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_3		97.64 8	97.60 10	97.79 30	98.14 104	93.94 52	97.93 77	98.65 19	96.70 4	99.38 1	99.07 9	89.92 87	99.81 30	99.16 10	99.43 48	99.61 24

fmvsm_s_conf0.5_n_2		96.62 63	96.82 48	96.02 141	97.98 117	90.43 184	97.50 143	98.59 22	96.59 6	99.31 2	99.08 6	84.47 173	99.75 50	99.37 3	98.45 124	97.88 205

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 57	98.21 97	92.75 87	97.83 91	98.73 10	95.04 40	99.30 3	98.84 32	93.34 22	99.78 42	99.32 4	99.13 89	99.50 46

test_fmvsm_n_1920		97.55 13	97.89 3	96.53 97	98.41 78	91.73 124	98.01 61	99.02 1	96.37 9	99.30 3	98.92 19	92.39 41	99.79 39	99.16 10	99.46 41	98.08 192

fmvsm_s_conf0.5_n_3		97.15 29	97.36 21	96.52 99	97.98 117	91.19 153	97.84 88	98.65 19	97.08 3	99.25 5	99.10 4	87.88 119	99.79 39	99.32 4	99.18 82	98.59 144

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 64	98.25 91	92.59 95	97.81 96	98.68 14	94.93 43	99.24 6	98.87 27	93.52 20	99.79 39	99.32 4	99.21 76	99.40 60

fmvsm_s_conf0.5_n_6		97.08 32	97.17 23	96.81 82	97.28 161	91.73 124	97.75 102	98.50 25	94.86 47	99.22 7	98.78 36	89.75 90	99.76 46	99.10 13	99.29 67	98.94 108

fmvsm_s_conf0.5_n_8		97.32 23	97.48 18	96.85 81	98.28 87	91.07 161	97.76 100	98.62 21	97.53 2	99.20 8	99.12 3	88.24 111	99.81 30	99.41 2	99.17 83	99.67 13

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 48	95.13 35	99.19 9	98.89 24	95.54 5	99.85 18	97.52 38	99.66 10	99.56 34

test_241102_ONE					99.42 7	95.30 17		98.27 48	95.09 38	99.19 9	98.81 33	95.54 5	99.65 71

fmvsm_s_conf0.1_n_2		96.33 76	96.44 72	96.00 145	97.30 159	90.37 187	97.53 140	97.92 119	96.52 7	99.14 11	99.08 6	83.21 195	99.74 51	99.22 7	98.06 141	97.88 205

fmvsm_s_conf0.5_n_4		96.75 55	97.07 27	95.79 155	97.76 133	89.57 210	97.66 119	98.66 17	95.36 25	99.03 12	98.90 21	88.39 108	99.73 53	99.17 9	98.66 112	98.08 192

SD-MVS		97.41 19	97.53 13	97.06 77	98.57 73	94.46 34	97.92 78	98.14 76	94.82 52	99.01 13	98.55 45	94.18 14	97.41 359	96.94 51	99.64 14	99.32 68
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
test0726					99.45 3	95.36 13	98.31 28	98.29 43	94.92 45	98.99 14	98.92 19	95.08 8

IU-MVS					99.42 7	95.39 11		97.94 116	90.40 228	98.94 15				97.41 45	99.66 10	99.74 8

fmvsm_s_conf0.1_n_a		96.40 72	96.47 66	96.16 133	95.48 280	90.69 175	97.91 79	98.33 38	94.07 84	98.93 16	99.14 1	87.44 133	99.61 82	98.63 22	98.32 129	98.18 178

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 62	95.39 11	99.29 1	98.28 45	94.78 56	98.93 16	98.87 27	96.04 2	99.86 9	97.45 42	99.58 23	99.59 26

test_241102_TWO								98.27 48	95.13 35	98.93 16	98.89 24	94.99 11	99.85 18	97.52 38	99.65 13	99.74 8

test_fmvsmconf_n		97.49 17	97.56 11	97.29 60	97.44 156	92.37 102	97.91 79	98.88 4	95.83 14	98.92 19	99.05 11	91.45 58	99.80 35	99.12 12	99.46 41	99.69 12

fmvsm_s_conf0.5_n_a		96.75 55	96.93 39	96.20 131	97.64 142	90.72 174	98.00 62	98.73 10	94.55 68	98.91 20	99.08 6	88.22 112	99.63 80	98.91 17	98.37 127	98.25 173

fmvsm_s_conf0.5_n_5		97.00 38	96.97 36	97.09 74	97.58 152	92.56 96	97.68 115	98.47 29	94.02 86	98.90 21	98.89 24	88.94 98	99.78 42	99.18 8	99.03 98	98.93 112

PC_three_1452									90.77 207	98.89 22	98.28 78	96.24 1	98.35 250	95.76 97	99.58 23	99.59 26

SMA-MVS		97.35 21	97.03 33	98.30 8	99.06 39	95.42 10	97.94 75	98.18 69	90.57 222	98.85 23	98.94 18	93.33 23	99.83 26	96.72 59	99.68 4	99.63 20
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
fmvsm_s_conf0.1_n		96.58 66	96.77 53	96.01 144	96.67 207	90.25 189	97.91 79	98.38 32	94.48 72	98.84 24	99.14 1	88.06 114	99.62 81	98.82 19	98.60 116	98.15 182

fmvsm_s_conf0.5_n		96.85 47	97.13 24	96.04 139	98.07 111	90.28 188	97.97 71	98.76 9	94.93 43	98.84 24	99.06 10	88.80 101	99.65 71	99.06 14	98.63 114	98.18 178

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 129	94.92 45	98.73 26	98.87 27	95.08 8	99.84 23	97.52 38	99.67 6	99.48 50
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									94.78 56	98.73 26	98.87 27	95.87 4	99.84 23	97.45 42	99.72 2	99.77 2

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 33	95.78 7	97.21 183	98.35 36	95.16 33	98.71 28	98.80 34	95.05 10	99.89 3	96.70 61	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
lecture		97.58 12	97.63 9	97.43 54	99.37 16	92.93 82	98.86 7	98.85 5	95.27 29	98.65 29	98.90 21	91.97 49	99.80 35	97.63 34	99.21 76	99.57 30

TSAR-MVS + MP.		97.42 18	97.33 22	97.69 42	99.25 28	94.24 41	98.07 56	97.85 129	93.72 96	98.57 30	98.35 64	93.69 18	99.40 124	97.06 49	99.46 41	99.44 55
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MSP-MVS		97.59 11	97.54 12	97.73 38	99.40 11	93.77 57	98.53 15	98.29 43	95.55 22	98.56 31	97.81 116	93.90 15	99.65 71	96.62 62	99.21 76	99.77 2
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
FOURS1					99.55 1	93.34 67	99.29 1	98.35 36	94.98 41	98.49 32

test_one_0601					99.32 23	95.20 20		98.25 54	95.13 35	98.48 33	98.87 27	95.16 7

fmvsm_s_conf0.5_n_7		96.45 70	96.80 50	95.37 182	97.29 160	88.38 253	97.23 180	98.47 29	95.14 34	98.43 34	99.09 5	87.58 126	99.72 57	98.80 21	99.21 76	98.02 196

test_fmvsmconf0.1_n		97.09 31	97.06 28	97.19 69	95.67 272	92.21 109	97.95 74	98.27 48	95.78 18	98.40 35	99.00 13	89.99 85	99.78 42	99.06 14	99.41 54	99.59 26

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 34	94.82 28	98.81 8	98.30 41	94.76 59	98.30 36	98.90 21	93.77 17	99.68 67	97.93 25	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SF-MVS		97.39 20	97.13 24	98.17 15	99.02 43	95.28 19	98.23 40	98.27 48	92.37 152	98.27 37	98.65 41	93.33 23	99.72 57	96.49 67	99.52 30	99.51 43

balanced_conf03		96.84 49	96.89 41	96.68 86	97.63 144	92.22 108	98.17 49	97.82 135	94.44 74	98.23 38	97.36 150	90.97 72	99.22 142	97.74 28	99.66 10	98.61 141

SteuartSystems-ACMMP		97.62 10	97.53 13	97.87 24	98.39 81	94.25 40	98.43 23	98.27 48	95.34 27	98.11 39	98.56 43	94.53 12	99.71 59	96.57 65	99.62 17	99.65 18
Skip Steuart: Steuart Systems R&D Blog.
test_vis1_n_1920		94.17 141	94.58 121	92.91 307	97.42 157	82.02 376	97.83 91	97.85 129	94.68 62	98.10 40	98.49 50	70.15 367	99.32 132	97.91 26	98.82 105	97.40 234

test_part2					99.28 26	95.74 8				98.10 40

APD-MVS		96.95 40	96.60 59	98.01 20	99.03 42	94.93 27	97.72 109	98.10 84	91.50 178	98.01 42	98.32 72	92.33 42	99.58 90	94.85 123	99.51 33	99.53 42
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
reproduce_model		97.51 16	97.51 15	97.50 50	98.99 47	93.01 78	97.79 98	98.21 60	95.73 19	97.99 43	99.03 12	92.63 36	99.82 28	97.80 27	99.42 51	99.67 13

patch_mono-2		96.83 50	97.44 19	95.01 198	99.05 40	85.39 329	96.98 202	98.77 8	94.70 61	97.99 43	98.66 39	93.61 19	99.91 1	97.67 33	99.50 35	99.72 11

DeepPCF-MVS	93.97 1	96.61 64	97.09 26	95.15 190	98.09 107	86.63 302	96.00 285	98.15 74	95.43 23	97.95 45	98.56 43	93.40 21	99.36 128	96.77 56	99.48 39	99.45 53

ACMMP_NAP		97.20 26	96.86 42	98.23 11	99.09 35	95.16 22	97.60 129	98.19 67	92.82 142	97.93 46	98.74 38	91.60 56	99.86 9	96.26 71	99.52 30	99.67 13

reproduce-ours		97.53 14	97.51 15	97.60 47	98.97 48	93.31 69	97.71 111	98.20 62	95.80 16	97.88 47	98.98 15	92.91 27	99.81 30	97.68 29	99.43 48	99.67 13

our_new_method		97.53 14	97.51 15	97.60 47	98.97 48	93.31 69	97.71 111	98.20 62	95.80 16	97.88 47	98.98 15	92.91 27	99.81 30	97.68 29	99.43 48	99.67 13

9.14			96.75 54		98.93 51		97.73 106	98.23 59	91.28 189	97.88 47	98.44 56	93.00 26	99.65 71	95.76 97	99.47 40

CNVR-MVS		97.68 6	97.44 19	98.37 7	98.90 54	95.86 6	97.27 174	98.08 86	95.81 15	97.87 50	98.31 73	94.26 13	99.68 67	97.02 50	99.49 38	99.57 30

test_vis1_n		92.37 216	92.26 201	92.72 315	94.75 330	82.64 366	98.02 60	96.80 258	91.18 193	97.77 51	97.93 101	58.02 419	98.29 255	97.63 34	98.21 134	97.23 243

test_cas_vis1_n_1920		94.48 135	94.55 125	94.28 242	96.78 200	86.45 307	97.63 126	97.64 156	93.32 116	97.68 52	98.36 63	73.75 343	99.08 168	96.73 58	99.05 95	97.31 239

test_fmvsmconf0.01_n		96.15 80	95.85 84	97.03 78	92.66 394	91.83 123	97.97 71	97.84 133	95.57 21	97.53 53	99.00 13	84.20 179	99.76 46	98.82 19	99.08 93	99.48 50

MM		97.29 25	96.98 35	98.23 11	98.01 114	95.03 26	98.07 56	95.76 311	97.78 1	97.52 54	98.80 34	88.09 113	99.86 9	99.44 1	99.37 62	99.80 1

VNet		95.89 90	95.45 93	97.21 67	98.07 111	92.94 81	97.50 143	98.15 74	93.87 92	97.52 54	97.61 135	85.29 162	99.53 104	95.81 96	95.27 214	99.16 79

SR-MVS		97.01 37	96.86 42	97.47 52	99.09 35	93.27 71	97.98 65	98.07 91	93.75 95	97.45 56	98.48 53	91.43 60	99.59 87	96.22 74	99.27 69	99.54 39

APD-MVS_3200maxsize		96.81 51	96.71 56	97.12 72	99.01 46	92.31 105	97.98 65	98.06 94	93.11 127	97.44 57	98.55 45	90.93 73	99.55 100	96.06 84	99.25 73	99.51 43

TSAR-MVS + GP.		96.69 60	96.49 64	97.27 63	98.31 85	93.39 63	96.79 219	96.72 261	94.17 82	97.44 57	97.66 128	92.76 31	99.33 130	96.86 55	97.76 153	99.08 90

SR-MVS-dyc-post		96.88 44	96.80 50	97.11 73	99.02 43	92.34 103	97.98 65	98.03 103	93.52 108	97.43 59	98.51 48	91.40 61	99.56 98	96.05 85	99.26 71	99.43 57

RE-MVS-def			96.72 55		99.02 43	92.34 103	97.98 65	98.03 103	93.52 108	97.43 59	98.51 48	90.71 77		96.05 85	99.26 71	99.43 57

dcpmvs_2		96.37 74	97.05 31	94.31 240	98.96 50	84.11 350	97.56 134	97.51 175	93.92 90	97.43 59	98.52 47	92.75 32	99.32 132	97.32 47	99.50 35	99.51 43

MVSMamba_PlusPlus		96.51 67	96.48 65	96.59 94	98.07 111	91.97 119	98.14 50	97.79 137	90.43 226	97.34 62	97.52 142	91.29 64	99.19 145	98.12 24	99.64 14	98.60 142

旧先验2							95.94 288		81.66 398	97.34 62			98.82 200	92.26 176

MSLP-MVS++		96.94 41	97.06 28	96.59 94	98.72 59	91.86 122	97.67 116	98.49 26	94.66 64	97.24 64	98.41 59	92.31 44	98.94 186	96.61 63	99.46 41	98.96 104

HFP-MVS		97.14 30	96.92 40	97.83 26	99.42 7	94.12 46	98.52 16	98.32 39	93.21 118	97.18 65	98.29 76	92.08 46	99.83 26	95.63 104	99.59 19	99.54 39

MVS_0304		96.74 57	96.31 74	98.02 19	96.87 189	94.65 30	97.58 130	94.39 377	96.47 8	97.16 66	98.39 60	87.53 129	99.87 7	98.97 16	99.41 54	99.55 37

ACMMPR		97.07 34	96.84 44	97.79 30	99.44 6	93.88 53	98.52 16	98.31 40	93.21 118	97.15 67	98.33 70	91.35 62	99.86 9	95.63 104	99.59 19	99.62 21

region2R		97.07 34	96.84 44	97.77 34	99.46 2	93.79 55	98.52 16	98.24 56	93.19 121	97.14 68	98.34 67	91.59 57	99.87 7	95.46 110	99.59 19	99.64 19

PGM-MVS		96.81 51	96.53 62	97.65 43	99.35 21	93.53 61	97.65 120	98.98 2	92.22 155	97.14 68	98.44 56	91.17 68	99.85 18	94.35 139	99.46 41	99.57 30

PHI-MVS		96.77 53	96.46 69	97.71 41	98.40 79	94.07 48	98.21 43	98.45 31	89.86 239	97.11 70	98.01 96	92.52 39	99.69 65	96.03 88	99.53 29	99.36 66

NCCC		97.30 24	97.03 33	98.11 17	98.77 57	95.06 25	97.34 167	98.04 101	95.96 11	97.09 71	97.88 107	93.18 25	99.71 59	95.84 95	99.17 83	99.56 34

CS-MVS		96.86 45	97.06 28	96.26 126	98.16 103	91.16 158	99.09 3	97.87 124	95.30 28	97.06 72	98.03 93	91.72 51	98.71 217	97.10 48	99.17 83	98.90 117

ZD-MVS					99.05 40	94.59 32		98.08 86	89.22 260	97.03 73	98.10 86	92.52 39	99.65 71	94.58 136	99.31 66

testdata				95.46 180	98.18 102	88.90 239		97.66 152	82.73 390	97.03 73	98.07 89	90.06 83	98.85 196	89.67 234	98.98 100	98.64 140

SPE-MVS-test		96.89 43	97.04 32	96.45 110	98.29 86	91.66 131	99.03 4	97.85 129	95.84 13	96.90 75	97.97 99	91.24 65	98.75 210	96.92 52	99.33 64	98.94 108

mvsany_test1		93.93 157	93.98 138	93.78 270	94.94 320	86.80 295	94.62 344	92.55 409	88.77 281	96.85 76	98.49 50	88.98 96	98.08 277	95.03 118	95.62 208	96.46 265

GDP-MVS		95.62 97	95.13 105	97.09 74	96.79 199	93.26 72	97.89 82	97.83 134	93.58 100	96.80 77	97.82 115	83.06 202	99.16 152	94.40 138	97.95 147	98.87 123

test_fmvs1		93.21 180	93.53 150	92.25 330	96.55 219	81.20 383	97.40 161	96.96 240	90.68 212	96.80 77	98.04 92	69.25 375	98.40 242	97.58 37	98.50 119	97.16 245

test_fmvs1_n		92.73 206	92.88 174	92.29 327	96.08 256	81.05 384	97.98 65	97.08 226	90.72 210	96.79 79	98.18 83	63.07 409	98.45 239	97.62 36	98.42 126	97.36 235

HPM-MVS_fast		96.51 67	96.27 76	97.22 66	99.32 23	92.74 88	98.74 10	98.06 94	90.57 222	96.77 80	98.35 64	90.21 82	99.53 104	94.80 128	99.63 16	99.38 64

h-mvs33		94.15 143	93.52 152	96.04 139	97.81 130	90.22 190	97.62 128	97.58 166	95.19 31	96.74 81	97.45 143	83.67 187	99.61 82	95.85 93	79.73 398	98.29 172

hse-mvs2		93.45 173	92.99 169	94.81 211	97.02 180	88.59 245	96.69 231	96.47 279	95.19 31	96.74 81	96.16 221	83.67 187	98.48 238	95.85 93	79.13 402	97.35 237

GST-MVS		96.85 47	96.52 63	97.82 27	99.36 19	94.14 45	98.29 30	98.13 77	92.72 145	96.70 83	98.06 90	91.35 62	99.86 9	94.83 125	99.28 68	99.47 52

xiu_mvs_v1_base_debu		95.01 115	94.76 113	95.75 158	96.58 213	91.71 127	96.25 269	97.35 206	92.99 130	96.70 83	96.63 196	82.67 213	99.44 120	96.22 74	97.46 157	96.11 277

xiu_mvs_v1_base		95.01 115	94.76 113	95.75 158	96.58 213	91.71 127	96.25 269	97.35 206	92.99 130	96.70 83	96.63 196	82.67 213	99.44 120	96.22 74	97.46 157	96.11 277

xiu_mvs_v1_base_debi		95.01 115	94.76 113	95.75 158	96.58 213	91.71 127	96.25 269	97.35 206	92.99 130	96.70 83	96.63 196	82.67 213	99.44 120	96.22 74	97.46 157	96.11 277

CDPH-MVS		95.97 86	95.38 98	97.77 34	98.93 51	94.44 35	96.35 261	97.88 122	86.98 330	96.65 87	97.89 105	91.99 48	99.47 116	92.26 176	99.46 41	99.39 62

EC-MVSNet		96.42 71	96.47 66	96.26 126	97.01 181	91.52 137	98.89 5	97.75 141	94.42 75	96.64 88	97.68 125	89.32 92	98.60 227	97.45 42	99.11 92	98.67 139

UA-Net		95.95 87	95.53 89	97.20 68	97.67 138	92.98 80	97.65 120	98.13 77	94.81 54	96.61 89	98.35 64	88.87 99	99.51 109	90.36 220	97.35 164	99.11 87

HPM-MVS++		97.34 22	96.97 36	98.47 5	99.08 37	96.16 4	97.55 139	97.97 113	95.59 20	96.61 89	97.89 105	92.57 38	99.84 23	95.95 90	99.51 33	99.40 60

XVS		97.18 27	96.96 38	97.81 28	99.38 14	94.03 50	98.59 13	98.20 62	94.85 48	96.59 91	98.29 76	91.70 53	99.80 35	95.66 99	99.40 56	99.62 21

X-MVStestdata		91.71 242	89.67 307	97.81 28	99.38 14	94.03 50	98.59 13	98.20 62	94.85 48	96.59 91	32.69 445	91.70 53	99.80 35	95.66 99	99.40 56	99.62 21

DeepC-MVS_fast	93.89 2	96.93 42	96.64 58	97.78 32	98.64 68	94.30 37	97.41 157	98.04 101	94.81 54	96.59 91	98.37 62	91.24 65	99.64 79	95.16 115	99.52 30	99.42 59
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SymmetryMVS		95.94 88	95.54 88	97.15 70	97.85 127	92.90 83	97.99 63	96.91 248	95.92 12	96.57 94	97.93 101	85.34 161	99.50 112	94.99 120	96.39 192	99.05 93

PS-MVSNAJ		95.37 103	95.33 100	95.49 176	97.35 158	90.66 177	95.31 323	97.48 179	93.85 93	96.51 95	95.70 248	88.65 104	99.65 71	94.80 128	98.27 132	96.17 271

EI-MVSNet-Vis-set		96.51 67	96.47 66	96.63 91	98.24 92	91.20 152	96.89 209	97.73 144	94.74 60	96.49 96	98.49 50	90.88 75	99.58 90	96.44 68	98.32 129	99.13 83

ETV-MVS		96.02 83	95.89 83	96.40 113	97.16 167	92.44 100	97.47 152	97.77 140	94.55 68	96.48 97	94.51 305	91.23 67	98.92 189	95.65 102	98.19 135	97.82 213

alignmvs		95.87 92	95.23 102	97.78 32	97.56 154	95.19 21	97.86 84	97.17 218	94.39 78	96.47 98	96.40 209	85.89 154	99.20 144	96.21 78	95.11 219	98.95 107

KinetiMVS		95.26 107	94.75 116	96.79 83	96.99 183	92.05 115	97.82 93	97.78 138	94.77 58	96.46 99	97.70 123	80.62 253	99.34 129	92.37 175	98.28 131	98.97 102

xiu_mvs_v2_base		95.32 105	95.29 101	95.40 181	97.22 163	90.50 180	95.44 316	97.44 193	93.70 98	96.46 99	96.18 218	88.59 107	99.53 104	94.79 130	97.81 150	96.17 271

CP-MVS		97.02 36	96.81 49	97.64 45	99.33 22	93.54 60	98.80 9	98.28 45	92.99 130	96.45 101	98.30 75	91.90 50	99.85 18	95.61 106	99.68 4	99.54 39

HPM-MVS		96.69 60	96.45 70	97.40 55	99.36 19	93.11 76	98.87 6	98.06 94	91.17 194	96.40 102	97.99 97	90.99 71	99.58 90	95.61 106	99.61 18	99.49 48
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
ZNCC-MVS		96.96 39	96.67 57	97.85 25	99.37 16	94.12 46	98.49 20	98.18 69	92.64 148	96.39 103	98.18 83	91.61 55	99.88 4	95.59 109	99.55 26	99.57 30

BP-MVS1		95.89 90	95.49 90	97.08 76	96.67 207	93.20 73	98.08 54	96.32 285	94.56 67	96.32 104	97.84 113	84.07 182	99.15 154	96.75 57	98.78 107	98.90 117

diffmvs		95.25 108	95.13 105	95.63 166	96.43 233	89.34 223	95.99 286	97.35 206	92.83 141	96.31 105	97.37 149	86.44 146	98.67 220	96.26 71	97.19 172	98.87 123
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LFMVS		93.60 167	92.63 186	96.52 99	98.13 106	91.27 147	97.94 75	93.39 398	90.57 222	96.29 106	98.31 73	69.00 377	99.16 152	94.18 141	95.87 200	99.12 86

sasdasda		96.02 83	95.45 93	97.75 36	97.59 148	95.15 23	98.28 31	97.60 162	94.52 70	96.27 107	96.12 223	87.65 123	99.18 148	96.20 79	94.82 223	98.91 114

canonicalmvs		96.02 83	95.45 93	97.75 36	97.59 148	95.15 23	98.28 31	97.60 162	94.52 70	96.27 107	96.12 223	87.65 123	99.18 148	96.20 79	94.82 223	98.91 114

MVSFormer		95.37 103	95.16 104	95.99 146	96.34 239	91.21 150	98.22 41	97.57 167	91.42 182	96.22 109	97.32 151	86.20 151	97.92 309	94.07 142	99.05 95	98.85 125

lupinMVS		94.99 119	94.56 122	96.29 124	96.34 239	91.21 150	95.83 294	96.27 289	88.93 272	96.22 109	96.88 178	86.20 151	98.85 196	95.27 112	99.05 95	98.82 129

MGCFI-Net		95.94 88	95.40 97	97.56 49	97.59 148	94.62 31	98.21 43	97.57 167	94.41 76	96.17 111	96.16 221	87.54 128	99.17 150	96.19 81	94.73 228	98.91 114

EI-MVSNet-UG-set		96.34 75	96.30 75	96.47 107	98.20 98	90.93 166	96.86 212	97.72 146	94.67 63	96.16 112	98.46 54	90.43 80	99.58 90	96.23 73	97.96 146	98.90 117

MTAPA		97.08 32	96.78 52	97.97 23	99.37 16	94.42 36	97.24 176	98.08 86	95.07 39	96.11 113	98.59 42	90.88 75	99.90 2	96.18 83	99.50 35	99.58 29

test_fmvsmvis_n_1920		96.70 58	96.84 44	96.31 120	96.62 209	91.73 124	97.98 65	98.30 41	96.19 10	96.10 114	98.95 17	89.42 91	99.76 46	98.90 18	99.08 93	97.43 232

MCST-MVS		97.18 27	96.84 44	98.20 14	99.30 25	95.35 15	97.12 190	98.07 91	93.54 105	96.08 115	97.69 124	93.86 16	99.71 59	96.50 66	99.39 58	99.55 37

TEST9					98.70 60	94.19 42	96.41 253	98.02 106	88.17 297	96.03 116	97.56 139	92.74 33	99.59 87

train_agg		96.30 77	95.83 85	97.72 39	98.70 60	94.19 42	96.41 253	98.02 106	88.58 284	96.03 116	97.56 139	92.73 34	99.59 87	95.04 117	99.37 62	99.39 62

test_prior2							96.35 261		92.80 143	96.03 116	97.59 136	92.01 47		95.01 119	99.38 59

jason		94.84 125	94.39 131	96.18 132	95.52 278	90.93 166	96.09 280	96.52 276	89.28 258	96.01 119	97.32 151	84.70 169	98.77 208	95.15 116	98.91 104	98.85 125
jason: jason.
test_8					98.67 62	94.06 49	96.37 260	98.01 109	88.58 284	95.98 120	97.55 141	92.73 34	99.58 90

mPP-MVS		96.86 45	96.60 59	97.64 45	99.40 11	93.44 62	98.50 19	98.09 85	93.27 117	95.95 121	98.33 70	91.04 70	99.88 4	95.20 113	99.57 25	99.60 25

LuminaMVS		94.89 122	94.35 132	96.53 97	95.48 280	92.80 86	96.88 211	96.18 296	92.85 140	95.92 122	96.87 180	81.44 239	98.83 199	96.43 69	97.10 175	97.94 201

DELS-MVS		96.61 64	96.38 73	97.30 59	97.79 131	93.19 74	95.96 287	98.18 69	95.23 30	95.87 123	97.65 129	91.45 58	99.70 64	95.87 91	99.44 47	99.00 100
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
VDD-MVS		93.82 161	93.08 167	96.02 141	97.88 126	89.96 199	97.72 109	95.85 307	92.43 150	95.86 124	98.44 56	68.42 384	99.39 125	96.31 70	94.85 221	98.71 136

MVS_111021_HR		96.68 62	96.58 61	96.99 79	98.46 74	92.31 105	96.20 274	98.90 3	94.30 81	95.86 124	97.74 121	92.33 42	99.38 127	96.04 87	99.42 51	99.28 71

MVS_111021_LR		96.24 79	96.19 78	96.39 115	98.23 96	91.35 145	96.24 272	98.79 7	93.99 88	95.80 126	97.65 129	89.92 87	99.24 140	95.87 91	99.20 80	98.58 145

VDDNet		93.05 189	92.07 204	96.02 141	96.84 192	90.39 186	98.08 54	95.85 307	86.22 345	95.79 127	98.46 54	67.59 387	99.19 145	94.92 122	94.85 221	98.47 157

新几何1				97.32 58	98.60 69	93.59 59		97.75 141	81.58 399	95.75 128	97.85 111	90.04 84	99.67 69	86.50 302	99.13 89	98.69 137

guyue		95.17 113	94.96 109	95.82 153	96.97 185	89.65 205	97.56 134	95.58 323	94.82 52	95.72 129	97.42 147	82.90 207	98.84 198	96.71 60	96.93 177	98.96 104

test_yl		94.78 128	94.23 134	96.43 111	97.74 134	91.22 148	96.85 213	97.10 223	91.23 191	95.71 130	96.93 173	84.30 176	99.31 134	93.10 163	95.12 217	98.75 131

DCV-MVSNet		94.78 128	94.23 134	96.43 111	97.74 134	91.22 148	96.85 213	97.10 223	91.23 191	95.71 130	96.93 173	84.30 176	99.31 134	93.10 163	95.12 217	98.75 131

AstraMVS		94.82 127	94.64 118	95.34 184	96.36 238	88.09 265	97.58 130	94.56 370	94.98 41	95.70 132	97.92 103	81.93 232	98.93 187	96.87 54	95.88 199	98.99 101

agg_prior					98.67 62	93.79 55		98.00 110		95.68 133			99.57 97

MG-MVS		95.61 98	95.38 98	96.31 120	98.42 77	90.53 179	96.04 282	97.48 179	93.47 110	95.67 134	98.10 86	89.17 94	99.25 139	91.27 203	98.77 108	99.13 83

baseline		95.58 99	95.42 96	96.08 135	96.78 200	90.41 185	97.16 187	97.45 189	93.69 99	95.65 135	97.85 111	87.29 136	98.68 219	95.66 99	97.25 170	99.13 83

MVS_Test		94.89 122	94.62 119	95.68 164	96.83 194	89.55 212	96.70 229	97.17 218	91.17 194	95.60 136	96.11 227	87.87 120	98.76 209	93.01 170	97.17 173	98.72 134

DPM-MVS		95.69 94	94.92 110	98.01 20	98.08 110	95.71 9	95.27 326	97.62 161	90.43 226	95.55 137	97.07 168	91.72 51	99.50 112	89.62 236	98.94 102	98.82 129

MP-MVS-pluss		96.70 58	96.27 76	97.98 22	99.23 31	94.71 29	96.96 204	98.06 94	90.67 213	95.55 137	98.78 36	91.07 69	99.86 9	96.58 64	99.55 26	99.38 64
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MP-MVS		96.77 53	96.45 70	97.72 39	99.39 13	93.80 54	98.41 24	98.06 94	93.37 113	95.54 139	98.34 67	90.59 79	99.88 4	94.83 125	99.54 28	99.49 48
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test12				97.65 43	98.46 74	94.26 39		97.66 152		95.52 140		90.89 74	99.46 117		99.25 73	99.22 76

casdiffmvs		95.64 96	95.49 90	96.08 135	96.76 205	90.45 182	97.29 173	97.44 193	94.00 87	95.46 141	97.98 98	87.52 131	98.73 213	95.64 103	97.33 165	99.08 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test222					98.24 92	92.21 109	95.33 321	97.60 162	79.22 412	95.25 142	97.84 113	88.80 101			99.15 87	98.72 134

test2506		91.60 248	90.78 256	94.04 252	97.66 140	83.81 353	98.27 33	75.53 446	93.43 111	95.23 143	98.21 80	67.21 390	99.07 172	93.01 170	98.49 120	99.25 74

原ACMM1				96.38 116	98.59 70	91.09 160		97.89 120	87.41 322	95.22 144	97.68 125	90.25 81	99.54 102	87.95 270	99.12 91	98.49 154

CPTT-MVS		95.57 100	95.19 103	96.70 85	99.27 27	91.48 139	98.33 27	98.11 82	87.79 311	95.17 145	98.03 93	87.09 139	99.61 82	93.51 154	99.42 51	99.02 94

casdiffmvs_mvg		95.81 93	95.57 87	96.51 103	96.87 189	91.49 138	97.50 143	97.56 171	93.99 88	95.13 146	97.92 103	87.89 118	98.78 205	95.97 89	97.33 165	99.26 73
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DP-MVS Recon		95.68 95	95.12 107	97.37 56	99.19 32	94.19 42	97.03 194	98.08 86	88.35 293	95.09 147	97.65 129	89.97 86	99.48 115	92.08 185	98.59 117	98.44 162

RRT-MVS		94.51 133	94.35 132	94.98 201	96.40 234	86.55 305	97.56 134	97.41 198	93.19 121	94.93 148	97.04 170	79.12 281	99.30 136	96.19 81	97.32 167	99.09 89

Vis-MVSNet		95.23 109	94.81 112	96.51 103	97.18 166	91.58 135	98.26 35	98.12 79	94.38 79	94.90 149	98.15 85	82.28 223	98.92 189	91.45 200	98.58 118	99.01 97
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CANet		96.39 73	96.02 80	97.50 50	97.62 145	93.38 64	97.02 196	97.96 114	95.42 24	94.86 150	97.81 116	87.38 135	99.82 28	96.88 53	99.20 80	99.29 69

Elysia		94.00 153	93.12 165	96.64 87	96.08 256	92.72 90	97.50 143	97.63 158	91.15 196	94.82 151	97.12 164	74.98 330	99.06 174	90.78 211	98.02 142	98.12 185

StellarMVS		94.00 153	93.12 165	96.64 87	96.08 256	92.72 90	97.50 143	97.63 158	91.15 196	94.82 151	97.12 164	74.98 330	99.06 174	90.78 211	98.02 142	98.12 185

API-MVS		94.84 125	94.49 127	95.90 148	97.90 125	92.00 118	97.80 97	97.48 179	89.19 261	94.81 153	96.71 185	88.84 100	99.17 150	88.91 256	98.76 109	96.53 260

mvsmamba		94.57 132	94.14 136	95.87 149	97.03 179	89.93 200	97.84 88	95.85 307	91.34 185	94.79 154	96.80 181	80.67 251	98.81 202	94.85 123	98.12 139	98.85 125

OMC-MVS		95.09 114	94.70 117	96.25 129	98.46 74	91.28 146	96.43 251	97.57 167	92.04 164	94.77 155	97.96 100	87.01 140	99.09 165	91.31 202	96.77 181	98.36 169

ECVR-MVS		93.19 182	92.73 182	94.57 226	97.66 140	85.41 327	98.21 43	88.23 430	93.43 111	94.70 156	98.21 80	72.57 347	99.07 172	93.05 167	98.49 120	99.25 74

WTY-MVS		94.71 130	94.02 137	96.79 83	97.71 136	92.05 115	96.59 244	97.35 206	90.61 219	94.64 157	96.93 173	86.41 147	99.39 125	91.20 205	94.71 229	98.94 108

test1111		93.19 182	92.82 176	94.30 241	97.58 152	84.56 344	98.21 43	89.02 428	93.53 106	94.58 158	98.21 80	72.69 346	99.05 177	93.06 166	98.48 122	99.28 71

ACMMP		96.27 78	95.93 81	97.28 62	99.24 29	92.62 93	98.25 36	98.81 6	92.99 130	94.56 159	98.39 60	88.96 97	99.85 18	94.57 137	97.63 154	99.36 66
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
mamv4		94.66 131	96.10 79	90.37 376	98.01 114	73.41 425	96.82 217	97.78 138	89.95 237	94.52 160	97.43 146	92.91 27	99.09 165	98.28 23	99.16 86	98.60 142

Effi-MVS+		94.93 120	94.45 129	96.36 118	96.61 210	91.47 140	96.41 253	97.41 198	91.02 202	94.50 161	95.92 232	87.53 129	98.78 205	93.89 148	96.81 180	98.84 128

sss		94.51 133	93.80 141	96.64 87	97.07 172	91.97 119	96.32 264	98.06 94	88.94 271	94.50 161	96.78 182	84.60 170	99.27 138	91.90 186	96.02 195	98.68 138

mmtdpeth		89.70 326	88.96 324	91.90 339	95.84 267	84.42 345	97.46 154	95.53 328	90.27 229	94.46 163	90.50 402	69.74 373	98.95 184	97.39 46	69.48 427	92.34 404

PVSNet_BlendedMVS		94.06 149	93.92 139	94.47 229	98.27 88	89.46 218	96.73 225	98.36 33	90.17 231	94.36 164	95.24 271	88.02 115	99.58 90	93.44 156	90.72 297	94.36 370

PVSNet_Blended		94.87 124	94.56 122	95.81 154	98.27 88	89.46 218	95.47 315	98.36 33	88.84 275	94.36 164	96.09 228	88.02 115	99.58 90	93.44 156	98.18 136	98.40 165

PMMVS		92.86 200	92.34 198	94.42 233	94.92 321	86.73 298	94.53 348	96.38 283	84.78 368	94.27 166	95.12 276	83.13 199	98.40 242	91.47 199	96.49 189	98.12 185

EPP-MVSNet		95.22 110	95.04 108	95.76 156	97.49 155	89.56 211	98.67 11	97.00 238	90.69 211	94.24 167	97.62 134	89.79 89	98.81 202	93.39 159	96.49 189	98.92 113

FA-MVS(test-final)		93.52 171	92.92 172	95.31 185	96.77 202	88.54 248	94.82 340	96.21 294	89.61 247	94.20 168	95.25 270	83.24 194	99.14 157	90.01 224	96.16 194	98.25 173

PVSNet_Blended_VisFu		95.27 106	94.91 111	96.38 116	98.20 98	90.86 168	97.27 174	98.25 54	90.21 230	94.18 169	97.27 155	87.48 132	99.73 53	93.53 153	97.77 152	98.55 146

FE-MVS		92.05 232	91.05 244	95.08 194	96.83 194	87.93 268	93.91 375	95.70 314	86.30 342	94.15 170	94.97 279	76.59 314	99.21 143	84.10 337	96.86 178	98.09 191

thisisatest0530		93.03 190	92.21 202	95.49 176	97.07 172	89.11 235	97.49 151	92.19 411	90.16 232	94.09 171	96.41 208	76.43 318	99.05 177	90.38 219	95.68 206	98.31 171

XVG-OURS-SEG-HR		93.86 160	93.55 148	94.81 211	97.06 175	88.53 249	95.28 324	97.45 189	91.68 174	94.08 172	97.68 125	82.41 221	98.90 192	93.84 150	92.47 266	96.98 248

XVG-OURS		93.72 165	93.35 160	94.80 214	97.07 172	88.61 244	94.79 341	97.46 184	91.97 167	93.99 173	97.86 110	81.74 235	98.88 193	92.64 174	92.67 265	96.92 252

IS-MVSNet		94.90 121	94.52 126	96.05 138	97.67 138	90.56 178	98.44 22	96.22 292	93.21 118	93.99 173	97.74 121	85.55 159	98.45 239	89.98 225	97.86 148	99.14 82

CSCG		96.05 82	95.91 82	96.46 109	99.24 29	90.47 181	98.30 29	98.57 24	89.01 267	93.97 175	97.57 137	92.62 37	99.76 46	94.66 131	99.27 69	99.15 81

EIA-MVS		95.53 101	95.47 92	95.71 163	97.06 175	89.63 206	97.82 93	97.87 124	93.57 101	93.92 176	95.04 277	90.61 78	98.95 184	94.62 133	98.68 111	98.54 147

tttt0517		92.96 193	92.33 199	94.87 208	97.11 170	87.16 289	97.97 71	92.09 412	90.63 217	93.88 177	97.01 172	76.50 315	99.06 174	90.29 222	95.45 211	98.38 167

HyFIR lowres test		93.66 166	92.92 172	95.87 149	98.24 92	89.88 201	94.58 346	98.49 26	85.06 363	93.78 178	95.78 243	82.86 208	98.67 220	91.77 191	95.71 205	99.07 92

CHOSEN 1792x2688		94.15 143	93.51 153	96.06 137	98.27 88	89.38 221	95.18 332	98.48 28	85.60 353	93.76 179	97.11 166	83.15 198	99.61 82	91.33 201	98.72 110	99.19 77

Anonymous202405211		92.07 231	90.83 255	95.76 156	98.19 100	88.75 241	97.58 130	95.00 350	86.00 348	93.64 180	97.45 143	66.24 399	99.53 104	90.68 216	92.71 263	99.01 97

CDS-MVSNet		94.14 146	93.54 149	95.93 147	96.18 246	91.46 141	96.33 263	97.04 233	88.97 270	93.56 181	96.51 203	87.55 127	97.89 313	89.80 230	95.95 197	98.44 162
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MDTV_nov1_ep13_2view						70.35 429	93.10 396		83.88 378	93.55 182		82.47 220		86.25 305		98.38 167

Anonymous20240529		91.98 234	90.73 261	95.73 161	98.14 104	89.40 220	97.99 63	97.72 146	79.63 410	93.54 183	97.41 148	69.94 369	99.56 98	91.04 208	91.11 290	98.22 175

CANet_DTU		94.37 136	93.65 145	96.55 96	96.46 231	92.13 113	96.21 273	96.67 268	94.38 79	93.53 184	97.03 171	79.34 277	99.71 59	90.76 213	98.45 124	97.82 213

tpmrst		91.44 260	91.32 232	91.79 345	95.15 309	79.20 409	93.42 389	95.37 332	88.55 287	93.49 185	93.67 352	82.49 219	98.27 256	90.41 218	89.34 311	97.90 203

TAMVS		94.01 152	93.46 155	95.64 165	96.16 248	90.45 182	96.71 228	96.89 251	89.27 259	93.46 186	96.92 176	87.29 136	97.94 306	88.70 261	95.74 203	98.53 148

thisisatest0515		92.29 221	91.30 234	95.25 187	96.60 211	88.90 239	94.36 357	92.32 410	87.92 304	93.43 187	94.57 301	77.28 310	99.00 181	89.42 241	95.86 201	97.86 209

DeepC-MVS	93.07 3	96.06 81	95.66 86	97.29 60	97.96 119	93.17 75	97.30 172	98.06 94	93.92 90	93.38 188	98.66 39	86.83 141	99.73 53	95.60 108	99.22 75	98.96 104
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thres600view7		92.49 211	91.60 222	95.18 189	97.91 124	89.47 216	97.65 120	94.66 366	92.18 161	93.33 189	94.91 283	78.06 303	99.10 162	81.61 360	94.06 246	96.98 248

thres100view900		92.43 212	91.58 223	94.98 201	97.92 123	89.37 222	97.71 111	94.66 366	92.20 157	93.31 190	94.90 284	78.06 303	99.08 168	81.40 364	94.08 242	96.48 263

thres200		92.23 225	91.39 229	94.75 218	97.61 146	89.03 236	96.60 243	95.09 347	92.08 163	93.28 191	94.00 338	78.39 297	99.04 180	81.26 370	94.18 238	96.19 270

tfpn200view9		92.38 215	91.52 226	94.95 205	97.85 127	89.29 226	97.41 157	94.88 358	92.19 159	93.27 192	94.46 310	78.17 299	99.08 168	81.40 364	94.08 242	96.48 263

thres400		92.42 213	91.52 226	95.12 193	97.85 127	89.29 226	97.41 157	94.88 358	92.19 159	93.27 192	94.46 310	78.17 299	99.08 168	81.40 364	94.08 242	96.98 248

testing3-2		92.10 230	92.05 205	92.27 328	97.71 136	79.56 403	97.42 156	94.41 376	93.53 106	93.22 194	95.49 259	69.16 376	99.11 160	93.25 160	94.22 236	98.13 183

ab-mvs		93.57 169	92.55 190	96.64 87	97.28 161	91.96 121	95.40 317	97.45 189	89.81 243	93.22 194	96.28 214	79.62 274	99.46 117	90.74 214	93.11 257	98.50 152

Vis-MVSNet (Re-imp)		94.15 143	93.88 140	94.95 205	97.61 146	87.92 269	98.10 52	95.80 310	92.22 155	93.02 196	97.45 143	84.53 172	97.91 312	88.24 265	97.97 145	99.02 94

114514_t		93.95 155	93.06 168	96.63 91	99.07 38	91.61 132	97.46 154	97.96 114	77.99 416	93.00 197	97.57 137	86.14 153	99.33 130	89.22 248	99.15 87	98.94 108

UGNet		94.04 151	93.28 162	96.31 120	96.85 191	91.19 153	97.88 83	97.68 151	94.40 77	93.00 197	96.18 218	73.39 345	99.61 82	91.72 192	98.46 123	98.13 183
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
HY-MVS	89.66 9	93.87 159	92.95 171	96.63 91	97.10 171	92.49 99	95.64 307	96.64 269	89.05 266	93.00 197	95.79 242	85.77 157	99.45 119	89.16 252	94.35 231	97.96 199

PVSNet	86.66 18	92.24 224	91.74 219	93.73 271	97.77 132	83.69 357	92.88 399	96.72 261	87.91 305	93.00 197	94.86 286	78.51 294	99.05 177	86.53 300	97.45 161	98.47 157

MAR-MVS		94.22 139	93.46 155	96.51 103	98.00 116	92.19 112	97.67 116	97.47 182	88.13 301	93.00 197	95.84 236	84.86 168	99.51 109	87.99 269	98.17 137	97.83 212
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		95.01 115	94.59 120	96.26 126	98.89 55	90.68 176	97.24 176	97.73 144	91.80 169	92.93 202	96.62 199	89.13 95	99.14 157	89.21 249	97.78 151	98.97 102

MDTV_nov1_ep13			90.76 257		95.22 303	80.33 393	93.03 397	95.28 337	88.14 300	92.84 203	93.83 342	81.34 240	98.08 277	82.86 349	94.34 232

CostFormer		91.18 278	90.70 263	92.62 319	94.84 326	81.76 378	94.09 368	94.43 374	84.15 374	92.72 204	93.77 346	79.43 276	98.20 261	90.70 215	92.18 272	97.90 203

EPNet		95.20 111	94.56 122	97.14 71	92.80 391	92.68 92	97.85 87	94.87 361	96.64 5	92.46 205	97.80 118	86.23 148	99.65 71	93.72 152	98.62 115	99.10 88
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CR-MVSNet		90.82 291	89.77 303	93.95 259	94.45 343	87.19 287	90.23 420	95.68 318	86.89 332	92.40 206	92.36 383	80.91 247	97.05 371	81.09 371	93.95 247	97.60 225

RPMNet		88.98 332	87.05 346	94.77 216	94.45 343	87.19 287	90.23 420	98.03 103	77.87 418	92.40 206	87.55 425	80.17 263	99.51 109	68.84 425	93.95 247	97.60 225

EPMVS		90.70 296	89.81 301	93.37 290	94.73 332	84.21 348	93.67 383	88.02 431	89.50 251	92.38 208	93.49 358	77.82 307	97.78 324	86.03 312	92.68 264	98.11 190

baseline1		92.82 203	91.90 212	95.55 172	97.20 165	90.77 172	97.19 184	94.58 369	92.20 157	92.36 209	96.34 212	84.16 180	98.21 260	89.20 250	83.90 378	97.68 219

PatchT		88.87 336	87.42 340	93.22 296	94.08 354	85.10 335	89.51 425	94.64 368	81.92 395	92.36 209	88.15 421	80.05 265	97.01 374	72.43 416	93.65 252	97.54 228

UWE-MVS		89.91 317	89.48 313	91.21 358	95.88 261	78.23 414	94.91 339	90.26 424	89.11 263	92.35 211	94.52 304	68.76 379	97.96 300	83.95 341	95.59 209	97.42 233

ETVMVS		90.52 302	89.14 322	94.67 220	96.81 198	87.85 273	95.91 290	93.97 389	89.71 245	92.34 212	92.48 378	65.41 404	97.96 300	81.37 367	94.27 235	98.21 176

PAPR		94.18 140	93.42 159	96.48 106	97.64 142	91.42 143	95.55 310	97.71 150	88.99 268	92.34 212	95.82 238	89.19 93	99.11 160	86.14 308	97.38 162	98.90 117

SCA		91.84 239	91.18 241	93.83 266	95.59 274	84.95 340	94.72 342	95.58 323	90.82 205	92.25 214	93.69 349	75.80 322	98.10 272	86.20 306	95.98 196	98.45 159

CVMVSNet		91.23 273	91.75 217	89.67 384	95.77 268	74.69 420	96.44 249	94.88 358	85.81 350	92.18 215	97.64 132	79.07 282	95.58 403	88.06 268	95.86 201	98.74 133

AUN-MVS		91.76 241	90.75 259	94.81 211	97.00 182	88.57 246	96.65 235	96.49 278	89.63 246	92.15 216	96.12 223	78.66 292	98.50 235	90.83 209	79.18 401	97.36 235

AdaColmap		94.34 137	93.68 144	96.31 120	98.59 70	91.68 130	96.59 244	97.81 136	89.87 238	92.15 216	97.06 169	83.62 189	99.54 102	89.34 243	98.07 140	97.70 218

GeoE		93.89 158	93.28 162	95.72 162	96.96 186	89.75 204	98.24 39	96.92 247	89.47 252	92.12 218	97.21 159	84.42 174	98.39 247	87.71 276	96.50 188	99.01 97

PatchmatchNet		91.91 236	91.35 230	93.59 280	95.38 287	84.11 350	93.15 394	95.39 330	89.54 249	92.10 219	93.68 351	82.82 210	98.13 267	84.81 328	95.32 213	98.52 149
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
VPA-MVSNet		93.24 179	92.48 195	95.51 174	95.70 270	92.39 101	97.86 84	98.66 17	92.30 153	92.09 220	95.37 263	80.49 256	98.40 242	93.95 145	85.86 345	95.75 294

tpm		90.25 309	89.74 306	91.76 348	93.92 357	79.73 402	93.98 369	93.54 396	88.28 294	91.99 221	93.25 366	77.51 309	97.44 356	87.30 290	87.94 324	98.12 185

myMVS_eth3d28		91.52 256	90.97 247	93.17 298	96.91 187	83.24 361	95.61 308	94.96 354	92.24 154	91.98 222	93.28 365	69.31 374	98.40 242	88.71 260	95.68 206	97.88 205

UBG		91.55 253	90.76 257	93.94 261	96.52 224	85.06 336	95.22 329	94.54 371	90.47 225	91.98 222	92.71 372	72.02 350	98.74 212	88.10 267	95.26 215	98.01 197

CNLPA		94.28 138	93.53 150	96.52 99	98.38 82	92.55 97	96.59 244	96.88 252	90.13 234	91.91 224	97.24 157	85.21 163	99.09 165	87.64 282	97.83 149	97.92 202

testing91		91.90 237	91.02 245	94.53 228	96.54 220	86.55 305	95.86 292	95.64 320	91.77 171	91.89 225	93.47 360	69.94 369	98.86 194	90.23 223	93.86 249	98.18 178

BH-RMVSNet		92.72 207	91.97 210	94.97 203	97.16 167	87.99 267	96.15 278	95.60 321	90.62 218	91.87 226	97.15 163	78.41 296	98.57 231	83.16 346	97.60 155	98.36 169

PatchMatch-RL		92.90 197	92.02 208	95.56 170	98.19 100	90.80 170	95.27 326	97.18 216	87.96 303	91.86 227	95.68 249	80.44 257	98.99 182	84.01 339	97.54 156	96.89 253

SDMVSNet		94.17 141	93.61 146	95.86 151	98.09 107	91.37 144	97.35 166	98.20 62	93.18 123	91.79 228	97.28 153	79.13 280	98.93 187	94.61 134	92.84 260	97.28 240

sd_testset		93.10 186	92.45 196	95.05 195	98.09 107	89.21 230	96.89 209	97.64 156	93.18 123	91.79 228	97.28 153	75.35 327	98.65 222	88.99 254	92.84 260	97.28 240

testing99		91.62 247	90.72 262	94.32 238	96.48 228	86.11 317	95.81 295	94.76 363	91.55 176	91.75 230	93.44 361	68.55 382	98.82 200	90.43 217	93.69 250	98.04 195

testing222		90.31 306	88.96 324	94.35 235	96.54 220	87.29 281	95.50 313	93.84 393	90.97 203	91.75 230	92.96 369	62.18 414	98.00 291	82.86 349	94.08 242	97.76 215

OPM-MVS		93.28 178	92.76 178	94.82 209	94.63 336	90.77 172	96.65 235	97.18 216	93.72 96	91.68 232	97.26 156	79.33 278	98.63 224	92.13 182	92.28 268	95.07 333
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
tpm2		89.96 316	89.21 319	92.23 331	94.91 323	81.25 381	93.78 378	94.42 375	80.62 406	91.56 233	93.44 361	76.44 317	97.94 306	85.60 318	92.08 276	97.49 229

TAPA-MVS	90.10 7	92.30 220	91.22 239	95.56 170	98.33 84	89.60 208	96.79 219	97.65 154	81.83 396	91.52 234	97.23 158	87.94 117	98.91 191	71.31 420	98.37 127	98.17 181
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvs2		89.77 324	89.93 296	89.31 390	93.68 366	76.37 417	97.64 124	95.90 304	89.84 242	91.49 235	96.26 216	58.77 417	97.10 369	94.65 132	91.13 289	94.46 366

TR-MVS		91.48 259	90.59 267	94.16 246	96.40 234	87.33 280	95.67 302	95.34 336	87.68 316	91.46 236	95.52 258	76.77 313	98.35 250	82.85 351	93.61 254	96.79 256

RPSCF		90.75 293	90.86 251	90.42 375	96.84 192	76.29 418	95.61 308	96.34 284	83.89 377	91.38 237	97.87 108	76.45 316	98.78 205	87.16 294	92.23 269	96.20 269

PLC	91.00 6	94.11 147	93.43 157	96.13 134	98.58 72	91.15 159	96.69 231	97.39 200	87.29 325	91.37 238	96.71 185	88.39 108	99.52 108	87.33 289	97.13 174	97.73 216
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
CHOSEN 280x420		93.12 185	92.72 183	94.34 237	96.71 206	87.27 283	90.29 419	97.72 146	86.61 337	91.34 239	95.29 265	84.29 178	98.41 241	93.25 160	98.94 102	97.35 237

HQP_MVS		93.78 163	93.43 157	94.82 209	96.21 243	89.99 195	97.74 104	97.51 175	94.85 48	91.34 239	96.64 192	81.32 241	98.60 227	93.02 168	92.23 269	95.86 282

plane_prior3						90.00 193			94.46 73	91.34 239

Fast-Effi-MVS+		93.46 172	92.75 180	95.59 169	96.77 202	90.03 192	96.81 218	97.13 220	88.19 296	91.30 242	94.27 323	86.21 150	98.63 224	87.66 281	96.46 191	98.12 185

EI-MVSNet		93.03 190	92.88 174	93.48 286	95.77 268	86.98 292	96.44 249	97.12 221	90.66 215	91.30 242	97.64 132	86.56 143	98.05 284	89.91 227	90.55 299	95.41 309

MVSTER		93.20 181	92.81 177	94.37 234	96.56 217	89.59 209	97.06 193	97.12 221	91.24 190	91.30 242	95.96 230	82.02 228	98.05 284	93.48 155	90.55 299	95.47 304

ADS-MVSNet2		89.45 328	88.59 330	92.03 335	95.86 262	82.26 374	90.93 415	94.32 382	83.23 387	91.28 245	91.81 393	79.01 287	95.99 392	79.52 380	91.39 285	97.84 210

ADS-MVSNet		89.89 319	88.68 329	93.53 284	95.86 262	84.89 341	90.93 415	95.07 348	83.23 387	91.28 245	91.81 393	79.01 287	97.85 315	79.52 380	91.39 285	97.84 210

testing11		91.68 245	90.75 259	94.47 229	96.53 222	86.56 304	95.76 299	94.51 373	91.10 200	91.24 247	93.59 355	68.59 381	98.86 194	91.10 206	94.29 234	98.00 198

nrg030		94.05 150	93.31 161	96.27 125	95.22 303	94.59 32	98.34 26	97.46 184	92.93 137	91.21 248	96.64 192	87.23 138	98.22 259	94.99 120	85.80 346	95.98 281

Effi-MVS+-dtu		93.08 187	93.21 164	92.68 318	96.02 259	83.25 360	97.14 189	96.72 261	93.85 93	91.20 249	93.44 361	83.08 200	98.30 254	91.69 195	95.73 204	96.50 262

VPNet		92.23 225	91.31 233	94.99 199	95.56 276	90.96 164	97.22 182	97.86 128	92.96 136	90.96 250	96.62 199	75.06 328	98.20 261	91.90 186	83.65 380	95.80 288

JIA-IIPM		88.26 343	87.04 347	91.91 338	93.52 371	81.42 380	89.38 426	94.38 378	80.84 403	90.93 251	80.74 433	79.22 279	97.92 309	82.76 353	91.62 280	96.38 266

MonoMVSNet		91.92 235	91.77 215	92.37 322	92.94 387	83.11 362	97.09 192	95.55 325	92.91 138	90.85 252	94.55 302	81.27 243	96.52 386	93.01 170	87.76 326	97.47 231

WB-MVSnew		89.88 320	89.56 310	90.82 367	94.57 340	83.06 363	95.65 306	92.85 404	87.86 307	90.83 253	94.10 332	79.66 273	96.88 378	76.34 398	94.19 237	92.54 401

test-LLR		91.42 261	91.19 240	92.12 333	94.59 337	80.66 387	94.29 362	92.98 402	91.11 198	90.76 254	92.37 380	79.02 285	98.07 281	88.81 257	96.74 182	97.63 220

test-mter		90.19 313	89.54 311	92.12 333	94.59 337	80.66 387	94.29 362	92.98 402	87.68 316	90.76 254	92.37 380	67.67 386	98.07 281	88.81 257	96.74 182	97.63 220

ACMM	89.79 8	92.96 193	92.50 194	94.35 235	96.30 241	88.71 242	97.58 130	97.36 205	91.40 184	90.53 256	96.65 191	79.77 270	98.75 210	91.24 204	91.64 279	95.59 300
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
F-COLMAP		93.58 168	92.98 170	95.37 182	98.40 79	88.98 237	97.18 185	97.29 211	87.75 314	90.49 257	97.10 167	85.21 163	99.50 112	86.70 299	96.72 184	97.63 220

TESTMET0.1,1		90.06 315	89.42 314	91.97 336	94.41 345	80.62 389	94.29 362	91.97 414	87.28 326	90.44 258	92.47 379	68.79 378	97.67 334	88.50 264	96.60 187	97.61 224

FIs		94.09 148	93.70 143	95.27 186	95.70 270	92.03 117	98.10 52	98.68 14	93.36 115	90.39 259	96.70 187	87.63 125	97.94 306	92.25 178	90.50 301	95.84 285

GA-MVS		91.38 263	90.31 276	94.59 221	94.65 335	87.62 277	94.34 358	96.19 295	90.73 209	90.35 260	93.83 342	71.84 352	97.96 300	87.22 291	93.61 254	98.21 176

LS3D		93.57 169	92.61 188	96.47 107	97.59 148	91.61 132	97.67 116	97.72 146	85.17 361	90.29 261	98.34 67	84.60 170	99.73 53	83.85 344	98.27 132	98.06 194

FC-MVSNet-test		93.94 156	93.57 147	95.04 196	95.48 280	91.45 142	98.12 51	98.71 12	93.37 113	90.23 262	96.70 187	87.66 122	97.85 315	91.49 198	90.39 302	95.83 286

HQP-NCC					95.86 262		96.65 235		93.55 102	90.14 263

ACMP_Plane					95.86 262		96.65 235		93.55 102	90.14 263

HQP4-MVS										90.14 263			98.50 235			95.78 290

HQP-MVS		93.19 182	92.74 181	94.54 227	95.86 262	89.33 224	96.65 235	97.39 200	93.55 102	90.14 263	95.87 234	80.95 245	98.50 235	92.13 182	92.10 274	95.78 290

UniMVSNet_NR-MVSNet		93.37 175	92.67 184	95.47 179	95.34 292	92.83 84	97.17 186	98.58 23	92.98 135	90.13 267	95.80 239	88.37 110	97.85 315	91.71 193	83.93 375	95.73 296

DU-MVS		92.90 197	92.04 206	95.49 176	94.95 318	92.83 84	97.16 187	98.24 56	93.02 129	90.13 267	95.71 246	83.47 190	97.85 315	91.71 193	83.93 375	95.78 290

LPG-MVS_test		92.94 195	92.56 189	94.10 248	96.16 248	88.26 257	97.65 120	97.46 184	91.29 186	90.12 269	97.16 161	79.05 283	98.73 213	92.25 178	91.89 277	95.31 319

LGP-MVS_train				94.10 248	96.16 248	88.26 257		97.46 184	91.29 186	90.12 269	97.16 161	79.05 283	98.73 213	92.25 178	91.89 277	95.31 319

UniMVSNet (Re)		93.31 177	92.55 190	95.61 168	95.39 286	93.34 67	97.39 162	98.71 12	93.14 126	90.10 271	94.83 288	87.71 121	98.03 288	91.67 196	83.99 374	95.46 305

mvs_anonymous		93.82 161	93.74 142	94.06 250	96.44 232	85.41 327	95.81 295	97.05 231	89.85 241	90.09 272	96.36 211	87.44 133	97.75 329	93.97 144	96.69 185	99.02 94

test_djsdf		93.07 188	92.76 178	94.00 254	93.49 373	88.70 243	98.22 41	97.57 167	91.42 182	90.08 273	95.55 256	82.85 209	97.92 309	94.07 142	91.58 281	95.40 312

dp		88.90 335	88.26 335	90.81 368	94.58 339	76.62 416	92.85 400	94.93 355	85.12 362	90.07 274	93.07 367	75.81 321	98.12 270	80.53 375	87.42 331	97.71 217

PS-MVSNAJss		93.74 164	93.51 153	94.44 231	93.91 358	89.28 228	97.75 102	97.56 171	92.50 149	89.94 275	96.54 202	88.65 104	98.18 264	93.83 151	90.90 295	95.86 282

UniMVSNet_ETH3D		91.34 268	90.22 284	94.68 219	94.86 325	87.86 272	97.23 180	97.46 184	87.99 302	89.90 276	96.92 176	66.35 397	98.23 258	90.30 221	90.99 293	97.96 199

CLD-MVS		92.98 192	92.53 192	94.32 238	96.12 253	89.20 231	95.28 324	97.47 182	92.66 146	89.90 276	95.62 252	80.58 254	98.40 242	92.73 173	92.40 267	95.38 314
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
gg-mvs-nofinetune		87.82 346	85.61 359	94.44 231	94.46 342	89.27 229	91.21 414	84.61 440	80.88 402	89.89 278	74.98 436	71.50 354	97.53 348	85.75 317	97.21 171	96.51 261

1112_ss		93.37 175	92.42 197	96.21 130	97.05 177	90.99 162	96.31 265	96.72 261	86.87 333	89.83 279	96.69 189	86.51 145	99.14 157	88.12 266	93.67 251	98.50 152

BH-untuned		92.94 195	92.62 187	93.92 264	97.22 163	86.16 316	96.40 257	96.25 291	90.06 235	89.79 280	96.17 220	83.19 196	98.35 250	87.19 292	97.27 169	97.24 242

VortexMVS		92.88 199	92.64 185	93.58 281	96.58 213	87.53 279	96.93 206	97.28 212	92.78 144	89.75 281	94.99 278	82.73 212	97.76 327	94.60 135	88.16 322	95.46 305

V42		91.58 251	90.87 250	93.73 271	94.05 355	88.50 250	97.32 170	96.97 239	88.80 280	89.71 282	94.33 318	82.54 217	98.05 284	89.01 253	85.07 358	94.64 363

Baseline_NR-MVSNet		91.20 275	90.62 265	92.95 306	93.83 361	88.03 266	97.01 199	95.12 346	88.42 291	89.70 283	95.13 275	83.47 190	97.44 356	89.66 235	83.24 383	93.37 389

v144192		91.06 281	90.28 278	93.39 289	93.66 367	87.23 286	96.83 216	97.07 228	87.43 321	89.69 284	94.28 322	81.48 238	98.00 291	87.18 293	84.92 362	94.93 341

v1144		91.37 265	90.60 266	93.68 276	93.89 359	88.23 259	96.84 215	97.03 235	88.37 292	89.69 284	94.39 312	82.04 227	97.98 293	87.80 273	85.37 351	94.84 347

Test_1112_low_res		92.84 202	91.84 214	95.85 152	97.04 178	89.97 198	95.53 312	96.64 269	85.38 356	89.65 286	95.18 272	85.86 155	99.10 162	87.70 277	93.58 256	98.49 154

v1192		91.07 280	90.23 282	93.58 281	93.70 364	87.82 274	96.73 225	97.07 228	87.77 312	89.58 287	94.32 320	80.90 249	97.97 296	86.52 301	85.48 349	94.95 337

v1240		90.70 296	89.85 299	93.23 295	93.51 372	86.80 295	96.61 241	97.02 237	87.16 328	89.58 287	94.31 321	79.55 275	97.98 293	85.52 319	85.44 350	94.90 344

TranMVSNet+NR-MVSNet		92.50 209	91.63 221	95.14 191	94.76 329	92.07 114	97.53 140	98.11 82	92.90 139	89.56 289	96.12 223	83.16 197	97.60 342	89.30 244	83.20 384	95.75 294

v2v482		91.59 249	90.85 253	93.80 268	93.87 360	88.17 262	96.94 205	96.88 252	89.54 249	89.53 290	94.90 284	81.70 236	98.02 289	89.25 247	85.04 360	95.20 327

v1921920		90.85 290	90.03 293	93.29 293	93.55 369	86.96 294	96.74 224	97.04 233	87.36 323	89.52 291	94.34 317	80.23 262	97.97 296	86.27 304	85.21 355	94.94 339

IterMVS-LS		92.29 221	91.94 211	93.34 291	96.25 242	86.97 293	96.57 247	97.05 231	90.67 213	89.50 292	94.80 290	86.59 142	97.64 337	89.91 227	86.11 344	95.40 312
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cascas		91.20 275	90.08 288	94.58 225	94.97 316	89.16 234	93.65 384	97.59 165	79.90 409	89.40 293	92.92 370	75.36 326	98.36 249	92.14 181	94.75 226	96.23 267

XVG-ACMP-BASELINE		90.93 288	90.21 285	93.09 301	94.31 349	85.89 318	95.33 321	97.26 213	91.06 201	89.38 294	95.44 262	68.61 380	98.60 227	89.46 239	91.05 291	94.79 355

GBi-Net		91.35 266	90.27 279	94.59 221	96.51 225	91.18 155	97.50 143	96.93 243	88.82 277	89.35 295	94.51 305	73.87 339	97.29 365	86.12 309	88.82 314	95.31 319

test1		91.35 266	90.27 279	94.59 221	96.51 225	91.18 155	97.50 143	96.93 243	88.82 277	89.35 295	94.51 305	73.87 339	97.29 365	86.12 309	88.82 314	95.31 319

FMVSNet3		91.78 240	90.69 264	95.03 197	96.53 222	92.27 107	97.02 196	96.93 243	89.79 244	89.35 295	94.65 298	77.01 311	97.47 353	86.12 309	88.82 314	95.35 316

WR-MVS		92.34 217	91.53 225	94.77 216	95.13 311	90.83 169	96.40 257	97.98 112	91.88 168	89.29 298	95.54 257	82.50 218	97.80 322	89.79 231	85.27 354	95.69 297

DP-MVS		92.76 205	91.51 228	96.52 99	98.77 57	90.99 162	97.38 164	96.08 299	82.38 392	89.29 298	97.87 108	83.77 185	99.69 65	81.37 367	96.69 185	98.89 121

BH-w/o		92.14 229	91.75 217	93.31 292	96.99 183	85.73 322	95.67 302	95.69 316	88.73 282	89.26 300	94.82 289	82.97 205	98.07 281	85.26 324	96.32 193	96.13 276

3Dnovator	91.36 5	95.19 112	94.44 130	97.44 53	96.56 217	93.36 66	98.65 12	98.36 33	94.12 83	89.25 301	98.06 90	82.20 225	99.77 45	93.41 158	99.32 65	99.18 78

tt0805		91.09 279	90.07 291	94.16 246	95.61 273	88.31 254	97.56 134	96.51 277	89.56 248	89.17 302	95.64 251	67.08 394	98.38 248	91.07 207	88.44 320	95.80 288

miper_enhance_ethall		91.54 255	91.01 246	93.15 299	95.35 291	87.07 291	93.97 370	96.90 249	86.79 334	89.17 302	93.43 364	86.55 144	97.64 337	89.97 226	86.93 335	94.74 359

Fast-Effi-MVS+-dtu		92.29 221	91.99 209	93.21 297	95.27 299	85.52 325	97.03 194	96.63 272	92.09 162	89.11 304	95.14 274	80.33 260	98.08 277	87.54 285	94.74 227	96.03 280

WBMVS		90.69 298	89.99 294	92.81 312	96.48 228	85.00 337	95.21 331	96.30 287	89.46 253	89.04 305	94.05 336	72.45 349	97.82 319	89.46 239	87.41 332	95.61 299

XXY-MVS		92.16 227	91.23 238	94.95 205	94.75 330	90.94 165	97.47 152	97.43 196	89.14 262	88.90 306	96.43 207	79.71 271	98.24 257	89.56 237	87.68 327	95.67 298

PCF-MVS	89.48 11	91.56 252	89.95 295	96.36 118	96.60 211	92.52 98	92.51 404	97.26 213	79.41 411	88.90 306	96.56 201	84.04 183	99.55 100	77.01 397	97.30 168	97.01 247
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
miper_ehance_all_eth		91.59 249	91.13 242	92.97 305	95.55 277	86.57 303	94.47 351	96.88 252	87.77 312	88.88 308	94.01 337	86.22 149	97.54 346	89.49 238	86.93 335	94.79 355

SSC-MVS3.2		89.74 325	89.26 318	91.19 361	95.16 306	80.29 395	94.53 348	97.03 235	91.79 170	88.86 309	94.10 332	69.94 369	97.82 319	85.29 322	86.66 340	95.45 307

jajsoiax		92.42 213	91.89 213	94.03 253	93.33 381	88.50 250	97.73 106	97.53 173	92.00 166	88.85 310	96.50 204	75.62 325	98.11 271	93.88 149	91.56 282	95.48 302

eth_miper_zixun_eth		91.02 283	90.59 267	92.34 325	95.33 295	84.35 346	94.10 367	96.90 249	88.56 286	88.84 311	94.33 318	84.08 181	97.60 342	88.77 259	84.37 371	95.06 334

c3_l		91.38 263	90.89 249	92.88 309	95.58 275	86.30 310	94.68 343	96.84 256	88.17 297	88.83 312	94.23 326	85.65 158	97.47 353	89.36 242	84.63 364	94.89 345

mvs_tets		92.31 219	91.76 216	93.94 261	93.41 378	88.29 255	97.63 126	97.53 173	92.04 164	88.76 313	96.45 206	74.62 335	98.09 276	93.91 147	91.48 283	95.45 307

v148		90.99 284	90.38 273	92.81 312	93.83 361	85.80 319	96.78 222	96.68 266	89.45 254	88.75 314	93.93 341	82.96 206	97.82 319	87.83 272	83.25 382	94.80 353

FMVSNet2		91.31 269	90.08 288	94.99 199	96.51 225	92.21 109	97.41 157	96.95 241	88.82 277	88.62 315	94.75 292	73.87 339	97.42 358	85.20 325	88.55 319	95.35 316

PAPM		91.52 256	90.30 277	95.20 188	95.30 298	89.83 202	93.38 390	96.85 255	86.26 344	88.59 316	95.80 239	84.88 167	98.15 266	75.67 402	95.93 198	97.63 220

cl22		91.21 274	90.56 269	93.14 300	96.09 255	86.80 295	94.41 355	96.58 275	87.80 310	88.58 317	93.99 339	80.85 250	97.62 340	89.87 229	86.93 335	94.99 336

3Dnovator+	91.43 4	95.40 102	94.48 128	98.16 16	96.90 188	95.34 16	98.48 21	97.87 124	94.65 65	88.53 318	98.02 95	83.69 186	99.71 59	93.18 162	98.96 101	99.44 55

dmvs_re		90.21 311	89.50 312	92.35 323	95.47 284	85.15 333	95.70 301	94.37 379	90.94 204	88.42 319	93.57 356	74.63 334	95.67 400	82.80 352	89.57 309	96.22 268

anonymousdsp		92.16 227	91.55 224	93.97 257	92.58 396	89.55 212	97.51 142	97.42 197	89.42 255	88.40 320	94.84 287	80.66 252	97.88 314	91.87 188	91.28 287	94.48 365

reproduce_monomvs		91.30 270	91.10 243	91.92 337	96.82 196	82.48 370	97.01 199	97.49 178	94.64 66	88.35 321	95.27 268	70.53 362	98.10 272	95.20 113	84.60 366	95.19 330

WR-MVS_H		92.00 233	91.35 230	93.95 259	95.09 313	89.47 216	98.04 59	98.68 14	91.46 180	88.34 322	94.68 295	85.86 155	97.56 344	85.77 316	84.24 372	94.82 350

v8		91.29 272	90.53 270	93.57 283	94.15 351	88.12 264	97.34 167	97.06 230	88.99 268	88.32 323	94.26 325	83.08 200	98.01 290	87.62 283	83.92 377	94.57 364

ACMP	89.59 10	92.62 208	92.14 203	94.05 251	96.40 234	88.20 260	97.36 165	97.25 215	91.52 177	88.30 324	96.64 192	78.46 295	98.72 216	91.86 189	91.48 283	95.23 326
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		91.04 282	90.23 282	93.49 285	94.12 352	88.16 263	97.32 170	97.08 226	88.26 295	88.29 325	94.22 328	82.17 226	97.97 296	86.45 303	84.12 373	94.33 371

QAPM		93.45 173	92.27 200	96.98 80	96.77 202	92.62 93	98.39 25	98.12 79	84.50 371	88.27 326	97.77 119	82.39 222	99.81 30	85.40 321	98.81 106	98.51 151

Anonymous20231211		90.63 299	89.42 314	94.27 243	98.24 92	89.19 233	98.05 58	97.89 120	79.95 408	88.25 327	94.96 280	72.56 348	98.13 267	89.70 233	85.14 356	95.49 301

CP-MVSNet		91.89 238	91.24 237	93.82 267	95.05 314	88.57 246	97.82 93	98.19 67	91.70 173	88.21 328	95.76 244	81.96 229	97.52 350	87.86 271	84.65 363	95.37 315

DIV-MVS_self_test		90.97 286	90.33 274	92.88 309	95.36 290	86.19 315	94.46 353	96.63 272	87.82 308	88.18 329	94.23 326	82.99 203	97.53 348	87.72 274	85.57 348	94.93 341

cl____		90.96 287	90.32 275	92.89 308	95.37 289	86.21 313	94.46 353	96.64 269	87.82 308	88.15 330	94.18 329	82.98 204	97.54 346	87.70 277	85.59 347	94.92 343

tpmvs		89.83 323	89.15 321	91.89 340	94.92 321	80.30 394	93.11 395	95.46 329	86.28 343	88.08 331	92.65 373	80.44 257	98.52 234	81.47 363	89.92 305	96.84 254

PS-CasMVS		91.55 253	90.84 254	93.69 275	94.96 317	88.28 256	97.84 88	98.24 56	91.46 180	88.04 332	95.80 239	79.67 272	97.48 352	87.02 296	84.54 369	95.31 319

MIMVSNet		88.50 340	86.76 350	93.72 273	94.84 326	87.77 275	91.39 410	94.05 386	86.41 340	87.99 333	92.59 376	63.27 408	95.82 397	77.44 391	92.84 260	97.57 227

GG-mvs-BLEND				93.62 278	93.69 365	89.20 231	92.39 406	83.33 442		87.98 334	89.84 410	71.00 358	96.87 379	82.08 359	95.40 212	94.80 353

miper_lstm_enhance		90.50 304	90.06 292	91.83 342	95.33 295	83.74 354	93.86 376	96.70 265	87.56 319	87.79 335	93.81 345	83.45 192	96.92 377	87.39 287	84.62 365	94.82 350

PEN-MVS		91.20 275	90.44 271	93.48 286	94.49 341	87.91 271	97.76 100	98.18 69	91.29 186	87.78 336	95.74 245	80.35 259	97.33 363	85.46 320	82.96 385	95.19 330

ITE_SJBPF				92.43 321	95.34 292	85.37 330		95.92 302	91.47 179	87.75 337	96.39 210	71.00 358	97.96 300	82.36 357	89.86 306	93.97 381

v7n		90.76 292	89.86 298	93.45 288	93.54 370	87.60 278	97.70 114	97.37 203	88.85 274	87.65 338	94.08 335	81.08 244	98.10 272	84.68 330	83.79 379	94.66 362

Patchmtry		88.64 339	87.25 342	92.78 314	94.09 353	86.64 299	89.82 424	95.68 318	80.81 404	87.63 339	92.36 383	80.91 247	97.03 372	78.86 386	85.12 357	94.67 361

testing3		87.67 348	86.88 349	90.05 380	96.14 251	80.71 386	97.10 191	92.85 404	90.15 233	87.54 340	94.55 302	55.70 424	94.10 416	73.77 412	94.10 241	95.35 316

pmmvs4		90.93 288	89.85 299	94.17 245	93.34 380	90.79 171	94.60 345	96.02 300	84.62 369	87.45 341	95.15 273	81.88 233	97.45 355	87.70 277	87.87 325	94.27 375

tpm cat1		88.36 341	87.21 344	91.81 344	95.13 311	80.55 390	92.58 403	95.70 314	74.97 422	87.45 341	91.96 391	78.01 305	98.17 265	80.39 376	88.74 317	96.72 258

FMVSNet1		89.88 320	88.31 333	94.59 221	95.41 285	91.18 155	97.50 143	96.93 243	86.62 336	87.41 343	94.51 305	65.94 402	97.29 365	83.04 348	87.43 330	95.31 319

IterMVS-SCA-FT		90.31 306	89.81 301	91.82 343	95.52 278	84.20 349	94.30 361	96.15 297	90.61 219	87.39 344	94.27 323	75.80 322	96.44 387	87.34 288	86.88 339	94.82 350

MVS		91.71 242	90.44 271	95.51 174	95.20 305	91.59 134	96.04 282	97.45 189	73.44 426	87.36 345	95.60 253	85.42 160	99.10 162	85.97 313	97.46 157	95.83 286

EU-MVSNet		88.72 338	88.90 326	88.20 394	93.15 384	74.21 422	96.63 240	94.22 384	85.18 360	87.32 346	95.97 229	76.16 319	94.98 409	85.27 323	86.17 342	95.41 309

IterMVS		90.15 314	89.67 307	91.61 350	95.48 280	83.72 355	94.33 359	96.12 298	89.99 236	87.31 347	94.15 331	75.78 324	96.27 390	86.97 297	86.89 338	94.83 348
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UWE-MVS-28		86.81 357	86.41 352	88.02 396	92.87 388	74.60 421	95.38 319	86.70 436	88.17 297	87.28 348	94.67 297	70.83 360	93.30 424	67.45 426	94.31 233	96.17 271

pmmvs5		89.86 322	88.87 327	92.82 311	92.86 389	86.23 312	96.26 268	95.39 330	84.24 373	87.12 349	94.51 305	74.27 337	97.36 362	87.61 284	87.57 328	94.86 346

DTE-MVSNet		90.56 300	89.75 305	93.01 303	93.95 356	87.25 284	97.64 124	97.65 154	90.74 208	87.12 349	95.68 249	79.97 267	97.00 375	83.33 345	81.66 391	94.78 357

mvs5depth		86.53 358	85.08 365	90.87 365	88.74 424	82.52 369	91.91 408	94.23 383	86.35 341	87.11 351	93.70 348	66.52 395	97.76 327	81.37 367	75.80 413	92.31 406

Patchmatch-test		89.42 329	87.99 336	93.70 274	95.27 299	85.11 334	88.98 427	94.37 379	81.11 400	87.10 352	93.69 349	82.28 223	97.50 351	74.37 408	94.76 225	98.48 156

IB-MVS	87.33 17	89.91 317	88.28 334	94.79 215	95.26 302	87.70 276	95.12 334	93.95 390	89.35 257	87.03 353	92.49 377	70.74 361	99.19 145	89.18 251	81.37 392	97.49 229
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
EPNet_dtu		91.71 242	91.28 235	92.99 304	93.76 363	83.71 356	96.69 231	95.28 337	93.15 125	87.02 354	95.95 231	83.37 193	97.38 361	79.46 383	96.84 179	97.88 205
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Syy-MVS		87.13 353	87.02 348	87.47 398	95.16 306	73.21 426	95.00 336	93.93 391	88.55 287	86.96 355	91.99 389	75.90 320	94.00 417	61.59 432	94.11 239	95.20 327

myMVS_eth3d		87.18 352	86.38 353	89.58 385	95.16 306	79.53 404	95.00 336	93.93 391	88.55 287	86.96 355	91.99 389	56.23 423	94.00 417	75.47 404	94.11 239	95.20 327

baseline2		91.63 246	90.86 251	93.94 261	94.33 347	86.32 309	95.92 289	91.64 416	89.37 256	86.94 357	94.69 294	81.62 237	98.69 218	88.64 262	94.57 230	96.81 255

MSDG		91.42 261	90.24 281	94.96 204	97.15 169	88.91 238	93.69 382	96.32 285	85.72 352	86.93 358	96.47 205	80.24 261	98.98 183	80.57 374	95.05 220	96.98 248

test0.0.03 1		89.37 330	88.70 328	91.41 355	92.47 398	85.63 323	95.22 329	92.70 407	91.11 198	86.91 359	93.65 353	79.02 285	93.19 426	78.00 390	89.18 312	95.41 309

COLMAP_ROB	87.81 15	90.40 305	89.28 317	93.79 269	97.95 120	87.13 290	96.92 207	95.89 306	82.83 389	86.88 360	97.18 160	73.77 342	99.29 137	78.44 388	93.62 253	94.95 337
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
D2MVS		91.30 270	90.95 248	92.35 323	94.71 333	85.52 325	96.18 276	98.21 60	88.89 273	86.60 361	93.82 344	79.92 268	97.95 304	89.29 245	90.95 294	93.56 385

OurMVSNet-221017-0		90.51 303	90.19 286	91.44 354	93.41 378	81.25 381	96.98 202	96.28 288	91.68 174	86.55 362	96.30 213	74.20 338	97.98 293	88.96 255	87.40 333	95.09 332

sc_t1		86.48 360	84.10 376	93.63 277	93.45 376	85.76 321	96.79 219	94.71 364	73.06 427	86.45 363	94.35 315	55.13 425	97.95 304	84.38 335	78.55 405	97.18 244

MS-PatchMatch		90.27 308	89.77 303	91.78 346	94.33 347	84.72 343	95.55 310	96.73 260	86.17 346	86.36 364	95.28 267	71.28 356	97.80 322	84.09 338	98.14 138	92.81 395

1314		92.81 204	92.03 207	95.14 191	95.33 295	89.52 215	96.04 282	97.44 193	87.72 315	86.25 365	95.33 264	83.84 184	98.79 204	89.26 246	97.05 176	97.11 246

tfpnnormal		89.70 326	88.40 332	93.60 279	95.15 309	90.10 191	97.56 134	98.16 73	87.28 326	86.16 366	94.63 299	77.57 308	98.05 284	74.48 406	84.59 367	92.65 398

pm-mvs1		90.72 295	89.65 309	93.96 258	94.29 350	89.63 206	97.79 98	96.82 257	89.07 264	86.12 367	95.48 261	78.61 293	97.78 324	86.97 297	81.67 390	94.46 366

OpenMVS	89.19 12	92.86 200	91.68 220	96.40 113	95.34 292	92.73 89	98.27 33	98.12 79	84.86 366	85.78 368	97.75 120	78.89 290	99.74 51	87.50 286	98.65 113	96.73 257

LTVRE_ROB	88.41 13	90.99 284	89.92 297	94.19 244	96.18 246	89.55 212	96.31 265	97.09 225	87.88 306	85.67 369	95.91 233	78.79 291	98.57 231	81.50 361	89.98 304	94.44 368
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
testgi		87.97 344	87.21 344	90.24 378	92.86 389	80.76 385	96.67 234	94.97 352	91.74 172	85.52 370	95.83 237	62.66 412	94.47 413	76.25 399	88.36 321	95.48 302

AllTest		90.23 310	88.98 323	93.98 255	97.94 121	86.64 299	96.51 248	95.54 326	85.38 356	85.49 371	96.77 183	70.28 364	99.15 154	80.02 378	92.87 258	96.15 274

TestCases				93.98 255	97.94 121	86.64 299		95.54 326	85.38 356	85.49 371	96.77 183	70.28 364	99.15 154	80.02 378	92.87 258	96.15 274

DSMNet-mixed		86.34 363	86.12 357	87.00 402	89.88 415	70.43 428	94.93 338	90.08 425	77.97 417	85.42 373	92.78 371	74.44 336	93.96 419	74.43 407	95.14 216	96.62 259

ppachtmachnet_test		88.35 342	87.29 341	91.53 351	92.45 399	83.57 358	93.75 379	95.97 301	84.28 372	85.32 374	94.18 329	79.00 289	96.93 376	75.71 401	84.99 361	94.10 376

CL-MVSNet_self_test		86.31 364	85.15 364	89.80 383	88.83 422	81.74 379	93.93 373	96.22 292	86.67 335	85.03 375	90.80 401	78.09 302	94.50 411	74.92 405	71.86 423	93.15 391

our_test_3		88.78 337	87.98 337	91.20 360	92.45 399	82.53 368	93.61 386	95.69 316	85.77 351	84.88 376	93.71 347	79.99 266	96.78 383	79.47 382	86.24 341	94.28 374

MVP-Stereo		90.74 294	90.08 288	92.71 316	93.19 383	88.20 260	95.86 292	96.27 289	86.07 347	84.86 377	94.76 291	77.84 306	97.75 329	83.88 343	98.01 144	92.17 410
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
ACMH+	87.92 14	90.20 312	89.18 320	93.25 294	96.48 228	86.45 307	96.99 201	96.68 266	88.83 276	84.79 378	96.22 217	70.16 366	98.53 233	84.42 334	88.04 323	94.77 358

NR-MVSNet		92.34 217	91.27 236	95.53 173	94.95 318	93.05 77	97.39 162	98.07 91	92.65 147	84.46 379	95.71 246	85.00 166	97.77 326	89.71 232	83.52 381	95.78 290

LF4IMVS		87.94 345	87.25 342	89.98 381	92.38 401	80.05 400	94.38 356	95.25 340	87.59 318	84.34 380	94.74 293	64.31 406	97.66 336	84.83 327	87.45 329	92.23 407

LCM-MVSNet-Re		92.50 209	92.52 193	92.44 320	96.82 196	81.89 377	96.92 207	93.71 395	92.41 151	84.30 381	94.60 300	85.08 165	97.03 372	91.51 197	97.36 163	98.40 165

TransMVSNet (Re)		88.94 333	87.56 339	93.08 302	94.35 346	88.45 252	97.73 106	95.23 341	87.47 320	84.26 382	95.29 265	79.86 269	97.33 363	79.44 384	74.44 418	93.45 388

Anonymous20231206		87.09 354	86.14 356	89.93 382	91.22 407	80.35 392	96.11 279	95.35 333	83.57 384	84.16 383	93.02 368	73.54 344	95.61 401	72.16 417	86.14 343	93.84 383

SixPastTwentyTwo		89.15 331	88.54 331	90.98 363	93.49 373	80.28 396	96.70 229	94.70 365	90.78 206	84.15 384	95.57 254	71.78 353	97.71 332	84.63 331	85.07 358	94.94 339

test_fmvs3		83.21 384	83.02 380	83.78 407	86.77 431	68.34 433	96.76 223	94.91 356	86.49 338	84.14 385	89.48 412	36.04 439	91.73 429	91.86 189	80.77 395	91.26 419

TDRefinement		86.53 358	84.76 370	91.85 341	82.23 439	84.25 347	96.38 259	95.35 333	84.97 365	84.09 386	94.94 281	65.76 403	98.34 253	84.60 332	74.52 417	92.97 392

KD-MVS_self_test		85.95 369	84.95 367	88.96 391	89.55 418	79.11 410	95.13 333	96.42 281	85.91 349	84.07 387	90.48 403	70.03 368	94.82 410	80.04 377	72.94 421	92.94 393

pmmvs6		87.81 347	86.19 355	92.69 317	91.32 406	86.30 310	97.34 167	96.41 282	80.59 407	84.05 388	94.37 314	67.37 389	97.67 334	84.75 329	79.51 400	94.09 378

ACMH	87.59 16	90.53 301	89.42 314	93.87 265	96.21 243	87.92 269	97.24 176	96.94 242	88.45 290	83.91 389	96.27 215	71.92 351	98.62 226	84.43 333	89.43 310	95.05 335
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
FMVSNet5		87.29 351	85.79 358	91.78 346	94.80 328	87.28 282	95.49 314	95.28 337	84.09 375	83.85 390	91.82 392	62.95 410	94.17 415	78.48 387	85.34 353	93.91 382

USDC		88.94 333	87.83 338	92.27 328	94.66 334	84.96 339	93.86 376	95.90 304	87.34 324	83.40 391	95.56 255	67.43 388	98.19 263	82.64 356	89.67 308	93.66 384

ttmdpeth		85.91 370	84.76 370	89.36 388	89.14 419	80.25 397	95.66 305	93.16 401	83.77 380	83.39 392	95.26 269	66.24 399	95.26 408	80.65 373	75.57 414	92.57 399

Anonymous20240521		86.42 362	85.44 360	89.34 389	90.33 411	79.79 401	96.73 225	95.92 302	83.71 382	83.25 393	91.36 398	63.92 407	96.01 391	78.39 389	85.36 352	92.22 408

KD-MVS_2432*1600		84.81 379	82.64 382	91.31 356	91.07 408	85.34 331	91.22 412	95.75 312	85.56 354	83.09 394	90.21 406	67.21 390	95.89 393	77.18 395	62.48 436	92.69 396

miper_refine_blended		84.81 379	82.64 382	91.31 356	91.07 408	85.34 331	91.22 412	95.75 312	85.56 354	83.09 394	90.21 406	67.21 390	95.89 393	77.18 395	62.48 436	92.69 396

PVSNet_0	82.17 19	85.46 374	83.64 377	90.92 364	95.27 299	79.49 406	90.55 418	95.60 321	83.76 381	83.00 396	89.95 408	71.09 357	97.97 296	82.75 354	60.79 438	95.31 319

tt0320		85.39 375	83.12 378	92.19 332	93.44 377	85.79 320	96.19 275	94.87 361	71.19 429	82.92 397	91.76 395	58.43 418	96.81 381	81.03 372	78.26 406	93.98 380

mvsany_test3		83.59 382	82.44 385	87.03 401	83.80 434	73.82 423	93.70 380	90.92 422	86.42 339	82.51 398	90.26 405	46.76 434	95.71 398	90.82 210	76.76 410	91.57 414

test_0402		86.46 361	84.79 369	91.45 353	95.02 315	85.55 324	96.29 267	94.89 357	80.90 401	82.21 399	93.97 340	68.21 385	97.29 365	62.98 430	88.68 318	91.51 415

Patchmatch-RL test		87.38 350	86.24 354	90.81 368	88.74 424	78.40 413	88.12 432	93.17 400	87.11 329	82.17 400	89.29 413	81.95 230	95.60 402	88.64 262	77.02 408	98.41 164

tt0320-xc		84.83 378	82.33 386	92.31 326	93.66 367	86.20 314	96.17 277	94.06 385	71.26 428	82.04 401	92.22 387	55.07 426	96.72 384	81.49 362	75.04 416	94.02 379

TinyColmap		86.82 356	85.35 363	91.21 358	94.91 323	82.99 364	93.94 372	94.02 388	83.58 383	81.56 402	94.68 295	62.34 413	98.13 267	75.78 400	87.35 334	92.52 402

test20.03		86.14 367	85.40 362	88.35 392	90.12 412	80.06 399	95.90 291	95.20 342	88.59 283	81.29 403	93.62 354	71.43 355	92.65 427	71.26 421	81.17 393	92.34 404

N_pmnet		78.73 394	78.71 395	78.79 412	92.80 391	46.50 451	94.14 366	43.71 453	78.61 414	80.83 404	91.66 396	74.94 332	96.36 388	67.24 427	84.45 370	93.50 386

MVS-HIRNet		82.47 387	81.21 390	86.26 404	95.38 287	69.21 431	88.96 428	89.49 426	66.28 433	80.79 405	74.08 438	68.48 383	97.39 360	71.93 418	95.47 210	92.18 409

PM-MVS		83.48 383	81.86 389	88.31 393	87.83 428	77.59 415	93.43 388	91.75 415	86.91 331	80.63 406	89.91 409	44.42 435	95.84 396	85.17 326	76.73 411	91.50 416

ambc				86.56 403	83.60 436	70.00 430	85.69 434	94.97 352		80.60 407	88.45 417	37.42 438	96.84 380	82.69 355	75.44 415	92.86 394

MIMVSNet1		84.93 377	83.05 379	90.56 373	89.56 417	84.84 342	95.40 317	95.35 333	83.91 376	80.38 408	92.21 388	57.23 420	93.34 423	70.69 423	82.75 388	93.50 386

lessismore_v0				90.45 374	91.96 404	79.09 411		87.19 434		80.32 409	94.39 312	66.31 398	97.55 345	84.00 340	76.84 409	94.70 360

K. test v3		87.64 349	86.75 351	90.32 377	93.02 386	79.48 407	96.61 241	92.08 413	90.66 215	80.25 410	94.09 334	67.21 390	96.65 385	85.96 314	80.83 394	94.83 348

OpenMVS_ROB	81.14 20	84.42 381	82.28 387	90.83 366	90.06 413	84.05 352	95.73 300	94.04 387	73.89 425	80.17 411	91.53 397	59.15 416	97.64 337	66.92 428	89.05 313	90.80 421

EG-PatchMatch MVS		87.02 355	85.44 360	91.76 348	92.67 393	85.00 337	96.08 281	96.45 280	83.41 386	79.52 412	93.49 358	57.10 421	97.72 331	79.34 385	90.87 296	92.56 400

pmmvs-eth3d		86.22 365	84.45 372	91.53 351	88.34 426	87.25 284	94.47 351	95.01 349	83.47 385	79.51 413	89.61 411	69.75 372	95.71 398	83.13 347	76.73 411	91.64 412

test_vis1_rt		86.16 366	85.06 366	89.46 386	93.47 375	80.46 391	96.41 253	86.61 437	85.22 359	79.15 414	88.64 416	52.41 429	97.06 370	93.08 165	90.57 298	90.87 420

pmmvs3		79.97 392	77.50 397	87.39 399	82.80 438	79.38 408	92.70 402	90.75 423	70.69 430	78.66 415	87.47 426	51.34 430	93.40 422	73.39 414	69.65 426	89.38 425

UnsupCasMVSNet_eth		85.99 368	84.45 372	90.62 372	89.97 414	82.40 373	93.62 385	97.37 203	89.86 239	78.59 416	92.37 380	65.25 405	95.35 407	82.27 358	70.75 424	94.10 376

dmvs_testset		81.38 390	82.60 384	77.73 413	91.74 405	51.49 448	93.03 397	84.21 441	89.07 264	78.28 417	91.25 399	76.97 312	88.53 436	56.57 436	82.24 389	93.16 390

test_f		80.57 391	79.62 393	83.41 408	83.38 437	67.80 435	93.57 387	93.72 394	80.80 405	77.91 418	87.63 424	33.40 440	92.08 428	87.14 295	79.04 403	90.34 423

new-patchmatchnet		83.18 385	81.87 388	87.11 400	86.88 430	75.99 419	93.70 380	95.18 343	85.02 364	77.30 419	88.40 418	65.99 401	93.88 420	74.19 410	70.18 425	91.47 417

UnsupCasMVSNet_bld		82.13 389	79.46 394	90.14 379	88.00 427	82.47 371	90.89 417	96.62 274	78.94 413	75.61 420	84.40 431	56.63 422	96.31 389	77.30 394	66.77 432	91.63 413

ET-MVSNet_ETH3D		91.49 258	90.11 287	95.63 166	96.40 234	91.57 136	95.34 320	93.48 397	90.60 221	75.58 421	95.49 259	80.08 264	96.79 382	94.25 140	89.76 307	98.52 149

new_pmnet		82.89 386	81.12 391	88.18 395	89.63 416	80.18 398	91.77 409	92.57 408	76.79 420	75.56 422	88.23 420	61.22 415	94.48 412	71.43 419	82.92 386	89.87 424

dongtai		69.99 401	69.33 403	71.98 422	88.78 423	61.64 442	89.86 423	59.93 452	75.67 421	74.96 423	85.45 428	50.19 431	81.66 441	43.86 440	55.27 439	72.63 437

APD_test1		79.31 393	77.70 396	84.14 406	89.11 421	69.07 432	92.36 407	91.50 417	69.07 431	73.87 424	92.63 375	39.93 437	94.32 414	70.54 424	80.25 396	89.02 426

CMPMVS	62.92 21	85.62 373	84.92 368	87.74 397	89.14 419	73.12 427	94.17 365	96.80 258	73.98 423	73.65 425	94.93 282	66.36 396	97.61 341	83.95 341	91.28 287	92.48 403
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVStest1		82.38 388	80.04 392	89.37 387	87.63 429	82.83 365	95.03 335	93.37 399	73.90 424	73.50 426	94.35 315	62.89 411	93.25 425	73.80 411	65.92 433	92.04 411

WB-MVS		76.77 395	76.63 398	77.18 414	85.32 432	56.82 446	94.53 348	89.39 427	82.66 391	71.35 427	89.18 414	75.03 329	88.88 434	35.42 443	66.79 431	85.84 428

SSC-MVS		76.05 396	75.83 399	76.72 418	84.77 433	56.22 447	94.32 360	88.96 429	81.82 397	70.52 428	88.91 415	74.79 333	88.71 435	33.69 444	64.71 434	85.23 429

YYNet1		85.87 371	84.23 374	90.78 371	92.38 401	82.46 372	93.17 392	95.14 345	82.12 394	67.69 429	92.36 383	78.16 301	95.50 405	77.31 393	79.73 398	94.39 369

kuosan		65.27 407	64.66 409	67.11 425	83.80 434	61.32 443	88.53 429	60.77 451	68.22 432	67.67 430	80.52 434	49.12 432	70.76 447	29.67 446	53.64 441	69.26 439

MDA-MVSNet_test_wron		85.87 371	84.23 374	90.80 370	92.38 401	82.57 367	93.17 392	95.15 344	82.15 393	67.65 431	92.33 386	78.20 298	95.51 404	77.33 392	79.74 397	94.31 373

DeepMVS_CX				74.68 421	90.84 410	64.34 439		81.61 444	65.34 434	67.47 432	88.01 423	48.60 433	80.13 443	62.33 431	73.68 420	79.58 433

LCM-MVSNet		72.55 398	69.39 402	82.03 409	70.81 449	65.42 438	90.12 422	94.36 381	55.02 439	65.88 433	81.72 432	24.16 447	89.96 430	74.32 409	68.10 430	90.71 422

test_method		66.11 406	64.89 408	69.79 423	72.62 447	35.23 455	65.19 442	92.83 406	20.35 445	65.20 434	88.08 422	43.14 436	82.70 440	73.12 415	63.46 435	91.45 418

MDA-MVSNet-bldmvs		85.00 376	82.95 381	91.17 362	93.13 385	83.33 359	94.56 347	95.00 350	84.57 370	65.13 435	92.65 373	70.45 363	95.85 395	73.57 413	77.49 407	94.33 371

PMMVS2		70.19 400	66.92 404	80.01 410	76.35 443	65.67 437	86.22 433	87.58 433	64.83 435	62.38 436	80.29 435	26.78 445	88.49 437	63.79 429	54.07 440	85.88 427

testf1		69.31 402	66.76 405	76.94 416	78.61 441	61.93 440	88.27 430	86.11 438	55.62 437	59.69 437	85.31 429	20.19 449	89.32 431	57.62 433	69.44 428	79.58 433

APD_test2		69.31 402	66.76 405	76.94 416	78.61 441	61.93 440	88.27 430	86.11 438	55.62 437	59.69 437	85.31 429	20.19 449	89.32 431	57.62 433	69.44 428	79.58 433

test_vis3_rt		72.73 397	70.55 400	79.27 411	80.02 440	68.13 434	93.92 374	74.30 448	76.90 419	58.99 439	73.58 439	20.29 448	95.37 406	84.16 336	72.80 422	74.31 436

FPMVS		71.27 399	69.85 401	75.50 419	74.64 444	59.03 444	91.30 411	91.50 417	58.80 436	57.92 440	88.28 419	29.98 443	85.53 439	53.43 437	82.84 387	81.95 432

Gipuma		67.86 405	65.41 407	75.18 420	92.66 394	73.45 424	66.50 441	94.52 372	53.33 440	57.80 441	66.07 441	30.81 441	89.20 433	48.15 439	78.88 404	62.90 441
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		51.94 413	53.82 413	46.29 429	33.73 453	45.30 453	78.32 439	67.24 450	18.02 446	50.93 442	87.05 427	52.99 428	53.11 448	70.76 422	25.29 446	40.46 444

ANet_high		63.94 408	59.58 411	77.02 415	61.24 451	66.06 436	85.66 435	87.93 432	78.53 415	42.94 443	71.04 440	25.42 446	80.71 442	52.60 438	30.83 444	84.28 430

E-PMN		53.28 410	52.56 414	55.43 427	74.43 445	47.13 450	83.63 437	76.30 445	42.23 442	42.59 444	62.22 443	28.57 444	74.40 444	31.53 445	31.51 443	44.78 442

EMVS		52.08 412	51.31 415	54.39 428	72.62 447	45.39 452	83.84 436	75.51 447	41.13 443	40.77 445	59.65 444	30.08 442	73.60 445	28.31 447	29.90 445	44.18 443

MVE	50.73 23	53.25 411	48.81 416	66.58 426	65.34 450	57.50 445	72.49 440	70.94 449	40.15 444	39.28 446	63.51 442	6.89 453	73.48 446	38.29 442	42.38 442	68.76 440
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	53.92 22	58.58 409	55.40 412	68.12 424	51.00 452	48.64 449	78.86 438	87.10 435	46.77 441	35.84 447	74.28 437	8.76 451	86.34 438	42.07 441	73.91 419	69.38 438
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		25.11 414	24.57 418	26.74 430	73.98 446	39.89 454	57.88 443	9.80 454	12.27 447	10.39 448	6.97 450	7.03 452	36.44 449	25.43 448	17.39 447	3.89 447

testmvs		13.36 416	16.33 419	4.48 432	5.04 454	2.26 457	93.18 391	3.28 455	2.70 448	8.24 449	21.66 446	2.29 455	2.19 450	7.58 449	2.96 448	9.00 446

test123		13.04 417	15.66 420	5.18 431	4.51 455	3.45 456	92.50 405	1.81 456	2.50 449	7.58 450	20.15 447	3.67 454	2.18 451	7.13 450	1.07 449	9.90 445

EGC-MVSNET		68.77 404	63.01 410	86.07 405	92.49 397	82.24 375	93.96 371	90.96 421	0.71 450	2.62 451	90.89 400	53.66 427	93.46 421	57.25 435	84.55 368	82.51 431

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		23.24 415	30.99 417	0.00 433	0.00 456	0.00 458	0.00 444	97.63 158	0.00 451	0.00 452	96.88 178	84.38 175	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		7.39 419	9.85 422	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	88.65 104	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		8.06 418	10.74 421	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	96.69 189	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						79.53 404								75.56 403

MSC_two_6792asdad				98.86 1	98.67 62	96.94 1		97.93 117					99.86 9	97.68 29	99.67 6	99.77 2

No_MVS				98.86 1	98.67 62	96.94 1		97.93 117					99.86 9	97.68 29	99.67 6	99.77 2

eth-test2					0.00 456

eth-test					0.00 456

OPU-MVS				98.55 3	98.82 56	96.86 3	98.25 36				98.26 79	96.04 2	99.24 140	95.36 111	99.59 19	99.56 34

save fliter					98.91 53	94.28 38	97.02 196	98.02 106	95.35 26

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 45					99.86 9	97.52 38	99.67 6	99.75 6

GSMVS																98.45 159

sam_mvs1												82.76 211				98.45 159

sam_mvs												81.94 231

MTGPA								98.08 86

test_post1							92.81 401				16.58 449	80.53 255	97.68 333	86.20 306

test_post											17.58 448	81.76 234	98.08 277

patchmatchnet-post											90.45 404	82.65 216	98.10 272

MTMP							97.86 84	82.03 443

gm-plane-assit					93.22 382	78.89 412			84.82 367		93.52 357		98.64 223	87.72 274

test9_res														94.81 127	99.38 59	99.45 53

agg_prior2														93.94 146	99.38 59	99.50 46

test_prior4						93.66 58	96.42 252

test_prior				97.23 65	98.67 62	92.99 79		98.00 110					99.41 123			99.29 69

新几何2							95.79 297

旧先验1					98.38 82	93.38 64		97.75 141			98.09 88	92.30 45			99.01 99	99.16 79

无先验							95.79 297	97.87 124	83.87 379				99.65 71	87.68 280		98.89 121

原ACMM2							95.67 302

testdata2													99.67 69	85.96 314

segment_acmp												92.89 30

testdata1							95.26 328		93.10 128

plane_prior7					96.21 243	89.98 197

plane_prior6					96.10 254	90.00 193						81.32 241

plane_prior5								97.51 175					98.60 227	93.02 168	92.23 269	95.86 282

plane_prior4											96.64 192

plane_prior2							97.74 104		94.85 48

plane_prior1					96.14 251

plane_prior						89.99 195	97.24 176		94.06 85						92.16 273

n2								0.00 457

nn								0.00 457

door-mid								91.06 420

test11								97.88 122

door								91.13 419

HQP5-MVS						89.33 224

BP-MVS														92.13 182

HQP3-MVS								97.39 200							92.10 274

HQP2-MVS												80.95 245

NP-MVS					95.99 260	89.81 203					95.87 234

ACMMP++_ref															90.30 303

ACMMP++															91.02 292

Test By Simon												88.73 103

High-resolution multi-view benchmark