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.

0.3-1-1-0.015		94.22 281	93.13 302	97.49 224	95.50 383	94.17 275	100.00 1	98.22 215	88.44 389	97.14 209	97.04 336	92.73 144	98.59 275	96.45 227	72.65 468	99.70 125

0.4-1-1-0.1		94.07 287	92.95 305	97.42 231	95.24 388	94.00 282	100.00 1	98.22 215	88.27 393	96.81 225	96.93 340	92.27 162	98.56 279	96.21 233	72.63 470	99.70 125

0.4-1-1-0.2		94.14 282	93.02 304	97.51 219	95.45 384	94.25 271	100.00 1	98.22 215	88.53 386	96.83 223	96.95 339	92.25 163	98.57 278	96.34 228	72.65 468	99.70 125

testing3-2		97.72 106	97.43 110	98.60 118	98.55 178	97.11 133	100.00 1	99.23 31	93.78 190	97.90 179	98.73 249	95.50 54	99.69 165	98.53 123	94.63 300	98.99 267

test_fmvsm_n_1920		98.44 49	98.61 30	97.92 175	99.27 116	95.18 230	100.00 1	98.90 50	98.05 20	99.80 28	99.73 92	92.64 148	99.99 40	99.58 58	99.51 118	98.59 291

DELS-MVS		98.54 41	98.22 52	99.50 35	99.15 124	98.65 59	100.00 1	98.58 106	97.70 32	98.21 169	99.24 175	92.58 151	99.94 95	98.63 118	99.94 59	99.92 93
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
PVSNet_Blended		97.94 82	97.64 96	98.83 100	99.59 93	96.99 138	100.00 1	99.10 34	95.38 118	98.27 163	99.08 192	89.00 221	99.95 86	99.12 80	99.25 141	99.57 163

fmvsm_s_conf0.5_n_11		98.03 79	97.89 82	98.46 137	99.35 110	97.76 99	99.99 8	98.04 243	98.20 9	99.90 7	99.78 67	86.21 266	99.95 86	99.89 22	99.68 94	97.65 320

fmvsm_s_conf0.5_n_10		98.24 69	97.90 80	99.26 55	99.24 117	97.88 93	99.99 8	98.76 73	98.20 9	99.92 5	99.74 88	85.97 270	99.94 95	99.72 47	99.53 114	99.96 75

fmvsm_l_conf0.5_n_9		98.55 40	98.23 51	99.49 37	99.10 126	98.50 66	99.99 8	98.70 80	98.14 16	99.94 2	99.68 112	89.02 220	99.98 52	99.89 22	99.61 105	99.99 26

fmvsm_s_conf0.5_n_9		98.15 73	98.02 68	98.55 124	99.28 114	95.84 190	99.99 8	98.57 108	98.17 13	99.93 3	99.74 88	87.04 250	99.97 65	99.86 28	99.59 109	99.83 105

fmvsm_s_conf0.5_n_5		98.08 77	97.71 92	99.17 66	98.67 167	97.69 105	99.99 8	98.57 108	97.40 40	99.89 11	99.69 105	85.99 269	99.96 77	99.80 33	99.40 133	99.85 103

MM		98.83 24	98.53 33	99.76 11	99.59 93	99.33 9	99.99 8	99.76 6	98.39 4	99.39 92	99.80 59	90.49 198	99.96 77	99.89 22	99.43 130	99.98 57

testing3		93.92 289	94.23 259	92.99 408	97.54 266	90.23 393	99.99 8	99.16 33	90.57 340	91.33 330	98.63 262	92.99 135	92.52 491	82.46 439	95.39 291	96.22 342

test_fmvsmconf_n		98.43 51	98.32 47	98.78 103	98.12 218	96.41 165	99.99 8	98.83 66	98.22 7	99.67 53	99.64 119	91.11 184	99.94 95	99.67 53	99.62 100	99.98 57

test_cas_vis1_n_1920		96.59 173	96.23 167	97.65 202	98.22 208	94.23 272	99.99 8	97.25 351	97.77 29	99.58 71	99.08 192	77.10 388	99.97 65	97.64 178	99.45 128	98.74 285

ET-MVSNet_ETH3D		94.37 275	93.28 296	97.64 203	98.30 200	97.99 86	99.99 8	97.61 293	94.35 158	71.57 495	99.45 141	96.23 40	95.34 460	96.91 207	85.14 383	99.59 155

CS-MVS		97.79 99	97.91 79	97.43 230	99.10 126	94.42 261	99.99 8	97.10 383	95.07 124	99.68 52	99.75 81	92.95 137	98.34 306	98.38 131	99.14 146	99.54 169

MGCNet		99.06 13	98.84 19	99.72 14	99.76 74	99.21 23	99.99 8	99.34 25	98.70 2	99.44 83	99.75 81	93.24 129	99.99 40	99.94 15	99.41 132	99.95 83

alignmvs		97.81 96	97.33 114	99.25 56	98.77 161	98.66 57	99.99 8	98.44 149	94.40 157	98.41 156	99.47 138	93.65 115	99.42 191	98.57 119	94.26 308	99.67 133

lupinMVS		97.85 90	97.60 98	98.62 116	97.28 296	97.70 103	99.99 8	97.55 300	95.50 117	99.43 85	99.67 114	90.92 188	98.71 258	98.40 130	99.62 100	99.45 192

EC-MVSNet		97.38 125	97.24 118	97.80 184	97.41 277	95.64 202	99.99 8	97.06 396	94.59 142	99.63 59	99.32 155	89.20 218	98.14 324	98.76 108	99.23 143	99.62 148

IB-MVS	92.85 6	94.99 249	93.94 270	98.16 156	97.72 246	95.69 200	99.99 8	98.81 67	94.28 164	92.70 316	96.90 341	95.08 63	99.17 206	96.07 234	73.88 462	99.60 154
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
fmvsm_s_conf0.5_n_8		98.38 57	98.05 66	99.35 50	99.20 119	98.12 78	99.98 24	98.81 67	98.22 7	99.80 28	99.71 98	87.37 245	99.97 65	99.91 20	99.48 122	99.97 67

fmvsm_s_conf0.5_n_6		98.27 63	97.96 75	99.23 58	97.66 254	98.11 79	99.98 24	98.64 91	97.85 27	99.87 14	99.72 95	88.86 224	99.93 105	99.64 55	99.36 136	99.63 147

fmvsm_l_conf0.5_n_3		98.41 53	98.08 64	99.39 46	99.12 125	98.29 71	99.98 24	98.64 91	98.14 16	99.86 16	99.76 73	87.99 233	99.97 65	99.72 47	99.54 112	99.91 95

fmvsm_s_conf0.5_n_3		97.95 81	97.66 94	98.81 101	98.99 137	98.07 81	99.98 24	98.81 67	98.18 12	99.89 11	99.70 101	84.15 309	99.97 65	99.76 41	99.50 120	98.39 298

fmvsm_s_conf0.5_n_2		97.59 113	97.28 116	98.53 130	99.01 132	98.15 73	99.98 24	98.59 104	98.17 13	99.75 42	99.63 122	81.83 336	99.94 95	99.78 36	98.79 164	97.51 329

fmvsm_l_conf0.5_n_a		99.00 18	98.91 15	99.28 53	99.21 118	97.91 92	99.98 24	98.85 62	98.25 5	99.92 5	99.75 81	94.72 75	99.97 65	99.87 26	99.64 98	99.95 83

fmvsm_l_conf0.5_n		98.94 19	98.84 19	99.25 56	99.17 122	97.81 97	99.98 24	98.86 59	98.25 5	99.90 7	99.76 73	94.21 98	99.97 65	99.87 26	99.52 115	99.98 57

fmvsm_s_conf0.5_n		97.80 97	97.85 85	97.67 199	99.06 129	94.41 262	99.98 24	98.97 43	97.34 42	99.63 59	99.69 105	87.27 246	99.97 65	99.62 56	99.06 152	98.62 290

test_vis1_n_1920		95.44 235	95.31 223	95.82 303	98.50 185	88.74 417	99.98 24	97.30 337	97.84 28	99.85 20	99.19 182	66.82 456	99.97 65	98.82 103	99.46 127	98.76 283

EIA-MVS		97.53 115	97.46 105	97.76 192	98.04 222	94.84 242	99.98 24	97.61 293	94.41 156	97.90 179	99.59 125	92.40 158	98.87 227	98.04 154	99.13 147	99.59 155

ETV-MVS		97.92 84	97.80 88	98.25 152	98.14 216	96.48 162	99.98 24	97.63 287	95.61 112	99.29 99	99.46 140	92.55 152	98.82 234	99.02 91	98.54 172	99.46 187

CANet		98.27 63	97.82 87	99.63 19	99.72 83	99.10 25	99.98 24	98.51 132	97.00 59	98.52 148	99.71 98	87.80 234	99.95 86	99.75 42	99.38 134	99.83 105

SPE-MVS-test		97.88 86	97.94 77	97.70 198	99.28 114	95.20 229	99.98 24	97.15 369	95.53 115	99.62 62	99.79 63	92.08 169	98.38 302	98.75 109	99.28 140	99.52 174

MSLP-MVS++		99.13 9	99.01 12	99.49 37	99.94 18	98.46 68	99.98 24	98.86 59	97.10 53	99.80 28	99.94 5	95.92 45	100.00 1	99.51 60	100.00 1	100.00 1

CNVR-MVS		99.40 1	99.26 1	99.84 7	99.98 2	99.51 7	99.98 24	98.69 82	98.20 9	99.93 3	99.98 2	96.82 26	100.00 1	99.75 42	100.00 1	99.99 26

SteuartSystems-ACMMP		99.02 15	98.97 14	99.18 63	98.72 164	97.71 101	99.98 24	98.44 149	96.85 64	99.80 28	99.91 19	97.57 9	99.85 131	99.44 67	99.99 21	99.99 26
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		98.41 53	98.21 53	99.03 85	99.86 59	97.10 134	99.98 24	98.80 71	90.78 335	99.62 62	99.78 67	95.30 58	100.00 1	99.80 33	99.93 65	99.99 26

CLD-MVS		94.06 288	93.90 271	94.55 347	96.02 358	90.69 382	99.98 24	97.72 279	96.62 77	91.05 333	98.85 240	77.21 387	98.47 285	98.11 149	89.51 337	94.48 351
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
aaatest				99.60 24	99.96 9	98.79 43	99.97 42	98.88 55	96.36 90	99.07 113	99.93 12		100.00 1	99.98 9	99.96 48	99.99 26

MED-MVS		99.24 8	99.12 5	99.60 24	99.96 9	98.79 43	99.97 42	98.88 55	96.91 62	99.07 113	99.92 16	97.36 18	100.00 1	99.98 9	99.98 32	100.00 1

TestfortrainingZip a		99.01 16	98.78 21	99.69 17	99.96 9	99.09 26	99.97 42	98.74 76	96.91 62	99.86 16	99.92 16	96.29 38	99.99 40	98.32 136	99.09 150	100.00 1

TestfortrainingZip				99.90 5	99.97 3	99.70 5	99.97 42	98.89 52	96.02 99	99.99 1	99.96 3	97.97 5	100.00 1		99.65 97	100.00 1

lecture		98.67 33	98.46 36	99.28 53	99.86 59	97.88 93	99.97 42	99.25 30	96.07 97	99.79 37	99.70 101	92.53 153	99.98 52	99.51 60	99.48 122	99.97 67

fmvsm_s_conf0.5_n_7		97.70 109	97.74 89	97.59 212	98.44 189	95.16 232	99.97 42	98.65 88	97.95 24	99.62 62	99.78 67	86.09 267	99.94 95	99.69 51	99.50 120	97.66 319

fmvsm_s_conf0.5_n_4		97.75 102	97.86 84	97.42 231	99.01 132	94.69 250	99.97 42	98.76 73	97.91 25	99.87 14	99.76 73	86.70 257	99.93 105	99.67 53	99.12 149	97.64 321

thisisatest0515		97.41 123	97.02 129	98.59 121	97.71 248	97.52 110	99.97 42	98.54 124	91.83 291	97.45 197	99.04 198	97.50 10	99.10 210	94.75 264	96.37 256	99.16 244

Fast-Effi-MVS+		95.02 248	94.19 260	97.52 218	97.88 230	94.55 253	99.97 42	97.08 387	88.85 378	94.47 290	97.96 306	84.59 302	98.41 294	89.84 359	97.10 227	99.59 155

MCST-MVS		99.32 3	99.14 4	99.86 6	99.97 3	99.59 6	99.97 42	98.64 91	98.47 3	99.13 108	99.92 16	96.38 37	100.00 1	99.74 44	100.00 1	100.00 1

TSAR-MVS + GP.		98.60 37	98.51 34	98.86 99	99.73 81	96.63 155	99.97 42	97.92 257	98.07 19	98.76 134	99.55 132	95.00 68	99.94 95	99.91 20	97.68 199	99.99 26

jason		97.24 130	96.86 135	98.38 145	95.73 371	97.32 119	99.97 42	97.40 319	95.34 120	98.60 146	99.54 134	87.70 236	98.56 279	97.94 160	99.47 125	99.25 235
jason: jason.
NCCC		99.37 2	99.25 2	99.71 16	99.96 9	99.15 24	99.97 42	98.62 98	98.02 22	99.90 7	99.95 4	97.33 19	100.00 1	99.54 59	100.00 1	100.00 1

CP-MVS		98.45 48	98.32 47	98.87 98	99.96 9	96.62 156	99.97 42	98.39 182	94.43 153	98.90 123	99.87 32	94.30 93	100.00 1	99.04 87	99.99 21	99.99 26

BP-MVS1		98.33 59	98.18 56	98.81 101	97.44 275	97.98 87	99.96 56	98.17 224	94.88 131	98.77 131	99.59 125	97.59 8	99.08 211	98.24 142	98.93 156	99.36 207

fmvsm_s_conf0.5_n_a		97.73 105	97.72 90	97.77 190	98.63 172	94.26 270	99.96 56	98.92 49	97.18 52	99.75 42	99.69 105	87.00 252	99.97 65	99.46 65	98.89 157	99.08 255

test_fmvs1		95.35 238	95.68 204	94.36 358	98.99 137	84.98 452	99.96 56	96.65 434	97.60 34	99.73 47	98.96 215	71.58 434	99.93 105	98.31 137	99.37 135	98.17 304

GeoE		94.36 277	93.48 285	96.99 257	97.29 295	93.54 300	99.96 56	96.72 431	88.35 391	93.43 304	98.94 222	82.05 331	98.05 331	88.12 389	96.48 253	99.37 205

SED-MVS		99.28 5	99.11 8	99.77 9	99.93 29	99.30 14	99.96 56	98.43 157	97.27 47	99.80 28	99.94 5	96.71 29	100.00 1	100.00 1	100.00 1	100.00 1

OPU-MVS				99.93 2	99.89 51	99.80 2	99.96 56				99.80 59	97.44 15	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 66	98.79 43	99.96 56	98.40 179	97.66 33

test0726					99.93 29	99.29 17	99.96 56	98.42 169	97.28 45	99.86 16	99.94 5	97.22 21

DPM-MVS		98.83 24	98.46 36	99.97 1	99.33 111	99.92 1	99.96 56	98.44 149	97.96 23	99.55 72	99.94 5	97.18 23	100.00 1	93.81 288	99.94 59	99.98 57

TEST9					99.92 37	98.92 32	99.96 56	98.43 157	93.90 186	99.71 49	99.86 34	95.88 46	99.85 131

train_agg		98.88 23	98.65 27	99.59 27	99.92 37	98.92 32	99.96 56	98.43 157	94.35 158	99.71 49	99.86 34	95.94 43	99.85 131	99.69 51	99.98 32	99.99 26

test_8					99.92 37	98.88 35	99.96 56	98.43 157	94.35 158	99.69 51	99.85 38	95.94 43	99.85 131

region2R		98.54 41	98.37 43	99.05 83	99.96 9	97.18 126	99.96 56	98.55 120	94.87 132	99.45 82	99.85 38	94.07 102	100.00 1	98.67 113	100.00 1	99.98 57

test-LLR		96.47 180	96.04 178	97.78 188	97.02 314	95.44 209	99.96 56	98.21 219	94.07 174	95.55 271	96.38 359	93.90 107	98.27 317	90.42 350	98.83 162	99.64 139

TESTMET0.1,1		96.74 164	96.26 166	98.16 156	97.36 287	96.48 162	99.96 56	98.29 205	91.93 287	95.77 265	98.07 300	95.54 51	98.29 312	90.55 347	98.89 157	99.70 125

test-mter		96.39 186	95.93 191	97.78 188	97.02 314	95.44 209	99.96 56	98.21 219	91.81 293	95.55 271	96.38 359	95.17 60	98.27 317	90.42 350	98.83 162	99.64 139

CPTT-MVS		97.64 111	97.32 115	98.58 122	99.97 3	95.77 193	99.96 56	98.35 192	89.90 358	98.36 159	99.79 63	91.18 183	99.99 40	98.37 133	99.99 21	99.99 26

cascas		94.64 263	93.61 277	97.74 194	97.82 235	96.26 172	99.96 56	97.78 273	85.76 426	94.00 300	97.54 317	76.95 394	99.21 200	97.23 191	95.43 290	97.76 318

DeepPCF-MVS	95.94 2	97.71 108	98.98 13	93.92 381	99.63 91	81.76 476	99.96 56	98.56 114	99.47 1	99.19 105	99.99 1	94.16 100	100.00 1	99.92 17	99.93 65	100.00 1

aaEdge-Enhanced		99.07 11	98.89 17	99.59 27	99.93 29	98.79 43	99.95 75	98.80 71	95.89 104	99.28 100	99.93 12	96.28 39	99.98 52	99.98 9	99.96 48	99.99 26

GDP-MVS		97.88 86	97.59 100	98.75 106	97.59 262	97.81 97	99.95 75	97.37 323	94.44 152	99.08 111	99.58 128	97.13 25	99.08 211	94.99 254	98.17 183	99.37 205

test_fmvsmvis_n_1920		97.67 110	97.59 100	97.91 177	97.02 314	95.34 217	99.95 75	98.45 144	97.87 26	97.02 213	99.59 125	89.64 208	99.98 52	99.41 69	99.34 138	98.42 297

patch_mono-2		98.24 69	99.12 5	95.59 308	99.67 89	86.91 440	99.95 75	98.89 52	97.60 34	99.90 7	99.76 73	96.54 34	99.98 52	99.94 15	99.82 85	99.88 98

DVP-MVS++		99.26 6	99.09 10	99.77 9	99.91 45	99.31 12	99.95 75	98.43 157	96.48 80	99.80 28	99.93 12	97.44 15	100.00 1	99.92 17	99.98 32	100.00 1

FOURS1					99.92 37	97.66 106	99.95 75	98.36 190	95.58 113	99.52 77

DVP-MVS		99.30 4	99.16 3	99.73 13	99.93 29	99.29 17	99.95 75	98.32 199	97.28 45	99.83 24	99.91 19	97.22 21	100.00 1	99.99 5	100.00 1	99.89 97
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				99.82 8	99.94 18	99.47 8	99.95 75	98.43 157					100.00 1	99.99 5	100.00 1	100.00 1

MSP-MVS		99.09 10	99.12 5	98.98 92	99.93 29	97.24 123	99.95 75	98.42 169	97.50 38	99.52 77	99.88 29	97.43 17	99.71 161	99.50 62	99.98 32	100.00 1
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
HFP-MVS		98.56 39	98.37 43	99.14 73	99.96 9	97.43 116	99.95 75	98.61 100	94.77 135	99.31 96	99.85 38	94.22 96	100.00 1	98.70 111	99.98 32	99.98 57

HPM-MVS++		99.07 11	98.88 18	99.63 19	99.90 48	99.02 28	99.95 75	98.56 114	97.56 37	99.44 83	99.85 38	95.38 57	100.00 1	99.31 72	99.99 21	99.87 100

test_prior2							99.95 75		95.78 106	99.73 47	99.76 73	96.00 42		99.78 36	100.00 1

ACMMPR		98.50 44	98.32 47	99.05 83	99.96 9	97.18 126	99.95 75	98.60 102	94.77 135	99.31 96	99.84 49	93.73 112	100.00 1	98.70 111	99.98 32	99.98 57

MP-MVS		98.23 71	97.97 72	99.03 85	99.94 18	97.17 130	99.95 75	98.39 182	94.70 139	98.26 165	99.81 58	91.84 174	100.00 1	98.85 102	99.97 44	99.93 88
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		98.39 56	98.20 54	98.97 93	99.97 3	96.92 141	99.95 75	98.38 186	95.04 125	98.61 143	99.80 59	93.39 119	100.00 1	98.64 116	100.00 1	99.98 57

PVSNet_BlendedMVS		96.05 205	95.82 197	96.72 269	99.59 93	96.99 138	99.95 75	99.10 34	94.06 176	98.27 163	95.80 377	89.00 221	99.95 86	99.12 80	87.53 366	93.24 439

PAPR		98.52 43	98.16 58	99.58 29	99.97 3	98.77 48	99.95 75	98.43 157	95.35 119	98.03 174	99.75 81	94.03 103	99.98 52	98.11 149	99.83 81	99.99 26

PVSNet	91.05 13	97.13 136	96.69 146	98.45 138	99.52 100	95.81 191	99.95 75	99.65 12	94.73 137	99.04 116	99.21 179	84.48 305	99.95 86	94.92 257	98.74 166	99.58 161

test_fmvsmconf0.1_n		97.74 103	97.44 108	98.64 115	95.76 368	96.20 178	99.94 93	98.05 242	98.17 13	98.89 124	99.42 142	87.65 237	99.90 114	99.50 62	99.60 108	99.82 107

ZNCC-MVS		98.31 60	98.03 67	99.17 66	99.88 55	97.59 107	99.94 93	98.44 149	94.31 161	98.50 151	99.82 54	93.06 134	99.99 40	98.30 138	99.99 21	99.93 88

test_prior4						98.05 83	99.94 93

XVS		98.70 32	98.55 31	99.15 71	99.94 18	97.50 112	99.94 93	98.42 169	96.22 93	99.41 88	99.78 67	94.34 90	99.96 77	98.92 96	99.95 54	99.99 26

X-MVStestdata		93.83 292	92.06 327	99.15 71	99.94 18	97.50 112	99.94 93	98.42 169	96.22 93	99.41 88	41.37 554	94.34 90	99.96 77	98.92 96	99.95 54	99.99 26

SD-MVS		98.92 21	98.70 23	99.56 30	99.70 86	98.73 52	99.94 93	98.34 196	96.38 86	99.81 26	99.76 73	94.59 78	99.98 52	99.84 30	99.96 48	99.97 67
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
PVSNet_0	88.03 19	91.80 347	90.27 361	96.38 283	98.27 205	90.46 389	99.94 93	99.61 13	93.99 179	86.26 428	97.39 323	71.13 438	99.89 119	98.77 107	67.05 488	98.79 282

GST-MVS		98.27 63	97.97 72	99.17 66	99.92 37	97.57 108	99.93 100	98.39 182	94.04 178	98.80 128	99.74 88	92.98 136	100.00 1	98.16 146	99.76 89	99.93 88

test0.0.03 1		93.86 291	93.61 277	94.64 341	95.02 393	92.18 337	99.93 100	98.58 106	94.07 174	87.96 402	98.50 276	93.90 107	94.96 465	81.33 446	93.17 321	96.78 334

MVS_111021_HR		98.72 31	98.62 29	99.01 89	99.36 109	97.18 126	99.93 100	99.90 1	96.81 69	98.67 138	99.77 71	93.92 105	99.89 119	99.27 75	99.94 59	99.96 75

myMVS_eth3d28		97.86 88	97.59 100	98.68 110	98.50 185	97.26 122	99.92 103	98.55 120	93.79 189	98.26 165	98.75 247	95.20 59	99.48 187	98.93 94	96.40 254	99.29 226

fmvsm_s_conf0.1_n_2		97.25 129	96.85 136	98.43 140	98.08 219	98.08 80	99.92 103	97.76 277	98.05 20	99.65 55	99.58 128	80.88 350	99.93 105	99.59 57	98.17 183	97.29 330

WBMVS		94.52 268	94.03 266	95.98 293	98.38 192	96.68 153	99.92 103	97.63 287	90.75 336	89.64 359	95.25 411	96.77 27	96.90 393	94.35 274	83.57 396	94.35 363

testing11		97.48 117	97.27 117	98.10 162	98.36 195	96.02 185	99.92 103	98.45 144	93.45 205	98.15 171	98.70 253	95.48 55	99.22 199	97.85 166	95.05 297	99.07 256

thisisatest0530		97.10 138	96.72 144	98.22 153	97.60 261	96.70 150	99.92 103	98.54 124	91.11 320	97.07 212	98.97 213	97.47 13	99.03 213	93.73 293	96.09 262	98.92 273

PVSNet_Blended_VisFu		97.27 128	96.81 139	98.66 113	98.81 158	96.67 154	99.92 103	98.64 91	94.51 145	96.38 247	98.49 277	89.05 219	99.88 125	97.10 196	98.34 176	99.43 196

DP-MVS Recon		98.41 53	98.02 68	99.56 30	99.97 3	98.70 54	99.92 103	98.44 149	92.06 284	98.40 158	99.84 49	95.68 49	100.00 1	98.19 144	99.71 92	99.97 67

PLC	95.54 3	97.93 83	97.89 82	98.05 166	99.82 66	94.77 247	99.92 103	98.46 143	93.93 183	97.20 206	99.27 166	95.44 56	99.97 65	97.41 183	99.51 118	99.41 200
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
testing91		97.16 134	96.90 133	97.97 169	98.35 197	95.67 201	99.91 111	98.42 169	92.91 233	97.33 202	98.72 250	94.81 73	99.21 200	96.98 201	94.63 300	99.03 264

testing99		97.17 133	96.91 132	97.95 171	98.35 197	95.70 198	99.91 111	98.43 157	92.94 231	97.36 200	98.72 250	94.83 72	99.21 200	97.00 199	94.64 299	98.95 269

9.14			98.38 41		99.87 57		99.91 111	98.33 197	93.22 215	99.78 39	99.89 27	94.57 81	99.85 131	99.84 30	99.97 44

APDe-MVS		99.06 13	98.91 15	99.51 34	99.94 18	98.76 51	99.91 111	98.39 182	97.20 51	99.46 81	99.85 38	95.53 53	99.79 146	99.86 28	100.00 1	99.99 26
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVSTER		95.53 233	95.22 227	96.45 279	98.56 175	97.72 100	99.91 111	97.67 283	92.38 271	91.39 328	97.14 328	97.24 20	97.30 364	94.80 262	87.85 359	94.34 365

PMMVS		96.76 159	96.76 141	96.76 267	98.28 204	92.10 338	99.91 111	97.98 249	94.12 171	99.53 75	99.39 150	86.93 253	98.73 254	96.95 204	97.73 196	99.45 192

PRO-TEST		97.72 106	97.51 103	98.33 146	98.30 200	97.18 126	99.90 117	97.46 311	95.98 101	99.62 62	99.42 142	88.95 223	98.28 314	99.12 80	98.88 160	99.52 174

AstraMVS		96.57 175	96.46 157	96.91 260	96.79 338	92.50 329	99.90 117	97.38 320	96.02 99	97.79 188	99.32 155	86.36 263	98.99 215	98.26 141	96.33 257	99.23 238

UBG		97.84 91	97.69 93	98.29 150	98.38 192	96.59 160	99.90 117	98.53 127	93.91 185	98.52 148	98.42 284	96.77 27	99.17 206	98.54 121	96.20 259	99.11 251

fmvsm_s_conf0.1_n		97.30 126	97.21 120	97.60 209	97.38 282	94.40 264	99.90 117	98.64 91	96.47 82	99.51 79	99.65 118	84.99 291	99.93 105	99.22 77	99.09 150	98.46 294

test_fmvs1_n		94.25 280	94.36 254	93.92 381	97.68 251	83.70 459	99.90 117	96.57 437	97.40 40	99.67 53	98.88 228	61.82 475	99.92 111	98.23 143	99.13 147	98.14 307

SF-MVS		98.67 33	98.40 39	99.50 35	99.77 73	98.67 55	99.90 117	98.21 219	93.53 198	99.81 26	99.89 27	94.70 77	99.86 130	99.84 30	99.93 65	99.96 75

原ACMM2							99.90 117

HPM-MVS		97.96 80	97.72 90	98.68 110	99.84 64	96.39 168	99.90 117	98.17 224	92.61 253	98.62 142	99.57 131	91.87 173	99.67 169	98.87 101	99.99 21	99.99 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EPNet		98.49 45	98.40 39	98.77 105	99.62 92	96.80 149	99.90 117	99.51 16	97.60 34	99.20 103	99.36 153	93.71 113	99.91 112	97.99 157	98.71 167	99.61 152
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CSCG		97.10 138	97.04 127	97.27 245	99.89 51	91.92 343	99.90 117	99.07 37	88.67 382	95.26 279	99.82 54	93.17 132	99.98 52	98.15 147	99.47 125	99.90 96

PAPM		98.60 37	98.42 38	99.14 73	96.05 357	98.96 29	99.90 117	99.35 24	96.68 73	98.35 160	99.66 116	96.45 35	98.51 284	99.45 66	99.89 74	99.96 75

ETVMVS		97.03 144	96.64 147	98.20 154	98.67 167	97.12 131	99.89 128	98.57 108	91.10 321	98.17 170	98.59 266	93.86 109	98.19 322	95.64 244	95.24 295	99.28 228

114514_t		97.41 123	96.83 137	99.14 73	99.51 102	97.83 95	99.89 128	98.27 208	88.48 387	99.06 115	99.66 116	90.30 201	99.64 174	96.32 230	99.97 44	99.96 75

WTY-MVS		98.10 76	97.60 98	99.60 24	98.92 147	99.28 19	99.89 128	99.52 14	95.58 113	98.24 167	99.39 150	93.33 122	99.74 157	97.98 159	95.58 286	99.78 115

GA-MVS		93.83 292	92.84 307	96.80 265	95.73 371	93.57 298	99.88 131	97.24 354	92.57 259	92.92 312	96.66 351	78.73 375	97.67 348	87.75 392	94.06 311	99.17 243

UniMVSNet (Re)		93.07 316	92.13 324	95.88 299	94.84 394	96.24 177	99.88 131	98.98 41	92.49 266	89.25 369	95.40 399	87.09 249	97.14 373	93.13 305	78.16 439	94.26 368

HPM-MVS_fast		97.80 97	97.50 104	98.68 110	99.79 70	96.42 164	99.88 131	98.16 229	91.75 296	98.94 121	99.54 134	91.82 175	99.65 173	97.62 180	99.99 21	99.99 26

FBQ-MVS		97.12 137	96.92 131	97.72 195	98.35 197	94.55 253	99.87 134	98.62 98	93.23 214	98.60 146	98.39 286	93.66 114	98.96 220	95.76 242	95.82 273	99.64 139

test_vis1_n		93.61 303	93.03 303	95.35 317	95.86 363	86.94 438	99.87 134	96.36 444	96.85 64	99.54 74	98.79 245	52.41 491	99.83 141	98.64 116	98.97 155	99.29 226

test_vis1_rt		86.87 420	86.05 417	89.34 450	96.12 354	78.07 488	99.87 134	83.54 522	92.03 285	78.21 477	89.51 488	45.80 499	99.91 112	96.25 231	93.11 323	90.03 484

DPE-MVS		99.26 6	99.10 9	99.74 12	99.89 51	99.24 21	99.87 134	98.44 149	97.48 39	99.64 58	99.94 5	96.68 31	99.99 40	99.99 5	100.00 1	99.99 26
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MTMP							99.87 134	96.49 441

CDPH-MVS		98.65 35	98.36 45	99.49 37	99.94 18	98.73 52	99.87 134	98.33 197	93.97 180	99.76 41	99.87 32	94.99 69	99.75 155	98.55 120	100.00 1	99.98 57

HQP-NCC					95.78 364		99.87 134		96.82 66	93.37 305

ACMP_Plane					95.78 364		99.87 134		96.82 66	93.37 305

APD-MVS		98.62 36	98.35 46	99.41 44	99.90 48	98.51 65	99.87 134	98.36 190	94.08 173	99.74 45	99.73 92	94.08 101	99.74 157	99.42 68	99.99 21	99.99 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
MVS_111021_LR		98.42 52	98.38 41	98.53 130	99.39 107	95.79 192	99.87 134	99.86 2	96.70 72	98.78 129	99.79 63	92.03 170	99.90 114	99.17 79	99.86 79	99.88 98

HQP-MVS		94.61 264	94.50 251	94.92 331	95.78 364	91.85 346	99.87 134	97.89 259	96.82 66	93.37 305	98.65 258	80.65 355	98.39 298	97.92 161	89.60 332	94.53 347

CNLPA		97.76 101	97.38 111	98.92 97	99.53 99	96.84 143	99.87 134	98.14 233	93.78 190	96.55 235	99.69 105	92.28 161	99.98 52	97.13 194	99.44 129	99.93 88

SMA-MVS		98.76 29	98.48 35	99.62 22	99.87 57	98.87 36	99.86 146	98.38 186	93.19 217	99.77 40	99.94 5	95.54 51	100.00 1	99.74 44	99.99 21	100.00 1
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
plane_prior						91.74 353	99.86 146		96.76 70						89.59 334

casdiffmvs_mvg		96.43 183	95.94 190	97.89 179	97.44 275	95.47 207	99.86 146	97.29 345	93.35 209	96.03 257	99.19 182	85.39 283	98.72 257	97.89 165	97.04 232	99.49 183
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
testing222		97.08 143	96.75 142	98.06 165	98.56 175	96.82 144	99.85 149	98.61 100	92.53 263	98.84 125	98.84 241	93.36 120	98.30 311	95.84 239	94.30 307	99.05 259

tttt0517		96.85 153	96.49 154	97.92 175	97.48 272	95.89 189	99.85 149	98.54 124	90.72 337	96.63 229	98.93 225	97.47 13	99.02 214	93.03 307	95.76 276	98.85 278

ACMMP_NAP		98.49 45	98.14 59	99.54 32	99.66 90	98.62 61	99.85 149	98.37 189	94.68 140	99.53 75	99.83 51	92.87 139	100.00 1	98.66 115	99.84 80	99.99 26

thres200		96.96 147	96.21 170	99.22 59	98.97 140	98.84 39	99.85 149	99.71 7	93.17 219	96.26 249	98.88 228	89.87 206	99.51 179	94.26 276	94.91 298	99.31 221

F-COLMAP		96.93 150	96.95 130	96.87 263	99.71 84	91.74 353	99.85 149	97.95 252	93.11 225	95.72 268	99.16 187	92.35 159	99.94 95	95.32 247	99.35 137	98.92 273

hybridcas		96.09 204	95.62 206	97.50 221	97.37 284	94.44 258	99.84 154	97.16 366	93.16 220	96.03 257	99.21 179	84.19 308	98.65 271	96.53 224	97.07 228	99.42 199

test_fmvsmconf0.01_n		96.39 186	95.74 200	98.32 148	91.47 462	95.56 205	99.84 154	97.30 337	97.74 30	97.89 181	99.35 154	79.62 365	99.85 131	99.25 76	99.24 142	99.55 165

SR-MVS		98.46 47	98.30 50	98.93 96	99.88 55	97.04 136	99.84 154	98.35 192	94.92 129	99.32 95	99.80 59	93.35 121	99.78 148	99.30 73	99.95 54	99.96 75

CANet_DTU		96.76 159	96.15 173	98.60 118	98.78 160	97.53 109	99.84 154	97.63 287	97.25 50	99.20 103	99.64 119	81.36 342	99.98 52	92.77 310	98.89 157	98.28 302

casdiffmvs		96.42 185	95.97 185	97.77 190	97.30 294	94.98 236	99.84 154	97.09 386	93.75 193	96.58 232	99.26 170	85.07 288	98.78 247	97.77 174	97.04 232	99.54 169
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HQP_MVS		94.49 271	94.36 254	94.87 332	95.71 374	91.74 353	99.84 154	97.87 261	96.38 86	93.01 310	98.59 266	80.47 359	98.37 304	97.79 172	89.55 335	94.52 349

plane_prior2							99.84 154		96.38 86

BH-w/o		95.71 226	95.38 221	96.68 270	98.49 187	92.28 334	99.84 154	97.50 308	92.12 281	92.06 324	98.79 245	84.69 300	98.67 266	95.29 248	99.66 96	99.09 253

onestephybrid01		96.75 161	96.44 158	97.71 196	97.47 273	95.03 235	99.83 162	97.27 347	94.15 169	98.66 139	99.25 173	85.72 273	98.81 238	98.42 129	97.17 222	99.28 228

viewmamba		96.61 171	96.34 163	97.42 231	97.26 299	94.37 266	99.83 162	97.16 366	94.51 145	97.89 181	99.26 170	86.38 261	98.66 269	97.70 177	97.06 231	99.23 238

usedtu_dtu_shiyan1		92.78 322	91.73 333	95.92 297	93.03 431	96.82 144	99.83 162	97.79 269	90.58 338	90.09 342	95.04 418	84.75 295	96.72 407	88.19 385	86.23 373	94.23 372

FE-MVSNET3		92.78 322	91.73 333	95.92 297	93.03 431	96.82 144	99.83 162	97.79 269	90.58 338	90.09 342	95.04 418	84.75 295	96.72 407	88.20 384	86.23 373	94.23 372

fmvsm_s_conf0.1_n_a		97.09 140	96.90 133	97.63 206	95.65 378	94.21 274	99.83 162	98.50 138	96.27 92	99.65 55	99.64 119	84.72 299	99.93 105	99.04 87	98.84 161	98.74 285

test_fmvs2		89.47 397	89.70 372	88.77 457	94.54 400	75.74 492	99.83 162	94.70 484	94.71 138	91.08 331	96.82 349	54.46 487	97.78 345	92.87 308	88.27 354	92.80 449

UniMVSNet_NR-MVSNet		92.95 318	92.11 325	95.49 309	94.61 399	95.28 224	99.83 162	99.08 36	91.49 303	89.21 372	96.86 344	87.14 248	96.73 405	93.20 301	77.52 444	94.46 352

APD-MVS_3200maxsize		98.25 68	98.08 64	98.78 103	99.81 68	96.60 158	99.82 169	98.30 204	93.95 182	99.37 93	99.77 71	92.84 140	99.76 154	98.95 92	99.92 68	99.97 67

PAPM_NR		98.12 75	97.93 78	98.70 109	99.94 18	96.13 182	99.82 169	98.43 157	94.56 143	97.52 193	99.70 101	94.40 85	99.98 52	97.00 199	99.98 32	99.99 26

hybridnocas07		96.57 175	96.16 172	97.81 183	97.36 287	95.32 219	99.81 171	97.12 375	94.17 168	98.02 175	98.90 226	85.05 289	98.80 243	97.85 166	97.18 218	99.32 216

gbinet_0.2-2-1-0.02		87.63 417	85.51 424	93.99 378	87.22 487	91.56 368	99.81 171	97.36 324	79.54 472	88.60 386	93.29 457	73.76 424	96.34 430	89.27 367	60.78 507	94.06 401

nrg030		93.51 305	92.53 319	96.45 279	94.36 404	97.20 125	99.81 171	97.16 366	91.60 300	89.86 351	97.46 319	86.37 262	97.68 347	95.88 238	80.31 427	94.46 352

diffmvs		97.00 145	96.64 147	98.09 163	97.64 256	96.17 181	99.81 171	97.19 360	94.67 141	98.95 120	99.28 162	86.43 260	98.76 250	98.37 133	97.42 205	99.33 214
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DU-MVS		92.46 333	91.45 342	95.49 309	94.05 410	95.28 224	99.81 171	98.74 76	92.25 279	89.21 372	96.64 353	81.66 338	96.73 405	93.20 301	77.52 444	94.46 352

ACMP	92.05 9	92.74 325	92.42 322	93.73 386	95.91 362	88.72 418	99.81 171	97.53 304	94.13 170	87.00 416	98.23 295	74.07 422	98.47 285	96.22 232	88.86 344	93.99 408
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
Casviewmamba		96.25 197	95.89 194	97.32 244	97.45 274	93.68 292	99.80 177	97.22 358	93.38 207	96.86 220	99.28 162	84.64 301	98.87 227	97.18 193	97.19 217	99.41 200

hybrid		96.53 178	96.15 173	97.67 199	97.39 281	95.12 233	99.80 177	97.15 369	93.38 207	98.23 168	99.16 187	85.20 286	98.70 261	97.92 161	97.15 223	99.20 241

E3new		96.75 161	96.43 159	97.71 196	97.79 237	94.83 243	99.80 177	97.33 329	93.52 201	97.49 196	99.31 158	87.73 235	98.83 231	97.52 181	97.40 207	99.48 184

mvsany_test1		97.82 95	97.90 80	97.55 214	98.77 161	93.04 314	99.80 177	97.93 254	96.95 61	99.61 70	99.68 112	90.92 188	99.83 141	99.18 78	98.29 181	99.80 111

Fast-Effi-MVS+-dtu		93.72 300	93.86 273	93.29 399	97.06 309	86.16 443	99.80 177	96.83 423	92.66 250	92.58 317	97.83 313	81.39 341	97.67 348	89.75 360	96.87 240	96.05 344

BH-untuned		95.18 242	94.83 242	96.22 287	98.36 195	91.22 372	99.80 177	97.32 335	90.91 325	91.08 331	98.67 255	83.51 315	98.54 283	94.23 277	99.61 105	98.92 273

dtuplus		95.79 221	95.42 213	96.93 259	97.24 300	93.16 309	99.78 183	96.93 415	91.69 298	96.18 254	99.29 161	83.80 313	98.73 254	96.83 210	97.02 235	98.89 277

viewdifsd2359ckpt09		96.21 200	95.77 198	97.53 216	97.69 250	94.50 257	99.78 183	97.23 356	92.88 234	96.58 232	99.26 170	84.85 293	98.66 269	96.61 220	97.02 235	99.43 196

viewmambaseed2359dif		95.92 212	95.55 209	97.04 255	97.38 282	93.41 304	99.78 183	96.97 408	91.14 319	96.58 232	99.27 166	84.85 293	98.75 252	96.87 208	97.12 226	98.97 268

tfpn200view9		96.79 156	95.99 180	99.19 62	98.94 142	98.82 40	99.78 183	99.71 7	92.86 235	96.02 259	98.87 235	89.33 213	99.50 181	93.84 285	94.57 302	99.27 231

thres400		96.78 158	95.99 180	99.16 69	98.94 142	98.82 40	99.78 183	99.71 7	92.86 235	96.02 259	98.87 235	89.33 213	99.50 181	93.84 285	94.57 302	99.16 244

TAPA-MVS	92.12 8	94.42 273	93.60 279	96.90 262	99.33 111	91.78 352	99.78 183	98.00 246	89.89 359	94.52 288	99.47 138	91.97 171	99.18 205	69.90 488	99.52 115	99.73 120
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
viewcassd2359sk11		96.59 173	96.23 167	97.66 201	97.63 258	94.70 248	99.77 189	97.33 329	93.41 206	97.34 201	99.17 184	86.72 254	98.83 231	97.40 184	97.32 211	99.46 187

TSAR-MVS + MP.		98.93 20	98.77 22	99.41 44	99.74 78	98.67 55	99.77 189	98.38 186	96.73 71	99.88 13	99.74 88	94.89 71	99.59 175	99.80 33	99.98 32	99.97 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
OPM-MVS		93.21 310	92.80 309	94.44 354	93.12 427	90.85 380	99.77 189	97.61 293	96.19 95	91.56 327	98.65 258	75.16 416	98.47 285	93.78 291	89.39 338	93.99 408
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
v2v482		91.30 354	90.07 368	95.01 327	93.13 425	93.79 286	99.77 189	97.02 400	88.05 395	89.25 369	95.37 403	80.73 353	97.15 372	87.28 399	80.04 430	94.09 398

Baseline_NR-MVSNet		90.33 378	89.51 378	92.81 412	92.84 438	89.95 401	99.77 189	93.94 493	84.69 441	89.04 376	95.66 384	81.66 338	96.52 416	90.99 337	76.98 450	91.97 464

ACMM	91.95 10	92.88 320	92.52 320	93.98 380	95.75 370	89.08 413	99.77 189	97.52 306	93.00 229	89.95 348	97.99 304	76.17 405	98.46 288	93.63 296	88.87 343	94.39 359
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
nomal-1		96.23 199	96.10 175	96.64 273	97.64 256	92.37 333	99.76 195	98.09 236	91.73 297	94.59 286	97.47 318	93.31 125	98.45 289	96.77 215	95.52 287	99.10 252

wanda-best-256-512		87.82 413	85.71 420	94.15 366	86.66 492	91.88 344	99.76 195	97.08 387	79.46 473	88.37 395	92.36 468	78.01 381	96.43 423	88.39 380	61.26 502	94.14 390

FE-blended-shiyan7		87.82 413	85.71 420	94.15 366	86.66 492	91.88 344	99.76 195	97.08 387	79.46 473	88.37 395	92.36 468	78.01 381	96.43 423	88.39 380	61.26 502	94.14 390

reproduce_monomvs		95.38 237	95.07 234	96.32 285	99.32 113	96.60 158	99.76 195	98.85 62	96.65 74	87.83 404	96.05 374	99.52 1	98.11 326	96.58 222	81.07 419	94.25 370

SR-MVS-dyc-post		98.31 60	98.17 57	98.71 108	99.79 70	96.37 169	99.76 195	98.31 201	94.43 153	99.40 90	99.75 81	93.28 127	99.78 148	98.90 99	99.92 68	99.97 67

RE-MVS-def			98.13 60		99.79 70	96.37 169	99.76 195	98.31 201	94.43 153	99.40 90	99.75 81	92.95 137		98.90 99	99.92 68	99.97 67

BH-RMVSNet		95.18 242	94.31 257	97.80 184	98.17 213	95.23 227	99.76 195	97.53 304	92.52 264	94.27 297	99.25 173	76.84 395	98.80 243	90.89 341	99.54 112	99.35 211

blend_shiyan4		90.13 386	88.79 391	94.17 363	87.12 488	91.83 348	99.75 202	97.08 387	79.27 477	88.69 382	92.53 463	92.25 163	96.50 417	89.35 364	73.04 466	94.18 379

v148		90.70 368	89.63 373	93.92 381	92.97 434	90.97 374	99.75 202	96.89 419	87.51 401	88.27 398	95.01 421	81.67 337	97.04 383	87.40 396	77.17 449	93.75 424

PGM-MVS		98.34 58	98.13 60	98.99 90	99.92 37	97.00 137	99.75 202	99.50 17	93.90 186	99.37 93	99.76 73	93.24 129	100.00 1	97.75 176	99.96 48	99.98 57

LPG-MVS_test		92.96 317	92.71 312	93.71 388	95.43 385	88.67 419	99.75 202	97.62 290	92.81 238	90.05 344	98.49 277	75.24 412	98.40 296	95.84 239	89.12 339	94.07 399

reproduce-ours		98.78 27	98.67 24	99.09 80	99.70 86	97.30 120	99.74 206	98.25 210	97.10 53	99.10 109	99.90 23	94.59 78	99.99 40	99.77 38	99.91 71	99.99 26

our_new_method		98.78 27	98.67 24	99.09 80	99.70 86	97.30 120	99.74 206	98.25 210	97.10 53	99.10 109	99.90 23	94.59 78	99.99 40	99.77 38	99.91 71	99.99 26

thres100view900		96.74 164	95.92 192	99.18 63	98.90 152	98.77 48	99.74 206	99.71 7	92.59 255	95.84 262	98.86 237	89.25 215	99.50 181	93.84 285	94.57 302	99.27 231

MP-MVS-pluss		98.07 78	97.64 96	99.38 49	99.74 78	98.41 70	99.74 206	98.18 223	93.35 209	96.45 239	99.85 38	92.64 148	99.97 65	98.91 98	99.89 74	99.77 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
pmmvs5		90.17 384	89.09 385	93.40 396	92.10 453	89.77 404	99.74 206	95.58 463	85.88 425	87.24 415	95.74 379	73.41 428	96.48 420	88.54 375	83.56 397	93.95 411

thres600view7		96.69 167	95.87 196	99.14 73	98.90 152	98.78 47	99.74 206	99.71 7	92.59 255	95.84 262	98.86 237	89.25 215	99.50 181	93.44 298	94.50 305	99.16 244

baseline2		96.71 166	96.49 154	97.37 237	95.63 380	95.96 187	99.74 206	98.88 55	92.94 231	91.61 326	98.97 213	97.72 7	98.62 274	94.83 261	98.08 191	97.53 328

reproduce_model		98.75 30	98.66 26	99.03 85	99.71 84	97.10 134	99.73 213	98.23 214	97.02 58	99.18 106	99.90 23	94.54 82	99.99 40	99.77 38	99.90 73	99.99 26

miper_enhance_ethall		94.36 277	93.98 268	95.49 309	98.68 166	95.24 226	99.73 213	97.29 345	93.28 213	89.86 351	95.97 375	94.37 89	97.05 380	92.20 314	84.45 389	94.19 378

testgi		89.01 402	88.04 403	91.90 423	93.49 420	84.89 453	99.73 213	95.66 461	93.89 188	85.14 436	98.17 296	59.68 480	94.66 472	77.73 470	88.88 342	96.16 343

sss		97.57 114	97.03 128	99.18 63	98.37 194	98.04 84	99.73 213	99.38 22	93.46 203	98.76 134	99.06 196	91.21 179	99.89 119	96.33 229	97.01 237	99.62 148

blended_shiyan8		87.82 413	85.71 420	94.16 364	86.54 497	91.79 350	99.72 217	97.08 387	79.32 475	88.44 389	92.35 471	77.88 385	96.56 414	88.53 376	61.51 501	94.15 386

blended_shiyan6		87.74 416	85.62 423	94.09 371	86.53 498	91.73 356	99.72 217	97.08 387	79.32 475	88.22 399	92.31 473	77.82 386	96.43 423	88.31 382	61.26 502	94.13 395

sasdasda		97.09 140	96.32 164	99.39 46	98.93 144	98.95 30	99.72 217	97.35 325	94.45 149	97.88 183	99.42 142	86.71 255	99.52 177	98.48 125	93.97 312	99.72 122

canonicalmvs		97.09 140	96.32 164	99.39 46	98.93 144	98.95 30	99.72 217	97.35 325	94.45 149	97.88 183	99.42 142	86.71 255	99.52 177	98.48 125	93.97 312	99.72 122

3Dnovator+	91.53 11	96.31 192	95.24 226	99.52 33	96.88 331	98.64 60	99.72 217	98.24 212	95.27 122	88.42 394	98.98 211	82.76 327	99.94 95	97.10 196	99.83 81	99.96 75

E2		96.36 188	95.95 188	97.60 209	97.41 277	94.52 255	99.71 222	97.33 329	93.20 216	97.02 213	99.07 194	85.37 284	98.82 234	97.27 187	97.14 224	99.46 187

E3		96.36 188	95.95 188	97.60 209	97.37 284	94.52 255	99.71 222	97.33 329	93.18 218	97.02 213	99.07 194	85.45 282	98.82 234	97.27 187	97.14 224	99.46 187

guyue		97.15 135	96.82 138	98.15 159	97.56 264	96.25 176	99.71 222	97.84 266	95.75 108	98.13 172	98.65 258	87.58 239	98.82 234	98.29 139	97.91 195	99.36 207

UWE-MVS		96.79 156	96.72 144	97.00 256	98.51 183	93.70 290	99.71 222	98.60 102	92.96 230	97.09 210	98.34 289	96.67 33	98.85 230	92.11 320	96.50 251	98.44 296

WB-MVSnew		92.90 319	92.77 311	93.26 401	96.95 325	93.63 293	99.71 222	98.16 229	91.49 303	94.28 296	98.14 297	81.33 343	96.48 420	79.47 458	95.46 288	89.68 488

Syy-MVS		90.00 388	90.63 353	88.11 463	97.68 251	74.66 496	99.71 222	98.35 192	90.79 333	92.10 322	98.67 255	79.10 372	93.09 487	63.35 506	95.95 268	96.59 337

myMVS_eth3d		94.46 272	94.76 247	93.55 394	97.68 251	90.97 374	99.71 222	98.35 192	90.79 333	92.10 322	98.67 255	92.46 157	93.09 487	87.13 401	95.95 268	96.59 337

viewdifsd2359ckpt13		96.19 201	95.77 198	97.45 226	97.62 259	94.40 264	99.70 229	97.23 356	92.76 243	96.63 229	99.05 197	84.96 292	98.64 272	96.65 219	97.35 209	99.31 221

viewmanbaseed2359cas		96.45 182	96.07 176	97.59 212	97.55 265	94.59 251	99.70 229	97.33 329	93.62 197	97.00 216	99.32 155	85.57 278	98.71 258	97.26 190	97.33 210	99.47 185

HyFIR lowres test		96.66 169	96.43 159	97.36 239	99.05 130	93.91 285	99.70 229	99.80 3	90.54 341	96.26 249	98.08 299	92.15 167	98.23 320	96.84 209	95.46 288	99.93 88

diffmvs_AUTHOR		96.75 161	96.41 161	97.79 186	97.20 301	95.46 208	99.69 232	97.15 369	94.46 148	98.78 129	99.21 179	85.64 276	98.77 248	98.27 140	97.31 212	99.13 248

D2MVS		92.76 324	92.59 318	93.27 400	95.13 389	89.54 407	99.69 232	99.38 22	92.26 278	87.59 407	94.61 435	85.05 289	97.79 343	91.59 327	88.01 357	92.47 456

TranMVSNet+NR-MVSNet		91.68 351	90.61 354	94.87 332	93.69 417	93.98 283	99.69 232	98.65 88	91.03 323	88.44 389	96.83 348	80.05 363	96.18 438	90.26 354	76.89 452	94.45 357

V42		91.28 356	90.12 367	94.74 337	93.42 422	93.46 302	99.68 235	97.02 400	87.36 404	89.85 353	95.05 417	81.31 344	97.34 359	87.34 397	80.07 429	93.40 434

testmvs		40.60 505	44.45 506	29.05 534	19.49 564	14.11 566	99.68 235	18.47 562	20.74 539	64.59 503	98.48 280	10.95 544	17.09 560	56.66 521	11.01 556	55.94 536

MGCFI-Net		97.00 145	96.22 169	99.34 51	98.86 155	98.80 42	99.67 237	97.30 337	94.31 161	97.77 189	99.41 147	86.36 263	99.50 181	98.38 131	93.90 314	99.72 122

DeepC-MVS	94.51 4	96.92 151	96.40 162	98.45 138	99.16 123	95.90 188	99.66 238	98.06 240	96.37 89	94.37 294	99.49 137	83.29 323	99.90 114	97.63 179	99.61 105	99.55 165
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
CHOSEN 1792x2688		96.81 155	96.53 152	97.64 203	98.91 151	93.07 311	99.65 239	99.80 3	95.64 111	95.39 275	98.86 237	84.35 307	99.90 114	96.98 201	99.16 145	99.95 83

Test_1112_low_res		95.72 224	94.83 242	98.42 142	97.79 237	96.41 165	99.65 239	96.65 434	92.70 247	92.86 315	96.13 370	92.15 167	99.30 195	91.88 324	93.64 316	99.55 165

1112_ss		96.01 207	95.20 228	98.42 142	97.80 236	96.41 165	99.65 239	96.66 433	92.71 246	92.88 314	99.40 148	92.16 166	99.30 195	91.92 323	93.66 315	99.55 165

OMC-MVS		97.28 127	97.23 119	97.41 234	99.76 74	93.36 308	99.65 239	97.95 252	96.03 98	97.41 199	99.70 101	89.61 209	99.51 179	96.73 218	98.25 182	99.38 203

test_yl		97.83 92	97.37 112	99.21 60	99.18 120	97.98 87	99.64 243	99.27 27	91.43 308	97.88 183	98.99 209	95.84 47	99.84 139	98.82 103	95.32 293	99.79 112

DCV-MVSNet		97.83 92	97.37 112	99.21 60	99.18 120	97.98 87	99.64 243	99.27 27	91.43 308	97.88 183	98.99 209	95.84 47	99.84 139	98.82 103	95.32 293	99.79 112

MG-MVS		98.91 22	98.65 27	99.68 18	99.94 18	99.07 27	99.64 243	99.44 19	97.33 44	99.00 119	99.72 95	94.03 103	99.98 52	98.73 110	100.00 1	100.00 1

viewdifsd2359ckpt11		94.09 285	93.63 276	95.46 313	96.68 343	88.92 414	99.62 246	97.12 375	93.07 226	95.73 266	99.22 176	77.05 389	98.88 226	96.52 225	87.69 364	98.58 292

viewmsd2359difaftdt		94.09 285	93.64 275	95.46 313	96.68 343	88.92 414	99.62 246	97.13 374	93.07 226	95.73 266	99.22 176	77.05 389	98.89 225	96.52 225	87.70 363	98.58 292

v1144		91.09 360	89.83 369	94.87 332	93.25 424	93.69 291	99.62 246	96.98 406	86.83 414	89.64 359	94.99 424	80.94 348	97.05 380	85.08 421	81.16 415	93.87 418

mvsmamba		96.94 148	96.73 143	97.55 214	97.99 224	94.37 266	99.62 246	97.70 280	93.13 223	98.42 155	97.92 307	88.02 232	98.75 252	98.78 106	99.01 154	99.52 174

NormalMVS		97.90 85	97.85 85	98.04 167	99.86 59	95.39 214	99.61 250	97.78 273	96.52 78	98.61 143	99.31 158	92.73 144	99.67 169	96.77 215	99.48 122	99.06 257

SymmetryMVS		97.64 111	97.46 105	98.17 155	98.74 163	95.39 214	99.61 250	99.26 29	96.52 78	98.61 143	99.31 158	92.73 144	99.67 169	96.77 215	95.63 284	99.45 192

cl22		93.77 297	93.25 297	95.33 319	99.49 103	94.43 260	99.61 250	98.09 236	90.38 346	89.16 375	95.61 386	90.56 196	97.34 359	91.93 322	84.45 389	94.21 377

viewdifsd2359ckpt07		95.83 216	95.42 213	97.07 254	97.40 279	93.04 314	99.60 253	97.24 354	92.39 270	96.09 256	99.14 189	83.07 326	98.93 223	97.02 198	96.87 240	99.23 238

WR-MVS		92.31 336	91.25 344	95.48 312	94.45 402	95.29 223	99.60 253	98.68 84	90.10 353	88.07 401	96.89 342	80.68 354	96.80 402	93.14 304	79.67 431	94.36 360

SDMVSNet		94.80 254	93.96 269	97.33 242	98.92 147	95.42 211	99.59 255	98.99 40	92.41 268	92.55 318	97.85 311	75.81 408	98.93 223	97.90 164	91.62 327	97.64 321

Effi-MVS+-dtu		94.53 267	95.30 224	92.22 419	97.77 239	82.54 469	99.59 255	97.06 396	94.92 129	95.29 277	95.37 403	85.81 271	97.89 340	94.80 262	97.07 228	96.23 341

casdiffseed414692147		95.07 245	94.26 258	97.50 221	97.01 317	94.70 248	99.58 257	97.02 400	91.27 314	94.66 285	98.82 244	80.79 352	98.55 282	93.39 299	95.79 274	99.27 231

MVSMamba_PlusPlus		97.83 92	97.45 107	98.99 90	98.60 173	98.15 73	99.58 257	97.74 278	90.34 349	99.26 102	98.32 290	94.29 94	99.23 198	99.03 90	99.89 74	99.58 161

DIV-MVS_self_test		92.32 335	91.60 336	94.47 352	97.31 293	92.74 320	99.58 257	96.75 429	86.99 411	87.64 406	95.54 390	89.55 210	96.50 417	88.58 374	82.44 405	94.17 380

FIs		94.10 284	93.43 286	96.11 289	94.70 397	96.82 144	99.58 257	98.93 48	92.54 262	89.34 367	97.31 324	87.62 238	97.10 377	94.22 278	86.58 370	94.40 358

E4		96.01 207	95.53 210	97.44 229	97.05 310	94.23 272	99.57 261	97.30 337	92.72 244	96.47 238	99.03 199	83.98 312	98.83 231	96.92 205	96.77 243	99.27 231

viewmacassd2359aftdt		95.93 211	95.45 211	97.36 239	97.09 306	94.12 278	99.57 261	97.26 350	93.05 228	96.50 236	99.17 184	82.76 327	98.68 264	96.61 220	97.04 232	99.28 228

cl____		92.31 336	91.58 337	94.52 348	97.33 291	92.77 318	99.57 261	96.78 428	86.97 412	87.56 408	95.51 393	89.43 211	96.62 411	88.60 373	82.44 405	94.16 385

EPNet_dtu		95.71 226	95.39 216	96.66 271	98.92 147	93.41 304	99.57 261	98.90 50	96.19 95	97.52 193	98.56 271	92.65 147	97.36 357	77.89 469	98.33 177	99.20 241
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
KinetiMVS		96.10 202	95.29 225	98.53 130	97.08 307	97.12 131	99.56 265	98.12 235	94.78 134	98.44 153	98.94 222	80.30 361	99.39 192	91.56 328	98.79 164	99.06 257

v144192		90.79 367	89.52 377	94.59 344	93.11 428	92.77 318	99.56 265	96.99 404	86.38 419	89.82 354	94.95 426	80.50 358	97.10 377	83.98 428	80.41 425	93.90 415

OpenMVS	90.15 15	94.77 257	93.59 280	98.33 146	96.07 356	97.48 114	99.56 265	98.57 108	90.46 345	86.51 422	98.95 220	78.57 377	99.94 95	93.86 284	99.74 90	97.57 326

MVSFormer		96.94 148	96.60 149	97.95 171	97.28 296	97.70 103	99.55 268	97.27 347	91.17 316	99.43 85	99.54 134	90.92 188	96.89 394	94.67 267	99.62 100	99.25 235

test_djsdf		92.83 321	92.29 323	94.47 352	91.90 455	92.46 330	99.55 268	97.27 347	91.17 316	89.96 347	96.07 373	81.10 345	96.89 394	94.67 267	88.91 341	94.05 402

PS-MVSNAJ		98.44 49	98.20 54	99.16 69	98.80 159	98.92 32	99.54 270	98.17 224	97.34 42	99.85 20	99.85 38	91.20 180	99.89 119	99.41 69	99.67 95	98.69 288

CDS-MVSNet		96.34 190	96.07 176	97.13 251	97.37 284	94.96 237	99.53 271	97.91 258	91.55 302	95.37 276	98.32 290	95.05 65	97.13 374	93.80 289	95.75 277	99.30 224
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
xiu_mvs_v2_base		98.23 71	97.97 72	99.02 88	98.69 165	98.66 57	99.52 272	98.08 239	97.05 56	99.86 16	99.86 34	90.65 193	99.71 161	99.39 71	98.63 168	98.69 288

PatchMatch-RL		96.04 206	95.40 215	97.95 171	99.59 93	95.22 228	99.52 272	99.07 37	93.96 181	96.49 237	98.35 287	82.28 330	99.82 143	90.15 355	99.22 144	98.81 281

test_method		80.79 455	79.70 458	84.08 474	92.83 440	67.06 504	99.51 274	95.42 466	54.34 517	81.07 462	93.53 452	44.48 500	92.22 494	78.90 465	77.23 448	92.94 446

baseline		96.43 183	95.98 182	97.76 192	97.34 289	95.17 231	99.51 274	97.17 364	93.92 184	96.90 219	99.28 162	85.37 284	98.64 272	97.50 182	96.86 242	99.46 187

miper_ehance_all_eth		93.16 313	92.60 314	94.82 336	97.57 263	93.56 299	99.50 276	97.07 395	88.75 380	88.85 379	95.52 392	90.97 187	96.74 404	90.77 343	84.45 389	94.17 380

v1192		90.62 372	89.25 382	94.72 339	93.13 425	93.07 311	99.50 276	97.02 400	86.33 420	89.56 363	95.01 421	79.22 369	97.09 379	82.34 441	81.16 415	94.01 405

SSC-MVS3.2		89.59 395	88.66 395	92.38 416	94.29 407	86.12 444	99.49 278	97.66 286	90.28 352	88.63 385	95.18 413	64.46 465	96.88 396	85.30 419	82.66 402	94.14 390

v1921920		90.46 374	89.12 384	94.50 350	92.96 435	92.46 330	99.49 278	96.98 406	86.10 422	89.61 361	95.30 406	78.55 378	97.03 385	82.17 442	80.89 423	94.01 405

无先验							99.49 278	98.71 79	93.46 203				100.00 1	94.36 272		99.99 26

pmmvs4		92.10 340	91.07 348	95.18 323	92.82 441	94.96 237	99.48 281	96.83 423	87.45 403	88.66 384	96.56 357	83.78 314	96.83 400	89.29 366	84.77 387	93.75 424

dongtai		91.55 353	91.13 346	92.82 411	98.16 214	86.35 441	99.47 282	98.51 132	83.24 450	85.07 439	97.56 316	90.33 200	94.94 466	76.09 477	91.73 325	97.18 332

BridgeMVS		98.27 63	97.99 70	99.11 78	98.64 171	98.43 69	99.47 282	97.79 269	94.56 143	99.74 45	98.35 287	94.33 92	99.25 197	99.12 80	99.96 48	99.64 139

Vis-MVSNet (Re-imp)		96.32 191	95.98 182	97.35 241	97.93 228	94.82 244	99.47 282	98.15 232	91.83 291	95.09 280	99.11 190	91.37 178	97.47 355	93.47 297	97.43 203	99.74 119

API-MVS		97.86 88	97.66 94	98.47 135	99.52 100	95.41 212	99.47 282	98.87 58	91.68 299	98.84 125	99.85 38	92.34 160	99.99 40	98.44 128	99.96 48	100.00 1

旧先验2							99.46 286		94.21 167	99.85 20			99.95 86	96.96 203

IterMVS-LS		92.69 327	92.11 325	94.43 356	96.80 335	92.74 320	99.45 287	96.89 419	88.98 371	89.65 358	95.38 402	88.77 225	96.34 430	90.98 338	82.04 408	94.22 375
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
3Dnovator	91.47 12	96.28 195	95.34 222	99.08 82	96.82 334	97.47 115	99.45 287	98.81 67	95.52 116	89.39 365	99.00 206	81.97 333	99.95 86	97.27 187	99.83 81	99.84 104

FC-MVSNet-test		93.81 295	93.15 300	95.80 304	94.30 406	96.20 178	99.42 289	98.89 52	92.33 273	89.03 377	97.27 326	87.39 244	96.83 400	93.20 301	86.48 371	94.36 360

balanced_ft_v1		96.88 152	96.52 153	97.96 170	98.60 173	94.94 239	99.41 290	97.56 299	93.53 198	99.42 87	97.89 310	83.33 322	99.31 194	99.29 74	99.62 100	99.64 139

c3_l		92.53 331	91.87 331	94.52 348	97.40 279	92.99 316	99.40 291	96.93 415	87.86 398	88.69 382	95.44 397	89.95 205	96.44 422	90.45 349	80.69 424	94.14 390

EI-MVSNet-Vis-set		98.27 63	98.11 62	98.75 106	99.83 65	96.59 160	99.40 291	98.51 132	95.29 121	98.51 150	99.76 73	93.60 117	99.71 161	98.53 123	99.52 115	99.95 83

新几何2							99.40 291

QAPM		95.40 236	94.17 261	99.10 79	96.92 326	97.71 101	99.40 291	98.68 84	89.31 364	88.94 378	98.89 227	82.48 329	99.96 77	93.12 306	99.83 81	99.62 148

UWE-MVS-28		95.95 209	96.49 154	94.34 359	98.51 183	89.99 399	99.39 295	98.57 108	93.14 222	97.33 202	98.31 292	93.44 118	94.68 471	93.69 295	95.98 265	98.34 301

MTAPA		98.29 62	97.96 75	99.30 52	99.85 62	97.93 91	99.39 295	98.28 206	95.76 107	97.18 208	99.88 29	92.74 143	100.00 1	98.67 113	99.88 77	99.99 26

miper_lstm_enhance		91.81 344	91.39 343	93.06 407	97.34 289	89.18 411	99.38 297	96.79 427	86.70 416	87.47 410	95.22 412	90.00 204	95.86 449	88.26 383	81.37 413	94.15 386

v1240		90.20 382	88.79 391	94.44 354	93.05 430	92.27 335	99.38 297	96.92 417	85.89 424	89.36 366	94.87 428	77.89 384	97.03 385	80.66 451	81.08 418	94.01 405

EPP-MVSNet		96.69 167	96.60 149	96.96 258	97.74 241	93.05 313	99.37 299	98.56 114	88.75 380	95.83 264	99.01 202	96.01 41	98.56 279	96.92 205	97.20 216	99.25 235

MSDG		94.37 275	93.36 294	97.40 235	98.88 154	93.95 284	99.37 299	97.38 320	85.75 428	90.80 337	99.17 184	84.11 311	99.88 125	86.35 409	98.43 175	98.36 300

EI-MVSNet-UG-set		98.14 74	97.99 70	98.60 118	99.80 69	96.27 171	99.36 301	98.50 138	95.21 123	98.30 162	99.75 81	93.29 126	99.73 160	98.37 133	99.30 139	99.81 109

VortexMVS		94.11 283	93.50 284	95.94 295	97.70 249	96.61 157	99.35 302	97.18 362	93.52 201	89.57 362	95.74 379	87.55 240	96.97 388	95.76 242	85.13 384	94.23 372

test222					99.55 98	97.41 118	99.34 303	98.55 120	91.86 290	99.27 101	99.83 51	93.84 110			99.95 54	99.99 26

our_test_3		90.39 375	89.48 380	93.12 404	92.40 448	89.57 406	99.33 304	96.35 445	87.84 399	85.30 435	94.99 424	84.14 310	96.09 443	80.38 454	84.56 388	93.71 429

ppachtmachnet_test		89.58 396	88.35 399	93.25 402	92.40 448	90.44 390	99.33 304	96.73 430	85.49 431	85.90 432	95.77 378	81.09 346	96.00 447	76.00 478	82.49 404	93.30 437

mvs_anonymous		95.65 230	95.03 236	97.53 216	98.19 211	95.74 195	99.33 304	97.49 309	90.87 326	90.47 340	97.10 330	88.23 230	97.16 371	95.92 237	97.66 200	99.68 131

E5new		95.83 216	95.39 216	97.15 247	97.03 311	93.59 294	99.32 307	97.30 337	92.58 257	96.45 239	99.00 206	83.37 319	98.81 238	96.81 211	96.65 246	99.04 260

E5		95.83 216	95.39 216	97.15 247	97.03 311	93.59 294	99.32 307	97.30 337	92.58 257	96.45 239	99.00 206	83.37 319	98.81 238	96.81 211	96.65 246	99.04 260

E6new		95.83 216	95.39 216	97.14 249	97.00 318	93.58 296	99.31 309	97.30 337	92.57 259	96.45 239	99.01 202	83.44 317	98.81 238	96.80 213	96.66 244	99.04 260

E6		95.83 216	95.39 216	97.14 249	97.00 318	93.58 296	99.31 309	97.30 337	92.57 259	96.45 239	99.01 202	83.44 317	98.81 238	96.80 213	96.66 244	99.04 260

AUN-MVS		93.28 309	92.60 314	95.34 318	98.29 202	90.09 397	99.31 309	98.56 114	91.80 294	96.35 248	98.00 302	89.38 212	98.28 314	92.46 311	69.22 481	97.64 321

xiu_mvs_v1_base_debu		97.43 118	97.06 124	98.55 124	97.74 241	98.14 75	99.31 309	97.86 263	96.43 83	99.62 62	99.69 105	85.56 279	99.68 166	99.05 84	98.31 178	97.83 314

xiu_mvs_v1_base		97.43 118	97.06 124	98.55 124	97.74 241	98.14 75	99.31 309	97.86 263	96.43 83	99.62 62	99.69 105	85.56 279	99.68 166	99.05 84	98.31 178	97.83 314

xiu_mvs_v1_base_debi		97.43 118	97.06 124	98.55 124	97.74 241	98.14 75	99.31 309	97.86 263	96.43 83	99.62 62	99.69 105	85.56 279	99.68 166	99.05 84	98.31 178	97.83 314

MVS_Test		96.46 181	95.74 200	98.61 117	98.18 212	97.23 124	99.31 309	97.15 369	91.07 322	98.84 125	97.05 334	88.17 231	98.97 218	94.39 271	97.50 202	99.61 152

hse-mvs2		94.38 274	94.08 265	95.31 320	98.27 205	90.02 398	99.29 316	98.56 114	95.90 102	98.77 131	98.00 302	90.89 191	98.26 319	97.80 169	69.20 482	97.64 321

testdata1							99.28 317		96.35 91

Vis-MVSNet		95.72 224	95.15 231	97.45 226	97.62 259	94.28 269	99.28 317	98.24 212	94.27 166	96.84 222	98.94 222	79.39 367	98.76 250	93.25 300	98.49 173	99.30 224
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
dtuonlycased		86.10 424	85.82 419	86.95 466	91.84 457	79.57 486	99.27 319	94.89 477	86.79 415	79.46 471	94.46 440	66.85 455	90.93 500	80.41 453	78.44 437	90.34 477

RRT-MVS		96.24 198	95.68 204	97.94 174	97.65 255	94.92 240	99.27 319	97.10 383	92.79 241	97.43 198	97.99 304	81.85 335	99.37 193	98.46 127	98.57 169	99.53 173

FMVSNet3		92.69 327	91.58 337	95.99 292	98.29 202	97.42 117	99.26 321	97.62 290	89.80 360	89.68 355	95.32 405	81.62 340	96.27 434	87.01 405	85.65 377	94.29 367

DeepC-MVS_fast	96.59 1	98.81 26	98.54 32	99.62 22	99.90 48	98.85 38	99.24 322	98.47 141	98.14 16	99.08 111	99.91 19	93.09 133	100.00 1	99.04 87	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
dcpmvs_2		97.42 122	98.09 63	95.42 315	99.58 97	87.24 436	99.23 323	96.95 410	94.28 164	98.93 122	99.73 92	94.39 88	99.16 208	99.89 22	99.82 85	99.86 102

YYNet1		85.50 430	83.33 437	92.00 421	90.89 467	88.38 426	99.22 324	96.55 438	79.60 471	57.26 514	92.72 460	79.09 373	93.78 481	77.25 472	77.37 447	93.84 420

v8		90.54 373	89.17 383	94.66 340	93.43 421	93.40 306	99.20 325	96.94 414	85.76 426	87.56 408	94.51 436	81.96 334	97.19 370	84.94 422	78.25 438	93.38 436

MDA-MVSNet_test_wron		85.51 429	83.32 438	92.10 420	90.96 466	88.58 422	99.20 325	96.52 439	79.70 470	57.12 515	92.69 461	79.11 371	93.86 479	77.10 473	77.46 446	93.86 419

ACMMP		97.74 103	97.44 108	98.66 113	99.92 37	96.13 182	99.18 327	99.45 18	94.84 133	96.41 246	99.71 98	91.40 177	99.99 40	97.99 157	98.03 192	99.87 100
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
WR-MVS_H		91.30 354	90.35 358	94.15 366	94.17 409	92.62 327	99.17 328	98.94 44	88.87 377	86.48 424	94.46 440	84.36 306	96.61 412	88.19 385	78.51 436	93.21 440

TAMVS		95.85 214	95.58 207	96.65 272	97.07 308	93.50 301	99.17 328	97.82 268	91.39 312	95.02 281	98.01 301	92.20 165	97.30 364	93.75 292	95.83 272	99.14 247

dtuonly		93.89 290	93.16 299	96.08 291	94.37 403	91.67 360	99.15 330	95.04 476	91.79 295	94.74 283	98.72 250	81.01 347	98.31 309	87.29 398	96.33 257	98.27 303

LuminaMVS		96.63 170	96.21 170	97.87 180	95.58 382	96.82 144	99.12 331	97.67 283	94.47 147	97.88 183	98.31 292	87.50 241	98.71 258	98.07 153	97.29 213	98.10 308

PS-MVSNAJss		93.64 302	93.31 295	94.61 342	92.11 452	92.19 336	99.12 331	97.38 320	92.51 265	88.45 388	96.99 338	91.20 180	97.29 367	94.36 272	87.71 361	94.36 360

SSM_0404		95.75 223	95.16 230	97.50 221	97.53 267	95.39 214	99.11 333	97.25 351	90.81 329	95.27 278	98.83 242	84.74 297	98.67 266	95.24 249	97.69 197	98.45 295

DTE-MVSNet		89.40 398	88.24 401	92.88 410	92.66 444	89.95 401	99.10 334	98.22 215	87.29 405	85.12 437	96.22 365	76.27 404	95.30 462	83.56 432	75.74 456	93.41 433

CP-MVSNet		91.23 358	90.22 362	94.26 361	93.96 412	92.39 332	99.09 335	98.57 108	88.95 374	86.42 425	96.57 356	79.19 370	96.37 428	90.29 353	78.95 433	94.02 403

AdaColmap		97.23 131	96.80 140	98.51 133	99.99 1	95.60 204	99.09 335	98.84 65	93.32 211	96.74 227	99.72 95	86.04 268	100.00 1	98.01 155	99.43 130	99.94 87

v10		90.25 381	88.82 390	94.57 346	93.53 419	93.43 303	99.08 337	96.87 421	85.00 436	87.34 414	94.51 436	80.93 349	97.02 387	82.85 436	79.23 432	93.26 438

XVG-OURS-SEG-HR		94.79 255	94.70 249	95.08 325	98.05 221	89.19 409	99.08 337	97.54 302	93.66 195	94.87 282	99.58 128	78.78 374	99.79 146	97.31 186	93.40 319	96.25 339

XVG-OURS		94.82 252	94.74 248	95.06 326	98.00 223	89.19 409	99.08 337	97.55 300	94.10 172	94.71 284	99.62 123	80.51 357	99.74 157	96.04 235	93.06 324	96.25 339

IS-MVSNet		96.29 194	95.90 193	97.45 226	98.13 217	94.80 245	99.08 337	97.61 293	92.02 286	95.54 273	98.96 215	90.64 194	98.08 328	93.73 293	97.41 206	99.47 185

v7n		89.65 394	88.29 400	93.72 387	92.22 450	90.56 387	99.07 341	97.10 383	85.42 433	86.73 418	94.72 429	80.06 362	97.13 374	81.14 447	78.12 440	93.49 432

EI-MVSNet		93.73 299	93.40 290	94.74 337	96.80 335	92.69 323	99.06 342	97.67 283	88.96 373	91.39 328	99.02 200	88.75 226	97.30 364	91.07 334	87.85 359	94.22 375

CVMVSNet		94.68 262	94.94 240	93.89 384	96.80 335	86.92 439	99.06 342	98.98 41	94.45 149	94.23 298	99.02 200	85.60 277	95.31 461	90.91 340	95.39 291	99.43 196

baseline1		95.78 222	94.86 241	98.54 128	98.47 188	98.07 81	99.06 342	97.99 247	92.68 249	94.13 299	98.62 263	93.28 127	98.69 263	93.79 290	85.76 376	98.84 279

PEN-MVS		90.19 383	89.06 386	93.57 393	93.06 429	90.90 378	99.06 342	98.47 141	88.11 394	85.91 431	96.30 363	76.67 397	95.94 448	87.07 402	76.91 451	93.89 416

test_fmvs3		79.99 459	80.17 457	79.45 483	84.02 510	62.83 507	99.05 346	93.49 498	88.29 392	80.06 468	86.65 505	28.09 512	88.00 507	88.63 372	73.27 465	87.54 503

Anonymous20231206		86.32 422	85.42 425	89.02 453	89.11 481	80.53 484	99.05 346	95.28 469	85.43 432	82.82 451	93.92 447	74.40 420	93.44 484	66.99 496	81.83 410	93.08 443

MAR-MVS		97.43 118	97.19 121	98.15 159	99.47 104	94.79 246	99.05 346	98.76 73	92.65 251	98.66 139	99.82 54	88.52 228	99.98 52	98.12 148	99.63 99	99.67 133
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
MonoMVSNet		94.82 252	94.43 252	95.98 293	94.54 400	90.73 381	99.03 349	97.06 396	93.16 220	93.15 309	95.47 396	88.29 229	97.57 351	97.85 166	91.33 329	99.62 148

VNet		97.21 132	96.57 151	99.13 77	98.97 140	97.82 96	99.03 349	99.21 32	94.31 161	99.18 106	98.88 228	86.26 265	99.89 119	98.93 94	94.32 306	99.69 130

LCM-MVSNet-Re		92.31 336	92.60 314	91.43 428	97.53 267	79.27 487	99.02 351	91.83 505	92.07 282	80.31 465	94.38 442	83.50 316	95.48 456	97.22 192	97.58 201	99.54 169

SSM_0407		95.62 231	94.95 239	97.61 208	97.14 302	95.31 220	99.00 352	97.25 351	90.81 329	94.40 291	98.83 242	84.74 297	98.58 276	95.24 249	97.18 218	98.93 270

jajsoiax		91.92 342	91.18 345	94.15 366	91.35 463	90.95 377	99.00 352	97.42 316	92.61 253	87.38 412	97.08 331	72.46 430	97.36 357	94.53 270	88.77 345	94.13 395

Elysia		94.50 269	93.38 291	97.85 181	96.49 347	96.70 150	98.98 354	97.78 273	90.81 329	96.19 252	98.55 273	73.63 426	98.98 216	89.41 361	98.56 170	97.88 312

StellarMVS		94.50 269	93.38 291	97.85 181	96.49 347	96.70 150	98.98 354	97.78 273	90.81 329	96.19 252	98.55 273	73.63 426	98.98 216	89.41 361	98.56 170	97.88 312

VPNet		91.81 344	90.46 355	95.85 301	94.74 396	95.54 206	98.98 354	98.59 104	92.14 280	90.77 338	97.44 320	68.73 446	97.54 353	94.89 260	77.89 441	94.46 352

PS-CasMVS		90.63 371	89.51 378	93.99 378	93.83 414	91.70 358	98.98 354	98.52 129	88.48 387	86.15 429	96.53 358	75.46 410	96.31 433	88.83 371	78.86 435	93.95 411

FMVSNet2		91.02 361	89.56 375	95.41 316	97.53 267	95.74 195	98.98 354	97.41 318	87.05 408	88.43 392	95.00 423	71.34 435	96.24 436	85.12 420	85.21 382	94.25 370

IMVS_0403		95.25 240	94.81 244	96.58 275	96.97 320	91.64 361	98.97 359	97.12 375	92.33 273	95.43 274	98.88 228	85.78 272	98.79 245	92.12 316	95.70 280	99.32 216

K. test v3		88.05 409	87.24 410	90.47 440	91.82 458	82.23 472	98.96 360	97.42 316	89.05 367	76.93 482	95.60 387	68.49 447	95.42 458	85.87 416	81.01 421	93.75 424

tfpnnormal		89.29 400	87.61 407	94.34 359	94.35 405	94.13 277	98.95 361	98.94 44	83.94 444	84.47 442	95.51 393	74.84 417	97.39 356	77.05 474	80.41 425	91.48 468

PatchmatchNet2					0.00 565	86.19 442	98.94 362	96.51 440	78.40 479
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
mmtdpeth		88.52 404	87.75 406	90.85 433	95.71 374	83.47 464	98.94 362	94.85 478	88.78 379	97.19 207	89.58 486	63.29 469	98.97 218	98.54 121	62.86 497	90.10 483

AllTest		92.48 332	91.64 335	95.00 328	99.01 132	88.43 423	98.94 362	96.82 425	86.50 417	88.71 380	98.47 281	74.73 418	99.88 125	85.39 417	96.18 260	96.71 335

h-mvs33		94.92 251	94.36 254	96.59 274	98.85 156	91.29 371	98.93 365	98.94 44	95.90 102	98.77 131	98.42 284	90.89 191	99.77 151	97.80 169	70.76 474	98.72 287

anonymousdsp		91.79 349	90.92 349	94.41 357	90.76 469	92.93 317	98.93 365	97.17 364	89.08 366	87.46 411	95.30 406	78.43 380	96.92 391	92.38 312	88.73 346	93.39 435

DP-MVS		94.54 265	93.42 287	97.91 177	99.46 106	94.04 279	98.93 365	97.48 310	81.15 464	90.04 346	99.55 132	87.02 251	99.95 86	88.97 370	98.11 188	99.73 120

ttmdpeth		88.23 408	87.06 411	91.75 426	89.91 477	87.35 435	98.92 368	95.73 457	87.92 397	84.02 445	96.31 362	68.23 450	96.84 398	86.33 410	76.12 454	91.06 470

IterMVS-SCA-FT		90.85 366	90.16 366	92.93 409	96.72 341	89.96 400	98.89 369	96.99 404	88.95 374	86.63 420	95.67 383	76.48 401	95.00 464	87.04 403	84.04 395	93.84 420

IterMVS		90.91 363	90.17 365	93.12 404	96.78 339	90.42 391	98.89 369	97.05 399	89.03 368	86.49 423	95.42 398	76.59 399	95.02 463	87.22 400	84.09 392	93.93 413
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous202405211		93.10 315	91.99 328	96.40 281	99.10 126	89.65 405	98.88 371	97.93 254	83.71 447	94.00 300	98.75 247	68.79 444	99.88 125	95.08 252	91.71 326	99.68 131

VPA-MVSNet		92.70 326	91.55 339	96.16 288	95.09 390	96.20 178	98.88 371	99.00 39	91.02 324	91.82 325	95.29 409	76.05 407	97.96 336	95.62 245	81.19 414	94.30 366

test20.03		84.72 439	83.99 431	86.91 467	88.19 485	80.62 483	98.88 371	95.94 453	88.36 390	78.87 472	94.62 434	68.75 445	89.11 506	66.52 499	75.82 455	91.00 471

XXY-MVS		91.82 343	90.46 355	95.88 299	93.91 413	95.40 213	98.87 374	97.69 282	88.63 384	87.87 403	97.08 331	74.38 421	97.89 340	91.66 326	84.07 393	94.35 363

test1111		95.57 232	94.98 238	97.37 237	98.56 175	93.37 307	98.86 375	98.45 144	94.95 126	96.63 229	98.95 220	75.21 415	99.11 209	95.02 253	98.14 187	99.64 139

SCA		94.69 260	93.81 274	97.33 242	97.10 305	94.44 258	98.86 375	98.32 199	93.30 212	96.17 255	95.59 388	76.48 401	97.95 337	91.06 335	97.43 203	99.59 155

ECVR-MVS		95.66 229	95.05 235	97.51 219	98.66 169	93.71 289	98.85 377	98.45 144	94.93 127	96.86 220	98.96 215	75.22 414	99.20 203	95.34 246	98.15 185	99.64 139

eth_miper_zixun_eth		92.41 334	91.93 329	93.84 385	97.28 296	90.68 383	98.83 378	96.97 408	88.57 385	89.19 374	95.73 382	89.24 217	96.69 409	89.97 358	81.55 411	94.15 386

CL-MVSNet_self_test		84.50 440	83.15 440	88.53 458	86.00 499	81.79 475	98.82 379	97.35 325	85.12 435	83.62 449	90.91 479	76.66 398	91.40 496	69.53 489	60.36 508	92.40 457

IMVS_0407		95.21 241	94.80 245	96.46 278	96.97 320	91.64 361	98.81 380	97.12 375	92.33 273	95.60 269	98.88 228	85.65 274	98.42 292	92.12 316	95.70 280	99.32 216

test2506		97.53 115	97.19 121	98.58 122	98.66 169	96.90 142	98.81 380	99.77 5	94.93 127	97.95 177	98.96 215	92.51 154	99.20 203	94.93 256	98.15 185	99.64 139

ACMH+	89.98 16	90.35 377	89.54 376	92.78 413	95.99 359	86.12 444	98.81 380	97.18 362	89.38 363	83.14 450	97.76 314	68.42 448	98.43 291	89.11 369	86.05 375	93.78 423

Anonymous20240521		85.15 433	83.81 435	89.16 452	88.32 483	82.69 467	98.80 383	95.74 456	79.72 469	81.53 458	90.99 477	65.38 462	94.16 475	72.69 483	81.11 417	90.63 476

N_pmnet		80.06 458	80.78 454	77.89 485	91.94 454	45.28 534	98.80 383	56.82 537	78.10 481	80.08 467	93.33 453	77.03 391	95.76 453	68.14 494	82.81 400	92.64 451

VDD-MVS		93.77 297	92.94 306	96.27 286	98.55 178	90.22 394	98.77 385	97.79 269	90.85 327	96.82 224	99.42 142	61.18 478	99.77 151	98.95 92	94.13 309	98.82 280

LFMVS		94.75 259	93.56 282	98.30 149	99.03 131	95.70 198	98.74 386	97.98 249	87.81 400	98.47 152	99.39 150	67.43 453	99.53 176	98.01 155	95.20 296	99.67 133

LS3D		95.84 215	95.11 232	98.02 168	99.85 62	95.10 234	98.74 386	98.50 138	87.22 407	93.66 303	99.86 34	87.45 243	99.95 86	90.94 339	99.81 87	99.02 265

Anonymous20240529		92.10 340	90.65 352	96.47 276	98.82 157	90.61 385	98.72 388	98.67 87	75.54 487	93.90 302	98.58 269	66.23 458	99.90 114	94.70 266	90.67 330	98.90 276

dmvs_re		93.20 311	93.15 300	93.34 397	96.54 346	83.81 458	98.71 389	98.51 132	91.39 312	92.37 320	98.56 271	78.66 376	97.83 342	93.89 283	89.74 331	98.38 299

TR-MVS		94.54 265	93.56 282	97.49 224	97.96 226	94.34 268	98.71 389	97.51 307	90.30 351	94.51 289	98.69 254	75.56 409	98.77 248	92.82 309	95.99 264	99.35 211

USDC		90.00 388	88.96 388	93.10 406	94.81 395	88.16 427	98.71 389	95.54 464	93.66 195	83.75 448	97.20 327	65.58 460	98.31 309	83.96 429	87.49 367	92.85 448

VDDNet		93.12 314	91.91 330	96.76 267	96.67 345	92.65 326	98.69 392	98.21 219	82.81 456	97.75 190	99.28 162	61.57 476	99.48 187	98.09 151	94.09 310	98.15 305

EU-MVSNet		90.14 385	90.34 359	89.54 449	92.55 445	81.06 480	98.69 392	98.04 243	91.41 311	86.59 421	96.84 347	80.83 351	93.31 485	86.20 411	81.91 409	94.26 368

mvs_tets		91.81 344	91.08 347	94.00 377	91.63 460	90.58 386	98.67 394	97.43 314	92.43 267	87.37 413	97.05 334	71.76 432	97.32 362	94.75 264	88.68 347	94.11 397

MDA-MVSNet-bldmvs		84.09 442	81.52 449	91.81 425	91.32 464	88.00 430	98.67 394	95.92 454	80.22 468	55.60 517	93.32 454	68.29 449	93.60 483	73.76 481	76.61 453	93.82 422

UGNet		95.33 239	94.57 250	97.62 207	98.55 178	94.85 241	98.67 394	99.32 26	95.75 108	96.80 226	96.27 364	72.18 431	99.96 77	94.58 269	99.05 153	98.04 309
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
icg_test_0407_2		95.04 247	94.78 246	95.84 302	96.97 320	91.64 361	98.63 397	97.12 375	92.33 273	95.60 269	98.88 228	85.65 274	96.56 414	92.12 316	95.70 280	99.32 216

pm-mvs1		89.36 399	87.81 405	94.01 376	93.40 423	91.93 342	98.62 398	96.48 442	86.25 421	83.86 447	96.14 369	73.68 425	97.04 383	86.16 412	75.73 457	93.04 444

MVStest1		85.03 434	82.76 443	91.83 424	92.95 436	89.16 412	98.57 399	94.82 479	71.68 495	68.54 500	95.11 416	83.17 325	95.66 454	74.69 480	65.32 491	90.65 475

test_0402		85.58 427	83.94 433	90.50 439	93.81 415	85.04 451	98.55 400	95.20 473	76.01 484	79.72 470	95.13 414	64.15 467	96.26 435	66.04 502	86.88 369	90.21 480

ACMH	89.72 17	90.64 370	89.63 373	93.66 392	95.64 379	88.64 421	98.55 400	97.45 312	89.03 368	81.62 457	97.61 315	69.75 442	98.41 294	89.37 363	87.62 365	93.92 414
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20231211		89.86 390	88.44 398	94.13 370	98.93 144	90.68 383	98.54 402	98.26 209	76.28 483	86.73 418	95.54 390	70.60 440	97.56 352	90.82 342	80.27 428	94.15 386

TransMVSNet (Re)		87.25 418	85.28 426	93.16 403	93.56 418	91.03 373	98.54 402	94.05 492	83.69 448	81.09 461	96.16 367	75.32 411	96.40 427	76.69 475	68.41 484	92.06 462

XVG-ACMP-BASELINE		91.22 359	90.75 350	92.63 415	93.73 416	85.61 447	98.52 404	97.44 313	92.77 242	89.90 350	96.85 345	66.64 457	98.39 298	92.29 313	88.61 348	93.89 416

CHOSEN 280x420		99.01 16	99.03 11	98.95 95	99.38 108	98.87 36	98.46 405	99.42 21	97.03 57	99.02 118	99.09 191	99.35 2	98.21 321	99.73 46	99.78 88	99.77 116

OpenMVS_ROB	79.82 20	83.77 445	81.68 448	90.03 446	88.30 484	82.82 466	98.46 405	95.22 472	73.92 492	76.00 485	91.29 476	55.00 486	96.94 390	68.40 491	88.51 352	90.34 477

kuosan		93.17 312	92.60 314	94.86 335	98.40 191	89.54 407	98.44 407	98.53 127	84.46 442	88.49 387	97.92 307	90.57 195	97.05 380	83.10 434	93.49 317	97.99 310

GBi-Net		90.88 364	89.82 370	94.08 372	97.53 267	91.97 339	98.43 408	96.95 410	87.05 408	89.68 355	94.72 429	71.34 435	96.11 440	87.01 405	85.65 377	94.17 380

test1		90.88 364	89.82 370	94.08 372	97.53 267	91.97 339	98.43 408	96.95 410	87.05 408	89.68 355	94.72 429	71.34 435	96.11 440	87.01 405	85.65 377	94.17 380

FMVSNet1		88.50 405	86.64 412	94.08 372	95.62 381	91.97 339	98.43 408	96.95 410	83.00 454	86.08 430	94.72 429	59.09 482	96.11 440	81.82 445	84.07 393	94.17 380

ArgMatch-Sym		85.85 425	85.07 428	88.21 461	92.84 438	77.63 490	98.42 411	94.70 484	89.91 357	84.33 443	96.72 350	51.42 494	94.89 468	82.48 438	74.80 460	92.10 460

COLMAP_ROB	90.47 14	92.18 339	91.49 341	94.25 362	99.00 136	88.04 429	98.42 411	96.70 432	82.30 459	88.43 392	99.01 202	76.97 393	99.85 131	86.11 413	96.50 251	94.86 346
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tt0805		91.28 356	90.18 364	94.60 343	96.26 352	87.55 432	98.39 413	98.72 78	89.00 370	89.22 371	98.47 281	62.98 471	98.96 220	90.57 346	88.00 358	97.28 331

test123		37.68 506	39.14 509	33.31 524	19.94 563	24.83 557	98.36 414	9.75 564	15.53 556	51.31 520	87.14 503	19.62 536	17.74 559	47.10 526	3.47 559	57.36 535

1314		96.84 154	95.96 186	99.48 40	96.74 340	98.52 64	98.31 415	98.86 59	95.82 105	89.91 349	98.98 211	87.49 242	99.96 77	97.80 169	99.73 91	99.96 75

MVS		96.60 172	95.56 208	99.72 14	96.85 332	99.22 22	98.31 415	98.94 44	91.57 301	90.90 334	99.61 124	86.66 258	99.96 77	97.36 185	99.88 77	99.99 26

FE-MVSNET2		83.57 447	81.36 450	90.20 443	82.83 514	87.59 431	98.28 417	96.04 451	85.33 434	74.13 491	87.45 499	59.16 481	93.26 486	79.12 464	69.91 476	89.77 487

NR-MVSNet		91.56 352	90.22 362	95.60 307	94.05 410	95.76 194	98.25 418	98.70 80	91.16 318	80.78 464	96.64 353	83.23 324	96.57 413	91.41 329	77.73 443	94.46 352

sd_testset		93.55 304	92.83 308	95.74 306	98.92 147	90.89 379	98.24 419	98.85 62	92.41 268	92.55 318	97.85 311	71.07 439	98.68 264	93.93 282	91.62 327	97.64 321

MS-PatchMatch		90.65 369	90.30 360	91.71 427	94.22 408	85.50 449	98.24 419	97.70 280	88.67 382	86.42 425	96.37 361	67.82 451	98.03 332	83.62 431	99.62 100	91.60 466

FE-MVSNET		81.05 454	78.81 462	87.79 464	81.98 515	83.70 459	98.23 421	91.78 506	81.27 463	74.29 490	87.44 500	60.92 479	90.67 502	64.92 504	68.43 483	89.01 496

pmmvs3		80.27 457	77.77 463	87.76 465	80.32 520	82.43 470	98.23 421	91.97 504	72.74 494	78.75 473	87.97 496	57.30 485	90.99 499	70.31 487	62.37 499	89.87 485

SixPastTwentyTwo		88.73 403	88.01 404	90.88 431	91.85 456	82.24 471	98.22 423	95.18 474	88.97 372	82.26 453	96.89 342	71.75 433	96.67 410	84.00 427	82.98 398	93.72 428

EG-PatchMatch MVS		85.35 431	83.81 435	89.99 447	90.39 471	81.89 474	98.21 424	96.09 450	81.78 461	74.73 488	93.72 451	51.56 493	97.12 376	79.16 463	88.61 348	90.96 472

OurMVSNet-221017-0		89.81 391	89.48 380	90.83 434	91.64 459	81.21 478	98.17 425	95.38 468	91.48 305	85.65 433	97.31 324	72.66 429	97.29 367	88.15 387	84.83 386	93.97 410

LF4IMVS		89.25 401	88.85 389	90.45 441	92.81 442	81.19 479	98.12 426	94.79 480	91.44 307	86.29 427	97.11 329	65.30 463	98.11 326	88.53 376	85.25 381	92.07 461

RPSCF		91.80 347	92.79 310	88.83 454	98.15 215	69.87 500	98.11 427	96.60 436	83.93 445	94.33 295	99.27 166	79.60 366	99.46 190	91.99 321	93.16 322	97.18 332

pmmvs-eth3d		84.03 443	81.97 447	90.20 443	84.15 508	87.09 437	98.10 428	94.73 482	83.05 453	74.10 492	87.77 497	65.56 461	94.01 476	81.08 448	69.24 480	89.49 491

DSMNet-mixed		88.28 407	88.24 401	88.42 460	89.64 478	75.38 495	98.06 429	89.86 510	85.59 430	88.20 400	92.14 474	76.15 406	91.95 495	78.46 467	96.05 263	97.92 311

MVP-Stereo		90.93 362	90.45 357	92.37 418	91.25 465	88.76 416	98.05 430	96.17 448	87.27 406	84.04 444	95.30 406	78.46 379	97.27 369	83.78 430	99.70 93	91.09 469
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UA-Net		96.54 177	95.96 186	98.27 151	98.23 207	95.71 197	98.00 431	98.45 144	93.72 194	98.41 156	99.27 166	88.71 227	99.66 172	91.19 332	97.69 197	99.44 195

ArgMatch-SfM		85.25 432	84.17 430	88.48 459	92.99 433	77.23 491	97.92 432	94.24 488	90.50 342	85.08 438	95.65 385	49.84 495	95.83 450	81.06 449	70.22 475	92.39 458

new-patchmatchnet		81.19 452	79.34 460	86.76 468	82.86 513	80.36 485	97.92 432	95.27 470	82.09 460	72.02 494	86.87 504	62.81 472	90.74 501	71.10 486	63.08 496	89.19 494

PCF-MVS	94.20 5	95.18 242	94.10 262	98.43 140	98.55 178	95.99 186	97.91 434	97.31 336	90.35 348	89.48 364	99.22 176	85.19 287	99.89 119	90.40 352	98.47 174	99.41 200
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVS		76.28 463	77.28 465	73.29 494	81.18 517	54.68 520	97.87 435	94.19 489	81.30 462	69.43 498	90.70 480	77.02 392	82.06 519	35.71 531	68.11 486	83.13 511

pmmvs6		85.69 426	83.84 434	91.26 430	90.00 476	84.41 456	97.82 436	96.15 449	75.86 485	81.29 460	95.39 401	61.21 477	96.87 397	83.52 433	73.29 464	92.50 455

UniMVSNet_ETH3D		90.06 387	88.58 396	94.49 351	94.67 398	88.09 428	97.81 437	97.57 298	83.91 446	88.44 389	97.41 321	57.44 484	97.62 350	91.41 329	88.59 350	97.77 317

IMVS_0404		93.83 292	93.17 298	95.80 304	96.97 320	91.64 361	97.78 438	97.12 375	92.33 273	90.87 335	98.88 228	76.78 396	96.43 423	92.12 316	95.70 280	99.32 216

SD_0403		92.63 330	93.38 291	90.40 442	97.32 292	77.91 489	97.75 439	98.03 245	91.89 288	90.83 336	98.29 294	82.00 332	93.79 480	88.51 378	95.75 277	99.52 174

TinyColmap		87.87 412	86.51 413	91.94 422	95.05 392	85.57 448	97.65 440	94.08 490	84.40 443	81.82 456	96.85 345	62.14 474	98.33 307	80.25 456	86.37 372	91.91 465

HY-MVS	92.50 7	97.79 99	97.17 123	99.63 19	98.98 139	99.32 11	97.49 441	99.52 14	95.69 110	98.32 161	97.41 321	93.32 123	99.77 151	98.08 152	95.75 277	99.81 109

usedtu_blend_shiyan5		86.75 421	84.29 429	94.16 364	86.66 492	91.83 348	97.42 442	95.23 471	69.94 499	88.37 395	92.36 468	78.01 381	96.50 417	89.35 364	61.26 502	94.14 390

SSC-MVS		75.42 466	76.40 467	72.49 499	80.68 519	53.62 521	97.42 442	94.06 491	80.42 467	68.75 499	90.14 484	76.54 400	81.66 520	33.25 532	66.34 490	82.19 512

Effi-MVS+		96.30 193	95.69 202	98.16 156	97.85 233	96.26 172	97.41 444	97.21 359	90.37 347	98.65 141	98.58 269	86.61 259	98.70 261	97.11 195	97.37 208	99.52 174

sc_t1		85.01 435	82.46 445	92.67 414	92.44 447	83.09 465	97.39 445	95.72 458	65.06 503	85.64 434	96.16 367	49.50 496	97.34 359	84.86 423	75.39 458	97.57 326

TDRefinement		84.76 437	82.56 444	91.38 429	74.58 527	84.80 455	97.36 446	94.56 486	84.73 440	80.21 466	96.12 372	63.56 468	98.39 298	87.92 390	63.97 495	90.95 473

FMVSNet5		88.32 406	87.47 408	90.88 431	96.90 330	88.39 425	97.28 447	95.68 460	82.60 458	84.67 441	92.40 467	79.83 364	91.16 497	76.39 476	81.51 412	93.09 442

KD-MVS_self_test		83.59 446	82.06 446	88.20 462	86.93 489	80.70 482	97.21 448	96.38 443	82.87 455	82.49 452	88.97 490	67.63 452	92.32 492	73.75 482	62.30 500	91.58 467

LTVRE_ROB	88.28 18	90.29 380	89.05 387	94.02 375	95.08 391	90.15 396	97.19 449	97.43 314	84.91 439	83.99 446	97.06 333	74.00 423	98.28 314	84.08 426	87.71 361	93.62 430
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
KD-MVS_2432*1600		88.00 410	86.10 414	93.70 390	96.91 327	94.04 279	97.17 450	97.12 375	84.93 437	81.96 454	92.41 465	92.48 155	94.51 473	79.23 460	52.68 519	92.56 452

miper_refine_blended		88.00 410	86.10 414	93.70 390	96.91 327	94.04 279	97.17 450	97.12 375	84.93 437	81.96 454	92.41 465	92.48 155	94.51 473	79.23 460	52.68 519	92.56 452

mvsany_test3		82.12 451	81.14 452	85.06 472	81.87 516	70.41 499	97.09 452	92.14 503	91.27 314	77.84 478	88.73 491	39.31 502	95.49 455	90.75 344	71.24 473	89.29 493

CostFormer		96.10 202	95.88 195	96.78 266	97.03 311	92.55 328	97.08 453	97.83 267	90.04 356	98.72 136	94.89 427	95.01 67	98.29 312	96.54 223	95.77 275	99.50 181

tpm		93.70 301	93.41 289	94.58 345	95.36 387	87.41 434	97.01 454	96.90 418	90.85 327	96.72 228	94.14 446	90.40 199	96.84 398	90.75 344	88.54 351	99.51 179

CMPMVS	61.59 21	84.75 438	85.14 427	83.57 475	90.32 472	62.54 509	96.98 455	97.59 297	74.33 491	69.95 497	96.66 351	64.17 466	98.32 308	87.88 391	88.41 353	89.84 486
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
test_f		78.40 462	77.59 464	80.81 482	80.82 518	62.48 510	96.96 456	93.08 500	83.44 449	74.57 489	84.57 511	27.95 514	92.63 490	84.15 425	72.79 467	87.32 504

tpm2		95.47 234	95.18 229	96.35 284	96.91 327	91.70 358	96.96 456	97.93 254	88.04 396	98.44 153	95.40 399	93.32 123	97.97 334	94.00 279	95.61 285	99.38 203

new_pmnet		84.49 441	82.92 441	89.21 451	90.03 475	82.60 468	96.89 458	95.62 462	80.59 466	75.77 487	89.17 489	65.04 464	94.79 470	72.12 485	81.02 420	90.23 479

tt0320-xc		82.94 449	80.35 456	90.72 437	92.90 437	83.54 462	96.85 459	94.73 482	63.12 506	79.85 469	93.77 450	49.43 497	95.46 457	80.98 450	71.54 472	93.16 441

tt0320		83.56 448	81.15 451	90.77 435	92.77 443	83.58 461	96.83 460	95.52 465	63.26 505	81.36 459	92.54 462	53.26 489	95.77 452	80.45 452	74.38 461	92.96 445

dmvs_testset		83.79 444	86.07 416	76.94 487	92.14 451	48.60 529	96.75 461	90.27 509	89.48 362	78.65 474	98.55 273	79.25 368	86.65 512	66.85 498	82.69 401	95.57 345

UnsupCasMVSNet_eth		85.52 428	83.99 431	90.10 445	89.36 480	83.51 463	96.65 462	97.99 247	89.14 365	75.89 486	93.83 448	63.25 470	93.92 477	81.92 444	67.90 487	92.88 447

MIMVSNet1		82.58 450	80.51 455	88.78 455	86.68 491	84.20 457	96.65 462	95.41 467	78.75 478	78.59 475	92.44 464	51.88 492	89.76 503	65.26 503	78.95 433	92.38 459

usedtu_dtu_shiyan2		75.87 465	72.37 470	86.39 469	76.18 525	75.49 494	96.53 464	93.82 495	64.74 504	72.53 493	88.48 492	37.67 503	91.12 498	64.13 505	57.22 512	92.56 452

ab-mvs		94.69 260	93.42 287	98.51 133	98.07 220	96.26 172	96.49 465	98.68 84	90.31 350	94.54 287	97.00 337	76.30 403	99.71 161	95.98 236	93.38 320	99.56 164

test_vis3_rt		68.82 474	66.69 478	75.21 493	76.24 524	60.41 513	96.44 466	68.71 531	75.13 489	50.54 522	69.52 527	16.42 539	96.32 432	80.27 455	66.92 489	68.89 528

EPMVS		96.53 178	96.01 179	98.09 163	98.43 190	96.12 184	96.36 467	99.43 20	93.53 198	97.64 191	95.04 418	94.41 84	98.38 302	91.13 333	98.11 188	99.75 118

tpmrst		96.27 196	95.98 182	97.13 251	97.96 226	93.15 310	96.34 468	98.17 224	92.07 282	98.71 137	95.12 415	93.91 106	98.73 254	94.91 259	96.62 248	99.50 181

FA-MVS(test-final)		95.86 213	95.09 233	98.15 159	97.74 241	95.62 203	96.31 469	98.17 224	91.42 310	96.26 249	96.13 370	90.56 196	99.47 189	92.18 315	97.07 228	99.35 211

dp		95.05 246	94.43 252	96.91 260	97.99 224	92.73 322	96.29 470	97.98 249	89.70 361	95.93 261	94.67 433	93.83 111	98.45 289	86.91 408	96.53 250	99.54 169

EGC-MVSNET		69.38 471	63.76 483	86.26 470	90.32 472	81.66 477	96.24 471	93.85 494	0.99 559	3.22 560	92.33 472	52.44 490	92.92 489	59.53 517	84.90 385	84.21 509

tpm cat1		93.51 305	92.52 320	96.47 276	97.77 239	91.47 370	96.13 472	98.06 240	80.98 465	92.91 313	93.78 449	89.66 207	98.87 227	87.03 404	96.39 255	99.09 253

MDTV_nov1_ep13_2view						96.26 172	96.11 473		91.89 288	98.06 173		94.40 85		94.30 275		99.67 133

PatchmatchNet		95.94 210	95.45 211	97.39 236	97.83 234	94.41 262	96.05 474	98.40 179	92.86 235	97.09 210	95.28 410	94.21 98	98.07 330	89.26 368	98.11 188	99.70 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
APD_test1		81.15 453	80.92 453	81.86 480	92.45 446	59.76 515	96.04 475	93.61 497	73.29 493	77.06 480	96.64 353	44.28 501	96.16 439	72.35 484	82.52 403	89.67 489

MDTV_nov1_ep13			95.69 202		97.90 229	94.15 276	95.98 476	98.44 149	93.12 224	97.98 176	95.74 379	95.10 62	98.58 276	90.02 356	96.92 239

FPMVS		68.72 475	68.72 473	68.71 502	65.95 538	44.27 537	95.97 477	94.74 481	51.13 519	53.26 519	90.50 481	25.11 520	83.00 517	60.80 513	80.97 422	78.87 522

PM-MVS		80.47 456	78.88 461	85.26 471	83.79 511	72.22 497	95.89 478	91.08 507	85.71 429	76.56 484	88.30 493	36.64 505	93.90 478	82.39 440	69.57 479	89.66 490

test_post1							95.78 479				59.23 542	93.20 131	97.74 346	91.06 335

tpmvs		94.28 279	93.57 281	96.40 281	98.55 178	91.50 369	95.70 480	98.55 120	87.47 402	92.15 321	94.26 444	91.42 176	98.95 222	88.15 387	95.85 271	98.76 283

FE-MVS		95.70 228	95.01 237	97.79 186	98.21 209	94.57 252	95.03 481	98.69 82	88.90 376	97.50 195	96.19 366	92.60 150	99.49 186	89.99 357	97.94 194	99.31 221

ADS-MVSNet2		93.80 296	93.88 272	93.55 394	97.87 231	85.94 446	94.24 482	96.84 422	90.07 354	96.43 244	94.48 438	90.29 202	95.37 459	87.44 394	97.23 214	99.36 207

ADS-MVSNet		94.79 255	94.02 267	97.11 253	97.87 231	93.79 286	94.24 482	98.16 229	90.07 354	96.43 244	94.48 438	90.29 202	98.19 322	87.44 394	97.23 214	99.36 207

EMVS		51.44 500	51.22 501	52.11 517	70.71 532	44.97 535	94.04 484	75.66 529	35.34 528	42.40 535	61.56 541	28.93 511	65.87 533	27.64 539	24.73 542	45.49 538

PMMVS2		67.15 479	64.15 482	76.14 490	70.56 533	62.07 511	93.89 485	87.52 517	58.09 513	60.02 509	78.32 518	22.38 527	84.54 515	59.56 516	47.03 527	81.80 514

GG-mvs-BLEND				98.54 128	98.21 209	98.01 85	93.87 486	98.52 129		97.92 178	97.92 307	99.02 3	97.94 339	98.17 145	99.58 110	99.67 133

LoFTR		74.41 468	70.88 471	84.99 473	86.56 496	67.85 502	93.74 487	89.63 512	69.46 500	54.95 518	87.39 501	30.76 506	96.92 391	61.37 512	64.06 494	90.19 481

UnsupCasMVSNet_bld		79.97 460	77.03 466	88.78 455	85.62 501	81.98 473	93.66 488	97.35 325	75.51 488	70.79 496	83.05 512	48.70 498	94.91 467	78.31 468	60.29 509	89.46 492

E-PMN		52.30 497	52.18 498	52.67 516	71.51 531	45.40 533	93.62 489	76.60 528	36.01 526	43.50 532	64.13 537	27.11 515	67.31 532	31.06 533	26.06 541	45.30 541

MatchFormer		70.84 470	66.72 477	83.19 478	85.99 500	64.61 506	93.58 490	88.62 516	59.32 512	50.64 521	82.31 516	28.00 513	96.79 403	52.52 523	59.50 510	88.18 498

RoMa-SfM		74.91 467	72.77 469	81.35 481	88.00 486	67.35 503	93.55 491	86.23 520	68.27 501	66.79 502	92.92 459	30.40 508	87.68 508	66.14 501	62.62 498	89.02 495

mamba_0408		94.98 250	94.09 263	97.64 203	97.14 302	95.31 220	93.48 492	97.08 387	90.48 343	94.40 291	98.62 263	84.49 303	98.67 266	93.99 280	97.18 218	98.93 270

SSM_04072		94.77 257	94.09 263	96.82 264	97.14 302	95.31 220	93.48 492	97.08 387	90.48 343	94.40 291	98.62 263	84.49 303	96.21 437	93.99 280	97.18 218	98.93 270

DenseAffine		75.91 464	73.39 468	83.47 476	89.52 479	71.86 498	93.39 494	89.29 515	71.44 496	66.83 501	90.32 483	30.65 507	89.67 504	68.20 493	60.88 506	88.88 497

JIA-IIPM		91.76 350	90.70 351	94.94 330	96.11 355	87.51 433	93.16 495	98.13 234	75.79 486	97.58 192	77.68 519	92.84 140	97.97 334	88.47 379	96.54 249	99.33 214

DKM		72.18 469	69.80 472	79.34 484	86.79 490	65.15 505	92.70 496	84.00 521	67.67 502	61.97 507	89.63 485	23.69 525	85.17 514	67.39 495	54.35 517	87.70 501

gg-mvs-nofinetune		93.51 305	91.86 332	98.47 135	97.72 246	97.96 90	92.62 497	98.51 132	74.70 490	97.33 202	69.59 526	98.91 4	97.79 343	97.77 174	99.56 111	99.67 133

MIMVSNet		90.30 379	88.67 394	95.17 324	96.45 349	91.64 361	92.39 498	97.15 369	85.99 423	90.50 339	93.19 458	66.95 454	94.86 469	82.01 443	93.43 318	99.01 266

MVS-HIRNet		86.22 423	83.19 439	95.31 320	96.71 342	90.29 392	92.12 499	97.33 329	62.85 507	86.82 417	70.37 524	69.37 443	97.49 354	75.12 479	97.99 193	98.15 305

CR-MVSNet		93.45 308	92.62 313	95.94 295	96.29 350	92.66 324	92.01 500	96.23 446	92.62 252	96.94 217	93.31 455	91.04 185	96.03 445	79.23 460	95.96 266	99.13 248

RPMNet		89.76 392	87.28 409	97.19 246	96.29 350	92.66 324	92.01 500	98.31 201	70.19 498	96.94 217	85.87 509	87.25 247	99.78 148	62.69 509	95.96 266	99.13 248

MASt3R-SfM		78.94 461	79.57 459	77.07 486	84.15 508	50.74 525	91.56 502	92.34 502	83.22 451	80.84 463	94.16 445	36.67 504	92.30 493	79.45 459	73.71 463	88.16 499

Patchmatch-test		92.65 329	91.50 340	96.10 290	96.85 332	90.49 388	91.50 503	97.19 360	82.76 457	90.23 341	95.59 388	95.02 66	98.00 333	77.41 471	96.98 238	99.82 107

Patchmtry		89.70 393	88.49 397	93.33 398	96.24 353	89.94 403	91.37 504	96.23 446	78.22 480	87.69 405	93.31 455	91.04 185	96.03 445	80.18 457	82.10 407	94.02 403

PatchT		90.38 376	88.75 393	95.25 322	95.99 359	90.16 395	91.22 505	97.54 302	76.80 482	97.26 205	86.01 508	91.88 172	96.07 444	66.16 500	95.91 270	99.51 179

mvs5depth		84.87 436	82.90 442	90.77 435	85.59 502	84.84 454	91.10 506	93.29 499	83.14 452	85.07 439	94.33 443	62.17 473	97.32 362	78.83 466	72.59 471	90.14 482

testf1		68.38 476	66.92 475	72.78 496	78.80 521	50.36 526	90.95 507	87.35 518	55.47 515	58.95 510	88.14 494	20.64 532	87.60 509	57.28 518	64.69 492	80.39 520

APD_test2		68.38 476	66.92 475	72.78 496	78.80 521	50.36 526	90.95 507	87.35 518	55.47 515	58.95 510	88.14 494	20.64 532	87.60 509	57.28 518	64.69 492	80.39 520

RoMa-HiRes		69.18 472	67.02 474	75.65 491	83.52 512	60.31 514	90.80 509	76.82 527	62.46 508	62.85 505	90.44 482	24.75 522	83.07 516	60.58 514	50.97 524	83.58 510

DKM-HiRes		68.91 473	66.34 479	76.62 489	84.17 507	60.69 512	90.78 510	78.55 525	62.17 509	58.82 512	87.54 498	20.94 529	82.56 518	63.05 507	51.00 523	86.61 505

Patchmatch-RL test		86.90 419	85.98 418	89.67 448	84.45 506	75.59 493	89.71 511	92.43 501	86.89 413	77.83 479	90.94 478	94.22 96	93.63 482	87.75 392	69.61 478	99.79 112

LCM-MVSNet		67.77 478	64.73 481	76.87 488	62.95 544	56.25 519	89.37 512	93.74 496	44.53 521	61.99 506	80.74 517	20.42 534	86.53 513	69.37 490	59.50 510	87.84 500

ambc				83.23 477	77.17 523	62.61 508	87.38 513	94.55 487		76.72 483	86.65 505	30.16 509	96.36 429	84.85 424	69.86 477	90.73 474

PDCNetPlus		59.83 484	57.26 487	67.55 504	76.18 525	56.71 518	87.01 514	45.27 547	59.54 511	48.80 524	83.01 513	26.63 516	76.54 526	62.12 511	26.78 540	69.40 527

SP-SuperGlue		55.29 488	53.71 490	60.00 512	85.11 504	38.86 542	86.96 515	57.95 535	32.77 531	44.54 529	68.00 531	23.90 524	59.51 536	29.61 536	54.59 516	81.63 516

SP-NN		55.28 490	53.59 492	60.34 508	86.63 495	39.01 541	86.70 516	56.31 539	31.08 534	43.77 531	68.45 530	23.39 526	60.24 534	29.19 537	56.76 514	81.77 515

SP-MNN		53.97 493	52.04 499	59.73 514	84.72 505	38.63 543	86.51 517	55.94 540	29.25 535	40.20 537	67.48 534	22.18 528	59.59 535	27.79 538	54.33 518	80.98 518

ELoFTR		64.32 482	60.56 485	75.60 492	73.46 530	53.20 522	86.50 518	80.09 524	60.74 510	45.95 527	82.48 515	16.05 540	89.20 505	56.48 522	43.34 529	84.38 508

SP-LightGlue		55.29 488	53.65 491	60.20 510	85.58 503	39.12 540	86.36 519	57.52 536	32.34 533	44.34 530	67.75 533	24.36 523	59.32 537	29.62 535	54.98 515	82.17 513

PMatch-SfM		62.12 483	58.57 486	72.76 498	74.34 528	52.97 523	84.95 520	65.57 532	56.89 514	46.61 526	85.70 510	9.51 550	80.54 522	60.53 515	43.03 530	84.77 506

ANet_high		56.10 487	52.24 497	67.66 503	49.27 557	56.82 517	83.94 521	82.02 523	70.47 497	33.28 542	64.54 536	17.23 538	69.16 531	45.59 527	23.85 544	77.02 524

SP-DiffGlue		56.84 486	55.72 488	60.19 511	65.70 539	40.86 538	81.89 522	60.28 534	34.62 530	50.39 523	76.88 520	26.61 517	58.81 538	48.21 525	56.94 513	80.90 519

ALIKED-LG		54.29 492	52.28 496	60.32 509	88.90 482	45.51 531	81.66 523	56.33 538	38.60 522	42.62 534	70.81 523	25.00 521	75.20 528	19.87 544	46.76 528	60.24 532

ALIKED-MNN		52.51 496	50.15 503	59.60 515	90.05 474	44.33 536	81.60 524	54.93 544	32.36 532	40.96 536	68.77 528	20.90 530	75.30 527	20.00 543	41.78 531	59.18 534

PMatch-Up-SfM		57.92 485	53.93 489	69.90 501	69.97 534	46.69 530	81.36 525	55.29 543	51.90 518	43.17 533	82.54 514	7.86 555	78.44 525	57.13 520	36.17 534	84.58 507

ALIKED-NN		54.48 491	52.67 495	59.89 513	90.79 468	45.45 532	81.25 526	55.75 541	34.99 529	44.87 528	71.98 522	25.50 519	74.36 529	21.88 542	47.04 526	59.85 533

tmp_tt		65.23 481	62.94 484	72.13 500	44.90 559	50.03 528	81.05 527	89.42 514	38.45 523	48.51 525	99.90 23	54.09 488	78.70 524	91.84 325	18.26 549	87.64 502

MVE	53.74 22	51.54 499	47.86 504	62.60 506	59.56 551	50.93 524	79.41 528	77.69 526	35.69 527	36.27 539	61.76 540	5.79 561	69.63 530	37.97 530	36.61 533	67.24 529
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GLUNet-SfM		51.10 501	46.61 505	64.56 505	61.54 548	39.88 539	79.38 529	65.13 533	36.09 525	33.36 541	69.94 525	14.50 542	78.76 523	42.46 529	17.10 550	75.02 525

PMVS	49.05 23	53.75 494	51.34 500	60.97 507	40.80 561	34.68 544	74.82 530	89.62 513	37.55 524	28.67 543	72.12 521	7.09 557	81.63 521	43.17 528	68.21 485	66.59 530
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
VLMVS		51.63 498	52.90 494	47.80 519	47.64 558	20.83 561	69.98 531	55.61 542	20.15 540	63.34 504	87.24 502	19.48 537	43.90 545	62.94 508	49.76 525	78.65 523

VLMVS_CLIP		52.57 495	53.54 493	49.65 518	41.84 560	19.27 562	69.54 532	70.45 530	22.22 538	56.57 516	86.16 507	15.89 541	54.77 539	66.88 497	52.29 521	74.91 526

XFeat-NN		42.54 503	42.87 507	41.54 522	59.73 550	27.86 549	69.53 533	45.34 546	24.36 536	37.16 538	64.79 535	20.84 531	51.40 541	30.01 534	34.12 536	45.36 540

XFeat-MNN		41.51 504	41.24 508	42.32 521	55.40 555	28.19 548	69.39 534	46.53 545	23.57 537	34.47 540	63.21 539	20.04 535	52.41 540	27.43 540	31.08 539	46.37 537

Gipuma		66.95 480	65.00 480	72.79 495	91.52 461	67.96 501	66.16 535	95.15 475	47.89 520	58.54 513	67.99 532	29.74 510	87.54 511	50.20 524	77.83 442	62.87 531
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SIFT-NN		35.94 507	36.54 510	34.16 523	73.93 529	29.52 545	62.74 536	37.28 548	19.65 541	27.91 544	49.19 543	11.66 543	46.35 542	9.19 546	37.30 532	26.61 542

SIFT-NN-NCMNet		33.88 509	34.14 512	33.10 526	66.88 537	28.42 547	60.42 537	36.72 550	19.15 542	24.06 546	47.14 547	10.24 545	44.77 544	8.72 547	33.94 537	26.10 544

SIFT-MNN		34.10 508	34.41 511	33.17 525	68.99 535	28.51 546	60.22 538	36.81 549	19.08 544	24.04 547	47.28 546	10.06 547	45.04 543	8.72 547	34.47 535	25.97 545

MVS_clip		48.84 502	50.24 502	44.65 520	64.05 542	23.54 560	58.84 539	20.46 561	18.73 546	60.84 508	89.57 487	25.96 518	29.22 557	62.25 510	51.44 522	81.19 517

SIFT-NN-UMatch		31.23 512	31.05 516	31.79 529	60.08 549	27.23 554	58.49 540	33.65 551	19.14 543	17.30 551	47.31 545	10.12 546	42.88 547	8.67 550	24.67 543	25.27 546

SIFT-NCM-Cal		31.73 510	31.67 513	31.91 528	67.18 536	27.55 552	58.36 541	33.09 553	18.38 548	14.93 554	45.16 552	8.60 551	43.82 546	7.62 556	31.68 538	24.36 548

SIFT-NN-CMatch		31.71 511	31.56 514	32.16 527	62.58 545	27.53 553	56.45 542	33.28 552	19.00 545	23.65 548	47.34 544	10.05 548	42.72 548	8.71 549	22.96 545	26.24 543

SIFT-UMatch		29.40 515	28.87 519	30.98 531	62.08 547	26.57 555	56.09 543	29.45 556	18.31 549	15.86 553	46.00 548	8.23 553	42.54 549	7.99 553	15.81 551	23.85 549

SIFT-NN-PointCN		29.63 514	29.72 518	29.36 533	57.55 552	23.55 559	56.07 544	30.57 555	17.99 552	20.99 549	45.21 551	9.94 549	39.33 553	8.40 551	20.81 546	25.20 547

SIFT-ConvMatch		30.09 513	29.76 517	31.09 530	65.16 541	27.56 551	54.13 545	31.17 554	18.55 547	17.88 550	45.89 549	8.40 552	42.26 550	8.11 552	18.51 548	23.46 550

SIFT-UM-Cal		27.47 517	27.02 521	28.83 535	62.12 546	24.58 558	53.60 546	23.46 559	18.14 550	12.85 556	45.56 550	7.49 556	39.45 552	7.68 554	12.30 554	22.45 552

SIFT-PointCN		25.49 518	25.71 522	24.84 536	56.17 553	18.65 563	51.37 547	26.53 557	16.31 553	12.78 557	39.87 556	6.41 559	34.09 555	6.51 558	15.42 552	21.77 553

SIFT-CM-Cal		28.34 516	27.90 520	29.63 532	63.75 543	25.98 556	50.66 548	26.18 558	18.12 551	16.88 552	44.64 553	8.08 554	39.70 551	7.65 555	15.19 553	23.22 551

wuyk23d		20.37 522	20.84 525	18.99 539	65.34 540	27.73 550	50.43 549	7.67 565	9.50 557	8.01 559	6.34 558	6.13 560	26.24 558	23.40 541	10.69 557	2.99 556

SIFT-PCN-Cal		24.67 519	24.81 523	24.24 537	56.13 554	18.04 564	49.05 550	23.39 560	16.07 554	12.99 555	40.17 555	6.97 558	34.68 554	6.71 557	11.81 555	19.99 554

SIFT-NCMNet		21.21 521	21.22 524	21.17 538	52.99 556	16.41 565	42.12 551	14.05 563	15.89 555	10.70 558	35.85 557	5.14 562	29.82 556	5.80 559	8.44 558	17.28 555

MVS_baseline		18.28 523	19.10 526	15.85 540	22.71 562	1.80 567	10.32 552	3.08 566	1.00 558	27.16 545	68.73 529	2.83 563	0.36 561	17.05 545	18.98 547	45.38 539

mmdepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

monomultidepth		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

test_blank		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.02 559	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uanet_test		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

DCPMVS		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

cdsmvs_eth3d_5k		23.43 520	31.24 515	0.00 541	0.00 565	0.00 568	0.00 553	98.09 236	0.00 560	0.00 561	99.67 114	83.37 319	0.00 562	0.00 560	0.00 560	0.00 557

pcd_1.5k_mvsjas		7.60 525	10.13 528	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	91.20 180	0.00 562	0.00 560	0.00 560	0.00 557

sosnet-low-res		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

sosnet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uncertanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

Regformer		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

ab-mvs-re		8.28 524	11.04 527	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	99.40 148	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

uanet		0.00 526	0.00 529	0.00 541	0.00 565	0.00 568	0.00 553	0.00 567	0.00 560	0.00 561	0.00 560	0.00 564	0.00 562	0.00 560	0.00 560	0.00 557

PatchmatchNet1														68.29 492	82.87 399	92.70 450
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
PatchmatchNet3													95.80 451
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo. CVPR 2021
test-260524					99.95 17	99.33 9		98.42 169		99.04 116		96.44 36	100.00 1	99.98 9	99.98 32

WAC-MVS						90.97 374								86.10 414

MSC_two_6792asdad				99.93 2	99.91 45	99.80 2		98.41 175					100.00 1	99.96 13	100.00 1	100.00 1

PC_three_1452									96.96 60	99.80 28	99.79 63	97.49 11	100.00 1	99.99 5	99.98 32	100.00 1

No_MVS				99.93 2	99.91 45	99.80 2		98.41 175					100.00 1	99.96 13	100.00 1	100.00 1

test_one_0601					99.94 18	99.30 14		98.41 175	96.63 75	99.75 42	99.93 12	97.49 11

eth-test2					0.00 565

eth-test					0.00 565

ZD-MVS					99.92 37	98.57 62		98.52 129	92.34 272	99.31 96	99.83 51	95.06 64	99.80 144	99.70 50	99.97 44

IU-MVS					99.93 29	99.31 12		98.41 175	97.71 31	99.84 23				100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 157	97.27 47	99.80 28	99.94 5	97.18 23	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 29	99.30 14		98.43 157	97.26 49	99.80 28	99.88 29	96.71 29	100.00 1

test_0728_THIRD									96.48 80	99.83 24	99.91 19	97.87 6	100.00 1	99.92 17	100.00 1	100.00 1

GSMVS																99.59 155

test_part2					99.89 51	99.25 20				99.49 80

sam_mvs1												94.72 75				99.59 155

sam_mvs												94.25 95

MTGPA								98.28 206

test_post											63.35 538	94.43 83	98.13 325

patchmatchnet-post											91.70 475	95.12 61	97.95 337

gm-plane-assit					96.97 320	93.76 288			91.47 306		98.96 215		98.79 245	94.92 257

test9_res														99.71 49	99.99 21	100.00 1

agg_prior2														99.48 64	100.00 1	100.00 1

agg_prior					99.93 29	98.77 48		98.43 157		99.63 59			99.85 131

TestCases				95.00 328	99.01 132	88.43 423		96.82 425	86.50 417	88.71 380	98.47 281	74.73 418	99.88 125	85.39 417	96.18 260	96.71 335

test_prior				99.43 41	99.94 18	98.49 67		98.65 88					99.80 144			99.99 26

新几何1				99.42 43	99.75 77	98.27 72		98.63 97	92.69 248	99.55 72	99.82 54	94.40 85	100.00 1	91.21 331	99.94 59	99.99 26

旧先验1					99.76 74	97.52 110		98.64 91			99.85 38	95.63 50			99.94 59	99.99 26

原ACMM1				98.96 94	99.73 81	96.99 138		98.51 132	94.06 176	99.62 62	99.85 38	94.97 70	99.96 77	95.11 251	99.95 54	99.92 93

testdata2													99.99 40	90.54 348

segment_acmp												96.68 31

testdata				98.42 142	99.47 104	95.33 218		98.56 114	93.78 190	99.79 37	99.85 38	93.64 116	99.94 95	94.97 255	99.94 59	100.00 1

test12				99.43 41	99.74 78	98.56 63		98.40 179		99.65 55		94.76 74	99.75 155		99.98 32	99.99 26

plane_prior7					95.71 374	91.59 367

plane_prior6					95.76 368	91.72 357						80.47 359

plane_prior5								97.87 261					98.37 304	97.79 172	89.55 335	94.52 349

plane_prior4											98.59 266

plane_prior3						91.64 361			96.63 75	93.01 310

plane_prior1					95.73 371

n2								0.00 567

nn								0.00 567

door-mid								89.69 511

lessismore_v0				90.53 438	90.58 470	80.90 481		95.80 455		77.01 481	95.84 376	66.15 459	96.95 389	83.03 435	75.05 459	93.74 427

LGP-MVS_train				93.71 388	95.43 385	88.67 419		97.62 290	92.81 238	90.05 344	98.49 277	75.24 412	98.40 296	95.84 239	89.12 339	94.07 399

test11								98.44 149

door								90.31 508

HQP5-MVS						91.85 346

BP-MVS														97.92 161

HQP4-MVS										93.37 305			98.39 298			94.53 347

HQP3-MVS								97.89 259							89.60 332

HQP2-MVS												80.65 355

NP-MVS					95.77 367	91.79 350					98.65 258

ACMMP++_ref															87.04 368

ACMMP++															88.23 355

Test By Simon												92.82 142

ITE_SJBPF				92.38 416	95.69 377	85.14 450		95.71 459	92.81 238	89.33 368	98.11 298	70.23 441	98.42 292	85.91 415	88.16 356	93.59 431

DeepMVS_CX				82.92 479	95.98 361	58.66 516		96.01 452	92.72 244	78.34 476	95.51 393	58.29 483	98.08 328	82.57 437	85.29 380	92.03 463

High-resolution multi-view benchmark