60 255

fmvsm_s_conf0.5_n_6		94.17 39	94.70 30	92.58 132	93.50 221	81.20 184	99.08 21	96.48 119	92.24 35	98.62 2	98.39 45	78.58 110	99.72 57	98.08 26	97.36 84	96.81 212

CSCG		92.02 100	91.65 103	93.12 99	98.53 40	80.59 210	97.47 123	97.18 28	77.06 376	84.64 234	97.98 76	83.98 53	99.52 85	90.72 142	97.33 85	99.23 24

CS-MVS		92.73 73	93.48 58	90.48 245	96.27 111	75.93 357	98.55 47	94.93 238	89.32 77	94.54 69	97.67 92	78.91 103	97.02 266	93.80 88	97.32 86	98.49 63

SR-MVS		92.16 97	92.27 88	91.83 188	98.37 49	78.41 290	96.67 199	95.76 189	82.19 284	91.97 108	98.07 70	76.44 154	98.64 143	93.71 90	97.27 87	98.45 66

gg-mvs-nofinetune		85.48 273	82.90 302	93.24 92	94.51 182	85.82 50	79.22 469	96.97 49	61.19 463	87.33 188	53.01 486	90.58 6	96.07 314	86.07 214	97.23 88	97.81 122

fmvsm_l_conf0.5_n_3		94.61 26	94.92 27	93.68 71	94.52 178	82.80 129	99.33 2	96.37 135	95.08 6	97.59 19	98.48 37	77.40 131	99.79 35	98.28 16	97.21 89	98.44 67

reproduce-ours		92.70 78	93.02 66	91.75 190	97.45 85	77.77 317	96.16 241	95.94 176	84.12 230	92.45 95	98.43 41	80.06 86	99.24 103	95.35 68	97.18 90	98.24 81

our_new_method		92.70 78	93.02 66	91.75 190	97.45 85	77.77 317	96.16 241	95.94 176	84.12 230	92.45 95	98.43 41	80.06 86	99.24 103	95.35 68	97.18 90	98.24 81

MAR-MVS		90.63 142	90.22 138	91.86 181	98.47 46	78.20 301	97.18 146	96.61 96	83.87 241	88.18 175	98.18 57	68.71 277	99.75 49	83.66 239	97.15 92	97.63 139
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_conf0.5_n_7		92.88 67	93.82 47	90.08 259	92.79 254	76.45 344	98.54 48	96.74 76	92.28 34	95.22 53	98.49 35	74.91 195	98.15 175	98.28 16	97.13 93	95.63 253

NormalMVS		92.88 67	92.97 69	92.59 131	97.80 69	82.02 152	97.94 84	94.70 253	92.34 32	92.15 104	96.53 149	77.03 140	98.57 147	91.13 131	97.12 94	97.19 186

lecture		93.17 57	93.57 55	91.96 175	97.80 69	78.79 279	98.50 50	96.98 46	86.61 152	94.75 66	98.16 61	78.36 114	99.35 99	93.89 87	97.12 94	97.75 126

EC-MVSNet		91.73 108	92.11 94	90.58 241	93.54 215	77.77 317	98.07 76	94.40 286	87.44 122	92.99 90	97.11 126	74.59 202	96.87 283	93.75 89	97.08 96	97.11 190

3Dnovator+	82.88 8	89.63 169	87.85 197	94.99 24	94.49 184	86.76 36	97.84 91	95.74 191	86.10 162	75.47 356	96.02 158	65.00 310	99.51 87	82.91 249	97.07 97	98.72 52

mvsmamba		90.53 147	90.08 143	91.88 180	94.81 169	80.93 199	93.94 346	94.45 280	88.24 98	87.02 197	92.35 280	68.04 279	95.80 329	94.86 74	97.03 98	98.92 38

reproduce_model		92.53 87	92.87 71	91.50 206	97.41 89	77.14 334	96.02 248	95.91 179	83.65 252	92.45 95	98.39 45	79.75 91	99.21 107	95.27 71	96.98 99	98.14 89

DeepC-MVS	86.58 3	91.53 115	91.06 117	92.94 109	94.52 178	81.89 163	95.95 252	95.98 170	90.76 56	83.76 250	96.76 142	73.24 220	99.71 60	91.67 125	96.96 100	97.22 180
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_10		94.36 34	94.73 29	93.23 93	95.19 154	82.87 127	99.18 9	96.39 130	93.97 18	97.91 7	98.53 31	75.88 171	99.82 23	98.58 11	96.95 101	97.00 200

CPTT-MVS		89.72 166	89.87 153	89.29 281	98.33 51	73.30 381	97.70 103	95.35 219	75.68 388	87.40 186	97.44 109	70.43 261	98.25 169	89.56 168	96.90 102	96.33 232

APD-MVS_3200maxsize		91.23 124	91.35 108	90.89 233	97.89 66	76.35 347	96.30 230	95.52 204	79.82 334	91.03 125	97.88 84	74.70 198	98.54 151	92.11 118	96.89 103	97.77 124

MVP-Stereo		82.65 326	81.67 321	85.59 369	86.10 410	78.29 293	93.33 363	92.82 384	77.75 365	69.17 414	87.98 353	59.28 355	95.76 333	71.77 364	96.88 104	82.73 455
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PAPM_NR		91.46 116	90.82 121	93.37 89	98.50 44	81.81 168	95.03 314	96.13 156	84.65 211	86.10 214	97.65 97	79.24 97	99.75 49	83.20 245	96.88 104	98.56 60

fmvsm_s_conf0.5_n_9		94.52 30	95.22 21	92.41 143	95.79 132	78.61 284	98.73 38	96.00 167	94.91 8	97.73 12	98.73 20	79.09 100	99.79 35	99.14 4	96.86 106	98.83 42

EIA-MVS		91.73 108	92.05 96	90.78 237	94.52 178	76.40 346	98.06 77	95.34 220	89.19 79	88.90 159	97.28 118	77.56 128	97.73 198	90.77 141	96.86 106	98.20 83

fmvsm_s_conf0.5_n_8		94.52 30	95.04 24	92.96 107	95.15 158	81.14 186	99.09 20	96.66 89	95.53 3	97.84 9	98.71 21	76.33 158	99.81 27	99.24 1	96.85 108	97.92 110

SR-MVS-dyc-post		91.29 122	91.45 107	90.80 235	97.76 73	76.03 352	96.20 238	95.44 211	80.56 312	90.72 129	97.84 85	75.76 173	98.61 144	91.99 119	96.79 109	97.75 126

RE-MVS-def			91.18 115		97.76 73	76.03 352	96.20 238	95.44 211	80.56 312	90.72 129	97.84 85	73.36 219		91.99 119	96.79 109	97.75 126

jason		92.73 73	92.23 90	94.21 46	90.50 337	87.30 31	98.65 43	95.09 231	90.61 59	92.76 94	97.13 124	75.28 189	97.30 247	93.32 97	96.75 111	98.02 97
jason: jason.
test_fmvsmconf_n		93.99 44	94.36 39	92.86 112	92.82 251	81.12 187	99.26 6	96.37 135	93.47 22	95.16 54	98.21 55	79.00 101	99.64 70	98.21 20	96.73 112	97.83 119

test_vis1_n_1920		89.95 159	90.59 125	88.03 318	92.36 267	68.98 425	99.12 16	94.34 291	93.86 19	93.64 80	97.01 132	51.54 409	99.59 76	96.76 52	96.71 113	95.53 259

fmvsm_s_conf0.5_n_3		93.95 45	94.53 33	92.20 161	94.41 187	80.04 237	98.90 33	95.96 172	94.53 12	97.63 18	98.58 26	75.95 168	99.79 35	98.25 18	96.60 114	96.77 215

xiu_mvs_v2_base		93.92 46	93.26 62	95.91 11	95.07 161	92.02 6	98.19 67	95.68 194	92.06 39	96.01 45	98.14 62	70.83 258	98.96 129	96.74 53	96.57 115	96.76 217

test_fmvsmconf0.1_n		93.08 61	93.22 64	92.65 125	88.45 380	80.81 204	99.00 28	95.11 230	93.21 24	94.00 75	97.91 81	76.84 145	99.59 76	97.91 29	96.55 116	97.54 148

MVS_111021_LR		91.60 114	91.64 104	91.47 208	95.74 133	78.79 279	96.15 243	96.77 71	88.49 89	88.64 165	97.07 129	72.33 232	99.19 113	93.13 104	96.48 117	96.43 227

PAPR		92.74 72	92.17 93	94.45 38	98.89 24	84.87 85	97.20 144	96.20 151	87.73 112	88.40 169	98.12 63	78.71 107	99.76 44	87.99 193	96.28 118	98.74 47

fmvsm_s_conf0.5_n_5		93.57 52	93.75 48	93.01 104	92.87 250	82.73 130	98.93 32	95.90 180	90.96 55	95.61 48	98.39 45	76.57 151	99.63 72	98.32 15	96.24 119	96.68 221

test_fmvsmvis_n_1920		92.12 98	92.10 95	92.17 163	90.87 328	81.04 190	98.34 61	93.90 325	92.71 28	87.24 191	97.90 82	74.83 196	99.72 57	96.96 49	96.20 120	95.76 251

test_cas_vis1_n_1920		89.90 160	90.02 147	89.54 278	90.14 348	74.63 369	98.71 40	94.43 283	93.04 26	92.40 98	96.35 152	53.41 405	99.08 123	95.59 64	96.16 121	94.90 276

Vis-MVSNet		88.67 197	87.82 198	91.24 218	92.68 255	78.82 272	96.95 174	93.85 329	87.55 117	87.07 196	95.13 200	63.43 322	97.21 254	77.58 307	96.15 122	97.70 132
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
balanced_ft_v1		92.00 101	91.12 116	94.64 34	96.35 108	86.78 34	94.96 315	94.70 253	87.65 116	90.20 137	93.01 271	69.71 267	98.02 180	97.40 42	96.13 123	99.11 28

EPNet		94.06 43	94.15 44	93.76 62	97.27 97	84.35 92	98.29 63	97.64 14	94.57 11	95.36 50	96.88 136	79.96 89	99.12 120	91.30 127	96.11 124	97.82 121
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
API-MVS		90.18 154	88.97 170	93.80 60	98.66 32	82.95 125	97.50 122	95.63 198	75.16 392	86.31 210	97.69 91	72.49 229	99.90 8	81.26 266	96.07 125	98.56 60

QAPM		86.88 243	84.51 266	93.98 54	94.04 202	85.89 49	97.19 145	96.05 163	73.62 404	75.12 359	95.62 174	62.02 336	99.74 52	70.88 373	96.06 126	96.30 234

fmvsm_l_conf0.5_n_a		94.91 17	95.30 19	93.72 67	94.50 183	84.30 94	99.14 14	96.00 167	91.94 42	97.91 7	98.60 25	84.78 41	99.77 42	98.84 8	96.03 127	97.08 197

1314		88.94 188	87.20 216	94.17 50	93.21 229	85.73 52	93.33 363	96.64 93	82.89 268	75.98 348	96.36 151	66.83 296	99.39 93	83.52 243	96.02 128	97.39 170

BP-MVS1		93.55 53	93.50 57	93.71 68	92.64 260	85.39 64	97.78 96	96.84 61	89.52 75	92.00 107	97.06 130	88.21 22	98.03 179	91.45 126	96.00 129	97.70 132

MS-PatchMatch		83.05 318	81.82 319	86.72 350	89.64 361	79.10 265	94.88 318	94.59 269	79.70 337	70.67 399	89.65 325	50.43 416	96.82 286	70.82 376	95.99 130	84.25 446

CHOSEN 280x420		91.71 111	91.85 98	91.29 215	94.94 165	82.69 131	87.89 432	96.17 154	85.94 171	87.27 190	94.31 235	90.27 8	95.65 341	94.04 86	95.86 131	95.53 259

OpenMVS	79.58 14	86.09 258	83.62 287	93.50 82	90.95 325	86.71 37	97.44 126	95.83 186	75.35 389	72.64 382	95.72 165	57.42 380	99.64 70	71.41 367	95.85 132	94.13 295

PVSNet_Blended		93.13 58	92.98 68	93.57 78	97.47 83	83.86 100	99.32 3	96.73 78	91.02 54	89.53 147	96.21 154	76.42 155	99.57 80	94.29 82	95.81 133	97.29 178

fmvsm_l_conf0.5_n		94.89 19	95.24 20	93.86 58	94.42 186	84.61 88	99.13 15	96.15 155	92.06 39	97.92 5	98.52 33	84.52 44	99.74 52	98.76 10	95.67 134	97.22 180

CHOSEN 1792x2688		91.07 129	90.21 139	93.64 73	95.18 156	83.53 112	96.26 232	96.13 156	88.92 81	84.90 227	93.10 269	72.86 223	99.62 74	88.86 176	95.67 134	97.79 123

fmvsm_s_conf0.5_n_4		93.59 50	94.32 40	91.41 210	93.89 205	79.24 258	98.89 34	96.53 111	92.82 27	97.37 21	98.47 38	77.21 139	99.78 38	98.11 25	95.59 136	95.21 270

test_fmvsmconf0.01_n		91.08 128	90.68 124	92.29 152	82.43 444	80.12 234	97.94 84	93.93 321	92.07 38	91.97 108	97.60 100	67.56 286	99.53 84	97.09 47	95.56 137	97.21 183

ETV-MVS		92.72 75	92.87 71	92.28 153	94.54 177	81.89 163	97.98 81	95.21 228	89.77 72	93.11 87	96.83 138	77.23 137	97.50 224	95.74 61	95.38 138	97.44 165

114514_t		88.79 195	87.57 207	92.45 138	98.21 57	81.74 170	96.99 166	95.45 210	75.16 392	82.48 266	95.69 168	68.59 278	98.50 153	80.33 271	95.18 139	97.10 192

CANet_DTU		90.98 131	90.04 146	93.83 59	94.76 171	86.23 42	96.32 228	93.12 380	93.11 25	93.71 78	96.82 140	63.08 325	99.48 89	84.29 227	95.12 140	95.77 250

DP-MVS Recon		91.72 110	90.85 120	94.34 40	99.50 1	85.00 82	98.51 49	95.96 172	80.57 311	88.08 178	97.63 99	76.84 145	99.89 10	85.67 217	94.88 141	98.13 91

test2506		90.96 132	90.39 132	92.65 125	93.54 215	82.46 140	96.37 221	97.35 19	86.78 146	87.55 184	95.25 187	77.83 124	97.50 224	84.07 229	94.80 142	97.98 105

ECVR-MVS		88.35 208	87.25 215	91.65 197	93.54 215	79.40 254	96.56 206	90.78 425	86.78 146	85.57 218	95.25 187	57.25 381	97.56 211	84.73 225	94.80 142	97.98 105

fmvsm_s_conf0.5_n		93.69 48	94.13 45	92.34 147	94.56 175	82.01 154	99.07 22	97.13 33	92.09 37	96.25 39	98.53 31	76.47 153	99.80 31	98.39 14	94.71 144	95.22 269

test1111		88.11 213	87.04 221	91.35 212	93.15 232	78.79 279	96.57 204	90.78 425	86.88 142	85.04 224	95.20 194	57.23 382	97.39 239	83.88 231	94.59 145	97.87 114

fmvsm_s_conf0.1_n		92.93 65	93.16 65	92.24 155	90.52 336	81.92 160	98.42 54	96.24 147	91.17 49	96.02 44	98.35 50	75.34 188	99.74 52	97.84 33	94.58 146	95.05 274

BH-w/o		88.24 211	87.47 211	90.54 244	95.03 164	78.54 285	97.41 131	93.82 334	84.08 232	78.23 315	94.51 229	69.34 271	97.21 254	80.21 275	94.58 146	95.87 244

fmvsm_s_conf0.5_n_2		92.97 63	93.38 61	91.73 193	94.10 199	80.64 209	98.96 30	95.89 181	94.09 16	97.05 25	98.40 44	68.92 276	99.80 31	98.53 13	94.50 148	94.74 282

MVS_Test		90.29 153	89.18 164	93.62 75	95.23 150	84.93 83	94.41 328	94.66 261	84.31 223	90.37 136	91.02 304	75.13 191	97.82 194	83.11 247	94.42 149	98.12 92

Vis-MVSNet (Re-imp)		88.88 191	88.87 175	88.91 289	93.89 205	74.43 372	96.93 176	94.19 309	84.39 221	83.22 260	95.67 169	78.24 115	94.70 392	78.88 291	94.40 150	97.61 142

test_fmvs1		87.79 224	88.52 184	85.62 368	92.98 242	64.31 446	97.88 89	92.42 391	87.95 105	92.24 101	95.82 162	47.94 427	98.44 161	95.31 70	94.09 151	94.09 296

UGNet		87.73 226	86.55 233	91.27 216	95.16 157	79.11 264	96.35 225	96.23 148	88.14 100	87.83 183	90.48 312	50.65 414	99.09 122	80.13 276	94.03 152	95.60 255
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
PVSNet	82.34 9	89.02 185	87.79 199	92.71 122	95.49 142	81.50 179	97.70 103	97.29 20	87.76 111	85.47 220	95.12 201	56.90 383	98.90 135	80.33 271	94.02 153	97.71 131

TSAR-MVS + GP.		94.35 35	94.50 34	93.89 57	97.38 94	83.04 123	98.10 73	95.29 224	91.57 44	93.81 77	97.45 106	86.64 30	99.43 92	96.28 54	94.01 154	99.20 25

GDP-MVS		92.85 70	92.55 80	93.75 63	92.82 251	85.76 51	97.63 107	95.05 234	88.34 94	93.15 86	97.10 127	86.92 28	98.01 182	87.95 194	94.00 155	97.47 159

PVSNet_Blended_VisFu		91.24 123	90.77 122	92.66 124	95.09 159	82.40 142	97.77 97	95.87 185	88.26 96	86.39 209	93.94 251	76.77 148	99.27 101	88.80 182	94.00 155	96.31 233

KinetiMVS		89.13 182	87.95 195	92.65 125	92.16 287	82.39 144	97.04 164	96.05 163	86.59 153	88.08 178	94.85 218	61.54 341	98.38 163	81.28 265	93.99 157	97.19 186

RRT-MVS		89.67 167	88.67 176	92.67 123	94.44 185	81.08 189	94.34 332	94.45 280	86.05 164	85.79 216	92.39 279	63.39 323	98.16 174	93.22 100	93.95 158	98.76 46

PMMVS		89.46 172	89.92 151	88.06 316	94.64 172	69.57 422	96.22 236	94.95 237	87.27 129	91.37 118	96.54 148	65.88 302	97.39 239	88.54 186	93.89 159	97.23 179

BH-untuned		86.95 242	85.94 239	89.99 263	94.52 178	77.46 325	96.78 189	93.37 369	81.80 289	76.62 335	93.81 257	66.64 297	97.02 266	76.06 326	93.88 160	95.48 261

BH-RMVSNet		86.84 244	85.28 254	91.49 207	95.35 147	80.26 227	96.95 174	92.21 396	82.86 270	81.77 281	95.46 181	59.34 354	97.64 203	69.79 380	93.81 161	96.57 224

fmvsm_s_conf0.1_n_2		92.26 96	92.48 82	91.60 201	92.29 277	80.55 214	98.73 38	94.33 294	93.80 20	96.18 41	98.11 64	66.93 294	99.75 49	98.19 21	93.74 162	94.50 289

fmvsm_s_conf0.5_n_a		93.34 56	93.71 50	92.22 158	93.38 224	81.71 172	98.86 35	96.98 46	91.64 43	96.85 29	98.55 27	75.58 177	99.77 42	97.88 32	93.68 163	95.18 271

Effi-MVS+		90.70 140	89.90 152	93.09 101	93.61 212	83.48 113	95.20 302	92.79 385	83.22 258	91.82 111	95.70 166	71.82 243	97.48 226	91.25 128	93.67 164	98.32 73

IS-MVSNet		88.67 197	88.16 192	90.20 257	93.61 212	76.86 337	96.77 191	93.07 381	84.02 234	83.62 253	95.60 175	74.69 201	96.24 310	78.43 295	93.66 165	97.49 157

test_fmvs1_n		86.34 254	86.72 229	85.17 376	87.54 392	63.64 451	96.91 178	92.37 393	87.49 119	91.33 119	95.58 176	40.81 456	98.46 157	95.00 73	93.49 166	93.41 310

AdaColmap		88.81 193	87.61 205	92.39 144	99.33 4	79.95 238	96.70 197	95.58 199	77.51 368	83.05 263	96.69 146	61.90 339	99.72 57	84.29 227	93.47 167	97.50 156

fmvsm_s_conf0.1_n_a		92.38 92	92.49 81	92.06 170	88.08 385	81.62 177	97.97 83	96.01 166	90.62 58	96.58 35	98.33 51	74.09 208	99.71 60	97.23 45	93.46 168	94.86 278

xiu_mvs_v1_base_debu		90.54 144	89.54 157	93.55 79	92.31 269	87.58 27	96.99 166	94.87 242	87.23 130	93.27 82	97.56 102	57.43 377	98.32 166	92.72 108	93.46 168	94.74 282

xiu_mvs_v1_base		90.54 144	89.54 157	93.55 79	92.31 269	87.58 27	96.99 166	94.87 242	87.23 130	93.27 82	97.56 102	57.43 377	98.32 166	92.72 108	93.46 168	94.74 282

xiu_mvs_v1_base_debi		90.54 144	89.54 157	93.55 79	92.31 269	87.58 27	96.99 166	94.87 242	87.23 130	93.27 82	97.56 102	57.43 377	98.32 166	92.72 108	93.46 168	94.74 282

mvs_anonymous		88.68 196	87.62 204	91.86 181	94.80 170	81.69 173	93.53 358	94.92 239	82.03 287	78.87 309	90.43 314	75.77 172	95.34 355	85.04 222	93.16 172	98.55 62

test_vis1_n		85.60 270	85.70 244	85.33 373	84.79 425	64.98 444	96.83 182	91.61 409	87.36 125	91.00 126	94.84 219	36.14 463	97.18 256	95.66 62	93.03 173	93.82 301

LCM-MVSNet-Re		83.75 306	83.54 289	84.39 391	93.54 215	64.14 448	92.51 378	84.03 470	83.90 240	66.14 428	86.59 376	67.36 289	92.68 422	84.89 224	92.87 174	96.35 229

casdiffmvs_mvg		91.13 126	90.45 130	93.17 97	92.99 241	83.58 111	97.46 125	94.56 270	87.69 113	87.19 193	94.98 210	74.50 203	97.60 205	91.88 124	92.79 175	98.34 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
casdiffmvs		90.95 133	90.39 132	92.63 128	92.82 251	82.53 134	96.83 182	94.47 277	87.69 113	88.47 167	95.56 177	74.04 209	97.54 218	90.90 136	92.74 176	97.83 119
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TAPA-MVS	81.61 12	85.02 284	83.67 282	89.06 285	96.79 102	73.27 384	95.92 255	94.79 250	74.81 395	80.47 291	96.83 138	71.07 252	98.19 172	49.82 465	92.57 177	95.71 252
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
diffmvs		91.17 125	90.74 123	92.44 140	93.11 236	82.50 139	96.25 233	93.62 356	87.79 110	90.40 135	95.93 159	73.44 218	97.42 234	93.62 92	92.55 178	97.41 167
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPMVS		87.47 236	85.90 241	92.18 162	95.41 144	82.26 147	87.00 439	96.28 143	85.88 173	84.23 239	85.57 395	75.07 193	96.26 307	71.14 372	92.50 179	98.03 96

LS3D		82.22 333	79.94 348	89.06 285	97.43 88	74.06 376	93.20 369	92.05 398	61.90 458	73.33 375	95.21 193	59.35 353	99.21 107	54.54 451	92.48 180	93.90 300

diffmvs_AUTHOR		90.86 137	90.41 131	92.24 155	92.01 297	82.22 148	96.18 240	93.64 354	87.28 127	90.46 134	95.64 171	72.82 224	97.39 239	93.17 101	92.46 181	97.11 190

Elysia		85.62 268	83.66 283	91.51 204	88.76 371	82.21 149	95.15 306	94.70 253	76.96 378	84.13 240	92.20 283	50.81 412	97.26 251	77.81 298	92.42 182	95.06 272

StellarMVS		85.62 268	83.66 283	91.51 204	88.76 371	82.21 149	95.15 306	94.70 253	76.96 378	84.13 240	92.20 283	50.81 412	97.26 251	77.81 298	92.42 182	95.06 272

ACMMP		90.39 148	89.97 148	91.64 198	97.58 80	78.21 300	96.78 189	96.72 80	84.73 208	84.72 231	97.23 120	71.22 250	99.63 72	88.37 191	92.41 184	97.08 197
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
TESTMET0.1,1		89.83 164	89.34 161	91.31 213	92.54 264	80.19 231	97.11 156	96.57 103	86.15 160	86.85 204	91.83 295	79.32 93	96.95 274	81.30 264	92.35 185	96.77 215

viewmanbaseed2359cas		90.74 139	90.07 144	92.76 118	92.98 242	82.93 126	96.53 207	94.28 297	87.08 136	88.96 157	95.64 171	72.03 241	97.58 209	90.85 138	92.26 186	97.76 125

PLC	83.97 7	88.00 218	87.38 213	89.83 271	98.02 63	76.46 343	97.16 150	94.43 283	79.26 347	81.98 276	96.28 153	69.36 270	99.27 101	77.71 304	92.25 187	93.77 302
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
baseline		90.76 138	90.10 142	92.74 120	92.90 249	82.56 133	94.60 325	94.56 270	87.69 113	89.06 156	95.67 169	73.76 213	97.51 223	90.43 150	92.23 188	98.16 87

PatchMatch-RL		85.00 285	83.66 283	89.02 287	95.86 127	74.55 371	92.49 379	93.60 357	79.30 345	79.29 306	91.47 296	58.53 360	98.45 159	70.22 378	92.17 189	94.07 297

test-LLR		88.48 203	87.98 194	89.98 264	92.26 279	77.23 330	97.11 156	95.96 172	83.76 247	86.30 211	91.38 298	72.30 233	96.78 290	80.82 267	91.92 190	95.94 241

test-mter		88.95 187	88.60 178	89.98 264	92.26 279	77.23 330	97.11 156	95.96 172	85.32 187	86.30 211	91.38 298	76.37 157	96.78 290	80.82 267	91.92 190	95.94 241

E3new		90.90 135	90.35 135	92.55 133	93.63 211	82.40 142	96.79 187	94.49 273	87.07 137	88.54 166	95.70 166	73.85 211	97.60 205	91.23 129	91.86 192	97.64 137

Fast-Effi-MVS+		87.93 220	86.94 225	90.92 230	94.04 202	79.16 262	98.26 64	93.72 349	81.29 295	83.94 247	92.90 272	69.83 265	96.68 293	76.70 317	91.74 193	96.93 204

FE-MVS		86.06 259	84.15 276	91.78 189	94.33 190	79.81 241	84.58 456	96.61 96	76.69 382	85.00 225	87.38 362	70.71 260	98.37 164	70.39 377	91.70 194	97.17 188

viewdifsd2359ckpt13		90.08 155	89.36 160	92.26 154	93.03 237	81.90 162	96.37 221	94.34 291	86.16 159	87.44 185	95.30 185	70.93 257	97.55 215	89.05 173	91.59 195	97.35 173

viewcassd2359sk11		90.66 141	90.06 145	92.47 136	93.22 228	82.21 149	96.70 197	94.47 277	86.94 140	88.22 174	95.50 179	73.15 221	97.59 207	90.86 137	91.48 196	97.60 143

UA-Net		88.92 189	88.48 185	90.24 255	94.06 201	77.18 332	93.04 371	94.66 261	87.39 124	91.09 123	93.89 252	74.92 194	98.18 173	75.83 329	91.43 197	95.35 264

PatchmatchNet		86.83 245	85.12 259	91.95 176	94.12 198	82.27 146	86.55 443	95.64 197	84.59 213	82.98 264	84.99 407	77.26 133	95.96 321	68.61 385	91.34 198	97.64 137
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
viewmacassd2359aftdt		89.89 161	89.01 169	92.52 135	91.56 310	82.46 140	96.32 228	94.06 317	86.41 154	88.11 177	95.01 207	69.68 268	97.47 227	88.73 185	91.19 199	97.63 139

SymmetryMVS		92.45 89	92.33 86	92.82 116	95.19 154	82.02 152	97.94 84	97.43 17	92.34 32	92.15 104	96.53 149	77.03 140	98.57 147	91.13 131	91.19 199	97.87 114

myMVS_eth3d28		92.72 75	92.23 90	94.21 46	96.16 115	87.46 30	97.37 134	96.99 45	88.13 101	88.18 175	95.47 180	84.12 51	98.04 178	92.46 113	91.17 201	97.14 189

viewdifsd2359ckpt09		90.00 158	89.28 163	92.15 165	93.31 226	81.38 180	96.37 221	93.64 354	86.34 156	86.62 206	95.64 171	71.58 247	97.52 221	88.93 174	91.06 202	97.54 148

PCF-MVS	84.09 5	86.77 247	85.00 261	92.08 168	92.06 295	83.07 122	92.14 385	94.47 277	79.63 338	76.90 331	94.78 220	71.15 251	99.20 112	72.87 358	91.05 203	93.98 298
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EI-MVSNet-Vis-set		91.84 107	91.77 101	92.04 172	97.60 78	81.17 185	96.61 200	96.87 58	88.20 99	89.19 152	97.55 105	78.69 108	99.14 117	90.29 155	90.94 204	95.80 245

E2		90.33 151	89.65 155	92.37 145	92.66 256	81.99 155	96.58 202	94.39 287	86.71 150	87.88 180	95.25 187	72.18 235	97.56 211	90.37 153	90.88 205	97.57 145

E3		90.33 151	89.65 155	92.37 145	92.64 260	81.99 155	96.58 202	94.39 287	86.71 150	87.87 181	95.27 186	72.17 236	97.56 211	90.37 153	90.88 205	97.57 145

CNLPA		86.96 241	85.37 251	91.72 195	97.59 79	79.34 257	97.21 142	91.05 420	74.22 399	78.90 307	96.75 144	67.21 291	98.95 131	74.68 343	90.77 207	96.88 209

UBG		92.68 82	92.35 84	93.70 69	95.61 138	85.65 58	97.25 140	97.06 40	87.92 106	89.28 151	95.03 205	86.06 35	98.07 176	92.24 115	90.69 208	97.37 171

SSM_0404		87.69 230	86.26 235	91.95 176	92.94 244	83.02 124	94.69 324	92.33 394	80.11 327	84.65 233	94.18 242	64.68 315	96.90 278	82.34 253	90.44 209	95.94 241

viewmambaseed2359dif		89.52 170	89.02 167	91.03 226	92.24 282	78.83 271	95.89 264	93.77 342	83.04 263	88.28 173	95.80 163	72.08 239	97.40 237	89.76 162	90.32 210	96.87 210

CVMVSNet		84.83 287	85.57 247	82.63 410	91.55 312	60.38 464	95.13 308	95.03 235	80.60 310	82.10 275	94.71 223	66.40 300	90.19 451	74.30 348	90.32 210	97.31 176

LuminaMVS		88.02 217	86.89 226	91.43 209	88.65 378	83.16 120	94.84 319	94.41 285	83.67 251	86.56 207	91.95 292	62.04 335	96.88 282	89.78 161	90.06 212	94.24 291

E4		89.85 162	89.06 165	92.22 158	91.88 302	81.63 176	96.43 217	94.27 298	86.32 157	87.29 189	94.97 211	70.81 259	97.52 221	89.57 166	90.00 213	97.51 155

EPNet_dtu		87.65 231	87.89 196	86.93 345	94.57 174	71.37 408	96.72 193	96.50 115	88.56 88	87.12 195	95.02 206	75.91 170	94.01 407	66.62 395	90.00 213	95.42 262
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FA-MVS(test-final)		87.71 229	86.23 237	92.17 163	94.19 193	80.55 214	87.16 438	96.07 162	82.12 285	85.98 215	88.35 347	72.04 240	98.49 154	80.26 273	89.87 215	97.48 158

baseline2		90.39 148	90.21 139	90.93 229	90.86 329	80.99 192	95.20 302	97.41 18	86.03 166	80.07 299	94.61 226	90.58 6	97.47 227	87.29 203	89.86 216	94.35 290

guyue		89.85 162	89.33 162	91.40 211	92.53 265	80.15 233	96.82 184	95.68 194	89.66 73	86.43 208	94.23 238	67.00 292	97.16 257	91.96 122	89.65 217	96.89 207

LFMVS		89.27 180	87.64 202	94.16 53	97.16 98	85.52 62	97.18 146	94.66 261	79.17 348	89.63 145	96.57 147	55.35 394	98.22 170	89.52 169	89.54 218	98.74 47

EI-MVSNet-UG-set		91.35 121	91.22 111	91.73 193	97.39 92	80.68 207	96.47 212	96.83 62	87.92 106	88.30 172	97.36 112	77.84 123	99.13 119	89.43 170	89.45 219	95.37 263

E5new		89.38 173	88.55 180	91.85 183	91.77 306	80.97 193	95.90 260	94.22 303	86.03 166	86.88 199	94.90 214	69.05 272	97.47 227	88.86 176	89.35 220	97.10 192

E5		89.38 173	88.55 180	91.85 183	91.77 306	80.97 193	95.90 260	94.22 303	86.03 166	86.88 199	94.90 214	69.05 272	97.47 227	88.86 176	89.35 220	97.10 192

E6new		89.37 175	88.55 180	91.85 183	91.75 308	80.97 193	95.90 260	94.22 303	86.03 166	86.88 199	94.91 212	69.05 272	97.47 227	88.86 176	89.34 222	97.10 192

E6		89.37 175	88.55 180	91.85 183	91.75 308	80.97 193	95.90 260	94.22 303	86.03 166	86.88 199	94.91 212	69.05 272	97.47 227	88.86 176	89.34 222	97.10 192

GeoE		86.36 253	85.20 255	89.83 271	93.17 231	76.13 349	97.53 118	92.11 397	79.58 339	80.99 285	94.01 247	66.60 298	96.17 313	73.48 355	89.30 224	97.20 185

viewdifsd2359ckpt07		89.04 184	88.30 188	91.27 216	92.32 268	78.90 269	95.89 264	93.77 342	84.48 219	85.18 222	95.16 197	69.83 265	97.70 199	88.75 184	89.29 225	97.22 180

UWE-MVS		88.56 202	88.91 174	87.50 332	94.17 194	72.19 393	95.82 271	97.05 41	84.96 203	84.78 229	93.51 263	81.33 71	94.75 390	79.43 282	89.17 226	95.57 257

sss		90.87 136	89.96 149	93.60 76	94.15 195	83.84 102	97.14 153	98.13 7	85.93 172	89.68 143	96.09 157	71.67 244	99.30 100	87.69 199	89.16 227	97.66 135

HY-MVS	84.06 6	91.63 112	90.37 134	95.39 20	96.12 117	88.25 18	90.22 408	97.58 15	88.33 95	90.50 132	91.96 290	79.26 96	99.06 124	90.29 155	89.07 228	98.88 41

testing11		92.48 88	92.04 97	93.78 61	95.94 124	86.00 45	97.56 115	97.08 38	87.52 118	89.32 150	95.40 182	84.60 42	98.02 180	91.93 123	89.04 229	97.32 174

thisisatest0515		90.95 133	90.26 136	93.01 104	94.03 204	84.27 96	97.91 87	96.67 86	83.18 259	86.87 203	95.51 178	88.66 17	97.85 193	80.46 270	89.01 230	96.92 206

CDS-MVSNet		89.50 171	88.96 171	91.14 223	91.94 301	80.93 199	97.09 160	95.81 187	84.26 228	84.72 231	94.20 241	80.31 80	95.64 342	83.37 244	88.96 231	96.85 211
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
VNet		92.11 99	91.22 111	94.79 29	96.91 101	86.98 32	97.91 87	97.96 10	86.38 155	93.65 79	95.74 164	70.16 264	98.95 131	93.39 93	88.87 232	98.43 68

alignmvs		92.97 63	92.26 89	95.12 22	95.54 141	87.77 23	98.67 42	96.38 132	88.04 103	93.01 89	97.45 106	79.20 98	98.60 145	93.25 99	88.76 233	98.99 34

WTY-MVS		92.65 83	91.68 102	95.56 15	96.00 120	88.90 13	98.23 65	97.65 13	88.57 87	89.82 141	97.22 121	79.29 95	99.06 124	89.57 166	88.73 234	98.73 51

icg_test_0407_2		87.55 233	86.59 232	90.43 246	92.30 272	78.81 274	92.17 384	93.84 330	85.14 194	83.68 251	94.49 230	67.75 282	95.02 382	81.33 260	88.61 235	97.46 160

IMVS_0407		87.82 222	86.72 229	91.14 223	92.30 272	78.81 274	93.34 362	93.84 330	85.14 194	83.68 251	94.49 230	67.75 282	97.14 262	81.33 260	88.61 235	97.46 160

IMVS_0404		85.34 276	83.69 280	90.29 253	92.30 272	78.81 274	90.62 405	93.84 330	85.14 194	72.51 385	94.49 230	54.36 401	94.61 395	81.33 260	88.61 235	97.46 160

IMVS_0403		88.07 214	87.02 222	91.24 218	92.30 272	78.81 274	93.62 354	93.84 330	85.14 194	84.36 236	94.49 230	69.49 269	97.46 233	81.33 260	88.61 235	97.46 160

ETVMVS		90.99 130	90.26 136	93.19 96	95.81 129	85.64 59	96.97 171	97.18 28	85.43 184	88.77 163	94.86 217	82.00 69	96.37 303	82.70 250	88.60 239	97.57 145

sasdasda		92.27 94	91.22 111	95.41 18	95.80 130	88.31 16	97.09 160	94.64 264	88.49 89	92.99 90	97.31 113	72.68 226	98.57 147	93.38 95	88.58 240	99.36 16

canonicalmvs		92.27 94	91.22 111	95.41 18	95.80 130	88.31 16	97.09 160	94.64 264	88.49 89	92.99 90	97.31 113	72.68 226	98.57 147	93.38 95	88.58 240	99.36 16

test_yl		91.46 116	90.53 127	94.24 44	97.41 89	85.18 71	98.08 74	97.72 11	80.94 301	89.85 139	96.14 155	75.61 174	98.81 139	90.42 151	88.56 242	98.74 47

DCV-MVSNet		91.46 116	90.53 127	94.24 44	97.41 89	85.18 71	98.08 74	97.72 11	80.94 301	89.85 139	96.14 155	75.61 174	98.81 139	90.42 151	88.56 242	98.74 47

mamba_0408		85.26 279	83.10 298	91.74 192	92.94 244	82.53 134	72.52 484	91.77 403	80.36 319	83.50 254	94.01 247	64.97 311	96.90 278	79.37 283	88.51 244	95.79 247

SSM_04072		84.64 290	83.10 298	89.25 282	92.94 244	82.53 134	72.52 484	91.77 403	80.36 319	83.50 254	94.01 247	64.97 311	89.41 454	79.37 283	88.51 244	95.79 247

SSM_0407		87.33 238	85.87 242	91.71 196	92.94 244	82.53 134	94.30 335	92.33 394	80.11 327	83.50 254	94.18 242	64.68 315	96.80 289	82.34 253	88.51 244	95.79 247

MGCFI-Net		91.95 102	91.03 118	94.72 32	95.68 135	86.38 38	96.93 176	94.48 274	88.25 97	92.78 93	97.24 119	72.34 231	98.46 157	93.13 104	88.43 247	99.32 19

HyFIR lowres test		89.36 177	88.60 178	91.63 200	94.91 167	80.76 206	95.60 283	95.53 202	82.56 277	84.03 243	91.24 301	78.03 119	96.81 287	87.07 206	88.41 248	97.32 174

testing222		91.09 127	90.49 129	92.87 111	95.82 128	85.04 79	96.51 210	97.28 21	86.05 164	89.13 153	95.34 184	80.16 85	96.62 296	85.82 215	88.31 249	96.96 202

TAMVS		88.48 203	87.79 199	90.56 242	91.09 323	79.18 261	96.45 214	95.88 183	83.64 253	83.12 261	93.33 264	75.94 169	95.74 337	82.40 252	88.27 250	96.75 218

EPP-MVSNet		89.76 165	89.72 154	89.87 269	93.78 207	76.02 354	97.22 141	96.51 113	79.35 342	85.11 223	95.01 207	84.82 40	97.10 264	87.46 202	88.21 251	96.50 225

MVS-HIRNet		71.36 425	67.00 431	84.46 389	90.58 335	69.74 420	79.15 470	87.74 449	46.09 483	61.96 449	50.50 487	45.14 436	95.64 342	53.74 453	88.11 252	88.00 398

testing99		91.91 104	91.35 108	93.60 76	95.98 122	85.70 53	97.31 138	96.92 55	86.82 144	88.91 158	95.25 187	84.26 50	97.89 192	88.80 182	87.94 253	97.21 183

testing91		91.90 105	91.31 110	93.66 72	95.99 121	85.68 55	97.39 133	96.89 56	86.75 148	88.85 160	95.23 191	83.93 54	97.90 191	88.91 175	87.89 254	97.41 167

TR-MVS		86.30 255	84.93 263	90.42 247	94.63 173	77.58 323	96.57 204	93.82 334	80.30 322	82.42 268	95.16 197	58.74 358	97.55 215	74.88 341	87.82 255	96.13 237

UWE-MVS-28		85.41 275	86.36 234	82.59 411	91.12 322	66.81 438	93.88 348	97.03 42	83.86 243	78.55 310	93.84 254	77.76 126	88.55 458	73.47 356	87.69 256	92.41 315

cascas		86.50 249	84.48 268	92.55 133	92.64 260	85.95 46	97.04 164	95.07 233	75.32 390	80.50 290	91.02 304	54.33 402	97.98 184	86.79 211	87.62 257	93.71 303

OMC-MVS		88.80 194	88.16 192	90.72 238	95.30 148	77.92 310	94.81 321	94.51 272	86.80 145	84.97 226	96.85 137	67.53 287	98.60 145	85.08 221	87.62 257	95.63 253

SCA		85.63 267	83.64 286	91.60 201	92.30 272	81.86 165	92.88 375	95.56 201	84.85 204	82.52 265	85.12 405	58.04 365	95.39 352	73.89 351	87.58 259	97.54 148

AstraMVS		88.99 186	88.35 187	90.92 230	90.81 332	78.29 293	96.73 192	94.24 300	89.96 69	86.13 213	95.04 204	62.12 334	97.41 235	92.54 112	87.57 260	97.06 199

thisisatest0530		89.65 168	89.02 167	91.53 203	93.46 222	80.78 205	96.52 208	96.67 86	81.69 292	83.79 249	94.90 214	88.85 16	97.68 201	77.80 300	87.49 261	96.14 236

WB-MVSnew		84.08 301	83.51 290	85.80 361	91.34 317	76.69 341	95.62 282	96.27 144	81.77 290	81.81 280	92.81 273	58.23 362	94.70 392	66.66 394	87.06 262	85.99 431

VDDNet		86.44 250	84.51 266	92.22 158	91.56 310	81.83 166	97.10 159	94.64 264	69.50 436	87.84 182	95.19 195	48.01 425	97.92 190	89.82 160	86.92 263	96.89 207

VDD-MVS		88.28 210	87.02 222	92.06 170	95.09 159	80.18 232	97.55 117	94.45 280	83.09 261	89.10 155	95.92 161	47.97 426	98.49 154	93.08 106	86.91 264	97.52 154

thres200		88.92 189	87.65 201	92.73 121	96.30 110	85.62 60	97.85 90	98.86 1	84.38 222	84.82 228	93.99 250	75.12 192	98.01 182	70.86 374	86.67 265	94.56 288

DP-MVS		81.47 343	78.28 362	91.04 225	98.14 59	78.48 286	95.09 313	86.97 452	61.14 464	71.12 396	92.78 276	59.59 350	99.38 94	53.11 455	86.61 266	95.27 268

F-COLMAP		84.50 295	83.44 292	87.67 324	95.22 151	72.22 391	95.95 252	93.78 339	75.74 387	76.30 342	95.18 196	59.50 352	98.45 159	72.67 360	86.59 267	92.35 317

mvsany_test1		87.58 232	88.22 189	85.67 366	89.78 354	67.18 433	95.25 299	87.93 447	83.96 237	88.79 161	97.06 130	72.52 228	94.53 398	92.21 116	86.45 268	95.30 266

tttt0517		88.57 201	88.19 191	89.71 275	93.00 238	75.99 355	95.67 278	96.67 86	80.78 306	81.82 279	94.40 234	88.97 15	97.58 209	76.05 327	86.31 269	95.57 257

CR-MVSNet		83.53 309	81.36 326	90.06 260	90.16 346	79.75 244	79.02 471	91.12 417	84.24 229	82.27 273	80.35 444	75.45 180	93.67 414	63.37 415	86.25 270	96.75 218

RPMNet		79.85 361	75.92 381	91.64 198	90.16 346	79.75 244	79.02 471	95.44 211	58.43 473	82.27 273	72.55 474	73.03 222	98.41 162	46.10 472	86.25 270	96.75 218

thres100view900		88.30 209	86.95 224	92.33 149	96.10 118	84.90 84	97.14 153	98.85 2	82.69 274	83.41 257	93.66 259	75.43 182	97.93 185	69.04 382	86.24 272	94.17 292

tfpn200view9		88.48 203	87.15 217	92.47 136	96.21 113	85.30 69	97.44 126	98.85 2	83.37 256	83.99 244	93.82 255	75.36 185	97.93 185	69.04 382	86.24 272	94.17 292

thres400		88.42 206	87.15 217	92.23 157	96.21 113	85.30 69	97.44 126	98.85 2	83.37 256	83.99 244	93.82 255	75.36 185	97.93 185	69.04 382	86.24 272	93.45 308

SD_0403		81.29 346	81.13 330	81.78 419	90.20 344	60.43 463	89.97 410	91.31 416	83.87 241	71.78 389	93.08 270	63.86 319	89.61 453	60.00 428	86.07 275	95.30 266

CostFormer		89.08 183	88.39 186	91.15 222	93.13 234	79.15 263	88.61 424	96.11 158	83.14 260	89.58 146	86.93 371	83.83 56	96.87 283	88.22 192	85.92 276	97.42 166

thres600view7		88.06 215	86.70 231	92.15 165	96.10 118	85.17 75	97.14 153	98.85 2	82.70 273	83.41 257	93.66 259	75.43 182	97.82 194	67.13 391	85.88 277	93.45 308

Effi-MVS+-dtu		84.61 292	84.90 264	83.72 398	91.96 299	63.14 454	94.95 316	93.34 370	85.57 179	79.79 300	87.12 368	61.99 337	95.61 345	83.55 240	85.83 278	92.41 315

JIA-IIPM		79.00 371	77.20 370	84.40 390	89.74 358	64.06 449	75.30 479	95.44 211	62.15 457	81.90 277	59.08 484	78.92 102	95.59 346	66.51 398	85.78 279	93.54 305

tpm2		87.35 237	86.26 235	90.62 240	92.93 248	78.67 282	88.06 431	95.99 169	79.33 343	87.40 186	86.43 382	80.28 81	96.40 301	80.23 274	85.73 280	96.79 213

1112_ss		88.60 200	87.47 211	92.00 174	93.21 229	80.97 193	96.47 212	92.46 388	83.64 253	80.86 287	97.30 116	80.24 82	97.62 204	77.60 306	85.49 281	97.40 169

Test_1112_low_res		88.03 216	86.73 228	91.94 178	93.15 232	80.88 202	96.44 215	92.41 392	83.59 255	80.74 289	91.16 302	80.18 83	97.59 207	77.48 309	85.40 282	97.36 172

GA-MVS		85.79 264	84.04 278	91.02 228	89.47 366	80.27 226	96.90 179	94.84 246	85.57 179	80.88 286	89.08 331	56.56 387	96.47 300	77.72 303	85.35 283	96.34 230

tpmrst		88.36 207	87.38 213	91.31 213	94.36 189	79.92 239	87.32 436	95.26 226	85.32 187	88.34 170	86.13 388	80.60 77	96.70 292	83.78 233	85.34 284	97.30 177

MDTV_nov1_ep13			83.69 280		94.09 200	81.01 191	86.78 441	96.09 159	83.81 245	84.75 230	84.32 412	74.44 204	96.54 297	63.88 411	85.07 285

Fast-Effi-MVS+-dtu		83.33 312	82.60 308	85.50 370	89.55 364	69.38 423	96.09 247	91.38 411	82.30 281	75.96 349	91.41 297	56.71 384	95.58 347	75.13 340	84.90 286	91.54 318

testing3-2		91.37 119	91.01 119	92.44 140	95.93 125	83.77 103	98.83 36	97.45 16	86.88 142	86.63 205	94.69 225	84.57 43	97.75 197	89.65 164	84.44 287	95.80 245

PatchT		79.75 362	76.85 374	88.42 298	89.55 364	75.49 363	77.37 475	94.61 267	63.07 453	82.46 267	73.32 471	75.52 179	93.41 419	51.36 459	84.43 288	96.36 228

XVG-OURS-SEG-HR		85.74 265	85.16 258	87.49 334	90.22 343	71.45 406	91.29 397	94.09 315	81.37 294	83.90 248	95.22 192	60.30 347	97.53 220	85.58 218	84.42 289	93.50 306

tpm cat1		83.63 308	81.38 325	90.39 248	93.53 220	78.19 302	85.56 450	95.09 231	70.78 429	78.51 311	83.28 422	74.80 197	97.03 265	66.77 393	84.05 290	95.95 240

DSMNet-mixed		73.13 414	72.45 408	75.19 453	77.51 466	46.82 484	85.09 454	82.01 477	67.61 445	69.27 413	81.33 439	50.89 411	86.28 471	54.54 451	83.80 291	92.46 313

ADS-MVSNet2		79.57 365	77.53 368	85.71 365	93.78 207	72.13 394	79.48 467	86.11 459	73.09 410	80.14 296	79.99 447	62.15 332	90.14 452	59.49 430	83.52 292	94.85 279

ADS-MVSNet		81.26 347	78.36 361	89.96 266	93.78 207	79.78 242	79.48 467	93.60 357	73.09 410	80.14 296	79.99 447	62.15 332	95.24 363	59.49 430	83.52 292	94.85 279

XVG-OURS		85.18 280	84.38 271	87.59 328	90.42 339	71.73 403	91.06 401	94.07 316	82.00 288	83.29 259	95.08 203	56.42 388	97.55 215	83.70 238	83.42 294	93.49 307

dp		84.30 298	82.31 311	90.28 254	94.24 192	77.97 306	86.57 442	95.53 202	79.94 333	80.75 288	85.16 403	71.49 249	96.39 302	63.73 412	83.36 295	96.48 226

MSDG		80.62 357	77.77 367	89.14 284	93.43 223	77.24 329	91.89 388	90.18 429	69.86 435	68.02 416	91.94 293	52.21 408	98.84 137	59.32 432	83.12 296	91.35 319

MIMVSNet		79.18 370	75.99 380	88.72 294	87.37 393	80.66 208	79.96 465	91.82 401	77.38 370	74.33 365	81.87 435	41.78 448	90.74 446	66.36 400	83.10 297	94.76 281

HQP3-MVS								94.80 248							83.01 298

HQP-MVS		87.91 221	87.55 208	88.98 288	92.08 292	78.48 286	97.63 107	94.80 248	90.52 60	82.30 269	94.56 227	65.40 306	97.32 245	87.67 200	83.01 298	91.13 320

plane_prior						77.96 307	97.52 121		90.36 65						82.96 300

CLD-MVS		87.97 219	87.48 210	89.44 279	92.16 287	80.54 218	98.14 68	94.92 239	91.41 46	79.43 304	95.40 182	62.34 328	97.27 250	90.60 145	82.90 301	90.50 328
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
HQP_MVS		87.50 235	87.09 220	88.74 293	91.86 303	77.96 307	97.18 146	94.69 257	89.89 70	81.33 282	94.15 244	64.77 313	97.30 247	87.08 204	82.82 302	90.96 322

plane_prior5								94.69 257					97.30 247	87.08 204	82.82 302	90.96 322

OPM-MVS		85.84 262	85.10 260	88.06 316	88.34 382	77.83 314	95.72 274	94.20 308	87.89 109	80.45 292	94.05 246	58.57 359	97.26 251	83.88 231	82.76 304	89.09 362
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Anonymous202405211		84.41 296	81.93 317	91.85 183	96.78 103	78.41 290	97.44 126	91.34 414	70.29 431	84.06 242	94.26 237	41.09 453	98.96 129	79.46 281	82.65 305	98.17 86

ab-mvs		87.08 239	84.94 262	93.48 84	93.34 225	83.67 109	88.82 421	95.70 193	81.18 297	84.55 235	90.14 320	62.72 326	98.94 133	85.49 219	82.54 306	97.85 117

Syy-MVS		77.97 383	78.05 364	77.74 441	92.13 289	56.85 472	93.97 344	94.23 301	82.43 278	73.39 371	93.57 261	57.95 368	87.86 463	32.40 485	82.34 307	88.51 384

myMVS_eth3d		81.93 336	82.18 312	81.18 422	92.13 289	67.18 433	93.97 344	94.23 301	82.43 278	73.39 371	93.57 261	76.98 143	87.86 463	50.53 463	82.34 307	88.51 384

ET-MVSNet_ETH3D		90.01 157	89.03 166	92.95 108	94.38 188	86.77 35	98.14 68	96.31 142	89.30 78	63.33 440	96.72 145	90.09 10	93.63 415	90.70 144	82.29 309	98.46 65

SDMVSNet		87.02 240	85.61 246	91.24 218	94.14 196	83.30 117	93.88 348	95.98 170	84.30 225	79.63 302	92.01 286	58.23 362	97.68 201	90.28 157	82.02 310	92.75 311

sd_testset		84.62 291	83.11 297	89.17 283	94.14 196	77.78 316	91.54 396	94.38 289	84.30 225	79.63 302	92.01 286	52.28 407	96.98 272	77.67 305	82.02 310	92.75 311

tpmvs		83.04 319	80.77 333	89.84 270	95.43 143	77.96 307	85.59 449	95.32 221	75.31 391	76.27 343	83.70 418	73.89 210	97.41 235	59.53 429	81.93 312	94.14 294

CMPMVS	54.94 21	75.71 401	74.56 395	79.17 434	79.69 456	55.98 474	89.59 413	93.30 371	60.28 466	53.85 473	89.07 332	47.68 430	96.33 305	76.55 320	81.02 313	85.22 437
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
dmvs_re		84.10 300	82.90 302	87.70 323	91.41 316	73.28 382	90.59 406	93.19 374	85.02 200	77.96 319	93.68 258	57.92 370	96.18 312	75.50 335	80.87 314	93.63 304

LPG-MVS_test		84.20 299	83.49 291	86.33 352	90.88 326	73.06 385	95.28 294	94.13 312	82.20 282	76.31 340	93.20 265	54.83 399	96.95 274	83.72 236	80.83 315	88.98 374

LGP-MVS_train				86.33 352	90.88 326	73.06 385		94.13 312	82.20 282	76.31 340	93.20 265	54.83 399	96.95 274	83.72 236	80.83 315	88.98 374

ACMM	80.70 13	83.72 307	82.85 304	86.31 355	91.19 319	72.12 395	95.88 266	94.29 296	80.44 315	77.02 329	91.96 290	55.24 395	97.14 262	79.30 286	80.38 317	89.67 344
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
jajsoiax		82.12 334	81.15 329	85.03 378	84.19 432	70.70 411	94.22 340	93.95 320	83.07 262	73.48 370	89.75 323	49.66 420	95.37 354	82.24 256	79.76 318	89.02 371

test_djsdf		83.00 321	82.45 310	84.64 384	84.07 434	69.78 419	94.80 322	94.48 274	80.74 307	75.41 357	87.70 357	61.32 344	95.10 374	83.77 234	79.76 318	89.04 368

ACMP	81.66 11	84.00 302	83.22 296	86.33 352	91.53 314	72.95 389	95.91 259	93.79 338	83.70 250	73.79 367	92.22 282	54.31 403	96.89 280	83.98 230	79.74 320	89.16 360
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
testing3		80.74 355	81.17 328	79.44 432	91.15 321	63.48 452	97.16 150	95.76 189	80.83 304	71.36 392	93.15 268	78.22 116	87.30 468	43.19 477	79.67 321	87.55 409

PVSNet_BlendedMVS		90.05 156	89.96 149	90.33 252	97.47 83	83.86 100	98.02 80	96.73 78	87.98 104	89.53 147	89.61 327	76.42 155	99.57 80	94.29 82	79.59 322	87.57 406

Patchmatch-test		78.25 378	74.72 393	88.83 291	91.20 318	74.10 375	73.91 482	88.70 445	59.89 469	66.82 423	85.12 405	78.38 112	94.54 397	48.84 468	79.58 323	97.86 116

mvs_tets		81.74 339	80.71 335	84.84 379	84.22 431	70.29 415	93.91 347	93.78 339	82.77 272	73.37 373	89.46 329	47.36 431	95.31 358	81.99 257	79.55 324	88.92 378

FIs		86.73 248	86.10 238	88.61 296	90.05 349	80.21 229	96.14 244	96.95 51	85.56 181	78.37 313	92.30 281	76.73 149	95.28 359	79.51 280	79.27 325	90.35 330

D2MVS		82.67 325	81.55 322	86.04 359	87.77 388	76.47 342	95.21 301	96.58 102	82.66 275	70.26 405	85.46 398	60.39 346	95.80 329	76.40 323	79.18 326	85.83 434

ACMMP++															79.05 327

PS-MVSNAJss		84.91 286	84.30 272	86.74 346	85.89 413	74.40 373	94.95 316	94.16 311	83.93 239	76.45 338	90.11 321	71.04 253	95.77 332	83.16 246	79.02 328	90.06 340

FC-MVSNet-test		85.96 260	85.39 250	87.66 325	89.38 368	78.02 304	95.65 280	96.87 58	85.12 198	77.34 322	91.94 293	76.28 160	94.74 391	77.09 312	78.82 329	90.21 333

EG-PatchMatch MVS		74.92 403	72.02 411	83.62 399	83.76 440	73.28 382	93.62 354	92.04 399	68.57 439	58.88 461	83.80 417	31.87 473	95.57 348	56.97 443	78.67 330	82.00 463

EI-MVSNet		85.80 263	85.20 255	87.59 328	91.55 312	77.41 326	95.13 308	95.36 217	80.43 317	80.33 294	94.71 223	73.72 214	95.97 318	76.96 315	78.64 331	89.39 348

MVSTER		89.25 181	88.92 173	90.24 255	95.98 122	84.66 87	96.79 187	95.36 217	87.19 133	80.33 294	90.61 311	90.02 11	95.97 318	85.38 220	78.64 331	90.09 338

anonymousdsp		80.98 353	79.97 347	84.01 392	81.73 446	70.44 414	92.49 379	93.58 359	77.10 375	72.98 379	86.31 384	57.58 376	94.90 383	79.32 285	78.63 333	86.69 419

UniMVSNet_ETH3D		80.86 354	78.75 360	87.22 341	86.31 404	72.02 396	91.95 386	93.76 344	73.51 405	75.06 361	90.16 319	43.04 444	95.66 339	76.37 324	78.55 334	93.98 298

ACMMP++_ref															78.45 335

test_fmvs2		79.59 364	79.90 349	78.67 437	82.86 443	55.82 476	95.20 302	89.55 434	81.09 299	80.12 298	89.80 322	34.31 468	93.51 417	87.82 195	78.36 336	86.69 419

Anonymous20240529		83.15 316	80.60 337	90.80 235	95.74 133	78.27 295	96.81 186	94.92 239	60.10 468	81.89 278	92.54 277	45.82 435	98.82 138	79.25 287	78.32 337	95.31 265

XVG-ACMP-BASELINE		79.38 368	77.90 366	83.81 394	84.98 424	67.14 437	89.03 420	93.18 376	80.26 325	72.87 380	88.15 351	38.55 458	96.26 307	76.05 327	78.05 338	88.02 397

tpm		85.55 271	84.47 269	88.80 292	90.19 345	75.39 364	88.79 422	94.69 257	84.83 205	83.96 246	85.21 401	78.22 116	94.68 394	76.32 325	78.02 339	96.34 230

test0.0.03 1		82.79 323	82.48 309	83.74 397	86.81 397	72.22 391	96.52 208	95.03 235	83.76 247	73.00 378	93.20 265	72.30 233	88.88 456	64.15 410	77.52 340	90.12 336

RPSCF		77.73 385	76.63 376	81.06 423	88.66 377	55.76 477	87.77 433	87.88 448	64.82 450	74.14 366	92.79 275	49.22 422	96.81 287	67.47 389	76.88 341	90.62 326

MonoMVSNet		85.68 266	84.22 274	90.03 261	88.43 381	77.83 314	92.95 374	91.46 410	87.28 127	78.11 316	85.96 390	66.31 301	94.81 388	90.71 143	76.81 342	97.46 160

usedtu_dtu_shiyan1		85.03 282	83.24 294	90.37 249	86.62 399	86.24 40	96.23 234	95.30 222	84.55 214	77.22 325	88.47 343	67.85 280	95.27 360	76.59 318	76.35 343	89.61 345

FE-MVSNET3		85.03 282	83.24 294	90.37 249	86.62 399	86.24 40	96.23 234	95.30 222	84.55 214	77.22 325	88.47 343	67.85 280	95.27 360	76.59 318	76.35 343	89.61 345

LTVRE_ROB	73.68 18	77.99 381	75.74 384	84.74 380	90.45 338	72.02 396	86.41 444	91.12 417	72.57 417	66.63 425	87.27 364	54.95 398	96.98 272	56.29 445	75.98 345	85.21 438
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
test_vis1_rt		73.96 406	72.40 409	78.64 438	83.91 436	61.16 462	95.63 281	68.18 492	76.32 383	60.09 457	74.77 465	29.01 479	97.54 218	87.74 198	75.94 346	77.22 475

OpenMVS_ROB	68.52 20	73.02 415	69.57 422	83.37 402	80.54 450	71.82 401	93.60 356	88.22 446	62.37 456	61.98 448	83.15 423	35.31 467	95.47 350	45.08 475	75.88 347	82.82 453

USDC		78.65 376	76.25 378	85.85 360	87.58 390	74.60 370	89.58 414	90.58 428	84.05 233	63.13 441	88.23 349	40.69 457	96.86 285	66.57 397	75.81 348	86.09 428

COLMAP_ROB	73.24 19	75.74 400	73.00 407	83.94 393	92.38 266	69.08 424	91.85 390	86.93 453	61.48 461	65.32 432	90.27 316	42.27 446	96.93 277	50.91 461	75.63 349	85.80 435
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
GBi-Net		82.42 329	80.43 340	88.39 301	92.66 256	81.95 157	94.30 335	93.38 366	79.06 351	75.82 351	85.66 391	56.38 389	93.84 410	71.23 369	75.38 350	89.38 350

test1		82.42 329	80.43 340	88.39 301	92.66 256	81.95 157	94.30 335	93.38 366	79.06 351	75.82 351	85.66 391	56.38 389	93.84 410	71.23 369	75.38 350	89.38 350

FMVSNet3		84.71 288	82.71 306	90.70 239	94.55 176	87.71 24	95.92 255	94.67 260	81.73 291	75.82 351	88.08 352	66.99 293	94.47 399	71.23 369	75.38 350	89.91 342

viewdifsd2359ckpt11		86.38 251	85.29 252	89.66 277	90.42 339	75.65 361	95.27 297	92.45 389	85.54 182	84.27 238	94.73 221	62.16 330	97.39 239	87.78 196	74.97 353	95.96 238

viewmsd2359difaftdt		86.38 251	85.29 252	89.67 276	90.42 339	75.65 361	95.27 297	92.45 389	85.54 182	84.28 237	94.73 221	62.16 330	97.39 239	87.78 196	74.97 353	95.96 238

tt0805		81.20 349	79.06 358	87.61 326	86.50 401	72.97 388	93.66 352	95.48 207	74.11 400	76.23 344	91.99 288	41.36 452	97.40 237	77.44 310	74.78 355	92.45 314

FMVSNet2		82.79 323	80.44 339	89.83 271	92.66 256	85.43 63	95.42 290	94.35 290	79.06 351	74.46 364	87.28 363	56.38 389	94.31 402	69.72 381	74.68 356	89.76 343

ITE_SJBPF				82.38 413	87.00 395	65.59 442		89.55 434	79.99 332	69.37 412	91.30 300	41.60 450	95.33 356	62.86 417	74.63 357	86.24 425

ACMH	75.40 17	77.99 381	74.96 389	87.10 343	90.67 334	76.41 345	93.19 370	91.64 408	72.47 418	63.44 439	87.61 360	43.34 441	97.16 257	58.34 435	73.94 358	87.72 401
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
baseline1		88.85 192	87.49 209	92.93 110	95.21 152	86.85 33	95.47 288	94.61 267	87.29 126	83.11 262	94.99 209	80.70 76	96.89 280	82.28 255	73.72 359	95.05 274

pmmvs4		82.54 327	80.79 332	87.79 321	86.11 409	80.49 222	93.55 357	93.18 376	77.29 371	73.35 374	89.40 330	65.26 309	95.05 381	75.32 338	73.61 360	87.83 400

AllTest		75.92 398	73.06 406	84.47 387	92.18 285	67.29 431	91.07 400	84.43 465	67.63 441	63.48 437	90.18 317	38.20 459	97.16 257	57.04 441	73.37 361	88.97 376

TestCases				84.47 387	92.18 285	67.29 431		84.43 465	67.63 441	63.48 437	90.18 317	38.20 459	97.16 257	57.04 441	73.37 361	88.97 376

pmmvs5		81.34 345	79.54 352	86.73 349	85.02 423	76.91 335	96.22 236	91.65 407	77.65 366	73.55 369	88.61 338	55.70 392	94.43 400	74.12 350	73.35 363	88.86 380

XXY-MVS		83.84 304	82.00 316	89.35 280	87.13 394	81.38 180	95.72 274	94.26 299	80.15 326	75.92 350	90.63 310	61.96 338	96.52 298	78.98 290	73.28 364	90.14 335

VortexMVS		85.45 274	84.40 270	88.63 295	93.25 227	81.66 174	95.39 293	94.34 291	87.15 135	75.10 360	87.65 358	66.58 299	95.19 365	86.89 208	73.21 365	89.03 369

WBMVS		87.73 226	86.79 227	90.56 242	95.61 138	85.68 55	97.63 107	95.52 204	83.77 246	78.30 314	88.44 345	86.14 34	95.78 331	82.54 251	73.15 366	90.21 333

FMVSNet1		79.50 366	76.54 377	88.39 301	88.47 379	81.95 157	94.30 335	93.38 366	73.14 409	72.04 388	85.66 391	43.86 438	93.84 410	65.48 402	72.53 367	89.38 350

cl22		85.11 281	84.17 275	87.92 319	95.06 163	78.82 272	95.51 286	94.22 303	79.74 336	76.77 332	87.92 354	75.96 167	95.68 338	79.93 278	72.42 368	89.27 356

miper_ehance_all_eth		84.57 293	83.60 288	87.50 332	92.64 260	78.25 296	95.40 292	93.47 361	79.28 346	76.41 339	87.64 359	76.53 152	95.24 363	78.58 293	72.42 368	89.01 373

miper_enhance_ethall		85.95 261	85.20 255	88.19 313	94.85 168	79.76 243	96.00 249	94.06 317	82.98 267	77.74 320	88.76 336	79.42 92	95.46 351	80.58 269	72.42 368	89.36 354

test_0402		72.68 416	69.54 423	82.09 416	88.67 376	71.81 402	92.72 377	86.77 456	61.52 460	62.21 447	83.91 416	43.22 442	93.76 413	34.60 483	72.23 371	80.72 470

dmvs_testset		72.00 422	73.36 405	67.91 459	83.83 437	31.90 499	85.30 452	77.12 484	82.80 271	63.05 443	92.46 278	61.54 341	82.55 481	42.22 480	71.89 372	89.29 355

SSC-MVS3.2		81.06 350	79.49 354	85.75 364	89.78 354	73.00 387	94.40 331	95.23 227	83.76 247	76.61 336	87.82 356	49.48 421	94.88 384	66.80 392	71.56 373	89.38 350

testgi		74.88 404	73.40 404	79.32 433	80.13 451	61.75 458	93.21 368	86.64 457	79.49 341	66.56 427	91.06 303	35.51 466	88.67 457	56.79 444	71.25 374	87.56 407

nrg030		86.79 246	85.43 249	90.87 234	88.76 371	85.34 65	97.06 163	94.33 294	84.31 223	80.45 292	91.98 289	72.36 230	96.36 304	88.48 189	71.13 375	90.93 324

ACMH+	76.62 16	77.47 389	74.94 390	85.05 377	91.07 324	71.58 405	93.26 367	90.01 430	71.80 424	64.76 434	88.55 339	41.62 449	96.48 299	62.35 418	71.00 376	87.09 415

VPA-MVSNet		85.32 277	83.83 279	89.77 274	90.25 342	82.63 132	96.36 224	97.07 39	83.03 265	81.21 284	89.02 333	61.58 340	96.31 306	85.02 223	70.95 377	90.36 329

IterMVS		80.67 356	79.16 356	85.20 375	89.79 353	76.08 350	92.97 373	91.86 400	80.28 323	71.20 394	85.14 404	57.93 369	91.34 440	72.52 361	70.74 378	88.18 395
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-LS		83.93 303	82.80 305	87.31 338	91.46 315	77.39 327	95.66 279	93.43 364	80.44 315	75.51 355	87.26 365	73.72 214	95.16 368	76.99 313	70.72 379	89.39 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		80.51 358	79.10 357	84.73 381	89.63 362	74.66 368	92.98 372	91.81 402	80.05 330	71.06 397	85.18 402	58.04 365	91.40 439	72.48 362	70.70 380	88.12 396

v1240		81.70 340	79.83 350	87.30 339	85.50 416	77.70 322	95.48 287	93.44 362	78.46 359	76.53 337	86.44 380	60.85 345	95.84 326	71.59 366	70.17 381	88.35 391

V42		83.04 319	81.53 323	87.57 330	86.27 406	79.09 266	95.87 267	94.11 314	80.35 321	77.22 325	86.79 374	65.32 308	96.02 316	77.74 302	70.14 382	87.61 405

v1192		82.31 332	80.55 338	87.60 327	85.94 411	78.47 289	95.85 269	93.80 337	79.33 343	76.97 330	86.51 377	63.33 324	95.87 325	73.11 357	70.13 383	88.46 388

v1144		82.90 322	81.27 327	87.78 322	86.29 405	79.07 267	96.14 244	93.93 321	80.05 330	77.38 321	86.80 373	65.50 304	95.93 323	75.21 339	70.13 383	88.33 392

Anonymous20231206		75.29 402	73.64 403	80.22 428	80.75 447	63.38 453	93.36 361	90.71 427	73.09 410	67.12 419	83.70 418	50.33 417	90.85 445	53.63 454	70.10 385	86.44 422

WR-MVS		84.32 297	82.96 300	88.41 299	89.38 368	80.32 223	96.59 201	96.25 146	83.97 236	76.63 334	90.36 315	67.53 287	94.86 386	75.82 330	70.09 386	90.06 340

EU-MVSNet		76.92 394	76.95 373	76.83 447	84.10 433	54.73 479	91.77 391	92.71 386	72.74 413	69.57 411	88.69 337	58.03 367	87.43 467	64.91 405	70.00 387	88.33 392

IB-MVS	85.34 4	88.67 197	87.14 219	93.26 91	93.12 235	84.32 93	98.76 37	97.27 22	87.19 133	79.36 305	90.45 313	83.92 55	98.53 152	84.41 226	69.79 388	96.93 204
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
v1921920		82.02 335	80.23 342	87.41 335	85.62 415	77.92 310	95.79 273	93.69 351	78.86 354	76.67 333	86.44 380	62.50 327	95.83 327	72.69 359	69.77 389	88.47 387

v2v482		83.46 310	81.86 318	88.25 308	86.19 407	79.65 249	96.34 226	94.02 319	81.56 293	77.32 323	88.23 349	65.62 303	96.03 315	77.77 301	69.72 390	89.09 362

v144192		82.43 328	80.73 334	87.54 331	85.81 414	78.22 297	95.98 250	93.78 339	79.09 350	77.11 328	86.49 378	64.66 317	95.91 324	74.20 349	69.42 391	88.49 386

cl____		83.27 313	82.12 313	86.74 346	92.20 283	75.95 356	95.11 310	93.27 372	78.44 360	74.82 362	87.02 370	74.19 206	95.19 365	74.67 344	69.32 392	89.09 362

DIV-MVS_self_test		83.27 313	82.12 313	86.74 346	92.19 284	75.92 358	95.11 310	93.26 373	78.44 360	74.81 363	87.08 369	74.19 206	95.19 365	74.66 345	69.30 393	89.11 361

Anonymous20231211		79.72 363	77.19 371	87.33 336	95.59 140	77.16 333	95.18 305	94.18 310	59.31 471	72.57 383	86.20 387	47.89 428	95.66 339	74.53 347	69.24 394	89.18 359

FMVSNet5		76.46 396	74.16 399	83.35 403	90.05 349	76.17 348	89.58 414	89.85 431	71.39 427	65.29 433	80.42 443	50.61 415	87.70 466	61.05 424	69.24 394	86.18 426

c3_l		83.80 305	82.65 307	87.25 340	92.10 291	77.74 321	95.25 299	93.04 382	78.58 357	76.01 347	87.21 367	75.25 190	95.11 373	77.54 308	68.89 396	88.91 379

TinyColmap		72.41 417	68.99 426	82.68 408	88.11 384	69.59 421	88.41 425	85.20 461	65.55 447	57.91 464	84.82 409	30.80 475	95.94 322	51.38 458	68.70 397	82.49 458

LF4IMVS		72.36 419	70.82 415	76.95 446	79.18 459	56.33 473	86.12 446	86.11 459	69.30 437	63.06 442	86.66 375	33.03 471	92.25 429	65.33 403	68.64 398	82.28 460

Anonymous20240521		72.06 421	69.91 421	78.50 439	77.11 468	61.67 460	91.62 395	90.97 422	65.52 448	62.37 446	79.05 450	36.32 462	90.96 444	57.75 438	68.52 399	82.87 452

OurMVSNet-221017-0		77.18 392	76.06 379	80.55 426	83.78 438	60.00 466	90.35 407	91.05 420	77.01 377	66.62 426	87.92 354	47.73 429	94.03 406	71.63 365	68.44 400	87.62 404

CP-MVSNet		81.01 352	80.08 344	83.79 395	87.91 387	70.51 412	94.29 339	95.65 196	80.83 304	72.54 384	88.84 335	63.71 320	92.32 428	68.58 386	68.36 401	88.55 383

UniMVSNet_NR-MVSNet		85.49 272	84.59 265	88.21 312	89.44 367	79.36 255	96.71 195	96.41 126	85.22 190	78.11 316	90.98 306	76.97 144	95.14 371	79.14 288	68.30 402	90.12 336

DU-MVS		84.57 293	83.33 293	88.28 305	88.76 371	79.36 255	96.43 217	95.41 216	85.42 185	78.11 316	90.82 307	67.61 284	95.14 371	79.14 288	68.30 402	90.33 331

PS-CasMVS		80.27 359	79.18 355	83.52 401	87.56 391	69.88 418	94.08 342	95.29 224	80.27 324	72.08 387	88.51 342	59.22 356	92.23 430	67.49 388	68.15 404	88.45 389

UniMVSNet (Re)		85.31 278	84.23 273	88.55 297	89.75 356	80.55 214	96.72 193	96.89 56	85.42 185	78.40 312	88.93 334	75.38 184	95.52 349	78.58 293	68.02 405	89.57 347

our_test_3		77.90 384	75.37 388	85.48 371	85.39 418	76.74 339	93.63 353	91.67 406	73.39 408	65.72 430	84.65 410	58.20 364	93.13 421	57.82 437	67.87 406	86.57 421

tfpnnormal		78.14 379	75.42 387	86.31 355	88.33 383	79.24 258	94.41 328	96.22 149	73.51 405	69.81 410	85.52 397	55.43 393	95.75 334	47.65 470	67.86 407	83.95 449

VPNet		84.69 289	82.92 301	90.01 262	89.01 370	83.45 114	96.71 195	95.46 209	85.71 177	79.65 301	92.18 285	56.66 386	96.01 317	83.05 248	67.84 408	90.56 327

v10		81.43 344	79.53 353	87.11 342	86.38 402	78.87 270	94.31 334	93.43 364	77.88 363	73.24 376	85.26 399	65.44 305	95.75 334	72.14 363	67.71 409	86.72 418

v8		81.88 337	80.06 346	87.32 337	86.63 398	79.04 268	94.41 328	93.65 353	78.77 355	73.19 377	85.57 395	66.87 295	95.81 328	73.84 353	67.61 410	87.11 414

v7n		79.32 369	77.34 369	85.28 374	84.05 435	72.89 390	93.38 360	93.87 327	75.02 394	70.68 398	84.37 411	59.58 351	95.62 344	67.60 387	67.50 411	87.32 413

WR-MVS_H		81.02 351	80.09 343	83.79 395	88.08 385	71.26 409	94.46 326	96.54 109	80.08 329	72.81 381	86.82 372	70.36 262	92.65 423	64.18 409	67.50 411	87.46 411

Patchmtry		77.36 390	74.59 394	85.67 366	89.75 356	75.75 360	77.85 474	91.12 417	60.28 466	71.23 393	80.35 444	75.45 180	93.56 416	57.94 436	67.34 413	87.68 403

reproduce_monomvs		87.80 223	87.60 206	88.40 300	96.56 104	80.26 227	95.80 272	96.32 141	91.56 45	73.60 368	88.36 346	88.53 18	96.25 309	90.47 147	67.23 414	88.67 381

eth_miper_zixun_eth		83.12 317	82.01 315	86.47 351	91.85 305	74.80 367	94.33 333	93.18 376	79.11 349	75.74 354	87.25 366	72.71 225	95.32 357	76.78 316	67.13 415	89.27 356

miper_lstm_enhance		81.66 342	80.66 336	84.67 383	91.19 319	71.97 398	91.94 387	93.19 374	77.86 364	72.27 386	85.26 399	73.46 217	93.42 418	73.71 354	67.05 416	88.61 382

v148		82.41 331	80.89 331	86.99 344	86.18 408	76.81 338	96.27 231	93.82 334	80.49 314	75.28 358	86.11 389	67.32 290	95.75 334	75.48 336	67.03 417	88.42 390

NR-MVSNet		83.35 311	81.52 324	88.84 290	88.76 371	81.31 183	94.45 327	95.16 229	84.65 211	67.81 417	90.82 307	70.36 262	94.87 385	74.75 342	66.89 418	90.33 331

Baseline_NR-MVSNet		81.22 348	80.07 345	84.68 382	85.32 421	75.12 366	96.48 211	88.80 442	76.24 386	77.28 324	86.40 383	67.61 284	94.39 401	75.73 331	66.73 419	84.54 443

blend_shiyan4		81.76 338	79.58 351	88.31 304	80.00 452	80.59 210	95.95 252	93.73 347	72.26 421	71.14 395	82.52 426	76.13 164	95.15 369	77.83 296	66.62 420	89.19 358

TranMVSNet+NR-MVSNet		83.24 315	81.71 320	87.83 320	87.71 389	78.81 274	96.13 246	94.82 247	84.52 216	76.18 346	90.78 309	64.07 318	94.60 396	74.60 346	66.59 421	90.09 338

0.3-1-1-0.015		87.79 224	85.93 240	93.38 88	89.87 352	85.09 78	98.43 52	96.55 106	81.13 298	87.21 192	89.75 323	77.23 137	97.02 266	86.87 209	66.38 422	98.02 97

0.4-1-1-0.2		87.73 226	85.82 243	93.46 87	89.97 351	85.31 68	98.49 51	96.55 106	81.24 296	87.14 194	89.63 326	76.16 163	97.02 266	86.84 210	66.38 422	98.05 95

0.4-1-1-0.1		87.53 234	85.67 245	93.13 98	89.70 359	84.41 91	98.30 62	96.55 106	80.85 303	86.94 198	89.53 328	76.18 161	96.99 271	86.62 213	66.36 424	97.98 105

h-mvs33		89.30 179	88.95 172	90.36 251	95.07 161	76.04 351	96.96 173	97.11 36	90.39 63	92.22 102	95.10 202	74.70 198	98.86 136	93.14 102	65.89 425	96.16 235

PEN-MVS		79.47 367	78.26 363	83.08 404	86.36 403	68.58 426	93.85 350	94.77 251	79.76 335	71.37 391	88.55 339	59.79 348	92.46 424	64.50 407	65.40 426	88.19 394

FPMVS		55.09 449	52.93 452	61.57 468	55.98 492	40.51 493	83.11 462	83.41 474	37.61 486	34.95 487	71.95 475	14.40 488	76.95 486	29.81 486	65.16 427	67.25 481

ppachtmachnet_test		77.19 391	74.22 398	86.13 358	85.39 418	78.22 297	93.98 343	91.36 413	71.74 425	67.11 420	84.87 408	56.67 385	93.37 420	52.21 456	64.59 428	86.80 417

AUN-MVS		86.25 257	85.57 247	88.26 306	93.57 214	73.38 379	95.45 289	95.88 183	83.94 238	85.47 220	94.21 240	73.70 216	96.67 294	83.54 241	64.41 429	94.73 286

hse-mvs2		88.22 212	88.21 190	88.25 308	93.54 215	73.41 378	95.41 291	95.89 181	90.39 63	92.22 102	94.22 239	74.70 198	96.66 295	93.14 102	64.37 430	94.69 287

pm-mvs1		80.05 360	78.02 365	86.15 357	85.42 417	75.81 359	95.11 310	92.69 387	77.13 373	70.36 401	87.43 361	58.44 361	95.27 360	71.36 368	64.25 431	87.36 412

N_pmnet		61.30 444	60.20 447	64.60 464	84.32 430	17.00 505	91.67 394	10.98 503	61.77 459	58.45 463	78.55 451	49.89 419	91.83 436	42.27 479	63.94 432	84.97 439

SixPastTwentyTwo		76.04 397	74.32 397	81.22 421	84.54 427	61.43 461	91.16 399	89.30 438	77.89 362	64.04 436	86.31 384	48.23 423	94.29 403	63.54 414	63.84 433	87.93 399

MIMVSNet1		69.44 432	66.65 434	77.84 440	76.48 470	62.84 455	87.42 435	88.97 440	66.96 446	57.75 467	79.72 449	32.77 472	85.83 473	46.32 471	63.42 434	84.85 440

DTE-MVSNet		78.37 377	77.06 372	82.32 415	85.22 422	67.17 436	93.40 359	93.66 352	78.71 356	70.53 400	88.29 348	59.06 357	92.23 430	61.38 422	63.28 435	87.56 407

new_pmnet		66.18 440	63.18 442	75.18 454	76.27 472	61.74 459	83.79 459	84.66 464	56.64 475	51.57 475	71.85 477	31.29 474	87.93 462	49.98 464	62.55 436	75.86 476

test_fmvs3		69.56 430	69.19 425	70.67 457	69.01 482	47.05 483	90.87 402	86.81 454	71.31 428	66.79 424	77.15 458	16.40 487	83.17 479	81.84 258	62.51 437	81.79 465

test20.03		72.36 419	71.15 414	75.98 451	77.79 464	59.16 468	92.40 381	89.35 437	74.09 401	61.50 451	84.32 412	48.09 424	85.54 474	50.63 462	62.15 438	83.24 450

EGC-MVSNET		52.46 452	47.56 455	67.15 460	81.98 445	60.11 465	82.54 463	72.44 488	0.11 500	0.70 501	74.59 466	25.11 480	83.26 478	29.04 487	61.51 439	58.09 485

pmmvs6		74.65 405	71.67 412	83.60 400	79.13 460	69.94 417	93.31 366	90.88 424	61.05 465	65.83 429	84.15 414	43.43 440	94.83 387	66.62 395	60.63 440	86.02 430

MDA-MVSNet_test_wron		73.54 411	70.43 419	82.86 406	84.55 426	71.85 400	91.74 392	91.32 415	67.63 441	46.73 479	81.09 441	55.11 396	90.42 450	55.91 447	59.76 441	86.31 424

YYNet1		73.53 412	70.43 419	82.85 407	84.52 428	71.73 403	91.69 393	91.37 412	67.63 441	46.79 478	81.21 440	55.04 397	90.43 449	55.93 446	59.70 442	86.38 423

test_f		64.01 443	62.13 445	69.65 458	63.00 490	45.30 489	83.66 460	80.68 479	61.30 462	55.70 470	72.62 473	14.23 489	84.64 475	69.84 379	58.11 443	79.00 472

Patchmatch-RL test		76.65 395	74.01 401	84.55 386	77.37 467	64.23 447	78.49 473	82.84 475	78.48 358	64.63 435	73.40 470	76.05 166	91.70 438	76.99 313	57.84 444	97.72 129

FE-MVSNET2		73.72 407	70.80 416	82.46 412	74.97 476	73.81 377	91.88 389	91.73 405	76.70 381	59.74 459	77.41 456	42.26 447	90.52 448	64.75 406	57.79 445	83.06 451

pmmvs-eth3d		73.59 409	70.66 417	82.38 413	76.40 471	73.38 379	89.39 418	89.43 436	72.69 414	60.34 456	77.79 453	46.43 434	91.26 442	66.42 399	57.06 446	82.51 456

PM-MVS		69.32 433	66.93 432	76.49 448	73.60 479	55.84 475	85.91 447	79.32 482	74.72 396	61.09 453	78.18 452	21.76 483	91.10 443	70.86 374	56.90 447	82.51 456

sc_t1		72.37 418	68.03 429	85.39 372	83.78 438	70.51 412	91.27 398	83.70 472	52.46 479	68.29 415	82.02 433	30.58 476	94.81 388	64.50 407	55.69 448	90.85 325

tt0320		70.21 427	66.07 435	82.64 409	83.42 441	70.82 410	89.63 412	84.10 468	49.75 482	62.71 445	77.28 457	33.35 469	92.45 426	58.78 434	55.62 449	84.64 442

kuosan		73.55 410	72.39 410	77.01 445	89.68 360	66.72 439	85.24 453	93.44 362	67.76 440	60.04 458	83.40 421	71.90 242	84.25 476	45.34 474	54.75 450	80.06 471

Gipuma		45.11 457	42.05 459	54.30 474	80.69 448	51.30 481	35.80 493	83.81 471	28.13 488	27.94 492	34.53 492	11.41 494	76.70 488	21.45 491	54.65 451	34.90 492
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
APD_test1		56.56 447	53.58 451	65.50 461	67.93 485	46.51 486	77.24 477	72.95 487	38.09 485	42.75 483	75.17 464	13.38 490	82.78 480	40.19 481	54.53 452	67.23 482

FE-MVSNET		69.26 434	66.03 436	78.93 435	73.82 478	68.33 428	89.65 411	84.06 469	70.21 432	57.79 466	76.94 461	41.48 451	86.98 470	45.85 473	54.51 453	81.48 468

MDA-MVSNet-bldmvs		71.45 423	67.94 430	81.98 417	85.33 420	68.50 427	92.35 382	88.76 443	70.40 430	42.99 482	81.96 434	46.57 433	91.31 441	48.75 469	54.39 454	86.11 427

K. test v3		73.62 408	71.59 413	79.69 430	82.98 442	59.85 467	90.85 403	88.83 441	77.13 373	58.90 460	82.11 431	43.62 439	91.72 437	65.83 401	54.10 455	87.50 410

blended_shiyan8		78.76 374	75.65 385	88.10 314	79.58 458	80.20 230	95.70 277	93.71 350	72.43 419	70.26 405	82.12 430	57.66 375	95.08 378	75.57 334	53.80 456	89.02 371

wanda-best-256-512		78.87 372	75.75 382	88.22 310	79.74 453	80.51 220	95.92 255	93.75 345	72.60 415	70.34 402	82.14 427	57.91 371	95.09 376	75.61 332	53.77 457	89.05 365

FE-blended-shiyan7		78.87 372	75.75 382	88.22 310	79.74 453	80.51 220	95.92 255	93.75 345	72.60 415	70.34 402	82.14 427	57.91 371	95.09 376	75.61 332	53.77 457	89.05 365

blended_shiyan6		78.74 375	75.63 386	88.07 315	79.63 457	80.10 235	95.72 274	93.73 347	72.43 419	70.17 408	82.09 432	57.69 374	95.07 379	75.47 337	53.77 457	89.03 369

usedtu_blend_shiyan5		77.51 388	73.93 402	88.26 306	79.74 453	80.59 210	90.76 404	89.69 432	63.21 452	70.34 402	82.14 427	57.91 371	95.15 369	77.83 296	53.77 457	89.05 365

CL-MVSNet_self_test		75.81 399	74.14 400	80.83 425	78.33 463	67.79 430	94.22 340	93.52 360	77.28 372	69.82 409	81.54 438	61.47 343	89.22 455	57.59 439	53.51 461	85.48 436

KD-MVS_self_test		70.97 426	69.31 424	75.95 452	76.24 473	55.39 478	87.45 434	90.94 423	70.20 433	62.96 444	77.48 455	44.01 437	88.09 461	61.25 423	53.26 462	84.37 445

TDRefinement		69.20 435	65.78 438	79.48 431	66.04 487	62.21 457	88.21 426	86.12 458	62.92 454	61.03 454	85.61 394	33.23 470	94.16 404	55.82 448	53.02 463	82.08 462

ambc				76.02 450	68.11 484	51.43 480	64.97 489	89.59 433		60.49 455	74.49 467	17.17 486	92.46 424	61.50 421	52.85 464	84.17 447

TransMVSNet (Re)		76.94 393	74.38 396	84.62 385	85.92 412	75.25 365	95.28 294	89.18 439	73.88 403	67.22 418	86.46 379	59.64 349	94.10 405	59.24 433	52.57 465	84.50 444

mvsany_test3		67.19 438	65.34 439	72.72 455	63.08 489	48.57 482	83.12 461	78.09 483	72.07 422	61.21 452	77.11 459	22.94 482	87.78 465	78.59 292	51.88 466	81.80 464

tt0320-xc		69.70 428	65.27 440	82.99 405	84.33 429	71.92 399	89.56 416	82.08 476	50.11 480	61.87 450	77.50 454	30.48 477	92.34 427	60.30 426	51.20 467	84.71 441

mvs5depth		71.40 424	68.36 428	80.54 427	75.31 475	65.56 443	79.94 466	85.14 462	69.11 438	71.75 390	81.59 436	41.02 454	93.94 408	60.90 425	50.46 468	82.10 461

test_vis3_rt		54.10 450	51.04 453	63.27 467	58.16 491	46.08 488	84.17 457	49.32 502	56.48 476	36.56 486	49.48 489	8.03 497	91.91 435	67.29 390	49.87 469	51.82 488

usedtu_dtu_shiyan2		64.65 442	60.40 446	77.38 444	64.24 488	57.84 471	89.16 419	87.60 450	52.95 478	53.43 474	71.31 479	23.41 481	88.27 460	51.95 457	49.58 470	86.03 429

PMVS	34.80 23	39.19 459	35.53 462	50.18 475	29.72 502	30.30 500	59.60 491	66.20 495	26.06 491	17.91 495	49.53 488	3.12 500	74.09 490	18.19 493	49.40 471	46.14 489
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
lessismore_v0				79.98 429	80.59 449	58.34 470		80.87 478		58.49 462	83.46 420	43.10 443	93.89 409	63.11 416	48.68 472	87.72 401

UnsupCasMVSNet_eth		73.25 413	70.57 418	81.30 420	77.53 465	66.33 440	87.24 437	93.89 326	80.38 318	57.90 465	81.59 436	42.91 445	90.56 447	65.18 404	48.51 473	87.01 416

new-patchmatchnet		68.85 436	65.93 437	77.61 442	73.57 480	63.94 450	90.11 409	88.73 444	71.62 426	55.08 471	73.60 469	40.84 455	87.22 469	51.35 460	48.49 474	81.67 467

dongtai		69.47 431	68.98 427	70.93 456	86.87 396	58.45 469	88.19 427	93.18 376	63.98 451	56.04 469	80.17 446	70.97 256	79.24 483	33.46 484	47.94 475	75.09 477

pmmvs3		65.75 441	62.18 444	76.45 449	67.12 486	64.54 445	88.68 423	85.05 463	54.77 477	57.54 468	73.79 468	29.40 478	86.21 472	55.49 450	47.77 476	78.62 473

test_method		56.77 446	54.53 450	63.49 466	76.49 469	40.70 492	75.68 478	74.24 486	19.47 494	48.73 476	71.89 476	19.31 484	65.80 494	57.46 440	47.51 477	83.97 448

ttmdpeth		69.58 429	66.92 433	77.54 443	75.95 474	62.40 456	88.09 428	84.32 467	62.87 455	65.70 431	86.25 386	36.53 461	88.53 459	55.65 449	46.96 478	81.70 466

mmtdpeth		78.04 380	76.76 375	81.86 418	89.60 363	66.12 441	92.34 383	87.18 451	76.83 380	85.55 219	76.49 462	46.77 432	97.02 266	90.85 138	45.24 479	82.43 459

UnsupCasMVSNet_bld		68.60 437	64.50 441	80.92 424	74.63 477	67.80 429	83.97 458	92.94 383	65.12 449	54.63 472	68.23 480	35.97 464	92.17 432	60.13 427	44.83 480	82.78 454

LCM-MVSNet		52.52 451	48.24 454	65.35 462	47.63 499	41.45 491	72.55 483	83.62 473	31.75 487	37.66 485	57.92 485	9.19 496	76.76 487	49.26 466	44.60 481	77.84 474

PVSNet_0	77.72 15	81.70 340	78.95 359	89.94 267	90.77 333	76.72 340	95.96 251	96.95 51	85.01 201	70.24 407	88.53 341	52.32 406	98.20 171	86.68 212	44.08 482	94.89 277

testf1		45.70 455	42.41 457	55.58 472	53.29 496	40.02 494	68.96 487	62.67 496	27.45 489	29.85 489	61.58 481	5.98 498	73.83 491	28.49 489	43.46 483	52.90 486

APD_test2		45.70 455	42.41 457	55.58 472	53.29 496	40.02 494	68.96 487	62.67 496	27.45 489	29.85 489	61.58 481	5.98 498	73.83 491	28.49 489	43.46 483	52.90 486

KD-MVS_2432*1600		77.63 386	74.92 391	85.77 362	90.86 329	79.44 252	88.08 429	93.92 323	76.26 384	67.05 421	82.78 424	72.15 237	91.92 433	61.53 419	41.62 485	85.94 432

miper_refine_blended		77.63 386	74.92 391	85.77 362	90.86 329	79.44 252	88.08 429	93.92 323	76.26 384	67.05 421	82.78 424	72.15 237	91.92 433	61.53 419	41.62 485	85.94 432

DeepMVS_CX				64.06 465	78.53 462	43.26 490		68.11 494	69.94 434	38.55 484	76.14 463	18.53 485	79.34 482	43.72 476	41.62 485	69.57 480

MVStest1		66.93 439	63.01 443	78.69 436	78.56 461	71.43 407	85.51 451	86.81 454	49.79 481	48.57 477	84.15 414	53.46 404	83.31 477	43.14 478	37.15 488	81.34 469

WB-MVS		57.26 445	56.22 448	60.39 470	69.29 481	35.91 497	86.39 445	70.06 490	59.84 470	46.46 480	72.71 472	51.18 410	78.11 484	15.19 494	34.89 489	67.14 483

SSC-MVS		56.01 448	54.96 449	59.17 471	68.42 483	34.13 498	84.98 455	69.23 491	58.08 474	45.36 481	71.67 478	50.30 418	77.46 485	14.28 495	32.33 490	65.91 484

PMMVS2		50.90 453	46.31 456	64.67 463	55.53 493	46.67 485	77.30 476	71.02 489	40.89 484	34.16 488	59.32 483	9.83 495	76.14 489	40.09 482	28.63 491	71.21 478

MVE	35.65 22	33.85 460	29.49 465	46.92 476	41.86 500	36.28 496	50.45 492	56.52 499	18.75 495	18.28 494	37.84 491	2.41 501	58.41 495	18.71 492	20.62 492	46.06 490
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 461	32.39 463	33.65 478	53.35 495	25.70 502	74.07 481	53.33 500	21.08 492	17.17 496	33.63 494	11.85 493	54.84 496	12.98 496	14.04 493	20.42 493

ANet_high		46.22 454	41.28 461	61.04 469	39.91 501	46.25 487	70.59 486	76.18 485	58.87 472	23.09 493	48.00 490	12.58 492	66.54 493	28.65 488	13.62 494	70.35 479

tmp_tt		41.54 458	41.93 460	40.38 477	20.10 503	26.84 501	61.93 490	59.09 498	14.81 496	28.51 491	80.58 442	35.53 465	48.33 498	63.70 413	13.11 495	45.96 491

EMVS		31.70 462	31.45 464	32.48 479	50.72 498	23.95 503	74.78 480	52.30 501	20.36 493	16.08 497	31.48 495	12.80 491	53.60 497	11.39 497	13.10 496	19.88 494

wuyk23d		14.10 464	13.89 467	14.72 480	55.23 494	22.91 504	33.83 494	3.56 504	4.94 497	4.11 498	2.28 500	2.06 502	19.66 499	10.23 498	8.74 497	1.59 497

testmvs		9.92 465	12.94 468	0.84 482	0.65 504	0.29 507	93.78 351	0.39 505	0.42 498	2.85 499	15.84 498	0.17 504	0.30 501	2.18 499	0.21 498	1.91 496

test123		9.07 466	11.73 469	1.11 481	0.50 505	0.77 506	89.44 417	0.20 506	0.34 499	2.15 500	10.72 499	0.34 503	0.32 500	1.79 500	0.08 499	2.23 495

mmdepth		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

monomultidepth		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

test_blank		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

uanet_test		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

DCPMVS		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

cdsmvs_eth3d_5k		21.43 463	28.57 466	0.00 483	0.00 506	0.00 508	0.00 495	95.93 178	0.00 501	0.00 502	97.66 93	63.57 321	0.00 502	0.00 501	0.00 500	0.00 498

pcd_1.5k_mvsjas		5.92 468	7.89 471	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	71.04 253	0.00 502	0.00 501	0.00 500	0.00 498

sosnet-low-res		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

sosnet		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

uncertanet		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

Regformer		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

ab-mvs-re		8.11 467	10.81 470	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	97.30 116	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

uanet		0.00 469	0.00 472	0.00 483	0.00 506	0.00 508	0.00 495	0.00 507	0.00 501	0.00 502	0.00 501	0.00 505	0.00 502	0.00 501	0.00 500	0.00 498

TestfortrainingZip							98.35 57

WAC-MVS						67.18 433								49.00 467

FOURS1					98.51 43	78.01 305	98.13 71	96.21 150	83.04 263	94.39 70

test_one_0601					98.91 22	84.56 90		96.70 82	88.06 102	96.57 36	98.77 15	88.04 23

eth-test2					0.00 506

eth-test					0.00 506

test_241102_ONE					99.03 19	85.03 80		96.78 65	88.72 84	97.79 10	98.90 5	88.48 19	99.82 23

save fliter					98.24 55	83.34 116	98.61 46	96.57 103	91.32 47

test0726					99.05 13	85.18 71	99.11 19	96.78 65	88.75 82	97.65 17	98.91 2	87.69 25

GSMVS																97.54 148

test_part2					98.90 23	85.14 77				96.07 43

sam_mvs1												77.59 127				97.54 148

sam_mvs												75.35 187

MTGPA								96.33 139

test_post1							85.88 448				30.24 496	73.77 212	95.07 379	73.89 351

test_post											33.80 493	76.17 162	95.97 318

patchmatchnet-post											77.09 460	77.78 125	95.39 352

MTMP							97.53 118	68.16 493

gm-plane-assit					92.27 278	79.64 250			84.47 220		95.15 199		97.93 185	85.81 216

TEST9					98.64 35	83.71 104	97.82 92	96.65 90	84.29 227	95.16 54	98.09 66	84.39 45	99.36 97

test_8					98.63 37	83.64 110	97.81 94	96.63 95	84.50 217	95.10 57	98.11 64	84.33 46	99.23 105

agg_prior					98.59 39	83.13 121		96.56 105		94.19 72			99.16 116

test_prior4						82.34 145	97.75 100

test_prior				93.09 101	98.68 30	81.91 161		96.40 128					99.06 124			98.29 77

旧先验2							96.97 171		74.06 402	96.10 42			97.76 196	88.38 190

新几何2							96.42 219

无先验							96.87 180	96.78 65	77.39 369				99.52 85	79.95 277		98.43 68

原ACMM2							96.84 181

testdata2													99.48 89	76.45 322

segment_acmp												82.69 66

testdata1							95.57 285		87.44 122

plane_prior7					91.86 303	77.55 324

plane_prior6					91.98 298	77.92 310						64.77 313

plane_prior4											94.15 244

plane_prior3						77.75 320			90.17 67	81.33 282

plane_prior2							97.18 146		89.89 70

plane_prior1					91.95 300

n2								0.00 507

nn								0.00 507

door-mid								79.75 481

test11								96.50 115

door								80.13 480

HQP5-MVS						78.48 286

HQP-NCC					92.08 292		97.63 107		90.52 60	82.30 269

ACMP_Plane					92.08 292		97.63 107		90.52 60	82.30 269

BP-MVS														87.67 200

HQP4-MVS										82.30 269			97.32 245			91.13 320

HQP2-MVS												65.40 306

NP-MVS					92.04 296	78.22 297					94.56 227

MDTV_nov1_ep13_2view						81.74 170	86.80 440		80.65 309	85.65 217		74.26 205		76.52 321		96.98 201

Test By Simon												71.65 245

High-resolution multi-view benchmark