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.

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 23	100.00 1	99.92 28	100.00 1	99.87 42

mvs_tets		99.90 2	99.90 4	99.90 8	99.96 7	99.79 54	99.72 33	99.88 63	99.92 44	99.98 14	99.93 22	99.94 4	99.98 27	99.77 53	100.00 1	99.92 24

test_fmvsmconf0.01_n		99.89 3	99.88 7	99.91 3	99.98 3	99.76 70	99.12 228	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_vis3_rt		99.89 3	99.90 4	99.87 25	99.98 3	99.75 78	99.70 38	100.00 1	99.73 106	100.00 1	99.89 41	99.79 22	99.88 229	99.98 1	100.00 1	99.98 5

jajsoiax		99.89 3	99.89 6	99.89 11	99.96 7	99.78 57	99.70 38	99.86 71	99.89 54	99.98 14	99.90 36	99.94 4	99.98 27	99.75 54	100.00 1	99.90 28

mvs5depth		99.88 6	99.91 3	99.80 61	99.92 29	99.42 188	99.94 3	100.00 1	99.97 23	99.89 71	99.99 12	99.63 37	99.97 42	99.87 42	99.99 16	100.00 1

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 48	100.00 1	99.97 14	99.61 41	99.97 42	99.75 54	100.00 1	99.84 50

LTVRE_ROB	99.19 1	99.88 6	99.87 11	99.88 19	99.91 31	99.90 7	99.96 1	99.92 42	99.90 48	99.97 23	99.87 56	99.81 20	99.95 78	99.54 85	99.99 16	99.80 62
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
test_fmvsmconf0.1_n		99.87 9	99.86 13	99.91 3	99.97 6	99.74 85	99.01 265	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

fmvsm_s_conf0.1_n		99.86 10	99.85 17	99.89 11	99.93 24	99.78 57	99.07 248	99.98 12	99.99 3	99.98 14	99.90 36	99.88 11	99.92 147	99.93 24	99.99 16	99.98 5

pmmvs6		99.86 10	99.86 13	99.83 39	99.94 18	99.90 7	99.83 7	99.91 51	99.85 70	99.94 46	99.95 16	99.73 27	99.90 195	99.65 69	99.97 70	99.69 110

fmvsm_l_conf0.5_n_3		99.85 12	99.83 21	99.92 2	99.88 45	99.86 19	99.08 244	99.97 20	99.98 16	99.96 32	99.79 110	99.90 9	99.99 8	99.96 9	99.99 16	99.90 28

fmvsm_s_conf0.1_n_a		99.85 12	99.83 21	99.91 3	99.95 15	99.82 42	99.10 236	99.98 12	99.99 3	99.98 14	99.91 31	99.68 33	99.93 116	99.93 24	99.99 16	99.99 2

test_fmvsmconf_n		99.85 12	99.84 20	99.88 19	99.91 31	99.73 88	98.97 280	99.98 12	99.99 3	99.96 32	99.85 68	99.93 7	99.99 8	99.94 19	99.99 16	99.93 20

mvsany_test3		99.85 12	99.88 7	99.75 93	99.95 15	99.37 203	99.53 91	99.98 12	99.77 104	99.99 7	99.95 16	99.85 14	99.94 95	99.95 14	99.98 48	99.94 17

UniMVSNet_ETH3D		99.85 12	99.83 21	99.90 8	99.89 39	99.91 4	99.89 5	99.71 161	99.93 41	99.95 43	99.89 41	99.71 28	99.96 67	99.51 90	99.97 70	99.84 50

test_fmvsmvis_n_1920		99.84 17	99.86 13	99.81 52	99.88 45	99.55 158	99.17 205	99.98 12	99.99 3	99.96 32	99.84 75	99.96 3	99.99 8	99.96 9	99.99 16	99.88 38

test_fmvsm_n_1920		99.84 17	99.85 17	99.83 39	99.82 85	99.70 106	99.17 205	99.97 20	99.99 3	99.96 32	99.82 88	99.94 4	100.00 1	99.95 14	100.00 1	99.80 62

PS-MVSNAJss		99.84 17	99.82 25	99.89 11	99.96 7	99.77 63	99.68 49	99.85 77	99.95 30	99.98 14	99.92 27	99.28 86	99.98 27	99.75 54	100.00 1	99.94 17

test_djsdf		99.84 17	99.81 28	99.91 3	99.94 18	99.84 27	99.77 19	99.80 107	99.73 106	99.97 23	99.92 27	99.77 25	99.98 27	99.43 101	100.00 1	99.90 28

fmvsm_l_conf0.5_n_9		99.83 21	99.81 28	99.89 11	99.86 57	99.80 51	98.94 288	99.96 28	99.98 16	99.96 32	99.78 122	99.88 11	99.98 27	99.96 9	99.99 16	99.90 28

fmvsm_s_conf0.5_n		99.83 21	99.81 28	99.87 25	99.85 65	99.78 57	99.03 257	99.96 28	99.99 3	99.97 23	99.84 75	99.78 23	99.92 147	99.92 28	99.99 16	99.92 24

test_fmvs3		99.83 21	99.93 2	99.53 206	99.96 7	98.62 314	99.67 53	100.00 1	99.95 30	100.00 1	99.95 16	99.85 14	99.99 8	99.98 1	99.99 16	99.98 5

fmvsm_s_conf0.5_n_9		99.82 24	99.82 25	99.82 44	99.83 76	99.59 145	98.97 280	99.92 42	99.99 3	99.97 23	99.84 75	99.90 9	99.94 95	99.94 19	99.99 16	99.92 24

tt0320-xc		99.82 24	99.82 25	99.82 44	99.82 85	99.84 27	99.82 10	99.92 42	99.94 34	99.94 46	99.93 22	99.34 78	99.92 147	99.70 59	99.96 84	99.70 102

fmvsm_s_conf0.5_n_a		99.82 24	99.79 34	99.89 11	99.85 65	99.82 42	99.03 257	99.96 28	99.99 3	99.97 23	99.84 75	99.58 45	99.93 116	99.92 28	99.98 48	99.93 20

v7n		99.82 24	99.80 32	99.88 19	99.96 7	99.84 27	99.82 10	99.82 93	99.84 74	99.94 46	99.91 31	99.13 109	99.96 67	99.83 44	99.99 16	99.83 54

sc_t1		99.81 28	99.80 32	99.82 44	99.88 45	99.88 12	99.83 7	99.79 114	99.94 34	99.93 51	99.92 27	99.35 77	99.92 147	99.64 72	99.94 117	99.68 116

fmvsm_s_conf0.1_n_2		99.81 28	99.78 39	99.89 11	99.93 24	99.76 70	98.92 291	99.98 12	99.99 3	99.99 7	99.88 50	99.43 61	99.94 95	99.94 19	99.99 16	99.99 2

fmvsm_s_conf0.5_n_6		99.80 30	99.78 39	99.85 31	99.78 125	99.78 57	99.00 268	99.97 20	99.96 26	99.97 23	99.56 281	99.92 8	99.93 116	99.91 31	99.99 16	99.83 54

fmvsm_l_conf0.5_n_a		99.80 30	99.79 34	99.84 36	99.88 45	99.64 126	99.12 228	99.91 51	99.98 16	99.95 43	99.67 205	99.67 34	99.99 8	99.94 19	99.99 16	99.88 38

fmvsm_l_conf0.5_n		99.80 30	99.78 39	99.85 31	99.88 45	99.66 117	99.11 233	99.91 51	99.98 16	99.96 32	99.64 217	99.60 43	99.99 8	99.95 14	99.99 16	99.88 38

anonymousdsp		99.80 30	99.77 45	99.90 8	99.96 7	99.88 12	99.73 30	99.85 77	99.70 120	99.92 58	99.93 22	99.45 58	99.97 42	99.36 114	100.00 1	99.85 47

tt0320		99.79 34	99.79 34	99.81 52	99.82 85	99.84 27	99.82 10	99.90 56	99.94 34	99.94 46	99.94 19	99.07 120	99.92 147	99.68 64	99.97 70	99.67 125

fmvsm_s_conf0.5_n_3		99.79 34	99.77 45	99.85 31	99.81 97	99.71 98	98.97 280	99.92 42	99.98 16	99.97 23	99.86 63	99.53 53	99.95 78	99.88 39	99.99 16	99.89 35

pm-mvs1		99.79 34	99.79 34	99.78 72	99.91 31	99.83 34	99.76 23	99.87 65	99.73 106	99.89 71	99.87 56	99.63 37	99.87 244	99.54 85	99.92 132	99.63 161

fmvsm_s_conf0.5_n_5		99.78 37	99.76 49	99.85 31	99.79 117	99.72 93	98.84 301	99.96 28	99.96 26	99.96 32	99.72 161	99.71 28	99.99 8	99.93 24	99.98 48	99.85 47

fmvsm_s_conf0.5_n_4		99.78 37	99.78 39	99.79 68	99.75 153	99.56 154	98.98 278	99.94 38	99.92 44	99.97 23	99.72 161	99.84 16	99.92 147	99.91 31	99.98 48	99.89 35

fmvsm_s_conf0.5_n_2		99.78 37	99.75 51	99.88 19	99.82 85	99.76 70	98.88 294	99.92 42	99.98 16	99.98 14	99.85 68	99.42 63	99.94 95	99.93 24	99.98 48	99.94 17

mmtdpeth		99.78 37	99.83 21	99.66 138	99.85 65	99.05 268	99.79 15	99.97 20	100.00 1	99.43 274	99.94 19	99.64 35	99.94 95	99.83 44	99.99 16	99.98 5

sd_testset		99.78 37	99.78 39	99.80 61	99.80 104	99.76 70	99.80 14	99.79 114	99.97 23	99.89 71	99.89 41	99.53 53	99.99 8	99.36 114	99.96 84	99.65 144

UA-Net		99.78 37	99.76 49	99.86 29	99.72 169	99.71 98	99.91 4	99.95 36	99.96 26	99.71 170	99.91 31	99.15 104	99.97 42	99.50 92	100.00 1	99.90 28

TransMVSNet (Re)		99.78 37	99.77 45	99.81 52	99.91 31	99.85 22	99.75 25	99.86 71	99.70 120	99.91 61	99.89 41	99.60 43	99.87 244	99.59 77	99.74 258	99.71 99

SDMVSNet		99.77 44	99.77 45	99.76 82	99.80 104	99.65 123	99.63 64	99.86 71	99.97 23	99.89 71	99.89 41	99.52 55	99.99 8	99.42 106	99.96 84	99.65 144

fmvsm_s_conf0.5_n_8		99.76 45	99.72 54	99.88 19	99.82 85	99.75 78	99.02 261	99.87 65	99.98 16	99.98 14	99.81 95	99.07 120	99.97 42	99.91 31	99.99 16	99.92 24

test_cas_vis1_n_1920		99.76 45	99.86 13	99.45 230	99.93 24	98.40 333	99.30 154	99.98 12	99.94 34	99.99 7	99.89 41	99.80 21	99.97 42	99.96 9	99.97 70	99.97 10

test_f		99.75 47	99.88 7	99.37 260	99.96 7	98.21 345	99.51 99	100.00 1	99.94 34	100.00 1	99.93 22	99.58 45	99.94 95	99.97 4	99.99 16	99.97 10

OurMVSNet-221017-0		99.75 47	99.71 55	99.84 36	99.96 7	99.83 34	99.83 7	99.85 77	99.80 93	99.93 51	99.93 22	98.54 202	99.93 116	99.59 77	99.98 48	99.76 81

Vis-MVSNet		99.75 47	99.74 52	99.79 68	99.88 45	99.66 117	99.69 45	99.92 42	99.67 129	99.77 138	99.75 145	99.61 41	99.98 27	99.35 117	99.98 48	99.72 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
fmvsm_s_conf0.5_n_7		99.73 50	99.78 39	99.60 175	99.74 161	98.93 282	98.85 299	99.96 28	99.96 26	99.97 23	99.76 137	99.82 18	99.96 67	99.95 14	99.98 48	99.90 28

mamv4		99.73 50	99.74 52	99.70 123	99.66 208	99.87 15	99.69 45	99.93 39	99.93 41	99.93 51	99.86 63	99.07 120	100.00 1	99.66 67	99.92 132	99.24 322

test_vis1_n_1920		99.72 52	99.88 7	99.27 293	99.93 24	97.84 372	99.34 137	100.00 1	99.99 3	99.99 7	99.82 88	99.87 13	99.99 8	99.97 4	99.99 16	99.97 10

test_fmvs2		99.72 52	99.85 17	99.34 268	99.91 31	98.08 359	99.48 107	100.00 1	99.90 48	99.99 7	99.91 31	99.50 57	99.98 27	99.98 1	99.99 16	99.96 13

TDRefinement		99.72 52	99.70 56	99.77 75	99.90 37	99.85 22	99.86 6	99.92 42	99.69 123	99.78 126	99.92 27	99.37 71	99.88 229	98.93 183	99.95 102	99.60 187

XXY-MVS		99.71 55	99.67 63	99.81 52	99.89 39	99.72 93	99.59 80	99.82 93	99.39 198	99.82 105	99.84 75	99.38 69	99.91 176	99.38 110	99.93 128	99.80 62

nrg030		99.70 56	99.66 65	99.82 44	99.76 140	99.84 27	99.61 73	99.70 170	99.93 41	99.78 126	99.68 201	99.10 112	99.78 352	99.45 99	99.96 84	99.83 54

FC-MVSNet-test		99.70 56	99.65 67	99.86 29	99.88 45	99.86 19	99.72 33	99.78 123	99.90 48	99.82 105	99.83 81	98.45 217	99.87 244	99.51 90	99.97 70	99.86 44

Elysia		99.69 58	99.65 67	99.81 52	99.86 57	99.72 93	99.34 137	99.77 126	99.94 34	99.91 61	99.76 137	98.55 198	99.99 8	99.70 59	99.98 48	99.72 94

StellarMVS		99.69 58	99.65 67	99.81 52	99.86 57	99.72 93	99.34 137	99.77 126	99.94 34	99.91 61	99.76 137	98.55 198	99.99 8	99.70 59	99.98 48	99.72 94

GeoE		99.69 58	99.66 65	99.78 72	99.76 140	99.76 70	99.60 79	99.82 93	99.46 178	99.75 147	99.56 281	99.63 37	99.95 78	99.43 101	99.88 166	99.62 172

v10		99.69 58	99.69 59	99.66 138	99.81 97	99.39 198	99.66 57	99.75 139	99.60 154	99.92 58	99.87 56	98.75 169	99.86 263	99.90 35	99.99 16	99.73 90

EC-MVSNet		99.69 58	99.69 59	99.68 127	99.71 172	99.91 4	99.76 23	99.96 28	99.86 64	99.51 257	99.39 332	99.57 47	99.93 116	99.64 72	99.86 186	99.20 335

test_vis1_n		99.68 63	99.79 34	99.36 265	99.94 18	98.18 348	99.52 92	100.00 1	99.86 64	100.00 1	99.88 50	98.99 134	99.96 67	99.97 4	99.96 84	99.95 14

test_fmvs1_n		99.68 63	99.81 28	99.28 288	99.95 15	97.93 368	99.49 105	100.00 1	99.82 83	99.99 7	99.89 41	99.21 95	99.98 27	99.97 4	99.98 48	99.93 20

SPE-MVS-test		99.68 63	99.70 56	99.64 151	99.57 243	99.83 34	99.78 17	99.97 20	99.92 44	99.50 259	99.38 334	99.57 47	99.95 78	99.69 62	99.90 144	99.15 347

v8		99.68 63	99.69 59	99.65 144	99.80 104	99.40 195	99.66 57	99.76 134	99.64 139	99.93 51	99.85 68	98.66 183	99.84 296	99.88 39	99.99 16	99.71 99

DTE-MVSNet		99.68 63	99.61 80	99.88 19	99.80 104	99.87 15	99.67 53	99.71 161	99.72 110	99.84 98	99.78 122	98.67 181	99.97 42	99.30 126	99.95 102	99.80 62

casdiffmvs_mvg		99.68 63	99.68 62	99.69 125	99.81 97	99.59 145	99.29 161	99.90 56	99.71 114	99.79 122	99.73 154	99.54 50	99.84 296	99.36 114	99.96 84	99.65 144
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS		99.67 69	99.70 56	99.58 181	99.53 266	99.84 27	99.79 15	99.96 28	99.90 48	99.61 217	99.41 324	99.51 56	99.95 78	99.66 67	99.89 157	98.96 389

KinetiMVS		99.66 70	99.63 74	99.76 82	99.89 39	99.57 153	99.37 129	99.82 93	99.95 30	99.90 66	99.63 232	98.57 194	99.97 42	99.65 69	99.94 117	99.74 86

VPA-MVSNet		99.66 70	99.62 76	99.79 68	99.68 200	99.75 78	99.62 67	99.69 178	99.85 70	99.80 116	99.81 95	98.81 157	99.91 176	99.47 96	99.88 166	99.70 102

PS-CasMVS		99.66 70	99.58 89	99.89 11	99.80 104	99.85 22	99.66 57	99.73 149	99.62 144	99.84 98	99.71 171	98.62 187	99.96 67	99.30 126	99.96 84	99.86 44

PEN-MVS		99.66 70	99.59 86	99.89 11	99.83 76	99.87 15	99.66 57	99.73 149	99.70 120	99.84 98	99.73 154	98.56 197	99.96 67	99.29 129	99.94 117	99.83 54

FMVSNet1		99.66 70	99.63 74	99.73 107	99.78 125	99.77 63	99.68 49	99.70 170	99.67 129	99.82 105	99.83 81	98.98 137	99.90 195	99.24 133	99.97 70	99.53 225

MIMVSNet1		99.66 70	99.62 76	99.80 61	99.94 18	99.87 15	99.69 45	99.77 126	99.78 100	99.93 51	99.89 41	97.94 267	99.92 147	99.65 69	99.98 48	99.62 172

FIs		99.65 76	99.58 89	99.84 36	99.84 70	99.85 22	99.66 57	99.75 139	99.86 64	99.74 157	99.79 110	98.27 239	99.85 281	99.37 113	99.93 128	99.83 54

SSC-MVS3.2		99.64 77	99.67 63	99.56 191	99.75 153	98.98 272	98.96 284	99.87 65	99.88 59	99.84 98	99.64 217	99.32 81	99.91 176	99.78 52	99.96 84	99.80 62

viewmacassd2359aftdt		99.63 78	99.61 80	99.68 127	99.84 70	99.61 139	99.14 216	99.87 65	99.71 114	99.75 147	99.77 132	99.54 50	99.72 376	98.91 184	99.96 84	99.70 102

testf1		99.63 78	99.60 84	99.72 114	99.94 18	99.95 2	99.47 110	99.89 59	99.43 189	99.88 81	99.80 100	99.26 90	99.90 195	98.81 193	99.88 166	99.32 307

APD_test2		99.63 78	99.60 84	99.72 114	99.94 18	99.95 2	99.47 110	99.89 59	99.43 189	99.88 81	99.80 100	99.26 90	99.90 195	98.81 193	99.88 166	99.32 307

tt0805		99.63 78	99.57 94	99.81 52	99.87 54	99.88 12	99.58 82	98.70 396	99.72 110	99.91 61	99.60 258	99.43 61	99.81 339	99.81 49	99.53 336	99.73 90

KD-MVS_self_test		99.63 78	99.59 86	99.76 82	99.84 70	99.90 7	99.37 129	99.79 114	99.83 80	99.88 81	99.85 68	98.42 221	99.90 195	99.60 76	99.73 264	99.49 247

casdiffmvs		99.63 78	99.61 80	99.67 131	99.79 117	99.59 145	99.13 223	99.85 77	99.79 97	99.76 142	99.72 161	99.33 80	99.82 324	99.21 139	99.94 117	99.59 194
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.63 78	99.62 76	99.66 138	99.80 104	99.62 133	99.44 116	99.80 107	99.71 114	99.72 165	99.69 190	99.15 104	99.83 312	99.32 123	99.94 117	99.53 225

viewmsd2359difaftdt		99.62 85	99.64 72	99.56 191	99.86 57	99.19 245	99.02 261	99.93 39	99.83 80	99.88 81	99.81 95	98.99 134	99.83 312	99.48 94	99.96 84	99.65 144

Anonymous20231211		99.62 85	99.57 94	99.76 82	99.61 221	99.60 143	99.81 13	99.73 149	99.82 83	99.90 66	99.90 36	97.97 266	99.86 263	99.42 106	99.96 84	99.80 62

DeepC-MVS	98.90 4	99.62 85	99.61 80	99.67 131	99.72 169	99.44 181	99.24 179	99.71 161	99.27 214	99.93 51	99.90 36	99.70 31	99.93 116	98.99 171	99.99 16	99.64 155
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
dcpmvs_2		99.61 88	99.64 72	99.53 206	99.79 117	98.82 291	99.58 82	99.97 20	99.95 30	99.96 32	99.76 137	98.44 218	99.99 8	99.34 118	99.96 84	99.78 72

WR-MVS_H		99.61 88	99.53 108	99.87 25	99.80 104	99.83 34	99.67 53	99.75 139	99.58 158	99.85 95	99.69 190	98.18 251	99.94 95	99.28 131	99.95 102	99.83 54

ACMH	98.42 6	99.59 90	99.54 104	99.72 114	99.86 57	99.62 133	99.56 87	99.79 114	98.77 292	99.80 116	99.85 68	99.64 35	99.85 281	98.70 210	99.89 157	99.70 102
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SSM_0404		99.57 91	99.58 89	99.54 202	99.76 140	99.28 221	99.19 196	99.84 83	99.80 93	99.78 126	99.70 181	99.44 59	99.93 116	98.74 202	99.95 102	99.41 283

v1192		99.57 91	99.57 94	99.57 188	99.77 136	99.22 239	99.04 254	99.60 232	99.18 229	99.87 90	99.72 161	99.08 117	99.85 281	99.89 38	99.98 48	99.66 135

EG-PatchMatch MVS		99.57 91	99.56 99	99.62 167	99.77 136	99.33 213	99.26 172	99.76 134	99.32 208	99.80 116	99.78 122	99.29 84	99.87 244	99.15 152	99.91 143	99.66 135

Gipuma		99.57 91	99.59 86	99.49 217	99.98 3	99.71 98	99.72 33	99.84 83	99.81 89	99.94 46	99.78 122	98.91 148	99.71 381	98.41 231	99.95 102	99.05 376
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
SSM_0407		99.56 95	99.56 99	99.54 202	99.71 172	99.24 233	99.15 213	99.84 83	99.80 93	99.78 126	99.70 181	99.44 59	99.93 116	98.74 202	99.90 144	99.45 260

lecture		99.56 95	99.48 114	99.81 52	99.78 125	99.86 19	99.50 100	99.70 170	99.59 156	99.75 147	99.71 171	98.94 142	99.92 147	98.59 218	99.76 247	99.66 135

v1921920		99.56 95	99.57 94	99.55 196	99.75 153	99.11 255	99.05 249	99.61 221	99.15 240	99.88 81	99.71 171	99.08 117	99.87 244	99.90 35	99.97 70	99.66 135

v1240		99.56 95	99.58 89	99.51 211	99.80 104	99.00 269	99.00 268	99.65 201	99.15 240	99.90 66	99.75 145	99.09 114	99.88 229	99.90 35	99.96 84	99.67 125

V42		99.56 95	99.54 104	99.63 158	99.79 117	99.46 174	99.39 122	99.59 238	99.24 220	99.86 92	99.70 181	98.55 198	99.82 324	99.79 51	99.95 102	99.60 187

SSM_04072		99.55 100	99.55 101	99.55 196	99.71 172	99.24 233	99.27 167	99.79 114	99.72 110	99.78 126	99.64 217	99.36 74	99.97 42	98.74 202	99.90 144	99.45 260

MVSMamba_PlusPlus		99.55 100	99.58 89	99.47 223	99.68 200	99.40 195	99.52 92	99.70 170	99.92 44	99.77 138	99.86 63	98.28 237	99.96 67	99.54 85	99.90 144	99.05 376

v144192		99.55 100	99.54 104	99.58 181	99.78 125	99.20 244	99.11 233	99.62 214	99.18 229	99.89 71	99.72 161	98.66 183	99.87 244	99.88 39	99.97 70	99.66 135

test20.03		99.55 100	99.54 104	99.58 181	99.79 117	99.37 203	99.02 261	99.89 59	99.60 154	99.82 105	99.62 241	98.81 157	99.89 214	99.43 101	99.86 186	99.47 255

mamba_0408		99.54 104	99.55 101	99.54 202	99.71 172	99.24 233	99.27 167	99.79 114	99.72 110	99.78 126	99.64 217	99.36 74	99.93 116	98.74 202	99.90 144	99.45 260

v1144		99.54 104	99.53 108	99.59 178	99.79 117	99.28 221	99.10 236	99.61 221	99.20 227	99.84 98	99.73 154	98.67 181	99.84 296	99.86 43	99.98 48	99.64 155

CP-MVSNet		99.54 104	99.43 128	99.87 25	99.76 140	99.82 42	99.57 85	99.61 221	99.54 159	99.80 116	99.64 217	97.79 278	99.95 78	99.21 139	99.94 117	99.84 50

TranMVSNet+NR-MVSNet		99.54 104	99.47 116	99.76 82	99.58 233	99.64 126	99.30 154	99.63 211	99.61 148	99.71 170	99.56 281	98.76 167	99.96 67	99.14 158	99.92 132	99.68 116

SSC-MVS		99.52 108	99.42 130	99.83 39	99.86 57	99.65 123	99.52 92	99.81 104	99.87 61	99.81 112	99.79 110	96.78 322	99.99 8	99.83 44	99.51 340	99.86 44

patch_mono-2		99.51 109	99.46 121	99.64 151	99.70 187	99.11 255	99.04 254	99.87 65	99.71 114	99.47 264	99.79 110	98.24 241	99.98 27	99.38 110	99.96 84	99.83 54

viewmanbaseed2359cas		99.50 110	99.47 116	99.61 171	99.73 165	99.52 163	99.03 257	99.83 87	99.49 167	99.65 196	99.64 217	99.18 98	99.71 381	98.73 207	99.92 132	99.58 199

reproduce_model		99.50 110	99.40 134	99.83 39	99.60 223	99.83 34	99.12 228	99.68 181	99.49 167	99.80 116	99.79 110	99.01 131	99.93 116	98.24 244	99.82 214	99.73 90

balanced_conf03		99.50 110	99.50 110	99.50 213	99.42 314	99.49 166	99.52 92	99.75 139	99.86 64	99.78 126	99.71 171	98.20 248	99.90 195	99.39 109	99.88 166	99.10 358

v2v482		99.50 110	99.47 116	99.58 181	99.78 125	99.25 229	99.14 216	99.58 247	99.25 218	99.81 112	99.62 241	98.24 241	99.84 296	99.83 44	99.97 70	99.64 155

ACMH+	98.40 8	99.50 110	99.43 128	99.71 119	99.86 57	99.76 70	99.32 146	99.77 126	99.53 161	99.77 138	99.76 137	99.26 90	99.78 352	97.77 288	99.88 166	99.60 187

Baseline_NR-MVSNet		99.49 115	99.37 141	99.82 44	99.91 31	99.84 27	98.83 304	99.86 71	99.68 125	99.65 196	99.88 50	97.67 286	99.87 244	99.03 168	99.86 186	99.76 81

TAMVS		99.49 115	99.45 123	99.63 158	99.48 291	99.42 188	99.45 114	99.57 249	99.66 133	99.78 126	99.83 81	97.85 274	99.86 263	99.44 100	99.96 84	99.61 183

diffmvs_AUTHOR		99.48 117	99.48 114	99.47 223	99.80 104	98.89 287	98.71 324	99.82 93	99.79 97	99.66 193	99.63 232	98.87 153	99.88 229	99.13 160	99.95 102	99.62 172

ttmdpeth		99.48 117	99.55 101	99.29 285	99.76 140	98.16 350	99.33 143	99.95 36	99.79 97	99.36 293	99.89 41	99.13 109	99.77 361	99.09 163	99.64 301	99.93 20

test_fmvs1		99.48 117	99.65 67	98.97 335	99.54 259	97.16 395	99.11 233	99.98 12	99.78 100	99.96 32	99.81 95	98.72 174	99.97 42	99.95 14	99.97 70	99.79 70

pmmvs-eth3d		99.48 117	99.47 116	99.51 211	99.77 136	99.41 194	98.81 309	99.66 191	99.42 193	99.75 147	99.66 210	99.20 96	99.76 364	98.98 173	99.99 16	99.36 297

EI-MVSNet-UG-set		99.48 117	99.50 110	99.42 240	99.57 243	98.65 310	99.24 179	99.46 301	99.68 125	99.80 116	99.66 210	98.99 134	99.89 214	99.19 144	99.90 144	99.72 94

APDe-MVS		99.48 117	99.36 144	99.85 31	99.55 257	99.81 47	99.50 100	99.69 178	98.99 256	99.75 147	99.71 171	98.79 162	99.93 116	98.46 225	99.85 191	99.80 62
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PMMVS2		99.48 117	99.45 123	99.57 188	99.76 140	98.99 271	98.09 390	99.90 56	98.95 263	99.78 126	99.58 270	99.57 47	99.93 116	99.48 94	99.95 102	99.79 70

DSMNet-mixed		99.48 117	99.65 67	98.95 338	99.71 172	97.27 392	99.50 100	99.82 93	99.59 156	99.41 283	99.85 68	99.62 40	100.00 1	99.53 88	99.89 157	99.59 194

DP-MVS		99.48 117	99.39 135	99.74 98	99.57 243	99.62 133	99.29 161	99.61 221	99.87 61	99.74 157	99.76 137	98.69 177	99.87 244	98.20 248	99.80 231	99.75 84

viewmambaseed2359dif		99.47 126	99.50 110	99.37 260	99.70 187	98.80 295	98.67 326	99.92 42	99.49 167	99.77 138	99.71 171	99.08 117	99.78 352	99.20 142	99.94 117	99.54 219

EI-MVSNet-Vis-set		99.47 126	99.49 113	99.42 240	99.57 243	98.66 307	99.24 179	99.46 301	99.67 129	99.79 122	99.65 215	98.97 139	99.89 214	99.15 152	99.89 157	99.71 99

reproduce-ours		99.46 128	99.35 146	99.82 44	99.56 254	99.83 34	99.05 249	99.65 201	99.45 181	99.78 126	99.78 122	98.93 143	99.93 116	98.11 258	99.81 224	99.70 102

our_new_method		99.46 128	99.35 146	99.82 44	99.56 254	99.83 34	99.05 249	99.65 201	99.45 181	99.78 126	99.78 122	98.93 143	99.93 116	98.11 258	99.81 224	99.70 102

VPNet		99.46 128	99.37 141	99.71 119	99.82 85	99.59 145	99.48 107	99.70 170	99.81 89	99.69 177	99.58 270	97.66 290	99.86 263	99.17 149	99.44 350	99.67 125

ACMM	98.09 11	99.46 128	99.38 138	99.72 114	99.80 104	99.69 110	99.13 223	99.65 201	98.99 256	99.64 198	99.72 161	99.39 65	99.86 263	98.23 245	99.81 224	99.60 187
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_rt		99.45 132	99.46 121	99.41 248	99.71 172	98.63 313	98.99 275	99.96 28	99.03 253	99.95 43	99.12 385	98.75 169	99.84 296	99.82 48	99.82 214	99.77 76

COLMAP_ROB	98.06 12	99.45 132	99.37 141	99.70 123	99.83 76	99.70 106	99.38 125	99.78 123	99.53 161	99.67 187	99.78 122	99.19 97	99.86 263	97.32 327	99.87 178	99.55 210
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
WB-MVS		99.44 134	99.32 153	99.80 61	99.81 97	99.61 139	99.47 110	99.81 104	99.82 83	99.71 170	99.72 161	96.60 326	99.98 27	99.75 54	99.23 381	99.82 61

mvsany_test1		99.44 134	99.45 123	99.40 251	99.37 323	98.64 312	97.90 413	99.59 238	99.27 214	99.92 58	99.82 88	99.74 26	99.93 116	99.55 84	99.87 178	99.63 161

Anonymous20240521		99.44 134	99.42 130	99.49 217	99.89 39	98.96 277	99.62 67	99.76 134	99.85 70	99.82 105	99.88 50	96.39 337	99.97 42	99.59 77	99.98 48	99.55 210

tfpnnormal		99.43 137	99.38 138	99.60 175	99.87 54	99.75 78	99.59 80	99.78 123	99.71 114	99.90 66	99.69 190	98.85 155	99.90 195	97.25 338	99.78 241	99.15 347

HPM-MVS_fast		99.43 137	99.30 160	99.80 61	99.83 76	99.81 47	99.52 92	99.70 170	98.35 340	99.51 257	99.50 302	99.31 82	99.88 229	98.18 252	99.84 196	99.69 110

3Dnovator	99.15 2	99.43 137	99.36 144	99.65 144	99.39 318	99.42 188	99.70 38	99.56 254	99.23 222	99.35 295	99.80 100	99.17 100	99.95 78	98.21 247	99.84 196	99.59 194

Anonymous20240529		99.42 140	99.34 148	99.65 144	99.53 266	99.60 143	99.63 64	99.39 322	99.47 175	99.76 142	99.78 122	98.13 253	99.86 263	98.70 210	99.68 288	99.49 247

SixPastTwentyTwo		99.42 140	99.30 160	99.76 82	99.92 29	99.67 115	99.70 38	99.14 373	99.65 136	99.89 71	99.90 36	96.20 344	99.94 95	99.42 106	99.92 132	99.67 125

GBi-Net		99.42 140	99.31 155	99.73 107	99.49 286	99.77 63	99.68 49	99.70 170	99.44 183	99.62 211	99.83 81	97.21 307	99.90 195	98.96 177	99.90 144	99.53 225

test1		99.42 140	99.31 155	99.73 107	99.49 286	99.77 63	99.68 49	99.70 170	99.44 183	99.62 211	99.83 81	97.21 307	99.90 195	98.96 177	99.90 144	99.53 225

MVSFormer		99.41 144	99.44 126	99.31 280	99.57 243	98.40 333	99.77 19	99.80 107	99.73 106	99.63 202	99.30 355	98.02 261	99.98 27	99.43 101	99.69 283	99.55 210

IterMVS-LS		99.41 144	99.47 116	99.25 299	99.81 97	98.09 356	98.85 299	99.76 134	99.62 144	99.83 104	99.64 217	98.54 202	99.97 42	99.15 152	99.99 16	99.68 116
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SED-MVS		99.40 146	99.28 168	99.77 75	99.69 192	99.82 42	99.20 190	99.54 266	99.13 242	99.82 105	99.63 232	98.91 148	99.92 147	97.85 283	99.70 275	99.58 199

v148		99.40 146	99.41 133	99.39 254	99.76 140	98.94 279	99.09 241	99.59 238	99.17 234	99.81 112	99.61 250	98.41 222	99.69 391	99.32 123	99.94 117	99.53 225

NR-MVSNet		99.40 146	99.31 155	99.68 127	99.43 309	99.55 158	99.73 30	99.50 290	99.46 178	99.88 81	99.36 341	97.54 293	99.87 244	98.97 175	99.87 178	99.63 161

PVSNet_Blended_VisFu		99.40 146	99.38 138	99.44 234	99.90 37	98.66 307	98.94 288	99.91 51	97.97 366	99.79 122	99.73 154	99.05 127	99.97 42	99.15 152	99.99 16	99.68 116

LuminaMVS		99.39 150	99.28 168	99.73 107	99.83 76	99.49 166	99.00 268	99.05 380	99.81 89	99.89 71	99.79 110	96.54 330	99.97 42	99.64 72	99.98 48	99.73 90

EU-MVSNet		99.39 150	99.62 76	98.72 367	99.88 45	96.44 411	99.56 87	99.85 77	99.90 48	99.90 66	99.85 68	98.09 256	99.83 312	99.58 80	99.95 102	99.90 28

CHOSEN 1792x2688		99.39 150	99.30 160	99.65 144	99.88 45	99.25 229	98.78 316	99.88 63	98.66 303	99.96 32	99.79 110	97.45 296	99.93 116	99.34 118	99.99 16	99.78 72

IMVS_0407		99.38 153	99.42 130	99.28 288	99.71 172	98.55 320	99.27 167	99.71 161	99.41 194	99.73 161	99.60 258	99.17 100	99.83 312	98.45 226	99.70 275	99.45 260

DVP-MVS++		99.38 153	99.25 175	99.77 75	99.03 401	99.77 63	99.74 27	99.61 221	99.18 229	99.76 142	99.61 250	99.00 132	99.92 147	97.72 294	99.60 316	99.62 172

EI-MVSNet		99.38 153	99.44 126	99.21 303	99.58 233	98.09 356	99.26 172	99.46 301	99.62 144	99.75 147	99.67 205	98.54 202	99.85 281	99.15 152	99.92 132	99.68 116

UGNet		99.38 153	99.34 148	99.49 217	98.90 412	98.90 286	99.70 38	99.35 331	99.86 64	98.57 396	99.81 95	98.50 212	99.93 116	99.38 110	99.98 48	99.66 135
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
IMVS_0403		99.37 157	99.39 135	99.28 288	99.71 172	98.55 320	99.19 196	99.71 161	99.41 194	99.67 187	99.60 258	99.12 111	99.84 296	98.45 226	99.70 275	99.45 260

UniMVSNet_NR-MVSNet		99.37 157	99.25 175	99.72 114	99.47 297	99.56 154	98.97 280	99.61 221	99.43 189	99.67 187	99.28 359	97.85 274	99.95 78	99.17 149	99.81 224	99.65 144

UniMVSNet (Re)		99.37 157	99.26 173	99.68 127	99.51 275	99.58 150	98.98 278	99.60 232	99.43 189	99.70 174	99.36 341	97.70 282	99.88 229	99.20 142	99.87 178	99.59 194

CSCG		99.37 157	99.29 165	99.60 175	99.71 172	99.46 174	99.43 118	99.85 77	98.79 288	99.41 283	99.60 258	98.92 146	99.92 147	98.02 263	99.92 132	99.43 278

APD_test1		99.36 161	99.28 168	99.61 171	99.89 39	99.89 10	99.32 146	99.74 145	99.18 229	99.69 177	99.75 145	98.41 222	99.84 296	97.85 283	99.70 275	99.10 358

PM-MVS		99.36 161	99.29 165	99.58 181	99.83 76	99.66 117	98.95 286	99.86 71	98.85 278	99.81 112	99.73 154	98.40 226	99.92 147	98.36 234	99.83 204	99.17 343

new-patchmatchnet		99.35 163	99.57 94	98.71 369	99.82 85	96.62 407	98.55 345	99.75 139	99.50 165	99.88 81	99.87 56	99.31 82	99.88 229	99.43 101	100.00 1	99.62 172

Anonymous20231206		99.35 163	99.31 155	99.47 223	99.74 161	99.06 267	99.28 163	99.74 145	99.23 222	99.72 165	99.53 293	97.63 292	99.88 229	99.11 161	99.84 196	99.48 251

MTAPA		99.35 163	99.20 181	99.80 61	99.81 97	99.81 47	99.33 143	99.53 276	99.27 214	99.42 277	99.63 232	98.21 246	99.95 78	97.83 287	99.79 236	99.65 144

FMVSNet2		99.35 163	99.28 168	99.55 196	99.49 286	99.35 210	99.45 114	99.57 249	99.44 183	99.70 174	99.74 150	97.21 307	99.87 244	99.03 168	99.94 117	99.44 272

3Dnovator+	98.92 3	99.35 163	99.24 177	99.67 131	99.35 330	99.47 170	99.62 67	99.50 290	99.44 183	99.12 340	99.78 122	98.77 166	99.94 95	97.87 280	99.72 270	99.62 172

TSAR-MVS + MP.		99.34 168	99.24 177	99.63 158	99.82 85	99.37 203	99.26 172	99.35 331	98.77 292	99.57 228	99.70 181	99.27 89	99.88 229	97.71 296	99.75 251	99.65 144
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
diffmvs		99.34 168	99.32 153	99.39 254	99.67 206	98.77 298	98.57 342	99.81 104	99.61 148	99.48 262	99.41 324	98.47 213	99.86 263	98.97 175	99.90 144	99.53 225
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DELS-MVS		99.34 168	99.30 160	99.48 221	99.51 275	99.36 207	98.12 386	99.53 276	99.36 203	99.41 283	99.61 250	99.22 94	99.87 244	99.21 139	99.68 288	99.20 335
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
DU-MVS		99.33 171	99.21 180	99.71 119	99.43 309	99.56 154	98.83 304	99.53 276	99.38 199	99.67 187	99.36 341	97.67 286	99.95 78	99.17 149	99.81 224	99.63 161

ab-mvs		99.33 171	99.28 168	99.47 223	99.57 243	99.39 198	99.78 17	99.43 309	98.87 275	99.57 228	99.82 88	98.06 259	99.87 244	98.69 212	99.73 264	99.15 347

DVP-MVS		99.32 173	99.17 185	99.77 75	99.69 192	99.80 51	99.14 216	99.31 340	99.16 236	99.62 211	99.61 250	98.35 230	99.91 176	97.88 277	99.72 270	99.61 183
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
APD-MVS_3200maxsize		99.31 174	99.16 186	99.74 98	99.53 266	99.75 78	99.27 167	99.61 221	99.19 228	99.57 228	99.64 217	98.76 167	99.90 195	97.29 329	99.62 306	99.56 207

icg_test_0407_2		99.30 175	99.29 165	99.31 280	99.71 172	98.55 320	98.17 380	99.71 161	99.41 194	99.73 161	99.60 258	99.17 100	99.92 147	98.45 226	99.70 275	99.45 260

SteuartSystems-ACMMP		99.30 175	99.14 190	99.76 82	99.87 54	99.66 117	99.18 200	99.60 232	98.55 314	99.57 228	99.67 205	99.03 130	99.94 95	97.01 349	99.80 231	99.69 110
Skip Steuart: Steuart Systems R&D Blog.
testgi		99.29 177	99.26 173	99.37 260	99.75 153	98.81 292	98.84 301	99.89 59	98.38 333	99.75 147	99.04 395	99.36 74	99.86 263	99.08 165	99.25 377	99.45 260

ACMMP_NAP		99.28 178	99.11 199	99.79 68	99.75 153	99.81 47	98.95 286	99.53 276	98.27 349	99.53 248	99.73 154	98.75 169	99.87 244	97.70 299	99.83 204	99.68 116

LCM-MVSNet-Re		99.28 178	99.15 189	99.67 131	99.33 344	99.76 70	99.34 137	99.97 20	98.93 267	99.91 61	99.79 110	98.68 178	99.93 116	96.80 363	99.56 325	99.30 313

mvs_anonymous		99.28 178	99.39 135	98.94 339	99.19 373	97.81 374	99.02 261	99.55 260	99.78 100	99.85 95	99.80 100	98.24 241	99.86 263	99.57 81	99.50 343	99.15 347

MVS_Test		99.28 178	99.31 155	99.19 306	99.35 330	98.79 296	99.36 133	99.49 294	99.17 234	99.21 327	99.67 205	98.78 164	99.66 413	99.09 163	99.66 297	99.10 358

SR-MVS-dyc-post		99.27 182	99.11 199	99.73 107	99.54 259	99.74 85	99.26 172	99.62 214	99.16 236	99.52 250	99.64 217	98.41 222	99.91 176	97.27 332	99.61 313	99.54 219

XVS		99.27 182	99.11 199	99.75 93	99.71 172	99.71 98	99.37 129	99.61 221	99.29 210	98.76 379	99.47 313	98.47 213	99.88 229	97.62 308	99.73 264	99.67 125

OPM-MVS		99.26 184	99.13 192	99.63 158	99.70 187	99.61 139	98.58 338	99.48 295	98.50 321	99.52 250	99.63 232	99.14 107	99.76 364	97.89 276	99.77 245	99.51 237
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HFP-MVS		99.25 185	99.08 210	99.76 82	99.73 165	99.70 106	99.31 151	99.59 238	98.36 335	99.36 293	99.37 337	98.80 161	99.91 176	97.43 321	99.75 251	99.68 116

HPM-MVS		99.25 185	99.07 214	99.78 72	99.81 97	99.75 78	99.61 73	99.67 186	97.72 381	99.35 295	99.25 366	99.23 93	99.92 147	97.21 341	99.82 214	99.67 125
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ACMMP		99.25 185	99.08 210	99.74 98	99.79 117	99.68 113	99.50 100	99.65 201	98.07 360	99.52 250	99.69 190	98.57 194	99.92 147	97.18 343	99.79 236	99.63 161
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
LS3D		99.24 188	99.11 199	99.61 171	98.38 448	99.79 54	99.57 85	99.68 181	99.61 148	99.15 335	99.71 171	98.70 176	99.91 176	97.54 314	99.68 288	99.13 355

IMVS_0404		99.23 189	99.20 181	99.32 276	99.71 172	98.55 320	98.57 342	99.71 161	99.41 194	99.52 250	99.60 258	98.12 255	99.95 78	98.45 226	99.70 275	99.45 260

xiu_mvs_v1_base_debu		99.23 189	99.34 148	98.91 345	99.59 228	98.23 342	98.47 357	99.66 191	99.61 148	99.68 180	98.94 411	99.39 65	99.97 42	99.18 146	99.55 329	98.51 428

xiu_mvs_v1_base		99.23 189	99.34 148	98.91 345	99.59 228	98.23 342	98.47 357	99.66 191	99.61 148	99.68 180	98.94 411	99.39 65	99.97 42	99.18 146	99.55 329	98.51 428

xiu_mvs_v1_base_debi		99.23 189	99.34 148	98.91 345	99.59 228	98.23 342	98.47 357	99.66 191	99.61 148	99.68 180	98.94 411	99.39 65	99.97 42	99.18 146	99.55 329	98.51 428

region2R		99.23 189	99.05 221	99.77 75	99.76 140	99.70 106	99.31 151	99.59 238	98.41 329	99.32 304	99.36 341	98.73 173	99.93 116	97.29 329	99.74 258	99.67 125

ACMMPR		99.23 189	99.06 216	99.76 82	99.74 161	99.69 110	99.31 151	99.59 238	98.36 335	99.35 295	99.38 334	98.61 189	99.93 116	97.43 321	99.75 251	99.67 125

XVG-ACMP-BASELINE		99.23 189	99.10 207	99.63 158	99.82 85	99.58 150	98.83 304	99.72 158	98.36 335	99.60 220	99.71 171	98.92 146	99.91 176	97.08 347	99.84 196	99.40 286

CP-MVS		99.23 189	99.05 221	99.75 93	99.66 208	99.66 117	99.38 125	99.62 214	98.38 333	99.06 348	99.27 361	98.79 162	99.94 95	97.51 317	99.82 214	99.66 135

DeepC-MVS_fast	98.47 5	99.23 189	99.12 196	99.56 191	99.28 355	99.22 239	98.99 275	99.40 319	99.08 247	99.58 225	99.64 217	98.90 151	99.83 312	97.44 320	99.75 251	99.63 161
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		99.22 198	99.04 227	99.77 75	99.76 140	99.73 88	99.28 163	99.56 254	98.19 354	99.14 337	99.29 358	98.84 156	99.92 147	97.53 316	99.80 231	99.64 155

D2MVS		99.22 198	99.19 183	99.29 285	99.69 192	98.74 300	98.81 309	99.41 312	98.55 314	99.68 180	99.69 190	98.13 253	99.87 244	98.82 191	99.98 48	99.24 322

LPG-MVS_test		99.22 198	99.05 221	99.74 98	99.82 85	99.63 131	99.16 211	99.73 149	97.56 386	99.64 198	99.69 190	99.37 71	99.89 214	96.66 371	99.87 178	99.69 110

CDS-MVSNet		99.22 198	99.13 192	99.50 213	99.35 330	99.11 255	98.96 284	99.54 266	99.46 178	99.61 217	99.70 181	96.31 340	99.83 312	99.34 118	99.88 166	99.55 210
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_0402		99.22 198	99.14 190	99.45 230	99.79 117	99.43 185	99.28 163	99.68 181	99.54 159	99.40 288	99.56 281	99.07 120	99.82 324	96.01 402	99.96 84	99.11 356

AllTest		99.21 203	99.07 214	99.63 158	99.78 125	99.64 126	99.12 228	99.83 87	98.63 306	99.63 202	99.72 161	98.68 178	99.75 368	96.38 389	99.83 204	99.51 237

XVG-OURS		99.21 203	99.06 216	99.65 144	99.82 85	99.62 133	97.87 414	99.74 145	98.36 335	99.66 193	99.68 201	99.71 28	99.90 195	96.84 361	99.88 166	99.43 278

Fast-Effi-MVS+-dtu		99.20 205	99.12 196	99.43 238	99.25 361	99.69 110	99.05 249	99.82 93	99.50 165	98.97 352	99.05 393	98.98 137	99.98 27	98.20 248	99.24 379	98.62 418

VDD-MVS		99.20 205	99.11 199	99.44 234	99.43 309	98.98 272	99.50 100	98.32 420	99.80 93	99.56 236	99.69 190	96.99 317	99.85 281	98.99 171	99.73 264	99.50 242

PGM-MVS		99.20 205	99.01 234	99.77 75	99.75 153	99.71 98	99.16 211	99.72 158	97.99 364	99.42 277	99.60 258	98.81 157	99.93 116	96.91 355	99.74 258	99.66 135

SR-MVS		99.19 208	99.00 238	99.74 98	99.51 275	99.72 93	99.18 200	99.60 232	98.85 278	99.47 264	99.58 270	98.38 227	99.92 147	96.92 354	99.54 334	99.57 205

SMA-MVS		99.19 208	99.00 238	99.73 107	99.46 301	99.73 88	99.13 223	99.52 281	97.40 397	99.57 228	99.64 217	98.93 143	99.83 312	97.61 310	99.79 236	99.63 161
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
pmmvs5		99.19 208	99.11 199	99.42 240	99.76 140	98.88 288	98.55 345	99.73 149	98.82 283	99.72 165	99.62 241	96.56 327	99.82 324	99.32 123	99.95 102	99.56 207

mPP-MVS		99.19 208	99.00 238	99.76 82	99.76 140	99.68 113	99.38 125	99.54 266	98.34 344	99.01 350	99.50 302	98.53 206	99.93 116	97.18 343	99.78 241	99.66 135

MM		99.18 212	99.05 221	99.55 196	99.35 330	98.81 292	99.05 249	97.79 435	99.99 3	99.48 262	99.59 267	96.29 342	99.95 78	99.94 19	99.98 48	99.88 38

ETV-MVS		99.18 212	99.18 184	99.16 309	99.34 339	99.28 221	99.12 228	99.79 114	99.48 170	98.93 356	98.55 434	99.40 64	99.93 116	98.51 223	99.52 339	98.28 438

VNet		99.18 212	99.06 216	99.56 191	99.24 363	99.36 207	99.33 143	99.31 340	99.67 129	99.47 264	99.57 277	96.48 331	99.84 296	99.15 152	99.30 369	99.47 255

RPSCF		99.18 212	99.02 230	99.64 151	99.83 76	99.85 22	99.44 116	99.82 93	98.33 345	99.50 259	99.78 122	97.90 269	99.65 420	96.78 364	99.83 204	99.44 272

DeepPCF-MVS	98.42 6	99.18 212	99.02 230	99.67 131	99.22 366	99.75 78	97.25 441	99.47 298	98.72 297	99.66 193	99.70 181	99.29 84	99.63 424	98.07 262	99.81 224	99.62 172

EPP-MVSNet		99.17 217	99.00 238	99.66 138	99.80 104	99.43 185	99.70 38	99.24 356	99.48 170	99.56 236	99.77 132	94.89 361	99.93 116	98.72 209	99.89 157	99.63 161

GST-MVS		99.16 218	98.96 251	99.75 93	99.73 165	99.73 88	99.20 190	99.55 260	98.22 351	99.32 304	99.35 346	98.65 185	99.91 176	96.86 358	99.74 258	99.62 172

MVP-Stereo		99.16 218	99.08 210	99.43 238	99.48 291	99.07 265	99.08 244	99.55 260	98.63 306	99.31 309	99.68 201	98.19 249	99.78 352	98.18 252	99.58 322	99.45 260
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
XVG-OURS-SEG-HR		99.16 218	98.99 245	99.66 138	99.84 70	99.64 126	98.25 375	99.73 149	98.39 332	99.63 202	99.43 321	99.70 31	99.90 195	97.34 326	98.64 419	99.44 272

jason		99.16 218	99.11 199	99.32 276	99.75 153	98.44 330	98.26 374	99.39 322	98.70 300	99.74 157	99.30 355	98.54 202	99.97 42	98.48 224	99.82 214	99.55 210
jason: jason.
AstraMVS		99.15 222	99.06 216	99.42 240	99.85 65	98.59 317	99.13 223	97.26 443	99.84 74	99.87 90	99.77 132	96.11 345	99.93 116	99.71 58	99.96 84	99.74 86

DPE-MVS		99.14 223	98.92 258	99.82 44	99.57 243	99.77 63	98.74 320	99.60 232	98.55 314	99.76 142	99.69 190	98.23 245	99.92 147	96.39 388	99.75 251	99.76 81
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MP-MVS-pluss		99.14 223	98.92 258	99.80 61	99.83 76	99.83 34	98.61 331	99.63 211	96.84 417	99.44 270	99.58 270	98.81 157	99.91 176	97.70 299	99.82 214	99.67 125
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VortexMVS		99.13 225	99.24 177	98.79 362	99.67 206	96.60 409	99.24 179	99.80 107	99.85 70	99.93 51	99.84 75	95.06 359	99.89 214	99.80 50	99.98 48	99.89 35

pmmvs4		99.13 225	99.06 216	99.36 265	99.57 243	99.10 262	98.01 399	99.25 353	98.78 290	99.58 225	99.44 320	98.24 241	99.76 364	98.74 202	99.93 128	99.22 328

MVS_111021_LR		99.13 225	99.03 229	99.42 240	99.58 233	99.32 215	97.91 412	99.73 149	98.68 301	99.31 309	99.48 309	99.09 114	99.66 413	97.70 299	99.77 245	99.29 316

guyue		99.12 228	99.02 230	99.41 248	99.84 70	98.56 318	99.19 196	98.30 421	99.82 83	99.84 98	99.75 145	94.84 362	99.92 147	99.68 64	99.94 117	99.74 86

EIA-MVS		99.12 228	99.01 234	99.45 230	99.36 326	99.62 133	99.34 137	99.79 114	98.41 329	98.84 369	98.89 415	98.75 169	99.84 296	98.15 256	99.51 340	98.89 400

TSAR-MVS + GP.		99.12 228	99.04 227	99.38 257	99.34 339	99.16 249	98.15 382	99.29 344	98.18 355	99.63 202	99.62 241	99.18 98	99.68 403	98.20 248	99.74 258	99.30 313

MVS_111021_HR		99.12 228	99.02 230	99.40 251	99.50 281	99.11 255	97.92 410	99.71 161	98.76 295	99.08 344	99.47 313	99.17 100	99.54 438	97.85 283	99.76 247	99.54 219

CANet		99.11 232	99.05 221	99.28 288	98.83 422	98.56 318	98.71 324	99.41 312	99.25 218	99.23 322	99.22 373	97.66 290	99.94 95	99.19 144	99.97 70	99.33 304

WR-MVS		99.11 232	98.93 254	99.66 138	99.30 350	99.42 188	98.42 363	99.37 327	99.04 252	99.57 228	99.20 377	96.89 319	99.86 263	98.66 214	99.87 178	99.70 102

PHI-MVS		99.11 232	98.95 252	99.59 178	99.13 382	99.59 145	99.17 205	99.65 201	97.88 374	99.25 318	99.46 316	98.97 139	99.80 346	97.26 334	99.82 214	99.37 294

SF-MVS		99.10 235	98.93 254	99.62 167	99.58 233	99.51 164	99.13 223	99.65 201	97.97 366	99.42 277	99.61 250	98.86 154	99.87 244	96.45 386	99.68 288	99.49 247

NormalMVS		99.09 236	98.91 262	99.62 167	99.78 125	99.11 255	99.36 133	99.77 126	99.82 83	99.68 180	99.53 293	93.30 380	99.99 8	99.24 133	99.76 247	99.74 86

RRT-MVS		99.08 237	99.00 238	99.33 271	99.27 357	98.65 310	99.62 67	99.93 39	99.66 133	99.67 187	99.82 88	95.27 358	99.93 116	98.64 216	99.09 387	99.41 283

mvsmamba		99.08 237	98.95 252	99.45 230	99.36 326	99.18 248	99.39 122	98.81 391	99.37 200	99.35 295	99.70 181	96.36 339	99.94 95	98.66 214	99.59 320	99.22 328

MSDG		99.08 237	98.98 248	99.37 260	99.60 223	99.13 252	97.54 427	99.74 145	98.84 281	99.53 248	99.55 289	99.10 112	99.79 349	97.07 348	99.86 186	99.18 340

Effi-MVS+-dtu		99.07 240	98.92 258	99.52 208	98.89 415	99.78 57	99.15 213	99.66 191	99.34 204	98.92 359	99.24 371	97.69 284	99.98 27	98.11 258	99.28 372	98.81 407

Effi-MVS+		99.06 241	98.97 249	99.34 268	99.31 346	98.98 272	98.31 370	99.91 51	98.81 285	98.79 376	98.94 411	99.14 107	99.84 296	98.79 195	98.74 412	99.20 335

MP-MVS		99.06 241	98.83 271	99.76 82	99.76 140	99.71 98	99.32 146	99.50 290	98.35 340	98.97 352	99.48 309	98.37 228	99.92 147	95.95 408	99.75 251	99.63 161
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MDA-MVSNet-bldmvs		99.06 241	99.05 221	99.07 325	99.80 104	97.83 373	98.89 293	99.72 158	99.29 210	99.63 202	99.70 181	96.47 332	99.89 214	98.17 254	99.82 214	99.50 242

MSLP-MVS++		99.05 244	99.09 208	98.91 345	99.21 368	98.36 338	98.82 308	99.47 298	98.85 278	98.90 362	99.56 281	98.78 164	99.09 454	98.57 220	99.68 288	99.26 319

1112_ss		99.05 244	98.84 269	99.67 131	99.66 208	99.29 219	98.52 351	99.82 93	97.65 384	99.43 274	99.16 379	96.42 334	99.91 176	99.07 166	99.84 196	99.80 62

ACMP	97.51 14	99.05 244	98.84 269	99.67 131	99.78 125	99.55 158	98.88 294	99.66 191	97.11 412	99.47 264	99.60 258	99.07 120	99.89 214	96.18 397	99.85 191	99.58 199
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MSP-MVS		99.04 247	98.79 277	99.81 52	99.78 125	99.73 88	99.35 136	99.57 249	98.54 317	99.54 243	98.99 402	96.81 321	99.93 116	96.97 352	99.53 336	99.77 76
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
PVSNet_BlendedMVS		99.03 248	99.01 234	99.09 320	99.54 259	97.99 362	98.58 338	99.82 93	97.62 385	99.34 299	99.71 171	98.52 209	99.77 361	97.98 268	99.97 70	99.52 235

IS-MVSNet		99.03 248	98.85 267	99.55 196	99.80 104	99.25 229	99.73 30	99.15 372	99.37 200	99.61 217	99.71 171	94.73 365	99.81 339	97.70 299	99.88 166	99.58 199

MGCFI-Net		99.02 250	99.01 234	99.06 327	99.11 389	98.60 315	99.63 64	99.67 186	99.63 141	98.58 394	97.65 453	99.07 120	99.57 434	98.85 187	98.92 399	99.03 380

sasdasda		99.02 250	99.00 238	99.09 320	99.10 391	98.70 302	99.61 73	99.66 191	99.63 141	98.64 388	97.65 453	99.04 128	99.54 438	98.79 195	98.92 399	99.04 378

xiu_mvs_v2_base		99.02 250	99.11 199	98.77 364	99.37 323	98.09 356	98.13 385	99.51 286	99.47 175	99.42 277	98.54 435	99.38 69	99.97 42	98.83 189	99.33 365	98.24 440

Fast-Effi-MVS+		99.02 250	98.87 265	99.46 227	99.38 321	99.50 165	99.04 254	99.79 114	97.17 408	98.62 390	98.74 425	99.34 78	99.95 78	98.32 238	99.41 355	98.92 396

canonicalmvs		99.02 250	99.00 238	99.09 320	99.10 391	98.70 302	99.61 73	99.66 191	99.63 141	98.64 388	97.65 453	99.04 128	99.54 438	98.79 195	98.92 399	99.04 378

MCST-MVS		99.02 250	98.81 274	99.65 144	99.58 233	99.49 166	98.58 338	99.07 377	98.40 331	99.04 349	99.25 366	98.51 211	99.80 346	97.31 328	99.51 340	99.65 144

SymmetryMVS		99.01 256	98.82 272	99.58 181	99.65 213	99.11 255	99.36 133	99.20 366	99.82 83	99.68 180	99.53 293	93.30 380	99.99 8	99.24 133	99.63 304	99.64 155

SD-MVS		99.01 256	99.30 160	98.15 395	99.50 281	99.40 195	98.94 288	99.61 221	99.22 226	99.75 147	99.82 88	99.54 50	95.51 465	97.48 318	99.87 178	99.54 219
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
LF4IMVS		99.01 256	98.92 258	99.27 293	99.71 172	99.28 221	98.59 336	99.77 126	98.32 346	99.39 290	99.41 324	98.62 187	99.84 296	96.62 376	99.84 196	98.69 416

IterMVS-SCA-FT		99.00 259	99.16 186	98.51 377	99.75 153	95.90 423	98.07 393	99.84 83	99.84 74	99.89 71	99.73 154	96.01 348	99.99 8	99.33 121	100.00 1	99.63 161

MS-PatchMatch		99.00 259	98.97 249	99.09 320	99.11 389	98.19 346	98.76 318	99.33 334	98.49 323	99.44 270	99.58 270	98.21 246	99.69 391	98.20 248	99.62 306	99.39 289

PS-MVSNAJ		99.00 259	99.08 210	98.76 365	99.37 323	98.10 355	98.00 401	99.51 286	99.47 175	99.41 283	98.50 437	99.28 86	99.97 42	98.83 189	99.34 364	98.20 444

CNVR-MVS		98.99 262	98.80 276	99.56 191	99.25 361	99.43 185	98.54 348	99.27 348	98.58 312	98.80 374	99.43 321	98.53 206	99.70 385	97.22 340	99.59 320	99.54 219

VDDNet		98.97 263	98.82 272	99.42 240	99.71 172	98.81 292	99.62 67	98.68 397	99.81 89	99.38 291	99.80 100	94.25 369	99.85 281	98.79 195	99.32 367	99.59 194

IterMVS		98.97 263	99.16 186	98.42 382	99.74 161	95.64 427	98.06 395	99.83 87	99.83 80	99.85 95	99.74 150	96.10 347	99.99 8	99.27 132	100.00 1	99.63 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TinyColmap		98.97 263	98.93 254	99.07 325	99.46 301	98.19 346	97.75 418	99.75 139	98.79 288	99.54 243	99.70 181	98.97 139	99.62 425	96.63 375	99.83 204	99.41 283

HPM-MVS++		98.96 266	98.70 283	99.74 98	99.52 273	99.71 98	98.86 297	99.19 367	98.47 325	98.59 393	99.06 392	98.08 258	99.91 176	96.94 353	99.60 316	99.60 187

lupinMVS		98.96 266	98.87 265	99.24 301	99.57 243	98.40 333	98.12 386	99.18 368	98.28 348	99.63 202	99.13 381	98.02 261	99.97 42	98.22 246	99.69 283	99.35 300

USDC		98.96 266	98.93 254	99.05 328	99.54 259	97.99 362	97.07 447	99.80 107	98.21 352	99.75 147	99.77 132	98.43 219	99.64 422	97.90 275	99.88 166	99.51 237

YYNet1		98.95 269	98.99 245	98.84 356	99.64 214	97.14 397	98.22 377	99.32 336	98.92 269	99.59 223	99.66 210	97.40 298	99.83 312	98.27 241	99.90 144	99.55 210

MDA-MVSNet_test_wron		98.95 269	98.99 245	98.85 354	99.64 214	97.16 395	98.23 376	99.33 334	98.93 267	99.56 236	99.66 210	97.39 300	99.83 312	98.29 239	99.88 166	99.55 210

Test_1112_low_res		98.95 269	98.73 279	99.63 158	99.68 200	99.15 251	98.09 390	99.80 107	97.14 410	99.46 268	99.40 328	96.11 345	99.89 214	99.01 170	99.84 196	99.84 50

CANet_DTU		98.91 272	98.85 267	99.09 320	98.79 428	98.13 351	98.18 378	99.31 340	99.48 170	98.86 367	99.51 299	96.56 327	99.95 78	99.05 167	99.95 102	99.19 338

HyFIR lowres test		98.91 272	98.64 285	99.73 107	99.85 65	99.47 170	98.07 393	99.83 87	98.64 305	99.89 71	99.60 258	92.57 389	100.00 1	99.33 121	99.97 70	99.72 94

HQP_MVS		98.90 274	98.68 284	99.55 196	99.58 233	99.24 233	98.80 312	99.54 266	98.94 264	99.14 337	99.25 366	97.24 305	99.82 324	95.84 412	99.78 241	99.60 187

sss		98.90 274	98.77 278	99.27 293	99.48 291	98.44 330	98.72 322	99.32 336	97.94 370	99.37 292	99.35 346	96.31 340	99.91 176	98.85 187	99.63 304	99.47 255

OMC-MVS		98.90 274	98.72 280	99.44 234	99.39 318	99.42 188	98.58 338	99.64 209	97.31 402	99.44 270	99.62 241	98.59 191	99.69 391	96.17 398	99.79 236	99.22 328

ppachtmachnet_test		98.89 277	99.12 196	98.20 394	99.66 208	95.24 434	97.63 423	99.68 181	99.08 247	99.78 126	99.62 241	98.65 185	99.88 229	98.02 263	99.96 84	99.48 251

new_pmnet		98.88 278	98.89 263	98.84 356	99.70 187	97.62 381	98.15 382	99.50 290	97.98 365	99.62 211	99.54 291	98.15 252	99.94 95	97.55 313	99.84 196	98.95 391

K. test v3		98.87 279	98.60 288	99.69 125	99.93 24	99.46 174	99.74 27	94.97 454	99.78 100	99.88 81	99.88 50	93.66 377	99.97 42	99.61 75	99.95 102	99.64 155

APD-MVS		98.87 279	98.59 290	99.71 119	99.50 281	99.62 133	99.01 265	99.57 249	96.80 419	99.54 243	99.63 232	98.29 236	99.91 176	95.24 424	99.71 273	99.61 183
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
our_test_3		98.85 281	99.09 208	98.13 396	99.66 208	94.90 438	97.72 419	99.58 247	99.07 249	99.64 198	99.62 241	98.19 249	99.93 116	98.41 231	99.95 102	99.55 210

UnsupCasMVSNet_eth		98.83 282	98.57 294	99.59 178	99.68 200	99.45 179	98.99 275	99.67 186	99.48 170	99.55 241	99.36 341	94.92 360	99.86 263	98.95 181	96.57 455	99.45 260

NCCC		98.82 283	98.57 294	99.58 181	99.21 368	99.31 216	98.61 331	99.25 353	98.65 304	98.43 404	99.26 364	97.86 272	99.81 339	96.55 377	99.27 375	99.61 183

PMVS	92.94 21	98.82 283	98.81 274	98.85 354	99.84 70	97.99 362	99.20 190	99.47 298	99.71 114	99.42 277	99.82 88	98.09 256	99.47 446	93.88 443	99.85 191	99.07 374
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GDP-MVS		98.81 285	98.57 294	99.50 213	99.53 266	99.12 254	99.28 163	99.86 71	99.53 161	99.57 228	99.32 350	90.88 410	99.98 27	99.46 97	99.74 258	99.42 282

FMVSNet3		98.80 286	98.63 287	99.32 276	99.13 382	98.72 301	99.10 236	99.48 295	99.23 222	99.62 211	99.64 217	92.57 389	99.86 263	98.96 177	99.90 144	99.39 289

Patchmtry		98.78 287	98.54 299	99.49 217	98.89 415	99.19 245	99.32 146	99.67 186	99.65 136	99.72 165	99.79 110	91.87 397	99.95 78	98.00 267	99.97 70	99.33 304

Vis-MVSNet (Re-imp)		98.77 288	98.58 293	99.34 268	99.78 125	98.88 288	99.61 73	99.56 254	99.11 246	99.24 321	99.56 281	93.00 387	99.78 352	97.43 321	99.89 157	99.35 300

CLD-MVS		98.76 289	98.57 294	99.33 271	99.57 243	98.97 275	97.53 429	99.55 260	96.41 422	99.27 316	99.13 381	99.07 120	99.78 352	96.73 367	99.89 157	99.23 326
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
Anonymous202405211		98.75 290	98.46 304	99.63 158	99.34 339	99.66 117	99.47 110	97.65 436	99.28 213	99.56 236	99.50 302	93.15 383	99.84 296	98.62 217	99.58 322	99.40 286

CPTT-MVS		98.74 291	98.44 307	99.64 151	99.61 221	99.38 200	99.18 200	99.55 260	96.49 421	99.27 316	99.37 337	97.11 313	99.92 147	95.74 415	99.67 294	99.62 172

F-COLMAP		98.74 291	98.45 306	99.62 167	99.57 243	99.47 170	98.84 301	99.65 201	96.31 425	98.93 356	99.19 378	97.68 285	99.87 244	96.52 379	99.37 360	99.53 225

N_pmnet		98.73 293	98.53 300	99.35 267	99.72 169	98.67 304	98.34 367	94.65 455	98.35 340	99.79 122	99.68 201	98.03 260	99.93 116	98.28 240	99.92 132	99.44 272

BP-MVS1		98.72 294	98.46 304	99.50 213	99.53 266	99.00 269	99.34 137	98.53 406	99.65 136	99.73 161	99.38 334	90.62 414	99.96 67	99.50 92	99.86 186	99.55 210

c3_l		98.72 294	98.71 281	98.72 367	99.12 384	97.22 394	97.68 422	99.56 254	98.90 271	99.54 243	99.48 309	96.37 338	99.73 374	97.88 277	99.88 166	99.21 331

CL-MVSNet_self_test		98.71 296	98.56 298	99.15 311	99.22 366	98.66 307	97.14 444	99.51 286	98.09 359	99.54 243	99.27 361	96.87 320	99.74 371	98.43 230	98.96 396	99.03 380

PVSNet_Blended		98.70 297	98.59 290	99.02 330	99.54 259	97.99 362	97.58 426	99.82 93	95.70 433	99.34 299	98.98 405	98.52 209	99.77 361	97.98 268	99.83 204	99.30 313

dmvs_re		98.69 298	98.48 302	99.31 280	99.55 257	99.42 188	99.54 90	98.38 417	99.32 208	98.72 382	98.71 426	96.76 323	99.21 452	96.01 402	99.35 363	99.31 311

eth_miper_zixun_eth		98.68 299	98.71 281	98.60 373	99.10 391	96.84 404	97.52 431	99.54 266	98.94 264	99.58 225	99.48 309	96.25 343	99.76 364	98.01 266	99.93 128	99.21 331

PatchMatch-RL		98.68 299	98.47 303	99.30 284	99.44 306	99.28 221	98.14 384	99.54 266	97.12 411	99.11 341	99.25 366	97.80 277	99.70 385	96.51 380	99.30 369	98.93 394

miper_lstm_enhance		98.65 301	98.60 288	98.82 361	99.20 371	97.33 391	97.78 417	99.66 191	99.01 255	99.59 223	99.50 302	94.62 366	99.85 281	98.12 257	99.90 144	99.26 319

h-mvs33		98.61 302	98.34 318	99.44 234	99.60 223	98.67 304	99.27 167	99.44 306	99.68 125	99.32 304	99.49 306	92.50 392	100.00 1	99.24 133	96.51 456	99.65 144

MVS_0304		98.61 302	98.30 323	99.52 208	97.88 460	98.95 278	98.76 318	94.11 459	99.84 74	99.32 304	99.57 277	95.57 354	99.95 78	99.68 64	99.98 48	99.68 116

CVMVSNet		98.61 302	98.88 264	97.80 408	99.58 233	93.60 446	99.26 172	99.64 209	99.66 133	99.72 165	99.67 205	93.26 382	99.93 116	99.30 126	99.81 224	99.87 42

Patchmatch-RL test		98.60 305	98.36 315	99.33 271	99.77 136	99.07 265	98.27 372	99.87 65	98.91 270	99.74 157	99.72 161	90.57 416	99.79 349	98.55 221	99.85 191	99.11 356

RPMNet		98.60 305	98.53 300	98.83 358	99.05 397	98.12 352	99.30 154	99.62 214	99.86 64	99.16 333	99.74 150	92.53 391	99.92 147	98.75 201	98.77 408	98.44 433

AdaColmap		98.60 305	98.35 317	99.38 257	99.12 384	99.22 239	98.67 326	99.42 311	97.84 378	98.81 372	99.27 361	97.32 303	99.81 339	95.14 426	99.53 336	99.10 358

miper_ehance_all_eth		98.59 308	98.59 290	98.59 374	98.98 407	97.07 398	97.49 432	99.52 281	98.50 321	99.52 250	99.37 337	96.41 336	99.71 381	97.86 281	99.62 306	99.00 387

WTY-MVS		98.59 308	98.37 314	99.26 296	99.43 309	98.40 333	98.74 320	99.13 375	98.10 357	99.21 327	99.24 371	94.82 363	99.90 195	97.86 281	98.77 408	99.49 247

CNLPA		98.57 310	98.34 318	99.28 288	99.18 376	99.10 262	98.34 367	99.41 312	98.48 324	98.52 399	98.98 405	97.05 315	99.78 352	95.59 417	99.50 343	98.96 389

CDPH-MVS		98.56 311	98.20 330	99.61 171	99.50 281	99.46 174	98.32 369	99.41 312	95.22 438	99.21 327	99.10 389	98.34 232	99.82 324	95.09 428	99.66 297	99.56 207

UnsupCasMVSNet_bld		98.55 312	98.27 326	99.40 251	99.56 254	99.37 203	97.97 406	99.68 181	97.49 393	99.08 344	99.35 346	95.41 357	99.82 324	97.70 299	98.19 436	99.01 386

cl____		98.54 313	98.41 310	98.92 343	99.03 401	97.80 376	97.46 433	99.59 238	98.90 271	99.60 220	99.46 316	93.85 373	99.78 352	97.97 270	99.89 157	99.17 343

DIV-MVS_self_test		98.54 313	98.42 309	98.92 343	99.03 401	97.80 376	97.46 433	99.59 238	98.90 271	99.60 220	99.46 316	93.87 372	99.78 352	97.97 270	99.89 157	99.18 340

FA-MVS(test-final)		98.52 315	98.32 320	99.10 319	99.48 291	98.67 304	99.77 19	98.60 404	97.35 400	99.63 202	99.80 100	93.07 385	99.84 296	97.92 273	99.30 369	98.78 410

hse-mvs2		98.52 315	98.30 323	99.16 309	99.29 352	98.60 315	98.77 317	99.02 382	99.68 125	99.32 304	99.04 395	92.50 392	99.85 281	99.24 133	97.87 446	99.03 380

MG-MVS		98.52 315	98.39 312	98.94 339	99.15 379	97.39 390	98.18 378	99.21 363	98.89 274	99.23 322	99.63 232	97.37 301	99.74 371	94.22 437	99.61 313	99.69 110

DP-MVS Recon		98.50 318	98.23 327	99.31 280	99.49 286	99.46 174	98.56 344	99.63 211	94.86 444	98.85 368	99.37 337	97.81 276	99.59 432	96.08 399	99.44 350	98.88 401

CMPMVS	77.52 23	98.50 318	98.19 333	99.41 248	98.33 450	99.56 154	99.01 265	99.59 238	95.44 435	99.57 228	99.80 100	95.64 351	99.46 448	96.47 384	99.92 132	99.21 331
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
114514_t		98.49 320	98.11 338	99.64 151	99.73 165	99.58 150	99.24 179	99.76 134	89.94 456	99.42 277	99.56 281	97.76 281	99.86 263	97.74 293	99.82 214	99.47 255

PMMVS		98.49 320	98.29 325	99.11 317	98.96 409	98.42 332	97.54 427	99.32 336	97.53 390	98.47 402	98.15 445	97.88 271	99.82 324	97.46 319	99.24 379	99.09 363

MVSTER		98.47 322	98.22 328	99.24 301	99.06 396	98.35 339	99.08 244	99.46 301	99.27 214	99.75 147	99.66 210	88.61 427	99.85 281	99.14 158	99.92 132	99.52 235

LFMVS		98.46 323	98.19 333	99.26 296	99.24 363	98.52 326	99.62 67	96.94 445	99.87 61	99.31 309	99.58 270	91.04 405	99.81 339	98.68 213	99.42 354	99.45 260

PatchT		98.45 324	98.32 320	98.83 358	98.94 410	98.29 340	99.24 179	98.82 390	99.84 74	99.08 344	99.76 137	91.37 400	99.94 95	98.82 191	99.00 394	98.26 439

MIMVSNet		98.43 325	98.20 330	99.11 317	99.53 266	98.38 337	99.58 82	98.61 402	98.96 260	99.33 301	99.76 137	90.92 407	99.81 339	97.38 324	99.76 247	99.15 347

PVSNet	97.47 15	98.42 326	98.44 307	98.35 385	99.46 301	96.26 416	96.70 452	99.34 333	97.68 383	99.00 351	99.13 381	97.40 298	99.72 376	97.59 312	99.68 288	99.08 369

CHOSEN 280x420		98.41 327	98.41 310	98.40 383	99.34 339	95.89 424	96.94 449	99.44 306	98.80 287	99.25 318	99.52 297	93.51 379	99.98 27	98.94 182	99.98 48	99.32 307

BH-RMVSNet		98.41 327	98.14 336	99.21 303	99.21 368	98.47 327	98.60 333	98.26 422	98.35 340	98.93 356	99.31 353	97.20 310	99.66 413	94.32 435	99.10 386	99.51 237

QAPM		98.40 329	97.99 345	99.65 144	99.39 318	99.47 170	99.67 53	99.52 281	91.70 453	98.78 378	99.80 100	98.55 198	99.95 78	94.71 432	99.75 251	99.53 225

API-MVS		98.38 330	98.39 312	98.35 385	98.83 422	99.26 226	99.14 216	99.18 368	98.59 311	98.66 387	98.78 423	98.61 189	99.57 434	94.14 438	99.56 325	96.21 459

HQP-MVS		98.36 331	98.02 344	99.39 254	99.31 346	98.94 279	97.98 403	99.37 327	97.45 394	98.15 413	98.83 419	96.67 324	99.70 385	94.73 430	99.67 294	99.53 225

PAPM_NR		98.36 331	98.04 342	99.33 271	99.48 291	98.93 282	98.79 315	99.28 347	97.54 389	98.56 398	98.57 432	97.12 312	99.69 391	94.09 439	98.90 403	99.38 291

PLC	97.35 16	98.36 331	97.99 345	99.48 221	99.32 345	99.24 233	98.50 353	99.51 286	95.19 440	98.58 394	98.96 409	96.95 318	99.83 312	95.63 416	99.25 377	99.37 294
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
train_agg		98.35 334	97.95 349	99.57 188	99.35 330	99.35 210	98.11 388	99.41 312	94.90 442	97.92 424	98.99 402	98.02 261	99.85 281	95.38 422	99.44 350	99.50 242

CR-MVSNet		98.35 334	98.20 330	98.83 358	99.05 397	98.12 352	99.30 154	99.67 186	97.39 398	99.16 333	99.79 110	91.87 397	99.91 176	98.78 199	98.77 408	98.44 433

WB-MVSnew		98.34 336	98.14 336	98.96 336	98.14 457	97.90 370	98.27 372	97.26 443	98.63 306	98.80 374	98.00 448	97.77 279	99.90 195	97.37 325	98.98 395	99.09 363

DPM-MVS		98.28 337	97.94 353	99.32 276	99.36 326	99.11 255	97.31 439	98.78 393	96.88 415	98.84 369	99.11 388	97.77 279	99.61 430	94.03 441	99.36 361	99.23 326

alignmvs		98.28 337	97.96 348	99.25 299	99.12 384	98.93 282	99.03 257	98.42 413	99.64 139	98.72 382	97.85 450	90.86 411	99.62 425	98.88 185	99.13 383	99.19 338

test_yl		98.25 339	97.95 349	99.13 315	99.17 377	98.47 327	99.00 268	98.67 399	98.97 258	99.22 325	99.02 400	91.31 401	99.69 391	97.26 334	98.93 397	99.24 322

DCV-MVSNet		98.25 339	97.95 349	99.13 315	99.17 377	98.47 327	99.00 268	98.67 399	98.97 258	99.22 325	99.02 400	91.31 401	99.69 391	97.26 334	98.93 397	99.24 322

MAR-MVS		98.24 341	97.92 355	99.19 306	98.78 430	99.65 123	99.17 205	99.14 373	95.36 436	98.04 420	98.81 422	97.47 295	99.72 376	95.47 420	99.06 388	98.21 442
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
MonoMVSNet		98.23 342	98.32 320	97.99 399	98.97 408	96.62 407	99.49 105	98.42 413	99.62 144	99.40 288	99.79 110	95.51 355	98.58 461	97.68 307	95.98 459	98.76 413

OpenMVS	98.12 10	98.23 342	97.89 358	99.26 296	99.19 373	99.26 226	99.65 62	99.69 178	91.33 454	98.14 417	99.77 132	98.28 237	99.96 67	95.41 421	99.55 329	98.58 423

MVStest1		98.22 344	98.09 339	98.62 371	99.04 400	96.23 417	99.20 190	99.92 42	99.44 183	99.98 14	99.87 56	85.87 440	99.67 408	99.91 31	99.57 324	99.95 14

BH-untuned		98.22 344	98.09 339	98.58 376	99.38 321	97.24 393	98.55 345	98.98 385	97.81 379	99.20 332	98.76 424	97.01 316	99.65 420	94.83 429	98.33 429	98.86 403

HY-MVS	98.23 9	98.21 346	97.95 349	98.99 332	99.03 401	98.24 341	99.61 73	98.72 395	96.81 418	98.73 381	99.51 299	94.06 370	99.86 263	96.91 355	98.20 434	98.86 403

Syy-MVS		98.17 347	97.85 359	99.15 311	98.50 445	98.79 296	98.60 333	99.21 363	97.89 372	96.76 448	96.37 471	95.47 356	99.57 434	99.10 162	98.73 415	99.09 363

EPNet		98.13 348	97.77 363	99.18 308	94.57 468	97.99 362	99.24 179	97.96 429	99.74 105	97.29 441	99.62 241	93.13 384	99.97 42	98.59 218	99.83 204	99.58 199
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SCA		98.11 349	98.36 315	97.36 420	99.20 371	92.99 448	98.17 380	98.49 410	98.24 350	99.10 343	99.57 277	96.01 348	99.94 95	96.86 358	99.62 306	99.14 352

Patchmatch-test		98.10 350	97.98 347	98.48 379	99.27 357	96.48 410	99.40 120	99.07 377	98.81 285	99.23 322	99.57 277	90.11 420	99.87 244	96.69 368	99.64 301	99.09 363

pmmvs3		98.08 351	97.80 360	98.91 345	99.41 316	97.69 380	97.87 414	99.66 191	95.87 429	99.50 259	99.51 299	90.35 418	99.97 42	98.55 221	99.47 347	99.08 369

JIA-IIPM		98.06 352	97.92 355	98.50 378	98.59 441	97.02 399	98.80 312	98.51 408	99.88 59	97.89 426	99.87 56	91.89 396	99.90 195	98.16 255	97.68 448	98.59 421

miper_enhance_ethall		98.03 353	97.94 353	98.32 388	98.27 451	96.43 412	96.95 448	99.41 312	96.37 424	99.43 274	98.96 409	94.74 364	99.69 391	97.71 296	99.62 306	98.83 406

TAPA-MVS	97.92 13	98.03 353	97.55 369	99.46 227	99.47 297	99.44 181	98.50 353	99.62 214	86.79 457	99.07 347	99.26 364	98.26 240	99.62 425	97.28 331	99.73 264	99.31 311
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
1314		98.00 355	97.90 357	98.27 393	98.90 412	97.45 387	99.30 154	99.06 379	94.98 441	97.21 443	99.12 385	98.43 219	99.67 408	95.58 418	98.56 422	97.71 451

GA-MVS		97.99 356	97.68 366	98.93 342	99.52 273	98.04 360	97.19 443	99.05 380	98.32 346	98.81 372	98.97 407	89.89 423	99.41 449	98.33 237	99.05 390	99.34 303

MVS-HIRNet		97.86 357	98.22 328	96.76 430	99.28 355	91.53 457	98.38 365	92.60 462	99.13 242	99.31 309	99.96 15	97.18 311	99.68 403	98.34 236	99.83 204	99.07 374

FE-MVS		97.85 358	97.42 372	99.15 311	99.44 306	98.75 299	99.77 19	98.20 424	95.85 430	99.33 301	99.80 100	88.86 426	99.88 229	96.40 387	99.12 384	98.81 407

AUN-MVS		97.82 359	97.38 373	99.14 314	99.27 357	98.53 324	98.72 322	99.02 382	98.10 357	97.18 444	99.03 399	89.26 425	99.85 281	97.94 272	97.91 444	99.03 380

FMVSNet5		97.80 360	97.25 377	99.42 240	98.83 422	98.97 275	99.38 125	99.80 107	98.87 275	99.25 318	99.69 190	80.60 450	99.91 176	98.96 177	99.90 144	99.38 291

ADS-MVSNet2		97.78 361	97.66 368	98.12 397	99.14 380	95.36 431	99.22 187	98.75 394	96.97 413	98.25 409	99.64 217	90.90 408	99.94 95	96.51 380	99.56 325	99.08 369

test1111		97.74 362	98.16 335	96.49 436	99.60 223	89.86 467	99.71 37	91.21 463	99.89 54	99.88 81	99.87 56	93.73 376	99.90 195	99.56 82	99.99 16	99.70 102

ECVR-MVS		97.73 363	98.04 342	96.78 429	99.59 228	90.81 462	99.72 33	90.43 465	99.89 54	99.86 92	99.86 63	93.60 378	99.89 214	99.46 97	99.99 16	99.65 144

baseline1		97.73 363	97.33 374	98.96 336	99.30 350	97.73 378	99.40 120	98.42 413	99.33 207	99.46 268	99.21 375	91.18 403	99.82 324	98.35 235	91.26 463	99.32 307

tpmrst		97.73 363	98.07 341	96.73 433	98.71 437	92.00 452	99.10 236	98.86 387	98.52 319	98.92 359	99.54 291	91.90 395	99.82 324	98.02 263	99.03 392	98.37 435

ADS-MVSNet		97.72 366	97.67 367	97.86 406	99.14 380	94.65 439	99.22 187	98.86 387	96.97 413	98.25 409	99.64 217	90.90 408	99.84 296	96.51 380	99.56 325	99.08 369

PatchmatchNet		97.65 367	97.80 360	97.18 426	98.82 425	92.49 450	99.17 205	98.39 416	98.12 356	98.79 376	99.58 270	90.71 413	99.89 214	97.23 339	99.41 355	99.16 345
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		97.62 368	97.20 378	98.90 351	99.76 140	97.40 389	99.48 107	94.36 456	99.06 251	99.70 174	99.49 306	84.55 443	99.94 95	98.73 207	99.65 299	99.36 297

EPNet_dtu		97.62 368	97.79 362	97.11 428	96.67 465	92.31 451	98.51 352	98.04 427	99.24 220	95.77 457	99.47 313	93.78 375	99.66 413	98.98 173	99.62 306	99.37 294
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
wuyk23d		97.58 370	99.13 192	92.93 444	99.69 192	99.49 166	99.52 92	99.77 126	97.97 366	99.96 32	99.79 110	99.84 16	99.94 95	95.85 411	99.82 214	79.36 462

cl22		97.56 371	97.28 375	98.40 383	98.37 449	96.75 405	97.24 442	99.37 327	97.31 402	99.41 283	99.22 373	87.30 429	99.37 450	97.70 299	99.62 306	99.08 369

PAPR		97.56 371	97.07 381	99.04 329	98.80 426	98.11 354	97.63 423	99.25 353	94.56 447	98.02 422	98.25 442	97.43 297	99.68 403	90.90 450	98.74 412	99.33 304

WBMVS		97.50 373	97.18 379	98.48 379	98.85 420	95.89 424	98.44 362	99.52 281	99.53 161	99.52 250	99.42 323	80.10 451	99.86 263	99.24 133	99.95 102	99.68 116

thisisatest0530		97.45 374	96.95 385	98.94 339	99.68 200	97.73 378	99.09 241	94.19 458	98.61 310	99.56 236	99.30 355	84.30 445	99.93 116	98.27 241	99.54 334	99.16 345

TR-MVS		97.44 375	97.15 380	98.32 388	98.53 443	97.46 386	98.47 357	97.91 431	96.85 416	98.21 412	98.51 436	96.42 334	99.51 444	92.16 446	97.29 451	97.98 448

SD_0403		97.42 376	96.90 389	98.98 334	99.54 259	97.90 370	99.52 92	99.54 266	99.34 204	97.87 428	98.85 418	98.72 174	99.64 422	78.93 463	99.83 204	99.40 286

reproduce_monomvs		97.40 377	97.46 370	97.20 425	99.05 397	91.91 453	99.20 190	99.18 368	99.84 74	99.86 92	99.75 145	80.67 448	99.83 312	99.69 62	99.95 102	99.85 47

tpmvs		97.39 378	97.69 365	96.52 435	98.41 447	91.76 454	99.30 154	98.94 386	97.74 380	97.85 430	99.55 289	92.40 394	99.73 374	96.25 394	98.73 415	98.06 447

test0.0.03 1		97.37 379	96.91 388	98.74 366	97.72 461	97.57 382	97.60 425	97.36 442	98.00 362	99.21 327	98.02 446	90.04 421	99.79 349	98.37 233	95.89 460	98.86 403

OpenMVS_ROB	97.31 17	97.36 380	96.84 390	98.89 352	99.29 352	99.45 179	98.87 296	99.48 295	86.54 459	99.44 270	99.74 150	97.34 302	99.86 263	91.61 447	99.28 372	97.37 455

dmvs_testset		97.27 381	96.83 391	98.59 374	99.46 301	97.55 383	99.25 178	96.84 446	98.78 290	97.24 442	97.67 452	97.11 313	98.97 456	86.59 461	98.54 423	99.27 317

BH-w/o		97.20 382	97.01 383	97.76 409	99.08 395	95.69 426	98.03 398	98.52 407	95.76 432	97.96 423	98.02 446	95.62 352	99.47 446	92.82 445	97.25 452	98.12 446

test-LLR		97.15 383	96.95 385	97.74 411	98.18 454	95.02 436	97.38 435	96.10 447	98.00 362	97.81 432	98.58 430	90.04 421	99.91 176	97.69 305	98.78 406	98.31 436

tpm		97.15 383	96.95 385	97.75 410	98.91 411	94.24 441	99.32 146	97.96 429	97.71 382	98.29 407	99.32 350	86.72 437	99.92 147	98.10 261	96.24 458	99.09 363

E-PMN		97.14 385	97.43 371	96.27 438	98.79 428	91.62 456	95.54 457	99.01 384	99.44 183	98.88 363	99.12 385	92.78 388	99.68 403	94.30 436	99.03 392	97.50 452

cascas		96.99 386	96.82 392	97.48 416	97.57 464	95.64 427	96.43 454	99.56 254	91.75 452	97.13 446	97.61 456	95.58 353	98.63 459	96.68 369	99.11 385	98.18 445

thisisatest0515		96.98 387	96.42 395	98.66 370	99.42 314	97.47 385	97.27 440	94.30 457	97.24 404	99.15 335	98.86 417	85.01 441	99.87 244	97.10 345	99.39 357	98.63 417

EMVS		96.96 388	97.28 375	95.99 442	98.76 433	91.03 460	95.26 459	98.61 402	99.34 204	98.92 359	98.88 416	93.79 374	99.66 413	92.87 444	99.05 390	97.30 456

dp		96.86 389	97.07 381	96.24 439	98.68 439	90.30 466	99.19 196	98.38 417	97.35 400	98.23 411	99.59 267	87.23 430	99.82 324	96.27 393	98.73 415	98.59 421

baseline2		96.83 390	96.28 397	98.46 381	99.09 394	96.91 402	98.83 304	93.87 461	97.23 405	96.23 456	98.36 439	88.12 428	99.90 195	96.68 369	98.14 439	98.57 425

ET-MVSNet_ETH3D		96.78 391	96.07 401	98.91 345	99.26 360	97.92 369	97.70 421	96.05 450	97.96 369	92.37 463	98.43 438	87.06 431	99.90 195	98.27 241	97.56 449	98.91 397

tpm cat1		96.78 391	96.98 384	96.16 440	98.85 420	90.59 464	99.08 244	99.32 336	92.37 450	97.73 436	99.46 316	91.15 404	99.69 391	96.07 400	98.80 405	98.21 442

PCF-MVS	96.03 18	96.73 393	95.86 406	99.33 271	99.44 306	99.16 249	96.87 450	99.44 306	86.58 458	98.95 354	99.40 328	94.38 368	99.88 229	87.93 455	99.80 231	98.95 391
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
CostFormer		96.71 394	96.79 393	96.46 437	98.90 412	90.71 463	99.41 119	98.68 397	94.69 446	98.14 417	99.34 349	86.32 439	99.80 346	97.60 311	98.07 442	98.88 401

MVE	92.54 22	96.66 395	96.11 400	98.31 390	99.68 200	97.55 383	97.94 408	95.60 453	99.37 200	90.68 464	98.70 428	96.56 327	98.61 460	86.94 460	99.55 329	98.77 412
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
thres600view7		96.60 396	96.16 399	97.93 403	99.63 216	96.09 421	99.18 200	97.57 437	98.77 292	98.72 382	97.32 458	87.04 432	99.72 376	88.57 453	98.62 420	97.98 448

UBG		96.53 397	95.95 403	98.29 392	98.87 418	96.31 415	98.48 356	98.07 426	98.83 282	97.32 439	96.54 469	79.81 453	99.62 425	96.84 361	98.74 412	98.95 391

EPMVS		96.53 397	96.32 396	97.17 427	98.18 454	92.97 449	99.39 122	89.95 466	98.21 352	98.61 391	99.59 267	86.69 438	99.72 376	96.99 350	99.23 381	98.81 407

testing3-2		96.51 399	96.43 394	96.74 432	99.36 326	91.38 459	99.10 236	97.87 433	99.48 170	98.57 396	98.71 426	76.65 460	99.66 413	98.87 186	99.26 376	99.18 340

testing3		96.48 400	95.63 412	99.01 331	99.23 365	97.81 374	98.90 292	99.10 376	98.72 297	97.84 431	97.92 449	72.44 466	99.85 281	97.21 341	99.33 365	99.35 300

thres400		96.40 401	95.89 404	97.92 404	99.58 233	96.11 419	99.00 268	97.54 440	98.43 326	98.52 399	96.98 462	86.85 434	99.67 408	87.62 456	98.51 424	97.98 448

thres100view900		96.39 402	96.03 402	97.47 417	99.63 216	95.93 422	99.18 200	97.57 437	98.75 296	98.70 385	97.31 459	87.04 432	99.67 408	87.62 456	98.51 424	96.81 457

tpm2		96.35 403	96.22 398	96.73 433	98.88 417	91.75 455	99.21 189	98.51 408	93.27 449	97.89 426	99.21 375	84.83 442	99.70 385	96.04 401	98.18 437	98.75 414

FPMVS		96.32 404	95.50 413	98.79 362	99.60 223	98.17 349	98.46 361	98.80 392	97.16 409	96.28 453	99.63 232	82.19 446	99.09 454	88.45 454	98.89 404	99.10 358

tfpn200view9		96.30 405	95.89 404	97.53 414	99.58 233	96.11 419	99.00 268	97.54 440	98.43 326	98.52 399	96.98 462	86.85 434	99.67 408	87.62 456	98.51 424	96.81 457

TESTMET0.1,1		96.24 406	95.84 407	97.41 419	98.24 452	93.84 444	97.38 435	95.84 451	98.43 326	97.81 432	98.56 433	79.77 454	99.89 214	97.77 288	98.77 408	98.52 427

myMVS_eth3d28		96.23 407	95.74 409	97.70 413	98.86 419	95.59 429	98.66 328	98.14 425	98.96 260	97.67 437	97.06 461	76.78 459	98.92 457	97.10 345	98.41 428	98.58 423

test-mter		96.23 407	95.73 410	97.74 411	98.18 454	95.02 436	97.38 435	96.10 447	97.90 371	97.81 432	98.58 430	79.12 457	99.91 176	97.69 305	98.78 406	98.31 436

UWE-MVS		96.21 409	95.78 408	97.49 415	98.53 443	93.83 445	98.04 396	93.94 460	98.96 260	98.46 403	98.17 444	79.86 452	99.87 244	96.99 350	99.06 388	98.78 410

ETVMVS		96.14 410	95.22 421	98.89 352	98.80 426	98.01 361	98.66 328	98.35 419	98.71 299	97.18 444	96.31 473	74.23 465	99.75 368	96.64 374	98.13 441	98.90 398

X-MVStestdata		96.09 411	94.87 424	99.75 93	99.71 172	99.71 98	99.37 129	99.61 221	99.29 210	98.76 379	61.30 474	98.47 213	99.88 229	97.62 308	99.73 264	99.67 125

thres200		96.09 411	95.68 411	97.33 422	99.48 291	96.22 418	98.53 350	97.57 437	98.06 361	98.37 406	96.73 466	86.84 436	99.61 430	86.99 459	98.57 421	96.16 460

testing11		96.05 413	95.41 416	97.97 401	98.78 430	95.27 433	98.59 336	98.23 423	98.86 277	96.56 451	96.91 464	75.20 462	99.69 391	97.26 334	98.29 431	98.93 394

testing91		96.00 414	95.32 419	98.02 398	98.76 433	95.39 430	98.38 365	98.65 401	98.82 283	96.84 447	96.71 467	75.06 463	99.71 381	96.46 385	98.23 433	98.98 388

KD-MVS_2432*1600		95.89 415	95.41 416	97.31 423	94.96 466	93.89 442	97.09 445	99.22 360	97.23 405	98.88 363	99.04 395	79.23 455	99.54 438	96.24 395	96.81 453	98.50 431

miper_refine_blended		95.89 415	95.41 416	97.31 423	94.96 466	93.89 442	97.09 445	99.22 360	97.23 405	98.88 363	99.04 395	79.23 455	99.54 438	96.24 395	96.81 453	98.50 431

gg-mvs-nofinetune		95.87 417	95.17 423	97.97 401	98.19 453	96.95 400	99.69 45	89.23 467	99.89 54	96.24 455	99.94 19	81.19 447	99.51 444	93.99 442	98.20 434	97.44 453

testing99		95.86 418	95.19 422	97.87 405	98.76 433	95.03 435	98.62 330	98.44 412	98.68 301	96.67 450	96.66 468	74.31 464	99.69 391	96.51 380	98.03 443	98.90 398

PVSNet_0	95.53 19	95.85 419	95.31 420	97.47 417	98.78 430	93.48 447	95.72 456	99.40 319	96.18 427	97.37 438	97.73 451	95.73 350	99.58 433	95.49 419	81.40 464	99.36 297

tmp_tt		95.75 420	95.42 415	96.76 430	89.90 470	94.42 440	98.86 297	97.87 433	78.01 461	99.30 314	99.69 190	97.70 282	95.89 463	99.29 129	98.14 439	99.95 14

MVS		95.72 421	94.63 427	98.99 332	98.56 442	97.98 367	99.30 154	98.86 387	72.71 463	97.30 440	99.08 390	98.34 232	99.74 371	89.21 451	98.33 429	99.26 319

UWE-MVS-28		95.64 422	95.47 414	96.14 441	97.98 458	90.39 465	98.49 355	95.81 452	99.02 254	98.03 421	98.19 443	84.49 444	99.28 451	88.75 452	98.47 427	98.75 414

myMVS_eth3d		95.63 423	94.73 425	98.34 387	98.50 445	96.36 413	98.60 333	99.21 363	97.89 372	96.76 448	96.37 471	72.10 467	99.57 434	94.38 434	98.73 415	99.09 363

PAPM		95.61 424	94.71 426	98.31 390	99.12 384	96.63 406	96.66 453	98.46 411	90.77 455	96.25 454	98.68 429	93.01 386	99.69 391	81.60 462	97.86 447	98.62 418

testing222		95.60 425	94.59 428	98.61 372	98.66 440	97.45 387	98.54 348	97.90 432	98.53 318	96.54 452	96.47 470	70.62 469	99.81 339	95.91 410	98.15 438	98.56 426

IB-MVS	95.41 20	95.30 426	94.46 430	97.84 407	98.76 433	95.33 432	97.33 438	96.07 449	96.02 428	95.37 460	97.41 457	76.17 461	99.96 67	97.54 314	95.44 462	98.22 441
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
test2506		94.73 427	94.59 428	95.15 443	99.59 228	85.90 469	99.75 25	74.01 471	99.89 54	99.71 170	99.86 63	79.00 458	99.90 195	99.52 89	99.99 16	99.65 144

test_method		91.72 428	92.32 431	89.91 446	93.49 469	70.18 472	90.28 460	99.56 254	61.71 464	95.39 459	99.52 297	93.90 371	99.94 95	98.76 200	98.27 432	99.62 172

dongtai		89.37 429	88.91 432	90.76 445	99.19 373	77.46 470	95.47 458	87.82 469	92.28 451	94.17 462	98.82 421	71.22 468	95.54 464	63.85 464	97.34 450	99.27 317

EGC-MVSNET		89.05 430	85.52 433	99.64 151	99.89 39	99.78 57	99.56 87	99.52 281	24.19 465	49.96 466	99.83 81	99.15 104	99.92 147	97.71 296	99.85 191	99.21 331

kuosan		85.65 431	84.57 434	88.90 447	97.91 459	77.11 471	96.37 455	87.62 470	85.24 460	85.45 465	96.83 465	69.94 470	90.98 466	45.90 465	95.83 461	98.62 418

test123		29.31 432	33.05 437	18.08 448	25.93 472	12.24 473	97.53 429	10.93 473	11.78 466	24.21 467	50.08 478	21.04 471	8.60 467	23.51 466	32.43 466	33.39 463

testmvs		28.94 433	33.33 435	15.79 449	26.03 471	9.81 474	96.77 451	15.67 472	11.55 467	23.87 468	50.74 477	19.03 472	8.53 468	23.21 467	33.07 465	29.03 464

cdsmvs_eth3d_5k		24.88 434	33.17 436	0.00 450	0.00 473	0.00 475	0.00 461	99.62 214	0.00 468	0.00 469	99.13 381	99.82 18	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		16.61 435	22.14 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	99.28 86	0.00 469	0.00 468	0.00 467	0.00 465

mmdepth		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		8.33 436	11.11 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	100.00 1	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		8.26 446	11.02 449	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	99.16 379	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						96.36 413								95.20 425

FOURS1					99.83 76	99.89 10	99.74 27	99.71 161	99.69 123	99.63 202

MSC_two_6792asdad				99.74 98	99.03 401	99.53 161		99.23 357					99.92 147	97.77 288	99.69 283	99.78 72

PC_three_1452									97.56 386	99.68 180	99.41 324	99.09 114	97.09 462	96.66 371	99.60 316	99.62 172

No_MVS				99.74 98	99.03 401	99.53 161		99.23 357					99.92 147	97.77 288	99.69 283	99.78 72

test_one_0601					99.63 216	99.76 70		99.55 260	99.23 222	99.31 309	99.61 250	98.59 191

eth-test2					0.00 473

eth-test					0.00 473

ZD-MVS					99.43 309	99.61 139		99.43 309	96.38 423	99.11 341	99.07 391	97.86 272	99.92 147	94.04 440	99.49 345

RE-MVS-def			99.13 192		99.54 259	99.74 85	99.26 172	99.62 214	99.16 236	99.52 250	99.64 217	98.57 194		97.27 332	99.61 313	99.54 219

IU-MVS					99.69 192	99.77 63		99.22 360	97.50 392	99.69 177				97.75 292	99.70 275	99.77 76

OPU-MVS				99.29 285	99.12 384	99.44 181	99.20 190				99.40 328	99.00 132	98.84 458	96.54 378	99.60 316	99.58 199

test_241102_TWO								99.54 266	99.13 242	99.76 142	99.63 232	98.32 235	99.92 147	97.85 283	99.69 283	99.75 84

test_241102_ONE					99.69 192	99.82 42		99.54 266	99.12 245	99.82 105	99.49 306	98.91 148	99.52 443

9.14			98.64 285		99.45 305		98.81 309	99.60 232	97.52 391	99.28 315	99.56 281	98.53 206	99.83 312	95.36 423	99.64 301

save fliter					99.53 266	99.25 229	98.29 371	99.38 326	99.07 249

test_0728_THIRD									99.18 229	99.62 211	99.61 250	98.58 193	99.91 176	97.72 294	99.80 231	99.77 76

test_0728_SECOND				99.83 39	99.70 187	99.79 54	99.14 216	99.61 221					99.92 147	97.88 277	99.72 270	99.77 76

test0726					99.69 192	99.80 51	99.24 179	99.57 249	99.16 236	99.73 161	99.65 215	98.35 230

GSMVS																99.14 352

test_part2					99.62 220	99.67 115				99.55 241

sam_mvs1												90.81 412				99.14 352

sam_mvs												90.52 417

ambc				99.20 305	99.35 330	98.53 324	99.17 205	99.46 301		99.67 187	99.80 100	98.46 216	99.70 385	97.92 273	99.70 275	99.38 291

MTGPA								99.53 276

test_post1							99.14 216				51.63 476	89.54 424	99.82 324	96.86 358

test_post											52.41 475	90.25 419	99.86 263

patchmatchnet-post											99.62 241	90.58 415	99.94 95

GG-mvs-BLEND				97.36 420	97.59 462	96.87 403	99.70 38	88.49 468		94.64 461	97.26 460	80.66 449	99.12 453	91.50 448	96.50 457	96.08 461

MTMP							99.09 241	98.59 405

gm-plane-assit					97.59 462	89.02 468			93.47 448		98.30 440		99.84 296	96.38 389

test9_res														95.10 427	99.44 350	99.50 242

TEST9					99.35 330	99.35 210	98.11 388	99.41 312	94.83 445	97.92 424	98.99 402	98.02 261	99.85 281

test_8					99.34 339	99.31 216	98.08 392	99.40 319	94.90 442	97.87 428	98.97 407	98.02 261	99.84 296

agg_prior2														94.58 433	99.46 349	99.50 242

agg_prior					99.35 330	99.36 207		99.39 322		97.76 435			99.85 281

TestCases				99.63 158	99.78 125	99.64 126		99.83 87	98.63 306	99.63 202	99.72 161	98.68 178	99.75 368	96.38 389	99.83 204	99.51 237

test_prior4						99.19 245	98.00 401

test_prior2							97.95 407		97.87 375	98.05 419	99.05 393	97.90 269		95.99 405	99.49 345

test_prior				99.46 227	99.35 330	99.22 239		99.39 322					99.69 391			99.48 251

旧先验2							97.94 408		95.33 437	98.94 355			99.88 229	96.75 365

新几何2							98.04 396

新几何1				99.52 208	99.50 281	99.22 239		99.26 350	95.66 434	98.60 392	99.28 359	97.67 286	99.89 214	95.95 408	99.32 367	99.45 260

旧先验1					99.49 286	99.29 219		99.26 350			99.39 332	97.67 286			99.36 361	99.46 259

无先验							98.01 399	99.23 357	95.83 431				99.85 281	95.79 414		99.44 272

原ACMM2							97.92 410

原ACMM1				99.37 260	99.47 297	98.87 290		99.27 348	96.74 420	98.26 408	99.32 350	97.93 268	99.82 324	95.96 407	99.38 358	99.43 278

test222					99.51 275	99.08 264	97.83 416	99.29 344	95.21 439	98.68 386	99.31 353	97.28 304			99.38 358	99.43 278

testdata2													99.89 214	95.99 405

segment_acmp												98.37 228

testdata				99.42 240	99.51 275	98.93 282		99.30 343	96.20 426	98.87 366	99.40 328	98.33 234	99.89 214	96.29 392	99.28 372	99.44 272

testdata1							97.72 419		97.86 377

test12				99.54 202	99.29 352	99.33 213		99.16 371		98.43 404		97.54 293	99.82 324		99.47 347	99.48 251

plane_prior7					99.58 233	99.38 200

plane_prior6					99.47 297	99.26 226						97.24 305

plane_prior5								99.54 266					99.82 324	95.84 412	99.78 241	99.60 187

plane_prior4											99.25 366

plane_prior3						99.31 216			98.36 335	99.14 337

plane_prior2							98.80 312		98.94 264

plane_prior1					99.51 275

plane_prior						99.24 233	98.42 363		97.87 375						99.71 273

n2								0.00 474

nn								0.00 474

door-mid								99.83 87

lessismore_v0				99.64 151	99.86 57	99.38 200		90.66 464		99.89 71	99.83 81	94.56 367	99.97 42	99.56 82	99.92 132	99.57 205

LGP-MVS_train				99.74 98	99.82 85	99.63 131		99.73 149	97.56 386	99.64 198	99.69 190	99.37 71	99.89 214	96.66 371	99.87 178	99.69 110

test11								99.29 344

door								99.77 126

HQP5-MVS						98.94 279

HQP-NCC					99.31 346		97.98 403		97.45 394	98.15 413

ACMP_Plane					99.31 346		97.98 403		97.45 394	98.15 413

BP-MVS														94.73 430

HQP4-MVS										98.15 413			99.70 385			99.53 225

HQP3-MVS								99.37 327							99.67 294

HQP2-MVS												96.67 324

NP-MVS					99.40 317	99.13 252					98.83 419

MDTV_nov1_ep13_2view						91.44 458	99.14 216		97.37 399	99.21 327		91.78 399		96.75 365		99.03 380

MDTV_nov1_ep13			97.73 364		98.70 438	90.83 461	99.15 213	98.02 428	98.51 320	98.82 371	99.61 250	90.98 406	99.66 413	96.89 357	98.92 399

ACMMP++_ref															99.94 117

ACMMP++															99.79 236

Test By Simon												98.41 222

ITE_SJBPF				99.38 257	99.63 216	99.44 181		99.73 149	98.56 313	99.33 301	99.53 293	98.88 152	99.68 403	96.01 402	99.65 299	99.02 385

DeepMVS_CX				97.98 400	99.69 192	96.95 400		99.26 350	75.51 462	95.74 458	98.28 441	96.47 332	99.62 425	91.23 449	97.89 445	97.38 454

High-resolution multi-view benchmark