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 61	99.79 32	99.36 253	99.94 18	98.18 332	99.52 92	100.00 1	99.86 62	100.00 1	99.88 50	98.99 122	99.96 64	99.97 4	99.96 82	99.95 14

test_vis3_rt		99.89 3	99.90 4	99.87 24	99.98 3	99.75 77	99.70 38	100.00 1	99.73 99	100.00 1	99.89 41	99.79 20	99.88 220	99.98 1	100.00 1	99.98 5

test_fmvs3		99.83 21	99.93 2	99.53 196	99.96 7	98.62 302	99.67 53	100.00 1	99.95 28	100.00 1	99.95 16	99.85 12	99.99 8	99.98 1	99.99 16	99.98 5

test_f		99.75 45	99.88 7	99.37 249	99.96 7	98.21 329	99.51 98	100.00 1	99.94 32	100.00 1	99.93 22	99.58 43	99.94 91	99.97 4	99.99 16	99.97 10

LCM-MVSNet		99.95 1	99.95 1	99.95 1	99.99 1	99.99 1	99.95 2	99.97 20	99.99 3	100.00 1	99.98 13	99.78 21	100.00 1	99.92 26	100.00 1	99.87 40

ANet_high		99.88 6	99.87 11	99.91 3	99.99 1	99.91 4	99.65 62	100.00 1	99.90 46	100.00 1	99.97 14	99.61 39	99.97 40	99.75 52	100.00 1	99.84 48

fmvsm_s_conf0.1_n_2		99.81 26	99.78 37	99.89 11	99.93 24	99.76 69	98.92 278	99.98 12	99.99 3	99.99 7	99.88 50	99.43 56	99.94 91	99.94 18	99.99 16	99.99 2

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 69	99.12 219	100.00 1	100.00 1	99.99 7	99.91 31	99.98 1	100.00 1	99.97 4	100.00 1	99.99 2

test_cas_vis1_n_1920		99.76 43	99.86 13	99.45 219	99.93 24	98.40 317	99.30 152	99.98 12	99.94 32	99.99 7	99.89 41	99.80 19	99.97 40	99.96 9	99.97 68	99.97 10

test_vis1_n_1920		99.72 50	99.88 7	99.27 277	99.93 24	97.84 355	99.34 135	100.00 1	99.99 3	99.99 7	99.82 87	99.87 11	99.99 8	99.97 4	99.99 16	99.97 10

test_fmvs1_n		99.68 61	99.81 27	99.28 274	99.95 15	97.93 352	99.49 104	100.00 1	99.82 80	99.99 7	99.89 41	99.21 88	99.98 26	99.97 4	99.98 46	99.93 20

test_fmvs2		99.72 50	99.85 17	99.34 256	99.91 31	98.08 343	99.48 106	100.00 1	99.90 46	99.99 7	99.91 31	99.50 54	99.98 26	99.98 1	99.99 16	99.96 13

mvsany_test3		99.85 12	99.88 7	99.75 91	99.95 15	99.37 199	99.53 91	99.98 12	99.77 97	99.99 7	99.95 16	99.85 12	99.94 91	99.95 13	99.98 46	99.94 17

fmvsm_s_conf0.5_n_8		99.76 43	99.72 52	99.88 18	99.82 81	99.75 77	99.02 251	99.87 61	99.98 15	99.98 14	99.81 94	99.07 108	99.97 40	99.91 29	99.99 16	99.92 24

fmvsm_s_conf0.5_n_2		99.78 35	99.75 49	99.88 18	99.82 81	99.76 69	98.88 281	99.92 40	99.98 15	99.98 14	99.85 68	99.42 58	99.94 91	99.93 22	99.98 46	99.94 17

MVStest1		98.22 328	98.09 323	98.62 354	99.04 383	96.23 400	99.20 185	99.92 40	99.44 171	99.98 14	99.87 56	85.87 423	99.67 392	99.91 29	99.57 307	99.95 14

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 42	99.10 227	99.98 12	99.99 3	99.98 14	99.91 31	99.68 31	99.93 111	99.93 22	99.99 16	99.99 2

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 56	99.07 239	99.98 12	99.99 3	99.98 14	99.90 36	99.88 10	99.92 139	99.93 22	99.99 16	99.98 5

test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 84	99.01 254	99.99 11	99.99 3	99.98 14	99.88 50	99.97 2	99.99 8	99.96 9	100.00 1	99.98 5

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 62	99.68 49	99.85 72	99.95 28	99.98 14	99.92 27	99.28 79	99.98 26	99.75 52	100.00 1	99.94 17

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 56	99.70 38	99.86 66	99.89 52	99.98 14	99.90 36	99.94 4	99.98 26	99.75 52	100.00 1	99.90 27

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 53	99.72 33	99.88 59	99.92 42	99.98 14	99.93 22	99.94 4	99.98 26	99.77 51	100.00 1	99.92 24

fmvsm_s_conf0.5_n_7		99.73 48	99.78 37	99.60 170	99.74 154	98.93 272	98.85 286	99.96 28	99.96 24	99.97 23	99.76 133	99.82 16	99.96 64	99.95 13	99.98 46	99.90 27

fmvsm_s_conf0.5_n_6		99.80 28	99.78 37	99.85 30	99.78 120	99.78 56	99.00 257	99.97 20	99.96 24	99.97 23	99.56 266	99.92 8	99.93 111	99.91 29	99.99 16	99.83 52

fmvsm_s_conf0.5_n_4		99.78 35	99.78 37	99.79 66	99.75 146	99.56 151	98.98 267	99.94 37	99.92 42	99.97 23	99.72 157	99.84 14	99.92 139	99.91 29	99.98 46	99.89 33

fmvsm_s_conf0.5_n_3		99.79 32	99.77 43	99.85 30	99.81 93	99.71 97	98.97 269	99.92 40	99.98 15	99.97 23	99.86 63	99.53 50	99.95 75	99.88 37	99.99 16	99.89 33

fmvsm_s_conf0.5_n_a		99.82 23	99.79 32	99.89 11	99.85 63	99.82 42	99.03 248	99.96 28	99.99 3	99.97 23	99.84 75	99.58 43	99.93 111	99.92 26	99.98 46	99.93 20

fmvsm_s_conf0.5_n		99.83 21	99.81 27	99.87 24	99.85 63	99.78 56	99.03 248	99.96 28	99.99 3	99.97 23	99.84 75	99.78 21	99.92 139	99.92 26	99.99 16	99.92 24

test_djsdf		99.84 17	99.81 27	99.91 3	99.94 18	99.84 27	99.77 19	99.80 98	99.73 99	99.97 23	99.92 27	99.77 23	99.98 26	99.43 98	100.00 1	99.90 27

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 18	99.91 31	99.90 7	99.96 1	99.92 40	99.90 46	99.97 23	99.87 56	99.81 18	99.95 75	99.54 83	99.99 16	99.80 60
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_s_conf0.5_n_5		99.78 35	99.76 47	99.85 30	99.79 112	99.72 92	98.84 288	99.96 28	99.96 24	99.96 31	99.72 157	99.71 26	99.99 8	99.93 22	99.98 46	99.85 45

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 45	99.86 19	99.08 235	99.97 20	99.98 15	99.96 31	99.79 108	99.90 9	99.99 8	99.96 9	99.99 16	99.90 27

fmvsm_l_conf0.5_n		99.80 28	99.78 37	99.85 30	99.88 45	99.66 116	99.11 224	99.91 47	99.98 15	99.96 31	99.64 210	99.60 41	99.99 8	99.95 13	99.99 16	99.88 36

test_fmvsmconf_n		99.85 12	99.84 20	99.88 18	99.91 31	99.73 87	98.97 269	99.98 12	99.99 3	99.96 31	99.85 68	99.93 7	99.99 8	99.94 18	99.99 16	99.93 20

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 50	99.88 45	99.55 155	99.17 198	99.98 12	99.99 3	99.96 31	99.84 75	99.96 3	99.99 8	99.96 9	99.99 16	99.88 36

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 38	99.82 81	99.70 105	99.17 198	99.97 20	99.99 3	99.96 31	99.82 87	99.94 4	100.00 1	99.95 13	100.00 1	99.80 60

test_fmvs1		99.48 108	99.65 65	98.97 318	99.54 243	97.16 378	99.11 224	99.98 12	99.78 93	99.96 31	99.81 94	98.72 160	99.97 40	99.95 13	99.97 68	99.79 68

dcpmvs_2		99.61 84	99.64 70	99.53 196	99.79 112	98.82 280	99.58 82	99.97 20	99.95 28	99.96 31	99.76 133	98.44 203	99.99 8	99.34 115	99.96 82	99.78 70

CHOSEN 1792x2688		99.39 139	99.30 147	99.65 141	99.88 45	99.25 224	98.78 303	99.88 59	98.66 286	99.96 31	99.79 108	97.45 280	99.93 111	99.34 115	99.99 16	99.78 70

wuyk23d		97.58 354	99.13 177	92.93 427	99.69 176	99.49 162	99.52 92	99.77 115	97.97 349	99.96 31	99.79 108	99.84 14	99.94 91	95.85 395	99.82 202	79.36 445

fmvsm_l_conf0.5_n_a		99.80 28	99.79 32	99.84 35	99.88 45	99.64 125	99.12 219	99.91 47	99.98 15	99.95 41	99.67 198	99.67 32	99.99 8	99.94 18	99.99 16	99.88 36

test_vis1_rt		99.45 121	99.46 110	99.41 237	99.71 164	98.63 301	98.99 264	99.96 28	99.03 236	99.95 41	99.12 369	98.75 155	99.84 286	99.82 46	99.82 202	99.77 74

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 149	99.93 39	99.95 41	99.89 41	99.71 26	99.96 64	99.51 88	99.97 68	99.84 48

tt0320-xc		99.82 23	99.82 25	99.82 43	99.82 81	99.84 27	99.82 10	99.92 40	99.94 32	99.94 44	99.93 22	99.34 71	99.92 139	99.70 57	99.96 82	99.70 99

tt0320		99.79 32	99.79 32	99.81 50	99.82 81	99.84 27	99.82 10	99.90 52	99.94 32	99.94 44	99.94 19	99.07 108	99.92 139	99.68 62	99.97 68	99.67 121

pmmvs6		99.86 10	99.86 13	99.83 38	99.94 18	99.90 7	99.83 7	99.91 47	99.85 68	99.94 44	99.95 16	99.73 25	99.90 186	99.65 67	99.97 68	99.69 106

v7n		99.82 23	99.80 30	99.88 18	99.96 7	99.84 27	99.82 10	99.82 85	99.84 72	99.94 44	99.91 31	99.13 99	99.96 64	99.83 42	99.99 16	99.83 52

Gipuma		99.57 87	99.59 82	99.49 207	99.98 3	99.71 97	99.72 33	99.84 78	99.81 85	99.94 44	99.78 120	98.91 135	99.71 366	98.41 215	99.95 98	99.05 359
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
VortexMVS		99.13 210	99.24 163	98.79 345	99.67 190	96.60 392	99.24 174	99.80 98	99.85 68	99.93 49	99.84 75	95.06 343	99.89 205	99.80 48	99.98 46	99.89 33

sc_t1		99.81 26	99.80 30	99.82 43	99.88 45	99.88 12	99.83 7	99.79 105	99.94 32	99.93 49	99.92 27	99.35 70	99.92 139	99.64 70	99.94 111	99.68 112

mamv4		99.73 48	99.74 50	99.70 121	99.66 192	99.87 15	99.69 45	99.93 38	99.93 39	99.93 49	99.86 63	99.07 108	100.00 1	99.66 65	99.92 125	99.24 305

v8		99.68 61	99.69 57	99.65 141	99.80 100	99.40 191	99.66 57	99.76 122	99.64 129	99.93 49	99.85 68	98.66 168	99.84 286	99.88 37	99.99 16	99.71 96

OurMVSNet-221017-0		99.75 45	99.71 53	99.84 35	99.96 7	99.83 34	99.83 7	99.85 72	99.80 89	99.93 49	99.93 22	98.54 187	99.93 111	99.59 75	99.98 46	99.76 79

MIMVSNet1		99.66 68	99.62 73	99.80 59	99.94 18	99.87 15	99.69 45	99.77 115	99.78 93	99.93 49	99.89 41	97.94 251	99.92 139	99.65 67	99.98 46	99.62 167

DeepC-MVS	98.90 4	99.62 82	99.61 77	99.67 128	99.72 161	99.44 177	99.24 174	99.71 149	99.27 197	99.93 49	99.90 36	99.70 29	99.93 111	98.99 165	99.99 16	99.64 150
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
mvsany_test1		99.44 123	99.45 112	99.40 240	99.37 306	98.64 300	97.90 396	99.59 222	99.27 197	99.92 56	99.82 87	99.74 24	99.93 111	99.55 82	99.87 167	99.63 156

anonymousdsp		99.80 28	99.77 43	99.90 8	99.96 7	99.88 12	99.73 30	99.85 72	99.70 110	99.92 56	99.93 22	99.45 55	99.97 40	99.36 111	100.00 1	99.85 45

v10		99.69 56	99.69 57	99.66 135	99.81 93	99.39 194	99.66 57	99.75 127	99.60 144	99.92 56	99.87 56	98.75 155	99.86 253	99.90 33	99.99 16	99.73 87

Elysia		99.69 56	99.65 65	99.81 50	99.86 57	99.72 92	99.34 135	99.77 115	99.94 32	99.91 59	99.76 133	98.55 183	99.99 8	99.70 57	99.98 46	99.72 91

StellarMVS		99.69 56	99.65 65	99.81 50	99.86 57	99.72 92	99.34 135	99.77 115	99.94 32	99.91 59	99.76 133	98.55 183	99.99 8	99.70 57	99.98 46	99.72 91

tt0805		99.63 76	99.57 89	99.81 50	99.87 54	99.88 12	99.58 82	98.70 379	99.72 103	99.91 59	99.60 247	99.43 56	99.81 326	99.81 47	99.53 319	99.73 87

LCM-MVSNet-Re		99.28 164	99.15 174	99.67 128	99.33 327	99.76 69	99.34 135	99.97 20	98.93 250	99.91 59	99.79 108	98.68 163	99.93 111	96.80 347	99.56 308	99.30 296

TransMVSNet (Re)		99.78 35	99.77 43	99.81 50	99.91 31	99.85 22	99.75 25	99.86 66	99.70 110	99.91 59	99.89 41	99.60 41	99.87 234	99.59 75	99.74 245	99.71 96

KinetiMVS		99.66 68	99.63 71	99.76 80	99.89 39	99.57 150	99.37 128	99.82 85	99.95 28	99.90 64	99.63 222	98.57 179	99.97 40	99.65 67	99.94 111	99.74 84

tfpnnormal		99.43 126	99.38 125	99.60 170	99.87 54	99.75 77	99.59 80	99.78 112	99.71 105	99.90 64	99.69 183	98.85 141	99.90 186	97.25 322	99.78 229	99.15 330

Anonymous20231211		99.62 82	99.57 89	99.76 80	99.61 205	99.60 141	99.81 13	99.73 137	99.82 80	99.90 64	99.90 36	97.97 250	99.86 253	99.42 103	99.96 82	99.80 60

v1240		99.56 90	99.58 85	99.51 201	99.80 100	99.00 259	99.00 257	99.65 185	99.15 223	99.90 64	99.75 141	99.09 103	99.88 220	99.90 33	99.96 82	99.67 121

EU-MVSNet		99.39 139	99.62 73	98.72 350	99.88 45	96.44 394	99.56 87	99.85 72	99.90 46	99.90 64	99.85 68	98.09 240	99.83 301	99.58 78	99.95 98	99.90 27

LuminaMVS		99.39 139	99.28 154	99.73 105	99.83 73	99.49 162	99.00 257	99.05 363	99.81 85	99.89 69	99.79 108	96.54 314	99.97 40	99.64 70	99.98 46	99.73 87

mvs5depth		99.88 6	99.91 3	99.80 59	99.92 29	99.42 184	99.94 3	100.00 1	99.97 21	99.89 69	99.99 12	99.63 35	99.97 40	99.87 40	99.99 16	100.00 1

SDMVSNet		99.77 42	99.77 43	99.76 80	99.80 100	99.65 122	99.63 64	99.86 66	99.97 21	99.89 69	99.89 41	99.52 52	99.99 8	99.42 103	99.96 82	99.65 140

sd_testset		99.78 35	99.78 37	99.80 59	99.80 100	99.76 69	99.80 14	99.79 105	99.97 21	99.89 69	99.89 41	99.53 50	99.99 8	99.36 111	99.96 82	99.65 140

IterMVS-SCA-FT		99.00 243	99.16 171	98.51 360	99.75 146	95.90 406	98.07 376	99.84 78	99.84 72	99.89 69	99.73 150	96.01 332	99.99 8	99.33 118	100.00 1	99.63 156

v144192		99.55 94	99.54 96	99.58 176	99.78 120	99.20 236	99.11 224	99.62 198	99.18 212	99.89 69	99.72 157	98.66 168	99.87 234	99.88 37	99.97 68	99.66 131

pm-mvs1		99.79 32	99.79 32	99.78 70	99.91 31	99.83 34	99.76 23	99.87 61	99.73 99	99.89 69	99.87 56	99.63 35	99.87 234	99.54 83	99.92 125	99.63 156

lessismore_v0				99.64 148	99.86 57	99.38 196		90.66 447		99.89 69	99.83 80	94.56 351	99.97 40	99.56 80	99.92 125	99.57 198

SixPastTwentyTwo		99.42 129	99.30 147	99.76 80	99.92 29	99.67 114	99.70 38	99.14 356	99.65 126	99.89 69	99.90 36	96.20 328	99.94 91	99.42 103	99.92 125	99.67 121

HyFIR lowres test		98.91 256	98.64 269	99.73 105	99.85 63	99.47 166	98.07 376	99.83 80	98.64 288	99.89 69	99.60 247	92.57 372	100.00 1	99.33 118	99.97 68	99.72 91

testf1		99.63 76	99.60 80	99.72 112	99.94 18	99.95 2	99.47 109	99.89 55	99.43 177	99.88 79	99.80 98	99.26 83	99.90 186	98.81 186	99.88 155	99.32 290

APD_test2		99.63 76	99.60 80	99.72 112	99.94 18	99.95 2	99.47 109	99.89 55	99.43 177	99.88 79	99.80 98	99.26 83	99.90 186	98.81 186	99.88 155	99.32 290

test1111		97.74 346	98.16 319	96.49 419	99.60 207	89.86 450	99.71 37	91.21 446	99.89 52	99.88 79	99.87 56	93.73 360	99.90 186	99.56 80	99.99 16	99.70 99

KD-MVS_self_test		99.63 76	99.59 82	99.76 80	99.84 68	99.90 7	99.37 128	99.79 105	99.83 78	99.88 79	99.85 68	98.42 206	99.90 186	99.60 74	99.73 251	99.49 239

new-patchmatchnet		99.35 150	99.57 89	98.71 352	99.82 81	96.62 390	98.55 329	99.75 127	99.50 155	99.88 79	99.87 56	99.31 75	99.88 220	99.43 98	100.00 1	99.62 167

v1921920		99.56 90	99.57 89	99.55 190	99.75 146	99.11 246	99.05 240	99.61 205	99.15 223	99.88 79	99.71 167	99.08 106	99.87 234	99.90 33	99.97 68	99.66 131

NR-MVSNet		99.40 135	99.31 142	99.68 125	99.43 292	99.55 155	99.73 30	99.50 273	99.46 166	99.88 79	99.36 325	97.54 277	99.87 234	98.97 169	99.87 167	99.63 156

K. test v3		98.87 263	98.60 272	99.69 123	99.93 24	99.46 170	99.74 27	94.97 437	99.78 93	99.88 79	99.88 50	93.66 361	99.97 40	99.61 73	99.95 98	99.64 150

AstraMVS		99.15 207	99.06 201	99.42 229	99.85 63	98.59 305	99.13 214	97.26 426	99.84 72	99.87 87	99.77 129	96.11 329	99.93 111	99.71 56	99.96 82	99.74 84

v1192		99.57 87	99.57 89	99.57 183	99.77 130	99.22 231	99.04 245	99.60 216	99.18 212	99.87 87	99.72 157	99.08 106	99.85 271	99.89 36	99.98 46	99.66 131

reproduce_monomvs		97.40 360	97.46 354	97.20 408	99.05 380	91.91 436	99.20 185	99.18 351	99.84 72	99.86 89	99.75 141	80.67 431	99.83 301	99.69 60	99.95 98	99.85 45

ECVR-MVS		97.73 347	98.04 326	96.78 412	99.59 212	90.81 445	99.72 33	90.43 448	99.89 52	99.86 89	99.86 63	93.60 362	99.89 205	99.46 94	99.99 16	99.65 140

V42		99.56 90	99.54 96	99.63 155	99.79 112	99.46 170	99.39 121	99.59 222	99.24 203	99.86 89	99.70 176	98.55 183	99.82 311	99.79 49	99.95 98	99.60 181

mvs_anonymous		99.28 164	99.39 123	98.94 322	99.19 356	97.81 357	99.02 251	99.55 244	99.78 93	99.85 92	99.80 98	98.24 226	99.86 253	99.57 79	99.50 326	99.15 330

WR-MVS_H		99.61 84	99.53 100	99.87 24	99.80 100	99.83 34	99.67 53	99.75 127	99.58 148	99.85 92	99.69 183	98.18 236	99.94 91	99.28 128	99.95 98	99.83 52

IterMVS		98.97 247	99.16 171	98.42 365	99.74 154	95.64 410	98.06 378	99.83 80	99.83 78	99.85 92	99.74 146	96.10 331	99.99 8	99.27 129	100.00 1	99.63 156
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
guyue		99.12 213	99.02 215	99.41 237	99.84 68	98.56 306	99.19 191	98.30 404	99.82 80	99.84 95	99.75 141	94.84 346	99.92 139	99.68 62	99.94 111	99.74 84

SSC-MVS3.2		99.64 75	99.67 61	99.56 186	99.75 146	98.98 262	98.96 272	99.87 61	99.88 57	99.84 95	99.64 210	99.32 74	99.91 167	99.78 50	99.96 82	99.80 60

v1144		99.54 97	99.53 100	99.59 173	99.79 112	99.28 217	99.10 227	99.61 205	99.20 210	99.84 95	99.73 150	98.67 166	99.84 286	99.86 41	99.98 46	99.64 150

PS-CasMVS		99.66 68	99.58 85	99.89 11	99.80 100	99.85 22	99.66 57	99.73 137	99.62 134	99.84 95	99.71 167	98.62 172	99.96 64	99.30 123	99.96 82	99.86 42

PEN-MVS		99.66 68	99.59 82	99.89 11	99.83 73	99.87 15	99.66 57	99.73 137	99.70 110	99.84 95	99.73 150	98.56 182	99.96 64	99.29 126	99.94 111	99.83 52

DTE-MVSNet		99.68 61	99.61 77	99.88 18	99.80 100	99.87 15	99.67 53	99.71 149	99.72 103	99.84 95	99.78 120	98.67 166	99.97 40	99.30 123	99.95 98	99.80 60

IterMVS-LS		99.41 133	99.47 106	99.25 283	99.81 93	98.09 340	98.85 286	99.76 122	99.62 134	99.83 101	99.64 210	98.54 187	99.97 40	99.15 147	99.99 16	99.68 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
Anonymous20240521		99.44 123	99.42 119	99.49 207	99.89 39	98.96 267	99.62 67	99.76 122	99.85 68	99.82 102	99.88 50	96.39 321	99.97 40	99.59 75	99.98 46	99.55 203

SED-MVS		99.40 135	99.28 154	99.77 73	99.69 176	99.82 42	99.20 185	99.54 250	99.13 225	99.82 102	99.63 222	98.91 135	99.92 139	97.85 267	99.70 262	99.58 193

test_241102_ONE					99.69 176	99.82 42		99.54 250	99.12 228	99.82 102	99.49 290	98.91 135	99.52 426

FC-MVSNet-test		99.70 54	99.65 65	99.86 28	99.88 45	99.86 19	99.72 33	99.78 112	99.90 46	99.82 102	99.83 80	98.45 202	99.87 234	99.51 88	99.97 68	99.86 42

test20.03		99.55 94	99.54 96	99.58 176	99.79 112	99.37 199	99.02 251	99.89 55	99.60 144	99.82 102	99.62 230	98.81 143	99.89 205	99.43 98	99.86 175	99.47 247

FMVSNet1		99.66 68	99.63 71	99.73 105	99.78 120	99.77 62	99.68 49	99.70 154	99.67 119	99.82 102	99.83 80	98.98 124	99.90 186	99.24 130	99.97 68	99.53 217

XXY-MVS		99.71 53	99.67 61	99.81 50	99.89 39	99.72 92	99.59 80	99.82 85	99.39 182	99.82 102	99.84 75	99.38 64	99.91 167	99.38 107	99.93 121	99.80 60

SSC-MVS		99.52 100	99.42 119	99.83 38	99.86 57	99.65 122	99.52 92	99.81 95	99.87 59	99.81 109	99.79 108	96.78 306	99.99 8	99.83 42	99.51 323	99.86 42

v148		99.40 135	99.41 121	99.39 243	99.76 134	98.94 269	99.09 232	99.59 222	99.17 217	99.81 109	99.61 239	98.41 207	99.69 375	99.32 120	99.94 111	99.53 217

v2v482		99.50 102	99.47 106	99.58 176	99.78 120	99.25 224	99.14 208	99.58 231	99.25 201	99.81 109	99.62 230	98.24 226	99.84 286	99.83 42	99.97 68	99.64 150

PM-MVS		99.36 148	99.29 152	99.58 176	99.83 73	99.66 116	98.95 274	99.86 66	98.85 261	99.81 109	99.73 150	98.40 211	99.92 139	98.36 218	99.83 193	99.17 326

reproduce_model		99.50 102	99.40 122	99.83 38	99.60 207	99.83 34	99.12 219	99.68 165	99.49 157	99.80 113	99.79 108	99.01 119	99.93 111	98.24 228	99.82 202	99.73 87

EI-MVSNet-UG-set		99.48 108	99.50 102	99.42 229	99.57 227	98.65 298	99.24 174	99.46 284	99.68 115	99.80 113	99.66 203	98.99 122	99.89 205	99.19 139	99.90 136	99.72 91

VPA-MVSNet		99.66 68	99.62 73	99.79 66	99.68 184	99.75 77	99.62 67	99.69 162	99.85 68	99.80 113	99.81 94	98.81 143	99.91 167	99.47 93	99.88 155	99.70 99

CP-MVSNet		99.54 97	99.43 117	99.87 24	99.76 134	99.82 42	99.57 85	99.61 205	99.54 149	99.80 113	99.64 210	97.79 262	99.95 75	99.21 135	99.94 111	99.84 48

EG-PatchMatch MVS		99.57 87	99.56 94	99.62 164	99.77 130	99.33 209	99.26 167	99.76 122	99.32 191	99.80 113	99.78 120	99.29 77	99.87 234	99.15 147	99.91 135	99.66 131

ACMH	98.42 6	99.59 86	99.54 96	99.72 112	99.86 57	99.62 132	99.56 87	99.79 105	98.77 275	99.80 113	99.85 68	99.64 33	99.85 271	98.70 198	99.89 146	99.70 99
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EI-MVSNet-Vis-set		99.47 116	99.49 104	99.42 229	99.57 227	98.66 295	99.24 174	99.46 284	99.67 119	99.79 119	99.65 208	98.97 126	99.89 205	99.15 147	99.89 146	99.71 96

casdiffmvs_mvg		99.68 61	99.68 60	99.69 123	99.81 93	99.59 143	99.29 159	99.90 52	99.71 105	99.79 119	99.73 150	99.54 48	99.84 286	99.36 111	99.96 82	99.65 140
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		99.40 135	99.38 125	99.44 223	99.90 37	98.66 295	98.94 276	99.91 47	97.97 349	99.79 119	99.73 150	99.05 115	99.97 40	99.15 147	99.99 16	99.68 112

N_pmnet		98.73 277	98.53 284	99.35 255	99.72 161	98.67 292	98.34 351	94.65 438	98.35 323	99.79 119	99.68 194	98.03 244	99.93 111	98.28 224	99.92 125	99.44 257

reproduce-ours		99.46 117	99.35 133	99.82 43	99.56 238	99.83 34	99.05 240	99.65 185	99.45 169	99.78 123	99.78 120	98.93 130	99.93 111	98.11 242	99.81 212	99.70 99

our_new_method		99.46 117	99.35 133	99.82 43	99.56 238	99.83 34	99.05 240	99.65 185	99.45 169	99.78 123	99.78 120	98.93 130	99.93 111	98.11 242	99.81 212	99.70 99

balanced_conf03		99.50 102	99.50 102	99.50 203	99.42 297	99.49 162	99.52 92	99.75 127	99.86 62	99.78 123	99.71 167	98.20 233	99.90 186	99.39 106	99.88 155	99.10 341

ppachtmachnet_test		98.89 261	99.12 181	98.20 377	99.66 192	95.24 417	97.63 406	99.68 165	99.08 230	99.78 123	99.62 230	98.65 170	99.88 220	98.02 247	99.96 82	99.48 243

nrg030		99.70 54	99.66 63	99.82 43	99.76 134	99.84 27	99.61 73	99.70 154	99.93 39	99.78 123	99.68 194	99.10 101	99.78 339	99.45 96	99.96 82	99.83 52

PMMVS2		99.48 108	99.45 112	99.57 183	99.76 134	98.99 261	98.09 373	99.90 52	98.95 246	99.78 123	99.58 255	99.57 45	99.93 111	99.48 92	99.95 98	99.79 68

TAMVS		99.49 106	99.45 112	99.63 155	99.48 274	99.42 184	99.45 113	99.57 233	99.66 123	99.78 123	99.83 80	97.85 258	99.86 253	99.44 97	99.96 82	99.61 177

TDRefinement		99.72 50	99.70 54	99.77 73	99.90 37	99.85 22	99.86 6	99.92 40	99.69 113	99.78 123	99.92 27	99.37 66	99.88 220	98.93 177	99.95 98	99.60 181

MVSMamba_PlusPlus		99.55 94	99.58 85	99.47 213	99.68 184	99.40 191	99.52 92	99.70 154	99.92 42	99.77 131	99.86 63	98.28 222	99.96 64	99.54 83	99.90 136	99.05 359

Vis-MVSNet		99.75 45	99.74 50	99.79 66	99.88 45	99.66 116	99.69 45	99.92 40	99.67 119	99.77 131	99.75 141	99.61 39	99.98 26	99.35 114	99.98 46	99.72 91
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ACMH+	98.40 8	99.50 102	99.43 117	99.71 117	99.86 57	99.76 69	99.32 144	99.77 115	99.53 151	99.77 131	99.76 133	99.26 83	99.78 339	97.77 272	99.88 155	99.60 181

DVP-MVS++		99.38 142	99.25 161	99.77 73	99.03 384	99.77 62	99.74 27	99.61 205	99.18 212	99.76 134	99.61 239	99.00 120	99.92 139	97.72 278	99.60 299	99.62 167

test_241102_TWO								99.54 250	99.13 225	99.76 134	99.63 222	98.32 220	99.92 139	97.85 267	99.69 266	99.75 82

Anonymous20240529		99.42 129	99.34 135	99.65 141	99.53 249	99.60 141	99.63 64	99.39 305	99.47 163	99.76 134	99.78 120	98.13 238	99.86 253	98.70 198	99.68 271	99.49 239

DPE-MVS		99.14 208	98.92 243	99.82 43	99.57 227	99.77 62	98.74 307	99.60 216	98.55 297	99.76 134	99.69 183	98.23 230	99.92 139	96.39 372	99.75 238	99.76 79
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
casdiffmvs		99.63 76	99.61 77	99.67 128	99.79 112	99.59 143	99.13 214	99.85 72	99.79 91	99.76 134	99.72 157	99.33 73	99.82 311	99.21 135	99.94 111	99.59 188
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
lecture		99.56 90	99.48 105	99.81 50	99.78 120	99.86 19	99.50 99	99.70 154	99.59 146	99.75 139	99.71 167	98.94 129	99.92 139	98.59 206	99.76 235	99.66 131

GeoE		99.69 56	99.66 63	99.78 70	99.76 134	99.76 69	99.60 79	99.82 85	99.46 166	99.75 139	99.56 266	99.63 35	99.95 75	99.43 98	99.88 155	99.62 167

pmmvs-eth3d		99.48 108	99.47 106	99.51 201	99.77 130	99.41 190	98.81 296	99.66 175	99.42 181	99.75 139	99.66 203	99.20 89	99.76 350	98.98 167	99.99 16	99.36 280

SD-MVS		99.01 240	99.30 147	98.15 378	99.50 264	99.40 191	98.94 276	99.61 205	99.22 209	99.75 139	99.82 87	99.54 48	95.51 448	97.48 302	99.87 167	99.54 212
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		99.48 108	99.36 131	99.85 30	99.55 241	99.81 47	99.50 99	99.69 162	98.99 239	99.75 139	99.71 167	98.79 148	99.93 111	98.46 213	99.85 180	99.80 60
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
EI-MVSNet		99.38 142	99.44 115	99.21 287	99.58 217	98.09 340	99.26 167	99.46 284	99.62 134	99.75 139	99.67 198	98.54 187	99.85 271	99.15 147	99.92 125	99.68 112

testgi		99.29 163	99.26 159	99.37 249	99.75 146	98.81 281	98.84 288	99.89 55	98.38 316	99.75 139	99.04 379	99.36 69	99.86 253	99.08 159	99.25 360	99.45 252

MVSTER		98.47 306	98.22 312	99.24 285	99.06 379	98.35 323	99.08 235	99.46 284	99.27 197	99.75 139	99.66 203	88.61 410	99.85 271	99.14 153	99.92 125	99.52 227

USDC		98.96 250	98.93 239	99.05 312	99.54 243	97.99 346	97.07 430	99.80 98	98.21 335	99.75 139	99.77 129	98.43 204	99.64 406	97.90 259	99.88 155	99.51 229

Patchmatch-RL test		98.60 289	98.36 299	99.33 259	99.77 130	99.07 255	98.27 356	99.87 61	98.91 253	99.74 148	99.72 157	90.57 399	99.79 336	98.55 209	99.85 180	99.11 339

FIs		99.65 74	99.58 85	99.84 35	99.84 68	99.85 22	99.66 57	99.75 127	99.86 62	99.74 148	99.79 108	98.27 224	99.85 271	99.37 110	99.93 121	99.83 52

jason		99.16 203	99.11 184	99.32 264	99.75 146	98.44 314	98.26 358	99.39 305	98.70 283	99.74 148	99.30 339	98.54 187	99.97 40	98.48 212	99.82 202	99.55 203
jason: jason.
DP-MVS		99.48 108	99.39 123	99.74 96	99.57 227	99.62 132	99.29 159	99.61 205	99.87 59	99.74 148	99.76 133	98.69 162	99.87 234	98.20 232	99.80 219	99.75 82

BP-MVS1		98.72 278	98.46 288	99.50 203	99.53 249	99.00 259	99.34 135	98.53 389	99.65 126	99.73 152	99.38 318	90.62 397	99.96 64	99.50 90	99.86 175	99.55 203

test0726					99.69 176	99.80 51	99.24 174	99.57 233	99.16 219	99.73 152	99.65 208	98.35 215

pmmvs5		99.19 193	99.11 184	99.42 229	99.76 134	98.88 277	98.55 329	99.73 137	98.82 266	99.72 154	99.62 230	96.56 311	99.82 311	99.32 120	99.95 98	99.56 200

Anonymous20231206		99.35 150	99.31 142	99.47 213	99.74 154	99.06 257	99.28 161	99.74 133	99.23 205	99.72 154	99.53 278	97.63 276	99.88 220	99.11 155	99.84 185	99.48 243

CVMVSNet		98.61 286	98.88 248	97.80 391	99.58 217	93.60 429	99.26 167	99.64 193	99.66 123	99.72 154	99.67 198	93.26 365	99.93 111	99.30 123	99.81 212	99.87 40

baseline		99.63 76	99.62 73	99.66 135	99.80 100	99.62 132	99.44 115	99.80 98	99.71 105	99.72 154	99.69 183	99.15 94	99.83 301	99.32 120	99.94 111	99.53 217

Patchmtry		98.78 271	98.54 283	99.49 207	98.89 398	99.19 237	99.32 144	99.67 170	99.65 126	99.72 154	99.79 108	91.87 380	99.95 75	98.00 251	99.97 68	99.33 287

WB-MVS		99.44 123	99.32 140	99.80 59	99.81 93	99.61 138	99.47 109	99.81 95	99.82 80	99.71 159	99.72 157	96.60 310	99.98 26	99.75 52	99.23 364	99.82 59

test2506		94.73 410	94.59 411	95.15 426	99.59 212	85.90 452	99.75 25	74.01 454	99.89 52	99.71 159	99.86 63	79.00 441	99.90 186	99.52 87	99.99 16	99.65 140

UA-Net		99.78 35	99.76 47	99.86 28	99.72 161	99.71 97	99.91 4	99.95 35	99.96 24	99.71 159	99.91 31	99.15 94	99.97 40	99.50 90	100.00 1	99.90 27

TranMVSNet+NR-MVSNet		99.54 97	99.47 106	99.76 80	99.58 217	99.64 125	99.30 152	99.63 195	99.61 138	99.71 159	99.56 266	98.76 153	99.96 64	99.14 153	99.92 125	99.68 112

tttt0517		97.62 352	97.20 362	98.90 334	99.76 134	97.40 372	99.48 106	94.36 439	99.06 234	99.70 163	99.49 290	84.55 426	99.94 91	98.73 196	99.65 282	99.36 280

UniMVSNet (Re)		99.37 145	99.26 159	99.68 125	99.51 258	99.58 147	98.98 267	99.60 216	99.43 177	99.70 163	99.36 325	97.70 266	99.88 220	99.20 138	99.87 167	99.59 188

FMVSNet2		99.35 150	99.28 154	99.55 190	99.49 269	99.35 206	99.45 113	99.57 233	99.44 171	99.70 163	99.74 146	97.21 291	99.87 234	99.03 162	99.94 111	99.44 257

APD_test1		99.36 148	99.28 154	99.61 167	99.89 39	99.89 10	99.32 144	99.74 133	99.18 212	99.69 166	99.75 141	98.41 207	99.84 286	97.85 267	99.70 262	99.10 341

IU-MVS					99.69 176	99.77 62		99.22 343	97.50 375	99.69 166				97.75 276	99.70 262	99.77 74

VPNet		99.46 117	99.37 128	99.71 117	99.82 81	99.59 143	99.48 106	99.70 154	99.81 85	99.69 166	99.58 255	97.66 274	99.86 253	99.17 144	99.44 333	99.67 121

SymmetryMVS		99.01 240	98.82 256	99.58 176	99.65 197	99.11 246	99.36 132	99.20 349	99.82 80	99.68 169	99.53 278	93.30 364	99.99 8	99.24 130	99.63 287	99.64 150

PC_three_1452									97.56 369	99.68 169	99.41 308	99.09 103	97.09 445	96.66 355	99.60 299	99.62 167

D2MVS		99.22 183	99.19 168	99.29 271	99.69 176	98.74 288	98.81 296	99.41 295	98.55 297	99.68 169	99.69 183	98.13 238	99.87 234	98.82 184	99.98 46	99.24 305

xiu_mvs_v1_base_debu		99.23 175	99.34 135	98.91 328	99.59 212	98.23 326	98.47 341	99.66 175	99.61 138	99.68 169	98.94 395	99.39 60	99.97 40	99.18 141	99.55 312	98.51 411

xiu_mvs_v1_base		99.23 175	99.34 135	98.91 328	99.59 212	98.23 326	98.47 341	99.66 175	99.61 138	99.68 169	98.94 395	99.39 60	99.97 40	99.18 141	99.55 312	98.51 411

xiu_mvs_v1_base_debi		99.23 175	99.34 135	98.91 328	99.59 212	98.23 326	98.47 341	99.66 175	99.61 138	99.68 169	98.94 395	99.39 60	99.97 40	99.18 141	99.55 312	98.51 411

ambc				99.20 289	99.35 313	98.53 308	99.17 198	99.46 284		99.67 175	99.80 98	98.46 201	99.70 369	97.92 257	99.70 262	99.38 274

RRT-MVS		99.08 221	99.00 223	99.33 259	99.27 340	98.65 298	99.62 67	99.93 38	99.66 123	99.67 175	99.82 87	95.27 342	99.93 111	98.64 204	99.09 370	99.41 268

UniMVSNet_NR-MVSNet		99.37 145	99.25 161	99.72 112	99.47 280	99.56 151	98.97 269	99.61 205	99.43 177	99.67 175	99.28 343	97.85 258	99.95 75	99.17 144	99.81 212	99.65 140

DU-MVS		99.33 158	99.21 166	99.71 117	99.43 292	99.56 151	98.83 291	99.53 259	99.38 183	99.67 175	99.36 325	97.67 270	99.95 75	99.17 144	99.81 212	99.63 156

COLMAP_ROB	98.06 12	99.45 121	99.37 128	99.70 121	99.83 73	99.70 105	99.38 124	99.78 112	99.53 151	99.67 175	99.78 120	99.19 90	99.86 253	97.32 311	99.87 167	99.55 203
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-OURS		99.21 188	99.06 201	99.65 141	99.82 81	99.62 132	97.87 397	99.74 133	98.36 318	99.66 180	99.68 194	99.71 26	99.90 186	96.84 345	99.88 155	99.43 263

DeepPCF-MVS	98.42 6	99.18 197	99.02 215	99.67 128	99.22 349	99.75 77	97.25 424	99.47 281	98.72 280	99.66 180	99.70 176	99.29 77	99.63 407	98.07 246	99.81 212	99.62 167

Baseline_NR-MVSNet		99.49 106	99.37 128	99.82 43	99.91 31	99.84 27	98.83 291	99.86 66	99.68 115	99.65 182	99.88 50	97.67 270	99.87 234	99.03 162	99.86 175	99.76 79

our_test_3		98.85 265	99.09 193	98.13 379	99.66 192	94.90 421	97.72 402	99.58 231	99.07 232	99.64 183	99.62 230	98.19 234	99.93 111	98.41 215	99.95 98	99.55 203

LPG-MVS_test		99.22 183	99.05 206	99.74 96	99.82 81	99.63 130	99.16 204	99.73 137	97.56 369	99.64 183	99.69 183	99.37 66	99.89 205	96.66 355	99.87 167	99.69 106

LGP-MVS_train				99.74 96	99.82 81	99.63 130		99.73 137	97.56 369	99.64 183	99.69 183	99.37 66	99.89 205	96.66 355	99.87 167	99.69 106

ACMM	98.09 11	99.46 117	99.38 125	99.72 112	99.80 100	99.69 109	99.13 214	99.65 185	98.99 239	99.64 183	99.72 157	99.39 60	99.86 253	98.23 229	99.81 212	99.60 181
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FA-MVS(test-final)		98.52 299	98.32 304	99.10 303	99.48 274	98.67 292	99.77 19	98.60 387	97.35 383	99.63 187	99.80 98	93.07 368	99.84 286	97.92 257	99.30 352	98.78 393

FOURS1					99.83 73	99.89 10	99.74 27	99.71 149	99.69 113	99.63 187

AllTest		99.21 188	99.07 199	99.63 155	99.78 120	99.64 125	99.12 219	99.83 80	98.63 289	99.63 187	99.72 157	98.68 163	99.75 354	96.38 373	99.83 193	99.51 229

TestCases				99.63 155	99.78 120	99.64 125		99.83 80	98.63 289	99.63 187	99.72 157	98.68 163	99.75 354	96.38 373	99.83 193	99.51 229

MDA-MVSNet-bldmvs		99.06 225	99.05 206	99.07 309	99.80 100	97.83 356	98.89 280	99.72 146	99.29 193	99.63 187	99.70 176	96.47 316	99.89 205	98.17 238	99.82 202	99.50 234

TSAR-MVS + GP.		99.12 213	99.04 212	99.38 246	99.34 322	99.16 240	98.15 365	99.29 327	98.18 338	99.63 187	99.62 230	99.18 91	99.68 387	98.20 232	99.74 245	99.30 296

XVG-OURS-SEG-HR		99.16 203	98.99 230	99.66 135	99.84 68	99.64 125	98.25 359	99.73 137	98.39 315	99.63 187	99.43 305	99.70 29	99.90 186	97.34 310	98.64 402	99.44 257

MVSFormer		99.41 133	99.44 115	99.31 267	99.57 227	98.40 317	99.77 19	99.80 98	99.73 99	99.63 187	99.30 339	98.02 245	99.98 26	99.43 98	99.69 266	99.55 203

lupinMVS		98.96 250	98.87 249	99.24 285	99.57 227	98.40 317	98.12 369	99.18 351	98.28 331	99.63 187	99.13 365	98.02 245	99.97 40	98.22 230	99.69 266	99.35 283

DVP-MVS		99.32 160	99.17 170	99.77 73	99.69 176	99.80 51	99.14 208	99.31 323	99.16 219	99.62 196	99.61 239	98.35 215	99.91 167	97.88 261	99.72 257	99.61 177
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									99.18 212	99.62 196	99.61 239	98.58 178	99.91 167	97.72 278	99.80 219	99.77 74

GBi-Net		99.42 129	99.31 142	99.73 105	99.49 269	99.77 62	99.68 49	99.70 154	99.44 171	99.62 196	99.83 80	97.21 291	99.90 186	98.96 171	99.90 136	99.53 217

test1		99.42 129	99.31 142	99.73 105	99.49 269	99.77 62	99.68 49	99.70 154	99.44 171	99.62 196	99.83 80	97.21 291	99.90 186	98.96 171	99.90 136	99.53 217

new_pmnet		98.88 262	98.89 247	98.84 339	99.70 172	97.62 364	98.15 365	99.50 273	97.98 348	99.62 196	99.54 276	98.15 237	99.94 91	97.55 297	99.84 185	98.95 374

FMVSNet3		98.80 270	98.63 271	99.32 264	99.13 365	98.72 289	99.10 227	99.48 278	99.23 205	99.62 196	99.64 210	92.57 372	99.86 253	98.96 171	99.90 136	99.39 272

CS-MVS		99.67 67	99.70 54	99.58 176	99.53 249	99.84 27	99.79 15	99.96 28	99.90 46	99.61 202	99.41 308	99.51 53	99.95 75	99.66 65	99.89 146	98.96 372

CDS-MVSNet		99.22 183	99.13 177	99.50 203	99.35 313	99.11 246	98.96 272	99.54 250	99.46 166	99.61 202	99.70 176	96.31 324	99.83 301	99.34 115	99.88 155	99.55 203
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
IS-MVSNet		99.03 232	98.85 251	99.55 190	99.80 100	99.25 224	99.73 30	99.15 355	99.37 184	99.61 202	99.71 167	94.73 349	99.81 326	97.70 283	99.88 155	99.58 193

cl____		98.54 297	98.41 294	98.92 326	99.03 384	97.80 359	97.46 416	99.59 222	98.90 254	99.60 205	99.46 300	93.85 357	99.78 339	97.97 254	99.89 146	99.17 326

DIV-MVS_self_test		98.54 297	98.42 293	98.92 326	99.03 384	97.80 359	97.46 416	99.59 222	98.90 254	99.60 205	99.46 300	93.87 356	99.78 339	97.97 254	99.89 146	99.18 323

XVG-ACMP-BASELINE		99.23 175	99.10 192	99.63 155	99.82 81	99.58 147	98.83 291	99.72 146	98.36 318	99.60 205	99.71 167	98.92 133	99.91 167	97.08 331	99.84 185	99.40 270

miper_lstm_enhance		98.65 285	98.60 272	98.82 344	99.20 354	97.33 374	97.78 400	99.66 175	99.01 238	99.59 208	99.50 286	94.62 350	99.85 271	98.12 241	99.90 136	99.26 302

YYNet1		98.95 253	98.99 230	98.84 339	99.64 198	97.14 380	98.22 361	99.32 319	98.92 252	99.59 208	99.66 203	97.40 282	99.83 301	98.27 225	99.90 136	99.55 203

eth_miper_zixun_eth		98.68 283	98.71 265	98.60 356	99.10 374	96.84 387	97.52 414	99.54 250	98.94 247	99.58 210	99.48 293	96.25 327	99.76 350	98.01 250	99.93 121	99.21 314

pmmvs4		99.13 210	99.06 201	99.36 253	99.57 227	99.10 252	98.01 382	99.25 336	98.78 273	99.58 210	99.44 304	98.24 226	99.76 350	98.74 195	99.93 121	99.22 311

DeepC-MVS_fast	98.47 5	99.23 175	99.12 181	99.56 186	99.28 338	99.22 231	98.99 264	99.40 302	99.08 230	99.58 210	99.64 210	98.90 138	99.83 301	97.44 304	99.75 238	99.63 156
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
GDP-MVS		98.81 269	98.57 278	99.50 203	99.53 249	99.12 245	99.28 161	99.86 66	99.53 151	99.57 213	99.32 334	90.88 393	99.98 26	99.46 94	99.74 245	99.42 267

SMA-MVS		99.19 193	99.00 223	99.73 105	99.46 284	99.73 87	99.13 214	99.52 264	97.40 380	99.57 213	99.64 210	98.93 130	99.83 301	97.61 294	99.79 224	99.63 156
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
TSAR-MVS + MP.		99.34 155	99.24 163	99.63 155	99.82 81	99.37 199	99.26 167	99.35 314	98.77 275	99.57 213	99.70 176	99.27 82	99.88 220	97.71 280	99.75 238	99.65 140
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		99.31 161	99.16 171	99.74 96	99.53 249	99.75 77	99.27 165	99.61 205	99.19 211	99.57 213	99.64 210	98.76 153	99.90 186	97.29 313	99.62 289	99.56 200

WR-MVS		99.11 217	98.93 239	99.66 135	99.30 333	99.42 184	98.42 347	99.37 310	99.04 235	99.57 213	99.20 361	96.89 303	99.86 253	98.66 202	99.87 167	99.70 99

SteuartSystems-ACMMP		99.30 162	99.14 175	99.76 80	99.87 54	99.66 116	99.18 193	99.60 216	98.55 297	99.57 213	99.67 198	99.03 118	99.94 91	97.01 333	99.80 219	99.69 106
Skip Steuart: Steuart Systems R&D Blog.
ab-mvs		99.33 158	99.28 154	99.47 213	99.57 227	99.39 194	99.78 17	99.43 292	98.87 258	99.57 213	99.82 87	98.06 243	99.87 234	98.69 200	99.73 251	99.15 330

CMPMVS	77.52 23	98.50 302	98.19 317	99.41 237	98.33 433	99.56 151	99.01 254	99.59 222	95.44 418	99.57 213	99.80 98	95.64 335	99.46 431	96.47 368	99.92 125	99.21 314
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
thisisatest0530		97.45 358	96.95 369	98.94 322	99.68 184	97.73 361	99.09 232	94.19 441	98.61 293	99.56 221	99.30 339	84.30 428	99.93 111	98.27 225	99.54 317	99.16 328

Anonymous202405211		98.75 274	98.46 288	99.63 155	99.34 322	99.66 116	99.47 109	97.65 419	99.28 196	99.56 221	99.50 286	93.15 366	99.84 286	98.62 205	99.58 305	99.40 270

VDD-MVS		99.20 190	99.11 184	99.44 223	99.43 292	98.98 262	99.50 99	98.32 403	99.80 89	99.56 221	99.69 183	96.99 301	99.85 271	98.99 165	99.73 251	99.50 234

MDA-MVSNet_test_wron		98.95 253	98.99 230	98.85 337	99.64 198	97.16 378	98.23 360	99.33 317	98.93 250	99.56 221	99.66 203	97.39 284	99.83 301	98.29 223	99.88 155	99.55 203

EPP-MVSNet		99.17 202	99.00 223	99.66 135	99.80 100	99.43 181	99.70 38	99.24 339	99.48 158	99.56 221	99.77 129	94.89 345	99.93 111	98.72 197	99.89 146	99.63 156

test_part2					99.62 204	99.67 114				99.55 226

UnsupCasMVSNet_eth		98.83 266	98.57 278	99.59 173	99.68 184	99.45 175	98.99 264	99.67 170	99.48 158	99.55 226	99.36 325	94.92 344	99.86 253	98.95 175	96.57 438	99.45 252

CL-MVSNet_self_test		98.71 280	98.56 282	99.15 295	99.22 349	98.66 295	97.14 427	99.51 269	98.09 342	99.54 228	99.27 345	96.87 304	99.74 357	98.43 214	98.96 379	99.03 363

c3_l		98.72 278	98.71 265	98.72 350	99.12 367	97.22 377	97.68 405	99.56 238	98.90 254	99.54 228	99.48 293	96.37 322	99.73 360	97.88 261	99.88 155	99.21 314

MSP-MVS		99.04 231	98.79 261	99.81 50	99.78 120	99.73 87	99.35 134	99.57 233	98.54 300	99.54 228	98.99 386	96.81 305	99.93 111	96.97 336	99.53 319	99.77 74
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		98.87 263	98.59 274	99.71 117	99.50 264	99.62 132	99.01 254	99.57 233	96.80 402	99.54 228	99.63 222	98.29 221	99.91 167	95.24 408	99.71 260	99.61 177
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
TinyColmap		98.97 247	98.93 239	99.07 309	99.46 284	98.19 330	97.75 401	99.75 127	98.79 271	99.54 228	99.70 176	98.97 126	99.62 408	96.63 359	99.83 193	99.41 268

ACMMP_NAP		99.28 164	99.11 184	99.79 66	99.75 146	99.81 47	98.95 274	99.53 259	98.27 332	99.53 233	99.73 150	98.75 155	99.87 234	97.70 283	99.83 193	99.68 112

MSDG		99.08 221	98.98 233	99.37 249	99.60 207	99.13 243	97.54 410	99.74 133	98.84 264	99.53 233	99.55 274	99.10 101	99.79 336	97.07 332	99.86 175	99.18 323

WBMVS		97.50 357	97.18 363	98.48 362	98.85 403	95.89 407	98.44 346	99.52 264	99.53 151	99.52 235	99.42 307	80.10 434	99.86 253	99.24 130	99.95 98	99.68 112

SR-MVS-dyc-post		99.27 168	99.11 184	99.73 105	99.54 243	99.74 84	99.26 167	99.62 198	99.16 219	99.52 235	99.64 210	98.41 207	99.91 167	97.27 316	99.61 296	99.54 212

RE-MVS-def			99.13 177		99.54 243	99.74 84	99.26 167	99.62 198	99.16 219	99.52 235	99.64 210	98.57 179		97.27 316	99.61 296	99.54 212

miper_ehance_all_eth		98.59 292	98.59 274	98.59 357	98.98 390	97.07 381	97.49 415	99.52 264	98.50 304	99.52 235	99.37 321	96.41 320	99.71 366	97.86 265	99.62 289	99.00 370

OPM-MVS		99.26 170	99.13 177	99.63 155	99.70 172	99.61 138	98.58 323	99.48 278	98.50 304	99.52 235	99.63 222	99.14 97	99.76 350	97.89 260	99.77 233	99.51 229
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMMP		99.25 171	99.08 195	99.74 96	99.79 112	99.68 112	99.50 99	99.65 185	98.07 343	99.52 235	99.69 183	98.57 179	99.92 139	97.18 327	99.79 224	99.63 156
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		99.43 126	99.30 147	99.80 59	99.83 73	99.81 47	99.52 92	99.70 154	98.35 323	99.51 241	99.50 286	99.31 75	99.88 220	98.18 236	99.84 185	99.69 106

EC-MVSNet		99.69 56	99.69 57	99.68 125	99.71 164	99.91 4	99.76 23	99.96 28	99.86 62	99.51 241	99.39 316	99.57 45	99.93 111	99.64 70	99.86 175	99.20 318

SPE-MVS-test		99.68 61	99.70 54	99.64 148	99.57 227	99.83 34	99.78 17	99.97 20	99.92 42	99.50 243	99.38 318	99.57 45	99.95 75	99.69 60	99.90 136	99.15 330

pmmvs3		98.08 335	97.80 344	98.91 328	99.41 299	97.69 363	97.87 397	99.66 175	95.87 412	99.50 243	99.51 283	90.35 401	99.97 40	98.55 209	99.47 330	99.08 352

RPSCF		99.18 197	99.02 215	99.64 148	99.83 73	99.85 22	99.44 115	99.82 85	98.33 328	99.50 243	99.78 120	97.90 253	99.65 404	96.78 348	99.83 193	99.44 257

MM		99.18 197	99.05 206	99.55 190	99.35 313	98.81 281	99.05 240	97.79 418	99.99 3	99.48 246	99.59 252	96.29 326	99.95 75	99.94 18	99.98 46	99.88 36

diffmvs		99.34 155	99.32 140	99.39 243	99.67 190	98.77 286	98.57 327	99.81 95	99.61 138	99.48 246	99.41 308	98.47 198	99.86 253	98.97 169	99.90 136	99.53 217
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
patch_mono-2		99.51 101	99.46 110	99.64 148	99.70 172	99.11 246	99.04 245	99.87 61	99.71 105	99.47 248	99.79 108	98.24 226	99.98 26	99.38 107	99.96 82	99.83 52

SR-MVS		99.19 193	99.00 223	99.74 96	99.51 258	99.72 92	99.18 193	99.60 216	98.85 261	99.47 248	99.58 255	98.38 212	99.92 139	96.92 338	99.54 317	99.57 198

VNet		99.18 197	99.06 201	99.56 186	99.24 346	99.36 203	99.33 141	99.31 323	99.67 119	99.47 248	99.57 262	96.48 315	99.84 286	99.15 147	99.30 352	99.47 247

ACMP	97.51 14	99.05 228	98.84 253	99.67 128	99.78 120	99.55 155	98.88 281	99.66 175	97.11 395	99.47 248	99.60 247	99.07 108	99.89 205	96.18 381	99.85 180	99.58 193
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
baseline1		97.73 347	97.33 358	98.96 319	99.30 333	97.73 361	99.40 119	98.42 396	99.33 190	99.46 252	99.21 359	91.18 386	99.82 311	98.35 219	91.26 446	99.32 290

Test_1112_low_res		98.95 253	98.73 263	99.63 155	99.68 184	99.15 242	98.09 373	99.80 98	97.14 393	99.46 252	99.40 312	96.11 329	99.89 205	99.01 164	99.84 185	99.84 48

MP-MVS-pluss		99.14 208	98.92 243	99.80 59	99.83 73	99.83 34	98.61 316	99.63 195	96.84 400	99.44 254	99.58 255	98.81 143	99.91 167	97.70 283	99.82 202	99.67 121
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MS-PatchMatch		99.00 243	98.97 234	99.09 304	99.11 372	98.19 330	98.76 305	99.33 317	98.49 306	99.44 254	99.58 255	98.21 231	99.69 375	98.20 232	99.62 289	99.39 272

OMC-MVS		98.90 258	98.72 264	99.44 223	99.39 301	99.42 184	98.58 323	99.64 193	97.31 385	99.44 254	99.62 230	98.59 176	99.69 375	96.17 382	99.79 224	99.22 311

OpenMVS_ROB	97.31 17	97.36 363	96.84 373	98.89 335	99.29 335	99.45 175	98.87 283	99.48 278	86.54 442	99.44 254	99.74 146	97.34 286	99.86 253	91.61 431	99.28 355	97.37 438

mmtdpeth		99.78 35	99.83 21	99.66 135	99.85 63	99.05 258	99.79 15	99.97 20	100.00 1	99.43 258	99.94 19	99.64 33	99.94 91	99.83 42	99.99 16	99.98 5

miper_enhance_ethall		98.03 337	97.94 337	98.32 371	98.27 434	96.43 395	96.95 431	99.41 295	96.37 407	99.43 258	98.96 393	94.74 348	99.69 375	97.71 280	99.62 289	98.83 389

1112_ss		99.05 228	98.84 253	99.67 128	99.66 192	99.29 215	98.52 335	99.82 85	97.65 367	99.43 258	99.16 363	96.42 318	99.91 167	99.07 160	99.84 185	99.80 60

SF-MVS		99.10 220	98.93 239	99.62 164	99.58 217	99.51 160	99.13 214	99.65 185	97.97 349	99.42 261	99.61 239	98.86 140	99.87 234	96.45 370	99.68 271	99.49 239

xiu_mvs_v2_base		99.02 234	99.11 184	98.77 347	99.37 306	98.09 340	98.13 368	99.51 269	99.47 163	99.42 261	98.54 418	99.38 64	99.97 40	98.83 182	99.33 348	98.24 423

MTAPA		99.35 150	99.20 167	99.80 59	99.81 93	99.81 47	99.33 141	99.53 259	99.27 197	99.42 261	99.63 222	98.21 231	99.95 75	97.83 271	99.79 224	99.65 140

PGM-MVS		99.20 190	99.01 219	99.77 73	99.75 146	99.71 97	99.16 204	99.72 146	97.99 347	99.42 261	99.60 247	98.81 143	99.93 111	96.91 339	99.74 245	99.66 131

114514_t		98.49 304	98.11 322	99.64 148	99.73 158	99.58 147	99.24 174	99.76 122	89.94 439	99.42 261	99.56 266	97.76 265	99.86 253	97.74 277	99.82 202	99.47 247

PMVS	92.94 21	98.82 267	98.81 258	98.85 337	99.84 68	97.99 346	99.20 185	99.47 281	99.71 105	99.42 261	99.82 87	98.09 240	99.47 429	93.88 427	99.85 180	99.07 357
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
cl22		97.56 355	97.28 359	98.40 366	98.37 432	96.75 388	97.24 425	99.37 310	97.31 385	99.41 267	99.22 357	87.30 412	99.37 433	97.70 283	99.62 289	99.08 352

PS-MVSNAJ		99.00 243	99.08 195	98.76 348	99.37 306	98.10 339	98.00 384	99.51 269	99.47 163	99.41 267	98.50 420	99.28 79	99.97 40	98.83 182	99.34 347	98.20 427

DSMNet-mixed		99.48 108	99.65 65	98.95 321	99.71 164	97.27 375	99.50 99	99.82 85	99.59 146	99.41 267	99.85 68	99.62 38	100.00 1	99.53 86	99.89 146	99.59 188

DELS-MVS		99.34 155	99.30 147	99.48 211	99.51 258	99.36 203	98.12 369	99.53 259	99.36 187	99.41 267	99.61 239	99.22 87	99.87 234	99.21 135	99.68 271	99.20 318
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		99.37 145	99.29 152	99.60 170	99.71 164	99.46 170	99.43 117	99.85 72	98.79 271	99.41 267	99.60 247	98.92 133	99.92 139	98.02 247	99.92 125	99.43 263

MonoMVSNet		98.23 326	98.32 304	97.99 382	98.97 391	96.62 390	99.49 104	98.42 396	99.62 134	99.40 272	99.79 108	95.51 339	98.58 444	97.68 291	95.98 442	98.76 396

test_0402		99.22 183	99.14 175	99.45 219	99.79 112	99.43 181	99.28 161	99.68 165	99.54 149	99.40 272	99.56 266	99.07 108	99.82 311	96.01 386	99.96 82	99.11 339

LF4IMVS		99.01 240	98.92 243	99.27 277	99.71 164	99.28 217	98.59 321	99.77 115	98.32 329	99.39 274	99.41 308	98.62 172	99.84 286	96.62 360	99.84 185	98.69 399

VDDNet		98.97 247	98.82 256	99.42 229	99.71 164	98.81 281	99.62 67	98.68 380	99.81 85	99.38 275	99.80 98	94.25 353	99.85 271	98.79 188	99.32 350	99.59 188

sss		98.90 258	98.77 262	99.27 277	99.48 274	98.44 314	98.72 309	99.32 319	97.94 353	99.37 276	99.35 330	96.31 324	99.91 167	98.85 180	99.63 287	99.47 247

ttmdpeth		99.48 108	99.55 95	99.29 271	99.76 134	98.16 334	99.33 141	99.95 35	99.79 91	99.36 277	99.89 41	99.13 99	99.77 347	99.09 157	99.64 284	99.93 20

HFP-MVS		99.25 171	99.08 195	99.76 80	99.73 158	99.70 105	99.31 149	99.59 222	98.36 318	99.36 277	99.37 321	98.80 147	99.91 167	97.43 305	99.75 238	99.68 112

ACMMPR		99.23 175	99.06 201	99.76 80	99.74 154	99.69 109	99.31 149	99.59 222	98.36 318	99.35 279	99.38 318	98.61 174	99.93 111	97.43 305	99.75 238	99.67 121

mvsmamba		99.08 221	98.95 237	99.45 219	99.36 309	99.18 239	99.39 121	98.81 374	99.37 184	99.35 279	99.70 176	96.36 323	99.94 91	98.66 202	99.59 303	99.22 311

HPM-MVS		99.25 171	99.07 199	99.78 70	99.81 93	99.75 77	99.61 73	99.67 170	97.72 364	99.35 279	99.25 350	99.23 86	99.92 139	97.21 325	99.82 202	99.67 121
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
3Dnovator	99.15 2	99.43 126	99.36 131	99.65 141	99.39 301	99.42 184	99.70 38	99.56 238	99.23 205	99.35 279	99.80 98	99.17 92	99.95 75	98.21 231	99.84 185	99.59 188

PVSNet_BlendedMVS		99.03 232	99.01 219	99.09 304	99.54 243	97.99 346	98.58 323	99.82 85	97.62 368	99.34 283	99.71 167	98.52 194	99.77 347	97.98 252	99.97 68	99.52 227

PVSNet_Blended		98.70 281	98.59 274	99.02 314	99.54 243	97.99 346	97.58 409	99.82 85	95.70 416	99.34 283	98.98 389	98.52 194	99.77 347	97.98 252	99.83 193	99.30 296

FE-MVS		97.85 342	97.42 356	99.15 295	99.44 289	98.75 287	99.77 19	98.20 407	95.85 413	99.33 285	99.80 98	88.86 409	99.88 220	96.40 371	99.12 367	98.81 390

MIMVSNet		98.43 309	98.20 314	99.11 301	99.53 249	98.38 321	99.58 82	98.61 385	98.96 243	99.33 285	99.76 133	90.92 390	99.81 326	97.38 308	99.76 235	99.15 330

ITE_SJBPF				99.38 246	99.63 200	99.44 177		99.73 137	98.56 296	99.33 285	99.53 278	98.88 139	99.68 387	96.01 386	99.65 282	99.02 368

h-mvs33		98.61 286	98.34 302	99.44 223	99.60 207	98.67 292	99.27 165	99.44 289	99.68 115	99.32 288	99.49 290	92.50 375	100.00 1	99.24 130	96.51 439	99.65 140

hse-mvs2		98.52 299	98.30 307	99.16 293	99.29 335	98.60 303	98.77 304	99.02 365	99.68 115	99.32 288	99.04 379	92.50 375	99.85 271	99.24 130	97.87 429	99.03 363

GST-MVS		99.16 203	98.96 236	99.75 91	99.73 158	99.73 87	99.20 185	99.55 244	98.22 334	99.32 288	99.35 330	98.65 170	99.91 167	96.86 342	99.74 245	99.62 167

MVS_0304		98.61 286	98.30 307	99.52 198	97.88 443	98.95 268	98.76 305	94.11 442	99.84 72	99.32 288	99.57 262	95.57 338	99.95 75	99.68 62	99.98 46	99.68 112

region2R		99.23 175	99.05 206	99.77 73	99.76 134	99.70 105	99.31 149	99.59 222	98.41 312	99.32 288	99.36 325	98.73 159	99.93 111	97.29 313	99.74 245	99.67 121

test_one_0601					99.63 200	99.76 69		99.55 244	99.23 205	99.31 293	99.61 239	98.59 176

MVP-Stereo		99.16 203	99.08 195	99.43 227	99.48 274	99.07 255	99.08 235	99.55 244	98.63 289	99.31 293	99.68 194	98.19 234	99.78 339	98.18 236	99.58 305	99.45 252
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LFMVS		98.46 307	98.19 317	99.26 280	99.24 346	98.52 310	99.62 67	96.94 428	99.87 59	99.31 293	99.58 255	91.04 388	99.81 326	98.68 201	99.42 337	99.45 252

MVS_111021_LR		99.13 210	99.03 214	99.42 229	99.58 217	99.32 211	97.91 395	99.73 137	98.68 284	99.31 293	99.48 293	99.09 103	99.66 397	97.70 283	99.77 233	99.29 299

MVS-HIRNet		97.86 341	98.22 312	96.76 413	99.28 338	91.53 440	98.38 349	92.60 445	99.13 225	99.31 293	99.96 15	97.18 295	99.68 387	98.34 220	99.83 193	99.07 357

tmp_tt		95.75 403	95.42 398	96.76 413	89.90 453	94.42 423	98.86 284	97.87 416	78.01 444	99.30 298	99.69 183	97.70 266	95.89 446	99.29 126	98.14 422	99.95 14

9.14			98.64 269		99.45 288		98.81 296	99.60 216	97.52 374	99.28 299	99.56 266	98.53 191	99.83 301	95.36 407	99.64 284

CPTT-MVS		98.74 275	98.44 291	99.64 148	99.61 205	99.38 196	99.18 193	99.55 244	96.49 404	99.27 300	99.37 321	97.11 297	99.92 139	95.74 399	99.67 277	99.62 167

CLD-MVS		98.76 273	98.57 278	99.33 259	99.57 227	98.97 265	97.53 412	99.55 244	96.41 405	99.27 300	99.13 365	99.07 108	99.78 339	96.73 351	99.89 146	99.23 309
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CHOSEN 280x420		98.41 311	98.41 294	98.40 366	99.34 322	95.89 407	96.94 432	99.44 289	98.80 270	99.25 302	99.52 281	93.51 363	99.98 26	98.94 176	99.98 46	99.32 290

FMVSNet5		97.80 344	97.25 361	99.42 229	98.83 405	98.97 265	99.38 124	99.80 98	98.87 258	99.25 302	99.69 183	80.60 433	99.91 167	98.96 171	99.90 136	99.38 274

PHI-MVS		99.11 217	98.95 237	99.59 173	99.13 365	99.59 143	99.17 198	99.65 185	97.88 357	99.25 302	99.46 300	98.97 126	99.80 333	97.26 318	99.82 202	99.37 277

Vis-MVSNet (Re-imp)		98.77 272	98.58 277	99.34 256	99.78 120	98.88 277	99.61 73	99.56 238	99.11 229	99.24 305	99.56 266	93.00 370	99.78 339	97.43 305	99.89 146	99.35 283

CANet		99.11 217	99.05 206	99.28 274	98.83 405	98.56 306	98.71 311	99.41 295	99.25 201	99.23 306	99.22 357	97.66 274	99.94 91	99.19 139	99.97 68	99.33 287

Patchmatch-test		98.10 334	97.98 331	98.48 362	99.27 340	96.48 393	99.40 119	99.07 360	98.81 268	99.23 306	99.57 262	90.11 403	99.87 234	96.69 352	99.64 284	99.09 346

MG-MVS		98.52 299	98.39 296	98.94 322	99.15 362	97.39 373	98.18 362	99.21 346	98.89 257	99.23 306	99.63 222	97.37 285	99.74 357	94.22 421	99.61 296	99.69 106

test_yl		98.25 323	97.95 333	99.13 299	99.17 360	98.47 311	99.00 257	98.67 382	98.97 241	99.22 309	99.02 384	91.31 384	99.69 375	97.26 318	98.93 380	99.24 305

DCV-MVSNet		98.25 323	97.95 333	99.13 299	99.17 360	98.47 311	99.00 257	98.67 382	98.97 241	99.22 309	99.02 384	91.31 384	99.69 375	97.26 318	98.93 380	99.24 305

test0.0.03 1		97.37 362	96.91 372	98.74 349	97.72 444	97.57 365	97.60 408	97.36 425	98.00 345	99.21 311	98.02 429	90.04 404	99.79 336	98.37 217	95.89 443	98.86 386

MVS_Test		99.28 164	99.31 142	99.19 290	99.35 313	98.79 284	99.36 132	99.49 277	99.17 217	99.21 311	99.67 198	98.78 150	99.66 397	99.09 157	99.66 280	99.10 341

CDPH-MVS		98.56 295	98.20 314	99.61 167	99.50 264	99.46 170	98.32 353	99.41 295	95.22 421	99.21 311	99.10 373	98.34 217	99.82 311	95.09 412	99.66 280	99.56 200

WTY-MVS		98.59 292	98.37 298	99.26 280	99.43 292	98.40 317	98.74 307	99.13 358	98.10 340	99.21 311	99.24 355	94.82 347	99.90 186	97.86 265	98.77 391	99.49 239

MDTV_nov1_ep13_2view						91.44 441	99.14 208		97.37 382	99.21 311		91.78 382		96.75 349		99.03 363

BH-untuned		98.22 328	98.09 323	98.58 359	99.38 304	97.24 376	98.55 329	98.98 368	97.81 362	99.20 316	98.76 407	97.01 300	99.65 404	94.83 413	98.33 412	98.86 386

CR-MVSNet		98.35 318	98.20 314	98.83 341	99.05 380	98.12 336	99.30 152	99.67 170	97.39 381	99.16 317	99.79 108	91.87 380	99.91 167	98.78 192	98.77 391	98.44 416

RPMNet		98.60 289	98.53 284	98.83 341	99.05 380	98.12 336	99.30 152	99.62 198	99.86 62	99.16 317	99.74 146	92.53 374	99.92 139	98.75 194	98.77 391	98.44 416

thisisatest0515		96.98 370	96.42 378	98.66 353	99.42 297	97.47 368	97.27 423	94.30 440	97.24 387	99.15 319	98.86 401	85.01 424	99.87 234	97.10 329	99.39 340	98.63 400

LS3D		99.24 174	99.11 184	99.61 167	98.38 431	99.79 53	99.57 85	99.68 165	99.61 138	99.15 319	99.71 167	98.70 161	99.91 167	97.54 298	99.68 271	99.13 338

ZNCC-MVS		99.22 183	99.04 212	99.77 73	99.76 134	99.73 87	99.28 161	99.56 238	98.19 337	99.14 321	99.29 342	98.84 142	99.92 139	97.53 300	99.80 219	99.64 150

HQP_MVS		98.90 258	98.68 268	99.55 190	99.58 217	99.24 228	98.80 299	99.54 250	98.94 247	99.14 321	99.25 350	97.24 289	99.82 311	95.84 396	99.78 229	99.60 181

plane_prior3						99.31 212			98.36 318	99.14 321

3Dnovator+	98.92 3	99.35 150	99.24 163	99.67 128	99.35 313	99.47 166	99.62 67	99.50 273	99.44 171	99.12 324	99.78 120	98.77 152	99.94 91	97.87 264	99.72 257	99.62 167

ZD-MVS					99.43 292	99.61 138		99.43 292	96.38 406	99.11 325	99.07 375	97.86 256	99.92 139	94.04 424	99.49 328

PatchMatch-RL		98.68 283	98.47 287	99.30 270	99.44 289	99.28 217	98.14 367	99.54 250	97.12 394	99.11 325	99.25 350	97.80 261	99.70 369	96.51 364	99.30 352	98.93 377

SCA		98.11 333	98.36 299	97.36 403	99.20 354	92.99 431	98.17 364	98.49 393	98.24 333	99.10 327	99.57 262	96.01 332	99.94 91	96.86 342	99.62 289	99.14 335

PatchT		98.45 308	98.32 304	98.83 341	98.94 393	98.29 324	99.24 174	98.82 373	99.84 72	99.08 328	99.76 133	91.37 383	99.94 91	98.82 184	99.00 377	98.26 422

UnsupCasMVSNet_bld		98.55 296	98.27 310	99.40 240	99.56 238	99.37 199	97.97 389	99.68 165	97.49 376	99.08 328	99.35 330	95.41 341	99.82 311	97.70 283	98.19 419	99.01 369

MVS_111021_HR		99.12 213	99.02 215	99.40 240	99.50 264	99.11 246	97.92 393	99.71 149	98.76 278	99.08 328	99.47 297	99.17 92	99.54 421	97.85 267	99.76 235	99.54 212

TAPA-MVS	97.92 13	98.03 337	97.55 353	99.46 216	99.47 280	99.44 177	98.50 337	99.62 198	86.79 440	99.07 331	99.26 348	98.26 225	99.62 408	97.28 315	99.73 251	99.31 294
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
CP-MVS		99.23 175	99.05 206	99.75 91	99.66 192	99.66 116	99.38 124	99.62 198	98.38 316	99.06 332	99.27 345	98.79 148	99.94 91	97.51 301	99.82 202	99.66 131

MCST-MVS		99.02 234	98.81 258	99.65 141	99.58 217	99.49 162	98.58 323	99.07 360	98.40 314	99.04 333	99.25 350	98.51 196	99.80 333	97.31 312	99.51 323	99.65 140

mPP-MVS		99.19 193	99.00 223	99.76 80	99.76 134	99.68 112	99.38 124	99.54 250	98.34 327	99.01 334	99.50 286	98.53 191	99.93 111	97.18 327	99.78 229	99.66 131

PVSNet	97.47 15	98.42 310	98.44 291	98.35 368	99.46 284	96.26 399	96.70 435	99.34 316	97.68 366	99.00 335	99.13 365	97.40 282	99.72 362	97.59 296	99.68 271	99.08 352

Fast-Effi-MVS+-dtu		99.20 190	99.12 181	99.43 227	99.25 344	99.69 109	99.05 240	99.82 85	99.50 155	98.97 336	99.05 377	98.98 124	99.98 26	98.20 232	99.24 362	98.62 401

MP-MVS		99.06 225	98.83 255	99.76 80	99.76 134	99.71 97	99.32 144	99.50 273	98.35 323	98.97 336	99.48 293	98.37 213	99.92 139	95.95 392	99.75 238	99.63 156
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PCF-MVS	96.03 18	96.73 376	95.86 389	99.33 259	99.44 289	99.16 240	96.87 433	99.44 289	86.58 441	98.95 338	99.40 312	94.38 352	99.88 220	87.93 439	99.80 219	98.95 374
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
旧先验2							97.94 391		95.33 420	98.94 339			99.88 220	96.75 349

ETV-MVS		99.18 197	99.18 169	99.16 293	99.34 322	99.28 217	99.12 219	99.79 105	99.48 158	98.93 340	98.55 417	99.40 59	99.93 111	98.51 211	99.52 322	98.28 421

BH-RMVSNet		98.41 311	98.14 320	99.21 287	99.21 351	98.47 311	98.60 318	98.26 405	98.35 323	98.93 340	99.31 337	97.20 294	99.66 397	94.32 419	99.10 369	99.51 229

F-COLMAP		98.74 275	98.45 290	99.62 164	99.57 227	99.47 166	98.84 288	99.65 185	96.31 408	98.93 340	99.19 362	97.68 269	99.87 234	96.52 363	99.37 343	99.53 217

Effi-MVS+-dtu		99.07 224	98.92 243	99.52 198	98.89 398	99.78 56	99.15 206	99.66 175	99.34 188	98.92 343	99.24 355	97.69 268	99.98 26	98.11 242	99.28 355	98.81 390

EMVS		96.96 371	97.28 359	95.99 425	98.76 416	91.03 443	95.26 442	98.61 385	99.34 188	98.92 343	98.88 400	93.79 358	99.66 397	92.87 428	99.05 373	97.30 439

tpmrst		97.73 347	98.07 325	96.73 416	98.71 420	92.00 435	99.10 227	98.86 370	98.52 302	98.92 343	99.54 276	91.90 378	99.82 311	98.02 247	99.03 375	98.37 418

MSLP-MVS++		99.05 228	99.09 193	98.91 328	99.21 351	98.36 322	98.82 295	99.47 281	98.85 261	98.90 346	99.56 266	98.78 150	99.09 437	98.57 208	99.68 271	99.26 302

KD-MVS_2432*1600		95.89 398	95.41 399	97.31 406	94.96 449	93.89 425	97.09 428	99.22 343	97.23 388	98.88 347	99.04 379	79.23 438	99.54 421	96.24 379	96.81 436	98.50 414

miper_refine_blended		95.89 398	95.41 399	97.31 406	94.96 449	93.89 425	97.09 428	99.22 343	97.23 388	98.88 347	99.04 379	79.23 438	99.54 421	96.24 379	96.81 436	98.50 414

E-PMN		97.14 368	97.43 355	96.27 421	98.79 411	91.62 439	95.54 440	99.01 367	99.44 171	98.88 347	99.12 369	92.78 371	99.68 387	94.30 420	99.03 375	97.50 435

testdata				99.42 229	99.51 258	98.93 272		99.30 326	96.20 409	98.87 350	99.40 312	98.33 219	99.89 205	96.29 376	99.28 355	99.44 257

CANet_DTU		98.91 256	98.85 251	99.09 304	98.79 411	98.13 335	98.18 362	99.31 323	99.48 158	98.86 351	99.51 283	96.56 311	99.95 75	99.05 161	99.95 98	99.19 321

DP-MVS Recon		98.50 302	98.23 311	99.31 267	99.49 269	99.46 170	98.56 328	99.63 195	94.86 427	98.85 352	99.37 321	97.81 260	99.59 415	96.08 383	99.44 333	98.88 384

EIA-MVS		99.12 213	99.01 219	99.45 219	99.36 309	99.62 132	99.34 135	99.79 105	98.41 312	98.84 353	98.89 399	98.75 155	99.84 286	98.15 240	99.51 323	98.89 383

DPM-MVS		98.28 321	97.94 337	99.32 264	99.36 309	99.11 246	97.31 422	98.78 376	96.88 398	98.84 353	99.11 372	97.77 263	99.61 413	94.03 425	99.36 344	99.23 309

MDTV_nov1_ep13			97.73 348		98.70 421	90.83 444	99.15 206	98.02 411	98.51 303	98.82 355	99.61 239	90.98 389	99.66 397	96.89 341	98.92 382

GA-MVS		97.99 340	97.68 350	98.93 325	99.52 256	98.04 344	97.19 426	99.05 363	98.32 329	98.81 356	98.97 391	89.89 406	99.41 432	98.33 221	99.05 373	99.34 286

AdaColmap		98.60 289	98.35 301	99.38 246	99.12 367	99.22 231	98.67 312	99.42 294	97.84 361	98.81 356	99.27 345	97.32 287	99.81 326	95.14 410	99.53 319	99.10 341

WB-MVSnew		98.34 320	98.14 320	98.96 319	98.14 440	97.90 354	98.27 356	97.26 426	98.63 289	98.80 358	98.00 431	97.77 263	99.90 186	97.37 309	98.98 378	99.09 346

CNVR-MVS		98.99 246	98.80 260	99.56 186	99.25 344	99.43 181	98.54 332	99.27 331	98.58 295	98.80 358	99.43 305	98.53 191	99.70 369	97.22 324	99.59 303	99.54 212

Effi-MVS+		99.06 225	98.97 234	99.34 256	99.31 329	98.98 262	98.31 354	99.91 47	98.81 268	98.79 360	98.94 395	99.14 97	99.84 286	98.79 188	98.74 395	99.20 318

PatchmatchNet		97.65 351	97.80 344	97.18 409	98.82 408	92.49 433	99.17 198	98.39 399	98.12 339	98.79 360	99.58 255	90.71 396	99.89 205	97.23 323	99.41 338	99.16 328
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
QAPM		98.40 313	97.99 329	99.65 141	99.39 301	99.47 166	99.67 53	99.52 264	91.70 436	98.78 362	99.80 98	98.55 183	99.95 75	94.71 416	99.75 238	99.53 217

XVS		99.27 168	99.11 184	99.75 91	99.71 164	99.71 97	99.37 128	99.61 205	99.29 193	98.76 363	99.47 297	98.47 198	99.88 220	97.62 292	99.73 251	99.67 121

X-MVStestdata		96.09 394	94.87 407	99.75 91	99.71 164	99.71 97	99.37 128	99.61 205	99.29 193	98.76 363	61.30 457	98.47 198	99.88 220	97.62 292	99.73 251	99.67 121

HY-MVS	98.23 9	98.21 330	97.95 333	98.99 316	99.03 384	98.24 325	99.61 73	98.72 378	96.81 401	98.73 365	99.51 283	94.06 354	99.86 253	96.91 339	98.20 417	98.86 386

dmvs_re		98.69 282	98.48 286	99.31 267	99.55 241	99.42 184	99.54 90	98.38 400	99.32 191	98.72 366	98.71 409	96.76 307	99.21 435	96.01 386	99.35 346	99.31 294

alignmvs		98.28 321	97.96 332	99.25 283	99.12 367	98.93 272	99.03 248	98.42 396	99.64 129	98.72 366	97.85 433	90.86 394	99.62 408	98.88 178	99.13 366	99.19 321

thres600view7		96.60 379	96.16 382	97.93 386	99.63 200	96.09 404	99.18 193	97.57 420	98.77 275	98.72 366	97.32 441	87.04 415	99.72 362	88.57 437	98.62 403	97.98 431

thres100view900		96.39 385	96.03 385	97.47 400	99.63 200	95.93 405	99.18 193	97.57 420	98.75 279	98.70 369	97.31 442	87.04 415	99.67 392	87.62 440	98.51 407	96.81 440

test222					99.51 258	99.08 254	97.83 399	99.29 327	95.21 422	98.68 370	99.31 337	97.28 288			99.38 341	99.43 263

API-MVS		98.38 314	98.39 296	98.35 368	98.83 405	99.26 221	99.14 208	99.18 351	98.59 294	98.66 371	98.78 406	98.61 174	99.57 417	94.14 422	99.56 308	96.21 442

sasdasda		99.02 234	99.00 223	99.09 304	99.10 374	98.70 290	99.61 73	99.66 175	99.63 131	98.64 372	97.65 436	99.04 116	99.54 421	98.79 188	98.92 382	99.04 361

canonicalmvs		99.02 234	99.00 223	99.09 304	99.10 374	98.70 290	99.61 73	99.66 175	99.63 131	98.64 372	97.65 436	99.04 116	99.54 421	98.79 188	98.92 382	99.04 361

Fast-Effi-MVS+		99.02 234	98.87 249	99.46 216	99.38 304	99.50 161	99.04 245	99.79 105	97.17 391	98.62 374	98.74 408	99.34 71	99.95 75	98.32 222	99.41 338	98.92 379

EPMVS		96.53 380	96.32 379	97.17 410	98.18 437	92.97 432	99.39 121	89.95 449	98.21 335	98.61 375	99.59 252	86.69 421	99.72 362	96.99 334	99.23 364	98.81 390

新几何1				99.52 198	99.50 264	99.22 231		99.26 333	95.66 417	98.60 376	99.28 343	97.67 270	99.89 205	95.95 392	99.32 350	99.45 252

HPM-MVS++		98.96 250	98.70 267	99.74 96	99.52 256	99.71 97	98.86 284	99.19 350	98.47 308	98.59 377	99.06 376	98.08 242	99.91 167	96.94 337	99.60 299	99.60 181

MGCFI-Net		99.02 234	99.01 219	99.06 311	99.11 372	98.60 303	99.63 64	99.67 170	99.63 131	98.58 378	97.65 436	99.07 108	99.57 417	98.85 180	98.92 382	99.03 363

PLC	97.35 16	98.36 315	97.99 329	99.48 211	99.32 328	99.24 228	98.50 337	99.51 269	95.19 423	98.58 378	98.96 393	96.95 302	99.83 301	95.63 400	99.25 360	99.37 277
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
testing3-2		96.51 382	96.43 377	96.74 415	99.36 309	91.38 442	99.10 227	97.87 416	99.48 158	98.57 380	98.71 409	76.65 443	99.66 397	98.87 179	99.26 359	99.18 323

UGNet		99.38 142	99.34 135	99.49 207	98.90 395	98.90 276	99.70 38	99.35 314	99.86 62	98.57 380	99.81 94	98.50 197	99.93 111	99.38 107	99.98 46	99.66 131
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		98.36 315	98.04 326	99.33 259	99.48 274	98.93 272	98.79 302	99.28 330	97.54 372	98.56 382	98.57 415	97.12 296	99.69 375	94.09 423	98.90 386	99.38 274

tfpn200view9		96.30 388	95.89 387	97.53 397	99.58 217	96.11 402	99.00 257	97.54 423	98.43 309	98.52 383	96.98 445	86.85 417	99.67 392	87.62 440	98.51 407	96.81 440

thres400		96.40 384	95.89 387	97.92 387	99.58 217	96.11 402	99.00 257	97.54 423	98.43 309	98.52 383	96.98 445	86.85 417	99.67 392	87.62 440	98.51 407	97.98 431

CNLPA		98.57 294	98.34 302	99.28 274	99.18 359	99.10 252	98.34 351	99.41 295	98.48 307	98.52 383	98.98 389	97.05 299	99.78 339	95.59 401	99.50 326	98.96 372

PMMVS		98.49 304	98.29 309	99.11 301	98.96 392	98.42 316	97.54 410	99.32 319	97.53 373	98.47 386	98.15 428	97.88 255	99.82 311	97.46 303	99.24 362	99.09 346

UWE-MVS		96.21 392	95.78 391	97.49 398	98.53 426	93.83 428	98.04 379	93.94 443	98.96 243	98.46 387	98.17 427	79.86 435	99.87 234	96.99 334	99.06 371	98.78 393

test12				99.54 195	99.29 335	99.33 209		99.16 354		98.43 388		97.54 277	99.82 311		99.47 330	99.48 243

NCCC		98.82 267	98.57 278	99.58 176	99.21 351	99.31 212	98.61 316	99.25 336	98.65 287	98.43 388	99.26 348	97.86 256	99.81 326	96.55 361	99.27 358	99.61 177

thres200		96.09 394	95.68 394	97.33 405	99.48 274	96.22 401	98.53 334	97.57 420	98.06 344	98.37 390	96.73 449	86.84 419	99.61 413	86.99 443	98.57 404	96.16 443

tpm		97.15 366	96.95 369	97.75 393	98.91 394	94.24 424	99.32 144	97.96 412	97.71 365	98.29 391	99.32 334	86.72 420	99.92 139	98.10 245	96.24 441	99.09 346

原ACMM1				99.37 249	99.47 280	98.87 279		99.27 331	96.74 403	98.26 392	99.32 334	97.93 252	99.82 311	95.96 391	99.38 341	99.43 263

ADS-MVSNet2		97.78 345	97.66 352	98.12 380	99.14 363	95.36 414	99.22 182	98.75 377	96.97 396	98.25 393	99.64 210	90.90 391	99.94 91	96.51 364	99.56 308	99.08 352

ADS-MVSNet		97.72 350	97.67 351	97.86 389	99.14 363	94.65 422	99.22 182	98.86 370	96.97 396	98.25 393	99.64 210	90.90 391	99.84 286	96.51 364	99.56 308	99.08 352

dp		96.86 372	97.07 365	96.24 422	98.68 422	90.30 449	99.19 191	98.38 400	97.35 383	98.23 395	99.59 252	87.23 413	99.82 311	96.27 377	98.73 398	98.59 404

TR-MVS		97.44 359	97.15 364	98.32 371	98.53 426	97.46 369	98.47 341	97.91 414	96.85 399	98.21 396	98.51 419	96.42 318	99.51 427	92.16 430	97.29 434	97.98 431

HQP-NCC					99.31 329		97.98 386		97.45 377	98.15 397

ACMP_Plane					99.31 329		97.98 386		97.45 377	98.15 397

HQP4-MVS										98.15 397			99.70 369			99.53 217

HQP-MVS		98.36 315	98.02 328	99.39 243	99.31 329	98.94 269	97.98 386	99.37 310	97.45 377	98.15 397	98.83 402	96.67 308	99.70 369	94.73 414	99.67 277	99.53 217

CostFormer		96.71 377	96.79 376	96.46 420	98.90 395	90.71 446	99.41 118	98.68 380	94.69 429	98.14 401	99.34 333	86.32 422	99.80 333	97.60 295	98.07 425	98.88 384

OpenMVS	98.12 10	98.23 326	97.89 342	99.26 280	99.19 356	99.26 221	99.65 62	99.69 162	91.33 437	98.14 401	99.77 129	98.28 222	99.96 64	95.41 405	99.55 312	98.58 406

test_prior2							97.95 390		97.87 358	98.05 403	99.05 377	97.90 253		95.99 389	99.49 328

MAR-MVS		98.24 325	97.92 339	99.19 290	98.78 413	99.65 122	99.17 198	99.14 356	95.36 419	98.04 404	98.81 405	97.47 279	99.72 362	95.47 404	99.06 371	98.21 425
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
UWE-MVS-28		95.64 405	95.47 397	96.14 424	97.98 441	90.39 448	98.49 339	95.81 435	99.02 237	98.03 405	98.19 426	84.49 427	99.28 434	88.75 436	98.47 410	98.75 397

PAPR		97.56 355	97.07 365	99.04 313	98.80 409	98.11 338	97.63 406	99.25 336	94.56 430	98.02 406	98.25 425	97.43 281	99.68 387	90.90 434	98.74 395	99.33 287

BH-w/o		97.20 365	97.01 367	97.76 392	99.08 378	95.69 409	98.03 381	98.52 390	95.76 415	97.96 407	98.02 429	95.62 336	99.47 429	92.82 429	97.25 435	98.12 429

TEST9					99.35 313	99.35 206	98.11 371	99.41 295	94.83 428	97.92 408	98.99 386	98.02 245	99.85 271

train_agg		98.35 318	97.95 333	99.57 183	99.35 313	99.35 206	98.11 371	99.41 295	94.90 425	97.92 408	98.99 386	98.02 245	99.85 271	95.38 406	99.44 333	99.50 234

tpm2		96.35 386	96.22 381	96.73 416	98.88 400	91.75 438	99.21 184	98.51 391	93.27 432	97.89 410	99.21 359	84.83 425	99.70 369	96.04 385	98.18 420	98.75 397

JIA-IIPM		98.06 336	97.92 339	98.50 361	98.59 424	97.02 382	98.80 299	98.51 391	99.88 57	97.89 410	99.87 56	91.89 379	99.90 186	98.16 239	97.68 431	98.59 404

test_8					99.34 322	99.31 212	98.08 375	99.40 302	94.90 425	97.87 412	98.97 391	98.02 245	99.84 286

tpmvs		97.39 361	97.69 349	96.52 418	98.41 430	91.76 437	99.30 152	98.94 369	97.74 363	97.85 413	99.55 274	92.40 377	99.73 360	96.25 378	98.73 398	98.06 430

testing3		96.48 383	95.63 395	99.01 315	99.23 348	97.81 357	98.90 279	99.10 359	98.72 280	97.84 414	97.92 432	72.44 449	99.85 271	97.21 325	99.33 348	99.35 283

test-LLR		97.15 366	96.95 369	97.74 394	98.18 437	95.02 419	97.38 418	96.10 430	98.00 345	97.81 415	98.58 413	90.04 404	99.91 167	97.69 289	98.78 389	98.31 419

TESTMET0.1,1		96.24 389	95.84 390	97.41 402	98.24 435	93.84 427	97.38 418	95.84 434	98.43 309	97.81 415	98.56 416	79.77 437	99.89 205	97.77 272	98.77 391	98.52 410

test-mter		96.23 390	95.73 393	97.74 394	98.18 437	95.02 419	97.38 418	96.10 430	97.90 354	97.81 415	98.58 413	79.12 440	99.91 167	97.69 289	98.78 389	98.31 419

agg_prior					99.35 313	99.36 203		99.39 305		97.76 418			99.85 271

tpm cat1		96.78 374	96.98 368	96.16 423	98.85 403	90.59 447	99.08 235	99.32 319	92.37 433	97.73 419	99.46 300	91.15 387	99.69 375	96.07 384	98.80 388	98.21 425

myMVS_eth3d28		96.23 390	95.74 392	97.70 396	98.86 402	95.59 412	98.66 313	98.14 408	98.96 243	97.67 420	97.06 444	76.78 442	98.92 440	97.10 329	98.41 411	98.58 406

PVSNet_0	95.53 19	95.85 402	95.31 403	97.47 400	98.78 413	93.48 430	95.72 439	99.40 302	96.18 410	97.37 421	97.73 434	95.73 334	99.58 416	95.49 403	81.40 447	99.36 280

UBG		96.53 380	95.95 386	98.29 375	98.87 401	96.31 398	98.48 340	98.07 409	98.83 265	97.32 422	96.54 452	79.81 436	99.62 408	96.84 345	98.74 395	98.95 374

MVS		95.72 404	94.63 410	98.99 316	98.56 425	97.98 351	99.30 152	98.86 370	72.71 446	97.30 423	99.08 374	98.34 217	99.74 357	89.21 435	98.33 412	99.26 302

EPNet		98.13 332	97.77 347	99.18 292	94.57 451	97.99 346	99.24 174	97.96 412	99.74 98	97.29 424	99.62 230	93.13 367	99.97 40	98.59 206	99.83 193	99.58 193
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dmvs_testset		97.27 364	96.83 374	98.59 357	99.46 284	97.55 366	99.25 173	96.84 429	98.78 273	97.24 425	97.67 435	97.11 297	98.97 439	86.59 445	98.54 406	99.27 300

1314		98.00 339	97.90 341	98.27 376	98.90 395	97.45 370	99.30 152	99.06 362	94.98 424	97.21 426	99.12 369	98.43 204	99.67 392	95.58 402	98.56 405	97.71 434

ETVMVS		96.14 393	95.22 404	98.89 335	98.80 409	98.01 345	98.66 313	98.35 402	98.71 282	97.18 427	96.31 456	74.23 448	99.75 354	96.64 358	98.13 424	98.90 381

AUN-MVS		97.82 343	97.38 357	99.14 298	99.27 340	98.53 308	98.72 309	99.02 365	98.10 340	97.18 427	99.03 383	89.26 408	99.85 271	97.94 256	97.91 427	99.03 363

cascas		96.99 369	96.82 375	97.48 399	97.57 447	95.64 410	96.43 437	99.56 238	91.75 435	97.13 429	97.61 439	95.58 337	98.63 442	96.68 353	99.11 368	98.18 428

testing91		96.00 397	95.32 402	98.02 381	98.76 416	95.39 413	98.38 349	98.65 384	98.82 266	96.84 430	96.71 450	75.06 446	99.71 366	96.46 369	98.23 416	98.98 371

Syy-MVS		98.17 331	97.85 343	99.15 295	98.50 428	98.79 284	98.60 318	99.21 346	97.89 355	96.76 431	96.37 454	95.47 340	99.57 417	99.10 156	98.73 398	99.09 346

myMVS_eth3d		95.63 406	94.73 408	98.34 370	98.50 428	96.36 396	98.60 318	99.21 346	97.89 355	96.76 431	96.37 454	72.10 450	99.57 417	94.38 418	98.73 398	99.09 346

testing99		95.86 401	95.19 405	97.87 388	98.76 416	95.03 418	98.62 315	98.44 395	98.68 284	96.67 433	96.66 451	74.31 447	99.69 375	96.51 364	98.03 426	98.90 381

testing11		96.05 396	95.41 399	97.97 384	98.78 413	95.27 416	98.59 321	98.23 406	98.86 260	96.56 434	96.91 447	75.20 445	99.69 375	97.26 318	98.29 414	98.93 377

testing222		95.60 408	94.59 411	98.61 355	98.66 423	97.45 370	98.54 332	97.90 415	98.53 301	96.54 435	96.47 453	70.62 452	99.81 326	95.91 394	98.15 421	98.56 409

FPMVS		96.32 387	95.50 396	98.79 345	99.60 207	98.17 333	98.46 345	98.80 375	97.16 392	96.28 436	99.63 222	82.19 429	99.09 437	88.45 438	98.89 387	99.10 341

PAPM		95.61 407	94.71 409	98.31 373	99.12 367	96.63 389	96.66 436	98.46 394	90.77 438	96.25 437	98.68 412	93.01 369	99.69 375	81.60 446	97.86 430	98.62 401

gg-mvs-nofinetune		95.87 400	95.17 406	97.97 384	98.19 436	96.95 383	99.69 45	89.23 450	99.89 52	96.24 438	99.94 19	81.19 430	99.51 427	93.99 426	98.20 417	97.44 436

baseline2		96.83 373	96.28 380	98.46 364	99.09 377	96.91 385	98.83 291	93.87 444	97.23 388	96.23 439	98.36 422	88.12 411	99.90 186	96.68 353	98.14 422	98.57 408

EPNet_dtu		97.62 352	97.79 346	97.11 411	96.67 448	92.31 434	98.51 336	98.04 410	99.24 203	95.77 440	99.47 297	93.78 359	99.66 397	98.98 167	99.62 289	99.37 277
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepMVS_CX				97.98 383	99.69 176	96.95 383		99.26 333	75.51 445	95.74 441	98.28 424	96.47 316	99.62 408	91.23 433	97.89 428	97.38 437

test_method		91.72 411	92.32 414	89.91 429	93.49 452	70.18 455	90.28 443	99.56 238	61.71 447	95.39 442	99.52 281	93.90 355	99.94 91	98.76 193	98.27 415	99.62 167

IB-MVS	95.41 20	95.30 409	94.46 413	97.84 390	98.76 416	95.33 415	97.33 421	96.07 432	96.02 411	95.37 443	97.41 440	76.17 444	99.96 64	97.54 298	95.44 445	98.22 424
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				97.36 403	97.59 445	96.87 386	99.70 38	88.49 451		94.64 444	97.26 443	80.66 432	99.12 436	91.50 432	96.50 440	96.08 444

dongtai		89.37 412	88.91 415	90.76 428	99.19 356	77.46 453	95.47 441	87.82 452	92.28 434	94.17 445	98.82 404	71.22 451	95.54 447	63.85 447	97.34 433	99.27 300

ET-MVSNet_ETH3D		96.78 374	96.07 384	98.91 328	99.26 343	97.92 353	97.70 404	96.05 433	97.96 352	92.37 446	98.43 421	87.06 414	99.90 186	98.27 225	97.56 432	98.91 380

MVE	92.54 22	96.66 378	96.11 383	98.31 373	99.68 184	97.55 366	97.94 391	95.60 436	99.37 184	90.68 447	98.70 411	96.56 311	98.61 443	86.94 444	99.55 312	98.77 395
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		85.65 414	84.57 417	88.90 430	97.91 442	77.11 454	96.37 438	87.62 453	85.24 443	85.45 448	96.83 448	69.94 453	90.98 449	45.90 448	95.83 444	98.62 401

EGC-MVSNET		89.05 413	85.52 416	99.64 148	99.89 39	99.78 56	99.56 87	99.52 264	24.19 448	49.96 449	99.83 80	99.15 94	99.92 139	97.71 280	99.85 180	99.21 314

test123		29.31 415	33.05 420	18.08 431	25.93 455	12.24 456	97.53 412	10.93 456	11.78 449	24.21 450	50.08 461	21.04 454	8.60 450	23.51 449	32.43 449	33.39 446

testmvs		28.94 416	33.33 418	15.79 432	26.03 454	9.81 457	96.77 434	15.67 455	11.55 450	23.87 451	50.74 460	19.03 455	8.53 451	23.21 450	33.07 448	29.03 447

mmdepth		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		24.88 417	33.17 419	0.00 433	0.00 456	0.00 458	0.00 444	99.62 198	0.00 451	0.00 452	99.13 365	99.82 16	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		16.61 418	22.14 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	99.28 79	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		8.26 429	11.02 432	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	99.16 363	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		8.33 419	11.11 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	100.00 1	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						96.36 396								95.20 409

MSC_two_6792asdad				99.74 96	99.03 384	99.53 158		99.23 340					99.92 139	97.77 272	99.69 266	99.78 70

No_MVS				99.74 96	99.03 384	99.53 158		99.23 340					99.92 139	97.77 272	99.69 266	99.78 70

eth-test2					0.00 456

eth-test					0.00 456

OPU-MVS				99.29 271	99.12 367	99.44 177	99.20 185				99.40 312	99.00 120	98.84 441	96.54 362	99.60 299	99.58 193

save fliter					99.53 249	99.25 224	98.29 355	99.38 309	99.07 232

test_0728_SECOND				99.83 38	99.70 172	99.79 53	99.14 208	99.61 205					99.92 139	97.88 261	99.72 257	99.77 74

GSMVS																99.14 335

sam_mvs1												90.81 395				99.14 335

sam_mvs												90.52 400

MTGPA								99.53 259

test_post1							99.14 208				51.63 459	89.54 407	99.82 311	96.86 342

test_post											52.41 458	90.25 402	99.86 253

patchmatchnet-post											99.62 230	90.58 398	99.94 91

MTMP							99.09 232	98.59 388

gm-plane-assit					97.59 445	89.02 451			93.47 431		98.30 423		99.84 286	96.38 373

test9_res														95.10 411	99.44 333	99.50 234

agg_prior2														94.58 417	99.46 332	99.50 234

test_prior4						99.19 237	98.00 384

test_prior				99.46 216	99.35 313	99.22 231		99.39 305					99.69 375			99.48 243

新几何2							98.04 379

旧先验1					99.49 269	99.29 215		99.26 333			99.39 316	97.67 270			99.36 344	99.46 251

无先验							98.01 382	99.23 340	95.83 414				99.85 271	95.79 398		99.44 257

原ACMM2							97.92 393

testdata2													99.89 205	95.99 389

segment_acmp												98.37 213

testdata1							97.72 402		97.86 360

plane_prior7					99.58 217	99.38 196

plane_prior6					99.47 280	99.26 221						97.24 289

plane_prior5								99.54 250					99.82 311	95.84 396	99.78 229	99.60 181

plane_prior4											99.25 350

plane_prior2							98.80 299		98.94 247

plane_prior1					99.51 258

plane_prior						99.24 228	98.42 347		97.87 358						99.71 260

n2								0.00 457

nn								0.00 457

door-mid								99.83 80

test11								99.29 327

door								99.77 115

HQP5-MVS						98.94 269

BP-MVS														94.73 414

HQP3-MVS								99.37 310							99.67 277

HQP2-MVS												96.67 308

NP-MVS					99.40 300	99.13 243					98.83 402

ACMMP++_ref															99.94 111

ACMMP++															99.79 224

Test By Simon												98.41 207

High-resolution multi-view benchmark