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.

mvs5depth		99.30 33	99.59 12	98.44 268	99.65 70	95.35 335	99.82 3	99.94 2	99.83 7	99.42 110	99.94 2	98.13 122	99.96 13	99.63 36	99.96 28	100.00 1

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 74	99.87 12	98.13 143	98.08 194	99.95 1	99.45 50	99.98 2	99.75 16	99.80 1	99.97 6	99.82 12	99.99 5	99.99 2

fmvsm_s_conf0.1_n_a		99.17 52	99.30 44	98.80 190	99.75 34	96.59 276	97.97 224	99.86 16	98.22 197	99.88 21	99.71 22	98.59 67	99.84 175	99.73 28	99.98 12	99.98 3

fmvsm_s_conf0.1_n_2		99.20 50	99.38 28	98.65 223	99.69 60	96.08 302	97.49 297	99.90 11	99.53 41	99.88 21	99.64 37	98.51 76	99.90 81	99.83 10	99.98 12	99.97 4

mmtdpeth		99.30 33	99.42 25	98.92 169	99.58 93	96.89 263	99.48 13	99.92 7	99.92 2	98.26 311	99.80 11	98.33 94	99.91 74	99.56 41	99.95 38	99.97 4

fmvsm_s_conf0.1_n		99.16 56	99.33 37	98.64 225	99.71 48	96.10 297	97.87 237	99.85 18	98.56 172	99.90 14	99.68 25	98.69 57	99.85 157	99.72 30	99.98 12	99.97 4

test_fmvs3		99.12 69	99.41 26	98.25 290	99.76 30	95.07 348	99.05 68	99.94 2	97.78 243	99.82 34	99.84 3	98.56 73	99.71 306	99.96 1	99.96 28	99.97 4

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 83	99.78 24	98.11 144	97.77 251	99.90 11	99.33 65	99.97 3	99.66 32	99.71 3	99.96 13	99.79 19	99.99 5	99.96 8

test_f		98.67 158	98.87 108	98.05 315	99.72 44	95.59 317	98.51 135	99.81 31	96.30 360	99.78 39	99.82 5	96.14 266	98.63 483	99.82 12	99.93 56	99.95 9

test_fmvs2		98.70 145	98.97 96	97.89 326	99.54 122	94.05 384	98.55 126	99.92 7	96.78 336	99.72 47	99.78 13	96.60 246	99.67 335	99.91 2	99.90 86	99.94 10

PS-MVSNAJss		99.46 17	99.49 16	99.35 80	99.90 4	98.15 140	99.20 49	99.65 69	99.48 44	99.92 8	99.71 22	98.07 125	99.96 13	99.53 48	100.00 1	99.93 11

test_vis3_rt		99.14 62	99.17 60	99.07 135	99.78 24	98.38 120	98.92 83	99.94 2	97.80 240	99.91 12	99.67 30	97.15 208	98.91 476	99.76 23	99.56 267	99.92 12

fmvsm_s_conf0.5_n_2		99.14 62	99.31 41	98.63 229	99.49 145	96.08 302	97.38 311	99.81 31	99.48 44	99.84 30	99.57 49	98.46 81	99.89 97	99.82 12	99.97 21	99.91 13

MVStest1		95.86 383	95.60 377	96.63 413	95.87 491	91.70 439	97.93 226	98.94 317	98.03 221	99.56 73	99.66 32	71.83 476	98.26 487	99.35 58	99.24 338	99.91 13

fmvsm_s_conf0.5_n_a		99.10 71	99.20 58	98.78 197	99.55 116	96.59 276	97.79 247	99.82 30	98.21 199	99.81 36	99.53 64	98.46 81	99.84 175	99.70 33	99.97 21	99.90 15

fmvsm_s_conf0.5_n_9		99.17 52	99.38 28	98.53 256	99.51 131	95.82 312	97.62 276	99.78 35	99.72 14	99.90 14	99.48 75	98.66 59	99.89 97	99.85 6	99.93 56	99.89 16

fmvsm_s_conf0.5_n		99.09 72	99.26 50	98.61 235	99.55 116	96.09 300	97.74 258	99.81 31	98.55 173	99.85 27	99.55 56	98.60 66	99.84 175	99.69 35	99.98 12	99.89 16

test_fmvsmconf_n		99.44 19	99.48 18	99.31 94	99.64 76	98.10 146	97.68 265	99.84 22	99.29 71	99.92 8	99.57 49	99.60 5	99.96 13	99.74 27	99.98 12	99.89 16

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 91	99.39 20	99.56 110	99.11 98	99.70 51	99.73 20	99.00 27	99.97 6	99.26 65	99.98 12	99.89 16

fmvsm_s_conf0.5_n_11		99.21 47	99.34 35	98.80 190	99.48 153	96.56 281	97.97 224	99.69 53	99.63 28	99.84 30	99.54 62	98.21 112	99.94 41	99.76 23	99.95 38	99.88 20

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 102	99.34 23	99.71 46	99.27 73	99.90 14	99.74 18	99.68 4	99.97 6	99.55 43	99.99 5	99.88 20

fmvsm_s_conf0.5_n_8		99.13 66	99.26 50	98.74 210	99.51 131	96.44 288	97.65 271	99.65 69	99.66 23	99.78 39	99.48 75	97.92 139	99.93 53	99.72 30	99.95 38	99.87 22

fmvsm_s_conf0.5_n_7		98.83 120	99.04 85	98.20 297	99.30 203	94.83 357	97.23 328	99.36 199	98.64 156	99.84 30	99.43 88	98.10 124	99.91 74	99.56 41	99.96 28	99.87 22

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 83	99.59 91	98.21 137	97.82 242	99.84 22	99.41 57	99.92 8	99.41 94	99.51 8	99.95 25	99.84 9	99.97 21	99.87 22

ttmdpeth		97.91 262	98.02 247	97.58 362	98.69 353	94.10 383	98.13 184	98.90 326	97.95 227	97.32 386	99.58 47	95.95 282	98.75 481	96.41 318	99.22 342	99.87 22

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 102	99.28 40	99.66 65	99.09 108	99.89 18	99.68 25	99.53 7	99.97 6	99.50 50	99.99 5	99.87 22

EU-MVSNet		97.66 287	98.50 171	95.13 453	99.63 82	85.84 484	98.35 161	98.21 393	98.23 196	99.54 78	99.46 80	95.02 310	99.68 331	98.24 143	99.87 97	99.87 22

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 197	99.46 159	96.58 279	97.65 271	99.72 44	99.47 47	99.86 24	99.50 68	98.94 31	99.89 97	99.75 26	99.97 21	99.86 28

UA-Net		99.47 16	99.40 27	99.70 2	99.49 145	99.29 24	99.80 4	99.72 44	99.82 8	99.04 192	99.81 8	98.05 128	99.96 13	98.85 98	99.99 5	99.86 28

fmvsm_l_conf0.5_n_9		99.32 32	99.43 24	98.98 156	99.59 91	97.18 241	97.44 306	99.83 25	99.56 39	99.91 12	99.34 114	99.36 13	99.93 53	99.83 10	99.98 12	99.85 30

MM		98.22 232	97.99 250	98.91 170	98.66 363	96.97 255	97.89 233	94.44 468	99.54 40	98.95 212	99.14 172	93.50 346	99.92 65	99.80 17	99.96 28	99.85 30

LCM-MVSNet		99.93 1	99.92 1	99.94 1	99.99 1	99.97 1	99.90 1	99.89 13	99.98 1	99.99 1	99.96 1	99.77 2	100.00 1	99.81 16	100.00 1	99.85 30

fmvsm_l_conf0.5_n_a		99.19 51	99.27 47	98.94 163	99.65 70	97.05 250	97.80 246	99.76 38	98.70 154	99.78 39	99.11 179	98.79 43	99.95 25	99.85 6	99.96 28	99.83 33

fmvsm_l_conf0.5_n		99.21 47	99.28 46	99.02 148	99.64 76	97.28 229	97.82 242	99.76 38	98.73 147	99.82 34	99.09 187	98.81 39	99.95 25	99.86 4	99.96 28	99.83 33

mvsany_test3		98.87 110	98.92 100	98.74 210	99.38 181	96.94 259	98.58 123	99.10 290	96.49 348	99.96 4	99.81 8	98.18 115	99.45 432	98.97 89	99.79 151	99.83 33

fmvsm_s_conf0.5_n_10		99.15 57	99.27 47	98.78 197	99.47 156	96.56 281	97.75 257	99.71 46	99.60 35	99.74 46	99.44 85	97.96 136	99.95 25	99.86 4	99.94 50	99.82 36

SSC-MVS		98.71 140	98.74 124	98.62 231	99.72 44	96.08 302	98.74 99	98.64 367	99.74 12	99.67 59	99.24 143	94.57 324	99.95 25	99.11 77	99.24 338	99.82 36

anonymousdsp		99.51 14	99.47 21	99.62 10	99.88 9	99.08 69	99.34 23	99.69 53	98.93 130	99.65 63	99.72 21	98.93 33	99.95 25	99.11 77	100.00 1	99.82 36

ANet_high		99.57 10	99.67 6	99.28 96	99.89 6	98.09 147	99.14 58	99.93 5	99.82 8	99.93 6	99.81 8	99.17 20	99.94 41	99.31 61	100.00 1	99.82 36

fmvsm_s_conf0.5_n_4		99.01 87	99.22 54	98.38 275	99.31 199	95.48 326	97.56 287	99.73 43	98.87 138	99.75 44	99.27 130	98.80 41	99.86 144	99.80 17	99.90 86	99.81 40

PS-CasMVS		99.40 25	99.33 37	99.62 10	99.71 48	99.10 65	99.29 36	99.53 123	99.53 41	99.46 101	99.41 94	98.23 107	99.95 25	98.89 96	99.95 38	99.81 40

VortexMVS		97.98 260	98.31 208	97.02 395	98.88 314	91.45 444	98.03 205	99.47 151	98.65 155	99.55 76	99.47 78	91.49 379	99.81 223	99.32 60	99.91 78	99.80 42

FC-MVSNet-test		99.27 37	99.25 52	99.34 83	99.77 27	98.37 122	99.30 35	99.57 101	99.61 34	99.40 115	99.50 68	97.12 209	99.85 157	99.02 86	99.94 50	99.80 42

test_cas_vis1_n_1920		98.33 216	98.68 139	97.27 384	99.69 60	92.29 433	98.03 205	99.85 18	97.62 254	99.96 4	99.62 40	93.98 339	99.74 288	99.52 49	99.86 104	99.79 44

test_vis1_n_1920		98.40 202	98.92 100	96.81 408	99.74 36	90.76 461	98.15 182	99.91 9	98.33 185	99.89 18	99.55 56	95.07 309	99.88 115	99.76 23	99.93 56	99.79 44

CP-MVSNet		99.21 47	99.09 80	99.56 26	99.65 70	98.96 77	99.13 59	99.34 211	99.42 55	99.33 130	99.26 136	97.01 217	99.94 41	98.74 107	99.93 56	99.79 44

fmvsm_s_conf0.5_n_5		99.07 79	99.10 78	98.99 152	99.47 156	97.22 235	97.40 308	99.83 25	97.61 257	99.85 27	99.30 124	98.80 41	99.95 25	99.71 32	99.90 86	99.78 47

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 19	99.69 5	99.58 94	99.90 3	99.86 24	99.78 13	99.58 6	99.95 25	99.00 87	99.95 38	99.78 47

CVMVSNet		96.25 369	97.21 309	93.38 474	99.10 260	80.56 502	97.20 333	98.19 396	96.94 323	99.00 197	99.02 202	89.50 398	99.80 232	96.36 322	99.59 255	99.78 47

TestfortrainingZip a		98.95 98	98.72 128	99.64 9	99.58 93	99.32 21	98.68 109	99.60 84	96.46 351	99.53 82	98.77 276	97.87 146	99.83 193	98.39 136	99.64 234	99.77 50

reproduce_monomvs		95.00 408	95.25 394	94.22 462	97.51 452	83.34 494	97.86 238	98.44 381	98.51 174	99.29 140	99.30 124	67.68 484	99.56 392	98.89 96	99.81 134	99.77 50

Anonymous20231211		99.27 37	99.27 47	99.26 101	99.29 205	98.18 138	99.49 12	99.51 129	99.70 15	99.80 37	99.68 25	96.84 226	99.83 193	99.21 70	99.91 78	99.77 50

PEN-MVS		99.41 24	99.34 35	99.62 10	99.73 37	99.14 57	99.29 36	99.54 119	99.62 32	99.56 73	99.42 89	98.16 119	99.96 13	98.78 102	99.93 56	99.77 50

WR-MVS_H		99.33 30	99.22 54	99.65 8	99.71 48	99.24 30	99.32 26	99.55 114	99.46 49	99.50 93	99.34 114	97.30 197	99.93 53	98.90 94	99.93 56	99.77 50

LTVRE_ROB	98.40 1	99.67 3	99.71 2	99.56 26	99.85 16	99.11 64	99.90 1	99.78 35	99.63 28	99.78 39	99.67 30	99.48 10	99.81 223	99.30 62	99.97 21	99.77 50
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
WB-MVS		98.52 189	98.55 162	98.43 269	99.65 70	95.59 317	98.52 130	98.77 352	99.65 25	99.52 87	99.00 217	94.34 330	99.93 53	98.65 114	98.83 386	99.76 56

patch_mono-2		98.51 190	98.63 149	98.17 300	99.38 181	94.78 359	97.36 316	99.69 53	98.16 209	98.49 292	99.29 127	97.06 212	99.97 6	98.29 142	99.91 78	99.76 56

nrg030		99.40 25	99.35 33	99.54 31	99.58 93	99.13 60	98.98 76	99.48 142	99.68 19	99.46 101	99.26 136	98.62 64	99.73 295	99.17 74	99.92 69	99.76 56

FIs		99.14 62	99.09 80	99.29 95	99.70 56	98.28 128	99.13 59	99.52 128	99.48 44	99.24 158	99.41 94	96.79 233	99.82 206	98.69 112	99.88 93	99.76 56

v7n		99.53 12	99.57 13	99.41 69	99.88 9	98.54 110	99.45 14	99.61 82	99.66 23	99.68 57	99.66 32	98.44 83	99.95 25	99.73 28	99.96 28	99.75 60

APDe-MVS		98.99 90	98.79 120	99.60 16	99.21 230	99.15 52	98.87 89	99.48 142	97.57 261	99.35 125	99.24 143	97.83 149	99.89 97	97.88 178	99.70 209	99.75 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet		99.43 22	99.35 33	99.66 7	99.71 48	99.30 22	99.31 30	99.51 129	99.64 26	99.56 73	99.46 80	98.23 107	99.97 6	98.78 102	99.93 56	99.72 62

MSC_two_6792asdad				99.32 91	98.43 392	98.37 122		98.86 337					99.89 97	97.14 243	99.60 251	99.71 63

No_MVS				99.32 91	98.43 392	98.37 122		98.86 337					99.89 97	97.14 243	99.60 251	99.71 63

PMMVS2		98.07 249	98.08 241	98.04 316	99.41 176	94.59 368	94.59 461	99.40 187	97.50 270	98.82 243	98.83 263	96.83 228	99.84 175	97.50 215	99.81 134	99.71 63

Baseline_NR-MVSNet		98.98 94	98.86 112	99.36 74	99.82 19	98.55 107	97.47 302	99.57 101	99.37 60	99.21 164	99.61 43	96.76 236	99.83 193	98.06 159	99.83 122	99.71 63

XXY-MVS		99.14 62	99.15 67	99.10 128	99.76 30	97.74 193	98.85 93	99.62 79	98.48 176	99.37 120	99.49 74	98.75 47	99.86 144	98.20 148	99.80 145	99.71 63

test_0728_THIRD									98.17 206	99.08 180	99.02 202	97.89 144	99.88 115	97.07 249	99.71 202	99.70 68

MSP-MVS		98.40 202	98.00 249	99.61 14	99.57 102	99.25 29	98.57 124	99.35 205	97.55 265	99.31 138	97.71 395	94.61 323	99.88 115	96.14 335	99.19 349	99.70 68
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
SSC-MVS3.2		98.53 185	98.79 120	97.74 341	99.46 159	93.62 410	96.45 376	99.34 211	99.33 65	98.93 220	98.70 295	97.90 140	99.90 81	99.12 76	99.92 69	99.69 70

NormalMVS		98.26 227	97.97 254	99.15 121	99.64 76	97.83 180	98.28 166	99.43 174	99.24 75	98.80 247	98.85 256	89.76 394	99.94 41	98.04 162	99.67 223	99.68 71

KinetiMVS		99.03 85	99.02 88	99.03 145	99.70 56	97.48 210	98.43 148	99.29 240	99.70 15	99.60 70	99.07 189	96.13 267	99.94 41	99.42 55	99.87 97	99.68 71

dcpmvs_2		98.78 131	99.11 72	97.78 334	99.56 110	93.67 407	99.06 66	99.86 16	99.50 43	99.66 60	99.26 136	97.21 205	99.99 2	98.00 167	99.91 78	99.68 71

test_0728_SECOND				99.60 16	99.50 137	99.23 31	98.02 208	99.32 219					99.88 115	96.99 256	99.63 241	99.68 71

OurMVSNet-221017-0		99.37 28	99.31 41	99.53 38	99.91 3	98.98 71	99.63 7	99.58 94	99.44 52	99.78 39	99.76 15	96.39 254	99.92 65	99.44 54	99.92 69	99.68 71

fmvsm_s_conf0.5_n_6		99.08 77	99.21 57	98.69 218	99.36 188	96.51 283	97.62 276	99.68 59	98.43 178	99.85 27	99.10 182	99.12 23	99.88 115	99.77 22	99.92 69	99.67 76

CHOSEN 1792x2688		97.49 299	97.14 314	98.54 254	99.68 63	96.09 300	96.50 374	99.62 79	91.58 459	98.84 239	98.97 226	92.36 365	99.88 115	96.76 279	99.95 38	99.67 76

reproduce_model		99.15 57	98.97 96	99.67 4	99.33 197	99.44 9	98.15 182	99.47 151	99.12 97	99.52 87	99.32 122	98.31 95	99.90 81	97.78 186	99.73 185	99.66 78

IU-MVS					99.49 145	99.15 52		98.87 332	92.97 444	99.41 112				96.76 279	99.62 244	99.66 78

test_241102_TWO								99.30 232	98.03 221	99.26 148	99.02 202	97.51 182	99.88 115	96.91 262	99.60 251	99.66 78

DPE-MVS		98.59 172	98.26 216	99.57 21	99.27 211	99.15 52	97.01 343	99.39 189	97.67 250	99.44 105	98.99 219	97.53 179	99.89 97	95.40 365	99.68 217	99.66 78
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TransMVSNet (Re)		99.44 19	99.47 21	99.36 74	99.80 21	98.58 105	99.27 42	99.57 101	99.39 58	99.75 44	99.62 40	99.17 20	99.83 193	99.06 82	99.62 244	99.66 78

EI-MVSNet-UG-set		98.69 149	98.71 133	98.62 231	99.10 260	96.37 290	97.23 328	98.87 332	99.20 82	99.19 166	98.99 219	97.30 197	99.85 157	98.77 105	99.79 151	99.65 83

Elysia		99.15 57	99.14 68	99.18 113	99.63 82	97.92 170	98.50 137	99.43 174	99.67 20	99.70 51	99.13 174	96.66 242	99.98 4	99.54 44	99.96 28	99.64 84

StellarMVS		99.15 57	99.14 68	99.18 113	99.63 82	97.92 170	98.50 137	99.43 174	99.67 20	99.70 51	99.13 174	96.66 242	99.98 4	99.54 44	99.96 28	99.64 84

pmmvs6		99.67 3	99.70 3	99.60 16	99.90 4	99.27 27	99.53 9	99.76 38	99.64 26	99.84 30	99.83 4	99.50 9	99.87 135	99.36 57	99.92 69	99.64 84

EI-MVSNet-Vis-set		98.68 155	98.70 136	98.63 229	99.09 263	96.40 289	97.23 328	98.86 337	99.20 82	99.18 171	98.97 226	97.29 199	99.85 157	98.72 109	99.78 156	99.64 84

ACMH	96.65 7	99.25 40	99.24 53	99.26 101	99.72 44	98.38 120	99.07 65	99.55 114	98.30 189	99.65 63	99.45 84	99.22 17	99.76 269	98.44 129	99.77 162	99.64 84
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DP-MVS		98.93 101	98.81 119	99.28 96	99.21 230	98.45 116	98.46 145	99.33 217	99.63 28	99.48 96	99.15 169	97.23 203	99.75 281	97.17 239	99.66 231	99.63 89

reproduce-ours		99.09 72	98.90 102	99.67 4	99.27 211	99.49 5	98.00 212	99.42 180	99.05 115	99.48 96	99.27 130	98.29 97	99.89 97	97.61 203	99.71 202	99.62 90

our_new_method		99.09 72	98.90 102	99.67 4	99.27 211	99.49 5	98.00 212	99.42 180	99.05 115	99.48 96	99.27 130	98.29 97	99.89 97	97.61 203	99.71 202	99.62 90

test_fmvs1_n		98.09 247	98.28 212	97.52 370	99.68 63	93.47 412	98.63 116	99.93 5	95.41 399	99.68 57	99.64 37	91.88 375	99.48 423	99.82 12	99.87 97	99.62 90

test1111		96.49 361	96.82 335	95.52 445	99.42 173	87.08 481	99.22 46	87.14 497	99.11 98	99.46 101	99.58 47	88.69 402	99.86 144	98.80 100	99.95 38	99.62 90

VPA-MVSNet		99.30 33	99.30 44	99.28 96	99.49 145	98.36 125	99.00 73	99.45 160	99.63 28	99.52 87	99.44 85	98.25 105	99.88 115	99.09 79	99.84 111	99.62 90

LPG-MVS_test		98.71 140	98.46 181	99.47 60	99.57 102	98.97 73	98.23 172	99.48 142	96.60 343	99.10 178	99.06 190	98.71 51	99.83 193	95.58 361	99.78 156	99.62 90

LGP-MVS_train				99.47 60	99.57 102	98.97 73		99.48 142	96.60 343	99.10 178	99.06 190	98.71 51	99.83 193	95.58 361	99.78 156	99.62 90

Test_1112_low_res		96.99 342	96.55 353	98.31 284	99.35 193	95.47 329	95.84 417	99.53 123	91.51 461	96.80 413	98.48 334	91.36 380	99.83 193	96.58 300	99.53 277	99.62 90

tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 44	98.98 71	99.51 10	99.85 18	99.86 6	99.88 21	99.82 5	99.02 26	99.90 81	99.54 44	99.95 38	99.61 98

v10		98.97 95	99.11 72	98.55 249	99.44 166	96.21 296	98.90 84	99.55 114	98.73 147	99.48 96	99.60 45	96.63 245	99.83 193	99.70 33	99.99 5	99.61 98

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 73	99.88 4	99.86 24	99.80 11	99.03 24	99.89 97	99.48 52	99.93 56	99.60 100

test_vis1_n		98.31 219	98.50 171	97.73 344	99.76 30	94.17 379	98.68 109	99.91 9	96.31 358	99.79 38	99.57 49	92.85 359	99.42 437	99.79 19	99.84 111	99.60 100

v8		99.01 87	99.16 62	98.57 242	99.47 156	96.31 293	98.90 84	99.47 151	99.03 119	99.52 87	99.57 49	96.93 222	99.81 223	99.60 37	99.98 12	99.60 100

EI-MVSNet		98.40 202	98.51 168	98.04 316	99.10 260	94.73 362	97.20 333	98.87 332	98.97 125	99.06 182	99.02 202	96.00 274	99.80 232	98.58 118	99.82 128	99.60 100

SixPastTwentyTwo		98.75 136	98.62 151	99.16 118	99.83 18	97.96 167	99.28 40	98.20 394	99.37 60	99.70 51	99.65 36	92.65 363	99.93 53	99.04 84	99.84 111	99.60 100

IterMVS-LS		98.55 180	98.70 136	98.09 308	99.48 153	94.73 362	97.22 332	99.39 189	98.97 125	99.38 118	99.31 123	96.00 274	99.93 53	98.58 118	99.97 21	99.60 100
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		97.19 327	96.60 351	98.96 160	99.62 86	97.28 229	95.17 442	99.50 132	94.21 426	99.01 196	98.32 352	86.61 416	99.99 2	97.10 247	99.84 111	99.60 100

lecture		99.25 40	99.12 70	99.62 10	99.64 76	99.40 11	98.89 88	99.51 129	99.19 87	99.37 120	99.25 141	98.36 88	99.88 115	98.23 145	99.67 223	99.59 107

tt0320		99.61 8	99.65 9	99.48 56	99.71 48	98.94 78	99.54 8	99.83 25	99.87 5	99.89 18	99.82 5	98.75 47	99.90 81	99.54 44	99.95 38	99.59 107

ACMMP_NAP		98.75 136	98.48 177	99.57 21	99.58 93	99.29 24	97.82 242	99.25 254	96.94 323	98.78 249	99.12 177	98.02 129	99.84 175	97.13 245	99.67 223	99.59 107

VPNet		98.87 110	98.83 116	99.01 149	99.70 56	97.62 202	98.43 148	99.35 205	99.47 47	99.28 142	99.05 197	96.72 239	99.82 206	98.09 156	99.36 315	99.59 107

WR-MVS		98.40 202	98.19 227	99.03 145	99.00 289	97.65 199	96.85 353	98.94 317	98.57 169	98.89 227	98.50 331	95.60 292	99.85 157	97.54 211	99.85 106	99.59 107

HPM-MVS		98.79 129	98.53 166	99.59 20	99.65 70	99.29 24	99.16 55	99.43 174	96.74 338	98.61 273	98.38 344	98.62 64	99.87 135	96.47 314	99.67 223	99.59 107
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EG-PatchMatch MVS		98.99 90	99.01 90	98.94 163	99.50 137	97.47 211	98.04 203	99.59 91	98.15 214	99.40 115	99.36 109	98.58 72	99.76 269	98.78 102	99.68 217	99.59 107

Vis-MVSNet		99.34 29	99.36 32	99.27 99	99.73 37	98.26 129	99.17 54	99.78 35	99.11 98	99.27 144	99.48 75	98.82 38	99.95 25	98.94 91	99.93 56	99.59 107
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MED-MVS test				99.45 63	99.58 93	98.93 79	98.68 109	99.60 84	96.46 351	99.53 82	98.77 276		99.83 193	96.67 291	99.64 234	99.58 115

MED-MVS		98.90 105	98.72 128	99.45 63	99.58 93	98.93 79	98.68 109	99.60 84	98.14 215	99.53 82	98.77 276	97.87 146	99.83 193	96.67 291	99.64 234	99.58 115

ME-MVS		98.61 168	98.33 206	99.44 65	99.24 222	98.93 79	97.45 304	99.06 295	98.14 215	99.06 182	98.77 276	96.97 220	99.82 206	96.67 291	99.64 234	99.58 115

MP-MVS-pluss		98.57 175	98.23 221	99.60 16	99.69 60	99.35 16	97.16 338	99.38 191	94.87 411	98.97 206	98.99 219	98.01 130	99.88 115	97.29 232	99.70 209	99.58 115
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		98.69 149	98.40 189	99.54 31	99.53 125	99.17 44	98.52 130	99.31 224	97.46 278	98.44 296	98.51 327	97.83 149	99.88 115	96.46 315	99.58 260	99.58 115

ACMMPR		98.70 145	98.42 187	99.54 31	99.52 128	99.14 57	98.52 130	99.31 224	97.47 273	98.56 283	98.54 322	97.75 157	99.88 115	96.57 302	99.59 255	99.58 115

PGM-MVS		98.66 159	98.37 196	99.55 28	99.53 125	99.18 43	98.23 172	99.49 140	97.01 320	98.69 260	98.88 250	98.00 131	99.89 97	95.87 347	99.59 255	99.58 115

SteuartSystems-ACMMP		98.79 129	98.54 164	99.54 31	99.73 37	99.16 48	98.23 172	99.31 224	97.92 231	98.90 224	98.90 243	98.00 131	99.88 115	96.15 334	99.72 193	99.58 115
Skip Steuart: Steuart Systems R&D Blog.
SDMVSNet		99.23 45	99.32 39	98.96 160	99.68 63	97.35 218	98.84 95	99.48 142	99.69 17	99.63 66	99.68 25	99.03 24	99.96 13	97.97 171	99.92 69	99.57 123

sd_testset		99.28 36	99.31 41	99.19 112	99.68 63	98.06 156	99.41 17	99.30 232	99.69 17	99.63 66	99.68 25	99.25 16	99.96 13	97.25 235	99.92 69	99.57 123

TranMVSNet+NR-MVSNet		99.17 52	99.07 83	99.46 62	99.37 187	98.87 84	98.39 157	99.42 180	99.42 55	99.36 123	99.06 190	98.38 87	99.95 25	98.34 139	99.90 86	99.57 123

mPP-MVS		98.64 162	98.34 201	99.54 31	99.54 122	99.17 44	98.63 116	99.24 259	97.47 273	98.09 325	98.68 299	97.62 168	99.89 97	96.22 329	99.62 244	99.57 123

PVSNet_Blended_VisFu		98.17 241	98.15 233	98.22 296	99.73 37	95.15 344	97.36 316	99.68 59	94.45 421	98.99 201	99.27 130	96.87 225	99.94 41	97.13 245	99.91 78	99.57 123

1112_ss		97.29 319	96.86 331	98.58 239	99.34 196	96.32 292	96.75 359	99.58 94	93.14 442	96.89 408	97.48 409	92.11 372	99.86 144	96.91 262	99.54 273	99.57 123

MTAPA		98.88 109	98.64 147	99.61 14	99.67 67	99.36 15	98.43 148	99.20 265	98.83 145	98.89 227	98.90 243	96.98 219	99.92 65	97.16 240	99.70 209	99.56 129

XVS		98.72 139	98.45 182	99.53 38	99.46 159	99.21 33	98.65 114	99.34 211	98.62 161	97.54 368	98.63 311	97.50 183	99.83 193	96.79 275	99.53 277	99.56 129

pm-mvs1		99.44 19	99.48 18	99.33 89	99.80 21	98.63 99	99.29 36	99.63 73	99.30 70	99.65 63	99.60 45	99.16 22	99.82 206	99.07 80	99.83 122	99.56 129

X-MVStestdata		94.32 415	92.59 434	99.53 38	99.46 159	99.21 33	98.65 114	99.34 211	98.62 161	97.54 368	45.85 499	97.50 183	99.83 193	96.79 275	99.53 277	99.56 129

HPM-MVS_fast		99.01 87	98.82 117	99.57 21	99.71 48	99.35 16	99.00 73	99.50 132	97.33 290	98.94 219	98.86 253	98.75 47	99.82 206	97.53 212	99.71 202	99.56 129

K. test v3		98.00 256	97.66 281	99.03 145	99.79 23	97.56 204	99.19 53	92.47 480	99.62 32	99.52 87	99.66 32	89.61 396	99.96 13	99.25 67	99.81 134	99.56 129

CP-MVS		98.70 145	98.42 187	99.52 44	99.36 188	99.12 62	98.72 104	99.36 199	97.54 267	98.30 305	98.40 341	97.86 148	99.89 97	96.53 311	99.72 193	99.56 129

viewmacassd2359aftdt		98.86 114	98.87 108	98.83 183	99.53 125	97.32 222	97.70 263	99.64 71	98.22 197	99.25 156	99.27 130	98.40 85	99.61 372	97.98 170	99.87 97	99.55 136

FE-MVSNET		98.59 172	98.50 171	98.87 174	99.58 93	97.30 223	98.08 194	99.74 42	96.94 323	98.97 206	99.10 182	96.94 221	99.74 288	97.33 229	99.86 104	99.55 136

ZNCC-MVS		98.68 155	98.40 189	99.54 31	99.57 102	99.21 33	98.46 145	99.29 240	97.28 296	98.11 323	98.39 342	98.00 131	99.87 135	96.86 272	99.64 234	99.55 136

v1192		98.60 170	98.66 144	98.41 271	99.27 211	95.88 308	97.52 292	99.36 199	97.41 282	99.33 130	99.20 152	96.37 257	99.82 206	99.57 39	99.92 69	99.55 136

v1240		98.55 180	98.62 151	98.32 282	99.22 228	95.58 319	97.51 294	99.45 160	97.16 311	99.45 104	99.24 143	96.12 269	99.85 157	99.60 37	99.88 93	99.55 136

UGNet		98.53 185	98.45 182	98.79 194	97.94 423	96.96 257	99.08 62	98.54 376	99.10 105	96.82 412	99.47 78	96.55 248	99.84 175	98.56 123	99.94 50	99.55 136
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
usedtu_dtu_shiyan2		98.99 90	98.86 112	99.39 72	99.73 37	98.71 97	99.05 68	99.47 151	99.16 92	99.49 94	99.12 177	96.34 259	99.93 53	98.05 161	99.36 315	99.54 142

E5new		99.05 80	99.11 72	98.85 177	99.60 87	97.30 223	98.42 151	99.63 73	98.73 147	99.26 148	99.39 100	98.71 51	99.70 313	98.43 131	99.84 111	99.54 142

E6new		99.05 80	99.11 72	98.85 177	99.60 87	97.30 223	98.42 151	99.63 73	98.73 147	99.26 148	99.39 100	98.71 51	99.70 313	98.43 131	99.84 111	99.54 142

E6		99.05 80	99.11 72	98.85 177	99.60 87	97.30 223	98.42 151	99.63 73	98.73 147	99.26 148	99.39 100	98.71 51	99.70 313	98.43 131	99.84 111	99.54 142

E5		99.05 80	99.11 72	98.85 177	99.60 87	97.30 223	98.42 151	99.63 73	98.73 147	99.26 148	99.39 100	98.71 51	99.70 313	98.43 131	99.84 111	99.54 142

AstraMVS		98.16 243	98.07 243	98.41 271	99.51 131	95.86 309	98.00 212	95.14 463	98.97 125	99.43 106	99.24 143	93.25 347	99.84 175	99.21 70	99.87 97	99.54 142

WBMVS		95.18 403	94.78 406	96.37 419	97.68 440	89.74 469	95.80 418	98.73 360	97.54 267	98.30 305	98.44 338	70.06 478	99.82 206	96.62 297	99.87 97	99.54 142

test2506		92.39 446	91.89 448	93.89 467	99.38 181	82.28 498	99.32 26	66.03 505	99.08 112	98.77 252	99.57 49	66.26 488	99.84 175	98.71 110	99.95 38	99.54 142

ECVR-MVS		96.42 363	96.61 349	95.85 436	99.38 181	88.18 476	99.22 46	86.00 499	99.08 112	99.36 123	99.57 49	88.47 407	99.82 206	98.52 126	99.95 38	99.54 142

v144192		98.54 183	98.57 160	98.45 266	99.21 230	95.98 305	97.63 275	99.36 199	97.15 313	99.32 136	99.18 159	95.84 286	99.84 175	99.50 50	99.91 78	99.54 142

v1921920		98.54 183	98.60 156	98.38 275	99.20 234	95.76 315	97.56 287	99.36 199	97.23 305	99.38 118	99.17 163	96.02 272	99.84 175	99.57 39	99.90 86	99.54 142

MP-MVS		98.46 195	98.09 238	99.54 31	99.57 102	99.22 32	98.50 137	99.19 269	97.61 257	97.58 364	98.66 304	97.40 191	99.88 115	94.72 380	99.60 251	99.54 142
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MIMVSNet1		99.38 27	99.32 39	99.55 28	99.86 14	99.19 42	99.41 17	99.59 91	99.59 36	99.71 49	99.57 49	97.12 209	99.90 81	99.21 70	99.87 97	99.54 142

ACMMP		98.75 136	98.50 171	99.52 44	99.56 110	99.16 48	98.87 89	99.37 195	97.16 311	98.82 243	99.01 213	97.71 159	99.87 135	96.29 326	99.69 212	99.54 142
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
SMA-MVS		98.40 202	98.03 246	99.51 48	99.16 249	99.21 33	98.05 201	99.22 262	94.16 427	98.98 202	99.10 182	97.52 181	99.79 245	96.45 316	99.64 234	99.53 156
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
HFP-MVS		98.71 140	98.44 184	99.51 48	99.49 145	99.16 48	98.52 130	99.31 224	97.47 273	98.58 279	98.50 331	97.97 135	99.85 157	96.57 302	99.59 255	99.53 156

UniMVSNet_NR-MVSNet		98.86 114	98.68 139	99.40 71	99.17 247	98.74 91	97.68 265	99.40 187	99.14 96	99.06 182	98.59 318	96.71 240	99.93 53	98.57 120	99.77 162	99.53 156

E4		98.87 110	98.88 105	98.81 187	99.52 128	97.23 232	97.62 276	99.61 82	98.58 167	99.18 171	99.33 117	98.29 97	99.69 321	97.99 169	99.83 122	99.52 159

GST-MVS		98.61 168	98.30 209	99.52 44	99.51 131	99.20 39	98.26 170	99.25 254	97.44 281	98.67 263	98.39 342	97.68 160	99.85 157	96.00 339	99.51 283	99.52 159

MGCNet		97.44 304	97.01 322	98.72 214	96.42 483	96.74 271	97.20 333	91.97 487	98.46 177	98.30 305	98.79 272	92.74 361	99.91 74	99.30 62	99.94 50	99.52 159

TDRefinement		99.42 23	99.38 28	99.55 28	99.76 30	99.33 20	99.68 6	99.71 46	99.38 59	99.53 82	99.61 43	98.64 61	99.80 232	98.24 143	99.84 111	99.52 159

FE-MVSNET2		99.15 57	99.22 54	98.94 163	99.70 56	97.49 207	98.62 118	99.67 64	98.85 143	99.34 127	99.54 62	98.47 77	99.81 223	98.93 92	99.91 78	99.51 163

v1144		98.60 170	98.66 144	98.41 271	99.36 188	95.90 307	97.58 285	99.34 211	97.51 269	99.27 144	99.15 169	96.34 259	99.80 232	99.47 53	99.93 56	99.51 163

v2v482		98.56 176	98.62 151	98.37 278	99.42 173	95.81 313	97.58 285	99.16 280	97.90 233	99.28 142	99.01 213	95.98 279	99.79 245	99.33 59	99.90 86	99.51 163

CPTT-MVS		97.84 276	97.36 300	99.27 99	99.31 199	98.46 115	98.29 165	99.27 247	94.90 410	97.83 348	98.37 345	94.90 312	99.84 175	93.85 408	99.54 273	99.51 163

casdiffseed414692147		99.09 72	99.12 70	99.01 149	99.55 116	97.91 172	98.30 164	99.68 59	99.04 117	99.19 166	99.37 104	98.98 28	99.61 372	98.13 152	99.83 122	99.50 167

viewdifsd2359ckpt11		98.84 117	99.04 85	98.24 292	99.56 110	95.51 322	97.38 311	99.70 51	99.16 92	99.57 71	99.40 97	98.26 103	99.71 306	98.55 124	99.82 128	99.50 167

viewmsd2359difaftdt		98.84 117	99.04 85	98.24 292	99.56 110	95.51 322	97.38 311	99.70 51	99.16 92	99.57 71	99.40 97	98.26 103	99.71 306	98.55 124	99.82 128	99.50 167

LuminaMVS		98.39 208	98.20 223	98.98 156	99.50 137	97.49 207	97.78 248	97.69 409	98.75 146	99.49 94	99.25 141	92.30 367	99.94 41	99.14 75	99.88 93	99.50 167

DU-MVS		98.82 123	98.63 149	99.39 72	99.16 249	98.74 91	97.54 290	99.25 254	98.84 144	99.06 182	98.76 282	96.76 236	99.93 53	98.57 120	99.77 162	99.50 167

NR-MVSNet		98.95 98	98.82 117	99.36 74	99.16 249	98.72 96	99.22 46	99.20 265	99.10 105	99.72 47	98.76 282	96.38 256	99.86 144	98.00 167	99.82 128	99.50 167

casdiffmvs_mvg		99.12 69	99.16 62	98.99 152	99.43 171	97.73 195	98.00 212	99.62 79	99.22 78	99.55 76	99.22 149	98.93 33	99.75 281	98.66 113	99.81 134	99.50 167
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMH+	96.62 9	99.08 77	99.00 92	99.33 89	99.71 48	98.83 86	98.60 121	99.58 94	99.11 98	99.53 82	99.18 159	98.81 39	99.67 335	96.71 286	99.77 162	99.50 167

SymmetryMVS		98.05 251	97.71 276	99.09 132	99.29 205	97.83 180	98.28 166	97.64 414	99.24 75	98.80 247	98.85 256	89.76 394	99.94 41	98.04 162	99.50 291	99.49 175

DVP-MVS++		98.90 105	98.70 136	99.51 48	98.43 392	99.15 52	99.43 15	99.32 219	98.17 206	99.26 148	99.02 202	98.18 115	99.88 115	97.07 249	99.45 298	99.49 175

PC_three_1452									93.27 440	99.40 115	98.54 322	98.22 110	97.00 494	95.17 368	99.45 298	99.49 175

GeoE		99.05 80	98.99 94	99.25 104	99.44 166	98.35 126	98.73 103	99.56 110	98.42 179	98.91 223	98.81 269	98.94 31	99.91 74	98.35 138	99.73 185	99.49 175

h-mvs33		97.77 279	97.33 303	99.10 128	99.21 230	97.84 179	98.35 161	98.57 373	99.11 98	98.58 279	99.02 202	88.65 405	99.96 13	98.11 154	96.34 466	99.49 175

IterMVS-SCA-FT		97.85 275	98.18 228	96.87 404	99.27 211	91.16 454	95.53 427	99.25 254	99.10 105	99.41 112	99.35 110	93.10 352	99.96 13	98.65 114	99.94 50	99.49 175

new-patchmatchnet		98.35 211	98.74 124	97.18 387	99.24 222	92.23 435	96.42 380	99.48 142	98.30 189	99.69 55	99.53 64	97.44 189	99.82 206	98.84 99	99.77 162	99.49 175

APD-MVS		98.10 245	97.67 278	99.42 67	99.11 258	98.93 79	97.76 254	99.28 244	94.97 408	98.72 258	98.77 276	97.04 213	99.85 157	93.79 409	99.54 273	99.49 175
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EPP-MVSNet		98.30 220	98.04 245	99.07 135	99.56 110	97.83 180	99.29 36	98.07 400	99.03 119	98.59 277	99.13 174	92.16 369	99.90 81	96.87 270	99.68 217	99.49 175

DeepC-MVS	97.60 4	98.97 95	98.93 99	99.10 128	99.35 193	97.98 163	98.01 211	99.46 156	97.56 263	99.54 78	99.50 68	98.97 29	99.84 175	98.06 159	99.92 69	99.49 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMM	96.08 12	98.91 103	98.73 126	99.48 56	99.55 116	99.14 57	98.07 198	99.37 195	97.62 254	99.04 192	98.96 229	98.84 37	99.79 245	97.43 223	99.65 232	99.49 175
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
guyue		98.01 255	97.93 259	98.26 288	99.45 164	95.48 326	98.08 194	96.24 446	98.89 136	99.34 127	99.14 172	91.32 381	99.82 206	99.07 80	99.83 122	99.48 186

DVP-MVS		98.77 134	98.52 167	99.52 44	99.50 137	99.21 33	98.02 208	98.84 341	97.97 225	99.08 180	99.02 202	97.61 170	99.88 115	96.99 256	99.63 241	99.48 186
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
SR-MVS		98.71 140	98.43 185	99.57 21	99.18 245	99.35 16	98.36 160	99.29 240	98.29 192	98.88 231	98.85 256	97.53 179	99.87 135	96.14 335	99.31 326	99.48 186

TSAR-MVS + MP.		98.63 164	98.49 176	99.06 141	99.64 76	97.90 174	98.51 135	98.94 317	96.96 321	99.24 158	98.89 249	97.83 149	99.81 223	96.88 269	99.49 293	99.48 186
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
VDDNet		98.21 234	97.95 255	99.01 149	99.58 93	97.74 193	99.01 71	97.29 422	99.67 20	98.97 206	99.50 68	90.45 389	99.80 232	97.88 178	99.20 346	99.48 186

IterMVS		97.73 281	98.11 237	96.57 414	99.24 222	90.28 464	95.52 429	99.21 263	98.86 140	99.33 130	99.33 117	93.11 351	99.94 41	98.49 127	99.94 50	99.48 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IS-MVSNet		98.19 237	97.90 263	99.08 133	99.57 102	97.97 164	99.31 30	98.32 387	99.01 121	98.98 202	99.03 201	91.59 377	99.79 245	95.49 363	99.80 145	99.48 186

ACMP	95.32 15	98.41 199	98.09 238	99.36 74	99.51 131	98.79 89	97.68 265	99.38 191	95.76 386	98.81 245	98.82 266	98.36 88	99.82 206	94.75 377	99.77 162	99.48 186
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MCST-MVS		98.00 256	97.63 284	99.10 128	99.24 222	98.17 139	96.89 352	98.73 360	95.66 387	97.92 339	97.70 397	97.17 207	99.66 348	96.18 333	99.23 341	99.47 194

3Dnovator+	97.89 3	98.69 149	98.51 168	99.24 106	98.81 329	98.40 118	99.02 70	99.19 269	98.99 122	98.07 327	99.28 128	97.11 211	99.84 175	96.84 273	99.32 324	99.47 194

diffmvs_AUTHOR		98.50 191	98.59 158	98.23 295	99.35 193	95.48 326	96.61 367	99.60 84	98.37 180	98.90 224	99.00 217	97.37 193	99.76 269	98.22 146	99.85 106	99.46 196

HPM-MVS++		98.10 245	97.64 283	99.48 56	99.09 263	99.13 60	97.52 292	98.75 357	97.46 278	96.90 407	97.83 388	96.01 273	99.84 175	95.82 351	99.35 318	99.46 196

V42		98.78 131	98.78 122	98.76 204	99.44 166	97.04 251	98.27 169	99.19 269	97.87 235	99.25 156	99.16 165	96.84 226	99.78 257	99.21 70	99.84 111	99.46 196

APD-MVS_3200maxsize		98.84 117	98.61 155	99.53 38	99.19 237	99.27 27	98.49 140	99.33 217	98.64 156	99.03 195	98.98 224	97.89 144	99.85 157	96.54 310	99.42 308	99.46 196

UniMVSNet (Re)		98.87 110	98.71 133	99.35 80	99.24 222	98.73 94	97.73 260	99.38 191	98.93 130	99.12 174	98.73 285	96.77 234	99.86 144	98.63 116	99.80 145	99.46 196

SR-MVS-dyc-post		98.81 125	98.55 162	99.57 21	99.20 234	99.38 12	98.48 143	99.30 232	98.64 156	98.95 212	98.96 229	97.49 186	99.86 144	96.56 306	99.39 311	99.45 201

RE-MVS-def			98.58 159		99.20 234	99.38 12	98.48 143	99.30 232	98.64 156	98.95 212	98.96 229	97.75 157		96.56 306	99.39 311	99.45 201

HQP_MVS		97.99 259	97.67 278	98.93 166	99.19 237	97.65 199	97.77 251	99.27 247	98.20 203	97.79 351	97.98 378	94.90 312	99.70 313	94.42 389	99.51 283	99.45 201

plane_prior5								99.27 247					99.70 313	94.42 389	99.51 283	99.45 201

lessismore_v0				98.97 158	99.73 37	97.53 206		86.71 498		99.37 120	99.52 67	89.93 392	99.92 65	98.99 88	99.72 193	99.44 205

TAMVS		98.24 231	98.05 244	98.80 190	99.07 267	97.18 241	97.88 234	98.81 346	96.66 342	99.17 173	99.21 150	94.81 318	99.77 263	96.96 260	99.88 93	99.44 205

DeepPCF-MVS	96.93 5	98.32 217	98.01 248	99.23 108	98.39 397	98.97 73	95.03 446	99.18 273	96.88 328	99.33 130	98.78 274	98.16 119	99.28 458	96.74 281	99.62 244	99.44 205

3Dnovator	98.27 2	98.81 125	98.73 126	99.05 142	98.76 334	97.81 188	99.25 43	99.30 232	98.57 169	98.55 285	99.33 117	97.95 137	99.90 81	97.16 240	99.67 223	99.44 205

E2		98.70 145	98.68 139	98.73 212	99.40 178	97.10 248	97.48 298	99.57 101	98.09 218	99.00 197	99.20 152	97.90 140	99.67 335	97.73 194	99.77 162	99.43 209

E3		98.69 149	98.68 139	98.73 212	99.40 178	97.10 248	97.48 298	99.57 101	98.09 218	99.00 197	99.20 152	97.90 140	99.67 335	97.73 194	99.77 162	99.43 209

MVSFormer		98.26 227	98.43 185	97.77 335	98.88 314	93.89 400	99.39 20	99.56 110	99.11 98	98.16 317	98.13 364	93.81 342	99.97 6	99.26 65	99.57 264	99.43 209

jason		97.45 303	97.35 301	97.76 338	99.24 222	93.93 396	95.86 414	98.42 383	94.24 425	98.50 291	98.13 364	94.82 316	99.91 74	97.22 236	99.73 185	99.43 209
jason: jason.
NCCC		97.86 270	97.47 295	99.05 142	98.61 368	98.07 153	96.98 345	98.90 326	97.63 253	97.04 397	97.93 383	95.99 278	99.66 348	95.31 366	98.82 388	99.43 209

Anonymous20240521		98.69 149	98.87 108	98.16 302	99.77 27	95.11 347	99.08 62	99.44 168	99.34 64	99.33 130	99.55 56	94.10 338	99.94 41	99.25 67	99.96 28	99.42 214

MVS_111021_HR		98.25 230	98.08 241	98.75 206	99.09 263	97.46 212	95.97 405	99.27 247	97.60 259	97.99 335	98.25 355	98.15 121	99.38 443	96.87 270	99.57 264	99.42 214

COLMAP_ROB	96.50 10	98.99 90	98.85 115	99.41 69	99.58 93	99.10 65	98.74 99	99.56 110	99.09 108	99.33 130	99.19 155	98.40 85	99.72 305	95.98 341	99.76 177	99.42 214
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
SED-MVS		98.91 103	98.72 128	99.49 54	99.49 145	99.17 44	98.10 191	99.31 224	98.03 221	99.66 60	99.02 202	98.36 88	99.88 115	96.91 262	99.62 244	99.41 217

OPU-MVS				98.82 185	98.59 373	98.30 127	98.10 191				98.52 326	98.18 115	98.75 481	94.62 381	99.48 294	99.41 217

our_test_3		97.39 309	97.73 274	96.34 420	98.70 348	89.78 468	94.61 460	98.97 316	96.50 347	99.04 192	98.85 256	95.98 279	99.84 175	97.26 234	99.67 223	99.41 217

casdiffmvs		98.95 98	99.00 92	98.81 187	99.38 181	97.33 220	97.82 242	99.57 101	99.17 91	99.35 125	99.17 163	98.35 92	99.69 321	98.46 128	99.73 185	99.41 217
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
YYNet1		97.60 290	97.67 278	97.39 380	99.04 276	93.04 419	95.27 438	98.38 386	97.25 299	98.92 222	98.95 233	95.48 298	99.73 295	96.99 256	98.74 390	99.41 217

MDA-MVSNet_test_wron		97.60 290	97.66 281	97.41 379	99.04 276	93.09 415	95.27 438	98.42 383	97.26 298	98.88 231	98.95 233	95.43 299	99.73 295	97.02 252	98.72 392	99.41 217

GBi-Net		98.65 160	98.47 179	99.17 115	98.90 308	98.24 131	99.20 49	99.44 168	98.59 164	98.95 212	99.55 56	94.14 334	99.86 144	97.77 187	99.69 212	99.41 217

test1		98.65 160	98.47 179	99.17 115	98.90 308	98.24 131	99.20 49	99.44 168	98.59 164	98.95 212	99.55 56	94.14 334	99.86 144	97.77 187	99.69 212	99.41 217

FMVSNet1		99.17 52	99.17 60	99.17 115	99.55 116	98.24 131	99.20 49	99.44 168	99.21 80	99.43 106	99.55 56	97.82 152	99.86 144	98.42 135	99.89 92	99.41 217

test_fmvs1		97.72 282	97.94 257	97.07 394	98.66 363	92.39 430	97.68 265	99.81 31	95.20 404	99.54 78	99.44 85	91.56 378	99.41 438	99.78 21	99.77 162	99.40 226

viewdifsd2359ckpt07		98.71 140	98.86 112	98.26 288	99.43 171	95.65 316	97.20 333	99.66 65	99.20 82	99.29 140	99.01 213	98.29 97	99.73 295	97.92 174	99.75 181	99.39 227

viewmanbaseed2359cas		98.58 174	98.54 164	98.70 216	99.28 208	97.13 247	97.47 302	99.55 114	97.55 265	98.96 211	98.92 237	97.77 155	99.59 380	97.59 206	99.77 162	99.39 227

KD-MVS_self_test		99.25 40	99.18 59	99.44 65	99.63 82	99.06 70	98.69 108	99.54 119	99.31 68	99.62 69	99.53 64	97.36 194	99.86 144	99.24 69	99.71 202	99.39 227

v148		98.45 196	98.60 156	98.00 318	99.44 166	94.98 350	97.44 306	99.06 295	98.30 189	99.32 136	98.97 226	96.65 244	99.62 365	98.37 137	99.85 106	99.39 227

test20.03		98.78 131	98.77 123	98.78 197	99.46 159	97.20 238	97.78 248	99.24 259	99.04 117	99.41 112	98.90 243	97.65 163	99.76 269	97.70 196	99.79 151	99.39 227

CDPH-MVS		97.26 320	96.66 347	99.07 135	99.00 289	98.15 140	96.03 403	99.01 310	91.21 465	97.79 351	97.85 387	96.89 224	99.69 321	92.75 435	99.38 314	99.39 227

EPNet		96.14 373	95.44 385	98.25 290	90.76 503	95.50 325	97.92 229	94.65 466	98.97 125	92.98 482	98.85 256	89.12 400	99.87 135	95.99 340	99.68 217	99.39 227
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		98.17 241	97.87 265	99.07 135	98.67 358	98.24 131	97.01 343	98.93 320	97.25 299	97.62 360	98.34 349	97.27 200	99.57 389	96.42 317	99.33 322	99.39 227

DeepC-MVS_fast	96.85 6	98.30 220	98.15 233	98.75 206	98.61 368	97.23 232	97.76 254	99.09 292	97.31 293	98.75 255	98.66 304	97.56 174	99.64 359	96.10 338	99.55 271	99.39 227
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		98.53 185	98.27 215	99.32 91	99.31 199	98.75 90	98.19 176	99.41 184	96.77 337	98.83 240	98.90 243	97.80 153	99.82 206	95.68 357	99.52 280	99.38 236

test9_res														93.28 421	99.15 354	99.38 236

BP-MVS1		97.40 308	96.97 323	98.71 215	99.07 267	96.81 266	98.34 163	97.18 424	98.58 167	98.17 314	98.61 315	84.01 443	99.94 41	98.97 89	99.78 156	99.37 238

OPM-MVS		98.56 176	98.32 207	99.25 104	99.41 176	98.73 94	97.13 340	99.18 273	97.10 314	98.75 255	98.92 237	98.18 115	99.65 355	96.68 290	99.56 267	99.37 238
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
agg_prior2														92.50 440	99.16 352	99.37 238

AllTest		98.44 197	98.20 223	99.16 118	99.50 137	98.55 107	98.25 171	99.58 94	96.80 334	98.88 231	99.06 190	97.65 163	99.57 389	94.45 387	99.61 249	99.37 238

TestCases				99.16 118	99.50 137	98.55 107		99.58 94	96.80 334	98.88 231	99.06 190	97.65 163	99.57 389	94.45 387	99.61 249	99.37 238

MDA-MVSNet-bldmvs		97.94 261	97.91 262	98.06 313	99.44 166	94.96 351	96.63 366	99.15 285	98.35 182	98.83 240	99.11 179	94.31 331	99.85 157	96.60 299	98.72 392	99.37 238

MVSTER		96.86 346	96.55 353	97.79 333	97.91 425	94.21 377	97.56 287	98.87 332	97.49 272	99.06 182	99.05 197	80.72 456	99.80 232	98.44 129	99.82 128	99.37 238

viewcassd2359sk11		98.55 180	98.51 168	98.67 221	99.29 205	96.99 254	97.39 309	99.54 119	97.73 246	98.81 245	99.08 188	97.55 175	99.66 348	97.52 214	99.67 223	99.36 245

pmmvs5		97.64 288	97.49 292	98.08 311	99.14 254	95.12 346	96.70 362	99.05 299	93.77 434	98.62 271	98.83 263	93.23 348	99.75 281	98.33 141	99.76 177	99.36 245

Anonymous20231206		98.21 234	98.21 222	98.20 297	99.51 131	95.43 331	98.13 184	99.32 219	96.16 367	98.93 220	98.82 266	96.00 274	99.83 193	97.32 231	99.73 185	99.36 245

train_agg		97.10 332	96.45 357	99.07 135	98.71 344	98.08 151	95.96 407	99.03 304	91.64 457	95.85 445	97.53 405	96.47 251	99.76 269	93.67 411	99.16 352	99.36 245

PVSNet_BlendedMVS		97.55 295	97.53 289	97.60 360	98.92 304	93.77 404	96.64 365	99.43 174	94.49 417	97.62 360	99.18 159	96.82 229	99.67 335	94.73 378	99.93 56	99.36 245

Anonymous20240529		98.93 101	98.87 108	99.12 124	99.19 237	98.22 136	99.01 71	98.99 313	99.25 74	99.54 78	99.37 104	97.04 213	99.80 232	97.89 175	99.52 280	99.35 250

F-COLMAP		97.30 317	96.68 344	99.14 122	99.19 237	98.39 119	97.27 327	99.30 232	92.93 445	96.62 422	98.00 376	95.73 289	99.68 331	92.62 438	98.46 409	99.35 250

viewdifsd2359ckpt13		98.39 208	98.29 211	98.70 216	99.26 220	97.19 239	97.51 294	99.48 142	96.94 323	98.58 279	98.82 266	97.47 188	99.55 396	97.21 237	99.33 322	99.34 252

ppachtmachnet_test		97.50 296	97.74 272	96.78 410	98.70 348	91.23 453	94.55 462	99.05 299	96.36 355	99.21 164	98.79 272	96.39 254	99.78 257	96.74 281	99.82 128	99.34 252

VDD-MVS		98.56 176	98.39 192	99.07 135	99.13 256	98.07 153	98.59 122	97.01 429	99.59 36	99.11 175	99.27 130	94.82 316	99.79 245	98.34 139	99.63 241	99.34 252

testgi		98.32 217	98.39 192	98.13 304	99.57 102	95.54 320	97.78 248	99.49 140	97.37 287	99.19 166	97.65 399	98.96 30	99.49 419	96.50 313	98.99 374	99.34 252

diffmvs		98.22 232	98.24 220	98.17 300	99.00 289	95.44 330	96.38 382	99.58 94	97.79 242	98.53 288	98.50 331	96.76 236	99.74 288	97.95 173	99.64 234	99.34 252
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
UnsupCasMVSNet_eth		97.89 265	97.60 286	98.75 206	99.31 199	97.17 243	97.62 276	99.35 205	98.72 153	98.76 254	98.68 299	92.57 364	99.74 288	97.76 191	95.60 479	99.34 252

viewmambaseed2359dif		98.19 237	98.26 216	97.99 319	99.02 286	95.03 349	96.59 369	99.53 123	96.21 362	99.00 197	98.99 219	97.62 168	99.61 372	97.62 202	99.72 193	99.33 258

baseline		98.96 97	99.02 88	98.76 204	99.38 181	97.26 231	98.49 140	99.50 132	98.86 140	99.19 166	99.06 190	98.23 107	99.69 321	98.71 110	99.76 177	99.33 258

MG-MVS		96.77 350	96.61 349	97.26 385	98.31 401	93.06 416	95.93 410	98.12 399	96.45 353	97.92 339	98.73 285	93.77 344	99.39 441	91.19 459	99.04 366	99.33 258

HQP4-MVS										95.56 450			99.54 402			99.32 261

CDS-MVSNet		97.69 284	97.35 301	98.69 218	98.73 338	97.02 253	96.92 351	98.75 357	95.89 380	98.59 277	98.67 301	92.08 373	99.74 288	96.72 284	99.81 134	99.32 261
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP-MVS		97.00 341	96.49 356	98.55 249	98.67 358	96.79 267	96.29 388	99.04 302	96.05 370	95.55 451	96.84 426	93.84 340	99.54 402	92.82 432	99.26 336	99.32 261

RPSCF		98.62 167	98.36 197	99.42 67	99.65 70	99.42 10	98.55 126	99.57 101	97.72 248	98.90 224	99.26 136	96.12 269	99.52 408	95.72 354	99.71 202	99.32 261

E3new		98.41 199	98.34 201	98.62 231	99.19 237	96.90 262	97.32 319	99.50 132	97.40 284	98.63 268	98.92 237	97.21 205	99.65 355	97.34 227	99.52 280	99.31 265

MVP-Stereo		98.08 248	97.92 260	98.57 242	98.96 296	96.79 267	97.90 232	99.18 273	96.41 354	98.46 294	98.95 233	95.93 283	99.60 376	96.51 312	98.98 377	99.31 265
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 202	98.68 139	97.54 368	98.96 296	97.99 160	97.88 234	99.36 199	98.20 203	99.63 66	99.04 199	98.76 46	95.33 498	96.56 306	99.74 182	99.31 265
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
VNet		98.42 198	98.30 209	98.79 194	98.79 333	97.29 228	98.23 172	98.66 364	99.31 68	98.85 237	98.80 270	94.80 319	99.78 257	98.13 152	99.13 357	99.31 265

test_prior				98.95 162	98.69 353	97.95 168		99.03 304					99.59 380			99.30 269

USDC		97.41 307	97.40 296	97.44 377	98.94 298	93.67 407	95.17 442	99.53 123	94.03 431	98.97 206	99.10 182	95.29 302	99.34 448	95.84 350	99.73 185	99.30 269

viewdifsd2359ckpt09		98.13 244	97.92 260	98.77 202	99.18 245	97.35 218	97.29 323	99.53 123	95.81 384	98.09 325	98.47 335	96.34 259	99.66 348	97.02 252	99.51 283	99.29 271

test_fmvsm_n_1920		99.33 30	99.45 23	98.99 152	99.57 102	97.73 195	97.93 226	99.83 25	99.22 78	99.93 6	99.30 124	99.42 11	99.96 13	99.85 6	99.99 5	99.29 271

FMVSNet2		98.49 192	98.40 189	98.75 206	98.90 308	97.14 246	98.61 120	99.13 286	98.59 164	99.19 166	99.28 128	94.14 334	99.82 206	97.97 171	99.80 145	99.29 271

gbinet_0.2-2-1-0.02		95.44 398	94.55 410	98.14 303	95.99 490	95.34 337	94.71 453	98.29 389	96.00 375	96.05 442	90.50 494	84.99 433	99.79 245	97.33 229	97.07 458	99.28 274

XVG-OURS-SEG-HR		98.49 192	98.28 212	99.14 122	99.49 145	98.83 86	96.54 370	99.48 142	97.32 292	99.11 175	98.61 315	99.33 15	99.30 454	96.23 328	98.38 410	99.28 274

mamba_0408		98.80 127	98.88 105	98.55 249	99.27 211	96.50 284	98.00 212	99.60 84	98.93 130	99.22 161	98.84 261	98.59 67	99.89 97	97.74 192	99.72 193	99.27 276

SSM_04072		98.80 127	98.88 105	98.56 247	99.27 211	96.50 284	98.00 212	99.60 84	98.93 130	99.22 161	98.84 261	98.59 67	99.90 81	97.74 192	99.72 193	99.27 276

SSM_0407		98.86 114	98.96 98	98.55 249	99.27 211	96.50 284	98.04 203	99.66 65	99.09 108	99.22 161	99.02 202	98.79 43	99.87 135	97.87 180	99.72 193	99.27 276

test12				98.93 166	98.58 375	97.83 180		98.66 364		96.53 426		95.51 296	99.69 321		99.13 357	99.27 276

DSMNet-mixed		97.42 306	97.60 286	96.87 404	99.15 253	91.46 443	98.54 128	99.12 287	92.87 447	97.58 364	99.63 39	96.21 264	99.90 81	95.74 353	99.54 273	99.27 276

N_pmnet		97.63 289	97.17 310	98.99 152	99.27 211	97.86 177	95.98 404	93.41 477	95.25 401	99.47 100	98.90 243	95.63 291	99.85 157	96.91 262	99.73 185	99.27 276

ambc				98.24 292	98.82 326	95.97 306	98.62 118	99.00 312		99.27 144	99.21 150	96.99 218	99.50 415	96.55 309	99.50 291	99.26 282

LFMVS		97.20 326	96.72 341	98.64 225	98.72 340	96.95 258	98.93 82	94.14 474	99.74 12	98.78 249	99.01 213	84.45 438	99.73 295	97.44 222	99.27 333	99.25 283

FMVSNet5		96.01 376	95.20 397	98.41 271	97.53 447	96.10 297	98.74 99	99.50 132	97.22 308	98.03 332	99.04 199	69.80 479	99.88 115	97.27 233	99.71 202	99.25 283

BH-RMVSNet		96.83 347	96.58 352	97.58 362	98.47 386	94.05 384	96.67 363	97.36 418	96.70 341	97.87 344	97.98 378	95.14 307	99.44 434	90.47 467	98.58 406	99.25 283

testf1		99.25 40	99.16 62	99.51 48	99.89 6	99.63 3	98.71 106	99.69 53	98.90 134	99.43 106	99.35 110	98.86 35	99.67 335	97.81 183	99.81 134	99.24 286

APD_test2		99.25 40	99.16 62	99.51 48	99.89 6	99.63 3	98.71 106	99.69 53	98.90 134	99.43 106	99.35 110	98.86 35	99.67 335	97.81 183	99.81 134	99.24 286

SSM_0404		98.90 105	99.01 90	98.57 242	99.42 173	96.59 276	98.13 184	99.66 65	99.09 108	99.30 139	99.02 202	98.79 43	99.89 97	97.87 180	99.80 145	99.23 288

旧先验1					98.82 326	97.45 213		98.76 354			98.34 349	95.50 297			99.01 371	99.23 288

test222					98.92 304	96.93 260	95.54 426	98.78 351	85.72 488	96.86 410	98.11 367	94.43 326			99.10 362	99.23 288

XVG-ACMP-BASELINE		98.56 176	98.34 201	99.22 109	99.54 122	98.59 104	97.71 261	99.46 156	97.25 299	98.98 202	98.99 219	97.54 177	99.84 175	95.88 344	99.74 182	99.23 288

FMVSNet3		97.50 296	97.24 307	98.29 286	98.08 417	95.83 311	97.86 238	98.91 325	97.89 234	98.95 212	98.95 233	87.06 413	99.81 223	97.77 187	99.69 212	99.23 288

icg_test_0407_2		98.20 236	98.38 194	97.65 353	99.03 279	94.03 387	95.78 419	99.45 160	98.16 209	99.06 182	98.71 288	98.27 101	99.68 331	97.50 215	99.45 298	99.22 293

IMVS_0407		98.39 208	98.64 147	97.66 351	99.03 279	94.03 387	98.10 191	99.45 160	98.16 209	99.06 182	98.71 288	98.27 101	99.71 306	97.50 215	99.45 298	99.22 293

IMVS_0404		98.07 249	98.20 223	97.69 346	99.03 279	94.03 387	96.67 363	99.45 160	98.16 209	98.03 332	98.71 288	96.80 232	99.82 206	97.50 215	99.45 298	99.22 293

IMVS_0403		98.34 212	98.56 161	97.66 351	99.03 279	94.03 387	97.98 220	99.45 160	98.16 209	98.89 227	98.71 288	97.90 140	99.74 288	97.50 215	99.45 298	99.22 293

无先验							95.74 421	98.74 359	89.38 477				99.73 295	92.38 442		99.22 293

blended_shiyan8		95.98 379	95.33 391	97.94 322	97.05 467	94.87 356	95.34 436	98.59 370	96.17 363	97.09 393	92.39 485	87.62 412	99.76 269	97.65 199	96.05 477	99.20 298

tttt0517		95.64 391	94.98 401	97.64 356	99.36 188	93.81 402	98.72 104	90.47 491	98.08 220	98.67 263	98.34 349	73.88 474	99.92 65	97.77 187	99.51 283	99.20 298

pmmvs-eth3d		98.47 194	98.34 201	98.86 176	99.30 203	97.76 191	97.16 338	99.28 244	95.54 392	99.42 110	99.19 155	97.27 200	99.63 362	97.89 175	99.97 21	99.20 298

MS-PatchMatch		97.68 285	97.75 271	97.45 376	98.23 408	93.78 403	97.29 323	98.84 341	96.10 369	98.64 267	98.65 306	96.04 271	99.36 444	96.84 273	99.14 355	99.20 298

新几何1				98.91 170	98.94 298	97.76 191		98.76 354	87.58 485	96.75 415	98.10 368	94.80 319	99.78 257	92.73 436	99.00 372	99.20 298

PHI-MVS		98.29 223	97.95 255	99.34 83	98.44 391	99.16 48	98.12 188	99.38 191	96.01 374	98.06 328	98.43 339	97.80 153	99.67 335	95.69 356	99.58 260	99.20 298

blended_shiyan6		95.99 378	95.33 391	97.95 321	97.06 465	94.89 354	95.34 436	98.58 371	96.17 363	97.06 395	92.41 484	87.64 411	99.76 269	97.64 200	96.09 471	99.19 304

GDP-MVS		97.50 296	97.11 317	98.67 221	99.02 286	96.85 264	98.16 181	99.71 46	98.32 187	98.52 290	98.54 322	83.39 447	99.95 25	98.79 101	99.56 267	99.19 304

Anonymous202405211		97.90 263	97.50 291	99.08 133	98.90 308	98.25 130	98.53 129	96.16 447	98.87 138	99.11 175	98.86 253	90.40 390	99.78 257	97.36 226	99.31 326	99.19 304

CANet		97.87 269	97.76 270	98.19 299	97.75 431	95.51 322	96.76 358	99.05 299	97.74 245	96.93 401	98.21 359	95.59 293	99.89 97	97.86 182	99.93 56	99.19 304

XVG-OURS		98.53 185	98.34 201	99.11 126	99.50 137	98.82 88	95.97 405	99.50 132	97.30 294	99.05 190	98.98 224	99.35 14	99.32 451	95.72 354	99.68 217	99.18 308

WTY-MVS		96.67 353	96.27 363	97.87 328	98.81 329	94.61 367	96.77 357	97.92 404	94.94 409	97.12 390	97.74 394	91.11 383	99.82 206	93.89 405	98.15 422	99.18 308

Vis-MVSNet (Re-imp)		97.46 301	97.16 311	98.34 281	99.55 116	96.10 297	98.94 81	98.44 381	98.32 187	98.16 317	98.62 313	88.76 401	99.73 295	93.88 406	99.79 151	99.18 308

TinyColmap		97.89 265	97.98 251	97.60 360	98.86 317	94.35 373	96.21 392	99.44 168	97.45 280	99.06 182	98.88 250	97.99 134	99.28 458	94.38 393	99.58 260	99.18 308

wanda-best-256-512		95.48 396	94.74 408	97.68 347	96.53 477	94.12 381	94.17 471	98.57 373	95.84 381	96.71 416	91.16 490	86.05 423	99.76 269	97.57 207	96.09 471	99.17 312

FE-blended-shiyan7		95.48 396	94.74 408	97.68 347	96.53 477	94.12 381	94.17 471	98.57 373	95.84 381	96.71 416	91.16 490	86.05 423	99.76 269	97.57 207	96.09 471	99.17 312

usedtu_blend_shiyan5		96.20 372	95.62 375	97.94 322	96.53 477	94.93 352	98.83 96	99.59 91	98.89 136	96.71 416	91.16 490	86.05 423	99.73 295	96.70 287	96.09 471	99.17 312

testdata				98.09 308	98.93 300	95.40 332		98.80 348	90.08 473	97.45 378	98.37 345	95.26 303	99.70 313	93.58 414	98.95 380	99.17 312

lupinMVS		97.06 335	96.86 331	97.65 353	98.88 314	93.89 400	95.48 430	97.97 402	93.53 437	98.16 317	97.58 403	93.81 342	99.91 74	96.77 278	99.57 264	99.17 312

Patchmtry		97.35 313	96.97 323	98.50 262	97.31 458	96.47 287	98.18 177	98.92 323	98.95 129	98.78 249	99.37 104	85.44 431	99.85 157	95.96 342	99.83 122	99.17 312

usedtu_dtu_shiyan1		97.37 310	97.13 315	98.11 305	99.03 279	95.40 332	94.47 464	98.99 313	96.87 329	97.97 336	97.81 389	92.12 370	99.75 281	97.49 220	99.43 306	99.16 318

FE-MVSNET3		97.37 310	97.13 315	98.11 305	99.03 279	95.40 332	94.47 464	98.99 313	96.87 329	97.97 336	97.81 389	92.12 370	99.75 281	97.49 220	99.43 306	99.16 318

SD_0403		96.28 367	95.83 368	97.64 356	98.72 340	94.30 374	98.87 89	98.77 352	97.80 240	96.53 426	98.02 375	97.34 195	99.47 426	76.93 495	99.48 294	99.16 318

RRT-MVS		97.88 267	97.98 251	97.61 359	98.15 412	93.77 404	98.97 77	99.64 71	99.16 92	98.69 260	99.42 89	91.60 376	99.89 97	97.63 201	98.52 408	99.16 318

sss		97.21 325	96.93 325	98.06 313	98.83 323	95.22 342	96.75 359	98.48 380	94.49 417	97.27 387	97.90 384	92.77 360	99.80 232	96.57 302	99.32 324	99.16 318

CSCG		98.68 155	98.50 171	99.20 110	99.45 164	98.63 99	98.56 125	99.57 101	97.87 235	98.85 237	98.04 374	97.66 162	99.84 175	96.72 284	99.81 134	99.13 323

MVS_111021_LR		98.30 220	98.12 236	98.83 183	99.16 249	98.03 158	96.09 401	99.30 232	97.58 260	98.10 324	98.24 356	98.25 105	99.34 448	96.69 289	99.65 232	99.12 324

miper_lstm_enhance		97.18 328	97.16 311	97.25 386	98.16 411	92.85 421	95.15 444	99.31 224	97.25 299	98.74 257	98.78 274	90.07 391	99.78 257	97.19 238	99.80 145	99.11 325

testing3		93.51 430	92.09 441	97.75 339	98.60 370	94.40 371	97.32 319	95.26 462	97.56 263	96.79 414	95.50 454	53.57 503	99.77 263	95.26 367	98.97 378	99.08 326

原ACMM1				98.35 280	98.90 308	96.25 294		98.83 345	92.48 451	96.07 440	98.10 368	95.39 300	99.71 306	92.61 439	98.99 374	99.08 326

QAPM		97.31 316	96.81 337	98.82 185	98.80 332	97.49 207	99.06 66	99.19 269	90.22 471	97.69 357	99.16 165	96.91 223	99.90 81	90.89 464	99.41 309	99.07 328

PAPM_NR		96.82 349	96.32 360	98.30 285	99.07 267	96.69 274	97.48 298	98.76 354	95.81 384	96.61 423	96.47 435	94.12 337	99.17 465	90.82 465	97.78 435	99.06 329

eth_miper_zixun_eth		97.23 324	97.25 306	97.17 389	98.00 421	92.77 423	94.71 453	99.18 273	97.27 297	98.56 283	98.74 284	91.89 374	99.69 321	97.06 251	99.81 134	99.05 330

D2MVS		97.84 276	97.84 267	97.83 330	99.14 254	94.74 361	96.94 347	98.88 330	95.84 381	98.89 227	98.96 229	94.40 328	99.69 321	97.55 209	99.95 38	99.05 330

c3_l		97.36 312	97.37 299	97.31 381	98.09 416	93.25 414	95.01 447	99.16 280	97.05 316	98.77 252	98.72 287	92.88 357	99.64 359	96.93 261	99.76 177	99.05 330

PLC	94.65 16	96.51 358	95.73 371	98.85 177	98.75 336	97.91 172	96.42 380	99.06 295	90.94 468	95.59 448	97.38 415	94.41 327	99.59 380	90.93 462	98.04 431	99.05 330
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tfpnnormal		98.90 105	98.90 102	98.91 170	99.67 67	97.82 185	99.00 73	99.44 168	99.45 50	99.51 92	99.24 143	98.20 114	99.86 144	95.92 343	99.69 212	99.04 334

CANet_DTU		97.26 320	97.06 319	97.84 329	97.57 442	94.65 366	96.19 394	98.79 349	97.23 305	95.14 460	98.24 356	93.22 349	99.84 175	97.34 227	99.84 111	99.04 334

PM-MVS		98.82 123	98.72 128	99.12 124	99.64 76	98.54 110	97.98 220	99.68 59	97.62 254	99.34 127	99.18 159	97.54 177	99.77 263	97.79 185	99.74 182	99.04 334

TestfortrainingZip				98.97 158	98.30 402	98.43 117	98.68 109	98.26 390	97.76 244	98.86 236	98.16 363	95.15 306	99.47 426		97.55 440	99.02 337

TSAR-MVS + GP.		98.18 239	97.98 251	98.77 202	98.71 344	97.88 175	96.32 386	98.66 364	96.33 356	99.23 160	98.51 327	97.48 187	99.40 439	97.16 240	99.46 296	99.02 337

DIV-MVS_self_test		97.02 338	96.84 333	97.58 362	97.82 429	94.03 387	94.66 457	99.16 280	97.04 317	98.63 268	98.71 288	88.69 402	99.69 321	97.00 254	99.81 134	99.01 339

GA-MVS		95.86 383	95.32 393	97.49 373	98.60 370	94.15 380	93.83 478	97.93 403	95.49 394	96.68 419	97.42 413	83.21 448	99.30 454	96.22 329	98.55 407	99.01 339

OMC-MVS		97.88 267	97.49 292	99.04 144	98.89 313	98.63 99	96.94 347	99.25 254	95.02 406	98.53 288	98.51 327	97.27 200	99.47 426	93.50 417	99.51 283	99.01 339

cl____		97.02 338	96.83 334	97.58 362	97.82 429	94.04 386	94.66 457	99.16 280	97.04 317	98.63 268	98.71 288	88.68 404	99.69 321	97.00 254	99.81 134	99.00 342

pmmvs4		97.58 293	97.28 304	98.51 258	98.84 321	96.93 260	95.40 434	98.52 378	93.60 436	98.61 273	98.65 306	95.10 308	99.60 376	96.97 259	99.79 151	98.99 343

blend_shiyan4		92.09 452	90.16 459	97.88 327	96.78 472	94.93 352	95.24 440	98.58 371	96.22 361	96.07 440	91.42 489	63.46 498	99.73 295	96.70 287	76.98 498	98.98 344

EPNet_dtu		94.93 409	94.78 406	95.38 450	93.58 496	87.68 478	96.78 356	95.69 459	97.35 289	89.14 493	98.09 370	88.15 409	99.49 419	94.95 374	99.30 329	98.98 344
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		96.50 360	95.77 369	98.69 218	99.48 153	97.43 215	97.84 241	99.55 114	81.42 494	96.51 429	98.58 319	95.53 294	99.67 335	93.41 419	99.58 260	98.98 344

PVSNet_Blended		96.88 345	96.68 344	97.47 375	98.92 304	93.77 404	94.71 453	99.43 174	90.98 467	97.62 360	97.36 417	96.82 229	99.67 335	94.73 378	99.56 267	98.98 344

APD_test1		98.83 120	98.66 144	99.34 83	99.78 24	99.47 8	98.42 151	99.45 160	98.28 194	98.98 202	99.19 155	97.76 156	99.58 387	96.57 302	99.55 271	98.97 348

PAPR		95.29 400	94.47 411	97.75 339	97.50 453	95.14 345	94.89 450	98.71 362	91.39 463	95.35 458	95.48 456	94.57 324	99.14 468	84.95 483	97.37 449	98.97 348

EGC-MVSNET		85.24 461	80.54 464	99.34 83	99.77 27	99.20 39	99.08 62	99.29 240	12.08 501	20.84 502	99.42 89	97.55 175	99.85 157	97.08 248	99.72 193	98.96 350

thisisatest0530		95.27 401	94.45 412	97.74 341	99.19 237	94.37 372	97.86 238	90.20 492	97.17 310	98.22 312	97.65 399	73.53 475	99.90 81	96.90 267	99.35 318	98.95 351

mvs_anonymous		97.83 278	98.16 232	96.87 404	98.18 410	91.89 437	97.31 321	98.90 326	97.37 287	98.83 240	99.46 80	96.28 262	99.79 245	98.90 94	98.16 421	98.95 351

baseline1		95.96 381	95.44 385	97.52 370	98.51 384	93.99 394	98.39 157	96.09 450	98.21 199	98.40 303	97.76 393	86.88 414	99.63 362	95.42 364	89.27 492	98.95 351

CLD-MVS		97.49 299	97.16 311	98.48 263	99.07 267	97.03 252	94.71 453	99.21 263	94.46 419	98.06 328	97.16 421	97.57 173	99.48 423	94.46 386	99.78 156	98.95 351
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++		98.02 253	98.14 235	97.64 356	98.58 375	95.19 343	97.48 298	99.23 261	97.47 273	97.90 341	98.62 313	97.04 213	98.81 479	97.55 209	99.41 309	98.94 355

DELS-MVS		98.27 225	98.20 223	98.48 263	98.86 317	96.70 273	95.60 425	99.20 265	97.73 246	98.45 295	98.71 288	97.50 183	99.82 206	98.21 147	99.59 255	98.93 356
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
cl22		95.79 386	95.39 388	96.98 398	96.77 473	92.79 422	94.40 467	98.53 377	94.59 416	97.89 342	98.17 362	82.82 452	99.24 460	96.37 320	99.03 367	98.92 357

LS3D		98.63 164	98.38 194	99.36 74	97.25 459	99.38 12	99.12 61	99.32 219	99.21 80	98.44 296	98.88 250	97.31 196	99.80 232	96.58 300	99.34 320	98.92 357

CMPMVS	75.91 23	96.29 366	95.44 385	98.84 182	96.25 486	98.69 98	97.02 342	99.12 287	88.90 480	97.83 348	98.86 253	89.51 397	98.90 477	91.92 443	99.51 283	98.92 357
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		98.64 162	98.48 177	99.11 126	98.85 320	98.51 112	98.49 140	99.83 25	98.37 180	99.69 55	99.46 80	98.21 112	99.92 65	94.13 399	99.30 329	98.91 360

mvsmamba		97.57 294	97.26 305	98.51 258	98.69 353	96.73 272	98.74 99	97.25 423	97.03 319	97.88 343	99.23 148	90.95 384	99.87 135	96.61 298	99.00 372	98.91 360

DPM-MVS		96.32 365	95.59 379	98.51 258	98.76 334	97.21 237	94.54 463	98.26 390	91.94 456	96.37 433	97.25 419	93.06 354	99.43 435	91.42 454	98.74 390	98.89 362

test_yl		96.69 351	96.29 361	97.90 324	98.28 403	95.24 340	97.29 323	97.36 418	98.21 199	98.17 314	97.86 385	86.27 418	99.55 396	94.87 375	98.32 411	98.89 362

DCV-MVSNet		96.69 351	96.29 361	97.90 324	98.28 403	95.24 340	97.29 323	97.36 418	98.21 199	98.17 314	97.86 385	86.27 418	99.55 396	94.87 375	98.32 411	98.89 362

SPE-MVS-test		99.13 66	99.09 80	99.26 101	99.13 256	98.97 73	99.31 30	99.88 14	99.44 52	98.16 317	98.51 327	98.64 61	99.93 53	98.91 93	99.85 106	98.88 365

UnsupCasMVSNet_bld		97.30 317	96.92 327	98.45 266	99.28 208	96.78 270	96.20 393	99.27 247	95.42 396	98.28 309	98.30 353	93.16 350	99.71 306	94.99 371	97.37 449	98.87 366

Effi-MVS+		98.02 253	97.82 268	98.62 231	98.53 382	97.19 239	97.33 318	99.68 59	97.30 294	96.68 419	97.46 411	98.56 73	99.80 232	96.63 296	98.20 417	98.86 367

test_0402		98.76 135	98.71 133	98.93 166	99.56 110	98.14 142	98.45 147	99.34 211	99.28 72	98.95 212	98.91 240	98.34 93	99.79 245	95.63 358	99.91 78	98.86 367

PatchmatchNet		95.58 392	95.67 374	95.30 452	97.34 457	87.32 480	97.65 271	96.65 439	95.30 400	97.07 394	98.69 297	84.77 435	99.75 281	94.97 373	98.64 401	98.83 369
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-2		93.78 426	93.91 418	93.39 473	98.82 326	81.72 500	97.76 254	95.28 461	98.60 163	96.54 425	96.66 430	65.85 491	99.62 365	96.65 295	98.99 374	98.82 370

test_vis1_rt		97.75 280	97.72 275	97.83 330	98.81 329	96.35 291	97.30 322	99.69 53	94.61 415	97.87 344	98.05 373	96.26 263	98.32 486	98.74 107	98.18 418	98.82 370

CL-MVSNet_self_test		97.44 304	97.22 308	98.08 311	98.57 377	95.78 314	94.30 469	98.79 349	96.58 345	98.60 275	98.19 361	94.74 322	99.64 359	96.41 318	98.84 385	98.82 370

miper_ehance_all_eth		97.06 335	97.03 320	97.16 391	97.83 428	93.06 416	94.66 457	99.09 292	95.99 376	98.69 260	98.45 337	92.73 362	99.61 372	96.79 275	99.03 367	98.82 370

MIMVSNet		96.62 356	96.25 364	97.71 345	99.04 276	94.66 365	99.16 55	96.92 435	97.23 305	97.87 344	99.10 182	86.11 422	99.65 355	91.65 449	99.21 345	98.82 370

hse-mvs2		97.46 301	97.07 318	98.64 225	98.73 338	97.33 220	97.45 304	97.64 414	99.11 98	98.58 279	97.98 378	88.65 405	99.79 245	98.11 154	97.39 448	98.81 375

GSMVS																98.81 375

sam_mvs1												84.74 436				98.81 375

SCA		96.41 364	96.66 347	95.67 440	98.24 406	88.35 474	95.85 416	96.88 436	96.11 368	97.67 358	98.67 301	93.10 352	99.85 157	94.16 395	99.22 342	98.81 375

Patchmatch-RL test		97.26 320	97.02 321	97.99 319	99.52 128	95.53 321	96.13 399	99.71 46	97.47 273	99.27 144	99.16 165	84.30 441	99.62 365	97.89 175	99.77 162	98.81 375

AUN-MVS		96.24 371	95.45 384	98.60 237	98.70 348	97.22 235	97.38 311	97.65 412	95.95 378	95.53 455	97.96 382	82.11 455	99.79 245	96.31 324	97.44 445	98.80 380

ITE_SJBPF				98.87 174	99.22 228	98.48 114		99.35 205	97.50 270	98.28 309	98.60 317	97.64 166	99.35 447	93.86 407	99.27 333	98.79 381

tpm		94.67 411	94.34 415	95.66 441	97.68 440	88.42 473	97.88 234	94.90 464	94.46 419	96.03 444	98.56 321	78.66 466	99.79 245	95.88 344	95.01 482	98.78 382

Patchmatch-test		96.55 357	96.34 359	97.17 389	98.35 398	93.06 416	98.40 156	97.79 405	97.33 290	98.41 299	98.67 301	83.68 446	99.69 321	95.16 369	99.31 326	98.77 383

EC-MVSNet		99.09 72	99.05 84	99.20 110	99.28 208	98.93 79	99.24 44	99.84 22	99.08 112	98.12 322	98.37 345	98.72 50	99.90 81	99.05 83	99.77 162	98.77 383

PMMVS		96.51 358	95.98 365	98.09 308	97.53 447	95.84 310	94.92 449	98.84 341	91.58 459	96.05 442	95.58 451	95.68 290	99.66 348	95.59 360	98.09 425	98.76 385

test_method		79.78 462	79.50 465	80.62 480	80.21 505	45.76 508	70.82 496	98.41 385	31.08 500	80.89 500	97.71 395	84.85 434	97.37 493	91.51 453	80.03 496	98.75 386

ab-mvs		98.41 199	98.36 197	98.59 238	99.19 237	97.23 232	99.32 26	98.81 346	97.66 251	98.62 271	99.40 97	96.82 229	99.80 232	95.88 344	99.51 283	98.75 386

CHOSEN 280x420		95.51 395	95.47 382	95.65 442	98.25 405	88.27 475	93.25 482	98.88 330	93.53 437	94.65 466	97.15 422	86.17 420	99.93 53	97.41 224	99.93 56	98.73 388

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 254	99.66 69	96.97 255	98.00 212	99.85 18	99.24 75	99.92 8	99.50 68	99.39 12	99.95 25	99.89 3	99.98 12	98.71 389

MVS_Test		98.18 239	98.36 197	97.67 349	98.48 385	94.73 362	98.18 177	99.02 307	97.69 249	98.04 331	99.11 179	97.22 204	99.56 392	98.57 120	98.90 384	98.71 389

PVSNet	93.40 17	95.67 389	95.70 372	95.57 443	98.83 323	88.57 472	92.50 485	97.72 407	92.69 449	96.49 432	96.44 436	93.72 345	99.43 435	93.61 412	99.28 332	98.71 389

alignmvs		97.35 313	96.88 330	98.78 197	98.54 380	98.09 147	97.71 261	97.69 409	99.20 82	97.59 363	95.90 446	88.12 410	99.55 396	98.18 149	98.96 379	98.70 392

ADS-MVSNet2		95.43 399	94.98 401	96.76 411	98.14 413	91.74 438	97.92 229	97.76 406	90.23 469	96.51 429	98.91 240	85.61 428	99.85 157	92.88 430	96.90 459	98.69 393

ADS-MVSNet		95.24 402	94.93 404	96.18 428	98.14 413	90.10 466	97.92 229	97.32 421	90.23 469	96.51 429	98.91 240	85.61 428	99.74 288	92.88 430	96.90 459	98.69 393

MDTV_nov1_ep13_2view						74.92 504	97.69 264		90.06 474	97.75 354		85.78 427		93.52 415		98.69 393

MSDG		97.71 283	97.52 290	98.28 287	98.91 307	96.82 265	94.42 466	99.37 195	97.65 252	98.37 304	98.29 354	97.40 191	99.33 450	94.09 400	99.22 342	98.68 396

mvsany_test1		97.60 290	97.54 288	97.77 335	97.72 432	95.35 335	95.36 435	97.13 427	94.13 428	99.71 49	99.33 117	97.93 138	99.30 454	97.60 205	98.94 381	98.67 397

CS-MVS		99.13 66	99.10 78	99.24 106	99.06 272	99.15 52	99.36 22	99.88 14	99.36 63	98.21 313	98.46 336	98.68 58	99.93 53	99.03 85	99.85 106	98.64 398

Syy-MVS		96.04 375	95.56 381	97.49 373	97.10 463	94.48 369	96.18 396	96.58 441	95.65 388	94.77 463	92.29 487	91.27 382	99.36 444	98.17 151	98.05 429	98.63 399

myMVS_eth3d		91.92 454	90.45 455	96.30 421	97.10 463	90.90 457	96.18 396	96.58 441	95.65 388	94.77 463	92.29 487	53.88 502	99.36 444	89.59 471	98.05 429	98.63 399

balanced_conf03		98.63 164	98.72 128	98.38 275	98.66 363	96.68 275	98.90 84	99.42 180	98.99 122	98.97 206	99.19 155	95.81 287	99.85 157	98.77 105	99.77 162	98.60 401

miper_enhance_ethall		96.01 376	95.74 370	96.81 408	96.41 484	92.27 434	93.69 480	98.89 329	91.14 466	98.30 305	97.35 418	90.58 388	99.58 387	96.31 324	99.03 367	98.60 401

Effi-MVS+-dtu		98.26 227	97.90 263	99.35 80	98.02 420	99.49 5	98.02 208	99.16 280	98.29 192	97.64 359	97.99 377	96.44 253	99.95 25	96.66 294	98.93 382	98.60 401

new_pmnet		96.99 342	96.76 339	97.67 349	98.72 340	94.89 354	95.95 409	98.20 394	92.62 450	98.55 285	98.54 322	94.88 315	99.52 408	93.96 403	99.44 305	98.59 404

MVSMamba_PlusPlus		98.83 120	98.98 95	98.36 279	99.32 198	96.58 279	98.90 84	99.41 184	99.75 10	98.72 258	99.50 68	96.17 265	99.94 41	99.27 64	99.78 156	98.57 405

testing91		93.32 433	92.27 438	96.47 417	97.54 445	91.25 451	96.17 398	96.76 438	97.18 309	93.65 480	93.50 477	65.11 493	99.63 362	93.04 425	97.45 444	98.53 406

EIA-MVS		98.00 256	97.74 272	98.80 190	98.72 340	98.09 147	98.05 201	99.60 84	97.39 285	96.63 421	95.55 452	97.68 160	99.80 232	96.73 283	99.27 333	98.52 407

PatchMatch-RL		97.24 323	96.78 338	98.61 235	99.03 279	97.83 180	96.36 383	99.06 295	93.49 439	97.36 385	97.78 391	95.75 288	99.49 419	93.44 418	98.77 389	98.52 407

sasdasda		98.34 212	98.26 216	98.58 239	98.46 388	97.82 185	98.96 78	99.46 156	99.19 87	97.46 375	95.46 457	98.59 67	99.46 430	98.08 157	98.71 394	98.46 409

ET-MVSNet_ETH3D		94.30 417	93.21 428	97.58 362	98.14 413	94.47 370	94.78 452	93.24 479	94.72 413	89.56 491	95.87 447	78.57 468	99.81 223	96.91 262	97.11 457	98.46 409

canonicalmvs		98.34 212	98.26 216	98.58 239	98.46 388	97.82 185	98.96 78	99.46 156	99.19 87	97.46 375	95.46 457	98.59 67	99.46 430	98.08 157	98.71 394	98.46 409

UBG		93.25 435	92.32 436	96.04 433	97.72 432	90.16 465	95.92 412	95.91 454	96.03 373	93.95 477	93.04 481	69.60 480	99.52 408	90.72 466	97.98 432	98.45 412

tt0805		98.69 149	98.62 151	98.90 173	99.75 34	99.30 22	99.15 57	96.97 431	98.86 140	98.87 235	97.62 402	98.63 63	98.96 473	99.41 56	98.29 414	98.45 412

TAPA-MVS	96.21 11	96.63 355	95.95 366	98.65 223	98.93 300	98.09 147	96.93 349	99.28 244	83.58 491	98.13 321	97.78 391	96.13 267	99.40 439	93.52 415	99.29 331	98.45 412
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net		98.34 212	98.28 212	98.51 258	98.47 386	97.59 203	98.96 78	99.48 142	99.18 90	97.40 381	95.50 454	98.66 59	99.50 415	98.18 149	98.71 394	98.44 415

BH-untuned		96.83 347	96.75 340	97.08 392	98.74 337	93.33 413	96.71 361	98.26 390	96.72 339	98.44 296	97.37 416	95.20 304	99.47 426	91.89 444	97.43 446	98.44 415

WB-MVSnew		95.73 388	95.57 380	96.23 426	96.70 474	90.70 462	96.07 402	93.86 475	95.60 390	97.04 397	95.45 460	96.00 274	99.55 396	91.04 460	98.31 413	98.43 417

pmmvs3		95.03 406	94.40 413	96.93 400	97.70 437	92.53 427	95.08 445	97.71 408	88.57 482	97.71 355	98.08 371	79.39 463	99.82 206	96.19 331	99.11 361	98.43 417

DP-MVS Recon		97.33 315	96.92 327	98.57 242	99.09 263	97.99 160	96.79 355	99.35 205	93.18 441	97.71 355	98.07 372	95.00 311	99.31 452	93.97 402	99.13 357	98.42 419

testing99		93.04 439	91.98 446	96.23 426	97.53 447	90.70 462	96.35 384	95.94 453	96.87 329	93.41 481	93.43 479	63.84 495	99.59 380	93.24 423	97.19 454	98.40 420

ETVMVS		92.60 444	91.08 453	97.18 387	97.70 437	93.65 409	96.54 370	95.70 457	96.51 346	94.68 465	92.39 485	61.80 499	99.50 415	86.97 478	97.41 447	98.40 420

Fast-Effi-MVS+-dtu		98.27 225	98.09 238	98.81 187	98.43 392	98.11 144	97.61 281	99.50 132	98.64 156	97.39 383	97.52 407	98.12 123	99.95 25	96.90 267	98.71 394	98.38 422

LF4IMVS		97.90 263	97.69 277	98.52 257	99.17 247	97.66 198	97.19 337	99.47 151	96.31 358	97.85 347	98.20 360	96.71 240	99.52 408	94.62 381	99.72 193	98.38 422

testing11		93.08 438	92.02 443	96.26 424	97.56 443	90.83 459	96.32 386	95.70 457	96.47 350	92.66 484	93.73 474	64.36 494	99.59 380	93.77 410	97.57 439	98.37 424

Fast-Effi-MVS+		97.67 286	97.38 298	98.57 242	98.71 344	97.43 215	97.23 328	99.45 160	94.82 412	96.13 437	96.51 432	98.52 75	99.91 74	96.19 331	98.83 386	98.37 424

test0.0.03 1		94.51 412	93.69 422	96.99 397	96.05 487	93.61 411	94.97 448	93.49 476	96.17 363	97.57 366	94.88 467	82.30 453	99.01 472	93.60 413	94.17 486	98.37 424

UWE-MVS		92.38 447	91.76 450	94.21 463	97.16 461	84.65 489	95.42 433	88.45 495	95.96 377	96.17 436	95.84 449	66.36 487	99.71 306	91.87 445	98.64 401	98.28 427

FE-MVS		95.66 390	94.95 403	97.77 335	98.53 382	95.28 339	99.40 19	96.09 450	93.11 443	97.96 338	99.26 136	79.10 465	99.77 263	92.40 441	98.71 394	98.27 428

baseline2		93.73 427	92.83 433	96.42 418	97.70 437	91.28 450	96.84 354	89.77 493	93.96 433	92.44 485	95.93 445	79.14 464	99.77 263	92.94 427	96.76 463	98.21 429

thisisatest0515		94.12 421	93.16 429	96.97 399	98.60 370	92.90 420	93.77 479	90.61 490	94.10 429	96.91 404	95.87 447	74.99 473	99.80 232	94.52 384	99.12 360	98.20 430

EPMVS		93.72 428	93.27 427	95.09 455	96.04 488	87.76 477	98.13 184	85.01 500	94.69 414	96.92 402	98.64 309	78.47 470	99.31 452	95.04 370	96.46 465	98.20 430

balanced_ft_v1		98.28 224	98.35 200	98.10 307	98.08 417	96.23 295	99.23 45	99.26 252	98.34 183	97.46 375	99.42 89	95.38 301	99.88 115	98.60 117	99.34 320	98.17 432

dp		93.47 431	93.59 424	93.13 476	96.64 475	81.62 501	97.66 269	96.42 444	92.80 448	96.11 438	98.64 309	78.55 469	99.59 380	93.31 420	92.18 491	98.16 433

CNLPA		97.17 329	96.71 342	98.55 249	98.56 378	98.05 157	96.33 385	98.93 320	96.91 327	97.06 395	97.39 414	94.38 329	99.45 432	91.66 448	99.18 351	98.14 434

dmvs_re		95.98 379	95.39 388	97.74 341	98.86 317	97.45 213	98.37 159	95.69 459	97.95 227	96.56 424	95.95 444	90.70 387	97.68 492	88.32 474	96.13 470	98.11 435

HY-MVS	95.94 13	95.90 382	95.35 390	97.55 367	97.95 422	94.79 358	98.81 98	96.94 434	92.28 454	95.17 459	98.57 320	89.90 393	99.75 281	91.20 458	97.33 453	98.10 436

CostFormer		93.97 423	93.78 421	94.51 459	97.53 447	85.83 485	97.98 220	95.96 452	89.29 478	94.99 462	98.63 311	78.63 467	99.62 365	94.54 383	96.50 464	98.09 437

FA-MVS(test-final)		96.99 342	96.82 335	97.50 372	98.70 348	94.78 359	99.34 23	96.99 430	95.07 405	98.48 293	99.33 117	88.41 408	99.65 355	96.13 337	98.92 383	98.07 438

AdaColmap		97.14 331	96.71 342	98.46 265	98.34 399	97.80 189	96.95 346	98.93 320	95.58 391	96.92 402	97.66 398	95.87 285	99.53 404	90.97 461	99.14 355	98.04 439

KD-MVS_2432*1600		92.87 442	91.99 444	95.51 446	91.37 500	89.27 470	94.07 473	98.14 397	95.42 396	97.25 388	96.44 436	67.86 482	99.24 460	91.28 456	96.08 475	98.02 440

miper_refine_blended		92.87 442	91.99 444	95.51 446	91.37 500	89.27 470	94.07 473	98.14 397	95.42 396	97.25 388	96.44 436	67.86 482	99.24 460	91.28 456	96.08 475	98.02 440

TESTMET0.1,1		92.19 451	91.77 449	93.46 471	96.48 482	82.80 497	94.05 475	91.52 489	94.45 421	94.00 475	94.88 467	66.65 486	99.56 392	95.78 352	98.11 424	98.02 440

testing222		91.96 453	90.37 456	96.72 412	97.47 454	92.59 425	96.11 400	94.76 465	96.83 333	92.90 483	92.87 482	57.92 501	99.55 396	86.93 479	97.52 441	98.00 443

PCF-MVS	92.86 18	94.36 414	93.00 432	98.42 270	98.70 348	97.56 204	93.16 483	99.11 289	79.59 495	97.55 367	97.43 412	92.19 368	99.73 295	79.85 492	99.45 298	97.97 444
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		90.22 457	89.28 460	93.02 477	94.50 495	82.87 496	96.52 373	87.51 496	95.21 403	92.36 486	96.04 441	71.57 477	98.25 488	72.04 497	97.77 436	97.94 445

myMVS_eth3d28		92.92 441	92.31 437	94.77 456	97.84 427	87.59 479	96.19 394	96.11 449	97.08 315	94.27 469	93.49 478	66.07 490	98.78 480	91.78 446	97.93 434	97.92 446

OpenMVS	96.65 7	97.09 333	96.68 344	98.32 282	98.32 400	97.16 244	98.86 92	99.37 195	89.48 476	96.29 435	99.15 169	96.56 247	99.90 81	92.90 429	99.20 346	97.89 447

Gipuma		99.03 85	99.16 62	98.64 225	99.94 2	98.51 112	99.32 26	99.75 41	99.58 38	98.60 275	99.62 40	98.22 110	99.51 414	97.70 196	99.73 185	97.89 447
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PVSNet_0	89.98 21	91.15 456	90.30 458	93.70 469	97.72 432	84.34 493	90.24 490	97.42 416	90.20 472	93.79 478	93.09 480	90.90 386	98.89 478	86.57 481	72.76 499	97.87 449

test-LLR		93.90 424	93.85 419	94.04 464	96.53 477	84.62 490	94.05 475	92.39 481	96.17 363	94.12 472	95.07 461	82.30 453	99.67 335	95.87 347	98.18 418	97.82 450

test-mter		92.33 449	91.76 450	94.04 464	96.53 477	84.62 490	94.05 475	92.39 481	94.00 432	94.12 472	95.07 461	65.63 492	99.67 335	95.87 347	98.18 418	97.82 450

tpm2		93.09 437	92.58 435	94.62 458	97.56 443	86.53 482	97.66 269	95.79 456	86.15 487	94.07 474	98.23 358	75.95 471	99.53 404	90.91 463	96.86 462	97.81 452

CR-MVSNet		96.28 367	95.95 366	97.28 383	97.71 435	94.22 375	98.11 189	98.92 323	92.31 453	96.91 404	99.37 104	85.44 431	99.81 223	97.39 225	97.36 451	97.81 452

RPMNet		97.02 338	96.93 325	97.30 382	97.71 435	94.22 375	98.11 189	99.30 232	99.37 60	96.91 404	99.34 114	86.72 415	99.87 135	97.53 212	97.36 451	97.81 452

tpmrst		95.07 405	95.46 383	93.91 466	97.11 462	84.36 492	97.62 276	96.96 432	94.98 407	96.35 434	98.80 270	85.46 430	99.59 380	95.60 359	96.23 468	97.79 455

PAPM		91.88 455	90.34 457	96.51 415	98.06 419	92.56 426	92.44 486	97.17 425	86.35 486	90.38 490	96.01 442	86.61 416	99.21 463	70.65 498	95.43 480	97.75 456

FPMVS		93.44 432	92.23 439	97.08 392	99.25 221	97.86 177	95.61 424	97.16 426	92.90 446	93.76 479	98.65 306	75.94 472	95.66 496	79.30 493	97.49 442	97.73 457

MAR-MVS		96.47 362	95.70 372	98.79 194	97.92 424	99.12 62	98.28 166	98.60 369	92.16 455	95.54 454	96.17 440	94.77 321	99.52 408	89.62 470	98.23 415	97.72 458
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
ETV-MVS		98.03 252	97.86 266	98.56 247	98.69 353	98.07 153	97.51 294	99.50 132	98.10 217	97.50 372	95.51 453	98.41 84	99.88 115	96.27 327	99.24 338	97.71 459

thres600view7		94.45 413	93.83 420	96.29 422	99.06 272	91.53 442	97.99 219	94.24 472	98.34 183	97.44 379	95.01 463	79.84 459	99.67 335	84.33 484	98.23 415	97.66 460

thres400		94.14 420	93.44 425	96.24 425	98.93 300	91.44 445	97.60 282	94.29 470	97.94 229	97.10 391	94.31 472	79.67 461	99.62 365	83.05 486	98.08 426	97.66 460

IB-MVS	91.63 19	92.24 450	90.90 454	96.27 423	97.22 460	91.24 452	94.36 468	93.33 478	92.37 452	92.24 487	94.58 471	66.20 489	99.89 97	93.16 424	94.63 484	97.66 460
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
tpmvs		95.02 407	95.25 394	94.33 460	96.39 485	85.87 483	98.08 194	96.83 437	95.46 395	95.51 456	98.69 297	85.91 426	99.53 404	94.16 395	96.23 468	97.58 463

cascas		94.79 410	94.33 416	96.15 432	96.02 489	92.36 432	92.34 487	99.26 252	85.34 489	95.08 461	94.96 466	92.96 356	98.53 484	94.41 392	98.59 405	97.56 464

PatchT		96.65 354	96.35 358	97.54 368	97.40 455	95.32 338	97.98 220	96.64 440	99.33 65	96.89 408	99.42 89	84.32 440	99.81 223	97.69 198	97.49 442	97.48 465

TR-MVS		95.55 393	95.12 399	96.86 407	97.54 445	93.94 395	96.49 375	96.53 443	94.36 424	97.03 399	96.61 431	94.26 333	99.16 466	86.91 480	96.31 467	97.47 466

dmvs_testset		92.94 440	92.21 440	95.13 453	98.59 373	90.99 456	97.65 271	92.09 483	96.95 322	94.00 475	93.55 476	92.34 366	96.97 495	72.20 496	92.52 489	97.43 467

MonoMVSNet		96.25 369	96.53 355	95.39 449	96.57 476	91.01 455	98.82 97	97.68 411	98.57 169	98.03 332	99.37 104	90.92 385	97.78 491	94.99 371	93.88 487	97.38 468

JIA-IIPM		95.52 394	95.03 400	97.00 396	96.85 470	94.03 387	96.93 349	95.82 455	99.20 82	94.63 467	99.71 22	83.09 449	99.60 376	94.42 389	94.64 483	97.36 469

BH-w/o		95.13 404	94.89 405	95.86 435	98.20 409	91.31 448	95.65 423	97.37 417	93.64 435	96.52 428	95.70 450	93.04 355	99.02 470	88.10 475	95.82 478	97.24 470

tpm cat1		93.29 434	93.13 431	93.75 468	97.39 456	84.74 488	97.39 309	97.65 412	83.39 492	94.16 471	98.41 340	82.86 451	99.39 441	91.56 452	95.35 481	97.14 471

xiu_mvs_v1_base_debu		97.86 270	98.17 229	96.92 401	98.98 293	93.91 397	96.45 376	99.17 277	97.85 237	98.41 299	97.14 423	98.47 77	99.92 65	98.02 164	99.05 363	96.92 472

xiu_mvs_v1_base		97.86 270	98.17 229	96.92 401	98.98 293	93.91 397	96.45 376	99.17 277	97.85 237	98.41 299	97.14 423	98.47 77	99.92 65	98.02 164	99.05 363	96.92 472

xiu_mvs_v1_base_debi		97.86 270	98.17 229	96.92 401	98.98 293	93.91 397	96.45 376	99.17 277	97.85 237	98.41 299	97.14 423	98.47 77	99.92 65	98.02 164	99.05 363	96.92 472

PMVS	91.26 20	97.86 270	97.94 257	97.65 353	99.71 48	97.94 169	98.52 130	98.68 363	98.99 122	97.52 370	99.35 110	97.41 190	98.18 489	91.59 451	99.67 223	96.82 475
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
0.4-1-1-0.1		88.42 458	85.91 461	95.94 434	93.08 497	91.54 441	90.99 489	92.04 485	89.96 475	84.83 497	83.25 496	63.75 496	99.52 408	93.25 422	82.07 493	96.75 476

1314		95.74 387	95.60 377	96.17 429	97.53 447	92.75 424	98.07 198	98.31 388	91.22 464	94.25 470	96.68 429	95.53 294	99.03 469	91.64 450	97.18 455	96.74 477

MVS-HIRNet		94.32 415	95.62 375	90.42 479	98.46 388	75.36 503	96.29 388	89.13 494	95.25 401	95.38 457	99.75 16	92.88 357	99.19 464	94.07 401	99.39 311	96.72 478

OpenMVS_ROB	95.38 14	95.84 385	95.18 398	97.81 332	98.41 396	97.15 245	97.37 315	98.62 368	83.86 490	98.65 266	98.37 345	94.29 332	99.68 331	88.41 473	98.62 404	96.60 479

0.3-1-1-0.015		87.27 460	84.50 463	95.57 443	91.70 499	90.77 460	89.41 494	92.04 485	88.98 479	82.46 499	81.35 497	60.36 500	99.50 415	92.96 426	81.23 495	96.45 480

0.4-1-1-0.2		87.49 459	84.89 462	95.31 451	91.33 502	90.08 467	88.47 495	92.07 484	88.70 481	84.06 498	81.08 498	63.62 497	99.49 419	92.93 428	81.71 494	96.37 481

thres100view900		94.19 418	93.67 423	95.75 439	99.06 272	91.35 447	98.03 205	94.24 472	98.33 185	97.40 381	94.98 465	79.84 459	99.62 365	83.05 486	98.08 426	96.29 482

tfpn200view9		94.03 422	93.44 425	95.78 438	98.93 300	91.44 445	97.60 282	94.29 470	97.94 229	97.10 391	94.31 472	79.67 461	99.62 365	83.05 486	98.08 426	96.29 482

MVS		93.19 436	92.09 441	96.50 416	96.91 468	94.03 387	98.07 198	98.06 401	68.01 497	94.56 468	96.48 434	95.96 281	99.30 454	83.84 485	96.89 461	96.17 484

gg-mvs-nofinetune		92.37 448	91.20 452	95.85 436	95.80 492	92.38 431	99.31 30	81.84 502	99.75 10	91.83 488	99.74 18	68.29 481	99.02 470	87.15 477	97.12 456	96.16 485

xiu_mvs_v2_base		97.16 330	97.49 292	96.17 429	98.54 380	92.46 428	95.45 431	98.84 341	97.25 299	97.48 374	96.49 433	98.31 95	99.90 81	96.34 323	98.68 399	96.15 486

PS-MVSNAJ		97.08 334	97.39 297	96.16 431	98.56 378	92.46 428	95.24 440	98.85 340	97.25 299	97.49 373	95.99 443	98.07 125	99.90 81	96.37 320	98.67 400	96.12 487

E-PMN		94.17 419	94.37 414	93.58 470	96.86 469	85.71 486	90.11 492	97.07 428	98.17 206	97.82 350	97.19 420	84.62 437	98.94 474	89.77 469	97.68 438	96.09 488

EMVS		93.83 425	94.02 417	93.23 475	96.83 471	84.96 487	89.77 493	96.32 445	97.92 231	97.43 380	96.36 439	86.17 420	98.93 475	87.68 476	97.73 437	95.81 489

MVE	83.40 22	92.50 445	91.92 447	94.25 461	98.83 323	91.64 440	92.71 484	83.52 501	95.92 379	86.46 496	95.46 457	95.20 304	95.40 497	80.51 491	98.64 401	95.73 490
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres200		93.72 428	93.14 430	95.46 448	98.66 363	91.29 449	96.61 367	94.63 467	97.39 285	96.83 411	93.71 475	79.88 458	99.56 392	82.40 489	98.13 423	95.54 491

API-MVS		97.04 337	96.91 329	97.42 378	97.88 426	98.23 135	98.18 177	98.50 379	97.57 261	97.39 383	96.75 428	96.77 234	99.15 467	90.16 468	99.02 370	94.88 492

GG-mvs-BLEND				94.76 457	94.54 494	92.13 436	99.31 30	80.47 503		88.73 494	91.01 493	67.59 485	98.16 490	82.30 490	94.53 485	93.98 493

DeepMVS_CX				93.44 472	98.24 406	94.21 377		94.34 469	64.28 498	91.34 489	94.87 469	89.45 399	92.77 499	77.54 494	93.14 488	93.35 494

tmp_tt		78.77 463	78.73 466	78.90 481	58.45 506	74.76 505	94.20 470	78.26 504	39.16 499	86.71 495	92.82 483	80.50 457	75.19 501	86.16 482	92.29 490	86.74 495

dongtai		76.24 464	75.95 467	77.12 482	92.39 498	67.91 506	90.16 491	59.44 507	82.04 493	89.42 492	94.67 470	49.68 504	81.74 500	48.06 499	77.66 497	81.72 496

kuosan		69.30 465	68.95 468	70.34 483	87.68 504	65.00 507	91.11 488	59.90 506	69.02 496	74.46 501	88.89 495	48.58 505	68.03 502	28.61 500	72.33 500	77.99 497

wuyk23d		96.06 374	97.62 285	91.38 478	98.65 367	98.57 106	98.85 93	96.95 433	96.86 332	99.90 14	99.16 165	99.18 19	98.40 485	89.23 472	99.77 162	77.18 498

test123		17.04 468	20.11 471	7.82 484	10.25 508	4.91 509	94.80 451	4.47 509	4.93 502	10.00 504	24.28 501	9.69 506	3.64 503	10.14 501	12.43 502	14.92 499

testmvs		17.12 467	20.53 470	6.87 485	12.05 507	4.20 510	93.62 481	6.73 508	4.62 503	10.41 503	24.33 500	8.28 507	3.56 504	9.69 502	15.07 501	12.86 500

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		24.66 466	32.88 469	0.00 486	0.00 509	0.00 511	0.00 497	99.10 290	0.00 504	0.00 505	97.58 403	99.21 18	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		8.17 469	10.90 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	98.07 125	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.12 470	10.83 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	97.48 409	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						90.90 457								91.37 455

FOURS1					99.73 37	99.67 2	99.43 15	99.54 119	99.43 54	99.26 148

test_one_0601					99.39 180	99.20 39		99.31 224	98.49 175	98.66 265	99.02 202	97.64 166

eth-test2					0.00 509

eth-test					0.00 509

ZD-MVS					99.01 288	98.84 85		99.07 294	94.10 429	98.05 330	98.12 366	96.36 258	99.86 144	92.70 437	99.19 349

test_241102_ONE					99.49 145	99.17 44		99.31 224	97.98 224	99.66 60	98.90 243	98.36 88	99.48 423

9.14			97.78 269		99.07 267		97.53 291	99.32 219	95.53 393	98.54 287	98.70 295	97.58 172	99.76 269	94.32 394	99.46 296

save fliter					99.11 258	97.97 164	96.53 372	99.02 307	98.24 195

test0726					99.50 137	99.21 33	98.17 180	99.35 205	97.97 225	99.26 148	99.06 190	97.61 170

test_part2					99.36 188	99.10 65				99.05 190

sam_mvs												84.29 442

MTGPA								99.20 265

test_post1							97.59 284				20.48 503	83.07 450	99.66 348	94.16 395

test_post											21.25 502	83.86 445	99.70 313

patchmatchnet-post											98.77 276	84.37 439	99.85 157

MTMP							97.93 226	91.91 488

gm-plane-assit					94.83 493	81.97 499			88.07 484		94.99 464		99.60 376	91.76 447

TEST9					98.71 344	98.08 151	95.96 407	99.03 304	91.40 462	95.85 445	97.53 405	96.52 249	99.76 269

test_8					98.67 358	98.01 159	95.91 413	99.02 307	91.64 457	95.79 447	97.50 408	96.47 251	99.76 269

agg_prior					98.68 357	97.99 160		99.01 310		95.59 448			99.77 263

test_prior4						97.97 164	95.86 414

test_prior2							95.74 421		96.48 349	96.11 438	97.63 401	95.92 284		94.16 395	99.20 346

旧先验2							95.76 420		88.56 483	97.52 370			99.66 348	94.48 385

新几何2							95.93 410

原ACMM2							95.53 427

testdata2													99.79 245	92.80 434

segment_acmp												97.02 216

testdata1							95.44 432		96.32 357

plane_prior7					99.19 237	97.87 176

plane_prior6					98.99 292	97.70 197						94.90 312

plane_prior4											97.98 378

plane_prior3						97.78 190			97.41 282	97.79 351

plane_prior2							97.77 251		98.20 203

plane_prior1					99.05 275

plane_prior						97.65 199	97.07 341		96.72 339						99.36 315

n2								0.00 510

nn								0.00 510

door-mid								99.57 101

test11								98.87 332

door								99.41 184

HQP5-MVS						96.79 267

HQP-NCC					98.67 358		96.29 388		96.05 370	95.55 451

ACMP_Plane					98.67 358		96.29 388		96.05 370	95.55 451

BP-MVS														92.82 432

HQP3-MVS								99.04 302							99.26 336

HQP2-MVS												93.84 340

NP-MVS					98.84 321	97.39 217					96.84 426

MDTV_nov1_ep13			95.22 396		97.06 465	83.20 495	97.74 258	96.16 447	94.37 423	96.99 400	98.83 263	83.95 444	99.53 404	93.90 404	97.95 433

ACMMP++_ref															99.77 162

ACMMP++															99.68 217

Test By Simon												96.52 249

High-resolution multi-view benchmark