High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_vis1_n		99.68 47	99.79 29	99.36 232	99.94 18	98.18 311	99.52 89	100.00 1	99.86 46	100.00 1	99.88 47	98.99 109	99.96 56	99.97 4	99.96 68	99.95 13

test_vis3_rt		99.89 3	99.90 4	99.87 20	99.98 3	99.75 69	99.70 35	100.00 1	99.73 78	100.00 1	99.89 38	99.79 16	99.88 198	99.98 1	100.00 1	99.98 4

test_fmvs3		99.83 20	99.93 2	99.53 177	99.96 7	98.62 283	99.67 50	100.00 1	99.95 20	100.00 1	99.95 16	99.85 10	99.99 8	99.98 1	99.99 16	99.98 4

test_f		99.75 34	99.88 7	99.37 228	99.96 7	98.21 308	99.51 95	100.00 1	99.94 23	100.00 1	99.93 21	99.58 38	99.94 81	99.97 4	99.99 16	99.97 9

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 19	99.99 3	100.00 1	99.98 13	99.78 17	100.00 1	99.92 21	100.00 1	99.87 32

ANet_high		99.88 6	99.87 11	99.91 2	99.99 1	99.91 4	99.65 59	100.00 1	99.90 31	100.00 1	99.97 14	99.61 34	99.97 35	99.75 41	100.00 1	99.84 39

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 2	99.98 3	99.76 63	99.12 208	100.00 1	100.00 1	99.99 7	99.91 28	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_cas_vis1_n_1920		99.76 33	99.86 13	99.45 200	99.93 24	98.40 296	99.30 144	99.98 12	99.94 23	99.99 7	99.89 38	99.80 15	99.97 35	99.96 9	99.97 55	99.97 9

test_vis1_n_1920		99.72 38	99.88 7	99.27 256	99.93 24	97.84 334	99.34 129	100.00 1	99.99 3	99.99 7	99.82 80	99.87 9	99.99 8	99.97 4	99.99 16	99.97 9

test_fmvs1_n		99.68 47	99.81 25	99.28 253	99.95 15	97.93 331	99.49 100	100.00 1	99.82 62	99.99 7	99.89 38	99.21 77	99.98 21	99.97 4	99.98 41	99.93 18

test_fmvs2		99.72 38	99.85 17	99.34 235	99.91 30	98.08 322	99.48 102	100.00 1	99.90 31	99.99 7	99.91 28	99.50 48	99.98 21	99.98 1	99.99 16	99.96 12

mvsany_test3		99.85 12	99.88 7	99.75 76	99.95 15	99.37 183	99.53 88	99.98 12	99.77 76	99.99 7	99.95 16	99.85 10	99.94 81	99.95 12	99.98 41	99.94 16

MVStest1		98.22 306	98.09 301	98.62 332	99.04 360	96.23 378	99.20 176	99.92 34	99.44 148	99.98 13	99.87 52	85.87 401	99.67 370	99.91 24	99.57 285	99.95 13

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 2	99.95 15	99.82 37	99.10 216	99.98 12	99.99 3	99.98 13	99.91 28	99.68 26	99.93 99	99.93 19	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 10	99.93 24	99.78 51	99.07 226	99.98 12	99.99 3	99.98 13	99.90 33	99.88 8	99.92 125	99.93 19	99.99 16	99.98 4

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 2	99.97 6	99.74 75	99.01 240	99.99 11	99.99 3	99.98 13	99.88 47	99.97 2	99.99 8	99.96 9	100.00 1	99.98 4

PS-MVSNAJss		99.84 16	99.82 24	99.89 10	99.96 7	99.77 56	99.68 46	99.85 60	99.95 20	99.98 13	99.92 25	99.28 68	99.98 21	99.75 41	100.00 1	99.94 16

jajsoiax		99.89 3	99.89 6	99.89 10	99.96 7	99.78 51	99.70 35	99.86 54	99.89 37	99.98 13	99.90 33	99.94 4	99.98 21	99.75 41	100.00 1	99.90 24

mvs_tets		99.90 2	99.90 4	99.90 7	99.96 7	99.79 48	99.72 30	99.88 49	99.92 28	99.98 13	99.93 21	99.94 4	99.98 21	99.77 40	100.00 1	99.92 22

fmvsm_s_conf0.5_n_a		99.82 22	99.79 29	99.89 10	99.85 57	99.82 37	99.03 235	99.96 25	99.99 3	99.97 20	99.84 69	99.58 38	99.93 99	99.92 21	99.98 41	99.93 18

fmvsm_s_conf0.5_n		99.83 20	99.81 25	99.87 20	99.85 57	99.78 51	99.03 235	99.96 25	99.99 3	99.97 20	99.84 69	99.78 17	99.92 125	99.92 21	99.99 16	99.92 22

test_djsdf		99.84 16	99.81 25	99.91 2	99.94 18	99.84 24	99.77 16	99.80 85	99.73 78	99.97 20	99.92 25	99.77 19	99.98 21	99.43 78	100.00 1	99.90 24

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 16	99.91 30	99.90 7	99.96 1	99.92 34	99.90 31	99.97 20	99.87 52	99.81 14	99.95 66	99.54 63	99.99 16	99.80 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
fmvsm_l_conf0.5_n		99.80 24	99.78 33	99.85 26	99.88 43	99.66 103	99.11 213	99.91 38	99.98 14	99.96 24	99.64 192	99.60 36	99.99 8	99.95 12	99.99 16	99.88 28

test_fmvsmconf_n		99.85 12	99.84 20	99.88 16	99.91 30	99.73 78	98.97 252	99.98 12	99.99 3	99.96 24	99.85 63	99.93 7	99.99 8	99.94 16	99.99 16	99.93 18

test_fmvsmvis_n_1920		99.84 16	99.86 13	99.81 41	99.88 43	99.55 140	99.17 188	99.98 12	99.99 3	99.96 24	99.84 69	99.96 3	99.99 8	99.96 9	99.99 16	99.88 28

test_fmvsm_n_1920		99.84 16	99.85 17	99.83 31	99.82 72	99.70 92	99.17 188	99.97 19	99.99 3	99.96 24	99.82 80	99.94 4	100.00 1	99.95 12	100.00 1	99.80 50

test_fmvs1		99.48 91	99.65 52	98.97 297	99.54 221	97.16 357	99.11 213	99.98 12	99.78 72	99.96 24	99.81 87	98.72 146	99.97 35	99.95 12	99.97 55	99.79 57

dcpmvs_2		99.61 68	99.64 55	99.53 177	99.79 98	98.82 261	99.58 79	99.97 19	99.95 20	99.96 24	99.76 122	98.44 186	99.99 8	99.34 95	99.96 68	99.78 59

CHOSEN 1792x2688		99.39 122	99.30 130	99.65 125	99.88 43	99.25 208	98.78 280	99.88 49	98.66 261	99.96 24	99.79 100	97.45 263	99.93 99	99.34 95	99.99 16	99.78 59

wuyk23d		97.58 332	99.13 158	92.93 402	99.69 156	99.49 147	99.52 89	99.77 100	97.97 324	99.96 24	99.79 100	99.84 12	99.94 81	95.85 371	99.82 182	79.36 420

fmvsm_l_conf0.5_n_a		99.80 24	99.79 29	99.84 28	99.88 43	99.64 112	99.12 208	99.91 38	99.98 14	99.95 32	99.67 180	99.67 27	99.99 8	99.94 16	99.99 16	99.88 28

test_vis1_rt		99.45 104	99.46 93	99.41 217	99.71 144	98.63 282	98.99 248	99.96 25	99.03 213	99.95 32	99.12 347	98.75 141	99.84 264	99.82 37	99.82 182	99.77 63

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 7	99.89 38	99.91 4	99.89 5	99.71 132	99.93 25	99.95 32	99.89 38	99.71 22	99.96 56	99.51 68	99.97 55	99.84 39

pmmvs6		99.86 10	99.86 13	99.83 31	99.94 18	99.90 7	99.83 7	99.91 38	99.85 52	99.94 35	99.95 16	99.73 21	99.90 165	99.65 50	99.97 55	99.69 88

v7n		99.82 22	99.80 28	99.88 16	99.96 7	99.84 24	99.82 9	99.82 73	99.84 55	99.94 35	99.91 28	99.13 88	99.96 56	99.83 33	99.99 16	99.83 43

Gipuma		99.57 71	99.59 66	99.49 188	99.98 3	99.71 85	99.72 30	99.84 66	99.81 65	99.94 35	99.78 110	98.91 121	99.71 344	98.41 192	99.95 81	99.05 336
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
mamv4		99.73 37	99.74 39	99.70 105	99.66 171	99.87 14	99.69 42	99.93 32	99.93 25	99.93 38	99.86 59	99.07 97	100.00 1	99.66 48	99.92 105	99.24 283

v8		99.68 47	99.69 45	99.65 125	99.80 86	99.40 175	99.66 54	99.76 105	99.64 108	99.93 38	99.85 63	98.66 154	99.84 264	99.88 29	99.99 16	99.71 79

OurMVSNet-221017-0		99.75 34	99.71 41	99.84 28	99.96 7	99.83 29	99.83 7	99.85 60	99.80 68	99.93 38	99.93 21	98.54 170	99.93 99	99.59 55	99.98 41	99.76 68

MIMVSNet1		99.66 54	99.62 57	99.80 46	99.94 18	99.87 14	99.69 42	99.77 100	99.78 72	99.93 38	99.89 38	97.94 234	99.92 125	99.65 50	99.98 41	99.62 145

DeepC-MVS	98.90 4	99.62 66	99.61 61	99.67 112	99.72 141	99.44 161	99.24 166	99.71 132	99.27 174	99.93 38	99.90 33	99.70 24	99.93 99	98.99 144	99.99 16	99.64 129
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mvsany_test1		99.44 106	99.45 95	99.40 219	99.37 284	98.64 281	97.90 371	99.59 204	99.27 174	99.92 43	99.82 80	99.74 20	99.93 99	99.55 62	99.87 147	99.63 134

anonymousdsp		99.80 24	99.77 35	99.90 7	99.96 7	99.88 12	99.73 27	99.85 60	99.70 89	99.92 43	99.93 21	99.45 49	99.97 35	99.36 91	100.00 1	99.85 37

v10		99.69 44	99.69 45	99.66 119	99.81 80	99.39 178	99.66 54	99.75 110	99.60 123	99.92 43	99.87 52	98.75 141	99.86 231	99.90 25	99.99 16	99.73 73

tt0805		99.63 60	99.57 73	99.81 41	99.87 50	99.88 12	99.58 79	98.70 359	99.72 82	99.91 46	99.60 227	99.43 50	99.81 304	99.81 38	99.53 297	99.73 73

LCM-MVSNet-Re		99.28 146	99.15 155	99.67 112	99.33 304	99.76 63	99.34 129	99.97 19	98.93 225	99.91 46	99.79 100	98.68 149	99.93 99	96.80 323	99.56 286	99.30 274

TransMVSNet (Re)		99.78 28	99.77 35	99.81 41	99.91 30	99.85 19	99.75 22	99.86 54	99.70 89	99.91 46	99.89 38	99.60 36	99.87 212	99.59 55	99.74 224	99.71 79

tfpnnormal		99.43 109	99.38 108	99.60 154	99.87 50	99.75 69	99.59 77	99.78 97	99.71 84	99.90 49	99.69 165	98.85 127	99.90 165	97.25 299	99.78 209	99.15 307

Anonymous20231211		99.62 66	99.57 73	99.76 66	99.61 183	99.60 128	99.81 10	99.73 120	99.82 62	99.90 49	99.90 33	97.97 233	99.86 231	99.42 83	99.96 68	99.80 50

v1240		99.56 74	99.58 69	99.51 182	99.80 86	99.00 242	99.00 243	99.65 167	99.15 200	99.90 49	99.75 127	99.09 92	99.88 198	99.90 25	99.96 68	99.67 102

EU-MVSNet		99.39 122	99.62 57	98.72 328	99.88 43	96.44 372	99.56 84	99.85 60	99.90 31	99.90 49	99.85 63	98.09 223	99.83 279	99.58 58	99.95 81	99.90 24

mvs5depth		99.88 6	99.91 3	99.80 46	99.92 28	99.42 168	99.94 3	100.00 1	99.97 16	99.89 53	99.99 12	99.63 30	99.97 35	99.87 31	99.99 16	100.00 1

SDMVSNet		99.77 32	99.77 35	99.76 66	99.80 86	99.65 109	99.63 61	99.86 54	99.97 16	99.89 53	99.89 38	99.52 46	99.99 8	99.42 83	99.96 68	99.65 119

sd_testset		99.78 28	99.78 33	99.80 46	99.80 86	99.76 63	99.80 11	99.79 91	99.97 16	99.89 53	99.89 38	99.53 45	99.99 8	99.36 91	99.96 68	99.65 119

IterMVS-SCA-FT		99.00 221	99.16 152	98.51 338	99.75 129	95.90 384	98.07 351	99.84 66	99.84 55	99.89 53	99.73 135	96.01 313	99.99 8	99.33 98	100.00 1	99.63 134

v144192		99.55 77	99.54 80	99.58 159	99.78 105	99.20 220	99.11 213	99.62 180	99.18 189	99.89 53	99.72 142	98.66 154	99.87 212	99.88 29	99.97 55	99.66 111

pm-mvs1		99.79 27	99.79 29	99.78 56	99.91 30	99.83 29	99.76 20	99.87 51	99.73 78	99.89 53	99.87 52	99.63 30	99.87 212	99.54 63	99.92 105	99.63 134

lessismore_v0				99.64 132	99.86 53	99.38 180		90.66 422		99.89 53	99.83 73	94.56 330	99.97 35	99.56 60	99.92 105	99.57 176

SixPastTwentyTwo		99.42 112	99.30 130	99.76 66	99.92 28	99.67 101	99.70 35	99.14 337	99.65 105	99.89 53	99.90 33	96.20 310	99.94 81	99.42 83	99.92 105	99.67 102

HyFIR lowres test		98.91 234	98.64 247	99.73 90	99.85 57	99.47 150	98.07 351	99.83 68	98.64 263	99.89 53	99.60 227	92.57 350	100.00 1	99.33 98	99.97 55	99.72 76

testf1		99.63 60	99.60 64	99.72 96	99.94 18	99.95 2	99.47 105	99.89 45	99.43 154	99.88 62	99.80 90	99.26 72	99.90 165	98.81 164	99.88 135	99.32 268

APD_test2		99.63 60	99.60 64	99.72 96	99.94 18	99.95 2	99.47 105	99.89 45	99.43 154	99.88 62	99.80 90	99.26 72	99.90 165	98.81 164	99.88 135	99.32 268

test1111		97.74 324	98.16 297	96.49 395	99.60 185	89.86 425	99.71 34	91.21 421	99.89 37	99.88 62	99.87 52	93.73 339	99.90 165	99.56 60	99.99 16	99.70 82

KD-MVS_self_test		99.63 60	99.59 66	99.76 66	99.84 61	99.90 7	99.37 124	99.79 91	99.83 60	99.88 62	99.85 63	98.42 189	99.90 165	99.60 54	99.73 230	99.49 217

new-patchmatchnet		99.35 132	99.57 73	98.71 330	99.82 72	96.62 369	98.55 305	99.75 110	99.50 133	99.88 62	99.87 52	99.31 64	99.88 198	99.43 78	100.00 1	99.62 145

v1921920		99.56 74	99.57 73	99.55 171	99.75 129	99.11 230	99.05 227	99.61 187	99.15 200	99.88 62	99.71 150	99.08 95	99.87 212	99.90 25	99.97 55	99.66 111

NR-MVSNet		99.40 118	99.31 125	99.68 109	99.43 270	99.55 140	99.73 27	99.50 255	99.46 143	99.88 62	99.36 303	97.54 260	99.87 212	98.97 148	99.87 147	99.63 134

K. test v3		98.87 241	98.60 250	99.69 107	99.93 24	99.46 154	99.74 24	94.97 412	99.78 72	99.88 62	99.88 47	93.66 340	99.97 35	99.61 53	99.95 81	99.64 129

v1192		99.57 71	99.57 73	99.57 165	99.77 113	99.22 215	99.04 232	99.60 198	99.18 189	99.87 70	99.72 142	99.08 95	99.85 249	99.89 28	99.98 41	99.66 111

reproduce_monomvs		97.40 338	97.46 332	97.20 385	99.05 357	91.91 413	99.20 176	99.18 332	99.84 55	99.86 71	99.75 127	80.67 408	99.83 279	99.69 45	99.95 81	99.85 37

ECVR-MVS		97.73 325	98.04 304	96.78 389	99.59 190	90.81 421	99.72 30	90.43 423	99.89 37	99.86 71	99.86 59	93.60 341	99.89 184	99.46 74	99.99 16	99.65 119

V42		99.56 74	99.54 80	99.63 139	99.79 98	99.46 154	99.39 117	99.59 204	99.24 180	99.86 71	99.70 158	98.55 168	99.82 289	99.79 39	99.95 81	99.60 159

mvs_anonymous		99.28 146	99.39 106	98.94 301	99.19 333	97.81 336	99.02 238	99.55 226	99.78 72	99.85 74	99.80 90	98.24 209	99.86 231	99.57 59	99.50 304	99.15 307

WR-MVS_H		99.61 68	99.53 84	99.87 20	99.80 86	99.83 29	99.67 50	99.75 110	99.58 126	99.85 74	99.69 165	98.18 219	99.94 81	99.28 108	99.95 81	99.83 43

IterMVS		98.97 225	99.16 152	98.42 343	99.74 135	95.64 388	98.06 353	99.83 68	99.83 60	99.85 74	99.74 131	96.10 312	99.99 8	99.27 109	100.00 1	99.63 134
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		99.54 80	99.53 84	99.59 156	99.79 98	99.28 201	99.10 216	99.61 187	99.20 187	99.84 77	99.73 135	98.67 152	99.84 264	99.86 32	99.98 41	99.64 129

PS-CasMVS		99.66 54	99.58 69	99.89 10	99.80 86	99.85 19	99.66 54	99.73 120	99.62 113	99.84 77	99.71 150	98.62 158	99.96 56	99.30 103	99.96 68	99.86 34

PEN-MVS		99.66 54	99.59 66	99.89 10	99.83 65	99.87 14	99.66 54	99.73 120	99.70 89	99.84 77	99.73 135	98.56 167	99.96 56	99.29 106	99.94 94	99.83 43

DTE-MVSNet		99.68 47	99.61 61	99.88 16	99.80 86	99.87 14	99.67 50	99.71 132	99.72 82	99.84 77	99.78 110	98.67 152	99.97 35	99.30 103	99.95 81	99.80 50

IterMVS-LS		99.41 116	99.47 89	99.25 262	99.81 80	98.09 319	98.85 265	99.76 105	99.62 113	99.83 81	99.64 192	98.54 170	99.97 35	99.15 126	99.99 16	99.68 94
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous20240521		99.44 106	99.42 102	99.49 188	99.89 38	98.96 249	99.62 64	99.76 105	99.85 52	99.82 82	99.88 47	96.39 303	99.97 35	99.59 55	99.98 41	99.55 181

SED-MVS		99.40 118	99.28 137	99.77 59	99.69 156	99.82 37	99.20 176	99.54 232	99.13 202	99.82 82	99.63 203	98.91 121	99.92 125	97.85 244	99.70 241	99.58 171

test_241102_ONE					99.69 156	99.82 37		99.54 232	99.12 205	99.82 82	99.49 268	98.91 121	99.52 403

FC-MVSNet-test		99.70 42	99.65 52	99.86 24	99.88 43	99.86 18	99.72 30	99.78 97	99.90 31	99.82 82	99.83 73	98.45 185	99.87 212	99.51 68	99.97 55	99.86 34

test20.03		99.55 77	99.54 80	99.58 159	99.79 98	99.37 183	99.02 238	99.89 45	99.60 123	99.82 82	99.62 210	98.81 129	99.89 184	99.43 78	99.86 155	99.47 225

FMVSNet1		99.66 54	99.63 56	99.73 90	99.78 105	99.77 56	99.68 46	99.70 137	99.67 98	99.82 82	99.83 73	98.98 111	99.90 165	99.24 110	99.97 55	99.53 195

XXY-MVS		99.71 41	99.67 49	99.81 41	99.89 38	99.72 83	99.59 77	99.82 73	99.39 159	99.82 82	99.84 69	99.38 56	99.91 147	99.38 87	99.93 101	99.80 50

SSC-MVS		99.52 83	99.42 102	99.83 31	99.86 53	99.65 109	99.52 89	99.81 82	99.87 43	99.81 89	99.79 100	96.78 289	99.99 8	99.83 33	99.51 301	99.86 34

v148		99.40 118	99.41 104	99.39 222	99.76 117	98.94 251	99.09 220	99.59 204	99.17 194	99.81 89	99.61 219	98.41 190	99.69 353	99.32 100	99.94 94	99.53 195

v2v482		99.50 85	99.47 89	99.58 159	99.78 105	99.25 208	99.14 198	99.58 213	99.25 178	99.81 89	99.62 210	98.24 209	99.84 264	99.83 33	99.97 55	99.64 129

PM-MVS		99.36 130	99.29 135	99.58 159	99.83 65	99.66 103	98.95 255	99.86 54	98.85 236	99.81 89	99.73 135	98.40 194	99.92 125	98.36 195	99.83 173	99.17 303

reproduce_model		99.50 85	99.40 105	99.83 31	99.60 185	99.83 29	99.12 208	99.68 147	99.49 135	99.80 93	99.79 100	99.01 106	99.93 99	98.24 205	99.82 182	99.73 73

EI-MVSNet-UG-set		99.48 91	99.50 86	99.42 210	99.57 205	98.65 279	99.24 166	99.46 266	99.68 94	99.80 93	99.66 185	98.99 109	99.89 184	99.19 118	99.90 116	99.72 76

VPA-MVSNet		99.66 54	99.62 57	99.79 53	99.68 164	99.75 69	99.62 64	99.69 144	99.85 52	99.80 93	99.81 87	98.81 129	99.91 147	99.47 73	99.88 135	99.70 82

CP-MVSNet		99.54 80	99.43 100	99.87 20	99.76 117	99.82 37	99.57 82	99.61 187	99.54 127	99.80 93	99.64 192	97.79 245	99.95 66	99.21 114	99.94 94	99.84 39

EG-PatchMatch MVS		99.57 71	99.56 78	99.62 148	99.77 113	99.33 193	99.26 159	99.76 105	99.32 168	99.80 93	99.78 110	99.29 66	99.87 212	99.15 126	99.91 115	99.66 111

ACMH	98.42 6	99.59 70	99.54 80	99.72 96	99.86 53	99.62 119	99.56 84	99.79 91	98.77 250	99.80 93	99.85 63	99.64 28	99.85 249	98.70 176	99.89 126	99.70 82
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EI-MVSNet-Vis-set		99.47 99	99.49 88	99.42 210	99.57 205	98.66 276	99.24 166	99.46 266	99.67 98	99.79 99	99.65 190	98.97 113	99.89 184	99.15 126	99.89 126	99.71 79

casdiffmvs_mvg		99.68 47	99.68 48	99.69 107	99.81 80	99.59 130	99.29 151	99.90 43	99.71 84	99.79 99	99.73 135	99.54 43	99.84 264	99.36 91	99.96 68	99.65 119
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		99.40 118	99.38 108	99.44 204	99.90 36	98.66 276	98.94 257	99.91 38	97.97 324	99.79 99	99.73 135	99.05 102	99.97 35	99.15 126	99.99 16	99.68 94

N_pmnet		98.73 255	98.53 262	99.35 234	99.72 141	98.67 273	98.34 326	94.65 413	98.35 298	99.79 99	99.68 176	98.03 227	99.93 99	98.28 201	99.92 105	99.44 235

reproduce-ours		99.46 100	99.35 116	99.82 36	99.56 216	99.83 29	99.05 227	99.65 167	99.45 146	99.78 103	99.78 110	98.93 116	99.93 99	98.11 219	99.81 192	99.70 82

our_new_method		99.46 100	99.35 116	99.82 36	99.56 216	99.83 29	99.05 227	99.65 167	99.45 146	99.78 103	99.78 110	98.93 116	99.93 99	98.11 219	99.81 192	99.70 82

balanced_conf03		99.50 85	99.50 86	99.50 184	99.42 275	99.49 147	99.52 89	99.75 110	99.86 46	99.78 103	99.71 150	98.20 216	99.90 165	99.39 86	99.88 135	99.10 318

ppachtmachnet_test		98.89 239	99.12 162	98.20 355	99.66 171	95.24 394	97.63 381	99.68 147	99.08 207	99.78 103	99.62 210	98.65 156	99.88 198	98.02 224	99.96 68	99.48 221

nrg030		99.70 42	99.66 50	99.82 36	99.76 117	99.84 24	99.61 70	99.70 137	99.93 25	99.78 103	99.68 176	99.10 90	99.78 317	99.45 76	99.96 68	99.83 43

PMMVS2		99.48 91	99.45 95	99.57 165	99.76 117	98.99 244	98.09 348	99.90 43	98.95 221	99.78 103	99.58 235	99.57 40	99.93 99	99.48 72	99.95 81	99.79 57

TAMVS		99.49 89	99.45 95	99.63 139	99.48 252	99.42 168	99.45 109	99.57 215	99.66 102	99.78 103	99.83 73	97.85 241	99.86 231	99.44 77	99.96 68	99.61 155

TDRefinement		99.72 38	99.70 42	99.77 59	99.90 36	99.85 19	99.86 6	99.92 34	99.69 92	99.78 103	99.92 25	99.37 58	99.88 198	98.93 156	99.95 81	99.60 159

MVSMamba_PlusPlus		99.55 77	99.58 69	99.47 194	99.68 164	99.40 175	99.52 89	99.70 137	99.92 28	99.77 111	99.86 59	98.28 205	99.96 56	99.54 63	99.90 116	99.05 336

Vis-MVSNet		99.75 34	99.74 39	99.79 53	99.88 43	99.66 103	99.69 42	99.92 34	99.67 98	99.77 111	99.75 127	99.61 34	99.98 21	99.35 94	99.98 41	99.72 76
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH+	98.40 8	99.50 85	99.43 100	99.71 101	99.86 53	99.76 63	99.32 136	99.77 100	99.53 129	99.77 111	99.76 122	99.26 72	99.78 317	97.77 249	99.88 135	99.60 159

DVP-MVS++		99.38 124	99.25 143	99.77 59	99.03 361	99.77 56	99.74 24	99.61 187	99.18 189	99.76 114	99.61 219	99.00 107	99.92 125	97.72 255	99.60 277	99.62 145

test_241102_TWO								99.54 232	99.13 202	99.76 114	99.63 203	98.32 203	99.92 125	97.85 244	99.69 245	99.75 71

Anonymous20240529		99.42 112	99.34 118	99.65 125	99.53 227	99.60 128	99.63 61	99.39 287	99.47 140	99.76 114	99.78 110	98.13 221	99.86 231	98.70 176	99.68 250	99.49 217

DPE-MVS		99.14 189	98.92 222	99.82 36	99.57 205	99.77 56	98.74 284	99.60 198	98.55 272	99.76 114	99.69 165	98.23 213	99.92 125	96.39 348	99.75 217	99.76 68
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
casdiffmvs		99.63 60	99.61 61	99.67 112	99.79 98	99.59 130	99.13 204	99.85 60	99.79 70	99.76 114	99.72 142	99.33 63	99.82 289	99.21 114	99.94 94	99.59 166
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GeoE		99.69 44	99.66 50	99.78 56	99.76 117	99.76 63	99.60 76	99.82 73	99.46 143	99.75 119	99.56 246	99.63 30	99.95 66	99.43 78	99.88 135	99.62 145

pmmvs-eth3d		99.48 91	99.47 89	99.51 182	99.77 113	99.41 174	98.81 273	99.66 157	99.42 158	99.75 119	99.66 185	99.20 78	99.76 328	98.98 146	99.99 16	99.36 258

SD-MVS		99.01 219	99.30 130	98.15 356	99.50 242	99.40 175	98.94 257	99.61 187	99.22 186	99.75 119	99.82 80	99.54 43	95.51 423	97.48 279	99.87 147	99.54 190
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
APDe-MVS		99.48 91	99.36 114	99.85 26	99.55 219	99.81 42	99.50 96	99.69 144	98.99 215	99.75 119	99.71 150	98.79 134	99.93 99	98.46 190	99.85 160	99.80 50
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EI-MVSNet		99.38 124	99.44 98	99.21 266	99.58 195	98.09 319	99.26 159	99.46 266	99.62 113	99.75 119	99.67 180	98.54 170	99.85 249	99.15 126	99.92 105	99.68 94

testgi		99.29 145	99.26 141	99.37 228	99.75 129	98.81 262	98.84 266	99.89 45	98.38 291	99.75 119	99.04 357	99.36 61	99.86 231	99.08 138	99.25 337	99.45 230

MVSTER		98.47 284	98.22 290	99.24 264	99.06 356	98.35 302	99.08 223	99.46 266	99.27 174	99.75 119	99.66 185	88.61 388	99.85 249	99.14 132	99.92 105	99.52 205

USDC		98.96 228	98.93 218	99.05 291	99.54 221	97.99 325	97.07 405	99.80 85	98.21 310	99.75 119	99.77 119	98.43 187	99.64 383	97.90 236	99.88 135	99.51 207

Patchmatch-RL test		98.60 267	98.36 277	99.33 238	99.77 113	99.07 238	98.27 331	99.87 51	98.91 228	99.74 127	99.72 142	90.57 377	99.79 314	98.55 186	99.85 160	99.11 316

FIs		99.65 59	99.58 69	99.84 28	99.84 61	99.85 19	99.66 54	99.75 110	99.86 46	99.74 127	99.79 100	98.27 207	99.85 249	99.37 90	99.93 101	99.83 43

jason		99.16 185	99.11 165	99.32 243	99.75 129	98.44 293	98.26 333	99.39 287	98.70 258	99.74 127	99.30 317	98.54 170	99.97 35	98.48 189	99.82 182	99.55 181
jason: jason.
DP-MVS		99.48 91	99.39 106	99.74 81	99.57 205	99.62 119	99.29 151	99.61 187	99.87 43	99.74 127	99.76 122	98.69 148	99.87 212	98.20 209	99.80 199	99.75 71

BP-MVS1		98.72 256	98.46 266	99.50 184	99.53 227	99.00 242	99.34 129	98.53 369	99.65 105	99.73 131	99.38 296	90.62 375	99.96 56	99.50 70	99.86 155	99.55 181

test0726					99.69 156	99.80 46	99.24 166	99.57 215	99.16 196	99.73 131	99.65 190	98.35 198

pmmvs5		99.19 175	99.11 165	99.42 210	99.76 117	98.88 258	98.55 305	99.73 120	98.82 241	99.72 133	99.62 210	96.56 294	99.82 289	99.32 100	99.95 81	99.56 178

Anonymous20231206		99.35 132	99.31 125	99.47 194	99.74 135	99.06 240	99.28 153	99.74 116	99.23 182	99.72 133	99.53 257	97.63 259	99.88 198	99.11 134	99.84 165	99.48 221

CVMVSNet		98.61 264	98.88 227	97.80 369	99.58 195	93.60 406	99.26 159	99.64 175	99.66 102	99.72 133	99.67 180	93.26 343	99.93 99	99.30 103	99.81 192	99.87 32

baseline		99.63 60	99.62 57	99.66 119	99.80 86	99.62 119	99.44 111	99.80 85	99.71 84	99.72 133	99.69 165	99.15 83	99.83 279	99.32 100	99.94 94	99.53 195

Patchmtry		98.78 249	98.54 261	99.49 188	98.89 375	99.19 221	99.32 136	99.67 152	99.65 105	99.72 133	99.79 100	91.87 358	99.95 66	98.00 228	99.97 55	99.33 265

WB-MVS		99.44 106	99.32 123	99.80 46	99.81 80	99.61 125	99.47 105	99.81 82	99.82 62	99.71 138	99.72 142	96.60 293	99.98 21	99.75 41	99.23 341	99.82 49

test2506		94.73 385	94.59 386	95.15 401	99.59 190	85.90 427	99.75 22	74.01 429	99.89 37	99.71 138	99.86 59	79.00 418	99.90 165	99.52 67	99.99 16	99.65 119

UA-Net		99.78 28	99.76 38	99.86 24	99.72 141	99.71 85	99.91 4	99.95 30	99.96 19	99.71 138	99.91 28	99.15 83	99.97 35	99.50 70	100.00 1	99.90 24

TranMVSNet+NR-MVSNet		99.54 80	99.47 89	99.76 66	99.58 195	99.64 112	99.30 144	99.63 177	99.61 117	99.71 138	99.56 246	98.76 139	99.96 56	99.14 132	99.92 105	99.68 94

tttt0517		97.62 330	97.20 340	98.90 313	99.76 117	97.40 351	99.48 102	94.36 414	99.06 211	99.70 142	99.49 268	84.55 404	99.94 81	98.73 174	99.65 261	99.36 258

UniMVSNet (Re)		99.37 127	99.26 141	99.68 109	99.51 236	99.58 134	98.98 251	99.60 198	99.43 154	99.70 142	99.36 303	97.70 249	99.88 198	99.20 117	99.87 147	99.59 166

FMVSNet2		99.35 132	99.28 137	99.55 171	99.49 247	99.35 190	99.45 109	99.57 215	99.44 148	99.70 142	99.74 131	97.21 274	99.87 212	99.03 141	99.94 94	99.44 235

APD_test1		99.36 130	99.28 137	99.61 151	99.89 38	99.89 10	99.32 136	99.74 116	99.18 189	99.69 145	99.75 127	98.41 190	99.84 264	97.85 244	99.70 241	99.10 318

IU-MVS					99.69 156	99.77 56		99.22 325	97.50 350	99.69 145				97.75 253	99.70 241	99.77 63

VPNet		99.46 100	99.37 111	99.71 101	99.82 72	99.59 130	99.48 102	99.70 137	99.81 65	99.69 145	99.58 235	97.66 257	99.86 231	99.17 123	99.44 311	99.67 102

PC_three_1452									97.56 344	99.68 148	99.41 286	99.09 92	97.09 420	96.66 331	99.60 277	99.62 145

D2MVS		99.22 165	99.19 149	99.29 250	99.69 156	98.74 269	98.81 273	99.41 277	98.55 272	99.68 148	99.69 165	98.13 221	99.87 212	98.82 162	99.98 41	99.24 283

xiu_mvs_v1_base_debu		99.23 157	99.34 118	98.91 307	99.59 190	98.23 305	98.47 316	99.66 157	99.61 117	99.68 148	98.94 373	99.39 52	99.97 35	99.18 120	99.55 290	98.51 386

xiu_mvs_v1_base		99.23 157	99.34 118	98.91 307	99.59 190	98.23 305	98.47 316	99.66 157	99.61 117	99.68 148	98.94 373	99.39 52	99.97 35	99.18 120	99.55 290	98.51 386

xiu_mvs_v1_base_debi		99.23 157	99.34 118	98.91 307	99.59 190	98.23 305	98.47 316	99.66 157	99.61 117	99.68 148	98.94 373	99.39 52	99.97 35	99.18 120	99.55 290	98.51 386

ambc				99.20 268	99.35 290	98.53 287	99.17 188	99.46 266		99.67 153	99.80 90	98.46 184	99.70 347	97.92 234	99.70 241	99.38 252

RRT-MVS		99.08 200	99.00 202	99.33 238	99.27 317	98.65 279	99.62 64	99.93 32	99.66 102	99.67 153	99.82 80	95.27 323	99.93 99	98.64 182	99.09 347	99.41 246

UniMVSNet_NR-MVSNet		99.37 127	99.25 143	99.72 96	99.47 258	99.56 137	98.97 252	99.61 187	99.43 154	99.67 153	99.28 321	97.85 241	99.95 66	99.17 123	99.81 192	99.65 119

DU-MVS		99.33 140	99.21 147	99.71 101	99.43 270	99.56 137	98.83 268	99.53 241	99.38 160	99.67 153	99.36 303	97.67 253	99.95 66	99.17 123	99.81 192	99.63 134

COLMAP_ROB	98.06 12	99.45 104	99.37 111	99.70 105	99.83 65	99.70 92	99.38 120	99.78 97	99.53 129	99.67 153	99.78 110	99.19 79	99.86 231	97.32 288	99.87 147	99.55 181
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-OURS		99.21 170	99.06 182	99.65 125	99.82 72	99.62 119	97.87 372	99.74 116	98.36 293	99.66 158	99.68 176	99.71 22	99.90 165	96.84 321	99.88 135	99.43 241

DeepPCF-MVS	98.42 6	99.18 179	99.02 195	99.67 112	99.22 326	99.75 69	97.25 399	99.47 263	98.72 255	99.66 158	99.70 158	99.29 66	99.63 384	98.07 223	99.81 192	99.62 145

Baseline_NR-MVSNet		99.49 89	99.37 111	99.82 36	99.91 30	99.84 24	98.83 268	99.86 54	99.68 94	99.65 160	99.88 47	97.67 253	99.87 212	99.03 141	99.86 155	99.76 68

our_test_3		98.85 243	99.09 174	98.13 357	99.66 171	94.90 398	97.72 377	99.58 213	99.07 209	99.64 161	99.62 210	98.19 217	99.93 99	98.41 192	99.95 81	99.55 181

LPG-MVS_test		99.22 165	99.05 186	99.74 81	99.82 72	99.63 117	99.16 194	99.73 120	97.56 344	99.64 161	99.69 165	99.37 58	99.89 184	96.66 331	99.87 147	99.69 88

LGP-MVS_train				99.74 81	99.82 72	99.63 117		99.73 120	97.56 344	99.64 161	99.69 165	99.37 58	99.89 184	96.66 331	99.87 147	99.69 88

ACMM	98.09 11	99.46 100	99.38 108	99.72 96	99.80 86	99.69 96	99.13 204	99.65 167	98.99 215	99.64 161	99.72 142	99.39 52	99.86 231	98.23 206	99.81 192	99.60 159
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FA-MVS(test-final)		98.52 277	98.32 282	99.10 282	99.48 252	98.67 273	99.77 16	98.60 367	97.35 358	99.63 165	99.80 90	93.07 346	99.84 264	97.92 234	99.30 330	98.78 370

FOURS1					99.83 65	99.89 10	99.74 24	99.71 132	99.69 92	99.63 165

AllTest		99.21 170	99.07 180	99.63 139	99.78 105	99.64 112	99.12 208	99.83 68	98.63 264	99.63 165	99.72 142	98.68 149	99.75 332	96.38 349	99.83 173	99.51 207

TestCases				99.63 139	99.78 105	99.64 112		99.83 68	98.63 264	99.63 165	99.72 142	98.68 149	99.75 332	96.38 349	99.83 173	99.51 207

MDA-MVSNet-bldmvs		99.06 204	99.05 186	99.07 288	99.80 86	97.83 335	98.89 260	99.72 129	99.29 170	99.63 165	99.70 158	96.47 298	99.89 184	98.17 215	99.82 182	99.50 212

TSAR-MVS + GP.		99.12 193	99.04 192	99.38 225	99.34 299	99.16 224	98.15 340	99.29 309	98.18 313	99.63 165	99.62 210	99.18 80	99.68 365	98.20 209	99.74 224	99.30 274

XVG-OURS-SEG-HR		99.16 185	98.99 209	99.66 119	99.84 61	99.64 112	98.25 334	99.73 120	98.39 290	99.63 165	99.43 283	99.70 24	99.90 165	97.34 287	98.64 379	99.44 235

MVSFormer		99.41 116	99.44 98	99.31 246	99.57 205	98.40 296	99.77 16	99.80 85	99.73 78	99.63 165	99.30 317	98.02 228	99.98 21	99.43 78	99.69 245	99.55 181

lupinMVS		98.96 228	98.87 228	99.24 264	99.57 205	98.40 296	98.12 344	99.18 332	98.28 306	99.63 165	99.13 343	98.02 228	99.97 35	98.22 207	99.69 245	99.35 261

DVP-MVS		99.32 142	99.17 151	99.77 59	99.69 156	99.80 46	99.14 198	99.31 305	99.16 196	99.62 174	99.61 219	98.35 198	99.91 147	97.88 238	99.72 236	99.61 155
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_THIRD									99.18 189	99.62 174	99.61 219	98.58 164	99.91 147	97.72 255	99.80 199	99.77 63

GBi-Net		99.42 112	99.31 125	99.73 90	99.49 247	99.77 56	99.68 46	99.70 137	99.44 148	99.62 174	99.83 73	97.21 274	99.90 165	98.96 150	99.90 116	99.53 195

test1		99.42 112	99.31 125	99.73 90	99.49 247	99.77 56	99.68 46	99.70 137	99.44 148	99.62 174	99.83 73	97.21 274	99.90 165	98.96 150	99.90 116	99.53 195

new_pmnet		98.88 240	98.89 226	98.84 318	99.70 152	97.62 343	98.15 340	99.50 255	97.98 323	99.62 174	99.54 255	98.15 220	99.94 81	97.55 274	99.84 165	98.95 351

FMVSNet3		98.80 248	98.63 249	99.32 243	99.13 342	98.72 270	99.10 216	99.48 260	99.23 182	99.62 174	99.64 192	92.57 350	99.86 231	98.96 150	99.90 116	99.39 250

CS-MVS		99.67 53	99.70 42	99.58 159	99.53 227	99.84 24	99.79 12	99.96 25	99.90 31	99.61 180	99.41 286	99.51 47	99.95 66	99.66 48	99.89 126	98.96 349

CDS-MVSNet		99.22 165	99.13 158	99.50 184	99.35 290	99.11 230	98.96 254	99.54 232	99.46 143	99.61 180	99.70 158	96.31 306	99.83 279	99.34 95	99.88 135	99.55 181
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		99.03 211	98.85 230	99.55 171	99.80 86	99.25 208	99.73 27	99.15 336	99.37 161	99.61 180	99.71 150	94.73 328	99.81 304	97.70 260	99.88 135	99.58 171

cl____		98.54 275	98.41 272	98.92 305	99.03 361	97.80 338	97.46 391	99.59 204	98.90 229	99.60 183	99.46 278	93.85 336	99.78 317	97.97 231	99.89 126	99.17 303

DIV-MVS_self_test		98.54 275	98.42 271	98.92 305	99.03 361	97.80 338	97.46 391	99.59 204	98.90 229	99.60 183	99.46 278	93.87 335	99.78 317	97.97 231	99.89 126	99.18 301

XVG-ACMP-BASELINE		99.23 157	99.10 173	99.63 139	99.82 72	99.58 134	98.83 268	99.72 129	98.36 293	99.60 183	99.71 150	98.92 119	99.91 147	97.08 307	99.84 165	99.40 248

miper_lstm_enhance		98.65 263	98.60 250	98.82 323	99.20 331	97.33 353	97.78 375	99.66 157	99.01 214	99.59 186	99.50 264	94.62 329	99.85 249	98.12 218	99.90 116	99.26 280

YYNet1		98.95 231	98.99 209	98.84 318	99.64 176	97.14 359	98.22 336	99.32 301	98.92 227	99.59 186	99.66 185	97.40 265	99.83 279	98.27 202	99.90 116	99.55 181

eth_miper_zixun_eth		98.68 261	98.71 243	98.60 334	99.10 351	96.84 366	97.52 389	99.54 232	98.94 222	99.58 188	99.48 271	96.25 309	99.76 328	98.01 227	99.93 101	99.21 292

pmmvs4		99.13 191	99.06 182	99.36 232	99.57 205	99.10 235	98.01 357	99.25 318	98.78 248	99.58 188	99.44 282	98.24 209	99.76 328	98.74 173	99.93 101	99.22 289

DeepC-MVS_fast	98.47 5	99.23 157	99.12 162	99.56 168	99.28 315	99.22 215	98.99 248	99.40 284	99.08 207	99.58 188	99.64 192	98.90 124	99.83 279	97.44 281	99.75 217	99.63 134
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GDP-MVS		98.81 247	98.57 256	99.50 184	99.53 227	99.12 229	99.28 153	99.86 54	99.53 129	99.57 191	99.32 312	90.88 371	99.98 21	99.46 74	99.74 224	99.42 245

SMA-MVS		99.19 175	99.00 202	99.73 90	99.46 262	99.73 78	99.13 204	99.52 246	97.40 355	99.57 191	99.64 192	98.93 116	99.83 279	97.61 271	99.79 204	99.63 134
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
TSAR-MVS + MP.		99.34 137	99.24 145	99.63 139	99.82 72	99.37 183	99.26 159	99.35 296	98.77 250	99.57 191	99.70 158	99.27 71	99.88 198	97.71 257	99.75 217	99.65 119
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
APD-MVS_3200maxsize		99.31 143	99.16 152	99.74 81	99.53 227	99.75 69	99.27 157	99.61 187	99.19 188	99.57 191	99.64 192	98.76 139	99.90 165	97.29 290	99.62 267	99.56 178

WR-MVS		99.11 196	98.93 218	99.66 119	99.30 310	99.42 168	98.42 322	99.37 292	99.04 212	99.57 191	99.20 339	96.89 286	99.86 231	98.66 180	99.87 147	99.70 82

SteuartSystems-ACMMP		99.30 144	99.14 156	99.76 66	99.87 50	99.66 103	99.18 183	99.60 198	98.55 272	99.57 191	99.67 180	99.03 105	99.94 81	97.01 309	99.80 199	99.69 88
Skip Steuart: Steuart Systems R&D Blog.
ab-mvs		99.33 140	99.28 137	99.47 194	99.57 205	99.39 178	99.78 14	99.43 274	98.87 233	99.57 191	99.82 80	98.06 226	99.87 212	98.69 178	99.73 230	99.15 307

CMPMVS	77.52 23	98.50 280	98.19 295	99.41 217	98.33 409	99.56 137	99.01 240	99.59 204	95.44 393	99.57 191	99.80 90	95.64 316	99.46 408	96.47 344	99.92 105	99.21 292
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
thisisatest0530		97.45 336	96.95 347	98.94 301	99.68 164	97.73 340	99.09 220	94.19 416	98.61 268	99.56 199	99.30 317	84.30 405	99.93 99	98.27 202	99.54 295	99.16 305

Anonymous202405211		98.75 252	98.46 266	99.63 139	99.34 299	99.66 103	99.47 105	97.65 396	99.28 173	99.56 199	99.50 264	93.15 344	99.84 264	98.62 183	99.58 283	99.40 248

VDD-MVS		99.20 172	99.11 165	99.44 204	99.43 270	98.98 245	99.50 96	98.32 383	99.80 68	99.56 199	99.69 165	96.99 284	99.85 249	98.99 144	99.73 230	99.50 212

MDA-MVSNet_test_wron		98.95 231	98.99 209	98.85 316	99.64 176	97.16 357	98.23 335	99.33 299	98.93 225	99.56 199	99.66 185	97.39 267	99.83 279	98.29 200	99.88 135	99.55 181

EPP-MVSNet		99.17 184	99.00 202	99.66 119	99.80 86	99.43 165	99.70 35	99.24 321	99.48 136	99.56 199	99.77 119	94.89 325	99.93 99	98.72 175	99.89 126	99.63 134

test_part2					99.62 182	99.67 101				99.55 204

UnsupCasMVSNet_eth		98.83 244	98.57 256	99.59 156	99.68 164	99.45 159	98.99 248	99.67 152	99.48 136	99.55 204	99.36 303	94.92 324	99.86 231	98.95 154	96.57 413	99.45 230

CL-MVSNet_self_test		98.71 258	98.56 260	99.15 274	99.22 326	98.66 276	97.14 402	99.51 251	98.09 317	99.54 206	99.27 323	96.87 287	99.74 335	98.43 191	98.96 356	99.03 340

c3_l		98.72 256	98.71 243	98.72 328	99.12 344	97.22 356	97.68 380	99.56 220	98.90 229	99.54 206	99.48 271	96.37 304	99.73 338	97.88 238	99.88 135	99.21 292

MSP-MVS		99.04 210	98.79 239	99.81 41	99.78 105	99.73 78	99.35 128	99.57 215	98.54 275	99.54 206	98.99 364	96.81 288	99.93 99	96.97 312	99.53 297	99.77 63
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
APD-MVS		98.87 241	98.59 252	99.71 101	99.50 242	99.62 119	99.01 240	99.57 215	96.80 377	99.54 206	99.63 203	98.29 204	99.91 147	95.24 384	99.71 239	99.61 155
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TinyColmap		98.97 225	98.93 218	99.07 288	99.46 262	98.19 309	97.75 376	99.75 110	98.79 246	99.54 206	99.70 158	98.97 113	99.62 385	96.63 335	99.83 173	99.41 246

ACMMP_NAP		99.28 146	99.11 165	99.79 53	99.75 129	99.81 42	98.95 255	99.53 241	98.27 307	99.53 211	99.73 135	98.75 141	99.87 212	97.70 260	99.83 173	99.68 94

MSDG		99.08 200	98.98 212	99.37 228	99.60 185	99.13 227	97.54 385	99.74 116	98.84 239	99.53 211	99.55 253	99.10 90	99.79 314	97.07 308	99.86 155	99.18 301

WBMVS		97.50 335	97.18 341	98.48 340	98.85 379	95.89 385	98.44 321	99.52 246	99.53 129	99.52 213	99.42 285	80.10 411	99.86 231	99.24 110	99.95 81	99.68 94

SR-MVS-dyc-post		99.27 150	99.11 165	99.73 90	99.54 221	99.74 75	99.26 159	99.62 180	99.16 196	99.52 213	99.64 192	98.41 190	99.91 147	97.27 293	99.61 274	99.54 190

RE-MVS-def			99.13 158		99.54 221	99.74 75	99.26 159	99.62 180	99.16 196	99.52 213	99.64 192	98.57 165		97.27 293	99.61 274	99.54 190

miper_ehance_all_eth		98.59 270	98.59 252	98.59 335	98.98 367	97.07 360	97.49 390	99.52 246	98.50 279	99.52 213	99.37 299	96.41 302	99.71 344	97.86 242	99.62 267	99.00 347

OPM-MVS		99.26 152	99.13 158	99.63 139	99.70 152	99.61 125	98.58 299	99.48 260	98.50 279	99.52 213	99.63 203	99.14 86	99.76 328	97.89 237	99.77 213	99.51 207
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMMP		99.25 153	99.08 176	99.74 81	99.79 98	99.68 99	99.50 96	99.65 167	98.07 318	99.52 213	99.69 165	98.57 165	99.92 125	97.18 304	99.79 204	99.63 134
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
HPM-MVS_fast		99.43 109	99.30 130	99.80 46	99.83 65	99.81 42	99.52 89	99.70 137	98.35 298	99.51 219	99.50 264	99.31 64	99.88 198	98.18 213	99.84 165	99.69 88

EC-MVSNet		99.69 44	99.69 45	99.68 109	99.71 144	99.91 4	99.76 20	99.96 25	99.86 46	99.51 219	99.39 294	99.57 40	99.93 99	99.64 52	99.86 155	99.20 296

SPE-MVS-test		99.68 47	99.70 42	99.64 132	99.57 205	99.83 29	99.78 14	99.97 19	99.92 28	99.50 221	99.38 296	99.57 40	99.95 66	99.69 45	99.90 116	99.15 307

pmmvs3		98.08 313	97.80 322	98.91 307	99.41 277	97.69 342	97.87 372	99.66 157	95.87 387	99.50 221	99.51 261	90.35 379	99.97 35	98.55 186	99.47 308	99.08 329

RPSCF		99.18 179	99.02 195	99.64 132	99.83 65	99.85 19	99.44 111	99.82 73	98.33 303	99.50 221	99.78 110	97.90 236	99.65 381	96.78 324	99.83 173	99.44 235

MM		99.18 179	99.05 186	99.55 171	99.35 290	98.81 262	99.05 227	97.79 395	99.99 3	99.48 224	99.59 232	96.29 308	99.95 66	99.94 16	99.98 41	99.88 28

diffmvs		99.34 137	99.32 123	99.39 222	99.67 170	98.77 267	98.57 303	99.81 82	99.61 117	99.48 224	99.41 286	98.47 181	99.86 231	98.97 148	99.90 116	99.53 195
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		99.51 84	99.46 93	99.64 132	99.70 152	99.11 230	99.04 232	99.87 51	99.71 84	99.47 226	99.79 100	98.24 209	99.98 21	99.38 87	99.96 68	99.83 43

SR-MVS		99.19 175	99.00 202	99.74 81	99.51 236	99.72 83	99.18 183	99.60 198	98.85 236	99.47 226	99.58 235	98.38 195	99.92 125	96.92 314	99.54 295	99.57 176

VNet		99.18 179	99.06 182	99.56 168	99.24 323	99.36 187	99.33 133	99.31 305	99.67 98	99.47 226	99.57 242	96.48 297	99.84 264	99.15 126	99.30 330	99.47 225

ACMP	97.51 14	99.05 207	98.84 232	99.67 112	99.78 105	99.55 140	98.88 261	99.66 157	97.11 370	99.47 226	99.60 227	99.07 97	99.89 184	96.18 357	99.85 160	99.58 171
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
baseline1		97.73 325	97.33 336	98.96 298	99.30 310	97.73 340	99.40 115	98.42 376	99.33 167	99.46 230	99.21 337	91.18 364	99.82 289	98.35 196	91.26 421	99.32 268

Test_1112_low_res		98.95 231	98.73 241	99.63 139	99.68 164	99.15 226	98.09 348	99.80 85	97.14 368	99.46 230	99.40 290	96.11 311	99.89 184	99.01 143	99.84 165	99.84 39

MP-MVS-pluss		99.14 189	98.92 222	99.80 46	99.83 65	99.83 29	98.61 292	99.63 177	96.84 375	99.44 232	99.58 235	98.81 129	99.91 147	97.70 260	99.82 182	99.67 102
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MS-PatchMatch		99.00 221	98.97 213	99.09 283	99.11 349	98.19 309	98.76 282	99.33 299	98.49 281	99.44 232	99.58 235	98.21 214	99.69 353	98.20 209	99.62 267	99.39 250

OMC-MVS		98.90 236	98.72 242	99.44 204	99.39 279	99.42 168	98.58 299	99.64 175	97.31 360	99.44 232	99.62 210	98.59 162	99.69 353	96.17 358	99.79 204	99.22 289

OpenMVS_ROB	97.31 17	97.36 341	96.84 351	98.89 314	99.29 312	99.45 159	98.87 262	99.48 260	86.54 417	99.44 232	99.74 131	97.34 269	99.86 231	91.61 407	99.28 333	97.37 413

mmtdpeth		99.78 28	99.83 21	99.66 119	99.85 57	99.05 241	99.79 12	99.97 19	100.00 1	99.43 236	99.94 19	99.64 28	99.94 81	99.83 33	99.99 16	99.98 4

miper_enhance_ethall		98.03 315	97.94 315	98.32 349	98.27 410	96.43 373	96.95 406	99.41 277	96.37 382	99.43 236	98.96 371	94.74 327	99.69 353	97.71 257	99.62 267	98.83 366

1112_ss		99.05 207	98.84 232	99.67 112	99.66 171	99.29 199	98.52 311	99.82 73	97.65 342	99.43 236	99.16 341	96.42 300	99.91 147	99.07 139	99.84 165	99.80 50

SF-MVS		99.10 199	98.93 218	99.62 148	99.58 195	99.51 145	99.13 204	99.65 167	97.97 324	99.42 239	99.61 219	98.86 126	99.87 212	96.45 346	99.68 250	99.49 217

xiu_mvs_v2_base		99.02 213	99.11 165	98.77 325	99.37 284	98.09 319	98.13 343	99.51 251	99.47 140	99.42 239	98.54 395	99.38 56	99.97 35	98.83 160	99.33 326	98.24 398

MTAPA		99.35 132	99.20 148	99.80 46	99.81 80	99.81 42	99.33 133	99.53 241	99.27 174	99.42 239	99.63 203	98.21 214	99.95 66	97.83 248	99.79 204	99.65 119

PGM-MVS		99.20 172	99.01 198	99.77 59	99.75 129	99.71 85	99.16 194	99.72 129	97.99 322	99.42 239	99.60 227	98.81 129	99.93 99	96.91 315	99.74 224	99.66 111

114514_t		98.49 282	98.11 300	99.64 132	99.73 138	99.58 134	99.24 166	99.76 105	89.94 414	99.42 239	99.56 246	97.76 248	99.86 231	97.74 254	99.82 182	99.47 225

PMVS	92.94 21	98.82 245	98.81 236	98.85 316	99.84 61	97.99 325	99.20 176	99.47 263	99.71 84	99.42 239	99.82 80	98.09 223	99.47 406	93.88 403	99.85 160	99.07 334
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
cl22		97.56 333	97.28 337	98.40 344	98.37 408	96.75 367	97.24 400	99.37 292	97.31 360	99.41 245	99.22 335	87.30 390	99.37 410	97.70 260	99.62 267	99.08 329

PS-MVSNAJ		99.00 221	99.08 176	98.76 326	99.37 284	98.10 318	98.00 359	99.51 251	99.47 140	99.41 245	98.50 397	99.28 68	99.97 35	98.83 160	99.34 325	98.20 402

DSMNet-mixed		99.48 91	99.65 52	98.95 300	99.71 144	97.27 354	99.50 96	99.82 73	99.59 125	99.41 245	99.85 63	99.62 33	100.00 1	99.53 66	99.89 126	99.59 166

DELS-MVS		99.34 137	99.30 130	99.48 192	99.51 236	99.36 187	98.12 344	99.53 241	99.36 164	99.41 245	99.61 219	99.22 76	99.87 212	99.21 114	99.68 250	99.20 296
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
CSCG		99.37 127	99.29 135	99.60 154	99.71 144	99.46 154	99.43 113	99.85 60	98.79 246	99.41 245	99.60 227	98.92 119	99.92 125	98.02 224	99.92 105	99.43 241

MonoMVSNet		98.23 304	98.32 282	97.99 360	98.97 368	96.62 369	99.49 100	98.42 376	99.62 113	99.40 250	99.79 100	95.51 320	98.58 419	97.68 268	95.98 417	98.76 373

test_0402		99.22 165	99.14 156	99.45 200	99.79 98	99.43 165	99.28 153	99.68 147	99.54 127	99.40 250	99.56 246	99.07 97	99.82 289	96.01 362	99.96 68	99.11 316

LF4IMVS		99.01 219	98.92 222	99.27 256	99.71 144	99.28 201	98.59 297	99.77 100	98.32 304	99.39 252	99.41 286	98.62 158	99.84 264	96.62 336	99.84 165	98.69 375

VDDNet		98.97 225	98.82 235	99.42 210	99.71 144	98.81 262	99.62 64	98.68 360	99.81 65	99.38 253	99.80 90	94.25 332	99.85 249	98.79 166	99.32 328	99.59 166

sss		98.90 236	98.77 240	99.27 256	99.48 252	98.44 293	98.72 286	99.32 301	97.94 328	99.37 254	99.35 308	96.31 306	99.91 147	98.85 158	99.63 266	99.47 225

ttmdpeth		99.48 91	99.55 79	99.29 250	99.76 117	98.16 313	99.33 133	99.95 30	99.79 70	99.36 255	99.89 38	99.13 88	99.77 325	99.09 136	99.64 263	99.93 18

HFP-MVS		99.25 153	99.08 176	99.76 66	99.73 138	99.70 92	99.31 141	99.59 204	98.36 293	99.36 255	99.37 299	98.80 133	99.91 147	97.43 282	99.75 217	99.68 94

ACMMPR		99.23 157	99.06 182	99.76 66	99.74 135	99.69 96	99.31 141	99.59 204	98.36 293	99.35 257	99.38 296	98.61 160	99.93 99	97.43 282	99.75 217	99.67 102

mvsmamba		99.08 200	98.95 216	99.45 200	99.36 287	99.18 223	99.39 117	98.81 354	99.37 161	99.35 257	99.70 158	96.36 305	99.94 81	98.66 180	99.59 281	99.22 289

HPM-MVS		99.25 153	99.07 180	99.78 56	99.81 80	99.75 69	99.61 70	99.67 152	97.72 339	99.35 257	99.25 328	99.23 75	99.92 125	97.21 302	99.82 182	99.67 102
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
3Dnovator	99.15 2	99.43 109	99.36 114	99.65 125	99.39 279	99.42 168	99.70 35	99.56 220	99.23 182	99.35 257	99.80 90	99.17 81	99.95 66	98.21 208	99.84 165	99.59 166

PVSNet_BlendedMVS		99.03 211	99.01 198	99.09 283	99.54 221	97.99 325	98.58 299	99.82 73	97.62 343	99.34 261	99.71 150	98.52 177	99.77 325	97.98 229	99.97 55	99.52 205

PVSNet_Blended		98.70 259	98.59 252	99.02 293	99.54 221	97.99 325	97.58 384	99.82 73	95.70 391	99.34 261	98.98 367	98.52 177	99.77 325	97.98 229	99.83 173	99.30 274

FE-MVS		97.85 320	97.42 334	99.15 274	99.44 267	98.75 268	99.77 16	98.20 386	95.85 388	99.33 263	99.80 90	88.86 387	99.88 198	96.40 347	99.12 344	98.81 367

MIMVSNet		98.43 287	98.20 292	99.11 280	99.53 227	98.38 300	99.58 79	98.61 365	98.96 219	99.33 263	99.76 122	90.92 368	99.81 304	97.38 285	99.76 215	99.15 307

ITE_SJBPF				99.38 225	99.63 178	99.44 161		99.73 120	98.56 271	99.33 263	99.53 257	98.88 125	99.68 365	96.01 362	99.65 261	99.02 345

h-mvs33		98.61 264	98.34 280	99.44 204	99.60 185	98.67 273	99.27 157	99.44 271	99.68 94	99.32 266	99.49 268	92.50 353	100.00 1	99.24 110	96.51 414	99.65 119

hse-mvs2		98.52 277	98.30 285	99.16 272	99.29 312	98.60 284	98.77 281	99.02 345	99.68 94	99.32 266	99.04 357	92.50 353	99.85 249	99.24 110	97.87 404	99.03 340

GST-MVS		99.16 185	98.96 215	99.75 76	99.73 138	99.73 78	99.20 176	99.55 226	98.22 309	99.32 266	99.35 308	98.65 156	99.91 147	96.86 318	99.74 224	99.62 145

MVS_0304		98.61 264	98.30 285	99.52 179	97.88 418	98.95 250	98.76 282	94.11 417	99.84 55	99.32 266	99.57 242	95.57 319	99.95 66	99.68 47	99.98 41	99.68 94

region2R		99.23 157	99.05 186	99.77 59	99.76 117	99.70 92	99.31 141	99.59 204	98.41 287	99.32 266	99.36 303	98.73 145	99.93 99	97.29 290	99.74 224	99.67 102

test_one_0601					99.63 178	99.76 63		99.55 226	99.23 182	99.31 271	99.61 219	98.59 162

MVP-Stereo		99.16 185	99.08 176	99.43 208	99.48 252	99.07 238	99.08 223	99.55 226	98.63 264	99.31 271	99.68 176	98.19 217	99.78 317	98.18 213	99.58 283	99.45 230
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LFMVS		98.46 285	98.19 295	99.26 259	99.24 323	98.52 289	99.62 64	96.94 404	99.87 43	99.31 271	99.58 235	91.04 366	99.81 304	98.68 179	99.42 315	99.45 230

MVS_111021_LR		99.13 191	99.03 194	99.42 210	99.58 195	99.32 195	97.91 370	99.73 120	98.68 259	99.31 271	99.48 271	99.09 92	99.66 375	97.70 260	99.77 213	99.29 277

MVS-HIRNet		97.86 319	98.22 290	96.76 390	99.28 315	91.53 417	98.38 324	92.60 420	99.13 202	99.31 271	99.96 15	97.18 278	99.68 365	98.34 197	99.83 173	99.07 334

tmp_tt		95.75 379	95.42 373	96.76 390	89.90 428	94.42 400	98.86 263	97.87 394	78.01 419	99.30 276	99.69 165	97.70 249	95.89 421	99.29 106	98.14 397	99.95 13

9.14			98.64 247		99.45 266		98.81 273	99.60 198	97.52 349	99.28 277	99.56 246	98.53 174	99.83 279	95.36 383	99.64 263

CPTT-MVS		98.74 253	98.44 269	99.64 132	99.61 183	99.38 180	99.18 183	99.55 226	96.49 379	99.27 278	99.37 299	97.11 280	99.92 125	95.74 375	99.67 256	99.62 145

CLD-MVS		98.76 251	98.57 256	99.33 238	99.57 205	98.97 247	97.53 387	99.55 226	96.41 380	99.27 278	99.13 343	99.07 97	99.78 317	96.73 327	99.89 126	99.23 287
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CHOSEN 280x420		98.41 289	98.41 272	98.40 344	99.34 299	95.89 385	96.94 407	99.44 271	98.80 245	99.25 280	99.52 259	93.51 342	99.98 21	98.94 155	99.98 41	99.32 268

FMVSNet5		97.80 322	97.25 339	99.42 210	98.83 381	98.97 247	99.38 120	99.80 85	98.87 233	99.25 280	99.69 165	80.60 410	99.91 147	98.96 150	99.90 116	99.38 252

PHI-MVS		99.11 196	98.95 216	99.59 156	99.13 342	99.59 130	99.17 188	99.65 167	97.88 332	99.25 280	99.46 278	98.97 113	99.80 311	97.26 295	99.82 182	99.37 255

Vis-MVSNet (Re-imp)		98.77 250	98.58 255	99.34 235	99.78 105	98.88 258	99.61 70	99.56 220	99.11 206	99.24 283	99.56 246	93.00 348	99.78 317	97.43 282	99.89 126	99.35 261

CANet		99.11 196	99.05 186	99.28 253	98.83 381	98.56 286	98.71 288	99.41 277	99.25 178	99.23 284	99.22 335	97.66 257	99.94 81	99.19 118	99.97 55	99.33 265

Patchmatch-test		98.10 312	97.98 309	98.48 340	99.27 317	96.48 371	99.40 115	99.07 341	98.81 243	99.23 284	99.57 242	90.11 381	99.87 212	96.69 328	99.64 263	99.09 323

MG-MVS		98.52 277	98.39 274	98.94 301	99.15 339	97.39 352	98.18 337	99.21 328	98.89 232	99.23 284	99.63 203	97.37 268	99.74 335	94.22 397	99.61 274	99.69 88

test_yl		98.25 301	97.95 311	99.13 278	99.17 337	98.47 290	99.00 243	98.67 362	98.97 217	99.22 287	99.02 362	91.31 362	99.69 353	97.26 295	98.93 357	99.24 283

DCV-MVSNet		98.25 301	97.95 311	99.13 278	99.17 337	98.47 290	99.00 243	98.67 362	98.97 217	99.22 287	99.02 362	91.31 362	99.69 353	97.26 295	98.93 357	99.24 283

test0.0.03 1		97.37 340	96.91 350	98.74 327	97.72 419	97.57 344	97.60 383	97.36 402	98.00 320	99.21 289	98.02 405	90.04 382	99.79 314	98.37 194	95.89 418	98.86 363

MVS_Test		99.28 146	99.31 125	99.19 269	99.35 290	98.79 265	99.36 127	99.49 259	99.17 194	99.21 289	99.67 180	98.78 136	99.66 375	99.09 136	99.66 259	99.10 318

CDPH-MVS		98.56 273	98.20 292	99.61 151	99.50 242	99.46 154	98.32 328	99.41 277	95.22 396	99.21 289	99.10 351	98.34 200	99.82 289	95.09 388	99.66 259	99.56 178

WTY-MVS		98.59 270	98.37 276	99.26 259	99.43 270	98.40 296	98.74 284	99.13 339	98.10 315	99.21 289	99.24 333	94.82 326	99.90 165	97.86 242	98.77 368	99.49 217

MDTV_nov1_ep13_2view						91.44 418	99.14 198		97.37 357	99.21 289		91.78 360		96.75 325		99.03 340

BH-untuned		98.22 306	98.09 301	98.58 337	99.38 282	97.24 355	98.55 305	98.98 348	97.81 337	99.20 294	98.76 385	97.01 283	99.65 381	94.83 389	98.33 387	98.86 363

CR-MVSNet		98.35 296	98.20 292	98.83 320	99.05 357	98.12 315	99.30 144	99.67 152	97.39 356	99.16 295	99.79 100	91.87 358	99.91 147	98.78 170	98.77 368	98.44 391

RPMNet		98.60 267	98.53 262	98.83 320	99.05 357	98.12 315	99.30 144	99.62 180	99.86 46	99.16 295	99.74 131	92.53 352	99.92 125	98.75 172	98.77 368	98.44 391

thisisatest0515		96.98 348	96.42 355	98.66 331	99.42 275	97.47 347	97.27 398	94.30 415	97.24 362	99.15 297	98.86 379	85.01 402	99.87 212	97.10 306	99.39 318	98.63 376

LS3D		99.24 156	99.11 165	99.61 151	98.38 407	99.79 48	99.57 82	99.68 147	99.61 117	99.15 297	99.71 150	98.70 147	99.91 147	97.54 275	99.68 250	99.13 315

ZNCC-MVS		99.22 165	99.04 192	99.77 59	99.76 117	99.73 78	99.28 153	99.56 220	98.19 312	99.14 299	99.29 320	98.84 128	99.92 125	97.53 277	99.80 199	99.64 129

HQP_MVS		98.90 236	98.68 246	99.55 171	99.58 195	99.24 212	98.80 276	99.54 232	98.94 222	99.14 299	99.25 328	97.24 272	99.82 289	95.84 372	99.78 209	99.60 159

plane_prior3						99.31 196			98.36 293	99.14 299

3Dnovator+	98.92 3	99.35 132	99.24 145	99.67 112	99.35 290	99.47 150	99.62 64	99.50 255	99.44 148	99.12 302	99.78 110	98.77 138	99.94 81	97.87 241	99.72 236	99.62 145

ZD-MVS					99.43 270	99.61 125		99.43 274	96.38 381	99.11 303	99.07 353	97.86 239	99.92 125	94.04 400	99.49 306

PatchMatch-RL		98.68 261	98.47 265	99.30 249	99.44 267	99.28 201	98.14 342	99.54 232	97.12 369	99.11 303	99.25 328	97.80 244	99.70 347	96.51 340	99.30 330	98.93 354

SCA		98.11 311	98.36 277	97.36 380	99.20 331	92.99 408	98.17 339	98.49 373	98.24 308	99.10 305	99.57 242	96.01 313	99.94 81	96.86 318	99.62 267	99.14 312

PatchT		98.45 286	98.32 282	98.83 320	98.94 370	98.29 303	99.24 166	98.82 353	99.84 55	99.08 306	99.76 122	91.37 361	99.94 81	98.82 162	99.00 354	98.26 397

UnsupCasMVSNet_bld		98.55 274	98.27 288	99.40 219	99.56 216	99.37 183	97.97 364	99.68 147	97.49 351	99.08 306	99.35 308	95.41 322	99.82 289	97.70 260	98.19 394	99.01 346

MVS_111021_HR		99.12 193	99.02 195	99.40 219	99.50 242	99.11 230	97.92 368	99.71 132	98.76 253	99.08 306	99.47 275	99.17 81	99.54 398	97.85 244	99.76 215	99.54 190

TAPA-MVS	97.92 13	98.03 315	97.55 331	99.46 197	99.47 258	99.44 161	98.50 313	99.62 180	86.79 415	99.07 309	99.26 326	98.26 208	99.62 385	97.28 292	99.73 230	99.31 272
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CP-MVS		99.23 157	99.05 186	99.75 76	99.66 171	99.66 103	99.38 120	99.62 180	98.38 291	99.06 310	99.27 323	98.79 134	99.94 81	97.51 278	99.82 182	99.66 111

MCST-MVS		99.02 213	98.81 236	99.65 125	99.58 195	99.49 147	98.58 299	99.07 341	98.40 289	99.04 311	99.25 328	98.51 179	99.80 311	97.31 289	99.51 301	99.65 119

mPP-MVS		99.19 175	99.00 202	99.76 66	99.76 117	99.68 99	99.38 120	99.54 232	98.34 302	99.01 312	99.50 264	98.53 174	99.93 99	97.18 304	99.78 209	99.66 111

PVSNet	97.47 15	98.42 288	98.44 269	98.35 346	99.46 262	96.26 377	96.70 410	99.34 298	97.68 341	99.00 313	99.13 343	97.40 265	99.72 340	97.59 273	99.68 250	99.08 329

Fast-Effi-MVS+-dtu		99.20 172	99.12 162	99.43 208	99.25 321	99.69 96	99.05 227	99.82 73	99.50 133	98.97 314	99.05 355	98.98 111	99.98 21	98.20 209	99.24 339	98.62 377

MP-MVS		99.06 204	98.83 234	99.76 66	99.76 117	99.71 85	99.32 136	99.50 255	98.35 298	98.97 314	99.48 271	98.37 196	99.92 125	95.95 368	99.75 217	99.63 134
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PCF-MVS	96.03 18	96.73 354	95.86 366	99.33 238	99.44 267	99.16 224	96.87 408	99.44 271	86.58 416	98.95 316	99.40 290	94.38 331	99.88 198	87.93 414	99.80 199	98.95 351
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
旧先验2							97.94 366		95.33 395	98.94 317			99.88 198	96.75 325

ETV-MVS		99.18 179	99.18 150	99.16 272	99.34 299	99.28 201	99.12 208	99.79 91	99.48 136	98.93 318	98.55 394	99.40 51	99.93 99	98.51 188	99.52 300	98.28 396

BH-RMVSNet		98.41 289	98.14 298	99.21 266	99.21 328	98.47 290	98.60 294	98.26 384	98.35 298	98.93 318	99.31 315	97.20 277	99.66 375	94.32 395	99.10 346	99.51 207

F-COLMAP		98.74 253	98.45 268	99.62 148	99.57 205	99.47 150	98.84 266	99.65 167	96.31 383	98.93 318	99.19 340	97.68 252	99.87 212	96.52 339	99.37 321	99.53 195

Effi-MVS+-dtu		99.07 203	98.92 222	99.52 179	98.89 375	99.78 51	99.15 196	99.66 157	99.34 165	98.92 321	99.24 333	97.69 251	99.98 21	98.11 219	99.28 333	98.81 367

EMVS		96.96 349	97.28 337	95.99 400	98.76 392	91.03 419	95.26 417	98.61 365	99.34 165	98.92 321	98.88 378	93.79 337	99.66 375	92.87 404	99.05 350	97.30 414

tpmrst		97.73 325	98.07 303	96.73 392	98.71 396	92.00 412	99.10 216	98.86 350	98.52 277	98.92 321	99.54 255	91.90 356	99.82 289	98.02 224	99.03 352	98.37 393

MSLP-MVS++		99.05 207	99.09 174	98.91 307	99.21 328	98.36 301	98.82 272	99.47 263	98.85 236	98.90 324	99.56 246	98.78 136	99.09 413	98.57 185	99.68 250	99.26 280

KD-MVS_2432*1600		95.89 374	95.41 374	97.31 383	94.96 424	93.89 402	97.09 403	99.22 325	97.23 363	98.88 325	99.04 357	79.23 415	99.54 398	96.24 355	96.81 411	98.50 389

miper_refine_blended		95.89 374	95.41 374	97.31 383	94.96 424	93.89 402	97.09 403	99.22 325	97.23 363	98.88 325	99.04 357	79.23 415	99.54 398	96.24 355	96.81 411	98.50 389

E-PMN		97.14 346	97.43 333	96.27 397	98.79 387	91.62 416	95.54 415	99.01 347	99.44 148	98.88 325	99.12 347	92.78 349	99.68 365	94.30 396	99.03 352	97.50 410

testdata				99.42 210	99.51 236	98.93 254		99.30 308	96.20 384	98.87 328	99.40 290	98.33 202	99.89 184	96.29 352	99.28 333	99.44 235

CANet_DTU		98.91 234	98.85 230	99.09 283	98.79 387	98.13 314	98.18 337	99.31 305	99.48 136	98.86 329	99.51 261	96.56 294	99.95 66	99.05 140	99.95 81	99.19 299

DP-MVS Recon		98.50 280	98.23 289	99.31 246	99.49 247	99.46 154	98.56 304	99.63 177	94.86 402	98.85 330	99.37 299	97.81 243	99.59 392	96.08 359	99.44 311	98.88 361

EIA-MVS		99.12 193	99.01 198	99.45 200	99.36 287	99.62 119	99.34 129	99.79 91	98.41 287	98.84 331	98.89 377	98.75 141	99.84 264	98.15 217	99.51 301	98.89 360

DPM-MVS		98.28 299	97.94 315	99.32 243	99.36 287	99.11 230	97.31 397	98.78 356	96.88 373	98.84 331	99.11 350	97.77 246	99.61 390	94.03 401	99.36 322	99.23 287

MDTV_nov1_ep13			97.73 326		98.70 397	90.83 420	99.15 196	98.02 389	98.51 278	98.82 333	99.61 219	90.98 367	99.66 375	96.89 317	98.92 359

GA-MVS		97.99 318	97.68 328	98.93 304	99.52 234	98.04 323	97.19 401	99.05 344	98.32 304	98.81 334	98.97 369	89.89 384	99.41 409	98.33 198	99.05 350	99.34 264

AdaColmap		98.60 267	98.35 279	99.38 225	99.12 344	99.22 215	98.67 289	99.42 276	97.84 336	98.81 334	99.27 323	97.32 270	99.81 304	95.14 386	99.53 297	99.10 318

WB-MVSnew		98.34 298	98.14 298	98.96 298	98.14 416	97.90 333	98.27 331	97.26 403	98.63 264	98.80 336	98.00 407	97.77 246	99.90 165	97.37 286	98.98 355	99.09 323

CNVR-MVS		98.99 224	98.80 238	99.56 168	99.25 321	99.43 165	98.54 308	99.27 313	98.58 270	98.80 336	99.43 283	98.53 174	99.70 347	97.22 301	99.59 281	99.54 190

Effi-MVS+		99.06 204	98.97 213	99.34 235	99.31 306	98.98 245	98.31 329	99.91 38	98.81 243	98.79 338	98.94 373	99.14 86	99.84 264	98.79 166	98.74 372	99.20 296

PatchmatchNet		97.65 329	97.80 322	97.18 386	98.82 384	92.49 410	99.17 188	98.39 379	98.12 314	98.79 338	99.58 235	90.71 374	99.89 184	97.23 300	99.41 316	99.16 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
QAPM		98.40 291	97.99 307	99.65 125	99.39 279	99.47 150	99.67 50	99.52 246	91.70 411	98.78 340	99.80 90	98.55 168	99.95 66	94.71 392	99.75 217	99.53 195

XVS		99.27 150	99.11 165	99.75 76	99.71 144	99.71 85	99.37 124	99.61 187	99.29 170	98.76 341	99.47 275	98.47 181	99.88 198	97.62 269	99.73 230	99.67 102

X-MVStestdata		96.09 370	94.87 382	99.75 76	99.71 144	99.71 85	99.37 124	99.61 187	99.29 170	98.76 341	61.30 432	98.47 181	99.88 198	97.62 269	99.73 230	99.67 102

HY-MVS	98.23 9	98.21 308	97.95 311	98.99 295	99.03 361	98.24 304	99.61 70	98.72 358	96.81 376	98.73 343	99.51 261	94.06 333	99.86 231	96.91 315	98.20 392	98.86 363

dmvs_re		98.69 260	98.48 264	99.31 246	99.55 219	99.42 168	99.54 87	98.38 380	99.32 168	98.72 344	98.71 387	96.76 290	99.21 411	96.01 362	99.35 324	99.31 272

alignmvs		98.28 299	97.96 310	99.25 262	99.12 344	98.93 254	99.03 235	98.42 376	99.64 108	98.72 344	97.85 409	90.86 372	99.62 385	98.88 157	99.13 343	99.19 299

thres600view7		96.60 357	96.16 359	97.93 364	99.63 178	96.09 382	99.18 183	97.57 397	98.77 250	98.72 344	97.32 417	87.04 393	99.72 340	88.57 412	98.62 380	97.98 406

thres100view900		96.39 362	96.03 362	97.47 377	99.63 178	95.93 383	99.18 183	97.57 397	98.75 254	98.70 347	97.31 418	87.04 393	99.67 370	87.62 415	98.51 384	96.81 415

test222					99.51 236	99.08 237	97.83 374	99.29 309	95.21 397	98.68 348	99.31 315	97.28 271			99.38 319	99.43 241

API-MVS		98.38 292	98.39 274	98.35 346	98.83 381	99.26 205	99.14 198	99.18 332	98.59 269	98.66 349	98.78 384	98.61 160	99.57 394	94.14 398	99.56 286	96.21 417

sasdasda		99.02 213	99.00 202	99.09 283	99.10 351	98.70 271	99.61 70	99.66 157	99.63 110	98.64 350	97.65 412	99.04 103	99.54 398	98.79 166	98.92 359	99.04 338

canonicalmvs		99.02 213	99.00 202	99.09 283	99.10 351	98.70 271	99.61 70	99.66 157	99.63 110	98.64 350	97.65 412	99.04 103	99.54 398	98.79 166	98.92 359	99.04 338

Fast-Effi-MVS+		99.02 213	98.87 228	99.46 197	99.38 282	99.50 146	99.04 232	99.79 91	97.17 366	98.62 352	98.74 386	99.34 62	99.95 66	98.32 199	99.41 316	98.92 356

EPMVS		96.53 358	96.32 356	97.17 387	98.18 413	92.97 409	99.39 117	89.95 424	98.21 310	98.61 353	99.59 232	86.69 399	99.72 340	96.99 310	99.23 341	98.81 367

新几何1				99.52 179	99.50 242	99.22 215		99.26 315	95.66 392	98.60 354	99.28 321	97.67 253	99.89 184	95.95 368	99.32 328	99.45 230

HPM-MVS++		98.96 228	98.70 245	99.74 81	99.52 234	99.71 85	98.86 263	99.19 331	98.47 283	98.59 355	99.06 354	98.08 225	99.91 147	96.94 313	99.60 277	99.60 159

MGCFI-Net		99.02 213	99.01 198	99.06 290	99.11 349	98.60 284	99.63 61	99.67 152	99.63 110	98.58 356	97.65 412	99.07 97	99.57 394	98.85 158	98.92 359	99.03 340

PLC	97.35 16	98.36 293	97.99 307	99.48 192	99.32 305	99.24 212	98.50 313	99.51 251	95.19 398	98.58 356	98.96 371	96.95 285	99.83 279	95.63 376	99.25 337	99.37 255
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
UGNet		99.38 124	99.34 118	99.49 188	98.90 372	98.90 257	99.70 35	99.35 296	99.86 46	98.57 358	99.81 87	98.50 180	99.93 99	99.38 87	99.98 41	99.66 111
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
PAPM_NR		98.36 293	98.04 304	99.33 238	99.48 252	98.93 254	98.79 279	99.28 312	97.54 347	98.56 359	98.57 392	97.12 279	99.69 353	94.09 399	98.90 363	99.38 252

tfpn200view9		96.30 365	95.89 364	97.53 374	99.58 195	96.11 380	99.00 243	97.54 400	98.43 284	98.52 360	96.98 420	86.85 395	99.67 370	87.62 415	98.51 384	96.81 415

thres400		96.40 361	95.89 364	97.92 365	99.58 195	96.11 380	99.00 243	97.54 400	98.43 284	98.52 360	96.98 420	86.85 395	99.67 370	87.62 415	98.51 384	97.98 406

CNLPA		98.57 272	98.34 280	99.28 253	99.18 336	99.10 235	98.34 326	99.41 277	98.48 282	98.52 360	98.98 367	97.05 282	99.78 317	95.59 377	99.50 304	98.96 349

PMMVS		98.49 282	98.29 287	99.11 280	98.96 369	98.42 295	97.54 385	99.32 301	97.53 348	98.47 363	98.15 404	97.88 238	99.82 289	97.46 280	99.24 339	99.09 323

UWE-MVS		96.21 368	95.78 368	97.49 375	98.53 402	93.83 405	98.04 354	93.94 418	98.96 219	98.46 364	98.17 403	79.86 412	99.87 212	96.99 310	99.06 348	98.78 370

test12				99.54 176	99.29 312	99.33 193		99.16 335		98.43 365		97.54 260	99.82 289		99.47 308	99.48 221

NCCC		98.82 245	98.57 256	99.58 159	99.21 328	99.31 196	98.61 292	99.25 318	98.65 262	98.43 365	99.26 326	97.86 239	99.81 304	96.55 337	99.27 336	99.61 155

thres200		96.09 370	95.68 370	97.33 382	99.48 252	96.22 379	98.53 310	97.57 397	98.06 319	98.37 367	96.73 424	86.84 397	99.61 390	86.99 418	98.57 381	96.16 418

tpm		97.15 344	96.95 347	97.75 371	98.91 371	94.24 401	99.32 136	97.96 390	97.71 340	98.29 368	99.32 312	86.72 398	99.92 125	98.10 222	96.24 416	99.09 323

原ACMM1				99.37 228	99.47 258	98.87 260		99.27 313	96.74 378	98.26 369	99.32 312	97.93 235	99.82 289	95.96 367	99.38 319	99.43 241

ADS-MVSNet2		97.78 323	97.66 330	98.12 358	99.14 340	95.36 391	99.22 173	98.75 357	96.97 371	98.25 370	99.64 192	90.90 369	99.94 81	96.51 340	99.56 286	99.08 329

ADS-MVSNet		97.72 328	97.67 329	97.86 367	99.14 340	94.65 399	99.22 173	98.86 350	96.97 371	98.25 370	99.64 192	90.90 369	99.84 264	96.51 340	99.56 286	99.08 329

dp		96.86 350	97.07 343	96.24 398	98.68 398	90.30 424	99.19 182	98.38 380	97.35 358	98.23 372	99.59 232	87.23 391	99.82 289	96.27 353	98.73 375	98.59 380

TR-MVS		97.44 337	97.15 342	98.32 349	98.53 402	97.46 348	98.47 316	97.91 392	96.85 374	98.21 373	98.51 396	96.42 300	99.51 404	92.16 406	97.29 409	97.98 406

HQP-NCC					99.31 306		97.98 361		97.45 352	98.15 374

ACMP_Plane					99.31 306		97.98 361		97.45 352	98.15 374

HQP4-MVS										98.15 374			99.70 347			99.53 195

HQP-MVS		98.36 293	98.02 306	99.39 222	99.31 306	98.94 251	97.98 361	99.37 292	97.45 352	98.15 374	98.83 380	96.67 291	99.70 347	94.73 390	99.67 256	99.53 195

CostFormer		96.71 355	96.79 354	96.46 396	98.90 372	90.71 422	99.41 114	98.68 360	94.69 404	98.14 378	99.34 311	86.32 400	99.80 311	97.60 272	98.07 400	98.88 361

OpenMVS	98.12 10	98.23 304	97.89 320	99.26 259	99.19 333	99.26 205	99.65 59	99.69 144	91.33 412	98.14 378	99.77 119	98.28 205	99.96 56	95.41 381	99.55 290	98.58 382

test_prior2							97.95 365		97.87 333	98.05 380	99.05 355	97.90 236		95.99 365	99.49 306

MAR-MVS		98.24 303	97.92 317	99.19 269	98.78 389	99.65 109	99.17 188	99.14 337	95.36 394	98.04 381	98.81 383	97.47 262	99.72 340	95.47 380	99.06 348	98.21 400
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
PAPR		97.56 333	97.07 343	99.04 292	98.80 385	98.11 317	97.63 381	99.25 318	94.56 405	98.02 382	98.25 402	97.43 264	99.68 365	90.90 410	98.74 372	99.33 265

BH-w/o		97.20 343	97.01 345	97.76 370	99.08 355	95.69 387	98.03 356	98.52 370	95.76 390	97.96 383	98.02 405	95.62 317	99.47 406	92.82 405	97.25 410	98.12 404

TEST9					99.35 290	99.35 190	98.11 346	99.41 277	94.83 403	97.92 384	98.99 364	98.02 228	99.85 249

train_agg		98.35 296	97.95 311	99.57 165	99.35 290	99.35 190	98.11 346	99.41 277	94.90 400	97.92 384	98.99 364	98.02 228	99.85 249	95.38 382	99.44 311	99.50 212

tpm2		96.35 363	96.22 358	96.73 392	98.88 377	91.75 415	99.21 175	98.51 371	93.27 407	97.89 386	99.21 337	84.83 403	99.70 347	96.04 361	98.18 395	98.75 374

JIA-IIPM		98.06 314	97.92 317	98.50 339	98.59 400	97.02 361	98.80 276	98.51 371	99.88 42	97.89 386	99.87 52	91.89 357	99.90 165	98.16 216	97.68 406	98.59 380

test_8					99.34 299	99.31 196	98.08 350	99.40 284	94.90 400	97.87 388	98.97 369	98.02 228	99.84 264

tpmvs		97.39 339	97.69 327	96.52 394	98.41 406	91.76 414	99.30 144	98.94 349	97.74 338	97.85 389	99.55 253	92.40 355	99.73 338	96.25 354	98.73 375	98.06 405

testing3		96.48 360	95.63 371	99.01 294	99.23 325	97.81 336	98.90 259	99.10 340	98.72 255	97.84 390	97.92 408	72.44 424	99.85 249	97.21 302	99.33 326	99.35 261

test-LLR		97.15 344	96.95 347	97.74 372	98.18 413	95.02 396	97.38 393	96.10 406	98.00 320	97.81 391	98.58 390	90.04 382	99.91 147	97.69 266	98.78 366	98.31 394

TESTMET0.1,1		96.24 366	95.84 367	97.41 379	98.24 411	93.84 404	97.38 393	95.84 410	98.43 284	97.81 391	98.56 393	79.77 414	99.89 184	97.77 249	98.77 368	98.52 385

test-mter		96.23 367	95.73 369	97.74 372	98.18 413	95.02 396	97.38 393	96.10 406	97.90 329	97.81 391	98.58 390	79.12 417	99.91 147	97.69 266	98.78 366	98.31 394

agg_prior					99.35 290	99.36 187		99.39 287		97.76 394			99.85 249

tpm cat1		96.78 352	96.98 346	96.16 399	98.85 379	90.59 423	99.08 223	99.32 301	92.37 408	97.73 395	99.46 278	91.15 365	99.69 353	96.07 360	98.80 365	98.21 400

PVSNet_0	95.53 19	95.85 378	95.31 378	97.47 377	98.78 389	93.48 407	95.72 414	99.40 284	96.18 385	97.37 396	97.73 410	95.73 315	99.58 393	95.49 379	81.40 422	99.36 258

UBG		96.53 358	95.95 363	98.29 353	98.87 378	96.31 376	98.48 315	98.07 387	98.83 240	97.32 397	96.54 427	79.81 413	99.62 385	96.84 321	98.74 372	98.95 351

MVS		95.72 380	94.63 385	98.99 295	98.56 401	97.98 330	99.30 144	98.86 350	72.71 421	97.30 398	99.08 352	98.34 200	99.74 335	89.21 411	98.33 387	99.26 280

EPNet		98.13 310	97.77 325	99.18 271	94.57 426	97.99 325	99.24 166	97.96 390	99.74 77	97.29 399	99.62 210	93.13 345	99.97 35	98.59 184	99.83 173	99.58 171
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dmvs_testset		97.27 342	96.83 352	98.59 335	99.46 262	97.55 345	99.25 165	96.84 405	98.78 248	97.24 400	97.67 411	97.11 280	98.97 415	86.59 420	98.54 383	99.27 278

1314		98.00 317	97.90 319	98.27 354	98.90 372	97.45 349	99.30 144	99.06 343	94.98 399	97.21 401	99.12 347	98.43 187	99.67 370	95.58 378	98.56 382	97.71 409

ETVMVS		96.14 369	95.22 379	98.89 314	98.80 385	98.01 324	98.66 290	98.35 382	98.71 257	97.18 402	96.31 431	74.23 423	99.75 332	96.64 334	98.13 399	98.90 358

AUN-MVS		97.82 321	97.38 335	99.14 277	99.27 317	98.53 287	98.72 286	99.02 345	98.10 315	97.18 402	99.03 361	89.26 386	99.85 249	97.94 233	97.91 402	99.03 340

cascas		96.99 347	96.82 353	97.48 376	97.57 422	95.64 388	96.43 412	99.56 220	91.75 410	97.13 404	97.61 415	95.58 318	98.63 417	96.68 329	99.11 345	98.18 403

testing91		96.00 373	95.32 377	98.02 359	98.76 392	95.39 390	98.38 324	98.65 364	98.82 241	96.84 405	96.71 425	75.06 421	99.71 344	96.46 345	98.23 391	98.98 348

Syy-MVS		98.17 309	97.85 321	99.15 274	98.50 404	98.79 265	98.60 294	99.21 328	97.89 330	96.76 406	96.37 429	95.47 321	99.57 394	99.10 135	98.73 375	99.09 323

myMVS_eth3d		95.63 381	94.73 383	98.34 348	98.50 404	96.36 374	98.60 294	99.21 328	97.89 330	96.76 406	96.37 429	72.10 425	99.57 394	94.38 394	98.73 375	99.09 323

testing99		95.86 377	95.19 380	97.87 366	98.76 392	95.03 395	98.62 291	98.44 375	98.68 259	96.67 408	96.66 426	74.31 422	99.69 353	96.51 340	98.03 401	98.90 358

testing11		96.05 372	95.41 374	97.97 362	98.78 389	95.27 393	98.59 297	98.23 385	98.86 235	96.56 409	96.91 422	75.20 420	99.69 353	97.26 295	98.29 389	98.93 354

testing222		95.60 383	94.59 386	98.61 333	98.66 399	97.45 349	98.54 308	97.90 393	98.53 276	96.54 410	96.47 428	70.62 427	99.81 304	95.91 370	98.15 396	98.56 384

FPMVS		96.32 364	95.50 372	98.79 324	99.60 185	98.17 312	98.46 320	98.80 355	97.16 367	96.28 411	99.63 203	82.19 406	99.09 413	88.45 413	98.89 364	99.10 318

PAPM		95.61 382	94.71 384	98.31 351	99.12 344	96.63 368	96.66 411	98.46 374	90.77 413	96.25 412	98.68 389	93.01 347	99.69 353	81.60 421	97.86 405	98.62 377

gg-mvs-nofinetune		95.87 376	95.17 381	97.97 362	98.19 412	96.95 362	99.69 42	89.23 425	99.89 37	96.24 413	99.94 19	81.19 407	99.51 404	93.99 402	98.20 392	97.44 411

baseline2		96.83 351	96.28 357	98.46 342	99.09 354	96.91 364	98.83 268	93.87 419	97.23 363	96.23 414	98.36 399	88.12 389	99.90 165	96.68 329	98.14 397	98.57 383

EPNet_dtu		97.62 330	97.79 324	97.11 388	96.67 423	92.31 411	98.51 312	98.04 388	99.24 180	95.77 415	99.47 275	93.78 338	99.66 375	98.98 146	99.62 267	99.37 255
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepMVS_CX				97.98 361	99.69 156	96.95 362		99.26 315	75.51 420	95.74 416	98.28 401	96.47 298	99.62 385	91.23 409	97.89 403	97.38 412

test_method		91.72 386	92.32 389	89.91 404	93.49 427	70.18 430	90.28 418	99.56 220	61.71 422	95.39 417	99.52 259	93.90 334	99.94 81	98.76 171	98.27 390	99.62 145

IB-MVS	95.41 20	95.30 384	94.46 388	97.84 368	98.76 392	95.33 392	97.33 396	96.07 408	96.02 386	95.37 418	97.41 416	76.17 419	99.96 56	97.54 275	95.44 420	98.22 399
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
GG-mvs-BLEND				97.36 380	97.59 420	96.87 365	99.70 35	88.49 426		94.64 419	97.26 419	80.66 409	99.12 412	91.50 408	96.50 415	96.08 419

dongtai		89.37 387	88.91 390	90.76 403	99.19 333	77.46 428	95.47 416	87.82 427	92.28 409	94.17 420	98.82 382	71.22 426	95.54 422	63.85 422	97.34 408	99.27 278

ET-MVSNet_ETH3D		96.78 352	96.07 361	98.91 307	99.26 320	97.92 332	97.70 379	96.05 409	97.96 327	92.37 421	98.43 398	87.06 392	99.90 165	98.27 202	97.56 407	98.91 357

MVE	92.54 22	96.66 356	96.11 360	98.31 351	99.68 164	97.55 345	97.94 366	95.60 411	99.37 161	90.68 422	98.70 388	96.56 294	98.61 418	86.94 419	99.55 290	98.77 372
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		85.65 389	84.57 392	88.90 405	97.91 417	77.11 429	96.37 413	87.62 428	85.24 418	85.45 423	96.83 423	69.94 428	90.98 424	45.90 423	95.83 419	98.62 377

EGC-MVSNET		89.05 388	85.52 391	99.64 132	99.89 38	99.78 51	99.56 84	99.52 246	24.19 423	49.96 424	99.83 73	99.15 83	99.92 125	97.71 257	99.85 160	99.21 292

test123		29.31 390	33.05 395	18.08 406	25.93 430	12.24 431	97.53 387	10.93 431	11.78 424	24.21 425	50.08 436	21.04 429	8.60 425	23.51 424	32.43 424	33.39 421

testmvs		28.94 391	33.33 393	15.79 407	26.03 429	9.81 432	96.77 409	15.67 430	11.55 425	23.87 426	50.74 435	19.03 430	8.53 426	23.21 425	33.07 423	29.03 422

mmdepth		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		24.88 392	33.17 394	0.00 408	0.00 431	0.00 433	0.00 419	99.62 180	0.00 426	0.00 427	99.13 343	99.82 13	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		16.61 393	22.14 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	99.28 68	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		8.26 404	11.02 407	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	99.16 341	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		8.33 394	11.11 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	100.00 1	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						96.36 374								95.20 385

MSC_two_6792asdad				99.74 81	99.03 361	99.53 143		99.23 322					99.92 125	97.77 249	99.69 245	99.78 59

No_MVS				99.74 81	99.03 361	99.53 143		99.23 322					99.92 125	97.77 249	99.69 245	99.78 59

eth-test2					0.00 431

eth-test					0.00 431

OPU-MVS				99.29 250	99.12 344	99.44 161	99.20 176				99.40 290	99.00 107	98.84 416	96.54 338	99.60 277	99.58 171

save fliter					99.53 227	99.25 208	98.29 330	99.38 291	99.07 209

test_0728_SECOND				99.83 31	99.70 152	99.79 48	99.14 198	99.61 187					99.92 125	97.88 238	99.72 236	99.77 63

GSMVS																99.14 312

sam_mvs1												90.81 373				99.14 312

sam_mvs												90.52 378

MTGPA								99.53 241

test_post1							99.14 198				51.63 434	89.54 385	99.82 289	96.86 318

test_post											52.41 433	90.25 380	99.86 231

patchmatchnet-post											99.62 210	90.58 376	99.94 81

MTMP							99.09 220	98.59 368

gm-plane-assit					97.59 420	89.02 426			93.47 406		98.30 400		99.84 264	96.38 349

test9_res														95.10 387	99.44 311	99.50 212

agg_prior2														94.58 393	99.46 310	99.50 212

test_prior4						99.19 221	98.00 359

test_prior				99.46 197	99.35 290	99.22 215		99.39 287					99.69 353			99.48 221

新几何2							98.04 354

旧先验1					99.49 247	99.29 199		99.26 315			99.39 294	97.67 253			99.36 322	99.46 229

无先验							98.01 357	99.23 322	95.83 389				99.85 249	95.79 374		99.44 235

原ACMM2							97.92 368

testdata2													99.89 184	95.99 365

segment_acmp												98.37 196

testdata1							97.72 377		97.86 335

plane_prior7					99.58 195	99.38 180

plane_prior6					99.47 258	99.26 205						97.24 272

plane_prior5								99.54 232					99.82 289	95.84 372	99.78 209	99.60 159

plane_prior4											99.25 328

plane_prior2							98.80 276		98.94 222

plane_prior1					99.51 236

plane_prior						99.24 212	98.42 322		97.87 333						99.71 239

n2								0.00 432

nn								0.00 432

door-mid								99.83 68

test11								99.29 309

door								99.77 100

HQP5-MVS						98.94 251

BP-MVS														94.73 390

HQP3-MVS								99.37 292							99.67 256

HQP2-MVS												96.67 291

NP-MVS					99.40 278	99.13 227					98.83 380

ACMMP++_ref															99.94 94

ACMMP++															99.79 204

Test By Simon												98.41 190

High-resolution multi-view benchmark