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 61	99.12 196	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 33	99.82 72	99.70 90	99.17 176	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

h-mvs33		98.61 253	98.34 269	99.44 195	99.60 182	98.67 265	99.27 146	99.44 259	99.68 90	99.32 254	99.49 255	92.50 343	100.00 1	99.24 104	96.51 399	99.65 112

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 87	99.65 50	98.95 290	99.71 143	97.27 344	99.50 90	99.82 67	99.59 116	99.41 236	99.85 56	99.62 31	100.00 1	99.53 62	99.89 124	99.59 159

HyFIR lowres test		98.91 225	98.64 238	99.73 88	99.85 58	99.47 147	98.07 335	99.83 62	98.64 248	99.89 53	99.60 213	92.57 340	100.00 1	99.33 91	99.97 56	99.72 73

fmvsm_l_conf0.5_n_a		99.80 23	99.79 27	99.84 30	99.88 44	99.64 110	99.12 196	99.91 33	99.98 14	99.95 31	99.67 166	99.67 27	99.99 7	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 44	99.66 101	99.11 200	99.91 33	99.98 14	99.96 23	99.64 178	99.60 34	99.99 7	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 73	99.01 227	99.99 10	99.99 2	99.98 13	99.88 42	99.97 2	99.99 7	99.96 9	100.00 1	99.98 3

SSC-MVS		99.52 81	99.42 98	99.83 33	99.86 54	99.65 107	99.52 85	99.81 76	99.87 41	99.81 88	99.79 93	96.78 281	99.99 7	99.83 32	99.51 291	99.86 32

test_fmvsmconf_n		99.85 11	99.84 19	99.88 17	99.91 31	99.73 76	98.97 239	99.98 11	99.99 2	99.96 23	99.85 56	99.93 7	99.99 7	99.94 16	99.99 16	99.93 15

test_fmvsmvis_n_1920		99.84 15	99.86 12	99.81 40	99.88 44	99.55 138	99.17 176	99.98 11	99.99 2	99.96 23	99.84 62	99.96 3	99.99 7	99.96 9	99.99 16	99.88 25

SDMVSNet		99.77 30	99.77 33	99.76 64	99.80 86	99.65 107	99.63 60	99.86 49	99.97 16	99.89 53	99.89 34	99.52 44	99.99 7	99.42 77	99.96 70	99.65 112

sd_testset		99.78 27	99.78 31	99.80 45	99.80 86	99.76 61	99.80 10	99.79 86	99.97 16	99.89 53	99.89 34	99.53 43	99.99 7	99.36 84	99.96 70	99.65 112

test_vis1_n_1920		99.72 36	99.88 6	99.27 245	99.93 25	97.84 324	99.34 121	100.00 1	99.99 2	99.99 7	99.82 73	99.87 9	99.99 7	99.97 4	99.99 16	99.97 7

test_fmvs3		99.83 19	99.93 2	99.53 174	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 7	99.98 1	99.99 16	99.98 3

dcpmvs_2		99.61 67	99.64 53	99.53 174	99.79 98	98.82 254	99.58 75	99.97 18	99.95 20	99.96 23	99.76 111	98.44 178	99.99 7	99.34 88	99.96 70	99.78 56

IterMVS-SCA-FT		99.00 211	99.16 145	98.51 327	99.75 128	95.90 371	98.07 335	99.84 60	99.84 53	99.89 53	99.73 123	96.01 304	99.99 7	99.33 91	100.00 1	99.63 127

IterMVS		98.97 215	99.16 145	98.42 331	99.74 134	95.64 374	98.06 337	99.83 62	99.83 56	99.85 73	99.74 119	96.10 303	99.99 7	99.27 103	100.00 1	99.63 127
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WB-MVS		99.44 99	99.32 116	99.80 45	99.81 80	99.61 123	99.47 98	99.81 76	99.82 58	99.71 132	99.72 130	96.60 285	99.98 20	99.75 39	99.23 331	99.82 46

test_fmvs1_n		99.68 45	99.81 23	99.28 242	99.95 15	97.93 321	99.49 94	100.00 1	99.82 58	99.99 7	99.89 34	99.21 75	99.98 20	99.97 4	99.98 41	99.93 15

test_fmvs2		99.72 36	99.85 16	99.34 226	99.91 31	98.08 311	99.48 95	100.00 1	99.90 29	99.99 7	99.91 24	99.50 46	99.98 20	99.98 1	99.99 16	99.96 10

patch_mono-2		99.51 82	99.46 89	99.64 128	99.70 151	99.11 225	99.04 218	99.87 46	99.71 80	99.47 218	99.79 93	98.24 201	99.98 20	99.38 80	99.96 70	99.83 40

CHOSEN 280x420		98.41 279	98.41 261	98.40 332	99.34 290	95.89 372	96.94 392	99.44 259	98.80 230	99.25 268	99.52 246	93.51 332	99.98 20	98.94 147	99.98 41	99.32 259

Fast-Effi-MVS+-dtu		99.20 165	99.12 155	99.43 199	99.25 311	99.69 94	99.05 215	99.82 67	99.50 122	98.97 302	99.05 339	98.98 104	99.98 20	98.20 198	99.24 329	98.62 359

Effi-MVS+-dtu		99.07 195	98.92 212	99.52 176	98.89 362	99.78 49	99.15 184	99.66 148	99.34 149	98.92 309	99.24 317	97.69 243	99.98 20	98.11 208	99.28 323	98.81 350

PS-MVSNAJss		99.84 15	99.82 22	99.89 11	99.96 7	99.77 54	99.68 45	99.85 54	99.95 20	99.98 13	99.92 21	99.28 66	99.98 20	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 49	99.89 35	99.98 13	99.90 29	99.94 4	99.98 20	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 44	99.92 27	99.98 13	99.93 17	99.94 4	99.98 20	99.77 38	100.00 1	99.92 18

MVSFormer		99.41 109	99.44 94	99.31 236	99.57 201	98.40 286	99.77 15	99.80 80	99.73 74	99.63 159	99.30 301	98.02 220	99.98 20	99.43 72	99.69 238	99.55 174

test_djsdf		99.84 15	99.81 23	99.91 2	99.94 18	99.84 24	99.77 15	99.80 80	99.73 74	99.97 19	99.92 21	99.77 19	99.98 20	99.43 72	100.00 1	99.90 20

Vis-MVSNet		99.75 32	99.74 37	99.79 51	99.88 44	99.66 101	99.69 42	99.92 30	99.67 94	99.77 106	99.75 116	99.61 32	99.98 20	99.35 87	99.98 41	99.72 73
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	99.45 192	99.93 25	98.40 286	99.30 134	99.98 11	99.94 23	99.99 7	99.89 34	99.80 15	99.97 33	99.96 9	99.97 56	99.97 7

test_fmvs1		99.48 87	99.65 50	98.97 287	99.54 215	97.16 347	99.11 200	99.98 11	99.78 68	99.96 23	99.81 79	98.72 137	99.97 33	99.95 12	99.97 56	99.79 54

Anonymous20240521		99.44 99	99.42 98	99.49 181	99.89 39	98.96 242	99.62 62	99.76 100	99.85 50	99.82 81	99.88 42	96.39 295	99.97 33	99.59 51	99.98 41	99.55 174

MVS_0304		99.17 177	99.03 187	99.59 152	99.44 259	98.90 249	99.04 218	95.32 397	99.99 2	99.68 142	99.57 229	98.30 196	99.97 33	99.94 16	99.98 41	99.88 25

xiu_mvs_v1_base_debu		99.23 150	99.34 111	98.91 297	99.59 186	98.23 295	98.47 301	99.66 148	99.61 108	99.68 142	98.94 358	99.39 50	99.97 33	99.18 113	99.55 280	98.51 367

xiu_mvs_v2_base		99.02 205	99.11 158	98.77 315	99.37 276	98.09 308	98.13 327	99.51 239	99.47 128	99.42 230	98.54 380	99.38 54	99.97 33	98.83 151	99.33 316	98.24 381

xiu_mvs_v1_base		99.23 150	99.34 111	98.91 297	99.59 186	98.23 295	98.47 301	99.66 148	99.61 108	99.68 142	98.94 358	99.39 50	99.97 33	99.18 113	99.55 280	98.51 367

xiu_mvs_v1_base_debi		99.23 150	99.34 111	98.91 297	99.59 186	98.23 295	98.47 301	99.66 148	99.61 108	99.68 142	98.94 358	99.39 50	99.97 33	99.18 113	99.55 280	98.51 367

anonymousdsp		99.80 23	99.77 33	99.90 8	99.96 7	99.88 12	99.73 27	99.85 54	99.70 85	99.92 41	99.93 17	99.45 47	99.97 33	99.36 84	100.00 1	99.85 35

UA-Net		99.78 27	99.76 36	99.86 25	99.72 140	99.71 83	99.91 3	99.95 28	99.96 18	99.71 132	99.91 24	99.15 81	99.97 33	99.50 66	100.00 1	99.90 20

PS-MVSNAJ		99.00 211	99.08 169	98.76 316	99.37 276	98.10 307	98.00 343	99.51 239	99.47 128	99.41 236	98.50 382	99.28 66	99.97 33	98.83 151	99.34 315	98.20 385

pmmvs3		98.08 301	97.80 310	98.91 297	99.41 269	97.69 332	97.87 357	99.66 148	95.87 372	99.50 213	99.51 248	90.35 367	99.97 33	98.55 174	99.47 298	99.08 316

DTE-MVSNet		99.68 45	99.61 59	99.88 17	99.80 86	99.87 15	99.67 49	99.71 126	99.72 78	99.84 76	99.78 101	98.67 143	99.97 33	99.30 97	99.95 83	99.80 47

jason		99.16 179	99.11 158	99.32 233	99.75 128	98.44 283	98.26 317	99.39 275	98.70 243	99.74 122	99.30 301	98.54 162	99.97 33	98.48 177	99.82 179	99.55 174
jason: jason.
lupinMVS		98.96 219	98.87 219	99.24 253	99.57 201	98.40 286	98.12 328	99.18 321	98.28 291	99.63 159	99.13 327	98.02 220	99.97 33	98.22 196	99.69 238	99.35 252

K. test v3		98.87 232	98.60 241	99.69 104	99.93 25	99.46 151	99.74 24	94.97 398	99.78 68	99.88 61	99.88 42	93.66 330	99.97 33	99.61 49	99.95 83	99.64 122

lessismore_v0				99.64 128	99.86 54	99.38 175		90.66 407		99.89 53	99.83 66	94.56 320	99.97 33	99.56 57	99.92 105	99.57 169

EPNet		98.13 298	97.77 313	99.18 260	94.57 409	97.99 314	99.24 155	97.96 374	99.74 73	97.29 384	99.62 196	93.13 335	99.97 33	98.59 172	99.83 170	99.58 164
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		99.40 111	99.38 103	99.44 195	99.90 37	98.66 268	98.94 244	99.91 33	97.97 309	99.79 97	99.73 123	99.05 97	99.97 33	99.15 119	99.99 16	99.68 89

IterMVS-LS		99.41 109	99.47 85	99.25 251	99.81 80	98.09 308	98.85 252	99.76 100	99.62 105	99.83 80	99.64 178	98.54 162	99.97 33	99.15 119	99.99 16	99.68 89
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 58	100.00 1	99.90 29	100.00 1	99.97 11	99.61 32	99.97 33	99.75 39	100.00 1	99.84 36

test_vis1_n		99.68 45	99.79 27	99.36 223	99.94 18	98.18 301	99.52 85	100.00 1	99.86 45	100.00 1	99.88 42	98.99 102	99.96 54	99.97 4	99.96 70	99.95 11

UniMVSNet_ETH3D		99.85 11	99.83 20	99.90 8	99.89 39	99.91 4	99.89 4	99.71 126	99.93 25	99.95 31	99.89 34	99.71 22	99.96 54	99.51 64	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 67	99.84 53	99.94 34	99.91 24	99.13 86	99.96 54	99.83 32	99.99 16	99.83 40

RRT_MVS		99.67 51	99.59 64	99.91 2	99.94 18	99.88 12	99.78 12	99.27 301	99.87 41	99.91 44	99.87 47	98.04 218	99.96 54	99.68 44	99.99 16	99.90 20

PS-CasMVS		99.66 53	99.58 68	99.89 11	99.80 86	99.85 19	99.66 53	99.73 114	99.62 105	99.84 76	99.71 138	98.62 149	99.96 54	99.30 97	99.96 70	99.86 32

PEN-MVS		99.66 53	99.59 64	99.89 11	99.83 65	99.87 15	99.66 53	99.73 114	99.70 85	99.84 76	99.73 123	98.56 159	99.96 54	99.29 100	99.94 94	99.83 40

TranMVSNet+NR-MVSNet		99.54 78	99.47 85	99.76 64	99.58 191	99.64 110	99.30 134	99.63 165	99.61 108	99.71 132	99.56 233	98.76 130	99.96 54	99.14 125	99.92 105	99.68 89

IB-MVS	95.41 20	95.30 369	94.46 373	97.84 354	98.76 377	95.33 378	97.33 381	96.07 393	96.02 371	95.37 403	97.41 399	76.17 404	99.96 54	97.54 261	95.44 403	98.22 382
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	98.23 294	97.89 308	99.26 248	99.19 323	99.26 200	99.65 58	99.69 137	91.33 396	98.14 364	99.77 108	98.28 198	99.96 54	95.41 366	99.55 280	98.58 363

MM		99.18 172	99.05 179	99.55 168	99.35 281	98.81 255	99.05 215	97.79 379	99.99 2	99.48 216	99.59 218	96.29 299	99.95 63	99.94 16	99.98 41	99.88 25

GeoE		99.69 42	99.66 48	99.78 54	99.76 117	99.76 61	99.60 72	99.82 67	99.46 131	99.75 114	99.56 233	99.63 29	99.95 63	99.43 72	99.88 134	99.62 138

CS-MVS		99.67 51	99.70 39	99.58 156	99.53 221	99.84 24	99.79 11	99.96 23	99.90 29	99.61 174	99.41 272	99.51 45	99.95 63	99.66 45	99.89 124	98.96 333

CANet_DTU		98.91 225	98.85 221	99.09 275	98.79 372	98.13 303	98.18 321	99.31 293	99.48 124	98.86 317	99.51 248	96.56 286	99.95 63	99.05 132	99.95 83	99.19 287

CS-MVS-test		99.68 45	99.70 39	99.64 128	99.57 201	99.83 29	99.78 12	99.97 18	99.92 27	99.50 213	99.38 282	99.57 38	99.95 63	99.69 43	99.90 115	99.15 295

Fast-Effi-MVS+		99.02 205	98.87 219	99.46 189	99.38 274	99.50 144	99.04 218	99.79 86	97.17 351	98.62 339	98.74 371	99.34 60	99.95 63	98.32 187	99.41 306	98.92 339

MTAPA		99.35 125	99.20 141	99.80 45	99.81 80	99.81 40	99.33 124	99.53 230	99.27 158	99.42 230	99.63 189	98.21 206	99.95 63	97.83 235	99.79 198	99.65 112

UniMVSNet_NR-MVSNet		99.37 120	99.25 136	99.72 94	99.47 250	99.56 135	98.97 239	99.61 175	99.43 139	99.67 148	99.28 305	97.85 233	99.95 63	99.17 116	99.81 188	99.65 112

DU-MVS		99.33 133	99.21 140	99.71 99	99.43 263	99.56 135	98.83 255	99.53 230	99.38 145	99.67 148	99.36 288	97.67 245	99.95 63	99.17 116	99.81 188	99.63 127

CP-MVSNet		99.54 78	99.43 96	99.87 21	99.76 117	99.82 35	99.57 78	99.61 175	99.54 118	99.80 92	99.64 178	97.79 237	99.95 63	99.21 107	99.94 94	99.84 36

Patchmtry		98.78 239	98.54 251	99.49 181	98.89 362	99.19 218	99.32 126	99.67 144	99.65 100	99.72 127	99.79 93	91.87 348	99.95 63	98.00 215	99.97 56	99.33 256

QAPM		98.40 281	97.99 295	99.65 121	99.39 271	99.47 147	99.67 49	99.52 235	91.70 395	98.78 328	99.80 83	98.55 160	99.95 63	94.71 377	99.75 211	99.53 187

3Dnovator	99.15 2	99.43 102	99.36 109	99.65 121	99.39 271	99.42 165	99.70 35	99.56 209	99.23 166	99.35 246	99.80 83	99.17 79	99.95 63	98.21 197	99.84 162	99.59 159

LTVRE_ROB	99.19 1	99.88 6	99.87 10	99.88 17	99.91 31	99.90 7	99.96 1	99.92 30	99.90 29	99.97 19	99.87 47	99.81 14	99.95 63	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 74	99.95 15	99.37 178	99.53 84	99.98 11	99.77 72	99.99 7	99.95 13	99.85 10	99.94 77	99.95 12	99.98 41	99.94 13

test_f		99.75 32	99.88 6	99.37 219	99.96 7	98.21 298	99.51 89	100.00 1	99.94 23	100.00 1	99.93 17	99.58 36	99.94 77	99.97 4	99.99 16	99.97 7

test_method		91.72 371	92.32 374	89.91 388	93.49 410	70.18 413	90.28 401	99.56 209	61.71 405	95.39 402	99.52 246	93.90 324	99.94 77	98.76 161	98.27 376	99.62 138

tttt0517		97.62 318	97.20 327	98.90 303	99.76 117	97.40 341	99.48 95	94.36 400	99.06 197	99.70 136	99.49 255	84.55 392	99.94 77	98.73 164	99.65 254	99.36 249

CANet		99.11 190	99.05 179	99.28 242	98.83 366	98.56 276	98.71 274	99.41 265	99.25 162	99.23 272	99.22 319	97.66 249	99.94 77	99.19 111	99.97 56	99.33 256

patchmatchnet-post											99.62 196	90.58 364	99.94 77

SCA		98.11 299	98.36 266	97.36 366	99.20 321	92.99 394	98.17 323	98.49 359	98.24 293	99.10 293	99.57 229	96.01 304	99.94 77	96.86 304	99.62 259	99.14 300

ADS-MVSNet2		97.78 311	97.66 318	98.12 345	99.14 329	95.36 377	99.22 163	98.75 344	96.97 356	98.25 356	99.64 178	90.90 359	99.94 77	96.51 325	99.56 276	99.08 316

WR-MVS_H		99.61 67	99.53 81	99.87 21	99.80 86	99.83 29	99.67 49	99.75 105	99.58 117	99.85 73	99.69 151	98.18 210	99.94 77	99.28 102	99.95 83	99.83 40

mvsmamba		99.74 35	99.70 39	99.85 27	99.93 25	99.83 29	99.76 19	99.81 76	99.96 18	99.91 44	99.81 79	98.60 153	99.94 77	99.58 54	99.98 41	99.77 60

SixPastTwentyTwo		99.42 105	99.30 123	99.76 64	99.92 30	99.67 99	99.70 35	99.14 325	99.65 100	99.89 53	99.90 29	96.20 301	99.94 77	99.42 77	99.92 105	99.67 95

CP-MVS		99.23 150	99.05 179	99.75 74	99.66 169	99.66 101	99.38 112	99.62 168	98.38 276	99.06 298	99.27 307	98.79 125	99.94 77	97.51 264	99.82 179	99.66 104

SteuartSystems-ACMMP		99.30 137	99.14 149	99.76 64	99.87 51	99.66 101	99.18 171	99.60 187	98.55 257	99.57 185	99.67 166	99.03 99	99.94 77	97.01 295	99.80 193	99.69 83
Skip Steuart: Steuart Systems R&D Blog.
PatchT		98.45 276	98.32 272	98.83 310	98.94 357	98.29 293	99.24 155	98.82 341	99.84 53	99.08 294	99.76 111	91.37 351	99.94 77	98.82 153	99.00 343	98.26 380

new_pmnet		98.88 231	98.89 217	98.84 308	99.70 151	97.62 333	98.15 324	99.50 243	97.98 308	99.62 168	99.54 242	98.15 211	99.94 77	97.55 260	99.84 162	98.95 335

wuyk23d		97.58 320	99.13 151	92.93 387	99.69 155	99.49 145	99.52 85	99.77 95	97.97 309	99.96 23	99.79 93	99.84 12	99.94 77	95.85 356	99.82 179	79.36 403

3Dnovator+	98.92 3	99.35 125	99.24 138	99.67 109	99.35 281	99.47 147	99.62 62	99.50 243	99.44 134	99.12 290	99.78 101	98.77 129	99.94 77	97.87 228	99.72 229	99.62 138

fmvsm_s_conf0.1_n_a		99.85 11	99.83 20	99.91 2	99.95 15	99.82 35	99.10 203	99.98 11	99.99 2	99.98 13	99.91 24	99.68 26	99.93 94	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 58	99.82 35	99.03 222	99.96 23	99.99 2	99.97 19	99.84 62	99.58 36	99.93 94	99.92 22	99.98 41	99.93 15

mvsany_test1		99.44 99	99.45 91	99.40 210	99.37 276	98.64 272	97.90 356	99.59 193	99.27 158	99.92 41	99.82 73	99.74 20	99.93 94	99.55 59	99.87 145	99.63 127

ETV-MVS		99.18 172	99.18 143	99.16 263	99.34 290	99.28 196	99.12 196	99.79 86	99.48 124	98.93 306	98.55 379	99.40 49	99.93 94	98.51 176	99.52 290	98.28 379

thisisatest0530		97.45 323	96.95 333	98.94 291	99.68 163	97.73 330	99.09 208	94.19 402	98.61 253	99.56 192	99.30 301	84.30 393	99.93 94	98.27 192	99.54 285	99.16 293

our_test_3		98.85 234	99.09 167	98.13 344	99.66 169	94.90 384	97.72 362	99.58 202	99.07 195	99.64 155	99.62 196	98.19 208	99.93 94	98.41 180	99.95 83	99.55 174

MSP-MVS		99.04 202	98.79 230	99.81 40	99.78 105	99.73 76	99.35 120	99.57 204	98.54 260	99.54 199	98.99 349	96.81 280	99.93 94	96.97 298	99.53 287	99.77 60
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		99.23 150	99.05 179	99.77 57	99.76 117	99.70 90	99.31 131	99.59 193	98.41 272	99.32 254	99.36 288	98.73 136	99.93 94	97.29 276	99.74 218	99.67 95

APDe-MVS		99.48 87	99.36 109	99.85 27	99.55 213	99.81 40	99.50 90	99.69 137	98.99 201	99.75 114	99.71 138	98.79 125	99.93 94	98.46 178	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	98.88 218	97.80 355	99.58 191	93.60 392	99.26 148	99.64 163	99.66 98	99.72 127	99.67 166	93.26 333	99.93 94	99.30 97	99.81 188	99.87 30

ACMMPR		99.23 150	99.06 175	99.76 64	99.74 134	99.69 94	99.31 131	99.59 193	98.36 278	99.35 246	99.38 282	98.61 151	99.93 94	97.43 268	99.75 211	99.67 95

PGM-MVS		99.20 165	99.01 192	99.77 57	99.75 128	99.71 83	99.16 182	99.72 123	97.99 307	99.42 230	99.60 213	98.81 120	99.93 94	96.91 301	99.74 218	99.66 104

LCM-MVSNet-Re		99.28 139	99.15 148	99.67 109	99.33 295	99.76 61	99.34 121	99.97 18	98.93 211	99.91 44	99.79 93	98.68 140	99.93 94	96.80 308	99.56 276	99.30 265

PMMVS2		99.48 87	99.45 91	99.57 162	99.76 117	98.99 237	98.09 332	99.90 38	98.95 207	99.78 101	99.58 221	99.57 38	99.93 94	99.48 67	99.95 83	99.79 54

mPP-MVS		99.19 168	99.00 195	99.76 64	99.76 117	99.68 97	99.38 112	99.54 221	98.34 287	99.01 300	99.50 251	98.53 166	99.93 94	97.18 290	99.78 203	99.66 104

OurMVSNet-221017-0		99.75 32	99.71 38	99.84 30	99.96 7	99.83 29	99.83 6	99.85 54	99.80 64	99.93 37	99.93 17	98.54 162	99.93 94	99.59 51	99.98 41	99.76 66

CHOSEN 1792x2688		99.39 115	99.30 123	99.65 121	99.88 44	99.25 203	98.78 267	99.88 44	98.66 246	99.96 23	99.79 93	97.45 255	99.93 94	99.34 88	99.99 16	99.78 56

N_pmnet		98.73 245	98.53 252	99.35 225	99.72 140	98.67 265	98.34 310	94.65 399	98.35 283	99.79 97	99.68 162	98.03 219	99.93 94	98.28 191	99.92 105	99.44 228

UGNet		99.38 117	99.34 111	99.49 181	98.90 359	98.90 249	99.70 35	99.35 284	99.86 45	98.57 344	99.81 79	98.50 172	99.93 94	99.38 80	99.98 41	99.66 104
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 42	99.69 43	99.68 106	99.71 143	99.91 4	99.76 19	99.96 23	99.86 45	99.51 211	99.39 280	99.57 38	99.93 94	99.64 48	99.86 153	99.20 284

EPP-MVSNet		99.17 177	99.00 195	99.66 116	99.80 86	99.43 162	99.70 35	99.24 310	99.48 124	99.56 192	99.77 108	94.89 314	99.93 94	98.72 165	99.89 124	99.63 127

DeepC-MVS	98.90 4	99.62 65	99.61 59	99.67 109	99.72 140	99.44 158	99.24 155	99.71 126	99.27 158	99.93 37	99.90 29	99.70 24	99.93 94	98.99 136	99.99 16	99.64 122
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 25	99.78 49	99.07 214	99.98 11	99.99 2	99.98 13	99.90 29	99.88 8	99.92 116	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 58	99.78 49	99.03 222	99.96 23	99.99 2	99.97 19	99.84 62	99.78 17	99.92 116	99.92 22	99.99 16	99.92 18

EGC-MVSNET		89.05 372	85.52 375	99.64 128	99.89 39	99.78 49	99.56 80	99.52 235	24.19 406	49.96 407	99.83 66	99.15 81	99.92 116	97.71 244	99.85 157	99.21 280

DVP-MVS++		99.38 117	99.25 136	99.77 57	99.03 349	99.77 54	99.74 24	99.61 175	99.18 174	99.76 108	99.61 205	99.00 100	99.92 116	97.72 242	99.60 269	99.62 138

MSC_two_6792asdad				99.74 79	99.03 349	99.53 141		99.23 311					99.92 116	97.77 236	99.69 238	99.78 56

No_MVS				99.74 79	99.03 349	99.53 141		99.23 311					99.92 116	97.77 236	99.69 238	99.78 56

ZD-MVS					99.43 263	99.61 123		99.43 262	96.38 366	99.11 291	99.07 337	97.86 231	99.92 116	94.04 385	99.49 296

SED-MVS		99.40 111	99.28 130	99.77 57	99.69 155	99.82 35	99.20 166	99.54 221	99.13 188	99.82 81	99.63 189	98.91 112	99.92 116	97.85 231	99.70 234	99.58 164

test_241102_TWO								99.54 221	99.13 188	99.76 108	99.63 189	98.32 195	99.92 116	97.85 231	99.69 238	99.75 69

ZNCC-MVS		99.22 158	99.04 185	99.77 57	99.76 117	99.73 76	99.28 143	99.56 209	98.19 297	99.14 287	99.29 304	98.84 119	99.92 116	97.53 263	99.80 193	99.64 122

test_0728_SECOND				99.83 33	99.70 151	99.79 46	99.14 186	99.61 175					99.92 116	97.88 225	99.72 229	99.77 60

SR-MVS		99.19 168	99.00 195	99.74 79	99.51 228	99.72 81	99.18 171	99.60 187	98.85 222	99.47 218	99.58 221	98.38 187	99.92 116	96.92 300	99.54 285	99.57 169

DPE-MVS		99.14 183	98.92 212	99.82 37	99.57 201	99.77 54	98.74 270	99.60 187	98.55 257	99.76 108	99.69 151	98.23 205	99.92 116	96.39 333	99.75 211	99.76 66
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
iter_conf05		98.46 274	98.23 277	99.15 265	99.04 348	97.99 314	99.10 203	99.61 175	99.79 66	99.76 108	99.58 221	87.88 378	99.92 116	99.31 96	99.97 56	99.53 187

MP-MVS		99.06 196	98.83 225	99.76 64	99.76 117	99.71 83	99.32 126	99.50 243	98.35 283	98.97 302	99.48 258	98.37 188	99.92 116	95.95 353	99.75 211	99.63 127
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PM-MVS		99.36 123	99.29 128	99.58 156	99.83 65	99.66 101	98.95 242	99.86 49	98.85 222	99.81 88	99.73 123	98.40 186	99.92 116	98.36 183	99.83 170	99.17 291

HPM-MVS		99.25 146	99.07 173	99.78 54	99.81 80	99.75 67	99.61 67	99.67 144	97.72 324	99.35 246	99.25 312	99.23 73	99.92 116	97.21 288	99.82 179	99.67 95
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
tpm		97.15 330	96.95 333	97.75 357	98.91 358	94.24 387	99.32 126	97.96 374	97.71 325	98.29 354	99.32 297	86.72 387	99.92 116	98.10 209	96.24 401	99.09 310

RPMNet		98.60 255	98.53 252	98.83 310	99.05 346	98.12 304	99.30 134	99.62 168	99.86 45	99.16 283	99.74 119	92.53 342	99.92 116	98.75 162	98.77 355	98.44 374

CPTT-MVS		98.74 243	98.44 258	99.64 128	99.61 180	99.38 175	99.18 171	99.55 215	96.49 364	99.27 266	99.37 284	97.11 272	99.92 116	95.74 360	99.67 249	99.62 138

MIMVSNet1		99.66 53	99.62 55	99.80 45	99.94 18	99.87 15	99.69 42	99.77 95	99.78 68	99.93 37	99.89 34	97.94 226	99.92 116	99.65 46	99.98 41	99.62 138

CSCG		99.37 120	99.29 128	99.60 150	99.71 143	99.46 151	99.43 106	99.85 54	98.79 231	99.41 236	99.60 213	98.92 110	99.92 116	98.02 211	99.92 105	99.43 234

ACMMP		99.25 146	99.08 169	99.74 79	99.79 98	99.68 97	99.50 90	99.65 157	98.07 303	99.52 206	99.69 151	98.57 157	99.92 116	97.18 290	99.79 198	99.63 127
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		99.27 143	99.11 158	99.73 88	99.54 215	99.74 73	99.26 148	99.62 168	99.16 182	99.52 206	99.64 178	98.41 182	99.91 139	97.27 279	99.61 266	99.54 182

DVP-MVS		99.32 135	99.17 144	99.77 57	99.69 155	99.80 44	99.14 186	99.31 293	99.16 182	99.62 168	99.61 205	98.35 190	99.91 139	97.88 225	99.72 229	99.61 148
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									99.18 174	99.62 168	99.61 205	98.58 156	99.91 139	97.72 242	99.80 193	99.77 60

GST-MVS		99.16 179	98.96 206	99.75 74	99.73 137	99.73 76	99.20 166	99.55 215	98.22 294	99.32 254	99.35 293	98.65 147	99.91 139	96.86 304	99.74 218	99.62 138

MP-MVS-pluss		99.14 183	98.92 212	99.80 45	99.83 65	99.83 29	98.61 278	99.63 165	96.84 360	99.44 224	99.58 221	98.81 120	99.91 139	97.70 247	99.82 179	99.67 95
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
HFP-MVS		99.25 146	99.08 169	99.76 64	99.73 137	99.70 90	99.31 131	99.59 193	98.36 278	99.36 245	99.37 284	98.80 124	99.91 139	97.43 268	99.75 211	99.68 89

HPM-MVS++		98.96 219	98.70 236	99.74 79	99.52 226	99.71 83	98.86 250	99.19 320	98.47 268	98.59 342	99.06 338	98.08 216	99.91 139	96.94 299	99.60 269	99.60 152

test-LLR		97.15 330	96.95 333	97.74 358	98.18 398	95.02 382	97.38 378	96.10 391	98.00 305	97.81 377	98.58 375	90.04 370	99.91 139	97.69 253	98.78 353	98.31 377

test-mter		96.23 352	95.73 354	97.74 358	98.18 398	95.02 382	97.38 378	96.10 391	97.90 314	97.81 377	98.58 375	79.12 402	99.91 139	97.69 253	98.78 353	98.31 377

VPA-MVSNet		99.66 53	99.62 55	99.79 51	99.68 163	99.75 67	99.62 62	99.69 137	99.85 50	99.80 92	99.81 79	98.81 120	99.91 139	99.47 68	99.88 134	99.70 79

XVG-ACMP-BASELINE		99.23 150	99.10 166	99.63 135	99.82 72	99.58 132	98.83 255	99.72 123	98.36 278	99.60 177	99.71 138	98.92 110	99.91 139	97.08 293	99.84 162	99.40 239

APD-MVS		98.87 232	98.59 243	99.71 99	99.50 234	99.62 117	99.01 227	99.57 204	96.80 362	99.54 199	99.63 189	98.29 197	99.91 139	95.24 369	99.71 232	99.61 148
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CR-MVSNet		98.35 286	98.20 281	98.83 310	99.05 346	98.12 304	99.30 134	99.67 144	97.39 341	99.16 283	99.79 93	91.87 348	99.91 139	98.78 160	98.77 355	98.44 374

FMVSNet5		97.80 310	97.25 326	99.42 201	98.83 366	98.97 240	99.38 112	99.80 80	98.87 219	99.25 268	99.69 151	80.60 397	99.91 139	98.96 142	99.90 115	99.38 243

XXY-MVS		99.71 39	99.67 47	99.81 40	99.89 39	99.72 81	99.59 73	99.82 67	99.39 144	99.82 81	99.84 62	99.38 54	99.91 139	99.38 80	99.93 101	99.80 47

sss		98.90 227	98.77 231	99.27 245	99.48 244	98.44 283	98.72 272	99.32 289	97.94 313	99.37 244	99.35 293	96.31 297	99.91 139	98.85 150	99.63 258	99.47 218

1112_ss		99.05 199	98.84 223	99.67 109	99.66 169	99.29 194	98.52 297	99.82 67	97.65 327	99.43 228	99.16 325	96.42 292	99.91 139	99.07 131	99.84 162	99.80 47

LS3D		99.24 149	99.11 158	99.61 147	98.38 392	99.79 46	99.57 78	99.68 140	99.61 108	99.15 285	99.71 138	98.70 138	99.91 139	97.54 261	99.68 243	99.13 303

WB-MVSnew		98.34 288	98.14 287	98.96 288	98.14 401	97.90 323	98.27 315	97.26 388	98.63 249	98.80 324	98.00 392	97.77 238	99.90 157	97.37 272	98.98 344	99.09 310

testf1		99.63 59	99.60 62	99.72 94	99.94 18	99.95 2	99.47 98	99.89 40	99.43 139	99.88 61	99.80 83	99.26 70	99.90 157	98.81 155	99.88 134	99.32 259

APD_test2		99.63 59	99.60 62	99.72 94	99.94 18	99.95 2	99.47 98	99.89 40	99.43 139	99.88 61	99.80 83	99.26 70	99.90 157	98.81 155	99.88 134	99.32 259

test2506		94.73 370	94.59 371	95.15 386	99.59 186	85.90 412	99.75 22	74.01 412	99.89 35	99.71 132	99.86 54	79.00 403	99.90 157	99.52 63	99.99 16	99.65 112

test1111		97.74 312	98.16 286	96.49 380	99.60 182	89.86 410	99.71 34	91.21 406	99.89 35	99.88 61	99.87 47	93.73 329	99.90 157	99.56 57	99.99 16	99.70 79

KD-MVS_self_test		99.63 59	99.59 64	99.76 64	99.84 61	99.90 7	99.37 116	99.79 86	99.83 56	99.88 61	99.85 56	98.42 181	99.90 157	99.60 50	99.73 223	99.49 210

ET-MVSNet_ETH3D		96.78 338	96.07 347	98.91 297	99.26 310	97.92 322	97.70 364	96.05 394	97.96 312	92.37 405	98.43 383	87.06 381	99.90 157	98.27 192	97.56 393	98.91 340

tfpnnormal		99.43 102	99.38 103	99.60 150	99.87 51	99.75 67	99.59 73	99.78 92	99.71 80	99.90 49	99.69 151	98.85 118	99.90 157	97.25 285	99.78 203	99.15 295

pmmvs6		99.86 9	99.86 12	99.83 33	99.94 18	99.90 7	99.83 6	99.91 33	99.85 50	99.94 34	99.95 13	99.73 21	99.90 157	99.65 46	99.97 56	99.69 83

APD-MVS_3200maxsize		99.31 136	99.16 145	99.74 79	99.53 221	99.75 67	99.27 146	99.61 175	99.19 173	99.57 185	99.64 178	98.76 130	99.90 157	97.29 276	99.62 259	99.56 171

baseline2		96.83 337	96.28 343	98.46 330	99.09 341	96.91 354	98.83 255	93.87 404	97.23 348	96.23 399	98.36 384	88.12 377	99.90 157	96.68 314	98.14 383	98.57 364

XVG-OURS-SEG-HR		99.16 179	98.99 200	99.66 116	99.84 61	99.64 110	98.25 318	99.73 114	98.39 275	99.63 159	99.43 270	99.70 24	99.90 157	97.34 273	98.64 365	99.44 228

XVG-OURS		99.21 163	99.06 175	99.65 121	99.82 72	99.62 117	97.87 357	99.74 110	98.36 278	99.66 152	99.68 162	99.71 22	99.90 157	96.84 307	99.88 134	99.43 234

JIA-IIPM		98.06 302	97.92 305	98.50 328	98.59 385	97.02 351	98.80 263	98.51 357	99.88 40	97.89 372	99.87 47	91.89 347	99.90 157	98.16 205	97.68 392	98.59 361

GBi-Net		99.42 105	99.31 118	99.73 88	99.49 239	99.77 54	99.68 45	99.70 131	99.44 134	99.62 168	99.83 66	97.21 266	99.90 157	98.96 142	99.90 115	99.53 187

test1		99.42 105	99.31 118	99.73 88	99.49 239	99.77 54	99.68 45	99.70 131	99.44 134	99.62 168	99.83 66	97.21 266	99.90 157	98.96 142	99.90 115	99.53 187

FMVSNet1		99.66 53	99.63 54	99.73 88	99.78 105	99.77 54	99.68 45	99.70 131	99.67 94	99.82 81	99.83 66	98.98 104	99.90 157	99.24 104	99.97 56	99.53 187

WTY-MVS		98.59 258	98.37 265	99.26 248	99.43 263	98.40 286	98.74 270	99.13 327	98.10 300	99.21 277	99.24 317	94.82 315	99.90 157	97.86 229	98.77 355	99.49 210

ECVR-MVS		97.73 313	98.04 292	96.78 374	99.59 186	90.81 406	99.72 30	90.43 408	99.89 35	99.86 71	99.86 54	93.60 331	99.89 175	99.46 69	99.99 16	99.65 112

EI-MVSNet-UG-set		99.48 87	99.50 83	99.42 201	99.57 201	98.65 271	99.24 155	99.46 254	99.68 90	99.80 92	99.66 171	98.99 102	99.89 175	99.19 111	99.90 115	99.72 73

EI-MVSNet-Vis-set		99.47 94	99.49 84	99.42 201	99.57 201	98.66 268	99.24 155	99.46 254	99.67 94	99.79 97	99.65 176	98.97 106	99.89 175	99.15 119	99.89 124	99.71 76

新几何1				99.52 176	99.50 234	99.22 211		99.26 304	95.66 377	98.60 341	99.28 305	97.67 245	99.89 175	95.95 353	99.32 318	99.45 223

testdata2													99.89 175	95.99 350

testdata				99.42 201	99.51 228	98.93 246		99.30 296	96.20 369	98.87 316	99.40 276	98.33 194	99.89 175	96.29 337	99.28 323	99.44 228

TESTMET0.1,1		96.24 351	95.84 352	97.41 365	98.24 396	93.84 390	97.38 378	95.84 395	98.43 269	97.81 377	98.56 378	79.77 399	99.89 175	97.77 236	98.77 355	98.52 366

test20.03		99.55 76	99.54 77	99.58 156	99.79 98	99.37 178	99.02 225	99.89 40	99.60 114	99.82 81	99.62 196	98.81 120	99.89 175	99.43 72	99.86 153	99.47 218

MDA-MVSNet-bldmvs		99.06 196	99.05 179	99.07 279	99.80 86	97.83 325	98.89 247	99.72 123	99.29 154	99.63 159	99.70 145	96.47 290	99.89 175	98.17 204	99.82 179	99.50 205

LPG-MVS_test		99.22 158	99.05 179	99.74 79	99.82 72	99.63 115	99.16 182	99.73 114	97.56 329	99.64 155	99.69 151	99.37 56	99.89 175	96.66 316	99.87 145	99.69 83

LGP-MVS_train				99.74 79	99.82 72	99.63 115		99.73 114	97.56 329	99.64 155	99.69 151	99.37 56	99.89 175	96.66 316	99.87 145	99.69 83

Test_1112_low_res		98.95 222	98.73 232	99.63 135	99.68 163	99.15 222	98.09 332	99.80 80	97.14 353	99.46 222	99.40 276	96.11 302	99.89 175	99.01 135	99.84 162	99.84 36

PatchmatchNet		97.65 317	97.80 310	97.18 371	98.82 369	92.49 396	99.17 176	98.39 364	98.12 299	98.79 326	99.58 221	90.71 363	99.89 175	97.23 286	99.41 306	99.16 293
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMP	97.51 14	99.05 199	98.84 223	99.67 109	99.78 105	99.55 138	98.88 248	99.66 148	97.11 355	99.47 218	99.60 213	99.07 94	99.89 175	96.18 342	99.85 157	99.58 164
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 67	99.70 35	100.00 1	99.73 74	100.00 1	99.89 34	99.79 16	99.88 189	99.98 1	100.00 1	99.98 3

FE-MVS		97.85 308	97.42 321	99.15 265	99.44 259	98.75 261	99.77 15	98.20 371	95.85 373	99.33 251	99.80 83	88.86 375	99.88 189	96.40 332	99.12 334	98.81 350

ppachtmachnet_test		98.89 230	99.12 155	98.20 342	99.66 169	95.24 380	97.63 366	99.68 140	99.08 193	99.78 101	99.62 196	98.65 147	99.88 189	98.02 211	99.96 70	99.48 214

TSAR-MVS + MP.		99.34 130	99.24 138	99.63 135	99.82 72	99.37 178	99.26 148	99.35 284	98.77 235	99.57 185	99.70 145	99.27 69	99.88 189	97.71 244	99.75 211	99.65 112
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
new-patchmatchnet		99.35 125	99.57 71	98.71 320	99.82 72	96.62 359	98.55 291	99.75 105	99.50 122	99.88 61	99.87 47	99.31 62	99.88 189	99.43 72	100.00 1	99.62 138

Anonymous20231206		99.35 125	99.31 118	99.47 187	99.74 134	99.06 235	99.28 143	99.74 110	99.23 166	99.72 127	99.53 244	97.63 251	99.88 189	99.11 127	99.84 162	99.48 214

XVS		99.27 143	99.11 158	99.75 74	99.71 143	99.71 83	99.37 116	99.61 175	99.29 154	98.76 329	99.47 262	98.47 173	99.88 189	97.62 255	99.73 223	99.67 95

v1240		99.56 73	99.58 68	99.51 178	99.80 86	99.00 236	99.00 230	99.65 157	99.15 186	99.90 49	99.75 116	99.09 89	99.88 189	99.90 25	99.96 70	99.67 95

X-MVStestdata		96.09 355	94.87 367	99.75 74	99.71 143	99.71 83	99.37 116	99.61 175	99.29 154	98.76 329	61.30 413	98.47 173	99.88 189	97.62 255	99.73 223	99.67 95

旧先验2							97.94 350		95.33 380	98.94 305			99.88 189	96.75 310

UniMVSNet (Re)		99.37 120	99.26 134	99.68 106	99.51 228	99.58 132	98.98 238	99.60 187	99.43 139	99.70 136	99.36 288	97.70 241	99.88 189	99.20 110	99.87 145	99.59 159

HPM-MVS_fast		99.43 102	99.30 123	99.80 45	99.83 65	99.81 40	99.52 85	99.70 131	98.35 283	99.51 211	99.50 251	99.31 62	99.88 189	98.18 202	99.84 162	99.69 83

TDRefinement		99.72 36	99.70 39	99.77 57	99.90 37	99.85 19	99.86 5	99.92 30	99.69 88	99.78 101	99.92 21	99.37 56	99.88 189	98.93 148	99.95 83	99.60 152

PCF-MVS	96.03 18	96.73 340	95.86 351	99.33 229	99.44 259	99.16 220	96.87 393	99.44 259	86.58 400	98.95 304	99.40 276	94.38 321	99.88 189	87.93 399	99.80 193	98.95 335
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		96.21 353	95.78 353	97.49 361	98.53 387	93.83 391	98.04 338	93.94 403	98.96 205	98.46 350	98.17 388	79.86 398	99.87 203	96.99 296	99.06 337	98.78 353

SF-MVS		99.10 193	98.93 208	99.62 144	99.58 191	99.51 143	99.13 192	99.65 157	97.97 309	99.42 230	99.61 205	98.86 117	99.87 203	96.45 331	99.68 243	99.49 210

D2MVS		99.22 158	99.19 142	99.29 240	99.69 155	98.74 262	98.81 260	99.41 265	98.55 257	99.68 142	99.69 151	98.13 212	99.87 203	98.82 153	99.98 41	99.24 273

thisisatest0515		96.98 334	96.42 341	98.66 321	99.42 268	97.47 337	97.27 383	94.30 401	97.24 347	99.15 285	98.86 365	85.01 390	99.87 203	97.10 292	99.39 308	98.63 358

ACMMP_NAP		99.28 139	99.11 158	99.79 51	99.75 128	99.81 40	98.95 242	99.53 230	98.27 292	99.53 204	99.73 123	98.75 132	99.87 203	97.70 247	99.83 170	99.68 89

Patchmatch-test		98.10 300	97.98 297	98.48 329	99.27 308	96.48 360	99.40 108	99.07 329	98.81 228	99.23 272	99.57 229	90.11 369	99.87 203	96.69 313	99.64 256	99.09 310

v144192		99.55 76	99.54 77	99.58 156	99.78 105	99.20 216	99.11 200	99.62 168	99.18 174	99.89 53	99.72 130	98.66 145	99.87 203	99.88 29	99.97 56	99.66 104

v1921920		99.56 73	99.57 71	99.55 168	99.75 128	99.11 225	99.05 215	99.61 175	99.15 186	99.88 61	99.71 138	99.08 92	99.87 203	99.90 25	99.97 56	99.66 104

FC-MVSNet-test		99.70 40	99.65 50	99.86 25	99.88 44	99.86 18	99.72 30	99.78 92	99.90 29	99.82 81	99.83 66	98.45 177	99.87 203	99.51 64	99.97 56	99.86 32

pm-mvs1		99.79 26	99.79 27	99.78 54	99.91 31	99.83 29	99.76 19	99.87 46	99.73 74	99.89 53	99.87 47	99.63 29	99.87 203	99.54 60	99.92 105	99.63 127

TransMVSNet (Re)		99.78 27	99.77 33	99.81 40	99.91 31	99.85 19	99.75 22	99.86 49	99.70 85	99.91 44	99.89 34	99.60 34	99.87 203	99.59 51	99.74 218	99.71 76

NR-MVSNet		99.40 111	99.31 118	99.68 106	99.43 263	99.55 138	99.73 27	99.50 243	99.46 131	99.88 61	99.36 288	97.54 252	99.87 203	98.97 140	99.87 145	99.63 127

Baseline_NR-MVSNet		99.49 85	99.37 106	99.82 37	99.91 31	99.84 24	98.83 255	99.86 49	99.68 90	99.65 154	99.88 42	97.67 245	99.87 203	99.03 133	99.86 153	99.76 66

EG-PatchMatch MVS		99.57 70	99.56 76	99.62 144	99.77 113	99.33 188	99.26 148	99.76 100	99.32 152	99.80 92	99.78 101	99.29 64	99.87 203	99.15 119	99.91 114	99.66 104

DELS-MVS		99.34 130	99.30 123	99.48 185	99.51 228	99.36 182	98.12 328	99.53 230	99.36 148	99.41 236	99.61 205	99.22 74	99.87 203	99.21 107	99.68 243	99.20 284
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		99.35 125	99.28 130	99.55 168	99.49 239	99.35 185	99.45 102	99.57 204	99.44 134	99.70 136	99.74 119	97.21 266	99.87 203	99.03 133	99.94 94	99.44 228

ab-mvs		99.33 133	99.28 130	99.47 187	99.57 201	99.39 173	99.78 12	99.43 262	98.87 219	99.57 185	99.82 73	98.06 217	99.87 203	98.69 168	99.73 223	99.15 295

DP-MVS		99.48 87	99.39 101	99.74 79	99.57 201	99.62 117	99.29 141	99.61 175	99.87 41	99.74 122	99.76 111	98.69 139	99.87 203	98.20 198	99.80 193	99.75 69

F-COLMAP		98.74 243	98.45 257	99.62 144	99.57 201	99.47 147	98.84 253	99.65 157	96.31 368	98.93 306	99.19 324	97.68 244	99.87 203	96.52 324	99.37 311	99.53 187

iter_conf05_11		98.54 263	98.33 271	99.18 260	99.07 343	99.20 216	97.94 350	97.59 381	99.17 179	99.30 263	98.92 362	94.79 316	99.86 222	98.29 188	99.89 124	98.47 372

Anonymous20240529		99.42 105	99.34 111	99.65 121	99.53 221	99.60 126	99.63 60	99.39 275	99.47 128	99.76 108	99.78 101	98.13 212	99.86 222	98.70 166	99.68 243	99.49 210

test_post											52.41 414	90.25 368	99.86 222

Anonymous20231211		99.62 65	99.57 71	99.76 64	99.61 180	99.60 126	99.81 9	99.73 114	99.82 58	99.90 49	99.90 29	97.97 225	99.86 222	99.42 77	99.96 70	99.80 47

v10		99.69 42	99.69 43	99.66 116	99.81 80	99.39 173	99.66 53	99.75 105	99.60 114	99.92 41	99.87 47	98.75 132	99.86 222	99.90 25	99.99 16	99.73 71

VPNet		99.46 95	99.37 106	99.71 99	99.82 72	99.59 128	99.48 95	99.70 131	99.81 61	99.69 139	99.58 221	97.66 249	99.86 222	99.17 116	99.44 301	99.67 95

testgi		99.29 138	99.26 134	99.37 219	99.75 128	98.81 255	98.84 253	99.89 40	98.38 276	99.75 114	99.04 341	99.36 59	99.86 222	99.08 130	99.25 327	99.45 223

mvs_anonymous		99.28 139	99.39 101	98.94 291	99.19 323	97.81 326	99.02 225	99.55 215	99.78 68	99.85 73	99.80 83	98.24 201	99.86 222	99.57 56	99.50 294	99.15 295

diffmvs		99.34 130	99.32 116	99.39 213	99.67 168	98.77 260	98.57 289	99.81 76	99.61 108	99.48 216	99.41 272	98.47 173	99.86 222	98.97 140	99.90 115	99.53 187
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	99.66 116	99.30 301	99.42 165	98.42 306	99.37 280	99.04 198	99.57 185	99.20 323	96.89 278	99.86 222	98.66 170	99.87 145	99.70 79

114514_t		98.49 271	98.11 289	99.64 128	99.73 137	99.58 132	99.24 155	99.76 100	89.94 398	99.42 230	99.56 233	97.76 240	99.86 222	97.74 241	99.82 179	99.47 218

UnsupCasMVSNet_eth		98.83 235	98.57 247	99.59 152	99.68 163	99.45 156	98.99 235	99.67 144	99.48 124	99.55 197	99.36 288	94.92 313	99.86 222	98.95 146	96.57 398	99.45 223

FMVSNet3		98.80 238	98.63 240	99.32 233	99.13 331	98.72 263	99.10 203	99.48 248	99.23 166	99.62 168	99.64 178	92.57 340	99.86 222	98.96 142	99.90 115	99.39 241

HY-MVS	98.23 9	98.21 296	97.95 299	98.99 285	99.03 349	98.24 294	99.61 67	98.72 345	96.81 361	98.73 331	99.51 248	94.06 323	99.86 222	96.91 301	98.20 378	98.86 346

TAMVS		99.49 85	99.45 91	99.63 135	99.48 244	99.42 165	99.45 102	99.57 204	99.66 98	99.78 101	99.83 66	97.85 233	99.86 222	99.44 71	99.96 70	99.61 148

ACMM	98.09 11	99.46 95	99.38 103	99.72 94	99.80 86	99.69 94	99.13 192	99.65 157	98.99 201	99.64 155	99.72 130	99.39 50	99.86 222	98.23 195	99.81 188	99.60 152
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
OpenMVS_ROB	97.31 17	97.36 327	96.84 337	98.89 304	99.29 303	99.45 156	98.87 249	99.48 248	86.54 401	99.44 224	99.74 119	97.34 261	99.86 222	91.61 392	99.28 323	97.37 396

COLMAP_ROB	98.06 12	99.45 97	99.37 106	99.70 103	99.83 65	99.70 90	99.38 112	99.78 92	99.53 120	99.67 148	99.78 101	99.19 77	99.86 222	97.32 274	99.87 145	99.55 174
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
testing3		96.48 345	95.63 356	99.01 284	99.23 315	97.81 326	98.90 246	99.10 328	98.72 240	97.84 376	97.92 393	72.44 409	99.85 240	97.21 288	99.33 316	99.35 252

hse-mvs2		98.52 266	98.30 274	99.16 263	99.29 303	98.60 275	98.77 268	99.02 333	99.68 90	99.32 254	99.04 341	92.50 343	99.85 240	99.24 104	97.87 390	99.03 325

AUN-MVS		97.82 309	97.38 322	99.14 269	99.27 308	98.53 277	98.72 272	99.02 333	98.10 300	97.18 387	99.03 345	89.26 374	99.85 240	97.94 220	97.91 388	99.03 325

miper_lstm_enhance		98.65 252	98.60 241	98.82 313	99.20 321	97.33 343	97.78 360	99.66 148	99.01 200	99.59 180	99.50 251	94.62 319	99.85 240	98.12 207	99.90 115	99.26 270

TEST9					99.35 281	99.35 185	98.11 330	99.41 265	94.83 388	97.92 370	98.99 349	98.02 220	99.85 240

train_agg		98.35 286	97.95 299	99.57 162	99.35 281	99.35 185	98.11 330	99.41 265	94.90 385	97.92 370	98.99 349	98.02 220	99.85 240	95.38 367	99.44 301	99.50 205

agg_prior					99.35 281	99.36 182		99.39 275		97.76 380			99.85 240

FIs		99.65 58	99.58 68	99.84 30	99.84 61	99.85 19	99.66 53	99.75 105	99.86 45	99.74 122	99.79 93	98.27 199	99.85 240	99.37 83	99.93 101	99.83 40

v1192		99.57 70	99.57 71	99.57 162	99.77 113	99.22 211	99.04 218	99.60 187	99.18 174	99.87 69	99.72 130	99.08 92	99.85 240	99.89 28	99.98 41	99.66 104

无先验							98.01 341	99.23 311	95.83 374				99.85 240	95.79 359		99.44 228

VDD-MVS		99.20 165	99.11 158	99.44 195	99.43 263	98.98 238	99.50 90	98.32 368	99.80 64	99.56 192	99.69 151	96.99 276	99.85 240	98.99 136	99.73 223	99.50 205

VDDNet		98.97 215	98.82 226	99.42 201	99.71 143	98.81 255	99.62 62	98.68 347	99.81 61	99.38 243	99.80 83	94.25 322	99.85 240	98.79 157	99.32 318	99.59 159

EI-MVSNet		99.38 117	99.44 94	99.21 255	99.58 191	98.09 308	99.26 148	99.46 254	99.62 105	99.75 114	99.67 166	98.54 162	99.85 240	99.15 119	99.92 105	99.68 89

MVSTER		98.47 273	98.22 279	99.24 253	99.06 345	98.35 292	99.08 211	99.46 254	99.27 158	99.75 114	99.66 171	88.61 376	99.85 240	99.14 125	99.92 105	99.52 198

ACMH	98.42 6	99.59 69	99.54 77	99.72 94	99.86 54	99.62 117	99.56 80	99.79 86	98.77 235	99.80 92	99.85 56	99.64 28	99.85 240	98.70 166	99.89 124	99.70 79
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
APD_test1		99.36 123	99.28 130	99.61 147	99.89 39	99.89 10	99.32 126	99.74 110	99.18 174	99.69 139	99.75 116	98.41 182	99.84 255	97.85 231	99.70 234	99.10 306

test_vis1_rt		99.45 97	99.46 89	99.41 208	99.71 143	98.63 273	98.99 235	99.96 23	99.03 199	99.95 31	99.12 331	98.75 132	99.84 255	99.82 35	99.82 179	99.77 60

FA-MVS(test-final)		98.52 266	98.32 272	99.10 274	99.48 244	98.67 265	99.77 15	98.60 354	97.35 343	99.63 159	99.80 83	93.07 336	99.84 255	97.92 221	99.30 320	98.78 353

EIA-MVS		99.12 187	99.01 192	99.45 192	99.36 279	99.62 117	99.34 121	99.79 86	98.41 272	98.84 319	98.89 363	98.75 132	99.84 255	98.15 206	99.51 291	98.89 343

Anonymous202405211		98.75 242	98.46 256	99.63 135	99.34 290	99.66 101	99.47 98	97.65 380	99.28 157	99.56 192	99.50 251	93.15 334	99.84 255	98.62 171	99.58 274	99.40 239

Effi-MVS+		99.06 196	98.97 204	99.34 226	99.31 297	98.98 238	98.31 313	99.91 33	98.81 228	98.79 326	98.94 358	99.14 84	99.84 255	98.79 157	98.74 359	99.20 284

gm-plane-assit					97.59 403	89.02 411			93.47 391		98.30 385		99.84 255	96.38 334

test_8					99.34 290	99.31 191	98.08 334	99.40 272	94.90 385	97.87 374	98.97 354	98.02 220	99.84 255

v1144		99.54 78	99.53 81	99.59 152	99.79 98	99.28 196	99.10 203	99.61 175	99.20 172	99.84 76	99.73 123	98.67 143	99.84 255	99.86 31	99.98 41	99.64 122

v8		99.68 45	99.69 43	99.65 121	99.80 86	99.40 171	99.66 53	99.76 100	99.64 102	99.93 37	99.85 56	98.66 145	99.84 255	99.88 29	99.99 16	99.71 76

v2v482		99.50 83	99.47 85	99.58 156	99.78 105	99.25 203	99.14 186	99.58 202	99.25 162	99.81 88	99.62 196	98.24 201	99.84 255	99.83 32	99.97 56	99.64 122

VNet		99.18 172	99.06 175	99.56 165	99.24 313	99.36 182	99.33 124	99.31 293	99.67 94	99.47 218	99.57 229	96.48 289	99.84 255	99.15 119	99.30 320	99.47 218

ADS-MVSNet		97.72 316	97.67 317	97.86 353	99.14 329	94.65 385	99.22 163	98.86 338	96.97 356	98.25 356	99.64 178	90.90 359	99.84 255	96.51 325	99.56 276	99.08 316

casdiffmvs_mvg		99.68 45	99.68 46	99.69 104	99.81 80	99.59 128	99.29 141	99.90 38	99.71 80	99.79 97	99.73 123	99.54 41	99.84 255	99.36 84	99.96 70	99.65 112
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	99.27 245	99.71 143	99.28 196	98.59 283	99.77 95	98.32 289	99.39 242	99.41 272	98.62 149	99.84 255	96.62 321	99.84 162	98.69 357

9.14			98.64 238		99.45 258		98.81 260	99.60 187	97.52 334	99.28 265	99.56 233	98.53 166	99.83 270	95.36 368	99.64 256

SMA-MVS		99.19 168	99.00 195	99.73 88	99.46 254	99.73 76	99.13 192	99.52 235	97.40 340	99.57 185	99.64 178	98.93 109	99.83 270	97.61 257	99.79 198	99.63 127
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		99.39 115	99.62 55	98.72 318	99.88 44	96.44 361	99.56 80	99.85 54	99.90 29	99.90 49	99.85 56	98.09 214	99.83 270	99.58 54	99.95 83	99.90 20

YYNet1		98.95 222	98.99 200	98.84 308	99.64 173	97.14 349	98.22 320	99.32 289	98.92 213	99.59 180	99.66 171	97.40 257	99.83 270	98.27 192	99.90 115	99.55 174

MDA-MVSNet_test_wron		98.95 222	98.99 200	98.85 306	99.64 173	97.16 347	98.23 319	99.33 287	98.93 211	99.56 192	99.66 171	97.39 259	99.83 270	98.29 188	99.88 134	99.55 174

baseline		99.63 59	99.62 55	99.66 116	99.80 86	99.62 117	99.44 104	99.80 80	99.71 80	99.72 127	99.69 151	99.15 81	99.83 270	99.32 93	99.94 94	99.53 187

CDS-MVSNet		99.22 158	99.13 151	99.50 180	99.35 281	99.11 225	98.96 241	99.54 221	99.46 131	99.61 174	99.70 145	96.31 297	99.83 270	99.34 88	99.88 134	99.55 174
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
DeepC-MVS_fast	98.47 5	99.23 150	99.12 155	99.56 165	99.28 306	99.22 211	98.99 235	99.40 272	99.08 193	99.58 182	99.64 178	98.90 115	99.83 270	97.44 267	99.75 211	99.63 127
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	98.36 283	97.99 295	99.48 185	99.32 296	99.24 207	98.50 299	99.51 239	95.19 383	98.58 343	98.96 356	96.95 277	99.83 270	95.63 361	99.25 327	99.37 246
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
pmmvs5		99.19 168	99.11 158	99.42 201	99.76 117	98.88 251	98.55 291	99.73 114	98.82 226	99.72 127	99.62 196	96.56 286	99.82 279	99.32 93	99.95 83	99.56 171

test_post1							99.14 186				51.63 415	89.54 373	99.82 279	96.86 304

原ACMM1				99.37 219	99.47 250	98.87 253		99.27 301	96.74 363	98.26 355	99.32 297	97.93 227	99.82 279	95.96 352	99.38 309	99.43 234

V42		99.56 73	99.54 77	99.63 135	99.79 98	99.46 151	99.39 110	99.59 193	99.24 164	99.86 71	99.70 145	98.55 160	99.82 279	99.79 37	99.95 83	99.60 152

CDPH-MVS		98.56 261	98.20 281	99.61 147	99.50 234	99.46 151	98.32 312	99.41 265	95.22 381	99.21 277	99.10 335	98.34 192	99.82 279	95.09 373	99.66 252	99.56 171

test12				99.54 173	99.29 303	99.33 188		99.16 323		98.43 351		97.54 252	99.82 279		99.47 298	99.48 214

casdiffmvs		99.63 59	99.61 59	99.67 109	99.79 98	99.59 128	99.13 192	99.85 54	99.79 66	99.76 108	99.72 130	99.33 61	99.82 279	99.21 107	99.94 94	99.59 159
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		97.73 313	97.33 323	98.96 288	99.30 301	97.73 330	99.40 108	98.42 362	99.33 151	99.46 222	99.21 321	91.18 354	99.82 279	98.35 184	91.26 404	99.32 259

HQP_MVS		98.90 227	98.68 237	99.55 168	99.58 191	99.24 207	98.80 263	99.54 221	98.94 208	99.14 287	99.25 312	97.24 264	99.82 279	95.84 357	99.78 203	99.60 152

plane_prior5								99.54 221					99.82 279	95.84 357	99.78 203	99.60 152

tpmrst		97.73 313	98.07 291	96.73 377	98.71 381	92.00 398	99.10 203	98.86 338	98.52 262	98.92 309	99.54 242	91.90 346	99.82 279	98.02 211	99.03 341	98.37 376

UnsupCasMVSNet_bld		98.55 262	98.27 276	99.40 210	99.56 212	99.37 178	97.97 348	99.68 140	97.49 336	99.08 294	99.35 293	95.41 312	99.82 279	97.70 247	98.19 380	99.01 330

dp		96.86 336	97.07 329	96.24 383	98.68 383	90.30 409	99.19 170	98.38 365	97.35 343	98.23 358	99.59 218	87.23 380	99.82 279	96.27 338	98.73 361	98.59 361

test_0402		99.22 158	99.14 149	99.45 192	99.79 98	99.43 162	99.28 143	99.68 140	99.54 118	99.40 241	99.56 233	99.07 94	99.82 279	96.01 347	99.96 70	99.11 304

PMMVS		98.49 271	98.29 275	99.11 272	98.96 356	98.42 285	97.54 370	99.32 289	97.53 333	98.47 349	98.15 389	97.88 230	99.82 279	97.46 266	99.24 329	99.09 310

testing222		95.60 368	94.59 371	98.61 322	98.66 384	97.45 339	98.54 294	97.90 377	98.53 261	96.54 395	96.47 409	70.62 411	99.81 294	95.91 355	98.15 382	98.56 365

bld_raw_dy_0_64		98.97 215	98.90 216	99.17 262	99.07 343	99.24 207	99.24 155	99.93 29	99.23 166	99.87 69	99.03 345	95.48 310	99.81 294	98.29 188	99.99 16	98.47 372

tt0805		99.63 59	99.57 71	99.81 40	99.87 51	99.88 12	99.58 75	98.70 346	99.72 78	99.91 44	99.60 213	99.43 48	99.81 294	99.81 36	99.53 287	99.73 71

LFMVS		98.46 274	98.19 284	99.26 248	99.24 313	98.52 279	99.62 62	96.94 389	99.87 41	99.31 258	99.58 221	91.04 356	99.81 294	98.68 169	99.42 305	99.45 223

NCCC		98.82 236	98.57 247	99.58 156	99.21 318	99.31 191	98.61 278	99.25 307	98.65 247	98.43 351	99.26 310	97.86 231	99.81 294	96.55 322	99.27 326	99.61 148

MIMVSNet		98.43 277	98.20 281	99.11 272	99.53 221	98.38 290	99.58 75	98.61 352	98.96 205	99.33 251	99.76 111	90.92 358	99.81 294	97.38 271	99.76 209	99.15 295

IS-MVSNet		99.03 203	98.85 221	99.55 168	99.80 86	99.25 203	99.73 27	99.15 324	99.37 146	99.61 174	99.71 138	94.73 318	99.81 294	97.70 247	99.88 134	99.58 164

AdaColmap		98.60 255	98.35 268	99.38 216	99.12 333	99.22 211	98.67 275	99.42 264	97.84 321	98.81 322	99.27 307	97.32 262	99.81 294	95.14 371	99.53 287	99.10 306

MCST-MVS		99.02 205	98.81 227	99.65 121	99.58 191	99.49 145	98.58 285	99.07 329	98.40 274	99.04 299	99.25 312	98.51 171	99.80 302	97.31 275	99.51 291	99.65 112

CostFormer		96.71 341	96.79 340	96.46 381	98.90 359	90.71 407	99.41 107	98.68 347	94.69 389	98.14 364	99.34 296	86.32 389	99.80 302	97.60 258	98.07 386	98.88 344

PHI-MVS		99.11 190	98.95 207	99.59 152	99.13 331	99.59 128	99.17 176	99.65 157	97.88 317	99.25 268	99.46 265	98.97 106	99.80 302	97.26 281	99.82 179	99.37 246

Patchmatch-RL test		98.60 255	98.36 266	99.33 229	99.77 113	99.07 233	98.27 315	99.87 46	98.91 214	99.74 122	99.72 130	90.57 365	99.79 305	98.55 174	99.85 157	99.11 304

test0.0.03 1		97.37 326	96.91 336	98.74 317	97.72 402	97.57 334	97.60 368	97.36 387	98.00 305	99.21 277	98.02 390	90.04 370	99.79 305	98.37 182	95.89 402	98.86 346

MSDG		99.08 194	98.98 203	99.37 219	99.60 182	99.13 223	97.54 370	99.74 110	98.84 225	99.53 204	99.55 240	99.10 87	99.79 305	97.07 294	99.86 153	99.18 289

cl____		98.54 263	98.41 261	98.92 295	99.03 349	97.80 328	97.46 376	99.59 193	98.90 215	99.60 177	99.46 265	93.85 326	99.78 308	97.97 218	99.89 124	99.17 291

DIV-MVS_self_test		98.54 263	98.42 260	98.92 295	99.03 349	97.80 328	97.46 376	99.59 193	98.90 215	99.60 177	99.46 265	93.87 325	99.78 308	97.97 218	99.89 124	99.18 289

MVP-Stereo		99.16 179	99.08 169	99.43 199	99.48 244	99.07 233	99.08 211	99.55 215	98.63 249	99.31 258	99.68 162	98.19 208	99.78 308	98.18 202	99.58 274	99.45 223
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 37	99.76 117	99.84 24	99.61 67	99.70 131	99.93 25	99.78 101	99.68 162	99.10 87	99.78 308	99.45 70	99.96 70	99.83 40

Vis-MVSNet (Re-imp)		98.77 240	98.58 246	99.34 226	99.78 105	98.88 251	99.61 67	99.56 209	99.11 192	99.24 271	99.56 233	93.00 338	99.78 308	97.43 268	99.89 124	99.35 252

CNLPA		98.57 260	98.34 269	99.28 242	99.18 325	99.10 230	98.34 310	99.41 265	98.48 267	98.52 346	98.98 352	97.05 274	99.78 308	95.59 362	99.50 294	98.96 333

ACMH+	98.40 8	99.50 83	99.43 96	99.71 99	99.86 54	99.76 61	99.32 126	99.77 95	99.53 120	99.77 106	99.76 111	99.26 70	99.78 308	97.77 236	99.88 134	99.60 152

CLD-MVS		98.76 241	98.57 247	99.33 229	99.57 201	98.97 240	97.53 372	99.55 215	96.41 365	99.27 266	99.13 327	99.07 94	99.78 308	96.73 312	99.89 124	99.23 276
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	99.54 215	97.99 314	98.58 285	99.82 67	97.62 328	99.34 249	99.71 138	98.52 169	99.77 316	97.98 216	99.97 56	99.52 198

PVSNet_Blended		98.70 248	98.59 243	99.02 283	99.54 215	97.99 314	97.58 369	99.82 67	95.70 376	99.34 249	98.98 352	98.52 169	99.77 316	97.98 216	99.83 170	99.30 265

eth_miper_zixun_eth		98.68 250	98.71 234	98.60 323	99.10 339	96.84 356	97.52 374	99.54 221	98.94 208	99.58 182	99.48 258	96.25 300	99.76 318	98.01 214	99.93 101	99.21 280

OPM-MVS		99.26 145	99.13 151	99.63 135	99.70 151	99.61 123	98.58 285	99.48 248	98.50 264	99.52 206	99.63 189	99.14 84	99.76 318	97.89 224	99.77 207	99.51 200
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
pmmvs-eth3d		99.48 87	99.47 85	99.51 178	99.77 113	99.41 170	98.81 260	99.66 148	99.42 143	99.75 114	99.66 171	99.20 76	99.76 318	98.98 138	99.99 16	99.36 249

pmmvs4		99.13 185	99.06 175	99.36 223	99.57 201	99.10 230	98.01 341	99.25 307	98.78 233	99.58 182	99.44 269	98.24 201	99.76 318	98.74 163	99.93 101	99.22 278

ETVMVS		96.14 354	95.22 364	98.89 304	98.80 370	98.01 313	98.66 276	98.35 367	98.71 242	97.18 387	96.31 412	74.23 408	99.75 322	96.64 319	98.13 385	98.90 341

AllTest		99.21 163	99.07 173	99.63 135	99.78 105	99.64 110	99.12 196	99.83 62	98.63 249	99.63 159	99.72 130	98.68 140	99.75 322	96.38 334	99.83 170	99.51 200

TestCases				99.63 135	99.78 105	99.64 110		99.83 62	98.63 249	99.63 159	99.72 130	98.68 140	99.75 322	96.38 334	99.83 170	99.51 200

CL-MVSNet_self_test		98.71 247	98.56 250	99.15 265	99.22 316	98.66 268	97.14 387	99.51 239	98.09 302	99.54 199	99.27 307	96.87 279	99.74 325	98.43 179	98.96 345	99.03 325

MVS		95.72 365	94.63 370	98.99 285	98.56 386	97.98 320	99.30 134	98.86 338	72.71 404	97.30 383	99.08 336	98.34 192	99.74 325	89.21 396	98.33 373	99.26 270

MG-MVS		98.52 266	98.39 263	98.94 291	99.15 328	97.39 342	98.18 321	99.21 317	98.89 218	99.23 272	99.63 189	97.37 260	99.74 325	94.22 382	99.61 266	99.69 83

c3_l		98.72 246	98.71 234	98.72 318	99.12 333	97.22 346	97.68 365	99.56 209	98.90 215	99.54 199	99.48 258	96.37 296	99.73 328	97.88 225	99.88 134	99.21 280

tpmvs		97.39 325	97.69 315	96.52 379	98.41 391	91.76 399	99.30 134	98.94 337	97.74 323	97.85 375	99.55 240	92.40 345	99.73 328	96.25 339	98.73 361	98.06 388

thres600view7		96.60 343	96.16 345	97.93 350	99.63 175	96.09 369	99.18 171	97.57 382	98.77 235	98.72 332	97.32 400	87.04 382	99.72 330	88.57 397	98.62 366	97.98 389

EPMVS		96.53 344	96.32 342	97.17 372	98.18 398	92.97 395	99.39 110	89.95 409	98.21 295	98.61 340	99.59 218	86.69 388	99.72 330	96.99 296	99.23 331	98.81 350

PVSNet	97.47 15	98.42 278	98.44 258	98.35 334	99.46 254	96.26 365	96.70 395	99.34 286	97.68 326	99.00 301	99.13 327	97.40 257	99.72 330	97.59 259	99.68 243	99.08 316

MAR-MVS		98.24 293	97.92 305	99.19 258	98.78 374	99.65 107	99.17 176	99.14 325	95.36 379	98.04 367	98.81 368	97.47 254	99.72 330	95.47 365	99.06 337	98.21 383
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
testing91		96.00 358	95.32 362	98.02 346	98.76 377	95.39 376	98.38 308	98.65 351	98.82 226	96.84 390	96.71 407	75.06 406	99.71 334	96.46 330	98.23 377	98.98 332

miper_ehance_all_eth		98.59 258	98.59 243	98.59 324	98.98 355	97.07 350	97.49 375	99.52 235	98.50 264	99.52 206	99.37 284	96.41 294	99.71 334	97.86 229	99.62 259	99.00 331

Gipuma		99.57 70	99.59 64	99.49 181	99.98 3	99.71 83	99.72 30	99.84 60	99.81 61	99.94 34	99.78 101	98.91 112	99.71 334	98.41 180	99.95 83	99.05 323
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ambc				99.20 257	99.35 281	98.53 277	99.17 176	99.46 254		99.67 148	99.80 83	98.46 176	99.70 337	97.92 221	99.70 234	99.38 243

HQP4-MVS										98.15 360			99.70 337			99.53 187

CNVR-MVS		98.99 214	98.80 229	99.56 165	99.25 311	99.43 162	98.54 294	99.27 301	98.58 255	98.80 324	99.43 270	98.53 166	99.70 337	97.22 287	99.59 273	99.54 182

tpm2		96.35 348	96.22 344	96.73 377	98.88 364	91.75 400	99.21 165	98.51 357	93.27 392	97.89 372	99.21 321	84.83 391	99.70 337	96.04 346	98.18 381	98.75 356

HQP-MVS		98.36 283	98.02 294	99.39 213	99.31 297	98.94 243	97.98 345	99.37 280	97.45 337	98.15 360	98.83 366	96.67 283	99.70 337	94.73 375	99.67 249	99.53 187

PatchMatch-RL		98.68 250	98.47 255	99.30 239	99.44 259	99.28 196	98.14 326	99.54 221	97.12 354	99.11 291	99.25 312	97.80 236	99.70 337	96.51 325	99.30 320	98.93 337

testing11		96.05 357	95.41 359	97.97 348	98.78 374	95.27 379	98.59 283	98.23 370	98.86 221	96.56 394	96.91 405	75.20 405	99.69 343	97.26 281	98.29 375	98.93 337

testing99		95.86 362	95.19 365	97.87 352	98.76 377	95.03 381	98.62 277	98.44 361	98.68 244	96.67 393	96.66 408	74.31 407	99.69 343	96.51 325	98.03 387	98.90 341

miper_enhance_ethall		98.03 303	97.94 303	98.32 337	98.27 395	96.43 362	96.95 391	99.41 265	96.37 367	99.43 228	98.96 356	94.74 317	99.69 343	97.71 244	99.62 259	98.83 349

test_yl		98.25 291	97.95 299	99.13 270	99.17 326	98.47 280	99.00 230	98.67 349	98.97 203	99.22 275	99.02 347	91.31 352	99.69 343	97.26 281	98.93 346	99.24 273

DCV-MVSNet		98.25 291	97.95 299	99.13 270	99.17 326	98.47 280	99.00 230	98.67 349	98.97 203	99.22 275	99.02 347	91.31 352	99.69 343	97.26 281	98.93 346	99.24 273

MS-PatchMatch		99.00 211	98.97 204	99.09 275	99.11 338	98.19 299	98.76 269	99.33 287	98.49 266	99.44 224	99.58 221	98.21 206	99.69 343	98.20 198	99.62 259	99.39 241

v148		99.40 111	99.41 100	99.39 213	99.76 117	98.94 243	99.09 208	99.59 193	99.17 179	99.81 88	99.61 205	98.41 182	99.69 343	99.32 93	99.94 94	99.53 187

test_prior				99.46 189	99.35 281	99.22 211		99.39 275					99.69 343			99.48 214

tpm cat1		96.78 338	96.98 332	96.16 384	98.85 365	90.59 408	99.08 211	99.32 289	92.37 393	97.73 381	99.46 265	91.15 355	99.69 343	96.07 345	98.80 352	98.21 383

PAPM_NR		98.36 283	98.04 292	99.33 229	99.48 244	98.93 246	98.79 266	99.28 300	97.54 332	98.56 345	98.57 377	97.12 271	99.69 343	94.09 384	98.90 350	99.38 243

PAPM		95.61 367	94.71 369	98.31 339	99.12 333	96.63 358	96.66 396	98.46 360	90.77 397	96.25 397	98.68 374	93.01 337	99.69 343	81.60 406	97.86 391	98.62 359

OMC-MVS		98.90 227	98.72 233	99.44 195	99.39 271	99.42 165	98.58 285	99.64 163	97.31 345	99.44 224	99.62 196	98.59 154	99.69 343	96.17 343	99.79 198	99.22 278

E-PMN		97.14 332	97.43 320	96.27 382	98.79 372	91.62 401	95.54 399	99.01 335	99.44 134	98.88 313	99.12 331	92.78 339	99.68 355	94.30 381	99.03 341	97.50 393

TSAR-MVS + GP.		99.12 187	99.04 185	99.38 216	99.34 290	99.16 220	98.15 324	99.29 297	98.18 298	99.63 159	99.62 196	99.18 78	99.68 355	98.20 198	99.74 218	99.30 265

MVS-HIRNet		97.86 307	98.22 279	96.76 375	99.28 306	91.53 402	98.38 308	92.60 405	99.13 188	99.31 258	99.96 12	97.18 270	99.68 355	98.34 185	99.83 170	99.07 321

PAPR		97.56 321	97.07 329	99.04 282	98.80 370	98.11 306	97.63 366	99.25 307	94.56 390	98.02 368	98.25 387	97.43 256	99.68 355	90.90 395	98.74 359	99.33 256

ITE_SJBPF				99.38 216	99.63 175	99.44 158		99.73 114	98.56 256	99.33 251	99.53 244	98.88 116	99.68 355	96.01 347	99.65 254	99.02 329

thres100view900		96.39 347	96.03 348	97.47 363	99.63 175	95.93 370	99.18 171	97.57 382	98.75 239	98.70 335	97.31 401	87.04 382	99.67 360	87.62 400	98.51 370	96.81 398

tfpn200view9		96.30 350	95.89 349	97.53 360	99.58 191	96.11 367	99.00 230	97.54 385	98.43 269	98.52 346	96.98 403	86.85 384	99.67 360	87.62 400	98.51 370	96.81 398

1314		98.00 305	97.90 307	98.27 341	98.90 359	97.45 339	99.30 134	99.06 331	94.98 384	97.21 386	99.12 331	98.43 179	99.67 360	95.58 363	98.56 368	97.71 392

thres400		96.40 346	95.89 349	97.92 351	99.58 191	96.11 367	99.00 230	97.54 385	98.43 269	98.52 346	96.98 403	86.85 384	99.67 360	87.62 400	98.51 370	97.98 389

EMVS		96.96 335	97.28 324	95.99 385	98.76 377	91.03 404	95.26 400	98.61 352	99.34 149	98.92 309	98.88 364	93.79 327	99.66 364	92.87 389	99.05 339	97.30 397

MVS_Test		99.28 139	99.31 118	99.19 258	99.35 281	98.79 258	99.36 119	99.49 247	99.17 179	99.21 277	99.67 166	98.78 127	99.66 364	99.09 129	99.66 252	99.10 306

EPNet_dtu		97.62 318	97.79 312	97.11 373	96.67 406	92.31 397	98.51 298	98.04 372	99.24 164	95.77 400	99.47 262	93.78 328	99.66 364	98.98 138	99.62 259	99.37 246
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
BH-RMVSNet		98.41 279	98.14 287	99.21 255	99.21 318	98.47 280	98.60 280	98.26 369	98.35 283	98.93 306	99.31 299	97.20 269	99.66 364	94.32 380	99.10 336	99.51 200

MDTV_nov1_ep13			97.73 314		98.70 382	90.83 405	99.15 184	98.02 373	98.51 263	98.82 321	99.61 205	90.98 357	99.66 364	96.89 303	98.92 348

MVS_111021_LR		99.13 185	99.03 187	99.42 201	99.58 191	99.32 190	97.91 355	99.73 114	98.68 244	99.31 258	99.48 258	99.09 89	99.66 364	97.70 247	99.77 207	99.29 268

BH-untuned		98.22 295	98.09 290	98.58 326	99.38 274	97.24 345	98.55 291	98.98 336	97.81 322	99.20 282	98.76 370	97.01 275	99.65 370	94.83 374	98.33 373	98.86 346

RPSCF		99.18 172	99.02 189	99.64 128	99.83 65	99.85 19	99.44 104	99.82 67	98.33 288	99.50 213	99.78 101	97.90 228	99.65 370	96.78 309	99.83 170	99.44 228

USDC		98.96 219	98.93 208	99.05 281	99.54 215	97.99 314	97.07 390	99.80 80	98.21 295	99.75 114	99.77 108	98.43 179	99.64 372	97.90 223	99.88 134	99.51 200

DeepPCF-MVS	98.42 6	99.18 172	99.02 189	99.67 109	99.22 316	99.75 67	97.25 384	99.47 251	98.72 240	99.66 152	99.70 145	99.29 64	99.63 373	98.07 210	99.81 188	99.62 138

alignmvs		98.28 289	97.96 298	99.25 251	99.12 333	98.93 246	99.03 222	98.42 362	99.64 102	98.72 332	97.85 394	90.86 361	99.62 374	98.88 149	99.13 333	99.19 287

DeepMVS_CX				97.98 347	99.69 155	96.95 352		99.26 304	75.51 403	95.74 401	98.28 386	96.47 290	99.62 374	91.23 394	97.89 389	97.38 395

TinyColmap		98.97 215	98.93 208	99.07 279	99.46 254	98.19 299	97.75 361	99.75 105	98.79 231	99.54 199	99.70 145	98.97 106	99.62 374	96.63 320	99.83 170	99.41 238

TAPA-MVS	97.92 13	98.03 303	97.55 319	99.46 189	99.47 250	99.44 158	98.50 299	99.62 168	86.79 399	99.07 297	99.26 310	98.26 200	99.62 374	97.28 278	99.73 223	99.31 263
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
DPM-MVS		98.28 289	97.94 303	99.32 233	99.36 279	99.11 225	97.31 382	98.78 343	96.88 358	98.84 319	99.11 334	97.77 238	99.61 378	94.03 386	99.36 312	99.23 276

thres200		96.09 355	95.68 355	97.33 368	99.48 244	96.22 366	98.53 296	97.57 382	98.06 304	98.37 353	96.73 406	86.84 386	99.61 378	86.99 403	98.57 367	96.16 401

DP-MVS Recon		98.50 269	98.23 277	99.31 236	99.49 239	99.46 151	98.56 290	99.63 165	94.86 387	98.85 318	99.37 284	97.81 235	99.59 380	96.08 344	99.44 301	98.88 344

PVSNet_0	95.53 19	95.85 363	95.31 363	97.47 363	98.78 374	93.48 393	95.72 398	99.40 272	96.18 370	97.37 382	97.73 395	95.73 306	99.58 381	95.49 364	81.40 405	99.36 249

Syy-MVS		98.17 297	97.85 309	99.15 265	98.50 389	98.79 258	98.60 280	99.21 317	97.89 315	96.76 391	96.37 410	95.47 311	99.57 382	99.10 128	98.73 361	99.09 310

myMVS_eth3d		95.63 366	94.73 368	98.34 336	98.50 389	96.36 363	98.60 280	99.21 317	97.89 315	96.76 391	96.37 410	72.10 410	99.57 382	94.38 379	98.73 361	99.09 310

API-MVS		98.38 282	98.39 263	98.35 334	98.83 366	99.26 200	99.14 186	99.18 321	98.59 254	98.66 337	98.78 369	98.61 151	99.57 382	94.14 383	99.56 276	96.21 400

KD-MVS_2432*1600		95.89 359	95.41 359	97.31 369	94.96 407	93.89 388	97.09 388	99.22 314	97.23 348	98.88 313	99.04 341	79.23 400	99.54 385	96.24 340	96.81 396	98.50 370

miper_refine_blended		95.89 359	95.41 359	97.31 369	94.96 407	93.89 388	97.09 388	99.22 314	97.23 348	98.88 313	99.04 341	79.23 400	99.54 385	96.24 340	96.81 396	98.50 370

canonicalmvs		99.02 205	99.00 195	99.09 275	99.10 339	98.70 264	99.61 67	99.66 148	99.63 104	98.64 338	97.65 397	99.04 98	99.54 385	98.79 157	98.92 348	99.04 324

MVS_111021_HR		99.12 187	99.02 189	99.40 210	99.50 234	99.11 225	97.92 353	99.71 126	98.76 238	99.08 294	99.47 262	99.17 79	99.54 385	97.85 231	99.76 209	99.54 182

test_241102_ONE					99.69 155	99.82 35		99.54 221	99.12 191	99.82 81	99.49 255	98.91 112	99.52 389

gg-mvs-nofinetune		95.87 361	95.17 366	97.97 348	98.19 397	96.95 352	99.69 42	89.23 410	99.89 35	96.24 398	99.94 16	81.19 395	99.51 390	93.99 387	98.20 378	97.44 394

TR-MVS		97.44 324	97.15 328	98.32 337	98.53 387	97.46 338	98.47 301	97.91 376	96.85 359	98.21 359	98.51 381	96.42 292	99.51 390	92.16 391	97.29 394	97.98 389

BH-w/o		97.20 329	97.01 331	97.76 356	99.08 342	95.69 373	98.03 340	98.52 356	95.76 375	97.96 369	98.02 390	95.62 308	99.47 392	92.82 390	97.25 395	98.12 387

PMVS	92.94 21	98.82 236	98.81 227	98.85 306	99.84 61	97.99 314	99.20 166	99.47 251	99.71 80	99.42 230	99.82 73	98.09 214	99.47 392	93.88 388	99.85 157	99.07 321
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
CMPMVS	77.52 23	98.50 269	98.19 284	99.41 208	98.33 394	99.56 135	99.01 227	99.59 193	95.44 378	99.57 185	99.80 83	95.64 307	99.46 394	96.47 329	99.92 105	99.21 280
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GA-MVS		97.99 306	97.68 316	98.93 294	99.52 226	98.04 312	97.19 386	99.05 332	98.32 289	98.81 322	98.97 354	89.89 372	99.41 395	98.33 186	99.05 339	99.34 255

cl22		97.56 321	97.28 324	98.40 332	98.37 393	96.75 357	97.24 385	99.37 280	97.31 345	99.41 236	99.22 319	87.30 379	99.37 396	97.70 247	99.62 259	99.08 316

dmvs_re		98.69 249	98.48 254	99.31 236	99.55 213	99.42 165	99.54 83	98.38 365	99.32 152	98.72 332	98.71 372	96.76 282	99.21 397	96.01 347	99.35 314	99.31 263

GG-mvs-BLEND				97.36 366	97.59 403	96.87 355	99.70 35	88.49 411		94.64 404	97.26 402	80.66 396	99.12 398	91.50 393	96.50 400	96.08 402

MSLP-MVS++		99.05 199	99.09 167	98.91 297	99.21 318	98.36 291	98.82 259	99.47 251	98.85 222	98.90 312	99.56 233	98.78 127	99.09 399	98.57 173	99.68 243	99.26 270

FPMVS		96.32 349	95.50 357	98.79 314	99.60 182	98.17 302	98.46 305	98.80 342	97.16 352	96.28 396	99.63 189	82.19 394	99.09 399	88.45 398	98.89 351	99.10 306

dmvs_testset		97.27 328	96.83 338	98.59 324	99.46 254	97.55 335	99.25 154	96.84 390	98.78 233	97.24 385	97.67 396	97.11 272	98.97 401	86.59 405	98.54 369	99.27 269

OPU-MVS				99.29 240	99.12 333	99.44 158	99.20 166				99.40 276	99.00 100	98.84 402	96.54 323	99.60 269	99.58 164

cascas		96.99 333	96.82 339	97.48 362	97.57 405	95.64 374	96.43 397	99.56 209	91.75 394	97.13 389	97.61 398	95.58 309	98.63 403	96.68 314	99.11 335	98.18 386

MVE	92.54 22	96.66 342	96.11 346	98.31 339	99.68 163	97.55 335	97.94 350	95.60 396	99.37 146	90.68 406	98.70 373	96.56 286	98.61 404	86.94 404	99.55 280	98.77 355
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PC_three_1452									97.56 329	99.68 142	99.41 272	99.09 89	97.09 405	96.66 316	99.60 269	99.62 138

tmp_tt		95.75 364	95.42 358	96.76 375	89.90 411	94.42 386	98.86 250	97.87 378	78.01 402	99.30 263	99.69 151	97.70 241	95.89 406	99.29 100	98.14 383	99.95 11

SD-MVS		99.01 209	99.30 123	98.15 343	99.50 234	99.40 171	98.94 244	99.61 175	99.22 171	99.75 114	99.82 73	99.54 41	95.51 407	97.48 265	99.87 145	99.54 182
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		29.31 373	33.05 378	18.08 389	25.93 413	12.24 414	97.53 372	10.93 414	11.78 407	24.21 408	50.08 417	21.04 412	8.60 408	23.51 407	32.43 407	33.39 404

testmvs		28.94 374	33.33 376	15.79 390	26.03 412	9.81 415	96.77 394	15.67 413	11.55 408	23.87 409	50.74 416	19.03 413	8.53 409	23.21 408	33.07 406	29.03 405

test_blank		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet_test		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

DCPMVS		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

cdsmvs_eth3d_5k		24.88 375	33.17 377	0.00 391	0.00 414	0.00 416	0.00 402	99.62 168	0.00 409	0.00 410	99.13 327	99.82 13	0.00 410	0.00 409	0.00 408	0.00 406

pcd_1.5k_mvsjas		16.61 376	22.14 379	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	99.28 66	0.00 410	0.00 409	0.00 408	0.00 406

sosnet-low-res		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

sosnet		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uncertanet		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

Regformer		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

ab-mvs-re		8.26 385	11.02 388	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	99.16 325	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

uanet		8.33 377	11.11 380	0.00 391	0.00 414	0.00 416	0.00 402	0.00 415	0.00 409	0.00 410	100.00 1	0.00 414	0.00 410	0.00 409	0.00 408	0.00 406

WAC-MVS						96.36 363								95.20 370

FOURS1					99.83 65	99.89 10	99.74 24	99.71 126	99.69 88	99.63 159

test_one_0601					99.63 175	99.76 61		99.55 215	99.23 166	99.31 258	99.61 205	98.59 154

eth-test2					0.00 414

eth-test					0.00 414

RE-MVS-def			99.13 151		99.54 215	99.74 73	99.26 148	99.62 168	99.16 182	99.52 206	99.64 178	98.57 157		97.27 279	99.61 266	99.54 182

IU-MVS					99.69 155	99.77 54		99.22 314	97.50 335	99.69 139				97.75 240	99.70 234	99.77 60

save fliter					99.53 221	99.25 203	98.29 314	99.38 279	99.07 195

test0726					99.69 155	99.80 44	99.24 155	99.57 204	99.16 182	99.73 126	99.65 176	98.35 190

GSMVS																99.14 300

test_part2					99.62 179	99.67 99				99.55 197

sam_mvs1												90.81 362				99.14 300

sam_mvs												90.52 366

MTGPA								99.53 230

MTMP							99.09 208	98.59 355

test9_res														95.10 372	99.44 301	99.50 205

agg_prior2														94.58 378	99.46 300	99.50 205

test_prior4						99.19 218	98.00 343

test_prior2							97.95 349		97.87 318	98.05 366	99.05 339	97.90 228		95.99 350	99.49 296

新几何2							98.04 338

旧先验1					99.49 239	99.29 194		99.26 304			99.39 280	97.67 245			99.36 312	99.46 222

原ACMM2							97.92 353

test222					99.51 228	99.08 232	97.83 359	99.29 297	95.21 382	98.68 336	99.31 299	97.28 263			99.38 309	99.43 234

segment_acmp												98.37 188

testdata1							97.72 362		97.86 320

plane_prior7					99.58 191	99.38 175

plane_prior6					99.47 250	99.26 200						97.24 264

plane_prior4											99.25 312

plane_prior3						99.31 191			98.36 278	99.14 287

plane_prior2							98.80 263		98.94 208

plane_prior1					99.51 228

plane_prior						99.24 207	98.42 306		97.87 318						99.71 232

n2								0.00 415

nn								0.00 415

door-mid								99.83 62

test11								99.29 297

door								99.77 95

HQP5-MVS						98.94 243

HQP-NCC					99.31 297		97.98 345		97.45 337	98.15 360

ACMP_Plane					99.31 297		97.98 345		97.45 337	98.15 360

BP-MVS														94.73 375

HQP3-MVS								99.37 280							99.67 249

HQP2-MVS												96.67 283

NP-MVS					99.40 270	99.13 223					98.83 366

MDTV_nov1_ep13_2view						91.44 403	99.14 186		97.37 342	99.21 277		91.78 350		96.75 310		99.03 325

ACMMP++_ref															99.94 94

ACMMP++															99.79 198

Test By Simon												98.41 182

High-resolution multi-view benchmark