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.

IU-MVS					99.63 21	95.38 21		97.73 75	95.54 15	99.54 1				99.69 5	99.81 23	99.99 1

PC_three_1452									94.60 21	99.41 2	99.12 48	95.50 7	99.96 30	99.84 2	99.92 3	99.97 7

CNVR-MVS		98.46 1	98.38 1	98.72 8	99.80 4	96.19 14	99.80 7	97.99 45	97.05 3	99.41 2	99.59 2	92.89 25	100.00 1	98.99 19	99.90 7	99.96 10

patch_mono-2		97.10 27	97.97 8	94.49 169	99.21 73	83.73 284	99.62 28	98.25 27	95.28 18	99.38 4	98.91 80	92.28 28	99.94 37	99.61 8	99.22 83	99.78 42

test0726					99.66 15	95.20 29	99.77 8	97.70 82	93.95 31	99.35 5	99.54 3	93.18 22

SED-MVS		98.18 2	98.10 4	98.41 17	99.63 21	95.24 24	99.77 8	97.72 77	94.17 26	99.30 6	99.54 3	93.32 19	99.98 10	99.70 3	99.81 23	99.99 1

test_241102_ONE					99.63 21	95.24 24		97.72 77	94.16 28	99.30 6	99.49 10	93.32 19	99.98 10

DVP-MVS++		98.18 2	98.09 5	98.44 15	99.61 27	95.38 21	99.55 35	97.68 86	93.01 53	99.23 8	99.45 16	95.12 8	99.98 10	99.25 15	99.92 3	99.97 7

test_241102_TWO								97.72 77	94.17 26	99.23 8	99.54 3	93.14 24	99.98 10	99.70 3	99.82 19	99.99 1

SMA-MVS		97.24 19	96.99 25	98.00 30	99.30 65	94.20 56	99.16 82	97.65 94	89.55 147	99.22 10	99.52 9	90.34 51	99.99 5	98.32 38	99.83 15	99.82 34
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
DVP-MVS		98.07 7	98.00 6	98.29 18	99.66 15	95.20 29	99.72 13	97.47 135	93.95 31	99.07 11	99.46 11	93.18 22	99.97 23	99.64 6	99.82 19	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									93.01 53	99.07 11	99.46 11	94.66 14	99.97 23	99.25 15	99.82 19	99.95 15

TSAR-MVS + MP.		97.44 16	97.46 13	97.39 52	99.12 78	93.49 71	98.52 159	97.50 130	94.46 23	98.99 13	98.64 101	91.58 30	99.08 144	98.49 30	99.83 15	99.60 78
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
PS-MVSNAJ		96.87 35	96.40 41	98.29 18	97.35 137	97.29 5	99.03 104	97.11 174	95.83 10	98.97 14	99.14 45	82.48 181	99.60 96	98.60 25	99.08 86	98.00 188

旧先验2							98.67 142		85.75 238	98.96 15			98.97 148	93.84 125

test_one_0601					99.59 31	94.89 34		97.64 95	93.14 52	98.93 16	99.45 16	93.45 18

xiu_mvs_v2_base		96.66 39	96.17 52	98.11 27	97.11 148	96.96 6	99.01 107	97.04 181	95.51 16	98.86 17	99.11 53	82.19 187	99.36 126	98.59 27	98.14 115	98.00 188

NCCC		98.12 5	98.11 3	98.13 23	99.76 6	94.46 49	99.81 5	97.88 51	96.54 5	98.84 18	99.46 11	92.55 27	99.98 10	98.25 40	99.93 1	99.94 18

SD-MVS		97.51 13	97.40 16	97.81 35	99.01 85	93.79 65	99.33 70	97.38 149	93.73 42	98.83 19	99.02 61	90.87 38	99.88 49	98.69 23	99.74 32	99.77 49
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
ETH3D-3000-0.1		97.29 17	97.01 24	98.12 25	99.18 75	94.97 32	99.47 45	97.52 124	89.85 135	98.79 20	99.46 11	90.41 49	99.69 80	98.78 21	99.67 42	99.70 62

xxxxxxxxxxxxxcwj		97.51 13	97.42 15	97.78 37	99.34 58	93.85 63	99.65 24	95.45 280	95.69 11	98.70 21	99.42 19	90.42 47	99.72 76	98.47 31	99.65 44	99.77 49

SF-MVS		97.22 22	96.92 26	98.12 25	99.11 79	94.88 35	99.44 53	97.45 138	89.60 143	98.70 21	99.42 19	90.42 47	99.72 76	98.47 31	99.65 44	99.77 49

ETH3 D test6400		97.67 11	97.33 18	98.69 9	99.69 9	96.43 11	99.63 26	97.73 75	91.05 101	98.66 23	99.53 7	90.59 42	99.71 78	99.32 12	99.80 27	99.91 22

DPE-MVS		98.11 6	98.00 6	98.44 15	99.50 47	95.39 20	99.29 73	97.72 77	94.50 22	98.64 24	99.54 3	93.32 19	99.97 23	99.58 9	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.77 9	98.18 2	96.53 101	99.54 40	90.14 143	99.41 59	97.70 82	95.46 17	98.60 25	99.19 34	95.71 4	99.49 109	98.15 42	99.85 13	99.95 15
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
9.14			96.87 28		99.34 58		99.50 42	97.49 132	89.41 150	98.59 26	99.43 18	89.78 56	99.69 80	98.69 23	99.62 51

APD-MVS		96.95 31	96.72 34	97.63 41	99.51 46	93.58 67	99.16 82	97.44 142	90.08 131	98.59 26	99.07 54	89.06 64	99.42 120	97.92 45	99.66 43	99.88 28
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
ETH3D cwj APD-0.16		96.94 33	96.58 38	98.01 29	98.62 102	94.73 44	99.13 94	97.38 149	88.44 180	98.53 28	99.39 21	89.66 60	99.69 80	98.43 33	99.61 55	99.61 77

testdata				95.26 144	98.20 111	87.28 211		97.60 105	85.21 245	98.48 29	99.15 43	88.15 79	98.72 158	90.29 165	99.45 66	99.78 42

testtj		97.23 21	97.05 22	97.75 38	99.75 7	93.34 73	99.16 82	97.74 71	91.28 98	98.40 30	99.29 24	89.95 54	99.98 10	98.20 41	99.70 39	99.94 18

TEST9					99.57 37	93.17 76	99.38 62	97.66 89	89.57 145	98.39 31	99.18 37	90.88 37	99.66 85

train_agg		97.20 23	97.08 21	97.57 45	99.57 37	93.17 76	99.38 62	97.66 89	90.18 126	98.39 31	99.18 37	90.94 35	99.66 85	98.58 28	99.85 13	99.88 28

test_8					99.55 39	93.07 80	99.37 65	97.64 95	90.18 126	98.36 33	99.19 34	90.94 35	99.64 91

CS-MVS-test		95.98 61	96.34 44	94.90 155	98.06 117	87.66 198	99.69 22	96.10 233	93.66 43	98.35 34	99.05 57	86.28 123	97.66 208	96.96 61	98.90 95	99.37 97

HPM-MVS++		97.72 10	97.59 11	98.14 22	99.53 45	94.76 42	99.19 77	97.75 69	95.66 13	98.21 35	99.29 24	91.10 33	99.99 5	97.68 48	99.87 9	99.68 66

DPM-MVS		97.86 8	97.25 19	99.68 1	98.25 109	99.10 1	99.76 11	97.78 66	96.61 4	98.15 36	99.53 7	93.62 17	100.00 1	91.79 150	99.80 27	99.94 18

test_part2					99.54 40	95.42 19				98.13 37

SteuartSystems-ACMMP		97.25 18	97.34 17	97.01 65	97.38 136	91.46 110	99.75 12	97.66 89	94.14 30	98.13 37	99.26 26	92.16 29	99.66 85	97.91 46	99.64 47	99.90 24
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 47	88.94 171	99.55 35	97.47 135	91.32 97	98.12 39

test_prior3		97.07 28	97.09 20	97.01 65	99.58 33	91.77 101	99.57 32	97.57 114	91.43 93	98.12 39	98.97 67	90.43 45	99.49 109	98.33 36	99.81 23	99.79 38

test_prior2							99.57 32		91.43 93	98.12 39	98.97 67	90.43 45		98.33 36	99.81 23

CS-MVS		95.75 73	96.19 48	94.40 173	97.88 121	86.22 237	99.66 23	96.12 232	92.69 62	98.07 42	98.89 83	87.09 100	97.59 214	96.71 64	98.62 107	99.39 96

PHI-MVS		96.65 40	96.46 40	97.21 59	99.34 58	91.77 101	99.70 16	98.05 41	86.48 230	98.05 43	99.20 33	89.33 62	99.96 30	98.38 34	99.62 51	99.90 24

MVSFormer		94.71 98	94.08 101	96.61 95	95.05 225	94.87 36	97.77 227	96.17 229	86.84 221	98.04 44	98.52 109	85.52 132	95.99 292	89.83 168	98.97 91	98.96 130

lupinMVS		96.32 51	95.94 60	97.44 48	95.05 225	94.87 36	99.86 2	96.50 208	93.82 40	98.04 44	98.77 89	85.52 132	98.09 179	96.98 60	98.97 91	99.37 97

APDe-MVS		97.53 12	97.47 12	97.70 39	99.58 33	93.63 66	99.56 34	97.52 124	93.59 46	98.01 46	99.12 48	90.80 40	99.55 99	99.26 14	99.79 29	99.93 21

ACMMP_NAP		96.59 41	96.18 49	97.81 35	98.82 95	93.55 68	98.88 120	97.59 109	90.66 111	97.98 47	99.14 45	86.59 114	100.00 1	96.47 72	99.46 64	99.89 27

agg_prior1		97.12 25	97.03 23	97.38 53	99.54 40	92.66 88	99.35 67	97.64 95	90.38 120	97.98 47	99.17 39	90.84 39	99.61 94	98.57 29	99.78 31	99.87 31

agg_prior					99.54 40	92.66 88		97.64 95		97.98 47			99.61 94

CDPH-MVS		96.56 42	96.18 49	97.70 39	99.59 31	93.92 61	99.13 94	97.44 142	89.02 160	97.90 50	99.22 31	88.90 67	99.49 109	94.63 113	99.79 29	99.68 66

EPNet		96.82 36	96.68 36	97.25 58	98.65 100	93.10 79	99.48 43	98.76 13	96.54 5	97.84 51	98.22 124	87.49 90	99.66 85	95.35 96	97.78 121	99.00 126
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		97.50 15	97.45 14	97.63 41	99.65 19	93.21 75	99.70 16	98.13 38	94.61 20	97.78 52	99.46 11	89.85 55	99.81 67	97.97 44	99.91 6	99.88 28

test12				97.83 34	99.33 64	94.45 50		97.55 117		97.56 53		88.60 70	99.50 108		99.71 38	99.55 82

xiu_mvs_v1_base_debu		94.73 95	93.98 103	96.99 68	95.19 212	95.24 24	98.62 148	96.50 208	92.99 55	97.52 54	98.83 86	72.37 258	99.15 138	97.03 56	96.74 137	96.58 218

xiu_mvs_v1_base		94.73 95	93.98 103	96.99 68	95.19 212	95.24 24	98.62 148	96.50 208	92.99 55	97.52 54	98.83 86	72.37 258	99.15 138	97.03 56	96.74 137	96.58 218

xiu_mvs_v1_base_debi		94.73 95	93.98 103	96.99 68	95.19 212	95.24 24	98.62 148	96.50 208	92.99 55	97.52 54	98.83 86	72.37 258	99.15 138	97.03 56	96.74 137	96.58 218

ZD-MVS					99.67 13	93.28 74		97.61 103	87.78 200	97.41 57	99.16 41	90.15 52	99.56 98	98.35 35	99.70 39

ETV-MVS		96.00 59	96.00 58	96.00 120	96.56 163	91.05 124	99.63 26	96.61 197	93.26 51	97.39 58	98.30 121	86.62 113	98.13 176	98.07 43	97.57 123	98.82 147

DeepPCF-MVS	93.56 1	96.55 43	97.84 10	92.68 219	98.71 99	78.11 336	99.70 16	97.71 81	98.18 1	97.36 59	99.76 1	90.37 50	99.94 37	99.27 13	99.54 61	99.99 1

DROMVSNet		95.09 86	95.17 79	94.84 158	95.42 205	88.17 186	99.48 43	95.92 246	91.47 91	97.34 60	98.36 118	82.77 174	97.41 225	97.24 53	98.58 108	98.94 135

CANet		97.00 29	96.49 39	98.55 11	98.86 94	96.10 15	99.83 4	97.52 124	95.90 9	97.21 61	98.90 81	82.66 178	99.93 40	98.71 22	98.80 101	99.63 74

CANet_DTU		94.31 107	93.35 116	97.20 60	97.03 152	94.71 45	98.62 148	95.54 275	95.61 14	97.21 61	98.47 115	71.88 263	99.84 60	88.38 188	97.46 128	97.04 212

VNet		95.08 87	94.26 93	97.55 46	98.07 116	93.88 62	98.68 140	98.73 16	90.33 122	97.16 63	97.43 151	79.19 210	99.53 102	96.91 63	91.85 198	99.24 109

region2R		96.30 52	96.17 52	96.70 91	99.70 8	90.31 139	99.46 50	97.66 89	90.55 115	97.07 64	99.07 54	86.85 106	99.97 23	95.43 94	99.74 32	99.81 35

原ACMM1				96.18 113	99.03 84	90.08 146		97.63 100	88.98 161	97.00 65	98.97 67	88.14 80	99.71 78	88.23 190	99.62 51	98.76 154

Regformer-1		96.97 30	96.80 32	97.47 47	99.46 52	93.11 78	98.89 118	97.94 47	92.89 59	96.90 66	99.02 61	89.78 56	99.53 102	97.06 55	99.26 80	99.75 53

HFP-MVS		96.42 48	96.26 47	96.90 77	99.69 9	90.96 127	99.47 45	97.81 61	90.54 116	96.88 67	99.05 57	87.57 87	99.96 30	95.65 87	99.72 34	99.78 42

#test#		96.48 45	96.34 44	96.90 77	99.69 9	90.96 127	99.53 40	97.81 61	90.94 105	96.88 67	99.05 57	87.57 87	99.96 30	95.87 84	99.72 34	99.78 42

Regformer-2		96.94 33	96.78 33	97.42 49	99.46 52	92.97 85	98.89 118	97.93 48	92.86 61	96.88 67	99.02 61	89.74 58	99.53 102	97.03 56	99.26 80	99.75 53

XVS		96.47 46	96.37 42	96.77 84	99.62 25	90.66 135	99.43 56	97.58 111	92.41 72	96.86 70	98.96 72	87.37 93	99.87 52	95.65 87	99.43 68	99.78 42

X-MVStestdata		90.69 186	88.66 207	96.77 84	99.62 25	90.66 135	99.43 56	97.58 111	92.41 72	96.86 70	29.59 380	87.37 93	99.87 52	95.65 87	99.43 68	99.78 42

1121		95.19 84	94.45 90	97.42 49	98.88 92	92.58 93	96.22 287	97.75 69	85.50 242	96.86 70	99.01 65	88.59 72	99.90 45	87.64 198	99.60 56	99.79 38

SR-MVS		96.13 56	96.16 54	96.07 118	99.42 54	89.04 166	98.59 154	97.33 153	90.44 118	96.84 73	99.12 48	86.75 108	99.41 122	97.47 49	99.44 67	99.76 52

TSAR-MVS + GP.		96.95 31	96.91 27	97.07 62	98.88 92	91.62 106	99.58 31	96.54 206	95.09 19	96.84 73	98.63 103	91.16 31	99.77 72	99.04 18	96.42 142	99.81 35

ACMMPR		96.28 53	96.14 56	96.73 88	99.68 12	90.47 137	99.47 45	97.80 63	90.54 116	96.83 75	99.03 60	86.51 118	99.95 34	95.65 87	99.72 34	99.75 53

PMMVS		93.62 125	93.90 109	92.79 215	96.79 158	81.40 310	98.85 121	96.81 191	91.25 99	96.82 76	98.15 128	77.02 224	98.13 176	93.15 138	96.30 146	98.83 146

PGM-MVS		95.85 67	95.65 72	96.45 104	99.50 47	89.77 157	98.22 193	98.90 12	89.19 155	96.74 77	98.95 74	85.91 130	99.92 41	93.94 122	99.46 64	99.66 70

jason		95.40 80	94.86 84	97.03 64	92.91 278	94.23 55	99.70 16	96.30 219	93.56 47	96.73 78	98.52 109	81.46 196	97.91 188	96.08 81	98.47 112	98.96 130
jason: jason.
新几何1				97.40 51	98.92 90	92.51 95		97.77 68	85.52 240	96.69 79	99.06 56	88.08 81	99.89 48	84.88 226	99.62 51	99.79 38

SR-MVS-dyc-post		95.75 73	95.86 63	95.41 139	99.22 71	87.26 214	98.40 177	97.21 162	89.63 141	96.67 80	98.97 67	86.73 110	99.36 126	96.62 66	99.31 76	99.60 78

RE-MVS-def			95.70 69		99.22 71	87.26 214	98.40 177	97.21 162	89.63 141	96.67 80	98.97 67	85.24 140		96.62 66	99.31 76	99.60 78

APD-MVS_3200maxsize		95.64 76	95.65 72	95.62 132	99.24 70	87.80 194	98.42 172	97.22 161	88.93 165	96.64 82	98.98 66	85.49 135	99.36 126	96.68 65	99.27 79	99.70 62

test1172		95.92 65	96.07 57	95.46 136	99.42 54	87.24 216	98.51 162	97.24 158	90.29 123	96.56 83	99.12 48	86.73 110	99.36 126	97.33 52	99.42 71	99.78 42

MG-MVS		97.24 19	96.83 31	98.47 14	99.79 5	95.71 17	99.07 98	99.06 9	94.45 24	96.42 84	98.70 98	88.81 68	99.74 75	95.35 96	99.86 12	99.97 7

h-mvs33		92.47 153	91.95 149	94.05 189	97.13 146	85.01 267	98.36 183	98.08 39	93.85 38	96.27 85	96.73 182	83.19 166	99.43 119	95.81 85	68.09 343	97.70 193

hse-mvs2		91.67 167	91.51 158	92.15 228	96.22 177	82.61 301	97.74 230	97.53 121	93.85 38	96.27 85	96.15 195	83.19 166	97.44 223	95.81 85	66.86 348	96.40 223

alignmvs		95.77 71	95.00 83	98.06 28	97.35 137	95.68 18	99.71 15	97.50 130	91.50 90	96.16 87	98.61 105	86.28 123	99.00 146	96.19 78	91.74 200	99.51 86

Regformer-3		96.50 44	96.36 43	96.91 76	99.34 58	91.72 104	98.71 133	97.90 50	92.48 67	96.00 88	98.95 74	88.60 70	99.52 105	96.44 73	98.83 98	99.49 88

CP-MVS		96.22 54	96.15 55	96.42 106	99.67 13	89.62 160	99.70 16	97.61 103	90.07 132	96.00 88	99.16 41	87.43 91	99.92 41	96.03 82	99.72 34	99.70 62

Regformer-4		96.45 47	96.33 46	96.81 83	99.34 58	91.44 111	98.71 133	97.88 51	92.43 68	95.97 90	98.95 74	88.42 74	99.51 106	96.40 74	98.83 98	99.49 88

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 9	99.70 16	97.98 46	97.18 2	95.96 91	99.33 23	92.62 26	100.00 1	98.99 19	99.93 1	99.98 6

diffmvs		94.59 103	94.19 96	95.81 126	95.54 201	90.69 133	98.70 137	95.68 267	91.61 87	95.96 91	97.81 132	80.11 202	98.06 182	96.52 71	95.76 156	98.67 159

GST-MVS		95.97 62	95.66 70	96.90 77	99.49 50	91.22 113	99.45 52	97.48 133	89.69 139	95.89 93	98.72 95	86.37 122	99.95 34	94.62 114	99.22 83	99.52 84

DeepC-MVS_fast	93.52 2	97.16 24	96.84 30	98.13 23	99.61 27	94.45 50	98.85 121	97.64 95	96.51 7	95.88 94	99.39 21	87.35 97	99.99 5	96.61 68	99.69 41	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test222					98.32 108	91.21 114	98.08 209	97.58 111	83.74 269	95.87 95	99.02 61	86.74 109			99.64 47	99.81 35

ZNCC-MVS		96.09 57	95.81 66	96.95 75	99.42 54	91.19 115	99.55 35	97.53 121	89.72 138	95.86 96	98.94 79	86.59 114	99.97 23	95.13 100	99.56 59	99.68 66

canonicalmvs		95.02 88	93.96 106	98.20 20	97.53 134	95.92 16	98.71 133	96.19 228	91.78 85	95.86 96	98.49 113	79.53 207	99.03 145	96.12 79	91.42 206	99.66 70

abl_6		94.63 101	94.48 89	95.09 147	98.61 103	86.96 219	98.06 212	96.97 187	89.31 151	95.86 96	98.56 107	79.82 203	99.64 91	94.53 116	98.65 106	98.66 162

dcpmvs_2		95.67 75	96.18 49	94.12 185	98.82 95	84.22 277	97.37 243	95.45 280	90.70 110	95.77 99	98.63 103	90.47 44	98.68 160	99.20 17	99.22 83	99.45 92

Effi-MVS+		93.87 116	93.15 122	96.02 119	95.79 192	90.76 131	96.70 273	95.78 260	86.98 218	95.71 100	97.17 164	79.58 205	98.01 186	94.57 115	96.09 150	99.31 103

HPM-MVS_fast		94.89 89	94.62 86	95.70 130	99.11 79	88.44 184	99.14 91	97.11 174	85.82 237	95.69 101	98.47 115	83.46 159	99.32 132	93.16 137	99.63 50	99.35 99

HY-MVS	88.56 7	95.29 81	94.23 94	98.48 13	97.72 124	96.41 12	94.03 318	98.74 14	92.42 71	95.65 102	94.76 219	86.52 117	99.49 109	95.29 98	92.97 179	99.53 83

CHOSEN 280x420		96.80 37	96.85 29	96.66 94	97.85 122	94.42 52	94.76 310	98.36 24	92.50 66	95.62 103	97.52 147	97.92 1	97.38 226	98.31 39	98.80 101	98.20 184

MP-MVS		96.00 59	95.82 64	96.54 100	99.47 51	90.13 145	99.36 66	97.41 146	90.64 114	95.49 104	98.95 74	85.51 134	99.98 10	96.00 83	99.59 58	99.52 84
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS		95.41 79	95.22 78	95.99 121	99.29 66	89.14 164	99.17 81	97.09 178	87.28 213	95.40 105	98.48 114	84.93 142	99.38 124	95.64 91	99.65 44	99.47 91
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 134	92.62 134	95.34 141	96.27 175	88.53 183	95.88 297	96.97 187	90.90 106	95.37 106	97.07 168	82.38 184	99.10 143	83.91 241	94.86 165	98.38 173

sss		94.85 91	93.94 107	97.58 43	96.43 168	94.09 60	98.93 113	99.16 8	89.50 148	95.27 107	97.85 130	81.50 194	99.65 89	92.79 144	94.02 171	98.99 127

WTY-MVS		95.97 62	95.11 81	98.54 12	97.62 128	96.65 8	99.44 53	98.74 14	92.25 76	95.21 108	98.46 117	86.56 116	99.46 116	95.00 104	92.69 183	99.50 87

DELS-MVS		97.12 25	96.60 37	98.68 10	98.03 118	96.57 10	99.84 3	97.84 55	96.36 8	95.20 109	98.24 123	88.17 78	99.83 62	96.11 80	99.60 56	99.64 72
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		96.69 38	96.69 35	96.72 90	98.58 104	91.00 126	99.14 91	99.45 1	93.86 37	95.15 110	98.73 93	88.48 73	99.76 73	97.23 54	99.56 59	99.40 95

MVS_Test		93.67 123	92.67 133	96.69 92	96.72 160	92.66 88	97.22 252	96.03 236	87.69 206	95.12 111	94.03 228	81.55 193	98.28 172	89.17 183	96.46 140	99.14 116

MVS_111021_LR		95.78 70	95.94 60	95.28 143	98.19 113	87.69 195	98.80 126	99.26 7	93.39 48	95.04 112	98.69 99	84.09 151	99.76 73	96.96 61	99.06 87	98.38 173

CostFormer		92.89 143	92.48 137	94.12 185	94.99 227	85.89 248	92.89 327	97.00 186	86.98 218	95.00 113	90.78 291	90.05 53	97.51 219	92.92 141	91.73 201	98.96 130

mPP-MVS		95.90 66	95.75 68	96.38 108	99.58 33	89.41 163	99.26 74	97.41 146	90.66 111	94.82 114	98.95 74	86.15 126	99.98 10	95.24 99	99.64 47	99.74 56

EI-MVSNet-Vis-set		95.76 72	95.63 74	96.17 115	99.14 77	90.33 138	98.49 166	97.82 58	91.92 82	94.75 115	98.88 84	87.06 102	99.48 114	95.40 95	97.17 134	98.70 157

LFMVS		92.23 158	90.84 171	96.42 106	98.24 110	91.08 123	98.24 192	96.22 225	83.39 276	94.74 116	98.31 120	61.12 324	98.85 150	94.45 117	92.82 180	99.32 102

tpmrst		92.78 144	92.16 143	94.65 165	96.27 175	87.45 205	91.83 335	97.10 177	89.10 159	94.68 117	90.69 295	88.22 77	97.73 206	89.78 171	91.80 199	98.77 153

test_yl		95.27 82	94.60 87	97.28 56	98.53 105	92.98 83	99.05 101	98.70 17	86.76 224	94.65 118	97.74 137	87.78 84	99.44 117	95.57 92	92.61 184	99.44 93

DCV-MVSNet		95.27 82	94.60 87	97.28 56	98.53 105	92.98 83	99.05 101	98.70 17	86.76 224	94.65 118	97.74 137	87.78 84	99.44 117	95.57 92	92.61 184	99.44 93

DP-MVS Recon		95.85 67	95.15 80	97.95 31	99.87 2	94.38 53	99.60 29	97.48 133	86.58 227	94.42 120	99.13 47	87.36 96	99.98 10	93.64 129	98.33 114	99.48 90

zzz-MVS		96.21 55	95.96 59	96.96 73	99.29 66	91.19 115	98.69 138	97.45 138	92.58 63	94.39 121	99.24 29	86.43 120	99.99 5	96.22 76	99.40 72	99.71 60

MTAPA		96.09 57	95.80 67	96.96 73	99.29 66	91.19 115	97.23 251	97.45 138	92.58 63	94.39 121	99.24 29	86.43 120	99.99 5	96.22 76	99.40 72	99.71 60

CPTT-MVS		94.60 102	94.43 91	95.09 147	99.66 15	86.85 221	99.44 53	97.47 135	83.22 278	94.34 123	98.96 72	82.50 179	99.55 99	94.81 107	99.50 62	98.88 140

PVSNet_BlendedMVS		93.36 132	93.20 120	93.84 196	98.77 97	91.61 107	99.47 45	98.04 42	91.44 92	94.21 124	92.63 260	83.50 157	99.87 52	97.41 50	83.37 257	90.05 322

PVSNet_Blended		95.94 64	95.66 70	96.75 86	98.77 97	91.61 107	99.88 1	98.04 42	93.64 45	94.21 124	97.76 135	83.50 157	99.87 52	97.41 50	97.75 122	98.79 150

EI-MVSNet-UG-set		95.43 77	95.29 76	95.86 125	99.07 83	89.87 154	98.43 171	97.80 63	91.78 85	94.11 126	98.77 89	86.25 125	99.48 114	94.95 106	96.45 141	98.22 182

EIA-MVS		95.11 85	95.27 77	94.64 166	96.34 173	86.51 225	99.59 30	96.62 196	92.51 65	94.08 127	98.64 101	86.05 127	98.24 173	95.07 102	98.50 111	99.18 114

MAR-MVS		94.43 105	94.09 100	95.45 137	99.10 81	87.47 204	98.39 181	97.79 65	88.37 183	94.02 128	99.17 39	78.64 216	99.91 43	92.48 145	98.85 97	98.96 130
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		96.35 49	95.94 60	97.58 43	94.10 247	95.25 23	98.93 113	98.17 33	94.26 25	93.94 129	98.72 95	89.68 59	97.88 191	96.36 75	99.29 78	99.62 76

GG-mvs-BLEND				96.98 71	96.53 164	94.81 41	87.20 351	97.74 71		93.91 130	96.40 190	96.56 2	96.94 240	95.08 101	98.95 94	99.20 113

API-MVS		94.78 93	94.18 98	96.59 96	99.21 73	90.06 150	98.80 126	97.78 66	83.59 273	93.85 131	99.21 32	83.79 154	99.97 23	92.37 146	99.00 90	99.74 56

tpm2		91.77 165	91.09 164	93.82 197	94.83 234	85.56 257	92.51 332	97.16 169	84.00 265	93.83 132	90.66 297	87.54 89	97.17 230	87.73 197	91.55 204	98.72 155

PAPR		96.35 49	95.82 64	97.94 32	99.63 21	94.19 57	99.42 58	97.55 117	92.43 68	93.82 133	99.12 48	87.30 98	99.91 43	94.02 120	99.06 87	99.74 56

PVSNet	87.13 12	93.69 120	92.83 130	96.28 111	97.99 119	90.22 142	99.38 62	98.93 11	91.42 95	93.66 134	97.68 140	71.29 270	99.64 91	87.94 195	97.20 131	98.98 128

baseline		93.91 114	93.30 117	95.72 129	95.10 222	90.07 147	97.48 239	95.91 251	91.03 102	93.54 135	97.68 140	79.58 205	98.02 185	94.27 119	95.14 162	99.08 122

test2506		94.80 92	94.21 95	96.58 97	96.41 169	92.18 99	98.01 214	98.96 10	90.82 108	93.46 136	97.28 154	85.92 128	98.45 165	89.82 170	97.19 132	99.12 118

VDD-MVS		91.24 177	90.18 181	94.45 172	97.08 149	85.84 251	98.40 177	96.10 233	86.99 215	93.36 137	98.16 127	54.27 345	99.20 135	96.59 69	90.63 214	98.31 179

VDDNet		90.08 198	88.54 213	94.69 164	94.41 242	87.68 196	98.21 195	96.40 213	76.21 336	93.33 138	97.75 136	54.93 343	98.77 153	94.71 111	90.96 209	97.61 198

thisisatest0515		94.75 94	94.19 96	96.43 105	96.13 187	92.64 92	99.47 45	97.60 105	87.55 209	93.17 139	97.59 145	94.71 13	98.42 166	88.28 189	93.20 176	98.24 181

MP-MVS-pluss		95.80 69	95.30 75	97.29 55	98.95 89	92.66 88	98.59 154	97.14 170	88.95 163	93.12 140	99.25 27	85.62 131	99.94 37	96.56 70	99.48 63	99.28 106
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 118	91.38 339		87.45 211	93.08 141		86.67 112		87.02 202		98.95 134

EPNet_dtu		92.28 156	92.15 144	92.70 218	97.29 139	84.84 269	98.64 146	97.82 58	92.91 58	93.02 142	97.02 170	85.48 137	95.70 306	72.25 326	94.89 164	97.55 199
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		90.00 199	87.71 221	96.89 82	96.15 182	94.69 46	85.15 357	97.74 71	68.32 359	92.97 143	60.16 369	96.10 3	96.84 242	93.89 123	98.87 96	99.14 116

casdiffmvs		93.98 112	93.43 115	95.61 133	95.07 224	89.86 155	98.80 126	95.84 259	90.98 104	92.74 144	97.66 142	79.71 204	98.10 178	94.72 110	95.37 161	98.87 142

114514_t		94.06 109	93.05 124	97.06 63	99.08 82	92.26 97	98.97 111	97.01 185	82.58 291	92.57 145	98.22 124	80.68 200	99.30 133	89.34 179	99.02 89	99.63 74

OMC-MVS		93.90 115	93.62 113	94.73 163	98.63 101	87.00 218	98.04 213	96.56 203	92.19 77	92.46 146	98.73 93	79.49 208	99.14 141	92.16 148	94.34 169	98.03 187

PAPM_NR		95.43 77	95.05 82	96.57 99	99.42 54	90.14 143	98.58 156	97.51 127	90.65 113	92.44 147	98.90 81	87.77 86	99.90 45	90.88 158	99.32 75	99.68 66

UGNet		91.91 164	90.85 170	95.10 146	97.06 150	88.69 179	98.01 214	98.24 29	92.41 72	92.39 148	93.61 241	60.52 325	99.68 83	88.14 191	97.25 130	96.92 214
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
MDTV_nov1_ep13			90.47 180		96.14 184	88.55 181	91.34 340	97.51 127	89.58 144	92.24 149	90.50 308	86.99 105	97.61 213	77.64 289	92.34 189

FE-MVS		91.38 173	90.16 182	95.05 151	96.46 167	87.53 202	89.69 349	97.84 55	82.97 283	92.18 150	92.00 269	84.07 152	98.93 149	80.71 269	95.52 160	98.68 158

Vis-MVSNet		92.64 147	91.85 150	95.03 152	95.12 218	88.23 185	98.48 167	96.81 191	91.61 87	92.16 151	97.22 160	71.58 268	98.00 187	85.85 219	97.81 118	98.88 140
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 159	91.08 165	95.64 131	96.05 188	88.98 168	91.60 337	97.25 155	86.99 215	91.84 152	92.12 263	83.03 169	99.00 146	86.91 206	93.91 172	98.93 136

TESTMET0.1,1		93.82 117	93.26 119	95.49 135	95.21 211	90.25 140	99.15 88	97.54 120	89.18 156	91.79 153	94.87 216	89.13 63	97.63 211	86.21 212	96.29 147	98.60 163

thisisatest0530		94.00 111	93.52 114	95.43 138	95.76 194	90.02 152	98.99 109	97.60 105	86.58 227	91.74 154	97.36 153	94.78 12	98.34 168	86.37 211	92.48 187	97.94 190

AUN-MVS		90.17 195	89.50 188	92.19 226	96.21 178	82.67 299	97.76 229	97.53 121	88.05 192	91.67 155	96.15 195	83.10 168	97.47 220	88.11 192	66.91 347	96.43 222

EPMVS		92.59 150	91.59 156	95.59 134	97.22 141	90.03 151	91.78 336	98.04 42	90.42 119	91.66 156	90.65 298	86.49 119	97.46 221	81.78 262	96.31 145	99.28 106

test-LLR		93.11 141	92.68 132	94.40 173	94.94 230	87.27 212	99.15 88	97.25 155	90.21 124	91.57 157	94.04 226	84.89 143	97.58 215	85.94 216	96.13 148	98.36 176

test-mter		93.27 136	92.89 129	94.40 173	94.94 230	87.27 212	99.15 88	97.25 155	88.95 163	91.57 157	94.04 226	88.03 82	97.58 215	85.94 216	96.13 148	98.36 176

JIA-IIPM		85.97 265	84.85 265	89.33 295	93.23 273	73.68 349	85.05 358	97.13 172	69.62 355	91.56 159	68.03 367	88.03 82	96.96 238	77.89 288	93.12 177	97.34 202

PVSNet_Blended_VisFu		94.67 99	94.11 99	96.34 110	97.14 145	91.10 121	99.32 71	97.43 144	92.10 81	91.53 160	96.38 193	83.29 163	99.68 83	93.42 134	96.37 143	98.25 180

CHOSEN 1792x2688		94.35 106	93.82 110	95.95 123	97.40 135	88.74 178	98.41 174	98.27 26	92.18 78	91.43 161	96.40 190	78.88 211	99.81 67	93.59 130	97.81 118	99.30 104

ACMMP		94.67 99	94.30 92	95.79 127	99.25 69	88.13 188	98.41 174	98.67 20	90.38 120	91.43 161	98.72 95	82.22 186	99.95 34	93.83 126	95.76 156	99.29 105
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
ECVR-MVS		92.29 155	91.33 160	95.15 145	96.41 169	87.84 193	98.10 206	94.84 304	90.82 108	91.42 163	97.28 154	65.61 306	98.49 164	90.33 164	97.19 132	99.12 118

EPP-MVSNet		93.75 119	93.67 112	94.01 191	95.86 191	85.70 253	98.67 142	97.66 89	84.46 259	91.36 164	97.18 163	91.16 31	97.79 197	92.93 140	93.75 173	98.53 165

PLC	91.07 3	94.23 108	94.01 102	94.87 156	99.17 76	87.49 203	99.25 75	96.55 204	88.43 181	91.26 165	98.21 126	85.92 128	99.86 57	89.77 172	97.57 123	97.24 205
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 122	93.29 118	94.87 156	97.57 132	88.04 190	98.18 197	98.47 22	87.57 208	91.24 166	95.05 213	85.49 135	97.46 221	93.22 136	92.82 180	99.10 120

thres200		93.69 120	92.59 135	96.97 72	97.76 123	94.74 43	99.35 67	99.36 2	89.23 154	91.21 167	96.97 172	83.42 160	98.77 153	85.08 222	90.96 209	97.39 201

mvs-test1		91.57 168	92.20 142	89.70 285	95.15 216	74.34 346	99.51 41	95.40 285	91.92 82	91.02 168	97.25 157	74.27 241	98.08 181	89.45 175	95.83 155	96.67 215

test1111		92.12 160	91.19 163	94.94 154	96.15 182	87.36 208	98.12 202	94.84 304	90.85 107	90.97 169	97.26 156	65.60 307	98.37 167	89.74 173	97.14 135	99.07 124

CDS-MVSNet		93.47 127	93.04 125	94.76 160	94.75 236	89.45 162	98.82 124	97.03 183	87.91 197	90.97 169	96.48 188	89.06 64	96.36 269	89.50 174	92.81 182	98.49 167
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 129	92.27 140	96.90 77	97.68 126	94.84 38	99.18 79	99.36 2	88.45 177	90.79 171	96.90 175	83.31 161	98.75 155	84.11 237	90.69 211	97.12 207

thres400		93.39 131	92.27 140	96.73 88	97.68 126	94.84 38	99.18 79	99.36 2	88.45 177	90.79 171	96.90 175	83.31 161	98.75 155	84.11 237	90.69 211	96.61 216

CR-MVSNet		88.83 219	87.38 226	93.16 209	93.47 266	86.24 235	84.97 359	94.20 322	88.92 166	90.76 173	86.88 342	84.43 147	94.82 326	70.64 330	92.17 194	98.41 170

RPMNet		85.07 278	81.88 295	94.64 166	93.47 266	86.24 235	84.97 359	97.21 162	64.85 365	90.76 173	78.80 363	80.95 199	99.27 134	53.76 366	92.17 194	98.41 170

PatchmatchNet		92.05 163	91.04 166	95.06 149	96.17 181	89.04 166	91.26 341	97.26 154	89.56 146	90.64 175	90.56 304	88.35 76	97.11 232	79.53 275	96.07 152	99.03 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		93.30 134	93.01 127	94.17 183	95.57 199	86.47 227	98.51 162	97.60 105	85.99 235	90.55 176	97.19 162	94.80 11	98.31 169	85.06 223	91.86 197	97.74 192

PatchT		85.44 275	83.19 282	92.22 224	93.13 275	83.00 291	83.80 365	96.37 215	70.62 350	90.55 176	79.63 362	84.81 145	94.87 324	58.18 363	91.59 203	98.79 150

tpm		89.67 204	88.95 200	91.82 234	92.54 281	81.43 309	92.95 326	95.92 246	87.81 199	90.50 178	89.44 323	84.99 141	95.65 307	83.67 244	82.71 263	98.38 173

thres100view900		93.34 133	92.15 144	96.90 77	97.62 128	94.84 38	99.06 100	99.36 2	87.96 195	90.47 179	96.78 180	83.29 163	98.75 155	84.11 237	90.69 211	97.12 207

thres600view7		93.18 139	92.00 147	96.75 86	97.62 128	94.92 33	99.07 98	99.36 2	87.96 195	90.47 179	96.78 180	83.29 163	98.71 159	82.93 251	90.47 215	96.61 216

AdaColmap		93.82 117	93.06 123	96.10 117	99.88 1	89.07 165	98.33 185	97.55 117	86.81 223	90.39 181	98.65 100	75.09 231	99.98 10	93.32 135	97.53 126	99.26 108

XVG-OURS-SEG-HR		90.95 180	90.66 177	91.83 233	95.18 215	81.14 317	95.92 294	95.92 246	88.40 182	90.33 182	97.85 130	70.66 273	99.38 124	92.83 142	88.83 220	94.98 230

IS-MVSNet		93.00 142	92.51 136	94.49 169	96.14 184	87.36 208	98.31 188	95.70 265	88.58 173	90.17 183	97.50 148	83.02 170	97.22 229	87.06 201	96.07 152	98.90 139

CSCG		94.87 90	94.71 85	95.36 140	99.54 40	86.49 226	99.34 69	98.15 36	82.71 289	90.15 184	99.25 27	89.48 61	99.86 57	94.97 105	98.82 100	99.72 59

SCA		90.64 187	89.25 195	94.83 159	94.95 229	88.83 174	96.26 284	97.21 162	90.06 133	90.03 185	90.62 300	66.61 298	96.81 244	83.16 247	94.36 168	98.84 143

XVG-OURS		90.83 182	90.49 179	91.86 232	95.23 210	81.25 314	95.79 302	95.92 246	88.96 162	90.02 186	98.03 129	71.60 267	99.35 130	91.06 155	87.78 224	94.98 230

ADS-MVSNet2		87.62 242	86.88 234	89.86 280	96.21 178	79.14 327	87.15 352	92.99 337	83.01 281	89.91 187	87.27 338	78.87 212	92.80 346	74.20 314	92.27 191	97.64 194

ADS-MVSNet		88.99 211	87.30 227	94.07 187	96.21 178	87.56 201	87.15 352	96.78 193	83.01 281	89.91 187	87.27 338	78.87 212	97.01 237	74.20 314	92.27 191	97.64 194

ab-mvs		91.05 179	89.17 196	96.69 92	95.96 189	91.72 104	92.62 331	97.23 160	85.61 239	89.74 189	93.89 234	68.55 282	99.42 120	91.09 154	87.84 223	98.92 138

TAMVS		92.62 148	92.09 146	94.20 182	94.10 247	87.68 196	98.41 174	96.97 187	87.53 210	89.74 189	96.04 199	84.77 146	96.49 262	88.97 185	92.31 190	98.42 169

Vis-MVSNet (Re-imp)		93.26 137	93.00 128	94.06 188	96.14 184	86.71 224	98.68 140	96.70 194	88.30 185	89.71 191	97.64 143	85.43 138	96.39 267	88.06 193	96.32 144	99.08 122

CNLPA		93.64 124	92.74 131	96.36 109	98.96 88	90.01 153	99.19 77	95.89 254	86.22 233	89.40 192	98.85 85	80.66 201	99.84 60	88.57 186	96.92 136	99.24 109

Anonymous202405211		88.84 217	87.03 232	94.27 179	98.14 115	84.18 278	98.44 170	95.58 273	76.79 335	89.34 193	96.88 177	53.42 348	99.54 101	87.53 200	87.12 227	99.09 121

Fast-Effi-MVS+		91.72 166	90.79 174	94.49 169	95.89 190	87.40 207	99.54 39	95.70 265	85.01 252	89.28 194	95.68 203	77.75 220	97.57 218	83.22 246	95.06 163	98.51 166

PatchMatch-RL		91.47 170	90.54 178	94.26 180	98.20 111	86.36 232	96.94 261	97.14 170	87.75 202	88.98 195	95.75 202	71.80 265	99.40 123	80.92 267	97.39 129	97.02 213

dp		90.16 196	88.83 203	94.14 184	96.38 172	86.42 228	91.57 338	97.06 180	84.76 256	88.81 196	90.19 316	84.29 149	97.43 224	75.05 307	91.35 208	98.56 164

DeepC-MVS	91.02 4	94.56 104	93.92 108	96.46 103	97.16 143	90.76 131	98.39 181	97.11 174	93.92 33	88.66 197	98.33 119	78.14 218	99.85 59	95.02 103	98.57 109	98.78 152
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		92.61 149	91.28 161	96.58 97	97.05 151	94.63 47	97.72 231	96.20 226	89.82 136	88.56 198	96.85 178	86.85 106	97.82 195	88.42 187	80.10 275	97.30 203

Anonymous20240529		87.66 241	85.58 254	93.92 193	97.59 131	85.01 267	98.13 200	97.13 172	66.69 363	88.47 199	96.01 200	55.09 342	99.51 106	87.00 203	84.12 248	97.23 206

CVMVSNet		90.30 191	90.91 169	88.46 308	94.32 243	73.58 350	97.61 236	97.59 109	90.16 129	88.43 200	97.10 166	76.83 225	92.86 343	82.64 253	93.54 175	98.93 136

TR-MVS		90.77 183	89.44 190	94.76 160	96.31 174	88.02 191	97.92 218	95.96 240	85.52 240	88.22 201	97.23 159	66.80 297	98.09 179	84.58 230	92.38 188	98.17 185

F-COLMAP		92.07 162	91.75 154	93.02 211	98.16 114	82.89 295	98.79 130	95.97 238	86.54 229	87.92 202	97.80 133	78.69 215	99.65 89	85.97 214	95.93 154	96.53 221

BH-RMVSNet		91.25 176	89.99 183	95.03 152	96.75 159	88.55 181	98.65 144	94.95 301	87.74 203	87.74 203	97.80 133	68.27 285	98.14 175	80.53 272	97.49 127	98.41 170

Effi-MVS+-dtu		89.97 201	90.68 176	87.81 312	95.15 216	71.98 356	97.87 222	95.40 285	91.92 82	87.57 204	91.44 279	74.27 241	96.84 242	89.45 175	93.10 178	94.60 232

HQP-NCC					93.95 251		99.16 82		93.92 33	87.57 204

ACMP_Plane					93.95 251		99.16 82		93.92 33	87.57 204

HQP4-MVS										87.57 204			97.77 199			92.72 239

HQP-MVS		91.50 169	91.23 162	92.29 223	93.95 251	86.39 230	99.16 82	96.37 215	93.92 33	87.57 204	96.67 184	73.34 248	97.77 199	93.82 127	86.29 229	92.72 239

TAPA-MVS	87.50 9	90.35 189	89.05 198	94.25 181	98.48 107	85.17 264	98.42 172	96.58 202	82.44 295	87.24 209	98.53 108	82.77 174	98.84 151	59.09 361	97.88 117	98.72 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 188	89.56 187	93.72 201	95.10 222	85.43 258	99.41 59	94.94 302	83.96 267	87.21 210	96.83 179	74.37 239	97.05 236	80.50 273	93.73 174	98.67 159

HQP_MVS		91.26 174	90.95 168	92.16 227	93.84 258	86.07 244	99.02 105	96.30 219	93.38 49	86.99 211	96.52 186	72.92 253	97.75 204	93.46 132	86.17 232	92.67 241

plane_prior3						85.91 247			93.65 44	86.99 211

iter_conf_final		93.22 138	93.04 125	93.76 198	97.03 152	92.22 98	99.05 101	93.31 335	92.11 80	86.93 213	95.42 208	95.01 10	96.59 252	93.98 121	84.48 244	92.46 244

GA-MVS		90.10 197	88.69 206	94.33 177	92.44 282	87.97 192	99.08 97	96.26 223	89.65 140	86.92 214	93.11 253	68.09 286	96.96 238	82.54 255	90.15 216	98.05 186

1112_ss		92.71 145	91.55 157	96.20 112	95.56 200	91.12 119	98.48 167	94.69 310	88.29 186	86.89 215	98.50 111	87.02 103	98.66 161	84.75 227	89.77 218	98.81 148

MVS_0304		84.13 292	82.66 291	88.52 306	93.07 276	80.15 322	95.81 301	98.21 31	79.27 320	86.85 216	86.40 345	41.33 367	94.69 329	76.36 299	86.69 228	90.73 306

Test_1112_low_res		92.27 157	90.97 167	96.18 113	95.53 202	91.10 121	98.47 169	94.66 311	88.28 187	86.83 217	93.50 245	87.00 104	98.65 162	84.69 228	89.74 219	98.80 149

cascas		90.93 181	89.33 194	95.76 128	95.69 196	93.03 82	98.99 109	96.59 199	80.49 315	86.79 218	94.45 223	65.23 309	98.60 163	93.52 131	92.18 193	95.66 229

iter_conf05		93.48 126	93.18 121	94.39 176	97.15 144	94.17 58	99.30 72	92.97 338	92.38 75	86.70 219	95.42 208	95.67 5	96.59 252	94.67 112	84.32 247	92.39 245

baseline2		94.04 110	93.80 111	94.74 162	93.07 276	90.25 140	98.12 202	98.16 35	89.86 134	86.53 220	96.95 173	95.56 6	98.05 183	91.44 152	94.53 166	95.93 227

OPM-MVS		89.76 203	89.15 197	91.57 241	90.53 308	85.58 256	98.11 205	95.93 245	92.88 60	86.05 221	96.47 189	67.06 296	97.87 192	89.29 182	86.08 234	91.26 290
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 210	87.66 222	93.45 204	92.56 280	91.02 125	97.97 217	98.32 25	86.92 220	86.03 222	92.01 267	68.84 281	97.10 234	90.92 157	75.34 296	92.23 252

tpm cat1		88.89 215	87.27 228	93.76 198	95.79 192	85.32 261	90.76 345	97.09 178	76.14 337	85.72 223	88.59 329	82.92 171	98.04 184	76.96 293	91.43 205	97.90 191

IB-MVS	89.43 6	92.12 160	90.83 173	95.98 122	95.40 207	90.78 130	99.81 5	98.06 40	91.23 100	85.63 224	93.66 240	90.63 41	98.78 152	91.22 153	71.85 333	98.36 176
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
EI-MVSNet		89.87 202	89.38 193	91.36 244	94.32 243	85.87 249	97.61 236	96.59 199	85.10 247	85.51 225	97.10 166	81.30 198	96.56 255	83.85 243	83.03 260	91.64 269

MVSTER		92.71 145	92.32 138	93.86 195	97.29 139	92.95 86	99.01 107	96.59 199	90.09 130	85.51 225	94.00 230	94.61 16	96.56 255	90.77 161	83.03 260	92.08 260

RPSCF		85.33 276	85.55 255	84.67 332	94.63 239	62.28 368	93.73 320	93.76 327	74.38 343	85.23 227	97.06 169	64.09 312	98.31 169	80.98 265	86.08 234	93.41 238

BH-w/o		92.32 154	91.79 152	93.91 194	96.85 155	86.18 239	99.11 96	95.74 263	88.13 190	84.81 228	97.00 171	77.26 223	97.91 188	89.16 184	98.03 116	97.64 194

mvsmamba		89.99 200	89.42 191	91.69 240	90.64 307	86.34 233	98.40 177	92.27 346	91.01 103	84.80 229	94.93 214	76.12 226	96.51 259	92.81 143	83.84 250	92.21 254

CLD-MVS		91.06 178	90.71 175	92.10 229	94.05 250	86.10 242	99.55 35	96.29 222	94.16 28	84.70 230	97.17 164	69.62 277	97.82 195	94.74 109	86.08 234	92.39 245
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 209	87.76 219	93.35 205	97.19 142	84.75 271	90.58 347	97.36 151	81.99 300	84.56 231	89.31 326	83.98 153	98.17 174	74.85 310	90.00 217	97.12 207

nrg030		90.23 192	88.87 201	94.32 178	91.53 296	93.54 69	98.79 130	95.89 254	88.12 191	84.55 232	94.61 221	78.80 214	96.88 241	92.35 147	75.21 297	92.53 243

VPNet		88.30 229	86.57 239	93.49 203	91.95 289	91.35 112	98.18 197	97.20 166	88.61 171	84.52 233	94.89 215	62.21 319	96.76 247	89.34 179	72.26 330	92.36 247

MVS		93.92 113	92.28 139	98.83 6	95.69 196	96.82 7	96.22 287	98.17 33	84.89 254	84.34 234	98.61 105	79.32 209	99.83 62	93.88 124	99.43 68	99.86 32

mvs_anonymous		92.50 152	91.65 155	95.06 149	96.60 162	89.64 159	97.06 257	96.44 212	86.64 226	84.14 235	93.93 232	82.49 180	96.17 285	91.47 151	96.08 151	99.35 99

Fast-Effi-MVS+-dtu		88.84 217	88.59 210	89.58 289	93.44 269	78.18 334	98.65 144	94.62 312	88.46 176	84.12 236	95.37 211	68.91 279	96.52 258	82.06 259	91.70 202	94.06 233

LS3D		90.19 194	88.72 205	94.59 168	98.97 86	86.33 234	96.90 263	96.60 198	74.96 340	84.06 237	98.74 92	75.78 228	99.83 62	74.93 308	97.57 123	97.62 197

ACMM	86.95 13	88.77 222	88.22 217	90.43 265	93.61 263	81.34 312	98.50 164	95.92 246	87.88 198	83.85 238	95.20 212	67.20 294	97.89 190	86.90 207	84.90 240	92.06 261
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 171	90.84 171	93.33 206	96.51 166	84.83 270	98.84 123	95.50 277	86.44 232	83.50 239	96.70 183	75.49 230	97.77 199	86.78 209	97.81 118	97.40 200

FIs		90.70 185	89.87 184	93.18 208	92.29 283	91.12 119	98.17 199	98.25 27	89.11 158	83.44 240	94.82 218	82.26 185	96.17 285	87.76 196	82.76 262	92.25 250

bld_raw_dy_0_64		87.82 234	86.71 237	91.15 247	89.54 322	85.61 254	97.37 243	89.16 368	89.26 153	83.42 241	94.50 222	65.79 303	96.18 283	88.00 194	83.37 257	91.67 268

UniMVSNet (Re)		89.50 208	88.32 215	93.03 210	92.21 285	90.96 127	98.90 117	98.39 23	89.13 157	83.22 242	92.03 265	81.69 192	96.34 275	86.79 208	72.53 326	91.81 266

UniMVSNet_NR-MVSNet		89.60 205	88.55 212	92.75 217	92.17 286	90.07 147	98.74 132	98.15 36	88.37 183	83.21 243	93.98 231	82.86 172	95.93 296	86.95 204	72.47 327	92.25 250

DU-MVS		88.83 219	87.51 223	92.79 215	91.46 297	90.07 147	98.71 133	97.62 102	88.87 167	83.21 243	93.68 238	74.63 232	95.93 296	86.95 204	72.47 327	92.36 247

LPG-MVS_test		88.86 216	88.47 214	90.06 274	93.35 271	80.95 319	98.22 193	95.94 243	87.73 204	83.17 245	96.11 197	66.28 301	97.77 199	90.19 166	85.19 238	91.46 280

LGP-MVS_train				90.06 274	93.35 271	80.95 319		95.94 243	87.73 204	83.17 245	96.11 197	66.28 301	97.77 199	90.19 166	85.19 238	91.46 280

miper_enhance_ethall		90.33 190	89.70 185	92.22 224	97.12 147	88.93 172	98.35 184	95.96 240	88.60 172	83.14 247	92.33 262	87.38 92	96.18 283	86.49 210	77.89 284	91.55 277

FC-MVSNet-test		90.22 193	89.40 192	92.67 220	91.78 293	89.86 155	97.89 219	98.22 30	88.81 168	82.96 248	94.66 220	81.90 191	95.96 294	85.89 218	82.52 265	92.20 255

PCF-MVS	89.78 5	91.26 174	89.63 186	96.16 116	95.44 204	91.58 109	95.29 306	96.10 233	85.07 249	82.75 249	97.45 150	78.28 217	99.78 71	80.60 271	95.65 159	97.12 207
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 248	85.68 253	90.98 252	89.91 314	86.08 243	98.32 187	95.61 271	83.67 272	82.72 250	90.67 296	74.00 245	96.53 257	81.94 261	74.28 309	90.32 315

v1144		86.83 251	85.31 258	91.40 242	89.75 317	87.21 217	98.31 188	95.45 280	83.22 278	82.70 251	90.78 291	73.36 247	96.36 269	79.49 276	74.69 303	90.63 310

v144192		86.40 259	84.89 264	90.91 253	89.48 324	85.59 255	98.21 195	95.43 284	82.45 294	82.62 252	90.58 303	72.79 256	96.36 269	78.45 285	74.04 313	90.79 302

3Dnovator	87.35 11	93.17 140	91.77 153	97.37 54	95.41 206	93.07 80	98.82 124	97.85 54	91.53 89	82.56 253	97.58 146	71.97 262	99.82 65	91.01 156	99.23 82	99.22 112

v2v482		87.27 246	85.76 251	91.78 239	89.59 319	87.58 200	98.56 157	95.54 275	84.53 258	82.51 254	91.78 273	73.11 252	96.47 263	82.07 258	74.14 312	91.30 288

Baseline_NR-MVSNet		85.83 268	84.82 266	88.87 304	88.73 332	83.34 288	98.63 147	91.66 355	80.41 318	82.44 255	91.35 281	74.63 232	95.42 313	84.13 236	71.39 336	87.84 343

v1192		86.32 261	84.71 268	91.17 246	89.53 323	86.40 229	98.13 200	95.44 283	82.52 293	82.42 256	90.62 300	71.58 268	96.33 276	77.23 290	74.88 300	90.79 302

RRT_MVS		88.91 214	88.56 211	89.93 278	90.31 311	81.61 308	98.08 209	96.38 214	89.30 152	82.41 257	94.84 217	73.15 251	96.04 291	90.38 163	82.23 267	92.15 256

test_djsdf		88.26 231	87.73 220	89.84 281	88.05 340	82.21 303	97.77 227	96.17 229	86.84 221	82.41 257	91.95 271	72.07 261	95.99 292	89.83 168	84.50 243	91.32 287

cl22		89.57 206	88.79 204	91.91 231	97.94 120	87.62 199	97.98 216	96.51 207	85.03 250	82.37 259	91.79 272	83.65 155	96.50 260	85.96 215	77.89 284	91.61 274

1314		93.44 128	91.98 148	97.84 33	95.24 209	94.38 53	96.22 287	97.92 49	90.18 126	82.28 260	97.71 139	77.63 221	99.80 69	91.94 149	98.67 105	99.34 101

v1921920		86.02 264	84.44 273	90.77 258	89.32 326	85.20 262	98.10 206	95.35 290	82.19 298	82.25 261	90.71 293	70.73 271	96.30 280	76.85 295	74.49 305	90.80 301

v1240		85.77 271	84.11 276	90.73 259	89.26 327	85.15 265	97.88 221	95.23 298	81.89 303	82.16 262	90.55 305	69.60 278	96.31 277	75.59 305	74.87 301	90.72 307

XVG-ACMP-BASELINE		85.86 267	84.95 263	88.57 305	89.90 315	77.12 339	94.30 314	95.60 272	87.40 212	82.12 263	92.99 256	53.42 348	97.66 208	85.02 224	83.83 251	90.92 298

GBi-Net		86.67 254	84.96 261	91.80 235	95.11 219	88.81 175	96.77 267	95.25 292	82.94 284	82.12 263	90.25 311	62.89 316	94.97 321	79.04 279	80.24 272	91.62 271

test1		86.67 254	84.96 261	91.80 235	95.11 219	88.81 175	96.77 267	95.25 292	82.94 284	82.12 263	90.25 311	62.89 316	94.97 321	79.04 279	80.24 272	91.62 271

FMVSNet3		88.81 221	87.08 231	93.99 192	96.52 165	94.59 48	98.08 209	96.20 226	85.85 236	82.12 263	91.60 276	74.05 244	95.40 314	79.04 279	80.24 272	91.99 263

IterMVS-LS		88.34 228	87.44 224	91.04 250	94.10 247	85.85 250	98.10 206	95.48 278	85.12 246	82.03 267	91.21 284	81.35 197	95.63 308	83.86 242	75.73 295	91.63 270
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		88.94 213	88.12 218	91.40 242	95.32 208	86.93 220	97.85 223	95.55 274	84.19 262	81.97 268	91.50 278	84.16 150	95.91 299	84.69 228	77.89 284	91.36 285

MIMVSNet		84.48 286	81.83 296	92.42 222	91.73 294	87.36 208	85.52 355	94.42 317	81.40 306	81.91 269	87.58 333	51.92 351	92.81 345	73.84 317	88.15 222	97.08 211

PS-MVSNAJss		89.54 207	89.05 198	91.00 251	88.77 331	84.36 275	97.39 240	95.97 238	88.47 174	81.88 270	93.80 236	82.48 181	96.50 260	89.34 179	83.34 259	92.15 256

WR-MVS		88.54 226	87.22 230	92.52 221	91.93 291	89.50 161	98.56 157	97.84 55	86.99 215	81.87 271	93.81 235	74.25 243	95.92 298	85.29 220	74.43 306	92.12 258

TranMVSNet+NR-MVSNet		87.75 238	86.31 243	92.07 230	90.81 304	88.56 180	98.33 185	97.18 167	87.76 201	81.87 271	93.90 233	72.45 257	95.43 312	83.13 249	71.30 337	92.23 252

eth_miper_zixun_eth		87.76 237	87.00 233	90.06 274	94.67 238	82.65 300	97.02 260	95.37 288	84.19 262	81.86 273	91.58 277	81.47 195	95.90 300	83.24 245	73.61 315	91.61 274

UniMVSNet_ETH3D		85.65 274	83.79 280	91.21 245	90.41 310	80.75 321	95.36 305	95.78 260	78.76 325	81.83 274	94.33 224	49.86 356	96.66 248	84.30 232	83.52 256	96.22 225

c3_l		88.19 232	87.23 229	91.06 249	94.97 228	86.17 240	97.72 231	95.38 287	83.43 275	81.68 275	91.37 280	82.81 173	95.72 305	84.04 240	73.70 314	91.29 289

DP-MVS		88.75 223	86.56 240	95.34 141	98.92 90	87.45 205	97.64 235	93.52 333	70.55 351	81.49 276	97.25 157	74.43 238	99.88 49	71.14 329	94.09 170	98.67 159

3Dnovator+	87.72 8	93.43 129	91.84 151	98.17 21	95.73 195	95.08 31	98.92 115	97.04 181	91.42 95	81.48 277	97.60 144	74.60 234	99.79 70	90.84 159	98.97 91	99.64 72

QAPM		91.41 172	89.49 189	97.17 61	95.66 198	93.42 72	98.60 152	97.51 127	80.92 313	81.39 278	97.41 152	72.89 255	99.87 52	82.33 256	98.68 104	98.21 183

XXY-MVS		87.75 238	86.02 247	92.95 213	90.46 309	89.70 158	97.71 233	95.90 252	84.02 264	80.95 279	94.05 225	67.51 292	97.10 234	85.16 221	78.41 281	92.04 262

v148		86.38 260	85.06 260	90.37 269	89.47 325	84.10 279	98.52 159	95.48 278	83.80 268	80.93 280	90.22 314	74.60 234	96.31 277	80.92 267	71.55 335	90.69 308

DIV-MVS_self_test		87.82 234	86.81 235	90.87 256	94.87 233	85.39 260	97.81 224	95.22 299	82.92 287	80.76 281	91.31 282	81.99 188	95.81 303	81.36 263	75.04 299	91.42 283

cl____		87.82 234	86.79 236	90.89 255	94.88 232	85.43 258	97.81 224	95.24 295	82.91 288	80.71 282	91.22 283	81.97 190	95.84 301	81.34 264	75.06 298	91.40 284

FMVSNet2		86.90 249	84.79 267	93.24 207	95.11 219	92.54 94	97.67 234	95.86 258	82.94 284	80.55 283	91.17 285	62.89 316	95.29 316	77.23 290	79.71 278	91.90 265

pmmvs4		87.58 243	86.17 246	91.80 235	89.58 320	88.92 173	97.25 249	95.28 291	82.54 292	80.49 284	93.17 251	75.62 229	96.05 290	82.75 252	78.90 279	90.42 313

ACMP	87.39 10	88.71 224	88.24 216	90.12 273	93.91 256	81.06 318	98.50 164	95.67 268	89.43 149	80.37 285	95.55 204	65.67 304	97.83 194	90.55 162	84.51 242	91.47 279
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
test_part1		88.43 227	86.68 238	93.67 202	97.56 133	92.40 96	98.12 202	96.55 204	82.26 297	80.31 286	93.16 252	74.59 236	96.62 250	85.00 225	72.61 325	91.99 263

pmmvs5		85.87 266	84.40 275	90.30 270	88.53 335	84.23 276	98.60 152	93.71 329	81.53 305	80.29 287	92.02 266	64.51 311	95.52 310	82.04 260	78.34 282	91.15 292

test0.0.03 1		88.96 212	88.61 208	90.03 277	91.09 301	84.43 274	98.97 111	97.02 184	90.21 124	80.29 287	96.31 194	84.89 143	91.93 357	72.98 323	85.70 237	93.73 234

miper_lstm_enhance		86.90 249	86.20 245	89.00 301	94.53 240	81.19 315	96.74 271	95.24 295	82.33 296	80.15 289	90.51 307	81.99 188	94.68 330	80.71 269	73.58 316	91.12 293

jajsoiax		87.35 244	86.51 241	89.87 279	87.75 345	81.74 306	97.03 258	95.98 237	88.47 174	80.15 289	93.80 236	61.47 321	96.36 269	89.44 177	84.47 245	91.50 278

mvs_tets		87.09 247	86.22 244	89.71 284	87.87 341	81.39 311	96.73 272	95.90 252	88.19 189	79.99 291	93.61 241	59.96 327	96.31 277	89.40 178	84.34 246	91.43 282

ITE_SJBPF				87.93 310	92.26 284	76.44 340		93.47 334	87.67 207	79.95 292	95.49 207	56.50 335	97.38 226	75.24 306	82.33 266	89.98 324

v8		86.11 263	84.45 272	91.10 248	89.99 313	86.85 221	97.24 250	95.36 289	81.99 300	79.89 293	89.86 319	74.53 237	96.39 267	78.83 283	72.32 329	90.05 322

v10		85.73 272	84.01 278	90.87 256	90.03 312	86.73 223	97.20 253	95.22 299	81.25 308	79.85 294	89.75 320	73.30 250	96.28 281	76.87 294	72.64 324	89.61 329

WR-MVS_H		86.53 258	85.49 256	89.66 288	91.04 302	83.31 289	97.53 238	98.20 32	84.95 253	79.64 295	90.90 289	78.01 219	95.33 315	76.29 300	72.81 322	90.35 314

anonymousdsp		86.69 253	85.75 252	89.53 290	86.46 351	82.94 292	96.39 278	95.71 264	83.97 266	79.63 296	90.70 294	68.85 280	95.94 295	86.01 213	84.02 249	89.72 327

Patchmtry		83.61 297	81.64 297	89.50 291	93.36 270	82.84 297	84.10 362	94.20 322	69.47 356	79.57 297	86.88 342	84.43 147	94.78 327	68.48 338	74.30 308	90.88 299

CP-MVSNet		86.54 257	85.45 257	89.79 283	91.02 303	82.78 298	97.38 242	97.56 116	85.37 243	79.53 298	93.03 254	71.86 264	95.25 317	79.92 274	73.43 320	91.34 286

Patchmatch-test		86.25 262	84.06 277	92.82 214	94.42 241	82.88 296	82.88 366	94.23 321	71.58 348	79.39 299	90.62 300	89.00 66	96.42 266	63.03 353	91.37 207	99.16 115

DSMNet-mixed		81.60 306	81.43 300	82.10 341	84.36 357	60.79 369	93.63 322	86.74 372	79.00 321	79.32 300	87.15 340	63.87 314	89.78 362	66.89 343	91.92 196	95.73 228

MSDG		88.29 230	86.37 242	94.04 190	96.90 154	86.15 241	96.52 276	94.36 319	77.89 331	79.22 301	96.95 173	69.72 276	99.59 97	73.20 322	92.58 186	96.37 224

Anonymous20231211		84.72 281	82.65 292	90.91 253	97.71 125	84.55 273	97.28 247	96.67 195	66.88 362	79.18 302	90.87 290	58.47 329	96.60 251	82.61 254	74.20 310	91.59 276

PS-CasMVS		85.81 269	84.58 271	89.49 293	90.77 305	82.11 304	97.20 253	97.36 151	84.83 255	79.12 303	92.84 257	67.42 293	95.16 319	78.39 286	73.25 321	91.21 291

IterMVS		85.81 269	84.67 269	89.22 296	93.51 265	83.67 285	96.32 281	94.80 306	85.09 248	78.69 304	90.17 317	66.57 300	93.17 342	79.48 277	77.42 290	90.81 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 277	83.93 279	89.07 300	89.89 316	81.31 313	97.09 256	97.24 158	84.45 260	78.66 305	92.68 259	68.44 284	94.87 324	75.98 302	70.92 338	91.04 295

IterMVS-SCA-FT		85.73 272	84.64 270	89.00 301	93.46 268	82.90 294	96.27 282	94.70 309	85.02 251	78.62 306	90.35 309	66.61 298	93.33 339	79.38 278	77.36 291	90.76 304

OpenMVS	85.28 14	90.75 184	88.84 202	96.48 102	93.58 264	93.51 70	98.80 126	97.41 146	82.59 290	78.62 306	97.49 149	68.00 288	99.82 65	84.52 231	98.55 110	96.11 226

PVSNet_0	83.28 16	87.31 245	85.16 259	93.74 200	94.78 235	84.59 272	98.91 116	98.69 19	89.81 137	78.59 308	93.23 249	61.95 320	99.34 131	94.75 108	55.72 365	97.30 203

EU-MVSNet		84.19 290	84.42 274	83.52 337	88.64 334	67.37 366	96.04 293	95.76 262	85.29 244	78.44 309	93.18 250	70.67 272	91.48 359	75.79 304	75.98 293	91.70 267

v7n		84.42 288	82.75 289	89.43 294	88.15 338	81.86 305	96.75 270	95.67 268	80.53 314	78.38 310	89.43 324	69.89 274	96.35 274	73.83 318	72.13 331	90.07 320

FMVSNet1		83.94 294	81.32 302	91.80 235	91.94 290	88.81 175	96.77 267	95.25 292	77.98 327	78.25 311	90.25 311	50.37 355	94.97 321	73.27 321	77.81 288	91.62 271

D2MVS		87.96 233	87.39 225	89.70 285	91.84 292	83.40 287	98.31 188	98.49 21	88.04 193	78.23 312	90.26 310	73.57 246	96.79 246	84.21 234	83.53 255	88.90 337

MS-PatchMatch		86.75 252	85.92 249	89.22 296	91.97 288	82.47 302	96.91 262	96.14 231	83.74 269	77.73 313	93.53 244	58.19 330	97.37 228	76.75 296	98.35 113	87.84 343

DTE-MVSNet		84.14 291	82.80 286	88.14 309	88.95 330	79.87 325	96.81 266	96.24 224	83.50 274	77.60 314	92.52 261	67.89 290	94.24 335	72.64 325	69.05 341	90.32 315

COLMAP_ROB	82.69 18	84.54 285	82.82 285	89.70 285	96.72 160	78.85 328	95.89 295	92.83 341	71.55 349	77.54 315	95.89 201	59.40 328	99.14 141	67.26 341	88.26 221	91.11 294
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 292	83.59 281	85.77 326	87.81 342	70.24 360	94.89 309	93.65 331	86.08 234	76.53 316	93.28 248	61.41 322	96.14 287	80.95 266	77.69 289	90.93 297

tfpnnormal		83.65 295	81.35 301	90.56 262	91.37 299	88.06 189	97.29 246	97.87 53	78.51 326	76.20 317	90.91 288	64.78 310	96.47 263	61.71 356	73.50 317	87.13 351

ppachtmachnet_test		83.63 296	81.57 299	89.80 282	89.01 328	85.09 266	97.13 255	94.50 314	78.84 323	76.14 318	91.00 287	69.78 275	94.61 331	63.40 351	74.36 307	89.71 328

pm-mvs1		84.68 282	82.78 288	90.40 266	89.58 320	85.18 263	97.31 245	94.73 308	81.93 302	76.05 319	92.01 267	65.48 308	96.11 288	78.75 284	69.14 340	89.91 325

AllTest		84.97 279	83.12 283	90.52 263	96.82 156	78.84 329	95.89 295	92.17 348	77.96 329	75.94 320	95.50 205	55.48 338	99.18 136	71.15 327	87.14 225	93.55 236

TestCases				90.52 263	96.82 156	78.84 329		92.17 348	77.96 329	75.94 320	95.50 205	55.48 338	99.18 136	71.15 327	87.14 225	93.55 236

CL-MVSNet_self_test		79.89 313	78.34 313	84.54 333	81.56 365	75.01 343	96.88 264	95.62 270	81.10 309	75.86 322	85.81 348	68.49 283	90.26 361	63.21 352	56.51 363	88.35 340

testgi		82.29 301	81.00 304	86.17 323	87.24 347	74.84 345	97.39 240	91.62 356	88.63 170	75.85 323	95.42 208	46.07 362	91.55 358	66.87 344	79.94 276	92.12 258

MVP-Stereo		86.61 256	85.83 250	88.93 303	88.70 333	83.85 283	96.07 292	94.41 318	82.15 299	75.64 324	91.96 270	67.65 291	96.45 265	77.20 292	98.72 103	86.51 354
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 304	81.17 303	84.25 334	87.23 348	68.87 365	93.35 324	91.93 353	83.35 277	75.40 325	93.00 255	49.25 359	96.65 249	78.88 282	78.11 283	87.22 350

our_test_3		84.47 287	82.80 286	89.50 291	89.01 328	83.90 282	97.03 258	94.56 313	81.33 307	75.36 326	90.52 306	71.69 266	94.54 332	68.81 336	76.84 292	90.07 320

LTVRE_ROB	81.71 19	84.59 284	82.72 290	90.18 271	92.89 279	83.18 290	93.15 325	94.74 307	78.99 322	75.14 327	92.69 258	65.64 305	97.63 211	69.46 334	81.82 269	89.74 326
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
Anonymous20231206		80.76 308	79.42 312	84.79 331	84.78 356	72.98 351	96.53 275	92.97 338	79.56 319	74.33 328	88.83 327	61.27 323	92.15 354	60.59 358	75.92 294	89.24 334

FMVSNet5		82.29 301	80.54 305	87.52 314	93.79 261	84.01 280	93.73 320	92.47 344	76.92 334	74.27 329	86.15 347	63.69 315	89.24 363	69.07 335	74.79 302	89.29 333

MVS-HIRNet		79.01 316	75.13 326	90.66 260	93.82 260	81.69 307	85.16 356	93.75 328	54.54 367	74.17 330	59.15 371	57.46 332	96.58 254	63.74 350	94.38 167	93.72 235

ACMH+	83.78 15	84.21 289	82.56 294	89.15 298	93.73 262	79.16 326	96.43 277	94.28 320	81.09 310	74.00 331	94.03 228	54.58 344	97.67 207	76.10 301	78.81 280	90.63 310

KD-MVS_2432*1600		82.98 298	80.52 306	90.38 267	94.32 243	88.98 168	92.87 328	95.87 256	80.46 316	73.79 332	87.49 335	82.76 176	93.29 340	70.56 331	46.53 370	88.87 338

miper_refine_blended		82.98 298	80.52 306	90.38 267	94.32 243	88.98 168	92.87 328	95.87 256	80.46 316	73.79 332	87.49 335	82.76 176	93.29 340	70.56 331	46.53 370	88.87 338

NR-MVSNet		87.74 240	86.00 248	92.96 212	91.46 297	90.68 134	96.65 274	97.42 145	88.02 194	73.42 334	93.68 238	77.31 222	95.83 302	84.26 233	71.82 334	92.36 247

USDC		84.74 280	82.93 284	90.16 272	91.73 294	83.54 286	95.00 308	93.30 336	88.77 169	73.19 335	93.30 247	53.62 347	97.65 210	75.88 303	81.54 270	89.30 332

KD-MVS_self_test		77.47 325	75.88 324	82.24 339	81.59 364	68.93 364	92.83 330	94.02 325	77.03 333	73.14 336	83.39 353	55.44 340	90.42 360	67.95 339	57.53 362	87.38 346

LCM-MVSNet-Re		88.59 225	88.61 208	88.51 307	95.53 202	72.68 354	96.85 265	88.43 370	88.45 177	73.14 336	90.63 299	75.82 227	94.38 333	92.95 139	95.71 158	98.48 168

TDRefinement		78.01 322	75.31 325	86.10 324	70.06 374	73.84 348	93.59 323	91.58 357	74.51 342	73.08 338	91.04 286	49.63 358	97.12 231	74.88 309	59.47 359	87.33 348

TransMVSNet (Re)		81.97 303	79.61 311	89.08 299	89.70 318	84.01 280	97.26 248	91.85 354	78.84 323	73.07 339	91.62 275	67.17 295	95.21 318	67.50 340	59.46 360	88.02 342

SixPastTwentyTwo		82.63 300	81.58 298	85.79 325	88.12 339	71.01 359	95.17 307	92.54 343	84.33 261	72.93 340	92.08 264	60.41 326	95.61 309	74.47 312	74.15 311	90.75 305

pmmvs6		79.90 312	77.31 317	87.67 313	84.17 358	78.13 335	95.86 299	93.68 330	67.94 360	72.67 341	89.62 322	50.98 354	95.75 304	74.80 311	66.04 349	89.14 335

ACMH	83.09 17	84.60 283	82.61 293	90.57 261	93.18 274	82.94 292	96.27 282	94.92 303	81.01 311	72.61 342	93.61 241	56.54 334	97.79 197	74.31 313	81.07 271	90.99 296
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 320	76.90 320	83.82 335	82.82 362	72.86 352	95.72 303	93.57 332	73.55 346	72.17 343	84.79 350	49.69 357	92.51 350	65.29 348	74.50 304	86.09 356

Patchmatch-RL test		81.90 305	80.13 308	87.23 317	80.71 367	70.12 362	84.07 363	88.19 371	83.16 280	70.57 344	82.18 356	87.18 99	92.59 348	82.28 257	62.78 353	98.98 128

test_0402		78.81 318	76.33 322	86.26 322	91.18 300	78.44 333	95.88 297	91.34 359	68.55 357	70.51 345	89.91 318	52.65 350	94.99 320	47.14 369	79.78 277	85.34 360

TinyColmap		80.42 310	77.94 314	87.85 311	92.09 287	78.58 331	93.74 319	89.94 364	74.99 339	69.77 346	91.78 273	46.09 361	97.58 215	65.17 349	77.89 284	87.38 346

test20.03		78.51 321	77.48 316	81.62 343	83.07 361	71.03 358	96.11 291	92.83 341	81.66 304	69.31 347	89.68 321	57.53 331	87.29 368	58.65 362	68.47 342	86.53 353

N_pmnet		70.19 332	69.87 334	71.12 351	88.24 337	30.63 384	95.85 300	28.70 384	70.18 353	68.73 348	86.55 344	64.04 313	93.81 336	53.12 367	73.46 318	88.94 336

OpenMVS_ROB	73.86 20	77.99 323	75.06 327	86.77 320	83.81 360	77.94 337	96.38 279	91.53 358	67.54 361	68.38 349	87.13 341	43.94 363	96.08 289	55.03 365	81.83 268	86.29 355

ambc				79.60 346	72.76 373	56.61 372	76.20 368	92.01 352		68.25 350	80.23 360	23.34 374	94.73 328	73.78 319	60.81 357	87.48 345

PM-MVS		74.88 328	72.85 331	80.98 345	78.98 370	64.75 367	90.81 344	85.77 373	80.95 312	68.23 351	82.81 354	29.08 373	92.84 344	76.54 298	62.46 355	85.36 359

pmmvs3		72.86 331	69.76 335	82.17 340	73.86 372	74.19 347	94.20 315	89.01 369	64.23 366	67.72 352	80.91 359	41.48 365	88.65 365	62.40 354	54.02 367	83.68 363

lessismore_v0				85.08 328	85.59 354	69.28 363		90.56 362		67.68 353	90.21 315	54.21 346	95.46 311	73.88 316	62.64 354	90.50 312

K. test v3		81.04 307	79.77 310	84.83 330	87.41 346	70.23 361	95.60 304	93.93 326	83.70 271	67.51 354	89.35 325	55.76 336	93.58 338	76.67 297	68.03 344	90.67 309

MIMVSNet1		75.92 327	73.30 330	83.81 336	81.29 366	75.57 342	92.26 333	92.05 351	73.09 347	67.48 355	86.18 346	40.87 368	87.64 367	55.78 364	70.68 339	88.21 341

ET-MVSNet_ETH3D		92.56 151	91.45 159	95.88 124	96.39 171	94.13 59	99.46 50	96.97 187	92.18 78	66.94 356	98.29 122	94.65 15	94.28 334	94.34 118	83.82 253	99.24 109

pmmvs-eth3d		78.71 319	76.16 323	86.38 321	80.25 368	81.19 315	94.17 316	92.13 350	77.97 328	66.90 357	82.31 355	55.76 336	92.56 349	73.63 320	62.31 356	85.38 358

EG-PatchMatch MVS		79.92 311	77.59 315	86.90 319	87.06 349	77.90 338	96.20 290	94.06 324	74.61 341	66.53 358	88.76 328	40.40 369	96.20 282	67.02 342	83.66 254	86.61 352

test_method		70.10 333	68.66 336	74.41 349	86.30 353	55.84 373	94.47 311	89.82 365	35.18 372	66.15 359	84.75 351	30.54 372	77.96 373	70.40 333	60.33 358	89.44 331

UnsupCasMVSNet_eth		78.90 317	76.67 321	85.58 327	82.81 363	74.94 344	91.98 334	96.31 218	84.64 257	65.84 360	87.71 332	51.33 352	92.23 353	72.89 324	56.50 364	89.56 330

new-patchmatchnet		74.80 329	72.40 332	81.99 342	78.36 371	72.20 355	94.44 312	92.36 345	77.06 332	63.47 361	79.98 361	51.04 353	88.85 364	60.53 359	54.35 366	84.92 361

new_pmnet		76.02 326	73.71 329	82.95 338	83.88 359	72.85 353	91.26 341	92.26 347	70.44 352	62.60 362	81.37 357	47.64 360	92.32 352	61.85 355	72.10 332	83.68 363

UnsupCasMVSNet_bld		73.85 330	70.14 333	84.99 329	79.44 369	75.73 341	88.53 350	95.24 295	70.12 354	61.94 363	74.81 364	41.41 366	93.62 337	68.65 337	51.13 369	85.62 357

CMPMVS	58.40 21	80.48 309	80.11 309	81.59 344	85.10 355	59.56 370	94.14 317	95.95 242	68.54 358	60.71 364	93.31 246	55.35 341	97.87 192	83.06 250	84.85 241	87.33 348
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
DeepMVS_CX				76.08 348	90.74 306	51.65 376		90.84 361	86.47 231	57.89 365	87.98 330	35.88 371	92.60 347	65.77 347	65.06 351	83.97 362

YYNet1		79.64 315	77.04 319	87.43 316	87.80 343	79.98 324	96.23 286	94.44 315	73.83 345	51.83 366	87.53 334	67.96 289	92.07 356	66.00 346	67.75 346	90.23 317

MDA-MVSNet_test_wron		79.65 314	77.05 318	87.45 315	87.79 344	80.13 323	96.25 285	94.44 315	73.87 344	51.80 367	87.47 337	68.04 287	92.12 355	66.02 345	67.79 345	90.09 318

LCM-MVSNet		60.07 336	56.37 338	71.18 350	54.81 380	48.67 377	82.17 367	89.48 367	37.95 370	49.13 368	69.12 365	13.75 381	81.76 369	59.28 360	51.63 368	83.10 365

MDA-MVSNet-bldmvs		77.82 324	74.75 328	87.03 318	88.33 336	78.52 332	96.34 280	92.85 340	75.57 338	48.87 369	87.89 331	57.32 333	92.49 351	60.79 357	64.80 352	90.08 319

PMMVS2		58.97 337	55.07 340	70.69 352	62.72 375	55.37 374	85.97 354	80.52 377	49.48 368	45.94 370	68.31 366	15.73 379	80.78 371	49.79 368	37.12 372	75.91 366

FPMVS		61.57 334	60.32 337	65.34 353	60.14 378	42.44 379	91.02 343	89.72 366	44.15 369	42.63 371	80.93 358	19.02 375	80.59 372	42.50 370	72.76 323	73.00 367

Gipuma		54.77 338	52.22 342	62.40 355	86.50 350	59.37 371	50.20 373	90.35 363	36.52 371	41.20 372	49.49 373	18.33 377	81.29 370	32.10 373	65.34 350	46.54 373
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 339	52.86 341	56.05 356	32.75 384	41.97 380	73.42 370	76.12 380	21.91 377	39.68 373	96.39 192	42.59 364	65.10 376	78.00 287	14.92 377	61.08 370

E-PMN		41.02 343	40.93 345	41.29 359	61.97 376	33.83 381	84.00 364	65.17 382	27.17 374	27.56 374	46.72 375	17.63 378	60.41 378	19.32 376	18.82 374	29.61 374

ANet_high		50.71 340	46.17 343	64.33 354	44.27 382	52.30 375	76.13 369	78.73 378	64.95 364	27.37 375	55.23 372	14.61 380	67.74 375	36.01 372	18.23 375	72.95 368

EMVS		39.96 344	39.88 346	40.18 360	59.57 379	32.12 383	84.79 361	64.57 383	26.27 375	26.14 376	44.18 378	18.73 376	59.29 379	17.03 377	17.67 376	29.12 375

MVE	44.00 22	41.70 342	37.64 347	53.90 358	49.46 381	43.37 378	65.09 372	66.66 381	26.19 376	25.77 377	48.53 374	3.58 384	63.35 377	26.15 375	27.28 373	54.97 372
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 341	42.50 344	55.17 357	34.28 383	32.37 382	66.24 371	78.71 379	30.72 373	22.04 378	59.59 370	4.59 382	77.85 374	27.49 374	58.84 361	55.29 371
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 346	23.05 349	6.10 363	4.48 385	2.29 387	97.78 226	3.00 386	3.27 379	18.60 379	62.71 368	1.53 386	2.49 382	14.26 379	1.80 379	13.50 377

test123		16.58 348	19.47 350	7.91 362	3.59 386	5.37 386	94.32 313	1.39 387	2.49 380	13.98 380	44.60 377	2.91 385	2.65 381	11.35 380	0.57 380	15.70 376

wuyk23d		16.71 347	16.73 351	16.65 361	60.15 377	25.22 385	41.24 374	5.17 385	6.56 378	5.48 381	3.61 381	3.64 383	22.72 380	15.20 378	9.52 378	1.99 378

EGC-MVSNET		60.70 335	55.37 339	76.72 347	86.35 352	71.08 357	89.96 348	84.44 376	0.38 381	1.50 382	84.09 352	37.30 370	88.10 366	40.85 371	73.44 319	70.97 369

test_blank		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet_test		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

DCPMVS		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

cdsmvs_eth3d_5k		22.52 345	30.03 348	0.00 364	0.00 387	0.00 388	0.00 375	97.17 168	0.00 382	0.00 383	98.77 89	74.35 240	0.00 383	0.00 381	0.00 381	0.00 379

pcd_1.5k_mvsjas		6.87 350	9.16 353	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	82.48 181	0.00 383	0.00 381	0.00 381	0.00 379

sosnet-low-res		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

sosnet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uncertanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

Regformer		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

ab-mvs-re		8.21 349	10.94 352	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	98.50 111	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

uanet		0.00 351	0.00 354	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	0.00 387	0.00 383	0.00 381	0.00 381	0.00 379

MSC_two_6792asdad				99.51 2	99.61 27	98.60 2		97.69 84					99.98 10	99.55 10	99.83 15	99.96 10

No_MVS				99.51 2	99.61 27	98.60 2		97.69 84					99.98 10	99.55 10	99.83 15	99.96 10

eth-test2					0.00 387

eth-test					0.00 387

OPU-MVS				99.49 4	99.64 20	98.51 4	99.77 8				99.19 34	95.12 8	99.97 23	99.90 1	99.92 3	99.99 1

save fliter					99.34 58	93.85 63	99.65 24	97.63 100	95.69 11

test_0728_SECOND				98.77 7	99.66 15	96.37 13	99.72 13	97.68 86					99.98 10	99.64 6	99.82 19	99.96 10

GSMVS																98.84 143

sam_mvs1												88.39 75				98.84 143

sam_mvs												87.08 101

MTGPA								97.45 138

test_post1							90.74 346				41.37 379	85.38 139	96.36 269	83.16 247

test_post											46.00 376	87.37 93	97.11 232

patchmatchnet-post											84.86 349	88.73 69	96.81 244

MTMP							99.21 76	91.09 360

gm-plane-assit					94.69 237	88.14 187			88.22 188		97.20 161		98.29 171	90.79 160

test9_res														98.60 25	99.87 9	99.90 24

agg_prior2														97.84 47	99.87 9	99.91 22

test_prior4						92.00 100	99.41 59

test_prior				97.01 65	99.58 33	91.77 101		97.57 114					99.49 109			99.79 38

新几何2							98.26 191

旧先验1					98.97 86	92.90 87		97.74 71			99.15 43	91.05 34			99.33 74	99.60 78

无先验							98.52 159	97.82 58	87.20 214				99.90 45	87.64 198		99.85 33

原ACMM2							98.69 138

testdata2													99.88 49	84.16 235

segment_acmp												90.56 43

testdata1							97.89 219		92.43 68

plane_prior7					93.84 258	85.73 252

plane_prior6					93.92 255	86.02 246						72.92 253

plane_prior5								96.30 219					97.75 204	93.46 132	86.17 232	92.67 241

plane_prior4											96.52 186

plane_prior2							99.02 105		93.38 49

plane_prior1					93.90 257

plane_prior						86.07 244	99.14 91		93.81 41						86.26 231

n2								0.00 388

nn								0.00 388

door-mid								84.90 375

test11								97.68 86

door								85.30 374

HQP5-MVS						86.39 230

BP-MVS														93.82 127

HQP3-MVS								96.37 215							86.29 229

HQP2-MVS												73.34 248

NP-MVS					93.94 254	86.22 237					96.67 184

ACMMP++_ref															82.64 264

ACMMP++															83.83 251

Test By Simon												83.62 156

High-resolution multi-view benchmark