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.

fmvsm_l_conf0.5_n_9		98.90 13	98.79 11	99.24 41	99.34 65	97.83 74	98.70 182	99.26 16	98.85 4	99.92 1	99.51 24	93.91 103	99.95 9	99.86 1	99.79 30	99.92 2

fmvsm_s_conf0.5_n_9		98.63 25	98.66 19	98.54 103	99.40 62	95.83 190	98.79 158	99.17 34	98.94 2	99.92 1	99.61 4	92.49 121	99.93 32	99.86 1	99.76 43	99.86 10

fmvsm_l_conf0.5_n_3		98.90 13	98.74 16	99.37 23	99.36 63	98.25 51	98.89 115	99.24 20	98.77 8	99.89 3	99.59 12	93.39 109	99.96 4	99.78 8	99.76 43	99.89 6

fmvsm_s_conf0.5_n_5		98.53 41	98.35 43	99.08 59	99.07 120	97.46 89	98.68 187	99.20 30	97.50 48	99.87 4	99.50 27	91.96 145	99.96 4	99.76 9	99.65 76	99.82 20

fmvsm_s_conf0.5_n_3		98.53 41	98.45 34	98.79 80	99.23 98	97.32 94	98.80 150	99.26 16	98.82 5	99.87 4	99.60 9	90.95 184	99.93 32	99.76 9	99.73 57	99.12 183

test_vis1_n_1920		96.71 168	96.84 144	96.31 308	99.11 116	89.74 387	99.05 70	98.58 171	98.08 22	99.87 4	99.37 52	78.48 391	99.93 32	99.29 25	99.69 67	99.27 151

fmvsm_s_conf0.5_n_6		98.65 22	98.55 25	98.95 72	98.50 181	97.30 97	98.79 158	99.16 36	98.14 21	99.86 7	99.41 44	93.71 106	99.91 51	99.71 13	99.64 81	99.65 78

fmvsm_l_conf0.5_n		99.07 4	99.05 2	99.14 53	99.41 61	97.54 83	98.89 115	99.31 13	98.49 15	99.86 7	99.42 42	96.45 24	99.96 4	99.86 1	99.74 54	99.90 5

test_fmvsm_n_1920		98.87 16	99.01 3	98.45 117	99.42 60	96.43 149	98.96 96	99.36 10	98.63 11	99.86 7	99.51 24	95.91 43	99.97 1	99.72 12	99.75 50	98.94 212

fmvsm_l_conf0.5_n_a		99.09 1	99.08 1	99.11 57	99.43 59	97.48 85	98.88 122	99.30 14	98.47 16	99.85 10	99.43 41	96.71 17	99.96 4	99.86 1	99.80 24	99.89 6

fmvsm_s_conf0.5_n_4		98.35 63	98.50 29	97.90 171	99.16 109	95.08 227	98.75 163	99.24 20	98.39 17	99.81 11	99.52 21	92.35 125	99.90 59	99.74 11	99.51 110	98.71 238

test_fmvsmconf_n		98.92 11	98.87 6	99.04 63	98.88 141	97.25 107	98.82 141	99.34 11	98.75 9	99.80 12	99.61 4	95.16 74	99.95 9	99.70 15	99.80 24	99.93 1

fmvsm_s_conf0.5_n_8		98.73 20	98.62 20	99.05 62	99.35 64	97.27 101	98.80 150	99.23 25	98.93 3	99.79 13	99.59 12	92.34 126	99.95 9	99.82 6	99.71 64	99.92 2

fmvsm_s_conf0.5_n_2		98.30 70	98.21 64	98.57 98	99.25 90	97.11 114	98.66 194	99.20 30	98.82 5	99.79 13	99.60 9	89.38 221	99.92 41	99.80 7	99.38 128	98.69 240

fmvsm_s_conf0.5_n_a		98.38 58	98.42 36	98.27 132	99.09 118	95.41 208	98.86 129	99.37 9	97.69 36	99.78 15	99.61 4	92.38 124	99.91 51	99.58 21	99.43 121	99.49 106

fmvsm_s_conf0.1_n_2		98.14 76	98.02 77	98.53 106	98.88 141	97.07 116	98.69 185	98.82 95	98.78 7	99.77 16	99.61 4	88.83 241	99.91 51	99.71 13	99.07 144	98.61 250

test_cas_vis1_n_1920		97.38 129	97.36 112	97.45 210	98.95 136	93.25 313	99.00 84	98.53 182	97.70 35	99.77 16	99.35 58	84.71 330	99.85 78	98.57 50	99.66 73	99.26 158

fmvsm_s_conf0.1_n_a		98.08 77	98.04 76	98.21 139	97.66 287	95.39 209	98.89 115	99.17 34	97.24 70	99.76 18	99.67 1	91.13 175	99.88 71	99.39 24	99.41 123	99.35 133

fmvsm_s_conf0.5_n		98.42 55	98.51 27	98.13 149	99.30 77	95.25 218	98.85 133	99.39 7	97.94 27	99.74 19	99.62 3	92.59 120	99.91 51	99.65 16	99.52 108	99.25 160

fmvsm_s_conf0.5_n_7		98.23 71	98.35 43	97.89 173	98.86 145	94.99 233	98.58 209	99.00 49	98.29 18	99.73 20	99.60 9	91.70 149	99.92 41	99.63 19	99.73 57	98.76 232

SED-MVS		99.09 1	98.91 4	99.63 4	99.71 21	99.24 5	99.02 80	98.87 80	97.65 37	99.73 20	99.48 31	97.53 7	99.94 13	98.43 65	99.81 15	99.70 62

test_241102_ONE					99.71 21	99.24 5		98.87 80	97.62 39	99.73 20	99.39 46	97.53 7	99.74 128

SD-MVS		98.64 24	98.68 17	98.53 106	99.33 68	98.36 44	98.90 111	98.85 89	97.28 65	99.72 23	99.39 46	96.63 20	97.60 404	98.17 78	99.85 6	99.64 81
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
fmvsm_s_conf0.1_n		98.18 75	98.21 64	98.11 153	98.54 179	95.24 219	98.87 125	99.24 20	97.50 48	99.70 24	99.67 1	91.33 165	99.89 62	99.47 23	99.54 105	99.21 166

test_fmvs1_n		95.90 209	95.99 190	95.63 339	98.67 166	88.32 418	99.26 28	98.22 263	96.40 117	99.67 25	99.26 73	73.91 428	99.70 136	99.02 32	99.50 111	98.87 217

test_vis1_n		95.47 231	95.13 232	96.49 291	97.77 276	90.41 376	99.27 27	98.11 287	96.58 108	99.66 26	99.18 91	67.00 442	99.62 157	99.21 27	99.40 126	99.44 118

mvsany_test1		97.69 99	97.70 88	97.66 199	98.24 216	94.18 275	97.53 350	97.53 343	95.52 161	99.66 26	99.51 24	94.30 95	99.56 166	98.38 68	98.62 172	99.23 162

test_fmvs1		96.42 183	96.67 157	95.66 338	98.82 150	88.53 414	98.80 150	98.20 266	96.39 118	99.64 28	99.20 85	80.35 379	99.67 143	99.04 31	99.57 94	98.78 228

IU-MVS					99.71 21	99.23 7		98.64 153	95.28 176	99.63 29				98.35 70	99.81 15	99.83 16

PC_three_1452									95.08 193	99.60 30	99.16 95	97.86 2	98.47 326	97.52 125	99.72 62	99.74 45

lecture		98.95 7	98.78 12	99.45 15	99.75 3	98.63 26	99.43 10	99.38 8	97.60 42	99.58 31	99.47 33	95.36 61	99.93 32	98.87 36	99.57 94	99.78 28

test0726					99.72 14	99.25 2	99.06 68	98.88 73	97.62 39	99.56 32	99.50 27	97.42 9

TSAR-MVS + MP.		98.78 17	98.62 20	99.24 41	99.69 26	98.28 49	99.14 55	98.66 148	96.84 92	99.56 32	99.31 65	96.34 28	99.70 136	98.32 71	99.73 57	99.73 50
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DPE-MVS		98.92 11	98.67 18	99.65 2	99.58 34	99.20 9	98.42 244	98.91 67	97.58 43	99.54 34	99.46 38	97.10 12	99.94 13	97.64 113	99.84 11	99.83 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DVP-MVS++		99.08 3	98.89 5	99.64 3	99.17 105	99.23 7	99.69 1	98.88 73	97.32 61	99.53 35	99.47 33	97.81 3	99.94 13	98.47 61	99.72 62	99.74 45

test_241102_TWO								98.87 80	97.65 37	99.53 35	99.48 31	97.34 11	99.94 13	98.43 65	99.80 24	99.83 16

DVP-MVS		99.03 5	98.83 9	99.63 4	99.72 14	99.25 2	98.97 91	98.58 171	97.62 39	99.45 37	99.46 38	97.42 9	99.94 13	98.47 61	99.81 15	99.69 65
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									97.32 61	99.45 37	99.46 38	97.88 1	99.94 13	98.47 61	99.86 2	99.85 13

test_fmvsmconf0.1_n		98.58 32	98.44 35	98.99 65	97.73 281	97.15 112	98.84 137	98.97 53	98.75 9	99.43 39	99.54 18	93.29 111	99.93 32	99.64 18	99.79 30	99.89 6

MSP-MVS		98.74 19	98.55 25	99.29 34	99.75 3	98.23 52	99.26 28	98.88 73	97.52 46	99.41 40	98.78 167	96.00 39	99.79 115	97.79 100	99.59 90	99.85 13
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
APDe-MVS		99.02 6	98.84 8	99.55 9	99.57 35	98.96 16	99.39 11	98.93 61	97.38 58	99.41 40	99.54 18	96.66 18	99.84 82	98.86 37	99.85 6	99.87 9
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
FOURS1					99.82 1	98.66 24	99.69 1	98.95 57	97.46 53	99.39 42

SMA-MVS		98.58 32	98.25 58	99.56 8	99.51 42	99.04 15	98.95 97	98.80 108	93.67 280	99.37 43	99.52 21	96.52 22	99.89 62	98.06 83	99.81 15	99.76 42
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
reproduce_model		98.94 8	98.81 10	99.34 27	99.52 41	98.26 50	98.94 100	98.84 90	98.06 23	99.35 44	99.61 4	96.39 27	99.94 13	98.77 40	99.82 14	99.83 16

balanced_conf03		98.45 51	98.35 43	98.74 84	98.65 170	97.55 81	99.19 45	98.60 159	96.72 102	99.35 44	98.77 170	95.06 79	99.55 173	98.95 33	99.87 1	99.12 183

SteuartSystems-ACMMP		98.90 13	98.75 15	99.36 25	99.22 100	98.43 34	99.10 64	98.87 80	97.38 58	99.35 44	99.40 45	97.78 5	99.87 73	97.77 101	99.85 6	99.78 28
Skip Steuart: Steuart Systems R&D Blog.
SF-MVS		98.59 30	98.32 54	99.41 18	99.54 37	98.71 22	99.04 74	98.81 101	95.12 188	99.32 47	99.39 46	96.22 30	99.84 82	97.72 104	99.73 57	99.67 74

reproduce-ours		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

our_new_method		98.93 9	98.78 12	99.38 19	99.49 48	98.38 36	98.86 129	98.83 92	98.06 23	99.29 48	99.58 14	96.40 25	99.94 13	98.68 43	99.81 15	99.81 22

dcpmvs_2		98.08 77	98.59 22	96.56 283	99.57 35	90.34 379	99.15 52	98.38 226	96.82 94	99.29 48	99.49 30	95.78 47	99.57 163	98.94 34	99.86 2	99.77 35

test_part2					99.63 31	99.18 10				99.27 51

DeepPCF-MVS	96.37 2	97.93 85	98.48 33	96.30 309	99.00 128	89.54 394	97.43 356	98.87 80	98.16 20	99.26 52	99.38 51	96.12 35	99.64 150	98.30 72	99.77 37	99.72 54

APD-MVS		98.35 63	98.00 79	99.42 17	99.51 42	98.72 21	98.80 150	98.82 95	94.52 230	99.23 53	99.25 78	95.54 54	99.80 103	96.52 176	99.77 37	99.74 45
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_one_0601					99.66 28	99.25 2		98.86 86	97.55 45	99.20 54	99.47 33	97.57 6

APD-MVS_3200maxsize		98.53 41	98.33 53	99.15 52	99.50 44	97.92 69	99.15 52	98.81 101	96.24 124	99.20 54	99.37 52	95.30 65	99.80 103	97.73 103	99.67 70	99.72 54

patch_mono-2		98.36 61	98.87 6	96.82 255	99.53 38	90.68 367	98.64 198	99.29 15	97.88 28	99.19 56	99.52 21	96.80 15	99.97 1	99.11 29	99.86 2	99.82 20

MM		98.51 44	98.24 60	99.33 31	99.12 114	98.14 61	98.93 106	97.02 390	98.96 1	99.17 57	99.47 33	91.97 144	99.94 13	99.85 5	99.69 67	99.91 4

SR-MVS-dyc-post		98.54 40	98.35 43	99.13 54	99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.34 63	99.82 91	97.72 104	99.65 76	99.71 58

RE-MVS-def			98.34 49		99.49 48	97.86 70	99.11 61	98.80 108	96.49 112	99.17 57	99.35 58	95.29 66		97.72 104	99.65 76	99.71 58

9.14			98.06 74		99.47 52		98.71 178	98.82 95	94.36 238	99.16 60	99.29 68	96.05 37	99.81 96	97.00 147	99.71 64

ACMMP_NAP		98.61 27	98.30 55	99.55 9	99.62 32	98.95 17	98.82 141	98.81 101	95.80 145	99.16 60	99.47 33	95.37 60	99.92 41	97.89 94	99.75 50	99.79 26

SR-MVS		98.57 36	98.35 43	99.24 41	99.53 38	98.18 56	99.09 65	98.82 95	96.58 108	99.10 62	99.32 63	95.39 58	99.82 91	97.70 109	99.63 83	99.72 54

PGM-MVS		98.49 46	98.23 62	99.27 39	99.72 14	98.08 63	98.99 87	99.49 5	95.43 165	99.03 63	99.32 63	95.56 52	99.94 13	96.80 167	99.77 37	99.78 28

KinetiMVS		97.48 118	97.05 132	98.78 81	98.37 195	97.30 97	98.99 87	98.70 135	97.18 75	99.02 64	99.01 127	87.50 275	99.67 143	95.33 219	99.33 134	99.37 129

VNet		97.79 93	97.40 109	98.96 70	98.88 141	97.55 81	98.63 201	98.93 61	96.74 99	99.02 64	98.84 154	90.33 196	99.83 84	98.53 53	96.66 255	99.50 101

xiu_mvs_v1_base_debu		97.60 107	97.56 95	97.72 188	98.35 197	95.98 168	97.86 323	98.51 188	97.13 80	99.01 66	98.40 210	91.56 154	99.80 103	98.53 53	98.68 167	97.37 302

xiu_mvs_v1_base		97.60 107	97.56 95	97.72 188	98.35 197	95.98 168	97.86 323	98.51 188	97.13 80	99.01 66	98.40 210	91.56 154	99.80 103	98.53 53	98.68 167	97.37 302

xiu_mvs_v1_base_debi		97.60 107	97.56 95	97.72 188	98.35 197	95.98 168	97.86 323	98.51 188	97.13 80	99.01 66	98.40 210	91.56 154	99.80 103	98.53 53	98.68 167	97.37 302

MVSMamba_PlusPlus		98.31 68	98.19 68	98.67 90	98.96 135	97.36 92	99.24 31	98.57 173	94.81 211	98.99 69	98.90 146	95.22 72	99.59 160	99.15 28	99.84 11	99.07 199

TSAR-MVS + GP.		98.38 58	98.24 60	98.81 79	99.22 100	97.25 107	98.11 288	98.29 250	97.19 74	98.99 69	99.02 123	96.22 30	99.67 143	98.52 59	98.56 177	99.51 99

CS-MVS		98.44 52	98.49 31	98.31 130	99.08 119	96.73 131	99.67 3	98.47 200	97.17 76	98.94 71	99.10 106	95.73 48	99.13 242	98.71 42	99.49 113	99.09 191

HFP-MVS		98.63 25	98.40 37	99.32 33	99.72 14	98.29 48	99.23 33	98.96 56	96.10 132	98.94 71	99.17 92	96.06 36	99.92 41	97.62 114	99.78 35	99.75 43

region2R		98.61 27	98.38 39	99.29 34	99.74 9	98.16 58	99.23 33	98.93 61	96.15 128	98.94 71	99.17 92	95.91 43	99.94 13	97.55 122	99.79 30	99.78 28

HPM-MVS_fast		98.38 58	98.13 69	99.12 56	99.75 3	97.86 70	99.44 9	98.82 95	94.46 235	98.94 71	99.20 85	95.16 74	99.74 128	97.58 117	99.85 6	99.77 35

test_fmvsmconf0.01_n		97.86 87	97.54 98	98.83 78	95.48 410	96.83 126	98.95 97	98.60 159	98.58 12	98.93 75	99.55 16	88.57 246	99.91 51	99.54 22	99.61 86	99.77 35

ACMMPR		98.59 30	98.36 41	99.29 34	99.74 9	98.15 59	99.23 33	98.95 57	96.10 132	98.93 75	99.19 90	95.70 49	99.94 13	97.62 114	99.79 30	99.78 28

DeepC-MVS_fast	96.70 1	98.55 39	98.34 49	99.18 48	99.25 90	98.04 64	98.50 228	98.78 115	97.72 32	98.92 77	99.28 69	95.27 67	99.82 91	97.55 122	99.77 37	99.69 65
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SPE-MVS-test		98.49 46	98.50 29	98.46 116	99.20 103	97.05 117	99.64 4	98.50 193	97.45 54	98.88 78	99.14 99	95.25 69	99.15 237	98.83 38	99.56 102	99.20 167

MVS_0304		98.23 71	97.91 82	99.21 45	98.06 244	97.96 68	98.58 209	95.51 428	98.58 12	98.87 79	99.26 73	92.99 115	99.95 9	99.62 20	99.67 70	99.73 50

EC-MVSNet		98.21 74	98.11 71	98.49 113	98.34 202	97.26 106	99.61 5	98.43 213	96.78 95	98.87 79	98.84 154	93.72 105	99.01 265	98.91 35	99.50 111	99.19 171

diffmvs_AUTHOR		97.59 110	97.44 106	98.01 164	98.26 214	95.47 205	98.12 285	98.36 231	96.38 119	98.84 81	99.10 106	91.13 175	99.26 219	98.24 77	98.56 177	99.30 145

EI-MVSNet-Vis-set		98.47 49	98.39 38	98.69 88	99.46 54	96.49 146	98.30 257	98.69 137	97.21 72	98.84 81	99.36 56	95.41 57	99.78 118	98.62 47	99.65 76	99.80 25

MSLP-MVS++		98.56 38	98.57 23	98.55 101	99.26 89	96.80 127	98.71 178	99.05 46	97.28 65	98.84 81	99.28 69	96.47 23	99.40 200	98.52 59	99.70 66	99.47 110

PHI-MVS		98.34 65	98.06 74	99.18 48	99.15 112	98.12 62	99.04 74	99.09 41	93.32 296	98.83 84	99.10 106	96.54 21	99.83 84	97.70 109	99.76 43	99.59 89

GDP-MVS		97.64 103	97.28 115	98.71 87	98.30 210	97.33 93	99.05 70	98.52 185	96.34 121	98.80 85	99.05 121	89.74 208	99.51 180	96.86 164	98.86 159	99.28 150

MVSFormer		97.57 112	97.49 101	97.84 175	98.07 241	95.76 193	99.47 7	98.40 218	94.98 200	98.79 86	98.83 158	92.34 126	98.41 339	96.91 152	99.59 90	99.34 135

lupinMVS		97.44 124	97.22 122	98.12 152	98.07 241	95.76 193	97.68 339	97.76 319	94.50 233	98.79 86	98.61 188	92.34 126	99.30 213	97.58 117	99.59 90	99.31 142

CDPH-MVS		97.94 84	97.49 101	99.28 37	99.47 52	98.44 32	97.91 313	98.67 145	92.57 328	98.77 88	98.85 153	95.93 42	99.72 130	95.56 212	99.69 67	99.68 70

CNVR-MVS		98.78 17	98.56 24	99.45 15	99.32 71	98.87 19	98.47 232	98.81 101	97.72 32	98.76 89	99.16 95	97.05 13	99.78 118	98.06 83	99.66 73	99.69 65

EI-MVSNet-UG-set		98.41 56	98.34 49	98.61 95	99.45 57	96.32 156	98.28 260	98.68 140	97.17 76	98.74 90	99.37 52	95.25 69	99.79 115	98.57 50	99.54 105	99.73 50

diffmvs		97.58 111	97.40 109	98.13 149	98.32 208	95.81 192	98.06 294	98.37 228	96.20 126	98.74 90	98.89 149	91.31 167	99.25 222	98.16 79	98.52 181	99.34 135
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
guyue		97.57 112	97.37 111	98.20 141	98.50 181	95.86 188	98.89 115	97.03 387	97.29 63	98.73 92	98.90 146	89.41 220	99.32 209	98.68 43	98.86 159	99.42 123

GST-MVS		98.43 54	98.12 70	99.34 27	99.72 14	98.38 36	99.09 65	98.82 95	95.71 151	98.73 92	99.06 120	95.27 67	99.93 32	97.07 146	99.63 83	99.72 54

UA-Net		97.96 82	97.62 90	98.98 67	98.86 145	97.47 87	98.89 115	99.08 42	96.67 105	98.72 94	99.54 18	93.15 113	99.81 96	94.87 234	98.83 162	99.65 78

NormalMVS		98.07 79	97.90 83	98.59 97	99.75 3	96.60 137	98.94 100	98.60 159	97.86 29	98.71 95	99.08 116	91.22 171	99.80 103	97.40 133	99.57 94	99.37 129

SymmetryMVS		97.84 90	97.58 92	98.62 94	99.01 126	96.60 137	98.94 100	98.44 205	97.86 29	98.71 95	99.08 116	91.22 171	99.80 103	97.40 133	97.53 232	99.47 110

LuminaMVS		97.49 117	97.18 124	98.42 123	97.50 302	97.15 112	98.45 234	97.68 322	96.56 111	98.68 97	98.78 167	89.84 205	99.32 209	98.60 48	98.57 176	98.79 224

h-mvs33		96.17 195	95.62 209	97.81 179	99.03 123	94.45 260	98.64 198	98.75 121	97.48 50	98.67 98	98.72 180	89.76 206	99.86 77	97.95 88	81.59 433	99.11 186

hse-mvs2		95.71 219	95.30 226	96.93 247	98.50 181	93.53 298	98.36 246	98.10 290	97.48 50	98.67 98	97.99 251	89.76 206	99.02 263	97.95 88	80.91 438	98.22 274

ZD-MVS					99.46 54	98.70 23		98.79 113	93.21 301	98.67 98	98.97 131	95.70 49	99.83 84	96.07 188	99.58 93

旧先验2							97.57 349		91.30 369	98.67 98			99.80 103	95.70 209

PS-MVSNAJ		97.73 95	97.77 85	97.62 202	98.68 165	95.58 198	97.34 365	98.51 188	97.29 63	98.66 102	97.88 263	94.51 88	99.90 59	97.87 95	99.17 142	97.39 300

xiu_mvs_v2_base		97.66 102	97.70 88	97.56 206	98.61 174	95.46 206	97.44 354	98.46 201	97.15 78	98.65 103	98.15 238	94.33 94	99.80 103	97.84 98	98.66 171	97.41 298

LFMVS		95.86 211	94.98 241	98.47 115	98.87 144	96.32 156	98.84 137	96.02 420	93.40 293	98.62 104	99.20 85	74.99 422	99.63 153	97.72 104	97.20 237	99.46 115

HPM-MVS		98.36 61	98.10 73	99.13 54	99.74 9	97.82 75	99.53 6	98.80 108	94.63 222	98.61 105	98.97 131	95.13 76	99.77 123	97.65 112	99.83 13	99.79 26
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
AstraMVS		97.34 132	97.24 119	97.65 200	98.13 236	94.15 276	98.94 100	96.25 419	97.47 52	98.60 106	99.28 69	89.67 210	99.41 199	98.73 41	98.07 207	99.38 128

testdata				98.26 135	99.20 103	95.36 211		98.68 140	91.89 350	98.60 106	99.10 106	94.44 93	99.82 91	94.27 262	99.44 120	99.58 93

CP-MVS		98.57 36	98.36 41	99.19 46	99.66 28	97.86 70	99.34 17	98.87 80	95.96 137	98.60 106	99.13 100	96.05 37	99.94 13	97.77 101	99.86 2	99.77 35

jason		97.32 133	97.08 129	98.06 160	97.45 308	95.59 197	97.87 321	97.91 313	94.79 212	98.55 109	98.83 158	91.12 177	99.23 225	97.58 117	99.60 88	99.34 135
jason: jason.
MCST-MVS		98.65 22	98.37 40	99.48 13	99.60 33	98.87 19	98.41 245	98.68 140	97.04 84	98.52 110	98.80 161	96.78 16	99.83 84	97.93 90	99.61 86	99.74 45

BP-MVS1		97.82 91	97.51 100	98.76 83	98.25 215	97.39 91	99.15 52	97.68 322	96.69 103	98.47 111	99.10 106	90.29 197	99.51 180	98.60 48	99.35 131	99.37 129

XVS		98.70 21	98.49 31	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	99.20 85	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

X-MVStestdata		94.06 337	92.30 363	99.34 27	99.70 24	98.35 45	99.29 23	98.88 73	97.40 55	98.46 112	43.50 462	95.90 45	99.89 62	97.85 96	99.74 54	99.78 28

MG-MVS		97.81 92	97.60 91	98.44 119	99.12 114	95.97 173	97.75 334	98.78 115	96.89 91	98.46 112	99.22 81	93.90 104	99.68 142	94.81 238	99.52 108	99.67 74

test_fmvsmvis_n_1920		98.44 52	98.51 27	98.23 138	98.33 205	96.15 163	98.97 91	99.15 38	98.55 14	98.45 115	99.55 16	94.26 97	99.97 1	99.65 16	99.66 73	98.57 257

NCCC		98.61 27	98.35 43	99.38 19	99.28 86	98.61 27	98.45 234	98.76 119	97.82 31	98.45 115	98.93 140	96.65 19	99.83 84	97.38 136	99.41 123	99.71 58

MVS_Test		97.28 135	97.00 134	98.13 149	98.33 205	95.97 173	98.74 167	98.07 297	94.27 240	98.44 117	98.07 243	92.48 122	99.26 219	96.43 179	98.19 202	99.16 177

MVS_111021_LR		98.34 65	98.23 62	98.67 90	99.27 87	96.90 123	97.95 306	99.58 3	97.14 79	98.44 117	99.01 127	95.03 80	99.62 157	97.91 92	99.75 50	99.50 101

ETV-MVS		97.96 82	97.81 84	98.40 125	98.42 188	97.27 101	98.73 173	98.55 178	96.84 92	98.38 119	97.44 305	95.39 58	99.35 205	97.62 114	98.89 155	98.58 256

test2506		94.44 308	93.91 306	96.04 318	99.02 124	88.99 405	99.06 68	79.47 467	96.96 88	98.36 120	99.26 73	77.21 406	99.52 179	96.78 168	99.04 146	99.59 89

VDDNet		95.36 243	94.53 263	97.86 174	98.10 239	95.13 225	98.85 133	97.75 320	90.46 386	98.36 120	99.39 46	73.27 430	99.64 150	97.98 87	96.58 258	98.81 223

mPP-MVS		98.51 44	98.26 57	99.25 40	99.75 3	98.04 64	99.28 25	98.81 101	96.24 124	98.35 122	99.23 79	95.46 55	99.94 13	97.42 131	99.81 15	99.77 35

DELS-MVS		98.40 57	98.20 66	98.99 65	99.00 128	97.66 76	97.75 334	98.89 70	97.71 34	98.33 123	98.97 131	94.97 81	99.88 71	98.42 67	99.76 43	99.42 123
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
MVS_111021_HR		98.47 49	98.34 49	98.88 77	99.22 100	97.32 94	97.91 313	99.58 3	97.20 73	98.33 123	99.00 129	95.99 40	99.64 150	98.05 85	99.76 43	99.69 65

ZNCC-MVS		98.49 46	98.20 66	99.35 26	99.73 13	98.39 35	99.19 45	98.86 86	95.77 147	98.31 125	99.10 106	95.46 55	99.93 32	97.57 121	99.81 15	99.74 45

HPM-MVS++		98.58 32	98.25 58	99.55 9	99.50 44	99.08 11	98.72 177	98.66 148	97.51 47	98.15 126	98.83 158	95.70 49	99.92 41	97.53 124	99.67 70	99.66 77

mvsmamba		97.25 138	96.99 136	98.02 163	98.34 202	95.54 202	99.18 49	97.47 349	95.04 194	98.15 126	98.57 196	89.46 217	99.31 212	97.68 111	99.01 149	99.22 164

新几何1				99.16 51	99.34 65	98.01 66		98.69 137	90.06 394	98.13 128	98.95 138	94.60 86	99.89 62	91.97 333	99.47 116	99.59 89

API-MVS		97.41 127	97.25 117	97.91 170	98.70 160	96.80 127	98.82 141	98.69 137	94.53 228	98.11 129	98.28 225	94.50 91	99.57 163	94.12 269	99.49 113	97.37 302

ECVR-MVS		95.95 203	95.71 203	96.65 268	99.02 124	90.86 362	99.03 77	91.80 454	96.96 88	98.10 130	99.26 73	81.31 365	99.51 180	96.90 155	99.04 146	99.59 89

CPTT-MVS		97.72 96	97.32 114	98.92 73	99.64 30	97.10 115	99.12 59	98.81 101	92.34 336	98.09 131	99.08 116	93.01 114	99.92 41	96.06 191	99.77 37	99.75 43

test12				99.18 48	99.16 109	98.19 55		98.53 182		98.07 132		95.13 76	99.72 130		99.56 102	99.63 83

RRT-MVS		97.03 151	96.78 149	97.77 184	97.90 268	94.34 267	99.12 59	98.35 232	95.87 142	98.06 133	98.70 181	86.45 294	99.63 153	98.04 86	98.54 179	99.35 133

test222					99.23 98	97.17 111	97.40 357	98.66 148	88.68 413	98.05 134	98.96 136	94.14 99			99.53 107	99.61 85

DP-MVS Recon		97.86 87	97.46 104	99.06 61	99.53 38	98.35 45	98.33 249	98.89 70	92.62 325	98.05 134	98.94 139	95.34 63	99.65 147	96.04 192	99.42 122	99.19 171

Vis-MVSNet		97.42 126	97.11 127	98.34 128	98.66 167	96.23 159	99.22 37	99.00 49	96.63 107	98.04 136	99.21 83	88.05 262	99.35 205	96.01 194	99.21 139	99.45 117
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test1111		95.94 206	95.78 197	96.41 301	98.99 131	90.12 381	99.04 74	92.45 453	96.99 87	98.03 137	99.27 72	81.40 364	99.48 189	96.87 161	99.04 146	99.63 83

baseline		97.64 103	97.44 106	98.25 136	98.35 197	96.20 160	99.00 84	98.32 237	96.33 123	98.03 137	99.17 92	91.35 164	99.16 234	98.10 81	98.29 201	99.39 126

test_yl		97.22 139	96.78 149	98.54 103	98.73 155	96.60 137	98.45 234	98.31 241	94.70 216	98.02 139	98.42 208	90.80 186	99.70 136	96.81 165	96.79 251	99.34 135

DCV-MVSNet		97.22 139	96.78 149	98.54 103	98.73 155	96.60 137	98.45 234	98.31 241	94.70 216	98.02 139	98.42 208	90.80 186	99.70 136	96.81 165	96.79 251	99.34 135

MTAPA		98.58 32	98.29 56	99.46 14	99.76 2	98.64 25	98.90 111	98.74 123	97.27 69	98.02 139	99.39 46	94.81 84	99.96 4	97.91 92	99.79 30	99.77 35

sss		97.39 128	96.98 138	98.61 95	98.60 175	96.61 136	98.22 266	98.93 61	93.97 255	98.01 142	98.48 203	91.98 142	99.85 78	96.45 178	98.15 203	99.39 126

alignmvs		97.56 114	97.07 130	99.01 64	98.66 167	98.37 43	98.83 139	98.06 302	96.74 99	98.00 143	97.65 286	90.80 186	99.48 189	98.37 69	96.56 259	99.19 171

viewmanbaseed2359cas		97.47 119	97.25 117	98.14 145	98.41 190	95.84 189	98.57 216	98.43 213	95.55 159	97.97 144	99.12 103	91.26 169	99.15 237	97.42 131	98.53 180	99.43 120

OMC-MVS		97.55 115	97.34 113	98.20 141	99.33 68	95.92 180	98.28 260	98.59 166	95.52 161	97.97 144	99.10 106	93.28 112	99.49 184	95.09 229	98.88 156	99.19 171

VDD-MVS		95.82 214	95.23 228	97.61 203	98.84 149	93.98 280	98.68 187	97.40 358	95.02 198	97.95 146	99.34 62	74.37 427	99.78 118	98.64 46	96.80 250	99.08 195

casdiffmvs		97.63 105	97.41 108	98.28 131	98.33 205	96.14 164	98.82 141	98.32 237	96.38 119	97.95 146	99.21 83	91.23 170	99.23 225	98.12 80	98.37 195	99.48 108
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_BlendedMVS		96.73 167	96.60 161	97.12 232	99.25 90	95.35 213	98.26 263	99.26 16	94.28 239	97.94 148	97.46 302	92.74 118	99.81 96	96.88 158	93.32 325	96.20 395

PVSNet_Blended		97.38 129	97.12 126	98.14 145	99.25 90	95.35 213	97.28 370	99.26 16	93.13 306	97.94 148	98.21 233	92.74 118	99.81 96	96.88 158	99.40 126	99.27 151

DPM-MVS		97.55 115	96.99 136	99.23 44	99.04 122	98.55 28	97.17 382	98.35 232	94.85 210	97.93 150	98.58 193	95.07 78	99.71 135	92.60 312	99.34 132	99.43 120

MP-MVS		98.33 67	98.01 78	99.28 37	99.75 3	98.18 56	99.22 37	98.79 113	96.13 129	97.92 151	99.23 79	94.54 87	99.94 13	96.74 170	99.78 35	99.73 50
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
Elysia		96.64 171	96.02 187	98.51 108	98.04 248	97.30 97	98.74 167	98.60 159	95.04 194	97.91 152	98.84 154	83.59 354	99.48 189	94.20 265	99.25 137	98.75 233

StellarMVS		96.64 171	96.02 187	98.51 108	98.04 248	97.30 97	98.74 167	98.60 159	95.04 194	97.91 152	98.84 154	83.59 354	99.48 189	94.20 265	99.25 137	98.75 233

MDTV_nov1_ep13_2view						84.26 435	96.89 402		90.97 378	97.90 154		89.89 204		93.91 276		99.18 176

test_prior2							97.80 330		96.12 131	97.89 155	98.69 182	95.96 41		96.89 156	99.60 88

viewmacassd2359aftdt		97.32 133	97.07 130	98.08 156	98.30 210	95.69 195	98.62 204	98.44 205	95.56 157	97.86 156	99.22 81	89.91 203	99.14 240	97.29 139	98.43 188	99.42 123

mamv4		97.13 147	98.11 71	94.17 393	98.97 134	83.70 437	98.66 194	98.71 131	94.63 222	97.83 157	98.90 146	96.25 29	99.55 173	99.27 26	99.76 43	99.27 151

原ACMM1				98.65 92	99.32 71	96.62 134		98.67 145	93.27 300	97.81 158	98.97 131	95.18 73	99.83 84	93.84 278	99.46 119	99.50 101

viewmambaseed2359dif		97.01 153	96.84 144	97.51 208	98.19 224	94.21 274	98.16 279	98.23 262	93.61 284	97.78 159	99.13 100	90.79 189	99.18 233	97.24 140	98.40 194	99.15 178

114514_t		96.93 156	96.27 176	98.92 73	99.50 44	97.63 78	98.85 133	98.90 68	84.80 433	97.77 160	99.11 104	92.84 116	99.66 146	94.85 235	99.77 37	99.47 110

casdiffmvs_mvg		97.72 96	97.48 103	98.44 119	98.42 188	96.59 141	98.92 108	98.44 205	96.20 126	97.76 161	99.20 85	91.66 152	99.23 225	98.27 76	98.41 193	99.49 106
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PMMVS		96.60 174	96.33 174	97.41 214	97.90 268	93.93 282	97.35 364	98.41 216	92.84 318	97.76 161	97.45 304	91.10 179	99.20 230	96.26 184	97.91 211	99.11 186

PVSNet	91.96 18	96.35 187	96.15 180	96.96 245	99.17 105	92.05 340	96.08 420	98.68 140	93.69 276	97.75 163	97.80 273	88.86 240	99.69 141	94.26 263	99.01 149	99.15 178

TEST9					99.31 73	98.50 30	97.92 311	98.73 126	92.63 324	97.74 164	98.68 183	96.20 32	99.80 103

train_agg		97.97 81	97.52 99	99.33 31	99.31 73	98.50 30	97.92 311	98.73 126	92.98 312	97.74 164	98.68 183	96.20 32	99.80 103	96.59 171	99.57 94	99.68 70

FE-MVS		95.62 225	94.90 245	97.78 181	98.37 195	94.92 238	97.17 382	97.38 360	90.95 379	97.73 166	97.70 279	85.32 318	99.63 153	91.18 347	98.33 198	98.79 224

mmtdpeth		93.12 359	92.61 355	94.63 379	97.60 291	89.68 391	99.21 40	97.32 363	94.02 249	97.72 167	94.42 427	77.01 411	99.44 196	99.05 30	77.18 449	94.78 427

CANet		98.05 80	97.76 86	98.90 76	98.73 155	97.27 101	98.35 247	98.78 115	97.37 60	97.72 167	98.96 136	91.53 158	99.92 41	98.79 39	99.65 76	99.51 99

test_8					99.29 82	98.44 32	97.89 319	98.72 128	92.98 312	97.70 169	98.66 186	96.20 32	99.80 103

MP-MVS-pluss		98.31 68	97.92 81	99.49 12	99.72 14	98.88 18	98.43 241	98.78 115	94.10 245	97.69 170	99.42 42	95.25 69	99.92 41	98.09 82	99.80 24	99.67 74
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
sasdasda		97.67 100	97.23 120	98.98 67	98.70 160	98.38 36	99.34 17	98.39 222	96.76 97	97.67 171	97.40 309	92.26 130	99.49 184	98.28 73	96.28 273	99.08 195

canonicalmvs		97.67 100	97.23 120	98.98 67	98.70 160	98.38 36	99.34 17	98.39 222	96.76 97	97.67 171	97.40 309	92.26 130	99.49 184	98.28 73	96.28 273	99.08 195

PVSNet_Blended_VisFu		97.70 98	97.46 104	98.44 119	99.27 87	95.91 181	98.63 201	99.16 36	94.48 234	97.67 171	98.88 150	92.80 117	99.91 51	97.11 144	99.12 143	99.50 101

WTY-MVS		97.37 131	96.92 140	98.72 86	98.86 145	96.89 125	98.31 254	98.71 131	95.26 177	97.67 171	98.56 197	92.21 134	99.78 118	95.89 196	96.85 249	99.48 108

Effi-MVS+		97.12 148	96.69 155	98.39 126	98.19 224	96.72 132	97.37 361	98.43 213	93.71 273	97.65 175	98.02 247	92.20 135	99.25 222	96.87 161	97.79 216	99.19 171

thisisatest0530		96.01 200	95.36 219	97.97 167	98.38 193	95.52 203	98.88 122	94.19 443	94.04 247	97.64 176	98.31 223	83.82 352	99.46 194	95.29 223	97.70 221	98.93 213

tttt0517		96.07 198	95.51 212	97.78 181	98.41 190	94.84 241	99.28 25	94.33 441	94.26 241	97.64 176	98.64 187	84.05 345	99.47 193	95.34 218	97.60 224	99.03 202

viewmsd2359difaftdt		96.30 189	96.13 181	96.81 256	98.10 239	92.10 337	98.49 231	98.40 218	96.02 134	97.61 178	99.31 65	86.37 296	99.30 213	97.52 125	93.37 324	99.04 201

HyFIR lowres test		96.90 158	96.49 167	98.14 145	99.33 68	95.56 199	97.38 359	99.65 2	92.34 336	97.61 178	98.20 234	89.29 224	99.10 251	96.97 149	97.60 224	99.77 35

ACMMP		98.23 71	97.95 80	99.09 58	99.74 9	97.62 79	99.03 77	99.41 6	95.98 136	97.60 180	99.36 56	94.45 92	99.93 32	97.14 143	98.85 161	99.70 62
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
MGCFI-Net		97.62 106	97.19 123	98.92 73	98.66 167	98.20 54	99.32 22	98.38 226	96.69 103	97.58 181	97.42 308	92.10 138	99.50 183	98.28 73	96.25 276	99.08 195

agg_prior					99.30 77	98.38 36		98.72 128		97.57 182			99.81 96

tpmrst		95.63 224	95.69 206	95.44 347	97.54 298	88.54 413	96.97 392	97.56 336	93.50 288	97.52 183	96.93 358	89.49 213	99.16 234	95.25 225	96.42 264	98.64 248

MDTV_nov1_ep13			95.40 214		97.48 303	88.34 417	96.85 405	97.29 366	93.74 269	97.48 184	97.26 318	89.18 227	99.05 256	91.92 334	97.43 234

FA-MVS(test-final)		96.41 186	95.94 191	97.82 178	98.21 220	95.20 221	97.80 330	97.58 333	93.21 301	97.36 185	97.70 279	89.47 215	99.56 166	94.12 269	97.99 208	98.71 238

icg_test_0407_2		96.56 178	96.50 166	96.73 260	97.99 255	92.82 325	97.18 379	98.27 251	95.16 182	97.30 186	98.79 163	91.53 158	98.10 369	94.74 240	97.54 228	99.27 151

IMVS_0407		96.74 165	96.64 159	97.05 238	97.99 255	92.82 325	98.45 234	98.27 251	95.16 182	97.30 186	98.79 163	91.53 158	99.06 255	94.74 240	97.54 228	99.27 151

EPMVS		94.99 267	94.48 266	96.52 289	97.22 323	91.75 345	97.23 372	91.66 455	94.11 244	97.28 188	96.81 367	85.70 308	98.84 290	93.04 301	97.28 236	98.97 208

EIA-MVS		97.75 94	97.58 92	98.27 132	98.38 193	96.44 148	99.01 82	98.60 159	95.88 141	97.26 189	97.53 299	94.97 81	99.33 208	97.38 136	99.20 140	99.05 200

SSM_0404		97.26 137	97.00 134	98.03 161	98.46 186	95.99 167	98.62 204	98.44 205	94.77 213	97.24 190	98.93 140	91.22 171	99.28 216	96.54 173	98.74 166	98.84 220

IS-MVSNet		97.22 139	96.88 141	98.25 136	98.85 148	96.36 154	99.19 45	97.97 307	95.39 168	97.23 191	98.99 130	91.11 178	98.93 277	94.60 249	98.59 174	99.47 110

testing3-2		95.45 234	95.34 220	95.77 334	98.69 163	88.75 409	98.87 125	97.21 374	96.13 129	97.22 192	97.68 284	77.95 399	99.65 147	97.58 117	96.77 253	98.91 215

EPP-MVSNet		97.46 120	97.28 115	97.99 166	98.64 171	95.38 210	99.33 21	98.31 241	93.61 284	97.19 193	99.07 119	94.05 100	99.23 225	96.89 156	98.43 188	99.37 129

thisisatest0515		95.61 228	94.89 246	97.76 185	98.15 235	95.15 224	96.77 408	94.41 439	92.95 314	97.18 194	97.43 306	84.78 327	99.45 195	94.63 246	97.73 220	98.68 242

IMVS_0403		96.74 165	96.61 160	97.12 232	97.99 255	92.82 325	98.47 232	98.27 251	95.16 182	97.13 195	98.79 163	91.44 161	99.26 219	94.74 240	97.54 228	99.27 151

CANet_DTU		96.96 155	96.55 163	98.21 139	98.17 233	96.07 166	97.98 304	98.21 264	97.24 70	97.13 195	98.93 140	86.88 286	99.91 51	95.00 232	99.37 130	98.66 246

CHOSEN 1792x2688		97.12 148	96.80 146	98.08 156	99.30 77	94.56 258	98.05 295	99.71 1	93.57 286	97.09 197	98.91 145	88.17 256	99.89 62	96.87 161	99.56 102	99.81 22

PatchT		93.06 360	91.97 367	96.35 305	96.69 359	92.67 329	94.48 446	97.08 381	86.62 421	97.08 198	92.23 446	87.94 264	97.90 388	78.89 443	96.69 254	98.49 261

PatchmatchNet		95.71 219	95.52 210	96.29 310	97.58 293	90.72 366	96.84 406	97.52 344	94.06 246	97.08 198	96.96 354	89.24 226	98.90 283	92.03 330	98.37 195	99.26 158
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
MAR-MVS		96.91 157	96.40 170	98.45 117	98.69 163	96.90 123	98.66 194	98.68 140	92.40 335	97.07 200	97.96 254	91.54 157	99.75 126	93.68 282	98.92 153	98.69 240
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
PAPM_NR		97.46 120	97.11 127	98.50 111	99.50 44	96.41 151	98.63 201	98.60 159	95.18 181	97.06 201	98.06 244	94.26 97	99.57 163	93.80 280	98.87 158	99.52 96

TAMVS		97.02 152	96.79 148	97.70 191	98.06 244	95.31 216	98.52 221	98.31 241	93.95 256	97.05 202	98.61 188	93.49 108	98.52 321	95.33 219	97.81 215	99.29 148

CSCG		97.85 89	97.74 87	98.20 141	99.67 27	95.16 222	99.22 37	99.32 12	93.04 310	97.02 203	98.92 144	95.36 61	99.91 51	97.43 130	99.64 81	99.52 96

CDS-MVSNet		96.99 154	96.69 155	97.90 171	98.05 246	95.98 168	98.20 269	98.33 236	93.67 280	96.95 204	98.49 202	93.54 107	98.42 332	95.24 226	97.74 219	99.31 142
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
XVG-OURS-SEG-HR		96.51 180	96.34 173	97.02 240	98.77 153	93.76 287	97.79 332	98.50 193	95.45 164	96.94 205	99.09 114	87.87 267	99.55 173	96.76 169	95.83 287	97.74 288

CR-MVSNet		94.76 282	94.15 287	96.59 279	97.00 337	93.43 301	94.96 436	97.56 336	92.46 329	96.93 206	96.24 387	88.15 257	97.88 392	87.38 403	96.65 256	98.46 263

RPMNet		92.81 362	91.34 373	97.24 221	97.00 337	93.43 301	94.96 436	98.80 108	82.27 440	96.93 206	92.12 447	86.98 284	99.82 91	76.32 448	96.65 256	98.46 263

SCA		95.46 232	95.13 232	96.46 297	97.67 285	91.29 354	97.33 366	97.60 332	94.68 219	96.92 208	97.10 329	83.97 347	98.89 284	92.59 314	98.32 200	99.20 167

PatchMatch-RL		96.59 175	96.03 186	98.27 132	99.31 73	96.51 145	97.91 313	99.06 44	93.72 272	96.92 208	98.06 244	88.50 251	99.65 147	91.77 337	99.00 151	98.66 246

DeepC-MVS	95.98 3	97.88 86	97.58 92	98.77 82	99.25 90	96.93 121	98.83 139	98.75 121	96.96 88	96.89 210	99.50 27	90.46 193	99.87 73	97.84 98	99.76 43	99.52 96
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
XVG-OURS		96.55 179	96.41 169	96.99 241	98.75 154	93.76 287	97.50 353	98.52 185	95.67 153	96.83 211	99.30 67	88.95 239	99.53 176	95.88 197	96.26 275	97.69 291

AdaColmap		97.15 146	96.70 154	98.48 114	99.16 109	96.69 133	98.01 300	98.89 70	94.44 236	96.83 211	98.68 183	90.69 190	99.76 124	94.36 257	99.29 136	98.98 207

CostFormer		94.95 272	94.73 252	95.60 341	97.28 319	89.06 402	97.53 350	96.89 399	89.66 401	96.82 213	96.72 371	86.05 302	98.95 276	95.53 214	96.13 281	98.79 224

UGNet		96.78 164	96.30 175	98.19 144	98.24 216	95.89 186	98.88 122	98.93 61	97.39 57	96.81 214	97.84 267	82.60 359	99.90 59	96.53 175	99.49 113	98.79 224
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
CNLPA		97.45 123	97.03 133	98.73 85	99.05 121	97.44 90	98.07 293	98.53 182	95.32 174	96.80 215	98.53 198	93.32 110	99.72 130	94.31 261	99.31 135	99.02 203

CHOSEN 280x420		97.18 143	97.18 124	97.20 223	98.81 151	93.27 310	95.78 427	99.15 38	95.25 178	96.79 216	98.11 241	92.29 129	99.07 254	98.56 52	99.85 6	99.25 160

mamba_0408		96.81 163	96.38 171	98.09 155	98.19 224	95.90 182	95.69 428	98.32 237	94.51 231	96.75 217	98.73 177	90.99 182	99.27 218	95.83 199	98.43 188	99.10 188

SSM_04072		96.71 168	96.38 171	97.68 194	98.19 224	95.90 182	95.69 428	98.32 237	94.51 231	96.75 217	98.73 177	90.99 182	98.02 378	95.83 199	98.43 188	99.10 188

SSM_0407		97.17 144	96.87 142	98.08 156	98.19 224	95.90 182	98.52 221	98.44 205	94.77 213	96.75 217	98.93 140	91.22 171	99.22 229	96.54 173	98.43 188	99.10 188

HY-MVS	93.96 8	96.82 162	96.23 179	98.57 98	98.46 186	97.00 118	98.14 282	98.21 264	93.95 256	96.72 220	97.99 251	91.58 153	99.76 124	94.51 253	96.54 260	98.95 211

PAPR		96.84 161	96.24 178	98.65 92	98.72 159	96.92 122	97.36 363	98.57 173	93.33 295	96.67 221	97.57 295	94.30 95	99.56 166	91.05 355	98.59 174	99.47 110

Anonymous20240529		95.10 260	94.22 281	97.75 186	99.01 126	94.26 271	98.87 125	98.83 92	85.79 429	96.64 222	98.97 131	78.73 388	99.85 78	96.27 183	94.89 293	99.12 183

UWE-MVS		94.30 315	93.89 309	95.53 342	97.83 272	88.95 406	97.52 352	93.25 447	94.44 236	96.63 223	97.07 336	78.70 389	99.28 216	91.99 331	97.56 227	98.36 268

thres600view7		95.49 230	94.77 249	97.67 196	98.98 132	95.02 229	98.85 133	96.90 397	95.38 169	96.63 223	96.90 360	84.29 337	99.59 160	88.65 393	96.33 266	98.40 265

thres100view900		95.38 240	94.70 254	97.41 214	98.98 132	94.92 238	98.87 125	96.90 397	95.38 169	96.61 225	96.88 361	84.29 337	99.56 166	88.11 396	96.29 270	97.76 286

Vis-MVSNet (Re-imp)		96.87 159	96.55 163	97.83 176	98.73 155	95.46 206	99.20 43	98.30 248	94.96 202	96.60 226	98.87 151	90.05 200	98.59 316	93.67 284	98.60 173	99.46 115

CVMVSNet		95.43 236	96.04 185	93.57 400	97.93 266	83.62 438	98.12 285	98.59 166	95.68 152	96.56 227	99.02 123	87.51 273	97.51 409	93.56 288	97.44 233	99.60 87

RPSCF		94.87 276	95.40 214	93.26 406	98.89 140	82.06 444	98.33 249	98.06 302	90.30 391	96.56 227	99.26 73	87.09 281	99.49 184	93.82 279	96.32 267	98.24 272

tfpn200view9		95.32 247	94.62 258	97.43 212	98.94 137	94.98 234	98.68 187	96.93 395	95.33 172	96.55 229	96.53 380	84.23 341	99.56 166	88.11 396	96.29 270	97.76 286

thres400		95.38 240	94.62 258	97.65 200	98.94 137	94.98 234	98.68 187	96.93 395	95.33 172	96.55 229	96.53 380	84.23 341	99.56 166	88.11 396	96.29 270	98.40 265

thres200		95.25 250	94.57 261	97.28 220	98.81 151	94.92 238	98.20 269	97.11 379	95.24 180	96.54 231	96.22 391	84.58 334	99.53 176	87.93 401	96.50 262	97.39 300

ab-mvs		96.42 183	95.71 203	98.55 101	98.63 172	96.75 130	97.88 320	98.74 123	93.84 262	96.54 231	98.18 236	85.34 316	99.75 126	95.93 195	96.35 265	99.15 178

Anonymous202405211		95.28 249	94.49 265	97.67 196	99.00 128	93.75 289	98.70 182	97.04 386	90.66 382	96.49 233	98.80 161	78.13 395	99.83 84	96.21 187	95.36 292	99.44 118

ADS-MVSNet2		94.58 294	94.40 275	95.11 357	98.00 253	88.74 410	96.04 421	97.30 365	90.15 392	96.47 234	96.64 377	87.89 265	97.56 407	90.08 367	97.06 241	99.02 203

ADS-MVSNet		95.00 265	94.45 271	96.63 273	98.00 253	91.91 342	96.04 421	97.74 321	90.15 392	96.47 234	96.64 377	87.89 265	98.96 271	90.08 367	97.06 241	99.02 203

Effi-MVS+-dtu		96.29 190	96.56 162	95.51 343	97.89 270	90.22 380	98.80 150	98.10 290	96.57 110	96.45 236	96.66 374	90.81 185	98.91 280	95.72 206	97.99 208	97.40 299

ETVMVS		94.50 302	93.44 336	97.68 194	98.18 230	95.35 213	98.19 272	97.11 379	93.73 270	96.40 237	95.39 416	74.53 424	98.84 290	91.10 349	96.31 268	98.84 220

PLC	95.07 4	97.20 142	96.78 149	98.44 119	99.29 82	96.31 158	98.14 282	98.76 119	92.41 334	96.39 238	98.31 223	94.92 83	99.78 118	94.06 272	98.77 165	99.23 162
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		94.13 329	93.80 315	95.12 356	96.50 368	87.91 423	97.44 354	95.89 426	92.62 325	96.37 239	96.30 386	84.13 344	98.30 355	93.24 294	91.66 347	99.14 181

TAPA-MVS	93.98 7	95.35 244	94.56 262	97.74 187	99.13 113	94.83 243	98.33 249	98.64 153	86.62 421	96.29 240	98.61 188	94.00 102	99.29 215	80.00 439	99.41 123	99.09 191
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
myMVS_eth3d28		95.12 258	94.62 258	96.64 272	98.17 233	92.17 334	98.02 299	97.32 363	95.41 167	96.22 241	96.05 397	78.01 397	99.13 242	95.22 227	97.16 238	98.60 251

baseline1		95.84 212	95.12 234	98.01 164	98.49 185	95.98 168	98.73 173	97.03 387	95.37 171	96.22 241	98.19 235	89.96 202	99.16 234	94.60 249	87.48 400	98.90 216

tpm2		94.19 324	93.76 320	95.46 346	97.23 322	89.04 403	97.31 368	96.85 403	87.08 420	96.21 243	96.79 368	83.75 353	98.74 301	92.43 322	96.23 278	98.59 254

UBG		95.32 247	94.72 253	97.13 230	98.05 246	93.26 311	97.87 321	97.20 375	94.96 202	96.18 244	95.66 413	80.97 371	99.35 205	94.47 255	97.08 240	98.78 228

F-COLMAP		97.09 150	96.80 146	97.97 167	99.45 57	94.95 237	98.55 219	98.62 158	93.02 311	96.17 245	98.58 193	94.01 101	99.81 96	93.95 274	98.90 154	99.14 181

GeoE		96.58 177	96.07 183	98.10 154	98.35 197	95.89 186	99.34 17	98.12 284	93.12 307	96.09 246	98.87 151	89.71 209	98.97 267	92.95 304	98.08 206	99.43 120

JIA-IIPM		93.35 349	92.49 359	95.92 324	96.48 370	90.65 368	95.01 435	96.96 393	85.93 427	96.08 247	87.33 452	87.70 271	98.78 299	91.35 345	95.58 290	98.34 269

BH-RMVSNet		95.92 208	95.32 224	97.69 192	98.32 208	94.64 250	98.19 272	97.45 354	94.56 226	96.03 248	98.61 188	85.02 321	99.12 245	90.68 360	99.06 145	99.30 145

dp		94.15 328	93.90 307	94.90 365	97.31 318	86.82 429	96.97 392	97.19 376	91.22 374	96.02 249	96.61 379	85.51 312	99.02 263	90.00 371	94.30 295	98.85 218

EPNet		97.28 135	96.87 142	98.51 108	94.98 419	96.14 164	98.90 111	97.02 390	98.28 19	95.99 250	99.11 104	91.36 163	99.89 62	96.98 148	99.19 141	99.50 101
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
LS3D		97.16 145	96.66 158	98.68 89	98.53 180	97.19 110	98.93 106	98.90 68	92.83 319	95.99 250	99.37 52	92.12 137	99.87 73	93.67 284	99.57 94	98.97 208

SDMVSNet		96.85 160	96.42 168	98.14 145	99.30 77	96.38 152	99.21 40	99.23 25	95.92 138	95.96 252	98.76 175	85.88 305	99.44 196	97.93 90	95.59 288	98.60 251

sd_testset		96.17 195	95.76 198	97.42 213	99.30 77	94.34 267	98.82 141	99.08 42	95.92 138	95.96 252	98.76 175	82.83 358	99.32 209	95.56 212	95.59 288	98.60 251

AUN-MVS		94.53 299	93.73 322	96.92 250	98.50 181	93.52 299	98.34 248	98.10 290	93.83 264	95.94 254	97.98 253	85.59 311	99.03 260	94.35 258	80.94 437	98.22 274

testing222		94.12 331	93.03 346	97.37 219	98.02 251	94.66 248	97.94 309	96.65 411	94.63 222	95.78 255	95.76 405	71.49 432	98.92 278	91.17 348	95.88 285	98.52 259

TR-MVS		94.94 274	94.20 282	97.17 227	97.75 277	94.14 277	97.59 347	97.02 390	92.28 340	95.75 256	97.64 289	83.88 349	98.96 271	89.77 373	96.15 280	98.40 265

WB-MVSnew		94.19 324	94.04 293	94.66 377	96.82 351	92.14 335	97.86 323	95.96 423	93.50 288	95.64 257	96.77 369	88.06 261	97.99 382	84.87 420	96.86 247	93.85 439

MonoMVSNet		95.51 229	95.45 213	95.68 336	95.54 406	90.87 361	98.92 108	97.37 361	95.79 146	95.53 258	97.38 311	89.58 212	97.68 400	96.40 180	92.59 335	98.49 261

VPA-MVSNet		95.75 217	95.11 235	97.69 192	97.24 321	97.27 101	98.94 100	99.23 25	95.13 187	95.51 259	97.32 315	85.73 307	98.91 280	97.33 138	89.55 375	96.89 326

testing91		94.98 269	94.25 280	97.20 223	97.94 264	93.41 303	98.00 302	97.58 333	94.99 199	95.45 260	96.04 398	77.20 407	99.42 198	94.97 233	96.02 283	98.78 228

testing99		94.83 277	94.08 291	97.07 237	97.94 264	93.13 317	98.10 290	97.17 377	94.86 208	95.34 261	96.00 402	76.31 415	99.40 200	95.08 230	95.90 284	98.68 242

HQP_MVS		96.14 197	95.90 193	96.85 253	97.42 310	94.60 256	98.80 150	98.56 176	97.28 65	95.34 261	98.28 225	87.09 281	99.03 260	96.07 188	94.27 296	96.92 318

plane_prior3						94.61 254			97.02 85	95.34 261

testing11		95.00 265	94.28 278	97.16 228	97.96 263	93.36 308	98.09 291	97.06 385	94.94 206	95.33 264	96.15 393	76.89 412	99.40 200	95.77 205	96.30 269	98.72 235

Fast-Effi-MVS+		96.28 192	95.70 205	98.03 161	98.29 212	95.97 173	98.58 209	98.25 260	91.74 353	95.29 265	97.23 322	91.03 181	99.15 237	92.90 306	97.96 210	98.97 208

test_fmvs2		93.43 347	93.58 329	92.95 410	96.97 340	83.91 436	99.19 45	97.24 371	95.74 148	95.20 266	98.27 228	69.65 434	98.72 303	96.26 184	93.73 313	96.24 393

EI-MVSNet		95.96 202	95.83 195	96.36 304	97.93 266	93.70 293	98.12 285	98.27 251	93.70 275	95.07 267	99.02 123	92.23 133	98.54 319	94.68 244	93.46 319	96.84 333

MVSTER		96.06 199	95.72 200	97.08 236	98.23 218	95.93 179	98.73 173	98.27 251	94.86 208	95.07 267	98.09 242	88.21 255	98.54 319	96.59 171	93.46 319	96.79 337

OPM-MVS		95.69 222	95.33 223	96.76 259	96.16 385	94.63 251	98.43 241	98.39 222	96.64 106	95.02 269	98.78 167	85.15 320	99.05 256	95.21 228	94.20 299	96.60 360
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
Fast-Effi-MVS+-dtu		95.87 210	95.85 194	95.91 325	97.74 280	91.74 346	98.69 185	98.15 280	95.56 157	94.92 270	97.68 284	88.98 237	98.79 298	93.19 296	97.78 217	97.20 306

TESTMET0.1,1		94.18 327	93.69 325	95.63 339	96.92 343	89.12 401	96.91 397	94.78 436	93.17 303	94.88 271	96.45 383	78.52 390	98.92 278	93.09 298	98.50 183	98.85 218

VPNet		94.99 267	94.19 283	97.40 216	97.16 330	96.57 142	98.71 178	98.97 53	95.67 153	94.84 272	98.24 232	80.36 378	98.67 308	96.46 177	87.32 404	96.96 313

1112_ss		96.63 173	96.00 189	98.50 111	98.56 176	96.37 153	98.18 277	98.10 290	92.92 315	94.84 272	98.43 206	92.14 136	99.58 162	94.35 258	96.51 261	99.56 95

test-LLR		95.10 260	94.87 247	95.80 331	96.77 353	89.70 389	96.91 397	95.21 431	95.11 189	94.83 274	95.72 410	87.71 269	98.97 267	93.06 299	98.50 183	98.72 235

test-mter		94.08 335	93.51 333	95.80 331	96.77 353	89.70 389	96.91 397	95.21 431	92.89 316	94.83 274	95.72 410	77.69 401	98.97 267	93.06 299	98.50 183	98.72 235

Test_1112_low_res		96.34 188	95.66 208	98.36 127	98.56 176	95.94 176	97.71 337	98.07 297	92.10 345	94.79 276	97.29 317	91.75 148	99.56 166	94.17 267	96.50 262	99.58 93

UWE-MVS-28		92.79 363	92.51 358	93.62 399	96.46 371	86.28 430	97.93 310	92.71 452	94.17 242	94.78 277	97.16 326	81.05 370	96.43 431	81.45 435	96.86 247	98.14 278

GA-MVS		94.81 278	94.03 295	97.14 229	97.15 331	93.86 284	96.76 409	97.58 333	94.00 253	94.76 278	97.04 344	80.91 372	98.48 323	91.79 336	96.25 276	99.09 191

BH-untuned		95.95 203	95.72 200	96.65 268	98.55 178	92.26 333	98.23 265	97.79 318	93.73 270	94.62 279	98.01 249	88.97 238	99.00 266	93.04 301	98.51 182	98.68 242

test_djsdf		96.00 201	95.69 206	96.93 247	95.72 401	95.49 204	99.47 7	98.40 218	94.98 200	94.58 280	97.86 264	89.16 228	98.41 339	96.91 152	94.12 304	96.88 327

cascas		94.63 290	93.86 311	96.93 247	96.91 345	94.27 270	96.00 424	98.51 188	85.55 430	94.54 281	96.23 389	84.20 343	98.87 287	95.80 203	96.98 246	97.66 292

DP-MVS		96.59 175	95.93 192	98.57 98	99.34 65	96.19 162	98.70 182	98.39 222	89.45 405	94.52 282	99.35 58	91.85 146	99.85 78	92.89 308	98.88 156	99.68 70

gg-mvs-nofinetune		92.21 371	90.58 379	97.13 230	96.75 356	95.09 226	95.85 425	89.40 460	85.43 431	94.50 283	81.98 455	80.80 375	98.40 345	92.16 324	98.33 198	97.88 283

mvs_anonymous		96.70 170	96.53 165	97.18 226	98.19 224	93.78 286	98.31 254	98.19 268	94.01 252	94.47 284	98.27 228	92.08 140	98.46 327	97.39 135	97.91 211	99.31 142

HQP-NCC					97.20 325		98.05 295		96.43 114	94.45 285

ACMP_Plane					97.20 325		98.05 295		96.43 114	94.45 285

HQP4-MVS										94.45 285			98.96 271			96.87 330

HQP-MVS		95.72 218	95.40 214	96.69 266	97.20 325	94.25 272	98.05 295	98.46 201	96.43 114	94.45 285	97.73 276	86.75 287	98.96 271	95.30 221	94.18 300	96.86 332

MSDG		95.93 207	95.30 226	97.83 176	98.90 139	95.36 211	96.83 407	98.37 228	91.32 368	94.43 289	98.73 177	90.27 198	99.60 159	90.05 369	98.82 163	98.52 259

dmvs_re		94.48 305	94.18 285	95.37 349	97.68 284	90.11 382	98.54 220	97.08 381	94.56 226	94.42 290	97.24 321	84.25 339	97.76 398	91.02 356	92.83 332	98.24 272

nrg030		96.28 192	95.72 200	97.96 169	96.90 346	98.15 59	99.39 11	98.31 241	95.47 163	94.42 290	98.35 216	92.09 139	98.69 304	97.50 128	89.05 384	97.04 309

CLD-MVS		95.62 225	95.34 220	96.46 297	97.52 301	93.75 289	97.27 371	98.46 201	95.53 160	94.42 290	98.00 250	86.21 299	98.97 267	96.25 186	94.37 294	96.66 355
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
LPG-MVS_test		95.62 225	95.34 220	96.47 294	97.46 305	93.54 296	98.99 87	98.54 180	94.67 220	94.36 293	98.77 170	85.39 313	99.11 247	95.71 207	94.15 302	96.76 340

LGP-MVS_train				96.47 294	97.46 305	93.54 296		98.54 180	94.67 220	94.36 293	98.77 170	85.39 313	99.11 247	95.71 207	94.15 302	96.76 340

v144192		94.39 311	93.70 324	96.48 293	96.06 389	94.35 266	98.58 209	98.16 279	91.45 361	94.33 295	97.02 347	87.50 275	98.45 328	91.08 352	89.11 383	96.63 357

IMVS_0404		95.82 214	95.52 210	96.73 260	97.99 255	92.82 325	97.23 372	98.27 251	95.16 182	94.31 296	98.79 163	85.63 309	98.10 369	94.74 240	97.54 228	99.27 151

V42		94.78 280	94.14 288	96.70 265	96.33 377	95.22 220	98.97 91	98.09 294	92.32 338	94.31 296	97.06 340	88.39 252	98.55 318	92.90 306	88.87 388	96.34 388

VortexMVS		95.95 203	95.79 196	96.42 300	98.29 212	93.96 281	98.68 187	98.31 241	96.02 134	94.29 298	97.57 295	89.47 215	98.37 346	97.51 127	91.93 341	96.94 316

ACMM	93.85 9	95.69 222	95.38 218	96.61 276	97.61 290	93.84 285	98.91 110	98.44 205	95.25 178	94.28 299	98.47 204	86.04 304	99.12 245	95.50 215	93.95 309	96.87 330
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
IterMVS-LS		95.46 232	95.21 229	96.22 312	98.12 237	93.72 292	98.32 253	98.13 283	93.71 273	94.26 300	97.31 316	92.24 132	98.10 369	94.63 246	90.12 366	96.84 333
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		94.20 323	93.47 335	96.40 303	95.98 393	94.08 278	98.52 221	98.15 280	91.33 367	94.25 301	97.20 325	86.41 295	98.42 332	90.04 370	89.39 380	96.69 354

BH-w/o		95.38 240	95.08 236	96.26 311	98.34 202	91.79 343	97.70 338	97.43 356	92.87 317	94.24 302	97.22 323	88.66 244	98.84 290	91.55 343	97.70 221	98.16 277

XVG-ACMP-BASELINE		94.54 297	94.14 288	95.75 335	96.55 365	91.65 348	98.11 288	98.44 205	94.96 202	94.22 303	97.90 260	79.18 387	99.11 247	94.05 273	93.85 311	96.48 382

v1144		94.59 293	93.92 304	96.60 278	96.21 379	94.78 247	98.59 207	98.14 282	91.86 352	94.21 304	97.02 347	87.97 263	98.41 339	91.72 338	89.57 373	96.61 359

v1192		94.32 314	93.58 329	96.53 288	96.10 387	94.45 260	98.50 228	98.17 277	91.54 359	94.19 305	97.06 340	86.95 285	98.43 331	90.14 365	89.57 373	96.70 349

PAPM		94.95 272	94.00 299	97.78 181	97.04 336	95.65 196	96.03 423	98.25 260	91.23 373	94.19 305	97.80 273	91.27 168	98.86 289	82.61 431	97.61 223	98.84 220

Patchmatch-test		94.42 309	93.68 326	96.63 273	97.60 291	91.76 344	94.83 440	97.49 348	89.45 405	94.14 307	97.10 329	88.99 234	98.83 293	85.37 417	98.13 204	99.29 148

v1240		94.06 337	93.29 341	96.34 306	96.03 391	93.90 283	98.44 239	98.17 277	91.18 376	94.13 308	97.01 349	86.05 302	98.42 332	89.13 387	89.50 377	96.70 349

GBi-Net		94.49 303	93.80 315	96.56 283	98.21 220	95.00 230	98.82 141	98.18 271	92.46 329	94.09 309	97.07 336	81.16 367	97.95 384	92.08 326	92.14 338	96.72 345

test1		94.49 303	93.80 315	96.56 283	98.21 220	95.00 230	98.82 141	98.18 271	92.46 329	94.09 309	97.07 336	81.16 367	97.95 384	92.08 326	92.14 338	96.72 345

FMVSNet3		94.97 271	94.26 279	97.11 234	98.18 230	96.62 134	98.56 218	98.26 259	93.67 280	94.09 309	97.10 329	84.25 339	98.01 379	92.08 326	92.14 338	96.70 349

MIMVSNet		93.26 353	92.21 364	96.41 301	97.73 281	93.13 317	95.65 430	97.03 387	91.27 372	94.04 312	96.06 396	75.33 420	97.19 414	86.56 407	96.23 278	98.92 214

FIs		96.51 180	96.12 182	97.67 196	97.13 332	97.54 83	99.36 14	99.22 29	95.89 140	94.03 313	98.35 216	91.98 142	98.44 330	96.40 180	92.76 333	97.01 310

v2v482		94.69 283	94.03 295	96.65 268	96.17 383	94.79 246	98.67 192	98.08 295	92.72 321	94.00 314	97.16 326	87.69 272	98.45 328	92.91 305	88.87 388	96.72 345

testing3		93.19 356	92.48 360	95.30 352	98.07 241	92.27 332	98.64 198	97.17 377	93.94 258	93.98 315	97.04 344	67.97 439	96.01 436	88.40 394	97.14 239	97.63 293

FC-MVSNet-test		96.42 183	96.05 184	97.53 207	96.95 341	97.27 101	99.36 14	99.23 25	95.83 144	93.93 316	98.37 214	92.00 141	98.32 351	96.02 193	92.72 334	97.00 311

UniMVSNet (Re)		95.78 216	95.19 230	97.58 204	96.99 339	97.47 87	98.79 158	99.18 33	95.60 155	93.92 317	97.04 344	91.68 150	98.48 323	95.80 203	87.66 399	96.79 337

miper_enhance_ethall		95.10 260	94.75 251	96.12 316	97.53 300	93.73 291	96.61 414	98.08 295	92.20 344	93.89 318	96.65 376	92.44 123	98.30 355	94.21 264	91.16 353	96.34 388

UniMVSNet_NR-MVSNet		95.71 219	95.15 231	97.40 216	96.84 349	96.97 119	98.74 167	99.24 20	95.16 182	93.88 319	97.72 278	91.68 150	98.31 353	95.81 201	87.25 405	96.92 318

DU-MVS		95.42 237	94.76 250	97.40 216	96.53 366	96.97 119	98.66 194	98.99 52	95.43 165	93.88 319	97.69 281	88.57 246	98.31 353	95.81 201	87.25 405	96.92 318

Baseline_NR-MVSNet		94.35 312	93.81 314	95.96 323	96.20 380	94.05 279	98.61 206	96.67 409	91.44 362	93.85 321	97.60 292	88.57 246	98.14 366	94.39 256	86.93 408	95.68 408

PS-MVSNAJss		96.43 182	96.26 177	96.92 250	95.84 399	95.08 227	99.16 51	98.50 193	95.87 142	93.84 322	98.34 220	94.51 88	98.61 312	96.88 158	93.45 321	97.06 308

UniMVSNet_ETH3D		94.24 321	93.33 339	96.97 244	97.19 328	93.38 306	98.74 167	98.57 173	91.21 375	93.81 323	98.58 193	72.85 431	98.77 300	95.05 231	93.93 310	98.77 231

tt0805		94.54 297	93.85 312	96.63 273	97.98 261	93.06 322	98.77 162	97.84 316	93.67 280	93.80 324	98.04 246	76.88 413	98.96 271	94.79 239	92.86 331	97.86 285

tpmvs		94.60 291	94.36 276	95.33 351	97.46 305	88.60 412	96.88 403	97.68 322	91.29 370	93.80 324	96.42 384	88.58 245	99.24 224	91.06 353	96.04 282	98.17 276

WBMVS		94.56 295	94.04 293	96.10 317	98.03 250	93.08 321	97.82 329	98.18 271	94.02 249	93.77 326	96.82 366	81.28 366	98.34 348	95.47 217	91.00 356	96.88 327

3Dnovator	94.51 5	97.46 120	96.93 139	99.07 60	97.78 275	97.64 77	99.35 16	99.06 44	97.02 85	93.75 327	99.16 95	89.25 225	99.92 41	97.22 142	99.75 50	99.64 81

eth_miper_zixun_eth		94.68 285	94.41 274	95.47 345	97.64 288	91.71 347	96.73 411	98.07 297	92.71 322	93.64 328	97.21 324	90.54 192	98.17 364	93.38 290	89.76 370	96.54 369

SD_0403		94.28 319	94.46 268	93.73 397	98.02 251	85.32 433	98.31 254	98.40 218	94.75 215	93.59 329	98.16 237	89.01 233	96.54 428	82.32 432	97.58 226	99.34 135

ITE_SJBPF				95.44 347	97.42 310	91.32 353		97.50 346	95.09 192	93.59 329	98.35 216	81.70 362	98.88 286	89.71 375	93.39 323	96.12 398

TranMVSNet+NR-MVSNet		95.14 257	94.48 266	97.11 234	96.45 372	96.36 154	99.03 77	99.03 47	95.04 194	93.58 331	97.93 257	88.27 254	98.03 377	94.13 268	86.90 410	96.95 315

COLMAP_ROB	93.27 12	95.33 246	94.87 247	96.71 263	99.29 82	93.24 314	98.58 209	98.11 287	89.92 396	93.57 332	99.10 106	86.37 296	99.79 115	90.78 358	98.10 205	97.09 307
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
tpm cat1		93.36 348	92.80 350	95.07 360	97.58 293	87.97 422	96.76 409	97.86 315	82.17 441	93.53 333	96.04 398	86.13 300	99.13 242	89.24 385	95.87 286	98.10 279

AllTest		95.24 251	94.65 257	96.99 241	99.25 90	93.21 315	98.59 207	98.18 271	91.36 364	93.52 334	98.77 170	84.67 331	99.72 130	89.70 376	97.87 213	98.02 281

TestCases				96.99 241	99.25 90	93.21 315		98.18 271	91.36 364	93.52 334	98.77 170	84.67 331	99.72 130	89.70 376	97.87 213	98.02 281

miper_ehance_all_eth		95.01 264	94.69 255	95.97 322	97.70 283	93.31 309	97.02 390	98.07 297	92.23 341	93.51 336	96.96 354	91.85 146	98.15 365	93.68 282	91.16 353	96.44 385

SSC-MVS3.2		93.59 346	93.13 344	94.97 362	96.81 352	89.71 388	97.95 306	98.49 198	94.59 225	93.50 337	96.91 359	77.74 400	98.37 346	91.69 339	90.47 361	96.83 335

FMVSNet2		94.47 306	93.61 328	97.04 239	98.21 220	96.43 149	98.79 158	98.27 251	92.46 329	93.50 337	97.09 333	81.16 367	98.00 381	91.09 350	91.93 341	96.70 349

v148		94.29 317	93.76 320	95.91 325	96.10 387	92.93 323	98.58 209	97.97 307	92.59 327	93.47 339	96.95 356	88.53 250	98.32 351	92.56 316	87.06 407	96.49 380

c3_l		94.79 279	94.43 273	95.89 327	97.75 277	93.12 319	97.16 384	98.03 304	92.23 341	93.46 340	97.05 343	91.39 162	98.01 379	93.58 287	89.21 382	96.53 371

Syy-MVS		92.55 367	92.61 355	92.38 413	97.39 314	83.41 439	97.91 313	97.46 350	93.16 304	93.42 341	95.37 417	84.75 328	96.12 434	77.00 447	96.99 243	97.60 294

myMVS_eth3d		92.73 364	92.01 366	94.89 366	97.39 314	90.94 359	97.91 313	97.46 350	93.16 304	93.42 341	95.37 417	68.09 438	96.12 434	88.34 395	96.99 243	97.60 294

pmmvs4		94.69 283	93.99 301	96.81 256	95.74 400	95.94 176	97.40 357	97.67 325	90.42 388	93.37 343	97.59 293	89.08 231	98.20 362	92.97 303	91.67 346	96.30 391

PCF-MVS	93.45 11	94.68 285	93.43 337	98.42 123	98.62 173	96.77 129	95.48 433	98.20 266	84.63 434	93.34 344	98.32 222	88.55 249	99.81 96	84.80 423	98.96 152	98.68 242
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		94.68 285	94.19 283	96.13 315	98.11 238	93.60 294	96.94 394	98.31 241	92.43 333	93.32 345	96.87 363	86.51 290	98.28 359	94.10 271	91.16 353	96.51 377

XXY-MVS		95.20 254	94.45 271	97.46 209	96.75 356	96.56 143	98.86 129	98.65 152	93.30 298	93.27 346	98.27 228	84.85 325	98.87 287	94.82 237	91.26 352	96.96 313

jajsoiax		95.45 234	95.03 238	96.73 260	95.42 414	94.63 251	99.14 55	98.52 185	95.74 148	93.22 347	98.36 215	83.87 350	98.65 309	96.95 151	94.04 305	96.91 323

reproduce_monomvs		94.77 281	94.67 256	95.08 359	98.40 192	89.48 395	98.80 150	98.64 153	97.57 44	93.21 348	97.65 286	80.57 377	98.83 293	97.72 104	89.47 378	96.93 317

mvs_tets		95.41 239	95.00 239	96.65 268	95.58 405	94.42 262	99.00 84	98.55 178	95.73 150	93.21 348	98.38 213	83.45 356	98.63 310	97.09 145	94.00 307	96.91 323

anonymousdsp		95.42 237	94.91 244	96.94 246	95.10 418	95.90 182	99.14 55	98.41 216	93.75 267	93.16 350	97.46 302	87.50 275	98.41 339	95.63 211	94.03 306	96.50 379

v8		94.47 306	93.77 318	96.57 282	96.36 375	94.83 243	99.05 70	98.19 268	91.92 349	93.16 350	96.97 352	88.82 243	98.48 323	91.69 339	87.79 397	96.39 386

WR-MVS		95.15 256	94.46 268	97.22 222	96.67 361	96.45 147	98.21 267	98.81 101	94.15 243	93.16 350	97.69 281	87.51 273	98.30 355	95.29 223	88.62 390	96.90 325

EPNet_dtu		95.21 253	94.95 243	95.99 320	96.17 383	90.45 374	98.16 279	97.27 369	96.77 96	93.14 353	98.33 221	90.34 195	98.42 332	85.57 414	98.81 164	99.09 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
QAPM		96.29 190	95.40 214	98.96 70	97.85 271	97.60 80	99.23 33	98.93 61	89.76 399	93.11 354	99.02 123	89.11 230	99.93 32	91.99 331	99.62 85	99.34 135

GG-mvs-BLEND				96.59 279	96.34 376	94.98 234	96.51 417	88.58 461		93.10 355	94.34 432	80.34 380	98.05 376	89.53 379	96.99 243	96.74 342

v10		94.29 317	93.55 331	96.51 290	96.39 374	94.80 245	98.99 87	98.19 268	91.35 366	93.02 356	96.99 350	88.09 259	98.41 339	90.50 362	88.41 392	96.33 390

3Dnovator+	94.38 6	97.43 125	96.78 149	99.38 19	97.83 272	98.52 29	99.37 13	98.71 131	97.09 83	92.99 357	99.13 100	89.36 222	99.89 62	96.97 149	99.57 94	99.71 58

D2MVS		95.18 255	95.08 236	95.48 344	97.10 334	92.07 339	98.30 257	99.13 40	94.02 249	92.90 358	96.73 370	89.48 214	98.73 302	94.48 254	93.60 318	95.65 409

Patchmtry		93.22 354	92.35 362	95.84 330	96.77 353	93.09 320	94.66 443	97.56 336	87.37 419	92.90 358	96.24 387	88.15 257	97.90 388	87.37 404	90.10 367	96.53 371

DIV-MVS_self_test		94.52 300	94.03 295	95.99 320	97.57 297	93.38 306	97.05 388	97.94 310	91.74 353	92.81 360	97.10 329	89.12 229	98.07 375	92.60 312	90.30 363	96.53 371

Anonymous20231211		94.10 333	93.26 342	96.61 276	99.11 116	94.28 269	99.01 82	98.88 73	86.43 423	92.81 360	97.57 295	81.66 363	98.68 307	94.83 236	89.02 386	96.88 327

cl____		94.51 301	94.01 298	96.02 319	97.58 293	93.40 305	97.05 388	97.96 309	91.73 355	92.76 362	97.08 335	89.06 232	98.13 367	92.61 311	90.29 364	96.52 374

miper_lstm_enhance		94.33 313	94.07 292	95.11 357	97.75 277	90.97 358	97.22 374	98.03 304	91.67 357	92.76 362	96.97 352	90.03 201	97.78 397	92.51 319	89.64 372	96.56 366

v7n		94.19 324	93.43 337	96.47 294	95.90 396	94.38 265	99.26 28	98.34 235	91.99 347	92.76 362	97.13 328	88.31 253	98.52 321	89.48 381	87.70 398	96.52 374

MVS		94.67 288	93.54 332	98.08 156	96.88 347	96.56 143	98.19 272	98.50 193	78.05 446	92.69 365	98.02 247	91.07 180	99.63 153	90.09 366	98.36 197	98.04 280

DSMNet-mixed		92.52 369	92.58 357	92.33 414	94.15 429	82.65 442	98.30 257	94.26 442	89.08 410	92.65 366	95.73 408	85.01 322	95.76 438	86.24 409	97.76 218	98.59 254

EU-MVSNet		93.66 342	94.14 288	92.25 416	95.96 395	83.38 440	98.52 221	98.12 284	94.69 218	92.61 367	98.13 240	87.36 279	96.39 432	91.82 335	90.00 368	96.98 312

IterMVS-SCA-FT		94.11 332	93.87 310	94.85 369	97.98 261	90.56 373	97.18 379	98.11 287	93.75 267	92.58 368	97.48 301	83.97 347	97.41 411	92.48 321	91.30 350	96.58 362

pmmvs5		93.65 344	92.97 348	95.68 336	95.49 409	92.37 331	98.20 269	97.28 368	89.66 401	92.58 368	97.26 318	82.14 360	98.09 373	93.18 297	90.95 357	96.58 362

WR-MVS_H		95.05 263	94.46 268	96.81 256	96.86 348	95.82 191	99.24 31	99.24 20	93.87 261	92.53 370	96.84 365	90.37 194	98.24 361	93.24 294	87.93 396	96.38 387

ACMP	93.49 10	95.34 245	94.98 241	96.43 299	97.67 285	93.48 300	98.73 173	98.44 205	94.94 206	92.53 370	98.53 198	84.50 336	99.14 240	95.48 216	94.00 307	96.66 355
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test0.0.03 1		94.08 335	93.51 333	95.80 331	95.53 408	92.89 324	97.38 359	95.97 422	95.11 189	92.51 372	96.66 374	87.71 269	96.94 418	87.03 405	93.67 314	97.57 296

IB-MVS	91.98 17	93.27 352	91.97 367	97.19 225	97.47 304	93.41 303	97.09 387	95.99 421	93.32 296	92.47 373	95.73 408	78.06 396	99.53 176	94.59 251	82.98 428	98.62 249
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
IterMVS		94.09 334	93.85 312	94.80 373	97.99 255	90.35 378	97.18 379	98.12 284	93.68 278	92.46 374	97.34 312	84.05 345	97.41 411	92.51 319	91.33 349	96.62 358
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CP-MVSNet		94.94 274	94.30 277	96.83 254	96.72 358	95.56 199	99.11 61	98.95 57	93.89 259	92.42 375	97.90 260	87.19 280	98.12 368	94.32 260	88.21 393	96.82 336

PS-CasMVS		94.67 288	93.99 301	96.71 263	96.68 360	95.26 217	99.13 58	99.03 47	93.68 278	92.33 376	97.95 255	85.35 315	98.10 369	93.59 286	88.16 395	96.79 337

FMVSNet1		93.19 356	92.07 365	96.56 283	97.54 298	95.00 230	98.82 141	98.18 271	90.38 389	92.27 377	97.07 336	73.68 429	97.95 384	89.36 383	91.30 350	96.72 345

PEN-MVS		94.42 309	93.73 322	96.49 291	96.28 378	94.84 241	99.17 50	99.00 49	93.51 287	92.23 378	97.83 270	86.10 301	97.90 388	92.55 317	86.92 409	96.74 342

sc_t1		91.01 383	89.39 389	95.85 329	95.99 392	90.39 377	98.43 241	97.64 328	78.79 444	92.20 379	97.94 256	66.00 444	98.60 315	91.59 342	85.94 418	98.57 257

OurMVSNet-221017-0		94.21 322	94.00 299	94.85 369	95.60 404	89.22 400	98.89 115	97.43 356	95.29 175	92.18 380	98.52 201	82.86 357	98.59 316	93.46 289	91.76 344	96.74 342

MS-PatchMatch		93.84 341	93.63 327	94.46 387	96.18 382	89.45 396	97.76 333	98.27 251	92.23 341	92.13 381	97.49 300	79.50 384	98.69 304	89.75 374	99.38 128	95.25 414

ppachtmachnet_test		93.22 354	92.63 354	94.97 362	95.45 412	90.84 363	96.88 403	97.88 314	90.60 383	92.08 382	97.26 318	88.08 260	97.86 393	85.12 419	90.33 362	96.22 394

1314		96.25 194	95.73 199	97.79 180	97.13 332	95.55 201	98.19 272	98.59 166	93.47 290	92.03 383	97.82 271	91.33 165	99.49 184	94.62 248	98.44 186	98.32 271

baseline2		95.11 259	94.52 264	96.87 252	96.65 362	93.56 295	98.27 262	94.10 445	93.45 291	92.02 384	97.43 306	87.45 278	99.19 231	93.88 277	97.41 235	97.87 284

DTE-MVSNet		93.98 339	93.26 342	96.14 314	96.06 389	94.39 264	99.20 43	98.86 86	93.06 309	91.78 385	97.81 272	85.87 306	97.58 406	90.53 361	86.17 414	96.46 384

LF4IMVS		93.14 358	92.79 351	94.20 391	95.88 397	88.67 411	97.66 341	97.07 383	93.81 265	91.71 386	97.65 286	77.96 398	98.81 296	91.47 344	91.92 343	95.12 417

mvs5depth		91.23 379	90.17 383	94.41 389	92.09 442	89.79 385	95.26 434	96.50 413	90.73 381	91.69 387	97.06 340	76.12 417	98.62 311	88.02 399	84.11 424	94.82 424

our_test_3		93.65 344	93.30 340	94.69 375	95.45 412	89.68 391	96.91 397	97.65 326	91.97 348	91.66 388	96.88 361	89.67 210	97.93 387	88.02 399	91.49 348	96.48 382

testgi		93.06 360	92.45 361	94.88 367	96.43 373	89.90 383	98.75 163	97.54 342	95.60 155	91.63 389	97.91 259	74.46 426	97.02 416	86.10 410	93.67 314	97.72 290

tfpnnormal		93.66 342	92.70 353	96.55 287	96.94 342	95.94 176	98.97 91	99.19 32	91.04 377	91.38 390	97.34 312	84.94 323	98.61 312	85.45 416	89.02 386	95.11 418

LTVRE_ROB	92.95 15	94.60 291	93.90 307	96.68 267	97.41 313	94.42 262	98.52 221	98.59 166	91.69 356	91.21 391	98.35 216	84.87 324	99.04 259	91.06 353	93.44 322	96.60 360
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
OpenMVS	93.04 13	95.83 213	95.00 239	98.32 129	97.18 329	97.32 94	99.21 40	98.97 53	89.96 395	91.14 392	99.05 121	86.64 289	99.92 41	93.38 290	99.47 116	97.73 289

pm-mvs1		93.94 340	93.06 345	96.59 279	96.49 369	95.16 222	98.95 97	98.03 304	92.32 338	91.08 393	97.84 267	84.54 335	98.41 339	92.16 324	86.13 417	96.19 396

MVS-HIRNet		89.46 400	88.40 398	92.64 411	97.58 293	82.15 443	94.16 449	93.05 451	75.73 451	90.90 394	82.52 454	79.42 385	98.33 350	83.53 428	98.68 167	97.43 297

FMVSNet5		91.81 372	90.92 375	94.49 384	97.21 324	92.09 338	98.00 302	97.55 341	89.31 408	90.86 395	95.61 414	74.48 425	95.32 442	85.57 414	89.70 371	96.07 400

USDC		93.33 351	92.71 352	95.21 353	96.83 350	90.83 364	96.91 397	97.50 346	93.84 262	90.72 396	98.14 239	77.69 401	98.82 295	89.51 380	93.21 328	95.97 402

MVP-Stereo		94.28 319	93.92 304	95.35 350	94.95 420	92.60 330	97.97 305	97.65 326	91.61 358	90.68 397	97.09 333	86.32 298	98.42 332	89.70 376	99.34 132	95.02 422
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	92.99 14	94.30 315	93.77 318	95.88 328	97.81 274	92.04 341	98.71 178	98.37 228	93.99 254	90.60 398	98.47 204	80.86 374	99.05 256	92.75 310	92.40 337	96.55 368

CL-MVSNet_self_test		90.11 391	89.14 393	93.02 409	91.86 444	88.23 420	96.51 417	98.07 297	90.49 384	90.49 399	94.41 428	84.75 328	95.34 441	80.79 437	74.95 452	95.50 410

KD-MVS_self_test		90.38 388	89.38 391	93.40 403	92.85 439	88.94 407	97.95 306	97.94 310	90.35 390	90.25 400	93.96 433	79.82 381	95.94 437	84.62 425	76.69 450	95.33 412

ttmdpeth		92.61 366	91.96 369	94.55 381	94.10 430	90.60 372	98.52 221	97.29 366	92.67 323	90.18 401	97.92 258	79.75 383	97.79 395	91.09 350	86.15 416	95.26 413

Anonymous20231206		91.66 374	91.10 374	93.33 404	94.02 434	87.35 426	98.58 209	97.26 370	90.48 385	90.16 402	96.31 385	83.83 351	96.53 429	79.36 441	89.90 369	96.12 398

SixPastTwentyTwo		93.34 350	92.86 349	94.75 374	95.67 402	89.41 398	98.75 163	96.67 409	93.89 259	90.15 403	98.25 231	80.87 373	98.27 360	90.90 357	90.64 359	96.57 364

PVSNet_0	88.72 19	91.28 378	90.03 385	95.00 361	97.99 255	87.29 427	94.84 439	98.50 193	92.06 346	89.86 404	95.19 419	79.81 382	99.39 203	92.27 323	69.79 455	98.33 270

ACMH	92.88 16	94.55 296	93.95 303	96.34 306	97.63 289	93.26 311	98.81 149	98.49 198	93.43 292	89.74 405	98.53 198	81.91 361	99.08 253	93.69 281	93.30 326	96.70 349
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0320		90.26 390	88.73 397	94.86 368	96.12 386	90.62 370	98.17 278	97.63 329	77.46 447	89.68 406	96.04 398	69.19 436	97.79 395	88.98 388	85.29 420	96.16 397

pmmvs6		91.77 373	90.63 378	95.17 355	94.69 426	91.24 355	98.67 192	97.92 312	86.14 425	89.62 407	97.56 298	75.79 419	98.34 348	90.75 359	84.56 421	95.94 403

TinyColmap		92.31 370	91.53 371	94.65 378	96.92 343	89.75 386	96.92 395	96.68 408	90.45 387	89.62 407	97.85 266	76.06 418	98.81 296	86.74 406	92.51 336	95.41 411

Anonymous20240521		91.18 380	90.44 380	93.42 401	93.70 435	88.47 415	98.94 100	97.56 336	88.46 414	89.56 409	95.08 422	77.15 409	96.97 417	83.92 426	89.55 375	94.82 424

TransMVSNet (Re)		92.67 365	91.51 372	96.15 313	96.58 364	94.65 249	98.90 111	96.73 405	90.86 380	89.46 410	97.86 264	85.62 310	98.09 373	86.45 408	81.12 435	95.71 407

NR-MVSNet		94.98 269	94.16 286	97.44 211	96.53 366	97.22 109	98.74 167	98.95 57	94.96 202	89.25 411	97.69 281	89.32 223	98.18 363	94.59 251	87.40 402	96.92 318

LCM-MVSNet-Re		95.22 252	95.32 224	94.91 364	98.18 230	87.85 424	98.75 163	95.66 427	95.11 189	88.96 412	96.85 364	90.26 199	97.65 401	95.65 210	98.44 186	99.22 164

KD-MVS_2432*1600		89.61 397	87.96 405	94.54 382	94.06 432	91.59 349	95.59 431	97.63 329	89.87 397	88.95 413	94.38 430	78.28 393	96.82 420	84.83 421	68.05 456	95.21 415

miper_refine_blended		89.61 397	87.96 405	94.54 382	94.06 432	91.59 349	95.59 431	97.63 329	89.87 397	88.95 413	94.38 430	78.28 393	96.82 420	84.83 421	68.05 456	95.21 415

test_fmvs3		87.17 407	87.06 410	87.50 425	91.21 446	75.66 450	99.05 70	96.61 412	92.79 320	88.85 415	92.78 442	43.72 457	93.49 448	93.95 274	84.56 421	93.34 442

TDRefinement		91.06 382	89.68 387	95.21 353	85.35 460	91.49 351	98.51 227	97.07 383	91.47 360	88.83 416	97.84 267	77.31 405	99.09 252	92.79 309	77.98 447	95.04 421

tt0320-xc		89.79 394	88.11 401	94.84 371	96.19 381	90.61 371	98.16 279	97.22 372	77.35 448	88.75 417	96.70 373	65.94 445	97.63 403	89.31 384	83.39 426	96.28 392

N_pmnet		87.12 409	87.77 407	85.17 429	95.46 411	61.92 465	97.37 361	70.66 470	85.83 428	88.73 418	96.04 398	85.33 317	97.76 398	80.02 438	90.48 360	95.84 404

test_0402		91.32 376	90.27 382	94.48 385	96.60 363	91.12 356	98.50 228	97.22 372	86.10 426	88.30 419	96.98 351	77.65 403	97.99 382	78.13 445	92.94 330	94.34 428

test20.03		90.89 385	90.38 381	92.43 412	93.48 436	88.14 421	98.33 249	97.56 336	93.40 293	87.96 420	96.71 372	80.69 376	94.13 447	79.15 442	86.17 414	95.01 423

MIMVSNet1		89.67 396	88.28 400	93.82 396	92.81 440	91.08 357	98.01 300	97.45 354	87.95 416	87.90 421	95.87 404	67.63 441	94.56 446	78.73 444	88.18 394	95.83 405

mvsany_test3		88.80 402	88.04 402	91.09 420	89.78 450	81.57 445	97.83 328	95.49 429	93.81 265	87.53 422	93.95 434	56.14 453	97.43 410	94.68 244	83.13 427	94.26 429

Patchmatch-RL test		91.49 375	90.85 376	93.41 402	91.37 445	84.40 434	92.81 450	95.93 425	91.87 351	87.25 423	94.87 423	88.99 234	96.53 429	92.54 318	82.00 430	99.30 145

pmmvs3		86.67 410	84.86 415	92.11 417	88.16 454	87.19 428	96.63 413	94.75 437	79.88 443	87.22 424	92.75 444	66.56 443	95.20 443	81.24 436	76.56 451	93.96 437

dongtai		82.47 414	81.88 417	84.22 431	95.19 417	76.03 448	94.59 445	74.14 469	82.63 438	87.19 425	96.09 395	64.10 447	87.85 459	58.91 457	84.11 424	88.78 451

test_vis1_rt		91.29 377	90.65 377	93.19 408	97.45 308	86.25 431	98.57 216	90.90 458	93.30 298	86.94 426	93.59 436	62.07 450	99.11 247	97.48 129	95.58 290	94.22 431

K. test v3		92.55 367	91.91 370	94.48 385	95.64 403	89.24 399	99.07 67	94.88 435	94.04 247	86.78 427	97.59 293	77.64 404	97.64 402	92.08 326	89.43 379	96.57 364

lessismore_v0				94.45 388	94.93 421	88.44 416		91.03 457		86.77 428	97.64 289	76.23 416	98.42 332	90.31 364	85.64 419	96.51 377

APD_test1		88.22 404	88.01 403	88.86 423	95.98 393	74.66 455	97.21 375	96.44 415	83.96 436	86.66 429	97.90 260	60.95 451	97.84 394	82.73 429	90.23 365	94.09 434

ambc				89.49 422	86.66 457	75.78 449	92.66 451	96.72 406		86.55 430	92.50 445	46.01 455	97.90 388	90.32 363	82.09 429	94.80 426

PM-MVS		87.77 405	86.55 411	91.40 419	91.03 448	83.36 441	96.92 395	95.18 433	91.28 371	86.48 431	93.42 437	53.27 454	96.74 422	89.43 382	81.97 431	94.11 433

OpenMVS_ROB	86.42 20	89.00 401	87.43 409	93.69 398	93.08 438	89.42 397	97.91 313	96.89 399	78.58 445	85.86 432	94.69 424	69.48 435	98.29 358	77.13 446	93.29 327	93.36 441

UnsupCasMVSNet_eth		90.99 384	89.92 386	94.19 392	94.08 431	89.83 384	97.13 386	98.67 145	93.69 276	85.83 433	96.19 392	75.15 421	96.74 422	89.14 386	79.41 442	96.00 401

new_pmnet		90.06 392	89.00 395	93.22 407	94.18 428	88.32 418	96.42 419	96.89 399	86.19 424	85.67 434	93.62 435	77.18 408	97.10 415	81.61 434	89.29 381	94.23 430

dmvs_testset		87.64 406	88.93 396	83.79 432	95.25 415	63.36 464	97.20 376	91.17 456	93.07 308	85.64 435	95.98 403	85.30 319	91.52 454	69.42 453	87.33 403	96.49 380

test_f		86.07 411	85.39 412	88.10 424	89.28 452	75.57 451	97.73 336	96.33 417	89.41 407	85.35 436	91.56 448	43.31 459	95.53 439	91.32 346	84.23 423	93.21 443

EG-PatchMatch MVS		91.13 381	90.12 384	94.17 393	94.73 425	89.00 404	98.13 284	97.81 317	89.22 409	85.32 437	96.46 382	67.71 440	98.42 332	87.89 402	93.82 312	95.08 419

pmmvs-eth3d		90.36 389	89.05 394	94.32 390	91.10 447	92.12 336	97.63 346	96.95 394	88.86 412	84.91 438	93.13 441	78.32 392	96.74 422	88.70 391	81.81 432	94.09 434

DeepMVS_CX				86.78 426	97.09 335	72.30 456		95.17 434	75.92 450	84.34 439	95.19 419	70.58 433	95.35 440	79.98 440	89.04 385	92.68 444

new-patchmatchnet		88.50 403	87.45 408	91.67 418	90.31 449	85.89 432	97.16 384	97.33 362	89.47 404	83.63 440	92.77 443	76.38 414	95.06 444	82.70 430	77.29 448	94.06 436

UnsupCasMVSNet_bld		87.17 407	85.12 414	93.31 405	91.94 443	88.77 408	94.92 438	98.30 248	84.30 435	82.30 441	90.04 449	63.96 448	97.25 413	85.85 413	74.47 454	93.93 438

WB-MVS		84.86 412	85.33 413	83.46 433	89.48 451	69.56 459	98.19 272	96.42 416	89.55 403	81.79 442	94.67 425	84.80 326	90.12 455	52.44 459	80.64 439	90.69 446

CMPMVS	66.06 21	89.70 395	89.67 388	89.78 421	93.19 437	76.56 447	97.00 391	98.35 232	80.97 442	81.57 443	97.75 275	74.75 423	98.61 312	89.85 372	93.63 316	94.17 432
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
SSC-MVS		84.27 413	84.71 416	82.96 437	89.19 453	68.83 460	98.08 292	96.30 418	89.04 411	81.37 444	94.47 426	84.60 333	89.89 456	49.80 461	79.52 441	90.15 447

MVStest1		89.53 399	87.99 404	94.14 395	94.39 427	90.42 375	98.25 264	96.84 404	82.81 437	81.18 445	97.33 314	77.09 410	96.94 418	85.27 418	78.79 443	95.06 420

test_method		79.03 416	78.17 418	81.63 438	86.06 459	54.40 470	82.75 458	96.89 399	39.54 462	80.98 446	95.57 415	58.37 452	94.73 445	84.74 424	78.61 444	95.75 406

kuosan		78.45 420	77.69 421	80.72 439	92.73 441	75.32 452	94.63 444	74.51 468	75.96 449	80.87 447	93.19 440	63.23 449	79.99 463	42.56 463	81.56 434	86.85 455

ET-MVSNet_ETH3D		94.13 329	92.98 347	97.58 204	98.22 219	96.20 160	97.31 368	95.37 430	94.53 228	79.56 448	97.63 291	86.51 290	97.53 408	96.91 152	90.74 358	99.02 203

LCM-MVSNet		78.70 419	76.24 425	86.08 427	77.26 466	71.99 457	94.34 447	96.72 406	61.62 457	76.53 449	89.33 450	33.91 465	92.78 452	81.85 433	74.60 453	93.46 440

PMMVS2		77.95 422	75.44 426	85.46 428	82.54 461	74.95 453	94.23 448	93.08 450	72.80 452	74.68 450	87.38 451	36.36 462	91.56 453	73.95 449	63.94 458	89.87 448

testf1		79.02 417	77.70 419	82.99 435	88.10 455	66.90 461	94.67 441	93.11 448	71.08 453	74.02 451	93.41 438	34.15 463	93.25 449	72.25 451	78.50 445	88.82 449

APD_test2		79.02 417	77.70 419	82.99 435	88.10 455	66.90 461	94.67 441	93.11 448	71.08 453	74.02 451	93.41 438	34.15 463	93.25 449	72.25 451	78.50 445	88.82 449

Gipuma		78.40 421	76.75 424	83.38 434	95.54 406	80.43 446	79.42 459	97.40 358	64.67 456	73.46 453	80.82 457	45.65 456	93.14 451	66.32 455	87.43 401	76.56 459
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		90.70 387	89.39 389	94.62 380	94.79 424	90.65 368	97.20 376	97.46 350	87.54 418	72.54 454	95.74 406	86.51 290	96.66 426	86.00 411	86.76 412	96.54 369

MDA-MVSNet_test_wron		90.71 386	89.38 391	94.68 376	94.83 422	90.78 365	97.19 378	97.46 350	87.60 417	72.41 455	95.72 410	86.51 290	96.71 425	85.92 412	86.80 411	96.56 366

MDA-MVSNet-bldmvs		89.97 393	88.35 399	94.83 372	95.21 416	91.34 352	97.64 343	97.51 345	88.36 415	71.17 456	96.13 394	79.22 386	96.63 427	83.65 427	86.27 413	96.52 374

FPMVS		77.62 423	77.14 423	79.05 441	79.25 464	60.97 466	95.79 426	95.94 424	65.96 455	67.93 457	94.40 429	37.73 461	88.88 458	68.83 454	88.46 391	87.29 452

test_vis3_rt		79.22 415	77.40 422	84.67 430	86.44 458	74.85 454	97.66 341	81.43 465	84.98 432	67.12 458	81.91 456	28.09 467	97.60 404	88.96 389	80.04 440	81.55 456

tmp_tt		68.90 426	66.97 428	74.68 443	50.78 470	59.95 467	87.13 455	83.47 464	38.80 463	62.21 459	96.23 389	64.70 446	76.91 465	88.91 390	30.49 463	87.19 453

E-PMN		64.94 428	64.25 430	67.02 445	82.28 462	59.36 468	91.83 453	85.63 462	52.69 459	60.22 460	77.28 459	41.06 460	80.12 462	46.15 462	41.14 460	61.57 461

EMVS		64.07 429	63.26 432	66.53 446	81.73 463	58.81 469	91.85 452	84.75 463	51.93 461	59.09 461	75.13 460	43.32 458	79.09 464	42.03 464	39.47 461	61.69 460

MVE	62.14 22	63.28 430	59.38 433	74.99 442	74.33 467	65.47 463	85.55 456	80.50 466	52.02 460	51.10 462	75.00 461	10.91 471	80.50 461	51.60 460	53.40 459	78.99 457
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		69.08 425	65.37 429	80.22 440	65.99 468	71.96 458	90.91 454	90.09 459	82.62 439	49.93 463	78.39 458	29.36 466	81.75 460	62.49 456	38.52 462	86.95 454

PMVS	61.03 23	65.95 427	63.57 431	73.09 444	57.90 469	51.22 471	85.05 457	93.93 446	54.45 458	44.32 464	83.57 453	13.22 468	89.15 457	58.68 458	81.00 436	78.91 458
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		21.48 433	24.95 436	11.09 449	14.89 471	6.47 474	96.56 415	9.87 472	7.55 465	17.93 465	39.02 463	9.43 472	5.90 468	16.56 467	12.72 465	20.91 463

test123		20.95 434	23.72 437	12.64 448	13.54 472	8.19 473	96.55 416	6.13 473	7.48 466	16.74 466	37.98 464	12.97 469	6.05 467	16.69 466	5.43 466	23.68 462

wuyk23d		30.17 431	30.18 435	30.16 447	78.61 465	43.29 472	66.79 460	14.21 471	17.31 464	14.82 467	11.93 467	11.55 470	41.43 466	37.08 465	19.30 464	5.76 464

EGC-MVSNET		75.22 424	69.54 427	92.28 415	94.81 423	89.58 393	97.64 343	96.50 413	1.82 467	5.57 468	95.74 406	68.21 437	96.26 433	73.80 450	91.71 345	90.99 445

mmdepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

monomultidepth		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

test_blank		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet_test		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

DCPMVS		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

cdsmvs_eth3d_5k		23.98 432	31.98 434	0.00 450	0.00 473	0.00 475	0.00 461	98.59 166	0.00 468	0.00 469	98.61 188	90.60 191	0.00 469	0.00 468	0.00 467	0.00 465

pcd_1.5k_mvsjas		7.88 436	10.50 439	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	94.51 88	0.00 469	0.00 468	0.00 467	0.00 465

sosnet-low-res		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

sosnet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uncertanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

Regformer		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

ab-mvs-re		8.20 435	10.94 438	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	98.43 206	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

uanet		0.00 437	0.00 440	0.00 450	0.00 473	0.00 475	0.00 461	0.00 474	0.00 468	0.00 469	0.00 468	0.00 473	0.00 469	0.00 468	0.00 467	0.00 465

WAC-MVS						90.94 359								88.66 392

MSC_two_6792asdad				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

No_MVS				99.62 6	99.17 105	99.08 11		98.63 156					99.94 13	98.53 53	99.80 24	99.86 10

eth-test2					0.00 473

eth-test					0.00 473

OPU-MVS				99.37 23	99.24 97	99.05 14	99.02 80				99.16 95	97.81 3	99.37 204	97.24 140	99.73 57	99.70 62

save fliter					99.46 54	98.38 36	98.21 267	98.71 131	97.95 26

test_0728_SECOND				99.71 1	99.72 14	99.35 1	98.97 91	98.88 73					99.94 13	98.47 61	99.81 15	99.84 15

GSMVS																99.20 167

sam_mvs1												89.45 218				99.20 167

sam_mvs												88.99 234

MTGPA								98.74 123

test_post1							96.68 412				30.43 466	87.85 268	98.69 304	92.59 314

test_post											31.83 465	88.83 241	98.91 280

patchmatchnet-post											95.10 421	89.42 219	98.89 284

MTMP							98.89 115	94.14 444

gm-plane-assit					95.88 397	87.47 425			89.74 400		96.94 357		99.19 231	93.32 293

test9_res														96.39 182	99.57 94	99.69 65

agg_prior2														95.87 198	99.57 94	99.68 70

test_prior4						98.01 66	97.86 323

test_prior				99.19 46	99.31 73	98.22 53		98.84 90					99.70 136			99.65 78

新几何2							97.64 343

旧先验1					99.29 82	97.48 85		98.70 135			99.09 114	95.56 52			99.47 116	99.61 85

无先验							97.58 348	98.72 128	91.38 363				99.87 73	93.36 292		99.60 87

原ACMM2							97.67 340

testdata2													99.89 62	91.65 341

segment_acmp												96.85 14

testdata1							97.32 367		96.34 121

plane_prior7					97.42 310	94.63 251

plane_prior6					97.35 317	94.61 254						87.09 281

plane_prior5								98.56 176					99.03 260	96.07 188	94.27 296	96.92 318

plane_prior4											98.28 225

plane_prior2							98.80 150		97.28 65

plane_prior1					97.37 316

plane_prior						94.60 256	98.44 239		96.74 99						94.22 298

n2								0.00 474

nn								0.00 474

door-mid								94.37 440

test11								98.66 148

door								94.64 438

HQP5-MVS						94.25 272

BP-MVS														95.30 221

HQP3-MVS								98.46 201							94.18 300

HQP2-MVS												86.75 287

NP-MVS					97.28 319	94.51 259					97.73 276

ACMMP++_ref															92.97 329

ACMMP++															93.61 317

Test By Simon												94.64 85

High-resolution multi-view benchmark