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.

test_fmvsmconf0.01_n		99.89 3	99.88 6	99.91 2	99.98 3	99.76 62	99.12 197	100.00 1	100.00 1	99.99 7	99.91 24	99.98 1	100.00 1	99.97 4	100.00 1	99.99 1

test_fmvsm_n_1920		99.84 15	99.85 16	99.83 34	99.82 73	99.70 91	99.17 177	99.97 18	99.99 2	99.96 23	99.82 73	99.94 4	100.00 1	99.95 12	100.00 1	99.80 47

bld_raw_dy_0_64		99.70 40	99.65 50	99.85 27	99.95 15	99.77 54	99.66 53	99.71 125	99.95 20	99.91 44	99.77 108	98.35 190	100.00 1	99.54 60	99.99 16	99.79 54

h-mvs33		98.61 253	98.34 269	99.44 196	99.60 183	98.67 265	99.27 147	99.44 260	99.68 92	99.32 255	99.49 257	92.50 341	100.00 1	99.24 106	96.51 392	99.65 113

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 18	99.99 2	100.00 1	99.98 10	99.78 17	100.00 1	99.92 22	100.00 1	99.87 30

DSMNet-mixed		99.48 88	99.65 50	98.95 289	99.71 144	97.27 341	99.50 91	99.82 66	99.59 118	99.41 237	99.85 56	99.62 31	100.00 1	99.53 63	99.89 125	99.59 160

HyFIR lowres test		98.91 224	98.64 237	99.73 89	99.85 59	99.47 148	98.07 330	99.83 61	98.64 243	99.89 54	99.60 214	92.57 338	100.00 1	99.33 93	99.97 56	99.72 74

fmvsm_l_conf0.5_n_a		99.80 23	99.79 27	99.84 31	99.88 45	99.64 111	99.12 197	99.91 32	99.98 14	99.95 31	99.67 167	99.67 27	99.99 8	99.94 16	99.99 16	99.88 25

fmvsm_l_conf0.5_n		99.80 23	99.78 31	99.85 27	99.88 45	99.66 102	99.11 201	99.91 32	99.98 14	99.96 23	99.64 179	99.60 34	99.99 8	99.95 12	99.99 16	99.88 25

test_fmvsmconf0.1_n		99.87 8	99.86 12	99.91 2	99.97 6	99.74 74	99.01 228	99.99 10	99.99 2	99.98 13	99.88 42	99.97 2	99.99 8	99.96 9	100.00 1	99.98 3

SSC-MVS		99.52 82	99.42 99	99.83 34	99.86 55	99.65 108	99.52 86	99.81 75	99.87 42	99.81 88	99.79 93	96.78 281	99.99 8	99.83 32	99.51 291	99.86 32

test_fmvsmconf_n		99.85 11	99.84 19	99.88 17	99.91 32	99.73 77	98.97 240	99.98 11	99.99 2	99.96 23	99.85 56	99.93 7	99.99 8	99.94 16	99.99 16	99.93 15

test_fmvsmvis_n_1920		99.84 15	99.86 12	99.81 41	99.88 45	99.55 139	99.17 177	99.98 11	99.99 2	99.96 23	99.84 62	99.96 3	99.99 8	99.96 9	99.99 16	99.88 25

SDMVSNet		99.77 30	99.77 33	99.76 65	99.80 87	99.65 108	99.63 61	99.86 48	99.97 16	99.89 54	99.89 34	99.52 44	99.99 8	99.42 78	99.96 71	99.65 113

sd_testset		99.78 27	99.78 31	99.80 46	99.80 87	99.76 62	99.80 10	99.79 85	99.97 16	99.89 54	99.89 34	99.53 43	99.99 8	99.36 86	99.96 71	99.65 113

test_vis1_n_1920		99.72 36	99.88 6	99.27 247	99.93 26	97.84 322	99.34 122	100.00 1	99.99 2	99.99 7	99.82 73	99.87 9	99.99 8	99.97 4	99.99 16	99.97 7

test_fmvs3		99.83 19	99.93 2	99.53 175	99.96 7	98.62 274	99.67 49	100.00 1	99.95 20	100.00 1	99.95 13	99.85 10	99.99 8	99.98 1	99.99 16	99.98 3

dcpmvs_2		99.61 68	99.64 54	99.53 175	99.79 99	98.82 253	99.58 76	99.97 18	99.95 20	99.96 23	99.76 112	98.44 178	99.99 8	99.34 90	99.96 71	99.78 57

IterMVS-SCA-FT		99.00 211	99.16 146	98.51 324	99.75 129	95.90 368	98.07 330	99.84 59	99.84 54	99.89 54	99.73 124	96.01 304	99.99 8	99.33 93	100.00 1	99.63 128

IterMVS		98.97 215	99.16 146	98.42 328	99.74 135	95.64 371	98.06 332	99.83 61	99.83 57	99.85 73	99.74 120	96.10 303	99.99 8	99.27 105	100.00 1	99.63 128
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WB-MVS		99.44 100	99.32 117	99.80 46	99.81 81	99.61 124	99.47 99	99.81 75	99.82 59	99.71 133	99.72 131	96.60 285	99.98 21	99.75 39	99.23 331	99.82 46

test_fmvs1_n		99.68 46	99.81 23	99.28 244	99.95 15	97.93 320	99.49 95	100.00 1	99.82 59	99.99 7	99.89 34	99.21 75	99.98 21	99.97 4	99.98 41	99.93 15

test_fmvs2		99.72 36	99.85 16	99.34 228	99.91 32	98.08 311	99.48 96	100.00 1	99.90 30	99.99 7	99.91 24	99.50 46	99.98 21	99.98 1	99.99 16	99.96 10

patch_mono-2		99.51 83	99.46 90	99.64 129	99.70 152	99.11 224	99.04 219	99.87 45	99.71 82	99.47 219	99.79 93	98.24 202	99.98 21	99.38 81	99.96 71	99.83 40

CHOSEN 280x420		98.41 278	98.41 261	98.40 329	99.34 290	95.89 369	96.94 385	99.44 260	98.80 227	99.25 268	99.52 248	93.51 330	99.98 21	98.94 149	99.98 41	99.32 261

Fast-Effi-MVS+-dtu		99.20 166	99.12 156	99.43 200	99.25 312	99.69 95	99.05 216	99.82 66	99.50 124	98.97 302	99.05 341	98.98 104	99.98 21	98.20 198	99.24 329	98.62 355

Effi-MVS+-dtu		99.07 195	98.92 212	99.52 177	98.89 361	99.78 49	99.15 185	99.66 148	99.34 151	98.92 309	99.24 319	97.69 243	99.98 21	98.11 208	99.28 323	98.81 347

PS-MVSNAJss		99.84 15	99.82 22	99.89 11	99.96 7	99.77 54	99.68 45	99.85 53	99.95 20	99.98 13	99.92 21	99.28 66	99.98 21	99.75 39	100.00 1	99.94 13

jajsoiax		99.89 3	99.89 5	99.89 11	99.96 7	99.78 49	99.70 35	99.86 48	99.89 36	99.98 13	99.90 29	99.94 4	99.98 21	99.75 39	100.00 1	99.90 20

mvs_tets		99.90 2	99.90 3	99.90 8	99.96 7	99.79 46	99.72 30	99.88 43	99.92 28	99.98 13	99.93 17	99.94 4	99.98 21	99.77 38	100.00 1	99.92 18

MVSFormer		99.41 110	99.44 95	99.31 238	99.57 202	98.40 286	99.77 15	99.80 79	99.73 76	99.63 160	99.30 303	98.02 221	99.98 21	99.43 73	99.69 238	99.55 175

test_djsdf		99.84 15	99.81 23	99.91 2	99.94 19	99.84 24	99.77 15	99.80 79	99.73 76	99.97 19	99.92 21	99.77 19	99.98 21	99.43 73	100.00 1	99.90 20

Vis-MVSNet		99.75 32	99.74 37	99.79 52	99.88 45	99.66 102	99.69 42	99.92 29	99.67 96	99.77 106	99.75 117	99.61 32	99.98 21	99.35 89	99.98 41	99.72 74
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_cas_vis1_n_1920		99.76 31	99.86 12	99.45 193	99.93 26	98.40 286	99.30 135	99.98 11	99.94 24	99.99 7	99.89 34	99.80 15	99.97 34	99.96 9	99.97 56	99.97 7

test_fmvs1		99.48 88	99.65 50	98.97 287	99.54 216	97.16 344	99.11 201	99.98 11	99.78 70	99.96 23	99.81 79	98.72 137	99.97 34	99.95 12	99.97 56	99.79 54

Anonymous20240521		99.44 100	99.42 99	99.49 182	99.89 40	98.96 241	99.62 63	99.76 99	99.85 51	99.82 81	99.88 42	96.39 295	99.97 34	99.59 51	99.98 41	99.55 175

MVS_0304		99.17 177	99.03 187	99.59 153	99.44 260	98.90 248	99.04 219	95.32 391	99.99 2	99.68 143	99.57 231	98.30 197	99.97 34	99.94 16	99.98 41	99.88 25

xiu_mvs_v1_base_debu		99.23 151	99.34 112	98.91 296	99.59 187	98.23 295	98.47 298	99.66 148	99.61 110	99.68 143	98.94 359	99.39 50	99.97 34	99.18 115	99.55 280	98.51 362

xiu_mvs_v2_base		99.02 205	99.11 159	98.77 313	99.37 277	98.09 308	98.13 322	99.51 240	99.47 130	99.42 231	98.54 380	99.38 54	99.97 34	98.83 153	99.33 316	98.24 374

xiu_mvs_v1_base		99.23 151	99.34 112	98.91 296	99.59 187	98.23 295	98.47 298	99.66 148	99.61 110	99.68 143	98.94 359	99.39 50	99.97 34	99.18 115	99.55 280	98.51 362

xiu_mvs_v1_base_debi		99.23 151	99.34 112	98.91 296	99.59 187	98.23 295	98.47 298	99.66 148	99.61 110	99.68 143	98.94 359	99.39 50	99.97 34	99.18 115	99.55 280	98.51 362

anonymousdsp		99.80 23	99.77 33	99.90 8	99.96 7	99.88 12	99.73 27	99.85 53	99.70 87	99.92 41	99.93 17	99.45 47	99.97 34	99.36 86	100.00 1	99.85 35

UA-Net		99.78 27	99.76 36	99.86 25	99.72 141	99.71 84	99.91 3	99.95 28	99.96 18	99.71 133	99.91 24	99.15 81	99.97 34	99.50 67	100.00 1	99.90 20

PS-MVSNAJ		99.00 211	99.08 170	98.76 314	99.37 277	98.10 307	98.00 337	99.51 240	99.47 130	99.41 237	98.50 382	99.28 66	99.97 34	98.83 153	99.34 315	98.20 378

pmmvs3		98.08 299	97.80 308	98.91 296	99.41 270	97.69 330	97.87 350	99.66 148	95.87 365	99.50 214	99.51 250	90.35 365	99.97 34	98.55 176	99.47 298	99.08 317

DTE-MVSNet		99.68 46	99.61 60	99.88 17	99.80 87	99.87 15	99.67 49	99.71 125	99.72 80	99.84 76	99.78 101	98.67 143	99.97 34	99.30 99	99.95 84	99.80 47

jason		99.16 179	99.11 159	99.32 235	99.75 129	98.44 283	98.26 312	99.39 276	98.70 239	99.74 123	99.30 303	98.54 162	99.97 34	98.48 179	99.82 179	99.55 175
jason: jason.
lupinMVS		98.96 218	98.87 218	99.24 255	99.57 202	98.40 286	98.12 323	99.18 322	98.28 284	99.63 160	99.13 329	98.02 221	99.97 34	98.22 196	99.69 238	99.35 254

K. test v3		98.87 231	98.60 240	99.69 105	99.93 26	99.46 152	99.74 24	94.97 392	99.78 70	99.88 62	99.88 42	93.66 328	99.97 34	99.61 49	99.95 84	99.64 123

lessismore_v0				99.64 129	99.86 55	99.38 176		90.66 400		99.89 54	99.83 66	94.56 318	99.97 34	99.56 57	99.92 106	99.57 170

EPNet		98.13 296	97.77 311	99.18 262	94.57 401	97.99 313	99.24 157	97.96 371	99.74 75	97.29 382	99.62 197	93.13 333	99.97 34	98.59 174	99.83 170	99.58 165
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		99.40 112	99.38 104	99.44 196	99.90 38	98.66 268	98.94 245	99.91 32	97.97 302	99.79 97	99.73 124	99.05 97	99.97 34	99.15 121	99.99 16	99.68 90

IterMVS-LS		99.41 110	99.47 86	99.25 253	99.81 81	98.09 308	98.85 253	99.76 99	99.62 107	99.83 80	99.64 179	98.54 162	99.97 34	99.15 121	99.99 16	99.68 90
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ANet_high		99.88 6	99.87 10	99.91 2	99.99 1	99.91 4	99.65 59	100.00 1	99.90 30	100.00 1	99.97 11	99.61 32	99.97 34	99.75 39	100.00 1	99.84 36

test_vis1_n		99.68 46	99.79 27	99.36 225	99.94 19	98.18 301	99.52 86	100.00 1	99.86 46	100.00 1	99.88 42	98.99 102	99.96 55	99.97 4	99.96 71	99.95 11

UniMVSNet_ETH3D		99.85 11	99.83 20	99.90 8	99.89 40	99.91 4	99.89 4	99.71 125	99.93 26	99.95 31	99.89 34	99.71 22	99.96 55	99.51 65	99.97 56	99.84 36

v7n		99.82 21	99.80 26	99.88 17	99.96 7	99.84 24	99.82 8	99.82 66	99.84 54	99.94 34	99.91 24	99.13 86	99.96 55	99.83 32	99.99 16	99.83 40

RRT_MVS		99.67 52	99.59 65	99.91 2	99.94 19	99.88 12	99.78 12	99.27 302	99.87 42	99.91 44	99.87 47	98.04 219	99.96 55	99.68 44	99.99 16	99.90 20

PS-CasMVS		99.66 54	99.58 69	99.89 11	99.80 87	99.85 19	99.66 53	99.73 113	99.62 107	99.84 76	99.71 139	98.62 149	99.96 55	99.30 99	99.96 71	99.86 32

PEN-MVS		99.66 54	99.59 65	99.89 11	99.83 66	99.87 15	99.66 53	99.73 113	99.70 87	99.84 76	99.73 124	98.56 159	99.96 55	99.29 102	99.94 95	99.83 40

TranMVSNet+NR-MVSNet		99.54 79	99.47 86	99.76 65	99.58 192	99.64 111	99.30 135	99.63 165	99.61 110	99.71 133	99.56 235	98.76 130	99.96 55	99.14 127	99.92 106	99.68 90

IB-MVS	95.41 20	95.30 361	94.46 365	97.84 348	98.76 374	95.33 374	97.33 374	96.07 387	96.02 364	95.37 396	97.41 397	76.17 402	99.96 55	97.54 261	95.44 396	98.22 375
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
OpenMVS	98.12 10	98.23 292	97.89 306	99.26 250	99.19 324	99.26 201	99.65 59	99.69 137	91.33 389	98.14 362	99.77 108	98.28 199	99.96 55	95.41 359	99.55 280	98.58 359

MM				99.55 169		98.81 254	99.05 216	97.79 375	99.99 2	99.48 217	99.59 219	96.29 299	99.95 64	99.94 16	99.98 41	99.88 25

GeoE		99.69 43	99.66 48	99.78 55	99.76 118	99.76 62	99.60 73	99.82 66	99.46 133	99.75 115	99.56 235	99.63 29	99.95 64	99.43 73	99.88 134	99.62 139

CS-MVS		99.67 52	99.70 39	99.58 157	99.53 222	99.84 24	99.79 11	99.96 23	99.90 30	99.61 175	99.41 274	99.51 45	99.95 64	99.66 45	99.89 125	98.96 333

CANet_DTU		98.91 224	98.85 220	99.09 275	98.79 370	98.13 303	98.18 316	99.31 294	99.48 126	98.86 317	99.51 250	96.56 286	99.95 64	99.05 134	99.95 84	99.19 289

CS-MVS-test		99.68 46	99.70 39	99.64 129	99.57 202	99.83 29	99.78 12	99.97 18	99.92 28	99.50 214	99.38 284	99.57 38	99.95 64	99.69 43	99.90 116	99.15 297

Fast-Effi-MVS+		99.02 205	98.87 218	99.46 190	99.38 275	99.50 145	99.04 219	99.79 85	97.17 344	98.62 338	98.74 371	99.34 60	99.95 64	98.32 189	99.41 306	98.92 338

MTAPA		99.35 126	99.20 142	99.80 46	99.81 81	99.81 40	99.33 125	99.53 231	99.27 160	99.42 231	99.63 190	98.21 207	99.95 64	97.83 235	99.79 198	99.65 113

UniMVSNet_NR-MVSNet		99.37 121	99.25 137	99.72 95	99.47 251	99.56 136	98.97 240	99.61 175	99.43 141	99.67 149	99.28 307	97.85 234	99.95 64	99.17 118	99.81 188	99.65 113

DU-MVS		99.33 134	99.21 141	99.71 100	99.43 264	99.56 136	98.83 256	99.53 231	99.38 147	99.67 149	99.36 290	97.67 245	99.95 64	99.17 118	99.81 188	99.63 128

CP-MVSNet		99.54 79	99.43 97	99.87 21	99.76 118	99.82 35	99.57 79	99.61 175	99.54 120	99.80 92	99.64 179	97.79 238	99.95 64	99.21 109	99.94 95	99.84 36

Patchmtry		98.78 238	98.54 250	99.49 182	98.89 361	99.19 217	99.32 127	99.67 144	99.65 102	99.72 128	99.79 93	91.87 346	99.95 64	98.00 215	99.97 56	99.33 258

QAPM		98.40 280	97.99 293	99.65 122	99.39 272	99.47 148	99.67 49	99.52 236	91.70 388	98.78 327	99.80 83	98.55 160	99.95 64	94.71 370	99.75 211	99.53 189

3Dnovator	99.15 2	99.43 103	99.36 110	99.65 122	99.39 272	99.42 166	99.70 35	99.56 210	99.23 168	99.35 247	99.80 83	99.17 79	99.95 64	98.21 197	99.84 162	99.59 160

LTVRE_ROB	99.19 1	99.88 6	99.87 10	99.88 17	99.91 32	99.90 7	99.96 1	99.92 29	99.90 30	99.97 19	99.87 47	99.81 14	99.95 64	99.54 60	99.99 16	99.80 47
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
mvsany_test3		99.85 11	99.88 6	99.75 75	99.95 15	99.37 179	99.53 85	99.98 11	99.77 74	99.99 7	99.95 13	99.85 10	99.94 78	99.95 12	99.98 41	99.94 13

test_f		99.75 32	99.88 6	99.37 221	99.96 7	98.21 298	99.51 90	100.00 1	99.94 24	100.00 1	99.93 17	99.58 36	99.94 78	99.97 4	99.99 16	99.97 7

test_method		91.72 363	92.32 366	89.91 381	93.49 402	70.18 406	90.28 394	99.56 210	61.71 398	95.39 395	99.52 248	93.90 322	99.94 78	98.76 163	98.27 373	99.62 139

tttt0517		97.62 316	97.20 325	98.90 302	99.76 118	97.40 338	99.48 96	94.36 394	99.06 197	99.70 137	99.49 257	84.55 391	99.94 78	98.73 166	99.65 254	99.36 251

CANet		99.11 190	99.05 180	99.28 244	98.83 365	98.56 276	98.71 275	99.41 266	99.25 164	99.23 272	99.22 321	97.66 249	99.94 78	99.19 113	99.97 56	99.33 258

patchmatchnet-post											99.62 197	90.58 362	99.94 78

SCA		98.11 297	98.36 266	97.36 359	99.20 322	92.99 387	98.17 318	98.49 359	98.24 286	99.10 293	99.57 231	96.01 304	99.94 78	96.86 301	99.62 259	99.14 302

ADS-MVSNet2		97.78 309	97.66 316	98.12 342	99.14 330	95.36 373	99.22 164	98.75 345	96.97 349	98.25 354	99.64 179	90.90 357	99.94 78	96.51 321	99.56 276	99.08 317

WR-MVS_H		99.61 68	99.53 82	99.87 21	99.80 87	99.83 29	99.67 49	99.75 104	99.58 119	99.85 73	99.69 152	98.18 211	99.94 78	99.28 104	99.95 84	99.83 40

mvsmamba		99.74 35	99.70 39	99.85 27	99.93 26	99.83 29	99.76 19	99.81 75	99.96 18	99.91 44	99.81 79	98.60 153	99.94 78	99.58 54	99.98 41	99.77 61

SixPastTwentyTwo		99.42 106	99.30 124	99.76 65	99.92 31	99.67 100	99.70 35	99.14 326	99.65 102	99.89 54	99.90 29	96.20 301	99.94 78	99.42 78	99.92 106	99.67 96

CP-MVS		99.23 151	99.05 180	99.75 75	99.66 170	99.66 102	99.38 113	99.62 168	98.38 269	99.06 298	99.27 309	98.79 125	99.94 78	97.51 264	99.82 179	99.66 105

SteuartSystems-ACMMP		99.30 138	99.14 150	99.76 65	99.87 52	99.66 102	99.18 172	99.60 187	98.55 251	99.57 186	99.67 167	99.03 99	99.94 78	97.01 293	99.80 193	99.69 84
Skip Steuart: Steuart Systems R&D Blog.
PatchT		98.45 275	98.32 271	98.83 308	98.94 356	98.29 293	99.24 157	98.82 342	99.84 54	99.08 294	99.76 112	91.37 349	99.94 78	98.82 155	99.00 342	98.26 373

new_pmnet		98.88 230	98.89 216	98.84 306	99.70 152	97.62 331	98.15 319	99.50 244	97.98 301	99.62 169	99.54 244	98.15 212	99.94 78	97.55 260	99.84 162	98.95 335

wuyk23d		97.58 318	99.13 152	92.93 380	99.69 156	99.49 146	99.52 86	99.77 94	97.97 302	99.96 23	99.79 93	99.84 12	99.94 78	95.85 349	99.82 179	79.36 396

3Dnovator+	98.92 3	99.35 126	99.24 139	99.67 110	99.35 282	99.47 148	99.62 63	99.50 244	99.44 136	99.12 290	99.78 101	98.77 129	99.94 78	97.87 228	99.72 229	99.62 139

fmvsm_s_conf0.1_n_a		99.85 11	99.83 20	99.91 2	99.95 15	99.82 35	99.10 204	99.98 11	99.99 2	99.98 13	99.91 24	99.68 26	99.93 95	99.93 20	99.99 16	99.99 1

fmvsm_s_conf0.5_n_a		99.82 21	99.79 27	99.89 11	99.85 59	99.82 35	99.03 223	99.96 23	99.99 2	99.97 19	99.84 62	99.58 36	99.93 95	99.92 22	99.98 41	99.93 15

mvsany_test1		99.44 100	99.45 92	99.40 211	99.37 277	98.64 272	97.90 349	99.59 193	99.27 160	99.92 41	99.82 73	99.74 20	99.93 95	99.55 59	99.87 145	99.63 128

ETV-MVS		99.18 173	99.18 144	99.16 263	99.34 290	99.28 197	99.12 197	99.79 85	99.48 126	98.93 306	98.55 379	99.40 49	99.93 95	98.51 178	99.52 290	98.28 372

thisisatest0530		97.45 321	96.95 331	98.94 290	99.68 164	97.73 328	99.09 209	94.19 396	98.61 247	99.56 193	99.30 303	84.30 392	99.93 95	98.27 192	99.54 285	99.16 295

our_test_3		98.85 233	99.09 168	98.13 341	99.66 170	94.90 378	97.72 355	99.58 203	99.07 195	99.64 156	99.62 197	98.19 209	99.93 95	98.41 182	99.95 84	99.55 175

MSP-MVS		99.04 202	98.79 229	99.81 41	99.78 106	99.73 77	99.35 121	99.57 205	98.54 254	99.54 200	98.99 350	96.81 280	99.93 95	96.97 295	99.53 287	99.77 61
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
region2R		99.23 151	99.05 180	99.77 58	99.76 118	99.70 91	99.31 132	99.59 193	98.41 265	99.32 255	99.36 290	98.73 136	99.93 95	97.29 275	99.74 218	99.67 96

APDe-MVS		99.48 88	99.36 110	99.85 27	99.55 214	99.81 40	99.50 91	99.69 137	98.99 201	99.75 115	99.71 139	98.79 125	99.93 95	98.46 180	99.85 157	99.80 47
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
CVMVSNet		98.61 253	98.88 217	97.80 349	99.58 192	93.60 385	99.26 149	99.64 163	99.66 100	99.72 128	99.67 167	93.26 331	99.93 95	99.30 99	99.81 188	99.87 30

ACMMPR		99.23 151	99.06 176	99.76 65	99.74 135	99.69 95	99.31 132	99.59 193	98.36 271	99.35 247	99.38 284	98.61 151	99.93 95	97.43 268	99.75 211	99.67 96

PGM-MVS		99.20 166	99.01 192	99.77 58	99.75 129	99.71 84	99.16 183	99.72 122	97.99 300	99.42 231	99.60 214	98.81 120	99.93 95	96.91 298	99.74 218	99.66 105

LCM-MVSNet-Re		99.28 140	99.15 149	99.67 110	99.33 295	99.76 62	99.34 122	99.97 18	98.93 210	99.91 44	99.79 93	98.68 140	99.93 95	96.80 305	99.56 276	99.30 267

PMMVS2		99.48 88	99.45 92	99.57 163	99.76 118	98.99 236	98.09 327	99.90 37	98.95 206	99.78 101	99.58 222	99.57 38	99.93 95	99.48 68	99.95 84	99.79 54

mPP-MVS		99.19 169	99.00 195	99.76 65	99.76 118	99.68 98	99.38 113	99.54 222	98.34 280	99.01 300	99.50 253	98.53 166	99.93 95	97.18 288	99.78 203	99.66 105

OurMVSNet-221017-0		99.75 32	99.71 38	99.84 31	99.96 7	99.83 29	99.83 6	99.85 53	99.80 65	99.93 37	99.93 17	98.54 162	99.93 95	99.59 51	99.98 41	99.76 67

CHOSEN 1792x2688		99.39 116	99.30 124	99.65 122	99.88 45	99.25 204	98.78 268	99.88 43	98.66 241	99.96 23	99.79 93	97.45 255	99.93 95	99.34 90	99.99 16	99.78 57

N_pmnet		98.73 245	98.53 252	99.35 227	99.72 141	98.67 265	98.34 306	94.65 393	98.35 276	99.79 97	99.68 163	98.03 220	99.93 95	98.28 191	99.92 106	99.44 230

UGNet		99.38 118	99.34 112	99.49 182	98.90 358	98.90 248	99.70 35	99.35 285	99.86 46	98.57 343	99.81 79	98.50 172	99.93 95	99.38 81	99.98 41	99.66 105
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
EC-MVSNet		99.69 43	99.69 43	99.68 107	99.71 144	99.91 4	99.76 19	99.96 23	99.86 46	99.51 212	99.39 282	99.57 38	99.93 95	99.64 48	99.86 153	99.20 286

EPP-MVSNet		99.17 177	99.00 195	99.66 117	99.80 87	99.43 163	99.70 35	99.24 311	99.48 126	99.56 193	99.77 108	94.89 313	99.93 95	98.72 167	99.89 125	99.63 128

DeepC-MVS	98.90 4	99.62 66	99.61 60	99.67 110	99.72 141	99.44 159	99.24 157	99.71 125	99.27 160	99.93 37	99.90 29	99.70 24	99.93 95	98.99 138	99.99 16	99.64 123
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
fmvsm_s_conf0.1_n		99.86 9	99.85 16	99.89 11	99.93 26	99.78 49	99.07 215	99.98 11	99.99 2	99.98 13	99.90 29	99.88 8	99.92 117	99.93 20	99.99 16	99.98 3

fmvsm_s_conf0.5_n		99.83 19	99.81 23	99.87 21	99.85 59	99.78 49	99.03 223	99.96 23	99.99 2	99.97 19	99.84 62	99.78 17	99.92 117	99.92 22	99.99 16	99.92 18

iter_conf_final		98.75 241	98.54 250	99.40 211	99.33 295	98.75 260	99.26 149	99.59 193	99.80 65	99.76 108	99.58 222	90.17 367	99.92 117	99.37 84	99.97 56	99.54 183

EGC-MVSNET		89.05 364	85.52 367	99.64 129	99.89 40	99.78 49	99.56 81	99.52 236	24.19 399	49.96 400	99.83 66	99.15 81	99.92 117	97.71 244	99.85 157	99.21 282

DVP-MVS++		99.38 118	99.25 137	99.77 58	99.03 348	99.77 54	99.74 24	99.61 175	99.18 175	99.76 108	99.61 206	99.00 100	99.92 117	97.72 242	99.60 269	99.62 139

MSC_two_6792asdad				99.74 80	99.03 348	99.53 142		99.23 312					99.92 117	97.77 236	99.69 238	99.78 57

No_MVS				99.74 80	99.03 348	99.53 142		99.23 312					99.92 117	97.77 236	99.69 238	99.78 57

ZD-MVS					99.43 264	99.61 124		99.43 263	96.38 359	99.11 291	99.07 339	97.86 232	99.92 117	94.04 378	99.49 296

SED-MVS		99.40 112	99.28 131	99.77 58	99.69 156	99.82 35	99.20 167	99.54 222	99.13 188	99.82 81	99.63 190	98.91 112	99.92 117	97.85 231	99.70 234	99.58 165

test_241102_TWO								99.54 222	99.13 188	99.76 108	99.63 190	98.32 196	99.92 117	97.85 231	99.69 238	99.75 70

ZNCC-MVS		99.22 159	99.04 185	99.77 58	99.76 118	99.73 77	99.28 144	99.56 210	98.19 290	99.14 287	99.29 306	98.84 119	99.92 117	97.53 263	99.80 193	99.64 123

test_0728_SECOND				99.83 34	99.70 152	99.79 46	99.14 187	99.61 175					99.92 117	97.88 225	99.72 229	99.77 61

SR-MVS		99.19 169	99.00 195	99.74 80	99.51 229	99.72 82	99.18 172	99.60 187	98.85 220	99.47 219	99.58 222	98.38 187	99.92 117	96.92 297	99.54 285	99.57 170

DPE-MVS		99.14 183	98.92 212	99.82 38	99.57 202	99.77 54	98.74 271	99.60 187	98.55 251	99.76 108	99.69 152	98.23 206	99.92 117	96.39 327	99.75 211	99.76 67
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
iter_conf05		98.46 273	98.23 276	99.15 265	99.04 347	97.99 313	99.10 204	99.61 175	99.79 68	99.76 108	99.58 222	87.88 377	99.92 117	99.31 98	99.97 56	99.53 189

MP-MVS		99.06 196	98.83 224	99.76 65	99.76 118	99.71 84	99.32 127	99.50 244	98.35 276	98.97 302	99.48 260	98.37 188	99.92 117	95.95 347	99.75 211	99.63 128
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PM-MVS		99.36 124	99.29 129	99.58 157	99.83 66	99.66 102	98.95 243	99.86 48	98.85 220	99.81 88	99.73 124	98.40 186	99.92 117	98.36 185	99.83 170	99.17 293

HPM-MVS		99.25 147	99.07 174	99.78 55	99.81 81	99.75 68	99.61 68	99.67 144	97.72 317	99.35 247	99.25 314	99.23 73	99.92 117	97.21 286	99.82 179	99.67 96
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm		97.15 328	96.95 331	97.75 351	98.91 357	94.24 381	99.32 127	97.96 371	97.71 318	98.29 352	99.32 299	86.72 386	99.92 117	98.10 209	96.24 394	99.09 312

RPMNet		98.60 255	98.53 252	98.83 308	99.05 345	98.12 304	99.30 135	99.62 168	99.86 46	99.16 283	99.74 120	92.53 340	99.92 117	98.75 164	98.77 353	98.44 367

CPTT-MVS		98.74 243	98.44 258	99.64 129	99.61 181	99.38 176	99.18 172	99.55 216	96.49 357	99.27 266	99.37 286	97.11 272	99.92 117	95.74 353	99.67 249	99.62 139

MIMVSNet1		99.66 54	99.62 56	99.80 46	99.94 19	99.87 15	99.69 42	99.77 94	99.78 70	99.93 37	99.89 34	97.94 227	99.92 117	99.65 46	99.98 41	99.62 139

CSCG		99.37 121	99.29 129	99.60 151	99.71 144	99.46 152	99.43 107	99.85 53	98.79 228	99.41 237	99.60 214	98.92 110	99.92 117	98.02 211	99.92 106	99.43 236

ACMMP		99.25 147	99.08 170	99.74 80	99.79 99	99.68 98	99.50 91	99.65 157	98.07 296	99.52 207	99.69 152	98.57 157	99.92 117	97.18 288	99.79 198	99.63 128
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
SR-MVS-dyc-post		99.27 144	99.11 159	99.73 89	99.54 216	99.74 74	99.26 149	99.62 168	99.16 182	99.52 207	99.64 179	98.41 182	99.91 141	97.27 278	99.61 266	99.54 183

DVP-MVS		99.32 136	99.17 145	99.77 58	99.69 156	99.80 44	99.14 187	99.31 294	99.16 182	99.62 169	99.61 206	98.35 190	99.91 141	97.88 225	99.72 229	99.61 149
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									99.18 175	99.62 169	99.61 206	98.58 156	99.91 141	97.72 242	99.80 193	99.77 61

GST-MVS		99.16 179	98.96 206	99.75 75	99.73 138	99.73 77	99.20 167	99.55 216	98.22 287	99.32 255	99.35 295	98.65 147	99.91 141	96.86 301	99.74 218	99.62 139

MP-MVS-pluss		99.14 183	98.92 212	99.80 46	99.83 66	99.83 29	98.61 277	99.63 165	96.84 353	99.44 225	99.58 222	98.81 120	99.91 141	97.70 247	99.82 179	99.67 96
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		99.25 147	99.08 170	99.76 65	99.73 138	99.70 91	99.31 132	99.59 193	98.36 271	99.36 246	99.37 286	98.80 124	99.91 141	97.43 268	99.75 211	99.68 90

HPM-MVS++		98.96 218	98.70 235	99.74 80	99.52 227	99.71 84	98.86 251	99.19 321	98.47 261	98.59 341	99.06 340	98.08 217	99.91 141	96.94 296	99.60 269	99.60 153

test-LLR		97.15 328	96.95 331	97.74 352	98.18 391	95.02 376	97.38 371	96.10 385	98.00 298	97.81 375	98.58 375	90.04 369	99.91 141	97.69 253	98.78 351	98.31 370

test-mter		96.23 350	95.73 351	97.74 352	98.18 391	95.02 376	97.38 371	96.10 385	97.90 307	97.81 375	98.58 375	79.12 400	99.91 141	97.69 253	98.78 351	98.31 370

VPA-MVSNet		99.66 54	99.62 56	99.79 52	99.68 164	99.75 68	99.62 63	99.69 137	99.85 51	99.80 92	99.81 79	98.81 120	99.91 141	99.47 69	99.88 134	99.70 80

XVG-ACMP-BASELINE		99.23 151	99.10 167	99.63 136	99.82 73	99.58 133	98.83 256	99.72 122	98.36 271	99.60 178	99.71 139	98.92 110	99.91 141	97.08 291	99.84 162	99.40 241

APD-MVS		98.87 231	98.59 242	99.71 100	99.50 235	99.62 118	99.01 228	99.57 205	96.80 355	99.54 200	99.63 190	98.29 198	99.91 141	95.24 362	99.71 232	99.61 149
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CR-MVSNet		98.35 285	98.20 280	98.83 308	99.05 345	98.12 304	99.30 135	99.67 144	97.39 334	99.16 283	99.79 93	91.87 346	99.91 141	98.78 162	98.77 353	98.44 367

FMVSNet5		97.80 308	97.25 324	99.42 202	98.83 365	98.97 239	99.38 113	99.80 79	98.87 218	99.25 268	99.69 152	80.60 396	99.91 141	98.96 144	99.90 116	99.38 245

XXY-MVS		99.71 39	99.67 47	99.81 41	99.89 40	99.72 82	99.59 74	99.82 66	99.39 146	99.82 81	99.84 62	99.38 54	99.91 141	99.38 81	99.93 102	99.80 47

sss		98.90 226	98.77 230	99.27 247	99.48 245	98.44 283	98.72 273	99.32 290	97.94 306	99.37 245	99.35 295	96.31 297	99.91 141	98.85 152	99.63 258	99.47 220

1112_ss		99.05 199	98.84 222	99.67 110	99.66 170	99.29 195	98.52 294	99.82 66	97.65 320	99.43 229	99.16 327	96.42 292	99.91 141	99.07 133	99.84 162	99.80 47

LS3D		99.24 150	99.11 159	99.61 148	98.38 385	99.79 46	99.57 79	99.68 140	99.61 110	99.15 285	99.71 139	98.70 138	99.91 141	97.54 261	99.68 243	99.13 305

testf1		99.63 60	99.60 63	99.72 95	99.94 19	99.95 2	99.47 99	99.89 39	99.43 141	99.88 62	99.80 83	99.26 70	99.90 159	98.81 157	99.88 134	99.32 261

APD_test2		99.63 60	99.60 63	99.72 95	99.94 19	99.95 2	99.47 99	99.89 39	99.43 141	99.88 62	99.80 83	99.26 70	99.90 159	98.81 157	99.88 134	99.32 261

test2506		94.73 362	94.59 364	95.15 379	99.59 187	85.90 405	99.75 22	74.01 405	99.89 36	99.71 133	99.86 54	79.00 401	99.90 159	99.52 64	99.99 16	99.65 113

test1111		97.74 310	98.16 285	96.49 373	99.60 183	89.86 403	99.71 34	91.21 399	99.89 36	99.88 62	99.87 47	93.73 327	99.90 159	99.56 57	99.99 16	99.70 80

KD-MVS_self_test		99.63 60	99.59 65	99.76 65	99.84 62	99.90 7	99.37 117	99.79 85	99.83 57	99.88 62	99.85 56	98.42 181	99.90 159	99.60 50	99.73 223	99.49 212

ET-MVSNet_ETH3D		96.78 336	96.07 345	98.91 296	99.26 311	97.92 321	97.70 357	96.05 388	97.96 305	92.37 398	98.43 383	87.06 380	99.90 159	98.27 192	97.56 386	98.91 339

tfpnnormal		99.43 103	99.38 104	99.60 151	99.87 52	99.75 68	99.59 74	99.78 91	99.71 82	99.90 50	99.69 152	98.85 118	99.90 159	97.25 283	99.78 203	99.15 297

pmmvs6		99.86 9	99.86 12	99.83 34	99.94 19	99.90 7	99.83 6	99.91 32	99.85 51	99.94 34	99.95 13	99.73 21	99.90 159	99.65 46	99.97 56	99.69 84

APD-MVS_3200maxsize		99.31 137	99.16 146	99.74 80	99.53 222	99.75 68	99.27 147	99.61 175	99.19 174	99.57 186	99.64 179	98.76 130	99.90 159	97.29 275	99.62 259	99.56 172

baseline2		96.83 335	96.28 341	98.46 327	99.09 342	96.91 351	98.83 256	93.87 397	97.23 341	96.23 392	98.36 384	88.12 376	99.90 159	96.68 311	98.14 378	98.57 360

XVG-OURS-SEG-HR		99.16 179	98.99 200	99.66 117	99.84 62	99.64 111	98.25 313	99.73 113	98.39 268	99.63 160	99.43 272	99.70 24	99.90 159	97.34 272	98.64 363	99.44 230

XVG-OURS		99.21 164	99.06 176	99.65 122	99.82 73	99.62 118	97.87 350	99.74 109	98.36 271	99.66 153	99.68 163	99.71 22	99.90 159	96.84 304	99.88 134	99.43 236

JIA-IIPM		98.06 300	97.92 303	98.50 325	98.59 379	97.02 348	98.80 264	98.51 357	99.88 41	97.89 370	99.87 47	91.89 345	99.90 159	98.16 205	97.68 385	98.59 357

GBi-Net		99.42 106	99.31 119	99.73 89	99.49 240	99.77 54	99.68 45	99.70 131	99.44 136	99.62 169	99.83 66	97.21 266	99.90 159	98.96 144	99.90 116	99.53 189

test1		99.42 106	99.31 119	99.73 89	99.49 240	99.77 54	99.68 45	99.70 131	99.44 136	99.62 169	99.83 66	97.21 266	99.90 159	98.96 144	99.90 116	99.53 189

FMVSNet1		99.66 54	99.63 55	99.73 89	99.78 106	99.77 54	99.68 45	99.70 131	99.67 96	99.82 81	99.83 66	98.98 104	99.90 159	99.24 106	99.97 56	99.53 189

WTY-MVS		98.59 258	98.37 265	99.26 250	99.43 264	98.40 286	98.74 271	99.13 328	98.10 293	99.21 277	99.24 319	94.82 314	99.90 159	97.86 229	98.77 353	99.49 212

ECVR-MVS		97.73 311	98.04 290	96.78 367	99.59 187	90.81 399	99.72 30	90.43 401	99.89 36	99.86 71	99.86 54	93.60 329	99.89 176	99.46 70	99.99 16	99.65 113

EI-MVSNet-UG-set		99.48 88	99.50 84	99.42 202	99.57 202	98.65 271	99.24 157	99.46 255	99.68 92	99.80 92	99.66 172	98.99 102	99.89 176	99.19 113	99.90 116	99.72 74

EI-MVSNet-Vis-set		99.47 95	99.49 85	99.42 202	99.57 202	98.66 268	99.24 157	99.46 255	99.67 96	99.79 97	99.65 177	98.97 106	99.89 176	99.15 121	99.89 125	99.71 77

新几何1				99.52 177	99.50 235	99.22 211		99.26 305	95.66 370	98.60 340	99.28 307	97.67 245	99.89 176	95.95 347	99.32 318	99.45 225

testdata2													99.89 176	95.99 344

testdata				99.42 202	99.51 229	98.93 245		99.30 297	96.20 362	98.87 316	99.40 278	98.33 195	99.89 176	96.29 331	99.28 323	99.44 230

TESTMET0.1,1		96.24 349	95.84 350	97.41 358	98.24 389	93.84 384	97.38 371	95.84 389	98.43 262	97.81 375	98.56 378	79.77 397	99.89 176	97.77 236	98.77 353	98.52 361

test20.03		99.55 77	99.54 78	99.58 157	99.79 99	99.37 179	99.02 226	99.89 39	99.60 116	99.82 81	99.62 197	98.81 120	99.89 176	99.43 73	99.86 153	99.47 220

MDA-MVSNet-bldmvs		99.06 196	99.05 180	99.07 279	99.80 87	97.83 323	98.89 248	99.72 122	99.29 156	99.63 160	99.70 146	96.47 290	99.89 176	98.17 204	99.82 179	99.50 207

LPG-MVS_test		99.22 159	99.05 180	99.74 80	99.82 73	99.63 116	99.16 183	99.73 113	97.56 322	99.64 156	99.69 152	99.37 56	99.89 176	96.66 313	99.87 145	99.69 84

LGP-MVS_train				99.74 80	99.82 73	99.63 116		99.73 113	97.56 322	99.64 156	99.69 152	99.37 56	99.89 176	96.66 313	99.87 145	99.69 84

Test_1112_low_res		98.95 221	98.73 231	99.63 136	99.68 164	99.15 221	98.09 327	99.80 79	97.14 346	99.46 223	99.40 278	96.11 302	99.89 176	99.01 137	99.84 162	99.84 36

PatchmatchNet		97.65 315	97.80 308	97.18 364	98.82 368	92.49 389	99.17 177	98.39 363	98.12 292	98.79 325	99.58 222	90.71 361	99.89 176	97.23 284	99.41 306	99.16 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMP	97.51 14	99.05 199	98.84 222	99.67 110	99.78 106	99.55 139	98.88 249	99.66 148	97.11 348	99.47 219	99.60 214	99.07 94	99.89 176	96.18 336	99.85 157	99.58 165
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_vis3_rt		99.89 3	99.90 3	99.87 21	99.98 3	99.75 68	99.70 35	100.00 1	99.73 76	100.00 1	99.89 34	99.79 16	99.88 190	99.98 1	100.00 1	99.98 3

FE-MVS		97.85 306	97.42 319	99.15 265	99.44 260	98.75 260	99.77 15	98.20 368	95.85 366	99.33 252	99.80 83	88.86 374	99.88 190	96.40 326	99.12 334	98.81 347

ppachtmachnet_test		98.89 229	99.12 156	98.20 339	99.66 170	95.24 375	97.63 359	99.68 140	99.08 193	99.78 101	99.62 197	98.65 147	99.88 190	98.02 211	99.96 71	99.48 216

TSAR-MVS + MP.		99.34 131	99.24 139	99.63 136	99.82 73	99.37 179	99.26 149	99.35 285	98.77 232	99.57 186	99.70 146	99.27 69	99.88 190	97.71 244	99.75 211	99.65 113
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
new-patchmatchnet		99.35 126	99.57 72	98.71 318	99.82 73	96.62 356	98.55 289	99.75 104	99.50 124	99.88 62	99.87 47	99.31 62	99.88 190	99.43 73	100.00 1	99.62 139

Anonymous20231206		99.35 126	99.31 119	99.47 188	99.74 135	99.06 234	99.28 144	99.74 109	99.23 168	99.72 128	99.53 246	97.63 251	99.88 190	99.11 129	99.84 162	99.48 216

XVS		99.27 144	99.11 159	99.75 75	99.71 144	99.71 84	99.37 117	99.61 175	99.29 156	98.76 328	99.47 264	98.47 173	99.88 190	97.62 255	99.73 223	99.67 96

v1240		99.56 74	99.58 69	99.51 179	99.80 87	99.00 235	99.00 231	99.65 157	99.15 186	99.90 50	99.75 117	99.09 89	99.88 190	99.90 25	99.96 71	99.67 96

X-MVStestdata		96.09 351	94.87 360	99.75 75	99.71 144	99.71 84	99.37 117	99.61 175	99.29 156	98.76 328	61.30 406	98.47 173	99.88 190	97.62 255	99.73 223	99.67 96

旧先验2							97.94 344		95.33 373	98.94 305			99.88 190	96.75 307

UniMVSNet (Re)		99.37 121	99.26 135	99.68 107	99.51 229	99.58 133	98.98 239	99.60 187	99.43 141	99.70 137	99.36 290	97.70 241	99.88 190	99.20 112	99.87 145	99.59 160

HPM-MVS_fast		99.43 103	99.30 124	99.80 46	99.83 66	99.81 40	99.52 86	99.70 131	98.35 276	99.51 212	99.50 253	99.31 62	99.88 190	98.18 202	99.84 162	99.69 84

TDRefinement		99.72 36	99.70 39	99.77 58	99.90 38	99.85 19	99.86 5	99.92 29	99.69 90	99.78 101	99.92 21	99.37 56	99.88 190	98.93 150	99.95 84	99.60 153

PCF-MVS	96.03 18	96.73 338	95.86 349	99.33 231	99.44 260	99.16 219	96.87 386	99.44 260	86.58 393	98.95 304	99.40 278	94.38 319	99.88 190	87.93 392	99.80 193	98.95 335
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
SF-MVS		99.10 193	98.93 208	99.62 145	99.58 192	99.51 144	99.13 193	99.65 157	97.97 302	99.42 231	99.61 206	98.86 117	99.87 204	96.45 325	99.68 243	99.49 212

D2MVS		99.22 159	99.19 143	99.29 242	99.69 156	98.74 262	98.81 261	99.41 266	98.55 251	99.68 143	99.69 152	98.13 213	99.87 204	98.82 155	99.98 41	99.24 275

thisisatest0515		96.98 332	96.42 339	98.66 319	99.42 269	97.47 335	97.27 376	94.30 395	97.24 340	99.15 285	98.86 365	85.01 389	99.87 204	97.10 290	99.39 308	98.63 354

ACMMP_NAP		99.28 140	99.11 159	99.79 52	99.75 129	99.81 40	98.95 243	99.53 231	98.27 285	99.53 205	99.73 124	98.75 132	99.87 204	97.70 247	99.83 170	99.68 90

Patchmatch-test		98.10 298	97.98 295	98.48 326	99.27 309	96.48 357	99.40 109	99.07 330	98.81 225	99.23 272	99.57 231	90.11 368	99.87 204	96.69 310	99.64 256	99.09 312

v144192		99.55 77	99.54 78	99.58 157	99.78 106	99.20 216	99.11 201	99.62 168	99.18 175	99.89 54	99.72 131	98.66 145	99.87 204	99.88 29	99.97 56	99.66 105

v1921920		99.56 74	99.57 72	99.55 169	99.75 129	99.11 224	99.05 216	99.61 175	99.15 186	99.88 62	99.71 139	99.08 92	99.87 204	99.90 25	99.97 56	99.66 105

FC-MVSNet-test		99.70 40	99.65 50	99.86 25	99.88 45	99.86 18	99.72 30	99.78 91	99.90 30	99.82 81	99.83 66	98.45 177	99.87 204	99.51 65	99.97 56	99.86 32

pm-mvs1		99.79 26	99.79 27	99.78 55	99.91 32	99.83 29	99.76 19	99.87 45	99.73 76	99.89 54	99.87 47	99.63 29	99.87 204	99.54 60	99.92 106	99.63 128

TransMVSNet (Re)		99.78 27	99.77 33	99.81 41	99.91 32	99.85 19	99.75 22	99.86 48	99.70 87	99.91 44	99.89 34	99.60 34	99.87 204	99.59 51	99.74 218	99.71 77

NR-MVSNet		99.40 112	99.31 119	99.68 107	99.43 264	99.55 139	99.73 27	99.50 244	99.46 133	99.88 62	99.36 290	97.54 252	99.87 204	98.97 142	99.87 145	99.63 128

Baseline_NR-MVSNet		99.49 86	99.37 107	99.82 38	99.91 32	99.84 24	98.83 256	99.86 48	99.68 92	99.65 155	99.88 42	97.67 245	99.87 204	99.03 135	99.86 153	99.76 67

EG-PatchMatch MVS		99.57 71	99.56 77	99.62 145	99.77 114	99.33 189	99.26 149	99.76 99	99.32 154	99.80 92	99.78 101	99.29 64	99.87 204	99.15 121	99.91 115	99.66 105

DELS-MVS		99.34 131	99.30 124	99.48 186	99.51 229	99.36 183	98.12 323	99.53 231	99.36 150	99.41 237	99.61 206	99.22 74	99.87 204	99.21 109	99.68 243	99.20 286
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
FMVSNet2		99.35 126	99.28 131	99.55 169	99.49 240	99.35 186	99.45 103	99.57 205	99.44 136	99.70 137	99.74 120	97.21 266	99.87 204	99.03 135	99.94 95	99.44 230

ab-mvs		99.33 134	99.28 131	99.47 188	99.57 202	99.39 174	99.78 12	99.43 263	98.87 218	99.57 186	99.82 73	98.06 218	99.87 204	98.69 170	99.73 223	99.15 297

DP-MVS		99.48 88	99.39 102	99.74 80	99.57 202	99.62 118	99.29 142	99.61 175	99.87 42	99.74 123	99.76 112	98.69 139	99.87 204	98.20 198	99.80 193	99.75 70

F-COLMAP		98.74 243	98.45 257	99.62 145	99.57 202	99.47 148	98.84 254	99.65 157	96.31 361	98.93 306	99.19 326	97.68 244	99.87 204	96.52 320	99.37 311	99.53 189

Anonymous20240529		99.42 106	99.34 112	99.65 122	99.53 222	99.60 127	99.63 61	99.39 276	99.47 130	99.76 108	99.78 101	98.13 213	99.86 222	98.70 168	99.68 243	99.49 212

test_post											52.41 407	90.25 366	99.86 222

Anonymous20231211		99.62 66	99.57 72	99.76 65	99.61 181	99.60 127	99.81 9	99.73 113	99.82 59	99.90 50	99.90 29	97.97 226	99.86 222	99.42 78	99.96 71	99.80 47

v10		99.69 43	99.69 43	99.66 117	99.81 81	99.39 174	99.66 53	99.75 104	99.60 116	99.92 41	99.87 47	98.75 132	99.86 222	99.90 25	99.99 16	99.73 72

VPNet		99.46 96	99.37 107	99.71 100	99.82 73	99.59 129	99.48 96	99.70 131	99.81 62	99.69 140	99.58 222	97.66 249	99.86 222	99.17 118	99.44 301	99.67 96

testgi		99.29 139	99.26 135	99.37 221	99.75 129	98.81 254	98.84 254	99.89 39	98.38 269	99.75 115	99.04 343	99.36 59	99.86 222	99.08 132	99.25 327	99.45 225

mvs_anonymous		99.28 140	99.39 102	98.94 290	99.19 324	97.81 324	99.02 226	99.55 216	99.78 70	99.85 73	99.80 83	98.24 202	99.86 222	99.57 56	99.50 294	99.15 297

diffmvs		99.34 131	99.32 117	99.39 215	99.67 169	98.77 259	98.57 287	99.81 75	99.61 110	99.48 217	99.41 274	98.47 173	99.86 222	98.97 142	99.90 116	99.53 189
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WR-MVS		99.11 190	98.93 208	99.66 117	99.30 302	99.42 166	98.42 303	99.37 281	99.04 198	99.57 186	99.20 325	96.89 278	99.86 222	98.66 172	99.87 145	99.70 80

114514_t		98.49 270	98.11 287	99.64 129	99.73 138	99.58 133	99.24 157	99.76 99	89.94 391	99.42 231	99.56 235	97.76 240	99.86 222	97.74 241	99.82 179	99.47 220

UnsupCasMVSNet_eth		98.83 234	98.57 246	99.59 153	99.68 164	99.45 157	98.99 236	99.67 144	99.48 126	99.55 198	99.36 290	94.92 312	99.86 222	98.95 148	96.57 391	99.45 225

FMVSNet3		98.80 237	98.63 239	99.32 235	99.13 332	98.72 263	99.10 204	99.48 249	99.23 168	99.62 169	99.64 179	92.57 338	99.86 222	98.96 144	99.90 116	99.39 243

HY-MVS	98.23 9	98.21 294	97.95 297	98.99 285	99.03 348	98.24 294	99.61 68	98.72 346	96.81 354	98.73 330	99.51 250	94.06 321	99.86 222	96.91 298	98.20 374	98.86 343

TAMVS		99.49 86	99.45 92	99.63 136	99.48 245	99.42 166	99.45 103	99.57 205	99.66 100	99.78 101	99.83 66	97.85 234	99.86 222	99.44 72	99.96 71	99.61 149

ACMM	98.09 11	99.46 96	99.38 104	99.72 95	99.80 87	99.69 95	99.13 193	99.65 157	98.99 201	99.64 156	99.72 131	99.39 50	99.86 222	98.23 195	99.81 188	99.60 153
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS_ROB	97.31 17	97.36 325	96.84 335	98.89 303	99.29 304	99.45 157	98.87 250	99.48 249	86.54 394	99.44 225	99.74 120	97.34 261	99.86 222	91.61 385	99.28 323	97.37 389

COLMAP_ROB	98.06 12	99.45 98	99.37 107	99.70 104	99.83 66	99.70 91	99.38 113	99.78 91	99.53 122	99.67 149	99.78 101	99.19 77	99.86 222	97.32 273	99.87 145	99.55 175
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing3		96.48 343	95.63 353	99.01 284	99.23 316	97.81 324	98.90 247	99.10 329	98.72 237	97.84 374	97.92 391	72.44 403	99.85 239	97.21 286	99.33 316	99.35 254

hse-mvs2		98.52 265	98.30 273	99.16 263	99.29 304	98.60 275	98.77 269	99.02 334	99.68 92	99.32 255	99.04 343	92.50 341	99.85 239	99.24 106	97.87 383	99.03 326

AUN-MVS		97.82 307	97.38 320	99.14 269	99.27 309	98.53 277	98.72 273	99.02 334	98.10 293	97.18 385	99.03 347	89.26 373	99.85 239	97.94 220	97.91 381	99.03 326

miper_lstm_enhance		98.65 252	98.60 240	98.82 311	99.20 322	97.33 340	97.78 353	99.66 148	99.01 200	99.59 181	99.50 253	94.62 317	99.85 239	98.12 207	99.90 116	99.26 272

TEST9					99.35 282	99.35 186	98.11 325	99.41 266	94.83 381	97.92 368	98.99 350	98.02 221	99.85 239

train_agg		98.35 285	97.95 297	99.57 163	99.35 282	99.35 186	98.11 325	99.41 266	94.90 378	97.92 368	98.99 350	98.02 221	99.85 239	95.38 360	99.44 301	99.50 207

agg_prior					99.35 282	99.36 183		99.39 276		97.76 378			99.85 239

FIs		99.65 59	99.58 69	99.84 31	99.84 62	99.85 19	99.66 53	99.75 104	99.86 46	99.74 123	99.79 93	98.27 200	99.85 239	99.37 84	99.93 102	99.83 40

v1192		99.57 71	99.57 72	99.57 163	99.77 114	99.22 211	99.04 219	99.60 187	99.18 175	99.87 70	99.72 131	99.08 92	99.85 239	99.89 28	99.98 41	99.66 105

无先验							98.01 335	99.23 312	95.83 367				99.85 239	95.79 352		99.44 230

VDD-MVS		99.20 166	99.11 159	99.44 196	99.43 264	98.98 237	99.50 91	98.32 366	99.80 65	99.56 193	99.69 152	96.99 276	99.85 239	98.99 138	99.73 223	99.50 207

VDDNet		98.97 215	98.82 225	99.42 202	99.71 144	98.81 254	99.62 63	98.68 348	99.81 62	99.38 244	99.80 83	94.25 320	99.85 239	98.79 159	99.32 318	99.59 160

EI-MVSNet		99.38 118	99.44 95	99.21 257	99.58 192	98.09 308	99.26 149	99.46 255	99.62 107	99.75 115	99.67 167	98.54 162	99.85 239	99.15 121	99.92 106	99.68 90

MVSTER		98.47 272	98.22 278	99.24 255	99.06 344	98.35 292	99.08 212	99.46 255	99.27 160	99.75 115	99.66 172	88.61 375	99.85 239	99.14 127	99.92 106	99.52 200

ACMH	98.42 6	99.59 70	99.54 78	99.72 95	99.86 55	99.62 118	99.56 81	99.79 85	98.77 232	99.80 92	99.85 56	99.64 28	99.85 239	98.70 168	99.89 125	99.70 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
APD_test1		99.36 124	99.28 131	99.61 148	99.89 40	99.89 10	99.32 127	99.74 109	99.18 175	99.69 140	99.75 117	98.41 182	99.84 254	97.85 231	99.70 234	99.10 308

test_vis1_rt		99.45 98	99.46 90	99.41 209	99.71 144	98.63 273	98.99 236	99.96 23	99.03 199	99.95 31	99.12 333	98.75 132	99.84 254	99.82 35	99.82 179	99.77 61

FA-MVS(test-final)		98.52 265	98.32 271	99.10 274	99.48 245	98.67 265	99.77 15	98.60 354	97.35 336	99.63 160	99.80 83	93.07 334	99.84 254	97.92 221	99.30 320	98.78 350

EIA-MVS		99.12 187	99.01 192	99.45 193	99.36 280	99.62 118	99.34 122	99.79 85	98.41 265	98.84 319	98.89 363	98.75 132	99.84 254	98.15 206	99.51 291	98.89 340

Anonymous202405211		98.75 241	98.46 256	99.63 136	99.34 290	99.66 102	99.47 99	97.65 376	99.28 159	99.56 193	99.50 253	93.15 332	99.84 254	98.62 173	99.58 274	99.40 241

Effi-MVS+		99.06 196	98.97 204	99.34 228	99.31 298	98.98 237	98.31 309	99.91 32	98.81 225	98.79 325	98.94 359	99.14 84	99.84 254	98.79 159	98.74 357	99.20 286

gm-plane-assit					97.59 395	89.02 404			93.47 384		98.30 385		99.84 254	96.38 328

test_8					99.34 290	99.31 192	98.08 329	99.40 273	94.90 378	97.87 372	98.97 355	98.02 221	99.84 254

v1144		99.54 79	99.53 82	99.59 153	99.79 99	99.28 197	99.10 204	99.61 175	99.20 173	99.84 76	99.73 124	98.67 143	99.84 254	99.86 31	99.98 41	99.64 123

v8		99.68 46	99.69 43	99.65 122	99.80 87	99.40 172	99.66 53	99.76 99	99.64 104	99.93 37	99.85 56	98.66 145	99.84 254	99.88 29	99.99 16	99.71 77

v2v482		99.50 84	99.47 86	99.58 157	99.78 106	99.25 204	99.14 187	99.58 203	99.25 164	99.81 88	99.62 197	98.24 202	99.84 254	99.83 32	99.97 56	99.64 123

VNet		99.18 173	99.06 176	99.56 166	99.24 314	99.36 183	99.33 125	99.31 294	99.67 96	99.47 219	99.57 231	96.48 289	99.84 254	99.15 121	99.30 320	99.47 220

ADS-MVSNet		97.72 314	97.67 315	97.86 347	99.14 330	94.65 379	99.22 164	98.86 339	96.97 349	98.25 354	99.64 179	90.90 357	99.84 254	96.51 321	99.56 276	99.08 317

casdiffmvs_mvg		99.68 46	99.68 46	99.69 105	99.81 81	99.59 129	99.29 142	99.90 37	99.71 82	99.79 97	99.73 124	99.54 41	99.84 254	99.36 86	99.96 71	99.65 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LF4IMVS		99.01 209	98.92 212	99.27 247	99.71 144	99.28 197	98.59 282	99.77 94	98.32 282	99.39 243	99.41 274	98.62 149	99.84 254	96.62 317	99.84 162	98.69 353

9.14			98.64 237		99.45 259		98.81 261	99.60 187	97.52 327	99.28 265	99.56 235	98.53 166	99.83 269	95.36 361	99.64 256

SMA-MVS		99.19 169	99.00 195	99.73 89	99.46 255	99.73 77	99.13 193	99.52 236	97.40 333	99.57 186	99.64 179	98.93 109	99.83 269	97.61 257	99.79 198	99.63 128
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
EU-MVSNet		99.39 116	99.62 56	98.72 316	99.88 45	96.44 358	99.56 81	99.85 53	99.90 30	99.90 50	99.85 56	98.09 215	99.83 269	99.58 54	99.95 84	99.90 20

YYNet1		98.95 221	98.99 200	98.84 306	99.64 174	97.14 346	98.22 315	99.32 290	98.92 212	99.59 181	99.66 172	97.40 257	99.83 269	98.27 192	99.90 116	99.55 175

MDA-MVSNet_test_wron		98.95 221	98.99 200	98.85 304	99.64 174	97.16 344	98.23 314	99.33 288	98.93 210	99.56 193	99.66 172	97.39 259	99.83 269	98.29 190	99.88 134	99.55 175

baseline		99.63 60	99.62 56	99.66 117	99.80 87	99.62 118	99.44 105	99.80 79	99.71 82	99.72 128	99.69 152	99.15 81	99.83 269	99.32 95	99.94 95	99.53 189

CDS-MVSNet		99.22 159	99.13 152	99.50 181	99.35 282	99.11 224	98.96 242	99.54 222	99.46 133	99.61 175	99.70 146	96.31 297	99.83 269	99.34 90	99.88 134	99.55 175
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DeepC-MVS_fast	98.47 5	99.23 151	99.12 156	99.56 166	99.28 307	99.22 211	98.99 236	99.40 273	99.08 193	99.58 183	99.64 179	98.90 115	99.83 269	97.44 267	99.75 211	99.63 128
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
PLC	97.35 16	98.36 282	97.99 293	99.48 186	99.32 297	99.24 208	98.50 296	99.51 240	95.19 376	98.58 342	98.96 357	96.95 277	99.83 269	95.63 354	99.25 327	99.37 248
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs5		99.19 169	99.11 159	99.42 202	99.76 118	98.88 250	98.55 289	99.73 113	98.82 224	99.72 128	99.62 197	96.56 286	99.82 278	99.32 95	99.95 84	99.56 172

test_post1							99.14 187				51.63 408	89.54 372	99.82 278	96.86 301

原ACMM1				99.37 221	99.47 251	98.87 252		99.27 302	96.74 356	98.26 353	99.32 299	97.93 228	99.82 278	95.96 346	99.38 309	99.43 236

V42		99.56 74	99.54 78	99.63 136	99.79 99	99.46 152	99.39 111	99.59 193	99.24 166	99.86 71	99.70 146	98.55 160	99.82 278	99.79 37	99.95 84	99.60 153

CDPH-MVS		98.56 261	98.20 280	99.61 148	99.50 235	99.46 152	98.32 308	99.41 266	95.22 374	99.21 277	99.10 337	98.34 193	99.82 278	95.09 366	99.66 252	99.56 172

test12				99.54 174	99.29 304	99.33 189		99.16 324		98.43 349		97.54 252	99.82 278		99.47 298	99.48 216

casdiffmvs		99.63 60	99.61 60	99.67 110	99.79 99	99.59 129	99.13 193	99.85 53	99.79 68	99.76 108	99.72 131	99.33 61	99.82 278	99.21 109	99.94 95	99.59 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline1		97.73 311	97.33 321	98.96 288	99.30 302	97.73 328	99.40 109	98.42 361	99.33 153	99.46 223	99.21 323	91.18 352	99.82 278	98.35 186	91.26 397	99.32 261

HQP_MVS		98.90 226	98.68 236	99.55 169	99.58 192	99.24 208	98.80 264	99.54 222	98.94 207	99.14 287	99.25 314	97.24 264	99.82 278	95.84 350	99.78 203	99.60 153

plane_prior5								99.54 222					99.82 278	95.84 350	99.78 203	99.60 153

tpmrst		97.73 311	98.07 289	96.73 370	98.71 376	92.00 391	99.10 204	98.86 339	98.52 255	98.92 309	99.54 244	91.90 344	99.82 278	98.02 211	99.03 340	98.37 369

UnsupCasMVSNet_bld		98.55 262	98.27 275	99.40 211	99.56 213	99.37 179	97.97 342	99.68 140	97.49 329	99.08 294	99.35 295	95.41 311	99.82 278	97.70 247	98.19 376	99.01 331

dp		96.86 334	97.07 327	96.24 376	98.68 378	90.30 402	99.19 171	98.38 364	97.35 336	98.23 356	99.59 219	87.23 379	99.82 278	96.27 332	98.73 359	98.59 357

test_0402		99.22 159	99.14 150	99.45 193	99.79 99	99.43 163	99.28 144	99.68 140	99.54 120	99.40 242	99.56 235	99.07 94	99.82 278	96.01 341	99.96 71	99.11 306

PMMVS		98.49 270	98.29 274	99.11 272	98.96 355	98.42 285	97.54 363	99.32 290	97.53 326	98.47 348	98.15 388	97.88 231	99.82 278	97.46 266	99.24 329	99.09 312

tt0805		99.63 60	99.57 72	99.81 41	99.87 52	99.88 12	99.58 76	98.70 347	99.72 80	99.91 44	99.60 214	99.43 48	99.81 293	99.81 36	99.53 287	99.73 72

LFMVS		98.46 273	98.19 283	99.26 250	99.24 314	98.52 279	99.62 63	96.94 383	99.87 42	99.31 259	99.58 222	91.04 354	99.81 293	98.68 171	99.42 305	99.45 225

NCCC		98.82 235	98.57 246	99.58 157	99.21 319	99.31 192	98.61 277	99.25 308	98.65 242	98.43 349	99.26 312	97.86 232	99.81 293	96.55 318	99.27 326	99.61 149

MIMVSNet		98.43 276	98.20 280	99.11 272	99.53 222	98.38 290	99.58 76	98.61 352	98.96 205	99.33 252	99.76 112	90.92 356	99.81 293	97.38 271	99.76 209	99.15 297

IS-MVSNet		99.03 203	98.85 220	99.55 169	99.80 87	99.25 204	99.73 27	99.15 325	99.37 148	99.61 175	99.71 139	94.73 316	99.81 293	97.70 247	99.88 134	99.58 165

AdaColmap		98.60 255	98.35 268	99.38 218	99.12 334	99.22 211	98.67 276	99.42 265	97.84 314	98.81 322	99.27 309	97.32 262	99.81 293	95.14 364	99.53 287	99.10 308

MCST-MVS		99.02 205	98.81 226	99.65 122	99.58 192	99.49 146	98.58 283	99.07 330	98.40 267	99.04 299	99.25 314	98.51 171	99.80 299	97.31 274	99.51 291	99.65 113

CostFormer		96.71 339	96.79 338	96.46 374	98.90 358	90.71 400	99.41 108	98.68 348	94.69 382	98.14 362	99.34 298	86.32 388	99.80 299	97.60 258	98.07 380	98.88 341

PHI-MVS		99.11 190	98.95 207	99.59 153	99.13 332	99.59 129	99.17 177	99.65 157	97.88 310	99.25 268	99.46 267	98.97 106	99.80 299	97.26 280	99.82 179	99.37 248

Patchmatch-RL test		98.60 255	98.36 266	99.33 231	99.77 114	99.07 232	98.27 311	99.87 45	98.91 213	99.74 123	99.72 131	90.57 363	99.79 302	98.55 176	99.85 157	99.11 306

test0.0.03 1		97.37 324	96.91 334	98.74 315	97.72 394	97.57 332	97.60 361	97.36 382	98.00 298	99.21 277	98.02 389	90.04 369	99.79 302	98.37 184	95.89 395	98.86 343

MSDG		99.08 194	98.98 203	99.37 221	99.60 183	99.13 222	97.54 363	99.74 109	98.84 223	99.53 205	99.55 242	99.10 87	99.79 302	97.07 292	99.86 153	99.18 291

cl____		98.54 263	98.41 261	98.92 294	99.03 348	97.80 326	97.46 369	99.59 193	98.90 214	99.60 178	99.46 267	93.85 324	99.78 305	97.97 218	99.89 125	99.17 293

DIV-MVS_self_test		98.54 263	98.42 260	98.92 294	99.03 348	97.80 326	97.46 369	99.59 193	98.90 214	99.60 178	99.46 267	93.87 323	99.78 305	97.97 218	99.89 125	99.18 291

MVP-Stereo		99.16 179	99.08 170	99.43 200	99.48 245	99.07 232	99.08 212	99.55 216	98.63 244	99.31 259	99.68 163	98.19 209	99.78 305	98.18 202	99.58 274	99.45 225
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
nrg030		99.70 40	99.66 48	99.82 38	99.76 118	99.84 24	99.61 68	99.70 131	99.93 26	99.78 101	99.68 163	99.10 87	99.78 305	99.45 71	99.96 71	99.83 40

Vis-MVSNet (Re-imp)		98.77 239	98.58 245	99.34 228	99.78 106	98.88 250	99.61 68	99.56 210	99.11 192	99.24 271	99.56 235	93.00 336	99.78 305	97.43 268	99.89 125	99.35 254

CNLPA		98.57 260	98.34 269	99.28 244	99.18 326	99.10 229	98.34 306	99.41 266	98.48 260	98.52 345	98.98 353	97.05 274	99.78 305	95.59 355	99.50 294	98.96 333

ACMH+	98.40 8	99.50 84	99.43 97	99.71 100	99.86 55	99.76 62	99.32 127	99.77 94	99.53 122	99.77 106	99.76 112	99.26 70	99.78 305	97.77 236	99.88 134	99.60 153

CLD-MVS		98.76 240	98.57 246	99.33 231	99.57 202	98.97 239	97.53 365	99.55 216	96.41 358	99.27 266	99.13 329	99.07 94	99.78 305	96.73 309	99.89 125	99.23 278
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
PVSNet_BlendedMVS		99.03 203	99.01 192	99.09 275	99.54 216	97.99 313	98.58 283	99.82 66	97.62 321	99.34 250	99.71 139	98.52 169	99.77 313	97.98 216	99.97 56	99.52 200

PVSNet_Blended		98.70 248	98.59 242	99.02 283	99.54 216	97.99 313	97.58 362	99.82 66	95.70 369	99.34 250	98.98 353	98.52 169	99.77 313	97.98 216	99.83 170	99.30 267

eth_miper_zixun_eth		98.68 250	98.71 233	98.60 320	99.10 340	96.84 353	97.52 367	99.54 222	98.94 207	99.58 183	99.48 260	96.25 300	99.76 315	98.01 214	99.93 102	99.21 282

OPM-MVS		99.26 146	99.13 152	99.63 136	99.70 152	99.61 124	98.58 283	99.48 249	98.50 257	99.52 207	99.63 190	99.14 84	99.76 315	97.89 224	99.77 207	99.51 202
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
pmmvs-eth3d		99.48 88	99.47 86	99.51 179	99.77 114	99.41 171	98.81 261	99.66 148	99.42 145	99.75 115	99.66 172	99.20 76	99.76 315	98.98 140	99.99 16	99.36 251

pmmvs4		99.13 185	99.06 176	99.36 225	99.57 202	99.10 229	98.01 335	99.25 308	98.78 230	99.58 183	99.44 271	98.24 202	99.76 315	98.74 165	99.93 102	99.22 280

AllTest		99.21 164	99.07 174	99.63 136	99.78 106	99.64 111	99.12 197	99.83 61	98.63 244	99.63 160	99.72 131	98.68 140	99.75 319	96.38 328	99.83 170	99.51 202

TestCases				99.63 136	99.78 106	99.64 111		99.83 61	98.63 244	99.63 160	99.72 131	98.68 140	99.75 319	96.38 328	99.83 170	99.51 202

CL-MVSNet_self_test		98.71 247	98.56 249	99.15 265	99.22 317	98.66 268	97.14 380	99.51 240	98.09 295	99.54 200	99.27 309	96.87 279	99.74 321	98.43 181	98.96 343	99.03 326

MVS		95.72 358	94.63 363	98.99 285	98.56 380	97.98 319	99.30 135	98.86 339	72.71 397	97.30 381	99.08 338	98.34 193	99.74 321	89.21 389	98.33 371	99.26 272

MG-MVS		98.52 265	98.39 263	98.94 290	99.15 329	97.39 339	98.18 316	99.21 318	98.89 217	99.23 272	99.63 190	97.37 260	99.74 321	94.22 375	99.61 266	99.69 84

c3_l		98.72 246	98.71 233	98.72 316	99.12 334	97.22 343	97.68 358	99.56 210	98.90 214	99.54 200	99.48 260	96.37 296	99.73 324	97.88 225	99.88 134	99.21 282

tpmvs		97.39 323	97.69 313	96.52 372	98.41 384	91.76 392	99.30 135	98.94 338	97.74 316	97.85 373	99.55 242	92.40 343	99.73 324	96.25 333	98.73 359	98.06 381

thres600view7		96.60 341	96.16 343	97.93 345	99.63 176	96.09 366	99.18 172	97.57 377	98.77 232	98.72 331	97.32 398	87.04 381	99.72 326	88.57 390	98.62 364	97.98 382

EPMVS		96.53 342	96.32 340	97.17 365	98.18 391	92.97 388	99.39 111	89.95 402	98.21 288	98.61 339	99.59 219	86.69 387	99.72 326	96.99 294	99.23 331	98.81 347

PVSNet	97.47 15	98.42 277	98.44 258	98.35 331	99.46 255	96.26 362	96.70 388	99.34 287	97.68 319	99.00 301	99.13 329	97.40 257	99.72 326	97.59 259	99.68 243	99.08 317

MAR-MVS		98.24 291	97.92 303	99.19 260	98.78 372	99.65 108	99.17 177	99.14 326	95.36 372	98.04 365	98.81 368	97.47 254	99.72 326	95.47 358	99.06 337	98.21 376
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
miper_ehance_all_eth		98.59 258	98.59 242	98.59 321	98.98 354	97.07 347	97.49 368	99.52 236	98.50 257	99.52 207	99.37 286	96.41 294	99.71 330	97.86 229	99.62 259	99.00 332

Gipuma		99.57 71	99.59 65	99.49 182	99.98 3	99.71 84	99.72 30	99.84 59	99.81 62	99.94 34	99.78 101	98.91 112	99.71 330	98.41 182	99.95 84	99.05 324
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ambc				99.20 259	99.35 282	98.53 277	99.17 177	99.46 255		99.67 149	99.80 83	98.46 176	99.70 332	97.92 221	99.70 234	99.38 245

HQP4-MVS										98.15 358			99.70 332			99.53 189

CNVR-MVS		98.99 214	98.80 228	99.56 166	99.25 312	99.43 163	98.54 292	99.27 302	98.58 249	98.80 324	99.43 272	98.53 166	99.70 332	97.22 285	99.59 273	99.54 183

tpm2		96.35 346	96.22 342	96.73 370	98.88 363	91.75 393	99.21 166	98.51 357	93.27 385	97.89 370	99.21 323	84.83 390	99.70 332	96.04 340	98.18 377	98.75 352

HQP-MVS		98.36 282	98.02 292	99.39 215	99.31 298	98.94 242	97.98 339	99.37 281	97.45 330	98.15 358	98.83 366	96.67 283	99.70 332	94.73 368	99.67 249	99.53 189

PatchMatch-RL		98.68 250	98.47 255	99.30 241	99.44 260	99.28 197	98.14 321	99.54 222	97.12 347	99.11 291	99.25 314	97.80 237	99.70 332	96.51 321	99.30 320	98.93 337

miper_enhance_ethall		98.03 301	97.94 301	98.32 334	98.27 388	96.43 359	96.95 384	99.41 266	96.37 360	99.43 229	98.96 357	94.74 315	99.69 338	97.71 244	99.62 259	98.83 346

test_yl		98.25 289	97.95 297	99.13 270	99.17 327	98.47 280	99.00 231	98.67 350	98.97 203	99.22 275	99.02 348	91.31 350	99.69 338	97.26 280	98.93 344	99.24 275

DCV-MVSNet		98.25 289	97.95 297	99.13 270	99.17 327	98.47 280	99.00 231	98.67 350	98.97 203	99.22 275	99.02 348	91.31 350	99.69 338	97.26 280	98.93 344	99.24 275

MS-PatchMatch		99.00 211	98.97 204	99.09 275	99.11 339	98.19 299	98.76 270	99.33 288	98.49 259	99.44 225	99.58 222	98.21 207	99.69 338	98.20 198	99.62 259	99.39 243

v148		99.40 112	99.41 101	99.39 215	99.76 118	98.94 242	99.09 209	99.59 193	99.17 180	99.81 88	99.61 206	98.41 182	99.69 338	99.32 95	99.94 95	99.53 189

test_prior				99.46 190	99.35 282	99.22 211		99.39 276					99.69 338			99.48 216

tpm cat1		96.78 336	96.98 330	96.16 377	98.85 364	90.59 401	99.08 212	99.32 290	92.37 386	97.73 379	99.46 267	91.15 353	99.69 338	96.07 339	98.80 350	98.21 376

PAPM_NR		98.36 282	98.04 290	99.33 231	99.48 245	98.93 245	98.79 267	99.28 301	97.54 325	98.56 344	98.57 377	97.12 271	99.69 338	94.09 377	98.90 348	99.38 245

PAPM		95.61 360	94.71 362	98.31 336	99.12 334	96.63 355	96.66 389	98.46 360	90.77 390	96.25 390	98.68 374	93.01 335	99.69 338	81.60 399	97.86 384	98.62 355

OMC-MVS		98.90 226	98.72 232	99.44 196	99.39 272	99.42 166	98.58 283	99.64 163	97.31 338	99.44 225	99.62 197	98.59 154	99.69 338	96.17 337	99.79 198	99.22 280

E-PMN		97.14 330	97.43 318	96.27 375	98.79 370	91.62 394	95.54 392	99.01 336	99.44 136	98.88 313	99.12 333	92.78 337	99.68 348	94.30 374	99.03 340	97.50 386

TSAR-MVS + GP.		99.12 187	99.04 185	99.38 218	99.34 290	99.16 219	98.15 319	99.29 298	98.18 291	99.63 160	99.62 197	99.18 78	99.68 348	98.20 198	99.74 218	99.30 267

MVS-HIRNet		97.86 305	98.22 278	96.76 368	99.28 307	91.53 395	98.38 305	92.60 398	99.13 188	99.31 259	99.96 12	97.18 270	99.68 348	98.34 187	99.83 170	99.07 322

PAPR		97.56 319	97.07 327	99.04 282	98.80 369	98.11 306	97.63 359	99.25 308	94.56 383	98.02 366	98.25 387	97.43 256	99.68 348	90.90 388	98.74 357	99.33 258

ITE_SJBPF				99.38 218	99.63 176	99.44 159		99.73 113	98.56 250	99.33 252	99.53 246	98.88 116	99.68 348	96.01 341	99.65 254	99.02 330

thres100view900		96.39 345	96.03 346	97.47 356	99.63 176	95.93 367	99.18 172	97.57 377	98.75 236	98.70 334	97.31 399	87.04 381	99.67 353	87.62 393	98.51 368	96.81 391

tfpn200view9		96.30 348	95.89 347	97.53 354	99.58 192	96.11 364	99.00 231	97.54 380	98.43 262	98.52 345	96.98 401	86.85 383	99.67 353	87.62 393	98.51 368	96.81 391

1314		98.00 303	97.90 305	98.27 338	98.90 358	97.45 337	99.30 135	99.06 332	94.98 377	97.21 384	99.12 333	98.43 179	99.67 353	95.58 356	98.56 366	97.71 385

thres400		96.40 344	95.89 347	97.92 346	99.58 192	96.11 364	99.00 231	97.54 380	98.43 262	98.52 345	96.98 401	86.85 383	99.67 353	87.62 393	98.51 368	97.98 382

EMVS		96.96 333	97.28 322	95.99 378	98.76 374	91.03 397	95.26 393	98.61 352	99.34 151	98.92 309	98.88 364	93.79 325	99.66 357	92.87 382	99.05 338	97.30 390

MVS_Test		99.28 140	99.31 119	99.19 260	99.35 282	98.79 257	99.36 120	99.49 248	99.17 180	99.21 277	99.67 167	98.78 127	99.66 357	99.09 131	99.66 252	99.10 308

EPNet_dtu		97.62 316	97.79 310	97.11 366	96.67 398	92.31 390	98.51 295	98.04 369	99.24 166	95.77 393	99.47 264	93.78 326	99.66 357	98.98 140	99.62 259	99.37 248
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-RMVSNet		98.41 278	98.14 286	99.21 257	99.21 319	98.47 280	98.60 279	98.26 367	98.35 276	98.93 306	99.31 301	97.20 269	99.66 357	94.32 373	99.10 336	99.51 202

MDTV_nov1_ep13			97.73 312		98.70 377	90.83 398	99.15 185	98.02 370	98.51 256	98.82 321	99.61 206	90.98 355	99.66 357	96.89 300	98.92 346

MVS_111021_LR		99.13 185	99.03 187	99.42 202	99.58 192	99.32 191	97.91 348	99.73 113	98.68 240	99.31 259	99.48 260	99.09 89	99.66 357	97.70 247	99.77 207	99.29 270

BH-untuned		98.22 293	98.09 288	98.58 323	99.38 275	97.24 342	98.55 289	98.98 337	97.81 315	99.20 282	98.76 370	97.01 275	99.65 363	94.83 367	98.33 371	98.86 343

RPSCF		99.18 173	99.02 189	99.64 129	99.83 66	99.85 19	99.44 105	99.82 66	98.33 281	99.50 214	99.78 101	97.90 229	99.65 363	96.78 306	99.83 170	99.44 230

USDC		98.96 218	98.93 208	99.05 281	99.54 216	97.99 313	97.07 383	99.80 79	98.21 288	99.75 115	99.77 108	98.43 179	99.64 365	97.90 223	99.88 134	99.51 202

DeepPCF-MVS	98.42 6	99.18 173	99.02 189	99.67 110	99.22 317	99.75 68	97.25 377	99.47 252	98.72 237	99.66 153	99.70 146	99.29 64	99.63 366	98.07 210	99.81 188	99.62 139

alignmvs		98.28 287	97.96 296	99.25 253	99.12 334	98.93 245	99.03 223	98.42 361	99.64 104	98.72 331	97.85 392	90.86 359	99.62 367	98.88 151	99.13 333	99.19 289

DeepMVS_CX				97.98 343	99.69 156	96.95 349		99.26 305	75.51 396	95.74 394	98.28 386	96.47 290	99.62 367	91.23 387	97.89 382	97.38 388

TinyColmap		98.97 215	98.93 208	99.07 279	99.46 255	98.19 299	97.75 354	99.75 104	98.79 228	99.54 200	99.70 146	98.97 106	99.62 367	96.63 316	99.83 170	99.41 240

TAPA-MVS	97.92 13	98.03 301	97.55 317	99.46 190	99.47 251	99.44 159	98.50 296	99.62 168	86.79 392	99.07 297	99.26 312	98.26 201	99.62 367	97.28 277	99.73 223	99.31 265
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPM-MVS		98.28 287	97.94 301	99.32 235	99.36 280	99.11 224	97.31 375	98.78 344	96.88 351	98.84 319	99.11 336	97.77 239	99.61 371	94.03 379	99.36 312	99.23 278

thres200		96.09 351	95.68 352	97.33 361	99.48 245	96.22 363	98.53 293	97.57 377	98.06 297	98.37 351	96.73 403	86.84 385	99.61 371	86.99 396	98.57 365	96.16 394

DP-MVS Recon		98.50 268	98.23 276	99.31 238	99.49 240	99.46 152	98.56 288	99.63 165	94.86 380	98.85 318	99.37 286	97.81 236	99.59 373	96.08 338	99.44 301	98.88 341

PVSNet_0	95.53 19	95.85 356	95.31 358	97.47 356	98.78 372	93.48 386	95.72 391	99.40 273	96.18 363	97.37 380	97.73 393	95.73 306	99.58 374	95.49 357	81.40 398	99.36 251

Syy-MVS		98.17 295	97.85 307	99.15 265	98.50 382	98.79 257	98.60 279	99.21 318	97.89 308	96.76 387	96.37 404	95.47 310	99.57 375	99.10 130	98.73 359	99.09 312

myMVS_eth3d		95.63 359	94.73 361	98.34 333	98.50 382	96.36 360	98.60 279	99.21 318	97.89 308	96.76 387	96.37 404	72.10 404	99.57 375	94.38 372	98.73 359	99.09 312

API-MVS		98.38 281	98.39 263	98.35 331	98.83 365	99.26 201	99.14 187	99.18 322	98.59 248	98.66 336	98.78 369	98.61 151	99.57 375	94.14 376	99.56 276	96.21 393

KD-MVS_2432*1600		95.89 353	95.41 356	97.31 362	94.96 399	93.89 382	97.09 381	99.22 315	97.23 341	98.88 313	99.04 343	79.23 398	99.54 378	96.24 334	96.81 389	98.50 365

miper_refine_blended		95.89 353	95.41 356	97.31 362	94.96 399	93.89 382	97.09 381	99.22 315	97.23 341	98.88 313	99.04 343	79.23 398	99.54 378	96.24 334	96.81 389	98.50 365

canonicalmvs		99.02 205	99.00 195	99.09 275	99.10 340	98.70 264	99.61 68	99.66 148	99.63 106	98.64 337	97.65 395	99.04 98	99.54 378	98.79 159	98.92 346	99.04 325

MVS_111021_HR		99.12 187	99.02 189	99.40 211	99.50 235	99.11 224	97.92 346	99.71 125	98.76 235	99.08 294	99.47 264	99.17 79	99.54 378	97.85 231	99.76 209	99.54 183

test_241102_ONE					99.69 156	99.82 35		99.54 222	99.12 191	99.82 81	99.49 257	98.91 112	99.52 382

gg-mvs-nofinetune		95.87 355	95.17 359	97.97 344	98.19 390	96.95 349	99.69 42	89.23 403	99.89 36	96.24 391	99.94 16	81.19 394	99.51 383	93.99 380	98.20 374	97.44 387

TR-MVS		97.44 322	97.15 326	98.32 334	98.53 381	97.46 336	98.47 298	97.91 373	96.85 352	98.21 357	98.51 381	96.42 292	99.51 383	92.16 384	97.29 387	97.98 382

BH-w/o		97.20 327	97.01 329	97.76 350	99.08 343	95.69 370	98.03 334	98.52 356	95.76 368	97.96 367	98.02 389	95.62 308	99.47 385	92.82 383	97.25 388	98.12 380

PMVS	92.94 21	98.82 235	98.81 226	98.85 304	99.84 62	97.99 313	99.20 167	99.47 252	99.71 82	99.42 231	99.82 73	98.09 215	99.47 385	93.88 381	99.85 157	99.07 322
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CMPMVS	77.52 23	98.50 268	98.19 283	99.41 209	98.33 387	99.56 136	99.01 228	99.59 193	95.44 371	99.57 186	99.80 83	95.64 307	99.46 387	96.47 324	99.92 106	99.21 282
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GA-MVS		97.99 304	97.68 314	98.93 293	99.52 227	98.04 312	97.19 379	99.05 333	98.32 282	98.81 322	98.97 355	89.89 371	99.41 388	98.33 188	99.05 338	99.34 257

cl22		97.56 319	97.28 322	98.40 329	98.37 386	96.75 354	97.24 378	99.37 281	97.31 338	99.41 237	99.22 321	87.30 378	99.37 389	97.70 247	99.62 259	99.08 317

dmvs_re		98.69 249	98.48 254	99.31 238	99.55 214	99.42 166	99.54 84	98.38 364	99.32 154	98.72 331	98.71 372	96.76 282	99.21 390	96.01 341	99.35 314	99.31 265

GG-mvs-BLEND				97.36 359	97.59 395	96.87 352	99.70 35	88.49 404		94.64 397	97.26 400	80.66 395	99.12 391	91.50 386	96.50 393	96.08 395

MSLP-MVS++		99.05 199	99.09 168	98.91 296	99.21 319	98.36 291	98.82 260	99.47 252	98.85 220	98.90 312	99.56 235	98.78 127	99.09 392	98.57 175	99.68 243	99.26 272

FPMVS		96.32 347	95.50 354	98.79 312	99.60 183	98.17 302	98.46 302	98.80 343	97.16 345	96.28 389	99.63 190	82.19 393	99.09 392	88.45 391	98.89 349	99.10 308

dmvs_testset		97.27 326	96.83 336	98.59 321	99.46 255	97.55 333	99.25 156	96.84 384	98.78 230	97.24 383	97.67 394	97.11 272	98.97 394	86.59 398	98.54 367	99.27 271

OPU-MVS				99.29 242	99.12 334	99.44 159	99.20 167				99.40 278	99.00 100	98.84 395	96.54 319	99.60 269	99.58 165

cascas		96.99 331	96.82 337	97.48 355	97.57 397	95.64 371	96.43 390	99.56 210	91.75 387	97.13 386	97.61 396	95.58 309	98.63 396	96.68 311	99.11 335	98.18 379

MVE	92.54 22	96.66 340	96.11 344	98.31 336	99.68 164	97.55 333	97.94 344	95.60 390	99.37 148	90.68 399	98.70 373	96.56 286	98.61 397	86.94 397	99.55 280	98.77 351
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PC_three_1452									97.56 322	99.68 143	99.41 274	99.09 89	97.09 398	96.66 313	99.60 269	99.62 139

tmp_tt		95.75 357	95.42 355	96.76 368	89.90 403	94.42 380	98.86 251	97.87 374	78.01 395	99.30 264	99.69 152	97.70 241	95.89 399	99.29 102	98.14 378	99.95 11

SD-MVS		99.01 209	99.30 124	98.15 340	99.50 235	99.40 172	98.94 245	99.61 175	99.22 172	99.75 115	99.82 73	99.54 41	95.51 400	97.48 265	99.87 145	99.54 183
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
test123		29.31 365	33.05 370	18.08 382	25.93 405	12.24 407	97.53 365	10.93 407	11.78 400	24.21 401	50.08 410	21.04 405	8.60 401	23.51 400	32.43 400	33.39 397

testmvs		28.94 366	33.33 368	15.79 383	26.03 404	9.81 408	96.77 387	15.67 406	11.55 401	23.87 402	50.74 409	19.03 406	8.53 402	23.21 401	33.07 399	29.03 398

test_blank		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

cdsmvs_eth3d_5k		24.88 367	33.17 369	0.00 384	0.00 406	0.00 409	0.00 395	99.62 168	0.00 402	0.00 403	99.13 329	99.82 13	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		16.61 368	22.14 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	99.28 66	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		8.26 377	11.02 380	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	99.16 327	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		8.33 369	11.11 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	100.00 1	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						96.36 360								95.20 363

FOURS1					99.83 66	99.89 10	99.74 24	99.71 125	99.69 90	99.63 160

test_one_0601					99.63 176	99.76 62		99.55 216	99.23 168	99.31 259	99.61 206	98.59 154

eth-test2					0.00 406

eth-test					0.00 406

RE-MVS-def			99.13 152		99.54 216	99.74 74	99.26 149	99.62 168	99.16 182	99.52 207	99.64 179	98.57 157		97.27 278	99.61 266	99.54 183

IU-MVS					99.69 156	99.77 54		99.22 315	97.50 328	99.69 140				97.75 240	99.70 234	99.77 61

save fliter					99.53 222	99.25 204	98.29 310	99.38 280	99.07 195

test0726					99.69 156	99.80 44	99.24 157	99.57 205	99.16 182	99.73 127	99.65 177	98.35 190

GSMVS																99.14 302

test_part2					99.62 180	99.67 100				99.55 198

sam_mvs1												90.81 360				99.14 302

sam_mvs												90.52 364

MTGPA								99.53 231

MTMP							99.09 209	98.59 355

test9_res														95.10 365	99.44 301	99.50 207

agg_prior2														94.58 371	99.46 300	99.50 207

test_prior4						99.19 217	98.00 337

test_prior2							97.95 343		97.87 311	98.05 364	99.05 341	97.90 229		95.99 344	99.49 296

新几何2							98.04 333

旧先验1					99.49 240	99.29 195		99.26 305			99.39 282	97.67 245			99.36 312	99.46 224

原ACMM2							97.92 346

test222					99.51 229	99.08 231	97.83 352	99.29 298	95.21 375	98.68 335	99.31 301	97.28 263			99.38 309	99.43 236

segment_acmp												98.37 188

testdata1							97.72 355		97.86 313

plane_prior7					99.58 192	99.38 176

plane_prior6					99.47 251	99.26 201						97.24 264

plane_prior4											99.25 314

plane_prior3						99.31 192			98.36 271	99.14 287

plane_prior2							98.80 264		98.94 207

plane_prior1					99.51 229

plane_prior						99.24 208	98.42 303		97.87 311						99.71 232

n2								0.00 408

nn								0.00 408

door-mid								99.83 61

test11								99.29 298

door								99.77 94

HQP5-MVS						98.94 242

HQP-NCC					99.31 298		97.98 339		97.45 330	98.15 358

ACMP_Plane					99.31 298		97.98 339		97.45 330	98.15 358

BP-MVS														94.73 368

HQP3-MVS								99.37 281							99.67 249

HQP2-MVS												96.67 283

NP-MVS					99.40 271	99.13 222					98.83 366

MDTV_nov1_ep13_2view						91.44 396	99.14 187		97.37 335	99.21 277		91.78 348		96.75 307		99.03 326

ACMMP++_ref															99.94 95

ACMMP++															99.79 198

Test By Simon												98.41 182

High-resolution multi-view benchmark