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.

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 15	98.69 68	98.20 7	99.93 1	99.98 2	96.82 22	100.00 1	99.75 28	100.00 1	99.99 23

fmvsm_l_conf0.5_n_a		99.00 14	98.91 14	99.28 45	99.21 102	97.91 76	99.98 15	98.85 56	98.25 4	99.92 2	99.75 71	94.72 64	99.97 53	99.87 19	99.64 88	99.95 71

fmvsm_l_conf0.5_n		98.94 15	98.84 17	99.25 46	99.17 106	97.81 79	99.98 15	98.86 53	98.25 4	99.90 3	99.76 65	94.21 82	99.97 53	99.87 19	99.52 100	99.98 48

patch_mono-2		98.24 56	99.12 5	95.59 226	99.67 77	86.91 345	99.95 53	98.89 49	97.60 22	99.90 3	99.76 65	96.54 28	99.98 43	99.94 11	99.82 77	99.88 85

NCCC		99.37 2	99.25 2	99.71 14	99.96 8	99.15 21	99.97 28	98.62 81	98.02 13	99.90 3	99.95 3	97.33 16	100.00 1	99.54 39	100.00 1	100.00 1

TSAR-MVS + MP.		98.93 16	98.77 18	99.41 38	99.74 69	98.67 49	99.77 148	98.38 159	96.73 53	99.88 6	99.74 78	94.89 60	99.59 149	99.80 25	99.98 32	99.97 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test0726					99.93 24	99.29 15	99.96 35	98.42 143	97.28 32	99.86 7	99.94 4	97.22 18

xiu_mvs_v2_base		98.23 57	97.97 59	99.02 72	98.69 143	98.66 51	99.52 205	98.08 203	97.05 41	99.86 7	99.86 26	90.65 167	99.71 138	99.39 50	98.63 139	98.69 220

test_vis1_n_1920		95.44 172	95.31 163	95.82 222	98.50 159	88.74 324	99.98 15	97.30 277	97.84 16	99.85 9	99.19 144	66.82 360	99.97 53	98.82 79	99.46 107	98.76 215

PS-MVSNAJ		98.44 41	98.20 46	99.16 57	98.80 138	98.92 29	99.54 203	98.17 191	97.34 29	99.85 9	99.85 30	91.20 154	99.89 96	99.41 48	99.67 86	98.69 220

旧先验2							99.46 216		94.21 134	99.85 9			99.95 69	96.96 157

IU-MVS					99.93 24	99.31 10		98.41 148	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 53	98.32 172	97.28 32	99.83 13	99.91 14	97.22 18	100.00 1	99.99 5	100.00 1	99.89 84
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_THIRD									96.48 61	99.83 13	99.91 14	97.87 5	100.00 1	99.92 12	100.00 1	100.00 1

iter_conf05_11		96.12 151	95.46 157	98.10 131	98.62 149	95.52 169	100.00 1	96.30 350	96.54 60	99.81 15	99.80 51	69.19 348	99.10 178	98.92 70	99.91 66	99.68 113

SF-MVS		98.67 27	98.40 32	99.50 30	99.77 65	98.67 49	99.90 91	98.21 186	93.53 161	99.81 15	99.89 19	94.70 66	99.86 107	99.84 22	99.93 60	99.96 64

SD-MVS		98.92 17	98.70 19	99.56 25	99.70 76	98.73 46	99.94 69	98.34 169	96.38 67	99.81 15	99.76 65	94.59 67	99.98 43	99.84 22	99.96 46	99.97 58
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
test_fmvsm_n_1920		98.44 41	98.61 23	97.92 143	99.27 101	95.18 185	100.00 1	98.90 47	98.05 12	99.80 18	99.73 80	92.64 126	99.99 36	99.58 38	99.51 103	98.59 223

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 53	98.43 131	96.48 61	99.80 18	99.93 11	97.44 13	100.00 1	99.92 12	99.98 32	100.00 1

PC_three_1452									96.96 44	99.80 18	99.79 57	97.49 9	100.00 1	99.99 5	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 35	98.43 131	97.27 34	99.80 18	99.94 4	96.71 23	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 131	97.27 34	99.80 18	99.94 4	97.18 20	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 131	97.26 36	99.80 18	99.88 21	96.71 23	100.00 1

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 15	98.86 53	97.10 40	99.80 18	99.94 4	95.92 36	100.00 1	99.51 40	100.00 1	100.00 1

SteuartSystems-ACMMP		99.02 12	98.97 13	99.18 52	98.72 142	97.71 81	99.98 15	98.44 123	96.85 46	99.80 18	99.91 14	97.57 7	99.85 108	99.44 46	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
testdata				98.42 115	99.47 92	95.33 177		98.56 92	93.78 154	99.79 26	99.85 30	93.64 99	99.94 77	94.97 186	99.94 54	100.00 1

9.14			98.38 34		99.87 51		99.91 84	98.33 170	93.22 171	99.78 27	99.89 19	94.57 68	99.85 108	99.84 22	99.97 42

SMA-MVS		98.76 24	98.48 29	99.62 20	99.87 51	98.87 33	99.86 118	98.38 159	93.19 172	99.77 28	99.94 4	95.54 42	100.00 1	99.74 30	99.99 21	100.00 1
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
CDPH-MVS		98.65 28	98.36 38	99.49 32	99.94 13	98.73 46	99.87 106	98.33 170	93.97 146	99.76 29	99.87 24	94.99 58	99.75 132	98.55 95	100.00 1	99.98 48

fmvsm_s_conf0.5_n_a		97.73 81	97.72 71	97.77 153	98.63 148	94.26 208	99.96 35	98.92 46	97.18 39	99.75 30	99.69 89	87.00 212	99.97 53	99.46 44	98.89 131	99.08 199

test_one_0601					99.94 13	99.30 12		98.41 148	96.63 56	99.75 30	99.93 11	97.49 9

APD-MVS		98.62 29	98.35 39	99.41 38	99.90 42	98.51 59	99.87 106	98.36 163	94.08 139	99.74 32	99.73 80	94.08 85	99.74 134	99.42 47	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1		95.35 174	95.68 154	94.36 274	98.99 117	84.98 354	99.96 35	96.65 338	97.60 22	99.73 33	98.96 165	71.58 338	99.93 85	98.31 106	99.37 114	98.17 230

test_prior2							99.95 53		95.78 81	99.73 33	99.76 65	96.00 33		99.78 27	100.00 1

TEST9					99.92 31	98.92 29	99.96 35	98.43 131	93.90 151	99.71 35	99.86 26	95.88 37	99.85 108

train_agg		98.88 19	98.65 20	99.59 23	99.92 31	98.92 29	99.96 35	98.43 131	94.35 125	99.71 35	99.86 26	95.94 34	99.85 108	99.69 35	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 35	98.43 131	94.35 125	99.69 37	99.85 30	95.94 34	99.85 108

CS-MVS		97.79 76	97.91 65	97.43 173	99.10 109	94.42 202	99.99 5	97.10 298	95.07 98	99.68 38	99.75 71	92.95 117	98.34 230	98.38 101	99.14 124	99.54 147

test_fmvsmconf_n		98.43 43	98.32 40	98.78 84	98.12 185	96.41 129	99.99 5	98.83 59	98.22 6	99.67 39	99.64 101	91.11 158	99.94 77	99.67 36	99.62 90	99.98 48

test_fmvs1_n		94.25 206	94.36 186	93.92 289	97.68 213	83.70 360	99.90 91	96.57 341	97.40 28	99.67 39	98.88 176	61.82 376	99.92 88	98.23 108	99.13 125	98.14 233

fmvsm_s_conf0.1_n_a		97.09 108	96.90 103	97.63 163	95.65 296	94.21 210	99.83 133	98.50 112	96.27 72	99.65 41	99.64 101	84.72 235	99.93 85	99.04 63	98.84 134	98.74 217

test12				99.43 35	99.74 69	98.56 57		98.40 152		99.65 41		94.76 63	99.75 132		99.98 32	99.99 23

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 106	98.44 123	97.48 27	99.64 43	99.94 4	96.68 25	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.5_n		97.80 74	97.85 68	97.67 159	99.06 111	94.41 203	99.98 15	98.97 40	97.34 29	99.63 44	99.69 89	87.27 207	99.97 53	99.62 37	99.06 128	98.62 222

agg_prior					99.93 24	98.77 42		98.43 131		99.63 44			99.85 108

EC-MVSNet		97.38 96	97.24 89	97.80 148	97.41 227	95.64 164	99.99 5	97.06 303	94.59 114	99.63 44	99.32 132	89.20 190	98.14 246	98.76 83	99.23 121	99.62 128

xiu_mvs_v1_base_debu		97.43 89	97.06 95	98.55 102	97.74 205	98.14 64	99.31 234	97.86 225	96.43 64	99.62 47	99.69 89	85.56 226	99.68 142	99.05 60	98.31 146	97.83 236

CS-MVS-test		97.88 67	97.94 63	97.70 158	99.28 100	95.20 184	99.98 15	97.15 293	95.53 89	99.62 47	99.79 57	92.08 143	98.38 226	98.75 84	99.28 118	99.52 151

xiu_mvs_v1_base		97.43 89	97.06 95	98.55 102	97.74 205	98.14 64	99.31 234	97.86 225	96.43 64	99.62 47	99.69 89	85.56 226	99.68 142	99.05 60	98.31 146	97.83 236

xiu_mvs_v1_base_debi		97.43 89	97.06 95	98.55 102	97.74 205	98.14 64	99.31 234	97.86 225	96.43 64	99.62 47	99.69 89	85.56 226	99.68 142	99.05 60	98.31 146	97.83 236

原ACMM1				98.96 77	99.73 72	96.99 111		98.51 107	94.06 142	99.62 47	99.85 30	94.97 59	99.96 61	95.11 182	99.95 49	99.92 81

PHI-MVS		98.41 45	98.21 45	99.03 70	99.86 53	97.10 108	99.98 15	98.80 62	90.78 260	99.62 47	99.78 61	95.30 48	100.00 1	99.80 25	99.93 60	99.99 23

mvsany_test1		97.82 72	97.90 66	97.55 166	98.77 140	93.04 241	99.80 142	97.93 216	96.95 45	99.61 53	99.68 95	90.92 162	99.83 118	99.18 56	98.29 149	99.80 96

test_cas_vis1_n_1920		96.59 134	96.23 127	97.65 160	98.22 176	94.23 209	99.99 5	97.25 284	97.77 17	99.58 54	99.08 150	77.10 298	99.97 53	97.64 138	99.45 108	98.74 217

DPM-MVS		98.83 21	98.46 30	99.97 1	99.33 98	99.92 1	99.96 35	98.44 123	97.96 14	99.55 55	99.94 4	97.18 20	100.00 1	93.81 216	99.94 54	99.98 48

新几何1				99.42 37	99.75 68	98.27 63		98.63 80	92.69 191	99.55 55	99.82 46	94.40 71	100.00 1	91.21 252	99.94 54	99.99 23

test_vis1_n		93.61 223	93.03 223	95.35 233	95.86 282	86.94 343	99.87 106	96.36 348	96.85 46	99.54 57	98.79 186	52.41 389	99.83 118	98.64 91	98.97 130	99.29 182

ACMMP_NAP		98.49 37	98.14 50	99.54 27	99.66 78	98.62 55	99.85 121	98.37 162	94.68 112	99.53 58	99.83 43	92.87 119	100.00 1	98.66 90	99.84 72	99.99 23

PMMVS		96.76 125	96.76 109	96.76 196	98.28 172	92.10 262	99.91 84	97.98 211	94.12 137	99.53 58	99.39 127	86.93 213	98.73 196	96.95 158	97.73 161	99.45 161

FOURS1					99.92 31	97.66 85	99.95 53	98.36 163	95.58 87	99.52 60

MSP-MVS		99.09 9	99.12 5	98.98 75	99.93 24	97.24 100	99.95 53	98.42 143	97.50 26	99.52 60	99.88 21	97.43 15	99.71 138	99.50 41	99.98 32	100.00 1
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
fmvsm_s_conf0.1_n		97.30 97	97.21 91	97.60 165	97.38 229	94.40 205	99.90 91	98.64 76	96.47 63	99.51 62	99.65 100	84.99 234	99.93 85	99.22 55	99.09 127	98.46 224

test_part2					99.89 45	99.25 18				99.49 63

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 84	98.39 155	97.20 38	99.46 64	99.85 30	95.53 44	99.79 123	99.86 21	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
region2R		98.54 33	98.37 36	99.05 68	99.96 8	97.18 103	99.96 35	98.55 98	94.87 105	99.45 65	99.85 30	94.07 86	100.00 1	98.67 88	100.00 1	99.98 48

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 53	98.56 92	97.56 25	99.44 66	99.85 30	95.38 47	100.00 1	99.31 51	99.99 21	99.87 87

MVSFormer		96.94 116	96.60 116	97.95 140	97.28 238	97.70 83	99.55 201	97.27 282	91.17 246	99.43 67	99.54 112	90.92 162	96.89 311	94.67 198	99.62 90	99.25 186

lupinMVS		97.85 69	97.60 76	98.62 95	97.28 238	97.70 83	99.99 5	97.55 249	95.50 91	99.43 67	99.67 96	90.92 162	98.71 199	98.40 100	99.62 90	99.45 161

XVS		98.70 26	98.55 25	99.15 59	99.94 13	97.50 92	99.94 69	98.42 143	96.22 73	99.41 69	99.78 61	94.34 76	99.96 61	98.92 70	99.95 49	99.99 23

X-MVStestdata		93.83 213	92.06 246	99.15 59	99.94 13	97.50 92	99.94 69	98.42 143	96.22 73	99.41 69	41.37 409	94.34 76	99.96 61	98.92 70	99.95 49	99.99 23

SR-MVS-dyc-post		98.31 49	98.17 48	98.71 88	99.79 62	96.37 133	99.76 153	98.31 174	94.43 120	99.40 71	99.75 71	93.28 108	99.78 125	98.90 75	99.92 63	99.97 58

RE-MVS-def			98.13 51		99.79 62	96.37 133	99.76 153	98.31 174	94.43 120	99.40 71	99.75 71	92.95 117		98.90 75	99.92 63	99.97 58

MM		98.83 21	98.53 27	99.76 10	99.59 81	99.33 8	99.99 5	99.76 6	98.39 3	99.39 73	99.80 51	90.49 171	99.96 61	99.89 16	99.43 111	99.98 48

APD-MVS_3200maxsize		98.25 55	98.08 55	98.78 84	99.81 60	96.60 124	99.82 136	98.30 177	93.95 148	99.37 74	99.77 63	92.84 120	99.76 131	98.95 67	99.92 63	99.97 58

PGM-MVS		98.34 48	98.13 51	98.99 74	99.92 31	97.00 110	99.75 156	99.50 18	93.90 151	99.37 74	99.76 65	93.24 110	100.00 1	97.75 137	99.96 46	99.98 48

SR-MVS		98.46 39	98.30 43	98.93 79	99.88 49	97.04 109	99.84 126	98.35 165	94.92 103	99.32 76	99.80 51	93.35 103	99.78 125	99.30 52	99.95 49	99.96 64

ZD-MVS					99.92 31	98.57 56		98.52 104	92.34 211	99.31 77	99.83 43	95.06 53	99.80 121	99.70 34	99.97 42

HFP-MVS		98.56 32	98.37 36	99.14 61	99.96 8	97.43 96	99.95 53	98.61 82	94.77 107	99.31 77	99.85 30	94.22 80	100.00 1	98.70 86	99.98 32	99.98 48

ACMMPR		98.50 36	98.32 40	99.05 68	99.96 8	97.18 103	99.95 53	98.60 84	94.77 107	99.31 77	99.84 41	93.73 96	100.00 1	98.70 86	99.98 32	99.98 48

ETV-MVS		97.92 66	97.80 70	98.25 123	98.14 183	96.48 126	99.98 15	97.63 238	95.61 86	99.29 80	99.46 118	92.55 130	98.82 189	99.02 66	98.54 140	99.46 159

test222					99.55 86	97.41 98	99.34 230	98.55 98	91.86 224	99.27 81	99.83 43	93.84 94			99.95 49	99.99 23

CANet_DTU		96.76 125	96.15 130	98.60 97	98.78 139	97.53 88	99.84 126	97.63 238	97.25 37	99.20 82	99.64 101	81.36 261	99.98 43	92.77 236	98.89 131	98.28 229

EPNet		98.49 37	98.40 32	98.77 86	99.62 80	96.80 119	99.90 91	99.51 17	97.60 22	99.20 82	99.36 130	93.71 97	99.91 89	97.99 121	98.71 138	99.61 131
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	95.94 2	97.71 82	98.98 12	93.92 289	99.63 79	81.76 372	99.96 35	98.56 92	99.47 1	99.19 84	99.99 1	94.16 84	100.00 1	99.92 12	99.93 60	100.00 1

VNet		97.21 102	96.57 118	99.13 65	98.97 119	97.82 78	99.03 267	99.21 29	94.31 128	99.18 85	98.88 176	86.26 222	99.89 96	98.93 69	94.32 228	99.69 112

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 28	98.64 76	98.47 2	99.13 86	99.92 13	96.38 30	100.00 1	99.74 30	100.00 1	100.00 1

DeepC-MVS_fast	96.59 1	98.81 23	98.54 26	99.62 20	99.90 42	98.85 35	99.24 243	98.47 115	98.14 10	99.08 87	99.91 14	93.09 113	100.00 1	99.04 63	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
114514_t		97.41 94	96.83 106	99.14 61	99.51 90	97.83 77	99.89 99	98.27 181	88.48 301	99.06 88	99.66 98	90.30 173	99.64 148	96.32 166	99.97 42	99.96 64

PVSNet	91.05 13	97.13 105	96.69 113	98.45 112	99.52 88	95.81 153	99.95 53	99.65 12	94.73 109	99.04 89	99.21 143	84.48 238	99.95 69	94.92 188	98.74 137	99.58 140

CHOSEN 280x420		99.01 13	99.03 10	98.95 78	99.38 96	98.87 33	98.46 312	99.42 22	97.03 42	99.02 90	99.09 149	99.35 1	98.21 243	99.73 32	99.78 80	99.77 101

MG-MVS		98.91 18	98.65 20	99.68 15	99.94 13	99.07 24	99.64 187	99.44 20	97.33 31	99.00 91	99.72 83	94.03 87	99.98 43	98.73 85	100.00 1	100.00 1

diffmvs		97.00 113	96.64 114	98.09 133	97.64 216	96.17 144	99.81 138	97.19 287	94.67 113	98.95 92	99.28 133	86.43 218	98.76 194	98.37 103	97.42 169	99.33 176
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS_fast		97.80 74	97.50 79	98.68 90	99.79 62	96.42 128	99.88 103	98.16 195	91.75 229	98.94 93	99.54 112	91.82 149	99.65 147	97.62 140	99.99 21	99.99 23

dcpmvs_2		97.42 93	98.09 54	95.42 231	99.58 85	87.24 341	99.23 244	96.95 314	94.28 131	98.93 94	99.73 80	94.39 74	99.16 176	99.89 16	99.82 77	99.86 89

CP-MVS		98.45 40	98.32 40	98.87 81	99.96 8	96.62 123	99.97 28	98.39 155	94.43 120	98.90 95	99.87 24	94.30 78	100.00 1	99.04 63	99.99 21	99.99 23

test_fmvsmconf0.1_n		97.74 79	97.44 81	98.64 94	95.76 287	96.20 141	99.94 69	98.05 206	98.17 8	98.89 96	99.42 120	87.65 202	99.90 91	99.50 41	99.60 96	99.82 92

testing222		97.08 111	96.75 110	98.06 135	98.56 151	96.82 117	99.85 121	98.61 82	92.53 202	98.84 97	98.84 185	93.36 102	98.30 234	95.84 174	94.30 229	99.05 201

MVS_Test		96.46 138	95.74 150	98.61 96	98.18 180	97.23 101	99.31 234	97.15 293	91.07 251	98.84 97	97.05 257	88.17 199	98.97 182	94.39 202	97.50 166	99.61 131

API-MVS		97.86 68	97.66 73	98.47 110	99.52 88	95.41 174	99.47 214	98.87 52	91.68 230	98.84 97	99.85 30	92.34 137	99.99 36	98.44 99	99.96 46	100.00 1

GST-MVS		98.27 52	97.97 59	99.17 55	99.92 31	97.57 87	99.93 76	98.39 155	94.04 144	98.80 100	99.74 78	92.98 116	100.00 1	98.16 111	99.76 81	99.93 76

MVS_111021_LR		98.42 44	98.38 34	98.53 107	99.39 95	95.79 154	99.87 106	99.86 2	96.70 54	98.78 101	99.79 57	92.03 144	99.90 91	99.17 57	99.86 71	99.88 85

h-mvs33		94.92 182	94.36 186	96.59 202	98.85 135	91.29 283	98.93 276	98.94 41	95.90 78	98.77 102	98.42 217	90.89 165	99.77 128	97.80 130	70.76 376	98.72 219

hse-mvs2		94.38 200	94.08 194	95.31 236	98.27 173	90.02 310	99.29 239	98.56 92	95.90 78	98.77 102	98.00 228	90.89 165	98.26 241	97.80 130	69.20 382	97.64 241

TSAR-MVS + GP.		98.60 30	98.51 28	98.86 82	99.73 72	96.63 122	99.97 28	97.92 219	98.07 11	98.76 104	99.55 110	95.00 57	99.94 77	99.91 15	97.68 163	99.99 23

sss		97.57 85	97.03 99	99.18 52	98.37 164	98.04 69	99.73 164	99.38 23	93.46 163	98.76 104	99.06 152	91.21 153	99.89 96	96.33 165	97.01 180	99.62 128

MVS_0304		98.87 20	98.61 23	99.67 16	99.18 103	99.13 22	99.87 106	99.65 12	98.17 8	98.75 106	99.75 71	92.76 123	99.94 77	99.88 18	99.44 109	99.94 74

CostFormer		96.10 152	95.88 147	96.78 195	97.03 244	92.55 254	97.08 351	97.83 228	90.04 273	98.72 107	94.89 335	95.01 56	98.29 235	96.54 164	95.77 205	99.50 155

tpmrst		96.27 150	95.98 136	97.13 185	97.96 191	93.15 237	96.34 363	98.17 191	92.07 217	98.71 108	95.12 326	93.91 90	98.73 196	94.91 190	96.62 185	99.50 155

MVS_111021_HR		98.72 25	98.62 22	99.01 73	99.36 97	97.18 103	99.93 76	99.90 1	96.81 51	98.67 109	99.77 63	93.92 89	99.89 96	99.27 53	99.94 54	99.96 64

MAR-MVS		97.43 89	97.19 92	98.15 129	99.47 92	94.79 196	99.05 264	98.76 63	92.65 194	98.66 110	99.82 46	88.52 197	99.98 43	98.12 113	99.63 89	99.67 117
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
Effi-MVS+		96.30 147	95.69 152	98.16 126	97.85 198	96.26 136	97.41 343	97.21 286	90.37 266	98.65 111	98.58 204	86.61 217	98.70 200	97.11 150	97.37 171	99.52 151

HPM-MVS		97.96 63	97.72 71	98.68 90	99.84 56	96.39 132	99.90 91	98.17 191	92.61 196	98.62 112	99.57 109	91.87 147	99.67 145	98.87 77	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		98.39 47	98.20 46	98.97 76	99.97 3	96.92 114	99.95 53	98.38 159	95.04 99	98.61 113	99.80 51	93.39 101	100.00 1	98.64 91	100.00 1	99.98 48

jason		97.24 100	96.86 105	98.38 118	95.73 290	97.32 99	99.97 28	97.40 267	95.34 94	98.60 114	99.54 112	87.70 201	98.56 207	97.94 124	99.47 105	99.25 186
jason: jason.
CANet		98.27 52	97.82 69	99.63 17	99.72 74	99.10 23	99.98 15	98.51 107	97.00 43	98.52 115	99.71 85	87.80 200	99.95 69	99.75 28	99.38 113	99.83 91

EI-MVSNet-Vis-set		98.27 52	98.11 53	98.75 87	99.83 57	96.59 125	99.40 220	98.51 107	95.29 95	98.51 116	99.76 65	93.60 100	99.71 138	98.53 96	99.52 100	99.95 71

ZNCC-MVS		98.31 49	98.03 56	99.17 55	99.88 49	97.59 86	99.94 69	98.44 123	94.31 128	98.50 117	99.82 46	93.06 114	99.99 36	98.30 107	99.99 21	99.93 76

LFMVS		94.75 188	93.56 209	98.30 121	99.03 113	95.70 160	98.74 295	97.98 211	87.81 311	98.47 118	99.39 127	67.43 358	99.53 150	98.01 119	95.20 219	99.67 117

tpm2		95.47 171	95.18 168	96.35 211	96.91 251	91.70 276	96.96 354	97.93 216	88.04 308	98.44 119	95.40 312	93.32 105	97.97 255	94.00 209	95.61 209	99.38 168

alignmvs		97.81 73	97.33 86	99.25 46	98.77 140	98.66 51	99.99 5	98.44 123	94.40 124	98.41 120	99.47 116	93.65 98	99.42 164	98.57 94	94.26 230	99.67 117

UA-Net		96.54 135	95.96 140	98.27 122	98.23 175	95.71 159	98.00 334	98.45 118	93.72 157	98.41 120	99.27 136	88.71 196	99.66 146	91.19 253	97.69 162	99.44 163

DP-MVS Recon		98.41 45	98.02 57	99.56 25	99.97 3	98.70 48	99.92 79	98.44 123	92.06 219	98.40 122	99.84 41	95.68 40	100.00 1	98.19 109	99.71 84	99.97 58

CPTT-MVS		97.64 84	97.32 87	98.58 100	99.97 3	95.77 155	99.96 35	98.35 165	89.90 274	98.36 123	99.79 57	91.18 157	99.99 36	98.37 103	99.99 21	99.99 23

PAPM		98.60 30	98.42 31	99.14 61	96.05 276	98.96 26	99.90 91	99.35 25	96.68 55	98.35 124	99.66 98	96.45 29	98.51 210	99.45 45	99.89 67	99.96 64

HY-MVS	92.50 7	97.79 76	97.17 94	99.63 17	98.98 118	99.32 9	97.49 341	99.52 15	95.69 84	98.32 125	97.41 244	93.32 105	99.77 128	98.08 117	95.75 207	99.81 94

EI-MVSNet-UG-set		98.14 59	97.99 58	98.60 97	99.80 61	96.27 135	99.36 229	98.50 112	95.21 97	98.30 126	99.75 71	93.29 107	99.73 137	98.37 103	99.30 117	99.81 94

PVSNet_BlendedMVS		96.05 154	95.82 149	96.72 198	99.59 81	96.99 111	99.95 53	99.10 31	94.06 142	98.27 127	95.80 293	89.00 192	99.95 69	99.12 58	87.53 286	93.24 344

PVSNet_Blended		97.94 64	97.64 74	98.83 83	99.59 81	96.99 111	100.00 1	99.10 31	95.38 92	98.27 127	99.08 150	89.00 192	99.95 69	99.12 58	99.25 119	99.57 141

MP-MVS		98.23 57	97.97 59	99.03 70	99.94 13	97.17 106	99.95 53	98.39 155	94.70 111	98.26 129	99.81 50	91.84 148	100.00 1	98.85 78	99.97 42	99.93 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
WTY-MVS		98.10 61	97.60 76	99.60 22	98.92 126	99.28 17	99.89 99	99.52 15	95.58 87	98.24 130	99.39 127	93.33 104	99.74 134	97.98 123	95.58 210	99.78 100

DELS-MVS		98.54 33	98.22 44	99.50 30	99.15 108	98.65 53	100.00 1	98.58 87	97.70 20	98.21 131	99.24 141	92.58 129	99.94 77	98.63 93	99.94 54	99.92 81
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
ETVMVS		97.03 112	96.64 114	98.20 125	98.67 145	97.12 107	99.89 99	98.57 89	91.10 250	98.17 132	98.59 201	93.86 93	98.19 244	95.64 177	95.24 218	99.28 183

testing11		97.48 88	97.27 88	98.10 131	98.36 165	96.02 148	99.92 79	98.45 118	93.45 165	98.15 133	98.70 191	95.48 45	99.22 167	97.85 129	95.05 220	99.07 200

MDTV_nov1_ep13_2view						96.26 136	96.11 368		91.89 223	98.06 134		94.40 71		94.30 205		99.67 117

PAPR		98.52 35	98.16 49	99.58 24	99.97 3	98.77 42	99.95 53	98.43 131	95.35 93	98.03 135	99.75 71	94.03 87	99.98 43	98.11 114	99.83 73	99.99 23

MDTV_nov1_ep13			95.69 152		97.90 194	94.15 211	95.98 371	98.44 123	93.12 174	97.98 136	95.74 295	95.10 51	98.58 206	90.02 277	96.92 182

test2506		97.53 86	97.19 92	98.58 100	98.66 146	96.90 115	98.81 290	99.77 5	94.93 101	97.95 137	98.96 165	92.51 131	99.20 171	94.93 187	98.15 151	99.64 123

GG-mvs-BLEND				98.54 105	98.21 177	98.01 70	93.87 381	98.52 104		97.92 138	97.92 233	99.02 2	97.94 260	98.17 110	99.58 97	99.67 117

EIA-MVS		97.53 86	97.46 80	97.76 155	98.04 188	94.84 193	99.98 15	97.61 243	94.41 123	97.90 139	99.59 106	92.40 135	98.87 186	98.04 118	99.13 125	99.59 134

test_fmvsmconf0.01_n		96.39 142	95.74 150	98.32 120	91.47 366	95.56 167	99.84 126	97.30 277	97.74 18	97.89 140	99.35 131	79.62 280	99.85 108	99.25 54	99.24 120	99.55 143

sasdasda		97.09 108	96.32 124	99.39 40	98.93 123	98.95 27	99.72 167	97.35 270	94.45 117	97.88 141	99.42 120	86.71 214	99.52 151	98.48 97	93.97 234	99.72 107

test_yl		97.83 70	97.37 84	99.21 49	99.18 103	97.98 72	99.64 187	99.27 27	91.43 239	97.88 141	98.99 159	95.84 38	99.84 116	98.82 79	95.32 216	99.79 97

DCV-MVSNet		97.83 70	97.37 84	99.21 49	99.18 103	97.98 72	99.64 187	99.27 27	91.43 239	97.88 141	98.99 159	95.84 38	99.84 116	98.82 79	95.32 216	99.79 97

canonicalmvs		97.09 108	96.32 124	99.39 40	98.93 123	98.95 27	99.72 167	97.35 270	94.45 117	97.88 141	99.42 120	86.71 214	99.52 151	98.48 97	93.97 234	99.72 107

MGCFI-Net		97.00 113	96.22 128	99.34 43	98.86 134	98.80 39	99.67 179	97.30 277	94.31 128	97.77 145	99.41 124	86.36 220	99.50 155	98.38 101	93.90 236	99.72 107

VDDNet		93.12 234	91.91 249	96.76 196	96.67 266	92.65 252	98.69 301	98.21 186	82.81 361	97.75 146	99.28 133	61.57 377	99.48 161	98.09 116	94.09 232	98.15 231

EPMVS		96.53 136	96.01 133	98.09 133	98.43 162	96.12 147	96.36 362	99.43 21	93.53 161	97.64 147	95.04 328	94.41 70	98.38 226	91.13 254	98.11 154	99.75 103

JIA-IIPM		91.76 267	90.70 267	94.94 247	96.11 274	87.51 339	93.16 384	98.13 200	75.79 383	97.58 148	77.68 397	92.84 120	97.97 255	88.47 293	96.54 186	99.33 176

EPNet_dtu		95.71 164	95.39 160	96.66 200	98.92 126	93.41 233	99.57 197	98.90 47	96.19 75	97.52 149	98.56 206	92.65 125	97.36 277	77.89 365	98.33 145	99.20 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		98.12 60	97.93 64	98.70 89	99.94 13	96.13 145	99.82 136	98.43 131	94.56 115	97.52 149	99.70 87	94.40 71	99.98 43	97.00 153	99.98 32	99.99 23

FE-MVS		95.70 166	95.01 174	97.79 150	98.21 177	94.57 198	95.03 376	98.69 68	88.90 292	97.50 151	96.19 284	92.60 128	99.49 160	89.99 278	97.94 160	99.31 178

thisisatest0515		97.41 94	97.02 100	98.59 99	97.71 212	97.52 89	99.97 28	98.54 101	91.83 225	97.45 152	99.04 153	97.50 8	99.10 178	94.75 195	96.37 192	99.16 191

OMC-MVS		97.28 98	97.23 90	97.41 174	99.76 66	93.36 236	99.65 183	97.95 214	96.03 77	97.41 153	99.70 87	89.61 181	99.51 153	96.73 162	98.25 150	99.38 168

testing99		97.17 103	96.91 102	97.95 140	98.35 167	95.70 160	99.91 84	98.43 131	92.94 178	97.36 154	98.72 189	94.83 61	99.21 168	97.00 153	94.64 222	98.95 205

testing91		97.16 104	96.90 103	97.97 139	98.35 167	95.67 163	99.91 84	98.42 143	92.91 180	97.33 155	98.72 189	94.81 62	99.21 168	96.98 155	94.63 223	99.03 202

gg-mvs-nofinetune		93.51 225	91.86 251	98.47 110	97.72 210	97.96 74	92.62 385	98.51 107	74.70 387	97.33 155	69.59 400	98.91 3	97.79 264	97.77 135	99.56 98	99.67 117

PatchT		90.38 292	88.75 308	95.25 238	95.99 278	90.16 306	91.22 392	97.54 251	76.80 379	97.26 157	86.01 391	91.88 146	96.07 346	66.16 390	95.91 202	99.51 153

PLC	95.54 3	97.93 65	97.89 67	98.05 136	99.82 58	94.77 197	99.92 79	98.46 117	93.93 149	97.20 158	99.27 136	95.44 46	99.97 53	97.41 142	99.51 103	99.41 166
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		98.29 51	97.96 62	99.30 44	99.85 54	97.93 75	99.39 224	98.28 179	95.76 82	97.18 159	99.88 21	92.74 124	100.00 1	98.67 88	99.88 69	99.99 23

UWE-MVS		96.79 122	96.72 111	97.00 188	98.51 158	93.70 224	99.71 170	98.60 84	92.96 177	97.09 160	98.34 219	96.67 27	98.85 188	92.11 242	96.50 188	98.44 225

PatchmatchNet		95.94 157	95.45 158	97.39 176	97.83 199	94.41 203	96.05 369	98.40 152	92.86 181	97.09 160	95.28 323	94.21 82	98.07 251	89.26 284	98.11 154	99.70 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		97.10 106	96.72 111	98.22 124	97.60 218	96.70 120	99.92 79	98.54 101	91.11 249	97.07 162	98.97 163	97.47 11	99.03 180	93.73 221	96.09 195	98.92 206

test_fmvsmvis_n_1920		97.67 83	97.59 78	97.91 145	97.02 245	95.34 176	99.95 53	98.45 118	97.87 15	97.02 163	99.59 106	89.64 180	99.98 43	99.41 48	99.34 116	98.42 226

CR-MVSNet		93.45 228	92.62 233	95.94 218	96.29 269	92.66 250	92.01 388	96.23 351	92.62 195	96.94 164	93.31 359	91.04 159	96.03 347	79.23 358	95.96 198	99.13 195

RPMNet		89.76 307	87.28 322	97.19 184	96.29 269	92.66 250	92.01 388	98.31 174	70.19 393	96.94 164	85.87 392	87.25 208	99.78 125	62.69 394	95.96 198	99.13 195

baseline		96.43 139	95.98 136	97.76 155	97.34 232	95.17 186	99.51 207	97.17 290	93.92 150	96.90 166	99.28 133	85.37 230	98.64 204	97.50 141	96.86 184	99.46 159

ECVR-MVS		95.66 167	95.05 172	97.51 169	98.66 146	93.71 223	98.85 287	98.45 118	94.93 101	96.86 167	98.96 165	75.22 321	99.20 171	95.34 179	98.15 151	99.64 123

Vis-MVSNet		95.72 162	95.15 169	97.45 171	97.62 217	94.28 207	99.28 240	98.24 183	94.27 133	96.84 168	98.94 172	79.39 282	98.76 194	93.25 226	98.49 141	99.30 180
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
VDD-MVS		93.77 217	92.94 225	96.27 212	98.55 154	90.22 305	98.77 294	97.79 230	90.85 256	96.82 169	99.42 120	61.18 379	99.77 128	98.95 67	94.13 231	98.82 212

UGNet		95.33 175	94.57 183	97.62 164	98.55 154	94.85 192	98.67 303	99.32 26	95.75 83	96.80 170	96.27 282	72.18 335	99.96 61	94.58 200	99.05 129	98.04 234
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
AdaColmap		97.23 101	96.80 108	98.51 108	99.99 1	95.60 166	99.09 253	98.84 58	93.32 168	96.74 171	99.72 83	86.04 223	100.00 1	98.01 119	99.43 111	99.94 74

tpm		93.70 221	93.41 215	94.58 261	95.36 302	87.41 340	97.01 352	96.90 321	90.85 256	96.72 172	94.14 351	90.40 172	96.84 314	90.75 265	88.54 271	99.51 153

test1111		95.57 169	94.98 175	97.37 177	98.56 151	93.37 235	98.86 285	98.45 118	94.95 100	96.63 173	98.95 170	75.21 322	99.11 177	95.02 185	98.14 153	99.64 123

tttt0517		96.85 119	96.49 120	97.92 143	97.48 225	95.89 152	99.85 121	98.54 101	90.72 261	96.63 173	98.93 174	97.47 11	99.02 181	93.03 233	95.76 206	98.85 210

casdiffmvs		96.42 141	95.97 139	97.77 153	97.30 236	94.98 189	99.84 126	97.09 300	93.75 156	96.58 175	99.26 139	85.07 232	98.78 192	97.77 135	97.04 178	99.54 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNLPA		97.76 78	97.38 83	98.92 80	99.53 87	96.84 116	99.87 106	98.14 199	93.78 154	96.55 176	99.69 89	92.28 138	99.98 43	97.13 149	99.44 109	99.93 76

PatchMatch-RL		96.04 155	95.40 159	97.95 140	99.59 81	95.22 183	99.52 205	99.07 34	93.96 147	96.49 177	98.35 218	82.28 252	99.82 120	90.15 276	99.22 122	98.81 213

MP-MVS-pluss		98.07 62	97.64 74	99.38 42	99.74 69	98.41 62	99.74 159	98.18 190	93.35 166	96.45 178	99.85 30	92.64 126	99.97 53	98.91 74	99.89 67	99.77 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ADS-MVSNet2		93.80 216	93.88 200	93.55 303	97.87 196	85.94 348	94.24 377	96.84 326	90.07 271	96.43 179	94.48 346	90.29 174	95.37 356	87.44 303	97.23 172	99.36 171

ADS-MVSNet		94.79 185	94.02 195	97.11 187	97.87 196	93.79 220	94.24 377	98.16 195	90.07 271	96.43 179	94.48 346	90.29 174	98.19 244	87.44 303	97.23 172	99.36 171

ACMMP		97.74 79	97.44 81	98.66 92	99.92 31	96.13 145	99.18 248	99.45 19	94.84 106	96.41 181	99.71 85	91.40 151	99.99 36	97.99 121	98.03 158	99.87 87
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
PVSNet_Blended_VisFu		97.27 99	96.81 107	98.66 92	98.81 137	96.67 121	99.92 79	98.64 76	94.51 116	96.38 182	98.49 210	89.05 191	99.88 102	97.10 151	98.34 144	99.43 164

AUN-MVS		93.28 229	92.60 234	95.34 234	98.29 170	90.09 308	99.31 234	98.56 92	91.80 228	96.35 183	98.00 228	89.38 184	98.28 237	92.46 237	69.22 381	97.64 241

FA-MVS(test-final)		95.86 158	95.09 171	98.15 129	97.74 205	95.62 165	96.31 364	98.17 191	91.42 241	96.26 184	96.13 287	90.56 169	99.47 162	92.18 241	97.07 176	99.35 173

thres200		96.96 115	96.21 129	99.22 48	98.97 119	98.84 36	99.85 121	99.71 7	93.17 173	96.26 184	98.88 176	89.87 178	99.51 153	94.26 206	94.91 221	99.31 178

HyFIR lowres test		96.66 132	96.43 122	97.36 179	99.05 112	93.91 219	99.70 174	99.80 3	90.54 263	96.26 184	98.08 225	92.15 141	98.23 242	96.84 161	95.46 211	99.93 76

SCA		94.69 189	93.81 202	97.33 181	97.10 241	94.44 200	98.86 285	98.32 172	93.30 169	96.17 187	95.59 302	76.48 308	97.95 258	91.06 256	97.43 167	99.59 134

casdiffmvs_mvg		96.43 139	95.94 143	97.89 147	97.44 226	95.47 170	99.86 118	97.29 280	93.35 166	96.03 188	99.19 144	85.39 229	98.72 198	97.89 128	97.04 178	99.49 157
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tfpn200view9		96.79 122	95.99 134	99.19 51	98.94 121	98.82 37	99.78 145	99.71 7	92.86 181	96.02 189	98.87 179	89.33 185	99.50 155	93.84 213	94.57 224	99.27 184

thres400		96.78 124	95.99 134	99.16 57	98.94 121	98.82 37	99.78 145	99.71 7	92.86 181	96.02 189	98.87 179	89.33 185	99.50 155	93.84 213	94.57 224	99.16 191

dp		95.05 179	94.43 185	96.91 191	97.99 190	92.73 248	96.29 365	97.98 211	89.70 277	95.93 191	94.67 341	93.83 95	98.45 215	86.91 316	96.53 187	99.54 147

thres100view900		96.74 127	95.92 145	99.18 52	98.90 131	98.77 42	99.74 159	99.71 7	92.59 198	95.84 192	98.86 181	89.25 187	99.50 155	93.84 213	94.57 224	99.27 184

thres600view7		96.69 130	95.87 148	99.14 61	98.90 131	98.78 41	99.74 159	99.71 7	92.59 198	95.84 192	98.86 181	89.25 187	99.50 155	93.44 225	94.50 227	99.16 191

EPP-MVSNet		96.69 130	96.60 116	96.96 190	97.74 205	93.05 240	99.37 227	98.56 92	88.75 295	95.83 194	99.01 156	96.01 32	98.56 207	96.92 159	97.20 174	99.25 186

TESTMET0.1,1		96.74 127	96.26 126	98.16 126	97.36 231	96.48 126	99.96 35	98.29 178	91.93 222	95.77 195	98.07 226	95.54 42	98.29 235	90.55 268	98.89 131	99.70 110

F-COLMAP		96.93 117	96.95 101	96.87 193	99.71 75	91.74 272	99.85 121	97.95 214	93.11 175	95.72 196	99.16 147	92.35 136	99.94 77	95.32 180	99.35 115	98.92 206

test-LLR		96.47 137	96.04 132	97.78 151	97.02 245	95.44 171	99.96 35	98.21 186	94.07 140	95.55 197	96.38 278	93.90 91	98.27 239	90.42 271	98.83 135	99.64 123

test-mter		96.39 142	95.93 144	97.78 151	97.02 245	95.44 171	99.96 35	98.21 186	91.81 227	95.55 197	96.38 278	95.17 49	98.27 239	90.42 271	98.83 135	99.64 123

IS-MVSNet		96.29 148	95.90 146	97.45 171	98.13 184	94.80 195	99.08 255	97.61 243	92.02 221	95.54 199	98.96 165	90.64 168	98.08 249	93.73 221	97.41 170	99.47 158

CHOSEN 1792x2688		96.81 121	96.53 119	97.64 161	98.91 130	93.07 238	99.65 183	99.80 3	95.64 85	95.39 200	98.86 181	84.35 241	99.90 91	96.98 155	99.16 123	99.95 71

CDS-MVSNet		96.34 144	96.07 131	97.13 185	97.37 230	94.96 190	99.53 204	97.91 220	91.55 233	95.37 201	98.32 220	95.05 54	97.13 294	93.80 217	95.75 207	99.30 180
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		94.53 196	95.30 164	92.22 325	97.77 203	82.54 365	99.59 193	97.06 303	94.92 103	95.29 202	95.37 316	85.81 224	97.89 261	94.80 193	97.07 176	96.23 256

CSCG		97.10 106	97.04 98	97.27 183	99.89 45	91.92 267	99.90 91	99.07 34	88.67 297	95.26 203	99.82 46	93.17 112	99.98 43	98.15 112	99.47 105	99.90 83

Vis-MVSNet (Re-imp)		96.32 145	95.98 136	97.35 180	97.93 193	94.82 194	99.47 214	98.15 198	91.83 225	95.09 204	99.11 148	91.37 152	97.47 275	93.47 224	97.43 167	99.74 104

TAMVS		95.85 159	95.58 155	96.65 201	97.07 242	93.50 230	99.17 249	97.82 229	91.39 243	95.02 205	98.01 227	92.20 139	97.30 283	93.75 220	95.83 204	99.14 194

XVG-OURS-SEG-HR		94.79 185	94.70 182	95.08 242	98.05 187	89.19 319	99.08 255	97.54 251	93.66 158	94.87 206	99.58 108	78.78 289	99.79 123	97.31 144	93.40 240	96.25 254

XVG-OURS		94.82 183	94.74 181	95.06 243	98.00 189	89.19 319	99.08 255	97.55 249	94.10 138	94.71 207	99.62 104	80.51 273	99.74 134	96.04 170	93.06 245	96.25 254

ab-mvs		94.69 189	93.42 213	98.51 108	98.07 186	96.26 136	96.49 360	98.68 70	90.31 268	94.54 208	97.00 259	76.30 310	99.71 138	95.98 171	93.38 241	99.56 142

TAPA-MVS	92.12 8	94.42 199	93.60 206	96.90 192	99.33 98	91.78 271	99.78 145	98.00 208	89.89 275	94.52 209	99.47 116	91.97 145	99.18 174	69.90 382	99.52 100	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TR-MVS		94.54 194	93.56 209	97.49 170	97.96 191	94.34 206	98.71 298	97.51 256	90.30 269	94.51 210	98.69 192	75.56 316	98.77 193	92.82 235	95.99 197	99.35 173

Fast-Effi-MVS+		95.02 180	94.19 191	97.52 168	97.88 195	94.55 199	99.97 28	97.08 301	88.85 294	94.47 211	97.96 232	84.59 237	98.41 218	89.84 280	97.10 175	99.59 134

DeepC-MVS	94.51 4	96.92 118	96.40 123	98.45 112	99.16 107	95.90 151	99.66 181	98.06 204	96.37 70	94.37 212	99.49 115	83.29 248	99.90 91	97.63 139	99.61 94	99.55 143
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		91.80 264	92.79 230	88.83 352	98.15 182	69.87 390	98.11 330	96.60 340	83.93 353	94.33 213	99.27 136	79.60 281	99.46 163	91.99 243	93.16 243	97.18 248

WB-MVSnew		92.90 239	92.77 231	93.26 310	96.95 249	93.63 226	99.71 170	98.16 195	91.49 234	94.28 214	98.14 223	81.33 262	96.48 328	79.47 357	95.46 211	89.68 380

BH-RMVSNet		95.18 176	94.31 189	97.80 148	98.17 181	95.23 182	99.76 153	97.53 253	92.52 204	94.27 215	99.25 140	76.84 303	98.80 190	90.89 262	99.54 99	99.35 173

CVMVSNet		94.68 191	94.94 176	93.89 292	96.80 259	86.92 344	99.06 260	98.98 38	94.45 117	94.23 216	99.02 154	85.60 225	95.31 358	90.91 261	95.39 214	99.43 164

baseline1		95.78 161	94.86 177	98.54 105	98.47 161	98.07 67	99.06 260	97.99 209	92.68 192	94.13 217	98.62 200	93.28 108	98.69 201	93.79 218	85.76 295	98.84 211

Anonymous202405211		93.10 235	91.99 247	96.40 208	99.10 109	89.65 316	98.88 281	97.93 216	83.71 355	94.00 218	98.75 188	68.79 349	99.88 102	95.08 184	91.71 246	99.68 113

cascas		94.64 192	93.61 204	97.74 157	97.82 200	96.26 136	99.96 35	97.78 231	85.76 336	94.00 218	97.54 241	76.95 302	99.21 168	97.23 147	95.43 213	97.76 240

Anonymous20240529		92.10 257	90.65 268	96.47 203	98.82 136	90.61 296	98.72 297	98.67 73	75.54 384	93.90 220	98.58 204	66.23 362	99.90 91	94.70 197	90.67 249	98.90 209

LS3D		95.84 160	95.11 170	98.02 137	99.85 54	95.10 187	98.74 295	98.50 112	87.22 318	93.66 221	99.86 26	87.45 205	99.95 69	90.94 260	99.81 79	99.02 203

GeoE		94.36 203	93.48 211	96.99 189	97.29 237	93.54 229	99.96 35	96.72 335	88.35 304	93.43 222	98.94 172	82.05 253	98.05 252	88.12 298	96.48 190	99.37 170

HQP-NCC					95.78 283		99.87 106		96.82 48	93.37 223

ACMP_Plane					95.78 283		99.87 106		96.82 48	93.37 223

HQP4-MVS										93.37 223			98.39 222			94.53 262

HQP-MVS		94.61 193	94.50 184	94.92 248	95.78 283	91.85 268	99.87 106	97.89 221	96.82 48	93.37 223	98.65 196	80.65 271	98.39 222	97.92 125	89.60 251	94.53 262

HQP_MVS		94.49 197	94.36 186	94.87 249	95.71 293	91.74 272	99.84 126	97.87 223	96.38 67	93.01 227	98.59 201	80.47 275	98.37 228	97.79 133	89.55 254	94.52 264

plane_prior3						91.64 278			96.63 56	93.01 227

GA-MVS		93.83 213	92.84 227	96.80 194	95.73 290	93.57 227	99.88 103	97.24 285	92.57 200	92.92 229	96.66 270	78.73 290	97.67 269	87.75 301	94.06 233	99.17 190

tpm cat1		93.51 225	92.52 239	96.47 203	97.77 203	91.47 282	96.13 367	98.06 204	80.98 369	92.91 230	93.78 354	89.66 179	98.87 186	87.03 312	96.39 191	99.09 197

1112_ss		96.01 156	95.20 167	98.42 115	97.80 201	96.41 129	99.65 183	96.66 337	92.71 189	92.88 231	99.40 125	92.16 140	99.30 165	91.92 245	93.66 237	99.55 143

Test_1112_low_res		95.72 162	94.83 178	98.42 115	97.79 202	96.41 129	99.65 183	96.65 338	92.70 190	92.86 232	96.13 287	92.15 141	99.30 165	91.88 246	93.64 238	99.55 143

IB-MVS	92.85 6	94.99 181	93.94 198	98.16 126	97.72 210	95.69 162	99.99 5	98.81 60	94.28 131	92.70 233	96.90 261	95.08 52	99.17 175	96.07 169	73.88 371	99.60 133
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
bld_raw_dy_0_64		94.22 207	92.97 224	97.98 138	98.62 149	95.09 188	99.89 99	93.09 391	96.55 59	92.59 234	99.80 51	68.57 352	99.19 173	98.92 70	88.69 266	99.68 113

Fast-Effi-MVS+-dtu		93.72 220	93.86 201	93.29 308	97.06 243	86.16 346	99.80 142	96.83 327	92.66 193	92.58 235	97.83 236	81.39 260	97.67 269	89.75 281	96.87 183	96.05 259

SDMVSNet		94.80 184	93.96 197	97.33 181	98.92 126	95.42 173	99.59 193	98.99 37	92.41 208	92.55 236	97.85 234	75.81 315	98.93 185	97.90 127	91.62 247	97.64 241

sd_testset		93.55 224	92.83 228	95.74 224	98.92 126	90.89 291	98.24 323	98.85 56	92.41 208	92.55 236	97.85 234	71.07 343	98.68 202	93.93 210	91.62 247	97.64 241

iter_conf05		96.07 153	95.95 142	96.44 207	98.43 162	97.52 89	99.91 84	96.85 325	94.16 135	92.49 238	97.98 231	98.20 4	97.34 279	97.26 146	88.29 274	94.45 272

dmvs_re		93.20 231	93.15 221	93.34 306	96.54 267	83.81 359	98.71 298	98.51 107	91.39 243	92.37 239	98.56 206	78.66 291	97.83 263	93.89 211	89.74 250	98.38 227

tpmvs		94.28 205	93.57 208	96.40 208	98.55 154	91.50 281	95.70 375	98.55 98	87.47 313	92.15 240	94.26 350	91.42 150	98.95 184	88.15 296	95.85 203	98.76 215

Syy-MVS		90.00 303	90.63 269	88.11 359	97.68 213	74.66 387	99.71 170	98.35 165	90.79 258	92.10 241	98.67 193	79.10 287	93.09 379	63.35 393	95.95 200	96.59 252

myMVS_eth3d		94.46 198	94.76 180	93.55 303	97.68 213	90.97 286	99.71 170	98.35 165	90.79 258	92.10 241	98.67 193	92.46 134	93.09 379	87.13 309	95.95 200	96.59 252

BH-w/o		95.71 164	95.38 161	96.68 199	98.49 160	92.28 258	99.84 126	97.50 257	92.12 216	92.06 243	98.79 186	84.69 236	98.67 203	95.29 181	99.66 87	99.09 197

VPA-MVSNet		92.70 244	91.55 256	96.16 214	95.09 304	96.20 141	98.88 281	99.00 36	91.02 253	91.82 244	95.29 322	76.05 314	97.96 257	95.62 178	81.19 329	94.30 283

baseline2		96.71 129	96.49 120	97.37 177	95.63 298	95.96 150	99.74 159	98.88 51	92.94 178	91.61 245	98.97 163	97.72 6	98.62 205	94.83 192	98.08 157	97.53 246

OPM-MVS		93.21 230	92.80 229	94.44 270	93.12 340	90.85 292	99.77 148	97.61 243	96.19 75	91.56 246	98.65 196	75.16 323	98.47 211	93.78 219	89.39 257	93.99 313
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		93.73 219	93.40 216	94.74 253	96.80 259	92.69 249	99.06 260	97.67 236	88.96 289	91.39 247	99.02 154	88.75 195	97.30 283	91.07 255	87.85 281	94.22 288

MVSTER		95.53 170	95.22 166	96.45 205	98.56 151	97.72 80	99.91 84	97.67 236	92.38 210	91.39 247	97.14 251	97.24 17	97.30 283	94.80 193	87.85 281	94.34 282

mvsmamba		94.10 208	93.72 203	95.25 238	93.57 329	94.13 212	99.67 179	96.45 346	93.63 160	91.34 249	97.77 237	86.29 221	97.22 289	96.65 163	88.10 278	94.40 274

testing3		93.92 211	94.23 190	92.99 317	97.54 220	90.23 304	99.99 5	99.16 30	90.57 262	91.33 250	98.63 199	92.99 115	92.52 383	82.46 342	95.39 214	96.22 257

test_fmvs2		89.47 311	89.70 288	88.77 355	94.54 314	75.74 384	99.83 133	94.70 379	94.71 110	91.08 251	96.82 269	54.46 386	97.78 266	92.87 234	88.27 275	92.80 352

BH-untuned		95.18 176	94.83 178	96.22 213	98.36 165	91.22 284	99.80 142	97.32 275	90.91 254	91.08 251	98.67 193	83.51 245	98.54 209	94.23 207	99.61 94	98.92 206

CLD-MVS		94.06 210	93.90 199	94.55 263	96.02 277	90.69 293	99.98 15	97.72 232	96.62 58	91.05 253	98.85 184	77.21 297	98.47 211	98.11 114	89.51 256	94.48 266
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS		96.60 133	95.56 156	99.72 13	96.85 256	99.22 20	98.31 320	98.94 41	91.57 232	90.90 254	99.61 105	86.66 216	99.96 61	97.36 143	99.88 69	99.99 23

MSDG		94.37 201	93.36 217	97.40 175	98.88 133	93.95 218	99.37 227	97.38 268	85.75 338	90.80 255	99.17 146	84.11 243	99.88 102	86.35 317	98.43 143	98.36 228

VPNet		91.81 261	90.46 271	95.85 221	94.74 310	95.54 168	98.98 270	98.59 86	92.14 215	90.77 256	97.44 243	68.73 351	97.54 273	94.89 191	77.89 354	94.46 267

MIMVSNet		90.30 295	88.67 309	95.17 241	96.45 268	91.64 278	92.39 386	97.15 293	85.99 333	90.50 257	93.19 361	66.95 359	94.86 364	82.01 346	93.43 239	99.01 204

mvs_anonymous		95.65 168	95.03 173	97.53 167	98.19 179	95.74 157	99.33 231	97.49 258	90.87 255	90.47 258	97.10 253	88.23 198	97.16 291	95.92 172	97.66 164	99.68 113

Patchmatch-test		92.65 247	91.50 257	96.10 216	96.85 256	90.49 299	91.50 390	97.19 287	82.76 362	90.23 259	95.59 302	95.02 55	98.00 254	77.41 367	96.98 181	99.82 92

LPG-MVS_test		92.96 237	92.71 232	93.71 297	95.43 300	88.67 326	99.75 156	97.62 240	92.81 184	90.05 260	98.49 210	75.24 319	98.40 220	95.84 174	89.12 258	94.07 305

LGP-MVS_train				93.71 297	95.43 300	88.67 326		97.62 240	92.81 184	90.05 260	98.49 210	75.24 319	98.40 220	95.84 174	89.12 258	94.07 305

DP-MVS		94.54 194	93.42 213	97.91 145	99.46 94	94.04 214	98.93 276	97.48 259	81.15 368	90.04 262	99.55 110	87.02 211	99.95 69	88.97 286	98.11 154	99.73 105

test_djsdf		92.83 241	92.29 242	94.47 268	91.90 360	92.46 255	99.55 201	97.27 282	91.17 246	89.96 263	96.07 290	81.10 264	96.89 311	94.67 198	88.91 260	94.05 307

ACMM	91.95 10	92.88 240	92.52 239	93.98 288	95.75 289	89.08 322	99.77 148	97.52 255	93.00 176	89.95 264	97.99 230	76.17 312	98.46 214	93.63 223	88.87 262	94.39 276
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
1314		96.84 120	95.96 140	99.48 34	96.74 263	98.52 58	98.31 320	98.86 53	95.82 80	89.91 265	98.98 161	87.49 204	99.96 61	97.80 130	99.73 83	99.96 64

XVG-ACMP-BASELINE		91.22 275	90.75 266	92.63 322	93.73 327	85.61 349	98.52 311	97.44 261	92.77 187	89.90 266	96.85 265	66.64 361	98.39 222	92.29 239	88.61 268	93.89 321

miper_enhance_ethall		94.36 203	93.98 196	95.49 227	98.68 144	95.24 181	99.73 164	97.29 280	93.28 170	89.86 267	95.97 291	94.37 75	97.05 300	92.20 240	84.45 307	94.19 291

nrg030		93.51 225	92.53 238	96.45 205	94.36 316	97.20 102	99.81 138	97.16 292	91.60 231	89.86 267	97.46 242	86.37 219	97.68 268	95.88 173	80.31 341	94.46 267

V42		91.28 272	90.12 283	94.74 253	93.42 334	93.46 231	99.68 177	97.02 306	87.36 315	89.85 269	95.05 327	81.31 263	97.34 279	87.34 306	80.07 343	93.40 339

v144192		90.79 283	89.52 293	94.59 260	93.11 341	92.77 244	99.56 199	96.99 309	86.38 329	89.82 270	94.95 334	80.50 274	97.10 297	83.98 333	80.41 339	93.90 320

GBi-Net		90.88 280	89.82 286	94.08 281	97.53 221	91.97 263	98.43 314	96.95 314	87.05 319	89.68 271	94.72 337	71.34 339	96.11 342	87.01 313	85.65 296	94.17 292

test1		90.88 280	89.82 286	94.08 281	97.53 221	91.97 263	98.43 314	96.95 314	87.05 319	89.68 271	94.72 337	71.34 339	96.11 342	87.01 313	85.65 296	94.17 292

FMVSNet3		92.69 245	91.58 254	95.99 217	98.29 170	97.42 97	99.26 242	97.62 240	89.80 276	89.68 271	95.32 318	81.62 259	96.27 337	87.01 313	85.65 296	94.29 284

IterMVS-LS		92.69 245	92.11 244	94.43 272	96.80 259	92.74 246	99.45 217	96.89 322	88.98 287	89.65 274	95.38 315	88.77 194	96.34 334	90.98 259	82.04 323	94.22 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		91.09 276	89.83 285	94.87 249	93.25 337	93.69 225	99.62 190	96.98 311	86.83 325	89.64 275	94.99 332	80.94 266	97.05 300	85.08 327	81.16 330	93.87 323

v1921920		90.46 290	89.12 300	94.50 266	92.96 345	92.46 255	99.49 211	96.98 311	86.10 332	89.61 276	95.30 319	78.55 293	97.03 304	82.17 345	80.89 337	94.01 310

v1192		90.62 288	89.25 298	94.72 255	93.13 338	93.07 238	99.50 209	97.02 306	86.33 330	89.56 277	95.01 329	79.22 284	97.09 299	82.34 344	81.16 330	94.01 310

PCF-MVS	94.20 5	95.18 176	94.10 193	98.43 114	98.55 154	95.99 149	97.91 336	97.31 276	90.35 267	89.48 278	99.22 142	85.19 231	99.89 96	90.40 273	98.47 142	99.41 166
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	91.47 12	96.28 149	95.34 162	99.08 67	96.82 258	97.47 95	99.45 217	98.81 60	95.52 90	89.39 279	99.00 158	81.97 254	99.95 69	97.27 145	99.83 73	99.84 90

v1240		90.20 298	88.79 307	94.44 270	93.05 343	92.27 259	99.38 225	96.92 320	85.89 334	89.36 280	94.87 336	77.89 296	97.03 304	80.66 352	81.08 333	94.01 310

FIs		94.10 208	93.43 212	96.11 215	94.70 311	96.82 117	99.58 195	98.93 45	92.54 201	89.34 281	97.31 247	87.62 203	97.10 297	94.22 208	86.58 291	94.40 274

ITE_SJBPF				92.38 323	95.69 295	85.14 352		95.71 361	92.81 184	89.33 282	98.11 224	70.23 345	98.42 217	85.91 322	88.16 277	93.59 336

v2v482		91.30 270	90.07 284	95.01 244	93.13 338	93.79 220	99.77 148	97.02 306	88.05 307	89.25 283	95.37 316	80.73 269	97.15 292	87.28 307	80.04 344	94.09 304

UniMVSNet (Re)		93.07 236	92.13 243	95.88 219	94.84 308	96.24 140	99.88 103	98.98 38	92.49 206	89.25 283	95.40 312	87.09 210	97.14 293	93.13 231	78.16 352	94.26 285

tt0805		91.28 272	90.18 280	94.60 259	96.26 271	87.55 338	98.39 318	98.72 65	89.00 286	89.22 285	98.47 214	62.98 373	98.96 183	90.57 267	88.00 280	97.28 247

UniMVSNet_NR-MVSNet		92.95 238	92.11 244	95.49 227	94.61 313	95.28 179	99.83 133	99.08 33	91.49 234	89.21 286	96.86 264	87.14 209	96.73 319	93.20 227	77.52 357	94.46 267

DU-MVS		92.46 250	91.45 259	95.49 227	94.05 321	95.28 179	99.81 138	98.74 64	92.25 214	89.21 286	96.64 272	81.66 257	96.73 319	93.20 227	77.52 357	94.46 267

eth_miper_zixun_eth		92.41 251	91.93 248	93.84 293	97.28 238	90.68 294	98.83 288	96.97 313	88.57 300	89.19 288	95.73 297	89.24 189	96.69 321	89.97 279	81.55 326	94.15 298

cl22		93.77 217	93.25 220	95.33 235	99.49 91	94.43 201	99.61 191	98.09 201	90.38 265	89.16 289	95.61 300	90.56 169	97.34 279	91.93 244	84.45 307	94.21 290

Baseline_NR-MVSNet		90.33 294	89.51 294	92.81 320	92.84 346	89.95 312	99.77 148	93.94 386	84.69 350	89.04 290	95.66 299	81.66 257	96.52 326	90.99 258	76.98 363	91.97 363

FC-MVSNet-test		93.81 215	93.15 221	95.80 223	94.30 318	96.20 141	99.42 219	98.89 49	92.33 212	89.03 291	97.27 249	87.39 206	96.83 315	93.20 227	86.48 292	94.36 278

QAPM		95.40 173	94.17 192	99.10 66	96.92 250	97.71 81	99.40 220	98.68 70	89.31 280	88.94 292	98.89 175	82.48 251	99.96 61	93.12 232	99.83 73	99.62 128

RRT_MVS		93.14 233	92.92 226	93.78 294	93.31 336	90.04 309	99.66 181	97.69 234	92.53 202	88.91 293	97.76 238	84.36 239	96.93 309	95.10 183	86.99 289	94.37 277

miper_ehance_all_eth		93.16 232	92.60 234	94.82 252	97.57 219	93.56 228	99.50 209	97.07 302	88.75 295	88.85 294	95.52 306	90.97 161	96.74 318	90.77 264	84.45 307	94.17 292

AllTest		92.48 249	91.64 252	95.00 245	99.01 114	88.43 330	98.94 275	96.82 329	86.50 327	88.71 295	98.47 214	74.73 325	99.88 102	85.39 324	96.18 193	96.71 250

TestCases				95.00 245	99.01 114	88.43 330		96.82 329	86.50 327	88.71 295	98.47 214	74.73 325	99.88 102	85.39 324	96.18 193	96.71 250

c3_l		92.53 248	91.87 250	94.52 264	97.40 228	92.99 242	99.40 220	96.93 319	87.86 309	88.69 297	95.44 310	89.95 177	96.44 330	90.45 270	80.69 338	94.14 301

pmmvs4		92.10 257	91.07 264	95.18 240	92.82 348	94.96 190	99.48 213	96.83 327	87.45 314	88.66 298	96.56 276	83.78 244	96.83 315	89.29 283	84.77 305	93.75 329

PS-MVSNAJss		93.64 222	93.31 218	94.61 258	92.11 357	92.19 260	99.12 251	97.38 268	92.51 205	88.45 299	96.99 260	91.20 154	97.29 286	94.36 203	87.71 283	94.36 278

UniMVSNet_ETH3D		90.06 302	88.58 310	94.49 267	94.67 312	88.09 335	97.81 339	97.57 248	83.91 354	88.44 300	97.41 244	57.44 383	97.62 271	91.41 250	88.59 270	97.77 239

TranMVSNet+NR-MVSNet		91.68 268	90.61 270	94.87 249	93.69 328	93.98 217	99.69 175	98.65 74	91.03 252	88.44 300	96.83 268	80.05 278	96.18 340	90.26 275	76.89 365	94.45 272

FMVSNet2		91.02 277	89.56 291	95.41 232	97.53 221	95.74 157	98.98 270	97.41 266	87.05 319	88.43 302	95.00 331	71.34 339	96.24 339	85.12 326	85.21 301	94.25 287

COLMAP_ROB	90.47 14	92.18 256	91.49 258	94.25 277	99.00 116	88.04 336	98.42 317	96.70 336	82.30 364	88.43 302	99.01 156	76.97 301	99.85 108	86.11 320	96.50 188	94.86 261
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator+	91.53 11	96.31 146	95.24 165	99.52 28	96.88 255	98.64 54	99.72 167	98.24 183	95.27 96	88.42 304	98.98 161	82.76 250	99.94 77	97.10 151	99.83 73	99.96 64

v148		90.70 284	89.63 289	93.92 289	92.97 344	90.97 286	99.75 156	96.89 322	87.51 312	88.27 305	95.01 329	81.67 256	97.04 302	87.40 305	77.17 362	93.75 329

DSMNet-mixed		88.28 320	88.24 315	88.42 357	89.64 379	75.38 386	98.06 332	89.86 400	85.59 340	88.20 306	92.14 369	76.15 313	91.95 386	78.46 363	96.05 196	97.92 235

WR-MVS		92.31 253	91.25 261	95.48 230	94.45 315	95.29 178	99.60 192	98.68 70	90.10 270	88.07 307	96.89 262	80.68 270	96.80 317	93.14 230	79.67 345	94.36 278

test0.0.03 1		93.86 212	93.61 204	94.64 257	95.02 307	92.18 261	99.93 76	98.58 87	94.07 140	87.96 308	98.50 209	93.90 91	94.96 362	81.33 349	93.17 242	96.78 249

XXY-MVS		91.82 260	90.46 271	95.88 219	93.91 324	95.40 175	98.87 284	97.69 234	88.63 299	87.87 309	97.08 254	74.38 328	97.89 261	91.66 248	84.07 311	94.35 281

Patchmtry		89.70 308	88.49 311	93.33 307	96.24 272	89.94 314	91.37 391	96.23 351	78.22 377	87.69 310	93.31 359	91.04 159	96.03 347	80.18 356	82.10 322	94.02 308

DIV-MVS_self_test		92.32 252	91.60 253	94.47 268	97.31 235	92.74 246	99.58 195	96.75 333	86.99 322	87.64 311	95.54 304	89.55 182	96.50 327	88.58 290	82.44 320	94.17 292

D2MVS		92.76 242	92.59 237	93.27 309	95.13 303	89.54 318	99.69 175	99.38 23	92.26 213	87.59 312	94.61 343	85.05 233	97.79 264	91.59 249	88.01 279	92.47 357

cl____		92.31 253	91.58 254	94.52 264	97.33 234	92.77 244	99.57 197	96.78 332	86.97 323	87.56 313	95.51 307	89.43 183	96.62 323	88.60 289	82.44 320	94.16 297

v8		90.54 289	89.17 299	94.66 256	93.43 333	93.40 234	99.20 246	96.94 318	85.76 336	87.56 313	94.51 344	81.96 255	97.19 290	84.94 328	78.25 351	93.38 341

miper_lstm_enhance		91.81 261	91.39 260	93.06 316	97.34 232	89.18 321	99.38 225	96.79 331	86.70 326	87.47 315	95.22 324	90.00 176	95.86 351	88.26 294	81.37 328	94.15 298

anonymousdsp		91.79 266	90.92 265	94.41 273	90.76 372	92.93 243	98.93 276	97.17 290	89.08 282	87.46 316	95.30 319	78.43 295	96.92 310	92.38 238	88.73 265	93.39 340

jajsoiax		91.92 259	91.18 262	94.15 278	91.35 367	90.95 289	99.00 269	97.42 264	92.61 196	87.38 317	97.08 254	72.46 334	97.36 277	94.53 201	88.77 264	94.13 302

mvs_tets		91.81 261	91.08 263	94.00 286	91.63 364	90.58 297	98.67 303	97.43 262	92.43 207	87.37 318	97.05 257	71.76 336	97.32 282	94.75 195	88.68 267	94.11 303

v10		90.25 297	88.82 306	94.57 262	93.53 331	93.43 232	99.08 255	96.87 324	85.00 345	87.34 319	94.51 344	80.93 267	97.02 306	82.85 340	79.23 346	93.26 343

pmmvs5		90.17 300	89.09 301	93.40 305	92.10 358	89.77 315	99.74 159	95.58 365	85.88 335	87.24 320	95.74 295	73.41 332	96.48 328	88.54 291	83.56 314	93.95 316

ACMP	92.05 9	92.74 243	92.42 241	93.73 295	95.91 281	88.72 325	99.81 138	97.53 253	94.13 136	87.00 321	98.23 221	74.07 329	98.47 211	96.22 168	88.86 263	93.99 313
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS-HIRNet		86.22 329	83.19 342	95.31 236	96.71 265	90.29 303	92.12 387	97.33 274	62.85 394	86.82 322	70.37 399	69.37 347	97.49 274	75.12 374	97.99 159	98.15 231

Anonymous20231211		89.86 305	88.44 312	94.13 280	98.93 123	90.68 294	98.54 309	98.26 182	76.28 380	86.73 323	95.54 304	70.60 344	97.56 272	90.82 263	80.27 342	94.15 298

v7n		89.65 309	88.29 314	93.72 296	92.22 355	90.56 298	99.07 259	97.10 298	85.42 343	86.73 323	94.72 337	80.06 277	97.13 294	81.14 350	78.12 353	93.49 337

IterMVS-SCA-FT		90.85 282	90.16 282	92.93 318	96.72 264	89.96 311	98.89 279	96.99 309	88.95 290	86.63 325	95.67 298	76.48 308	95.00 361	87.04 311	84.04 313	93.84 325

EU-MVSNet		90.14 301	90.34 275	89.54 347	92.55 351	81.06 376	98.69 301	98.04 207	91.41 242	86.59 326	96.84 267	80.83 268	93.31 378	86.20 318	81.91 324	94.26 285

OpenMVS	90.15 15	94.77 187	93.59 207	98.33 119	96.07 275	97.48 94	99.56 199	98.57 89	90.46 264	86.51 327	98.95 170	78.57 292	99.94 77	93.86 212	99.74 82	97.57 245

IterMVS		90.91 279	90.17 281	93.12 313	96.78 262	90.42 302	98.89 279	97.05 305	89.03 284	86.49 328	95.42 311	76.59 306	95.02 360	87.22 308	84.09 310	93.93 318
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS_H		91.30 270	90.35 274	94.15 278	94.17 320	92.62 253	99.17 249	98.94 41	88.87 293	86.48 329	94.46 348	84.36 239	96.61 324	88.19 295	78.51 350	93.21 345

MS-PatchMatch		90.65 285	90.30 276	91.71 331	94.22 319	85.50 351	98.24 323	97.70 233	88.67 297	86.42 330	96.37 280	67.82 356	98.03 253	83.62 336	99.62 90	91.60 365

CP-MVSNet		91.23 274	90.22 278	94.26 276	93.96 323	92.39 257	99.09 253	98.57 89	88.95 290	86.42 330	96.57 275	79.19 285	96.37 332	90.29 274	78.95 347	94.02 308

LF4IMVS		89.25 315	88.85 305	90.45 341	92.81 349	81.19 375	98.12 329	94.79 376	91.44 238	86.29 332	97.11 252	65.30 367	98.11 248	88.53 292	85.25 300	92.07 360

PVSNet_0	88.03 19	91.80 264	90.27 277	96.38 210	98.27 173	90.46 300	99.94 69	99.61 14	93.99 145	86.26 333	97.39 246	71.13 342	99.89 96	98.77 82	67.05 387	98.79 214

PS-CasMVS		90.63 287	89.51 294	93.99 287	93.83 325	91.70 276	98.98 270	98.52 104	88.48 301	86.15 334	96.53 277	75.46 317	96.31 336	88.83 287	78.86 349	93.95 316

FMVSNet1		88.50 318	86.64 324	94.08 281	95.62 299	91.97 263	98.43 314	96.95 314	83.00 359	86.08 335	94.72 337	59.09 381	96.11 342	81.82 348	84.07 311	94.17 292

PEN-MVS		90.19 299	89.06 302	93.57 302	93.06 342	90.90 290	99.06 260	98.47 115	88.11 306	85.91 336	96.30 281	76.67 304	95.94 350	87.07 310	76.91 364	93.89 321

ppachtmachnet_test		89.58 310	88.35 313	93.25 311	92.40 353	90.44 301	99.33 231	96.73 334	85.49 341	85.90 337	95.77 294	81.09 265	96.00 349	76.00 373	82.49 319	93.30 342

OurMVSNet-221017-0		89.81 306	89.48 296	90.83 337	91.64 363	81.21 374	98.17 328	95.38 369	91.48 236	85.65 338	97.31 247	72.66 333	97.29 286	88.15 296	84.83 304	93.97 315

our_test_3		90.39 291	89.48 296	93.12 313	92.40 353	89.57 317	99.33 231	96.35 349	87.84 310	85.30 339	94.99 332	84.14 242	96.09 345	80.38 353	84.56 306	93.71 334

testgi		89.01 316	88.04 317	91.90 329	93.49 332	84.89 355	99.73 164	95.66 363	93.89 153	85.14 340	98.17 222	59.68 380	94.66 366	77.73 366	88.88 261	96.16 258

DTE-MVSNet		89.40 312	88.24 315	92.88 319	92.66 350	89.95 312	99.10 252	98.22 185	87.29 316	85.12 341	96.22 283	76.27 311	95.30 359	83.56 337	75.74 368	93.41 338

FMVSNet5		88.32 319	87.47 321	90.88 335	96.90 254	88.39 332	97.28 345	95.68 362	82.60 363	84.67 342	92.40 367	79.83 279	91.16 388	76.39 372	81.51 327	93.09 346

tfpnnormal		89.29 314	87.61 320	94.34 275	94.35 317	94.13 212	98.95 274	98.94 41	83.94 352	84.47 343	95.51 307	74.84 324	97.39 276	77.05 370	80.41 339	91.48 367

MVP-Stereo		90.93 278	90.45 273	92.37 324	91.25 369	88.76 323	98.05 333	96.17 353	87.27 317	84.04 344	95.30 319	78.46 294	97.27 288	83.78 335	99.70 85	91.09 368
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LTVRE_ROB	88.28 18	90.29 296	89.05 303	94.02 284	95.08 305	90.15 307	97.19 347	97.43 262	84.91 348	83.99 345	97.06 256	74.00 330	98.28 237	84.08 331	87.71 283	93.62 335
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
pm-mvs1		89.36 313	87.81 319	94.01 285	93.40 335	91.93 266	98.62 306	96.48 345	86.25 331	83.86 346	96.14 286	73.68 331	97.04 302	86.16 319	75.73 369	93.04 348

USDC		90.00 303	88.96 304	93.10 315	94.81 309	88.16 334	98.71 298	95.54 366	93.66 158	83.75 347	97.20 250	65.58 364	98.31 233	83.96 334	87.49 287	92.85 351

CL-MVSNet_self_test		84.50 340	83.15 343	88.53 356	86.00 387	81.79 371	98.82 289	97.35 270	85.12 344	83.62 348	90.91 374	76.66 305	91.40 387	69.53 383	60.36 396	92.40 358

ACMH+	89.98 16	90.35 293	89.54 292	92.78 321	95.99 278	86.12 347	98.81 290	97.18 289	89.38 279	83.14 349	97.76 238	68.42 354	98.43 216	89.11 285	86.05 294	93.78 328

Anonymous20231206		86.32 328	85.42 331	89.02 351	89.11 381	80.53 380	99.05 264	95.28 370	85.43 342	82.82 350	93.92 352	74.40 327	93.44 377	66.99 387	81.83 325	93.08 347

KD-MVS_self_test		83.59 346	82.06 346	88.20 358	86.93 385	80.70 378	97.21 346	96.38 347	82.87 360	82.49 351	88.97 380	67.63 357	92.32 384	73.75 376	62.30 395	91.58 366

SixPastTwentyTwo		88.73 317	88.01 318	90.88 335	91.85 361	82.24 367	98.22 326	95.18 374	88.97 288	82.26 352	96.89 262	71.75 337	96.67 322	84.00 332	82.98 315	93.72 333

KD-MVS_2432*1600		88.00 322	86.10 326	93.70 299	96.91 251	94.04 214	97.17 348	97.12 296	84.93 346	81.96 353	92.41 365	92.48 132	94.51 367	79.23 358	52.68 399	92.56 354

miper_refine_blended		88.00 322	86.10 326	93.70 299	96.91 251	94.04 214	97.17 348	97.12 296	84.93 346	81.96 353	92.41 365	92.48 132	94.51 367	79.23 358	52.68 399	92.56 354

TinyColmap		87.87 324	86.51 325	91.94 328	95.05 306	85.57 350	97.65 340	94.08 383	84.40 351	81.82 355	96.85 265	62.14 375	98.33 231	80.25 355	86.37 293	91.91 364

ACMH	89.72 17	90.64 286	89.63 289	93.66 301	95.64 297	88.64 328	98.55 307	97.45 260	89.03 284	81.62 356	97.61 240	69.75 346	98.41 218	89.37 282	87.62 285	93.92 319
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		85.15 336	83.81 338	89.16 350	88.32 382	82.69 363	98.80 292	95.74 360	79.72 373	81.53 357	90.99 372	65.38 366	94.16 369	72.69 377	81.11 332	90.63 373

pmmvs6		85.69 330	83.84 337	91.26 334	90.00 378	84.41 357	97.82 338	96.15 354	75.86 382	81.29 358	95.39 314	61.21 378	96.87 313	83.52 338	73.29 372	92.50 356

TransMVSNet (Re)		87.25 325	85.28 332	93.16 312	93.56 330	91.03 285	98.54 309	94.05 385	83.69 356	81.09 359	96.16 285	75.32 318	96.40 331	76.69 371	68.41 383	92.06 361

test_method		80.79 351	79.70 355	84.08 366	92.83 347	67.06 392	99.51 207	95.42 367	54.34 398	81.07 360	93.53 356	44.48 394	92.22 385	78.90 362	77.23 361	92.94 349

NR-MVSNet		91.56 269	90.22 278	95.60 225	94.05 321	95.76 156	98.25 322	98.70 67	91.16 248	80.78 361	96.64 272	83.23 249	96.57 325	91.41 250	77.73 356	94.46 267

LCM-MVSNet-Re		92.31 253	92.60 234	91.43 332	97.53 221	79.27 382	99.02 268	91.83 396	92.07 217	80.31 362	94.38 349	83.50 246	95.48 354	97.22 148	97.58 165	99.54 147

TDRefinement		84.76 337	82.56 345	91.38 333	74.58 403	84.80 356	97.36 344	94.56 380	84.73 349	80.21 363	96.12 289	63.56 371	98.39 222	87.92 299	63.97 392	90.95 371

N_pmnet		80.06 354	80.78 352	77.89 373	91.94 359	45.28 411	98.80 292	56.82 413	78.10 378	80.08 364	93.33 357	77.03 299	95.76 352	68.14 386	82.81 316	92.64 353

test_fmvs3		79.99 355	80.17 354	79.45 372	84.02 391	62.83 393	99.05 264	93.49 390	88.29 305	80.06 365	86.65 389	28.09 401	88.00 393	88.63 288	73.27 373	87.54 389

test_0402		85.58 331	83.94 336	90.50 339	93.81 326	85.04 353	98.55 307	95.20 373	76.01 381	79.72 366	95.13 325	64.15 370	96.26 338	66.04 391	86.88 290	90.21 376

test20.03		84.72 339	83.99 334	86.91 361	88.19 384	80.62 379	98.88 281	95.94 357	88.36 303	78.87 367	94.62 342	68.75 350	89.11 392	66.52 389	75.82 367	91.00 369

pmmvs3		80.27 353	77.77 358	87.76 360	80.32 398	82.43 366	98.23 325	91.97 395	72.74 391	78.75 368	87.97 385	57.30 384	90.99 389	70.31 381	62.37 394	89.87 378

dmvs_testset		83.79 344	86.07 328	76.94 374	92.14 356	48.60 409	96.75 357	90.27 399	89.48 278	78.65 369	98.55 208	79.25 283	86.65 397	66.85 388	82.69 317	95.57 260

MIMVSNet1		82.58 347	80.51 353	88.78 353	86.68 386	84.20 358	96.65 358	95.41 368	78.75 376	78.59 370	92.44 364	51.88 390	89.76 391	65.26 392	78.95 347	92.38 359

DeepMVS_CX				82.92 369	95.98 280	58.66 400		96.01 356	92.72 188	78.34 371	95.51 307	58.29 382	98.08 249	82.57 341	85.29 299	92.03 362

test_vis1_rt		86.87 327	86.05 329	89.34 348	96.12 273	78.07 383	99.87 106	83.54 407	92.03 220	78.21 372	89.51 378	45.80 393	99.91 89	96.25 167	93.11 244	90.03 377

mvsany_test3		82.12 348	81.14 350	85.06 365	81.87 394	70.41 389	97.09 350	92.14 394	91.27 245	77.84 373	88.73 381	39.31 396	95.49 353	90.75 265	71.24 375	89.29 385

Patchmatch-RL test		86.90 326	85.98 330	89.67 346	84.45 389	75.59 385	89.71 395	92.43 393	86.89 324	77.83 374	90.94 373	94.22 80	93.63 375	87.75 301	69.61 378	99.79 97

APD_test1		81.15 350	80.92 351	81.86 370	92.45 352	59.76 399	96.04 370	93.61 389	73.29 390	77.06 375	96.64 272	44.28 395	96.16 341	72.35 378	82.52 318	89.67 381

lessismore_v0				90.53 338	90.58 373	80.90 377		95.80 359		77.01 376	95.84 292	66.15 363	96.95 307	83.03 339	75.05 370	93.74 332

K. test v3		88.05 321	87.24 323	90.47 340	91.82 362	82.23 368	98.96 273	97.42 264	89.05 283	76.93 377	95.60 301	68.49 353	95.42 355	85.87 323	81.01 335	93.75 329

ambc				83.23 368	77.17 401	62.61 394	87.38 397	94.55 381		76.72 378	86.65 389	30.16 398	96.36 333	84.85 329	69.86 377	90.73 372

PM-MVS		80.47 352	78.88 357	85.26 364	83.79 392	72.22 388	95.89 373	91.08 397	85.71 339	76.56 379	88.30 382	36.64 397	93.90 372	82.39 343	69.57 379	89.66 382

OpenMVS_ROB	79.82 20	83.77 345	81.68 348	90.03 344	88.30 383	82.82 362	98.46 312	95.22 372	73.92 389	76.00 380	91.29 371	55.00 385	96.94 308	68.40 385	88.51 272	90.34 374

UnsupCasMVSNet_eth		85.52 332	83.99 334	90.10 343	89.36 380	83.51 361	96.65 358	97.99 209	89.14 281	75.89 381	93.83 353	63.25 372	93.92 371	81.92 347	67.90 386	92.88 350

new_pmnet		84.49 341	82.92 344	89.21 349	90.03 377	82.60 364	96.89 356	95.62 364	80.59 370	75.77 382	89.17 379	65.04 368	94.79 365	72.12 379	81.02 334	90.23 375

EG-PatchMatch MVS		85.35 335	83.81 338	89.99 345	90.39 374	81.89 370	98.21 327	96.09 355	81.78 366	74.73 383	93.72 355	51.56 391	97.12 296	79.16 361	88.61 268	90.96 370

test_f		78.40 357	77.59 359	80.81 371	80.82 396	62.48 396	96.96 354	93.08 392	83.44 357	74.57 384	84.57 393	27.95 402	92.63 382	84.15 330	72.79 374	87.32 390

pmmvs-eth3d		84.03 343	81.97 347	90.20 342	84.15 390	87.09 342	98.10 331	94.73 378	83.05 358	74.10 385	87.77 386	65.56 365	94.01 370	81.08 351	69.24 380	89.49 383

new-patchmatchnet		81.19 349	79.34 356	86.76 362	82.86 393	80.36 381	97.92 335	95.27 371	82.09 365	72.02 386	86.87 388	62.81 374	90.74 390	71.10 380	63.08 393	89.19 386

ET-MVSNet_ETH3D		94.37 201	93.28 219	97.64 161	98.30 169	97.99 71	99.99 5	97.61 243	94.35 125	71.57 387	99.45 119	96.23 31	95.34 357	96.91 160	85.14 302	99.59 134

UnsupCasMVSNet_bld		79.97 356	77.03 361	88.78 353	85.62 388	81.98 369	93.66 382	97.35 270	75.51 385	70.79 388	83.05 394	48.70 392	94.91 363	78.31 364	60.29 397	89.46 384

CMPMVS	61.59 21	84.75 338	85.14 333	83.57 367	90.32 375	62.54 395	96.98 353	97.59 247	74.33 388	69.95 389	96.66 270	64.17 369	98.32 232	87.88 300	88.41 273	89.84 379
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		76.28 358	77.28 360	73.29 378	81.18 395	54.68 403	97.87 337	94.19 382	81.30 367	69.43 390	90.70 375	77.02 300	82.06 401	35.71 406	68.11 385	83.13 392

SSC-MVS		75.42 359	76.40 362	72.49 382	80.68 397	53.62 404	97.42 342	94.06 384	80.42 371	68.75 391	90.14 377	76.54 307	81.66 402	33.25 407	66.34 389	82.19 393

testmvs		40.60 374	44.45 377	29.05 391	19.49 415	14.11 417	99.68 177	18.47 414	20.74 407	64.59 392	98.48 213	10.95 412	17.09 411	56.66 400	11.01 407	55.94 404

LCM-MVSNet		67.77 365	64.73 368	76.87 375	62.95 409	56.25 402	89.37 396	93.74 388	44.53 401	61.99 393	80.74 395	20.42 408	86.53 398	69.37 384	59.50 398	87.84 387

PMMVS2		67.15 366	64.15 369	76.14 376	70.56 406	62.07 397	93.89 380	87.52 404	58.09 395	60.02 394	78.32 396	22.38 405	84.54 399	59.56 396	47.03 401	81.80 394

testf1		68.38 363	66.92 364	72.78 380	78.80 399	50.36 406	90.95 393	87.35 405	55.47 396	58.95 395	88.14 383	20.64 406	87.60 394	57.28 398	64.69 390	80.39 395

APD_test2		68.38 363	66.92 364	72.78 380	78.80 399	50.36 406	90.95 393	87.35 405	55.47 396	58.95 395	88.14 383	20.64 406	87.60 394	57.28 398	64.69 390	80.39 395

Gipuma		66.95 367	65.00 367	72.79 379	91.52 365	67.96 391	66.16 402	95.15 375	47.89 400	58.54 397	67.99 402	29.74 399	87.54 396	50.20 401	77.83 355	62.87 402
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		85.50 334	83.33 340	92.00 327	90.89 371	88.38 333	99.22 245	96.55 342	79.60 375	57.26 398	92.72 362	79.09 288	93.78 374	77.25 368	77.37 360	93.84 325

MDA-MVSNet_test_wron		85.51 333	83.32 341	92.10 326	90.96 370	88.58 329	99.20 246	96.52 343	79.70 374	57.12 399	92.69 363	79.11 286	93.86 373	77.10 369	77.46 359	93.86 324

MDA-MVSNet-bldmvs		84.09 342	81.52 349	91.81 330	91.32 368	88.00 337	98.67 303	95.92 358	80.22 372	55.60 400	93.32 358	68.29 355	93.60 376	73.76 375	76.61 366	93.82 327

FPMVS		68.72 362	68.72 363	68.71 384	65.95 407	44.27 413	95.97 372	94.74 377	51.13 399	53.26 401	90.50 376	25.11 404	83.00 400	60.80 395	80.97 336	78.87 397

test123		37.68 375	39.14 378	33.31 390	19.94 414	24.83 416	98.36 319	9.75 415	15.53 408	51.31 402	87.14 387	19.62 409	17.74 410	47.10 402	3.47 409	57.36 403

test_vis3_rt		68.82 361	66.69 366	75.21 377	76.24 402	60.41 398	96.44 361	68.71 412	75.13 386	50.54 403	69.52 401	16.42 411	96.32 335	80.27 354	66.92 388	68.89 399

tmp_tt		65.23 368	62.94 371	72.13 383	44.90 412	50.03 408	81.05 399	89.42 403	38.45 402	48.51 404	99.90 18	54.09 387	78.70 404	91.84 247	18.26 406	87.64 388

E-PMN		52.30 371	52.18 373	52.67 388	71.51 404	45.40 410	93.62 383	76.60 410	36.01 404	43.50 405	64.13 404	27.11 403	67.31 407	31.06 408	26.06 403	45.30 406

EMVS		51.44 373	51.22 375	52.11 389	70.71 405	44.97 412	94.04 379	75.66 411	35.34 406	42.40 406	61.56 407	28.93 400	65.87 408	27.64 409	24.73 404	45.49 405

MVE	53.74 22	51.54 372	47.86 376	62.60 386	59.56 410	50.93 405	79.41 400	77.69 409	35.69 405	36.27 407	61.76 406	5.79 415	69.63 405	37.97 405	36.61 402	67.24 400
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 369	52.24 372	67.66 385	49.27 411	56.82 401	83.94 398	82.02 408	70.47 392	33.28 408	64.54 403	17.23 410	69.16 406	45.59 403	23.85 405	77.02 398

PMVS	49.05 23	53.75 370	51.34 374	60.97 387	40.80 413	34.68 414	74.82 401	89.62 402	37.55 403	28.67 409	72.12 398	7.09 413	81.63 403	43.17 404	68.21 384	66.59 401
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 377	20.84 380	18.99 392	65.34 408	27.73 415	50.43 403	7.67 416	9.50 409	8.01 410	6.34 410	6.13 414	26.24 409	23.40 410	10.69 408	2.99 407

EGC-MVSNET		69.38 360	63.76 370	86.26 363	90.32 375	81.66 373	96.24 366	93.85 387	0.99 410	3.22 411	92.33 368	52.44 388	92.92 381	59.53 397	84.90 303	84.21 391

test_blank		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.02 411	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet_test		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

DCPMVS		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

cdsmvs_eth3d_5k		23.43 376	31.24 379	0.00 393	0.00 416	0.00 418	0.00 404	98.09 201	0.00 411	0.00 412	99.67 96	83.37 247	0.00 412	0.00 411	0.00 410	0.00 408

pcd_1.5k_mvsjas		7.60 379	10.13 382	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	91.20 154	0.00 412	0.00 411	0.00 410	0.00 408

sosnet-low-res		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

sosnet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uncertanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

Regformer		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

ab-mvs-re		8.28 378	11.04 381	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	99.40 125	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

uanet		0.00 380	0.00 383	0.00 393	0.00 416	0.00 418	0.00 404	0.00 417	0.00 411	0.00 412	0.00 412	0.00 416	0.00 412	0.00 411	0.00 410	0.00 408

WAC-MVS						90.97 286								86.10 321

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 148					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 148					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 416

eth-test					0.00 416

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 35				99.80 51	97.44 13	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 58	98.79 40	99.96 35	98.40 152	97.66 21

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 53	98.43 131					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 134

sam_mvs1												94.72 64				99.59 134

sam_mvs												94.25 79

MTGPA								98.28 179

test_post1							95.78 374				59.23 408	93.20 111	97.74 267	91.06 256

test_post											63.35 405	94.43 69	98.13 247

patchmatchnet-post											91.70 370	95.12 50	97.95 258

MTMP							99.87 106	96.49 344

gm-plane-assit					96.97 248	93.76 222			91.47 237		98.96 165		98.79 191	94.92 188

test9_res														99.71 33	99.99 21	100.00 1

agg_prior2														99.48 43	100.00 1	100.00 1

test_prior4						98.05 68	99.94 69

test_prior				99.43 35	99.94 13	98.49 60		98.65 74					99.80 121			99.99 23

新几何2							99.40 220

旧先验1					99.76 66	97.52 89		98.64 76			99.85 30	95.63 41			99.94 54	99.99 23

无先验							99.49 211	98.71 66	93.46 163				100.00 1	94.36 203		99.99 23

原ACMM2							99.90 91

testdata2													99.99 36	90.54 269

segment_acmp												96.68 25

testdata1							99.28 240		96.35 71

plane_prior7					95.71 293	91.59 280

plane_prior6					95.76 287	91.72 275						80.47 275

plane_prior5								97.87 223					98.37 228	97.79 133	89.55 254	94.52 264

plane_prior4											98.59 201

plane_prior2							99.84 126		96.38 67

plane_prior1					95.73 290

plane_prior						91.74 272	99.86 118		96.76 52						89.59 253

n2								0.00 417

nn								0.00 417

door-mid								89.69 401

test11								98.44 123

door								90.31 398

HQP5-MVS						91.85 268

BP-MVS														97.92 125

HQP3-MVS								97.89 221							89.60 251

HQP2-MVS												80.65 271

NP-MVS					95.77 286	91.79 270					98.65 196

ACMMP++_ref															87.04 288

ACMMP++															88.23 276

Test By Simon												92.82 122

High-resolution multi-view benchmark