High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

LCM-MVSNet		99.43 1	99.49 1	99.24 1	99.95 1	98.13 1	99.37 1	99.57 1	99.82 1	99.86 1	99.85 1	99.52 1	99.73 1	97.58 1	99.94 1	99.85 1

UA-Net		97.35 4	97.24 11	97.69 5	98.22 75	93.87 31	98.42 6	98.19 36	96.95 14	95.46 135	99.23 4	93.45 77	99.57 14	95.34 17	99.89 2	99.63 9

test_part1		94.39 116	94.55 114	93.92 155	96.14 208	82.86 216	95.54 83	98.09 54	95.36 36	98.27 20	98.36 31	75.91 303	99.44 30	93.41 63	99.84 3	99.47 19

PS-CasMVS		96.69 20	97.43 5	94.49 135	99.13 6	84.09 201	96.61 32	97.97 77	97.91 5	98.64 13	98.13 38	95.24 36	99.65 3	93.39 64	99.84 3	99.72 2

WR-MVS_H		96.60 25	97.05 14	95.24 100	99.02 12	86.44 164	96.78 28	98.08 55	97.42 9	98.48 16	97.86 54	91.76 122	99.63 6	94.23 30	99.84 3	99.66 6

FC-MVSNet-test		95.32 80	95.88 59	93.62 164	98.49 59	81.77 225	95.90 68	98.32 21	93.93 57	97.53 43	97.56 65	88.48 179	99.40 49	92.91 84	99.83 6	99.68 4

PEN-MVS		96.69 20	97.39 8	94.61 124	99.16 4	84.50 192	96.54 35	98.05 62	98.06 4	98.64 13	98.25 34	95.01 48	99.65 3	92.95 83	99.83 6	99.68 4

DTE-MVSNet		96.74 17	97.43 5	94.67 121	99.13 6	84.68 191	96.51 36	97.94 83	98.14 3	98.67 12	98.32 32	95.04 45	99.69 2	93.27 70	99.82 8	99.62 10

CP-MVSNet		96.19 47	96.80 17	94.38 141	98.99 14	83.82 204	96.31 51	97.53 114	97.60 7	98.34 19	97.52 68	91.98 118	99.63 6	93.08 79	99.81 9	99.70 3

LTVRE_ROB	93.87 1	97.93 2	98.16 2	97.26 26	98.81 26	93.86 32	99.07 2	98.98 6	97.01 13	98.92 4	98.78 14	95.22 37	98.61 184	96.85 2	99.77 10	99.31 31
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
v7n		96.82 10	97.31 10	95.33 95	98.54 46	86.81 153	96.83 24	98.07 58	96.59 20	98.46 17	98.43 30	92.91 96	99.52 19	96.25 6	99.76 11	99.65 8

TranMVSNet+NR-MVSNet		96.07 51	96.26 38	95.50 89	98.26 72	87.69 135	93.75 147	97.86 85	95.96 30	97.48 46	97.14 95	95.33 32	99.44 30	90.79 133	99.76 11	99.38 25

Anonymous20231211		96.60 25	97.13 12	95.00 108	97.46 129	86.35 168	97.11 19	98.24 31	97.58 8	98.72 8	98.97 7	93.15 88	99.15 92	93.18 73	99.74 13	99.50 17

UniMVSNet_ETH3D		97.13 6	97.72 3	95.35 93	99.51 2	87.38 139	97.70 8	97.54 112	98.16 2	98.94 2	99.33 2	97.84 4	99.08 104	90.73 134	99.73 14	99.59 13

test_low_dy_conf_001		95.63 65	95.32 83	96.56 47	98.74 30	90.71 77	97.10 20	95.47 234	90.00 153	97.57 39	98.49 26	84.73 232	99.46 26	96.06 8	99.69 15	99.50 17

pmmvs6		96.80 13	97.36 9	95.15 104	99.12 8	87.82 134	96.68 30	97.86 85	96.10 26	98.14 24	99.28 3	97.94 3	98.21 221	91.38 124	99.69 15	99.42 21

FIs		94.90 95	95.35 79	93.55 167	98.28 70	81.76 226	95.33 89	98.14 45	93.05 74	97.07 59	97.18 93	87.65 193	99.29 76	91.72 114	99.69 15	99.61 11

RRT_MVS		95.41 76	95.20 89	96.05 59	98.86 21	88.92 108	97.49 10	94.48 260	93.12 72	97.94 28	98.54 21	81.19 266	99.63 6	95.48 14	99.69 15	99.60 12

bld_raw_conf005		96.23 45	96.22 40	96.26 54	98.53 49	89.90 88	97.25 13	98.12 47	92.70 76	98.10 25	98.51 25	87.19 202	99.46 26	95.86 10	99.69 15	99.42 21

OurMVSNet-221017-0		96.80 13	96.75 18	96.96 36	99.03 11	91.85 59	97.98 7	98.01 71	94.15 51	98.93 3	99.07 5	88.07 186	99.57 14	95.86 10	99.69 15	99.46 20

Anonymous20240521		92.86 166	93.57 145	90.74 262	96.57 173	75.50 319	94.15 134	95.60 223	89.38 167	95.90 118	97.90 53	80.39 270	97.96 243	92.60 92	99.68 21	98.75 91

ANet_high		94.83 101	96.28 37	90.47 268	96.65 166	73.16 336	94.33 128	98.74 10	96.39 23	98.09 26	98.93 8	93.37 81	98.70 172	90.38 142	99.68 21	99.53 15

DeepC-MVS	91.39 4	95.43 74	95.33 81	95.71 82	97.67 115	90.17 83	93.86 145	98.02 69	87.35 213	96.22 101	97.99 47	94.48 62	99.05 109	92.73 88	99.68 21	97.93 169
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NR-MVSNet		95.28 84	95.28 85	95.26 99	97.75 106	87.21 143	95.08 100	97.37 123	93.92 59	97.65 34	95.90 172	90.10 165	99.33 73	90.11 156	99.66 24	99.26 33

Baseline_NR-MVSNet		94.47 115	95.09 94	92.60 202	98.50 58	80.82 240	92.08 202	96.68 180	93.82 60	96.29 95	98.56 20	90.10 165	97.75 263	90.10 158	99.66 24	99.24 35

mvsmamba		95.61 67	95.40 78	96.22 55	98.44 61	89.86 90	97.14 17	97.45 120	91.25 127	97.49 45	98.14 36	83.49 237	99.45 28	95.52 13	99.66 24	99.36 27

UniMVSNet (Re)		95.32 80	95.15 90	95.80 76	97.79 104	88.91 109	92.91 167	98.07 58	93.46 67	96.31 93	95.97 171	90.14 161	99.34 68	92.11 99	99.64 27	99.16 41

WR-MVS		93.49 142	93.72 138	92.80 194	97.57 122	80.03 250	90.14 264	95.68 221	93.70 62	96.62 81	95.39 204	87.21 201	99.04 112	87.50 211	99.64 27	99.33 29

MIMVSNet1		95.52 70	95.45 75	95.72 81	99.14 5	89.02 106	96.23 56	96.87 168	93.73 61	97.87 29	98.49 26	90.73 151	99.05 109	86.43 231	99.60 29	99.10 50

ACMH+	88.43 11	96.48 30	96.82 16	95.47 90	98.54 46	89.06 105	95.65 78	98.61 11	96.10 26	98.16 23	97.52 68	96.90 7	98.62 183	90.30 147	99.60 29	98.72 97

VPA-MVSNet		95.14 88	95.67 69	93.58 166	97.76 105	83.15 212	94.58 119	97.58 109	93.39 68	97.05 62	98.04 44	93.25 84	98.51 197	89.75 166	99.59 31	99.08 51

LPG-MVS_test		96.38 40	96.23 39	96.84 40	98.36 67	92.13 54	95.33 89	98.25 28	91.78 109	97.07 59	97.22 91	96.38 13	99.28 78	92.07 102	99.59 31	99.11 47

LGP-MVS_train				96.84 40	98.36 67	92.13 54		98.25 28	91.78 109	97.07 59	97.22 91	96.38 13	99.28 78	92.07 102	99.59 31	99.11 47

ACMH	88.36 12	96.59 27	97.43 5	94.07 148	98.56 40	85.33 185	96.33 48	98.30 24	94.66 40	98.72 8	98.30 33	97.51 5	98.00 239	94.87 18	99.59 31	98.86 78
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet_NR-MVSNet		95.35 78	95.21 87	95.76 79	97.69 113	88.59 117	92.26 196	97.84 89	94.91 38	96.80 74	95.78 182	90.42 156	99.41 42	91.60 118	99.58 35	99.29 32

DU-MVS		95.28 84	95.12 92	95.75 80	97.75 106	88.59 117	92.58 177	97.81 92	93.99 53	96.80 74	95.90 172	90.10 165	99.41 42	91.60 118	99.58 35	99.26 33

ACMP	88.15 13	95.71 63	95.43 77	96.54 48	98.17 78	91.73 62	94.24 131	98.08 55	89.46 165	96.61 82	96.47 138	95.85 17	99.12 100	90.45 139	99.56 37	98.77 90
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
v10		94.68 107	95.27 86	92.90 190	96.57 173	80.15 244	94.65 116	97.57 110	90.68 140	97.43 48	98.00 46	88.18 183	99.15 92	94.84 19	99.55 38	99.41 23

bld_raw_dy_0_64		94.27 123	94.15 129	94.65 123	98.55 43	86.28 170	95.80 72	95.55 230	88.41 192	97.09 58	98.08 41	78.69 279	98.87 138	95.63 12	99.53 39	98.81 84

PS-MVSNAJss		96.01 52	96.04 53	95.89 72	98.82 25	88.51 121	95.57 82	97.88 84	88.72 184	98.81 6	98.86 10	90.77 147	99.60 9	95.43 16	99.53 39	99.57 14

TDRefinement		97.68 3	97.60 4	97.93 2	99.02 12	95.95 5	98.61 3	98.81 8	97.41 10	97.28 53	98.46 28	94.62 58	98.84 142	94.64 21	99.53 39	98.99 58

IS-MVSNet		94.49 114	94.35 121	94.92 110	98.25 74	86.46 163	97.13 18	94.31 264	96.24 24	96.28 98	96.36 151	82.88 244	99.35 65	88.19 197	99.52 42	98.96 65

nrg030		96.32 41	96.55 26	95.62 84	97.83 101	88.55 119	95.77 73	98.29 27	92.68 77	98.03 27	97.91 51	95.13 40	98.95 126	93.85 40	99.49 43	99.36 27

MP-MVS-pluss		96.08 50	95.92 58	96.57 46	99.06 10	91.21 67	93.25 159	98.32 21	87.89 202	96.86 71	97.38 76	95.55 24	99.39 54	95.47 15	99.47 44	99.11 47
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
mvs_tets		96.83 9	96.71 19	97.17 27	98.83 24	92.51 50	96.58 34	97.61 107	87.57 211	98.80 7	98.90 9	96.50 10	99.59 13	96.15 7	99.47 44	99.40 24

v8		94.65 108	95.29 84	92.74 195	96.65 166	79.77 258	94.59 117	97.17 144	91.86 101	97.47 47	97.93 49	88.16 184	99.08 104	94.32 26	99.47 44	99.38 25

CLD-MVS		91.82 192	91.41 198	93.04 181	96.37 185	83.65 206	86.82 328	97.29 136	84.65 256	92.27 249	89.67 338	92.20 112	97.85 253	83.95 258	99.47 44	97.62 198
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
CS-MVS-test		95.32 80	95.10 93	95.96 63	96.86 157	90.75 76	96.33 48	99.20 2	93.99 53	91.03 269	93.73 267	93.52 76	99.55 18	91.81 111	99.45 48	97.58 200

jajsoiax		96.59 27	96.42 29	97.12 29	98.76 29	92.49 51	96.44 42	97.42 121	86.96 220	98.71 10	98.72 17	95.36 31	99.56 17	95.92 9	99.45 48	99.32 30

test_djsdf		96.62 23	96.49 28	97.01 33	98.55 43	91.77 61	97.15 15	97.37 123	88.98 178	98.26 22	98.86 10	93.35 82	99.60 9	96.41 4	99.45 48	99.66 6

CP-MVS		96.44 35	96.08 50	97.54 11	98.29 69	94.62 14	96.80 26	98.08 55	92.67 79	95.08 155	96.39 148	94.77 54	99.42 35	93.17 74	99.44 51	98.58 116

COLMAP_ROB	91.06 5	96.75 16	96.62 23	97.13 28	98.38 64	94.31 17	96.79 27	98.32 21	96.69 17	96.86 71	97.56 65	95.48 25	98.77 160	90.11 156	99.44 51	98.31 133
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_0728_THIRD									93.26 70	97.40 51	97.35 83	94.69 55	99.34 68	93.88 38	99.42 53	98.89 75

zzz-MVS		96.47 31	96.14 46	97.47 15	98.95 16	94.05 23	93.69 149	97.62 104	94.46 45	96.29 95	96.94 106	93.56 73	99.37 62	94.29 28	99.42 53	98.99 58

MTAPA		96.65 22	96.38 33	97.47 15	98.95 16	94.05 23	95.88 69	97.62 104	94.46 45	96.29 95	96.94 106	93.56 73	99.37 62	94.29 28	99.42 53	98.99 58

pm-mvs1		95.43 74	95.94 56	93.93 154	98.38 64	85.08 188	95.46 86	97.12 149	91.84 105	97.28 53	98.46 28	95.30 34	97.71 265	90.17 154	99.42 53	98.99 58

XVG-ACMP-BASELINE		95.68 64	95.34 80	96.69 43	98.40 62	93.04 43	94.54 124	98.05 62	90.45 146	96.31 93	96.76 120	92.91 96	98.72 166	91.19 125	99.42 53	98.32 131

wuyk23d		87.83 275	90.79 213	78.96 355	90.46 346	88.63 115	92.72 172	90.67 319	91.65 117	98.68 11	97.64 62	96.06 16	77.53 376	59.84 371	99.41 58	70.73 374

anonymousdsp		96.74 17	96.42 29	97.68 7	98.00 93	94.03 26	96.97 21	97.61 107	87.68 208	98.45 18	98.77 15	94.20 67	99.50 21	96.70 3	99.40 59	99.53 15

SixPastTwentyTwo		94.91 94	95.21 87	93.98 150	98.52 50	83.19 211	95.93 66	94.84 249	94.86 39	98.49 15	98.74 16	81.45 260	99.60 9	94.69 20	99.39 60	99.15 42

HPM-MVS_fast		97.01 7	96.89 15	97.39 22	99.12 8	93.92 29	97.16 14	98.17 41	93.11 73	96.48 85	97.36 80	96.92 6	99.34 68	94.31 27	99.38 61	98.92 72

HPM-MVS		96.81 12	96.62 23	97.36 24	98.89 19	93.53 39	97.51 9	98.44 13	92.35 86	95.95 113	96.41 143	96.71 8	99.42 35	93.99 37	99.36 62	99.13 44
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
KD-MVS_self_test		94.10 130	94.73 106	92.19 212	97.66 116	79.49 263	94.86 108	97.12 149	89.59 164	96.87 70	97.65 61	90.40 159	98.34 211	89.08 181	99.35 63	98.75 91

ACMMP_NAP		96.21 46	96.12 48	96.49 51	98.90 18	91.42 65	94.57 120	98.03 67	90.42 147	96.37 88	97.35 83	95.68 19	99.25 82	94.44 24	99.34 64	98.80 86

SteuartSystems-ACMMP		96.40 38	96.30 36	96.71 42	98.63 33	91.96 57	95.70 75	98.01 71	93.34 69	96.64 80	96.57 135	94.99 49	99.36 64	93.48 55	99.34 64	98.82 83
Skip Steuart: Steuart Systems R&D Blog.
ACMMP		96.61 24	96.34 34	97.43 19	98.61 36	93.88 30	96.95 22	98.18 37	92.26 89	96.33 91	96.84 116	95.10 43	99.40 49	93.47 56	99.33 66	99.02 55
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
ACMM	88.83 9	96.30 43	96.07 51	96.97 35	98.39 63	92.95 46	94.74 112	98.03 67	90.82 136	97.15 56	96.85 113	96.25 15	99.00 118	93.10 77	99.33 66	98.95 66
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test1111		90.39 222	90.61 217	89.74 286	98.04 89	71.50 347	95.59 79	79.72 374	89.41 166	95.94 115	98.14 36	70.79 319	98.81 149	88.52 193	99.32 68	98.90 74

DVP-MVS		95.82 59	96.18 43	94.72 119	98.51 51	86.69 156	95.20 95	97.00 155	91.85 102	97.40 51	97.35 83	95.58 22	99.34 68	93.44 60	99.31 69	98.13 148
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_SECOND				94.88 112	98.55 43	86.72 155	95.20 95	98.22 33					99.38 60	93.44 60	99.31 69	98.53 118

MSC_two_6792asdad				95.90 70	96.54 176	89.57 95		96.87 168					99.41 42	94.06 34	99.30 71	98.72 97

No_MVS				95.90 70	96.54 176	89.57 95		96.87 168					99.41 42	94.06 34	99.30 71	98.72 97

APDe-MVS		96.46 32	96.64 22	95.93 67	97.68 114	89.38 102	96.90 23	98.41 17	92.52 81	97.43 48	97.92 50	95.11 42	99.50 21	94.45 23	99.30 71	98.92 72

SED-MVS		96.00 53	96.41 32	94.76 117	98.51 51	86.97 149	95.21 93	98.10 51	91.95 96	97.63 35	97.25 88	96.48 11	99.35 65	93.29 68	99.29 74	97.95 167

IU-MVS					98.51 51	86.66 158		96.83 171	72.74 339	95.83 120				93.00 81	99.29 74	98.64 107

SMA-MVS		95.77 60	95.54 72	96.47 52	98.27 71	91.19 68	95.09 99	97.79 96	86.48 223	97.42 50	97.51 70	94.47 63	99.29 76	93.55 50	99.29 74	98.93 68
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
MP-MVS		96.14 48	95.68 68	97.51 13	98.81 26	94.06 21	96.10 59	97.78 97	92.73 75	93.48 203	96.72 126	94.23 66	99.42 35	91.99 104	99.29 74	99.05 53
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test_0402		95.73 62	96.22 40	94.26 143	98.19 77	85.77 180	93.24 160	97.24 140	96.88 16	97.69 33	97.77 57	94.12 68	99.13 96	91.54 121	99.29 74	97.88 176

ZNCC-MVS		96.42 36	96.20 42	97.07 30	98.80 28	92.79 48	96.08 60	98.16 44	91.74 113	95.34 140	96.36 151	95.68 19	99.44 30	94.41 25	99.28 79	98.97 64

DPE-MVS		95.89 55	95.88 59	95.92 69	97.93 98	89.83 91	93.46 155	98.30 24	92.37 84	97.75 32	96.95 105	95.14 39	99.51 20	91.74 113	99.28 79	98.41 127
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
iter_conf05		88.94 258	88.09 266	91.50 235	92.74 314	76.97 303	92.80 170	95.92 213	82.82 273	93.65 198	95.37 206	49.41 376	99.13 96	90.82 132	99.28 79	98.40 128

mPP-MVS		96.46 32	96.05 52	97.69 5	98.62 34	94.65 13	96.45 40	97.74 98	92.59 80	95.47 133	96.68 128	94.50 61	99.42 35	93.10 77	99.26 82	98.99 58

test_241102_TWO								98.10 51	91.95 96	97.54 41	97.25 88	95.37 28	99.35 65	93.29 68	99.25 83	98.49 121

ACMMP++															99.25 83

CSCG		94.69 106	94.75 104	94.52 132	97.55 123	87.87 132	95.01 104	97.57 110	92.68 77	96.20 103	93.44 274	91.92 119	98.78 156	89.11 180	99.24 85	96.92 232

TransMVSNet (Re)		95.27 86	96.04 53	92.97 184	98.37 66	81.92 224	95.07 101	96.76 177	93.97 56	97.77 31	98.57 19	95.72 18	97.90 245	88.89 185	99.23 86	99.08 51

abl_6		97.31 5	97.12 13	97.86 3	98.54 46	95.32 7	96.61 32	98.35 20	95.81 31	97.55 40	97.44 73	96.51 9	99.40 49	94.06 34	99.23 86	98.85 81

DROMVSNet		95.44 73	95.62 70	94.89 111	96.93 153	87.69 135	96.48 39	99.14 4	93.93 57	92.77 229	94.52 239	93.95 70	99.49 24	93.62 47	99.22 88	97.51 206

EGC-MVSNET		80.97 333	75.73 344	96.67 44	98.85 23	94.55 15	96.83 24	96.60 184	2.44 379	5.32 380	98.25 34	92.24 110	98.02 237	91.85 110	99.21 89	97.45 209

PGM-MVS		96.32 41	95.94 56	97.43 19	98.59 39	93.84 33	95.33 89	98.30 24	91.40 122	95.76 122	96.87 112	95.26 35	99.45 28	92.77 85	99.21 89	99.00 56

SD-MVS		95.19 87	95.73 67	93.55 167	96.62 170	88.88 112	94.67 114	98.05 62	91.26 125	97.25 55	96.40 144	95.42 26	94.36 349	92.72 89	99.19 91	97.40 215
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
Vis-MVSNet (Re-imp)		90.42 220	90.16 225	91.20 246	97.66 116	77.32 296	94.33 128	87.66 335	91.20 128	92.99 222	95.13 212	75.40 305	98.28 214	77.86 312	99.19 91	97.99 162

test2506		85.42 304	84.57 306	87.96 314	97.81 102	66.53 365	96.14 57	56.35 382	89.04 176	93.55 202	98.10 39	42.88 384	98.68 176	88.09 201	99.18 93	98.67 101

ECVR-MVS		90.12 233	90.16 225	90.00 283	97.81 102	72.68 341	95.76 74	78.54 375	89.04 176	95.36 139	98.10 39	70.51 320	98.64 182	87.10 218	99.18 93	98.67 101

tfpnnormal		94.27 123	94.87 100	92.48 206	97.71 110	80.88 239	94.55 123	95.41 236	93.70 62	96.67 79	97.72 58	91.40 130	98.18 225	87.45 212	99.18 93	98.36 129

FMVSNet1		94.84 100	95.13 91	93.97 151	97.60 119	84.29 194	95.99 62	96.56 186	92.38 83	97.03 63	98.53 22	90.12 162	98.98 119	88.78 187	99.16 96	98.65 103

ACMMPR		96.46 32	96.14 46	97.41 21	98.60 37	93.82 34	96.30 53	97.96 78	92.35 86	95.57 131	96.61 133	94.93 51	99.41 42	93.78 42	99.15 97	99.00 56

HFP-MVS		96.39 39	96.17 45	97.04 31	98.51 51	93.37 40	96.30 53	97.98 74	92.35 86	95.63 128	96.47 138	95.37 28	99.27 80	93.78 42	99.14 98	98.48 122

#test#		95.89 55	95.51 73	97.04 31	98.51 51	93.37 40	95.14 98	97.98 74	89.34 169	95.63 128	96.47 138	95.37 28	99.27 80	91.99 104	99.14 98	98.48 122

VDD-MVS		94.37 117	94.37 120	94.40 140	97.49 126	86.07 175	93.97 142	93.28 281	94.49 44	96.24 99	97.78 55	87.99 189	98.79 152	88.92 183	99.14 98	98.34 130

region2R		96.41 37	96.09 49	97.38 23	98.62 34	93.81 36	96.32 50	97.96 78	92.26 89	95.28 144	96.57 135	95.02 47	99.41 42	93.63 46	99.11 101	98.94 67

Gipuma		95.31 83	95.80 65	93.81 161	97.99 96	90.91 72	96.42 43	97.95 80	96.69 17	91.78 258	98.85 12	91.77 121	95.49 332	91.72 114	99.08 102	95.02 297
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
GST-MVS		96.24 44	95.99 55	97.00 34	98.65 32	92.71 49	95.69 77	98.01 71	92.08 94	95.74 124	96.28 156	95.22 37	99.42 35	93.17 74	99.06 103	98.88 77

OPM-MVS		95.61 67	95.45 75	96.08 58	98.49 59	91.00 70	92.65 176	97.33 132	90.05 152	96.77 76	96.85 113	95.04 45	98.56 192	92.77 85	99.06 103	98.70 100
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPNet		93.08 156	93.76 137	91.03 250	98.60 37	75.83 317	91.51 227	95.62 222	91.84 105	95.74 124	97.10 97	89.31 173	98.32 212	85.07 248	99.06 103	98.93 68

xxxxxxxxxxxxxcwj		95.03 89	94.93 97	95.33 95	97.46 129	88.05 128	92.04 204	98.42 16	87.63 209	96.36 89	96.68 128	94.37 64	99.32 74	92.41 95	99.05 106	98.64 107

SF-MVS		95.88 57	95.88 59	95.87 73	98.12 80	89.65 94	95.58 81	98.56 12	91.84 105	96.36 89	96.68 128	94.37 64	99.32 74	92.41 95	99.05 106	98.64 107

CS-MVS		95.77 60	95.58 71	96.37 53	96.84 158	91.72 63	96.73 29	99.06 5	94.23 49	92.48 237	94.79 231	93.56 73	99.49 24	93.47 56	99.05 106	97.89 175

XVS		96.49 29	96.18 43	97.44 17	98.56 40	93.99 27	96.50 37	97.95 80	94.58 41	94.38 178	96.49 137	94.56 59	99.39 54	93.57 48	99.05 106	98.93 68

X-MVStestdata		90.70 213	88.45 255	97.44 17	98.56 40	93.99 27	96.50 37	97.95 80	94.58 41	94.38 178	26.89 377	94.56 59	99.39 54	93.57 48	99.05 106	98.93 68

test20.03		90.80 210	90.85 211	90.63 265	95.63 242	79.24 268	89.81 275	92.87 287	89.90 156	94.39 177	96.40 144	85.77 223	95.27 340	73.86 338	99.05 106	97.39 216

Anonymous20240529		95.50 71	95.83 63	94.50 133	97.33 135	85.93 177	95.19 97	96.77 176	96.64 19	97.61 38	98.05 43	93.23 85	98.79 152	88.60 192	99.04 112	98.78 88

IterMVS-LS		93.78 137	94.28 124	92.27 209	96.27 197	79.21 270	91.87 216	96.78 174	91.77 111	96.57 84	97.07 98	87.15 203	98.74 164	91.99 104	99.03 113	98.86 78
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ETH3D-3000-0.1		94.86 98	94.55 114	95.81 74	97.61 118	89.72 92	94.05 138	98.37 18	88.09 198	95.06 156	95.85 174	92.58 104	99.10 103	90.33 146	98.99 114	98.62 111

cl____		90.65 215	90.56 219	90.91 257	91.85 327	76.98 302	86.75 329	95.36 240	85.53 240	94.06 185	94.89 224	77.36 293	97.98 242	90.27 149	98.98 115	97.76 188

AllTest		94.88 97	94.51 117	96.00 61	98.02 91	92.17 52	95.26 92	98.43 14	90.48 144	95.04 157	96.74 123	92.54 106	97.86 251	85.11 246	98.98 115	97.98 163

TestCases				96.00 61	98.02 91	92.17 52		98.43 14	90.48 144	95.04 157	96.74 123	92.54 106	97.86 251	85.11 246	98.98 115	97.98 163

Patchmtry		90.11 234	89.92 231	90.66 264	90.35 347	77.00 300	92.96 165	92.81 288	90.25 150	94.74 169	96.93 108	67.11 328	97.52 272	85.17 241	98.98 115	97.46 208

DIV-MVS_self_test		90.65 215	90.56 219	90.91 257	91.85 327	76.99 301	86.75 329	95.36 240	85.52 242	94.06 185	94.89 224	77.37 292	97.99 241	90.28 148	98.97 119	97.76 188

9.14			94.81 101		97.49 126		94.11 136	98.37 18	87.56 212	95.38 137	96.03 168	94.66 56	99.08 104	90.70 135	98.97 119

D2MVS		89.93 240	89.60 238	90.92 255	94.03 289	78.40 281	88.69 301	94.85 248	78.96 306	93.08 218	95.09 214	74.57 306	96.94 296	88.19 197	98.96 121	97.41 212

PHI-MVS		94.34 120	93.80 135	95.95 64	95.65 240	91.67 64	94.82 109	97.86 85	87.86 203	93.04 221	94.16 251	91.58 126	98.78 156	90.27 149	98.96 121	97.41 212

iter_conf_final		90.23 230	89.32 239	92.95 186	94.65 275	81.46 231	94.32 130	95.40 239	85.61 239	92.84 226	95.37 206	54.58 369	99.13 96	92.16 98	98.94 123	98.25 138

ambc				92.98 183	96.88 155	83.01 215	95.92 67	96.38 196		96.41 86	97.48 71	88.26 182	97.80 256	89.96 161	98.93 124	98.12 149

EPNet		89.80 244	88.25 260	94.45 138	83.91 378	86.18 173	93.87 144	87.07 339	91.16 130	80.64 366	94.72 233	78.83 277	98.89 132	85.17 241	98.89 125	98.28 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EPP-MVSNet		93.91 135	93.68 141	94.59 129	98.08 83	85.55 183	97.44 11	94.03 269	94.22 50	94.94 160	96.19 161	82.07 255	99.57 14	87.28 216	98.89 125	98.65 103

v1192		93.49 142	93.78 136	92.62 201	96.16 206	79.62 260	91.83 221	97.22 142	86.07 230	96.10 109	96.38 149	87.22 200	99.02 115	94.14 33	98.88 127	99.22 36

v1144		93.50 141	93.81 134	92.57 203	96.28 196	79.61 261	91.86 220	96.96 158	86.95 221	95.91 117	96.32 153	87.65 193	98.96 124	93.51 51	98.88 127	99.13 44

APD-MVS_3200maxsize		96.82 10	96.65 21	97.32 25	97.95 97	93.82 34	96.31 51	98.25 28	95.51 35	96.99 66	97.05 100	95.63 21	99.39 54	93.31 67	98.88 127	98.75 91

APD-MVS		95.00 91	94.69 107	95.93 67	97.38 132	90.88 73	94.59 117	97.81 92	89.22 174	95.46 135	96.17 164	93.42 80	99.34 68	89.30 172	98.87 130	97.56 203
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
OMC-MVS		94.22 127	93.69 140	95.81 74	97.25 136	91.27 66	92.27 195	97.40 122	87.10 219	94.56 173	95.42 201	93.74 71	98.11 230	86.62 226	98.85 131	98.06 151

SR-MVS-dyc-post		96.84 8	96.60 25	97.56 10	98.07 84	95.27 8	96.37 45	98.12 47	95.66 33	97.00 64	97.03 101	94.85 52	99.42 35	93.49 52	98.84 132	98.00 159

RE-MVS-def			96.66 20		98.07 84	95.27 8	96.37 45	98.12 47	95.66 33	97.00 64	97.03 101	95.40 27		93.49 52	98.84 132	98.00 159

v144192		93.20 155	93.54 147	92.16 216	96.05 215	78.26 283	91.95 208	97.14 146	84.98 251	95.96 112	96.11 165	87.08 205	99.04 112	93.79 41	98.84 132	99.17 40

v1921920		93.26 150	93.61 143	92.19 212	96.04 219	78.31 282	91.88 215	97.24 140	85.17 245	96.19 105	96.19 161	86.76 213	99.05 109	94.18 32	98.84 132	99.22 36

DP-MVS		95.62 66	95.84 62	94.97 109	97.16 142	88.62 116	94.54 124	97.64 103	96.94 15	96.58 83	97.32 86	93.07 92	98.72 166	90.45 139	98.84 132	97.57 201

VDDNet		94.03 132	94.27 126	93.31 176	98.87 20	82.36 220	95.51 85	91.78 311	97.19 12	96.32 92	98.60 18	84.24 234	98.75 161	87.09 219	98.83 137	98.81 84

CPTT-MVS		94.74 104	94.12 130	96.60 45	98.15 79	93.01 44	95.84 70	97.66 102	89.21 175	93.28 210	95.46 198	88.89 176	98.98 119	89.80 163	98.82 138	97.80 185

ACMMP++_ref															98.82 138

test1172		96.79 15	96.52 27	97.60 9	98.03 90	94.87 10	96.07 61	98.06 61	95.76 32	96.89 69	96.85 113	94.85 52	99.42 35	93.35 66	98.81 140	98.53 118

v2v482		93.29 147	93.63 142	92.29 208	96.35 190	78.82 276	91.77 224	96.28 198	88.45 190	95.70 127	96.26 158	86.02 222	98.90 130	93.02 80	98.81 140	99.14 43

USDC		89.02 253	89.08 243	88.84 301	95.07 258	74.50 326	88.97 293	96.39 195	73.21 336	93.27 211	96.28 156	82.16 254	96.39 313	77.55 316	98.80 142	95.62 286

tttt0517		89.81 243	88.90 249	92.55 204	97.00 148	79.73 259	95.03 103	83.65 363	89.88 157	95.30 142	94.79 231	53.64 372	99.39 54	91.99 104	98.79 143	98.54 117

PMVS	87.21 14	94.97 92	95.33 81	93.91 156	98.97 15	97.16 2	95.54 83	95.85 217	96.47 21	93.40 206	97.46 72	95.31 33	95.47 333	86.18 235	98.78 144	89.11 360
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
TinyColmap		92.00 190	92.76 164	89.71 287	95.62 243	77.02 299	90.72 245	96.17 207	87.70 207	95.26 145	96.29 155	92.54 106	96.45 311	81.77 278	98.77 145	95.66 283

v1240		93.29 147	93.71 139	92.06 219	96.01 220	77.89 288	91.81 222	97.37 123	85.12 247	96.69 78	96.40 144	86.67 214	99.07 108	94.51 22	98.76 146	99.22 36

DeepPCF-MVS	90.46 6	94.20 128	93.56 146	96.14 56	95.96 222	92.96 45	89.48 281	97.46 118	85.14 246	96.23 100	95.42 201	93.19 86	98.08 231	90.37 143	98.76 146	97.38 218

Anonymous20231206		88.77 262	88.29 259	90.20 278	96.31 194	78.81 277	89.56 280	93.49 279	74.26 331	92.38 243	95.58 191	82.21 252	95.43 335	72.07 347	98.75 148	96.34 254

SR-MVS		96.70 19	96.42 29	97.54 11	98.05 86	94.69 11	96.13 58	98.07 58	95.17 37	96.82 73	96.73 125	95.09 44	99.43 34	92.99 82	98.71 149	98.50 120

UGNet		93.08 156	92.50 173	94.79 116	93.87 293	87.99 130	95.07 101	94.26 266	90.64 141	87.33 329	97.67 60	86.89 211	98.49 198	88.10 200	98.71 149	97.91 172
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
LFMVS		91.33 203	91.16 206	91.82 223	96.27 197	79.36 265	95.01 104	85.61 351	96.04 29	94.82 165	97.06 99	72.03 316	98.46 204	84.96 249	98.70 151	97.65 196

HPM-MVS++		95.02 90	94.39 119	96.91 38	97.88 99	93.58 38	94.09 137	96.99 157	91.05 131	92.40 242	95.22 209	91.03 145	99.25 82	92.11 99	98.69 152	97.90 173

DVP-MVS++		95.93 54	96.34 34	94.70 120	96.54 176	86.66 158	98.45 4	98.22 33	93.26 70	97.54 41	97.36 80	93.12 89	99.38 60	93.88 38	98.68 153	98.04 154

PC_three_1452									75.31 327	95.87 119	95.75 183	92.93 95	96.34 318	87.18 217	98.68 153	98.04 154

miper_lstm_enhance		89.90 241	89.80 233	90.19 279	91.37 335	77.50 293	83.82 355	95.00 244	84.84 253	93.05 220	94.96 221	76.53 302	95.20 341	89.96 161	98.67 155	97.86 178

FMVSNet2		92.78 168	92.73 167	92.95 186	95.40 249	81.98 223	94.18 133	95.53 232	88.63 186	96.05 110	97.37 77	81.31 262	98.81 149	87.38 215	98.67 155	98.06 151

DeepC-MVS_fast	89.96 7	93.73 138	93.44 149	94.60 128	96.14 208	87.90 131	93.36 158	97.14 146	85.53 240	93.90 192	95.45 199	91.30 134	98.59 188	89.51 169	98.62 157	97.31 221
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
OPU-MVS				95.15 104	96.84 158	89.43 99	95.21 93				95.66 186	93.12 89	98.06 232	86.28 234	98.61 158	97.95 167

114514_t		90.51 217	89.80 233	92.63 200	98.00 93	82.24 221	93.40 157	97.29 136	65.84 364	89.40 299	94.80 230	86.99 206	98.75 161	83.88 259	98.61 158	96.89 234

patch_mono-2		92.46 179	92.72 168	91.71 228	96.65 166	78.91 274	88.85 296	97.17 144	83.89 261	92.45 239	96.76 120	89.86 169	97.09 291	90.24 151	98.59 160	99.12 46

dcpmvs_2		93.96 134	95.01 95	90.82 260	97.60 119	74.04 331	93.68 151	98.85 7	89.80 159	97.82 30	97.01 104	91.14 143	99.21 86	90.56 137	98.59 160	99.19 39

CDPH-MVS		92.67 172	91.83 186	95.18 103	96.94 151	88.46 122	90.70 246	97.07 152	77.38 315	92.34 247	95.08 215	92.67 103	98.88 133	85.74 237	98.57 162	98.20 143

c3_l		91.32 204	91.42 197	91.00 253	92.29 318	76.79 306	87.52 315	96.42 193	85.76 236	94.72 171	93.89 262	82.73 247	98.16 227	90.93 131	98.55 163	98.04 154

test_prior3		93.29 147	92.85 161	94.61 124	95.95 223	87.23 141	90.21 260	97.36 128	89.33 170	90.77 272	94.81 227	90.41 157	98.68 176	88.21 195	98.55 163	97.93 169

test_prior2							90.21 260		89.33 170	90.77 272	94.81 227	90.41 157		88.21 195	98.55 163

LCM-MVSNet-Re		94.20 128	94.58 113	93.04 181	95.91 226	83.13 213	93.79 146	99.19 3	92.00 95	98.84 5	98.04 44	93.64 72	99.02 115	81.28 282	98.54 166	96.96 231

Patchmatch-RL test		88.81 261	88.52 253	89.69 288	95.33 254	79.94 252	86.22 337	92.71 292	78.46 310	95.80 121	94.18 250	66.25 336	95.33 338	89.22 178	98.53 167	93.78 325

Anonymous202405211		92.58 175	92.50 173	92.83 193	96.55 175	83.22 210	92.43 185	91.64 312	94.10 52	95.59 130	96.64 131	81.88 259	97.50 273	85.12 245	98.52 168	97.77 187

CNVR-MVS		94.58 110	94.29 123	95.46 91	96.94 151	89.35 103	91.81 222	96.80 173	89.66 161	93.90 192	95.44 200	92.80 100	98.72 166	92.74 87	98.52 168	98.32 131

HQP_MVS		94.26 125	93.93 132	95.23 101	97.71 110	88.12 126	94.56 121	97.81 92	91.74 113	93.31 207	95.59 188	86.93 208	98.95 126	89.26 176	98.51 170	98.60 114

plane_prior5								97.81 92					98.95 126	89.26 176	98.51 170	98.60 114

baseline		94.26 125	94.80 102	92.64 198	96.08 213	80.99 237	93.69 149	98.04 66	90.80 137	94.89 163	96.32 153	93.19 86	98.48 202	91.68 116	98.51 170	98.43 126

ETH3D cwj APD-0.16		93.99 133	93.38 151	95.80 76	96.82 160	89.92 86	92.72 172	98.02 69	84.73 255	93.65 198	95.54 195	91.68 124	99.22 85	88.78 187	98.49 173	98.26 137

thisisatest0530		88.69 264	87.52 274	92.20 211	96.33 192	79.36 265	92.81 169	84.01 362	86.44 224	93.67 197	92.68 293	53.62 373	99.25 82	89.65 168	98.45 174	98.00 159

train_agg		92.71 171	91.83 186	95.35 93	96.45 183	89.46 97	90.60 248	96.92 162	79.37 299	90.49 277	94.39 243	91.20 139	98.88 133	88.66 191	98.43 175	97.72 191

GeoE		94.55 111	94.68 109	94.15 145	97.23 137	85.11 187	94.14 135	97.34 131	88.71 185	95.26 145	95.50 196	94.65 57	99.12 100	90.94 130	98.40 176	98.23 139

ZD-MVS					97.23 137	90.32 82		97.54 112	84.40 257	94.78 167	95.79 179	92.76 101	99.39 54	88.72 190	98.40 176

test9_res														88.16 199	98.40 176	97.83 181

ETH3 D test6400		91.91 191	91.25 202	93.89 157	96.59 171	84.41 193	92.10 201	97.72 100	78.52 309	91.82 257	93.78 266	88.70 177	99.13 96	83.61 260	98.39 179	98.14 146

TSAR-MVS + GP.		93.07 158	92.41 175	95.06 107	95.82 229	90.87 74	90.97 239	92.61 296	88.04 199	94.61 172	93.79 265	88.08 185	97.81 255	89.41 171	98.39 179	96.50 248

VNet		92.67 172	92.96 158	91.79 224	96.27 197	80.15 244	91.95 208	94.98 245	92.19 92	94.52 175	96.07 166	87.43 197	97.39 282	84.83 250	98.38 181	97.83 181

GBi-Net		93.21 153	92.96 158	93.97 151	95.40 249	84.29 194	95.99 62	96.56 186	88.63 186	95.10 152	98.53 22	81.31 262	98.98 119	86.74 222	98.38 181	98.65 103

test1		93.21 153	92.96 158	93.97 151	95.40 249	84.29 194	95.99 62	96.56 186	88.63 186	95.10 152	98.53 22	81.31 262	98.98 119	86.74 222	98.38 181	98.65 103

FMVSNet3		90.78 211	90.32 224	92.16 216	93.03 307	79.92 253	92.54 178	94.95 246	86.17 229	95.10 152	96.01 169	69.97 322	98.75 161	86.74 222	98.38 181	97.82 183

MVS_111021_HR		93.63 140	93.42 150	94.26 143	96.65 166	86.96 151	89.30 287	96.23 202	88.36 194	93.57 201	94.60 236	93.45 77	97.77 260	90.23 152	98.38 181	98.03 157

agg_prior1		92.60 174	91.76 189	95.10 106	96.20 202	88.89 110	90.37 255	96.88 166	79.67 296	90.21 282	94.41 241	91.30 134	98.78 156	88.46 194	98.37 186	97.64 197

agg_prior2														87.06 220	98.36 187	97.98 163

TSAR-MVS + MP.		94.96 93	94.75 104	95.57 87	98.86 21	88.69 113	96.37 45	96.81 172	85.23 243	94.75 168	97.12 96	91.85 120	99.40 49	93.45 58	98.33 188	98.62 111
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
pmmvs-eth3d		91.54 198	90.73 215	93.99 149	95.76 234	87.86 133	90.83 242	93.98 273	78.23 312	94.02 188	96.22 160	82.62 250	96.83 301	86.57 227	98.33 188	97.29 222

casdiffmvs		94.32 121	94.80 102	92.85 192	96.05 215	81.44 232	92.35 191	98.05 62	91.53 120	95.75 123	96.80 117	93.35 82	98.49 198	91.01 129	98.32 190	98.64 107

Regformer-1		94.55 111	94.33 122	95.19 102	92.83 310	88.54 120	91.87 216	95.84 218	93.99 53	95.95 113	95.04 217	92.00 116	98.79 152	93.14 76	98.31 191	98.23 139

Regformer-2		94.86 98	94.55 114	95.77 78	92.83 310	89.98 85	91.87 216	96.40 194	94.38 47	96.19 105	95.04 217	92.47 109	99.04 112	93.49 52	98.31 191	98.28 135

3Dnovator+	92.74 2	95.86 58	95.77 66	96.13 57	96.81 162	90.79 75	96.30 53	97.82 91	96.13 25	94.74 169	97.23 90	91.33 132	99.16 91	93.25 71	98.30 193	98.46 124

MVS_111021_LR		93.66 139	93.28 154	94.80 115	96.25 200	90.95 71	90.21 260	95.43 235	87.91 200	93.74 196	94.40 242	92.88 98	96.38 314	90.39 141	98.28 194	97.07 225

CANet		92.38 181	91.99 182	93.52 171	93.82 295	83.46 207	91.14 235	97.00 155	89.81 158	86.47 333	94.04 254	87.90 191	99.21 86	89.50 170	98.27 195	97.90 173

EI-MVSNet		92.99 160	93.26 156	92.19 212	92.12 323	79.21 270	92.32 193	94.67 258	91.77 111	95.24 148	95.85 174	87.14 204	98.49 198	91.99 104	98.26 196	98.86 78

MVSTER		89.32 249	88.75 251	91.03 250	90.10 349	76.62 307	90.85 241	94.67 258	82.27 279	95.24 148	95.79 179	61.09 359	98.49 198	90.49 138	98.26 196	97.97 166

testtj		94.81 102	94.42 118	96.01 60	97.23 137	90.51 81	94.77 111	97.85 88	91.29 124	94.92 162	95.66 186	91.71 123	99.40 49	88.07 202	98.25 198	98.11 150

MSLP-MVS++		93.25 152	93.88 133	91.37 238	96.34 191	82.81 217	93.11 161	97.74 98	89.37 168	94.08 183	95.29 208	90.40 159	96.35 316	90.35 144	98.25 198	94.96 298

LF4IMVS		92.72 170	92.02 181	94.84 114	95.65 240	91.99 56	92.92 166	96.60 184	85.08 249	92.44 240	93.62 269	86.80 212	96.35 316	86.81 221	98.25 198	96.18 261

EI-MVSNet-UG-set		94.35 119	94.27 126	94.59 129	92.46 316	85.87 178	92.42 186	94.69 256	93.67 66	96.13 107	95.84 177	91.20 139	98.86 139	93.78 42	98.23 201	99.03 54

PM-MVS		93.33 146	92.67 169	95.33 95	96.58 172	94.06 21	92.26 196	92.18 302	85.92 233	96.22 101	96.61 133	85.64 227	95.99 325	90.35 144	98.23 201	95.93 270

EI-MVSNet-Vis-set		94.36 118	94.28 124	94.61 124	92.55 315	85.98 176	92.44 184	94.69 256	93.70 62	96.12 108	95.81 178	91.24 136	98.86 139	93.76 45	98.22 203	98.98 63

V42		93.43 144	93.58 144	92.97 184	95.34 253	81.22 234	92.67 175	96.49 191	87.25 215	96.20 103	96.37 150	87.32 199	98.85 141	92.39 97	98.21 204	98.85 81

TAMVS		90.16 232	89.05 244	93.49 172	96.49 181	86.37 166	90.34 257	92.55 297	80.84 288	92.99 222	94.57 238	81.94 258	98.20 222	73.51 339	98.21 204	95.90 273

K. test v3		93.37 145	93.27 155	93.66 163	98.05 86	82.62 218	94.35 127	86.62 341	96.05 28	97.51 44	98.85 12	76.59 301	99.65 3	93.21 72	98.20 206	98.73 96

DELS-MVS		92.05 189	92.16 177	91.72 227	94.44 279	80.13 246	87.62 309	97.25 139	87.34 214	92.22 250	93.18 281	89.54 172	98.73 165	89.67 167	98.20 206	96.30 256
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
TAPA-MVS	88.58 10	92.49 178	91.75 190	94.73 118	96.50 180	89.69 93	92.91 167	97.68 101	78.02 313	92.79 228	94.10 252	90.85 146	97.96 243	84.76 252	98.16 208	96.54 243
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
LS3D		96.11 49	95.83 63	96.95 37	94.75 267	94.20 19	97.34 12	97.98 74	97.31 11	95.32 141	96.77 118	93.08 91	99.20 88	91.79 112	98.16 208	97.44 211

Regformer-3		94.28 122	94.23 128	94.46 137	92.78 312	86.28 170	92.39 188	94.70 255	93.69 65	95.97 111	95.56 193	91.34 131	98.48 202	93.45 58	98.14 210	98.62 111

Regformer-4		94.90 95	94.67 110	95.59 85	92.78 312	89.02 106	92.39 188	95.91 214	94.50 43	96.41 86	95.56 193	92.10 114	99.01 117	94.23 30	98.14 210	98.74 94

DP-MVS Recon		92.31 183	91.88 185	93.60 165	97.18 141	86.87 152	91.10 237	97.37 123	84.92 252	92.08 253	94.08 253	88.59 178	98.20 222	83.50 261	98.14 210	95.73 279

EG-PatchMatch MVS		94.54 113	94.67 110	94.14 146	97.87 100	86.50 160	92.00 207	96.74 178	88.16 197	96.93 68	97.61 63	93.04 93	97.90 245	91.60 118	98.12 213	98.03 157

PCF-MVS	84.52 17	89.12 252	87.71 271	93.34 174	96.06 214	85.84 179	86.58 336	97.31 133	68.46 357	93.61 200	93.89 262	87.51 196	98.52 196	67.85 362	98.11 214	95.66 283
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	92.54 3	94.80 103	94.90 98	94.47 136	95.47 247	87.06 146	96.63 31	97.28 138	91.82 108	94.34 180	97.41 74	90.60 154	98.65 181	92.47 94	98.11 214	97.70 192

PMMVS2		81.31 329	83.44 313	74.92 357	90.52 344	46.49 382	69.19 371	85.23 357	84.30 258	87.95 322	94.71 234	76.95 297	84.36 375	64.07 368	98.09 216	93.89 323

lessismore_v0				93.87 159	98.05 86	83.77 205		80.32 372		97.13 57	97.91 51	77.49 289	99.11 102	92.62 91	98.08 217	98.74 94

new-patchmatchnet		88.97 256	90.79 213	83.50 346	94.28 283	55.83 380	85.34 341	93.56 277	86.18 228	95.47 133	95.73 184	83.10 242	96.51 309	85.40 240	98.06 218	98.16 144

plane_prior						88.12 126	93.01 163		88.98 178						98.06 218

PVSNet_BlendedMVS		90.35 225	89.96 230	91.54 234	94.81 264	78.80 278	90.14 264	96.93 160	79.43 298	88.68 313	95.06 216	86.27 219	98.15 228	80.27 290	98.04 220	97.68 194

CL-MVSNet_self_test		90.04 239	89.90 232	90.47 268	95.24 255	77.81 289	86.60 335	92.62 295	85.64 238	93.25 214	93.92 260	83.84 236	96.06 323	79.93 297	98.03 221	97.53 205

FMVSNet5		87.82 276	86.56 291	91.62 231	92.31 317	79.81 257	93.49 154	94.81 252	83.26 264	91.36 262	96.93 108	52.77 374	97.49 275	76.07 327	98.03 221	97.55 204

原ACMM1				92.87 191	96.91 154	84.22 197		97.01 154	76.84 320	89.64 297	94.46 240	88.00 188	98.70 172	81.53 280	98.01 223	95.70 281

v148		92.87 165	93.29 152	91.62 231	96.25 200	77.72 291	91.28 233	95.05 243	89.69 160	95.93 116	96.04 167	87.34 198	98.38 207	90.05 159	97.99 224	98.78 88

ITE_SJBPF				95.95 64	97.34 134	93.36 42		96.55 189	91.93 98	94.82 165	95.39 204	91.99 117	97.08 292	85.53 239	97.96 225	97.41 212

test12				94.43 139	95.95 223	86.75 154		96.24 201		89.76 295		89.79 170	98.79 152		97.95 226	97.75 190

MCST-MVS		92.91 162	92.51 172	94.10 147	97.52 124	85.72 181	91.36 232	97.13 148	80.33 290	92.91 225	94.24 247	91.23 137	98.72 166	89.99 160	97.93 227	97.86 178

CDS-MVSNet		89.55 245	88.22 263	93.53 170	95.37 252	86.49 161	89.26 288	93.59 276	79.76 294	91.15 267	92.31 301	77.12 294	98.38 207	77.51 317	97.92 228	95.71 280
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
旧先验1					96.20 202	84.17 199		94.82 250			95.57 192	89.57 171			97.89 229	96.32 255

alignmvs		93.26 150	92.85 161	94.50 133	95.70 236	87.45 137	93.45 156	95.76 219	91.58 118	95.25 147	92.42 300	81.96 257	98.72 166	91.61 117	97.87 230	97.33 220

testgi		90.38 223	91.34 200	87.50 320	97.49 126	71.54 346	89.43 282	95.16 242	88.38 193	94.54 174	94.68 235	92.88 98	93.09 359	71.60 351	97.85 231	97.88 176

MVS_0304		90.96 208	90.15 228	93.37 173	93.17 302	87.06 146	93.62 152	92.43 300	89.60 163	82.25 358	95.50 196	82.56 251	97.83 254	84.41 256	97.83 232	95.22 291

新几何1				93.17 180	97.16 142	87.29 140		94.43 261	67.95 358	91.29 263	94.94 222	86.97 207	98.23 220	81.06 287	97.75 233	93.98 321

ETV-MVS		92.99 160	92.74 165	93.72 162	95.86 228	86.30 169	92.33 192	97.84 89	91.70 116	92.81 227	86.17 362	92.22 111	99.19 89	88.03 203	97.73 234	95.66 283

HQP3-MVS								97.31 133							97.73 234

HQP-MVS		92.09 188	91.49 196	93.88 158	96.36 187	84.89 189	91.37 229	97.31 133	87.16 216	88.81 306	93.40 275	84.76 230	98.60 186	86.55 228	97.73 234	98.14 146

1121		90.26 229	89.23 240	93.34 174	97.15 144	87.40 138	91.94 210	94.39 262	67.88 359	91.02 270	94.91 223	86.91 210	98.59 188	81.17 285	97.71 237	94.02 320

CANet_DTU		89.85 242	89.17 242	91.87 222	92.20 321	80.02 251	90.79 243	95.87 216	86.02 231	82.53 357	91.77 309	80.01 271	98.57 191	85.66 238	97.70 238	97.01 229

NCCC		94.08 131	93.54 147	95.70 83	96.49 181	89.90 88	92.39 188	96.91 164	90.64 141	92.33 248	94.60 236	90.58 155	98.96 124	90.21 153	97.70 238	98.23 139

Vis-MVSNet		95.50 71	95.48 74	95.56 88	98.11 81	89.40 101	95.35 87	98.22 33	92.36 85	94.11 181	98.07 42	92.02 115	99.44 30	93.38 65	97.67 240	97.85 180
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
AdaColmap		91.63 196	91.36 199	92.47 207	95.56 245	86.36 167	92.24 198	96.27 199	88.88 182	89.90 290	92.69 292	91.65 125	98.32 212	77.38 319	97.64 241	92.72 343

EPNet_dtu		85.63 303	84.37 307	89.40 292	86.30 372	74.33 328	91.64 225	88.26 329	84.84 253	72.96 375	89.85 331	71.27 318	97.69 266	76.60 324	97.62 242	96.18 261
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
XVG-OURS		94.72 105	94.12 130	96.50 50	98.00 93	94.23 18	91.48 228	98.17 41	90.72 138	95.30 142	96.47 138	87.94 190	96.98 295	91.41 123	97.61 243	98.30 134

canonicalmvs		94.59 109	94.69 107	94.30 142	95.60 244	87.03 148	95.59 79	98.24 31	91.56 119	95.21 150	92.04 306	94.95 50	98.66 179	91.45 122	97.57 244	97.20 224

XXY-MVS		92.58 175	93.16 157	90.84 259	97.75 106	79.84 254	91.87 216	96.22 204	85.94 232	95.53 132	97.68 59	92.69 102	94.48 345	83.21 264	97.51 245	98.21 142

Effi-MVS+-dtu		93.90 136	92.60 171	97.77 4	94.74 268	96.67 3	94.00 140	95.41 236	89.94 154	91.93 256	92.13 304	90.12 162	98.97 123	87.68 209	97.48 246	97.67 195

OpenMVS	89.45 8	92.27 185	92.13 179	92.68 197	94.53 278	84.10 200	95.70 75	97.03 153	82.44 278	91.14 268	96.42 142	88.47 180	98.38 207	85.95 236	97.47 247	95.55 287

ab-mvs		92.40 180	92.62 170	91.74 226	97.02 147	81.65 227	95.84 70	95.50 233	86.95 221	92.95 224	97.56 65	90.70 152	97.50 273	79.63 300	97.43 248	96.06 265

thisisatest0515		84.72 309	82.99 317	89.90 284	92.96 308	75.33 320	84.36 350	83.42 364	77.37 316	88.27 318	86.65 357	53.94 371	98.72 166	82.56 270	97.40 249	95.67 282

test222					96.95 150	85.27 186	88.83 297	93.61 275	65.09 366	90.74 274	94.85 226	84.62 233			97.36 250	93.91 322

API-MVS		91.52 199	91.61 191	91.26 242	94.16 284	86.26 172	94.66 115	94.82 250	91.17 129	92.13 252	91.08 319	90.03 168	97.06 293	79.09 307	97.35 251	90.45 358

EIA-MVS		92.35 182	92.03 180	93.30 177	95.81 231	83.97 202	92.80 170	98.17 41	87.71 206	89.79 294	87.56 352	91.17 142	99.18 90	87.97 204	97.27 252	96.77 239

testdata				91.03 250	96.87 156	82.01 222		94.28 265	71.55 343	92.46 238	95.42 201	85.65 226	97.38 284	82.64 269	97.27 252	93.70 328

N_pmnet		88.90 259	87.25 278	93.83 160	94.40 281	93.81 36	84.73 345	87.09 338	79.36 301	93.26 212	92.43 299	79.29 275	91.68 364	77.50 318	97.22 254	96.00 267

ppachtmachnet_test		88.61 265	88.64 252	88.50 307	91.76 329	70.99 350	84.59 348	92.98 285	79.30 303	92.38 243	93.53 273	79.57 273	97.45 277	86.50 230	97.17 255	97.07 225

CNLPA		91.72 194	91.20 203	93.26 178	96.17 205	91.02 69	91.14 235	95.55 230	90.16 151	90.87 271	93.56 272	86.31 218	94.40 348	79.92 299	97.12 256	94.37 311

jason		89.17 251	88.32 257	91.70 229	95.73 235	80.07 247	88.10 306	93.22 282	71.98 342	90.09 284	92.79 289	78.53 283	98.56 192	87.43 213	97.06 257	96.46 250
jason: jason.
RPSCF		95.58 69	94.89 99	97.62 8	97.58 121	96.30 4	95.97 65	97.53 114	92.42 82	93.41 204	97.78 55	91.21 138	97.77 260	91.06 126	97.06 257	98.80 86

cl22		89.02 253	88.50 254	90.59 266	89.76 351	76.45 309	86.62 334	94.03 269	82.98 271	92.65 232	92.49 295	72.05 315	97.53 271	88.93 182	97.02 259	97.78 186

miper_ehance_all_eth		90.48 218	90.42 222	90.69 263	91.62 332	76.57 308	86.83 327	96.18 206	83.38 263	94.06 185	92.66 294	82.20 253	98.04 233	89.79 164	97.02 259	97.45 209

miper_enhance_ethall		88.42 267	87.87 269	90.07 280	88.67 363	75.52 318	85.10 342	95.59 227	75.68 322	92.49 236	89.45 341	78.96 276	97.88 247	87.86 207	97.02 259	96.81 237

eth_miper_zixun_eth		90.72 212	90.61 217	91.05 249	92.04 325	76.84 305	86.91 324	96.67 181	85.21 244	94.41 176	93.92 260	79.53 274	98.26 218	89.76 165	97.02 259	98.06 151

QAPM		92.88 164	92.77 163	93.22 179	95.82 229	83.31 208	96.45 40	97.35 130	83.91 260	93.75 194	96.77 118	89.25 174	98.88 133	84.56 254	97.02 259	97.49 207

thres600view7		87.66 279	87.10 283	89.36 293	96.05 215	73.17 335	92.72 172	85.31 354	91.89 100	93.29 209	90.97 320	63.42 350	98.39 205	73.23 341	96.99 264	96.51 245

test_yl		90.11 234	89.73 236	91.26 242	94.09 287	79.82 255	90.44 252	92.65 293	90.90 132	93.19 216	93.30 277	73.90 308	98.03 234	82.23 274	96.87 265	95.93 270

DCV-MVSNet		90.11 234	89.73 236	91.26 242	94.09 287	79.82 255	90.44 252	92.65 293	90.90 132	93.19 216	93.30 277	73.90 308	98.03 234	82.23 274	96.87 265	95.93 270

MSP-MVS		95.34 79	94.63 112	97.48 14	98.67 31	94.05 23	96.41 44	98.18 37	91.26 125	95.12 151	95.15 210	86.60 216	99.50 21	93.43 62	96.81 267	98.89 75
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
pmmvs5		87.87 274	87.14 281	90.07 280	93.26 301	76.97 303	88.89 295	92.18 302	73.71 334	88.36 316	93.89 262	76.86 300	96.73 304	80.32 289	96.81 267	96.51 245

PVSNet_Blended_VisFu		91.63 196	91.20 203	92.94 188	97.73 109	83.95 203	92.14 200	97.46 118	78.85 308	92.35 245	94.98 220	84.16 235	99.08 104	86.36 232	96.77 269	95.79 277

MVSFormer		92.18 187	92.23 176	92.04 220	94.74 268	80.06 248	97.15 15	97.37 123	88.98 178	88.83 304	92.79 289	77.02 295	99.60 9	96.41 4	96.75 270	96.46 250

lupinMVS		88.34 269	87.31 276	91.45 236	94.74 268	80.06 248	87.23 317	92.27 301	71.10 346	88.83 304	91.15 317	77.02 295	98.53 195	86.67 225	96.75 270	95.76 278

diffmvs		91.74 193	91.93 184	91.15 248	93.06 305	78.17 284	88.77 299	97.51 117	86.28 226	92.42 241	93.96 259	88.04 187	97.46 276	90.69 136	96.67 272	97.82 183

DPM-MVS		89.35 248	88.40 256	92.18 215	96.13 211	84.20 198	86.96 323	96.15 208	75.40 326	87.36 328	91.55 314	83.30 240	98.01 238	82.17 276	96.62 273	94.32 313

thres100view900		87.35 287	86.89 285	88.72 303	96.14 208	73.09 337	93.00 164	85.31 354	92.13 93	93.26 212	90.96 321	63.42 350	98.28 214	71.27 353	96.54 274	94.79 301

tfpn200view9		87.05 295	86.52 293	88.67 304	95.77 232	72.94 338	91.89 213	86.00 346	90.84 134	92.61 233	89.80 333	63.93 347	98.28 214	71.27 353	96.54 274	94.79 301

thres400		87.20 291	86.52 293	89.24 297	95.77 232	72.94 338	91.89 213	86.00 346	90.84 134	92.61 233	89.80 333	63.93 347	98.28 214	71.27 353	96.54 274	96.51 245

CMPMVS	68.83 22	87.28 288	85.67 301	92.09 218	88.77 362	85.42 184	90.31 258	94.38 263	70.02 352	88.00 321	93.30 277	73.78 310	94.03 353	75.96 329	96.54 274	96.83 236
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
pmmvs4		88.95 257	87.70 272	92.70 196	94.30 282	85.60 182	87.22 318	92.16 304	74.62 329	89.75 296	94.19 249	77.97 287	96.41 312	82.71 268	96.36 278	96.09 263

Fast-Effi-MVS+-dtu		92.77 169	92.16 177	94.58 131	94.66 274	88.25 124	92.05 203	96.65 182	89.62 162	90.08 285	91.23 316	92.56 105	98.60 186	86.30 233	96.27 279	96.90 233

MAR-MVS		90.32 227	88.87 250	94.66 122	94.82 263	91.85 59	94.22 132	94.75 253	80.91 285	87.52 327	88.07 351	86.63 215	97.87 250	76.67 323	96.21 280	94.25 314
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
AUN-MVS		90.05 238	88.30 258	95.32 98	96.09 212	90.52 80	92.42 186	92.05 308	82.08 281	88.45 315	92.86 286	65.76 338	98.69 174	88.91 184	96.07 281	96.75 241

hse-mvs2		92.24 186	91.20 203	95.38 92	96.16 206	90.65 78	92.52 179	92.01 309	89.23 172	93.95 189	92.99 284	76.88 298	98.69 174	91.02 127	96.03 282	96.81 237

PVSNet_Blended		88.74 263	88.16 265	90.46 270	94.81 264	78.80 278	86.64 332	96.93 160	74.67 328	88.68 313	89.18 344	86.27 219	98.15 228	80.27 290	96.00 283	94.44 310

F-COLMAP		92.28 184	91.06 207	95.95 64	97.52 124	91.90 58	93.53 153	97.18 143	83.98 259	88.70 312	94.04 254	88.41 181	98.55 194	80.17 293	95.99 284	97.39 216

xiu_mvs_v1_base_debu		91.47 200	91.52 193	91.33 239	95.69 237	81.56 228	89.92 271	96.05 210	83.22 265	91.26 264	90.74 323	91.55 127	98.82 144	89.29 173	95.91 285	93.62 330

xiu_mvs_v1_base		91.47 200	91.52 193	91.33 239	95.69 237	81.56 228	89.92 271	96.05 210	83.22 265	91.26 264	90.74 323	91.55 127	98.82 144	89.29 173	95.91 285	93.62 330

xiu_mvs_v1_base_debi		91.47 200	91.52 193	91.33 239	95.69 237	81.56 228	89.92 271	96.05 210	83.22 265	91.26 264	90.74 323	91.55 127	98.82 144	89.29 173	95.91 285	93.62 330

thres200		85.85 302	85.18 303	87.88 317	94.44 279	72.52 342	89.08 292	86.21 343	88.57 189	91.44 261	88.40 349	64.22 345	98.00 239	68.35 361	95.88 288	93.12 336

Patchmatch-test		86.10 301	86.01 298	86.38 330	90.63 342	74.22 330	89.57 279	86.69 340	85.73 237	89.81 293	92.83 287	65.24 342	91.04 366	77.82 315	95.78 289	93.88 324

h-mvs33		92.89 163	91.99 182	95.58 86	96.97 149	90.55 79	93.94 143	94.01 272	89.23 172	93.95 189	96.19 161	76.88 298	99.14 94	91.02 127	95.71 290	97.04 228

mvs-test1		93.07 158	91.80 188	96.89 39	94.74 268	95.83 6	92.17 199	95.41 236	89.94 154	89.85 291	90.59 329	90.12 162	98.88 133	87.68 209	95.66 291	95.97 268

cascas		87.02 296	86.28 297	89.25 296	91.56 333	76.45 309	84.33 351	96.78 174	71.01 347	86.89 332	85.91 363	81.35 261	96.94 296	83.09 265	95.60 292	94.35 312

XVG-OURS-SEG-HR		95.38 77	95.00 96	96.51 49	98.10 82	94.07 20	92.46 183	98.13 46	90.69 139	93.75 194	96.25 159	98.03 2	97.02 294	92.08 101	95.55 293	98.45 125

DSMNet-mixed		82.21 323	81.56 322	84.16 343	89.57 355	70.00 356	90.65 247	77.66 377	54.99 375	83.30 353	97.57 64	77.89 288	90.50 368	66.86 365	95.54 294	91.97 348

MVS_Test		92.57 177	93.29 152	90.40 271	93.53 297	75.85 315	92.52 179	96.96 158	88.73 183	92.35 245	96.70 127	90.77 147	98.37 210	92.53 93	95.49 295	96.99 230

MIMVSNet		87.13 294	86.54 292	88.89 300	96.05 215	76.11 312	94.39 126	88.51 327	81.37 284	88.27 318	96.75 122	72.38 313	95.52 330	65.71 367	95.47 296	95.03 296

Fast-Effi-MVS+		91.28 205	90.86 210	92.53 205	95.45 248	82.53 219	89.25 290	96.52 190	85.00 250	89.91 289	88.55 348	92.94 94	98.84 142	84.72 253	95.44 297	96.22 259

ET-MVSNet_ETH3D		86.15 300	84.27 309	91.79 224	93.04 306	81.28 233	87.17 320	86.14 344	79.57 297	83.65 349	88.66 346	57.10 364	98.18 225	87.74 208	95.40 298	95.90 273

BH-RMVSNet		90.47 219	90.44 221	90.56 267	95.21 256	78.65 280	89.15 291	93.94 274	88.21 195	92.74 230	94.22 248	86.38 217	97.88 247	78.67 309	95.39 299	95.14 294

CHOSEN 1792x2688		87.19 292	85.92 300	91.00 253	97.13 145	79.41 264	84.51 349	95.60 223	64.14 367	90.07 286	94.81 227	78.26 285	97.14 290	73.34 340	95.38 300	96.46 250

Effi-MVS+		92.79 167	92.74 165	92.94 188	95.10 257	83.30 209	94.00 140	97.53 114	91.36 123	89.35 300	90.65 328	94.01 69	98.66 179	87.40 214	95.30 301	96.88 235

MG-MVS		89.54 246	89.80 233	88.76 302	94.88 260	72.47 343	89.60 278	92.44 299	85.82 234	89.48 298	95.98 170	82.85 245	97.74 264	81.87 277	95.27 302	96.08 264

HyFIR lowres test		87.19 292	85.51 302	92.24 210	97.12 146	80.51 241	85.03 343	96.06 209	66.11 363	91.66 259	92.98 285	70.12 321	99.14 94	75.29 331	95.23 303	97.07 225

BH-untuned		90.68 214	90.90 208	90.05 282	95.98 221	79.57 262	90.04 267	94.94 247	87.91 200	94.07 184	93.00 283	87.76 192	97.78 259	79.19 306	95.17 304	92.80 342

pmmvs3		80.83 334	78.96 340	86.45 327	87.23 368	77.48 294	84.87 344	82.31 366	63.83 368	85.03 340	89.50 340	49.66 375	93.10 358	73.12 343	95.10 305	88.78 363

mvs_anonymous		90.37 224	91.30 201	87.58 319	92.17 322	68.00 360	89.84 274	94.73 254	83.82 262	93.22 215	97.40 75	87.54 195	97.40 281	87.94 205	95.05 306	97.34 219

IterMVS-SCA-FT		91.65 195	91.55 192	91.94 221	93.89 292	79.22 269	87.56 312	93.51 278	91.53 120	95.37 138	96.62 132	78.65 280	98.90 130	91.89 109	94.95 307	97.70 192

test-LLR		83.58 314	83.17 315	84.79 339	89.68 353	66.86 363	83.08 356	84.52 359	83.07 269	82.85 355	84.78 366	62.86 353	93.49 356	82.85 266	94.86 308	94.03 318

test-mter		81.21 331	80.01 338	84.79 339	89.68 353	66.86 363	83.08 356	84.52 359	73.85 333	82.85 355	84.78 366	43.66 381	93.49 356	82.85 266	94.86 308	94.03 318

PatchMatch-RL		89.18 250	88.02 268	92.64 198	95.90 227	92.87 47	88.67 303	91.06 315	80.34 289	90.03 287	91.67 311	83.34 239	94.42 347	76.35 326	94.84 310	90.64 357

OpenMVS_ROB	85.12 16	89.52 247	89.05 244	90.92 255	94.58 277	81.21 235	91.10 237	93.41 280	77.03 319	93.41 204	93.99 258	83.23 241	97.80 256	79.93 297	94.80 311	93.74 327

our_test_3		87.55 282	87.59 273	87.44 321	91.76 329	70.48 351	83.83 354	90.55 320	79.79 293	92.06 254	92.17 303	78.63 282	95.63 328	84.77 251	94.73 312	96.22 259

CHOSEN 280x420		80.04 338	77.97 343	86.23 331	90.13 348	74.53 325	72.87 369	89.59 323	66.38 362	76.29 372	85.32 365	56.96 365	95.36 336	69.49 360	94.72 313	88.79 362

IterMVS		90.18 231	90.16 225	90.21 277	93.15 303	75.98 314	87.56 312	92.97 286	86.43 225	94.09 182	96.40 144	78.32 284	97.43 278	87.87 206	94.69 314	97.23 223
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EMVS		80.35 337	80.28 336	80.54 352	84.73 377	69.07 358	72.54 370	80.73 370	87.80 204	81.66 364	81.73 371	62.89 352	89.84 369	75.79 330	94.65 315	82.71 370

PLC	85.34 15	90.40 221	88.92 247	94.85 113	96.53 179	90.02 84	91.58 226	96.48 192	80.16 291	86.14 335	92.18 302	85.73 224	98.25 219	76.87 322	94.61 316	96.30 256
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MSDG		90.82 209	90.67 216	91.26 242	94.16 284	83.08 214	86.63 333	96.19 205	90.60 143	91.94 255	91.89 307	89.16 175	95.75 327	80.96 288	94.51 317	94.95 299

xiu_mvs_v2_base		89.00 255	89.19 241	88.46 309	94.86 262	74.63 323	86.97 322	95.60 223	80.88 286	87.83 323	88.62 347	91.04 144	98.81 149	82.51 272	94.38 318	91.93 349

PS-MVSNAJ		88.86 260	88.99 246	88.48 308	94.88 260	74.71 321	86.69 331	95.60 223	80.88 286	87.83 323	87.37 355	90.77 147	98.82 144	82.52 271	94.37 319	91.93 349

EU-MVSNet		87.39 286	86.71 289	89.44 290	93.40 298	76.11 312	94.93 107	90.00 322	57.17 373	95.71 126	97.37 77	64.77 344	97.68 267	92.67 90	94.37 319	94.52 308

E-PMN		80.72 335	80.86 330	80.29 353	85.11 375	68.77 359	72.96 368	81.97 367	87.76 205	83.25 354	83.01 370	62.22 356	89.17 371	77.15 321	94.31 321	82.93 369

GA-MVS		87.70 277	86.82 286	90.31 272	93.27 300	77.22 298	84.72 347	92.79 290	85.11 248	89.82 292	90.07 330	66.80 331	97.76 262	84.56 254	94.27 322	95.96 269

sss		87.23 289	86.82 286	88.46 309	93.96 290	77.94 285	86.84 326	92.78 291	77.59 314	87.61 326	91.83 308	78.75 278	91.92 363	77.84 313	94.20 323	95.52 288

MDA-MVSNet-bldmvs		91.04 206	90.88 209	91.55 233	94.68 273	80.16 243	85.49 340	92.14 305	90.41 148	94.93 161	95.79 179	85.10 228	96.93 298	85.15 243	94.19 324	97.57 201

PAPM_NR		91.03 207	90.81 212	91.68 230	96.73 164	81.10 236	93.72 148	96.35 197	88.19 196	88.77 310	92.12 305	85.09 229	97.25 286	82.40 273	93.90 325	96.68 242

YYNet1		88.17 270	88.24 261	87.93 315	92.21 320	73.62 333	80.75 363	88.77 325	82.51 277	94.99 159	95.11 213	82.70 248	93.70 354	83.33 262	93.83 326	96.48 249

MDA-MVSNet_test_wron		88.16 271	88.23 262	87.93 315	92.22 319	73.71 332	80.71 364	88.84 324	82.52 276	94.88 164	95.14 211	82.70 248	93.61 355	83.28 263	93.80 327	96.46 250

1112_ss		88.42 267	87.41 275	91.45 236	96.69 165	80.99 237	89.72 276	96.72 179	73.37 335	87.00 331	90.69 326	77.38 291	98.20 222	81.38 281	93.72 328	95.15 293

PVSNet	76.22 20	82.89 319	82.37 319	84.48 341	93.96 290	64.38 373	78.60 366	88.61 326	71.50 344	84.43 346	86.36 361	74.27 307	94.60 344	69.87 359	93.69 329	94.46 309

TESTMET0.1,1		79.09 340	78.04 342	82.25 349	87.52 366	64.03 374	83.08 356	80.62 371	70.28 351	80.16 367	83.22 369	44.13 380	90.56 367	79.95 295	93.36 330	92.15 347

PAPR		87.65 280	86.77 288	90.27 274	92.85 309	77.38 295	88.56 304	96.23 202	76.82 321	84.98 341	89.75 337	86.08 221	97.16 289	72.33 346	93.35 331	96.26 258

SCA		87.43 285	87.21 279	88.10 313	92.01 326	71.98 345	89.43 282	88.11 333	82.26 280	88.71 311	92.83 287	78.65 280	97.59 269	79.61 301	93.30 332	94.75 303

Test_1112_low_res		87.50 284	86.58 290	90.25 275	96.80 163	77.75 290	87.53 314	96.25 200	69.73 353	86.47 333	93.61 270	75.67 304	97.88 247	79.95 295	93.20 333	95.11 295

MDTV_nov1_ep13			83.88 312		89.42 357	61.52 376	88.74 300	87.41 336	73.99 332	84.96 342	94.01 257	65.25 341	95.53 329	78.02 311	93.16 334

WTY-MVS		86.93 297	86.50 295	88.24 311	94.96 259	74.64 322	87.19 319	92.07 307	78.29 311	88.32 317	91.59 313	78.06 286	94.27 350	74.88 333	93.15 335	95.80 276

PMMVS		83.00 318	81.11 326	88.66 305	83.81 379	86.44 164	82.24 360	85.65 349	61.75 371	82.07 360	85.64 364	79.75 272	91.59 365	75.99 328	93.09 336	87.94 364

UnsupCasMVSNet_bld		88.50 266	88.03 267	89.90 284	95.52 246	78.88 275	87.39 316	94.02 271	79.32 302	93.06 219	94.02 256	80.72 268	94.27 350	75.16 332	93.08 337	96.54 243

MVS		84.98 308	84.30 308	87.01 323	91.03 337	77.69 292	91.94 210	94.16 267	59.36 372	84.23 347	87.50 354	85.66 225	96.80 302	71.79 348	93.05 338	86.54 365

PatchT		87.51 283	88.17 264	85.55 333	90.64 341	66.91 362	92.02 206	86.09 345	92.20 91	89.05 303	97.16 94	64.15 346	96.37 315	89.21 179	92.98 339	93.37 334

MS-PatchMatch		88.05 272	87.75 270	88.95 298	93.28 299	77.93 286	87.88 308	92.49 298	75.42 325	92.57 235	93.59 271	80.44 269	94.24 352	81.28 282	92.75 340	94.69 306

CR-MVSNet		87.89 273	87.12 282	90.22 276	91.01 338	78.93 272	92.52 179	92.81 288	73.08 337	89.10 301	96.93 108	67.11 328	97.64 268	88.80 186	92.70 341	94.08 315

RPMNet		90.31 228	90.14 229	90.81 261	91.01 338	78.93 272	92.52 179	98.12 47	91.91 99	89.10 301	96.89 111	68.84 323	99.41 42	90.17 154	92.70 341	94.08 315

KD-MVS_2432*1600		82.17 324	80.75 331	86.42 328	82.04 380	70.09 354	81.75 361	90.80 317	82.56 274	90.37 280	89.30 342	42.90 382	96.11 321	74.47 334	92.55 343	93.06 337

miper_refine_blended		82.17 324	80.75 331	86.42 328	82.04 380	70.09 354	81.75 361	90.80 317	82.56 274	90.37 280	89.30 342	42.90 382	96.11 321	74.47 334	92.55 343	93.06 337

BH-w/o		87.21 290	87.02 284	87.79 318	94.77 266	77.27 297	87.90 307	93.21 284	81.74 283	89.99 288	88.39 350	83.47 238	96.93 298	71.29 352	92.43 345	89.15 359

IB-MVS	77.21 19	83.11 316	81.05 327	89.29 294	91.15 336	75.85 315	85.66 339	86.00 346	79.70 295	82.02 362	86.61 358	48.26 377	98.39 205	77.84 313	92.22 346	93.63 329
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
gg-mvs-nofinetune		82.10 326	81.02 328	85.34 335	87.46 367	71.04 348	94.74 112	67.56 379	96.44 22	79.43 369	98.99 6	45.24 378	96.15 319	67.18 364	92.17 347	88.85 361

HY-MVS	82.50 18	86.81 298	85.93 299	89.47 289	93.63 296	77.93 286	94.02 139	91.58 313	75.68 322	83.64 350	93.64 268	77.40 290	97.42 279	71.70 350	92.07 348	93.05 339

TR-MVS		87.70 277	87.17 280	89.27 295	94.11 286	79.26 267	88.69 301	91.86 310	81.94 282	90.69 275	89.79 335	82.82 246	97.42 279	72.65 345	91.98 349	91.14 354

new_pmnet		81.22 330	81.01 329	81.86 350	90.92 340	70.15 353	84.03 352	80.25 373	70.83 348	85.97 336	89.78 336	67.93 327	84.65 374	67.44 363	91.90 350	90.78 356

FPMVS		84.50 310	83.28 314	88.16 312	96.32 193	94.49 16	85.76 338	85.47 352	83.09 268	85.20 339	94.26 246	63.79 349	86.58 373	63.72 369	91.88 351	83.40 368

UnsupCasMVSNet_eth		90.33 226	90.34 223	90.28 273	94.64 276	80.24 242	89.69 277	95.88 215	85.77 235	93.94 191	95.69 185	81.99 256	92.98 360	84.21 257	91.30 352	97.62 198

MVP-Stereo		90.07 237	88.92 247	93.54 169	96.31 194	86.49 161	90.93 240	95.59 227	79.80 292	91.48 260	95.59 188	80.79 267	97.39 282	78.57 310	91.19 353	96.76 240
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
1314		86.46 299	86.33 296	86.87 325	91.65 331	74.54 324	91.94 210	94.10 268	74.28 330	84.78 343	87.33 356	83.03 243	95.00 342	78.72 308	91.16 354	91.06 355

tpm		84.38 311	84.08 310	85.30 336	90.47 345	63.43 375	89.34 285	85.63 350	77.24 318	87.62 325	95.03 219	61.00 360	97.30 285	79.26 305	91.09 355	95.16 292

CVMVSNet		85.16 306	84.72 304	86.48 326	92.12 323	70.19 352	92.32 193	88.17 332	56.15 374	90.64 276	95.85 174	67.97 326	96.69 305	88.78 187	90.52 356	92.56 344

test0.0.03 1		82.48 321	81.47 325	85.48 334	89.70 352	73.57 334	84.73 345	81.64 368	83.07 269	88.13 320	86.61 358	62.86 353	89.10 372	66.24 366	90.29 357	93.77 326

baseline2		83.38 315	81.54 324	88.90 299	91.38 334	72.84 340	88.78 298	81.22 369	78.97 305	79.82 368	87.56 352	61.73 357	97.80 256	74.30 336	90.05 358	96.05 266

PAPM		81.91 327	80.11 337	87.31 322	93.87 293	72.32 344	84.02 353	93.22 282	69.47 354	76.13 373	89.84 332	72.15 314	97.23 287	53.27 375	89.02 359	92.37 346

MVS-HIRNet		78.83 341	80.60 333	73.51 358	93.07 304	47.37 381	87.10 321	78.00 376	68.94 355	77.53 371	97.26 87	71.45 317	94.62 343	63.28 370	88.74 360	78.55 373

tpm2		81.46 328	80.35 335	84.80 338	89.90 350	65.14 369	90.44 252	85.36 353	65.82 365	82.05 361	92.44 298	57.94 363	96.69 305	70.71 356	88.49 361	92.56 344

CostFormer		83.09 317	82.21 320	85.73 332	89.27 358	67.01 361	90.35 256	86.47 342	70.42 350	83.52 352	93.23 280	61.18 358	96.85 300	77.21 320	88.26 362	93.34 335

GG-mvs-BLEND				83.24 347	85.06 376	71.03 349	94.99 106	65.55 380		74.09 374	75.51 374	44.57 379	94.46 346	59.57 372	87.54 363	84.24 367

PatchmatchNet		85.22 305	84.64 305	86.98 324	89.51 356	69.83 357	90.52 250	87.34 337	78.87 307	87.22 330	92.74 291	66.91 330	96.53 307	81.77 278	86.88 364	94.58 307
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
baseline1		87.62 281	87.31 276	88.54 306	94.71 272	74.27 329	93.10 162	88.20 331	86.20 227	92.18 251	93.04 282	73.21 311	95.52 330	79.32 304	85.82 365	95.83 275

tpmvs		84.22 312	83.97 311	84.94 337	87.09 369	65.18 368	91.21 234	88.35 328	82.87 272	85.21 338	90.96 321	65.24 342	96.75 303	79.60 303	85.25 366	92.90 341

ADS-MVSNet2		84.01 313	82.20 321	89.41 291	89.04 359	76.37 311	87.57 310	90.98 316	72.71 340	84.46 344	92.45 296	68.08 324	96.48 310	70.58 357	83.97 367	95.38 289

ADS-MVSNet		82.25 322	81.55 323	84.34 342	89.04 359	65.30 367	87.57 310	85.13 358	72.71 340	84.46 344	92.45 296	68.08 324	92.33 362	70.58 357	83.97 367	95.38 289

JIA-IIPM		85.08 307	83.04 316	91.19 247	87.56 365	86.14 174	89.40 284	84.44 361	88.98 178	82.20 359	97.95 48	56.82 366	96.15 319	76.55 325	83.45 369	91.30 353

MVE	59.87 23	73.86 343	72.65 346	77.47 356	87.00 371	74.35 327	61.37 373	60.93 381	67.27 360	69.69 376	86.49 360	81.24 265	72.33 377	56.45 374	83.45 369	85.74 366
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
EPMVS		81.17 332	80.37 334	83.58 345	85.58 374	65.08 370	90.31 258	71.34 378	77.31 317	85.80 337	91.30 315	59.38 361	92.70 361	79.99 294	82.34 371	92.96 340

tpmrst		82.85 320	82.93 318	82.64 348	87.65 364	58.99 378	90.14 264	87.90 334	75.54 324	83.93 348	91.63 312	66.79 333	95.36 336	81.21 284	81.54 372	93.57 333

tpm cat1		80.61 336	79.46 339	84.07 344	88.78 361	65.06 371	89.26 288	88.23 330	62.27 370	81.90 363	89.66 339	62.70 355	95.29 339	71.72 349	80.60 373	91.86 351

dp		79.28 339	78.62 341	81.24 351	85.97 373	56.45 379	86.91 324	85.26 356	72.97 338	81.45 365	89.17 345	56.01 368	95.45 334	73.19 342	76.68 374	91.82 352

DeepMVS_CX				53.83 360	70.38 382	64.56 372		48.52 384	33.01 376	65.50 377	74.21 375	56.19 367	46.64 379	38.45 378	70.07 375	50.30 375

tmp_tt		37.97 345	44.33 348	18.88 361	11.80 384	21.54 384	63.51 372	45.66 385	4.23 378	51.34 378	50.48 376	59.08 362	22.11 380	44.50 377	68.35 376	13.00 376

PVSNet_0	70.34 21	74.58 342	72.96 345	79.47 354	90.63 342	66.24 366	73.26 367	83.40 365	63.67 369	78.02 370	78.35 373	72.53 312	89.59 370	56.68 373	60.05 377	82.57 371

test_method		50.44 344	48.94 347	54.93 359	39.68 383	12.38 385	28.59 374	90.09 321	6.82 377	41.10 379	78.41 372	54.41 370	70.69 378	50.12 376	51.26 378	81.72 372

test123		9.49 347	12.01 350	1.91 362	2.87 385	1.30 386	82.38 359	1.34 387	1.36 380	2.84 381	6.56 379	2.45 385	0.97 381	2.73 379	5.56 379	3.47 377

testmvs		9.02 348	11.42 351	1.81 363	2.77 386	1.13 387	79.44 365	1.90 386	1.18 381	2.65 382	6.80 378	1.95 386	0.87 382	2.62 380	3.45 380	3.44 378

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		23.35 346	31.13 349	0.00 364	0.00 387	0.00 388	0.00 375	95.58 229	0.00 382	0.00 383	91.15 317	93.43 79	0.00 383	0.00 381	0.00 381	0.00 379

pcd_1.5k_mvsjas		7.56 349	10.09 352	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	0.00 382	90.77 147	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		7.56 349	10.08 353	0.00 364	0.00 387	0.00 388	0.00 375	0.00 388	0.00 382	0.00 383	90.69 326	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

FOURS1					99.21 3	94.68 12	98.45 4	98.81 8	97.73 6	98.27 20

test_one_0601					98.26 72	87.14 144		98.18 37	94.25 48	96.99 66	97.36 80	95.13 40

eth-test2					0.00 387

eth-test					0.00 387

test_241102_ONE					98.51 51	86.97 149		98.10 51	91.85 102	97.63 35	97.03 101	96.48 11	98.95 126

save fliter					97.46 129	88.05 128	92.04 204	97.08 151	87.63 209

test0726					98.51 51	86.69 156	95.34 88	98.18 37	91.85 102	97.63 35	97.37 77	95.58 22

GSMVS																94.75 303

test_part2					98.21 76	89.41 100				96.72 77

sam_mvs1												66.64 334				94.75 303

sam_mvs												66.41 335

MTGPA								97.62 104

test_post1							90.21 260				5.85 381	65.36 340	96.00 324	79.61 301

test_post											6.07 380	65.74 339	95.84 326

patchmatchnet-post											91.71 310	66.22 337	97.59 269

MTMP							94.82 109	54.62 383

gm-plane-assit					87.08 370	59.33 377			71.22 345		83.58 368		97.20 288	73.95 337

TEST9					96.45 183	89.46 97	90.60 248	96.92 162	79.09 304	90.49 277	94.39 243	91.31 133	98.88 133

test_8					96.37 185	89.14 104	90.51 251	96.89 165	79.37 299	90.42 279	94.36 245	91.20 139	98.82 144

agg_prior					96.20 202	88.89 110		96.88 166		90.21 282			98.78 156

test_prior4						89.91 87	90.74 244

test_prior				94.61 124	95.95 223	87.23 141		97.36 128					98.68 176			97.93 169

旧先验2							90.00 269		68.65 356	92.71 231			96.52 308	85.15 243

新几何2							90.02 268

无先验							89.94 270	95.75 220	70.81 349				98.59 188	81.17 285		94.81 300

原ACMM2							89.34 285

testdata2													98.03 234	80.24 292

segment_acmp												92.14 113

testdata1							88.96 294		88.44 191

plane_prior7					97.71 110	88.68 114

plane_prior6					97.21 140	88.23 125						86.93 208

plane_prior4											95.59 188

plane_prior3						88.43 123			90.35 149	93.31 207

plane_prior2							94.56 121		91.74 113

plane_prior1					97.38 132

n2								0.00 388

nn								0.00 388

door-mid								92.13 306

test11								96.65 182

door								91.26 314

HQP5-MVS						84.89 189

HQP-NCC					96.36 187		91.37 229		87.16 216	88.81 306

ACMP_Plane					96.36 187		91.37 229		87.16 216	88.81 306

BP-MVS														86.55 228

HQP4-MVS										88.81 306			98.61 184			98.15 145

HQP2-MVS												84.76 230

NP-MVS					96.82 160	87.10 145					93.40 275

MDTV_nov1_ep13_2view						42.48 383	88.45 305		67.22 361	83.56 351		66.80 331		72.86 344		94.06 317

Test By Simon												90.61 153

High-resolution multi-view benchmark