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		99.43 1	99.49 1	99.24 2	99.95 1	98.13 2	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 2	97.58 2	99.94 1	99.85 2

LTVRE_ROB	93.87 1	97.93 3	98.16 2	97.26 30	98.81 27	93.86 35	99.07 2	98.98 9	97.01 15	98.92 5	98.78 16	95.22 42	98.61 176	96.85 8	99.77 9	99.31 30
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
TDRefinement		97.68 4	97.60 5	97.93 3	99.02 12	95.95 9	98.61 3	98.81 11	97.41 11	97.28 59	98.46 33	94.62 66	98.84 134	94.64 45	99.53 37	98.99 59

DVP-MVS++		95.93 56	96.34 38	94.70 115	96.54 188	86.66 159	98.45 4	98.22 47	93.26 78	97.54 43	97.36 106	93.12 101	99.38 58	93.88 62	98.68 165	98.04 170

FOURS1					99.21 3	94.68 16	98.45 4	98.81 11	97.73 7	98.27 21

UA-Net		97.35 5	97.24 12	97.69 6	98.22 75	93.87 34	98.42 6	98.19 50	96.95 16	95.46 155	99.23 6	93.45 88	99.57 15	95.34 37	99.89 2	99.63 12

OurMVSNet-221017-0		96.80 16	96.75 21	96.96 39	99.03 11	91.85 61	97.98 7	98.01 85	94.15 58	98.93 4	99.07 7	88.07 203	99.57 15	95.86 23	99.69 14	99.46 20

UniMVSNet_ETH3D		97.13 9	97.72 4	95.35 86	99.51 2	87.38 138	97.70 8	97.54 129	98.16 3	98.94 3	99.33 3	97.84 4	99.08 100	90.73 158	99.73 13	99.59 15

tt0805		95.42 80	95.93 63	93.86 156	98.75 31	88.47 120	97.68 9	94.29 287	96.48 24	95.38 158	93.63 304	94.89 59	97.94 249	95.38 35	96.92 289	95.17 332

HPM-MVS		96.81 15	96.62 26	97.36 27	98.89 20	93.53 42	97.51 10	98.44 21	92.35 93	95.95 127	96.41 179	96.71 8	99.42 36	93.99 61	99.36 59	99.13 43
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPP-MVSNet		93.91 151	93.68 161	94.59 125	98.08 83	85.55 189	97.44 11	94.03 292	94.22 57	94.94 186	96.19 199	82.07 280	99.57 15	87.28 246	98.89 131	98.65 110

mvs5depth		95.28 88	95.82 72	93.66 165	96.42 199	83.08 228	97.35 12	99.28 3	96.44 26	96.20 117	99.65 2	84.10 258	98.01 241	94.06 58	98.93 127	99.87 1

LS3D		96.11 51	95.83 70	96.95 40	94.75 297	94.20 23	97.34 13	97.98 88	97.31 12	95.32 163	96.77 155	93.08 103	99.20 87	91.79 133	98.16 219	97.44 233

HPM-MVS_fast		97.01 10	96.89 18	97.39 25	99.12 8	93.92 32	97.16 14	98.17 56	93.11 80	96.48 98	97.36 106	96.92 6	99.34 65	94.31 53	99.38 58	98.92 75

MVSFormer		92.18 207	92.23 199	92.04 236	94.74 298	80.06 274	97.15 15	97.37 142	88.98 187	88.83 344	92.79 326	77.02 323	99.60 10	96.41 15	96.75 296	96.46 281

test_djsdf		96.62 27	96.49 30	97.01 36	98.55 44	91.77 63	97.15 15	97.37 142	88.98 187	98.26 24	98.86 12	93.35 93	99.60 10	96.41 15	99.45 46	99.66 9

IS-MVSNet		94.49 122	94.35 138	94.92 105	98.25 73	86.46 164	97.13 17	94.31 286	96.24 31	96.28 111	96.36 187	82.88 268	99.35 62	88.19 226	99.52 39	98.96 67

Anonymous20231211		96.60 29	97.13 16	95.00 103	97.46 132	86.35 169	97.11 18	98.24 43	97.58 9	98.72 9	98.97 9	93.15 100	99.15 91	93.18 94	99.74 12	99.50 19

anonymousdsp		96.74 21	96.42 33	97.68 8	98.00 92	94.03 29	96.97 19	97.61 121	87.68 219	98.45 19	98.77 17	94.20 77	99.50 22	96.70 10	99.40 56	99.53 17

ACMMP		96.61 28	96.34 38	97.43 22	98.61 37	93.88 33	96.95 20	98.18 52	92.26 96	96.33 104	96.84 153	95.10 48	99.40 49	93.47 79	99.33 66	99.02 56
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
APDe-MVS		96.46 35	96.64 25	95.93 64	97.68 118	89.38 98	96.90 21	98.41 24	92.52 88	97.43 50	97.92 62	95.11 47	99.50 22	94.45 49	99.30 73	98.92 75
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EGC-MVSNET		80.97 380	75.73 398	96.67 46	98.85 23	94.55 19	96.83 22	96.60 204	2.44 436	5.32 437	98.25 40	92.24 122	98.02 240	91.85 131	99.21 91	97.45 231

v7n		96.82 13	97.31 11	95.33 88	98.54 46	86.81 153	96.83 22	98.07 73	96.59 23	98.46 18	98.43 35	92.91 109	99.52 20	96.25 18	99.76 10	99.65 11

CP-MVS		96.44 38	96.08 53	97.54 15	98.29 68	94.62 18	96.80 24	98.08 70	92.67 86	95.08 181	96.39 184	94.77 62	99.42 36	93.17 95	99.44 49	98.58 122

COLMAP_ROB	91.06 5	96.75 20	96.62 26	97.13 32	98.38 61	94.31 21	96.79 25	98.32 33	96.69 19	96.86 80	97.56 87	95.48 27	98.77 151	90.11 182	99.44 49	98.31 147
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WR-MVS_H		96.60 29	97.05 17	95.24 94	99.02 12	86.44 165	96.78 26	98.08 70	97.42 10	98.48 17	97.86 67	91.76 136	99.63 8	94.23 55	99.84 3	99.66 9

FE-MVS		89.06 280	88.29 288	91.36 258	94.78 295	79.57 289	96.77 27	90.99 345	84.87 279	92.96 257	96.29 191	60.69 402	98.80 144	80.18 332	97.11 280	95.71 316

CS-MVS		95.77 64	95.58 81	96.37 54	96.84 164	91.72 65	96.73 28	99.06 8	94.23 56	92.48 272	94.79 264	93.56 85	99.49 28	93.47 79	99.05 108	97.89 192

pmmvs6		96.80 16	97.36 10	95.15 100	99.12 8	87.82 132	96.68 29	97.86 99	96.10 33	98.14 28	99.28 5	97.94 3	98.21 217	91.38 147	99.69 14	99.42 21

mvsmamba		90.24 252	89.43 266	92.64 210	95.52 273	82.36 241	96.64 30	92.29 327	81.77 316	92.14 288	96.28 193	70.59 354	99.10 99	84.44 289	95.22 337	96.47 280

3Dnovator	92.54 3	94.80 108	94.90 109	94.47 132	95.47 275	87.06 146	96.63 31	97.28 156	91.82 117	94.34 206	97.41 100	90.60 167	98.65 173	92.47 116	98.11 224	97.70 214

PS-CasMVS		96.69 24	97.43 6	94.49 131	99.13 6	84.09 211	96.61 32	97.97 90	97.91 6	98.64 14	98.13 43	95.24 40	99.65 5	93.39 86	99.84 3	99.72 4

mvs_tets		96.83 12	96.71 22	97.17 31	98.83 24	92.51 52	96.58 33	97.61 121	87.57 221	98.80 8	98.90 11	96.50 9	99.59 14	96.15 19	99.47 42	99.40 24

PEN-MVS		96.69 24	97.39 9	94.61 121	99.16 4	84.50 201	96.54 34	98.05 77	98.06 5	98.64 14	98.25 40	95.01 53	99.65 5	92.95 103	99.83 5	99.68 7

MVSMamba_PlusPlus		94.82 107	95.89 65	91.62 249	97.82 104	78.88 304	96.52 35	97.60 123	97.14 14	94.23 207	98.48 32	87.01 223	99.71 3	95.43 33	98.80 148	96.28 289

DTE-MVSNet		96.74 21	97.43 6	94.67 118	99.13 6	84.68 200	96.51 36	97.94 96	98.14 4	98.67 13	98.32 37	95.04 50	99.69 4	93.27 91	99.82 7	99.62 13

XVS		96.49 33	96.18 46	97.44 20	98.56 41	93.99 30	96.50 37	97.95 93	94.58 50	94.38 204	96.49 173	94.56 69	99.39 52	93.57 72	99.05 108	98.93 71

X-MVStestdata		90.70 234	88.45 283	97.44 20	98.56 41	93.99 30	96.50 37	97.95 93	94.58 50	94.38 204	26.89 434	94.56 69	99.39 52	93.57 72	99.05 108	98.93 71

mmtdpeth		95.82 62	96.02 58	95.23 95	96.91 158	88.62 113	96.49 39	99.26 4	95.07 44	93.41 232	99.29 4	90.25 173	97.27 301	94.49 47	99.01 115	99.80 3

EC-MVSNet		95.44 76	95.62 79	94.89 106	96.93 157	87.69 134	96.48 40	99.14 7	93.93 63	92.77 263	94.52 276	93.95 82	99.49 28	93.62 71	99.22 90	97.51 228

mPP-MVS		96.46 35	96.05 55	97.69 6	98.62 35	94.65 17	96.45 41	97.74 112	92.59 87	95.47 153	96.68 165	94.50 71	99.42 36	93.10 97	99.26 83	98.99 59

QAPM		92.88 182	92.77 184	93.22 186	95.82 253	83.31 220	96.45 41	97.35 148	83.91 289	93.75 223	96.77 155	89.25 189	98.88 127	84.56 287	97.02 283	97.49 229

jajsoiax		96.59 31	96.42 33	97.12 33	98.76 30	92.49 53	96.44 43	97.42 139	86.96 233	98.71 11	98.72 19	95.36 34	99.56 18	95.92 21	99.45 46	99.32 29

Gipuma		95.31 87	95.80 73	93.81 159	97.99 95	90.91 74	96.42 44	97.95 93	96.69 19	91.78 294	98.85 14	91.77 134	95.49 364	91.72 135	99.08 104	95.02 341
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MSP-MVS		95.34 83	94.63 127	97.48 18	98.67 32	94.05 27	96.41 45	98.18 52	91.26 139	95.12 177	95.15 246	86.60 233	99.50 22	93.43 85	96.81 293	98.89 78
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
SR-MVS-dyc-post		96.84 11	96.60 28	97.56 14	98.07 84	95.27 10	96.37 46	98.12 63	95.66 39	97.00 73	97.03 138	94.85 60	99.42 36	93.49 76	98.84 138	98.00 175

RE-MVS-def			96.66 23		98.07 84	95.27 10	96.37 46	98.12 63	95.66 39	97.00 73	97.03 138	95.40 31		93.49 76	98.84 138	98.00 175

TSAR-MVS + MP.		94.96 101	94.75 117	95.57 80	98.86 22	88.69 110	96.37 46	96.81 191	85.23 269	94.75 194	97.12 130	91.85 131	99.40 49	93.45 81	98.33 202	98.62 119
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		95.32 84	95.10 104	95.96 60	96.86 162	90.75 78	96.33 49	99.20 5	93.99 60	91.03 307	93.73 302	93.52 87	99.55 19	91.81 132	99.45 46	97.58 222

ACMH	88.36 12	96.59 31	97.43 6	94.07 145	98.56 41	85.33 193	96.33 49	98.30 36	94.66 49	98.72 9	98.30 38	97.51 5	98.00 243	94.87 42	99.59 27	98.86 81
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
region2R		96.41 40	96.09 51	97.38 26	98.62 35	93.81 39	96.32 51	97.96 91	92.26 96	95.28 167	96.57 171	95.02 52	99.41 42	93.63 70	99.11 102	98.94 69

testf1		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 31	94.96 45	97.30 57	97.93 57	96.05 16	97.90 250	89.32 199	99.23 87	98.19 157

APD_test2		96.77 18	96.49 30	97.60 10	99.01 14	96.70 4	96.31 52	98.33 31	94.96 45	97.30 57	97.93 57	96.05 16	97.90 250	89.32 199	99.23 87	98.19 157

APD-MVS_3200maxsize		96.82 13	96.65 24	97.32 29	97.95 96	93.82 37	96.31 52	98.25 40	95.51 41	96.99 75	97.05 137	95.63 23	99.39 52	93.31 88	98.88 133	98.75 95

CP-MVSNet		96.19 49	96.80 20	94.38 136	98.99 16	83.82 214	96.31 52	97.53 131	97.60 8	98.34 20	97.52 92	91.98 129	99.63 8	93.08 99	99.81 8	99.70 5

HFP-MVS		96.39 42	96.17 48	97.04 35	98.51 49	93.37 43	96.30 56	97.98 88	92.35 93	95.63 145	96.47 174	95.37 32	99.27 80	93.78 66	99.14 100	98.48 132

ACMMPR		96.46 35	96.14 49	97.41 24	98.60 38	93.82 37	96.30 56	97.96 91	92.35 93	95.57 148	96.61 169	94.93 58	99.41 42	93.78 66	99.15 99	99.00 57

3Dnovator+	92.74 2	95.86 61	95.77 74	96.13 56	96.81 167	90.79 77	96.30 56	97.82 104	96.13 32	94.74 195	97.23 119	91.33 144	99.16 90	93.25 92	98.30 205	98.46 133

MIMVSNet1		95.52 73	95.45 85	95.72 75	99.14 5	89.02 105	96.23 59	96.87 187	93.73 67	97.87 31	98.49 31	90.73 164	99.05 105	86.43 262	99.60 25	99.10 50

balanced_conf03		93.45 163	94.17 145	91.28 263	95.81 255	78.40 311	96.20 60	97.48 136	88.56 199	95.29 166	97.20 124	85.56 247	99.21 84	92.52 115	98.91 130	96.24 292

test2506		85.42 340	84.57 343	87.96 343	97.81 105	66.53 404	96.14 61	56.35 437	89.04 185	93.55 229	98.10 44	42.88 434	98.68 168	88.09 230	99.18 95	98.67 108

SR-MVS		96.70 23	96.42 33	97.54 15	98.05 86	94.69 15	96.13 62	98.07 73	95.17 43	96.82 84	96.73 162	95.09 49	99.43 35	92.99 102	98.71 161	98.50 129

mamv4		98.21 2	97.86 3	99.26 1	98.24 74	99.36 1	96.10 63	99.32 2	98.75 2	99.58 2	98.70 20	91.78 133	99.88 1	98.60 1	99.67 20	98.54 125

MP-MVS		96.14 50	95.68 77	97.51 17	98.81 27	94.06 25	96.10 63	97.78 110	92.73 83	93.48 230	96.72 163	94.23 76	99.42 36	91.99 126	99.29 76	99.05 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
ZNCC-MVS		96.42 39	96.20 45	97.07 34	98.80 29	92.79 50	96.08 65	98.16 59	91.74 122	95.34 162	96.36 187	95.68 21	99.44 32	94.41 51	99.28 81	98.97 65

FA-MVS(test-final)		91.81 212	91.85 210	91.68 247	94.95 288	79.99 278	96.00 66	93.44 305	87.80 214	94.02 216	97.29 114	77.60 314	98.45 196	88.04 232	97.49 265	96.61 272

GBi-Net		93.21 172	92.96 179	93.97 148	95.40 277	84.29 204	95.99 67	96.56 208	88.63 195	95.10 178	98.53 28	81.31 287	98.98 113	86.74 252	98.38 196	98.65 110

test1		93.21 172	92.96 179	93.97 148	95.40 277	84.29 204	95.99 67	96.56 208	88.63 195	95.10 178	98.53 28	81.31 287	98.98 113	86.74 252	98.38 196	98.65 110

FMVSNet1		94.84 105	95.13 102	93.97 148	97.60 122	84.29 204	95.99 67	96.56 208	92.38 90	97.03 72	98.53 28	90.12 177	98.98 113	88.78 218	99.16 98	98.65 110

RPSCF		95.58 72	94.89 110	97.62 9	97.58 124	96.30 8	95.97 70	97.53 131	92.42 89	93.41 232	97.78 69	91.21 149	97.77 269	91.06 150	97.06 281	98.80 89

SixPastTwentyTwo		94.91 102	95.21 99	93.98 147	98.52 48	83.19 225	95.93 71	94.84 273	94.86 48	98.49 16	98.74 18	81.45 285	99.60 10	94.69 44	99.39 57	99.15 41

ambc				92.98 192	96.88 160	83.01 230	95.92 72	96.38 218		96.41 101	97.48 98	88.26 199	97.80 264	89.96 187	98.93 127	98.12 164

FC-MVSNet-test		95.32 84	95.88 66	93.62 167	98.49 56	81.77 248	95.90 73	98.32 33	93.93 63	97.53 45	97.56 87	88.48 194	99.40 49	92.91 104	99.83 5	99.68 7

reproduce_model		97.35 5	97.24 12	97.70 5	98.44 58	95.08 12	95.88 74	98.50 18	96.62 22	98.27 21	97.93 57	94.57 68	99.50 22	95.57 28	99.35 60	98.52 128

MTAPA		96.65 26	96.38 37	97.47 19	98.95 18	94.05 27	95.88 74	97.62 119	94.46 54	96.29 109	96.94 144	93.56 85	99.37 60	94.29 54	99.42 51	98.99 59

CPTT-MVS		94.74 109	94.12 147	96.60 47	98.15 79	93.01 46	95.84 76	97.66 116	89.21 184	93.28 240	95.46 235	88.89 191	98.98 113	89.80 189	98.82 144	97.80 205

ab-mvs		92.40 199	92.62 191	91.74 243	97.02 151	81.65 252	95.84 76	95.50 254	86.95 234	92.95 258	97.56 87	90.70 165	97.50 286	79.63 340	97.43 269	96.06 300

nrg030		96.32 44	96.55 29	95.62 78	97.83 103	88.55 118	95.77 78	98.29 39	92.68 84	98.03 30	97.91 64	95.13 45	98.95 120	93.85 64	99.49 41	99.36 27

ECVR-MVS		90.12 256	90.16 251	90.00 306	97.81 105	72.68 375	95.76 79	78.54 426	89.04 185	95.36 161	98.10 44	70.51 355	98.64 174	87.10 248	99.18 95	98.67 108

SteuartSystems-ACMMP		96.40 41	96.30 40	96.71 44	98.63 34	91.96 59	95.70 80	98.01 85	93.34 77	96.64 92	96.57 171	94.99 54	99.36 61	93.48 78	99.34 64	98.82 85
Skip Steuart: Steuart Systems R&D Blog.
OpenMVS	89.45 8	92.27 205	92.13 203	92.68 209	94.53 306	84.10 210	95.70 80	97.03 173	82.44 310	91.14 306	96.42 178	88.47 195	98.38 202	85.95 267	97.47 267	95.55 325

GST-MVS		96.24 47	95.99 59	97.00 37	98.65 33	92.71 51	95.69 82	98.01 85	92.08 103	95.74 140	96.28 193	95.22 42	99.42 36	93.17 95	99.06 105	98.88 80

ACMH+	88.43 11	96.48 34	96.82 19	95.47 83	98.54 46	89.06 104	95.65 83	98.61 15	96.10 33	98.16 27	97.52 92	96.90 7	98.62 175	90.30 173	99.60 25	98.72 100

APD_test1		95.91 57	95.42 88	97.36 27	98.82 25	96.62 7	95.64 84	97.64 117	93.38 76	95.89 132	97.23 119	93.35 93	97.66 279	88.20 225	98.66 169	97.79 206

sasdasda		94.59 116	94.69 121	94.30 137	95.60 269	87.03 147	95.59 85	98.24 43	91.56 128	95.21 173	92.04 344	94.95 55	98.66 170	91.45 144	97.57 262	97.20 248

test1111		90.39 245	90.61 242	89.74 310	98.04 89	71.50 381	95.59 85	79.72 423	89.41 177	95.94 128	98.14 42	70.79 353	98.81 141	88.52 223	99.32 70	98.90 77

canonicalmvs		94.59 116	94.69 121	94.30 137	95.60 269	87.03 147	95.59 85	98.24 43	91.56 128	95.21 173	92.04 344	94.95 55	98.66 170	91.45 144	97.57 262	97.20 248

SF-MVS		95.88 60	95.88 66	95.87 70	98.12 80	89.65 90	95.58 88	98.56 17	91.84 114	96.36 103	96.68 165	94.37 75	99.32 71	92.41 117	99.05 108	98.64 115

reproduce-ours		97.28 7	97.19 14	97.57 12	98.37 63	94.84 13	95.57 89	98.40 25	96.36 29	98.18 25	97.78 69	95.47 28	99.50 22	95.26 38	99.33 66	98.36 140

our_new_method		97.28 7	97.19 14	97.57 12	98.37 63	94.84 13	95.57 89	98.40 25	96.36 29	98.18 25	97.78 69	95.47 28	99.50 22	95.26 38	99.33 66	98.36 140

PS-MVSNAJss		96.01 54	96.04 56	95.89 69	98.82 25	88.51 119	95.57 89	97.88 97	88.72 193	98.81 7	98.86 12	90.77 160	99.60 10	95.43 33	99.53 37	99.57 16

PMVS	87.21 14	94.97 100	95.33 94	93.91 153	98.97 17	97.16 3	95.54 92	95.85 239	96.47 25	93.40 235	97.46 99	95.31 37	95.47 365	86.18 266	98.78 152	89.11 412
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VDDNet		94.03 146	94.27 142	93.31 182	98.87 21	82.36 241	95.51 93	91.78 339	97.19 13	96.32 106	98.60 25	84.24 256	98.75 152	87.09 249	98.83 143	98.81 87

pm-mvs1		95.43 77	95.94 61	93.93 152	98.38 61	85.08 196	95.46 94	97.12 168	91.84 114	97.28 59	98.46 33	95.30 38	97.71 276	90.17 180	99.42 51	98.99 59

RRT-MVS		92.28 203	93.01 178	90.07 302	94.06 317	73.01 371	95.36 95	97.88 97	92.24 98	95.16 175	97.52 92	78.51 308	99.29 74	90.55 163	95.83 319	97.92 188

Vis-MVSNet		95.50 74	95.48 84	95.56 81	98.11 81	89.40 97	95.35 96	98.22 47	92.36 92	94.11 209	98.07 46	92.02 127	99.44 32	93.38 87	97.67 257	97.85 198
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test0726					98.51 49	86.69 157	95.34 97	98.18 52	91.85 111	97.63 38	97.37 103	95.58 24

FIs		94.90 103	95.35 91	93.55 171	98.28 69	81.76 249	95.33 98	98.14 60	93.05 82	97.07 68	97.18 125	87.65 211	99.29 74	91.72 135	99.69 14	99.61 14

PGM-MVS		96.32 44	95.94 61	97.43 22	98.59 40	93.84 36	95.33 98	98.30 36	91.40 136	95.76 137	96.87 149	95.26 39	99.45 31	92.77 105	99.21 91	99.00 57

LPG-MVS_test		96.38 43	96.23 43	96.84 42	98.36 66	92.13 56	95.33 98	98.25 40	91.78 118	97.07 68	97.22 121	96.38 12	99.28 78	92.07 124	99.59 27	99.11 47

MonoMVSNet		88.46 296	89.28 267	85.98 372	90.52 391	70.07 390	95.31 101	94.81 276	88.38 202	93.47 231	96.13 203	73.21 342	95.07 374	82.61 304	89.12 411	92.81 392

AllTest		94.88 104	94.51 132	96.00 58	98.02 90	92.17 54	95.26 102	98.43 22	90.48 158	95.04 182	96.74 160	92.54 118	97.86 258	85.11 279	98.98 117	97.98 179

MGCFI-Net		94.44 124	94.67 125	93.75 161	95.56 271	85.47 190	95.25 103	98.24 43	91.53 130	95.04 182	92.21 339	94.94 57	98.54 186	91.56 142	97.66 258	97.24 246

SED-MVS		96.00 55	96.41 36	94.76 112	98.51 49	86.97 149	95.21 104	98.10 67	91.95 105	97.63 38	97.25 117	96.48 10	99.35 62	93.29 89	99.29 76	97.95 183

OPU-MVS				95.15 100	96.84 164	89.43 95	95.21 104				95.66 227	93.12 101	98.06 233	86.28 265	98.61 172	97.95 183

DVP-MVS		95.82 62	96.18 46	94.72 114	98.51 49	86.69 157	95.20 106	97.00 175	91.85 111	97.40 54	97.35 109	95.58 24	99.34 65	93.44 82	99.31 71	98.13 163
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				94.88 107	98.55 44	86.72 156	95.20 106	98.22 47					99.38 58	93.44 82	99.31 71	98.53 127

Anonymous20240529		95.50 74	95.83 70	94.50 129	97.33 138	85.93 179	95.19 108	96.77 195	96.64 21	97.61 41	98.05 47	93.23 97	98.79 145	88.60 222	99.04 113	98.78 91

SMA-MVS		95.77 64	95.54 82	96.47 53	98.27 70	91.19 70	95.09 109	97.79 109	86.48 240	97.42 52	97.51 96	94.47 74	99.29 74	93.55 74	99.29 76	98.93 71
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
NR-MVSNet		95.28 88	95.28 97	95.26 92	97.75 109	87.21 142	95.08 110	97.37 142	93.92 65	97.65 37	95.90 212	90.10 179	99.33 70	90.11 182	99.66 21	99.26 32

TransMVSNet (Re)		95.27 91	96.04 56	92.97 193	98.37 63	81.92 247	95.07 111	96.76 196	93.97 62	97.77 34	98.57 26	95.72 20	97.90 250	88.89 216	99.23 87	99.08 51

UGNet		93.08 175	92.50 194	94.79 111	93.87 322	87.99 128	95.07 111	94.26 289	90.64 154	87.33 373	97.67 79	86.89 228	98.49 190	88.10 229	98.71 161	97.91 189
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
tttt0517		89.81 267	88.90 277	92.55 219	97.00 152	79.73 286	95.03 113	83.65 405	89.88 169	95.30 164	94.79 264	53.64 413	99.39 52	91.99 126	98.79 151	98.54 125

LFMVS		91.33 225	91.16 228	91.82 240	96.27 217	79.36 293	95.01 114	85.61 392	96.04 36	94.82 191	97.06 136	72.03 349	98.46 195	84.96 282	98.70 163	97.65 218

CSCG		94.69 113	94.75 117	94.52 128	97.55 126	87.87 130	95.01 114	97.57 126	92.68 84	96.20 117	93.44 310	91.92 130	98.78 148	89.11 210	99.24 86	96.92 260

GG-mvs-BLEND				83.24 396	85.06 430	71.03 383	94.99 116	65.55 435		74.09 429	75.51 429	44.57 427	94.46 382	59.57 425	87.54 416	84.24 422

EU-MVSNet		87.39 318	86.71 323	89.44 314	93.40 329	76.11 343	94.93 117	90.00 353	57.17 429	95.71 143	97.37 103	64.77 383	97.68 278	92.67 110	94.37 357	94.52 357

KD-MVS_self_test		94.10 144	94.73 120	92.19 228	97.66 120	79.49 291	94.86 118	97.12 168	89.59 175	96.87 79	97.65 81	90.40 171	98.34 207	89.08 211	99.35 60	98.75 95

MTMP							94.82 119	54.62 438

PHI-MVS		94.34 131	93.80 155	95.95 61	95.65 265	91.67 66	94.82 119	97.86 99	87.86 213	93.04 253	94.16 287	91.58 138	98.78 148	90.27 175	98.96 124	97.41 234

gg-mvs-nofinetune		82.10 372	81.02 374	85.34 378	87.46 419	71.04 382	94.74 121	67.56 433	96.44 26	79.43 423	98.99 8	45.24 425	96.15 348	67.18 412	92.17 397	88.85 413

ACMM	88.83 9	96.30 46	96.07 54	96.97 38	98.39 60	92.95 48	94.74 121	98.03 82	90.82 149	97.15 65	96.85 150	96.25 14	99.00 112	93.10 97	99.33 66	98.95 68
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SD-MVS		95.19 93	95.73 75	93.55 171	96.62 182	88.88 109	94.67 123	98.05 77	91.26 139	97.25 61	96.40 180	95.42 30	94.36 385	92.72 109	99.19 93	97.40 237
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
API-MVS		91.52 221	91.61 214	91.26 264	94.16 312	86.26 171	94.66 124	94.82 274	91.17 142	92.13 289	91.08 358	90.03 182	97.06 316	79.09 347	97.35 273	90.45 410

v10		94.68 114	95.27 98	92.90 200	96.57 185	80.15 270	94.65 125	97.57 126	90.68 153	97.43 50	98.00 52	88.18 200	99.15 91	94.84 43	99.55 35	99.41 23

v8		94.65 115	95.29 96	92.74 206	96.65 177	79.77 285	94.59 126	97.17 163	91.86 110	97.47 49	97.93 57	88.16 201	99.08 100	94.32 52	99.47 42	99.38 25

APD-MVS		95.00 99	94.69 121	95.93 64	97.38 134	90.88 75	94.59 126	97.81 105	89.22 183	95.46 155	96.17 202	93.42 91	99.34 65	89.30 201	98.87 136	97.56 225
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
VPA-MVSNet		95.14 95	95.67 78	93.58 170	97.76 108	83.15 226	94.58 128	97.58 125	93.39 75	97.05 71	98.04 49	93.25 96	98.51 189	89.75 192	99.59 27	99.08 51

ACMMP_NAP		96.21 48	96.12 50	96.49 52	98.90 19	91.42 67	94.57 129	98.03 82	90.42 161	96.37 102	97.35 109	95.68 21	99.25 81	94.44 50	99.34 64	98.80 89

HQP_MVS		94.26 134	93.93 151	95.23 95	97.71 114	88.12 125	94.56 130	97.81 105	91.74 122	93.31 237	95.59 229	86.93 226	98.95 120	89.26 205	98.51 184	98.60 120

plane_prior2							94.56 130		91.74 122

tfpnnormal		94.27 133	94.87 111	92.48 221	97.71 114	80.88 265	94.55 132	95.41 258	93.70 68	96.67 91	97.72 75	91.40 143	98.18 221	87.45 242	99.18 95	98.36 140

XVG-ACMP-BASELINE		95.68 68	95.34 92	96.69 45	98.40 59	93.04 45	94.54 133	98.05 77	90.45 160	96.31 107	96.76 157	92.91 109	98.72 157	91.19 148	99.42 51	98.32 145

DP-MVS		95.62 69	95.84 69	94.97 104	97.16 146	88.62 113	94.54 133	97.64 117	96.94 17	96.58 96	97.32 113	93.07 104	98.72 157	90.45 165	98.84 138	97.57 223

MIMVSNet		87.13 326	86.54 327	88.89 325	96.05 237	76.11 343	94.39 135	88.51 360	81.37 320	88.27 359	96.75 159	72.38 346	95.52 362	65.71 415	95.47 328	95.03 340

K. test v3		93.37 165	93.27 175	93.66 165	98.05 86	82.62 237	94.35 136	86.62 379	96.05 35	97.51 46	98.85 14	76.59 330	99.65 5	93.21 93	98.20 217	98.73 99

Vis-MVSNet (Re-imp)		90.42 242	90.16 251	91.20 268	97.66 120	77.32 327	94.33 137	87.66 371	91.20 141	92.99 254	95.13 248	75.40 335	98.28 210	77.86 352	99.19 93	97.99 178

ANet_high		94.83 106	96.28 41	90.47 290	96.65 177	73.16 369	94.33 137	98.74 14	96.39 28	98.09 29	98.93 10	93.37 92	98.70 164	90.38 168	99.68 17	99.53 17

MM		94.41 126	94.14 146	95.22 97	95.84 251	87.21 142	94.31 139	90.92 347	94.48 53	92.80 261	97.52 92	85.27 248	99.49 28	96.58 14	99.57 33	98.97 65

test_fmvsmconf0.01_n		95.90 58	96.09 51	95.31 91	97.30 139	89.21 100	94.24 140	98.76 13	86.25 245	97.56 42	98.66 21	95.73 19	98.44 198	97.35 4	98.99 116	98.27 151

ACMP	88.15 13	95.71 67	95.43 87	96.54 49	98.17 78	91.73 64	94.24 140	98.08 70	89.46 176	96.61 94	96.47 174	95.85 18	99.12 96	90.45 165	99.56 34	98.77 94
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MAR-MVS		90.32 250	88.87 278	94.66 120	94.82 292	91.85 61	94.22 142	94.75 278	80.91 324	87.52 371	88.07 394	86.63 232	97.87 257	76.67 363	96.21 310	94.25 363
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
FMVSNet2		92.78 187	92.73 188	92.95 195	95.40 277	81.98 246	94.18 143	95.53 253	88.63 195	96.05 124	97.37 103	81.31 287	98.81 141	87.38 245	98.67 167	98.06 166

fmvsm_s_conf0.1_n_a		94.26 134	94.37 136	93.95 151	97.36 136	85.72 185	94.15 144	95.44 255	83.25 296	95.51 150	98.05 47	92.54 118	97.19 307	95.55 29	97.46 268	98.94 69

Anonymous20240521		92.86 185	93.57 166	90.74 284	96.57 185	75.50 350	94.15 144	95.60 245	89.38 178	95.90 131	97.90 66	80.39 294	97.96 247	92.60 113	99.68 17	98.75 95

GeoE		94.55 119	94.68 124	94.15 141	97.23 141	85.11 195	94.14 146	97.34 149	88.71 194	95.26 168	95.50 234	94.65 65	99.12 96	90.94 154	98.40 191	98.23 153

9.14			94.81 112		97.49 129		94.11 147	98.37 29	87.56 222	95.38 158	96.03 208	94.66 64	99.08 100	90.70 159	98.97 122

BP-MVS1		91.77 213	91.10 229	93.75 161	96.42 199	83.40 219	94.10 148	91.89 337	91.27 138	93.36 236	94.85 259	64.43 384	99.29 74	94.88 41	98.74 158	98.56 124

HPM-MVS++		95.02 98	94.39 134	96.91 41	97.88 100	93.58 41	94.09 149	96.99 177	91.05 144	92.40 277	95.22 245	91.03 156	99.25 81	92.11 121	98.69 164	97.90 190

HY-MVS	82.50 18	86.81 332	85.93 334	89.47 313	93.63 326	77.93 317	94.02 150	91.58 342	75.68 367	83.64 400	93.64 303	77.40 317	97.42 293	71.70 396	92.07 398	93.05 388

Effi-MVS+-dtu		93.90 152	92.60 192	97.77 4	94.74 298	96.67 6	94.00 151	95.41 258	89.94 167	91.93 293	92.13 342	90.12 177	98.97 117	87.68 239	97.48 266	97.67 217

Effi-MVS+		92.79 186	92.74 186	92.94 197	95.10 285	83.30 221	94.00 151	97.53 131	91.36 137	89.35 339	90.65 368	94.01 81	98.66 170	87.40 244	95.30 334	96.88 264

VDD-MVS		94.37 128	94.37 136	94.40 135	97.49 129	86.07 176	93.97 153	93.28 307	94.49 52	96.24 113	97.78 69	87.99 207	98.79 145	88.92 214	99.14 100	98.34 144

h-mvs33		92.89 181	91.99 206	95.58 79	96.97 153	90.55 80	93.94 154	94.01 295	89.23 181	93.95 218	96.19 199	76.88 326	99.14 93	91.02 151	95.71 321	97.04 256

EPNet		89.80 268	88.25 291	94.45 133	83.91 432	86.18 173	93.87 155	87.07 377	91.16 143	80.64 420	94.72 266	78.83 302	98.89 126	85.17 274	98.89 131	98.28 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_fmvs3		92.42 198	92.40 197	92.46 223	93.80 325	87.28 140	93.86 156	97.05 172	76.86 362	96.25 112	98.66 21	82.87 269	91.26 405	95.44 32	96.83 292	98.82 85

DeepC-MVS	91.39 4	95.43 77	95.33 94	95.71 76	97.67 119	90.17 84	93.86 156	98.02 84	87.35 223	96.22 115	97.99 54	94.48 73	99.05 105	92.73 108	99.68 17	97.93 186
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LCM-MVSNet-Re		94.20 140	94.58 129	93.04 190	95.91 247	83.13 227	93.79 158	99.19 6	92.00 104	98.84 6	98.04 49	93.64 84	99.02 110	81.28 321	98.54 180	96.96 259

TranMVSNet+NR-MVSNet		96.07 53	96.26 42	95.50 82	98.26 71	87.69 134	93.75 159	97.86 99	95.96 38	97.48 48	97.14 128	95.33 36	99.44 32	90.79 156	99.76 10	99.38 25

fmvsm_s_conf0.1_n		94.19 142	94.41 133	93.52 176	97.22 143	84.37 202	93.73 160	95.26 262	84.45 284	95.76 137	98.00 52	91.85 131	97.21 304	95.62 25	97.82 249	98.98 63

PAPM_NR		91.03 229	90.81 237	91.68 247	96.73 172	81.10 262	93.72 161	96.35 219	88.19 206	88.77 350	92.12 343	85.09 251	97.25 302	82.40 309	93.90 369	96.68 271

baseline		94.26 134	94.80 113	92.64 210	96.08 235	80.99 263	93.69 162	98.04 81	90.80 150	94.89 189	96.32 189	93.19 98	98.48 194	91.68 137	98.51 184	98.43 136

dcpmvs_2		93.96 149	95.01 107	90.82 282	97.60 122	74.04 364	93.68 163	98.85 10	89.80 171	97.82 32	97.01 141	91.14 154	99.21 84	90.56 162	98.59 175	99.19 38

GDP-MVS		91.56 219	90.83 236	93.77 160	96.34 208	83.65 216	93.66 164	98.12 63	87.32 225	92.98 256	94.71 267	63.58 390	99.30 73	92.61 112	98.14 221	98.35 143

fmvsm_s_conf0.5_n_a		94.02 147	94.08 149	93.84 157	96.72 173	85.73 184	93.65 165	95.23 263	83.30 294	95.13 176	97.56 87	92.22 123	97.17 308	95.51 30	97.41 270	98.64 115

F-COLMAP		92.28 203	91.06 230	95.95 61	97.52 127	91.90 60	93.53 166	97.18 162	83.98 288	88.70 352	94.04 290	88.41 197	98.55 185	80.17 333	95.99 314	97.39 238

test_fmvsmconf0.1_n		95.61 70	95.72 76	95.26 92	96.85 163	89.20 101	93.51 167	98.60 16	85.68 259	97.42 52	98.30 38	95.34 35	98.39 199	96.85 8	98.98 117	98.19 157

FMVSNet5		87.82 307	86.56 326	91.62 249	92.31 353	79.81 284	93.49 168	94.81 276	83.26 295	91.36 300	96.93 145	52.77 415	97.49 288	76.07 369	98.03 232	97.55 226

DPE-MVS		95.89 59	95.88 66	95.92 66	97.93 97	89.83 88	93.46 169	98.30 36	92.37 91	97.75 35	96.95 143	95.14 44	99.51 21	91.74 134	99.28 81	98.41 138
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
alignmvs		93.26 169	92.85 183	94.50 129	95.70 261	87.45 137	93.45 170	95.76 240	91.58 127	95.25 170	92.42 337	81.96 282	98.72 157	91.61 138	97.87 247	97.33 242

test_fmvsmvis_n_1920		95.08 97	95.40 89	94.13 143	96.66 176	87.75 133	93.44 171	98.49 20	85.57 263	98.27 21	97.11 131	94.11 80	97.75 272	96.26 17	98.72 159	96.89 262

114514_t		90.51 239	89.80 260	92.63 213	98.00 92	82.24 243	93.40 172	97.29 154	65.84 420	89.40 338	94.80 263	86.99 224	98.75 152	83.88 294	98.61 172	96.89 262

fmvsm_s_conf0.5_n		94.00 148	94.20 144	93.42 180	96.69 174	84.37 202	93.38 173	95.13 265	84.50 283	95.40 157	97.55 91	91.77 134	97.20 305	95.59 26	97.79 250	98.69 107

DeepC-MVS_fast	89.96 7	93.73 155	93.44 170	94.60 124	96.14 229	87.90 129	93.36 174	97.14 165	85.53 264	93.90 221	95.45 236	91.30 146	98.59 180	89.51 195	98.62 171	97.31 243
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS-pluss		96.08 52	95.92 64	96.57 48	99.06 10	91.21 69	93.25 175	98.32 33	87.89 212	96.86 80	97.38 102	95.55 26	99.39 52	95.47 31	99.47 42	99.11 47
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
test_0402		95.73 66	96.22 44	94.26 139	98.19 77	85.77 183	93.24 176	97.24 159	96.88 18	97.69 36	97.77 73	94.12 79	99.13 95	91.54 143	99.29 76	97.88 193

test_fmvsmconf_n		95.43 77	95.50 83	95.22 97	96.48 196	89.19 102	93.23 177	98.36 30	85.61 262	96.92 78	98.02 51	95.23 41	98.38 202	96.69 11	98.95 126	98.09 165

test_fmvsm_n_1920		94.72 110	94.74 119	94.67 118	96.30 214	88.62 113	93.19 178	98.07 73	85.63 261	97.08 67	97.35 109	90.86 157	97.66 279	95.70 24	98.48 187	97.74 212

sd_testset		93.94 150	94.39 134	92.61 216	97.93 97	83.24 222	93.17 179	95.04 267	93.65 72	95.51 150	98.63 23	94.49 72	95.89 357	81.72 316	99.35 60	98.70 104

fmvsm_s_conf0.5_n_3		95.20 92	95.95 60	92.94 197	96.60 183	82.18 244	93.13 180	98.39 27	91.44 134	97.16 64	97.68 77	93.03 106	97.82 261	97.54 3	98.63 170	98.81 87

MSLP-MVS++		93.25 171	93.88 152	91.37 257	96.34 208	82.81 233	93.11 181	97.74 112	89.37 179	94.08 211	95.29 244	90.40 171	96.35 345	90.35 170	98.25 210	94.96 342

baseline1		87.62 312	87.31 307	88.54 332	94.71 301	74.27 361	93.10 182	88.20 364	86.20 247	92.18 287	93.04 319	73.21 342	95.52 362	79.32 344	85.82 419	95.83 311

fmvsm_l_conf0.5_n_3		95.19 93	95.36 90	94.68 117	96.79 170	87.49 136	93.05 183	98.38 28	87.21 227	96.59 95	97.76 74	94.20 77	98.11 228	95.90 22	98.40 191	98.42 137

plane_prior						88.12 125	93.01 184		88.98 187						98.06 229

thres100view900		87.35 319	86.89 319	88.72 328	96.14 229	73.09 370	93.00 185	85.31 395	92.13 102	93.26 242	90.96 361	63.42 391	98.28 210	71.27 399	96.54 302	94.79 350

Patchmtry		90.11 257	89.92 257	90.66 286	90.35 395	77.00 331	92.96 186	92.81 314	90.25 164	94.74 195	96.93 145	67.11 366	97.52 285	85.17 274	98.98 117	97.46 230

LF4IMVS		92.72 189	92.02 205	94.84 109	95.65 265	91.99 58	92.92 187	96.60 204	85.08 275	92.44 275	93.62 305	86.80 229	96.35 345	86.81 251	98.25 210	96.18 295

UniMVSNet (Re)		95.32 84	95.15 101	95.80 72	97.79 107	88.91 107	92.91 188	98.07 73	93.46 74	96.31 107	95.97 211	90.14 176	99.34 65	92.11 121	99.64 23	99.16 40

TAPA-MVS	88.58 10	92.49 196	91.75 213	94.73 113	96.50 193	89.69 89	92.91 188	97.68 115	78.02 353	92.79 262	94.10 288	90.85 158	97.96 247	84.76 285	98.16 219	96.54 273
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MVS_0304		92.88 182	92.27 198	94.69 116	92.35 352	86.03 177	92.88 190	89.68 354	90.53 157	91.52 297	96.43 177	82.52 276	99.32 71	95.01 40	99.54 36	98.71 103

fmvsm_s_conf0.5_n_5		94.50 121	94.80 113	93.60 168	96.80 168	84.93 197	92.81 191	97.59 124	85.27 268	96.85 83	97.29 114	91.48 142	98.05 234	96.67 12	98.47 188	97.83 200

thisisatest0530		88.69 293	87.52 305	92.20 227	96.33 210	79.36 293	92.81 191	84.01 404	86.44 241	93.67 226	92.68 330	53.62 414	99.25 81	89.65 194	98.45 189	98.00 175

EIA-MVS		92.35 201	92.03 204	93.30 184	95.81 255	83.97 212	92.80 193	98.17 56	87.71 217	89.79 332	87.56 396	91.17 153	99.18 89	87.97 234	97.27 274	96.77 268

thres600view7		87.66 310	87.10 316	89.36 317	96.05 237	73.17 368	92.72 194	85.31 395	91.89 109	93.29 239	90.97 360	63.42 391	98.39 199	73.23 387	96.99 288	96.51 275

wuyk23d		87.83 306	90.79 238	78.96 409	90.46 394	88.63 112	92.72 194	90.67 350	91.65 126	98.68 12	97.64 82	96.06 15	77.53 431	59.84 424	99.41 55	70.73 429

fmvsm_s_conf0.5_n_6		94.14 143	94.54 131	92.95 195	96.51 192	82.74 235	92.71 196	98.13 61	86.56 239	96.44 99	96.85 150	88.51 193	98.05 234	96.03 20	99.09 103	98.06 166

test_fmvs2		90.62 238	90.40 248	91.29 262	91.93 368	85.46 191	92.70 197	96.48 214	74.44 377	94.91 188	97.59 85	75.52 334	90.57 408	93.44 82	96.56 301	97.84 199

V42		93.43 164	93.58 165	92.97 193	95.34 281	81.22 260	92.67 198	96.49 213	87.25 226	96.20 117	96.37 186	87.32 217	98.85 133	92.39 118	98.21 215	98.85 84

casdiffmvs_mvg		95.10 96	95.62 79	93.53 174	96.25 220	83.23 223	92.66 199	98.19 50	93.06 81	97.49 47	97.15 127	94.78 61	98.71 163	92.27 119	98.72 159	98.65 110
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
OPM-MVS		95.61 70	95.45 85	96.08 57	98.49 56	91.00 72	92.65 200	97.33 150	90.05 166	96.77 87	96.85 150	95.04 50	98.56 183	92.77 105	99.06 105	98.70 104
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n_8		94.70 112	95.34 92	92.78 205	96.77 171	81.50 256	92.64 201	98.50 18	91.51 133	97.22 62	97.93 57	88.07 203	98.45 196	96.62 13	98.80 148	98.39 139

test_vis1_n		89.01 283	89.01 273	89.03 322	92.57 347	82.46 240	92.62 202	96.06 231	73.02 388	90.40 318	95.77 223	74.86 336	89.68 414	90.78 157	94.98 342	94.95 343

fmvsm_s_conf0.5_n_4		94.26 134	94.58 129	93.31 182	96.40 201	82.73 236	92.59 203	97.41 140	86.60 237	96.33 104	97.07 134	89.91 183	98.07 232	96.88 7	98.01 235	99.13 43

DU-MVS		95.28 88	95.12 103	95.75 74	97.75 109	88.59 116	92.58 204	97.81 105	93.99 60	96.80 85	95.90 212	90.10 179	99.41 42	91.60 139	99.58 31	99.26 32

FMVSNet3		90.78 232	90.32 250	92.16 232	93.03 338	79.92 280	92.54 205	94.95 270	86.17 249	95.10 178	96.01 209	69.97 357	98.75 152	86.74 252	98.38 196	97.82 203

hse-mvs2		92.24 206	91.20 225	95.38 85	96.16 226	90.65 79	92.52 206	92.01 336	89.23 181	93.95 218	92.99 321	76.88 326	98.69 166	91.02 151	96.03 312	96.81 266

MVS_Test		92.57 195	93.29 172	90.40 293	93.53 328	75.85 346	92.52 206	96.96 178	88.73 192	92.35 281	96.70 164	90.77 160	98.37 206	92.53 114	95.49 327	96.99 258

CR-MVSNet		87.89 304	87.12 315	90.22 298	91.01 384	78.93 300	92.52 206	92.81 314	73.08 387	89.10 340	96.93 145	67.11 366	97.64 281	88.80 217	92.70 391	94.08 364

RPMNet		90.31 251	90.14 254	90.81 283	91.01 384	78.93 300	92.52 206	98.12 63	91.91 108	89.10 340	96.89 148	68.84 359	99.41 42	90.17 180	92.70 391	94.08 364

fmvsm_l_conf0.5_n		93.79 153	93.81 153	93.73 163	96.16 226	86.26 171	92.46 210	96.72 198	81.69 318	95.77 136	97.11 131	90.83 159	97.82 261	95.58 27	97.99 238	97.11 251

XVG-OURS-SEG-HR		95.38 81	95.00 108	96.51 50	98.10 82	94.07 24	92.46 210	98.13 61	90.69 152	93.75 223	96.25 197	98.03 2	97.02 317	92.08 123	95.55 325	98.45 134

EI-MVSNet-Vis-set		94.36 129	94.28 140	94.61 121	92.55 348	85.98 178	92.44 212	94.69 280	93.70 68	96.12 122	95.81 218	91.24 147	98.86 131	93.76 69	98.22 214	98.98 63

Anonymous202405211		92.58 193	92.50 194	92.83 203	96.55 187	83.22 224	92.43 213	91.64 341	94.10 59	95.59 147	96.64 167	81.88 284	97.50 286	85.12 278	98.52 182	97.77 208

AUN-MVS		90.05 261	88.30 287	95.32 90	96.09 234	90.52 81	92.42 214	92.05 335	82.08 314	88.45 356	92.86 323	65.76 376	98.69 166	88.91 215	96.07 311	96.75 270

EI-MVSNet-UG-set		94.35 130	94.27 142	94.59 125	92.46 351	85.87 181	92.42 214	94.69 280	93.67 71	96.13 121	95.84 216	91.20 150	98.86 131	93.78 66	98.23 212	99.03 55

NCCC		94.08 145	93.54 168	95.70 77	96.49 194	89.90 87	92.39 216	96.91 184	90.64 154	92.33 284	94.60 272	90.58 168	98.96 118	90.21 179	97.70 255	98.23 153

casdiffmvs		94.32 132	94.80 113	92.85 202	96.05 237	81.44 257	92.35 217	98.05 77	91.53 130	95.75 139	96.80 154	93.35 93	98.49 190	91.01 153	98.32 204	98.64 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ETV-MVS		92.99 178	92.74 186	93.72 164	95.86 250	86.30 170	92.33 218	97.84 102	91.70 125	92.81 260	86.17 406	92.22 123	99.19 88	88.03 233	97.73 252	95.66 320

fmvsm_l_conf0.5_n_a		93.59 159	93.63 162	93.49 178	96.10 233	85.66 187	92.32 219	96.57 207	81.32 321	95.63 145	97.14 128	90.19 174	97.73 275	95.37 36	98.03 232	97.07 252

EI-MVSNet		92.99 178	93.26 176	92.19 228	92.12 361	79.21 298	92.32 219	94.67 282	91.77 120	95.24 171	95.85 214	87.14 221	98.49 190	91.99 126	98.26 208	98.86 81

CVMVSNet		85.16 342	84.72 340	86.48 364	92.12 361	70.19 386	92.32 219	88.17 365	56.15 430	90.64 314	95.85 214	67.97 364	96.69 332	88.78 218	90.52 407	92.56 395

test_fmvs1_n		88.73 292	88.38 285	89.76 309	92.06 363	82.53 238	92.30 222	96.59 206	71.14 398	92.58 269	95.41 241	68.55 360	89.57 416	91.12 149	95.66 322	97.18 250

OMC-MVS		94.22 139	93.69 160	95.81 71	97.25 140	91.27 68	92.27 223	97.40 141	87.10 231	94.56 199	95.42 238	93.74 83	98.11 228	86.62 256	98.85 137	98.06 166

PM-MVS		93.33 166	92.67 190	95.33 88	96.58 184	94.06 25	92.26 224	92.18 329	85.92 253	96.22 115	96.61 169	85.64 245	95.99 355	90.35 170	98.23 212	95.93 306

UniMVSNet_NR-MVSNet		95.35 82	95.21 99	95.76 73	97.69 117	88.59 116	92.26 224	97.84 102	94.91 47	96.80 85	95.78 222	90.42 169	99.41 42	91.60 139	99.58 31	99.29 31

AdaColmap		91.63 217	91.36 222	92.47 222	95.56 271	86.36 168	92.24 226	96.27 221	88.88 191	89.90 329	92.69 329	91.65 137	98.32 208	77.38 359	97.64 259	92.72 394

PVSNet_Blended_VisFu		91.63 217	91.20 225	92.94 197	97.73 112	83.95 213	92.14 227	97.46 137	78.85 349	92.35 281	94.98 254	84.16 257	99.08 100	86.36 263	96.77 295	95.79 313

Baseline_NR-MVSNet		94.47 123	95.09 105	92.60 217	98.50 55	80.82 266	92.08 228	96.68 200	93.82 66	96.29 109	98.56 27	90.10 179	97.75 272	90.10 184	99.66 21	99.24 34

Fast-Effi-MVS+-dtu		92.77 188	92.16 200	94.58 127	94.66 303	88.25 123	92.05 229	96.65 202	89.62 174	90.08 324	91.23 355	92.56 117	98.60 178	86.30 264	96.27 309	96.90 261

save fliter					97.46 132	88.05 127	92.04 230	97.08 170	87.63 220

PatchT		87.51 315	88.17 296	85.55 376	90.64 388	66.91 401	92.02 231	86.09 383	92.20 99	89.05 343	97.16 126	64.15 386	96.37 344	89.21 208	92.98 389	93.37 383

EG-PatchMatch MVS		94.54 120	94.67 125	94.14 142	97.87 102	86.50 161	92.00 232	96.74 197	88.16 208	96.93 77	97.61 84	93.04 105	97.90 250	91.60 139	98.12 223	98.03 173

fmvsm_s_conf0.1_n_2		94.38 127	94.78 116	93.19 187	97.07 150	81.72 251	91.97 233	97.51 134	87.05 232	97.31 56	97.92 62	88.29 198	98.15 224	97.10 5	98.81 146	99.70 5

v144192		93.20 174	93.54 168	92.16 232	96.05 237	78.26 314	91.95 234	97.14 165	84.98 277	95.96 126	96.11 204	87.08 222	99.04 108	93.79 65	98.84 138	99.17 39

VNet		92.67 191	92.96 179	91.79 241	96.27 217	80.15 270	91.95 234	94.98 269	92.19 100	94.52 201	96.07 206	87.43 215	97.39 296	84.83 283	98.38 196	97.83 200

1314		86.46 334	86.33 331	86.87 360	91.65 375	74.54 356	91.94 236	94.10 291	74.28 379	84.78 390	87.33 400	83.03 267	95.00 375	78.72 348	91.16 404	91.06 407

MVS		84.98 344	84.30 345	87.01 355	91.03 383	77.69 323	91.94 236	94.16 290	59.36 428	84.23 395	87.50 398	85.66 243	96.80 329	71.79 394	93.05 388	86.54 420

SDMVSNet		94.43 125	95.02 106	92.69 208	97.93 97	82.88 232	91.92 238	95.99 236	93.65 72	95.51 150	98.63 23	94.60 67	96.48 338	87.57 240	99.35 60	98.70 104

tfpn200view9		87.05 328	86.52 328	88.67 329	95.77 257	72.94 372	91.89 239	86.00 384	90.84 147	92.61 267	89.80 372	63.93 387	98.28 210	71.27 399	96.54 302	94.79 350

thres400		87.20 323	86.52 328	89.24 321	95.77 257	72.94 372	91.89 239	86.00 384	90.84 147	92.61 267	89.80 372	63.93 387	98.28 210	71.27 399	96.54 302	96.51 275

v1921920		93.26 169	93.61 164	92.19 228	96.04 241	78.31 313	91.88 241	97.24 159	85.17 271	96.19 120	96.19 199	86.76 230	99.05 105	94.18 56	98.84 138	99.22 35

XXY-MVS		92.58 193	93.16 177	90.84 281	97.75 109	79.84 281	91.87 242	96.22 226	85.94 252	95.53 149	97.68 77	92.69 115	94.48 381	83.21 298	97.51 264	98.21 155

IterMVS-LS		93.78 154	94.28 140	92.27 225	96.27 217	79.21 298	91.87 242	96.78 193	91.77 120	96.57 97	97.07 134	87.15 220	98.74 155	91.99 126	99.03 114	98.86 81
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		93.50 160	93.81 153	92.57 218	96.28 215	79.61 288	91.86 244	96.96 178	86.95 234	95.91 130	96.32 189	87.65 211	98.96 118	93.51 75	98.88 133	99.13 43

v1192		93.49 161	93.78 156	92.62 215	96.16 226	79.62 287	91.83 245	97.22 161	86.07 250	96.10 123	96.38 185	87.22 218	99.02 110	94.14 57	98.88 133	99.22 35

v1240		93.29 167	93.71 159	92.06 235	96.01 242	77.89 319	91.81 246	97.37 142	85.12 273	96.69 90	96.40 180	86.67 231	99.07 104	94.51 46	98.76 155	99.22 35

CNVR-MVS		94.58 118	94.29 139	95.46 84	96.94 155	89.35 99	91.81 246	96.80 192	89.66 173	93.90 221	95.44 237	92.80 113	98.72 157	92.74 107	98.52 182	98.32 145

v2v482		93.29 167	93.63 162	92.29 224	96.35 207	78.82 306	91.77 248	96.28 220	88.45 200	95.70 144	96.26 196	86.02 240	98.90 124	93.02 100	98.81 146	99.14 42

fmvsm_s_conf0.5_n_2		94.25 138	94.63 127	93.10 189	96.65 177	81.75 250	91.72 249	97.25 157	86.93 236	97.20 63	97.67 79	88.44 196	98.14 227	97.06 6	98.77 153	99.42 21

EPNet_dtu		85.63 338	84.37 344	89.40 316	86.30 424	74.33 360	91.64 250	88.26 362	84.84 280	72.96 430	89.85 370	71.27 352	97.69 277	76.60 364	97.62 260	96.18 295
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PLC	85.34 15	90.40 243	88.92 275	94.85 108	96.53 191	90.02 85	91.58 251	96.48 214	80.16 330	86.14 379	92.18 340	85.73 242	98.25 215	76.87 362	94.61 353	96.30 287
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
VPNet		93.08 175	93.76 157	91.03 272	98.60 38	75.83 348	91.51 252	95.62 244	91.84 114	95.74 140	97.10 133	89.31 188	98.32 208	85.07 281	99.06 105	98.93 71

ttmdpeth		86.91 331	86.57 325	87.91 346	89.68 402	74.24 362	91.49 253	87.09 375	79.84 331	89.46 337	97.86 67	65.42 378	91.04 406	81.57 318	96.74 298	98.44 135

XVG-OURS		94.72 110	94.12 147	96.50 51	98.00 92	94.23 22	91.48 254	98.17 56	90.72 151	95.30 164	96.47 174	87.94 208	96.98 318	91.41 146	97.61 261	98.30 149

HQP-NCC					96.36 204		91.37 255		87.16 228	88.81 346

ACMP_Plane					96.36 204		91.37 255		87.16 228	88.81 346

HQP-MVS		92.09 208	91.49 219	93.88 154	96.36 204	84.89 198	91.37 255	97.31 151	87.16 228	88.81 346	93.40 311	84.76 253	98.60 178	86.55 259	97.73 252	98.14 162

MCST-MVS		92.91 180	92.51 193	94.10 144	97.52 127	85.72 185	91.36 258	97.13 167	80.33 329	92.91 259	94.24 283	91.23 148	98.72 157	89.99 186	97.93 243	97.86 196

v148		92.87 184	93.29 172	91.62 249	96.25 220	77.72 322	91.28 259	95.05 266	89.69 172	95.93 129	96.04 207	87.34 216	98.38 202	90.05 185	97.99 238	98.78 91

tpmvs		84.22 351	83.97 350	84.94 382	87.09 421	65.18 411	91.21 260	88.35 361	82.87 304	85.21 383	90.96 361	65.24 381	96.75 330	79.60 343	85.25 420	92.90 391

reproduce_monomvs		87.13 326	86.90 318	87.84 348	90.92 386	68.15 396	91.19 261	93.75 298	85.84 254	94.21 208	95.83 217	42.99 431	97.10 312	89.46 197	97.88 246	98.26 152

CANet		92.38 200	91.99 206	93.52 176	93.82 324	83.46 218	91.14 262	97.00 175	89.81 170	86.47 377	94.04 290	87.90 209	99.21 84	89.50 196	98.27 207	97.90 190

CNLPA		91.72 215	91.20 225	93.26 185	96.17 225	91.02 71	91.14 262	95.55 252	90.16 165	90.87 308	93.56 308	86.31 236	94.40 384	79.92 339	97.12 279	94.37 360

DP-MVS Recon		92.31 202	91.88 209	93.60 168	97.18 145	86.87 152	91.10 264	97.37 142	84.92 278	92.08 290	94.08 289	88.59 192	98.20 218	83.50 295	98.14 221	95.73 315

OpenMVS_ROB	85.12 16	89.52 271	89.05 271	90.92 277	94.58 305	81.21 261	91.10 264	93.41 306	77.03 361	93.41 232	93.99 294	83.23 264	97.80 264	79.93 337	94.80 348	93.74 375

MVStest1		84.79 346	84.06 349	86.98 356	77.73 437	74.76 352	91.08 266	85.63 389	77.70 354	96.86 80	97.97 55	41.05 436	88.24 421	92.22 120	96.28 308	97.94 185

TSAR-MVS + GP.		93.07 177	92.41 196	95.06 102	95.82 253	90.87 76	90.97 267	92.61 322	88.04 209	94.61 198	93.79 301	88.08 202	97.81 263	89.41 198	98.39 195	96.50 278

MVP-Stereo		90.07 260	88.92 275	93.54 173	96.31 212	86.49 162	90.93 268	95.59 249	79.80 332	91.48 298	95.59 229	80.79 291	97.39 296	78.57 350	91.19 403	96.76 269
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MVSTER		89.32 275	88.75 279	91.03 272	90.10 398	76.62 338	90.85 269	94.67 282	82.27 311	95.24 171	95.79 219	61.09 400	98.49 190	90.49 164	98.26 208	97.97 182

pmmvs-eth3d		91.54 220	90.73 240	93.99 146	95.76 259	87.86 131	90.83 270	93.98 296	78.23 352	94.02 216	96.22 198	82.62 275	96.83 327	86.57 257	98.33 202	97.29 244

fmvsm_s_conf0.5_n_7		93.61 158	93.94 150	92.63 213	96.11 232	82.76 234	90.81 271	97.55 128	86.57 238	93.14 249	97.69 76	90.17 175	96.83 327	94.46 48	98.93 127	98.31 147

CANet_DTU		89.85 266	89.17 269	91.87 238	92.20 358	80.02 277	90.79 272	95.87 238	86.02 251	82.53 410	91.77 348	80.01 295	98.57 182	85.66 271	97.70 255	97.01 257

SSC-MVS		90.16 254	92.96 179	81.78 402	97.88 100	48.48 435	90.75 273	87.69 370	96.02 37	96.70 89	97.63 83	85.60 246	97.80 264	85.73 270	98.60 174	99.06 53

test_prior4						89.91 86	90.74 274

TinyColmap		92.00 210	92.76 185	89.71 311	95.62 268	77.02 330	90.72 275	96.17 229	87.70 218	95.26 168	96.29 191	92.54 118	96.45 340	81.77 314	98.77 153	95.66 320

CDPH-MVS		92.67 191	91.83 211	95.18 99	96.94 155	88.46 121	90.70 276	97.07 171	77.38 356	92.34 283	95.08 251	92.67 116	98.88 127	85.74 269	98.57 177	98.20 156

test_vis1_n_1920		89.45 272	89.85 259	88.28 338	93.59 327	76.71 337	90.67 277	97.78 110	79.67 336	90.30 321	96.11 204	76.62 329	92.17 401	90.31 172	93.57 374	95.96 304

DSMNet-mixed		82.21 369	81.56 368	84.16 390	89.57 405	70.00 391	90.65 278	77.66 428	54.99 431	83.30 404	97.57 86	77.89 313	90.50 410	66.86 413	95.54 326	91.97 399

TEST9					96.45 197	89.46 93	90.60 279	96.92 182	79.09 345	90.49 315	94.39 279	91.31 145	98.88 127

train_agg		92.71 190	91.83 211	95.35 86	96.45 197	89.46 93	90.60 279	96.92 182	79.37 340	90.49 315	94.39 279	91.20 150	98.88 127	88.66 221	98.43 190	97.72 213

PatchmatchNet		85.22 341	84.64 341	86.98 356	89.51 406	69.83 392	90.52 281	87.34 374	78.87 348	87.22 374	92.74 328	66.91 368	96.53 335	81.77 314	86.88 417	94.58 356
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
test_8					96.37 202	89.14 103	90.51 282	96.89 185	79.37 340	90.42 317	94.36 281	91.20 150	98.82 136

test_yl		90.11 257	89.73 263	91.26 264	94.09 315	79.82 282	90.44 283	92.65 319	90.90 145	93.19 247	93.30 313	73.90 339	98.03 237	82.23 310	96.87 290	95.93 306

DCV-MVSNet		90.11 257	89.73 263	91.26 264	94.09 315	79.82 282	90.44 283	92.65 319	90.90 145	93.19 247	93.30 313	73.90 339	98.03 237	82.23 310	96.87 290	95.93 306

tpm2		81.46 375	80.35 383	84.80 383	89.90 399	65.14 412	90.44 283	85.36 394	65.82 421	82.05 413	92.44 335	57.94 405	96.69 332	70.71 403	88.49 414	92.56 395

test_fmvs1		87.59 313	87.27 309	88.54 332	88.32 414	81.26 259	90.43 286	95.72 242	70.55 404	91.70 295	94.63 270	68.13 361	89.42 418	90.59 161	95.34 333	94.94 345

test_vis3_rt		90.40 243	90.03 255	91.52 254	92.58 346	88.95 106	90.38 287	97.72 114	73.30 385	97.79 33	97.51 96	77.05 322	87.10 423	89.03 212	94.89 344	98.50 129

CostFormer		83.09 362	82.21 365	85.73 373	89.27 408	67.01 400	90.35 288	86.47 380	70.42 405	83.52 402	93.23 316	61.18 399	96.85 326	77.21 360	88.26 415	93.34 384

TAMVS		90.16 254	89.05 271	93.49 178	96.49 194	86.37 167	90.34 289	92.55 323	80.84 327	92.99 254	94.57 275	81.94 283	98.20 218	73.51 385	98.21 215	95.90 309

EPMVS		81.17 379	80.37 382	83.58 394	85.58 427	65.08 413	90.31 290	71.34 432	77.31 359	85.80 381	91.30 354	59.38 403	92.70 399	79.99 334	82.34 426	92.96 390

CMPMVS	68.83 22	87.28 320	85.67 336	92.09 234	88.77 412	85.42 192	90.31 290	94.38 285	70.02 407	88.00 362	93.30 313	73.78 341	94.03 390	75.96 371	96.54 302	96.83 265
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_post1							90.21 292				5.85 438	65.36 379	96.00 354	79.61 341

test_prior2							90.21 292		89.33 180	90.77 310	94.81 261	90.41 170		88.21 224	98.55 178

MVS_111021_LR		93.66 156	93.28 174	94.80 110	96.25 220	90.95 73	90.21 292	95.43 257	87.91 210	93.74 225	94.40 278	92.88 111	96.38 343	90.39 167	98.28 206	97.07 252

WR-MVS		93.49 161	93.72 158	92.80 204	97.57 125	80.03 276	90.14 295	95.68 243	93.70 68	96.62 93	95.39 242	87.21 219	99.04 108	87.50 241	99.64 23	99.33 28

tpmrst		82.85 366	82.93 360	82.64 398	87.65 416	58.99 428	90.14 295	87.90 369	75.54 369	83.93 398	91.63 351	66.79 371	95.36 368	81.21 323	81.54 427	93.57 382

PVSNet_BlendedMVS		90.35 248	89.96 256	91.54 253	94.81 293	78.80 308	90.14 295	96.93 180	79.43 339	88.68 353	95.06 252	86.27 237	98.15 224	80.27 329	98.04 231	97.68 216

BH-untuned		90.68 235	90.90 232	90.05 305	95.98 243	79.57 289	90.04 298	94.94 271	87.91 210	94.07 212	93.00 320	87.76 210	97.78 268	79.19 346	95.17 338	92.80 393

新几何2							90.02 299

旧先验2							90.00 300		68.65 412	92.71 265			96.52 336	85.15 276

无先验							89.94 301	95.75 241	70.81 402				98.59 180	81.17 324		94.81 348

xiu_mvs_v1_base_debu		91.47 222	91.52 216	91.33 259	95.69 262	81.56 253	89.92 302	96.05 233	83.22 297	91.26 302	90.74 363	91.55 139	98.82 136	89.29 202	95.91 315	93.62 379

xiu_mvs_v1_base		91.47 222	91.52 216	91.33 259	95.69 262	81.56 253	89.92 302	96.05 233	83.22 297	91.26 302	90.74 363	91.55 139	98.82 136	89.29 202	95.91 315	93.62 379

xiu_mvs_v1_base_debi		91.47 222	91.52 216	91.33 259	95.69 262	81.56 253	89.92 302	96.05 233	83.22 297	91.26 302	90.74 363	91.55 139	98.82 136	89.29 202	95.91 315	93.62 379

mvs_anonymous		90.37 247	91.30 224	87.58 350	92.17 360	68.00 397	89.84 305	94.73 279	83.82 291	93.22 246	97.40 101	87.54 213	97.40 295	87.94 235	95.05 341	97.34 241

test20.03		90.80 231	90.85 235	90.63 287	95.63 267	79.24 296	89.81 306	92.87 313	89.90 168	94.39 203	96.40 180	85.77 241	95.27 372	73.86 384	99.05 108	97.39 238

testing3		83.66 357	82.52 362	87.08 354	95.84 251	65.84 409	89.80 307	77.17 430	88.17 207	90.84 309	88.63 387	30.95 439	98.11 228	84.05 292	97.19 277	97.28 245

WB-MVS		89.44 273	92.15 202	81.32 403	97.73 112	48.22 436	89.73 308	87.98 368	95.24 42	96.05 124	96.99 142	85.18 249	96.95 319	82.45 308	97.97 240	98.78 91

1112_ss		88.42 297	87.41 306	91.45 255	96.69 174	80.99 263	89.72 309	96.72 198	73.37 384	87.00 375	90.69 366	77.38 318	98.20 218	81.38 320	93.72 372	95.15 334

UnsupCasMVSNet_eth		90.33 249	90.34 249	90.28 295	94.64 304	80.24 268	89.69 310	95.88 237	85.77 256	93.94 220	95.69 226	81.99 281	92.98 398	84.21 291	91.30 402	97.62 219

MG-MVS		89.54 270	89.80 260	88.76 327	94.88 289	72.47 377	89.60 311	92.44 325	85.82 255	89.48 336	95.98 210	82.85 270	97.74 274	81.87 313	95.27 335	96.08 299

Patchmatch-test		86.10 336	86.01 333	86.38 368	90.63 389	74.22 363	89.57 312	86.69 378	85.73 258	89.81 331	92.83 324	65.24 381	91.04 406	77.82 355	95.78 320	93.88 372

Anonymous20231206		88.77 290	88.29 288	90.20 300	96.31 212	78.81 307	89.56 313	93.49 304	74.26 380	92.38 278	95.58 232	82.21 277	95.43 367	72.07 393	98.75 157	96.34 285

dmvs_re		84.69 348	83.94 351	86.95 358	92.24 355	82.93 231	89.51 314	87.37 373	84.38 286	85.37 382	85.08 414	72.44 345	86.59 424	68.05 409	91.03 406	91.33 404

DeepPCF-MVS	90.46 6	94.20 140	93.56 167	96.14 55	95.96 244	92.96 47	89.48 315	97.46 137	85.14 272	96.23 114	95.42 238	93.19 98	98.08 231	90.37 169	98.76 155	97.38 240

test_cas_vis1_n_1920		88.25 300	88.27 290	88.20 340	92.19 359	78.92 302	89.45 316	95.44 255	75.29 374	93.23 245	95.65 228	71.58 350	90.23 412	88.05 231	93.55 376	95.44 328

SCA		87.43 317	87.21 311	88.10 342	92.01 365	71.98 379	89.43 317	88.11 366	82.26 312	88.71 351	92.83 324	78.65 304	97.59 282	79.61 341	93.30 380	94.75 352

testgi		90.38 246	91.34 223	87.50 351	97.49 129	71.54 380	89.43 317	95.16 264	88.38 202	94.54 200	94.68 269	92.88 111	93.09 397	71.60 397	97.85 248	97.88 193

JIA-IIPM		85.08 343	83.04 358	91.19 269	87.56 417	86.14 174	89.40 319	84.44 403	88.98 187	82.20 411	97.95 56	56.82 408	96.15 348	76.55 366	83.45 423	91.30 405

原ACMM2							89.34 320

tpm		84.38 350	84.08 348	85.30 379	90.47 393	63.43 419	89.34 320	85.63 389	77.24 360	87.62 369	95.03 253	61.00 401	97.30 299	79.26 345	91.09 405	95.16 333

MVS_111021_HR		93.63 157	93.42 171	94.26 139	96.65 177	86.96 151	89.30 322	96.23 224	88.36 204	93.57 228	94.60 272	93.45 88	97.77 269	90.23 178	98.38 196	98.03 173

tpm cat1		80.61 384	79.46 387	84.07 391	88.78 411	65.06 414	89.26 323	88.23 363	62.27 426	81.90 415	89.66 378	62.70 396	95.29 371	71.72 395	80.60 428	91.86 402

CDS-MVSNet		89.55 269	88.22 294	93.53 174	95.37 280	86.49 162	89.26 323	93.59 300	79.76 334	91.15 305	92.31 338	77.12 321	98.38 202	77.51 357	97.92 244	95.71 316
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Fast-Effi-MVS+		91.28 227	90.86 234	92.53 220	95.45 276	82.53 238	89.25 325	96.52 212	85.00 276	89.91 328	88.55 389	92.94 107	98.84 134	84.72 286	95.44 329	96.22 293

BH-RMVSNet		90.47 241	90.44 246	90.56 289	95.21 284	78.65 310	89.15 326	93.94 297	88.21 205	92.74 264	94.22 284	86.38 234	97.88 254	78.67 349	95.39 331	95.14 335

thres200		85.85 337	85.18 338	87.88 347	94.44 307	72.52 376	89.08 327	86.21 381	88.57 198	91.44 299	88.40 390	64.22 385	98.00 243	68.35 408	95.88 318	93.12 385

USDC		89.02 281	89.08 270	88.84 326	95.07 286	74.50 358	88.97 328	96.39 217	73.21 386	93.27 241	96.28 193	82.16 279	96.39 342	77.55 356	98.80 148	95.62 323

testdata1							88.96 329		88.44 201

pmmvs5		87.87 305	87.14 313	90.07 302	93.26 333	76.97 334	88.89 330	92.18 329	73.71 383	88.36 357	93.89 298	76.86 328	96.73 331	80.32 328	96.81 293	96.51 275

dmvs_testset		78.23 395	78.99 389	75.94 411	91.99 366	55.34 433	88.86 331	78.70 425	82.69 305	81.64 417	79.46 426	75.93 332	85.74 426	48.78 431	82.85 425	86.76 419

patch_mono-2		92.46 197	92.72 189	91.71 245	96.65 177	78.91 303	88.85 332	97.17 163	83.89 290	92.45 274	96.76 157	89.86 184	97.09 313	90.24 177	98.59 175	99.12 46

test222					96.95 154	85.27 194	88.83 333	93.61 299	65.09 422	90.74 311	94.85 259	84.62 255			97.36 272	93.91 370

baseline2		83.38 360	81.54 370	88.90 324	91.38 379	72.84 374	88.78 334	81.22 416	78.97 346	79.82 422	87.56 396	61.73 398	97.80 264	74.30 381	90.05 409	96.05 301

diffmvs		91.74 214	91.93 208	91.15 270	93.06 336	78.17 315	88.77 335	97.51 134	86.28 244	92.42 276	93.96 295	88.04 205	97.46 289	90.69 160	96.67 299	97.82 203
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MDTV_nov1_ep13			83.88 353		89.42 407	61.52 422	88.74 336	87.41 372	73.99 381	84.96 389	94.01 293	65.25 380	95.53 361	78.02 351	93.16 383

D2MVS		89.93 263	89.60 265	90.92 277	94.03 318	78.40 311	88.69 337	94.85 272	78.96 347	93.08 250	95.09 250	74.57 337	96.94 320	88.19 226	98.96 124	97.41 234

TR-MVS		87.70 308	87.17 312	89.27 319	94.11 314	79.26 295	88.69 337	91.86 338	81.94 315	90.69 313	89.79 374	82.82 271	97.42 293	72.65 391	91.98 399	91.14 406

PatchMatch-RL		89.18 276	88.02 299	92.64 210	95.90 248	92.87 49	88.67 339	91.06 344	80.34 328	90.03 326	91.67 350	83.34 262	94.42 383	76.35 367	94.84 347	90.64 409

PAPR		87.65 311	86.77 322	90.27 296	92.85 343	77.38 326	88.56 340	96.23 224	76.82 364	84.98 388	89.75 376	86.08 239	97.16 310	72.33 392	93.35 379	96.26 291

testing3-2		83.95 355	84.22 347	83.13 397	96.28 215	54.34 434	88.51 341	83.01 409	92.19 100	89.09 342	90.98 359	45.51 424	97.44 291	74.38 380	98.01 235	97.60 221

MDTV_nov1_ep13_2view						42.48 439	88.45 342		67.22 416	83.56 401		66.80 369		72.86 390		94.06 366

WB-MVSnew		84.20 352	83.89 352	85.16 381	91.62 376	66.15 408	88.44 343	81.00 417	76.23 366	87.98 363	87.77 395	84.98 252	93.35 395	62.85 422	94.10 367	95.98 303

jason		89.17 277	88.32 286	91.70 246	95.73 260	80.07 273	88.10 344	93.22 308	71.98 393	90.09 323	92.79 326	78.53 307	98.56 183	87.43 243	97.06 281	96.46 281
jason: jason.
mvsany_test3		89.11 279	88.21 295	91.83 239	91.30 381	90.25 83	88.09 345	78.76 424	76.37 365	96.43 100	98.39 36	83.79 260	90.43 411	86.57 257	94.20 362	94.80 349

BH-w/o		87.21 322	87.02 317	87.79 349	94.77 296	77.27 328	87.90 346	93.21 310	81.74 317	89.99 327	88.39 391	83.47 261	96.93 322	71.29 398	92.43 395	89.15 411

MS-PatchMatch		88.05 303	87.75 301	88.95 323	93.28 331	77.93 317	87.88 347	92.49 324	75.42 370	92.57 270	93.59 307	80.44 293	94.24 388	81.28 321	92.75 390	94.69 355

UWE-MVS-28		74.73 396	73.18 399	79.35 408	85.42 428	55.55 432	87.63 348	65.92 434	74.39 378	77.33 426	88.19 392	47.63 420	89.48 417	39.01 433	93.14 385	93.03 389

DELS-MVS		92.05 209	92.16 200	91.72 244	94.44 307	80.13 272	87.62 349	97.25 157	87.34 224	92.22 286	93.18 318	89.54 187	98.73 156	89.67 193	98.20 217	96.30 287
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
ADS-MVSNet2		84.01 353	82.20 366	89.41 315	89.04 409	76.37 342	87.57 350	90.98 346	72.71 391	84.46 391	92.45 333	68.08 362	96.48 338	70.58 404	83.97 421	95.38 329

ADS-MVSNet		82.25 368	81.55 369	84.34 388	89.04 409	65.30 410	87.57 350	85.13 399	72.71 391	84.46 391	92.45 333	68.08 362	92.33 400	70.58 404	83.97 421	95.38 329

IterMVS-SCA-FT		91.65 216	91.55 215	91.94 237	93.89 321	79.22 297	87.56 352	93.51 303	91.53 130	95.37 160	96.62 168	78.65 304	98.90 124	91.89 130	94.95 343	97.70 214

IterMVS		90.18 253	90.16 251	90.21 299	93.15 334	75.98 345	87.56 352	92.97 312	86.43 242	94.09 210	96.40 180	78.32 309	97.43 292	87.87 236	94.69 351	97.23 247
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Test_1112_low_res		87.50 316	86.58 324	90.25 297	96.80 168	77.75 321	87.53 354	96.25 222	69.73 409	86.47 377	93.61 306	75.67 333	97.88 254	79.95 335	93.20 382	95.11 338

c3_l		91.32 226	91.42 220	91.00 275	92.29 354	76.79 336	87.52 355	96.42 216	85.76 257	94.72 197	93.89 298	82.73 272	98.16 223	90.93 155	98.55 178	98.04 170

UnsupCasMVSNet_bld		88.50 295	88.03 298	89.90 307	95.52 273	78.88 304	87.39 356	94.02 294	79.32 343	93.06 251	94.02 292	80.72 292	94.27 386	75.16 375	93.08 387	96.54 273

lupinMVS		88.34 299	87.31 307	91.45 255	94.74 298	80.06 274	87.23 357	92.27 328	71.10 399	88.83 344	91.15 356	77.02 323	98.53 187	86.67 255	96.75 296	95.76 314

pmmvs4		88.95 286	87.70 303	92.70 207	94.30 310	85.60 188	87.22 358	92.16 331	74.62 376	89.75 334	94.19 285	77.97 312	96.41 341	82.71 302	96.36 306	96.09 298

WTY-MVS		86.93 330	86.50 330	88.24 339	94.96 287	74.64 354	87.19 359	92.07 334	78.29 351	88.32 358	91.59 352	78.06 311	94.27 386	74.88 376	93.15 384	95.80 312

ET-MVSNet_ETH3D		86.15 335	84.27 346	91.79 241	93.04 337	81.28 258	87.17 360	86.14 382	79.57 337	83.65 399	88.66 386	57.10 406	98.18 221	87.74 238	95.40 330	95.90 309

MVS-HIRNet		78.83 394	80.60 379	73.51 413	93.07 335	47.37 437	87.10 361	78.00 427	68.94 411	77.53 425	97.26 116	71.45 351	94.62 379	63.28 420	88.74 413	78.55 428

xiu_mvs_v2_base		89.00 284	89.19 268	88.46 336	94.86 291	74.63 355	86.97 362	95.60 245	80.88 325	87.83 365	88.62 388	91.04 155	98.81 141	82.51 307	94.38 356	91.93 400

DPM-MVS		89.35 274	88.40 284	92.18 231	96.13 231	84.20 208	86.96 363	96.15 230	75.40 371	87.36 372	91.55 353	83.30 263	98.01 241	82.17 312	96.62 300	94.32 362

eth_miper_zixun_eth		90.72 233	90.61 242	91.05 271	92.04 364	76.84 335	86.91 364	96.67 201	85.21 270	94.41 202	93.92 296	79.53 298	98.26 214	89.76 191	97.02 283	98.06 166

dp		79.28 392	78.62 392	81.24 404	85.97 426	56.45 430	86.91 364	85.26 397	72.97 389	81.45 418	89.17 385	56.01 410	95.45 366	73.19 388	76.68 429	91.82 403

sss		87.23 321	86.82 320	88.46 336	93.96 319	77.94 316	86.84 366	92.78 317	77.59 355	87.61 370	91.83 347	78.75 303	91.92 402	77.84 353	94.20 362	95.52 327

miper_ehance_all_eth		90.48 240	90.42 247	90.69 285	91.62 376	76.57 339	86.83 367	96.18 228	83.38 293	94.06 213	92.66 331	82.20 278	98.04 236	89.79 190	97.02 283	97.45 231

CLD-MVS		91.82 211	91.41 221	93.04 190	96.37 202	83.65 216	86.82 368	97.29 154	84.65 282	92.27 285	89.67 377	92.20 125	97.85 260	83.95 293	99.47 42	97.62 219
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
cl____		90.65 236	90.56 244	90.91 279	91.85 369	76.98 333	86.75 369	95.36 260	85.53 264	94.06 213	94.89 257	77.36 320	97.98 246	90.27 175	98.98 117	97.76 209

DIV-MVS_self_test		90.65 236	90.56 244	90.91 279	91.85 369	76.99 332	86.75 369	95.36 260	85.52 266	94.06 213	94.89 257	77.37 319	97.99 245	90.28 174	98.97 122	97.76 209

PS-MVSNAJ		88.86 288	88.99 274	88.48 335	94.88 289	74.71 353	86.69 371	95.60 245	80.88 325	87.83 365	87.37 399	90.77 160	98.82 136	82.52 306	94.37 357	91.93 400

PVSNet_Blended		88.74 291	88.16 297	90.46 292	94.81 293	78.80 308	86.64 372	96.93 180	74.67 375	88.68 353	89.18 384	86.27 237	98.15 224	80.27 329	96.00 313	94.44 359

MSDG		90.82 230	90.67 241	91.26 264	94.16 312	83.08 228	86.63 373	96.19 227	90.60 156	91.94 292	91.89 346	89.16 190	95.75 359	80.96 326	94.51 354	94.95 343

cl22		89.02 281	88.50 282	90.59 288	89.76 400	76.45 340	86.62 374	94.03 292	82.98 303	92.65 266	92.49 332	72.05 348	97.53 284	88.93 213	97.02 283	97.78 207

CL-MVSNet_self_test		90.04 262	89.90 258	90.47 290	95.24 283	77.81 320	86.60 375	92.62 321	85.64 260	93.25 244	93.92 296	83.84 259	96.06 352	79.93 337	98.03 232	97.53 227

PCF-MVS	84.52 17	89.12 278	87.71 302	93.34 181	96.06 236	85.84 182	86.58 376	97.31 151	68.46 413	93.61 227	93.89 298	87.51 214	98.52 188	67.85 410	98.11 224	95.66 320
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_f		86.65 333	87.13 314	85.19 380	90.28 396	86.11 175	86.52 377	91.66 340	69.76 408	95.73 142	97.21 123	69.51 358	81.28 430	89.15 209	94.40 355	88.17 416

UWE-MVS		80.29 387	79.10 388	83.87 392	91.97 367	59.56 426	86.50 378	77.43 429	75.40 371	87.79 367	88.10 393	44.08 429	96.90 324	64.23 417	96.36 306	95.14 335

testing91		83.56 359	82.45 363	86.91 359	92.92 341	67.29 398	86.33 379	88.07 367	86.22 246	84.26 394	85.76 408	48.15 419	97.17 308	76.27 368	94.08 368	96.27 290

testing222		80.54 385	78.53 393	86.58 363	92.54 350	68.60 395	86.24 380	82.72 410	83.78 292	82.68 409	84.24 417	39.25 437	95.94 356	60.25 423	95.09 340	95.20 331

Patchmatch-RL test		88.81 289	88.52 281	89.69 312	95.33 282	79.94 279	86.22 381	92.71 318	78.46 350	95.80 135	94.18 286	66.25 374	95.33 370	89.22 207	98.53 181	93.78 373

ETVMVS		79.85 390	77.94 397	85.59 374	92.97 339	66.20 407	86.13 382	80.99 418	81.41 319	83.52 402	83.89 418	41.81 435	94.98 378	56.47 427	94.25 361	95.61 324

testing99		82.94 364	81.72 367	86.59 362	92.55 348	66.53 404	86.08 383	85.70 387	85.47 267	83.95 397	85.70 409	45.87 423	97.07 315	76.58 365	93.56 375	96.17 297

Syy-MVS		84.81 345	84.93 339	84.42 387	91.71 373	63.36 420	85.89 384	81.49 414	81.03 322	85.13 385	81.64 424	77.44 316	95.00 375	85.94 268	94.12 365	94.91 346

myMVS_eth3d		79.62 391	78.26 394	83.72 393	91.71 373	61.25 424	85.89 384	81.49 414	81.03 322	85.13 385	81.64 424	32.12 438	95.00 375	71.17 402	94.12 365	94.91 346

testing11		81.98 373	80.52 380	86.38 368	92.69 345	67.13 399	85.79 386	84.80 400	82.16 313	81.19 419	85.41 411	45.24 425	96.88 325	74.14 382	93.24 381	95.14 335

FPMVS		84.50 349	83.28 356	88.16 341	96.32 211	94.49 20	85.76 387	85.47 393	83.09 300	85.20 384	94.26 282	63.79 389	86.58 425	63.72 419	91.88 401	83.40 423

IB-MVS	77.21 19	83.11 361	81.05 373	89.29 318	91.15 382	75.85 346	85.66 388	86.00 384	79.70 335	82.02 414	86.61 402	48.26 417	98.39 199	77.84 353	92.22 396	93.63 378
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
MDA-MVSNet-bldmvs		91.04 228	90.88 233	91.55 252	94.68 302	80.16 269	85.49 389	92.14 332	90.41 162	94.93 187	95.79 219	85.10 250	96.93 322	85.15 276	94.19 364	97.57 223

test_vis1_rt		85.58 339	84.58 342	88.60 331	87.97 415	86.76 154	85.45 390	93.59 300	66.43 417	87.64 368	89.20 383	79.33 299	85.38 427	81.59 317	89.98 410	93.66 377

new-patchmatchnet		88.97 285	90.79 238	83.50 395	94.28 311	55.83 431	85.34 391	93.56 302	86.18 248	95.47 153	95.73 225	83.10 265	96.51 337	85.40 273	98.06 229	98.16 160

miper_enhance_ethall		88.42 297	87.87 300	90.07 302	88.67 413	75.52 349	85.10 392	95.59 249	75.68 367	92.49 271	89.45 380	78.96 301	97.88 254	87.86 237	97.02 283	96.81 266

HyFIR lowres test		87.19 324	85.51 337	92.24 226	97.12 149	80.51 267	85.03 393	96.06 231	66.11 419	91.66 296	92.98 322	70.12 356	99.14 93	75.29 374	95.23 336	97.07 252

pmmvs3		80.83 382	78.96 390	86.45 365	87.23 420	77.48 325	84.87 394	82.31 411	63.83 424	85.03 387	89.50 379	49.66 416	93.10 396	73.12 389	95.10 339	88.78 415

test0.0.03 1		82.48 367	81.47 371	85.48 377	89.70 401	73.57 367	84.73 395	81.64 413	83.07 301	88.13 361	86.61 402	62.86 394	89.10 420	66.24 414	90.29 408	93.77 374

N_pmnet		88.90 287	87.25 310	93.83 158	94.40 309	93.81 39	84.73 395	87.09 375	79.36 342	93.26 242	92.43 336	79.29 300	91.68 403	77.50 358	97.22 276	96.00 302

GA-MVS		87.70 308	86.82 320	90.31 294	93.27 332	77.22 329	84.72 397	92.79 316	85.11 274	89.82 330	90.07 369	66.80 369	97.76 271	84.56 287	94.27 360	95.96 304

myMVS_eth3d28		80.97 380	80.42 381	82.62 399	93.35 330	58.25 429	84.70 398	85.62 391	86.31 243	84.04 396	85.20 413	46.00 422	94.07 389	62.93 421	95.65 323	95.53 326

ppachtmachnet_test		88.61 294	88.64 280	88.50 334	91.76 371	70.99 384	84.59 399	92.98 311	79.30 344	92.38 278	93.53 309	79.57 297	97.45 290	86.50 261	97.17 278	97.07 252

CHOSEN 1792x2688		87.19 324	85.92 335	91.00 275	97.13 148	79.41 292	84.51 400	95.60 245	64.14 423	90.07 325	94.81 261	78.26 310	97.14 311	73.34 386	95.38 332	96.46 281

thisisatest0515		84.72 347	82.99 359	89.90 307	92.96 340	75.33 351	84.36 401	83.42 406	77.37 357	88.27 359	86.65 401	53.94 412	98.72 157	82.56 305	97.40 271	95.67 319

cascas		87.02 329	86.28 332	89.25 320	91.56 378	76.45 340	84.33 402	96.78 193	71.01 400	86.89 376	85.91 407	81.35 286	96.94 320	83.09 299	95.60 324	94.35 361

new_pmnet		81.22 377	81.01 375	81.86 401	90.92 386	70.15 387	84.03 403	80.25 422	70.83 401	85.97 380	89.78 375	67.93 365	84.65 428	67.44 411	91.90 400	90.78 408

PAPM		81.91 374	80.11 385	87.31 353	93.87 322	72.32 378	84.02 404	93.22 308	69.47 410	76.13 428	89.84 371	72.15 347	97.23 303	53.27 429	89.02 412	92.37 397

UBG		80.28 388	78.94 391	84.31 389	92.86 342	61.77 421	83.87 405	83.31 408	77.33 358	82.78 408	83.72 419	47.60 421	96.06 352	65.47 416	93.48 377	95.11 338

our_test_3		87.55 314	87.59 304	87.44 352	91.76 371	70.48 385	83.83 406	90.55 351	79.79 333	92.06 291	92.17 341	78.63 306	95.63 360	84.77 284	94.73 349	96.22 293

WBMVS		84.00 354	83.48 354	85.56 375	92.71 344	61.52 422	83.82 407	89.38 356	79.56 338	90.74 311	93.20 317	48.21 418	97.28 300	75.63 373	98.10 226	97.88 193

miper_lstm_enhance		89.90 264	89.80 260	90.19 301	91.37 380	77.50 324	83.82 407	95.00 268	84.84 280	93.05 252	94.96 255	76.53 331	95.20 373	89.96 187	98.67 167	97.86 196

test-LLR		83.58 358	83.17 357	84.79 384	89.68 402	66.86 402	83.08 409	84.52 401	83.07 301	82.85 406	84.78 415	62.86 394	93.49 393	82.85 300	94.86 345	94.03 367

TESTMET0.1,1		79.09 393	78.04 395	82.25 400	87.52 418	64.03 417	83.08 409	80.62 420	70.28 406	80.16 421	83.22 421	44.13 428	90.56 409	79.95 335	93.36 378	92.15 398

test-mter		81.21 378	80.01 386	84.79 384	89.68 402	66.86 402	83.08 409	84.52 401	73.85 382	82.85 406	84.78 415	43.66 430	93.49 393	82.85 300	94.86 345	94.03 367

SSC-MVS3.2		89.88 265	91.06 230	86.31 370	95.90 248	63.76 418	82.68 412	92.43 326	91.42 135	92.37 280	94.58 274	86.34 235	96.60 334	84.35 290	99.50 40	98.57 123

test123		9.49 404	12.01 407	1.91 419	2.87 442	1.30 444	82.38 413	1.34 444	1.36 437	2.84 438	6.56 436	2.45 442	0.97 438	2.73 437	5.56 436	3.47 434

PMMVS		83.00 363	81.11 372	88.66 330	83.81 433	86.44 165	82.24 414	85.65 388	61.75 427	82.07 412	85.64 410	79.75 296	91.59 404	75.99 370	93.09 386	87.94 417

KD-MVS_2432*1600		82.17 370	80.75 377	86.42 366	82.04 434	70.09 388	81.75 415	90.80 348	82.56 306	90.37 319	89.30 381	42.90 432	96.11 350	74.47 378	92.55 393	93.06 386

miper_refine_blended		82.17 370	80.75 377	86.42 366	82.04 434	70.09 388	81.75 415	90.80 348	82.56 306	90.37 319	89.30 381	42.90 432	96.11 350	74.47 378	92.55 393	93.06 386

mvsany_test1		83.91 356	82.93 360	86.84 361	86.18 425	85.93 179	81.11 417	75.03 431	70.80 403	88.57 355	94.63 270	83.08 266	87.38 422	80.39 327	86.57 418	87.21 418

YYNet1		88.17 301	88.24 292	87.93 344	92.21 357	73.62 366	80.75 418	88.77 358	82.51 309	94.99 185	95.11 249	82.70 273	93.70 391	83.33 296	93.83 370	96.48 279

MDA-MVSNet_test_wron		88.16 302	88.23 293	87.93 344	92.22 356	73.71 365	80.71 419	88.84 357	82.52 308	94.88 190	95.14 247	82.70 273	93.61 392	83.28 297	93.80 371	96.46 281

testmvs		9.02 405	11.42 408	1.81 420	2.77 443	1.13 445	79.44 420	1.90 443	1.18 438	2.65 439	6.80 435	1.95 443	0.87 439	2.62 438	3.45 437	3.44 435

PVSNet	76.22 20	82.89 365	82.37 364	84.48 386	93.96 319	64.38 416	78.60 421	88.61 359	71.50 396	84.43 393	86.36 405	74.27 338	94.60 380	69.87 406	93.69 373	94.46 358

dongtai		53.72 399	53.79 402	53.51 416	79.69 436	36.70 440	77.18 422	32.53 442	71.69 394	68.63 432	60.79 431	26.65 440	73.11 432	30.67 435	36.29 434	50.73 430

kuosan		43.63 401	44.25 405	41.78 417	66.04 439	34.37 441	75.56 423	32.62 441	53.25 432	50.46 435	51.18 432	25.28 441	49.13 435	13.44 436	30.41 435	41.84 432

PVSNet_0	70.34 21	74.58 397	72.96 400	79.47 407	90.63 389	66.24 406	73.26 424	83.40 407	63.67 425	78.02 424	78.35 428	72.53 344	89.59 415	56.68 426	60.05 432	82.57 426

E-PMN		80.72 383	80.86 376	80.29 406	85.11 429	68.77 394	72.96 425	81.97 412	87.76 216	83.25 405	83.01 422	62.22 397	89.17 419	77.15 361	94.31 359	82.93 424

CHOSEN 280x420		80.04 389	77.97 396	86.23 371	90.13 397	74.53 357	72.87 426	89.59 355	66.38 418	76.29 427	85.32 412	56.96 407	95.36 368	69.49 407	94.72 350	88.79 414

EMVS		80.35 386	80.28 384	80.54 405	84.73 431	69.07 393	72.54 427	80.73 419	87.80 214	81.66 416	81.73 423	62.89 393	89.84 413	75.79 372	94.65 352	82.71 425

PMMVS2		81.31 376	83.44 355	74.92 412	90.52 391	46.49 438	69.19 428	85.23 398	84.30 287	87.95 364	94.71 267	76.95 325	84.36 429	64.07 418	98.09 227	93.89 371

tmp_tt		37.97 402	44.33 404	18.88 418	11.80 441	21.54 442	63.51 429	45.66 440	4.23 435	51.34 434	50.48 433	59.08 404	22.11 437	44.50 432	68.35 431	13.00 433

MVE	59.87 23	73.86 398	72.65 401	77.47 410	87.00 423	74.35 359	61.37 430	60.93 436	67.27 415	69.69 431	86.49 404	81.24 290	72.33 433	56.45 428	83.45 423	85.74 421
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		50.44 400	48.94 403	54.93 414	39.68 440	12.38 443	28.59 431	90.09 352	6.82 434	41.10 436	78.41 427	54.41 411	70.69 434	50.12 430	51.26 433	81.72 427

mmdepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

monomultidepth		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

test_blank		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet_test		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

DCPMVS		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

cdsmvs_eth3d_5k		23.35 403	31.13 406	0.00 421	0.00 444	0.00 446	0.00 432	95.58 251	0.00 439	0.00 440	91.15 356	93.43 90	0.00 440	0.00 439	0.00 438	0.00 436

pcd_1.5k_mvsjas		7.56 406	10.09 409	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	90.77 160	0.00 440	0.00 439	0.00 438	0.00 436

sosnet-low-res		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

sosnet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uncertanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

Regformer		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

ab-mvs-re		7.56 406	10.08 410	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	90.69 366	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

uanet		0.00 408	0.00 411	0.00 421	0.00 444	0.00 446	0.00 432	0.00 445	0.00 439	0.00 440	0.00 439	0.00 444	0.00 440	0.00 439	0.00 438	0.00 436

WAC-MVS						61.25 424								74.55 377

MSC_two_6792asdad				95.90 67	96.54 188	89.57 91		96.87 187					99.41 42	94.06 58	99.30 73	98.72 100

PC_three_1452									75.31 373	95.87 133	95.75 224	92.93 108	96.34 347	87.18 247	98.68 165	98.04 170

No_MVS				95.90 67	96.54 188	89.57 91		96.87 187					99.41 42	94.06 58	99.30 73	98.72 100

test_one_0601					98.26 71	87.14 144		98.18 52	94.25 55	96.99 75	97.36 106	95.13 45

eth-test2					0.00 444

eth-test					0.00 444

ZD-MVS					97.23 141	90.32 82		97.54 129	84.40 285	94.78 193	95.79 219	92.76 114	99.39 52	88.72 220	98.40 191

IU-MVS					98.51 49	86.66 159		96.83 190	72.74 390	95.83 134				93.00 101	99.29 76	98.64 115

test_241102_TWO								98.10 67	91.95 105	97.54 43	97.25 117	95.37 32	99.35 62	93.29 89	99.25 84	98.49 131

test_241102_ONE					98.51 49	86.97 149		98.10 67	91.85 111	97.63 38	97.03 138	96.48 10	98.95 120

test_0728_THIRD									93.26 78	97.40 54	97.35 109	94.69 63	99.34 65	93.88 62	99.42 51	98.89 78

GSMVS																94.75 352

test_part2					98.21 76	89.41 96				96.72 88

sam_mvs1												66.64 372				94.75 352

sam_mvs												66.41 373

MTGPA								97.62 119

test_post											6.07 437	65.74 377	95.84 358

patchmatchnet-post											91.71 349	66.22 375	97.59 282

gm-plane-assit					87.08 422	59.33 427			71.22 397		83.58 420		97.20 305	73.95 383

test9_res														88.16 228	98.40 191	97.83 200

agg_prior2														87.06 250	98.36 201	97.98 179

agg_prior					96.20 223	88.89 108		96.88 186		90.21 322			98.78 148

TestCases				96.00 58	98.02 90	92.17 54		98.43 22	90.48 158	95.04 182	96.74 160	92.54 118	97.86 258	85.11 279	98.98 117	97.98 179

test_prior				94.61 121	95.95 245	87.23 141		97.36 147					98.68 168			97.93 186

新几何1				93.17 188	97.16 146	87.29 139		94.43 284	67.95 414	91.29 301	94.94 256	86.97 225	98.23 216	81.06 325	97.75 251	93.98 369

旧先验1					96.20 223	84.17 209		94.82 274			95.57 233	89.57 186			97.89 245	96.32 286

原ACMM1				92.87 201	96.91 158	84.22 207		97.01 174	76.84 363	89.64 335	94.46 277	88.00 206	98.70 164	81.53 319	98.01 235	95.70 318

testdata2													98.03 237	80.24 331

segment_acmp												92.14 126

testdata				91.03 272	96.87 161	82.01 245		94.28 288	71.55 395	92.46 273	95.42 238	85.65 244	97.38 298	82.64 303	97.27 274	93.70 376

test12				94.43 134	95.95 245	86.75 155		96.24 223		89.76 333		89.79 185	98.79 145		97.95 242	97.75 211

plane_prior7					97.71 114	88.68 111

plane_prior6					97.21 144	88.23 124						86.93 226

plane_prior5								97.81 105					98.95 120	89.26 205	98.51 184	98.60 120

plane_prior4											95.59 229

plane_prior3						88.43 122			90.35 163	93.31 237

plane_prior1					97.38 134

n2								0.00 445

nn								0.00 445

door-mid								92.13 333

lessismore_v0				93.87 155	98.05 86	83.77 215		80.32 421		97.13 66	97.91 64	77.49 315	99.11 98	92.62 111	98.08 228	98.74 98

LGP-MVS_train				96.84 42	98.36 66	92.13 56		98.25 40	91.78 118	97.07 68	97.22 121	96.38 12	99.28 78	92.07 124	99.59 27	99.11 47

test11								96.65 202

door								91.26 343

HQP5-MVS						84.89 198

BP-MVS														86.55 259

HQP4-MVS										88.81 346			98.61 176			98.15 161

HQP3-MVS								97.31 151							97.73 252

HQP2-MVS												84.76 253

NP-MVS					96.82 166	87.10 145					93.40 311

ACMMP++_ref															98.82 144

ACMMP++															99.25 84

Test By Simon												90.61 166

ITE_SJBPF				95.95 61	97.34 137	93.36 44		96.55 211	91.93 107	94.82 191	95.39 242	91.99 128	97.08 314	85.53 272	97.96 241	97.41 234

DeepMVS_CX				53.83 415	70.38 438	64.56 415		48.52 439	33.01 433	65.50 433	74.21 430	56.19 409	46.64 436	38.45 434	70.07 430	50.30 431

High-resolution multi-view benchmark