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		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 8	99.98 1	99.99 1	99.96 1	99.77 1	100.00 1	99.81 5	100.00 1	99.85 12

mvs_tets		99.63 5	99.67 5	99.49 48	99.88 9	98.61 92	99.34 19	99.71 21	99.27 49	99.90 6	99.74 12	99.68 2	99.97 4	99.55 16	99.99 5	99.88 7

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 18	99.34 15	99.69 4	99.58 42	99.90 2	99.86 10	99.78 8	99.58 3	99.95 17	99.00 47	99.95 19	99.78 20

jajsoiax		99.58 6	99.61 7	99.48 51	99.87 12	98.61 92	99.28 36	99.66 32	99.09 71	99.89 8	99.68 18	99.53 4	99.97 4	99.50 18	99.99 5	99.87 9

pmmvs6		99.67 3	99.70 3	99.60 11	99.90 4	99.27 22	99.53 7	99.76 18	99.64 11	99.84 11	99.83 3	99.50 5	99.87 89	99.36 24	99.92 42	99.64 50

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 21	99.85 16	99.11 59	99.90 1	99.78 16	99.63 13	99.78 15	99.67 20	99.48 6	99.81 163	99.30 29	99.97 12	99.77 22
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
XVG-OURS		98.53 123	98.34 132	99.11 109	99.50 93	98.82 78	95.97 298	99.50 74	97.30 203	99.05 125	98.98 152	99.35 7	99.32 336	95.72 252	99.68 152	99.18 221

XVG-OURS-SEG-HR		98.49 127	98.28 139	99.14 105	99.49 100	98.83 76	96.54 274	99.48 83	97.32 201	99.11 113	98.61 229	99.33 8	99.30 339	96.23 226	98.38 313	99.28 199

ACMH	96.65 7	99.25 27	99.24 27	99.26 88	99.72 42	98.38 109	99.07 61	99.55 60	98.30 118	99.65 32	99.45 59	99.22 9	99.76 205	98.44 82	99.77 109	99.64 50
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
cdsmvs_eth3d_5k		24.66 344	32.88 347	0.00 362	0.00 385	0.00 386	0.00 373	99.10 211	0.00 380	0.00 381	97.58 309	99.21 10	0.00 381	0.00 379	0.00 379	0.00 377

wuyk23d		96.06 282	97.62 199	91.38 356	98.65 276	98.57 96	98.85 81	96.95 334	96.86 232	99.90 6	99.16 110	99.18 11	98.40 368	89.23 356	99.77 109	77.18 374

TransMVSNet (Re)		99.44 13	99.47 12	99.36 64	99.80 22	98.58 95	99.27 38	99.57 49	99.39 36	99.75 18	99.62 28	99.17 12	99.83 140	99.06 42	99.62 172	99.66 45

ANet_high		99.57 7	99.67 5	99.28 83	99.89 6	98.09 133	99.14 53	99.93 3	99.82 3	99.93 3	99.81 5	99.17 12	99.94 26	99.31 27	100.00 1	99.82 14

pm-mvs1		99.44 13	99.48 11	99.33 76	99.80 22	98.63 89	99.29 32	99.63 34	99.30 47	99.65 32	99.60 32	99.16 14	99.82 150	99.07 41	99.83 77	99.56 82

test_djsdf		99.52 9	99.51 9	99.53 34	99.86 14	98.74 82	99.39 16	99.56 56	99.11 61	99.70 23	99.73 14	99.00 15	99.97 4	99.26 30	99.98 9	99.89 6

DeepC-MVS	97.60 4	98.97 54	98.93 55	99.10 111	99.35 136	97.98 148	98.01 167	99.46 91	97.56 175	99.54 41	99.50 49	98.97 16	99.84 126	98.06 102	99.92 42	99.49 112
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
testgi		98.32 144	98.39 125	98.13 224	99.57 69	95.54 246	97.78 187	99.49 81	97.37 196	99.19 106	97.65 305	98.96 17	99.49 310	96.50 212	98.99 284	99.34 182

GeoE		99.05 46	98.99 52	99.25 91	99.44 114	98.35 115	98.73 86	99.56 56	98.42 111	98.91 150	98.81 193	98.94 18	99.91 47	98.35 86	99.73 127	99.49 112

anonymousdsp		99.51 10	99.47 12	99.62 6	99.88 9	99.08 63	99.34 19	99.69 24	98.93 86	99.65 32	99.72 15	98.93 19	99.95 17	99.11 39	100.00 1	99.82 14

casdiffmvs_mvg		99.12 40	99.16 32	98.99 131	99.43 119	97.73 174	98.00 168	99.62 35	99.22 51	99.55 40	99.22 97	98.93 19	99.75 212	98.66 69	99.81 84	99.50 108
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testf1		99.25 27	99.16 32	99.51 43	99.89 6	99.63 3	98.71 89	99.69 24	98.90 88	99.43 60	99.35 73	98.86 21	99.67 248	97.81 117	99.81 84	99.24 207

APD_test2		99.25 27	99.16 32	99.51 43	99.89 6	99.63 3	98.71 89	99.69 24	98.90 88	99.43 60	99.35 73	98.86 21	99.67 248	97.81 117	99.81 84	99.24 207

ACMM	96.08 12	98.91 61	98.73 72	99.48 51	99.55 80	99.14 52	98.07 157	99.37 119	97.62 168	99.04 127	98.96 157	98.84 23	99.79 183	97.43 136	99.65 164	99.49 112
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Vis-MVSNet		99.34 22	99.36 17	99.27 86	99.73 36	98.26 118	99.17 49	99.78 16	99.11 61	99.27 92	99.48 53	98.82 24	99.95 17	98.94 50	99.93 31	99.59 67
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH+	96.62 9	99.08 44	99.00 49	99.33 76	99.71 44	98.83 76	98.60 99	99.58 42	99.11 61	99.53 45	99.18 104	98.81 25	99.67 248	96.71 193	99.77 109	99.50 108

SD-MVS		98.40 136	98.68 82	97.54 269	98.96 213	97.99 145	97.88 178	99.36 123	98.20 129	99.63 35	99.04 133	98.76 26	95.33 376	96.56 205	99.74 124	99.31 193
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
HPM-MVS_fast		99.01 48	98.82 65	99.57 16	99.71 44	99.35 12	99.00 68	99.50 74	97.33 199	98.94 147	98.86 181	98.75 27	99.82 150	97.53 132	99.71 139	99.56 82

XXY-MVS		99.14 35	99.15 37	99.10 111	99.76 30	97.74 172	98.85 81	99.62 35	98.48 110	99.37 74	99.49 52	98.75 27	99.86 98	98.20 94	99.80 95	99.71 33

DROMVSNet		99.09 42	99.05 46	99.20 97	99.28 144	98.93 71	99.24 40	99.84 12	99.08 73	98.12 236	98.37 255	98.72 29	99.90 52	99.05 43	99.77 109	98.77 285

LPG-MVS_test		98.71 87	98.46 114	99.47 54	99.57 69	98.97 66	98.23 139	99.48 83	96.60 242	99.10 116	99.06 124	98.71 30	99.83 140	95.58 259	99.78 105	99.62 54

LGP-MVS_train				99.47 54	99.57 69	98.97 66		99.48 83	96.60 242	99.10 116	99.06 124	98.71 30	99.83 140	95.58 259	99.78 105	99.62 54

CS-MVS		99.13 38	99.10 41	99.24 93	99.06 197	99.15 47	99.36 18	99.88 9	99.36 41	98.21 228	98.46 247	98.68 32	99.93 31	99.03 45	99.85 66	98.64 299

CS-MVS-test		99.13 38	99.09 42	99.26 88	99.13 182	98.97 66	99.31 26	99.88 9	99.44 31	98.16 231	98.51 239	98.64 33	99.93 31	98.91 51	99.85 66	98.88 268

TDRefinement		99.42 16	99.38 16	99.55 23	99.76 30	99.33 16	99.68 5	99.71 21	99.38 37	99.53 45	99.61 30	98.64 33	99.80 170	98.24 91	99.84 70	99.52 103

tt0805		98.69 93	98.62 90	98.90 142	99.75 34	99.30 17	99.15 52	96.97 332	98.86 91	98.87 161	97.62 308	98.63 35	98.96 358	99.41 23	98.29 316	98.45 307

nrg030		99.40 18	99.35 18	99.54 27	99.58 65	99.13 55	98.98 71	99.48 83	99.68 8	99.46 55	99.26 89	98.62 36	99.73 221	99.17 38	99.92 42	99.76 26

HPM-MVS		98.79 76	98.53 101	99.59 15	99.65 57	99.29 19	99.16 50	99.43 104	96.74 237	98.61 193	98.38 254	98.62 36	99.87 89	96.47 213	99.67 158	99.59 67
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
canonicalmvs		98.34 143	98.26 142	98.58 179	98.46 295	97.82 165	98.96 72	99.46 91	99.19 58	97.46 283	95.46 357	98.59 38	99.46 318	98.08 101	98.71 301	98.46 305

EG-PatchMatch MVS		98.99 50	99.01 48	98.94 136	99.50 93	97.47 185	98.04 162	99.59 40	98.15 136	99.40 67	99.36 72	98.58 39	99.76 205	98.78 58	99.68 152	99.59 67

test_fmvs3		99.12 40	99.41 14	98.25 215	99.76 30	95.07 265	99.05 64	99.94 1	97.78 158	99.82 12	99.84 2	98.56 40	99.71 229	99.96 1	99.96 15	99.97 1

Effi-MVS+		98.02 171	97.82 183	98.62 174	98.53 289	97.19 201	97.33 231	99.68 29	97.30 203	96.68 316	97.46 317	98.56 40	99.80 170	96.63 197	98.20 319	98.86 270

Fast-Effi-MVS+		97.67 200	97.38 212	98.57 181	98.71 257	97.43 188	97.23 238	99.45 94	94.82 293	96.13 330	96.51 337	98.52 42	99.91 47	96.19 229	98.83 294	98.37 314

xiu_mvs_v1_base_debu		97.86 184	98.17 151	96.92 298	98.98 210	93.91 299	96.45 278	99.17 196	97.85 153	98.41 217	97.14 329	98.47 43	99.92 39	98.02 104	99.05 274	96.92 353

xiu_mvs_v1_base		97.86 184	98.17 151	96.92 298	98.98 210	93.91 299	96.45 278	99.17 196	97.85 153	98.41 217	97.14 329	98.47 43	99.92 39	98.02 104	99.05 274	96.92 353

xiu_mvs_v1_base_debi		97.86 184	98.17 151	96.92 298	98.98 210	93.91 299	96.45 278	99.17 196	97.85 153	98.41 217	97.14 329	98.47 43	99.92 39	98.02 104	99.05 274	96.92 353

v7n		99.53 8	99.57 8	99.41 60	99.88 9	98.54 100	99.45 10	99.61 38	99.66 10	99.68 27	99.66 22	98.44 46	99.95 17	99.73 10	99.96 15	99.75 29

ETV-MVS		98.03 170	97.86 181	98.56 185	98.69 266	98.07 139	97.51 219	99.50 74	98.10 137	97.50 280	95.51 355	98.41 47	99.88 71	96.27 225	99.24 252	97.71 342

COLMAP_ROB	96.50 10	98.99 50	98.85 63	99.41 60	99.58 65	99.10 60	98.74 84	99.56 56	99.09 71	99.33 81	99.19 101	98.40 48	99.72 228	95.98 239	99.76 120	99.42 146
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
TranMVSNet+NR-MVSNet		99.17 33	99.07 45	99.46 56	99.37 131	98.87 73	98.39 128	99.42 107	99.42 34	99.36 76	99.06 124	98.38 49	99.95 17	98.34 87	99.90 55	99.57 78

SED-MVS		98.91 61	98.72 74	99.49 48	99.49 100	99.17 39	98.10 154	99.31 146	98.03 140	99.66 29	99.02 136	98.36 50	99.88 71	96.91 169	99.62 172	99.41 149

test_241102_ONE					99.49 100	99.17 39		99.31 146	97.98 142	99.66 29	98.90 171	98.36 50	99.48 313

ACMP	95.32 15	98.41 134	98.09 160	99.36 64	99.51 90	98.79 80	97.68 198	99.38 115	95.76 271	98.81 171	98.82 191	98.36 50	99.82 150	94.75 273	99.77 109	99.48 122
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
casdiffmvs		98.95 57	99.00 49	98.81 150	99.38 125	97.33 191	97.82 185	99.57 49	99.17 59	99.35 78	99.17 108	98.35 53	99.69 236	98.46 81	99.73 127	99.41 149
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_0402		98.76 82	98.71 76	98.93 137	99.56 76	98.14 131	98.45 123	99.34 134	99.28 48	98.95 141	98.91 168	98.34 54	99.79 183	95.63 256	99.91 48	98.86 270

xiu_mvs_v2_base		97.16 239	97.49 206	96.17 318	98.54 287	92.46 326	95.45 321	98.84 257	97.25 208	97.48 282	96.49 338	98.31 55	99.90 52	96.34 221	98.68 304	96.15 364

VPA-MVSNet		99.30 24	99.30 24	99.28 83	99.49 100	98.36 114	99.00 68	99.45 94	99.63 13	99.52 47	99.44 60	98.25 56	99.88 71	99.09 40	99.84 70	99.62 54

MVS_111021_LR		98.30 147	98.12 158	98.83 147	99.16 175	98.03 143	96.09 295	99.30 154	97.58 172	98.10 238	98.24 266	98.25 56	99.34 333	96.69 194	99.65 164	99.12 230

PS-CasMVS		99.40 18	99.33 21	99.62 6	99.71 44	99.10 60	99.29 32	99.53 68	99.53 23	99.46 55	99.41 66	98.23 58	99.95 17	98.89 54	99.95 19	99.81 16

DTE-MVSNet		99.43 15	99.35 18	99.66 4	99.71 44	99.30 17	99.31 26	99.51 72	99.64 11	99.56 38	99.46 55	98.23 58	99.97 4	98.78 58	99.93 31	99.72 32

baseline		98.96 56	99.02 47	98.76 160	99.38 125	97.26 195	98.49 116	99.50 74	98.86 91	99.19 106	99.06 124	98.23 58	99.69 236	98.71 65	99.76 120	99.33 187

PC_three_1452									93.27 321	99.40 67	98.54 235	98.22 61	97.00 373	95.17 265	99.45 221	99.49 112

Gipuma		99.03 47	99.16 32	98.64 170	99.94 2	98.51 102	99.32 22	99.75 19	99.58 21	98.60 195	99.62 28	98.22 61	99.51 308	97.70 125	99.73 127	97.89 330
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
LCM-MVSNet-Re		98.64 105	98.48 110	99.11 109	98.85 235	98.51 102	98.49 116	99.83 13	98.37 112	99.69 25	99.46 55	98.21 63	99.92 39	94.13 295	99.30 243	98.91 264

tfpnnormal		98.90 63	98.90 58	98.91 140	99.67 55	97.82 165	99.00 68	99.44 98	99.45 30	99.51 50	99.24 94	98.20 64	99.86 98	95.92 241	99.69 147	99.04 239

mvsany_test3		98.87 66	98.92 56	98.74 166	99.38 125	96.94 212	98.58 102	99.10 211	96.49 246	99.96 2	99.81 5	98.18 65	99.45 319	98.97 49	99.79 100	99.83 13

DVP-MVS++		98.90 63	98.70 79	99.51 43	98.43 298	99.15 47	99.43 11	99.32 141	98.17 132	99.26 96	99.02 136	98.18 65	99.88 71	97.07 157	99.45 221	99.49 112

OPU-MVS				98.82 148	98.59 281	98.30 116	98.10 154				98.52 238	98.18 65	98.75 365	94.62 277	99.48 218	99.41 149

OPM-MVS		98.56 115	98.32 136	99.25 91	99.41 122	98.73 85	97.13 247	99.18 192	97.10 222	98.75 178	98.92 167	98.18 65	99.65 264	96.68 195	99.56 195	99.37 170
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PEN-MVS		99.41 17	99.34 20	99.62 6	99.73 36	99.14 52	99.29 32	99.54 65	99.62 16	99.56 38	99.42 63	98.16 69	99.96 11	98.78 58	99.93 31	99.77 22

DeepPCF-MVS	96.93 5	98.32 144	98.01 168	99.23 95	98.39 303	98.97 66	95.03 332	99.18 192	96.88 231	99.33 81	98.78 197	98.16 69	99.28 343	96.74 188	99.62 172	99.44 139

MVS_111021_HR		98.25 155	98.08 163	98.75 162	99.09 189	97.46 186	95.97 298	99.27 167	97.60 171	97.99 246	98.25 265	98.15 71	99.38 330	96.87 177	99.57 192	99.42 146

Fast-Effi-MVS+-dtu		98.27 151	98.09 160	98.81 150	98.43 298	98.11 132	97.61 207	99.50 74	98.64 98	97.39 288	97.52 313	98.12 72	99.95 17	96.90 174	98.71 301	98.38 312

pcd_1.5k_mvsjas		8.17 347	10.90 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	98.07 73	0.00 381	0.00 379	0.00 379	0.00 377

PS-MVSNAJss		99.46 12	99.49 10	99.35 69	99.90 4	98.15 129	99.20 44	99.65 33	99.48 26	99.92 4	99.71 16	98.07 73	99.96 11	99.53 17	100.00 1	99.93 4

PS-MVSNAJ		97.08 244	97.39 211	96.16 320	98.56 285	92.46 326	95.24 327	98.85 256	97.25 208	97.49 281	95.99 347	98.07 73	99.90 52	96.37 218	98.67 305	96.12 365

UA-Net		99.47 11	99.40 15	99.70 2	99.49 100	99.29 19	99.80 3	99.72 20	99.82 3	99.04 127	99.81 5	98.05 76	99.96 11	98.85 55	99.99 5	99.86 11

ACMMP_NAP		98.75 83	98.48 110	99.57 16	99.58 65	99.29 19	97.82 185	99.25 173	96.94 228	98.78 172	99.12 118	98.02 77	99.84 126	97.13 153	99.67 158	99.59 67

MP-MVS-pluss		98.57 114	98.23 145	99.60 11	99.69 52	99.35 12	97.16 245	99.38 115	94.87 292	98.97 138	98.99 148	98.01 78	99.88 71	97.29 142	99.70 144	99.58 73
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ZNCC-MVS		98.68 98	98.40 122	99.54 27	99.57 69	99.21 28	98.46 121	99.29 161	97.28 205	98.11 237	98.39 252	98.00 79	99.87 89	96.86 179	99.64 166	99.55 89

PGM-MVS		98.66 102	98.37 128	99.55 23	99.53 86	99.18 38	98.23 139	99.49 81	97.01 226	98.69 182	98.88 178	98.00 79	99.89 62	95.87 245	99.59 183	99.58 73

SteuartSystems-ACMMP		98.79 76	98.54 100	99.54 27	99.73 36	99.16 43	98.23 139	99.31 146	97.92 147	98.90 151	98.90 171	98.00 79	99.88 71	96.15 232	99.72 134	99.58 73
Skip Steuart: Steuart Systems R&D Blog.
TinyColmap		97.89 180	97.98 170	97.60 262	98.86 233	94.35 283	96.21 291	99.44 98	97.45 189	99.06 120	98.88 178	97.99 82	99.28 343	94.38 289	99.58 188	99.18 221

HFP-MVS		98.71 87	98.44 117	99.51 43	99.49 100	99.16 43	98.52 109	99.31 146	97.47 182	98.58 199	98.50 243	97.97 83	99.85 110	96.57 201	99.59 183	99.53 100

3Dnovator	98.27 2	98.81 74	98.73 72	99.05 124	98.76 248	97.81 167	99.25 39	99.30 154	98.57 107	98.55 204	99.33 79	97.95 84	99.90 52	97.16 148	99.67 158	99.44 139

mvsany_test1		97.60 205	97.54 202	97.77 248	97.72 336	95.35 254	95.36 324	97.13 328	94.13 309	99.71 21	99.33 79	97.93 85	99.30 339	97.60 128	98.94 289	98.67 298

test_0728_THIRD									98.17 132	99.08 118	99.02 136	97.89 86	99.88 71	97.07 157	99.71 139	99.70 38

APD-MVS_3200maxsize		98.84 70	98.61 94	99.53 34	99.19 165	99.27 22	98.49 116	99.33 139	98.64 98	99.03 130	98.98 152	97.89 86	99.85 110	96.54 209	99.42 225	99.46 131

CP-MVS		98.70 90	98.42 120	99.52 39	99.36 132	99.12 57	98.72 87	99.36 123	97.54 177	98.30 223	98.40 251	97.86 88	99.89 62	96.53 210	99.72 134	99.56 82

TSAR-MVS + MP.		98.63 107	98.49 109	99.06 123	99.64 60	97.90 156	98.51 113	98.94 235	96.96 227	99.24 101	98.89 177	97.83 89	99.81 163	96.88 176	99.49 217	99.48 122
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
region2R		98.69 93	98.40 122	99.54 27	99.53 86	99.17 39	98.52 109	99.31 146	97.46 187	98.44 214	98.51 239	97.83 89	99.88 71	96.46 214	99.58 188	99.58 73

APDe-MVS		98.99 50	98.79 68	99.60 11	99.21 158	99.15 47	98.87 78	99.48 83	97.57 173	99.35 78	99.24 94	97.83 89	99.89 62	97.88 114	99.70 144	99.75 29

FMVSNet1		99.17 33	99.17 30	99.17 99	99.55 80	98.24 120	99.20 44	99.44 98	99.21 52	99.43 60	99.55 40	97.82 92	99.86 98	98.42 84	99.89 59	99.41 149

SF-MVS		98.53 123	98.27 141	99.32 78	99.31 139	98.75 81	98.19 143	99.41 108	96.77 236	98.83 166	98.90 171	97.80 93	99.82 150	95.68 255	99.52 207	99.38 168

PHI-MVS		98.29 150	97.95 172	99.34 72	98.44 297	99.16 43	98.12 151	99.38 115	96.01 264	98.06 241	98.43 249	97.80 93	99.67 248	95.69 254	99.58 188	99.20 214

APD_test1		98.83 71	98.66 84	99.34 72	99.78 25	99.47 6	98.42 126	99.45 94	98.28 123	98.98 134	99.19 101	97.76 95	99.58 287	96.57 201	99.55 198	98.97 252

RE-MVS-def			98.58 97		99.20 162	99.38 8	98.48 119	99.30 154	98.64 98	98.95 141	98.96 157	97.75 96		96.56 205	99.39 228	99.45 135

ACMMPR		98.70 90	98.42 120	99.54 27	99.52 88	99.14 52	98.52 109	99.31 146	97.47 182	98.56 202	98.54 235	97.75 96	99.88 71	96.57 201	99.59 183	99.58 73

ACMMP		98.75 83	98.50 105	99.52 39	99.56 76	99.16 43	98.87 78	99.37 119	97.16 219	98.82 169	99.01 145	97.71 98	99.87 89	96.29 224	99.69 147	99.54 93
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
EIA-MVS		98.00 173	97.74 187	98.80 152	98.72 254	98.09 133	98.05 160	99.60 39	97.39 194	96.63 318	95.55 354	97.68 99	99.80 170	96.73 190	99.27 247	98.52 303

GST-MVS		98.61 110	98.30 137	99.52 39	99.51 90	99.20 34	98.26 137	99.25 173	97.44 190	98.67 184	98.39 252	97.68 99	99.85 110	96.00 237	99.51 209	99.52 103

CSCG		98.68 98	98.50 105	99.20 97	99.45 113	98.63 89	98.56 104	99.57 49	97.87 151	98.85 162	98.04 283	97.66 101	99.84 126	96.72 191	99.81 84	99.13 229

AllTest		98.44 132	98.20 147	99.16 102	99.50 93	98.55 97	98.25 138	99.58 42	96.80 233	98.88 157	99.06 124	97.65 102	99.57 289	94.45 283	99.61 177	99.37 170

TestCases				99.16 102	99.50 93	98.55 97		99.58 42	96.80 233	98.88 157	99.06 124	97.65 102	99.57 289	94.45 283	99.61 177	99.37 170

test20.03		98.78 78	98.77 70	98.78 157	99.46 110	97.20 200	97.78 187	99.24 178	99.04 76	99.41 64	98.90 171	97.65 102	99.76 205	97.70 125	99.79 100	99.39 161

test_one_0601					99.39 124	99.20 34		99.31 146	98.49 109	98.66 186	99.02 136	97.64 105

ITE_SJBPF				98.87 143	99.22 156	98.48 104		99.35 128	97.50 179	98.28 225	98.60 230	97.64 105	99.35 332	93.86 303	99.27 247	98.79 283

mPP-MVS		98.64 105	98.34 132	99.54 27	99.54 83	99.17 39	98.63 95	99.24 178	97.47 182	98.09 239	98.68 213	97.62 107	99.89 62	96.22 227	99.62 172	99.57 78

DVP-MVS		98.77 81	98.52 102	99.52 39	99.50 93	99.21 28	98.02 164	98.84 257	97.97 143	99.08 118	99.02 136	97.61 108	99.88 71	96.99 163	99.63 169	99.48 122
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					99.50 93	99.21 28	98.17 147	99.35 128	97.97 143	99.26 96	99.06 124	97.61 108

9.14			97.78 184		99.07 193		97.53 216	99.32 141	95.53 275	98.54 206	98.70 210	97.58 110	99.76 205	94.32 290	99.46 219

CLD-MVS		97.49 212	97.16 225	98.48 195	99.07 193	97.03 208	94.71 339	99.21 182	94.46 300	98.06 241	97.16 327	97.57 111	99.48 313	94.46 282	99.78 105	98.95 255
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DeepC-MVS_fast	96.85 6	98.30 147	98.15 155	98.75 162	98.61 277	97.23 196	97.76 191	99.09 213	97.31 202	98.75 178	98.66 218	97.56 112	99.64 267	96.10 236	99.55 198	99.39 161
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
EGC-MVSNET		85.24 341	80.54 344	99.34 72	99.77 27	99.20 34	99.08 58	99.29 161	12.08 377	20.84 378	99.42 63	97.55 113	99.85 110	97.08 156	99.72 134	98.96 254

PM-MVS		98.82 72	98.72 74	99.12 107	99.64 60	98.54 100	97.98 170	99.68 29	97.62 168	99.34 80	99.18 104	97.54 114	99.77 200	97.79 119	99.74 124	99.04 239

XVG-ACMP-BASELINE		98.56 115	98.34 132	99.22 96	99.54 83	98.59 94	97.71 195	99.46 91	97.25 208	98.98 134	98.99 148	97.54 114	99.84 126	95.88 242	99.74 124	99.23 209

SR-MVS		98.71 87	98.43 118	99.57 16	99.18 172	99.35 12	98.36 130	99.29 161	98.29 121	98.88 157	98.85 184	97.53 116	99.87 89	96.14 233	99.31 240	99.48 122

DPE-MVS		98.59 113	98.26 142	99.57 16	99.27 146	99.15 47	97.01 250	99.39 113	97.67 164	99.44 59	98.99 148	97.53 116	99.89 62	95.40 263	99.68 152	99.66 45
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
SMA-MVS		98.40 136	98.03 167	99.51 43	99.16 175	99.21 28	98.05 160	99.22 181	94.16 308	98.98 134	99.10 121	97.52 118	99.79 183	96.45 215	99.64 166	99.53 100
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
test_241102_TWO								99.30 154	98.03 140	99.26 96	99.02 136	97.51 119	99.88 71	96.91 169	99.60 179	99.66 45

XVS		98.72 86	98.45 115	99.53 34	99.46 110	99.21 28	98.65 93	99.34 134	98.62 102	97.54 276	98.63 225	97.50 120	99.83 140	96.79 182	99.53 204	99.56 82

X-MVStestdata		94.32 312	92.59 330	99.53 34	99.46 110	99.21 28	98.65 93	99.34 134	98.62 102	97.54 276	45.85 375	97.50 120	99.83 140	96.79 182	99.53 204	99.56 82

DELS-MVS		98.27 151	98.20 147	98.48 195	98.86 233	96.70 220	95.60 315	99.20 184	97.73 160	98.45 213	98.71 207	97.50 120	99.82 150	98.21 93	99.59 183	98.93 260
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
SR-MVS-dyc-post		98.81 74	98.55 99	99.57 16	99.20 162	99.38 8	98.48 119	99.30 154	98.64 98	98.95 141	98.96 157	97.49 123	99.86 98	96.56 205	99.39 228	99.45 135

TSAR-MVS + GP.		98.18 161	97.98 170	98.77 159	98.71 257	97.88 157	96.32 286	98.66 277	96.33 251	99.23 103	98.51 239	97.48 124	99.40 326	97.16 148	99.46 219	99.02 242

new-patchmatchnet		98.35 142	98.74 71	97.18 286	99.24 151	92.23 332	96.42 281	99.48 83	98.30 118	99.69 25	99.53 45	97.44 125	99.82 150	98.84 56	99.77 109	99.49 112

PMVS	91.26 20	97.86 184	97.94 174	97.65 258	99.71 44	97.94 154	98.52 109	98.68 276	98.99 80	97.52 278	99.35 73	97.41 126	98.18 370	91.59 339	99.67 158	96.82 356
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MP-MVS		98.46 130	98.09 160	99.54 27	99.57 69	99.22 27	98.50 115	99.19 188	97.61 170	97.58 272	98.66 218	97.40 127	99.88 71	94.72 276	99.60 179	99.54 93
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MSDG		97.71 197	97.52 204	98.28 214	98.91 224	96.82 215	94.42 349	99.37 119	97.65 166	98.37 222	98.29 264	97.40 127	99.33 335	94.09 296	99.22 254	98.68 297

KD-MVS_self_test		99.25 27	99.18 29	99.44 57	99.63 62	99.06 64	98.69 91	99.54 65	99.31 45	99.62 36	99.53 45	97.36 129	99.86 98	99.24 34	99.71 139	99.39 161

LS3D		98.63 107	98.38 127	99.36 64	97.25 355	99.38 8	99.12 56	99.32 141	99.21 52	98.44 214	98.88 178	97.31 130	99.80 170	96.58 199	99.34 236	98.92 261

EI-MVSNet-UG-set		98.69 93	98.71 76	98.62 174	99.10 186	96.37 225	97.23 238	98.87 248	99.20 54	99.19 106	98.99 148	97.30 131	99.85 110	98.77 61	99.79 100	99.65 49

WR-MVS_H		99.33 23	99.22 28	99.65 5	99.71 44	99.24 25	99.32 22	99.55 60	99.46 29	99.50 51	99.34 77	97.30 131	99.93 31	98.90 52	99.93 31	99.77 22

EI-MVSNet-Vis-set		98.68 98	98.70 79	98.63 173	99.09 189	96.40 224	97.23 238	98.86 253	99.20 54	99.18 110	98.97 154	97.29 133	99.85 110	98.72 64	99.78 105	99.64 50

pmmvs-eth3d		98.47 129	98.34 132	98.86 144	99.30 142	97.76 170	97.16 245	99.28 164	95.54 274	99.42 63	99.19 101	97.27 134	99.63 270	97.89 111	99.97 12	99.20 214

CNVR-MVS		98.17 163	97.87 180	99.07 117	98.67 269	98.24 120	97.01 250	98.93 237	97.25 208	97.62 268	98.34 259	97.27 134	99.57 289	96.42 216	99.33 237	99.39 161

OMC-MVS		97.88 182	97.49 206	99.04 126	98.89 230	98.63 89	96.94 254	99.25 173	95.02 287	98.53 207	98.51 239	97.27 134	99.47 316	93.50 312	99.51 209	99.01 243

DP-MVS		98.93 59	98.81 67	99.28 83	99.21 158	98.45 106	98.46 121	99.33 139	99.63 13	99.48 52	99.15 114	97.23 137	99.75 212	97.17 147	99.66 163	99.63 53

MVS_Test		98.18 161	98.36 129	97.67 256	98.48 293	94.73 273	98.18 144	99.02 227	97.69 163	98.04 244	99.11 119	97.22 138	99.56 292	98.57 74	98.90 292	98.71 291

dcpmvs_2		98.78 78	99.11 39	97.78 247	99.56 76	93.67 308	99.06 62	99.86 11	99.50 24	99.66 29	99.26 89	97.21 139	99.99 2	98.00 107	99.91 48	99.68 41

MCST-MVS		98.00 173	97.63 198	99.10 111	99.24 151	98.17 128	96.89 259	98.73 274	95.66 272	97.92 248	97.70 303	97.17 140	99.66 259	96.18 231	99.23 253	99.47 129

test_vis3_rt		99.14 35	99.17 30	99.07 117	99.78 25	98.38 109	98.92 75	99.94 1	97.80 156	99.91 5	99.67 20	97.15 141	98.91 361	99.76 8	99.56 195	99.92 5

FC-MVSNet-test		99.27 25	99.25 26	99.34 72	99.77 27	98.37 111	99.30 31	99.57 49	99.61 18	99.40 67	99.50 49	97.12 142	99.85 110	99.02 46	99.94 27	99.80 17

MIMVSNet1		99.38 20	99.32 22	99.55 23	99.86 14	99.19 37	99.41 13	99.59 40	99.59 19	99.71 21	99.57 35	97.12 142	99.90 52	99.21 35	99.87 63	99.54 93

3Dnovator+	97.89 3	98.69 93	98.51 103	99.24 93	98.81 243	98.40 107	99.02 65	99.19 188	98.99 80	98.07 240	99.28 85	97.11 144	99.84 126	96.84 180	99.32 238	99.47 129

patch_mono-2		98.51 126	98.63 88	98.17 221	99.38 125	94.78 270	97.36 229	99.69 24	98.16 135	98.49 210	99.29 84	97.06 145	99.97 4	98.29 90	99.91 48	99.76 26

Anonymous20240529		98.93 59	98.87 59	99.12 107	99.19 165	98.22 125	99.01 66	98.99 233	99.25 50	99.54 41	99.37 69	97.04 146	99.80 170	97.89 111	99.52 207	99.35 180

MSLP-MVS++		98.02 171	98.14 157	97.64 260	98.58 282	95.19 260	97.48 221	99.23 180	97.47 182	97.90 250	98.62 227	97.04 146	98.81 364	97.55 129	99.41 226	98.94 259

APD-MVS		98.10 165	97.67 192	99.42 58	99.11 184	98.93 71	97.76 191	99.28 164	94.97 289	98.72 181	98.77 199	97.04 146	99.85 110	93.79 305	99.54 200	99.49 112
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
segment_acmp												97.02 149

CP-MVSNet		99.21 32	99.09 42	99.56 21	99.65 57	98.96 70	99.13 54	99.34 134	99.42 34	99.33 81	99.26 89	97.01 150	99.94 26	98.74 62	99.93 31	99.79 18

ambc				98.24 217	98.82 241	95.97 236	98.62 97	99.00 232		99.27 92	99.21 98	96.99 151	99.50 309	96.55 208	99.50 216	99.26 203

MTAPA		98.88 65	98.64 87	99.61 9	99.67 55	99.36 11	98.43 124	99.20 184	98.83 95	98.89 153	98.90 171	96.98 152	99.92 39	97.16 148	99.70 144	99.56 82

v8		99.01 48	99.16 32	98.57 181	99.47 109	96.31 228	98.90 76	99.47 89	99.03 77	99.52 47	99.57 35	96.93 153	99.81 163	99.60 12	99.98 9	99.60 61

QAPM		97.31 225	96.81 246	98.82 148	98.80 246	97.49 184	99.06 62	99.19 188	90.22 352	97.69 265	99.16 110	96.91 154	99.90 52	90.89 350	99.41 226	99.07 233

CDPH-MVS		97.26 229	96.66 256	99.07 117	99.00 206	98.15 129	96.03 296	99.01 230	91.21 346	97.79 259	97.85 295	96.89 155	99.69 236	92.75 325	99.38 231	99.39 161

PVSNet_Blended_VisFu		98.17 163	98.15 155	98.22 218	99.73 36	95.15 261	97.36 229	99.68 29	94.45 302	98.99 133	99.27 87	96.87 156	99.94 26	97.13 153	99.91 48	99.57 78

Anonymous20231211		99.27 25	99.27 25	99.26 88	99.29 143	98.18 126	99.49 8	99.51 72	99.70 7	99.80 13	99.68 18	96.84 157	99.83 140	99.21 35	99.91 48	99.77 22

V42		98.78 78	98.78 69	98.76 160	99.44 114	97.04 207	98.27 136	99.19 188	97.87 151	99.25 100	99.16 110	96.84 157	99.78 194	99.21 35	99.84 70	99.46 131

PMMVS2		98.07 169	98.08 163	98.04 233	99.41 122	94.59 279	94.59 346	99.40 110	97.50 179	98.82 169	98.83 188	96.83 159	99.84 126	97.50 134	99.81 84	99.71 33

PVSNet_BlendedMVS		97.55 209	97.53 203	97.60 262	98.92 221	93.77 306	96.64 271	99.43 104	94.49 298	97.62 268	99.18 104	96.82 160	99.67 248	94.73 274	99.93 31	99.36 176

PVSNet_Blended		96.88 255	96.68 253	97.47 275	98.92 221	93.77 306	94.71 339	99.43 104	90.98 348	97.62 268	97.36 323	96.82 160	99.67 248	94.73 274	99.56 195	98.98 248

ab-mvs		98.41 134	98.36 129	98.59 178	99.19 165	97.23 196	99.32 22	98.81 262	97.66 165	98.62 191	99.40 68	96.82 160	99.80 170	95.88 242	99.51 209	98.75 288

FIs		99.14 35	99.09 42	99.29 81	99.70 50	98.28 117	99.13 54	99.52 71	99.48 26	99.24 101	99.41 66	96.79 163	99.82 150	98.69 67	99.88 60	99.76 26

UniMVSNet (Re)		98.87 66	98.71 76	99.35 69	99.24 151	98.73 85	97.73 194	99.38 115	98.93 86	99.12 112	98.73 204	96.77 164	99.86 98	98.63 71	99.80 95	99.46 131

API-MVS		97.04 247	96.91 238	97.42 278	97.88 330	98.23 124	98.18 144	98.50 286	97.57 173	97.39 288	96.75 334	96.77 164	99.15 352	90.16 353	99.02 281	94.88 370

diffmvs		98.22 157	98.24 144	98.17 221	99.00 206	95.44 251	96.38 283	99.58 42	97.79 157	98.53 207	98.50 243	96.76 166	99.74 217	97.95 110	99.64 166	99.34 182
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DU-MVS		98.82 72	98.63 88	99.39 63	99.16 175	98.74 82	97.54 215	99.25 173	98.84 94	99.06 120	98.76 201	96.76 166	99.93 31	98.57 74	99.77 109	99.50 108

Baseline_NR-MVSNet		98.98 53	98.86 62	99.36 64	99.82 21	98.55 97	97.47 223	99.57 49	99.37 38	99.21 104	99.61 30	96.76 166	99.83 140	98.06 102	99.83 77	99.71 33

VPNet		98.87 66	98.83 64	99.01 129	99.70 50	97.62 180	98.43 124	99.35 128	99.47 28	99.28 90	99.05 131	96.72 169	99.82 150	98.09 100	99.36 232	99.59 67

UniMVSNet_NR-MVSNet		98.86 69	98.68 82	99.40 62	99.17 173	98.74 82	97.68 198	99.40 110	99.14 60	99.06 120	98.59 231	96.71 170	99.93 31	98.57 74	99.77 109	99.53 100

LF4IMVS		97.90 178	97.69 191	98.52 190	99.17 173	97.66 176	97.19 244	99.47 89	96.31 253	97.85 255	98.20 270	96.71 170	99.52 304	94.62 277	99.72 134	98.38 312

v148		98.45 131	98.60 95	98.00 235	99.44 114	94.98 266	97.44 225	99.06 216	98.30 118	99.32 87	98.97 154	96.65 172	99.62 272	98.37 85	99.85 66	99.39 161

v10		98.97 54	99.11 39	98.55 186	99.44 114	96.21 230	98.90 76	99.55 60	98.73 96	99.48 52	99.60 32	96.63 173	99.83 140	99.70 11	99.99 5	99.61 60

test_fmvs2		98.70 90	98.97 53	97.89 240	99.54 83	94.05 290	98.55 105	99.92 5	96.78 235	99.72 19	99.78 8	96.60 174	99.67 248	99.91 2	99.90 55	99.94 3

OpenMVS	96.65 7	97.09 243	96.68 253	98.32 209	98.32 306	97.16 204	98.86 80	99.37 119	89.48 356	96.29 329	99.15 114	96.56 175	99.90 52	92.90 319	99.20 257	97.89 330

UGNet		98.53 123	98.45 115	98.79 154	97.94 326	96.96 210	99.08 58	98.54 283	99.10 68	96.82 313	99.47 54	96.55 176	99.84 126	98.56 77	99.94 27	99.55 89
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
TEST9					98.71 257	98.08 137	95.96 300	99.03 224	91.40 343	95.85 336	97.53 311	96.52 177	99.76 205

Test By Simon												96.52 177

train_agg		97.10 241	96.45 266	99.07 117	98.71 257	98.08 137	95.96 300	99.03 224	91.64 338	95.85 336	97.53 311	96.47 179	99.76 205	93.67 306	99.16 263	99.36 176

test_8					98.67 269	98.01 144	95.91 305	99.02 227	91.64 338	95.79 338	97.50 314	96.47 179	99.76 205

Effi-MVS+-dtu		98.26 153	97.90 178	99.35 69	98.02 323	99.49 5	98.02 164	99.16 199	98.29 121	97.64 267	97.99 285	96.44 181	99.95 17	96.66 196	98.93 290	98.60 300

ppachtmachnet_test		97.50 210	97.74 187	96.78 307	98.70 261	91.23 346	94.55 347	99.05 219	96.36 250	99.21 104	98.79 196	96.39 182	99.78 194	96.74 188	99.82 80	99.34 182

OurMVSNet-221017-0		99.37 21	99.31 23	99.53 34	99.91 3	98.98 65	99.63 6	99.58 42	99.44 31	99.78 15	99.76 10	96.39 182	99.92 39	99.44 22	99.92 42	99.68 41

NR-MVSNet		98.95 57	98.82 65	99.36 64	99.16 175	98.72 87	99.22 41	99.20 184	99.10 68	99.72 19	98.76 201	96.38 184	99.86 98	98.00 107	99.82 80	99.50 108

v1192		98.60 111	98.66 84	98.41 202	99.27 146	95.88 238	97.52 217	99.36 123	97.41 192	99.33 81	99.20 100	96.37 185	99.82 150	99.57 14	99.92 42	99.55 89

ZD-MVS					99.01 205	98.84 75		99.07 215	94.10 310	98.05 243	98.12 275	96.36 186	99.86 98	92.70 327	99.19 260

v1144		98.60 111	98.66 84	98.41 202	99.36 132	95.90 237	97.58 211	99.34 134	97.51 178	99.27 92	99.15 114	96.34 187	99.80 170	99.47 20	99.93 31	99.51 105

mvs_anonymous		97.83 192	98.16 154	96.87 301	98.18 315	91.89 334	97.31 232	98.90 243	97.37 196	98.83 166	99.46 55	96.28 188	99.79 183	98.90 52	98.16 323	98.95 255

test_vis1_rt		97.75 194	97.72 190	97.83 243	98.81 243	96.35 226	97.30 233	99.69 24	94.61 296	97.87 252	98.05 282	96.26 189	98.32 369	98.74 62	98.18 320	98.82 273

DSMNet-mixed		97.42 218	97.60 200	96.87 301	99.15 179	91.46 338	98.54 107	99.12 207	92.87 328	97.58 272	99.63 27	96.21 190	99.90 52	95.74 251	99.54 200	99.27 200

test_f		98.67 101	98.87 59	98.05 232	99.72 42	95.59 244	98.51 113	99.81 14	96.30 255	99.78 15	99.82 4	96.14 191	98.63 366	99.82 3	99.93 31	99.95 2

TAPA-MVS	96.21 11	96.63 265	95.95 276	98.65 169	98.93 217	98.09 133	96.93 256	99.28 164	83.58 369	98.13 235	97.78 297	96.13 192	99.40 326	93.52 310	99.29 245	98.45 307
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
v1240		98.55 119	98.62 90	98.32 209	99.22 156	95.58 245	97.51 219	99.45 94	97.16 219	99.45 58	99.24 94	96.12 193	99.85 110	99.60 12	99.88 60	99.55 89

RPSCF		98.62 109	98.36 129	99.42 58	99.65 57	99.42 7	98.55 105	99.57 49	97.72 162	98.90 151	99.26 89	96.12 193	99.52 304	95.72 252	99.71 139	99.32 189

MS-PatchMatch		97.68 199	97.75 186	97.45 276	98.23 313	93.78 305	97.29 234	98.84 257	96.10 260	98.64 188	98.65 220	96.04 195	99.36 331	96.84 180	99.14 266	99.20 214

v1921920		98.54 121	98.60 95	98.38 205	99.20 162	95.76 243	97.56 213	99.36 123	97.23 214	99.38 71	99.17 108	96.02 196	99.84 126	99.57 14	99.90 55	99.54 93

HPM-MVS++		98.10 165	97.64 197	99.48 51	99.09 189	99.13 55	97.52 217	98.75 271	97.46 187	96.90 308	97.83 296	96.01 197	99.84 126	95.82 249	99.35 234	99.46 131

Anonymous20231206		98.21 158	98.21 146	98.20 219	99.51 90	95.43 252	98.13 149	99.32 141	96.16 258	98.93 148	98.82 191	96.00 198	99.83 140	97.32 141	99.73 127	99.36 176

EI-MVSNet		98.40 136	98.51 103	98.04 233	99.10 186	94.73 273	97.20 242	98.87 248	98.97 82	99.06 120	99.02 136	96.00 198	99.80 170	98.58 72	99.82 80	99.60 61

IterMVS-LS		98.55 119	98.70 79	98.09 225	99.48 107	94.73 273	97.22 241	99.39 113	98.97 82	99.38 71	99.31 83	96.00 198	99.93 31	98.58 72	99.97 12	99.60 61
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
NCCC		97.86 184	97.47 209	99.05 124	98.61 277	98.07 139	96.98 252	98.90 243	97.63 167	97.04 299	97.93 291	95.99 201	99.66 259	95.31 264	98.82 295	99.43 143

our_test_3		97.39 220	97.73 189	96.34 313	98.70 261	89.78 351	94.61 345	98.97 234	96.50 245	99.04 127	98.85 184	95.98 202	99.84 126	97.26 144	99.67 158	99.41 149

v2v482		98.56 115	98.62 90	98.37 206	99.42 120	95.81 241	97.58 211	99.16 199	97.90 149	99.28 90	99.01 145	95.98 202	99.79 183	99.33 25	99.90 55	99.51 105

MVS		93.19 329	92.09 333	96.50 311	96.91 359	94.03 293	98.07 157	98.06 306	68.01 373	94.56 356	96.48 339	95.96 204	99.30 339	83.84 366	96.89 351	96.17 362

MVP-Stereo		98.08 168	97.92 176	98.57 181	98.96 213	96.79 216	97.90 177	99.18 192	96.41 249	98.46 212	98.95 161	95.93 205	99.60 279	96.51 211	98.98 286	99.31 193
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
test_prior2							95.74 311		96.48 247	96.11 331	97.63 307	95.92 206		94.16 291	99.20 257

AdaColmap		97.14 240	96.71 251	98.46 197	98.34 305	97.80 168	96.95 253	98.93 237	95.58 273	96.92 303	97.66 304	95.87 207	99.53 300	90.97 347	99.14 266	98.04 325

mvsmamba		99.24 31	99.15 37	99.49 48	99.83 19	98.85 74	99.41 13	99.55 60	99.54 22	99.40 67	99.52 47	95.86 208	99.91 47	99.32 26	99.95 19	99.70 38

v144192		98.54 121	98.57 98	98.45 198	99.21 158	95.98 235	97.63 204	99.36 123	97.15 221	99.32 87	99.18 104	95.84 209	99.84 126	99.50 18	99.91 48	99.54 93

PatchMatch-RL		97.24 232	96.78 247	98.61 176	99.03 204	97.83 162	96.36 284	99.06 216	93.49 320	97.36 290	97.78 297	95.75 210	99.49 310	93.44 313	98.77 296	98.52 303

F-COLMAP		97.30 226	96.68 253	99.14 105	99.19 165	98.39 108	97.27 237	99.30 154	92.93 326	96.62 319	98.00 284	95.73 211	99.68 245	92.62 328	98.46 312	99.35 180

PMMVS		96.51 269	95.98 275	98.09 225	97.53 346	95.84 239	94.92 335	98.84 257	91.58 340	96.05 334	95.58 353	95.68 212	99.66 259	95.59 258	98.09 327	98.76 287

N_pmnet		97.63 204	97.17 224	98.99 131	99.27 146	97.86 159	95.98 297	93.41 362	95.25 283	99.47 54	98.90 171	95.63 213	99.85 110	96.91 169	99.73 127	99.27 200

WR-MVS		98.40 136	98.19 149	99.03 127	99.00 206	97.65 177	96.85 260	98.94 235	98.57 107	98.89 153	98.50 243	95.60 214	99.85 110	97.54 131	99.85 66	99.59 67

CANet		97.87 183	97.76 185	98.19 220	97.75 335	95.51 248	96.76 265	99.05 219	97.74 159	96.93 302	98.21 269	95.59 215	99.89 62	97.86 116	99.93 31	99.19 219

1314		95.74 290	95.60 285	96.17 318	97.53 346	92.75 323	98.07 157	98.31 294	91.22 345	94.25 357	96.68 335	95.53 216	99.03 354	91.64 338	97.18 346	96.74 357

114514_t		96.50 271	95.77 278	98.69 167	99.48 107	97.43 188	97.84 184	99.55 60	81.42 371	96.51 323	98.58 232	95.53 216	99.67 248	93.41 314	99.58 188	98.98 248

test12				98.93 137	98.58 282	97.83 162		98.66 277		96.53 321		95.51 218	99.69 236		99.13 268	99.27 200

旧先验1					98.82 241	97.45 187		98.76 268			98.34 259	95.50 219			99.01 282	99.23 209

YYNet1		97.60 205	97.67 192	97.39 280	99.04 201	93.04 318	95.27 325	98.38 292	97.25 208	98.92 149	98.95 161	95.48 220	99.73 221	96.99 163	98.74 297	99.41 149

MDA-MVSNet_test_wron		97.60 205	97.66 195	97.41 279	99.04 201	93.09 314	95.27 325	98.42 289	97.26 207	98.88 157	98.95 161	95.43 221	99.73 221	97.02 160	98.72 299	99.41 149

原ACMM1				98.35 207	98.90 225	96.25 229		98.83 261	92.48 332	96.07 333	98.10 277	95.39 222	99.71 229	92.61 329	98.99 284	99.08 232

USDC		97.41 219	97.40 210	97.44 277	98.94 215	93.67 308	95.17 328	99.53 68	94.03 312	98.97 138	99.10 121	95.29 223	99.34 333	95.84 248	99.73 127	99.30 196

testdata				98.09 225	98.93 217	95.40 253		98.80 264	90.08 354	97.45 284	98.37 255	95.26 224	99.70 232	93.58 309	98.95 288	99.17 225

bld_raw_dy_0_64		99.07 45	99.00 49	99.29 81	99.85 16	98.18 126	99.11 57	99.40 110	99.33 43	99.38 71	99.44 60	95.21 225	99.97 4	99.31 27	99.98 9	99.73 31

BH-untuned		96.83 257	96.75 249	97.08 290	98.74 251	93.33 312	96.71 268	98.26 295	96.72 238	98.44 214	97.37 322	95.20 226	99.47 316	91.89 334	97.43 339	98.44 309

MVE	83.40 22	92.50 333	91.92 336	94.25 343	98.83 238	91.64 336	92.71 365	83.52 379	95.92 267	86.46 376	95.46 357	95.20 226	95.40 375	80.51 372	98.64 306	95.73 368
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
BH-RMVSNet		96.83 257	96.58 262	97.58 264	98.47 294	94.05 290	96.67 270	97.36 321	96.70 240	97.87 252	97.98 286	95.14 228	99.44 321	90.47 352	98.58 310	99.25 204

pmmvs4		97.58 208	97.28 219	98.51 192	98.84 236	96.93 213	95.40 323	98.52 285	93.60 317	98.61 193	98.65 220	95.10 229	99.60 279	96.97 166	99.79 100	98.99 247

test_vis1_n_1920		98.40 136	98.92 56	96.81 305	99.74 35	90.76 348	98.15 148	99.91 6	98.33 115	99.89 8	99.55 40	95.07 230	99.88 71	99.76 8	99.93 31	99.79 18

EU-MVSNet		97.66 201	98.50 105	95.13 337	99.63 62	85.84 365	98.35 131	98.21 297	98.23 125	99.54 41	99.46 55	95.02 231	99.68 245	98.24 91	99.87 63	99.87 9

DP-MVS Recon		97.33 224	96.92 236	98.57 181	99.09 189	97.99 145	96.79 262	99.35 128	93.18 322	97.71 263	98.07 281	95.00 232	99.31 337	93.97 298	99.13 268	98.42 311

HQP_MVS		97.99 176	97.67 192	98.93 137	99.19 165	97.65 177	97.77 189	99.27 167	98.20 129	97.79 259	97.98 286	94.90 233	99.70 232	94.42 285	99.51 209	99.45 135

plane_prior6					98.99 209	97.70 175						94.90 233

CPTT-MVS		97.84 190	97.36 214	99.27 86	99.31 139	98.46 105	98.29 134	99.27 167	94.90 291	97.83 256	98.37 255	94.90 233	99.84 126	93.85 304	99.54 200	99.51 105

new_pmnet		96.99 252	96.76 248	97.67 256	98.72 254	94.89 268	95.95 302	98.20 298	92.62 331	98.55 204	98.54 235	94.88 236	99.52 304	93.96 299	99.44 224	98.59 302

VDD-MVS		98.56 115	98.39 125	99.07 117	99.13 182	98.07 139	98.59 100	97.01 330	99.59 19	99.11 113	99.27 87	94.82 237	99.79 183	98.34 87	99.63 169	99.34 182

jason		97.45 216	97.35 215	97.76 251	99.24 151	93.93 298	95.86 306	98.42 289	94.24 306	98.50 209	98.13 273	94.82 237	99.91 47	97.22 145	99.73 127	99.43 143
jason: jason.
TAMVS		98.24 156	98.05 165	98.80 152	99.07 193	97.18 202	97.88 178	98.81 262	96.66 241	99.17 111	99.21 98	94.81 239	99.77 200	96.96 167	99.88 60	99.44 139

新几何1				98.91 140	98.94 215	97.76 170		98.76 268	87.58 363	96.75 315	98.10 277	94.80 240	99.78 194	92.73 326	99.00 283	99.20 214

VNet		98.42 133	98.30 137	98.79 154	98.79 247	97.29 193	98.23 139	98.66 277	99.31 45	98.85 162	98.80 194	94.80 240	99.78 194	98.13 96	99.13 268	99.31 193

RRT_MVS		99.09 42	98.94 54	99.55 23	99.87 12	98.82 78	99.48 9	98.16 301	99.49 25	99.59 37	99.65 24	94.79 242	99.95 17	99.45 21	99.96 15	99.88 7

MAR-MVS		96.47 273	95.70 281	98.79 154	97.92 327	99.12 57	98.28 135	98.60 281	92.16 336	95.54 345	96.17 345	94.77 243	99.52 304	89.62 355	98.23 317	97.72 341
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
CL-MVSNet_self_test		97.44 217	97.22 222	98.08 228	98.57 284	95.78 242	94.30 352	98.79 265	96.58 244	98.60 195	98.19 271	94.74 244	99.64 267	96.41 217	98.84 293	98.82 273

MSP-MVS		98.40 136	98.00 169	99.61 9	99.57 69	99.25 24	98.57 103	99.35 128	97.55 176	99.31 89	97.71 301	94.61 245	99.88 71	96.14 233	99.19 260	99.70 38
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
PAPR		95.29 299	94.47 308	97.75 252	97.50 350	95.14 262	94.89 336	98.71 275	91.39 344	95.35 349	95.48 356	94.57 246	99.14 353	84.95 364	97.37 341	98.97 252

test222					98.92 221	96.93 213	95.54 316	98.78 267	85.72 366	96.86 311	98.11 276	94.43 247			99.10 273	99.23 209

PLC	94.65 16	96.51 269	95.73 280	98.85 145	98.75 250	97.91 155	96.42 281	99.06 216	90.94 349	95.59 339	97.38 321	94.41 248	99.59 283	90.93 348	98.04 331	99.05 235
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
D2MVS		97.84 190	97.84 182	97.83 243	99.14 180	94.74 272	96.94 254	98.88 246	95.84 269	98.89 153	98.96 157	94.40 249	99.69 236	97.55 129	99.95 19	99.05 235

CNLPA		97.17 238	96.71 251	98.55 186	98.56 285	98.05 142	96.33 285	98.93 237	96.91 230	97.06 298	97.39 320	94.38 250	99.45 319	91.66 336	99.18 262	98.14 321

MDA-MVSNet-bldmvs		97.94 177	97.91 177	98.06 230	99.44 114	94.96 267	96.63 272	99.15 204	98.35 113	98.83 166	99.11 119	94.31 251	99.85 110	96.60 198	98.72 299	99.37 170

OpenMVS_ROB	95.38 14	95.84 288	95.18 299	97.81 245	98.41 302	97.15 205	97.37 228	98.62 280	83.86 368	98.65 187	98.37 255	94.29 252	99.68 245	88.41 357	98.62 308	96.60 359

TR-MVS		95.55 295	95.12 300	96.86 304	97.54 345	93.94 297	96.49 277	96.53 341	94.36 305	97.03 300	96.61 336	94.26 253	99.16 351	86.91 361	96.31 357	97.47 349

GBi-Net		98.65 103	98.47 112	99.17 99	98.90 225	98.24 120	99.20 44	99.44 98	98.59 104	98.95 141	99.55 40	94.14 254	99.86 98	97.77 120	99.69 147	99.41 149

test1		98.65 103	98.47 112	99.17 99	98.90 225	98.24 120	99.20 44	99.44 98	98.59 104	98.95 141	99.55 40	94.14 254	99.86 98	97.77 120	99.69 147	99.41 149

FMVSNet2		98.49 127	98.40 122	98.75 162	98.90 225	97.14 206	98.61 98	99.13 206	98.59 104	99.19 106	99.28 85	94.14 254	99.82 150	97.97 109	99.80 95	99.29 198

PAPM_NR		96.82 259	96.32 269	98.30 212	99.07 193	96.69 221	97.48 221	98.76 268	95.81 270	96.61 320	96.47 340	94.12 257	99.17 350	90.82 351	97.78 333	99.06 234

Anonymous20240521		98.69 93	98.87 59	98.16 223	99.77 27	95.11 264	99.08 58	99.44 98	99.34 42	99.33 81	99.55 40	94.10 258	99.94 26	99.25 32	99.96 15	99.42 146

HQP2-MVS												93.84 259

HQP-MVS		97.00 251	96.49 265	98.55 186	98.67 269	96.79 216	96.29 287	99.04 222	96.05 261	95.55 342	96.84 332	93.84 259	99.54 298	92.82 322	99.26 250	99.32 189

MVSFormer		98.26 153	98.43 118	97.77 248	98.88 231	93.89 302	99.39 16	99.56 56	99.11 61	98.16 231	98.13 273	93.81 261	99.97 4	99.26 30	99.57 192	99.43 143

lupinMVS		97.06 245	96.86 240	97.65 258	98.88 231	93.89 302	95.48 320	97.97 308	93.53 318	98.16 231	97.58 309	93.81 261	99.91 47	96.77 185	99.57 192	99.17 225

MG-MVS		96.77 260	96.61 259	97.26 284	98.31 307	93.06 315	95.93 303	98.12 304	96.45 248	97.92 248	98.73 204	93.77 263	99.39 328	91.19 346	99.04 277	99.33 187

PVSNet	93.40 17	95.67 291	95.70 281	95.57 330	98.83 238	88.57 354	92.50 366	97.72 313	92.69 330	96.49 326	96.44 341	93.72 264	99.43 322	93.61 307	99.28 246	98.71 291

MVS_0304		97.64 202	97.35 215	98.52 190	97.87 331	96.69 221	98.59 100	98.05 307	97.44 190	93.74 365	98.85 184	93.69 265	99.88 71	98.11 97	99.81 84	98.98 248

pmmvs5		97.64 202	97.49 206	98.08 228	99.14 180	95.12 263	96.70 269	99.05 219	93.77 315	98.62 191	98.83 188	93.23 266	99.75 212	98.33 89	99.76 120	99.36 176

CANet_DTU		97.26 229	97.06 230	97.84 242	97.57 343	94.65 277	96.19 293	98.79 265	97.23 214	95.14 351	98.24 266	93.22 267	99.84 126	97.34 140	99.84 70	99.04 239

UnsupCasMVSNet_bld		97.30 226	96.92 236	98.45 198	99.28 144	96.78 219	96.20 292	99.27 167	95.42 278	98.28 225	98.30 263	93.16 268	99.71 229	94.99 268	97.37 341	98.87 269

IterMVS		97.73 195	98.11 159	96.57 309	99.24 151	90.28 349	95.52 319	99.21 182	98.86 91	99.33 81	99.33 79	93.11 269	99.94 26	98.49 80	99.94 27	99.48 122
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		97.85 189	98.18 150	96.87 301	99.27 146	91.16 347	95.53 317	99.25 173	99.10 68	99.41 64	99.35 73	93.10 270	99.96 11	98.65 70	99.94 27	99.49 112

SCA		96.41 275	96.66 256	95.67 327	98.24 311	88.35 356	95.85 308	96.88 337	96.11 259	97.67 266	98.67 215	93.10 270	99.85 110	94.16 291	99.22 254	98.81 277

DPM-MVS		96.32 276	95.59 286	98.51 192	98.76 248	97.21 199	94.54 348	98.26 295	91.94 337	96.37 327	97.25 325	93.06 272	99.43 322	91.42 342	98.74 297	98.89 265

BH-w/o		95.13 302	94.89 306	95.86 322	98.20 314	91.31 342	95.65 313	97.37 320	93.64 316	96.52 322	95.70 352	93.04 273	99.02 355	88.10 358	95.82 362	97.24 351

cascas		94.79 307	94.33 313	96.15 321	96.02 373	92.36 330	92.34 368	99.26 172	85.34 367	95.08 352	94.96 364	92.96 274	98.53 367	94.41 288	98.59 309	97.56 347

c3_l		97.36 221	97.37 213	97.31 281	98.09 320	93.25 313	95.01 333	99.16 199	97.05 223	98.77 175	98.72 206	92.88 275	99.64 267	96.93 168	99.76 120	99.05 235

MVS-HIRNet		94.32 312	95.62 284	90.42 357	98.46 295	75.36 380	96.29 287	89.13 374	95.25 283	95.38 348	99.75 11	92.88 275	99.19 349	94.07 297	99.39 228	96.72 358

test_vis1_n		98.31 146	98.50 105	97.73 254	99.76 30	94.17 288	98.68 92	99.91 6	96.31 253	99.79 14	99.57 35	92.85 277	99.42 324	99.79 6	99.84 70	99.60 61

sss		97.21 234	96.93 234	98.06 230	98.83 238	95.22 259	96.75 266	98.48 287	94.49 298	97.27 291	97.90 292	92.77 278	99.80 170	96.57 201	99.32 238	99.16 228

miper_ehance_all_eth		97.06 245	97.03 231	97.16 289	97.83 332	93.06 315	94.66 342	99.09 213	95.99 265	98.69 182	98.45 248	92.73 279	99.61 278	96.79 182	99.03 278	98.82 273

SixPastTwentyTwo		98.75 83	98.62 90	99.16 102	99.83 19	97.96 152	99.28 36	98.20 298	99.37 38	99.70 23	99.65 24	92.65 280	99.93 31	99.04 44	99.84 70	99.60 61

UnsupCasMVSNet_eth		97.89 180	97.60 200	98.75 162	99.31 139	97.17 203	97.62 205	99.35 128	98.72 97	98.76 177	98.68 213	92.57 281	99.74 217	97.76 124	95.60 363	99.34 182

CHOSEN 1792x2688		97.49 212	97.14 228	98.54 189	99.68 53	96.09 233	96.50 276	99.62 35	91.58 340	98.84 165	98.97 154	92.36 282	99.88 71	96.76 186	99.95 19	99.67 44

PCF-MVS	92.86 18	94.36 311	93.00 328	98.42 201	98.70 261	97.56 181	93.16 364	99.11 209	79.59 372	97.55 275	97.43 318	92.19 283	99.73 221	79.85 373	99.45 221	97.97 329
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
EPP-MVSNet		98.30 147	98.04 166	99.07 117	99.56 76	97.83 162	99.29 32	98.07 305	99.03 77	98.59 197	99.13 117	92.16 284	99.90 52	96.87 177	99.68 152	99.49 112

1112_ss		97.29 228	96.86 240	98.58 179	99.34 138	96.32 227	96.75 266	99.58 42	93.14 323	96.89 309	97.48 315	92.11 285	99.86 98	96.91 169	99.54 200	99.57 78

CDS-MVSNet		97.69 198	97.35 215	98.69 167	98.73 252	97.02 209	96.92 258	98.75 271	95.89 268	98.59 197	98.67 215	92.08 286	99.74 217	96.72 191	99.81 84	99.32 189
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
eth_miper_zixun_eth		97.23 233	97.25 220	97.17 287	98.00 324	92.77 322	94.71 339	99.18 192	97.27 206	98.56 202	98.74 203	91.89 287	99.69 236	97.06 159	99.81 84	99.05 235

test_fmvs1_n		98.09 167	98.28 139	97.52 271	99.68 53	93.47 311	98.63 95	99.93 3	95.41 281	99.68 27	99.64 26	91.88 288	99.48 313	99.82 3	99.87 63	99.62 54

IS-MVSNet		98.19 160	97.90 178	99.08 115	99.57 69	97.97 149	99.31 26	98.32 293	99.01 79	98.98 134	99.03 135	91.59 289	99.79 183	95.49 261	99.80 95	99.48 122

test_fmvs1		97.72 196	97.94 174	97.07 292	98.66 274	92.39 328	97.68 198	99.81 14	95.20 285	99.54 41	99.44 60	91.56 290	99.41 325	99.78 7	99.77 109	99.40 158

Test_1112_low_res		96.99 252	96.55 263	98.31 211	99.35 136	95.47 250	95.84 309	99.53 68	91.51 342	96.80 314	98.48 246	91.36 291	99.83 140	96.58 199	99.53 204	99.62 54

WTY-MVS		96.67 263	96.27 272	97.87 241	98.81 243	94.61 278	96.77 264	97.92 310	94.94 290	97.12 294	97.74 300	91.11 292	99.82 150	93.89 301	98.15 324	99.18 221

PVSNet_0	89.98 21	91.15 340	90.30 343	93.70 349	97.72 336	84.34 373	90.24 369	97.42 319	90.20 353	93.79 363	93.09 372	90.90 293	98.89 363	86.57 362	72.76 376	97.87 332

miper_enhance_ethall		96.01 283	95.74 279	96.81 305	96.41 368	92.27 331	93.69 361	98.89 245	91.14 347	98.30 223	97.35 324	90.58 294	99.58 287	96.31 222	99.03 278	98.60 300

VDDNet		98.21 158	97.95 172	99.01 129	99.58 65	97.74 172	99.01 66	97.29 325	99.67 9	98.97 138	99.50 49	90.45 295	99.80 170	97.88 114	99.20 257	99.48 122

Anonymous202405211		97.90 178	97.50 205	99.08 115	98.90 225	98.25 119	98.53 108	96.16 344	98.87 90	99.11 113	98.86 181	90.40 296	99.78 194	97.36 139	99.31 240	99.19 219

miper_lstm_enhance		97.18 237	97.16 225	97.25 285	98.16 316	92.85 320	95.15 330	99.31 146	97.25 208	98.74 180	98.78 197	90.07 297	99.78 194	97.19 146	99.80 95	99.11 231

lessismore_v0				98.97 133	99.73 36	97.53 183		86.71 376		99.37 74	99.52 47	89.93 298	99.92 39	98.99 48	99.72 134	99.44 139

HY-MVS	95.94 13	95.90 286	95.35 294	97.55 268	97.95 325	94.79 269	98.81 83	96.94 335	92.28 335	95.17 350	98.57 233	89.90 299	99.75 212	91.20 345	97.33 345	98.10 322

K. test v3		98.00 173	97.66 195	99.03 127	99.79 24	97.56 181	99.19 48	92.47 365	99.62 16	99.52 47	99.66 22	89.61 300	99.96 11	99.25 32	99.81 84	99.56 82

CMPMVS	75.91 23	96.29 277	95.44 290	98.84 146	96.25 370	98.69 88	97.02 249	99.12 207	88.90 359	97.83 256	98.86 181	89.51 301	98.90 362	91.92 333	99.51 209	98.92 261
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
CVMVSNet		96.25 279	97.21 223	93.38 353	99.10 186	80.56 379	97.20 242	98.19 300	96.94 228	99.00 132	99.02 136	89.50 302	99.80 170	96.36 220	99.59 183	99.78 20

DeepMVS_CX				93.44 352	98.24 311	94.21 286		94.34 355	64.28 374	91.34 370	94.87 367	89.45 303	92.77 377	77.54 375	93.14 371	93.35 372

EPNet		96.14 281	95.44 290	98.25 215	90.76 380	95.50 249	97.92 174	94.65 353	98.97 82	92.98 366	98.85 184	89.12 304	99.87 89	95.99 238	99.68 152	99.39 161
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet (Re-imp)		97.46 214	97.16 225	98.34 208	99.55 80	96.10 231	98.94 73	98.44 288	98.32 117	98.16 231	98.62 227	88.76 305	99.73 221	93.88 302	99.79 100	99.18 221

test1111		96.49 272	96.82 244	95.52 331	99.42 120	87.08 362	99.22 41	87.14 375	99.11 61	99.46 55	99.58 34	88.69 306	99.86 98	98.80 57	99.95 19	99.62 54

DIV-MVS_self_test		97.02 248	96.84 242	97.58 264	97.82 333	94.03 293	94.66 342	99.16 199	97.04 224	98.63 189	98.71 207	88.69 306	99.69 236	97.00 161	99.81 84	99.01 243

cl____		97.02 248	96.83 243	97.58 264	97.82 333	94.04 292	94.66 342	99.16 199	97.04 224	98.63 189	98.71 207	88.68 308	99.69 236	97.00 161	99.81 84	99.00 246

h-mvs33		97.77 193	97.33 218	99.10 111	99.21 158	97.84 161	98.35 131	98.57 282	99.11 61	98.58 199	99.02 136	88.65 309	99.96 11	98.11 97	96.34 356	99.49 112

hse-mvs2		97.46 214	97.07 229	98.64 170	98.73 252	97.33 191	97.45 224	97.64 318	99.11 61	98.58 199	97.98 286	88.65 309	99.79 183	98.11 97	97.39 340	98.81 277

ECVR-MVS		96.42 274	96.61 259	95.85 323	99.38 125	88.18 358	99.22 41	86.00 377	99.08 73	99.36 76	99.57 35	88.47 311	99.82 150	98.52 78	99.95 19	99.54 93

FA-MVS(test-final)		96.99 252	96.82 244	97.50 273	98.70 261	94.78 270	99.34 19	96.99 331	95.07 286	98.48 211	99.33 79	88.41 312	99.65 264	96.13 235	98.92 291	98.07 324

EPNet_dtu		94.93 306	94.78 307	95.38 335	93.58 377	87.68 360	96.78 263	95.69 351	97.35 198	89.14 373	98.09 279	88.15 313	99.49 310	94.95 270	99.30 243	98.98 248
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
alignmvs		97.35 222	96.88 239	98.78 157	98.54 287	98.09 133	97.71 195	97.69 315	99.20 54	97.59 271	95.90 349	88.12 314	99.55 295	98.18 95	98.96 287	98.70 293

FMVSNet3		97.50 210	97.24 221	98.29 213	98.08 321	95.83 240	97.86 182	98.91 242	97.89 150	98.95 141	98.95 161	87.06 315	99.81 163	97.77 120	99.69 147	99.23 209

baseline1		95.96 285	95.44 290	97.52 271	98.51 292	93.99 296	98.39 128	96.09 346	98.21 126	98.40 221	97.76 299	86.88 316	99.63 270	95.42 262	89.27 374	98.95 255

RPMNet		97.02 248	96.93 234	97.30 282	97.71 338	94.22 284	98.11 152	99.30 154	99.37 38	96.91 305	99.34 77	86.72 317	99.87 89	97.53 132	97.36 343	97.81 335

HyFIR lowres test		97.19 236	96.60 261	98.96 134	99.62 64	97.28 194	95.17 328	99.50 74	94.21 307	99.01 131	98.32 262	86.61 318	99.99 2	97.10 155	99.84 70	99.60 61

PAPM		91.88 339	90.34 342	96.51 310	98.06 322	92.56 324	92.44 367	97.17 326	86.35 364	90.38 371	96.01 346	86.61 318	99.21 348	70.65 376	95.43 364	97.75 339

test_yl		96.69 261	96.29 270	97.90 238	98.28 308	95.24 257	97.29 234	97.36 321	98.21 126	98.17 229	97.86 293	86.27 320	99.55 295	94.87 271	98.32 314	98.89 265

DCV-MVSNet		96.69 261	96.29 270	97.90 238	98.28 308	95.24 257	97.29 234	97.36 321	98.21 126	98.17 229	97.86 293	86.27 320	99.55 295	94.87 271	98.32 314	98.89 265

CHOSEN 280x420		95.51 297	95.47 287	95.65 329	98.25 310	88.27 357	93.25 363	98.88 246	93.53 318	94.65 354	97.15 328	86.17 322	99.93 31	97.41 137	99.93 31	98.73 290

EMVS		93.83 322	94.02 314	93.23 354	96.83 362	84.96 368	89.77 371	96.32 343	97.92 147	97.43 286	96.36 344	86.17 322	98.93 360	87.68 359	97.73 334	95.81 367

MIMVSNet		96.62 266	96.25 273	97.71 255	99.04 201	94.66 276	99.16 50	96.92 336	97.23 214	97.87 252	99.10 121	86.11 324	99.65 264	91.65 337	99.21 256	98.82 273

tpmvs		95.02 305	95.25 296	94.33 342	96.39 369	85.87 364	98.08 156	96.83 338	95.46 277	95.51 347	98.69 211	85.91 325	99.53 300	94.16 291	96.23 358	97.58 346

MDTV_nov1_ep13_2view						74.92 381	97.69 197		90.06 355	97.75 262		85.78 326		93.52 310		98.69 294

ADS-MVSNet2		95.43 298	94.98 302	96.76 308	98.14 317	91.74 335	97.92 174	97.76 312	90.23 350	96.51 323	98.91 168	85.61 327	99.85 110	92.88 320	96.90 349	98.69 294

ADS-MVSNet		95.24 301	94.93 305	96.18 317	98.14 317	90.10 350	97.92 174	97.32 324	90.23 350	96.51 323	98.91 168	85.61 327	99.74 217	92.88 320	96.90 349	98.69 294

tpmrst		95.07 303	95.46 288	93.91 346	97.11 357	84.36 372	97.62 205	96.96 333	94.98 288	96.35 328	98.80 194	85.46 329	99.59 283	95.60 257	96.23 358	97.79 338

CR-MVSNet		96.28 278	95.95 276	97.28 283	97.71 338	94.22 284	98.11 152	98.92 240	92.31 334	96.91 305	99.37 69	85.44 330	99.81 163	97.39 138	97.36 343	97.81 335

Patchmtry		97.35 222	96.97 233	98.50 194	97.31 354	96.47 223	98.18 144	98.92 240	98.95 85	98.78 172	99.37 69	85.44 330	99.85 110	95.96 240	99.83 77	99.17 225

test_method		79.78 342	79.50 345	80.62 358	80.21 381	45.76 383	70.82 372	98.41 291	31.08 376	80.89 377	97.71 301	84.85 332	97.37 372	91.51 341	80.03 375	98.75 288

PatchmatchNet		95.58 294	95.67 283	95.30 336	97.34 353	87.32 361	97.65 203	96.65 339	95.30 282	97.07 297	98.69 211	84.77 333	99.75 212	94.97 269	98.64 306	98.83 272
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
sam_mvs1												84.74 334				98.81 277

E-PMN		94.17 316	94.37 311	93.58 350	96.86 360	85.71 367	90.11 370	97.07 329	98.17 132	97.82 258	97.19 326	84.62 335	98.94 359	89.77 354	97.68 335	96.09 366

LFMVS		97.20 235	96.72 250	98.64 170	98.72 254	96.95 211	98.93 74	94.14 360	99.74 6	98.78 172	99.01 145	84.45 336	99.73 221	97.44 135	99.27 247	99.25 204

patchmatchnet-post											98.77 199	84.37 337	99.85 110

PatchT		96.65 264	96.35 267	97.54 269	97.40 351	95.32 255	97.98 170	96.64 340	99.33 43	96.89 309	99.42 63	84.32 338	99.81 163	97.69 127	97.49 336	97.48 348

Patchmatch-RL test		97.26 229	97.02 232	97.99 236	99.52 88	95.53 247	96.13 294	99.71 21	97.47 182	99.27 92	99.16 110	84.30 339	99.62 272	97.89 111	99.77 109	98.81 277

sam_mvs												84.29 340

MDTV_nov1_ep13			95.22 297		97.06 358	83.20 374	97.74 193	96.16 344	94.37 304	96.99 301	98.83 188	83.95 341	99.53 300	93.90 300	97.95 332

test_post											21.25 378	83.86 342	99.70 232

Patchmatch-test		96.55 267	96.34 268	97.17 287	98.35 304	93.06 315	98.40 127	97.79 311	97.33 199	98.41 217	98.67 215	83.68 343	99.69 236	95.16 266	99.31 240	98.77 285

GA-MVS		95.86 287	95.32 295	97.49 274	98.60 279	94.15 289	93.83 359	97.93 309	95.49 276	96.68 316	97.42 319	83.21 344	99.30 339	96.22 227	98.55 311	99.01 243

JIA-IIPM		95.52 296	95.03 301	97.00 293	96.85 361	94.03 293	96.93 256	95.82 349	99.20 54	94.63 355	99.71 16	83.09 345	99.60 279	94.42 285	94.64 367	97.36 350

test_post1							97.59 210				20.48 379	83.07 346	99.66 259	94.16 291

tpm cat1		93.29 328	93.13 327	93.75 348	97.39 352	84.74 369	97.39 226	97.65 316	83.39 370	94.16 358	98.41 250	82.86 347	99.39 328	91.56 340	95.35 365	97.14 352

cl22		95.79 289	95.39 293	96.98 295	96.77 363	92.79 321	94.40 350	98.53 284	94.59 297	97.89 251	98.17 272	82.82 348	99.24 345	96.37 218	99.03 278	98.92 261

test-LLR		93.90 321	93.85 315	94.04 344	96.53 365	84.62 370	94.05 356	92.39 366	96.17 256	94.12 359	95.07 359	82.30 349	99.67 248	95.87 245	98.18 320	97.82 333

test0.0.03 1		94.51 309	93.69 318	96.99 294	96.05 371	93.61 310	94.97 334	93.49 361	96.17 256	97.57 274	94.88 365	82.30 349	99.01 357	93.60 308	94.17 370	98.37 314

AUN-MVS		96.24 280	95.45 289	98.60 177	98.70 261	97.22 198	97.38 227	97.65 316	95.95 266	95.53 346	97.96 290	82.11 351	99.79 183	96.31 222	97.44 338	98.80 282

MVSTER		96.86 256	96.55 263	97.79 246	97.91 328	94.21 286	97.56 213	98.87 248	97.49 181	99.06 120	99.05 131	80.72 352	99.80 170	98.44 82	99.82 80	99.37 170

tmp_tt		78.77 343	78.73 346	78.90 359	58.45 382	74.76 382	94.20 353	78.26 382	39.16 375	86.71 375	92.82 373	80.50 353	75.19 378	86.16 363	92.29 372	86.74 373

thres200		93.72 324	93.14 326	95.46 334	98.66 274	91.29 343	96.61 273	94.63 354	97.39 194	96.83 312	93.71 371	79.88 354	99.56 292	82.40 370	98.13 325	95.54 369

thres100view900		94.19 315	93.67 319	95.75 326	99.06 197	91.35 341	98.03 163	94.24 358	98.33 115	97.40 287	94.98 363	79.84 355	99.62 272	83.05 367	98.08 328	96.29 360

thres600view7		94.45 310	93.83 316	96.29 314	99.06 197	91.53 337	97.99 169	94.24 358	98.34 114	97.44 285	95.01 361	79.84 355	99.67 248	84.33 365	98.23 317	97.66 343

tfpn200view9		94.03 319	93.44 321	95.78 325	98.93 217	91.44 339	97.60 208	94.29 356	97.94 145	97.10 295	94.31 369	79.67 357	99.62 272	83.05 367	98.08 328	96.29 360

thres400		94.14 317	93.44 321	96.24 316	98.93 217	91.44 339	97.60 208	94.29 356	97.94 145	97.10 295	94.31 369	79.67 357	99.62 272	83.05 367	98.08 328	97.66 343

pmmvs3		95.03 304	94.40 310	96.93 297	97.70 340	92.53 325	95.08 331	97.71 314	88.57 360	97.71 263	98.08 280	79.39 359	99.82 150	96.19 229	99.11 272	98.43 310

iter_conf_final		97.10 241	96.65 258	98.45 198	98.53 289	96.08 234	98.30 133	99.11 209	98.10 137	98.85 162	98.95 161	79.38 360	99.87 89	98.68 68	99.91 48	99.40 158

baseline2		93.73 323	92.83 329	96.42 312	97.70 340	91.28 344	96.84 261	89.77 373	93.96 314	92.44 367	95.93 348	79.14 361	99.77 200	92.94 318	96.76 353	98.21 317

FE-MVS		95.66 292	94.95 304	97.77 248	98.53 289	95.28 256	99.40 15	96.09 346	93.11 324	97.96 247	99.26 89	79.10 362	99.77 200	92.40 331	98.71 301	98.27 316

tpm		94.67 308	94.34 312	95.66 328	97.68 342	88.42 355	97.88 178	94.90 352	94.46 300	96.03 335	98.56 234	78.66 363	99.79 183	95.88 242	95.01 366	98.78 284

CostFormer		93.97 320	93.78 317	94.51 341	97.53 346	85.83 366	97.98 170	95.96 348	89.29 358	94.99 353	98.63 225	78.63 364	99.62 272	94.54 279	96.50 354	98.09 323

ET-MVSNet_ETH3D		94.30 314	93.21 324	97.58 264	98.14 317	94.47 281	94.78 338	93.24 364	94.72 294	89.56 372	95.87 350	78.57 365	99.81 163	96.91 169	97.11 348	98.46 305

dp		93.47 326	93.59 320	93.13 355	96.64 364	81.62 378	97.66 201	96.42 342	92.80 329	96.11 331	98.64 223	78.55 366	99.59 283	93.31 315	92.18 373	98.16 320

EPMVS		93.72 324	93.27 323	95.09 338	96.04 372	87.76 359	98.13 149	85.01 378	94.69 295	96.92 303	98.64 223	78.47 367	99.31 337	95.04 267	96.46 355	98.20 318

tpm2		93.09 330	92.58 331	94.62 340	97.56 344	86.53 363	97.66 201	95.79 350	86.15 365	94.07 361	98.23 268	75.95 368	99.53 300	90.91 349	96.86 352	97.81 335

FPMVS		93.44 327	92.23 332	97.08 290	99.25 150	97.86 159	95.61 314	97.16 327	92.90 327	93.76 364	98.65 220	75.94 369	95.66 374	79.30 374	97.49 336	97.73 340

iter_conf05		96.54 268	96.07 274	97.92 237	97.90 329	94.50 280	97.87 181	99.14 205	97.73 160	98.89 153	98.95 161	75.75 370	99.87 89	98.50 79	99.92 42	99.40 158

thisisatest0515		94.12 318	93.16 325	96.97 296	98.60 279	92.90 319	93.77 360	90.61 370	94.10 310	96.91 305	95.87 350	74.99 371	99.80 170	94.52 280	99.12 271	98.20 318

tttt0517		95.64 293	94.98 302	97.64 260	99.36 132	93.81 304	98.72 87	90.47 371	98.08 139	98.67 184	98.34 259	73.88 372	99.92 39	97.77 120	99.51 209	99.20 214

thisisatest0530		95.27 300	94.45 309	97.74 253	99.19 165	94.37 282	97.86 182	90.20 372	97.17 218	98.22 227	97.65 305	73.53 373	99.90 52	96.90 174	99.35 234	98.95 255

FMVSNet5		96.01 283	95.20 298	98.41 202	97.53 346	96.10 231	98.74 84	99.50 74	97.22 217	98.03 245	99.04 133	69.80 374	99.88 71	97.27 143	99.71 139	99.25 204

gg-mvs-nofinetune		92.37 335	91.20 340	95.85 323	95.80 374	92.38 329	99.31 26	81.84 380	99.75 5	91.83 369	99.74 12	68.29 375	99.02 355	87.15 360	97.12 347	96.16 363

KD-MVS_2432*1600		92.87 331	91.99 334	95.51 332	91.37 378	89.27 352	94.07 354	98.14 302	95.42 278	97.25 292	96.44 341	67.86 376	99.24 345	91.28 343	96.08 360	98.02 326

miper_refine_blended		92.87 331	91.99 334	95.51 332	91.37 378	89.27 352	94.07 354	98.14 302	95.42 278	97.25 292	96.44 341	67.86 376	99.24 345	91.28 343	96.08 360	98.02 326

GG-mvs-BLEND				94.76 339	94.54 376	92.13 333	99.31 26	80.47 381		88.73 374	91.01 374	67.59 378	98.16 371	82.30 371	94.53 369	93.98 371

TESTMET0.1,1		92.19 338	91.77 338	93.46 351	96.48 367	82.80 375	94.05 356	91.52 369	94.45 302	94.00 362	94.88 365	66.65 379	99.56 292	95.78 250	98.11 326	98.02 326

test2506		92.39 334	91.89 337	93.89 347	99.38 125	82.28 376	99.32 22	66.03 383	99.08 73	98.77 175	99.57 35	66.26 380	99.84 126	98.71 65	99.95 19	99.54 93

IB-MVS	91.63 19	92.24 337	90.90 341	96.27 315	97.22 356	91.24 345	94.36 351	93.33 363	92.37 333	92.24 368	94.58 368	66.20 381	99.89 62	93.16 317	94.63 368	97.66 343
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
test-mter		92.33 336	91.76 339	94.04 344	96.53 365	84.62 370	94.05 356	92.39 366	94.00 313	94.12 359	95.07 359	65.63 382	99.67 248	95.87 245	98.18 320	97.82 333

test123		17.04 346	20.11 349	7.82 360	10.25 384	4.91 384	94.80 337	4.47 385	4.93 378	10.00 380	24.28 377	9.69 383	3.64 379	10.14 377	12.43 378	14.92 375

testmvs		17.12 345	20.53 348	6.87 361	12.05 383	4.20 385	93.62 362	6.73 384	4.62 379	10.41 379	24.33 376	8.28 384	3.56 380	9.69 378	15.07 377	12.86 376

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.12 348	10.83 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	97.48 315	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					99.73 36	99.67 2	99.43 11	99.54 65	99.43 33	99.26 96

MSC_two_6792asdad				99.32 78	98.43 298	98.37 111		98.86 253					99.89 62	97.14 151	99.60 179	99.71 33

No_MVS				99.32 78	98.43 298	98.37 111		98.86 253					99.89 62	97.14 151	99.60 179	99.71 33

eth-test2					0.00 385

eth-test					0.00 385

IU-MVS					99.49 100	99.15 47		98.87 248	92.97 325	99.41 64				96.76 186	99.62 172	99.66 45

save fliter					99.11 184	97.97 149	96.53 275	99.02 227	98.24 124

test_0728_SECOND				99.60 11	99.50 93	99.23 26	98.02 164	99.32 141					99.88 71	96.99 163	99.63 169	99.68 41

GSMVS																98.81 277

test_part2					99.36 132	99.10 60				99.05 125

MTGPA								99.20 184

MTMP							97.93 173	91.91 368

gm-plane-assit					94.83 375	81.97 377			88.07 362		94.99 362		99.60 279	91.76 335

test9_res														93.28 316	99.15 265	99.38 168

agg_prior2														92.50 330	99.16 263	99.37 170

agg_prior					98.68 268	97.99 145		99.01 230		95.59 339			99.77 200

test_prior4						97.97 149	95.86 306

test_prior				98.95 135	98.69 266	97.95 153		99.03 224					99.59 283			99.30 196

旧先验2							95.76 310		88.56 361	97.52 278			99.66 259	94.48 281

新几何2							95.93 303

无先验							95.74 311	98.74 273	89.38 357				99.73 221	92.38 332		99.22 213

原ACMM2							95.53 317

testdata2													99.79 183	92.80 324

testdata1							95.44 322		96.32 252

plane_prior7					99.19 165	97.87 158

plane_prior5								99.27 167					99.70 232	94.42 285	99.51 209	99.45 135

plane_prior4											97.98 286

plane_prior3						97.78 169			97.41 192	97.79 259

plane_prior2							97.77 189		98.20 129

plane_prior1					99.05 200

plane_prior						97.65 177	97.07 248		96.72 238						99.36 232

n2								0.00 386

nn								0.00 386

door-mid								99.57 49

test11								98.87 248

door								99.41 108

HQP5-MVS						96.79 216

HQP-NCC					98.67 269		96.29 287		96.05 261	95.55 342

ACMP_Plane					98.67 269		96.29 287		96.05 261	95.55 342

BP-MVS														92.82 322

HQP4-MVS										95.56 341			99.54 298			99.32 189

HQP3-MVS								99.04 222							99.26 250

NP-MVS					98.84 236	97.39 190					96.84 332

ACMMP++_ref															99.77 109

ACMMP++															99.68 152

High-resolution multi-view benchmark