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.

LCM-MVSNet		99.86 1	99.86 1	99.87 1	99.99 1	99.77 1	99.77 1	99.80 3	99.97 1	99.97 1	99.95 1	99.74 1	99.98 1	99.56 1	100.00 1	99.85 6

pmmvs6		99.07 6	99.24 7	98.56 52	99.81 2	96.38 66	98.87 12	99.30 40	99.01 23	99.63 15	99.66 6	99.27 2	99.68 143	97.75 72	99.89 26	99.62 43

testf1		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 91	99.42 33	97.69 75	98.92 70	98.77 93	97.80 30	99.25 308	96.27 134	99.69 94	98.76 265

APD_test2		98.57 22	98.45 37	98.93 22	99.79 3	98.78 3	97.69 91	99.42 33	97.69 75	98.92 70	98.77 93	97.80 30	99.25 308	96.27 134	99.69 94	98.76 265

UniMVSNet_ETH3D		99.12 3	99.28 5	98.65 46	99.77 5	96.34 70	99.18 6	99.20 50	99.67 3	99.73 7	99.65 8	99.15 3	99.86 28	97.22 93	99.92 15	99.77 15

OurMVSNet-221017-0		98.61 20	98.61 28	98.63 48	99.77 5	96.35 69	99.17 7	99.05 91	98.05 61	99.61 17	99.52 12	93.72 224	99.88 23	98.72 37	99.88 28	99.65 39

Gipuma		98.07 58	98.31 49	97.36 158	99.76 7	96.28 73	98.51 30	99.10 72	98.76 30	96.79 262	99.34 29	96.61 103	98.82 366	96.38 127	99.50 168	96.98 398
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
sc_t1		99.09 5	99.28 5	98.53 55	99.72 8	96.21 74	98.87 12	99.19 52	99.71 2	99.76 5	99.65 8	98.64 9	99.79 54	98.07 55	99.90 25	99.58 48

MIMVSNet1		98.51 29	98.45 37	98.67 44	99.72 8	96.71 54	98.76 16	98.89 135	98.49 41	99.38 32	99.14 53	95.44 164	99.84 34	96.47 122	99.80 61	99.47 103

LTVRE_ROB	96.88 1	99.18 2	99.34 2	98.72 41	99.71 10	96.99 48	99.69 2	99.57 21	99.02 22	99.62 16	99.36 26	98.53 11	99.52 216	98.58 41	99.95 5	99.66 36
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
mvs_tets		98.90 9	98.94 9	98.75 35	99.69 11	96.48 64	98.54 26	99.22 47	96.23 147	99.71 8	99.48 15	98.77 7	99.93 4	98.89 29	99.95 5	99.84 8

PS-MVSNAJss		98.53 28	98.63 24	98.21 85	99.68 12	94.82 137	98.10 59	99.21 48	96.91 113	99.75 6	99.45 18	95.82 145	99.92 6	98.80 31	99.96 4	99.89 4

jajsoiax		98.77 13	98.79 16	98.74 38	99.66 13	96.48 64	98.45 34	99.12 68	95.83 179	99.67 11	99.37 24	98.25 17	99.92 6	98.77 32	99.94 8	99.82 9

v7n		98.73 15	98.99 8	97.95 106	99.64 14	94.20 164	98.67 18	99.14 65	99.08 17	99.42 29	99.23 38	96.53 109	99.91 14	99.27 10	99.93 11	99.73 26

test_djsdf		98.73 15	98.74 20	98.69 43	99.63 15	96.30 72	98.67 18	99.02 102	96.50 134	99.32 37	99.44 19	97.43 46	99.92 6	98.73 35	99.95 5	99.86 5

anonymousdsp		98.72 18	98.63 24	98.99 14	99.62 16	97.29 41	98.65 22	99.19 52	95.62 188	99.35 36	99.37 24	97.38 48	99.90 18	98.59 40	99.91 19	99.77 15

APD_test1		97.95 71	97.68 108	98.75 35	99.60 17	98.60 6	97.21 126	99.08 81	96.57 132	98.07 169	98.38 143	96.22 130	99.14 326	94.71 240	99.31 230	98.52 292

FOURS1					99.59 18	98.20 8	99.03 8	99.25 46	98.96 25	98.87 75

PEN-MVS		98.75 14	98.85 14	98.44 62	99.58 19	95.67 97	98.45 34	99.15 62	99.33 9	99.30 38	99.00 67	97.27 53	99.92 6	97.64 78	99.92 15	99.75 24

tt0320-xc		99.10 4	99.31 3	98.49 58	99.57 20	96.09 80	98.91 11	99.55 24	99.67 3	99.78 3	99.69 4	98.63 10	99.77 70	98.02 57	99.93 11	99.60 44

EGC-MVSNET		83.08 425	77.93 428	98.53 55	99.57 20	97.55 30	98.33 41	98.57 219	4.71 463	10.38 464	98.90 83	95.60 158	99.50 221	95.69 163	99.61 118	98.55 289

Baseline_NR-MVSNet		97.72 105	97.79 94	97.50 143	99.56 22	93.29 200	95.44 262	98.86 147	98.20 56	98.37 126	99.24 36	94.69 190	99.55 207	95.98 149	99.79 63	99.65 39

SixPastTwentyTwo		97.49 127	97.57 124	97.26 167	99.56 22	92.33 224	98.28 45	96.97 335	98.30 50	99.45 25	99.35 28	88.43 322	99.89 21	98.01 58	99.76 69	99.54 70

tt0320		99.07 6	99.29 4	98.43 63	99.55 24	95.92 87	98.97 10	99.53 26	99.67 3	99.79 2	99.71 3	98.33 14	99.78 59	98.11 51	99.92 15	99.57 56

tt0805		97.44 133	97.56 125	97.11 177	99.55 24	96.36 68	98.66 21	95.66 363	98.31 48	97.09 242	95.45 376	97.17 62	98.50 401	98.67 38	97.45 382	96.48 419

PS-CasMVS		98.73 15	98.85 14	98.39 67	99.55 24	95.47 110	98.49 31	99.13 67	99.22 13	99.22 44	98.96 73	97.35 49	99.92 6	97.79 69	99.93 11	99.79 13

DTE-MVSNet		98.79 12	98.86 12	98.59 50	99.55 24	96.12 78	98.48 33	99.10 72	99.36 8	99.29 39	99.06 61	97.27 53	99.93 4	97.71 74	99.91 19	99.70 31

HPM-MVS_fast		98.32 39	98.13 57	98.88 27	99.54 28	97.48 34	98.35 38	99.03 99	95.88 175	97.88 189	98.22 176	98.15 20	99.74 93	96.50 121	99.62 112	99.42 121

TDRefinement		98.90 9	98.86 12	99.02 10	99.54 28	98.06 9	99.34 5	99.44 31	98.85 28	99.00 61	99.20 41	97.42 47	99.59 192	97.21 94	99.76 69	99.40 124

pm-mvs1		98.47 32	98.67 22	97.86 111	99.52 30	94.58 147	98.28 45	99.00 113	97.57 79	99.27 40	99.22 39	98.32 15	99.50 221	97.09 101	99.75 78	99.50 85

TransMVSNet (Re)		98.38 36	98.67 22	97.51 139	99.51 31	93.39 198	98.20 54	98.87 144	98.23 54	99.48 22	99.27 34	98.47 13	99.55 207	96.52 120	99.53 154	99.60 44

WR-MVS_H		98.65 19	98.62 26	98.75 35	99.51 31	96.61 60	98.55 25	99.17 55	99.05 20	99.17 46	98.79 89	95.47 162	99.89 21	97.95 61	99.91 19	99.75 24

PMVS	89.60 17	96.71 190	96.97 166	95.95 268	99.51 31	97.81 20	97.42 115	97.49 315	97.93 63	95.95 314	98.58 117	96.88 89	96.91 440	89.59 365	99.36 212	93.12 449
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MP-MVS-pluss		97.69 107	97.36 141	98.70 42	99.50 34	96.84 51	95.38 270	98.99 117	92.45 318	98.11 162	98.31 155	97.25 58	99.77 70	96.60 117	99.62 112	99.48 99
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
FC-MVSNet-test		98.16 49	98.37 41	97.56 134	99.49 35	93.10 205	98.35 38	99.21 48	98.43 43	98.89 73	98.83 88	94.30 208	99.81 44	97.87 64	99.91 19	99.77 15

NormalMVS		96.87 173	96.39 210	98.30 74	99.48 36	95.57 100	96.87 146	98.90 131	96.94 111	96.85 259	97.88 219	85.36 355	99.76 76	95.63 169	99.59 128	99.57 56

lecture		98.59 21	98.60 29	98.55 53	99.48 36	96.38 66	98.08 61	99.09 77	98.46 42	98.68 95	98.73 98	97.88 27	99.80 51	97.43 86	99.59 128	99.48 99

VPNet		97.26 148	97.49 134	96.59 219	99.47 38	90.58 275	96.27 190	98.53 221	97.77 67	98.46 116	98.41 139	94.59 196	99.68 143	94.61 241	99.29 233	99.52 78

CP-MVSNet		98.42 34	98.46 34	98.30 74	99.46 39	95.22 126	98.27 47	98.84 155	99.05 20	99.01 59	98.65 111	95.37 167	99.90 18	97.57 80	99.91 19	99.77 15

XXY-MVS		97.54 124	97.70 104	97.07 183	99.46 39	92.21 230	97.22 125	99.00 113	94.93 224	98.58 103	98.92 79	97.31 51	99.41 256	94.44 246	99.43 194	99.59 47

MTAPA		98.14 50	97.84 86	99.06 7	99.44 41	97.90 16	97.25 122	98.73 187	97.69 75	97.90 187	97.96 211	95.81 149	99.82 39	96.13 139	99.61 118	99.45 109

SteuartSystems-ACMMP		98.02 62	97.76 100	98.79 33	99.43 42	97.21 45	97.15 128	98.90 131	96.58 129	98.08 167	97.87 222	97.02 75	99.76 76	95.25 196	99.59 128	99.40 124
Skip Steuart: Steuart Systems R&D Blog.
ACMH	93.61 9	98.44 33	98.76 17	97.51 139	99.43 42	93.54 189	98.23 49	99.05 91	97.40 93	99.37 33	99.08 60	98.79 6	99.47 232	97.74 73	99.71 88	99.50 85
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HPM-MVS		98.11 54	97.83 89	98.92 25	99.42 44	97.46 35	98.57 23	99.05 91	95.43 201	97.41 219	97.50 258	97.98 23	99.79 54	95.58 175	99.57 136	99.50 85
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SDMVSNet		97.97 65	98.26 55	97.11 177	99.41 45	92.21 230	96.92 142	98.60 213	98.58 37	98.78 83	99.39 21	97.80 30	99.62 179	94.98 227	99.86 35	99.52 78

sd_testset		97.97 65	98.12 58	97.51 139	99.41 45	93.44 194	97.96 68	98.25 254	98.58 37	98.78 83	99.39 21	98.21 18	99.56 203	92.65 298	99.86 35	99.52 78

K. test v3		96.44 204	96.28 217	96.95 192	99.41 45	91.53 251	97.65 95	90.31 438	98.89 27	98.93 69	99.36 26	84.57 363	99.92 6	97.81 67	99.56 139	99.39 129

VDDNet		96.98 165	96.84 176	97.41 155	99.40 48	93.26 202	97.94 71	95.31 375	99.26 12	98.39 125	99.18 46	87.85 332	99.62 179	95.13 211	99.09 263	99.35 140

test_fmvsmconf0.01_n		98.57 22	98.74 20	98.06 96	99.39 49	94.63 144	96.70 165	99.82 1	95.44 200	99.64 14	99.52 12	98.96 4	99.74 93	99.38 6	99.86 35	99.81 10

ACMH+	93.58 10	98.23 46	98.31 49	97.98 105	99.39 49	95.22 126	97.55 103	99.20 50	98.21 55	99.25 42	98.51 127	98.21 18	99.40 258	94.79 233	99.72 85	99.32 142

TSAR-MVS + MP.		97.42 137	97.23 150	98.00 103	99.38 51	95.00 133	97.63 97	98.20 261	93.00 303	98.16 157	98.06 201	95.89 140	99.72 105	95.67 165	99.10 262	99.28 154
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
FIs		97.93 77	98.07 63	97.48 147	99.38 51	92.95 209	98.03 65	99.11 69	98.04 62	98.62 98	98.66 107	93.75 223	99.78 59	97.23 92	99.84 48	99.73 26

lessismore_v0				97.05 184	99.36 53	92.12 235		84.07 455		98.77 87	98.98 70	85.36 355	99.74 93	97.34 91	99.37 208	99.30 147

Anonymous20240521		97.07 158	97.51 130	95.76 277	99.35 54	88.18 329	97.78 82	98.40 237	97.11 104	98.34 133	99.04 63	89.58 307	99.79 54	98.09 53	99.93 11	99.30 147

ACMMP_NAP		97.89 85	97.63 117	98.67 44	99.35 54	96.84 51	96.36 184	98.79 175	95.07 216	97.88 189	98.35 147	97.24 59	99.72 105	96.05 142	99.58 133	99.45 109

Vis-MVSNet		98.27 43	98.34 46	98.07 94	99.33 56	95.21 128	98.04 63	99.46 29	97.32 98	97.82 196	99.11 55	96.75 97	99.86 28	97.84 66	99.36 212	99.15 181
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ANet_high		98.31 40	98.94 9	96.41 238	99.33 56	89.64 294	97.92 73	99.56 23	99.27 11	99.66 13	99.50 14	97.67 36	99.83 36	97.55 81	99.98 2	99.77 15

ZNCC-MVS		97.92 78	97.62 119	98.83 29	99.32 58	97.24 43	97.45 111	98.84 155	95.76 181	96.93 254	97.43 262	97.26 57	99.79 54	96.06 140	99.53 154	99.45 109

MP-MVS		97.64 113	97.18 154	99.00 13	99.32 58	97.77 21	97.49 109	98.73 187	96.27 144	95.59 331	97.75 238	96.30 125	99.78 59	93.70 279	99.48 175	99.45 109
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Elysia		98.19 47	98.37 41	97.66 127	99.28 60	93.52 190	97.35 117	98.90 131	98.63 33	99.45 25	98.32 153	94.31 206	99.91 14	99.19 14	99.88 28	99.54 70

StellarMVS		98.19 47	98.37 41	97.66 127	99.28 60	93.52 190	97.35 117	98.90 131	98.63 33	99.45 25	98.32 153	94.31 206	99.91 14	99.19 14	99.88 28	99.54 70

SSC-MVS		95.92 230	97.03 163	92.58 400	99.28 60	78.39 437	96.68 166	95.12 379	98.90 26	99.11 50	98.66 107	91.36 282	99.68 143	95.00 220	99.16 252	99.67 34

PVSNet_Blended_VisFu		95.95 229	95.80 243	96.42 235	99.28 60	90.62 274	95.31 279	99.08 81	88.40 382	96.97 252	98.17 182	92.11 269	99.78 59	93.64 280	99.21 244	98.86 248

tfpnnormal		97.72 105	97.97 75	96.94 193	99.26 64	92.23 229	97.83 80	98.45 228	98.25 53	99.13 49	98.66 107	96.65 100	99.69 137	93.92 271	99.62 112	98.91 237

MSP-MVS		97.45 131	96.92 172	99.03 9	99.26 64	97.70 22	97.66 94	98.89 135	95.65 186	98.51 108	96.46 336	92.15 267	99.81 44	95.14 209	98.58 323	99.58 48
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
testgi		96.07 222	96.50 205	94.80 326	99.26 64	87.69 344	95.96 224	98.58 217	95.08 215	98.02 175	96.25 347	97.92 24	97.60 433	88.68 379	98.74 305	99.11 198

IS-MVSNet		96.93 167	96.68 187	97.70 123	99.25 67	94.00 171	98.57 23	96.74 344	98.36 46	98.14 160	97.98 210	88.23 325	99.71 121	93.10 294	99.72 85	99.38 131

KinetiMVS		97.82 95	98.02 69	97.24 170	99.24 68	92.32 226	96.92 142	98.38 240	98.56 40	99.03 56	98.33 150	93.22 235	99.83 36	98.74 34	99.71 88	99.57 56

DVP-MVS		97.78 100	97.65 112	98.16 87	99.24 68	95.51 105	96.74 159	98.23 257	95.92 172	98.40 123	98.28 164	97.06 69	99.71 121	95.48 181	99.52 159	99.26 159
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test0726					99.24 68	95.51 105	96.89 145	98.89 135	95.92 172	98.64 96	98.31 155	97.06 69

test_0728_SECOND				98.25 80	99.23 71	95.49 109	96.74 159	98.89 135					99.75 84	95.48 181	99.52 159	99.53 75

GST-MVS		97.82 95	97.49 134	98.81 31	99.23 71	97.25 42	97.16 127	98.79 175	95.96 167	97.53 206	97.40 264	96.93 82	99.77 70	95.04 215	99.35 217	99.42 121

ACMMP		98.05 60	97.75 102	98.93 22	99.23 71	97.60 26	98.09 60	98.96 124	95.75 183	97.91 186	98.06 201	96.89 87	99.76 76	95.32 193	99.57 136	99.43 120
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
KD-MVS_self_test		97.86 90	98.07 63	97.25 168	99.22 74	92.81 212	97.55 103	98.94 127	97.10 105	98.85 76	98.88 85	95.03 180	99.67 152	97.39 88	99.65 105	99.26 159

SED-MVS		97.94 74	97.90 79	98.07 94	99.22 74	95.35 116	96.79 155	98.83 161	96.11 153	99.08 53	98.24 171	97.87 28	99.72 105	95.44 185	99.51 164	99.14 186

IU-MVS					99.22 74	95.40 111		98.14 274	85.77 411	98.36 129				95.23 198	99.51 164	99.49 93

test_241102_ONE					99.22 74	95.35 116		98.83 161	96.04 161	99.08 53	98.13 185	97.87 28	99.33 283

nrg030		98.54 26	98.62 26	98.32 71	99.22 74	95.66 98	97.90 75	99.08 81	98.31 48	99.02 58	98.74 97	97.68 35	99.61 187	97.77 71	99.85 45	99.70 31

region2R		97.92 78	97.59 122	98.92 25	99.22 74	97.55 30	97.60 98	98.84 155	96.00 164	97.22 226	97.62 249	96.87 91	99.76 76	95.48 181	99.43 194	99.46 105

mPP-MVS		97.91 82	97.53 128	99.04 8	99.22 74	97.87 18	97.74 88	98.78 179	96.04 161	97.10 237	97.73 241	96.53 109	99.78 59	95.16 206	99.50 168	99.46 105

WB-MVS		95.50 252	96.62 189	92.11 410	99.21 81	77.26 447	96.12 206	95.40 373	98.62 35	98.84 78	98.26 169	91.08 285	99.50 221	93.37 284	98.70 311	99.58 48

COLMAP_ROB	94.48 6	98.25 45	98.11 60	98.64 47	99.21 81	97.35 39	97.96 68	99.16 56	98.34 47	98.78 83	98.52 125	97.32 50	99.45 240	94.08 262	99.67 101	99.13 188
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
ACMMPR		97.95 71	97.62 119	98.94 19	99.20 83	97.56 29	97.59 100	98.83 161	96.05 159	97.46 216	97.63 248	96.77 96	99.76 76	95.61 172	99.46 180	99.49 93

PGM-MVS		97.88 86	97.52 129	98.96 17	99.20 83	97.62 25	97.09 133	99.06 85	95.45 198	97.55 205	97.94 214	97.11 63	99.78 59	94.77 236	99.46 180	99.48 99

test_0402		97.84 91	97.97 75	97.47 148	99.19 85	94.07 167	96.71 164	98.73 187	98.66 32	98.56 105	98.41 139	96.84 93	99.69 137	94.82 231	99.81 57	98.64 279

EPP-MVSNet		96.84 175	96.58 193	97.65 129	99.18 86	93.78 180	98.68 17	96.34 349	97.91 64	97.30 221	98.06 201	88.46 321	99.85 31	93.85 273	99.40 202	99.32 142

fmvsm_s_conf0.1_n_a		97.80 98	98.01 71	97.18 172	99.17 87	92.51 220	96.57 169	99.15 62	93.68 274	98.89 73	99.30 32	96.42 119	99.37 271	99.03 25	99.83 52	99.66 36

test_fmvsmconf0.1_n		98.41 35	98.54 31	98.03 101	99.16 88	94.61 145	96.18 199	99.73 5	95.05 218	99.60 18	99.34 29	98.68 8	99.72 105	99.21 12	99.85 45	99.76 21

XVG-ACMP-BASELINE		97.58 122	97.28 147	98.49 58	99.16 88	96.90 50	96.39 179	98.98 120	95.05 218	98.06 170	98.02 205	95.86 141	99.56 203	94.37 251	99.64 107	99.00 214

CHOSEN 1792x2688		94.10 318	93.41 330	96.18 255	99.16 88	90.04 283	92.15 400	98.68 199	79.90 443	96.22 303	97.83 226	87.92 331	99.42 247	89.18 371	99.65 105	99.08 203

HFP-MVS		97.94 74	97.64 115	98.83 29	99.15 91	97.50 33	97.59 100	98.84 155	96.05 159	97.49 210	97.54 254	97.07 68	99.70 130	95.61 172	99.46 180	99.30 147

XVS		97.96 67	97.63 117	98.94 19	99.15 91	97.66 23	97.77 83	98.83 161	97.42 88	96.32 294	97.64 247	96.49 112	99.72 105	95.66 166	99.37 208	99.45 109

X-MVStestdata		92.86 350	90.83 379	98.94 19	99.15 91	97.66 23	97.77 83	98.83 161	97.42 88	96.32 294	36.50 461	96.49 112	99.72 105	95.66 166	99.37 208	99.45 109

LPG-MVS_test		97.94 74	97.67 109	98.74 38	99.15 91	97.02 46	97.09 133	99.02 102	95.15 212	98.34 133	98.23 173	97.91 25	99.70 130	94.41 248	99.73 80	99.50 85

LGP-MVS_train				98.74 38	99.15 91	97.02 46		99.02 102	95.15 212	98.34 133	98.23 173	97.91 25	99.70 130	94.41 248	99.73 80	99.50 85

RPSCF		97.87 88	97.51 130	98.95 18	99.15 91	98.43 7	97.56 102	99.06 85	96.19 150	98.48 113	98.70 104	94.72 188	99.24 312	94.37 251	99.33 225	99.17 177

ACMM	93.33 11	98.05 60	97.79 94	98.85 28	99.15 91	97.55 30	96.68 166	98.83 161	95.21 208	98.36 129	98.13 185	98.13 22	99.62 179	96.04 143	99.54 150	99.39 129
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet1		97.95 71	98.08 62	97.56 134	99.14 98	93.67 183	98.23 49	98.66 205	97.41 92	99.00 61	99.19 42	95.47 162	99.73 99	95.83 158	99.76 69	99.30 147

Vis-MVSNet (Re-imp)		95.11 274	94.85 277	95.87 273	99.12 99	89.17 304	97.54 108	94.92 383	96.50 134	96.58 280	97.27 278	83.64 370	99.48 230	88.42 382	99.67 101	98.97 223

dcpmvs_2		97.12 156	97.99 73	94.51 344	99.11 100	84.00 405	97.75 86	99.65 13	97.38 95	99.14 48	98.42 137	95.16 176	99.96 2	95.52 176	99.78 67	99.58 48

OPM-MVS		97.54 124	97.25 148	98.41 65	99.11 100	96.61 60	95.24 283	98.46 227	94.58 239	98.10 164	98.07 196	97.09 66	99.39 263	95.16 206	99.44 184	99.21 169
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
UA-Net		98.88 11	98.76 17	99.22 3	99.11 100	97.89 17	99.47 3	99.32 38	99.08 17	97.87 192	99.67 5	96.47 114	99.92 6	97.88 63	99.98 2	99.85 6

fmvsm_s_conf0.1_n		97.73 103	98.02 69	96.85 202	99.09 103	91.43 256	96.37 183	99.11 69	94.19 257	99.01 59	99.25 35	96.30 125	99.38 266	99.00 26	99.88 28	99.73 26

AllTest		97.20 151	96.92 172	98.06 96	99.08 104	96.16 76	97.14 130	99.16 56	94.35 251	97.78 197	98.07 196	95.84 142	99.12 330	91.41 319	99.42 197	98.91 237

TestCases				98.06 96	99.08 104	96.16 76		99.16 56	94.35 251	97.78 197	98.07 196	95.84 142	99.12 330	91.41 319	99.42 197	98.91 237

mmtdpeth		98.33 37	98.53 32	97.71 121	99.07 106	93.44 194	98.80 15	99.78 4	99.10 16	96.61 278	99.63 10	95.42 165	99.73 99	98.53 42	99.86 35	99.95 2

TranMVSNet+NR-MVSNet		98.33 37	98.30 51	98.43 63	99.07 106	95.87 89	96.73 163	99.05 91	98.67 31	98.84 78	98.45 133	97.58 43	99.88 23	96.45 123	99.86 35	99.54 70

fmvsm_s_conf0.1_n_2		97.68 109	98.18 56	96.20 252	99.06 108	89.08 310	95.51 259	99.72 6	96.06 158	99.48 22	99.24 36	95.18 174	99.60 190	99.45 3	99.88 28	99.94 3

reproduce_model		98.54 26	98.33 47	99.15 4	99.06 108	98.04 12	97.04 136	99.09 77	98.42 44	99.03 56	98.71 102	96.93 82	99.83 36	97.09 101	99.63 109	99.56 64

test1111		94.53 304	94.81 281	93.72 367	99.06 108	81.94 420	98.31 42	83.87 456	96.37 140	98.49 111	99.17 49	81.49 380	99.73 99	96.64 115	99.86 35	99.49 93

VPA-MVSNet		98.27 43	98.46 34	97.70 123	99.06 108	93.80 178	97.76 85	99.00 113	98.40 45	99.07 55	98.98 70	96.89 87	99.75 84	97.19 97	99.79 63	99.55 68

114514_t		93.96 324	93.22 333	96.19 254	99.06 108	90.97 265	95.99 220	98.94 127	73.88 456	93.43 393	96.93 306	92.38 264	99.37 271	89.09 372	99.28 234	98.25 323

EG-PatchMatch MVS		97.69 107	97.79 94	97.40 156	99.06 108	93.52 190	95.96 224	98.97 123	94.55 240	98.82 80	98.76 96	97.31 51	99.29 300	97.20 96	99.44 184	99.38 131

test_one_0601					99.05 114	95.50 108		98.87 144	97.21 103	98.03 174	98.30 159	96.93 82

ACMP	92.54 13	97.47 129	97.10 157	98.55 53	99.04 115	96.70 55	96.24 196	98.89 135	93.71 271	97.97 180	97.75 238	97.44 45	99.63 174	93.22 291	99.70 92	99.32 142
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_fmvsmvis_n_1920		98.08 56	98.47 33	96.93 194	99.03 116	93.29 200	96.32 187	99.65 13	95.59 190	99.71 8	99.01 66	97.66 38	99.60 190	99.44 4	99.83 52	97.90 356

test_part2					99.03 116	96.07 81				98.08 167

XVG-OURS-SEG-HR		97.38 140	97.07 160	98.30 74	99.01 118	97.41 38	94.66 315	99.02 102	95.20 209	98.15 159	97.52 256	98.83 5	98.43 406	94.87 229	96.41 409	99.07 205

reproduce-ours		98.48 30	98.27 53	99.12 5	98.99 119	98.02 13	96.81 151	99.02 102	98.29 51	98.97 65	98.61 114	97.27 53	99.82 39	96.86 112	99.61 118	99.51 82

our_new_method		98.48 30	98.27 53	99.12 5	98.99 119	98.02 13	96.81 151	99.02 102	98.29 51	98.97 65	98.61 114	97.27 53	99.82 39	96.86 112	99.61 118	99.51 82

XVG-OURS		97.12 156	96.74 184	98.26 77	98.99 119	97.45 36	93.82 350	99.05 91	95.19 210	98.32 137	97.70 243	95.22 173	98.41 407	94.27 255	98.13 346	98.93 233

CP-MVS		97.92 78	97.56 125	98.99 14	98.99 119	97.82 19	97.93 72	98.96 124	96.11 153	96.89 257	97.45 260	96.85 92	99.78 59	95.19 201	99.63 109	99.38 131

mvs5depth		98.06 59	98.58 30	96.51 228	98.97 123	89.65 293	99.43 4	99.81 2	99.30 10	98.36 129	99.86 2	93.15 237	99.88 23	98.50 43	99.84 48	99.99 1

test2506		89.86 394	89.16 399	91.97 411	98.95 124	76.83 448	98.54 26	61.07 466	96.20 148	97.07 243	99.16 50	55.19 460	99.69 137	96.43 125	99.83 52	99.38 131

ECVR-MVS		94.37 310	94.48 299	94.05 362	98.95 124	83.10 410	98.31 42	82.48 458	96.20 148	98.23 149	99.16 50	81.18 383	99.66 160	95.95 150	99.83 52	99.38 131

CSCG		97.40 138	97.30 144	97.69 125	98.95 124	94.83 136	97.28 121	98.99 117	96.35 143	98.13 161	95.95 362	95.99 136	99.66 160	94.36 253	99.73 80	98.59 285

fmvsm_l_conf0.5_n_9		97.92 78	98.37 41	96.57 222	98.94 127	90.54 278	95.39 268	99.58 19	96.82 116	99.56 19	98.77 93	97.23 60	99.61 187	99.17 17	99.86 35	99.57 56

LuminaMVS		96.76 184	96.58 193	97.30 162	98.94 127	92.96 208	96.17 203	96.15 351	95.54 194	98.96 67	98.18 181	87.73 333	99.80 51	97.98 59	99.61 118	99.15 181

test_fmvsmconf_n		98.30 41	98.41 40	97.99 104	98.94 127	94.60 146	96.00 217	99.64 16	94.99 221	99.43 28	99.18 46	98.51 12	99.71 121	99.13 20	99.84 48	99.67 34

mamv4		99.05 8	98.91 11	99.46 2	98.94 127	99.62 2	97.98 67	99.70 8	99.49 6	99.78 3	99.22 39	95.92 138	99.95 3	99.31 8	99.83 52	98.83 250

SF-MVS		97.60 118	97.39 137	98.22 82	98.93 131	95.69 95	97.05 135	99.10 72	95.32 205	97.83 195	97.88 219	96.44 117	99.72 105	94.59 245	99.39 206	99.25 164

HyFIR lowres test		93.72 330	92.65 347	96.91 197	98.93 131	91.81 247	91.23 422	98.52 222	82.69 431	96.46 288	96.52 334	80.38 388	99.90 18	90.36 354	98.79 296	99.03 210

fmvsm_s_conf0.5_n_9		97.98 64	98.32 48	96.96 191	98.92 133	91.45 254	95.87 231	99.53 26	97.44 86	99.56 19	99.05 62	95.34 168	99.67 152	99.52 2	99.70 92	99.77 15

fmvsm_l_conf0.5_n_a		97.60 118	97.76 100	97.11 177	98.92 133	92.28 227	95.83 234	99.32 38	93.22 291	98.91 72	98.49 128	96.31 124	99.64 169	99.07 24	99.76 69	99.40 124

fmvsm_l_conf0.5_n		97.68 109	97.81 92	97.27 165	98.92 133	92.71 217	95.89 230	99.41 36	93.36 285	99.00 61	98.44 135	96.46 116	99.65 163	99.09 23	99.76 69	99.45 109

AstraMVS		96.41 208	96.48 206	96.20 252	98.91 136	89.69 291	96.28 189	93.29 402	96.11 153	98.70 94	98.36 145	89.41 314	99.66 160	97.60 79	99.63 109	99.26 159

PM-MVS		97.36 144	97.10 157	98.14 90	98.91 136	96.77 53	96.20 198	98.63 211	93.82 268	98.54 106	98.33 150	93.98 215	99.05 342	95.99 148	99.45 183	98.61 284

fmvsm_l_conf0.5_n_3		98.29 42	98.46 34	97.79 115	98.90 138	94.05 169	96.06 210	99.63 17	96.07 157	99.37 33	98.93 77	98.29 16	99.68 143	99.11 22	99.79 63	99.65 39

CPTT-MVS		96.69 191	96.08 226	98.49 58	98.89 139	96.64 59	97.25 122	98.77 180	92.89 309	96.01 313	97.13 290	92.23 265	99.67 152	92.24 305	99.34 220	99.17 177

MVSMamba_PlusPlus		97.43 135	97.98 74	95.78 276	98.88 140	89.70 290	98.03 65	98.85 151	99.18 14	96.84 261	99.12 54	93.04 240	99.91 14	98.38 46	99.55 145	97.73 370

test_fmvsm_n_1920		98.08 56	98.29 52	97.43 152	98.88 140	93.95 173	96.17 203	99.57 21	95.66 185	99.52 21	98.71 102	97.04 73	99.64 169	99.21 12	99.87 33	98.69 275

patch_mono-2		96.59 195	96.93 170	95.55 290	98.88 140	87.12 355	94.47 320	99.30 40	94.12 260	96.65 276	98.41 139	94.98 183	99.87 26	95.81 160	99.78 67	99.66 36

GeoE		97.75 102	97.70 104	97.89 109	98.88 140	94.53 148	97.10 132	98.98 120	95.75 183	97.62 201	97.59 251	97.61 42	99.77 70	96.34 130	99.44 184	99.36 138

DPE-MVS		97.64 113	97.35 142	98.50 57	98.85 144	96.18 75	95.21 285	98.99 117	95.84 178	98.78 83	98.08 194	96.84 93	99.81 44	93.98 268	99.57 136	99.52 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		97.48 128	97.11 156	98.60 49	98.83 145	96.67 57	96.74 159	98.73 187	91.61 333	98.48 113	98.36 145	96.53 109	99.68 143	95.17 204	99.54 150	99.45 109
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
SSM_0404		97.47 129	97.75 102	96.64 216	98.81 146	91.26 259	96.57 169	99.16 56	96.95 109	98.44 119	98.09 192	97.05 71	99.72 105	95.21 199	99.44 184	98.95 226

SR-MVS-dyc-post		98.14 50	97.84 86	99.02 10	98.81 146	98.05 10	97.55 103	98.86 147	97.77 67	98.20 151	98.07 196	96.60 105	99.76 76	95.49 177	99.20 245	99.26 159

RE-MVS-def			97.88 84		98.81 146	98.05 10	97.55 103	98.86 147	97.77 67	98.20 151	98.07 196	96.94 80		95.49 177	99.20 245	99.26 159

guyue		96.21 216	96.29 216	95.98 265	98.80 149	89.14 307	96.40 177	94.34 390	95.99 166	98.58 103	98.13 185	87.42 337	99.64 169	97.39 88	99.55 145	99.16 180

fmvsm_s_conf0.5_n_a		97.65 112	97.83 89	97.13 176	98.80 149	92.51 220	96.25 194	99.06 85	93.67 275	98.64 96	99.00 67	96.23 129	99.36 274	98.99 27	99.80 61	99.53 75

UniMVSNet (Re)		97.83 92	97.65 112	98.35 70	98.80 149	95.86 90	95.92 228	99.04 98	97.51 83	98.22 150	97.81 231	94.68 192	99.78 59	97.14 99	99.75 78	99.41 123

fmvsm_s_conf0.5_n_8		97.66 111	98.12 58	96.27 247	98.79 152	89.43 300	95.76 239	99.42 33	97.49 84	99.16 47	99.04 63	94.56 199	99.69 137	99.18 16	99.73 80	99.70 31

fmvsm_s_conf0.5_n		97.62 116	97.89 82	96.80 206	98.79 152	91.44 255	96.14 205	99.06 85	94.19 257	98.82 80	98.98 70	96.22 130	99.38 266	98.98 28	99.86 35	99.58 48

Anonymous20231211		98.55 25	98.76 17	97.94 107	98.79 152	94.37 156	98.84 14	99.15 62	99.37 7	99.67 11	99.43 20	95.61 157	99.72 105	98.12 50	99.86 35	99.73 26

APD-MVS_3200maxsize		98.13 53	97.90 79	98.79 33	98.79 152	97.31 40	97.55 103	98.92 129	97.72 72	98.25 147	98.13 185	97.10 64	99.75 84	95.44 185	99.24 243	99.32 142

fmvsm_s_conf0.5_n_2		97.59 121	98.07 63	96.17 256	98.78 156	89.10 309	95.33 276	99.55 24	95.96 167	99.41 31	99.10 56	95.18 174	99.59 192	99.43 5	99.86 35	99.81 10

DeepC-MVS	95.41 4	97.82 95	97.70 104	98.16 87	98.78 156	95.72 93	96.23 197	99.02 102	93.92 267	98.62 98	98.99 69	97.69 34	99.62 179	96.18 138	99.87 33	99.15 181
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_5		97.63 115	97.83 89	97.04 186	98.77 158	92.33 224	95.63 254	99.58 19	93.53 278	99.10 51	98.66 107	96.44 117	99.65 163	99.12 21	99.68 98	99.12 194

SR-MVS		98.00 63	97.66 111	99.01 12	98.77 158	97.93 15	97.38 116	98.83 161	97.32 98	98.06 170	97.85 223	96.65 100	99.77 70	95.00 220	99.11 260	99.32 142

MCST-MVS		96.24 215	95.80 243	97.56 134	98.75 160	94.13 166	94.66 315	98.17 267	90.17 359	96.21 304	96.10 356	95.14 177	99.43 245	94.13 261	98.85 290	99.13 188

fmvsm_s_conf0.5_n_3		97.88 86	98.37 41	96.41 238	98.73 161	89.82 288	95.94 226	99.49 28	96.81 117	99.09 52	99.03 65	97.09 66	99.65 163	99.37 7	99.76 69	99.76 21

DU-MVS		97.79 99	97.60 121	98.36 69	98.73 161	95.78 91	95.65 249	98.87 144	97.57 79	98.31 139	97.83 226	94.69 190	99.85 31	97.02 106	99.71 88	99.46 105

NR-MVSNet		97.96 67	97.86 85	98.26 77	98.73 161	95.54 103	98.14 57	98.73 187	97.79 66	99.42 29	97.83 226	94.40 204	99.78 59	95.91 153	99.76 69	99.46 105

Anonymous20231206		95.27 267	95.06 266	95.88 272	98.72 164	89.37 301	95.70 242	97.85 293	88.00 388	96.98 251	97.62 249	91.95 274	99.34 281	89.21 370	99.53 154	98.94 229

APDe-MVS		98.14 50	98.03 68	98.47 61	98.72 164	96.04 82	98.07 62	99.10 72	95.96 167	98.59 102	98.69 105	96.94 80	99.81 44	96.64 115	99.58 133	99.57 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
UniMVSNet_NR-MVSNet		97.83 92	97.65 112	98.37 68	98.72 164	95.78 91	95.66 247	99.02 102	98.11 58	98.31 139	97.69 244	94.65 194	99.85 31	97.02 106	99.71 88	99.48 99

tttt0517		93.31 342	92.56 350	95.57 286	98.71 167	87.86 338	97.44 112	87.17 450	95.79 180	97.47 215	96.84 312	64.12 441	99.81 44	96.20 137	99.32 227	99.02 213

v8		97.60 118	98.06 66	96.23 249	98.71 167	89.44 299	97.43 114	98.82 169	97.29 100	98.74 90	99.10 56	93.86 218	99.68 143	98.61 39	99.94 8	99.56 64

HQP_MVS		96.66 193	96.33 215	97.68 126	98.70 169	94.29 159	96.50 173	98.75 184	96.36 141	96.16 307	96.77 318	91.91 277	99.46 235	92.59 300	99.20 245	99.28 154

plane_prior7					98.70 169	94.67 142

SSC-MVS3.2		95.75 240	96.56 196	93.34 374	98.69 171	80.75 429	91.60 411	97.43 319	97.37 96	96.99 248	97.02 299	93.69 225	99.71 121	96.32 131	99.89 26	99.55 68

Anonymous20240529		97.96 67	98.04 67	97.71 121	98.69 171	94.28 162	97.86 77	98.31 251	98.79 29	99.23 43	98.86 87	95.76 151	99.61 187	95.49 177	99.36 212	99.23 167

VDD-MVS		97.37 142	97.25 148	97.74 119	98.69 171	94.50 151	97.04 136	95.61 367	98.59 36	98.51 108	98.72 99	92.54 258	99.58 195	96.02 145	99.49 171	99.12 194

EC-MVSNet		97.90 84	97.94 78	97.79 115	98.66 174	95.14 129	98.31 42	99.66 12	97.57 79	95.95 314	97.01 302	96.99 77	99.82 39	97.66 77	99.64 107	98.39 304

HPM-MVS++		96.99 162	96.38 212	98.81 31	98.64 175	97.59 27	95.97 222	98.20 261	95.51 195	95.06 344	96.53 332	94.10 212	99.70 130	94.29 254	99.15 253	99.13 188

ab-mvs		96.59 195	96.59 192	96.60 218	98.64 175	92.21 230	98.35 38	97.67 304	94.45 248	96.99 248	98.79 89	94.96 185	99.49 227	90.39 353	99.07 266	98.08 336

F-COLMAP		95.30 266	94.38 305	98.05 100	98.64 175	96.04 82	95.61 255	98.66 205	89.00 373	93.22 397	96.40 341	92.90 245	99.35 278	87.45 397	97.53 377	98.77 264

ITE_SJBPF				97.85 112	98.64 175	96.66 58		98.51 224	95.63 187	97.22 226	97.30 277	95.52 160	98.55 397	90.97 330	98.90 283	98.34 312

test_fmvs3		97.38 140	97.56 125	96.84 204	98.63 179	92.81 212	97.60 98	99.61 18	90.87 347	98.76 88	99.66 6	94.03 214	97.90 427	99.24 11	99.68 98	99.81 10

v148		96.58 197	96.97 166	95.42 296	98.63 179	87.57 345	95.09 293	97.90 290	95.91 174	98.24 148	97.96 211	93.42 231	99.39 263	96.04 143	99.52 159	99.29 153

UnsupCasMVSNet_bld		94.72 293	94.26 307	96.08 260	98.62 181	90.54 278	93.38 367	98.05 285	90.30 356	97.02 246	96.80 317	89.54 308	99.16 324	88.44 381	96.18 416	98.56 287

DP-MVS		97.87 88	97.89 82	97.81 114	98.62 181	94.82 137	97.13 131	98.79 175	98.98 24	98.74 90	98.49 128	95.80 150	99.49 227	95.04 215	99.44 184	99.11 198

v10		97.55 123	97.97 75	96.31 245	98.60 183	89.64 294	97.44 112	99.02 102	96.60 125	98.72 92	99.16 50	93.48 230	99.72 105	98.76 33	99.92 15	99.58 48

Test_1112_low_res		93.53 337	92.86 339	95.54 291	98.60 183	88.86 315	92.75 381	98.69 197	82.66 432	92.65 410	96.92 308	84.75 361	99.56 203	90.94 331	97.76 362	98.19 329

V42		97.04 159	97.16 155	96.68 215	98.59 185	91.05 262	96.33 186	98.36 243	94.60 236	97.99 176	98.30 159	93.32 232	99.62 179	97.40 87	99.53 154	99.38 131

1112_ss		94.12 317	93.42 329	96.23 249	98.59 185	90.85 269	94.24 328	98.85 151	85.49 412	92.97 402	94.94 384	86.01 348	99.64 169	91.78 315	97.92 354	98.20 328

SymmetryMVS		96.43 206	95.85 240	98.17 86	98.58 187	95.57 100	96.87 146	95.29 376	96.94 111	96.85 259	97.88 219	85.36 355	99.76 76	95.63 169	99.27 236	99.19 173

fmvsm_s_conf0.5_n_6		97.45 131	97.79 94	96.44 232	98.58 187	90.31 280	95.77 238	99.33 37	94.52 241	98.85 76	98.44 135	95.68 153	99.62 179	99.15 19	99.81 57	99.38 131

v2v482		96.78 182	97.06 161	95.95 268	98.57 189	88.77 318	95.36 271	98.26 253	95.18 211	97.85 194	98.23 173	92.58 254	99.63 174	97.80 68	99.69 94	99.45 109

casdiffmvs_mvg		97.83 92	98.11 60	97.00 190	98.57 189	92.10 238	95.97 222	99.18 54	97.67 78	99.00 61	98.48 132	97.64 39	99.50 221	96.96 108	99.54 150	99.40 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		96.90 170	96.81 178	97.16 173	98.56 191	92.20 233	94.33 323	98.12 276	97.34 97	98.20 151	97.33 275	92.81 246	99.75 84	94.79 233	99.81 57	99.54 70

test_vis1_n_1920		95.77 238	96.41 209	93.85 363	98.55 192	84.86 393	95.91 229	99.71 7	92.72 313	97.67 200	98.90 83	87.44 336	98.73 376	97.96 60	98.85 290	97.96 352

APD-MVS		97.00 161	96.53 202	98.41 65	98.55 192	96.31 71	96.32 187	98.77 180	92.96 308	97.44 218	97.58 253	95.84 142	99.74 93	91.96 308	99.35 217	99.19 173
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Patchmatch-RL test		94.66 297	94.49 298	95.19 303	98.54 194	88.91 313	92.57 387	98.74 186	91.46 338	98.32 137	97.75 238	77.31 403	98.81 368	96.06 140	99.61 118	97.85 360

9.14			96.69 186		98.53 195		96.02 215	98.98 120	93.23 290	97.18 231	97.46 259	96.47 114	99.62 179	92.99 295	99.32 227

SPE-MVS-test		97.91 82	97.84 86	98.14 90	98.52 196	96.03 84	98.38 37	99.67 10	98.11 58	95.50 335	96.92 308	96.81 95	99.87 26	96.87 111	99.76 69	98.51 293

baseline		97.44 133	97.78 98	96.43 234	98.52 196	90.75 273	96.84 148	99.03 99	96.51 133	97.86 193	98.02 205	96.67 99	99.36 274	97.09 101	99.47 177	99.19 173

mamba_0408		97.17 153	97.38 139	96.55 226	98.51 198	90.96 266	95.19 286	99.06 85	96.60 125	98.27 143	97.78 233	96.58 106	99.72 105	95.04 215	99.40 202	98.98 220

SSM_04072		97.14 154	97.38 139	96.42 235	98.51 198	90.96 266	95.19 286	99.06 85	96.60 125	98.27 143	97.78 233	96.58 106	99.31 292	95.04 215	99.40 202	98.98 220

SSM_0407		97.39 139	97.67 109	96.54 227	98.51 198	90.96 266	96.40 177	99.16 56	96.95 109	98.27 143	98.09 192	97.05 71	99.67 152	95.21 199	99.40 202	98.98 220

casdiffmvs		97.50 126	97.81 92	96.56 224	98.51 198	91.04 263	95.83 234	99.09 77	97.23 101	98.33 136	98.30 159	97.03 74	99.37 271	96.58 119	99.38 207	99.28 154
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
IterMVS-LS		96.92 168	97.29 145	95.79 275	98.51 198	88.13 332	95.10 292	98.66 205	96.99 106	98.46 116	98.68 106	92.55 256	99.74 93	96.91 109	99.79 63	99.50 85
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS Recon		95.55 251	95.13 261	96.80 206	98.51 198	93.99 172	94.60 317	98.69 197	90.20 358	95.78 324	96.21 349	92.73 249	98.98 352	90.58 348	98.86 289	97.42 387

h-mvs33		96.29 212	95.63 250	98.26 77	98.50 204	96.11 79	96.90 144	97.09 329	96.58 129	97.21 228	98.19 178	84.14 365	99.78 59	95.89 154	96.17 417	98.89 241

test20.03		96.58 197	96.61 191	96.48 231	98.49 205	91.72 248	95.68 245	97.69 303	96.81 117	98.27 143	97.92 217	94.18 211	98.71 379	90.78 337	99.66 104	99.00 214

plane_prior1					98.49 205

fmvsm_s_conf0.5_n_4		97.43 135	97.77 99	96.39 241	98.48 207	89.89 286	95.65 249	99.26 44	94.73 230	98.72 92	98.58 117	95.58 159	99.57 201	99.28 9	99.67 101	99.73 26

save fliter					98.48 207	94.71 139	94.53 319	98.41 235	95.02 220

MDA-MVSNet-bldmvs		95.69 242	95.67 247	95.74 278	98.48 207	88.76 319	92.84 378	97.25 321	96.00 164	97.59 202	97.95 213	91.38 281	99.46 235	93.16 293	96.35 412	98.99 217

UnsupCasMVSNet_eth		95.91 231	95.73 246	96.44 232	98.48 207	91.52 252	95.31 279	98.45 228	95.76 181	97.48 213	97.54 254	89.53 310	98.69 382	94.43 247	94.61 435	99.13 188

CS-MVS		98.09 55	98.01 71	98.32 71	98.45 211	96.69 56	98.52 29	99.69 9	98.07 60	96.07 310	97.19 283	96.88 89	99.86 28	97.50 83	99.73 80	98.41 301

test_vis3_rt		97.04 159	96.98 165	97.23 171	98.44 212	95.88 88	96.82 150	99.67 10	90.30 356	99.27 40	99.33 31	94.04 213	96.03 448	97.14 99	97.83 359	99.78 14

fmvsm_s_conf0.5_n_7		97.13 155	97.50 132	96.04 261	98.43 213	89.03 311	94.92 303	99.00 113	94.51 242	98.42 120	98.96 73	94.97 184	99.54 210	98.42 45	99.85 45	99.56 64

ZD-MVS					98.43 213	95.94 86		98.56 220	90.72 349	96.66 274	97.07 295	95.02 181	99.74 93	91.08 326	98.93 281

thisisatest0530		92.71 353	91.76 362	95.56 289	98.42 215	88.23 327	96.03 214	87.35 449	94.04 264	96.56 282	95.47 375	64.03 442	99.77 70	94.78 235	99.11 260	98.68 278

v1144		96.84 175	97.08 159	96.13 259	98.42 215	89.28 303	95.41 266	98.67 202	94.21 255	97.97 180	98.31 155	93.06 239	99.65 163	98.06 56	99.62 112	99.45 109

viewmanbaseed2359cas		96.77 183	96.94 169	96.27 247	98.41 217	90.24 281	95.11 291	99.03 99	94.28 254	97.45 217	97.85 223	95.92 138	99.32 291	95.18 203	99.19 249	99.24 165

plane_prior6					98.38 218	94.37 156						91.91 277

FPMVS		89.92 393	88.63 401	93.82 364	98.37 219	96.94 49	91.58 412	93.34 401	88.00 388	90.32 431	97.10 294	70.87 432	91.13 458	71.91 455	96.16 418	93.39 448

PAPM_NR		94.61 300	94.17 312	95.96 266	98.36 220	91.23 260	95.93 227	97.95 286	92.98 304	93.42 394	94.43 396	90.53 292	98.38 410	87.60 392	96.29 414	98.27 321

BP-MVS1		95.36 261	94.86 276	96.89 199	98.35 221	91.72 248	96.76 157	95.21 377	96.48 137	96.23 302	97.19 283	75.97 411	99.80 51	97.91 62	99.60 125	99.15 181

MVS_111021_HR		96.73 187	96.54 201	97.27 165	98.35 221	93.66 186	93.42 365	98.36 243	94.74 228	96.58 280	96.76 320	96.54 108	98.99 350	94.87 229	99.27 236	99.15 181

TAMVS		95.49 253	94.94 268	97.16 173	98.31 223	93.41 197	95.07 296	96.82 340	91.09 344	97.51 208	97.82 229	89.96 303	99.42 247	88.42 382	99.44 184	98.64 279

OMC-MVS		96.48 202	96.00 230	97.91 108	98.30 224	96.01 85	94.86 307	98.60 213	91.88 328	97.18 231	97.21 282	96.11 132	99.04 344	90.49 352	99.34 220	98.69 275

新几何1				97.25 168	98.29 225	94.70 141		97.73 301	77.98 449	94.83 351	96.67 325	92.08 271	99.45 240	88.17 386	98.65 317	97.61 378

jason		94.39 309	94.04 316	95.41 298	98.29 225	87.85 340	92.74 383	96.75 343	85.38 416	95.29 339	96.15 351	88.21 326	99.65 163	94.24 256	99.34 220	98.74 267
jason: jason.
v1192		96.83 178	97.06 161	96.15 258	98.28 227	89.29 302	95.36 271	98.77 180	93.73 270	98.11 162	98.34 149	93.02 244	99.67 152	98.35 47	99.58 133	99.50 85

CDPH-MVS		95.45 258	94.65 287	97.84 113	98.28 227	94.96 134	93.73 354	98.33 247	85.03 419	95.44 336	96.60 328	95.31 170	99.44 243	90.01 358	99.13 256	99.11 198

MVS_111021_LR		96.82 179	96.55 199	97.62 131	98.27 229	95.34 118	93.81 352	98.33 247	94.59 238	96.56 282	96.63 327	96.61 103	98.73 376	94.80 232	99.34 220	98.78 257

CLD-MVS		95.47 256	95.07 264	96.69 214	98.27 229	92.53 219	91.36 416	98.67 202	91.22 343	95.78 324	94.12 399	95.65 156	98.98 352	90.81 335	99.72 85	98.57 286
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
GDP-MVS		95.39 260	94.89 273	96.90 198	98.26 231	91.91 243	96.48 175	99.28 42	95.06 217	96.54 285	97.12 292	74.83 415	99.82 39	97.19 97	99.27 236	98.96 224

Anonymous202405211		96.34 211	95.98 232	97.43 152	98.25 232	93.85 176	96.74 159	94.41 388	97.72 72	98.37 126	98.03 204	87.15 339	99.53 213	94.06 263	99.07 266	98.92 236

pmmvs-eth3d		96.49 201	96.18 222	97.42 154	98.25 232	94.29 159	94.77 311	98.07 283	89.81 363	97.97 180	98.33 150	93.11 238	99.08 339	95.46 184	99.84 48	98.89 241

v144192		96.69 191	96.90 174	96.03 262	98.25 232	88.92 312	95.49 260	98.77 180	93.05 301	98.09 165	98.29 163	92.51 261	99.70 130	98.11 51	99.56 139	99.47 103

ambc				96.56 224	98.23 235	91.68 250	97.88 76	98.13 275		98.42 120	98.56 121	94.22 210	99.04 344	94.05 265	99.35 217	98.95 226

test_cas_vis1_n_1920		95.34 263	95.67 247	94.35 352	98.21 236	86.83 361	95.61 255	99.26 44	90.45 354	98.17 156	98.96 73	84.43 364	98.31 415	96.74 114	99.17 251	97.90 356

thres100view900		91.76 372	91.26 372	93.26 377	98.21 236	84.50 397	96.39 179	90.39 435	96.87 114	96.33 293	93.08 411	73.44 425	99.42 247	78.85 443	97.74 363	95.85 427

v1921920		96.72 188	96.96 168	95.99 263	98.21 236	88.79 317	95.42 264	98.79 175	93.22 291	98.19 155	98.26 169	92.68 250	99.70 130	98.34 48	99.55 145	99.49 93

thres600view7		92.03 367	91.43 365	93.82 364	98.19 239	84.61 396	96.27 190	90.39 435	96.81 117	96.37 292	93.11 407	73.44 425	99.49 227	80.32 438	97.95 353	97.36 388

PatchMatch-RL		94.61 300	93.81 322	97.02 189	98.19 239	95.72 93	93.66 356	97.23 322	88.17 386	94.94 349	95.62 371	91.43 280	98.57 394	87.36 398	97.68 369	96.76 411

LF4IMVS		96.07 222	95.63 250	97.36 158	98.19 239	95.55 102	95.44 262	98.82 169	92.29 321	95.70 328	96.55 330	92.63 253	98.69 382	91.75 317	99.33 225	97.85 360

test_vis1_n		95.67 245	95.89 238	95.03 312	98.18 242	89.89 286	96.94 141	99.28 42	88.25 385	98.20 151	98.92 79	86.69 344	97.19 435	97.70 76	98.82 294	98.00 350

v1240		96.74 185	97.02 164	95.91 271	98.18 242	88.52 320	95.39 268	98.88 142	93.15 299	98.46 116	98.40 142	92.80 247	99.71 121	98.45 44	99.49 171	99.49 93

TAPA-MVS	93.32 12	94.93 281	94.23 308	97.04 186	98.18 242	94.51 149	95.22 284	98.73 187	81.22 438	96.25 301	95.95 362	93.80 221	98.98 352	89.89 361	98.87 287	97.62 377
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test222					98.17 245	93.24 203	92.74 383	97.61 313	75.17 454	94.65 354	96.69 324	90.96 288			98.66 315	97.66 374

MIMVSNet		93.42 339	92.86 339	95.10 309	98.17 245	88.19 328	98.13 58	93.69 394	92.07 322	95.04 347	98.21 177	80.95 386	99.03 347	81.42 434	98.06 349	98.07 338

原ACMM1				96.58 220	98.16 247	92.12 235		98.15 273	85.90 409	93.49 390	96.43 338	92.47 262	99.38 266	87.66 391	98.62 319	98.23 324

testdata				95.70 281	98.16 247	90.58 275		97.72 302	80.38 441	95.62 329	97.02 299	92.06 272	98.98 352	89.06 374	98.52 325	97.54 382

test_fmvs1_n		95.21 269	95.28 255	94.99 315	98.15 249	89.13 308	96.81 151	99.43 32	86.97 399	97.21 228	98.92 79	83.00 375	97.13 436	98.09 53	98.94 278	98.72 270

MVP-Stereo		95.69 242	95.28 255	96.92 195	98.15 249	93.03 206	95.64 253	98.20 261	90.39 355	96.63 277	97.73 241	91.63 279	99.10 337	91.84 313	97.31 386	98.63 281
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		97.37 142	97.70 104	96.35 242	98.14 251	95.13 130	96.54 172	98.92 129	95.94 170	99.19 45	98.08 194	97.74 33	95.06 451	95.24 197	99.54 150	98.87 247
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
EU-MVSNet		94.25 311	94.47 300	93.60 370	98.14 251	82.60 415	97.24 124	92.72 409	85.08 417	98.48 113	98.94 76	82.59 378	98.76 374	97.47 85	99.53 154	99.44 119

NP-MVS					98.14 251	93.72 181					95.08 380

LCM-MVSNet-Re		97.33 145	97.33 143	97.32 161	98.13 254	93.79 179	96.99 139	99.65 13	96.74 120	99.47 24	98.93 77	96.91 86	99.84 34	90.11 356	99.06 269	98.32 313

3Dnovator+	96.13 3	97.73 103	97.59 122	98.15 89	98.11 255	95.60 99	98.04 63	98.70 196	98.13 57	96.93 254	98.45 133	95.30 171	99.62 179	95.64 168	98.96 275	99.24 165

testing3-2		90.09 388	90.38 387	89.24 430	98.07 256	69.88 463	95.12 289	90.71 434	96.65 122	93.60 387	94.03 400	55.81 456	99.33 283	90.69 345	98.71 309	98.51 293

VNet		96.84 175	96.83 177	96.88 200	98.06 257	92.02 240	96.35 185	97.57 314	97.70 74	97.88 189	97.80 232	92.40 263	99.54 210	94.73 238	98.96 275	99.08 203

diffmvs_AUTHOR		96.50 200	96.81 178	95.57 286	98.03 258	88.26 326	93.73 354	99.14 65	94.92 225	97.24 225	97.84 225	94.62 195	99.33 283	96.44 124	99.37 208	99.13 188

LFMVS		95.32 265	94.88 275	96.62 217	98.03 258	91.47 253	97.65 95	90.72 433	99.11 15	97.89 188	98.31 155	79.20 391	99.48 230	93.91 272	99.12 259	98.93 233

tfpn200view9		91.55 374	91.00 374	93.21 381	98.02 260	84.35 401	95.70 242	90.79 431	96.26 145	95.90 319	92.13 428	73.62 422	99.42 247	78.85 443	97.74 363	95.85 427

thres400		91.68 373	91.00 374	93.71 368	98.02 260	84.35 401	95.70 242	90.79 431	96.26 145	95.90 319	92.13 428	73.62 422	99.42 247	78.85 443	97.74 363	97.36 388

OPU-MVS				97.64 130	98.01 262	95.27 121	96.79 155				97.35 273	96.97 78	98.51 400	91.21 325	99.25 240	99.14 186

xiu_mvs_v1_base_debu		95.62 248	95.96 233	94.60 337	98.01 262	88.42 321	93.99 342	98.21 258	92.98 304	95.91 316	94.53 392	96.39 120	99.72 105	95.43 188	98.19 343	95.64 431

xiu_mvs_v1_base		95.62 248	95.96 233	94.60 337	98.01 262	88.42 321	93.99 342	98.21 258	92.98 304	95.91 316	94.53 392	96.39 120	99.72 105	95.43 188	98.19 343	95.64 431

xiu_mvs_v1_base_debi		95.62 248	95.96 233	94.60 337	98.01 262	88.42 321	93.99 342	98.21 258	92.98 304	95.91 316	94.53 392	96.39 120	99.72 105	95.43 188	98.19 343	95.64 431

CNVR-MVS		96.92 168	96.55 199	98.03 101	98.00 266	95.54 103	94.87 306	98.17 267	94.60 236	96.38 291	97.05 297	95.67 155	99.36 274	95.12 212	99.08 264	99.19 173

PLC	91.02 16	94.05 321	92.90 338	97.51 139	98.00 266	95.12 131	94.25 327	98.25 254	86.17 405	91.48 423	95.25 378	91.01 286	99.19 318	85.02 418	96.69 403	98.22 326
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
GBi-Net		96.99 162	96.80 180	97.56 134	97.96 268	93.67 183	98.23 49	98.66 205	95.59 190	97.99 176	99.19 42	89.51 311	99.73 99	94.60 242	99.44 184	99.30 147

test1		96.99 162	96.80 180	97.56 134	97.96 268	93.67 183	98.23 49	98.66 205	95.59 190	97.99 176	99.19 42	89.51 311	99.73 99	94.60 242	99.44 184	99.30 147

FMVSNet2		96.72 188	96.67 188	96.87 201	97.96 268	91.88 244	97.15 128	98.06 284	95.59 190	98.50 110	98.62 113	89.51 311	99.65 163	94.99 226	99.60 125	99.07 205

BH-untuned		94.69 294	94.75 284	94.52 343	97.95 271	87.53 346	94.07 339	97.01 333	93.99 265	97.10 237	95.65 369	92.65 252	98.95 357	87.60 392	96.74 400	97.09 395

DPM-MVS		93.68 332	92.77 345	96.42 235	97.91 272	92.54 218	91.17 423	97.47 317	84.99 421	93.08 400	94.74 388	89.90 304	99.00 348	87.54 394	98.09 348	97.72 372

QAPM		95.88 232	95.57 252	96.80 206	97.90 273	91.84 246	98.18 56	98.73 187	88.41 381	96.42 289	98.13 185	94.73 187	99.75 84	88.72 377	98.94 278	98.81 253

TinyColmap		96.00 228	96.34 214	94.96 317	97.90 273	87.91 337	94.13 337	98.49 225	94.41 249	98.16 157	97.76 235	96.29 127	98.68 385	90.52 349	99.42 197	98.30 317

SD_0403		93.73 329	93.43 328	94.64 333	97.85 275	86.35 368	97.47 110	97.94 287	93.50 280	93.71 380	96.73 321	93.77 222	98.84 365	73.48 452	96.39 410	98.72 270

test_fmvs2		96.38 209	96.45 207	96.16 257	97.85 275	91.30 257	96.81 151	99.45 30	89.24 369	98.49 111	99.38 23	88.68 319	97.62 432	98.83 30	99.32 227	99.57 56

HQP-NCC					97.85 275		94.26 324		93.18 295	92.86 404

ACMP_Plane					97.85 275		94.26 324		93.18 295	92.86 404

N_pmnet		95.18 271	94.23 308	98.06 96	97.85 275	96.55 62	92.49 389	91.63 421	89.34 367	98.09 165	97.41 263	90.33 297	99.06 341	91.58 318	99.31 230	98.56 287

HQP-MVS		95.17 273	94.58 295	96.92 195	97.85 275	92.47 222	94.26 324	98.43 231	93.18 295	92.86 404	95.08 380	90.33 297	99.23 314	90.51 350	98.74 305	99.05 209

hse-mvs2		95.77 238	95.09 263	97.79 115	97.84 281	95.51 105	95.66 247	95.43 372	96.58 129	97.21 228	96.16 350	84.14 365	99.54 210	95.89 154	96.92 391	98.32 313

TEST9					97.84 281	95.23 123	93.62 358	98.39 238	86.81 400	93.78 376	95.99 358	94.68 192	99.52 216

train_agg		95.46 257	94.66 286	97.88 110	97.84 281	95.23 123	93.62 358	98.39 238	87.04 396	93.78 376	95.99 358	94.58 197	99.52 216	91.76 316	98.90 283	98.89 241

icg_test_0407_2		95.88 232	96.39 210	94.36 350	97.83 284	86.11 371	91.82 408	98.82 169	94.48 243	97.57 203	97.14 286	96.08 133	98.20 422	95.00 220	98.78 297	98.78 257

IMVS_0407		96.35 210	96.88 175	94.74 331	97.83 284	86.11 371	96.25 194	98.82 169	94.48 243	97.57 203	97.14 286	96.08 133	99.33 283	95.00 220	98.78 297	98.78 257

IMVS_0404		95.66 247	96.03 228	94.55 341	97.83 284	86.11 371	93.24 371	98.82 169	94.48 243	95.51 334	97.14 286	93.49 229	98.78 370	95.00 220	98.78 297	98.78 257

IMVS_0403		96.27 213	96.77 183	94.76 329	97.83 284	86.11 371	96.00 217	98.82 169	94.48 243	97.49 210	97.14 286	95.38 166	99.40 258	95.00 220	98.78 297	98.78 257

MSLP-MVS++		96.42 207	96.71 185	95.57 286	97.82 288	90.56 277	95.71 241	98.84 155	94.72 231	96.71 269	97.39 268	94.91 186	98.10 424	95.28 194	99.02 271	98.05 345

test_8					97.81 289	95.07 132	93.54 362	98.38 240	87.04 396	93.71 380	95.96 361	94.58 197	99.52 216

NCCC		96.52 199	95.99 231	98.10 93	97.81 289	95.68 96	95.00 301	98.20 261	95.39 202	95.40 338	96.36 343	93.81 220	99.45 240	93.55 282	98.42 334	99.17 177

WTY-MVS		93.55 336	93.00 337	95.19 303	97.81 289	87.86 338	93.89 348	96.00 355	89.02 372	94.07 369	95.44 377	86.27 346	99.33 283	87.69 390	96.82 397	98.39 304

CNLPA		95.04 277	94.47 300	96.75 210	97.81 289	95.25 122	94.12 338	97.89 291	94.41 249	94.57 355	95.69 367	90.30 300	98.35 413	86.72 404	98.76 303	96.64 413

AUN-MVS		93.95 326	92.69 346	97.74 119	97.80 293	95.38 113	95.57 258	95.46 371	91.26 342	92.64 411	96.10 356	74.67 416	99.55 207	93.72 278	96.97 390	98.30 317

EIA-MVS		96.04 224	95.77 245	96.85 202	97.80 293	92.98 207	96.12 206	99.16 56	94.65 234	93.77 378	91.69 433	95.68 153	99.67 152	94.18 258	98.85 290	97.91 355

agg_prior					97.80 293	94.96 134		98.36 243		93.49 390			99.53 213

旧先验1					97.80 293	93.87 175		97.75 300			97.04 298	93.57 227			98.68 312	98.72 270

PCF-MVS	89.43 18	92.12 363	90.64 383	96.57 222	97.80 293	93.48 193	89.88 441	98.45 228	74.46 455	96.04 312	95.68 368	90.71 291	99.31 292	73.73 451	99.01 273	96.91 402
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_prior				97.46 149	97.79 298	94.26 163		98.42 234					99.34 281			98.79 256

PVSNet_BlendedMVS		95.02 280	94.93 270	95.27 300	97.79 298	87.40 350	94.14 336	98.68 199	88.94 374	94.51 357	98.01 207	93.04 240	99.30 296	89.77 363	99.49 171	99.11 198

PVSNet_Blended		93.96 324	93.65 324	94.91 318	97.79 298	87.40 350	91.43 415	98.68 199	84.50 426	94.51 357	94.48 395	93.04 240	99.30 296	89.77 363	98.61 320	98.02 348

USDC		94.56 302	94.57 297	94.55 341	97.78 301	86.43 366	92.75 381	98.65 210	85.96 407	96.91 256	97.93 216	90.82 289	98.74 375	90.71 343	99.59 128	98.47 298

alignmvs		96.01 227	95.52 253	97.50 143	97.77 302	94.71 139	96.07 209	96.84 338	97.48 85	96.78 266	94.28 398	85.50 354	99.40 258	96.22 136	98.73 308	98.40 302

ETV-MVS		96.13 221	95.90 237	96.82 205	97.76 303	93.89 174	95.40 267	98.95 126	95.87 176	95.58 332	91.00 439	96.36 123	99.72 105	93.36 285	98.83 293	96.85 405

D2MVS		95.18 271	95.17 260	95.21 302	97.76 303	87.76 343	94.15 334	97.94 287	89.77 364	96.99 248	97.68 245	87.45 335	99.14 326	95.03 219	99.81 57	98.74 267

DVP-MVS++		97.96 67	97.90 79	98.12 92	97.75 305	95.40 111	99.03 8	98.89 135	96.62 123	98.62 98	98.30 159	96.97 78	99.75 84	95.70 161	99.25 240	99.21 169

MSC_two_6792asdad				98.22 82	97.75 305	95.34 118		98.16 271					99.75 84	95.87 156	99.51 164	99.57 56

No_MVS				98.22 82	97.75 305	95.34 118		98.16 271					99.75 84	95.87 156	99.51 164	99.57 56

TSAR-MVS + GP.		96.47 203	96.12 223	97.49 146	97.74 308	95.23 123	94.15 334	96.90 337	93.26 289	98.04 173	96.70 323	94.41 203	98.89 360	94.77 236	99.14 254	98.37 306

3Dnovator	96.53 2	97.61 117	97.64 115	97.50 143	97.74 308	93.65 187	98.49 31	98.88 142	96.86 115	97.11 236	98.55 122	95.82 145	99.73 99	95.94 151	99.42 197	99.13 188

MM		96.87 173	96.62 189	97.62 131	97.72 310	93.30 199	96.39 179	92.61 412	97.90 65	96.76 267	98.64 112	90.46 294	99.81 44	99.16 18	99.94 8	99.76 21

sss		94.22 312	93.72 323	95.74 278	97.71 311	89.95 285	93.84 349	96.98 334	88.38 383	93.75 379	95.74 366	87.94 327	98.89 360	91.02 328	98.10 347	98.37 306

DeepC-MVS_fast	94.34 7	96.74 185	96.51 204	97.44 151	97.69 312	94.15 165	96.02 215	98.43 231	93.17 298	97.30 221	97.38 270	95.48 161	99.28 302	93.74 276	99.34 220	98.88 245
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MGCFI-Net		97.20 151	97.23 150	97.08 182	97.68 313	93.71 182	97.79 81	99.09 77	97.40 93	96.59 279	93.96 401	97.67 36	99.35 278	96.43 125	98.50 329	98.17 332

IterMVS-SCA-FT		95.86 234	96.19 221	94.85 323	97.68 313	85.53 379	92.42 394	97.63 312	96.99 106	98.36 129	98.54 124	87.94 327	99.75 84	97.07 104	99.08 264	99.27 158

MVSFormer		96.14 220	96.36 213	95.49 293	97.68 313	87.81 341	98.67 18	99.02 102	96.50 134	94.48 359	96.15 351	86.90 341	99.92 6	98.73 35	99.13 256	98.74 267

lupinMVS		93.77 327	93.28 331	95.24 301	97.68 313	87.81 341	92.12 401	96.05 353	84.52 425	94.48 359	95.06 382	86.90 341	99.63 174	93.62 281	99.13 256	98.27 321

Fast-Effi-MVS+		95.49 253	95.07 264	96.75 210	97.67 317	92.82 210	94.22 330	98.60 213	91.61 333	93.42 394	92.90 414	96.73 98	99.70 130	92.60 299	97.89 357	97.74 369

testing3		89.72 396	88.26 405	94.10 361	97.66 318	84.30 403	94.80 308	88.25 447	94.66 233	95.07 343	92.51 423	41.15 466	99.43 245	91.81 314	98.44 333	98.55 289

balanced_conf03		96.88 172	97.29 145	95.63 283	97.66 318	89.47 298	97.95 70	98.89 135	95.94 170	97.77 199	98.55 122	92.23 265	99.68 143	97.05 105	99.61 118	97.73 370

sasdasda		97.23 149	97.21 152	97.30 162	97.65 320	94.39 153	97.84 78	99.05 91	97.42 88	96.68 270	93.85 403	97.63 40	99.33 283	96.29 132	98.47 330	98.18 330

canonicalmvs		97.23 149	97.21 152	97.30 162	97.65 320	94.39 153	97.84 78	99.05 91	97.42 88	96.68 270	93.85 403	97.63 40	99.33 283	96.29 132	98.47 330	98.18 330

mvsmamba		94.91 282	94.41 304	96.40 240	97.65 320	91.30 257	97.92 73	95.32 374	91.50 336	95.54 333	98.38 143	83.06 374	99.68 143	92.46 303	97.84 358	98.23 324

CDS-MVSNet		94.88 285	94.12 314	97.14 175	97.64 323	93.57 188	93.96 346	97.06 331	90.05 360	96.30 298	96.55 330	86.10 347	99.47 232	90.10 357	99.31 230	98.40 302
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
pmmvs5		94.63 299	94.34 306	95.50 292	97.63 324	88.34 324	94.02 340	97.13 327	87.15 395	95.22 341	97.15 285	87.50 334	99.27 305	93.99 267	99.26 239	98.88 245

test_f		95.82 236	95.88 239	95.66 282	97.61 325	93.21 204	95.61 255	98.17 267	86.98 398	98.42 120	99.47 16	90.46 294	94.74 453	97.71 74	98.45 332	99.03 210

test12				97.46 149	97.61 325	94.07 167		97.78 299		93.57 388		93.31 233	99.42 247		98.78 297	98.89 241

VortexMVS		96.04 224	96.56 196	94.49 346	97.60 327	84.36 400	96.05 211	98.67 202	94.74 228	98.95 68	98.78 92	87.13 340	99.50 221	97.37 90	99.76 69	99.60 44

PMMVS2		93.66 333	94.07 315	92.45 404	97.57 328	80.67 430	86.46 449	96.00 355	93.99 265	97.10 237	97.38 270	89.90 304	97.82 429	88.76 376	99.47 177	98.86 248

BH-RMVSNet		94.56 302	94.44 303	94.91 318	97.57 328	87.44 348	93.78 353	96.26 350	93.69 273	96.41 290	96.50 335	92.10 270	99.00 348	85.96 406	97.71 366	98.31 315

PVSNet	86.72 19	91.10 380	90.97 376	91.49 415	97.56 330	78.04 440	87.17 448	94.60 386	84.65 424	92.34 415	92.20 427	87.37 338	98.47 404	85.17 417	97.69 368	97.96 352

DELS-MVS		96.17 219	96.23 219	95.99 263	97.55 331	90.04 283	92.38 397	98.52 222	94.13 259	96.55 284	97.06 296	94.99 182	99.58 195	95.62 171	99.28 234	98.37 306
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
IterMVS		95.42 259	95.83 242	94.20 358	97.52 332	83.78 407	92.41 395	97.47 317	95.49 197	98.06 170	98.49 128	87.94 327	99.58 195	96.02 145	99.02 271	99.23 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
viewmambaseed2359dif		95.68 244	95.85 240	95.17 305	97.51 333	87.41 349	93.61 360	98.58 217	91.06 345	96.68 270	97.66 246	94.71 189	99.11 333	93.93 270	98.94 278	98.99 217

FA-MVS(test-final)		94.91 282	94.89 273	94.99 315	97.51 333	88.11 334	98.27 47	95.20 378	92.40 320	96.68 270	98.60 116	83.44 371	99.28 302	93.34 286	98.53 324	97.59 380

CL-MVSNet_self_test		95.04 277	94.79 283	95.82 274	97.51 333	89.79 289	91.14 424	96.82 340	93.05 301	96.72 268	96.40 341	90.82 289	99.16 324	91.95 309	98.66 315	98.50 296

new-patchmatchnet		95.67 245	96.58 193	92.94 391	97.48 336	80.21 432	92.96 376	98.19 266	94.83 226	98.82 80	98.79 89	93.31 233	99.51 220	95.83 158	99.04 270	99.12 194

MDA-MVSNet_test_wron		94.73 289	94.83 280	94.42 348	97.48 336	85.15 387	90.28 435	95.87 360	92.52 315	97.48 213	97.76 235	91.92 276	99.17 323	93.32 287	96.80 399	98.94 229

PHI-MVS		96.96 166	96.53 202	98.25 80	97.48 336	96.50 63	96.76 157	98.85 151	93.52 279	96.19 306	96.85 311	95.94 137	99.42 247	93.79 275	99.43 194	98.83 250

DeepPCF-MVS	94.58 5	96.90 170	96.43 208	98.31 73	97.48 336	97.23 44	92.56 388	98.60 213	92.84 310	98.54 106	97.40 264	96.64 102	98.78 370	94.40 250	99.41 201	98.93 233

thres200		91.00 382	90.42 386	92.77 396	97.47 340	83.98 406	94.01 341	91.18 428	95.12 214	95.44 336	91.21 437	73.93 418	99.31 292	77.76 446	97.63 374	95.01 438

YYNet1		94.73 289	94.84 278	94.41 349	97.47 340	85.09 389	90.29 434	95.85 361	92.52 315	97.53 206	97.76 235	91.97 273	99.18 319	93.31 288	96.86 394	98.95 226

Effi-MVS+		96.19 218	96.01 229	96.71 212	97.43 342	92.19 234	96.12 206	99.10 72	95.45 198	93.33 396	94.71 389	97.23 60	99.56 203	93.21 292	97.54 376	98.37 306

pmmvs4		94.82 287	94.19 311	96.70 213	97.42 343	92.75 216	92.09 403	96.76 342	86.80 401	95.73 327	97.22 281	89.28 315	98.89 360	93.28 289	99.14 254	98.46 300

mvsany_test3		96.21 216	95.93 236	97.05 184	97.40 344	94.33 158	95.76 239	94.20 391	89.10 370	99.36 35	99.60 11	93.97 216	97.85 428	95.40 192	98.63 318	98.99 217

MSDG		95.33 264	95.13 261	95.94 270	97.40 344	91.85 245	91.02 427	98.37 242	95.30 206	96.31 297	95.99 358	94.51 201	98.38 410	89.59 365	97.65 373	97.60 379

EI-MVSNet-Vis-set		97.32 146	97.39 137	97.11 177	97.36 346	92.08 239	95.34 275	97.65 308	97.74 70	98.29 142	98.11 190	95.05 178	99.68 143	97.50 83	99.50 168	99.56 64

PS-MVSNAJ		94.10 318	94.47 300	93.00 388	97.35 347	84.88 391	91.86 406	97.84 295	91.96 326	94.17 365	92.50 424	95.82 145	99.71 121	91.27 322	97.48 379	94.40 442

diffmvs		96.04 224	96.23 219	95.46 295	97.35 347	88.03 335	93.42 365	99.08 81	94.09 263	96.66 274	96.93 306	93.85 219	99.29 300	96.01 147	98.67 313	99.06 207
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet-UG-set		97.32 146	97.40 136	97.09 181	97.34 349	92.01 241	95.33 276	97.65 308	97.74 70	98.30 141	98.14 183	95.04 179	99.69 137	97.55 81	99.52 159	99.58 48

baseline1		93.14 347	92.64 348	94.62 336	97.34 349	87.20 354	96.67 168	93.02 404	94.71 232	96.51 286	95.83 365	81.64 379	98.60 393	90.00 359	88.06 453	98.07 338

AdaColmap		95.11 274	94.62 291	96.58 220	97.33 351	94.45 152	94.92 303	98.08 279	93.15 299	93.98 374	95.53 374	94.34 205	99.10 337	85.69 409	98.61 320	96.20 424

xiu_mvs_v2_base		94.22 312	94.63 290	92.99 389	97.32 352	84.84 394	92.12 401	97.84 295	91.96 326	94.17 365	93.43 405	96.07 135	99.71 121	91.27 322	97.48 379	94.42 441

OpenMVS_ROB	91.80 14	93.64 334	93.05 334	95.42 296	97.31 353	91.21 261	95.08 295	96.68 347	81.56 435	96.88 258	96.41 339	90.44 296	99.25 308	85.39 414	97.67 370	95.80 429

EI-MVSNet		96.63 194	96.93 170	95.74 278	97.26 354	88.13 332	95.29 281	97.65 308	96.99 106	97.94 184	98.19 178	92.55 256	99.58 195	96.91 109	99.56 139	99.50 85

CVMVSNet		92.33 359	92.79 342	90.95 420	97.26 354	75.84 451	95.29 281	92.33 415	81.86 433	96.27 299	98.19 178	81.44 381	98.46 405	94.23 257	98.29 340	98.55 289

FE-MVS		92.95 349	92.22 354	95.11 307	97.21 356	88.33 325	98.54 26	93.66 397	89.91 362	96.21 304	98.14 183	70.33 434	99.50 221	87.79 388	98.24 342	97.51 383

Fast-Effi-MVS+-dtu		96.44 204	96.12 223	97.39 157	97.18 357	94.39 153	95.46 261	98.73 187	96.03 163	94.72 352	94.92 386	96.28 128	99.69 137	93.81 274	97.98 351	98.09 335

dmvs_re		92.08 365	91.27 370	94.51 344	97.16 358	92.79 215	95.65 249	92.64 411	94.11 261	92.74 407	90.98 440	83.41 372	94.44 455	80.72 437	94.07 438	96.29 422

OpenMVS	94.22 8	95.48 255	95.20 257	96.32 244	97.16 358	91.96 242	97.74 88	98.84 155	87.26 393	94.36 361	98.01 207	93.95 217	99.67 152	90.70 344	98.75 304	97.35 390

BH-w/o		92.14 362	91.94 357	92.73 397	97.13 360	85.30 383	92.46 391	95.64 364	89.33 368	94.21 363	92.74 419	89.60 306	98.24 418	81.68 433	94.66 434	94.66 440

MG-MVS		94.08 320	94.00 317	94.32 354	97.09 361	85.89 376	93.19 374	95.96 357	92.52 315	94.93 350	97.51 257	89.54 308	98.77 372	87.52 396	97.71 366	98.31 315

thisisatest0515		90.43 385	89.18 398	94.17 360	97.07 362	85.44 380	89.75 442	87.58 448	88.28 384	93.69 383	91.72 432	65.27 440	99.58 195	90.59 347	98.67 313	97.50 385

MVS-HIRNet		88.40 408	90.20 389	82.99 440	97.01 363	60.04 465	93.11 375	85.61 454	84.45 427	88.72 445	99.09 58	84.72 362	98.23 419	82.52 430	96.59 406	90.69 455

GA-MVS		92.83 351	92.15 356	94.87 322	96.97 364	87.27 353	90.03 436	96.12 352	91.83 329	94.05 370	94.57 390	76.01 410	98.97 356	92.46 303	97.34 385	98.36 311

test_yl		94.40 307	94.00 317	95.59 284	96.95 365	89.52 296	94.75 312	95.55 369	96.18 151	96.79 262	96.14 353	81.09 384	99.18 319	90.75 339	97.77 360	98.07 338

DCV-MVSNet		94.40 307	94.00 317	95.59 284	96.95 365	89.52 296	94.75 312	95.55 369	96.18 151	96.79 262	96.14 353	81.09 384	99.18 319	90.75 339	97.77 360	98.07 338

MVS_Test		96.27 213	96.79 182	94.73 332	96.94 367	86.63 363	96.18 199	98.33 247	94.94 222	96.07 310	98.28 164	95.25 172	99.26 306	97.21 94	97.90 356	98.30 317

MAR-MVS		94.21 314	93.03 335	97.76 118	96.94 367	97.44 37	96.97 140	97.15 326	87.89 390	92.00 418	92.73 420	92.14 268	99.12 330	83.92 423	97.51 378	96.73 412
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+-dtu		96.81 180	96.09 225	98.99 14	96.90 369	98.69 5	96.42 176	98.09 278	95.86 177	95.15 342	95.54 373	94.26 209	99.81 44	94.06 263	98.51 328	98.47 298

MS-PatchMatch		94.83 286	94.91 272	94.57 340	96.81 370	87.10 356	94.23 329	97.34 320	88.74 377	97.14 233	97.11 293	91.94 275	98.23 419	92.99 295	97.92 354	98.37 306

dmvs_testset		87.30 419	86.99 416	88.24 435	96.71 371	77.48 444	94.68 314	86.81 452	92.64 314	89.61 440	87.01 455	85.91 349	93.12 456	61.04 459	88.49 452	94.13 443

RRT-MVS		95.78 237	96.25 218	94.35 352	96.68 372	84.47 398	97.72 90	99.11 69	97.23 101	97.27 223	98.72 99	86.39 345	99.79 54	95.49 177	97.67 370	98.80 254

UGNet		96.81 180	96.56 196	97.58 133	96.64 373	93.84 177	97.75 86	97.12 328	96.47 138	93.62 384	98.88 85	93.22 235	99.53 213	95.61 172	99.69 94	99.36 138
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
API-MVS		95.09 276	95.01 267	95.31 299	96.61 374	94.02 170	96.83 149	97.18 325	95.60 189	95.79 322	94.33 397	94.54 200	98.37 412	85.70 408	98.52 325	93.52 446

PAPM		87.64 415	85.84 422	93.04 385	96.54 375	84.99 390	88.42 447	95.57 368	79.52 444	83.82 455	93.05 413	80.57 387	98.41 407	62.29 458	92.79 442	95.71 430

FMVSNet3		95.26 268	94.94 268	96.22 251	96.53 376	90.06 282	95.99 220	97.66 306	94.11 261	97.99 176	97.91 218	80.22 389	99.63 174	94.60 242	99.44 184	98.96 224

HY-MVS	91.43 15	92.58 354	91.81 360	94.90 320	96.49 377	88.87 314	97.31 119	94.62 385	85.92 408	90.50 429	96.84 312	85.05 358	99.40 258	83.77 426	95.78 423	96.43 420

TR-MVS		92.54 355	92.20 355	93.57 371	96.49 377	86.66 362	93.51 363	94.73 384	89.96 361	94.95 348	93.87 402	90.24 302	98.61 391	81.18 436	94.88 432	95.45 435

myMVS_eth3d28		88.32 409	87.73 410	90.11 427	96.42 379	74.96 456	92.21 399	92.37 414	93.56 277	90.14 434	89.61 448	56.13 454	98.05 426	81.84 431	97.26 388	97.33 391

ET-MVSNet_ETH3D		91.12 378	89.67 392	95.47 294	96.41 380	89.15 306	91.54 413	90.23 439	89.07 371	86.78 453	92.84 417	69.39 436	99.44 243	94.16 259	96.61 405	97.82 362

CANet		95.86 234	95.65 249	96.49 230	96.41 380	90.82 270	94.36 322	98.41 235	94.94 222	92.62 413	96.73 321	92.68 250	99.71 121	95.12 212	99.60 125	98.94 229

mvs_anonymous		95.36 261	96.07 227	93.21 381	96.29 382	81.56 422	94.60 317	97.66 306	93.30 288	96.95 253	98.91 82	93.03 243	99.38 266	96.60 117	97.30 387	98.69 275

SCA		93.38 341	93.52 327	92.96 390	96.24 383	81.40 424	93.24 371	94.00 392	91.58 335	94.57 355	96.97 303	87.94 327	99.42 247	89.47 367	97.66 372	98.06 342

LS3D		97.77 101	97.50 132	98.57 51	96.24 383	97.58 28	98.45 34	98.85 151	98.58 37	97.51 208	97.94 214	95.74 152	99.63 174	95.19 201	98.97 274	98.51 293

new_pmnet		92.34 358	91.69 363	94.32 354	96.23 385	89.16 305	92.27 398	92.88 406	84.39 428	95.29 339	96.35 344	85.66 352	96.74 445	84.53 421	97.56 375	97.05 396

MVE	73.61 22	86.48 422	85.92 421	88.18 436	96.23 385	85.28 385	81.78 457	75.79 461	86.01 406	82.53 457	91.88 430	92.74 248	87.47 460	71.42 456	94.86 433	91.78 451
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
c3_l		95.20 270	95.32 254	94.83 325	96.19 387	86.43 366	91.83 407	98.35 246	93.47 282	97.36 220	97.26 279	88.69 318	99.28 302	95.41 191	99.36 212	98.78 257

DSMNet-mixed		92.19 361	91.83 359	93.25 378	96.18 388	83.68 408	96.27 190	93.68 396	76.97 453	92.54 414	99.18 46	89.20 317	98.55 397	83.88 424	98.60 322	97.51 383

miper_lstm_enhance		94.81 288	94.80 282	94.85 323	96.16 389	86.45 365	91.14 424	98.20 261	93.49 281	97.03 245	97.37 272	84.97 360	99.26 306	95.28 194	99.56 139	98.83 250

our_test_3		94.20 316	94.58 295	93.07 384	96.16 389	81.20 426	90.42 433	96.84 338	90.72 349	97.14 233	97.13 290	90.47 293	99.11 333	94.04 266	98.25 341	98.91 237

ppachtmachnet_test		94.49 306	94.84 278	93.46 373	96.16 389	82.10 417	90.59 431	97.48 316	90.53 353	97.01 247	97.59 251	91.01 286	99.36 274	93.97 269	99.18 250	98.94 229

ETVMVS		87.62 416	85.75 423	93.22 380	96.15 392	83.26 409	92.94 377	90.37 437	91.39 339	90.37 430	88.45 451	51.93 463	98.64 388	73.76 450	96.38 411	97.75 368

Patchmatch-test		93.60 335	93.25 332	94.63 335	96.14 393	87.47 347	96.04 213	94.50 387	93.57 276	96.47 287	96.97 303	76.50 406	98.61 391	90.67 346	98.41 335	97.81 364

UBG		88.29 410	87.17 414	91.63 414	96.08 394	78.21 438	91.61 410	91.50 423	89.67 365	89.71 439	88.97 450	59.01 446	98.91 358	81.28 435	96.72 402	97.77 367

wuyk23d		93.25 345	95.20 257	87.40 439	96.07 395	95.38 113	97.04 136	94.97 381	95.33 204	99.70 10	98.11 190	98.14 21	91.94 457	77.76 446	99.68 98	74.89 457

WBMVS		91.11 379	90.72 381	92.26 407	95.99 396	77.98 442	91.47 414	95.90 359	91.63 331	95.90 319	96.45 337	59.60 445	99.46 235	89.97 360	99.59 128	99.33 141

eth_miper_zixun_eth		94.89 284	94.93 270	94.75 330	95.99 396	86.12 370	91.35 417	98.49 225	93.40 283	97.12 235	97.25 280	86.87 343	99.35 278	95.08 214	98.82 294	98.78 257

test_fmvs1		94.51 305	94.60 292	94.26 357	95.91 398	87.92 336	95.35 274	99.02 102	86.56 403	96.79 262	98.52 125	82.64 377	97.00 439	97.87 64	98.71 309	97.88 358

testing91		89.67 397	88.55 402	93.04 385	95.90 399	81.80 421	92.71 385	93.71 393	93.71 271	90.18 433	90.15 445	57.11 449	99.22 316	87.17 401	96.32 413	98.12 334

CANet_DTU		94.65 298	94.21 310	95.96 266	95.90 399	89.68 292	93.92 347	97.83 297	93.19 294	90.12 435	95.64 370	88.52 320	99.57 201	93.27 290	99.47 177	98.62 282

testing11		88.93 403	87.63 412	92.80 395	95.87 401	81.49 423	92.48 390	91.54 422	91.62 332	88.27 447	90.24 443	55.12 461	99.11 333	87.30 399	96.28 415	97.81 364

DIV-MVS_self_test		94.73 289	94.64 288	95.01 313	95.86 402	87.00 357	91.33 418	98.08 279	93.34 286	97.10 237	97.34 274	84.02 368	99.31 292	95.15 208	99.55 145	98.72 270

cl____		94.73 289	94.64 288	95.01 313	95.85 403	87.00 357	91.33 418	98.08 279	93.34 286	97.10 237	97.33 275	84.01 369	99.30 296	95.14 209	99.56 139	98.71 274

MVSTER		94.21 314	93.93 321	95.05 311	95.83 404	86.46 364	95.18 288	97.65 308	92.41 319	97.94 184	98.00 209	72.39 427	99.58 195	96.36 128	99.56 139	99.12 194

FMVSNet5		93.39 340	92.35 351	96.50 229	95.83 404	90.81 272	97.31 119	98.27 252	92.74 312	96.27 299	98.28 164	62.23 443	99.67 152	90.86 333	99.36 212	99.03 210

ttmdpeth		94.05 321	94.15 313	93.75 366	95.81 406	85.32 382	96.00 217	94.93 382	92.07 322	94.19 364	99.09 58	85.73 351	96.41 447	90.98 329	98.52 325	99.53 75

testing222		87.35 418	85.50 425	92.93 392	95.79 407	82.83 411	92.40 396	90.10 441	92.80 311	88.87 444	89.02 449	48.34 464	98.70 380	75.40 449	96.74 400	97.27 393

testing99		89.21 401	88.04 407	92.70 398	95.78 408	81.00 428	92.65 386	92.03 416	93.20 293	89.90 438	90.08 447	55.25 458	99.14 326	87.54 394	95.95 419	97.97 351

miper_ehance_all_eth		94.69 294	94.70 285	94.64 333	95.77 409	86.22 369	91.32 420	98.24 256	91.67 330	97.05 244	96.65 326	88.39 323	99.22 316	94.88 228	98.34 337	98.49 297

test_vis1_rt		94.03 323	93.65 324	95.17 305	95.76 410	93.42 196	93.97 345	98.33 247	84.68 423	93.17 398	95.89 364	92.53 260	94.79 452	93.50 283	94.97 431	97.31 392

PVSNet_0	81.89 21	84.49 423	83.21 426	88.34 434	95.76 410	74.97 455	83.49 454	92.70 410	78.47 448	87.94 448	86.90 456	83.38 373	96.63 446	73.44 453	66.86 460	93.40 447

PAPR		92.22 360	91.27 370	95.07 310	95.73 412	88.81 316	91.97 404	97.87 292	85.80 410	90.91 425	92.73 420	91.16 283	98.33 414	79.48 440	95.76 424	98.08 336

baseline2		89.65 398	88.44 404	93.25 378	95.62 413	82.71 412	93.82 350	85.94 453	88.89 375	87.35 451	92.54 422	71.23 430	99.33 283	86.01 405	94.60 436	97.72 372

CHOSEN 280x420		89.98 391	89.19 397	92.37 405	95.60 414	81.13 427	86.22 450	97.09 329	81.44 437	87.44 450	93.15 406	73.99 417	99.47 232	88.69 378	99.07 266	96.52 417

ADS-MVSNet2		91.47 376	90.51 385	94.36 350	95.51 415	85.63 377	95.05 298	95.70 362	83.46 429	92.69 408	96.84 312	79.15 392	99.41 256	85.66 410	90.52 447	98.04 346

ADS-MVSNet		90.95 383	90.26 388	93.04 385	95.51 415	82.37 416	95.05 298	93.41 400	83.46 429	92.69 408	96.84 312	79.15 392	98.70 380	85.66 410	90.52 447	98.04 346

CR-MVSNet		93.29 344	92.79 342	94.78 328	95.44 417	88.15 330	96.18 199	97.20 323	84.94 422	94.10 367	98.57 119	77.67 398	99.39 263	95.17 204	95.81 420	96.81 409

RPMNet		94.68 296	94.60 292	94.90 320	95.44 417	88.15 330	96.18 199	98.86 147	97.43 87	94.10 367	98.49 128	79.40 390	99.76 76	95.69 163	95.81 420	96.81 409

reproduce_monomvs		92.05 366	92.26 353	91.43 416	95.42 419	75.72 452	95.68 245	97.05 332	94.47 247	97.95 183	98.35 147	55.58 457	99.05 342	96.36 128	99.44 184	99.51 82

1314		92.38 357	92.30 352	92.64 399	95.42 419	85.15 387	95.86 232	96.97 335	85.40 415	90.62 426	93.06 412	91.12 284	97.80 430	86.74 403	95.49 428	94.97 439

tpm		91.08 381	90.85 378	91.75 413	95.33 421	78.09 439	95.03 300	91.27 427	88.75 376	93.53 389	97.40 264	71.24 429	99.30 296	91.25 324	93.87 439	97.87 359

UWE-MVS		87.57 417	86.72 419	90.13 426	95.21 422	73.56 457	91.94 405	83.78 457	88.73 378	93.00 401	92.87 416	55.22 459	99.25 308	81.74 432	97.96 352	97.59 380

Syy-MVS		92.09 364	91.80 361	92.93 392	95.19 423	82.65 413	92.46 391	91.35 424	90.67 351	91.76 421	87.61 453	85.64 353	98.50 401	94.73 238	96.84 395	97.65 375

myMVS_eth3d		87.16 421	85.61 424	91.82 412	95.19 423	79.32 434	92.46 391	91.35 424	90.67 351	91.76 421	87.61 453	41.96 465	98.50 401	82.66 429	96.84 395	97.65 375

IB-MVS	85.98 20	88.63 406	86.95 418	93.68 369	95.12 425	84.82 395	90.85 428	90.17 440	87.55 392	88.48 446	91.34 436	58.01 447	99.59 192	87.24 400	93.80 440	96.63 415
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
PatchT		93.75 328	93.57 326	94.29 356	95.05 426	87.32 352	96.05 211	92.98 405	97.54 82	94.25 362	98.72 99	75.79 412	99.24 312	95.92 152	95.81 420	96.32 421

tpm2		88.47 407	87.69 411	90.79 421	94.98 427	77.34 445	95.09 293	91.83 419	77.51 452	89.40 441	96.41 339	67.83 438	98.73 376	83.58 428	92.60 444	96.29 422

WB-MVSnew		91.50 375	91.29 368	92.14 409	94.85 428	80.32 431	93.29 370	88.77 445	88.57 380	94.03 371	92.21 426	92.56 255	98.28 417	80.21 439	97.08 389	97.81 364

MVS_0304		95.71 241	95.18 259	97.33 160	94.85 428	92.82 210	95.36 271	90.89 430	95.51 195	95.61 330	97.82 229	88.39 323	99.78 59	98.23 49	99.91 19	99.40 124

Patchmtry		95.03 279	94.59 294	96.33 243	94.83 430	90.82 270	96.38 182	97.20 323	96.59 128	97.49 210	98.57 119	77.67 398	99.38 266	92.95 297	99.62 112	98.80 254

MVS		90.02 389	89.20 396	92.47 403	94.71 431	86.90 359	95.86 232	96.74 344	64.72 458	90.62 426	92.77 418	92.54 258	98.39 409	79.30 441	95.56 427	92.12 450

CostFormer		89.75 395	89.25 393	91.26 419	94.69 432	78.00 441	95.32 278	91.98 418	81.50 436	90.55 428	96.96 305	71.06 431	98.89 360	88.59 380	92.63 443	96.87 403

PatchmatchNet		91.98 368	91.87 358	92.30 406	94.60 433	79.71 433	95.12 289	93.59 399	89.52 366	93.61 385	97.02 299	77.94 396	99.18 319	90.84 334	94.57 437	98.01 349
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm cat1		88.01 413	87.33 413	90.05 428	94.48 434	76.28 450	94.47 320	94.35 389	73.84 457	89.26 442	95.61 372	73.64 421	98.30 416	84.13 422	86.20 455	95.57 434

MDTV_nov1_ep13			91.28 369		94.31 435	73.51 458	94.80 308	93.16 403	86.75 402	93.45 392	97.40 264	76.37 407	98.55 397	88.85 375	96.43 408

cl22		93.25 345	92.84 341	94.46 347	94.30 436	86.00 375	91.09 426	96.64 348	90.74 348	95.79 322	96.31 345	78.24 395	98.77 372	94.15 260	98.34 337	98.62 282

cascas		91.89 369	91.35 367	93.51 372	94.27 437	85.60 378	88.86 446	98.61 212	79.32 445	92.16 417	91.44 435	89.22 316	98.12 423	90.80 336	97.47 381	96.82 408

test-LLR		89.97 392	89.90 390	90.16 424	94.24 438	74.98 453	89.89 438	89.06 443	92.02 324	89.97 436	90.77 441	73.92 419	98.57 394	91.88 311	97.36 383	96.92 400

test-mter		87.92 414	87.17 414	90.16 424	94.24 438	74.98 453	89.89 438	89.06 443	86.44 404	89.97 436	90.77 441	54.96 462	98.57 394	91.88 311	97.36 383	96.92 400

pmmvs3		90.00 390	88.90 400	93.32 375	94.20 440	85.34 381	91.25 421	92.56 413	78.59 447	93.82 375	95.17 379	67.36 439	98.69 382	89.08 373	98.03 350	95.92 425

MonoMVSNet		93.30 343	93.96 320	91.33 418	94.14 441	81.33 425	97.68 93	96.69 346	95.38 203	96.32 294	98.42 137	84.12 367	96.76 444	90.78 337	92.12 445	95.89 426

tpmrst		90.31 386	90.61 384	89.41 429	94.06 442	72.37 460	95.06 297	93.69 394	88.01 387	92.32 416	96.86 310	77.45 400	98.82 366	91.04 327	87.01 454	97.04 397

mvsany_test1		93.47 338	93.03 335	94.79 327	94.05 443	92.12 235	90.82 429	90.01 442	85.02 420	97.26 224	98.28 164	93.57 227	97.03 437	92.51 302	95.75 425	95.23 437

test0.0.03 1		90.11 387	89.21 395	92.83 394	93.89 444	86.87 360	91.74 409	88.74 446	92.02 324	94.71 353	91.14 438	73.92 419	94.48 454	83.75 427	92.94 441	97.16 394

JIA-IIPM		91.79 371	90.69 382	95.11 307	93.80 445	90.98 264	94.16 333	91.78 420	96.38 139	90.30 432	99.30 32	72.02 428	98.90 359	88.28 384	90.17 449	95.45 435

miper_enhance_ethall		93.14 347	92.78 344	94.20 358	93.65 446	85.29 384	89.97 437	97.85 293	85.05 418	96.15 309	94.56 391	85.74 350	99.14 326	93.74 276	98.34 337	98.17 332

TESTMET0.1,1		87.20 420	86.57 420	89.07 431	93.62 447	72.84 459	89.89 438	87.01 451	85.46 414	89.12 443	90.20 444	56.00 455	97.72 431	90.91 332	96.92 391	96.64 413

CMPMVS	73.10 23	92.74 352	91.39 366	96.77 209	93.57 448	94.67 142	94.21 331	97.67 304	80.36 442	93.61 385	96.60 328	82.85 376	97.35 434	84.86 419	98.78 297	98.29 320
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
E-PMN		89.52 399	89.78 391	88.73 432	93.14 449	77.61 443	83.26 455	92.02 417	94.82 227	93.71 380	93.11 407	75.31 413	96.81 441	85.81 407	96.81 398	91.77 452

PMMVS		92.39 356	91.08 373	96.30 246	93.12 450	92.81 212	90.58 432	95.96 357	79.17 446	91.85 420	92.27 425	90.29 301	98.66 387	89.85 362	96.68 404	97.43 386

EMVS		89.06 402	89.22 394	88.61 433	93.00 451	77.34 445	82.91 456	90.92 429	94.64 235	92.63 412	91.81 431	76.30 408	97.02 438	83.83 425	96.90 393	91.48 453

dp		88.08 412	88.05 406	88.16 437	92.85 452	68.81 464	94.17 332	92.88 406	85.47 413	91.38 424	96.14 353	68.87 437	98.81 368	86.88 402	83.80 457	96.87 403

gg-mvs-nofinetune		88.28 411	86.96 417	92.23 408	92.84 453	84.44 399	98.19 55	74.60 462	99.08 17	87.01 452	99.47 16	56.93 450	98.23 419	78.91 442	95.61 426	94.01 444

tpmvs		90.79 384	90.87 377	90.57 423	92.75 454	76.30 449	95.79 237	93.64 398	91.04 346	91.91 419	96.26 346	77.19 404	98.86 364	89.38 369	89.85 450	96.56 416

EPMVS		89.26 400	88.55 402	91.39 417	92.36 455	79.11 436	95.65 249	79.86 459	88.60 379	93.12 399	96.53 332	70.73 433	98.10 424	90.75 339	89.32 451	96.98 398

gm-plane-assit					91.79 456	71.40 462			81.67 434		90.11 446		98.99 350	84.86 419

GG-mvs-BLEND				90.60 422	91.00 457	84.21 404	98.23 49	72.63 465		82.76 456	84.11 457	56.14 453	96.79 442	72.20 454	92.09 446	90.78 454

DeepMVS_CX				77.17 441	90.94 458	85.28 385		74.08 464	52.51 460	80.87 460	88.03 452	75.25 414	70.63 462	59.23 460	84.94 456	75.62 456

UWE-MVS-28		83.78 424	82.36 427	88.03 438	90.72 459	71.58 461	93.64 357	77.87 460	87.62 391	85.91 454	92.89 415	59.94 444	95.99 449	56.06 461	96.56 407	96.52 417

EPNet_dtu		91.39 377	90.75 380	93.31 376	90.48 460	82.61 414	94.80 308	92.88 406	93.39 284	81.74 458	94.90 387	81.36 382	99.11 333	88.28 384	98.87 287	98.21 327
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MVStest1		91.89 369	91.45 364	93.21 381	89.01 461	84.87 392	95.82 236	95.05 380	91.50 336	98.75 89	99.19 42	57.56 448	95.11 450	97.78 70	98.37 336	99.64 42

KD-MVS_2432*1600		88.93 403	87.74 408	92.49 401	88.04 462	81.99 418	89.63 443	95.62 365	91.35 340	95.06 344	93.11 407	56.58 451	98.63 389	85.19 415	95.07 429	96.85 405

miper_refine_blended		88.93 403	87.74 408	92.49 401	88.04 462	81.99 418	89.63 443	95.62 365	91.35 340	95.06 344	93.11 407	56.58 451	98.63 389	85.19 415	95.07 429	96.85 405

EPNet		93.72 330	92.62 349	97.03 188	87.61 464	92.25 228	96.27 190	91.28 426	96.74 120	87.65 449	97.39 268	85.00 359	99.64 169	92.14 306	99.48 175	99.20 172
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		63.43 427	63.37 430	63.60 443	83.91 465	53.17 467	85.14 451	43.40 469	77.91 451	80.96 459	79.17 459	36.36 467	77.10 461	37.88 462	45.63 461	60.54 458

kuosan		54.81 429	54.94 432	54.42 444	74.43 466	50.03 468	84.98 452	44.27 468	61.80 459	62.49 463	70.43 460	35.16 468	58.04 463	19.30 463	41.61 462	55.19 459

test_method		66.88 426	66.13 429	69.11 442	62.68 467	25.73 470	49.76 458	96.04 354	14.32 462	64.27 462	91.69 433	73.45 424	88.05 459	76.06 448	66.94 459	93.54 445

tmp_tt		57.23 428	62.50 431	41.44 445	34.77 468	49.21 469	83.93 453	60.22 467	15.31 461	71.11 461	79.37 458	70.09 435	44.86 464	64.76 457	82.93 458	30.25 460

test123		12.59 431	15.49 434	3.87 446	6.07 469	2.55 471	90.75 430	2.59 471	2.52 464	5.20 466	13.02 463	4.96 469	1.85 466	5.20 464	9.09 463	7.23 461

testmvs		12.33 432	15.23 435	3.64 447	5.77 470	2.23 472	88.99 445	3.62 470	2.30 465	5.29 465	13.09 462	4.52 470	1.95 465	5.16 465	8.32 464	6.75 462

mmdepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

eth-test2					0.00 471

eth-test					0.00 471

uanet_test		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

cdsmvs_eth3d_5k		24.22 430	32.30 433	0.00 448	0.00 471	0.00 473	0.00 459	98.10 277	0.00 466	0.00 467	95.06 382	97.54 44	0.00 467	0.00 466	0.00 465	0.00 463

pcd_1.5k_mvsjas		7.98 433	10.65 436	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	95.82 145	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

ab-mvs-re		7.91 434	10.55 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	94.94 384	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.00 435	0.00 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.00 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						79.32 434								85.41 413

PC_three_1452									87.24 394	98.37 126	97.44 261	97.00 76	96.78 443	92.01 307	99.25 240	99.21 169

test_241102_TWO								98.83 161	96.11 153	98.62 98	98.24 171	96.92 85	99.72 105	95.44 185	99.49 171	99.49 93

test_0728_THIRD									96.62 123	98.40 123	98.28 164	97.10 64	99.71 121	95.70 161	99.62 112	99.58 48

GSMVS																98.06 342

sam_mvs1												77.80 397				98.06 342

sam_mvs												77.38 401

MTGPA								98.73 187

test_post1							94.98 302				10.37 465	76.21 409	99.04 344	89.47 367

test_post											10.87 464	76.83 405	99.07 340

patchmatchnet-post											96.84 312	77.36 402	99.42 247

MTMP							96.55 171	74.60 462

test9_res														91.29 321	98.89 286	99.00 214

agg_prior2														90.34 355	98.90 283	99.10 202

test_prior4						95.38 113	93.61 360

test_prior2							93.33 369		94.21 255	94.02 372	96.25 347	93.64 226		91.90 310	98.96 275

旧先验2							93.35 368		77.95 450	95.77 326			98.67 386	90.74 342

新几何2							93.43 364

无先验							93.20 373	97.91 289	80.78 439				99.40 258	87.71 389		97.94 354

原ACMM2							92.82 379

testdata2													99.46 235	87.84 387

segment_acmp												95.34 168

testdata1							92.77 380		93.78 269

plane_prior5								98.75 184					99.46 235	92.59 300	99.20 245	99.28 154

plane_prior4											96.77 318

plane_prior3						94.51 149			95.29 207	96.16 307

plane_prior2							96.50 173		96.36 141

plane_prior						94.29 159	95.42 264		94.31 253						98.93 281

n2								0.00 472

nn								0.00 472

door-mid								98.17 267

test11								98.08 279

door								97.81 298

HQP5-MVS						92.47 222

BP-MVS														90.51 350

HQP4-MVS										92.87 403			99.23 314			99.06 207

HQP3-MVS								98.43 231							98.74 305

HQP2-MVS												90.33 297

MDTV_nov1_ep13_2view						57.28 466	94.89 305		80.59 440	94.02 372		78.66 394		85.50 412		97.82 362

ACMMP++_ref															99.52 159

ACMMP++															99.55 145

Test By Simon												94.51 201

High-resolution multi-view benchmark