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 18	95.38 20		97.73 68	95.54 15	99.54 1				99.69 5	99.81 23	99.99 1

PC_three_1452									94.60 23	99.41 2	99.12 41	95.50 7	99.96 28	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 13	99.80 8	97.99 45	97.05 3	99.41 2	99.59 2	92.89 25	100.00 1	98.99 18	99.90 7	99.96 10

patch_mono-2		97.10 22	97.97 8	94.49 154	99.21 61	83.73 268	99.62 27	98.25 27	95.28 18	99.38 4	98.91 65	92.28 28	99.94 34	99.61 8	99.22 70	99.78 37

test0726					99.66 12	95.20 28	99.77 9	97.70 74	93.95 34	99.35 5	99.54 3	93.18 22

SED-MVS		98.18 2	98.10 4	98.41 16	99.63 18	95.24 23	99.77 9	97.72 69	94.17 29	99.30 6	99.54 3	93.32 19	99.98 9	99.70 3	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 23		97.72 69	94.16 31	99.30 6	99.49 9	93.32 19	99.98 9

DVP-MVS++		98.18 2	98.09 5	98.44 14	99.61 24	95.38 20	99.55 33	97.68 78	93.01 56	99.23 8	99.45 14	95.12 8	99.98 9	99.25 14	99.92 3	99.97 7

test_241102_TWO								97.72 69	94.17 29	99.23 8	99.54 3	93.14 24	99.98 9	99.70 3	99.82 19	99.99 1

SMA-MVS		97.24 16	96.99 19	98.00 27	99.30 54	94.20 53	99.16 78	97.65 86	89.55 140	99.22 10	99.52 8	90.34 46	99.99 5	98.32 32	99.83 15	99.82 31
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 17	99.66 12	95.20 28	99.72 14	97.47 124	93.95 34	99.07 11	99.46 10	93.18 22	99.97 21	99.64 6	99.82 19	99.69 53
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 56	99.07 11	99.46 10	94.66 14	99.97 21	99.25 14	99.82 19	99.95 15

TSAR-MVS + MP.		97.44 14	97.46 13	97.39 44	99.12 65	93.49 67	98.52 152	97.50 119	94.46 25	98.99 13	98.64 87	91.58 30	99.08 134	98.49 27	99.83 15	99.60 65
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 26	96.40 32	98.29 17	97.35 120	97.29 5	99.03 100	97.11 161	95.83 11	98.97 14	99.14 38	82.48 167	99.60 89	98.60 23	99.08 73	98.00 173

旧先验2							98.67 135		85.75 230	98.96 15			98.97 138	93.84 116

test_one_0601					99.59 28	94.89 32		97.64 87	93.14 55	98.93 16	99.45 14	93.45 18

xiu_mvs_v2_base		96.66 30	96.17 40	98.11 25	97.11 132	96.96 6	99.01 103	97.04 168	95.51 16	98.86 17	99.11 45	82.19 173	99.36 116	98.59 25	98.14 101	98.00 173

NCCC		98.12 5	98.11 3	98.13 22	99.76 6	94.46 46	99.81 6	97.88 48	96.54 6	98.84 18	99.46 10	92.55 27	99.98 9	98.25 34	99.93 1	99.94 18

SD-MVS		97.51 12	97.40 15	97.81 32	99.01 72	93.79 61	99.33 65	97.38 137	93.73 45	98.83 19	99.02 52	90.87 38	99.88 46	98.69 21	99.74 29	99.77 42
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
SF-MVS		97.22 18	96.92 20	98.12 24	99.11 66	94.88 33	99.44 49	97.45 127	89.60 136	98.70 20	99.42 17	90.42 44	99.72 75	98.47 28	99.65 38	99.77 42

DPE-MVS		98.11 6	98.00 6	98.44 14	99.50 42	95.39 19	99.29 68	97.72 69	94.50 24	98.64 21	99.54 3	93.32 19	99.97 21	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 87	99.54 36	90.14 129	99.41 55	97.70 74	95.46 17	98.60 22	99.19 28	95.71 4	99.49 98	98.15 35	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 22		99.34 50		99.50 39	97.49 121	89.41 143	98.59 23	99.43 16	89.78 50	99.69 77	98.69 21	99.62 44

APD-MVS		96.95 24	96.72 26	97.63 36	99.51 41	93.58 63	99.16 78	97.44 130	90.08 125	98.59 23	99.07 46	89.06 55	99.42 109	97.92 38	99.66 37	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_n_1920		93.08 128	93.42 101	92.04 216	96.31 158	79.36 312	99.83 4	96.06 221	96.72 4	98.53 25	98.10 114	58.57 314	99.91 40	97.86 40	98.79 88	96.85 201

testdata				95.26 130	98.20 95	87.28 197		97.60 96	85.21 236	98.48 26	99.15 36	88.15 67	98.72 148	90.29 158	99.45 57	99.78 37

TEST9					99.57 33	93.17 71	99.38 58	97.66 81	89.57 138	98.39 27	99.18 31	90.88 37	99.66 80

train_agg		97.20 19	97.08 18	97.57 40	99.57 33	93.17 71	99.38 58	97.66 81	90.18 120	98.39 27	99.18 31	90.94 35	99.66 80	98.58 26	99.85 13	99.88 26

test_8					99.55 35	93.07 74	99.37 61	97.64 87	90.18 120	98.36 29	99.19 28	90.94 35	99.64 86

CS-MVS-test		95.98 48	96.34 34	94.90 140	98.06 101	87.66 184	99.69 23	96.10 218	93.66 46	98.35 30	99.05 49	86.28 108	97.66 199	96.96 56	98.90 82	99.37 82

HPM-MVS++		97.72 10	97.59 11	98.14 21	99.53 40	94.76 40	99.19 72	97.75 64	95.66 13	98.21 31	99.29 20	91.10 33	99.99 5	97.68 42	99.87 9	99.68 54

DPM-MVS		97.86 8	97.25 17	99.68 1	98.25 93	99.10 1	99.76 12	97.78 61	96.61 5	98.15 32	99.53 7	93.62 17	100.00 1	91.79 142	99.80 26	99.94 18

test_part2					99.54 36	95.42 18				98.13 33

SteuartSystems-ACMMP		97.25 15	97.34 16	97.01 56	97.38 119	91.46 98	99.75 13	97.66 81	94.14 33	98.13 33	99.26 21	92.16 29	99.66 80	97.91 39	99.64 40	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 42	88.94 157	99.55 33	97.47 124	91.32 94	98.12 35

test_prior2							99.57 31		91.43 91	98.12 35	98.97 55	90.43 43		98.33 31	99.81 23

CS-MVS		95.75 59	96.19 36	94.40 158	97.88 105	86.22 221	99.66 24	96.12 217	92.69 64	98.07 37	98.89 68	87.09 87	97.59 205	96.71 59	98.62 92	99.39 81

PHI-MVS		96.65 31	96.46 31	97.21 50	99.34 50	91.77 91	99.70 17	98.05 41	86.48 221	98.05 38	99.20 27	89.33 53	99.96 28	98.38 29	99.62 44	99.90 22

MVSFormer		94.71 83	94.08 86	96.61 81	95.05 211	94.87 34	97.77 218	96.17 214	86.84 212	98.04 39	98.52 94	85.52 117	95.99 283	89.83 161	98.97 78	98.96 116

lupinMVS		96.32 39	95.94 46	97.44 42	95.05 211	94.87 34	99.86 2	96.50 193	93.82 43	98.04 39	98.77 74	85.52 117	98.09 170	96.98 55	98.97 78	99.37 82

APDe-MVS		97.53 11	97.47 12	97.70 34	99.58 30	93.63 62	99.56 32	97.52 114	93.59 49	98.01 41	99.12 41	90.80 39	99.55 92	99.26 13	99.79 27	99.93 20

ACMMP_NAP		96.59 32	96.18 37	97.81 32	98.82 81	93.55 64	98.88 115	97.59 100	90.66 105	97.98 42	99.14 38	86.59 100	100.00 1	96.47 67	99.46 55	99.89 25

agg_prior					99.54 36	92.66 81		97.64 87		97.98 42			99.61 88

CDPH-MVS		96.56 33	96.18 37	97.70 34	99.59 28	93.92 58	99.13 89	97.44 130	89.02 152	97.90 44	99.22 25	88.90 58	99.49 98	94.63 105	99.79 27	99.68 54

EPNet		96.82 27	96.68 28	97.25 49	98.65 86	93.10 73	99.48 40	98.76 13	96.54 6	97.84 45	98.22 109	87.49 77	99.66 80	95.35 87	97.78 108	99.00 112
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		97.50 13	97.45 14	97.63 36	99.65 16	93.21 70	99.70 17	98.13 38	94.61 22	97.78 46	99.46 10	89.85 49	99.81 66	97.97 37	99.91 6	99.88 26

test12				97.83 31	99.33 53	94.45 47		97.55 107		97.56 47		88.60 61	99.50 97		99.71 34	99.55 69

xiu_mvs_v1_base_debu		94.73 80	93.98 88	96.99 58	95.19 199	95.24 23	98.62 141	96.50 193	92.99 58	97.52 48	98.83 71	72.37 242	99.15 127	97.03 52	96.74 125	96.58 204

xiu_mvs_v1_base		94.73 80	93.98 88	96.99 58	95.19 199	95.24 23	98.62 141	96.50 193	92.99 58	97.52 48	98.83 71	72.37 242	99.15 127	97.03 52	96.74 125	96.58 204

xiu_mvs_v1_base_debi		94.73 80	93.98 88	96.99 58	95.19 199	95.24 23	98.62 141	96.50 193	92.99 58	97.52 48	98.83 71	72.37 242	99.15 127	97.03 52	96.74 125	96.58 204

ZD-MVS					99.67 10	93.28 69		97.61 94	87.78 191	97.41 51	99.16 34	90.15 47	99.56 91	98.35 30	99.70 35

ETV-MVS		96.00 46	96.00 45	96.00 107	96.56 147	91.05 110	99.63 26	96.61 183	93.26 54	97.39 52	98.30 106	86.62 99	98.13 167	98.07 36	97.57 111	98.82 133

DeepPCF-MVS	93.56 1	96.55 34	97.84 10	92.68 204	98.71 85	78.11 323	99.70 17	97.71 73	98.18 1	97.36 53	99.76 1	90.37 45	99.94 34	99.27 12	99.54 52	99.99 1

test_vis1_n		90.40 177	90.27 169	90.79 245	91.55 284	76.48 327	99.12 90	94.44 303	94.31 27	97.34 54	96.95 161	43.60 353	99.42 109	97.57 44	97.60 110	96.47 208

DROMVSNet		95.09 71	95.17 65	94.84 143	95.42 191	88.17 172	99.48 40	95.92 233	91.47 89	97.34 54	98.36 103	82.77 160	97.41 216	97.24 49	98.58 93	98.94 121

CANet		97.00 23	96.49 30	98.55 10	98.86 80	96.10 14	99.83 4	97.52 114	95.90 10	97.21 56	98.90 66	82.66 164	99.93 37	98.71 20	98.80 86	99.63 62

CANet_DTU		94.31 92	93.35 102	97.20 51	97.03 136	94.71 42	98.62 141	95.54 262	95.61 14	97.21 56	98.47 100	71.88 247	99.84 57	88.38 180	97.46 116	97.04 198

VNet		95.08 72	94.26 78	97.55 41	98.07 100	93.88 59	98.68 133	98.73 16	90.33 117	97.16 58	97.43 139	79.19 196	99.53 95	96.91 58	91.85 187	99.24 94

region2R		96.30 40	96.17 40	96.70 77	99.70 7	90.31 125	99.46 46	97.66 81	90.55 110	97.07 59	99.07 46	86.85 93	99.97 21	95.43 85	99.74 29	99.81 32

原ACMM1				96.18 99	99.03 71	90.08 132		97.63 91	88.98 153	97.00 60	98.97 55	88.14 68	99.71 76	88.23 182	99.62 44	98.76 140

HFP-MVS		96.42 36	96.26 35	96.90 65	99.69 8	90.96 113	99.47 42	97.81 57	90.54 111	96.88 61	99.05 49	87.57 75	99.96 28	95.65 78	99.72 31	99.78 37

XVS		96.47 35	96.37 33	96.77 70	99.62 22	90.66 121	99.43 52	97.58 102	92.41 71	96.86 62	98.96 59	87.37 80	99.87 49	95.65 78	99.43 59	99.78 37

X-MVStestdata		90.69 174	88.66 196	96.77 70	99.62 22	90.66 121	99.43 52	97.58 102	92.41 71	96.86 62	29.59 378	87.37 80	99.87 49	95.65 78	99.43 59	99.78 37

SR-MVS		96.13 43	96.16 42	96.07 104	99.42 47	89.04 152	98.59 147	97.33 141	90.44 114	96.84 64	99.12 41	86.75 95	99.41 112	97.47 45	99.44 58	99.76 44

TSAR-MVS + GP.		96.95 24	96.91 21	97.07 53	98.88 79	91.62 94	99.58 30	96.54 191	95.09 20	96.84 64	98.63 89	91.16 31	99.77 71	99.04 17	96.42 130	99.81 32

ACMMPR		96.28 41	96.14 44	96.73 74	99.68 9	90.47 123	99.47 42	97.80 58	90.54 111	96.83 66	99.03 51	86.51 104	99.95 31	95.65 78	99.72 31	99.75 45

test_fmvs1		92.35 141	92.94 116	90.57 249	97.19 125	75.43 331	99.55 33	94.97 287	95.20 19	96.82 67	97.57 133	59.59 312	99.84 57	97.30 48	98.29 100	96.46 209

PMMVS		93.62 111	93.90 94	92.79 200	96.79 142	81.40 296	98.85 116	96.81 177	91.25 95	96.82 67	98.15 113	77.02 210	98.13 167	93.15 129	96.30 134	98.83 132

PGM-MVS		95.85 53	95.65 58	96.45 90	99.50 42	89.77 143	98.22 186	98.90 12	89.19 147	96.74 69	98.95 61	85.91 115	99.92 38	93.94 113	99.46 55	99.66 58

jason		95.40 66	94.86 71	97.03 55	92.91 265	94.23 52	99.70 17	96.30 204	93.56 50	96.73 70	98.52 94	81.46 182	97.91 179	96.08 73	98.47 97	98.96 116
jason: jason.
新几何1				97.40 43	98.92 77	92.51 86		97.77 63	85.52 232	96.69 71	99.06 48	88.08 69	99.89 45	84.88 218	99.62 44	99.79 35

SR-MVS-dyc-post		95.75 59	95.86 49	95.41 125	99.22 59	87.26 200	98.40 170	97.21 149	89.63 134	96.67 72	98.97 55	86.73 97	99.36 116	96.62 61	99.31 65	99.60 65

RE-MVS-def			95.70 55		99.22 59	87.26 200	98.40 170	97.21 149	89.63 134	96.67 72	98.97 55	85.24 125		96.62 61	99.31 65	99.60 65

APD-MVS_3200maxsize		95.64 62	95.65 58	95.62 119	99.24 58	87.80 180	98.42 165	97.22 148	88.93 157	96.64 74	98.98 54	85.49 120	99.36 116	96.68 60	99.27 68	99.70 51

mvsany_test1		94.57 88	95.09 68	92.98 196	95.84 177	82.07 289	98.76 127	95.24 280	92.87 63	96.45 75	98.71 83	84.81 130	99.15 127	97.68 42	95.49 148	97.73 178

MG-MVS		97.24 16	96.83 25	98.47 13	99.79 5	95.71 16	99.07 94	99.06 9	94.45 26	96.42 76	98.70 84	88.81 59	99.74 74	95.35 87	99.86 12	99.97 7

test_fmvs1_n		91.07 165	91.41 147	90.06 263	94.10 233	74.31 335	99.18 74	94.84 291	94.81 21	96.37 77	97.46 137	50.86 342	99.82 63	97.14 51	97.90 103	96.04 215

h-mvs33		92.47 140	91.95 136	94.05 174	97.13 130	85.01 251	98.36 176	98.08 39	93.85 41	96.27 78	96.73 171	83.19 152	99.43 108	95.81 76	68.09 334	97.70 179

hse-mvs2		91.67 155	91.51 145	92.15 213	96.22 162	82.61 285	97.74 221	97.53 111	93.85 41	96.27 78	96.15 184	83.19 152	97.44 214	95.81 76	66.86 341	96.40 211

alignmvs		95.77 57	95.00 70	98.06 26	97.35 120	95.68 17	99.71 16	97.50 119	91.50 88	96.16 80	98.61 91	86.28 108	99.00 136	96.19 70	91.74 189	99.51 73

CP-MVS		96.22 42	96.15 43	96.42 92	99.67 10	89.62 146	99.70 17	97.61 94	90.07 126	96.00 81	99.16 34	87.43 78	99.92 38	96.03 74	99.72 31	99.70 51

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 9	99.70 17	97.98 46	97.18 2	95.96 82	99.33 19	92.62 26	100.00 1	98.99 18	99.93 1	99.98 6

diffmvs		94.59 87	94.19 81	95.81 113	95.54 187	90.69 119	98.70 131	95.68 254	91.61 85	95.96 82	97.81 118	80.11 188	98.06 172	96.52 66	95.76 143	98.67 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		95.97 49	95.66 56	96.90 65	99.49 45	91.22 100	99.45 48	97.48 122	89.69 132	95.89 84	98.72 80	86.37 107	99.95 31	94.62 106	99.22 70	99.52 71

DeepC-MVS_fast	93.52 2	97.16 20	96.84 24	98.13 22	99.61 24	94.45 47	98.85 116	97.64 87	96.51 8	95.88 85	99.39 18	87.35 84	99.99 5	96.61 63	99.69 36	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 92	91.21 101	98.08 201	97.58 102	83.74 261	95.87 86	99.02 52	86.74 96			99.64 40	99.81 32

ZNCC-MVS		96.09 44	95.81 52	96.95 64	99.42 47	91.19 102	99.55 33	97.53 111	89.72 131	95.86 87	98.94 64	86.59 100	99.97 21	95.13 91	99.56 50	99.68 54

canonicalmvs		95.02 73	93.96 91	98.20 19	97.53 117	95.92 15	98.71 129	96.19 213	91.78 83	95.86 87	98.49 98	79.53 193	99.03 135	96.12 71	91.42 195	99.66 58

dcpmvs_2		95.67 61	96.18 37	94.12 170	98.82 81	84.22 261	97.37 234	95.45 267	90.70 104	95.77 89	98.63 89	90.47 42	98.68 150	99.20 16	99.22 70	99.45 77

Effi-MVS+		93.87 102	93.15 109	96.02 106	95.79 178	90.76 117	96.70 264	95.78 247	86.98 209	95.71 90	97.17 152	79.58 191	98.01 177	94.57 107	96.09 138	99.31 88

HPM-MVS_fast		94.89 74	94.62 73	95.70 117	99.11 66	88.44 170	99.14 86	97.11 161	85.82 228	95.69 91	98.47 100	83.46 145	99.32 121	93.16 128	99.63 43	99.35 84

HY-MVS	88.56 7	95.29 67	94.23 79	98.48 12	97.72 108	96.41 11	94.03 310	98.74 14	92.42 70	95.65 92	94.76 209	86.52 103	99.49 98	95.29 89	92.97 168	99.53 70

CHOSEN 280x420		96.80 28	96.85 23	96.66 80	97.85 106	94.42 49	94.76 302	98.36 24	92.50 67	95.62 93	97.52 134	97.92 1	97.38 217	98.31 33	98.80 86	98.20 169

MP-MVS		96.00 46	95.82 50	96.54 86	99.47 46	90.13 131	99.36 62	97.41 134	90.64 108	95.49 94	98.95 61	85.51 119	99.98 9	96.00 75	99.59 49	99.52 71
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS		95.41 65	95.22 64	95.99 108	99.29 55	89.14 150	99.17 77	97.09 165	87.28 204	95.40 95	98.48 99	84.93 127	99.38 114	95.64 82	99.65 38	99.47 76
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 120	92.62 122	95.34 127	96.27 160	88.53 169	95.88 289	96.97 174	90.90 100	95.37 96	97.07 156	82.38 170	99.10 133	83.91 234	94.86 154	98.38 158

sss		94.85 76	93.94 92	97.58 38	96.43 152	94.09 57	98.93 110	99.16 8	89.50 141	95.27 97	97.85 116	81.50 180	99.65 84	92.79 135	94.02 160	98.99 113

WTY-MVS		95.97 49	95.11 67	98.54 11	97.62 112	96.65 8	99.44 49	98.74 14	92.25 75	95.21 98	98.46 102	86.56 102	99.46 104	95.00 96	92.69 172	99.50 74

DELS-MVS		97.12 21	96.60 29	98.68 9	98.03 102	96.57 10	99.84 3	97.84 51	96.36 9	95.20 99	98.24 108	88.17 66	99.83 60	96.11 72	99.60 48	99.64 60
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 29	96.69 27	96.72 76	98.58 88	91.00 112	99.14 86	99.45 1	93.86 40	95.15 100	98.73 78	88.48 62	99.76 72	97.23 50	99.56 50	99.40 80

MVS_Test		93.67 109	92.67 121	96.69 78	96.72 144	92.66 81	97.22 243	96.03 222	87.69 197	95.12 101	94.03 218	81.55 179	98.28 162	89.17 175	96.46 128	99.14 101

MVS_111021_LR		95.78 56	95.94 46	95.28 129	98.19 97	87.69 181	98.80 121	99.26 7	93.39 51	95.04 102	98.69 85	84.09 137	99.76 72	96.96 56	99.06 74	98.38 158

CostFormer		92.89 130	92.48 125	94.12 170	94.99 213	85.89 232	92.89 319	97.00 173	86.98 209	95.00 103	90.78 281	90.05 48	97.51 210	92.92 132	91.73 190	98.96 116

mPP-MVS		95.90 52	95.75 54	96.38 94	99.58 30	89.41 149	99.26 69	97.41 134	90.66 105	94.82 104	98.95 61	86.15 111	99.98 9	95.24 90	99.64 40	99.74 46

EI-MVSNet-Vis-set		95.76 58	95.63 60	96.17 101	99.14 64	90.33 124	98.49 158	97.82 54	91.92 81	94.75 105	98.88 69	87.06 89	99.48 102	95.40 86	97.17 122	98.70 143

LFMVS		92.23 146	90.84 159	96.42 92	98.24 94	91.08 109	98.24 185	96.22 210	83.39 268	94.74 106	98.31 105	61.12 308	98.85 140	94.45 108	92.82 169	99.32 87

tpmrst		92.78 131	92.16 130	94.65 150	96.27 160	87.45 191	91.83 327	97.10 164	89.10 151	94.68 107	90.69 285	88.22 65	97.73 197	89.78 164	91.80 188	98.77 139

test_yl		95.27 68	94.60 74	97.28 47	98.53 89	92.98 77	99.05 97	98.70 17	86.76 215	94.65 108	97.74 123	87.78 72	99.44 105	95.57 83	92.61 173	99.44 78

DCV-MVSNet		95.27 68	94.60 74	97.28 47	98.53 89	92.98 77	99.05 97	98.70 17	86.76 215	94.65 108	97.74 123	87.78 72	99.44 105	95.57 83	92.61 173	99.44 78

DP-MVS Recon		95.85 53	95.15 66	97.95 28	99.87 2	94.38 50	99.60 28	97.48 122	86.58 218	94.42 110	99.13 40	87.36 83	99.98 9	93.64 120	98.33 99	99.48 75

MTAPA		96.09 44	95.80 53	96.96 63	99.29 55	91.19 102	97.23 242	97.45 127	92.58 65	94.39 111	99.24 24	86.43 106	99.99 5	96.22 69	99.40 62	99.71 50

CPTT-MVS		94.60 86	94.43 76	95.09 133	99.66 12	86.85 205	99.44 49	97.47 124	83.22 270	94.34 112	98.96 59	82.50 165	99.55 92	94.81 99	99.50 53	98.88 126

PVSNet_BlendedMVS		93.36 118	93.20 107	93.84 181	98.77 83	91.61 95	99.47 42	98.04 42	91.44 90	94.21 113	92.63 250	83.50 143	99.87 49	97.41 46	83.37 248	90.05 311

PVSNet_Blended		95.94 51	95.66 56	96.75 72	98.77 83	91.61 95	99.88 1	98.04 42	93.64 48	94.21 113	97.76 121	83.50 143	99.87 49	97.41 46	97.75 109	98.79 136

EI-MVSNet-UG-set		95.43 63	95.29 62	95.86 112	99.07 70	89.87 140	98.43 164	97.80 58	91.78 83	94.11 115	98.77 74	86.25 110	99.48 102	94.95 98	96.45 129	98.22 167

EIA-MVS		95.11 70	95.27 63	94.64 151	96.34 157	86.51 209	99.59 29	96.62 182	92.51 66	94.08 116	98.64 87	86.05 112	98.24 164	95.07 93	98.50 96	99.18 99

MAR-MVS		94.43 90	94.09 85	95.45 123	99.10 68	87.47 190	98.39 174	97.79 60	88.37 174	94.02 117	99.17 33	78.64 202	99.91 40	92.48 137	98.85 84	98.96 116
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 37	95.94 46	97.58 38	94.10 233	95.25 22	98.93 110	98.17 33	94.26 28	93.94 118	98.72 80	89.68 51	97.88 182	96.36 68	99.29 67	99.62 64

GG-mvs-BLEND				96.98 61	96.53 148	94.81 39	87.20 347	97.74 65		93.91 119	96.40 179	96.56 2	96.94 231	95.08 92	98.95 81	99.20 98

API-MVS		94.78 78	94.18 83	96.59 82	99.21 61	90.06 136	98.80 121	97.78 61	83.59 265	93.85 120	99.21 26	83.79 140	99.97 21	92.37 138	99.00 77	99.74 46

tpm2		91.77 153	91.09 152	93.82 182	94.83 220	85.56 241	92.51 324	97.16 156	84.00 256	93.83 121	90.66 287	87.54 76	97.17 221	87.73 189	91.55 193	98.72 141

PAPR		96.35 37	95.82 50	97.94 29	99.63 18	94.19 54	99.42 54	97.55 107	92.43 68	93.82 122	99.12 41	87.30 85	99.91 40	94.02 111	99.06 74	99.74 46

PVSNet	87.13 12	93.69 106	92.83 118	96.28 97	97.99 103	90.22 128	99.38 58	98.93 11	91.42 92	93.66 123	97.68 126	71.29 254	99.64 86	87.94 187	97.20 119	98.98 114

baseline		93.91 100	93.30 104	95.72 116	95.10 208	90.07 133	97.48 230	95.91 238	91.03 97	93.54 124	97.68 126	79.58 191	98.02 176	94.27 110	95.14 151	99.08 108

test2506		94.80 77	94.21 80	96.58 83	96.41 153	92.18 89	98.01 205	98.96 10	90.82 102	93.46 125	97.28 143	85.92 113	98.45 155	89.82 163	97.19 120	99.12 104

VDD-MVS		91.24 164	90.18 170	94.45 157	97.08 133	85.84 235	98.40 170	96.10 218	86.99 206	93.36 126	98.16 112	54.27 331	99.20 124	96.59 64	90.63 203	98.31 164

VDDNet		90.08 187	88.54 202	94.69 149	94.41 228	87.68 182	98.21 188	96.40 198	76.21 329	93.33 127	97.75 122	54.93 329	98.77 143	94.71 103	90.96 198	97.61 184

thisisatest0515		94.75 79	94.19 81	96.43 91	96.13 172	92.64 84	99.47 42	97.60 96	87.55 200	93.17 128	97.59 131	94.71 13	98.42 156	88.28 181	93.20 165	98.24 166

MP-MVS-pluss		95.80 55	95.30 61	97.29 46	98.95 76	92.66 81	98.59 147	97.14 157	88.95 155	93.12 129	99.25 22	85.62 116	99.94 34	96.56 65	99.48 54	99.28 91
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 104	91.38 333		87.45 202	93.08 130		86.67 98		87.02 193		98.95 120

EPNet_dtu		92.28 144	92.15 131	92.70 203	97.29 122	84.84 253	98.64 139	97.82 54	92.91 61	93.02 131	97.02 158	85.48 122	95.70 297	72.25 321	94.89 153	97.55 185
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		90.00 188	87.71 210	96.89 69	96.15 167	94.69 43	85.15 353	97.74 65	68.32 353	92.97 132	60.16 366	96.10 3	96.84 233	93.89 114	98.87 83	99.14 101

casdiffmvs		93.98 98	93.43 100	95.61 120	95.07 210	89.86 141	98.80 121	95.84 246	90.98 99	92.74 133	97.66 128	79.71 190	98.10 169	94.72 102	95.37 149	98.87 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
114514_t		94.06 94	93.05 111	97.06 54	99.08 69	92.26 87	98.97 108	97.01 172	82.58 283	92.57 134	98.22 109	80.68 186	99.30 122	89.34 171	99.02 76	99.63 62

OMC-MVS		93.90 101	93.62 98	94.73 148	98.63 87	87.00 203	98.04 204	96.56 189	92.19 76	92.46 135	98.73 78	79.49 194	99.14 131	92.16 140	94.34 158	98.03 172

PAPM_NR		95.43 63	95.05 69	96.57 85	99.42 47	90.14 129	98.58 149	97.51 116	90.65 107	92.44 136	98.90 66	87.77 74	99.90 43	90.88 150	99.32 64	99.68 54

UGNet		91.91 152	90.85 158	95.10 132	97.06 134	88.69 165	98.01 205	98.24 29	92.41 71	92.39 137	93.61 231	60.52 309	99.68 78	88.14 183	97.25 118	96.92 200
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			90.47 168		96.14 169	88.55 167	91.34 334	97.51 116	89.58 137	92.24 138	90.50 298	86.99 92	97.61 204	77.64 283	92.34 178

FE-MVS		91.38 160	90.16 171	95.05 136	96.46 151	87.53 188	89.69 344	97.84 51	82.97 275	92.18 139	92.00 259	84.07 138	98.93 139	80.71 262	95.52 147	98.68 144

Vis-MVSNet		92.64 134	91.85 137	95.03 137	95.12 204	88.23 171	98.48 160	96.81 177	91.61 85	92.16 140	97.22 148	71.58 252	98.00 178	85.85 211	97.81 105	98.88 126
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 147	91.08 153	95.64 118	96.05 173	88.98 154	91.60 331	97.25 143	86.99 206	91.84 141	92.12 253	83.03 155	99.00 136	86.91 197	93.91 161	98.93 122

TESTMET0.1,1		93.82 103	93.26 106	95.49 122	95.21 198	90.25 126	99.15 83	97.54 110	89.18 148	91.79 142	94.87 206	89.13 54	97.63 202	86.21 204	96.29 135	98.60 148

thisisatest0530		94.00 96	93.52 99	95.43 124	95.76 180	90.02 138	98.99 105	97.60 96	86.58 218	91.74 143	97.36 142	94.78 12	98.34 158	86.37 203	92.48 176	97.94 175

AUN-MVS		90.17 184	89.50 177	92.19 211	96.21 163	82.67 283	97.76 220	97.53 111	88.05 183	91.67 144	96.15 184	83.10 154	97.47 211	88.11 184	66.91 340	96.43 210

EPMVS		92.59 137	91.59 143	95.59 121	97.22 124	90.03 137	91.78 328	98.04 42	90.42 115	91.66 145	90.65 288	86.49 105	97.46 212	81.78 255	96.31 133	99.28 91

test-LLR		93.11 127	92.68 120	94.40 158	94.94 216	87.27 198	99.15 83	97.25 143	90.21 118	91.57 146	94.04 216	84.89 128	97.58 206	85.94 208	96.13 136	98.36 161

test-mter		93.27 122	92.89 117	94.40 158	94.94 216	87.27 198	99.15 83	97.25 143	88.95 155	91.57 146	94.04 216	88.03 70	97.58 206	85.94 208	96.13 136	98.36 161

JIA-IIPM		85.97 254	84.85 254	89.33 284	93.23 260	73.68 338	85.05 354	97.13 159	69.62 349	91.56 148	68.03 364	88.03 70	96.96 229	77.89 282	93.12 166	97.34 188

casdiffmvs_mvg		94.00 96	93.33 103	96.03 105	95.22 197	90.90 115	99.09 92	95.99 223	90.58 109	91.55 149	97.37 141	79.91 189	98.06 172	95.01 95	95.22 150	99.13 103
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		94.67 84	94.11 84	96.34 96	97.14 129	91.10 107	99.32 66	97.43 132	92.10 80	91.53 150	96.38 182	83.29 149	99.68 78	93.42 125	96.37 131	98.25 165

CHOSEN 1792x2688		94.35 91	93.82 95	95.95 110	97.40 118	88.74 164	98.41 167	98.27 26	92.18 77	91.43 151	96.40 179	78.88 197	99.81 66	93.59 121	97.81 105	99.30 89

ACMMP		94.67 84	94.30 77	95.79 114	99.25 57	88.13 174	98.41 167	98.67 20	90.38 116	91.43 151	98.72 80	82.22 172	99.95 31	93.83 117	95.76 143	99.29 90
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		92.29 143	91.33 148	95.15 131	96.41 153	87.84 179	98.10 198	94.84 291	90.82 102	91.42 153	97.28 143	65.61 290	98.49 154	90.33 157	97.19 120	99.12 104

EPP-MVSNet		93.75 105	93.67 97	94.01 176	95.86 176	85.70 237	98.67 135	97.66 81	84.46 250	91.36 154	97.18 151	91.16 31	97.79 188	92.93 131	93.75 162	98.53 150

PLC	91.07 3	94.23 93	94.01 87	94.87 141	99.17 63	87.49 189	99.25 70	96.55 190	88.43 172	91.26 155	98.21 111	85.92 113	99.86 54	89.77 165	97.57 111	97.24 191
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 108	93.29 105	94.87 141	97.57 116	88.04 176	98.18 190	98.47 22	87.57 199	91.24 156	95.05 203	85.49 120	97.46 212	93.22 127	92.82 169	99.10 106

thres200		93.69 106	92.59 123	96.97 62	97.76 107	94.74 41	99.35 63	99.36 2	89.23 146	91.21 157	96.97 160	83.42 146	98.77 143	85.08 215	90.96 198	97.39 187

test1111		92.12 148	91.19 151	94.94 139	96.15 167	87.36 194	98.12 195	94.84 291	90.85 101	90.97 158	97.26 145	65.60 291	98.37 157	89.74 166	97.14 123	99.07 110

CDS-MVSNet		93.47 113	93.04 112	94.76 145	94.75 222	89.45 148	98.82 119	97.03 170	87.91 188	90.97 158	96.48 177	89.06 55	96.36 260	89.50 167	92.81 171	98.49 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 115	92.27 128	96.90 65	97.68 110	94.84 36	99.18 74	99.36 2	88.45 169	90.79 160	96.90 164	83.31 147	98.75 145	84.11 230	90.69 200	97.12 193

thres400		93.39 117	92.27 128	96.73 74	97.68 110	94.84 36	99.18 74	99.36 2	88.45 169	90.79 160	96.90 164	83.31 147	98.75 145	84.11 230	90.69 200	96.61 202

CR-MVSNet		88.83 208	87.38 215	93.16 193	93.47 253	86.24 219	84.97 355	94.20 311	88.92 158	90.76 162	86.88 333	84.43 133	94.82 317	70.64 325	92.17 183	98.41 155

RPMNet		85.07 268	81.88 285	94.64 151	93.47 253	86.24 219	84.97 355	97.21 149	64.85 360	90.76 162	78.80 357	80.95 185	99.27 123	53.76 362	92.17 183	98.41 155

PatchmatchNet		92.05 151	91.04 154	95.06 134	96.17 166	89.04 152	91.26 335	97.26 142	89.56 139	90.64 164	90.56 294	88.35 64	97.11 223	79.53 268	96.07 140	99.03 111
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		93.30 120	93.01 114	94.17 168	95.57 185	86.47 211	98.51 155	97.60 96	85.99 226	90.55 165	97.19 150	94.80 11	98.31 159	85.06 216	91.86 186	97.74 177

PatchT		85.44 264	83.19 272	92.22 209	93.13 262	83.00 275	83.80 361	96.37 200	70.62 344	90.55 165	79.63 356	84.81 130	94.87 315	58.18 358	91.59 192	98.79 136

tpm		89.67 193	88.95 189	91.82 220	92.54 268	81.43 295	92.95 318	95.92 233	87.81 190	90.50 167	89.44 313	84.99 126	95.65 298	83.67 237	82.71 254	98.38 158

thres100view900		93.34 119	92.15 131	96.90 65	97.62 112	94.84 36	99.06 96	99.36 2	87.96 186	90.47 168	96.78 169	83.29 149	98.75 145	84.11 230	90.69 200	97.12 193

thres600view7		93.18 125	92.00 134	96.75 72	97.62 112	94.92 31	99.07 94	99.36 2	87.96 186	90.47 168	96.78 169	83.29 149	98.71 149	82.93 244	90.47 204	96.61 202

AdaColmap		93.82 103	93.06 110	96.10 103	99.88 1	89.07 151	98.33 178	97.55 107	86.81 214	90.39 170	98.65 86	75.09 217	99.98 9	93.32 126	97.53 114	99.26 93

XVG-OURS-SEG-HR		90.95 168	90.66 165	91.83 219	95.18 202	81.14 303	95.92 286	95.92 233	88.40 173	90.33 171	97.85 116	70.66 257	99.38 114	92.83 133	88.83 209	94.98 220

IS-MVSNet		93.00 129	92.51 124	94.49 154	96.14 169	87.36 194	98.31 181	95.70 252	88.58 165	90.17 172	97.50 135	83.02 156	97.22 220	87.06 192	96.07 140	98.90 125

CSCG		94.87 75	94.71 72	95.36 126	99.54 36	86.49 210	99.34 64	98.15 36	82.71 281	90.15 173	99.25 22	89.48 52	99.86 54	94.97 97	98.82 85	99.72 49

SCA		90.64 175	89.25 184	94.83 144	94.95 215	88.83 160	96.26 276	97.21 149	90.06 127	90.03 174	90.62 290	66.61 282	96.81 235	83.16 240	94.36 157	98.84 129

XVG-OURS		90.83 170	90.49 167	91.86 218	95.23 196	81.25 300	95.79 294	95.92 233	88.96 154	90.02 175	98.03 115	71.60 251	99.35 119	91.06 147	87.78 213	94.98 220

ADS-MVSNet2		87.62 230	86.88 223	89.86 270	96.21 163	79.14 314	87.15 348	92.99 326	83.01 273	89.91 176	87.27 329	78.87 198	92.80 339	74.20 309	92.27 180	97.64 180

ADS-MVSNet		88.99 200	87.30 216	94.07 172	96.21 163	87.56 187	87.15 348	96.78 179	83.01 273	89.91 176	87.27 329	78.87 198	97.01 228	74.20 309	92.27 180	97.64 180

ab-mvs		91.05 167	89.17 185	96.69 78	95.96 174	91.72 93	92.62 323	97.23 147	85.61 231	89.74 178	93.89 224	68.55 266	99.42 109	91.09 146	87.84 212	98.92 124

TAMVS		92.62 135	92.09 133	94.20 167	94.10 233	87.68 182	98.41 167	96.97 174	87.53 201	89.74 178	96.04 188	84.77 132	96.49 253	88.97 177	92.31 179	98.42 154

Vis-MVSNet (Re-imp)		93.26 123	93.00 115	94.06 173	96.14 169	86.71 208	98.68 133	96.70 180	88.30 176	89.71 180	97.64 129	85.43 123	96.39 258	88.06 185	96.32 132	99.08 108

CNLPA		93.64 110	92.74 119	96.36 95	98.96 75	90.01 139	99.19 72	95.89 241	86.22 224	89.40 181	98.85 70	80.66 187	99.84 57	88.57 178	96.92 124	99.24 94

Anonymous202405211		88.84 206	87.03 221	94.27 164	98.14 99	84.18 262	98.44 163	95.58 260	76.79 328	89.34 182	96.88 166	53.42 334	99.54 94	87.53 191	87.12 216	99.09 107

Fast-Effi-MVS+		91.72 154	90.79 162	94.49 154	95.89 175	87.40 193	99.54 38	95.70 252	85.01 243	89.28 183	95.68 193	77.75 206	97.57 209	83.22 239	95.06 152	98.51 151

PatchMatch-RL		91.47 157	90.54 166	94.26 165	98.20 95	86.36 216	96.94 252	97.14 157	87.75 193	88.98 184	95.75 192	71.80 249	99.40 113	80.92 260	97.39 117	97.02 199

dp		90.16 185	88.83 192	94.14 169	96.38 156	86.42 212	91.57 332	97.06 167	84.76 247	88.81 185	90.19 306	84.29 135	97.43 215	75.05 301	91.35 197	98.56 149

DeepC-MVS	91.02 4	94.56 89	93.92 93	96.46 89	97.16 127	90.76 117	98.39 174	97.11 161	93.92 36	88.66 186	98.33 104	78.14 204	99.85 56	95.02 94	98.57 94	98.78 138
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		92.61 136	91.28 149	96.58 83	97.05 135	94.63 44	97.72 222	96.20 211	89.82 129	88.56 187	96.85 167	86.85 93	97.82 186	88.42 179	80.10 267	97.30 189

Anonymous20240529		87.66 229	85.58 242	93.92 178	97.59 115	85.01 251	98.13 193	97.13 159	66.69 358	88.47 188	96.01 189	55.09 328	99.51 96	87.00 194	84.12 239	97.23 192

CVMVSNet		90.30 180	90.91 157	88.46 297	94.32 229	73.58 339	97.61 227	97.59 100	90.16 123	88.43 189	97.10 154	76.83 211	92.86 336	82.64 246	93.54 164	98.93 122

TR-MVS		90.77 171	89.44 179	94.76 145	96.31 158	88.02 177	97.92 209	95.96 227	85.52 232	88.22 190	97.23 147	66.80 281	98.09 170	84.58 222	92.38 177	98.17 170

F-COLMAP		92.07 150	91.75 141	93.02 195	98.16 98	82.89 279	98.79 125	95.97 225	86.54 220	87.92 191	97.80 119	78.69 201	99.65 84	85.97 206	95.93 142	96.53 207

BH-RMVSNet		91.25 163	89.99 172	95.03 137	96.75 143	88.55 167	98.65 137	94.95 288	87.74 194	87.74 192	97.80 119	68.27 269	98.14 166	80.53 265	97.49 115	98.41 155

Effi-MVS+-dtu		89.97 190	90.68 164	87.81 301	95.15 203	71.98 345	97.87 213	95.40 271	91.92 81	87.57 193	91.44 269	74.27 226	96.84 233	89.45 168	93.10 167	94.60 222

HQP-NCC					93.95 238		99.16 78		93.92 36	87.57 193

ACMP_Plane					93.95 238		99.16 78		93.92 36	87.57 193

HQP4-MVS										87.57 193			97.77 190			92.72 229

HQP-MVS		91.50 156	91.23 150	92.29 208	93.95 238	86.39 214	99.16 78	96.37 200	93.92 36	87.57 193	96.67 173	73.34 232	97.77 190	93.82 118	86.29 219	92.72 229

TAPA-MVS	87.50 9	90.35 178	89.05 187	94.25 166	98.48 91	85.17 248	98.42 165	96.58 188	82.44 288	87.24 198	98.53 93	82.77 160	98.84 141	59.09 356	97.88 104	98.72 141
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 176	89.56 176	93.72 186	95.10 208	85.43 242	99.41 55	94.94 289	83.96 258	87.21 199	96.83 168	74.37 224	97.05 227	80.50 266	93.73 163	98.67 145

HQP_MVS		91.26 161	90.95 156	92.16 212	93.84 245	86.07 228	99.02 101	96.30 204	93.38 52	86.99 200	96.52 175	72.92 237	97.75 195	93.46 123	86.17 222	92.67 231

plane_prior3						85.91 231			93.65 47	86.99 200

iter_conf_final		93.22 124	93.04 112	93.76 183	97.03 136	92.22 88	99.05 97	93.31 324	92.11 79	86.93 202	95.42 198	95.01 10	96.59 242	93.98 112	84.48 234	92.46 234

GA-MVS		90.10 186	88.69 195	94.33 162	92.44 269	87.97 178	99.08 93	96.26 208	89.65 133	86.92 203	93.11 243	68.09 270	96.96 229	82.54 248	90.15 205	98.05 171

1112_ss		92.71 132	91.55 144	96.20 98	95.56 186	91.12 105	98.48 160	94.69 298	88.29 177	86.89 204	98.50 96	87.02 90	98.66 151	84.75 219	89.77 207	98.81 134

MVS_0304		84.13 282	82.66 281	88.52 295	93.07 263	80.15 308	95.81 293	98.21 31	79.27 313	86.85 205	86.40 336	41.33 357	94.69 321	76.36 293	86.69 217	90.73 295

Test_1112_low_res		92.27 145	90.97 155	96.18 99	95.53 188	91.10 107	98.47 162	94.66 299	88.28 178	86.83 206	93.50 235	87.00 91	98.65 152	84.69 220	89.74 208	98.80 135

cascas		90.93 169	89.33 183	95.76 115	95.69 182	93.03 76	98.99 105	96.59 185	80.49 308	86.79 207	94.45 213	65.23 293	98.60 153	93.52 122	92.18 182	95.66 218

iter_conf05		93.48 112	93.18 108	94.39 161	97.15 128	94.17 55	99.30 67	92.97 327	92.38 74	86.70 208	95.42 198	95.67 5	96.59 242	94.67 104	84.32 237	92.39 235

baseline2		94.04 95	93.80 96	94.74 147	93.07 263	90.25 126	98.12 195	98.16 35	89.86 128	86.53 209	96.95 161	95.56 6	98.05 174	91.44 144	94.53 155	95.93 216

OPM-MVS		89.76 192	89.15 186	91.57 228	90.53 298	85.58 240	98.11 197	95.93 232	92.88 62	86.05 210	96.47 178	67.06 280	97.87 183	89.29 174	86.08 224	91.26 279
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 199	87.66 211	93.45 188	92.56 267	91.02 111	97.97 208	98.32 25	86.92 211	86.03 211	92.01 257	68.84 265	97.10 225	90.92 149	75.34 288	92.23 242

tpm cat1		88.89 204	87.27 217	93.76 183	95.79 178	85.32 245	90.76 340	97.09 165	76.14 330	85.72 212	88.59 319	82.92 157	98.04 175	76.96 287	91.43 194	97.90 176

IB-MVS	89.43 6	92.12 148	90.83 161	95.98 109	95.40 193	90.78 116	99.81 6	98.06 40	91.23 96	85.63 213	93.66 230	90.63 40	98.78 142	91.22 145	71.85 324	98.36 161
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		89.87 191	89.38 182	91.36 231	94.32 229	85.87 233	97.61 227	96.59 185	85.10 238	85.51 214	97.10 154	81.30 184	96.56 246	83.85 236	83.03 251	91.64 258

MVSTER		92.71 132	92.32 126	93.86 180	97.29 122	92.95 79	99.01 103	96.59 185	90.09 124	85.51 214	94.00 220	94.61 16	96.56 246	90.77 154	83.03 251	92.08 250

test_fmvs2		85.10 267	85.45 245	84.02 325	89.85 307	65.63 357	98.49 158	92.59 332	90.45 113	85.43 216	93.32 236	43.94 351	96.59 242	90.81 152	84.19 238	89.85 315

RPSCF		85.33 265	85.55 243	84.67 322	94.63 225	62.28 359	93.73 312	93.76 316	74.38 337	85.23 217	97.06 157	64.09 296	98.31 159	80.98 258	86.08 224	93.41 228

BH-w/o		92.32 142	91.79 139	93.91 179	96.85 139	86.18 223	99.11 91	95.74 250	88.13 181	84.81 218	97.00 159	77.26 209	97.91 179	89.16 176	98.03 102	97.64 180

mvsmamba		89.99 189	89.42 180	91.69 226	90.64 297	86.34 217	98.40 170	92.27 336	91.01 98	84.80 219	94.93 204	76.12 212	96.51 250	92.81 134	83.84 241	92.21 244

CLD-MVS		91.06 166	90.71 163	92.10 214	94.05 237	86.10 226	99.55 33	96.29 207	94.16 31	84.70 220	97.17 152	69.62 261	97.82 186	94.74 101	86.08 224	92.39 235
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 198	87.76 208	93.35 189	97.19 125	84.75 255	90.58 342	97.36 139	81.99 293	84.56 221	89.31 316	83.98 139	98.17 165	74.85 304	90.00 206	97.12 193

nrg030		90.23 181	88.87 190	94.32 163	91.53 285	93.54 65	98.79 125	95.89 241	88.12 182	84.55 222	94.61 211	78.80 200	96.88 232	92.35 139	75.21 289	92.53 233

VPNet		88.30 217	86.57 227	93.49 187	91.95 277	91.35 99	98.18 190	97.20 153	88.61 163	84.52 223	94.89 205	62.21 303	96.76 238	89.34 171	72.26 321	92.36 237

MVS		93.92 99	92.28 127	98.83 6	95.69 182	96.82 7	96.22 279	98.17 33	84.89 245	84.34 224	98.61 91	79.32 195	99.83 60	93.88 115	99.43 59	99.86 29

mvs_anonymous		92.50 139	91.65 142	95.06 134	96.60 146	89.64 145	97.06 248	96.44 197	86.64 217	84.14 225	93.93 222	82.49 166	96.17 276	91.47 143	96.08 139	99.35 84

Fast-Effi-MVS+-dtu		88.84 206	88.59 199	89.58 278	93.44 256	78.18 321	98.65 137	94.62 300	88.46 168	84.12 226	95.37 201	68.91 263	96.52 249	82.06 252	91.70 191	94.06 223

LS3D		90.19 183	88.72 194	94.59 153	98.97 73	86.33 218	96.90 254	96.60 184	74.96 334	84.06 227	98.74 77	75.78 214	99.83 60	74.93 302	97.57 111	97.62 183

ACMM	86.95 13	88.77 211	88.22 206	90.43 254	93.61 250	81.34 298	98.50 156	95.92 233	87.88 189	83.85 228	95.20 202	67.20 278	97.89 181	86.90 198	84.90 230	92.06 251
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 158	90.84 159	93.33 190	96.51 150	84.83 254	98.84 118	95.50 264	86.44 223	83.50 229	96.70 172	75.49 216	97.77 190	86.78 200	97.81 105	97.40 186

FIs		90.70 173	89.87 173	93.18 192	92.29 270	91.12 105	98.17 192	98.25 27	89.11 150	83.44 230	94.82 208	82.26 171	96.17 276	87.76 188	82.76 253	92.25 240

bld_raw_dy_0_64		87.82 222	86.71 226	91.15 234	89.54 313	85.61 238	97.37 234	89.16 360	89.26 145	83.42 231	94.50 212	65.79 287	96.18 274	88.00 186	83.37 248	91.67 257

UniMVSNet (Re)		89.50 197	88.32 204	93.03 194	92.21 272	90.96 113	98.90 114	98.39 23	89.13 149	83.22 232	92.03 255	81.69 178	96.34 266	86.79 199	72.53 317	91.81 255

UniMVSNet_NR-MVSNet		89.60 194	88.55 201	92.75 202	92.17 273	90.07 133	98.74 128	98.15 36	88.37 174	83.21 233	93.98 221	82.86 158	95.93 287	86.95 195	72.47 318	92.25 240

DU-MVS		88.83 208	87.51 212	92.79 200	91.46 286	90.07 133	98.71 129	97.62 93	88.87 159	83.21 233	93.68 228	74.63 218	95.93 287	86.95 195	72.47 318	92.36 237

LPG-MVS_test		88.86 205	88.47 203	90.06 263	93.35 258	80.95 305	98.22 186	95.94 230	87.73 195	83.17 235	96.11 186	66.28 285	97.77 190	90.19 159	85.19 228	91.46 269

LGP-MVS_train				90.06 263	93.35 258	80.95 305		95.94 230	87.73 195	83.17 235	96.11 186	66.28 285	97.77 190	90.19 159	85.19 228	91.46 269

miper_enhance_ethall		90.33 179	89.70 174	92.22 209	97.12 131	88.93 158	98.35 177	95.96 227	88.60 164	83.14 237	92.33 252	87.38 79	96.18 274	86.49 202	77.89 276	91.55 266

FC-MVSNet-test		90.22 182	89.40 181	92.67 205	91.78 281	89.86 141	97.89 210	98.22 30	88.81 160	82.96 238	94.66 210	81.90 177	95.96 285	85.89 210	82.52 256	92.20 245

PCF-MVS	89.78 5	91.26 161	89.63 175	96.16 102	95.44 190	91.58 97	95.29 298	96.10 218	85.07 240	82.75 239	97.45 138	78.28 203	99.78 70	80.60 264	95.65 146	97.12 193
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 236	85.68 241	90.98 239	89.91 304	86.08 227	98.32 180	95.61 258	83.67 264	82.72 240	90.67 286	74.00 229	96.53 248	81.94 254	74.28 301	90.32 304

v1144		86.83 239	85.31 247	91.40 229	89.75 308	87.21 202	98.31 181	95.45 267	83.22 270	82.70 241	90.78 281	73.36 231	96.36 260	79.49 269	74.69 295	90.63 299

v144192		86.40 248	84.89 253	90.91 240	89.48 315	85.59 239	98.21 188	95.43 270	82.45 287	82.62 242	90.58 293	72.79 240	96.36 260	78.45 279	74.04 305	90.79 291

3Dnovator	87.35 11	93.17 126	91.77 140	97.37 45	95.41 192	93.07 74	98.82 119	97.85 50	91.53 87	82.56 243	97.58 132	71.97 246	99.82 63	91.01 148	99.23 69	99.22 97

v2v482		87.27 234	85.76 239	91.78 225	89.59 310	87.58 186	98.56 150	95.54 262	84.53 249	82.51 244	91.78 263	73.11 236	96.47 254	82.07 251	74.14 304	91.30 277

tt0805		86.50 247	84.79 256	91.63 227	91.97 275	81.49 294	96.49 268	97.38 137	82.24 290	82.44 245	95.82 191	51.22 339	98.25 163	84.55 223	80.96 263	95.13 219

Baseline_NR-MVSNet		85.83 257	84.82 255	88.87 293	88.73 323	83.34 272	98.63 140	91.66 345	80.41 311	82.44 245	91.35 271	74.63 218	95.42 304	84.13 229	71.39 327	87.84 333

v1192		86.32 250	84.71 258	91.17 233	89.53 314	86.40 213	98.13 193	95.44 269	82.52 285	82.42 247	90.62 290	71.58 252	96.33 267	77.23 284	74.88 292	90.79 291

RRT_MVS		88.91 203	88.56 200	89.93 268	90.31 301	81.61 293	98.08 201	96.38 199	89.30 144	82.41 248	94.84 207	73.15 235	96.04 282	90.38 156	82.23 258	92.15 246

test_djsdf		88.26 219	87.73 209	89.84 271	88.05 331	82.21 287	97.77 218	96.17 214	86.84 212	82.41 248	91.95 261	72.07 245	95.99 283	89.83 161	84.50 233	91.32 276

cl22		89.57 195	88.79 193	91.91 217	97.94 104	87.62 185	97.98 207	96.51 192	85.03 241	82.37 250	91.79 262	83.65 141	96.50 251	85.96 207	77.89 276	91.61 263

1314		93.44 114	91.98 135	97.84 30	95.24 195	94.38 50	96.22 279	97.92 47	90.18 120	82.28 251	97.71 125	77.63 207	99.80 68	91.94 141	98.67 91	99.34 86

v1921920		86.02 253	84.44 263	90.77 246	89.32 317	85.20 246	98.10 198	95.35 275	82.19 291	82.25 252	90.71 283	70.73 255	96.30 271	76.85 289	74.49 297	90.80 290

v1240		85.77 260	84.11 266	90.73 247	89.26 318	85.15 249	97.88 212	95.23 284	81.89 296	82.16 253	90.55 295	69.60 262	96.31 268	75.59 299	74.87 293	90.72 296

XVG-ACMP-BASELINE		85.86 256	84.95 252	88.57 294	89.90 305	77.12 326	94.30 306	95.60 259	87.40 203	82.12 254	92.99 246	53.42 334	97.66 199	85.02 217	83.83 242	90.92 287

GBi-Net		86.67 242	84.96 250	91.80 221	95.11 205	88.81 161	96.77 258	95.25 277	82.94 276	82.12 254	90.25 301	62.89 300	94.97 312	79.04 272	80.24 264	91.62 260

test1		86.67 242	84.96 250	91.80 221	95.11 205	88.81 161	96.77 258	95.25 277	82.94 276	82.12 254	90.25 301	62.89 300	94.97 312	79.04 272	80.24 264	91.62 260

FMVSNet3		88.81 210	87.08 220	93.99 177	96.52 149	94.59 45	98.08 201	96.20 211	85.85 227	82.12 254	91.60 266	74.05 228	95.40 305	79.04 272	80.24 264	91.99 253

IterMVS-LS		88.34 216	87.44 213	91.04 237	94.10 233	85.85 234	98.10 198	95.48 265	85.12 237	82.03 258	91.21 274	81.35 183	95.63 299	83.86 235	75.73 287	91.63 259
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
miper_ehance_all_eth		88.94 202	88.12 207	91.40 229	95.32 194	86.93 204	97.85 214	95.55 261	84.19 253	81.97 259	91.50 268	84.16 136	95.91 290	84.69 220	77.89 276	91.36 274

MIMVSNet		84.48 276	81.83 286	92.42 207	91.73 282	87.36 194	85.52 351	94.42 306	81.40 299	81.91 260	87.58 323	51.92 337	92.81 338	73.84 312	88.15 211	97.08 197

PS-MVSNAJss		89.54 196	89.05 187	91.00 238	88.77 322	84.36 259	97.39 231	95.97 225	88.47 166	81.88 261	93.80 226	82.48 167	96.50 251	89.34 171	83.34 250	92.15 246

WR-MVS		88.54 215	87.22 219	92.52 206	91.93 279	89.50 147	98.56 150	97.84 51	86.99 206	81.87 262	93.81 225	74.25 227	95.92 289	85.29 213	74.43 298	92.12 248

TranMVSNet+NR-MVSNet		87.75 226	86.31 231	92.07 215	90.81 294	88.56 166	98.33 178	97.18 154	87.76 192	81.87 262	93.90 223	72.45 241	95.43 303	83.13 242	71.30 328	92.23 242

eth_miper_zixun_eth		87.76 225	87.00 222	90.06 263	94.67 224	82.65 284	97.02 251	95.37 273	84.19 253	81.86 264	91.58 267	81.47 181	95.90 291	83.24 238	73.61 307	91.61 263

UniMVSNet_ETH3D		85.65 263	83.79 270	91.21 232	90.41 300	80.75 307	95.36 297	95.78 247	78.76 318	81.83 265	94.33 214	49.86 344	96.66 239	84.30 225	83.52 247	96.22 213

c3_l		88.19 220	87.23 218	91.06 236	94.97 214	86.17 224	97.72 222	95.38 272	83.43 267	81.68 266	91.37 270	82.81 159	95.72 296	84.04 233	73.70 306	91.29 278

DP-MVS		88.75 212	86.56 228	95.34 127	98.92 77	87.45 191	97.64 226	93.52 322	70.55 345	81.49 267	97.25 146	74.43 223	99.88 46	71.14 324	94.09 159	98.67 145

3Dnovator+	87.72 8	93.43 115	91.84 138	98.17 20	95.73 181	95.08 30	98.92 112	97.04 168	91.42 92	81.48 268	97.60 130	74.60 220	99.79 69	90.84 151	98.97 78	99.64 60

QAPM		91.41 159	89.49 178	97.17 52	95.66 184	93.42 68	98.60 145	97.51 116	80.92 306	81.39 269	97.41 140	72.89 239	99.87 49	82.33 249	98.68 90	98.21 168

XXY-MVS		87.75 226	86.02 235	92.95 198	90.46 299	89.70 144	97.71 224	95.90 239	84.02 255	80.95 270	94.05 215	67.51 276	97.10 225	85.16 214	78.41 273	92.04 252

v148		86.38 249	85.06 249	90.37 258	89.47 316	84.10 263	98.52 152	95.48 265	83.80 260	80.93 271	90.22 304	74.60 220	96.31 268	80.92 260	71.55 326	90.69 297

DIV-MVS_self_test		87.82 222	86.81 224	90.87 243	94.87 219	85.39 244	97.81 215	95.22 285	82.92 279	80.76 272	91.31 272	81.99 174	95.81 294	81.36 256	75.04 291	91.42 272

cl____		87.82 222	86.79 225	90.89 242	94.88 218	85.43 242	97.81 215	95.24 280	82.91 280	80.71 273	91.22 273	81.97 176	95.84 292	81.34 257	75.06 290	91.40 273

FMVSNet2		86.90 237	84.79 256	93.24 191	95.11 205	92.54 85	97.67 225	95.86 245	82.94 276	80.55 274	91.17 275	62.89 300	95.29 307	77.23 284	79.71 270	91.90 254

pmmvs4		87.58 231	86.17 234	91.80 221	89.58 311	88.92 159	97.25 240	95.28 276	82.54 284	80.49 275	93.17 242	75.62 215	96.05 281	82.75 245	78.90 271	90.42 302

ACMP	87.39 10	88.71 213	88.24 205	90.12 262	93.91 243	81.06 304	98.50 156	95.67 255	89.43 142	80.37 276	95.55 194	65.67 288	97.83 185	90.55 155	84.51 232	91.47 268
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs5		85.87 255	84.40 265	90.30 259	88.53 326	84.23 260	98.60 145	93.71 318	81.53 298	80.29 277	92.02 256	64.51 295	95.52 301	82.04 253	78.34 274	91.15 281

test0.0.03 1		88.96 201	88.61 197	90.03 267	91.09 291	84.43 258	98.97 108	97.02 171	90.21 118	80.29 277	96.31 183	84.89 128	91.93 350	72.98 318	85.70 227	93.73 224

miper_lstm_enhance		86.90 237	86.20 233	89.00 290	94.53 226	81.19 301	96.74 262	95.24 280	82.33 289	80.15 279	90.51 297	81.99 174	94.68 322	80.71 262	73.58 308	91.12 282

jajsoiax		87.35 232	86.51 229	89.87 269	87.75 336	81.74 291	97.03 249	95.98 224	88.47 166	80.15 279	93.80 226	61.47 305	96.36 260	89.44 169	84.47 235	91.50 267

mvs_tets		87.09 235	86.22 232	89.71 274	87.87 332	81.39 297	96.73 263	95.90 239	88.19 180	79.99 281	93.61 231	59.96 311	96.31 268	89.40 170	84.34 236	91.43 271

ITE_SJBPF				87.93 299	92.26 271	76.44 328		93.47 323	87.67 198	79.95 282	95.49 197	56.50 321	97.38 217	75.24 300	82.33 257	89.98 313

v8		86.11 252	84.45 262	91.10 235	89.99 303	86.85 205	97.24 241	95.36 274	81.99 293	79.89 283	89.86 309	74.53 222	96.39 258	78.83 276	72.32 320	90.05 311

v10		85.73 261	84.01 268	90.87 243	90.03 302	86.73 207	97.20 244	95.22 285	81.25 301	79.85 284	89.75 310	73.30 234	96.28 272	76.87 288	72.64 316	89.61 319

WR-MVS_H		86.53 246	85.49 244	89.66 277	91.04 292	83.31 273	97.53 229	98.20 32	84.95 244	79.64 285	90.90 279	78.01 205	95.33 306	76.29 294	72.81 314	90.35 303

anonymousdsp		86.69 241	85.75 240	89.53 279	86.46 342	82.94 276	96.39 270	95.71 251	83.97 257	79.63 286	90.70 284	68.85 264	95.94 286	86.01 205	84.02 240	89.72 317

Patchmtry		83.61 287	81.64 287	89.50 280	93.36 257	82.84 281	84.10 358	94.20 311	69.47 350	79.57 287	86.88 333	84.43 133	94.78 318	68.48 333	74.30 300	90.88 288

CP-MVSNet		86.54 245	85.45 245	89.79 273	91.02 293	82.78 282	97.38 233	97.56 106	85.37 234	79.53 288	93.03 244	71.86 248	95.25 308	79.92 267	73.43 312	91.34 275

Patchmatch-test		86.25 251	84.06 267	92.82 199	94.42 227	82.88 280	82.88 362	94.23 310	71.58 342	79.39 289	90.62 290	89.00 57	96.42 257	63.03 348	91.37 196	99.16 100

DSMNet-mixed		81.60 296	81.43 290	82.10 332	84.36 348	60.79 360	93.63 314	86.74 365	79.00 314	79.32 290	87.15 331	63.87 298	89.78 356	66.89 338	91.92 185	95.73 217

MSDG		88.29 218	86.37 230	94.04 175	96.90 138	86.15 225	96.52 267	94.36 308	77.89 324	79.22 291	96.95 161	69.72 260	99.59 90	73.20 317	92.58 175	96.37 212

Anonymous20231211		84.72 271	82.65 282	90.91 240	97.71 109	84.55 257	97.28 238	96.67 181	66.88 357	79.18 292	90.87 280	58.47 315	96.60 241	82.61 247	74.20 302	91.59 265

PS-CasMVS		85.81 258	84.58 261	89.49 282	90.77 295	82.11 288	97.20 244	97.36 139	84.83 246	79.12 293	92.84 247	67.42 277	95.16 310	78.39 280	73.25 313	91.21 280

IterMVS		85.81 258	84.67 259	89.22 285	93.51 252	83.67 269	96.32 273	94.80 294	85.09 239	78.69 294	90.17 307	66.57 284	93.17 335	79.48 270	77.42 282	90.81 289
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 266	83.93 269	89.07 289	89.89 306	81.31 299	97.09 247	97.24 146	84.45 251	78.66 295	92.68 249	68.44 268	94.87 315	75.98 296	70.92 329	91.04 284

IterMVS-SCA-FT		85.73 261	84.64 260	89.00 290	93.46 255	82.90 278	96.27 274	94.70 297	85.02 242	78.62 296	90.35 299	66.61 282	93.33 332	79.38 271	77.36 283	90.76 293

OpenMVS	85.28 14	90.75 172	88.84 191	96.48 88	93.58 251	93.51 66	98.80 121	97.41 134	82.59 282	78.62 296	97.49 136	68.00 272	99.82 63	84.52 224	98.55 95	96.11 214

PVSNet_0	83.28 16	87.31 233	85.16 248	93.74 185	94.78 221	84.59 256	98.91 113	98.69 19	89.81 130	78.59 298	93.23 240	61.95 304	99.34 120	94.75 100	55.72 361	97.30 189

EU-MVSNet		84.19 280	84.42 264	83.52 328	88.64 325	67.37 356	96.04 284	95.76 249	85.29 235	78.44 299	93.18 241	70.67 256	91.48 352	75.79 298	75.98 285	91.70 256

v7n		84.42 278	82.75 279	89.43 283	88.15 329	81.86 290	96.75 261	95.67 255	80.53 307	78.38 300	89.43 314	69.89 258	96.35 265	73.83 313	72.13 322	90.07 309

FMVSNet1		83.94 284	81.32 292	91.80 221	91.94 278	88.81 161	96.77 258	95.25 277	77.98 320	78.25 301	90.25 301	50.37 343	94.97 312	73.27 316	77.81 280	91.62 260

D2MVS		87.96 221	87.39 214	89.70 275	91.84 280	83.40 271	98.31 181	98.49 21	88.04 184	78.23 302	90.26 300	73.57 230	96.79 237	84.21 227	83.53 246	88.90 327

MS-PatchMatch		86.75 240	85.92 237	89.22 285	91.97 275	82.47 286	96.91 253	96.14 216	83.74 261	77.73 303	93.53 234	58.19 316	97.37 219	76.75 290	98.35 98	87.84 333

DTE-MVSNet		84.14 281	82.80 276	88.14 298	88.95 321	79.87 311	96.81 257	96.24 209	83.50 266	77.60 304	92.52 251	67.89 274	94.24 327	72.64 320	69.05 332	90.32 304

COLMAP_ROB	82.69 18	84.54 275	82.82 275	89.70 275	96.72 144	78.85 315	95.89 287	92.83 330	71.55 343	77.54 305	95.89 190	59.40 313	99.14 131	67.26 336	88.26 210	91.11 283
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 282	83.59 271	85.77 315	87.81 333	70.24 350	94.89 301	93.65 320	86.08 225	76.53 306	93.28 239	61.41 306	96.14 278	80.95 259	77.69 281	90.93 286

tfpnnormal		83.65 285	81.35 291	90.56 251	91.37 288	88.06 175	97.29 237	97.87 49	78.51 319	76.20 307	90.91 278	64.78 294	96.47 254	61.71 351	73.50 309	87.13 341

ppachtmachnet_test		83.63 286	81.57 289	89.80 272	89.01 319	85.09 250	97.13 246	94.50 302	78.84 316	76.14 308	91.00 277	69.78 259	94.61 323	63.40 346	74.36 299	89.71 318

pm-mvs1		84.68 272	82.78 278	90.40 255	89.58 311	85.18 247	97.31 236	94.73 296	81.93 295	76.05 309	92.01 257	65.48 292	96.11 279	78.75 277	69.14 331	89.91 314

AllTest		84.97 269	83.12 273	90.52 252	96.82 140	78.84 316	95.89 287	92.17 338	77.96 322	75.94 310	95.50 195	55.48 324	99.18 125	71.15 322	87.14 214	93.55 226

TestCases				90.52 252	96.82 140	78.84 316		92.17 338	77.96 322	75.94 310	95.50 195	55.48 324	99.18 125	71.15 322	87.14 214	93.55 226

CL-MVSNet_self_test		79.89 304	78.34 304	84.54 323	81.56 356	75.01 332	96.88 255	95.62 257	81.10 302	75.86 312	85.81 339	68.49 267	90.26 354	63.21 347	56.51 359	88.35 330

testgi		82.29 291	81.00 294	86.17 312	87.24 338	74.84 334	97.39 231	91.62 346	88.63 162	75.85 313	95.42 198	46.07 350	91.55 351	66.87 339	79.94 268	92.12 248

MVP-Stereo		86.61 244	85.83 238	88.93 292	88.70 324	83.85 267	96.07 283	94.41 307	82.15 292	75.64 314	91.96 260	67.65 275	96.45 256	77.20 286	98.72 89	86.51 344
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 294	81.17 293	84.25 324	87.23 339	68.87 355	93.35 316	91.93 343	83.35 269	75.40 315	93.00 245	49.25 347	96.65 240	78.88 275	78.11 275	87.22 340

our_test_3		84.47 277	82.80 276	89.50 280	89.01 319	83.90 266	97.03 249	94.56 301	81.33 300	75.36 316	90.52 296	71.69 250	94.54 324	68.81 331	76.84 284	90.07 309

LTVRE_ROB	81.71 19	84.59 274	82.72 280	90.18 260	92.89 266	83.18 274	93.15 317	94.74 295	78.99 315	75.14 317	92.69 248	65.64 289	97.63 202	69.46 329	81.82 260	89.74 316
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		80.76 299	79.42 303	84.79 321	84.78 347	72.98 340	96.53 266	92.97 327	79.56 312	74.33 318	88.83 317	61.27 307	92.15 347	60.59 353	75.92 286	89.24 324

FMVSNet5		82.29 291	80.54 295	87.52 303	93.79 248	84.01 264	93.73 312	92.47 334	76.92 327	74.27 319	86.15 338	63.69 299	89.24 358	69.07 330	74.79 294	89.29 323

MVS-HIRNet		79.01 307	75.13 318	90.66 248	93.82 247	81.69 292	85.16 352	93.75 317	54.54 362	74.17 320	59.15 368	57.46 318	96.58 245	63.74 345	94.38 156	93.72 225

ACMH+	83.78 15	84.21 279	82.56 284	89.15 287	93.73 249	79.16 313	96.43 269	94.28 309	81.09 303	74.00 321	94.03 218	54.58 330	97.67 198	76.10 295	78.81 272	90.63 299

KD-MVS_2432*1600		82.98 288	80.52 296	90.38 256	94.32 229	88.98 154	92.87 320	95.87 243	80.46 309	73.79 322	87.49 326	82.76 162	93.29 333	70.56 326	46.53 368	88.87 328

miper_refine_blended		82.98 288	80.52 296	90.38 256	94.32 229	88.98 154	92.87 320	95.87 243	80.46 309	73.79 322	87.49 326	82.76 162	93.29 333	70.56 326	46.53 368	88.87 328

NR-MVSNet		87.74 228	86.00 236	92.96 197	91.46 286	90.68 120	96.65 265	97.42 133	88.02 185	73.42 324	93.68 228	77.31 208	95.83 293	84.26 226	71.82 325	92.36 237

test_fmvs3		75.09 320	75.19 317	74.81 342	77.45 364	54.08 367	95.93 285	90.64 352	82.51 286	73.29 325	81.19 351	22.29 368	86.29 364	85.50 212	67.89 336	84.06 354

USDC		84.74 270	82.93 274	90.16 261	91.73 282	83.54 270	95.00 300	93.30 325	88.77 161	73.19 326	93.30 238	53.62 333	97.65 201	75.88 297	81.54 261	89.30 322

KD-MVS_self_test		77.47 316	75.88 315	82.24 330	81.59 355	68.93 354	92.83 322	94.02 314	77.03 326	73.14 327	83.39 344	55.44 326	90.42 353	67.95 334	57.53 358	87.38 336

LCM-MVSNet-Re		88.59 214	88.61 197	88.51 296	95.53 188	72.68 343	96.85 256	88.43 362	88.45 169	73.14 327	90.63 289	75.82 213	94.38 325	92.95 130	95.71 145	98.48 153

TDRefinement		78.01 313	75.31 316	86.10 313	70.06 369	73.84 337	93.59 315	91.58 347	74.51 336	73.08 329	91.04 276	49.63 346	97.12 222	74.88 303	59.47 354	87.33 338

TransMVSNet (Re)		81.97 293	79.61 302	89.08 288	89.70 309	84.01 264	97.26 239	91.85 344	78.84 316	73.07 330	91.62 265	67.17 279	95.21 309	67.50 335	59.46 355	88.02 332

SixPastTwentyTwo		82.63 290	81.58 288	85.79 314	88.12 330	71.01 348	95.17 299	92.54 333	84.33 252	72.93 331	92.08 254	60.41 310	95.61 300	74.47 306	74.15 303	90.75 294

pmmvs6		79.90 303	77.31 308	87.67 302	84.17 349	78.13 322	95.86 291	93.68 319	67.94 354	72.67 332	89.62 312	50.98 341	95.75 295	74.80 305	66.04 342	89.14 325

ACMH	83.09 17	84.60 273	82.61 283	90.57 249	93.18 261	82.94 276	96.27 274	94.92 290	81.01 304	72.61 333	93.61 231	56.54 320	97.79 188	74.31 307	81.07 262	90.99 285
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 311	76.90 311	83.82 326	82.82 353	72.86 341	95.72 295	93.57 321	73.55 340	72.17 334	84.79 341	49.69 345	92.51 343	65.29 343	74.50 296	86.09 346

Patchmatch-RL test		81.90 295	80.13 298	87.23 306	80.71 358	70.12 352	84.07 359	88.19 363	83.16 272	70.57 335	82.18 349	87.18 86	92.59 341	82.28 250	62.78 348	98.98 114

mvsany_test3		75.85 319	74.52 321	79.83 337	73.53 366	60.64 361	91.73 329	87.87 364	83.91 259	70.55 336	82.52 346	31.12 363	93.66 329	86.66 201	62.83 347	85.19 352

test_0402		78.81 309	76.33 313	86.26 311	91.18 290	78.44 320	95.88 289	91.34 349	68.55 351	70.51 337	89.91 308	52.65 336	94.99 311	47.14 365	79.78 269	85.34 350

TinyColmap		80.42 301	77.94 305	87.85 300	92.09 274	78.58 318	93.74 311	89.94 355	74.99 333	69.77 338	91.78 263	46.09 349	97.58 206	65.17 344	77.89 276	87.38 336

test20.03		78.51 312	77.48 307	81.62 334	83.07 352	71.03 347	96.11 282	92.83 330	81.66 297	69.31 339	89.68 311	57.53 317	87.29 363	58.65 357	68.47 333	86.53 343

test_vis1_rt		81.31 297	80.05 300	85.11 317	91.29 289	70.66 349	98.98 107	77.39 374	85.76 229	68.80 340	82.40 347	36.56 361	99.44 105	92.67 136	86.55 218	85.24 351

N_pmnet		70.19 326	69.87 328	71.12 346	88.24 328	30.63 382	95.85 292	28.70 382	70.18 347	68.73 341	86.55 335	64.04 297	93.81 328	53.12 363	73.46 310	88.94 326

OpenMVS_ROB	73.86 20	77.99 314	75.06 319	86.77 309	83.81 351	77.94 324	96.38 271	91.53 348	67.54 355	68.38 342	87.13 332	43.94 351	96.08 280	55.03 361	81.83 259	86.29 345

ambc				79.60 338	72.76 368	56.61 364	76.20 366	92.01 342		68.25 343	80.23 354	23.34 367	94.73 319	73.78 314	60.81 352	87.48 335

PM-MVS		74.88 321	72.85 324	80.98 336	78.98 362	64.75 358	90.81 339	85.77 366	80.95 305	68.23 344	82.81 345	29.08 365	92.84 337	76.54 292	62.46 350	85.36 349

pmmvs3		72.86 324	69.76 329	82.17 331	73.86 365	74.19 336	94.20 307	89.01 361	64.23 361	67.72 345	80.91 353	41.48 355	88.65 360	62.40 349	54.02 363	83.68 356

lessismore_v0				85.08 318	85.59 345	69.28 353		90.56 353		67.68 346	90.21 305	54.21 332	95.46 302	73.88 311	62.64 349	90.50 301

K. test v3		81.04 298	79.77 301	84.83 320	87.41 337	70.23 351	95.60 296	93.93 315	83.70 263	67.51 347	89.35 315	55.76 322	93.58 331	76.67 291	68.03 335	90.67 298

MIMVSNet1		75.92 318	73.30 323	83.81 327	81.29 357	75.57 330	92.26 325	92.05 341	73.09 341	67.48 348	86.18 337	40.87 358	87.64 362	55.78 360	70.68 330	88.21 331

ET-MVSNet_ETH3D		92.56 138	91.45 146	95.88 111	96.39 155	94.13 56	99.46 46	96.97 174	92.18 77	66.94 349	98.29 107	94.65 15	94.28 326	94.34 109	83.82 244	99.24 94

pmmvs-eth3d		78.71 310	76.16 314	86.38 310	80.25 360	81.19 301	94.17 308	92.13 340	77.97 321	66.90 350	82.31 348	55.76 322	92.56 342	73.63 315	62.31 351	85.38 348

EG-PatchMatch MVS		79.92 302	77.59 306	86.90 308	87.06 340	77.90 325	96.20 281	94.06 313	74.61 335	66.53 351	88.76 318	40.40 359	96.20 273	67.02 337	83.66 245	86.61 342

test_method		70.10 327	68.66 330	74.41 344	86.30 344	55.84 365	94.47 303	89.82 356	35.18 370	66.15 352	84.75 342	30.54 364	77.96 371	70.40 328	60.33 353	89.44 321

UnsupCasMVSNet_eth		78.90 308	76.67 312	85.58 316	82.81 354	74.94 333	91.98 326	96.31 203	84.64 248	65.84 353	87.71 322	51.33 338	92.23 346	72.89 319	56.50 360	89.56 320

test_f		71.94 325	70.82 326	75.30 341	72.77 367	53.28 368	91.62 330	89.66 358	75.44 332	64.47 354	78.31 358	20.48 369	89.56 357	78.63 278	66.02 343	83.05 359

new-patchmatchnet		74.80 322	72.40 325	81.99 333	78.36 363	72.20 344	94.44 304	92.36 335	77.06 325	63.47 355	79.98 355	51.04 340	88.85 359	60.53 354	54.35 362	84.92 353

new_pmnet		76.02 317	73.71 322	82.95 329	83.88 350	72.85 342	91.26 335	92.26 337	70.44 346	62.60 356	81.37 350	47.64 348	92.32 345	61.85 350	72.10 323	83.68 356

UnsupCasMVSNet_bld		73.85 323	70.14 327	84.99 319	79.44 361	75.73 329	88.53 345	95.24 280	70.12 348	61.94 357	74.81 361	41.41 356	93.62 330	68.65 332	51.13 367	85.62 347

CMPMVS	58.40 21	80.48 300	80.11 299	81.59 335	85.10 346	59.56 362	94.14 309	95.95 229	68.54 352	60.71 358	93.31 237	55.35 327	97.87 183	83.06 243	84.85 231	87.33 338
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		68.93 328	66.98 331	74.77 343	80.62 359	53.15 369	87.97 346	85.01 368	53.76 363	59.26 359	87.52 325	25.19 366	89.95 355	56.20 359	67.33 339	81.19 360

DeepMVS_CX				76.08 340	90.74 296	51.65 372		90.84 351	86.47 222	57.89 360	87.98 320	35.88 362	92.60 340	65.77 342	65.06 345	83.97 355

YYNet1		79.64 306	77.04 310	87.43 305	87.80 334	79.98 310	96.23 278	94.44 303	73.83 339	51.83 361	87.53 324	67.96 273	92.07 349	66.00 341	67.75 338	90.23 306

MDA-MVSNet_test_wron		79.65 305	77.05 309	87.45 304	87.79 335	80.13 309	96.25 277	94.44 303	73.87 338	51.80 362	87.47 328	68.04 271	92.12 348	66.02 340	67.79 337	90.09 307

LCM-MVSNet		60.07 332	56.37 334	71.18 345	54.81 378	48.67 373	82.17 363	89.48 359	37.95 368	49.13 363	69.12 362	13.75 376	81.76 365	59.28 355	51.63 366	83.10 358

MDA-MVSNet-bldmvs		77.82 315	74.75 320	87.03 307	88.33 327	78.52 319	96.34 272	92.85 329	75.57 331	48.87 364	87.89 321	57.32 319	92.49 344	60.79 352	64.80 346	90.08 308

PMMVS2		58.97 333	55.07 336	70.69 347	62.72 373	55.37 366	85.97 350	80.52 371	49.48 364	45.94 365	68.31 363	15.73 374	80.78 369	49.79 364	37.12 370	75.91 361

testf1		56.38 334	53.73 337	64.31 351	64.84 371	45.11 374	80.50 364	75.94 376	38.87 366	42.74 366	75.07 359	11.26 378	81.19 367	41.11 367	53.27 364	66.63 365

APD_test2		56.38 334	53.73 337	64.31 351	64.84 371	45.11 374	80.50 364	75.94 376	38.87 366	42.74 366	75.07 359	11.26 378	81.19 367	41.11 367	53.27 364	66.63 365

FPMVS		61.57 329	60.32 332	65.34 349	60.14 376	42.44 377	91.02 338	89.72 357	44.15 365	42.63 368	80.93 352	19.02 370	80.59 370	42.50 366	72.76 315	73.00 362

test_vis3_rt		61.29 330	58.75 333	68.92 348	67.41 370	52.84 370	91.18 337	59.23 381	66.96 356	41.96 369	58.44 369	11.37 377	94.72 320	74.25 308	57.97 357	59.20 368

Gipuma		54.77 336	52.22 340	62.40 353	86.50 341	59.37 363	50.20 371	90.35 354	36.52 369	41.20 370	49.49 371	18.33 372	81.29 366	32.10 371	65.34 344	46.54 371
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 337	52.86 339	56.05 354	32.75 382	41.97 378	73.42 368	76.12 375	21.91 375	39.68 371	96.39 181	42.59 354	65.10 374	78.00 281	14.92 375	61.08 367

E-PMN		41.02 341	40.93 343	41.29 357	61.97 374	33.83 379	84.00 360	65.17 379	27.17 372	27.56 372	46.72 373	17.63 373	60.41 376	19.32 374	18.82 372	29.61 372

ANet_high		50.71 338	46.17 341	64.33 350	44.27 380	52.30 371	76.13 367	78.73 372	64.95 359	27.37 373	55.23 370	14.61 375	67.74 373	36.01 370	18.23 373	72.95 363

EMVS		39.96 342	39.88 344	40.18 358	59.57 377	32.12 381	84.79 357	64.57 380	26.27 373	26.14 374	44.18 376	18.73 371	59.29 377	17.03 375	17.67 374	29.12 373

MVE	44.00 22	41.70 340	37.64 345	53.90 356	49.46 379	43.37 376	65.09 370	66.66 378	26.19 374	25.77 375	48.53 372	3.58 382	63.35 375	26.15 373	27.28 371	54.97 370
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 339	42.50 342	55.17 355	34.28 381	32.37 380	66.24 369	78.71 373	30.72 371	22.04 376	59.59 367	4.59 380	77.85 372	27.49 372	58.84 356	55.29 369
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 344	23.05 347	6.10 361	4.48 383	2.29 385	97.78 217	3.00 384	3.27 377	18.60 377	62.71 365	1.53 384	2.49 380	14.26 377	1.80 377	13.50 375

test123		16.58 346	19.47 348	7.91 360	3.59 384	5.37 384	94.32 305	1.39 385	2.49 378	13.98 378	44.60 375	2.91 383	2.65 379	11.35 378	0.57 378	15.70 374

wuyk23d		16.71 345	16.73 349	16.65 359	60.15 375	25.22 383	41.24 372	5.17 383	6.56 376	5.48 379	3.61 379	3.64 381	22.72 378	15.20 376	9.52 376	1.99 376

EGC-MVSNET		60.70 331	55.37 335	76.72 339	86.35 343	71.08 346	89.96 343	84.44 370	0.38 379	1.50 380	84.09 343	37.30 360	88.10 361	40.85 369	73.44 311	70.97 364

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

cdsmvs_eth3d_5k		22.52 343	30.03 346	0.00 362	0.00 385	0.00 386	0.00 373	97.17 155	0.00 380	0.00 381	98.77 74	74.35 225	0.00 381	0.00 379	0.00 379	0.00 377

pcd_1.5k_mvsjas		6.87 348	9.16 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	82.48 167	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.21 347	10.94 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	98.50 96	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 76					99.98 9	99.55 10	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 76					99.98 9	99.55 10	99.83 15	99.96 10

eth-test2					0.00 385

eth-test					0.00 385

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 9				99.19 28	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

save fliter					99.34 50	93.85 60	99.65 25	97.63 91	95.69 12

test_0728_SECOND				98.77 7	99.66 12	96.37 12	99.72 14	97.68 78					99.98 9	99.64 6	99.82 19	99.96 10

GSMVS																98.84 129

sam_mvs1												88.39 63				98.84 129

sam_mvs												87.08 88

MTGPA								97.45 127

test_post1							90.74 341				41.37 377	85.38 124	96.36 260	83.16 240

test_post											46.00 374	87.37 80	97.11 223

patchmatchnet-post											84.86 340	88.73 60	96.81 235

MTMP							99.21 71	91.09 350

gm-plane-assit					94.69 223	88.14 173			88.22 179		97.20 149		98.29 161	90.79 153

test9_res														98.60 23	99.87 9	99.90 22

agg_prior2														97.84 41	99.87 9	99.91 21

test_prior4						92.00 90	99.41 55

test_prior				97.01 56	99.58 30	91.77 91		97.57 105					99.49 98			99.79 35

新几何2							98.26 184

旧先验1					98.97 73	92.90 80		97.74 65			99.15 36	91.05 34			99.33 63	99.60 65

无先验							98.52 152	97.82 54	87.20 205				99.90 43	87.64 190		99.85 30

原ACMM2							98.69 132

testdata2													99.88 46	84.16 228

segment_acmp												90.56 41

testdata1							97.89 210		92.43 68

plane_prior7					93.84 245	85.73 236

plane_prior6					93.92 242	86.02 230						72.92 237

plane_prior5								96.30 204					97.75 195	93.46 123	86.17 222	92.67 231

plane_prior4											96.52 175

plane_prior2							99.02 101		93.38 52

plane_prior1					93.90 244

plane_prior						86.07 228	99.14 86		93.81 44						86.26 221

n2								0.00 386

nn								0.00 386

door-mid								84.90 369

test11								97.68 78

door								85.30 367

HQP5-MVS						86.39 214

BP-MVS														93.82 118

HQP3-MVS								96.37 200							86.29 219

HQP2-MVS												73.34 232

NP-MVS					93.94 241	86.22 221					96.67 173

ACMMP++_ref															82.64 255

ACMMP++															83.83 242

Test By Simon												83.62 142

High-resolution multi-view benchmark