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	98.44 240	99.65 68	95.35 300	99.82 3	99.94 2	99.83 7	99.42 102	99.94 2	98.13 103	99.96 14	99.63 33	99.96 27	100.00 1

test_fmvsmconf0.01_n		99.57 10	99.63 10	99.36 70	99.87 12	98.13 138	98.08 179	99.95 1	99.45 48	99.98 2	99.75 16	99.80 1	99.97 7	99.82 10	99.99 5	99.99 2

fmvsm_s_conf0.1_n_a		99.17 51	99.30 43	98.80 175	99.75 34	96.59 254	97.97 204	99.86 16	98.22 177	99.88 20	99.71 22	98.59 59	99.84 167	99.73 25	99.98 12	99.98 3

fmvsm_s_conf0.1_n_2		99.20 49	99.38 28	98.65 200	99.69 58	96.08 273	97.49 272	99.90 11	99.53 39	99.88 20	99.64 37	98.51 66	99.90 78	99.83 9	99.98 12	99.97 4

mmtdpeth		99.30 33	99.42 24	98.92 161	99.58 86	96.89 241	99.48 13	99.92 7	99.92 2	98.26 276	99.80 11	98.33 82	99.91 71	99.56 38	99.95 37	99.97 4

fmvsm_s_conf0.1_n		99.16 55	99.33 36	98.64 202	99.71 47	96.10 268	97.87 216	99.85 18	98.56 154	99.90 13	99.68 25	98.69 49	99.85 149	99.72 27	99.98 12	99.97 4

test_fmvs3		99.12 66	99.41 25	98.25 261	99.76 30	95.07 312	99.05 67	99.94 2	97.78 213	99.82 32	99.84 3	98.56 63	99.71 279	99.96 1	99.96 27	99.97 4

test_fmvsmconf0.1_n		99.49 15	99.54 14	99.34 79	99.78 24	98.11 139	97.77 230	99.90 11	99.33 63	99.97 3	99.66 32	99.71 3	99.96 14	99.79 17	99.99 5	99.96 8

test_f		98.67 136	98.87 93	98.05 279	99.72 43	95.59 287	98.51 127	99.81 30	96.30 320	99.78 38	99.82 5	96.14 230	98.63 432	99.82 10	99.93 53	99.95 9

test_fmvs2		98.70 125	98.97 85	97.89 286	99.54 108	94.05 340	98.55 118	99.92 7	96.78 298	99.72 45	99.78 13	96.60 212	99.67 299	99.91 2	99.90 82	99.94 10

PS-MVSNAJss		99.46 17	99.49 16	99.35 76	99.90 4	98.15 135	99.20 48	99.65 59	99.48 42	99.92 8	99.71 22	98.07 106	99.96 14	99.53 45	100.00 1	99.93 11

test_vis3_rt		99.14 59	99.17 57	99.07 131	99.78 24	98.38 115	98.92 82	99.94 2	97.80 211	99.91 12	99.67 30	97.15 177	98.91 425	99.76 21	99.56 239	99.92 12

fmvsm_s_conf0.5_n_2		99.14 59	99.31 40	98.63 206	99.49 129	96.08 273	97.38 280	99.81 30	99.48 42	99.84 29	99.57 49	98.46 70	99.89 93	99.82 10	99.97 20	99.91 13

MVStest1		95.86 341	95.60 337	96.63 365	95.87 443	91.70 391	97.93 205	98.94 277	98.03 192	99.56 69	99.66 32	71.83 430	98.26 436	99.35 56	99.24 298	99.91 13

fmvsm_s_conf0.5_n_a		99.10 68	99.20 55	98.78 181	99.55 103	96.59 254	97.79 226	99.82 29	98.21 178	99.81 35	99.53 63	98.46 70	99.84 167	99.70 30	99.97 20	99.90 15

fmvsm_s_conf0.5_n_9		99.17 51	99.38 28	98.53 228	99.51 115	95.82 283	97.62 253	99.78 35	99.72 15	99.90 13	99.48 74	98.66 51	99.89 93	99.85 5	99.93 53	99.89 16

fmvsm_s_conf0.5_n		99.09 69	99.26 48	98.61 211	99.55 103	96.09 271	97.74 236	99.81 30	98.55 155	99.85 26	99.55 57	98.60 58	99.84 167	99.69 32	99.98 12	99.89 16

test_fmvsmconf_n		99.44 19	99.48 18	99.31 90	99.64 74	98.10 141	97.68 242	99.84 22	99.29 69	99.92 8	99.57 49	99.60 5	99.96 14	99.74 24	99.98 12	99.89 16

test_djsdf		99.52 13	99.51 15	99.53 38	99.86 14	98.74 88	99.39 20	99.56 85	99.11 92	99.70 49	99.73 20	99.00 26	99.97 7	99.26 63	99.98 12	99.89 16

mvs_tets		99.63 6	99.67 6	99.49 54	99.88 9	98.61 98	99.34 23	99.71 45	99.27 71	99.90 13	99.74 18	99.68 4	99.97 7	99.55 40	99.99 5	99.88 20

fmvsm_s_conf0.5_n_8		99.13 63	99.26 48	98.74 192	99.51 115	96.44 260	97.65 248	99.65 59	99.66 24	99.78 38	99.48 74	97.92 119	99.93 52	99.72 27	99.95 37	99.87 21

fmvsm_s_conf0.5_n_7		98.83 103	99.04 77	98.20 265	99.30 180	94.83 316	97.23 293	99.36 163	98.64 139	99.84 29	99.43 86	98.10 105	99.91 71	99.56 38	99.96 27	99.87 21

fmvsm_l_conf0.5_n_3		99.45 18	99.48 18	99.34 79	99.59 85	98.21 132	97.82 221	99.84 22	99.41 55	99.92 8	99.41 91	99.51 8	99.95 26	99.84 8	99.97 20	99.87 21

ttmdpeth		97.91 226	98.02 212	97.58 314	98.69 314	94.10 339	98.13 171	98.90 286	97.95 198	97.32 346	99.58 47	95.95 246	98.75 430	96.41 272	99.22 302	99.87 21

jajsoiax		99.58 9	99.61 11	99.48 56	99.87 12	98.61 98	99.28 40	99.66 58	99.09 102	99.89 17	99.68 25	99.53 7	99.97 7	99.50 48	99.99 5	99.87 21

EU-MVSNet		97.66 251	98.50 144	95.13 402	99.63 80	85.84 433	98.35 149	98.21 345	98.23 176	99.54 74	99.46 79	95.02 272	99.68 296	98.24 132	99.87 94	99.87 21

fmvsm_s_conf0.5_n_3		99.22 46	99.37 31	98.78 181	99.46 141	96.58 256	97.65 248	99.72 43	99.47 45	99.86 23	99.50 67	98.94 29	99.89 93	99.75 23	99.97 20	99.86 27

UA-Net		99.47 16	99.40 26	99.70 2	99.49 129	99.29 24	99.80 4	99.72 43	99.82 8	99.04 168	99.81 8	98.05 109	99.96 14	98.85 95	99.99 5	99.86 27

MM		98.22 200	97.99 215	98.91 162	98.66 324	96.97 234	97.89 212	94.44 420	99.54 38	98.95 183	99.14 157	93.50 308	99.92 62	99.80 15	99.96 27	99.85 29

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 14	100.00 1	99.85 29

fmvsm_l_conf0.5_n_a		99.19 50	99.27 46	98.94 156	99.65 68	97.05 230	97.80 225	99.76 38	98.70 137	99.78 38	99.11 163	98.79 41	99.95 26	99.85 5	99.96 27	99.83 31

fmvsm_l_conf0.5_n		99.21 47	99.28 45	99.02 144	99.64 74	97.28 215	97.82 221	99.76 38	98.73 134	99.82 32	99.09 170	98.81 37	99.95 26	99.86 4	99.96 27	99.83 31

mvsany_test3		98.87 98	98.92 88	98.74 192	99.38 159	96.94 238	98.58 115	99.10 253	96.49 310	99.96 4	99.81 8	98.18 96	99.45 381	98.97 87	99.79 136	99.83 31

SSC-MVS		98.71 121	98.74 106	98.62 208	99.72 43	96.08 273	98.74 96	98.64 326	99.74 13	99.67 57	99.24 130	94.57 286	99.95 26	99.11 75	99.24 298	99.82 34

anonymousdsp		99.51 14	99.47 21	99.62 9	99.88 9	99.08 69	99.34 23	99.69 49	98.93 121	99.65 61	99.72 21	98.93 31	99.95 26	99.11 75	100.00 1	99.82 34

ANet_high		99.57 10	99.67 6	99.28 92	99.89 6	98.09 142	99.14 57	99.93 5	99.82 8	99.93 6	99.81 8	99.17 19	99.94 41	99.31 59	100.00 1	99.82 34

fmvsm_s_conf0.5_n_4		99.01 79	99.22 52	98.38 247	99.31 176	95.48 294	97.56 263	99.73 42	98.87 126	99.75 43	99.27 118	98.80 39	99.86 136	99.80 15	99.90 82	99.81 37

PS-CasMVS		99.40 26	99.33 36	99.62 9	99.71 47	99.10 65	99.29 36	99.53 96	99.53 39	99.46 93	99.41 91	98.23 89	99.95 26	98.89 93	99.95 37	99.81 37

VortexMVS		97.98 224	98.31 176	97.02 347	98.88 276	91.45 395	98.03 188	99.47 120	98.65 138	99.55 72	99.47 77	91.49 339	99.81 210	99.32 58	99.91 75	99.80 39

FC-MVSNet-test		99.27 37	99.25 50	99.34 79	99.77 27	98.37 117	99.30 35	99.57 78	99.61 34	99.40 107	99.50 67	97.12 178	99.85 149	99.02 84	99.94 48	99.80 39

test_cas_vis1_n_1920		98.33 185	98.68 119	97.27 336	99.69 58	92.29 385	98.03 188	99.85 18	97.62 222	99.96 4	99.62 40	93.98 301	99.74 266	99.52 47	99.86 100	99.79 41

test_vis1_n_1920		98.40 174	98.92 88	96.81 360	99.74 36	90.76 411	98.15 169	99.91 9	98.33 165	99.89 17	99.55 57	95.07 271	99.88 109	99.76 21	99.93 53	99.79 41

CP-MVSNet		99.21 47	99.09 72	99.56 26	99.65 68	98.96 77	99.13 58	99.34 175	99.42 53	99.33 121	99.26 123	97.01 186	99.94 41	98.74 104	99.93 53	99.79 41

fmvsm_s_conf0.5_n_5		99.07 75	99.10 70	98.99 147	99.47 139	97.22 220	97.40 278	99.83 25	97.61 225	99.85 26	99.30 112	98.80 39	99.95 26	99.71 29	99.90 82	99.78 44

UniMVSNet_ETH3D		99.69 2	99.69 4	99.69 3	99.84 17	99.34 20	99.69 5	99.58 71	99.90 3	99.86 23	99.78 13	99.58 6	99.95 26	99.00 85	99.95 37	99.78 44

CVMVSNet		96.25 330	97.21 273	93.38 423	99.10 229	80.56 451	97.20 298	98.19 348	96.94 289	99.00 173	99.02 184	89.50 358	99.80 218	96.36 276	99.59 227	99.78 44

reproduce_monomvs		95.00 363	95.25 352	94.22 411	97.51 411	83.34 443	97.86 217	98.44 335	98.51 156	99.29 130	99.30 112	67.68 438	99.56 347	98.89 93	99.81 120	99.77 47

Anonymous20231211		99.27 37	99.27 46	99.26 97	99.29 183	98.18 133	99.49 12	99.51 100	99.70 16	99.80 36	99.68 25	96.84 193	99.83 185	99.21 68	99.91 75	99.77 47

PEN-MVS		99.41 25	99.34 35	99.62 9	99.73 37	99.14 57	99.29 36	99.54 93	99.62 32	99.56 69	99.42 87	98.16 100	99.96 14	98.78 99	99.93 53	99.77 47

WR-MVS_H		99.33 31	99.22 52	99.65 8	99.71 47	99.24 30	99.32 26	99.55 89	99.46 47	99.50 86	99.34 104	97.30 167	99.93 52	98.90 91	99.93 53	99.77 47

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 29	99.78 38	99.67 30	99.48 10	99.81 210	99.30 60	99.97 20	99.77 47
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
WB-MVS		98.52 163	98.55 137	98.43 241	99.65 68	95.59 287	98.52 122	98.77 312	99.65 26	99.52 80	99.00 196	94.34 292	99.93 52	98.65 111	98.83 346	99.76 52

patch_mono-2		98.51 164	98.63 126	98.17 268	99.38 159	94.78 318	97.36 283	99.69 49	98.16 188	98.49 257	99.29 115	97.06 181	99.97 7	98.29 131	99.91 75	99.76 52

nrg030		99.40 26	99.35 33	99.54 31	99.58 86	99.13 60	98.98 75	99.48 112	99.68 20	99.46 93	99.26 123	98.62 56	99.73 271	99.17 72	99.92 66	99.76 52

FIs		99.14 59	99.09 72	99.29 91	99.70 55	98.28 123	99.13 58	99.52 99	99.48 42	99.24 142	99.41 91	96.79 199	99.82 195	98.69 109	99.88 90	99.76 52

v7n		99.53 12	99.57 13	99.41 66	99.88 9	98.54 106	99.45 14	99.61 67	99.66 24	99.68 55	99.66 32	98.44 72	99.95 26	99.73 25	99.96 27	99.75 56

APDe-MVS		98.99 82	98.79 102	99.60 15	99.21 201	99.15 52	98.87 88	99.48 112	97.57 229	99.35 117	99.24 130	97.83 124	99.89 93	97.88 161	99.70 186	99.75 56
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DTE-MVSNet		99.43 23	99.35 33	99.66 7	99.71 47	99.30 22	99.31 30	99.51 100	99.64 27	99.56 69	99.46 79	98.23 89	99.97 7	98.78 99	99.93 53	99.72 58

MSC_two_6792asdad				99.32 87	98.43 353	98.37 117		98.86 297					99.89 93	97.14 203	99.60 223	99.71 59

No_MVS				99.32 87	98.43 353	98.37 117		98.86 297					99.89 93	97.14 203	99.60 223	99.71 59

PMMVS2		98.07 214	98.08 206	98.04 280	99.41 156	94.59 327	94.59 417	99.40 151	97.50 237	98.82 211	98.83 236	96.83 195	99.84 167	97.50 185	99.81 120	99.71 59

Baseline_NR-MVSNet		98.98 85	98.86 96	99.36 70	99.82 19	98.55 103	97.47 275	99.57 78	99.37 58	99.21 145	99.61 43	96.76 202	99.83 185	98.06 146	99.83 112	99.71 59

XXY-MVS		99.14 59	99.15 64	99.10 124	99.76 30	97.74 187	98.85 91	99.62 64	98.48 158	99.37 112	99.49 73	98.75 43	99.86 136	98.20 136	99.80 131	99.71 59

test_0728_THIRD									98.17 185	99.08 159	99.02 184	97.89 121	99.88 109	97.07 209	99.71 179	99.70 64

MSP-MVS		98.40 174	98.00 214	99.61 13	99.57 91	99.25 29	98.57 116	99.35 169	97.55 233	99.31 129	97.71 354	94.61 285	99.88 109	96.14 289	99.19 309	99.70 64
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		98.53 159	98.79 102	97.74 300	99.46 141	93.62 362	96.45 337	99.34 175	99.33 63	98.93 191	98.70 259	97.90 120	99.90 78	99.12 74	99.92 66	99.69 66

NormalMVS		98.26 195	97.97 219	99.15 117	99.64 74	97.83 174	98.28 153	99.43 138	99.24 73	98.80 214	98.85 231	89.76 354	99.94 41	98.04 148	99.67 200	99.68 67

KinetiMVS		99.03 77	99.02 78	99.03 141	99.70 55	97.48 203	98.43 140	99.29 204	99.70 16	99.60 68	99.07 171	96.13 231	99.94 41	99.42 53	99.87 94	99.68 67

dcpmvs_2		98.78 112	99.11 68	97.78 293	99.56 99	93.67 359	99.06 65	99.86 16	99.50 41	99.66 58	99.26 123	97.21 175	99.99 2	98.00 153	99.91 75	99.68 67

test_0728_SECOND				99.60 15	99.50 121	99.23 31	98.02 191	99.32 183					99.88 109	96.99 215	99.63 213	99.68 67

OurMVSNet-221017-0		99.37 29	99.31 40	99.53 38	99.91 3	98.98 71	99.63 7	99.58 71	99.44 50	99.78 38	99.76 15	96.39 220	99.92 62	99.44 52	99.92 66	99.68 67

fmvsm_s_conf0.5_n_6		99.08 73	99.21 54	98.69 196	99.36 166	96.51 258	97.62 253	99.68 54	98.43 160	99.85 26	99.10 166	99.12 22	99.88 109	99.77 20	99.92 66	99.67 72

CHOSEN 1792x2688		97.49 263	97.14 278	98.54 226	99.68 61	96.09 271	96.50 335	99.62 64	91.58 411	98.84 207	98.97 203	92.36 327	99.88 109	96.76 238	99.95 37	99.67 72

reproduce_model		99.15 56	98.97 85	99.67 4	99.33 174	99.44 10	98.15 169	99.47 120	99.12 91	99.52 80	99.32 110	98.31 83	99.90 78	97.78 167	99.73 166	99.66 74

IU-MVS					99.49 129	99.15 52		98.87 292	92.97 396	99.41 104				96.76 238	99.62 216	99.66 74

test_241102_TWO								99.30 196	98.03 192	99.26 137	99.02 184	97.51 155	99.88 109	96.91 221	99.60 223	99.66 74

DPE-MVS		98.59 149	98.26 183	99.57 21	99.27 187	99.15 52	97.01 307	99.39 153	97.67 218	99.44 97	98.99 197	97.53 152	99.89 93	95.40 319	99.68 194	99.66 74
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 70	99.80 21	98.58 101	99.27 42	99.57 78	99.39 56	99.75 43	99.62 40	99.17 19	99.83 185	99.06 80	99.62 216	99.66 74

EI-MVSNet-UG-set		98.69 128	98.71 113	98.62 208	99.10 229	96.37 262	97.23 293	98.87 292	99.20 80	99.19 147	98.99 197	97.30 167	99.85 149	98.77 102	99.79 136	99.65 79

Elysia		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 129	99.43 138	99.67 21	99.70 49	99.13 159	96.66 208	99.98 4	99.54 41	99.96 27	99.64 80

StellarMVS		99.15 56	99.14 65	99.18 109	99.63 80	97.92 165	98.50 129	99.43 138	99.67 21	99.70 49	99.13 159	96.66 208	99.98 4	99.54 41	99.96 27	99.64 80

pmmvs6		99.67 3	99.70 3	99.60 15	99.90 4	99.27 27	99.53 9	99.76 38	99.64 27	99.84 29	99.83 4	99.50 9	99.87 128	99.36 55	99.92 66	99.64 80

EI-MVSNet-Vis-set		98.68 133	98.70 116	98.63 206	99.09 232	96.40 261	97.23 293	98.86 297	99.20 80	99.18 151	98.97 203	97.29 169	99.85 149	98.72 106	99.78 141	99.64 80

ACMH	96.65 7	99.25 40	99.24 51	99.26 97	99.72 43	98.38 115	99.07 64	99.55 89	98.30 169	99.65 61	99.45 83	99.22 16	99.76 254	98.44 123	99.77 147	99.64 80
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
DP-MVS		98.93 91	98.81 101	99.28 92	99.21 201	98.45 112	98.46 137	99.33 181	99.63 29	99.48 88	99.15 154	97.23 173	99.75 261	97.17 199	99.66 207	99.63 85

reproduce-ours		99.09 69	98.90 90	99.67 4	99.27 187	99.49 6	98.00 195	99.42 144	99.05 107	99.48 88	99.27 118	98.29 85	99.89 93	97.61 177	99.71 179	99.62 86

our_new_method		99.09 69	98.90 90	99.67 4	99.27 187	99.49 6	98.00 195	99.42 144	99.05 107	99.48 88	99.27 118	98.29 85	99.89 93	97.61 177	99.71 179	99.62 86

test_fmvs1_n		98.09 212	98.28 179	97.52 322	99.68 61	93.47 364	98.63 109	99.93 5	95.41 351	99.68 55	99.64 37	91.88 335	99.48 374	99.82 10	99.87 94	99.62 86

test1111		96.49 323	96.82 297	95.52 395	99.42 154	87.08 430	99.22 45	87.14 446	99.11 92	99.46 93	99.58 47	88.69 362	99.86 136	98.80 97	99.95 37	99.62 86

VPA-MVSNet		99.30 33	99.30 43	99.28 92	99.49 129	98.36 120	99.00 72	99.45 128	99.63 29	99.52 80	99.44 84	98.25 87	99.88 109	99.09 77	99.84 105	99.62 86

LPG-MVS_test		98.71 121	98.46 153	99.47 60	99.57 91	98.97 73	98.23 159	99.48 112	96.60 305	99.10 157	99.06 172	98.71 47	99.83 185	95.58 315	99.78 141	99.62 86

LGP-MVS_train				99.47 60	99.57 91	98.97 73		99.48 112	96.60 305	99.10 157	99.06 172	98.71 47	99.83 185	95.58 315	99.78 141	99.62 86

Test_1112_low_res		96.99 304	96.55 315	98.31 256	99.35 171	95.47 296	95.84 378	99.53 96	91.51 413	96.80 371	98.48 298	91.36 340	99.83 185	96.58 254	99.53 249	99.62 86

tt0320-xc		99.64 5	99.68 5	99.50 53	99.72 43	98.98 71	99.51 10	99.85 18	99.86 6	99.88 20	99.82 5	99.02 25	99.90 78	99.54 41	99.95 37	99.61 94

v10		98.97 86	99.11 68	98.55 223	99.44 148	96.21 267	98.90 83	99.55 89	98.73 134	99.48 88	99.60 45	96.63 211	99.83 185	99.70 30	99.99 5	99.61 94

sc_t1		99.62 7	99.66 8	99.53 38	99.82 19	99.09 68	99.50 11	99.63 62	99.88 4	99.86 23	99.80 11	99.03 23	99.89 93	99.48 50	99.93 53	99.60 96

test_vis1_n		98.31 188	98.50 144	97.73 303	99.76 30	94.17 337	98.68 106	99.91 9	96.31 318	99.79 37	99.57 49	92.85 321	99.42 386	99.79 17	99.84 105	99.60 96

v8		99.01 79	99.16 59	98.57 218	99.47 139	96.31 265	98.90 83	99.47 120	99.03 110	99.52 80	99.57 49	96.93 189	99.81 210	99.60 34	99.98 12	99.60 96

EI-MVSNet		98.40 174	98.51 142	98.04 280	99.10 229	94.73 321	97.20 298	98.87 292	98.97 116	99.06 161	99.02 184	96.00 238	99.80 218	98.58 114	99.82 116	99.60 96

SixPastTwentyTwo		98.75 117	98.62 128	99.16 114	99.83 18	97.96 162	99.28 40	98.20 346	99.37 58	99.70 49	99.65 36	92.65 325	99.93 52	99.04 82	99.84 105	99.60 96

IterMVS-LS		98.55 155	98.70 116	98.09 272	99.48 137	94.73 321	97.22 297	99.39 153	98.97 116	99.38 110	99.31 111	96.00 238	99.93 52	98.58 114	99.97 20	99.60 96
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
HyFIR lowres test		97.19 289	96.60 313	98.96 153	99.62 84	97.28 215	95.17 399	99.50 103	94.21 378	99.01 172	98.32 315	86.61 374	99.99 2	97.10 207	99.84 105	99.60 96

lecture		99.25 40	99.12 67	99.62 9	99.64 74	99.40 12	98.89 87	99.51 100	99.19 84	99.37 112	99.25 128	98.36 76	99.88 109	98.23 134	99.67 200	99.59 103

tt0320		99.61 8	99.65 9	99.48 56	99.71 47	98.94 78	99.54 8	99.83 25	99.87 5	99.89 17	99.82 5	98.75 43	99.90 78	99.54 41	99.95 37	99.59 103

ACMMP_NAP		98.75 117	98.48 149	99.57 21	99.58 86	99.29 24	97.82 221	99.25 217	96.94 289	98.78 216	99.12 162	98.02 110	99.84 167	97.13 205	99.67 200	99.59 103

VPNet		98.87 98	98.83 98	99.01 145	99.70 55	97.62 196	98.43 140	99.35 169	99.47 45	99.28 131	99.05 179	96.72 205	99.82 195	98.09 143	99.36 278	99.59 103

WR-MVS		98.40 174	98.19 192	99.03 141	99.00 251	97.65 193	96.85 317	98.94 277	98.57 151	98.89 197	98.50 295	95.60 256	99.85 149	97.54 182	99.85 101	99.59 103

HPM-MVS		98.79 110	98.53 140	99.59 19	99.65 68	99.29 24	99.16 54	99.43 138	96.74 300	98.61 239	98.38 307	98.62 56	99.87 128	96.47 268	99.67 200	99.59 103
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
EG-PatchMatch MVS		98.99 82	99.01 80	98.94 156	99.50 121	97.47 204	98.04 187	99.59 69	98.15 189	99.40 107	99.36 99	98.58 62	99.76 254	98.78 99	99.68 194	99.59 103

Vis-MVSNet		99.34 30	99.36 32	99.27 95	99.73 37	98.26 124	99.17 53	99.78 35	99.11 92	99.27 133	99.48 74	98.82 36	99.95 26	98.94 89	99.93 53	99.59 103
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
MP-MVS-pluss		98.57 150	98.23 187	99.60 15	99.69 58	99.35 17	97.16 302	99.38 155	94.87 363	98.97 179	98.99 197	98.01 111	99.88 109	97.29 193	99.70 186	99.58 111
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
region2R		98.69 128	98.40 161	99.54 31	99.53 111	99.17 44	98.52 122	99.31 188	97.46 245	98.44 261	98.51 291	97.83 124	99.88 109	96.46 269	99.58 232	99.58 111

ACMMPR		98.70 125	98.42 159	99.54 31	99.52 113	99.14 57	98.52 122	99.31 188	97.47 240	98.56 248	98.54 286	97.75 132	99.88 109	96.57 256	99.59 227	99.58 111

PGM-MVS		98.66 137	98.37 167	99.55 28	99.53 111	99.18 43	98.23 159	99.49 110	97.01 286	98.69 227	98.88 225	98.00 112	99.89 93	95.87 301	99.59 227	99.58 111

SteuartSystems-ACMMP		98.79 110	98.54 139	99.54 31	99.73 37	99.16 48	98.23 159	99.31 188	97.92 202	98.90 195	98.90 218	98.00 112	99.88 109	96.15 288	99.72 174	99.58 111
Skip Steuart: Steuart Systems R&D Blog.
SDMVSNet		99.23 45	99.32 38	98.96 153	99.68 61	97.35 211	98.84 93	99.48 112	99.69 18	99.63 64	99.68 25	99.03 23	99.96 14	97.97 155	99.92 66	99.57 116

sd_testset		99.28 36	99.31 40	99.19 108	99.68 61	98.06 151	99.41 17	99.30 196	99.69 18	99.63 64	99.68 25	99.25 15	99.96 14	97.25 196	99.92 66	99.57 116

TranMVSNet+NR-MVSNet		99.17 51	99.07 75	99.46 62	99.37 165	98.87 81	98.39 145	99.42 144	99.42 53	99.36 115	99.06 172	98.38 75	99.95 26	98.34 128	99.90 82	99.57 116

mPP-MVS		98.64 140	98.34 171	99.54 31	99.54 108	99.17 44	98.63 109	99.24 222	97.47 240	98.09 290	98.68 263	97.62 143	99.89 93	96.22 283	99.62 216	99.57 116

PVSNet_Blended_VisFu		98.17 207	98.15 198	98.22 264	99.73 37	95.15 308	97.36 283	99.68 54	94.45 373	98.99 174	99.27 118	96.87 192	99.94 41	97.13 205	99.91 75	99.57 116

1112_ss		97.29 281	96.86 293	98.58 215	99.34 173	96.32 264	96.75 323	99.58 71	93.14 394	96.89 366	97.48 368	92.11 332	99.86 136	96.91 221	99.54 245	99.57 116

MTAPA		98.88 97	98.64 125	99.61 13	99.67 65	99.36 16	98.43 140	99.20 228	98.83 132	98.89 197	98.90 218	96.98 188	99.92 62	97.16 200	99.70 186	99.56 122

XVS		98.72 120	98.45 154	99.53 38	99.46 141	99.21 33	98.65 107	99.34 175	98.62 144	97.54 329	98.63 275	97.50 156	99.83 185	96.79 234	99.53 249	99.56 122

pm-mvs1		99.44 19	99.48 18	99.33 85	99.80 21	98.63 95	99.29 36	99.63 62	99.30 68	99.65 61	99.60 45	99.16 21	99.82 195	99.07 78	99.83 112	99.56 122

X-MVStestdata		94.32 370	92.59 389	99.53 38	99.46 141	99.21 33	98.65 107	99.34 175	98.62 144	97.54 329	45.85 448	97.50 156	99.83 185	96.79 234	99.53 249	99.56 122

HPM-MVS_fast		99.01 79	98.82 99	99.57 21	99.71 47	99.35 17	99.00 72	99.50 103	97.33 256	98.94 190	98.86 228	98.75 43	99.82 195	97.53 183	99.71 179	99.56 122

K. test v3		98.00 220	97.66 245	99.03 141	99.79 23	97.56 198	99.19 52	92.47 432	99.62 32	99.52 80	99.66 32	89.61 356	99.96 14	99.25 65	99.81 120	99.56 122

CP-MVS		98.70 125	98.42 159	99.52 44	99.36 166	99.12 62	98.72 101	99.36 163	97.54 234	98.30 270	98.40 304	97.86 123	99.89 93	96.53 265	99.72 174	99.56 122

ZNCC-MVS		98.68 133	98.40 161	99.54 31	99.57 91	99.21 33	98.46 137	99.29 204	97.28 262	98.11 288	98.39 305	98.00 112	99.87 128	96.86 231	99.64 210	99.55 129

v1192		98.60 147	98.66 122	98.41 243	99.27 187	95.88 279	97.52 268	99.36 163	97.41 249	99.33 121	99.20 139	96.37 223	99.82 195	99.57 36	99.92 66	99.55 129

v1240		98.55 155	98.62 128	98.32 254	99.22 199	95.58 289	97.51 270	99.45 128	97.16 277	99.45 96	99.24 130	96.12 233	99.85 149	99.60 34	99.88 90	99.55 129

UGNet		98.53 159	98.45 154	98.79 178	97.94 382	96.96 236	99.08 61	98.54 330	99.10 99	96.82 370	99.47 77	96.55 214	99.84 167	98.56 119	99.94 48	99.55 129
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
AstraMVS		98.16 209	98.07 208	98.41 243	99.51 115	95.86 280	98.00 195	95.14 415	98.97 116	99.43 98	99.24 130	93.25 309	99.84 167	99.21 68	99.87 94	99.54 133

WBMVS		95.18 358	94.78 364	96.37 371	97.68 399	89.74 418	95.80 379	98.73 319	97.54 234	98.30 270	98.44 301	70.06 432	99.82 195	96.62 251	99.87 94	99.54 133

test2506		92.39 401	91.89 403	93.89 416	99.38 159	82.28 447	99.32 26	66.03 454	99.08 104	98.77 219	99.57 49	66.26 442	99.84 167	98.71 107	99.95 37	99.54 133

ECVR-MVS		96.42 325	96.61 311	95.85 387	99.38 159	88.18 425	99.22 45	86.00 448	99.08 104	99.36 115	99.57 49	88.47 367	99.82 195	98.52 120	99.95 37	99.54 133

v144192		98.54 157	98.57 136	98.45 238	99.21 201	95.98 276	97.63 252	99.36 163	97.15 279	99.32 127	99.18 144	95.84 250	99.84 167	99.50 48	99.91 75	99.54 133

v1921920		98.54 157	98.60 133	98.38 247	99.20 205	95.76 286	97.56 263	99.36 163	97.23 271	99.38 110	99.17 148	96.02 236	99.84 167	99.57 36	99.90 82	99.54 133

MP-MVS		98.46 168	98.09 203	99.54 31	99.57 91	99.22 32	98.50 129	99.19 232	97.61 225	97.58 325	98.66 268	97.40 163	99.88 109	94.72 334	99.60 223	99.54 133
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MIMVSNet1		99.38 28	99.32 38	99.55 28	99.86 14	99.19 42	99.41 17	99.59 69	99.59 35	99.71 47	99.57 49	97.12 178	99.90 78	99.21 68	99.87 94	99.54 133

ACMMP		98.75 117	98.50 144	99.52 44	99.56 99	99.16 48	98.87 88	99.37 159	97.16 277	98.82 211	99.01 193	97.71 134	99.87 128	96.29 280	99.69 189	99.54 133
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		98.40 174	98.03 211	99.51 48	99.16 218	99.21 33	98.05 185	99.22 225	94.16 379	98.98 175	99.10 166	97.52 154	99.79 231	96.45 270	99.64 210	99.53 142
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		98.71 121	98.44 156	99.51 48	99.49 129	99.16 48	98.52 122	99.31 188	97.47 240	98.58 245	98.50 295	97.97 116	99.85 149	96.57 256	99.59 227	99.53 142

UniMVSNet_NR-MVSNet		98.86 101	98.68 119	99.40 68	99.17 216	98.74 88	97.68 242	99.40 151	99.14 90	99.06 161	98.59 282	96.71 206	99.93 52	98.57 116	99.77 147	99.53 142

GST-MVS		98.61 146	98.30 177	99.52 44	99.51 115	99.20 39	98.26 157	99.25 217	97.44 248	98.67 230	98.39 305	97.68 135	99.85 149	96.00 293	99.51 254	99.52 145

MVS_0304		97.44 268	97.01 284	98.72 194	96.42 436	96.74 249	97.20 298	91.97 436	98.46 159	98.30 270	98.79 244	92.74 323	99.91 71	99.30 60	99.94 48	99.52 145

TDRefinement		99.42 24	99.38 28	99.55 28	99.76 30	99.33 21	99.68 6	99.71 45	99.38 57	99.53 78	99.61 43	98.64 53	99.80 218	98.24 132	99.84 105	99.52 145

v1144		98.60 147	98.66 122	98.41 243	99.36 166	95.90 278	97.58 261	99.34 175	97.51 236	99.27 133	99.15 154	96.34 225	99.80 218	99.47 51	99.93 53	99.51 148

v2v482		98.56 151	98.62 128	98.37 250	99.42 154	95.81 284	97.58 261	99.16 243	97.90 204	99.28 131	99.01 193	95.98 243	99.79 231	99.33 57	99.90 82	99.51 148

CPTT-MVS		97.84 240	97.36 264	99.27 95	99.31 176	98.46 111	98.29 152	99.27 211	94.90 362	97.83 309	98.37 308	94.90 274	99.84 167	93.85 362	99.54 245	99.51 148

LuminaMVS		98.39 180	98.20 189	98.98 151	99.50 121	97.49 201	97.78 227	97.69 361	98.75 133	99.49 87	99.25 128	92.30 329	99.94 41	99.14 73	99.88 90	99.50 151

DU-MVS		98.82 106	98.63 126	99.39 69	99.16 218	98.74 88	97.54 266	99.25 217	98.84 131	99.06 161	98.76 250	96.76 202	99.93 52	98.57 116	99.77 147	99.50 151

NR-MVSNet		98.95 89	98.82 99	99.36 70	99.16 218	98.72 93	99.22 45	99.20 228	99.10 99	99.72 45	98.76 250	96.38 222	99.86 136	98.00 153	99.82 116	99.50 151

casdiffmvs_mvg		99.12 66	99.16 59	98.99 147	99.43 153	97.73 189	98.00 195	99.62 64	99.22 76	99.55 72	99.22 136	98.93 31	99.75 261	98.66 110	99.81 120	99.50 151
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 73	99.00 81	99.33 85	99.71 47	98.83 83	98.60 113	99.58 71	99.11 92	99.53 78	99.18 144	98.81 37	99.67 299	96.71 245	99.77 147	99.50 151

SymmetryMVS		98.05 215	97.71 240	99.09 128	99.29 183	97.83 174	98.28 153	97.64 366	99.24 73	98.80 214	98.85 231	89.76 354	99.94 41	98.04 148	99.50 261	99.49 156

DVP-MVS++		98.90 95	98.70 116	99.51 48	98.43 353	99.15 52	99.43 15	99.32 183	98.17 185	99.26 137	99.02 184	98.18 96	99.88 109	97.07 209	99.45 267	99.49 156

PC_three_1452									93.27 392	99.40 107	98.54 286	98.22 92	97.00 443	95.17 322	99.45 267	99.49 156

GeoE		99.05 76	98.99 83	99.25 100	99.44 148	98.35 121	98.73 100	99.56 85	98.42 161	98.91 194	98.81 241	98.94 29	99.91 71	98.35 127	99.73 166	99.49 156

h-mvs33		97.77 243	97.33 267	99.10 124	99.21 201	97.84 173	98.35 149	98.57 329	99.11 92	98.58 245	99.02 184	88.65 365	99.96 14	98.11 141	96.34 424	99.49 156

IterMVS-SCA-FT		97.85 239	98.18 193	96.87 356	99.27 187	91.16 405	95.53 387	99.25 217	99.10 99	99.41 104	99.35 100	93.10 314	99.96 14	98.65 111	99.94 48	99.49 156

new-patchmatchnet		98.35 181	98.74 106	97.18 339	99.24 194	92.23 387	96.42 341	99.48 112	98.30 169	99.69 53	99.53 63	97.44 161	99.82 195	98.84 96	99.77 147	99.49 156

APD-MVS		98.10 210	97.67 242	99.42 64	99.11 227	98.93 79	97.76 233	99.28 208	94.97 360	98.72 225	98.77 248	97.04 182	99.85 149	93.79 363	99.54 245	99.49 156
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
EPP-MVSNet		98.30 189	98.04 210	99.07 131	99.56 99	97.83 174	99.29 36	98.07 352	99.03 110	98.59 243	99.13 159	92.16 331	99.90 78	96.87 229	99.68 194	99.49 156

DeepC-MVS	97.60 4	98.97 86	98.93 87	99.10 124	99.35 171	97.98 158	98.01 194	99.46 124	97.56 231	99.54 74	99.50 67	98.97 27	99.84 167	98.06 146	99.92 66	99.49 156
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 93	98.73 108	99.48 56	99.55 103	99.14 57	98.07 182	99.37 159	97.62 222	99.04 168	98.96 206	98.84 35	99.79 231	97.43 187	99.65 208	99.49 156
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
guyue		98.01 219	97.93 224	98.26 260	99.45 146	95.48 294	98.08 179	96.24 398	98.89 125	99.34 119	99.14 157	91.32 341	99.82 195	99.07 78	99.83 112	99.48 167

DVP-MVS		98.77 115	98.52 141	99.52 44	99.50 121	99.21 33	98.02 191	98.84 301	97.97 196	99.08 159	99.02 184	97.61 144	99.88 109	96.99 215	99.63 213	99.48 167
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		98.71 121	98.43 157	99.57 21	99.18 215	99.35 17	98.36 148	99.29 204	98.29 172	98.88 200	98.85 231	97.53 152	99.87 128	96.14 289	99.31 286	99.48 167

TSAR-MVS + MP.		98.63 142	98.49 148	99.06 137	99.64 74	97.90 168	98.51 127	98.94 277	96.96 287	99.24 142	98.89 224	97.83 124	99.81 210	96.88 228	99.49 263	99.48 167
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
VDDNet		98.21 202	97.95 220	99.01 145	99.58 86	97.74 187	99.01 70	97.29 374	99.67 21	98.97 179	99.50 67	90.45 349	99.80 218	97.88 161	99.20 306	99.48 167

IterMVS		97.73 245	98.11 202	96.57 366	99.24 194	90.28 414	95.52 389	99.21 226	98.86 128	99.33 121	99.33 106	93.11 313	99.94 41	98.49 121	99.94 48	99.48 167
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IS-MVSNet		98.19 204	97.90 227	99.08 129	99.57 91	97.97 159	99.31 30	98.32 341	99.01 112	98.98 175	99.03 183	91.59 337	99.79 231	95.49 317	99.80 131	99.48 167

ACMP	95.32 15	98.41 172	98.09 203	99.36 70	99.51 115	98.79 86	97.68 242	99.38 155	95.76 338	98.81 213	98.82 239	98.36 76	99.82 195	94.75 331	99.77 147	99.48 167
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MCST-MVS		98.00 220	97.63 248	99.10 124	99.24 194	98.17 134	96.89 316	98.73 319	95.66 339	97.92 300	97.70 356	97.17 176	99.66 310	96.18 287	99.23 301	99.47 175

3Dnovator+	97.89 3	98.69 128	98.51 142	99.24 102	98.81 291	98.40 113	99.02 69	99.19 232	98.99 113	98.07 291	99.28 116	97.11 180	99.84 167	96.84 232	99.32 284	99.47 175

HPM-MVS++		98.10 210	97.64 247	99.48 56	99.09 232	99.13 60	97.52 268	98.75 316	97.46 245	96.90 365	97.83 349	96.01 237	99.84 167	95.82 305	99.35 280	99.46 177

V42		98.78 112	98.78 104	98.76 186	99.44 148	97.04 231	98.27 156	99.19 232	97.87 206	99.25 141	99.16 150	96.84 193	99.78 242	99.21 68	99.84 105	99.46 177

APD-MVS_3200maxsize		98.84 102	98.61 132	99.53 38	99.19 208	99.27 27	98.49 132	99.33 181	98.64 139	99.03 171	98.98 201	97.89 121	99.85 149	96.54 264	99.42 271	99.46 177

UniMVSNet (Re)		98.87 98	98.71 113	99.35 76	99.24 194	98.73 91	97.73 238	99.38 155	98.93 121	99.12 153	98.73 253	96.77 200	99.86 136	98.63 113	99.80 131	99.46 177

SR-MVS-dyc-post		98.81 108	98.55 137	99.57 21	99.20 205	99.38 13	98.48 135	99.30 196	98.64 139	98.95 183	98.96 206	97.49 159	99.86 136	96.56 260	99.39 274	99.45 181

RE-MVS-def			98.58 135		99.20 205	99.38 13	98.48 135	99.30 196	98.64 139	98.95 183	98.96 206	97.75 132		96.56 260	99.39 274	99.45 181

HQP_MVS		97.99 223	97.67 242	98.93 158	99.19 208	97.65 193	97.77 230	99.27 211	98.20 182	97.79 312	97.98 339	94.90 274	99.70 283	94.42 343	99.51 254	99.45 181

plane_prior5								99.27 211					99.70 283	94.42 343	99.51 254	99.45 181

lessismore_v0				98.97 152	99.73 37	97.53 200		86.71 447		99.37 112	99.52 66	89.93 352	99.92 62	98.99 86	99.72 174	99.44 185

TAMVS		98.24 199	98.05 209	98.80 175	99.07 236	97.18 225	97.88 213	98.81 306	96.66 304	99.17 152	99.21 137	94.81 280	99.77 248	96.96 219	99.88 90	99.44 185

DeepPCF-MVS	96.93 5	98.32 186	98.01 213	99.23 104	98.39 358	98.97 73	95.03 403	99.18 236	96.88 292	99.33 121	98.78 246	98.16 100	99.28 407	96.74 240	99.62 216	99.44 185

3Dnovator	98.27 2	98.81 108	98.73 108	99.05 138	98.76 296	97.81 182	99.25 43	99.30 196	98.57 151	98.55 250	99.33 106	97.95 117	99.90 78	97.16 200	99.67 200	99.44 185

MVSFormer		98.26 195	98.43 157	97.77 294	98.88 276	93.89 352	99.39 20	99.56 85	99.11 92	98.16 282	98.13 326	93.81 304	99.97 7	99.26 63	99.57 236	99.43 189

jason		97.45 267	97.35 265	97.76 297	99.24 194	93.93 348	95.86 375	98.42 337	94.24 377	98.50 256	98.13 326	94.82 278	99.91 71	97.22 197	99.73 166	99.43 189
jason: jason.
NCCC		97.86 234	97.47 259	99.05 138	98.61 329	98.07 148	96.98 309	98.90 286	97.63 221	97.04 355	97.93 344	95.99 242	99.66 310	95.31 320	98.82 348	99.43 189

Anonymous20240521		98.69 128	98.87 93	98.16 270	99.77 27	95.11 311	99.08 61	99.44 132	99.34 62	99.33 121	99.55 57	94.10 300	99.94 41	99.25 65	99.96 27	99.42 192

MVS_111021_HR		98.25 198	98.08 206	98.75 188	99.09 232	97.46 205	95.97 366	99.27 211	97.60 227	97.99 298	98.25 318	98.15 102	99.38 392	96.87 229	99.57 236	99.42 192

COLMAP_ROB	96.50 10	98.99 82	98.85 97	99.41 66	99.58 86	99.10 65	98.74 96	99.56 85	99.09 102	99.33 121	99.19 140	98.40 74	99.72 278	95.98 295	99.76 159	99.42 192
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 93	98.72 110	99.49 54	99.49 129	99.17 44	98.10 177	99.31 188	98.03 192	99.66 58	99.02 184	98.36 76	99.88 109	96.91 221	99.62 216	99.41 195

OPU-MVS				98.82 171	98.59 334	98.30 122	98.10 177				98.52 290	98.18 96	98.75 430	94.62 335	99.48 264	99.41 195

our_test_3		97.39 273	97.73 238	96.34 372	98.70 309	89.78 417	94.61 416	98.97 276	96.50 309	99.04 168	98.85 231	95.98 243	99.84 167	97.26 195	99.67 200	99.41 195

casdiffmvs		98.95 89	99.00 81	98.81 173	99.38 159	97.33 212	97.82 221	99.57 78	99.17 88	99.35 117	99.17 148	98.35 80	99.69 287	98.46 122	99.73 166	99.41 195
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		97.60 254	97.67 242	97.39 332	99.04 245	93.04 371	95.27 396	98.38 340	97.25 265	98.92 193	98.95 210	95.48 262	99.73 271	96.99 215	98.74 350	99.41 195

MDA-MVSNet_test_wron		97.60 254	97.66 245	97.41 331	99.04 245	93.09 367	95.27 396	98.42 337	97.26 264	98.88 200	98.95 210	95.43 263	99.73 271	97.02 212	98.72 352	99.41 195

GBi-Net		98.65 138	98.47 151	99.17 111	98.90 270	98.24 126	99.20 48	99.44 132	98.59 147	98.95 183	99.55 57	94.14 296	99.86 136	97.77 168	99.69 189	99.41 195

test1		98.65 138	98.47 151	99.17 111	98.90 270	98.24 126	99.20 48	99.44 132	98.59 147	98.95 183	99.55 57	94.14 296	99.86 136	97.77 168	99.69 189	99.41 195

FMVSNet1		99.17 51	99.17 57	99.17 111	99.55 103	98.24 126	99.20 48	99.44 132	99.21 78	99.43 98	99.55 57	97.82 127	99.86 136	98.42 125	99.89 88	99.41 195

test_fmvs1		97.72 246	97.94 222	97.07 346	98.66 324	92.39 382	97.68 242	99.81 30	95.20 356	99.54 74	99.44 84	91.56 338	99.41 387	99.78 19	99.77 147	99.40 204

KD-MVS_self_test		99.25 40	99.18 56	99.44 63	99.63 80	99.06 70	98.69 105	99.54 93	99.31 66	99.62 67	99.53 63	97.36 165	99.86 136	99.24 67	99.71 179	99.39 205

v148		98.45 169	98.60 133	98.00 282	99.44 148	94.98 313	97.44 277	99.06 258	98.30 169	99.32 127	98.97 203	96.65 210	99.62 324	98.37 126	99.85 101	99.39 205

test20.03		98.78 112	98.77 105	98.78 181	99.46 141	97.20 223	97.78 227	99.24 222	99.04 109	99.41 104	98.90 218	97.65 138	99.76 254	97.70 173	99.79 136	99.39 205

CDPH-MVS		97.26 282	96.66 309	99.07 131	99.00 251	98.15 135	96.03 364	99.01 272	91.21 417	97.79 312	97.85 348	96.89 191	99.69 287	92.75 386	99.38 277	99.39 205

EPNet		96.14 333	95.44 345	98.25 261	90.76 452	95.50 293	97.92 208	94.65 418	98.97 116	92.98 434	98.85 231	89.12 360	99.87 128	95.99 294	99.68 194	99.39 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNVR-MVS		98.17 207	97.87 229	99.07 131	98.67 319	98.24 126	97.01 307	98.93 280	97.25 265	97.62 321	98.34 312	97.27 170	99.57 344	96.42 271	99.33 283	99.39 205

DeepC-MVS_fast	96.85 6	98.30 189	98.15 198	98.75 188	98.61 329	97.23 218	97.76 233	99.09 255	97.31 259	98.75 222	98.66 268	97.56 148	99.64 318	96.10 292	99.55 243	99.39 205
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SF-MVS		98.53 159	98.27 182	99.32 87	99.31 176	98.75 87	98.19 163	99.41 148	96.77 299	98.83 208	98.90 218	97.80 129	99.82 195	95.68 311	99.52 252	99.38 212

test9_res														93.28 375	99.15 314	99.38 212

BP-MVS1		97.40 272	96.97 285	98.71 195	99.07 236	96.81 244	98.34 151	97.18 376	98.58 150	98.17 279	98.61 279	84.01 397	99.94 41	98.97 87	99.78 141	99.37 214

OPM-MVS		98.56 151	98.32 175	99.25 100	99.41 156	98.73 91	97.13 304	99.18 236	97.10 280	98.75 222	98.92 214	98.18 96	99.65 315	96.68 247	99.56 239	99.37 214
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
agg_prior2														92.50 391	99.16 312	99.37 214

AllTest		98.44 170	98.20 189	99.16 114	99.50 121	98.55 103	98.25 158	99.58 71	96.80 296	98.88 200	99.06 172	97.65 138	99.57 344	94.45 341	99.61 221	99.37 214

TestCases				99.16 114	99.50 121	98.55 103		99.58 71	96.80 296	98.88 200	99.06 172	97.65 138	99.57 344	94.45 341	99.61 221	99.37 214

MDA-MVSNet-bldmvs		97.94 225	97.91 226	98.06 277	99.44 148	94.96 314	96.63 329	99.15 248	98.35 163	98.83 208	99.11 163	94.31 293	99.85 149	96.60 253	98.72 352	99.37 214

MVSTER		96.86 308	96.55 315	97.79 292	97.91 384	94.21 335	97.56 263	98.87 292	97.49 239	99.06 161	99.05 179	80.72 410	99.80 218	98.44 123	99.82 116	99.37 214

pmmvs5		97.64 252	97.49 256	98.08 275	99.14 223	95.12 310	96.70 326	99.05 261	93.77 386	98.62 237	98.83 236	93.23 310	99.75 261	98.33 130	99.76 159	99.36 221

Anonymous20231206		98.21 202	98.21 188	98.20 265	99.51 115	95.43 298	98.13 171	99.32 183	96.16 323	98.93 191	98.82 239	96.00 238	99.83 185	97.32 192	99.73 166	99.36 221

train_agg		97.10 294	96.45 319	99.07 131	98.71 305	98.08 146	95.96 368	99.03 266	91.64 409	95.85 397	97.53 364	96.47 217	99.76 254	93.67 365	99.16 312	99.36 221

PVSNet_BlendedMVS		97.55 259	97.53 253	97.60 312	98.92 266	93.77 356	96.64 328	99.43 138	94.49 369	97.62 321	99.18 144	96.82 196	99.67 299	94.73 332	99.93 53	99.36 221

Anonymous20240529		98.93 91	98.87 93	99.12 120	99.19 208	98.22 131	99.01 70	98.99 275	99.25 72	99.54 74	99.37 95	97.04 182	99.80 218	97.89 158	99.52 252	99.35 225

F-COLMAP		97.30 279	96.68 306	99.14 118	99.19 208	98.39 114	97.27 292	99.30 196	92.93 397	96.62 377	98.00 337	95.73 253	99.68 296	92.62 389	98.46 369	99.35 225

ppachtmachnet_test		97.50 260	97.74 236	96.78 362	98.70 309	91.23 404	94.55 418	99.05 261	96.36 315	99.21 145	98.79 244	96.39 220	99.78 242	96.74 240	99.82 116	99.34 227

VDD-MVS		98.56 151	98.39 164	99.07 131	99.13 225	98.07 148	98.59 114	97.01 381	99.59 35	99.11 154	99.27 118	94.82 278	99.79 231	98.34 128	99.63 213	99.34 227

testgi		98.32 186	98.39 164	98.13 271	99.57 91	95.54 290	97.78 227	99.49 110	97.37 253	99.19 147	97.65 358	98.96 28	99.49 371	96.50 267	98.99 334	99.34 227

diffmvs		98.22 200	98.24 186	98.17 268	99.00 251	95.44 297	96.38 343	99.58 71	97.79 212	98.53 253	98.50 295	96.76 202	99.74 266	97.95 157	99.64 210	99.34 227
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		97.89 229	97.60 250	98.75 188	99.31 176	97.17 226	97.62 253	99.35 169	98.72 136	98.76 221	98.68 263	92.57 326	99.74 266	97.76 172	95.60 432	99.34 227

baseline		98.96 88	99.02 78	98.76 186	99.38 159	97.26 217	98.49 132	99.50 103	98.86 128	99.19 147	99.06 172	98.23 89	99.69 287	98.71 107	99.76 159	99.33 232

MG-MVS		96.77 312	96.61 311	97.26 337	98.31 362	93.06 368	95.93 371	98.12 351	96.45 313	97.92 300	98.73 253	93.77 306	99.39 390	91.19 410	99.04 326	99.33 232

HQP4-MVS										95.56 402			99.54 356			99.32 234

CDS-MVSNet		97.69 248	97.35 265	98.69 196	98.73 300	97.02 233	96.92 315	98.75 316	95.89 335	98.59 243	98.67 265	92.08 333	99.74 266	96.72 243	99.81 120	99.32 234
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
HQP-MVS		97.00 303	96.49 318	98.55 223	98.67 319	96.79 245	96.29 349	99.04 264	96.05 326	95.55 403	96.84 385	93.84 302	99.54 356	92.82 383	99.26 296	99.32 234

RPSCF		98.62 145	98.36 168	99.42 64	99.65 68	99.42 11	98.55 118	99.57 78	97.72 216	98.90 195	99.26 123	96.12 233	99.52 362	95.72 308	99.71 179	99.32 234

MVP-Stereo		98.08 213	97.92 225	98.57 218	98.96 258	96.79 245	97.90 211	99.18 236	96.41 314	98.46 259	98.95 210	95.93 247	99.60 332	96.51 266	98.98 337	99.31 238
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
SD-MVS		98.40 174	98.68 119	97.54 320	98.96 258	97.99 155	97.88 213	99.36 163	98.20 182	99.63 64	99.04 181	98.76 42	95.33 447	96.56 260	99.74 163	99.31 238
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		98.42 171	98.30 177	98.79 178	98.79 295	97.29 214	98.23 159	98.66 323	99.31 66	98.85 205	98.80 242	94.80 281	99.78 242	98.13 140	99.13 317	99.31 238

test_prior				98.95 155	98.69 314	97.95 163		99.03 266					99.59 336			99.30 241

USDC		97.41 271	97.40 260	97.44 329	98.94 260	93.67 359	95.17 399	99.53 96	94.03 383	98.97 179	99.10 166	95.29 265	99.34 397	95.84 304	99.73 166	99.30 241

test_fmvsm_n_1920		99.33 31	99.45 23	98.99 147	99.57 91	97.73 189	97.93 205	99.83 25	99.22 76	99.93 6	99.30 112	99.42 11	99.96 14	99.85 5	99.99 5	99.29 243

FMVSNet2		98.49 165	98.40 161	98.75 188	98.90 270	97.14 229	98.61 112	99.13 249	98.59 147	99.19 147	99.28 116	94.14 296	99.82 195	97.97 155	99.80 131	99.29 243

XVG-OURS-SEG-HR		98.49 165	98.28 179	99.14 118	99.49 129	98.83 83	96.54 331	99.48 112	97.32 258	99.11 154	98.61 279	99.33 14	99.30 403	96.23 282	98.38 370	99.28 245

test12				98.93 158	98.58 336	97.83 174		98.66 323		96.53 381		95.51 260	99.69 287		99.13 317	99.27 246

DSMNet-mixed		97.42 270	97.60 250	96.87 356	99.15 222	91.46 394	98.54 120	99.12 250	92.87 399	97.58 325	99.63 39	96.21 228	99.90 78	95.74 307	99.54 245	99.27 246

N_pmnet		97.63 253	97.17 274	98.99 147	99.27 187	97.86 171	95.98 365	93.41 429	95.25 353	99.47 92	98.90 218	95.63 255	99.85 149	96.91 221	99.73 166	99.27 246

ambc				98.24 263	98.82 288	95.97 277	98.62 111	99.00 274		99.27 133	99.21 137	96.99 187	99.50 368	96.55 263	99.50 261	99.26 249

LFMVS		97.20 288	96.72 303	98.64 202	98.72 302	96.95 237	98.93 81	94.14 426	99.74 13	98.78 216	99.01 193	84.45 392	99.73 271	97.44 186	99.27 293	99.25 250

FMVSNet5		96.01 336	95.20 355	98.41 243	97.53 406	96.10 268	98.74 96	99.50 103	97.22 274	98.03 296	99.04 181	69.80 433	99.88 109	97.27 194	99.71 179	99.25 250

BH-RMVSNet		96.83 309	96.58 314	97.58 314	98.47 347	94.05 340	96.67 327	97.36 370	96.70 303	97.87 305	97.98 339	95.14 269	99.44 383	90.47 418	98.58 366	99.25 250

testf1		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 103	99.69 49	98.90 123	99.43 98	99.35 100	98.86 33	99.67 299	97.81 164	99.81 120	99.24 253

APD_test2		99.25 40	99.16 59	99.51 48	99.89 6	99.63 4	98.71 103	99.69 49	98.90 123	99.43 98	99.35 100	98.86 33	99.67 299	97.81 164	99.81 120	99.24 253

旧先验1					98.82 288	97.45 206		98.76 313			98.34 312	95.50 261			99.01 331	99.23 255

test222					98.92 266	96.93 239	95.54 386	98.78 311	85.72 437	96.86 368	98.11 329	94.43 288			99.10 322	99.23 255

XVG-ACMP-BASELINE		98.56 151	98.34 171	99.22 105	99.54 108	98.59 100	97.71 239	99.46 124	97.25 265	98.98 175	98.99 197	97.54 150	99.84 167	95.88 298	99.74 163	99.23 255

FMVSNet3		97.50 260	97.24 271	98.29 258	98.08 377	95.83 282	97.86 217	98.91 285	97.89 205	98.95 183	98.95 210	87.06 371	99.81 210	97.77 168	99.69 189	99.23 255

无先验							95.74 381	98.74 318	89.38 428				99.73 271	92.38 393		99.22 259

tttt0517		95.64 349	94.98 359	97.64 309	99.36 166	93.81 354	98.72 101	90.47 440	98.08 191	98.67 230	98.34 312	73.88 428	99.92 62	97.77 168	99.51 254	99.20 260

pmmvs-eth3d		98.47 167	98.34 171	98.86 167	99.30 180	97.76 185	97.16 302	99.28 208	95.54 344	99.42 102	99.19 140	97.27 170	99.63 321	97.89 158	99.97 20	99.20 260

MS-PatchMatch		97.68 249	97.75 235	97.45 328	98.23 368	93.78 355	97.29 289	98.84 301	96.10 325	98.64 234	98.65 270	96.04 235	99.36 393	96.84 232	99.14 315	99.20 260

新几何1				98.91 162	98.94 260	97.76 185		98.76 313	87.58 434	96.75 373	98.10 330	94.80 281	99.78 242	92.73 387	99.00 332	99.20 260

PHI-MVS		98.29 192	97.95 220	99.34 79	98.44 352	99.16 48	98.12 174	99.38 155	96.01 330	98.06 292	98.43 302	97.80 129	99.67 299	95.69 310	99.58 232	99.20 260

GDP-MVS		97.50 260	97.11 279	98.67 199	99.02 249	96.85 242	98.16 168	99.71 45	98.32 167	98.52 255	98.54 286	83.39 401	99.95 26	98.79 98	99.56 239	99.19 265

Anonymous202405211		97.90 227	97.50 255	99.08 129	98.90 270	98.25 125	98.53 121	96.16 399	98.87 126	99.11 154	98.86 228	90.40 350	99.78 242	97.36 190	99.31 286	99.19 265

CANet		97.87 233	97.76 234	98.19 267	97.75 390	95.51 292	96.76 322	99.05 261	97.74 214	96.93 359	98.21 322	95.59 257	99.89 93	97.86 163	99.93 53	99.19 265

XVG-OURS		98.53 159	98.34 171	99.11 122	99.50 121	98.82 85	95.97 366	99.50 103	97.30 260	99.05 166	98.98 201	99.35 13	99.32 400	95.72 308	99.68 194	99.18 268

WTY-MVS		96.67 315	96.27 325	97.87 287	98.81 291	94.61 326	96.77 321	97.92 356	94.94 361	97.12 350	97.74 353	91.11 343	99.82 195	93.89 359	98.15 382	99.18 268

Vis-MVSNet (Re-imp)		97.46 265	97.16 275	98.34 253	99.55 103	96.10 268	98.94 80	98.44 335	98.32 167	98.16 282	98.62 277	88.76 361	99.73 271	93.88 360	99.79 136	99.18 268

TinyColmap		97.89 229	97.98 216	97.60 312	98.86 279	94.35 332	96.21 353	99.44 132	97.45 247	99.06 161	98.88 225	97.99 115	99.28 407	94.38 347	99.58 232	99.18 268

testdata				98.09 272	98.93 262	95.40 299		98.80 308	90.08 425	97.45 338	98.37 308	95.26 266	99.70 283	93.58 368	98.95 340	99.17 272

lupinMVS		97.06 297	96.86 293	97.65 307	98.88 276	93.89 352	95.48 390	97.97 354	93.53 389	98.16 282	97.58 362	93.81 304	99.91 71	96.77 237	99.57 236	99.17 272

Patchmtry		97.35 275	96.97 285	98.50 234	97.31 417	96.47 259	98.18 164	98.92 283	98.95 120	98.78 216	99.37 95	85.44 386	99.85 149	95.96 296	99.83 112	99.17 272

RRT-MVS		97.88 231	97.98 216	97.61 311	98.15 372	93.77 356	98.97 76	99.64 61	99.16 89	98.69 227	99.42 87	91.60 336	99.89 93	97.63 176	98.52 368	99.16 275

sss		97.21 287	96.93 287	98.06 277	98.83 285	95.22 306	96.75 323	98.48 334	94.49 369	97.27 347	97.90 345	92.77 322	99.80 218	96.57 256	99.32 284	99.16 275

CSCG		98.68 133	98.50 144	99.20 106	99.45 146	98.63 95	98.56 117	99.57 78	97.87 206	98.85 205	98.04 336	97.66 137	99.84 167	96.72 243	99.81 120	99.13 277

MVS_111021_LR		98.30 189	98.12 201	98.83 170	99.16 218	98.03 153	96.09 362	99.30 196	97.58 228	98.10 289	98.24 319	98.25 87	99.34 397	96.69 246	99.65 208	99.12 278

miper_lstm_enhance		97.18 290	97.16 275	97.25 338	98.16 371	92.85 373	95.15 401	99.31 188	97.25 265	98.74 224	98.78 246	90.07 351	99.78 242	97.19 198	99.80 131	99.11 279

testing3		93.51 385	92.09 396	97.75 298	98.60 331	94.40 330	97.32 286	95.26 414	97.56 231	96.79 372	95.50 413	53.57 453	99.77 248	95.26 321	98.97 338	99.08 280

原ACMM1				98.35 252	98.90 270	96.25 266		98.83 305	92.48 403	96.07 394	98.10 330	95.39 264	99.71 279	92.61 390	98.99 334	99.08 280

QAPM		97.31 278	96.81 299	98.82 171	98.80 294	97.49 201	99.06 65	99.19 232	90.22 423	97.69 318	99.16 150	96.91 190	99.90 78	90.89 415	99.41 272	99.07 282

PAPM_NR		96.82 311	96.32 322	98.30 257	99.07 236	96.69 252	97.48 273	98.76 313	95.81 337	96.61 378	96.47 394	94.12 299	99.17 414	90.82 416	97.78 395	99.06 283

eth_miper_zixun_eth		97.23 286	97.25 270	97.17 341	98.00 380	92.77 375	94.71 410	99.18 236	97.27 263	98.56 248	98.74 252	91.89 334	99.69 287	97.06 211	99.81 120	99.05 284

D2MVS		97.84 240	97.84 231	97.83 289	99.14 223	94.74 320	96.94 311	98.88 290	95.84 336	98.89 197	98.96 206	94.40 290	99.69 287	97.55 180	99.95 37	99.05 284

c3_l		97.36 274	97.37 263	97.31 333	98.09 376	93.25 366	95.01 404	99.16 243	97.05 282	98.77 219	98.72 255	92.88 319	99.64 318	96.93 220	99.76 159	99.05 284

PLC	94.65 16	96.51 320	95.73 332	98.85 168	98.75 298	97.91 167	96.42 341	99.06 258	90.94 420	95.59 400	97.38 374	94.41 289	99.59 336	90.93 413	98.04 391	99.05 284
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tfpnnormal		98.90 95	98.90 90	98.91 162	99.67 65	97.82 179	99.00 72	99.44 132	99.45 48	99.51 85	99.24 130	98.20 95	99.86 136	95.92 297	99.69 189	99.04 288

CANet_DTU		97.26 282	97.06 281	97.84 288	97.57 401	94.65 325	96.19 355	98.79 309	97.23 271	95.14 412	98.24 319	93.22 311	99.84 167	97.34 191	99.84 105	99.04 288

PM-MVS		98.82 106	98.72 110	99.12 120	99.64 74	98.54 106	97.98 201	99.68 54	97.62 222	99.34 119	99.18 144	97.54 150	99.77 248	97.79 166	99.74 163	99.04 288

TSAR-MVS + GP.		98.18 205	97.98 216	98.77 185	98.71 305	97.88 169	96.32 347	98.66 323	96.33 316	99.23 144	98.51 291	97.48 160	99.40 388	97.16 200	99.46 265	99.02 291

DIV-MVS_self_test		97.02 300	96.84 295	97.58 314	97.82 388	94.03 343	94.66 413	99.16 243	97.04 283	98.63 235	98.71 256	88.69 362	99.69 287	97.00 213	99.81 120	99.01 292

mamv4		99.44 19	99.39 27	99.58 20	99.30 180	99.74 2	99.04 68	99.81 30	99.77 10	99.82 32	99.57 49	97.82 127	99.98 4	99.53 45	99.89 88	99.01 292

GA-MVS		95.86 341	95.32 351	97.49 325	98.60 331	94.15 338	93.83 430	97.93 355	95.49 346	96.68 374	97.42 372	83.21 402	99.30 403	96.22 283	98.55 367	99.01 292

OMC-MVS		97.88 231	97.49 256	99.04 140	98.89 275	98.63 95	96.94 311	99.25 217	95.02 358	98.53 253	98.51 291	97.27 170	99.47 377	93.50 371	99.51 254	99.01 292

cl____		97.02 300	96.83 296	97.58 314	97.82 388	94.04 342	94.66 413	99.16 243	97.04 283	98.63 235	98.71 256	88.68 364	99.69 287	97.00 213	99.81 120	99.00 296

pmmvs4		97.58 257	97.28 268	98.51 230	98.84 283	96.93 239	95.40 394	98.52 332	93.60 388	98.61 239	98.65 270	95.10 270	99.60 332	96.97 218	99.79 136	98.99 297

EPNet_dtu		94.93 364	94.78 364	95.38 400	93.58 448	87.68 427	96.78 320	95.69 411	97.35 255	89.14 445	98.09 332	88.15 369	99.49 371	94.95 328	99.30 289	98.98 298
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
114514_t		96.50 322	95.77 330	98.69 196	99.48 137	97.43 208	97.84 220	99.55 89	81.42 443	96.51 383	98.58 283	95.53 258	99.67 299	93.41 373	99.58 232	98.98 298

PVSNet_Blended		96.88 307	96.68 306	97.47 327	98.92 266	93.77 356	94.71 410	99.43 138	90.98 419	97.62 321	97.36 376	96.82 196	99.67 299	94.73 332	99.56 239	98.98 298

APD_test1		98.83 103	98.66 122	99.34 79	99.78 24	99.47 9	98.42 143	99.45 128	98.28 174	98.98 175	99.19 140	97.76 131	99.58 342	96.57 256	99.55 243	98.97 301

PAPR		95.29 355	94.47 366	97.75 298	97.50 412	95.14 309	94.89 407	98.71 321	91.39 415	95.35 410	95.48 415	94.57 286	99.14 417	84.95 434	97.37 408	98.97 301

EGC-MVSNET		85.24 412	80.54 415	99.34 79	99.77 27	99.20 39	99.08 61	99.29 204	12.08 450	20.84 451	99.42 87	97.55 149	99.85 149	97.08 208	99.72 174	98.96 303

thisisatest0530		95.27 356	94.45 367	97.74 300	99.19 208	94.37 331	97.86 217	90.20 441	97.17 276	98.22 277	97.65 358	73.53 429	99.90 78	96.90 226	99.35 280	98.95 304

mvs_anonymous		97.83 242	98.16 197	96.87 356	98.18 370	91.89 389	97.31 287	98.90 286	97.37 253	98.83 208	99.46 79	96.28 226	99.79 231	98.90 91	98.16 381	98.95 304

baseline1		95.96 339	95.44 345	97.52 322	98.51 345	93.99 346	98.39 145	96.09 402	98.21 178	98.40 268	97.76 352	86.88 372	99.63 321	95.42 318	89.27 445	98.95 304

CLD-MVS		97.49 263	97.16 275	98.48 235	99.07 236	97.03 232	94.71 410	99.21 226	94.46 371	98.06 292	97.16 380	97.57 147	99.48 374	94.46 340	99.78 141	98.95 304
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MSLP-MVS++		98.02 217	98.14 200	97.64 309	98.58 336	95.19 307	97.48 273	99.23 224	97.47 240	97.90 302	98.62 277	97.04 182	98.81 428	97.55 180	99.41 272	98.94 308

DELS-MVS		98.27 193	98.20 189	98.48 235	98.86 279	96.70 251	95.60 385	99.20 228	97.73 215	98.45 260	98.71 256	97.50 156	99.82 195	98.21 135	99.59 227	98.93 309
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		95.79 344	95.39 348	96.98 350	96.77 429	92.79 374	94.40 421	98.53 331	94.59 368	97.89 303	98.17 325	82.82 406	99.24 409	96.37 274	99.03 327	98.92 310

LS3D		98.63 142	98.38 166	99.36 70	97.25 418	99.38 13	99.12 60	99.32 183	99.21 78	98.44 261	98.88 225	97.31 166	99.80 218	96.58 254	99.34 282	98.92 310

CMPMVS	75.91 23	96.29 328	95.44 345	98.84 169	96.25 439	98.69 94	97.02 306	99.12 250	88.90 430	97.83 309	98.86 228	89.51 357	98.90 426	91.92 394	99.51 254	98.92 310
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
LCM-MVSNet-Re		98.64 140	98.48 149	99.11 122	98.85 282	98.51 108	98.49 132	99.83 25	98.37 162	99.69 53	99.46 79	98.21 94	99.92 62	94.13 353	99.30 289	98.91 313

mvsmamba		97.57 258	97.26 269	98.51 230	98.69 314	96.73 250	98.74 96	97.25 375	97.03 285	97.88 304	99.23 135	90.95 344	99.87 128	96.61 252	99.00 332	98.91 313

DPM-MVS		96.32 327	95.59 339	98.51 230	98.76 296	97.21 222	94.54 419	98.26 343	91.94 408	96.37 387	97.25 378	93.06 316	99.43 384	91.42 405	98.74 350	98.89 315

test_yl		96.69 313	96.29 323	97.90 284	98.28 363	95.24 304	97.29 289	97.36 370	98.21 178	98.17 279	97.86 346	86.27 376	99.55 351	94.87 329	98.32 371	98.89 315

DCV-MVSNet		96.69 313	96.29 323	97.90 284	98.28 363	95.24 304	97.29 289	97.36 370	98.21 178	98.17 279	97.86 346	86.27 376	99.55 351	94.87 329	98.32 371	98.89 315

SPE-MVS-test		99.13 63	99.09 72	99.26 97	99.13 225	98.97 73	99.31 30	99.88 14	99.44 50	98.16 282	98.51 291	98.64 53	99.93 52	98.91 90	99.85 101	98.88 318

UnsupCasMVSNet_bld		97.30 279	96.92 289	98.45 238	99.28 185	96.78 248	96.20 354	99.27 211	95.42 348	98.28 274	98.30 316	93.16 312	99.71 279	94.99 325	97.37 408	98.87 319

Effi-MVS+		98.02 217	97.82 232	98.62 208	98.53 343	97.19 224	97.33 285	99.68 54	97.30 260	96.68 374	97.46 370	98.56 63	99.80 218	96.63 250	98.20 377	98.86 320

test_0402		98.76 116	98.71 113	98.93 158	99.56 99	98.14 137	98.45 139	99.34 175	99.28 70	98.95 183	98.91 215	98.34 81	99.79 231	95.63 312	99.91 75	98.86 320

PatchmatchNet		95.58 350	95.67 335	95.30 401	97.34 416	87.32 429	97.65 248	96.65 391	95.30 352	97.07 353	98.69 261	84.77 389	99.75 261	94.97 327	98.64 361	98.83 322
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
testing3-2		93.78 381	93.91 373	93.39 422	98.82 288	81.72 449	97.76 233	95.28 413	98.60 146	96.54 380	96.66 389	65.85 445	99.62 324	96.65 249	98.99 334	98.82 323

test_vis1_rt		97.75 244	97.72 239	97.83 289	98.81 291	96.35 263	97.30 288	99.69 49	94.61 367	97.87 305	98.05 335	96.26 227	98.32 435	98.74 104	98.18 378	98.82 323

CL-MVSNet_self_test		97.44 268	97.22 272	98.08 275	98.57 338	95.78 285	94.30 423	98.79 309	96.58 307	98.60 241	98.19 324	94.74 284	99.64 318	96.41 272	98.84 345	98.82 323

miper_ehance_all_eth		97.06 297	97.03 282	97.16 343	97.83 387	93.06 368	94.66 413	99.09 255	95.99 331	98.69 227	98.45 300	92.73 324	99.61 331	96.79 234	99.03 327	98.82 323

MIMVSNet		96.62 318	96.25 326	97.71 304	99.04 245	94.66 324	99.16 54	96.92 387	97.23 271	97.87 305	99.10 166	86.11 380	99.65 315	91.65 400	99.21 305	98.82 323

hse-mvs2		97.46 265	97.07 280	98.64 202	98.73 300	97.33 212	97.45 276	97.64 366	99.11 92	98.58 245	97.98 339	88.65 365	99.79 231	98.11 141	97.39 407	98.81 328

GSMVS																98.81 328

sam_mvs1												84.74 390				98.81 328

SCA		96.41 326	96.66 309	95.67 391	98.24 366	88.35 423	95.85 377	96.88 388	96.11 324	97.67 319	98.67 265	93.10 314	99.85 149	94.16 349	99.22 302	98.81 328

Patchmatch-RL test		97.26 282	97.02 283	97.99 283	99.52 113	95.53 291	96.13 360	99.71 45	97.47 240	99.27 133	99.16 150	84.30 395	99.62 324	97.89 158	99.77 147	98.81 328

AUN-MVS		96.24 332	95.45 344	98.60 213	98.70 309	97.22 220	97.38 280	97.65 364	95.95 333	95.53 407	97.96 343	82.11 409	99.79 231	96.31 278	97.44 404	98.80 333

ITE_SJBPF				98.87 166	99.22 199	98.48 110		99.35 169	97.50 237	98.28 274	98.60 281	97.64 141	99.35 396	93.86 361	99.27 293	98.79 334

tpm		94.67 366	94.34 370	95.66 392	97.68 399	88.42 422	97.88 213	94.90 416	94.46 371	96.03 396	98.56 285	78.66 420	99.79 231	95.88 298	95.01 435	98.78 335

Patchmatch-test		96.55 319	96.34 321	97.17 341	98.35 359	93.06 368	98.40 144	97.79 357	97.33 256	98.41 264	98.67 265	83.68 400	99.69 287	95.16 323	99.31 286	98.77 336

EC-MVSNet		99.09 69	99.05 76	99.20 106	99.28 185	98.93 79	99.24 44	99.84 22	99.08 104	98.12 287	98.37 308	98.72 46	99.90 78	99.05 81	99.77 147	98.77 336

PMMVS		96.51 320	95.98 327	98.09 272	97.53 406	95.84 281	94.92 406	98.84 301	91.58 411	96.05 395	95.58 410	95.68 254	99.66 310	95.59 314	98.09 385	98.76 338

test_method		79.78 413	79.50 416	80.62 429	80.21 454	45.76 457	70.82 445	98.41 339	31.08 449	80.89 449	97.71 354	84.85 388	97.37 442	91.51 404	80.03 446	98.75 339

ab-mvs		98.41 172	98.36 168	98.59 214	99.19 208	97.23 218	99.32 26	98.81 306	97.66 219	98.62 237	99.40 94	96.82 196	99.80 218	95.88 298	99.51 254	98.75 339

CHOSEN 280x420		95.51 353	95.47 342	95.65 393	98.25 365	88.27 424	93.25 434	98.88 290	93.53 389	94.65 418	97.15 381	86.17 378	99.93 52	97.41 188	99.93 53	98.73 341

test_fmvsmvis_n_1920		99.26 39	99.49 16	98.54 226	99.66 67	96.97 234	98.00 195	99.85 18	99.24 73	99.92 8	99.50 67	99.39 12	99.95 26	99.89 3	99.98 12	98.71 342

MVS_Test		98.18 205	98.36 168	97.67 305	98.48 346	94.73 321	98.18 164	99.02 269	97.69 217	98.04 295	99.11 163	97.22 174	99.56 347	98.57 116	98.90 344	98.71 342

PVSNet	93.40 17	95.67 347	95.70 333	95.57 394	98.83 285	88.57 421	92.50 437	97.72 359	92.69 401	96.49 386	96.44 395	93.72 307	99.43 384	93.61 366	99.28 292	98.71 342

alignmvs		97.35 275	96.88 292	98.78 181	98.54 341	98.09 142	97.71 239	97.69 361	99.20 80	97.59 324	95.90 405	88.12 370	99.55 351	98.18 137	98.96 339	98.70 345

ADS-MVSNet2		95.43 354	94.98 359	96.76 363	98.14 373	91.74 390	97.92 208	97.76 358	90.23 421	96.51 383	98.91 215	85.61 383	99.85 149	92.88 381	96.90 417	98.69 346

ADS-MVSNet		95.24 357	94.93 362	96.18 380	98.14 373	90.10 416	97.92 208	97.32 373	90.23 421	96.51 383	98.91 215	85.61 383	99.74 266	92.88 381	96.90 417	98.69 346

MDTV_nov1_ep13_2view						74.92 453	97.69 241		90.06 426	97.75 315		85.78 382		93.52 369		98.69 346

MSDG		97.71 247	97.52 254	98.28 259	98.91 269	96.82 243	94.42 420	99.37 159	97.65 220	98.37 269	98.29 317	97.40 163	99.33 399	94.09 354	99.22 302	98.68 349

mvsany_test1		97.60 254	97.54 252	97.77 294	97.72 391	95.35 300	95.36 395	97.13 379	94.13 380	99.71 47	99.33 106	97.93 118	99.30 403	97.60 179	98.94 341	98.67 350

CS-MVS		99.13 63	99.10 70	99.24 102	99.06 241	99.15 52	99.36 22	99.88 14	99.36 61	98.21 278	98.46 299	98.68 50	99.93 52	99.03 83	99.85 101	98.64 351

Syy-MVS		96.04 335	95.56 341	97.49 325	97.10 422	94.48 328	96.18 357	96.58 393	95.65 340	94.77 415	92.29 444	91.27 342	99.36 393	98.17 139	98.05 389	98.63 352

myMVS_eth3d		91.92 408	90.45 410	96.30 373	97.10 422	90.90 408	96.18 357	96.58 393	95.65 340	94.77 415	92.29 444	53.88 452	99.36 393	89.59 422	98.05 389	98.63 352

balanced_conf03		98.63 142	98.72 110	98.38 247	98.66 324	96.68 253	98.90 83	99.42 144	98.99 113	98.97 179	99.19 140	95.81 251	99.85 149	98.77 102	99.77 147	98.60 354

miper_enhance_ethall		96.01 336	95.74 331	96.81 360	96.41 437	92.27 386	93.69 432	98.89 289	91.14 418	98.30 270	97.35 377	90.58 348	99.58 342	96.31 278	99.03 327	98.60 354

Effi-MVS+-dtu		98.26 195	97.90 227	99.35 76	98.02 379	99.49 6	98.02 191	99.16 243	98.29 172	97.64 320	97.99 338	96.44 219	99.95 26	96.66 248	98.93 342	98.60 354

new_pmnet		96.99 304	96.76 301	97.67 305	98.72 302	94.89 315	95.95 370	98.20 346	92.62 402	98.55 250	98.54 286	94.88 277	99.52 362	93.96 357	99.44 270	98.59 357

MVSMamba_PlusPlus		98.83 103	98.98 84	98.36 251	99.32 175	96.58 256	98.90 83	99.41 148	99.75 11	98.72 225	99.50 67	96.17 229	99.94 41	99.27 62	99.78 141	98.57 358

testing91		93.32 388	92.27 393	96.47 369	97.54 404	91.25 402	96.17 359	96.76 390	97.18 275	93.65 432	93.50 436	65.11 447	99.63 321	93.04 378	97.45 403	98.53 359

EIA-MVS		98.00 220	97.74 236	98.80 175	98.72 302	98.09 142	98.05 185	99.60 68	97.39 251	96.63 376	95.55 411	97.68 135	99.80 218	96.73 242	99.27 293	98.52 360

PatchMatch-RL		97.24 285	96.78 300	98.61 211	99.03 248	97.83 174	96.36 344	99.06 258	93.49 391	97.36 345	97.78 350	95.75 252	99.49 371	93.44 372	98.77 349	98.52 360

sasdasda		98.34 182	98.26 183	98.58 215	98.46 349	97.82 179	98.96 77	99.46 124	99.19 84	97.46 336	95.46 416	98.59 59	99.46 379	98.08 144	98.71 354	98.46 362

ET-MVSNet_ETH3D		94.30 372	93.21 383	97.58 314	98.14 373	94.47 329	94.78 409	93.24 431	94.72 365	89.56 443	95.87 406	78.57 422	99.81 210	96.91 221	97.11 416	98.46 362

canonicalmvs		98.34 182	98.26 183	98.58 215	98.46 349	97.82 179	98.96 77	99.46 124	99.19 84	97.46 336	95.46 416	98.59 59	99.46 379	98.08 144	98.71 354	98.46 362

UBG		93.25 390	92.32 391	96.04 385	97.72 391	90.16 415	95.92 373	95.91 406	96.03 329	93.95 429	93.04 440	69.60 434	99.52 362	90.72 417	97.98 392	98.45 365

tt0805		98.69 128	98.62 128	98.90 165	99.75 34	99.30 22	99.15 56	96.97 383	98.86 128	98.87 204	97.62 361	98.63 55	98.96 422	99.41 54	98.29 374	98.45 365

TAPA-MVS	96.21 11	96.63 317	95.95 328	98.65 200	98.93 262	98.09 142	96.93 313	99.28 208	83.58 440	98.13 286	97.78 350	96.13 231	99.40 388	93.52 369	99.29 291	98.45 365
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
MGCFI-Net		98.34 182	98.28 179	98.51 230	98.47 347	97.59 197	98.96 77	99.48 112	99.18 87	97.40 341	95.50 413	98.66 51	99.50 368	98.18 137	98.71 354	98.44 368

BH-untuned		96.83 309	96.75 302	97.08 344	98.74 299	93.33 365	96.71 325	98.26 343	96.72 301	98.44 261	97.37 375	95.20 267	99.47 377	91.89 395	97.43 405	98.44 368

WB-MVSnew		95.73 346	95.57 340	96.23 378	96.70 430	90.70 412	96.07 363	93.86 427	95.60 342	97.04 355	95.45 419	96.00 238	99.55 351	91.04 411	98.31 373	98.43 370

pmmvs3		95.03 361	94.40 368	96.93 352	97.70 396	92.53 379	95.08 402	97.71 360	88.57 431	97.71 316	98.08 333	79.39 417	99.82 195	96.19 285	99.11 321	98.43 370

DP-MVS Recon		97.33 277	96.92 289	98.57 218	99.09 232	97.99 155	96.79 319	99.35 169	93.18 393	97.71 316	98.07 334	95.00 273	99.31 401	93.97 356	99.13 317	98.42 372

testing99		93.04 394	91.98 401	96.23 378	97.53 406	90.70 412	96.35 345	95.94 405	96.87 293	93.41 433	93.43 438	63.84 449	99.59 336	93.24 376	97.19 413	98.40 373

ETVMVS		92.60 399	91.08 408	97.18 339	97.70 396	93.65 361	96.54 331	95.70 409	96.51 308	94.68 417	92.39 443	61.80 450	99.50 368	86.97 429	97.41 406	98.40 373

Fast-Effi-MVS+-dtu		98.27 193	98.09 203	98.81 173	98.43 353	98.11 139	97.61 257	99.50 103	98.64 139	97.39 343	97.52 366	98.12 104	99.95 26	96.90 226	98.71 354	98.38 375

LF4IMVS		97.90 227	97.69 241	98.52 229	99.17 216	97.66 192	97.19 301	99.47 120	96.31 318	97.85 308	98.20 323	96.71 206	99.52 362	94.62 335	99.72 174	98.38 375

testing11		93.08 393	92.02 398	96.26 376	97.56 402	90.83 410	96.32 347	95.70 409	96.47 312	92.66 436	93.73 433	64.36 448	99.59 336	93.77 364	97.57 399	98.37 377

Fast-Effi-MVS+		97.67 250	97.38 262	98.57 218	98.71 305	97.43 208	97.23 293	99.45 128	94.82 364	96.13 391	96.51 391	98.52 65	99.91 71	96.19 285	98.83 346	98.37 377

test0.0.03 1		94.51 367	93.69 377	96.99 349	96.05 440	93.61 363	94.97 405	93.49 428	96.17 321	97.57 327	94.88 426	82.30 407	99.01 421	93.60 367	94.17 439	98.37 377

UWE-MVS		92.38 402	91.76 405	94.21 412	97.16 420	84.65 438	95.42 393	88.45 444	95.96 332	96.17 390	95.84 408	66.36 441	99.71 279	91.87 396	98.64 361	98.28 380

FE-MVS		95.66 348	94.95 361	97.77 294	98.53 343	95.28 303	99.40 19	96.09 402	93.11 395	97.96 299	99.26 123	79.10 419	99.77 248	92.40 392	98.71 354	98.27 381

baseline2		93.73 382	92.83 388	96.42 370	97.70 396	91.28 401	96.84 318	89.77 442	93.96 385	92.44 437	95.93 404	79.14 418	99.77 248	92.94 379	96.76 421	98.21 382

thisisatest0515		94.12 376	93.16 384	96.97 351	98.60 331	92.90 372	93.77 431	90.61 439	94.10 381	96.91 362	95.87 406	74.99 427	99.80 218	94.52 338	99.12 320	98.20 383

EPMVS		93.72 383	93.27 382	95.09 404	96.04 441	87.76 426	98.13 171	85.01 449	94.69 366	96.92 360	98.64 273	78.47 424	99.31 401	95.04 324	96.46 423	98.20 383

dp		93.47 386	93.59 379	93.13 425	96.64 431	81.62 450	97.66 246	96.42 396	92.80 400	96.11 392	98.64 273	78.55 423	99.59 336	93.31 374	92.18 444	98.16 385

CNLPA		97.17 291	96.71 304	98.55 223	98.56 339	98.05 152	96.33 346	98.93 280	96.91 291	97.06 354	97.39 373	94.38 291	99.45 381	91.66 399	99.18 311	98.14 386

dmvs_re		95.98 338	95.39 348	97.74 300	98.86 279	97.45 206	98.37 147	95.69 411	97.95 198	96.56 379	95.95 403	90.70 347	97.68 441	88.32 425	96.13 428	98.11 387

HY-MVS	95.94 13	95.90 340	95.35 350	97.55 319	97.95 381	94.79 317	98.81 95	96.94 386	92.28 406	95.17 411	98.57 284	89.90 353	99.75 261	91.20 409	97.33 412	98.10 388

CostFormer		93.97 378	93.78 376	94.51 408	97.53 406	85.83 434	97.98 201	95.96 404	89.29 429	94.99 414	98.63 275	78.63 421	99.62 324	94.54 337	96.50 422	98.09 389

FA-MVS(test-final)		96.99 304	96.82 297	97.50 324	98.70 309	94.78 318	99.34 23	96.99 382	95.07 357	98.48 258	99.33 106	88.41 368	99.65 315	96.13 291	98.92 343	98.07 390

AdaColmap		97.14 293	96.71 304	98.46 237	98.34 360	97.80 183	96.95 310	98.93 280	95.58 343	96.92 360	97.66 357	95.87 249	99.53 358	90.97 412	99.14 315	98.04 391

KD-MVS_2432*1600		92.87 397	91.99 399	95.51 396	91.37 450	89.27 419	94.07 425	98.14 349	95.42 348	97.25 348	96.44 395	67.86 436	99.24 409	91.28 407	96.08 429	98.02 392

miper_refine_blended		92.87 397	91.99 399	95.51 396	91.37 450	89.27 419	94.07 425	98.14 349	95.42 348	97.25 348	96.44 395	67.86 436	99.24 409	91.28 407	96.08 429	98.02 392

TESTMET0.1,1		92.19 406	91.77 404	93.46 420	96.48 435	82.80 446	94.05 427	91.52 438	94.45 373	94.00 427	94.88 426	66.65 440	99.56 347	95.78 306	98.11 384	98.02 392

testing222		91.96 407	90.37 411	96.72 364	97.47 413	92.59 377	96.11 361	94.76 417	96.83 295	92.90 435	92.87 441	57.92 451	99.55 351	86.93 430	97.52 400	98.00 395

PCF-MVS	92.86 18	94.36 369	93.00 387	98.42 242	98.70 309	97.56 198	93.16 435	99.11 252	79.59 444	97.55 328	97.43 371	92.19 330	99.73 271	79.85 443	99.45 267	97.97 396
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS-28		90.22 411	89.28 414	93.02 426	94.50 447	82.87 445	96.52 334	87.51 445	95.21 355	92.36 438	96.04 400	71.57 431	98.25 437	72.04 447	97.77 396	97.94 397

myMVS_eth3d28		92.92 396	92.31 392	94.77 405	97.84 386	87.59 428	96.19 355	96.11 401	97.08 281	94.27 421	93.49 437	66.07 444	98.78 429	91.78 397	97.93 394	97.92 398

OpenMVS	96.65 7	97.09 295	96.68 306	98.32 254	98.32 361	97.16 227	98.86 90	99.37 159	89.48 427	96.29 389	99.15 154	96.56 213	99.90 78	92.90 380	99.20 306	97.89 399

Gipuma		99.03 77	99.16 59	98.64 202	99.94 2	98.51 108	99.32 26	99.75 41	99.58 37	98.60 241	99.62 40	98.22 92	99.51 367	97.70 173	99.73 166	97.89 399
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PVSNet_0	89.98 21	91.15 410	90.30 413	93.70 418	97.72 391	84.34 442	90.24 441	97.42 368	90.20 424	93.79 430	93.09 439	90.90 346	98.89 427	86.57 432	72.76 448	97.87 401

test-LLR		93.90 379	93.85 374	94.04 413	96.53 433	84.62 439	94.05 427	92.39 433	96.17 321	94.12 424	95.07 420	82.30 407	99.67 299	95.87 301	98.18 378	97.82 402

test-mter		92.33 404	91.76 405	94.04 413	96.53 433	84.62 439	94.05 427	92.39 433	94.00 384	94.12 424	95.07 420	65.63 446	99.67 299	95.87 301	98.18 378	97.82 402

tpm2		93.09 392	92.58 390	94.62 407	97.56 402	86.53 431	97.66 246	95.79 408	86.15 436	94.07 426	98.23 321	75.95 425	99.53 358	90.91 414	96.86 420	97.81 404

CR-MVSNet		96.28 329	95.95 328	97.28 335	97.71 394	94.22 333	98.11 175	98.92 283	92.31 405	96.91 362	99.37 95	85.44 386	99.81 210	97.39 189	97.36 410	97.81 404

RPMNet		97.02 300	96.93 287	97.30 334	97.71 394	94.22 333	98.11 175	99.30 196	99.37 58	96.91 362	99.34 104	86.72 373	99.87 128	97.53 183	97.36 410	97.81 404

tpmrst		95.07 360	95.46 343	93.91 415	97.11 421	84.36 441	97.62 253	96.96 384	94.98 359	96.35 388	98.80 242	85.46 385	99.59 336	95.60 313	96.23 426	97.79 407

PAPM		91.88 409	90.34 412	96.51 367	98.06 378	92.56 378	92.44 438	97.17 377	86.35 435	90.38 442	96.01 401	86.61 374	99.21 412	70.65 448	95.43 433	97.75 408

FPMVS		93.44 387	92.23 394	97.08 344	99.25 193	97.86 171	95.61 384	97.16 378	92.90 398	93.76 431	98.65 270	75.94 426	95.66 445	79.30 444	97.49 401	97.73 409

MAR-MVS		96.47 324	95.70 333	98.79 178	97.92 383	99.12 62	98.28 153	98.60 328	92.16 407	95.54 406	96.17 399	94.77 283	99.52 362	89.62 421	98.23 375	97.72 410
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		98.03 216	97.86 230	98.56 222	98.69 314	98.07 148	97.51 270	99.50 103	98.10 190	97.50 333	95.51 412	98.41 73	99.88 109	96.27 281	99.24 298	97.71 411

thres600view7		94.45 368	93.83 375	96.29 374	99.06 241	91.53 393	97.99 200	94.24 424	98.34 164	97.44 339	95.01 422	79.84 413	99.67 299	84.33 435	98.23 375	97.66 412

thres400		94.14 375	93.44 380	96.24 377	98.93 262	91.44 396	97.60 258	94.29 422	97.94 200	97.10 351	94.31 431	79.67 415	99.62 324	83.05 437	98.08 386	97.66 412

IB-MVS	91.63 19	92.24 405	90.90 409	96.27 375	97.22 419	91.24 403	94.36 422	93.33 430	92.37 404	92.24 439	94.58 430	66.20 443	99.89 93	93.16 377	94.63 437	97.66 412
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		95.02 362	95.25 352	94.33 409	96.39 438	85.87 432	98.08 179	96.83 389	95.46 347	95.51 408	98.69 261	85.91 381	99.53 358	94.16 349	96.23 426	97.58 415

cascas		94.79 365	94.33 371	96.15 384	96.02 442	92.36 384	92.34 439	99.26 216	85.34 438	95.08 413	94.96 425	92.96 318	98.53 433	94.41 346	98.59 365	97.56 416

PatchT		96.65 316	96.35 320	97.54 320	97.40 414	95.32 302	97.98 201	96.64 392	99.33 63	96.89 366	99.42 87	84.32 394	99.81 210	97.69 175	97.49 401	97.48 417

TR-MVS		95.55 351	95.12 357	96.86 359	97.54 404	93.94 347	96.49 336	96.53 395	94.36 376	97.03 357	96.61 390	94.26 295	99.16 415	86.91 431	96.31 425	97.47 418

dmvs_testset		92.94 395	92.21 395	95.13 402	98.59 334	90.99 407	97.65 248	92.09 435	96.95 288	94.00 427	93.55 435	92.34 328	96.97 444	72.20 446	92.52 442	97.43 419

MonoMVSNet		96.25 330	96.53 317	95.39 399	96.57 432	91.01 406	98.82 94	97.68 363	98.57 151	98.03 296	99.37 95	90.92 345	97.78 440	94.99 325	93.88 440	97.38 420

JIA-IIPM		95.52 352	95.03 358	97.00 348	96.85 427	94.03 343	96.93 313	95.82 407	99.20 80	94.63 419	99.71 22	83.09 403	99.60 332	94.42 343	94.64 436	97.36 421

BH-w/o		95.13 359	94.89 363	95.86 386	98.20 369	91.31 399	95.65 383	97.37 369	93.64 387	96.52 382	95.70 409	93.04 317	99.02 419	88.10 426	95.82 431	97.24 422

tpm cat1		93.29 389	93.13 386	93.75 417	97.39 415	84.74 437	97.39 279	97.65 364	83.39 441	94.16 423	98.41 303	82.86 405	99.39 390	91.56 403	95.35 434	97.14 423

xiu_mvs_v1_base_debu		97.86 234	98.17 194	96.92 353	98.98 255	93.91 349	96.45 337	99.17 240	97.85 208	98.41 264	97.14 382	98.47 67	99.92 62	98.02 150	99.05 323	96.92 424

xiu_mvs_v1_base		97.86 234	98.17 194	96.92 353	98.98 255	93.91 349	96.45 337	99.17 240	97.85 208	98.41 264	97.14 382	98.47 67	99.92 62	98.02 150	99.05 323	96.92 424

xiu_mvs_v1_base_debi		97.86 234	98.17 194	96.92 353	98.98 255	93.91 349	96.45 337	99.17 240	97.85 208	98.41 264	97.14 382	98.47 67	99.92 62	98.02 150	99.05 323	96.92 424

PMVS	91.26 20	97.86 234	97.94 222	97.65 307	99.71 47	97.94 164	98.52 122	98.68 322	98.99 113	97.52 331	99.35 100	97.41 162	98.18 438	91.59 402	99.67 200	96.82 427
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
1314		95.74 345	95.60 337	96.17 381	97.53 406	92.75 376	98.07 182	98.31 342	91.22 416	94.25 422	96.68 388	95.53 258	99.03 418	91.64 401	97.18 414	96.74 428

MVS-HIRNet		94.32 370	95.62 336	90.42 428	98.46 349	75.36 452	96.29 349	89.13 443	95.25 353	95.38 409	99.75 16	92.88 319	99.19 413	94.07 355	99.39 274	96.72 429

OpenMVS_ROB	95.38 14	95.84 343	95.18 356	97.81 291	98.41 357	97.15 228	97.37 282	98.62 327	83.86 439	98.65 233	98.37 308	94.29 294	99.68 296	88.41 424	98.62 364	96.60 430

thres100view900		94.19 373	93.67 378	95.75 390	99.06 241	91.35 398	98.03 188	94.24 424	98.33 165	97.40 341	94.98 424	79.84 413	99.62 324	83.05 437	98.08 386	96.29 431

tfpn200view9		94.03 377	93.44 380	95.78 389	98.93 262	91.44 396	97.60 258	94.29 422	97.94 200	97.10 351	94.31 431	79.67 415	99.62 324	83.05 437	98.08 386	96.29 431

MVS		93.19 391	92.09 396	96.50 368	96.91 425	94.03 343	98.07 182	98.06 353	68.01 446	94.56 420	96.48 393	95.96 245	99.30 403	83.84 436	96.89 419	96.17 433

gg-mvs-nofinetune		92.37 403	91.20 407	95.85 387	95.80 444	92.38 383	99.31 30	81.84 451	99.75 11	91.83 440	99.74 18	68.29 435	99.02 419	87.15 428	97.12 415	96.16 434

xiu_mvs_v2_base		97.16 292	97.49 256	96.17 381	98.54 341	92.46 380	95.45 391	98.84 301	97.25 265	97.48 335	96.49 392	98.31 83	99.90 78	96.34 277	98.68 359	96.15 435

PS-MVSNAJ		97.08 296	97.39 261	96.16 383	98.56 339	92.46 380	95.24 398	98.85 300	97.25 265	97.49 334	95.99 402	98.07 106	99.90 78	96.37 274	98.67 360	96.12 436

E-PMN		94.17 374	94.37 369	93.58 419	96.86 426	85.71 435	90.11 443	97.07 380	98.17 185	97.82 311	97.19 379	84.62 391	98.94 423	89.77 420	97.68 398	96.09 437

EMVS		93.83 380	94.02 372	93.23 424	96.83 428	84.96 436	89.77 444	96.32 397	97.92 202	97.43 340	96.36 398	86.17 378	98.93 424	87.68 427	97.73 397	95.81 438

MVE	83.40 22	92.50 400	91.92 402	94.25 410	98.83 285	91.64 392	92.71 436	83.52 450	95.92 334	86.46 448	95.46 416	95.20 267	95.40 446	80.51 442	98.64 361	95.73 439
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres200		93.72 383	93.14 385	95.46 398	98.66 324	91.29 400	96.61 330	94.63 419	97.39 251	96.83 369	93.71 434	79.88 412	99.56 347	82.40 440	98.13 383	95.54 440

API-MVS		97.04 299	96.91 291	97.42 330	97.88 385	98.23 130	98.18 164	98.50 333	97.57 229	97.39 343	96.75 387	96.77 200	99.15 416	90.16 419	99.02 330	94.88 441

GG-mvs-BLEND				94.76 406	94.54 446	92.13 388	99.31 30	80.47 452		88.73 446	91.01 446	67.59 439	98.16 439	82.30 441	94.53 438	93.98 442

DeepMVS_CX				93.44 421	98.24 366	94.21 335		94.34 421	64.28 447	91.34 441	94.87 428	89.45 359	92.77 448	77.54 445	93.14 441	93.35 443

tmp_tt		78.77 414	78.73 417	78.90 430	58.45 455	74.76 454	94.20 424	78.26 453	39.16 448	86.71 447	92.82 442	80.50 411	75.19 450	86.16 433	92.29 443	86.74 444

dongtai		76.24 415	75.95 418	77.12 431	92.39 449	67.91 455	90.16 442	59.44 456	82.04 442	89.42 444	94.67 429	49.68 454	81.74 449	48.06 449	77.66 447	81.72 445

kuosan		69.30 416	68.95 419	70.34 432	87.68 453	65.00 456	91.11 440	59.90 455	69.02 445	74.46 450	88.89 447	48.58 455	68.03 451	28.61 450	72.33 449	77.99 446

wuyk23d		96.06 334	97.62 249	91.38 427	98.65 328	98.57 102	98.85 91	96.95 385	96.86 294	99.90 13	99.16 150	99.18 18	98.40 434	89.23 423	99.77 147	77.18 447

test123		17.04 419	20.11 422	7.82 433	10.25 457	4.91 458	94.80 408	4.47 458	4.93 451	10.00 453	24.28 450	9.69 456	3.64 452	10.14 451	12.43 451	14.92 448

testmvs		17.12 418	20.53 421	6.87 434	12.05 456	4.20 459	93.62 433	6.73 457	4.62 452	10.41 452	24.33 449	8.28 457	3.56 453	9.69 452	15.07 450	12.86 449

mmdepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

monomultidepth		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

test_blank		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uanet_test		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

DCPMVS		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

cdsmvs_eth3d_5k		24.66 417	32.88 420	0.00 435	0.00 458	0.00 460	0.00 446	99.10 253	0.00 453	0.00 454	97.58 362	99.21 17	0.00 454	0.00 453	0.00 452	0.00 450

pcd_1.5k_mvsjas		8.17 420	10.90 423	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	98.07 106	0.00 454	0.00 453	0.00 452	0.00 450

sosnet-low-res		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

sosnet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uncertanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

Regformer		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

ab-mvs-re		8.12 421	10.83 424	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	97.48 368	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

uanet		0.00 422	0.00 425	0.00 435	0.00 458	0.00 460	0.00 446	0.00 459	0.00 453	0.00 454	0.00 453	0.00 458	0.00 454	0.00 453	0.00 452	0.00 450

WAC-MVS						90.90 408								91.37 406

FOURS1					99.73 37	99.67 3	99.43 15	99.54 93	99.43 52	99.26 137

test_one_0601					99.39 158	99.20 39		99.31 188	98.49 157	98.66 232	99.02 184	97.64 141

eth-test2					0.00 458

eth-test					0.00 458

ZD-MVS					99.01 250	98.84 82		99.07 257	94.10 381	98.05 294	98.12 328	96.36 224	99.86 136	92.70 388	99.19 309

test_241102_ONE					99.49 129	99.17 44		99.31 188	97.98 195	99.66 58	98.90 218	98.36 76	99.48 374

9.14			97.78 233		99.07 236		97.53 267	99.32 183	95.53 345	98.54 252	98.70 259	97.58 146	99.76 254	94.32 348	99.46 265

save fliter					99.11 227	97.97 159	96.53 333	99.02 269	98.24 175

test0726					99.50 121	99.21 33	98.17 167	99.35 169	97.97 196	99.26 137	99.06 172	97.61 144

test_part2					99.36 166	99.10 65				99.05 166

sam_mvs												84.29 396

MTGPA								99.20 228

test_post1							97.59 260				20.48 452	83.07 404	99.66 310	94.16 349

test_post											21.25 451	83.86 399	99.70 283

patchmatchnet-post											98.77 248	84.37 393	99.85 149

MTMP							97.93 205	91.91 437

gm-plane-assit					94.83 445	81.97 448			88.07 433		94.99 423		99.60 332	91.76 398

TEST9					98.71 305	98.08 146	95.96 368	99.03 266	91.40 414	95.85 397	97.53 364	96.52 215	99.76 254

test_8					98.67 319	98.01 154	95.91 374	99.02 269	91.64 409	95.79 399	97.50 367	96.47 217	99.76 254

agg_prior					98.68 318	97.99 155		99.01 272		95.59 400			99.77 248

test_prior4						97.97 159	95.86 375

test_prior2							95.74 381		96.48 311	96.11 392	97.63 360	95.92 248		94.16 349	99.20 306

旧先验2							95.76 380		88.56 432	97.52 331			99.66 310	94.48 339

新几何2							95.93 371

原ACMM2							95.53 387

testdata2													99.79 231	92.80 385

segment_acmp												97.02 185

testdata1							95.44 392		96.32 317

plane_prior7					99.19 208	97.87 170

plane_prior6					98.99 254	97.70 191						94.90 274

plane_prior4											97.98 339

plane_prior3						97.78 184			97.41 249	97.79 312

plane_prior2							97.77 230		98.20 182

plane_prior1					99.05 244

plane_prior						97.65 193	97.07 305		96.72 301						99.36 278

n2								0.00 459

nn								0.00 459

door-mid								99.57 78

test11								98.87 292

door								99.41 148

HQP5-MVS						96.79 245

HQP-NCC					98.67 319		96.29 349		96.05 326	95.55 403

ACMP_Plane					98.67 319		96.29 349		96.05 326	95.55 403

BP-MVS														92.82 383

HQP3-MVS								99.04 264							99.26 296

HQP2-MVS												93.84 302

NP-MVS					98.84 283	97.39 210					96.84 385

MDTV_nov1_ep13			95.22 354		97.06 424	83.20 444	97.74 236	96.16 399	94.37 375	96.99 358	98.83 236	83.95 398	99.53 358	93.90 358	97.95 393

ACMMP++_ref															99.77 147

ACMMP++															99.68 194

Test By Simon												96.52 215

High-resolution multi-view benchmark