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		95.70 1	96.40 1	93.61 2	98.67 1	85.39 33	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 13	85.07 51	99.27 1	99.54 1

FOURS1					96.08 11	87.41 10	96.19 2	95.83 4	92.95 2	96.57 2

DTE-MVSNet		89.98 43	91.91 13	84.21 151	96.51 7	57.84 300	88.93 85	92.84 87	91.92 3	96.16 3	96.23 18	86.95 48	95.99 9	79.05 112	98.57 14	98.80 6

PS-CasMVS		90.06 39	91.92 11	84.47 143	96.56 6	58.83 293	89.04 83	92.74 90	91.40 5	96.12 4	96.06 22	87.23 45	95.57 37	79.42 110	98.74 5	99.00 2

LCM-MVSNet-Re		83.48 154	85.06 121	78.75 246	85.94 251	55.75 316	80.05 239	94.27 19	76.47 126	96.09 5	94.54 62	83.31 83	89.75 229	59.95 292	94.89 166	90.75 211

PEN-MVS		90.03 41	91.88 14	84.48 142	96.57 5	58.88 290	88.95 84	93.19 69	91.62 4	96.01 6	96.16 20	87.02 47	95.60 35	78.69 115	98.72 8	98.97 3

CP-MVSNet		89.27 58	90.91 40	84.37 144	96.34 8	58.61 296	88.66 91	92.06 105	90.78 6	95.67 7	95.17 43	81.80 107	95.54 40	79.00 113	98.69 9	98.95 4

LTVRE_ROB	86.10 1	93.04 3	93.44 2	91.82 20	93.73 60	85.72 30	96.79 1	95.51 8	88.86 12	95.63 8	96.99 8	84.81 67	93.16 131	91.10 1	97.53 70	96.58 30
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
WR-MVS_H		89.91 46	91.31 29	85.71 121	96.32 9	62.39 247	89.54 74	93.31 64	90.21 10	95.57 9	95.66 29	81.42 111	95.90 14	80.94 90	98.80 2	98.84 5

OurMVSNet-221017-0		90.01 42	89.74 52	90.83 32	93.16 76	80.37 68	91.91 33	93.11 73	81.10 74	95.32 10	97.24 5	72.94 198	94.85 66	85.07 51	97.78 53	97.26 16

anonymousdsp		89.73 49	88.88 66	92.27 7	89.82 167	86.67 14	90.51 50	90.20 163	69.87 215	95.06 11	96.14 21	84.28 72	93.07 135	87.68 13	96.34 106	97.09 21

wuyk23d		75.13 258	79.30 211	62.63 348	75.56 350	75.18 120	80.89 231	73.10 334	75.06 147	94.76 12	95.32 35	87.73 40	52.85 378	34.16 377	97.11 80	59.85 375

ACMH	76.49 14	89.34 55	91.14 31	83.96 156	92.50 92	70.36 167	89.55 72	93.84 46	81.89 65	94.70 13	95.44 34	90.69 8	88.31 253	83.33 67	98.30 24	93.20 134
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 85	87.45 83	86.45 102	92.52 91	69.19 180	87.84 103	88.05 201	81.66 67	94.64 14	96.53 14	65.94 238	94.75 68	83.02 71	96.83 88	95.41 51

mvs_tets		89.78 48	89.27 59	91.30 25	93.51 65	84.79 40	89.89 63	90.63 146	70.00 214	94.55 15	96.67 11	87.94 37	93.59 114	84.27 61	95.97 122	95.52 49

jajsoiax		89.41 53	88.81 68	91.19 28	93.38 69	84.72 41	89.70 66	90.29 160	69.27 218	94.39 16	96.38 15	86.02 60	93.52 118	83.96 63	95.92 127	95.34 53

test_0402		88.65 65	89.58 56	85.88 117	92.55 90	72.22 149	84.01 160	89.44 180	88.63 16	94.38 17	95.77 26	86.38 56	93.59 114	79.84 102	95.21 151	91.82 186

UniMVSNet_ETH3D		89.12 61	90.72 43	84.31 149	97.00 2	64.33 223	89.67 69	88.38 193	88.84 13	94.29 18	97.57 3	90.48 13	91.26 182	72.57 192	97.65 60	97.34 15

v7n		90.13 36	90.96 38	87.65 88	91.95 110	71.06 161	89.99 59	93.05 77	86.53 26	94.29 18	96.27 17	82.69 87	94.08 94	86.25 38	97.63 61	97.82 8

test_djsdf		89.62 50	89.01 63	91.45 22	92.36 95	82.98 53	91.98 31	90.08 166	71.54 195	94.28 20	96.54 13	81.57 109	94.27 83	86.26 36	96.49 100	97.09 21

PS-MVSNAJss		88.31 69	87.90 76	89.56 57	93.31 71	77.96 89	87.94 101	91.97 108	70.73 204	94.19 21	96.67 11	76.94 154	94.57 75	83.07 69	96.28 108	96.15 33

SED-MVS		90.46 33	91.64 17	86.93 93	94.18 46	72.65 135	90.47 51	93.69 50	83.77 45	94.11 22	94.27 74	90.28 14	95.84 22	86.03 42	97.92 46	92.29 169

test_241102_ONE					94.18 46	72.65 135		93.69 50	83.62 47	94.11 22	93.78 104	90.28 14	95.50 45

DPE-MVS		90.53 32	91.08 33	88.88 66	93.38 69	78.65 83	89.15 82	94.05 36	84.68 39	93.90 24	94.11 87	88.13 34	96.30 3	84.51 59	97.81 52	91.70 190
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		91.22 21	91.92 11	89.14 64	92.97 80	78.04 86	92.84 15	94.14 31	83.33 51	93.90 24	95.73 27	88.77 25	96.41 1	87.60 16	97.98 42	92.98 142

ACMH+	77.89 11	90.73 27	91.50 21	88.44 75	93.00 79	76.26 112	89.65 70	95.55 7	87.72 21	93.89 26	94.94 48	91.62 3	93.44 122	78.35 118	98.76 3	95.61 48

ACMM	79.39 9	90.65 28	90.99 37	89.63 55	95.03 33	83.53 47	89.62 71	93.35 60	79.20 97	93.83 27	93.60 109	90.81 7	92.96 137	85.02 53	98.45 18	92.41 162
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		92.41 5	92.41 6	92.39 4	94.13 51	88.95 5	92.87 13	94.16 27	88.75 14	93.79 28	94.43 67	88.83 24	95.51 43	87.16 27	97.60 64	92.73 148

RE-MVS-def			92.61 4		94.13 51	88.95 5	92.87 13	94.16 27	88.75 14	93.79 28	94.43 67	90.64 10		87.16 27	97.60 64	92.73 148

DVP-MVS		90.06 39	91.32 28	86.29 105	94.16 49	72.56 141	90.54 48	91.01 136	83.61 48	93.75 30	94.65 57	89.76 18	95.78 27	86.42 32	97.97 43	90.55 220
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									85.33 32	93.75 30	94.65 57	87.44 43	95.78 27	87.41 20	98.21 29	92.98 142

test0726					94.16 49	72.56 141	90.63 45	93.90 42	83.61 48	93.75 30	94.49 64	89.76 18

LPG-MVS_test		91.47 17	91.68 16	90.82 33	94.75 40	81.69 59	90.00 57	94.27 19	82.35 60	93.67 33	94.82 52	91.18 4	95.52 41	85.36 48	98.73 6	95.23 59

LGP-MVS_train				90.82 33	94.75 40	81.69 59		94.27 19	82.35 60	93.67 33	94.82 52	91.18 4	95.52 41	85.36 48	98.73 6	95.23 59

RRT_MVS		88.30 70	87.83 77	89.70 52	93.62 64	75.70 117	92.36 26	89.06 185	77.34 119	93.63 35	95.83 25	65.40 241	95.90 14	85.01 54	98.23 27	97.49 13

DVP-MVS++		90.07 38	91.09 32	87.00 92	91.55 127	72.64 137	96.19 2	94.10 34	85.33 32	93.49 36	94.64 60	81.12 114	95.88 16	87.41 20	95.94 125	92.48 159

test_241102_TWO								93.71 49	83.77 45	93.49 36	94.27 74	89.27 21	95.84 22	86.03 42	97.82 51	92.04 179

test_one_0601					93.85 58	73.27 130		94.11 33	86.57 25	93.47 38	94.64 60	88.42 26

SR-MVS		92.23 6	92.34 7	91.91 15	94.89 37	87.85 8	92.51 23	93.87 45	88.20 19	93.24 39	94.02 90	90.15 16	95.67 33	86.82 30	97.34 74	92.19 175

APD-MVS_3200maxsize		92.05 8	92.24 8	91.48 21	93.02 78	85.17 35	92.47 25	95.05 13	87.65 22	93.21 40	94.39 72	90.09 17	95.08 60	86.67 31	97.60 64	94.18 92

testf1		89.30 56	89.12 60	89.84 48	88.67 189	85.64 31	90.61 46	93.17 70	86.02 29	93.12 41	95.30 36	84.94 64	89.44 234	74.12 168	96.10 117	94.45 82

APD_test2		89.30 56	89.12 60	89.84 48	88.67 189	85.64 31	90.61 46	93.17 70	86.02 29	93.12 41	95.30 36	84.94 64	89.44 234	74.12 168	96.10 117	94.45 82

Anonymous20231211		88.40 67	89.62 55	84.73 138	90.46 155	65.27 213	88.86 86	93.02 81	87.15 23	93.05 43	97.10 6	82.28 97	92.02 163	76.70 142	97.99 40	96.88 25

MP-MVS-pluss		90.81 26	91.08 33	89.99 46	95.97 13	79.88 71	88.13 98	94.51 17	75.79 137	92.94 44	94.96 47	88.36 28	95.01 62	90.70 2	98.40 19	95.09 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 63	89.88 49	86.22 108	91.63 121	77.07 102	89.82 64	93.77 47	78.90 101	92.88 45	92.29 144	86.11 58	90.22 213	86.24 39	97.24 77	91.36 198
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
ACMP	79.16 10	90.54 31	90.60 45	90.35 41	94.36 43	80.98 65	89.16 81	94.05 36	79.03 100	92.87 46	93.74 105	90.60 11	95.21 57	82.87 72	98.76 3	94.87 67
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TDRefinement		93.52 2	93.39 3	93.88 1	95.94 14	90.26 3	95.70 4	96.46 2	90.58 8	92.86 47	96.29 16	88.16 33	94.17 91	86.07 41	98.48 17	97.22 19

SMA-MVS		90.31 34	90.48 46	89.83 50	95.31 29	79.52 77	90.98 43	93.24 68	75.37 144	92.84 48	95.28 38	85.58 62	96.09 6	87.92 9	97.76 55	93.88 106
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
test_part2					93.86 57	77.77 91				92.84 48

v10		86.54 93	87.10 88	84.84 133	88.16 203	63.28 233	86.64 123	92.20 102	75.42 143	92.81 50	94.50 63	74.05 183	94.06 95	83.88 64	96.28 108	97.17 20

dcpmvs_2		84.23 136	85.14 120	81.50 207	88.61 192	61.98 254	82.90 193	93.11 73	68.66 227	92.77 51	92.39 139	78.50 135	87.63 259	76.99 141	92.30 222	94.90 65

v8		86.22 99	86.83 95	84.36 146	87.82 207	62.35 249	86.42 126	91.33 127	76.78 125	92.73 52	94.48 65	73.41 192	93.72 106	83.10 68	95.41 143	97.01 23

nrg030		87.85 80	88.49 70	85.91 115	90.07 163	69.73 171	87.86 102	94.20 25	74.04 155	92.70 53	94.66 56	85.88 61	91.50 174	79.72 105	97.32 75	96.50 31

SteuartSystems-ACMMP		91.16 23	91.36 24	90.55 37	93.91 56	80.97 66	91.49 37	93.48 57	82.82 57	92.60 54	93.97 92	88.19 31	96.29 4	87.61 15	98.20 31	94.39 86
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 47	89.97 48	89.27 61	94.76 39	79.86 72	86.76 120	92.78 89	78.78 103	92.51 55	93.64 108	88.13 34	93.84 103	84.83 56	97.55 67	94.10 98
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HPM-MVS_fast		92.50 4	92.54 5	92.37 5	95.93 15	85.81 29	92.99 12	94.23 22	85.21 34	92.51 55	95.13 44	90.65 9	95.34 51	88.06 8	98.15 34	95.95 41

K. test v3		85.14 114	84.73 126	86.37 103	91.13 141	69.63 173	85.45 136	76.68 308	84.06 43	92.44 57	96.99 8	62.03 258	94.65 71	80.58 96	93.24 205	94.83 72

ACMMP		91.91 10	91.87 15	92.03 11	95.53 26	85.91 24	93.35 11	94.16 27	82.52 59	92.39 58	94.14 84	89.15 23	95.62 34	87.35 22	98.24 26	94.56 76
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
SF-MVS		90.27 35	90.80 42	88.68 73	92.86 84	77.09 101	91.19 40	95.74 5	81.38 70	92.28 59	93.80 102	86.89 49	94.64 72	85.52 47	97.51 71	94.30 89

mvsmamba		87.87 78	87.23 86	89.78 51	92.31 99	76.51 109	91.09 42	91.87 112	72.61 182	92.16 60	95.23 41	66.01 237	95.59 36	86.02 44	97.78 53	97.24 17

COLMAP_ROB	83.01 3	91.97 9	91.95 10	92.04 10	93.68 62	86.15 20	93.37 10	95.10 12	90.28 9	92.11 61	95.03 46	89.75 20	94.93 64	79.95 101	98.27 25	95.04 64
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
XVG-ACMP-BASELINE		89.98 43	89.84 50	90.41 39	94.91 36	84.50 44	89.49 76	93.98 38	79.68 89	92.09 62	93.89 100	83.80 76	93.10 134	82.67 74	98.04 36	93.64 119

TranMVSNet+NR-MVSNet		87.86 79	88.76 69	85.18 129	94.02 54	64.13 224	84.38 153	91.29 128	84.88 38	92.06 63	93.84 101	86.45 54	93.73 105	73.22 183	98.66 10	97.69 9

MTAPA		91.52 14	91.60 18	91.29 26	96.59 4	86.29 17	92.02 30	91.81 116	84.07 42	92.00 64	94.40 71	86.63 51	95.28 54	88.59 5	98.31 23	92.30 168

ACMMP_NAP		90.65 28	91.07 35	89.42 59	95.93 15	79.54 76	89.95 61	93.68 52	77.65 116	91.97 65	94.89 49	88.38 27	95.45 47	89.27 3	97.87 50	93.27 131

FC-MVSNet-test		85.93 104	87.05 90	82.58 190	92.25 100	56.44 311	85.75 132	93.09 75	77.33 120	91.94 66	94.65 57	74.78 175	93.41 124	75.11 160	98.58 13	97.88 7

lessismore_v0				85.95 114	91.10 142	70.99 162		70.91 348		91.79 67	94.42 69	61.76 259	92.93 139	79.52 109	93.03 210	93.93 104

HPM-MVS		92.13 7	92.20 9	91.91 15	95.58 25	84.67 42	93.51 8	94.85 14	82.88 56	91.77 68	93.94 98	90.55 12	95.73 30	88.50 6	98.23 27	95.33 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PGM-MVS		91.20 22	90.95 39	91.93 13	95.67 22	85.85 27	90.00 57	93.90 42	80.32 82	91.74 69	94.41 70	88.17 32	95.98 10	86.37 34	97.99 40	93.96 103

mPP-MVS		91.69 11	91.47 22	92.37 5	96.04 12	88.48 7	92.72 17	92.60 93	83.09 53	91.54 70	94.25 78	87.67 41	95.51 43	87.21 26	98.11 35	93.12 138

HFP-MVS		91.30 19	91.39 23	91.02 29	95.43 28	84.66 43	92.58 21	93.29 66	81.99 62	91.47 71	93.96 95	88.35 29	95.56 38	87.74 11	97.74 57	92.85 145

ACMMPR		91.49 15	91.35 26	91.92 14	95.74 19	85.88 26	92.58 21	93.25 67	81.99 62	91.40 72	94.17 83	87.51 42	95.87 18	87.74 11	97.76 55	93.99 100

GST-MVS		90.96 25	91.01 36	90.82 33	95.45 27	82.73 55	91.75 35	93.74 48	80.98 76	91.38 73	93.80 102	87.20 46	95.80 24	87.10 29	97.69 59	93.93 104

test_fmvsmvis_n_1920		85.22 111	85.36 118	84.81 134	85.80 252	76.13 115	85.15 140	92.32 99	61.40 283	91.33 74	90.85 184	83.76 78	86.16 280	84.31 60	93.28 204	92.15 177

ANet_high		83.17 160	85.68 113	75.65 290	81.24 300	45.26 369	79.94 241	92.91 84	83.83 44	91.33 74	96.88 10	80.25 124	85.92 283	68.89 224	95.89 128	95.76 43

ZNCC-MVS		91.26 20	91.34 27	91.01 30	95.73 20	83.05 52	92.18 28	94.22 24	80.14 85	91.29 76	93.97 92	87.93 38	95.87 18	88.65 4	97.96 45	94.12 96

bld_raw_dy_0_64		84.85 120	84.44 135	86.07 113	93.73 60	74.93 121	88.57 92	81.90 278	70.44 206	91.28 77	95.18 42	56.62 293	89.28 239	85.15 50	97.09 81	93.99 100

casdiffmvs_mvg		86.72 91	87.51 82	84.36 146	87.09 226	65.22 214	84.16 155	94.23 22	77.89 113	91.28 77	93.66 107	84.35 71	92.71 143	80.07 98	94.87 169	95.16 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
APD-MVS		89.54 52	89.63 54	89.26 62	92.57 89	81.34 64	90.19 56	93.08 76	80.87 78	91.13 79	93.19 113	86.22 57	95.97 11	82.23 80	97.18 79	90.45 222
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 58		91.84 117		88.80 88	95.32 11	75.14 146	91.07 80	92.89 125	87.27 44	93.78 104	83.69 66	97.55 67

CP-MVS		91.67 12	91.58 19	91.96 12	95.29 30	87.62 9	93.38 9	93.36 59	83.16 52	91.06 81	94.00 91	88.26 30	95.71 31	87.28 25	98.39 20	92.55 157

FIs		85.35 110	86.27 101	82.60 189	91.86 114	57.31 304	85.10 141	93.05 77	75.83 136	91.02 82	93.97 92	73.57 188	92.91 141	73.97 171	98.02 39	97.58 12

UniMVSNet_NR-MVSNet		86.84 89	87.06 89	86.17 111	92.86 84	67.02 196	82.55 202	91.56 119	83.08 54	90.92 83	91.82 156	78.25 138	93.99 96	74.16 166	98.35 21	97.49 13

DU-MVS		86.80 90	86.99 91	86.21 109	93.24 74	67.02 196	83.16 186	92.21 101	81.73 66	90.92 83	91.97 150	77.20 148	93.99 96	74.16 166	98.35 21	97.61 10

tt0805		88.09 74	89.79 51	82.98 179	93.26 73	63.94 227	91.10 41	89.64 175	85.07 35	90.91 85	91.09 174	89.16 22	91.87 168	82.03 81	95.87 129	93.13 136

V42		83.47 155	83.37 152	83.75 161	83.16 284	63.33 232	81.31 224	90.23 162	69.51 217	90.91 85	90.81 186	74.16 181	92.29 157	80.06 99	90.22 263	95.62 47

region2R		91.44 18	91.30 30	91.87 17	95.75 18	85.90 25	92.63 20	93.30 65	81.91 64	90.88 87	94.21 79	87.75 39	95.87 18	87.60 16	97.71 58	93.83 108

APD_test1		88.40 67	87.91 75	89.88 47	89.50 170	86.65 16	89.98 60	91.91 111	84.26 40	90.87 88	93.92 99	82.18 98	89.29 238	73.75 175	94.81 170	93.70 115

WR-MVS		83.56 152	84.40 138	81.06 215	93.43 68	54.88 322	78.67 263	85.02 247	81.24 72	90.74 89	91.56 162	72.85 199	91.08 188	68.00 234	98.04 36	97.23 18

v1240		84.30 132	84.51 134	83.65 163	87.65 212	61.26 260	82.85 194	91.54 120	67.94 236	90.68 90	90.65 192	71.71 212	93.64 108	82.84 73	94.78 171	96.07 36

ZD-MVS					92.22 102	80.48 67		91.85 113	71.22 200	90.38 91	92.98 120	86.06 59	96.11 5	81.99 83	96.75 91

MIMVSNet1		83.63 150	84.59 131	80.74 219	94.06 53	62.77 240	82.72 196	84.53 255	77.57 118	90.34 92	95.92 24	76.88 160	85.83 286	61.88 280	97.42 72	93.62 120

LS3D		90.60 30	90.34 47	91.38 24	89.03 181	84.23 45	93.58 6	94.68 16	90.65 7	90.33 93	93.95 97	84.50 69	95.37 50	80.87 91	95.50 142	94.53 79

KD-MVS_self_test		81.93 178	83.14 157	78.30 255	84.75 264	52.75 334	80.37 236	89.42 181	70.24 212	90.26 94	93.39 111	74.55 180	86.77 271	68.61 229	96.64 93	95.38 52

PMVS	80.48 6	90.08 37	90.66 44	88.34 78	96.71 3	92.97 1	90.31 54	89.57 178	88.51 17	90.11 95	95.12 45	90.98 6	88.92 243	77.55 132	97.07 82	83.13 317
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 301	90.06 96	91.33 167	80.66 120	93.03 136	75.78 152	95.94 125	92.48 159

v1921920		84.23 136	84.37 139	83.79 159	87.64 213	61.71 255	82.91 192	91.20 131	67.94 236	90.06 96	90.34 197	72.04 209	93.59 114	82.32 78	94.91 164	96.07 36

ITE_SJBPF				90.11 45	90.72 150	84.97 37		90.30 158	81.56 68	90.02 98	91.20 171	82.40 92	90.81 198	73.58 178	94.66 175	94.56 76

XVS		91.54 13	91.36 24	92.08 8	95.64 23	86.25 18	92.64 18	93.33 61	85.07 35	89.99 99	94.03 89	86.57 52	95.80 24	87.35 22	97.62 62	94.20 90

X-MVStestdata		85.04 116	82.70 164	92.08 8	95.64 23	86.25 18	92.64 18	93.33 61	85.07 35	89.99 99	16.05 382	86.57 52	95.80 24	87.35 22	97.62 62	94.20 90

v1192		84.57 125	84.69 130	84.21 151	87.75 209	62.88 237	83.02 189	91.43 123	69.08 221	89.98 101	90.89 182	72.70 202	93.62 112	82.41 77	94.97 163	96.13 34

Anonymous20240529		86.20 100	87.13 87	83.42 169	90.19 159	64.55 221	84.55 148	90.71 143	85.85 31	89.94 102	95.24 40	82.13 99	90.40 209	69.19 220	96.40 105	95.31 55

pmmvs6		86.52 94	88.06 74	81.90 199	92.22 102	62.28 250	84.66 146	89.15 183	83.54 50	89.85 103	97.32 4	88.08 36	86.80 270	70.43 208	97.30 76	96.62 28

v144192		84.24 135	84.41 137	83.71 162	87.59 214	61.57 256	82.95 191	91.03 135	67.82 239	89.80 104	90.49 195	73.28 195	93.51 119	81.88 85	94.89 166	96.04 38

v1144		84.54 127	84.72 128	84.00 154	87.67 211	62.55 244	82.97 190	90.93 139	70.32 210	89.80 104	90.99 177	73.50 189	93.48 120	81.69 86	94.65 176	95.97 39

DeepC-MVS	82.31 4	89.15 60	89.08 62	89.37 60	93.64 63	79.07 79	88.54 93	94.20 25	73.53 163	89.71 106	94.82 52	85.09 63	95.77 29	84.17 62	98.03 38	93.26 132
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		88.00 76	86.93 93	91.22 27	90.08 161	89.30 4	89.68 68	91.11 133	79.26 96	89.68 107	94.81 55	82.44 90	87.74 257	76.54 145	88.74 278	96.61 29

IU-MVS					94.18 46	72.64 137		90.82 141	56.98 315	89.67 108				85.78 46	97.92 46	93.28 130

FMVSNet1		84.55 126	85.45 116	81.85 201	90.27 158	61.05 263	86.83 117	88.27 198	78.57 107	89.66 109	95.64 30	75.43 166	90.68 202	69.09 221	95.33 146	93.82 109

IterMVS-LS		84.73 122	84.98 123	83.96 156	87.35 217	63.66 228	83.25 182	89.88 170	76.06 129	89.62 110	92.37 143	73.40 194	92.52 148	78.16 123	94.77 173	95.69 44
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 66	89.01 63	87.36 90	91.30 134	77.50 94	87.55 105	92.97 83	87.95 20	89.62 110	92.87 126	84.56 68	93.89 100	77.65 130	96.62 94	90.70 214

UniMVSNet (Re)		86.87 87	86.98 92	86.55 100	93.11 77	68.48 184	83.80 169	92.87 85	80.37 80	89.61 112	91.81 157	77.72 142	94.18 89	75.00 161	98.53 15	96.99 24

IS-MVSNet		86.66 92	86.82 96	86.17 111	92.05 108	66.87 199	91.21 39	88.64 190	86.30 28	89.60 113	92.59 134	69.22 221	94.91 65	73.89 172	97.89 49	96.72 26

v2v482		84.09 139	84.24 141	83.62 164	87.13 222	61.40 257	82.71 197	89.71 173	72.19 191	89.55 114	91.41 165	70.70 217	93.20 129	81.02 89	93.76 193	96.25 32

Baseline_NR-MVSNet		84.00 143	85.90 108	78.29 256	91.47 132	53.44 330	82.29 210	87.00 221	79.06 99	89.55 114	95.72 28	77.20 148	86.14 281	72.30 194	98.51 16	95.28 56

CSCG		86.26 97	86.47 98	85.60 123	90.87 147	74.26 125	87.98 100	91.85 113	80.35 81	89.54 116	88.01 235	79.09 131	92.13 159	75.51 154	95.06 158	90.41 223

ambc				82.98 179	90.55 154	64.86 217	88.20 96	89.15 183		89.40 117	93.96 95	71.67 213	91.38 181	78.83 114	96.55 96	92.71 151

DeepPCF-MVS	81.24 5	87.28 84	86.21 103	90.49 38	91.48 131	84.90 38	83.41 178	92.38 98	70.25 211	89.35 118	90.68 190	82.85 86	94.57 75	79.55 107	95.95 124	92.00 181

MSP-MVS		89.08 62	88.16 73	91.83 18	95.76 17	86.14 21	92.75 16	93.90 42	78.43 108	89.16 119	92.25 146	72.03 210	96.36 2	88.21 7	90.93 251	92.98 142
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
XVG-OURS		89.18 59	88.83 67	90.23 43	94.28 44	86.11 22	85.91 129	93.60 55	80.16 84	89.13 120	93.44 110	83.82 75	90.98 190	83.86 65	95.30 150	93.60 121

MDA-MVSNet-bldmvs		77.47 234	76.90 238	79.16 242	79.03 325	64.59 218	66.58 352	75.67 314	73.15 174	88.86 121	88.99 223	66.94 231	81.23 314	64.71 259	88.22 286	91.64 192

EG-PatchMatch MVS		84.08 140	84.11 142	83.98 155	92.22 102	72.61 140	82.20 216	87.02 218	72.63 181	88.86 121	91.02 176	78.52 134	91.11 187	73.41 180	91.09 245	88.21 256

3Dnovator+	83.92 2	89.97 45	89.66 53	90.92 31	91.27 136	81.66 62	91.25 38	94.13 32	88.89 11	88.83 123	94.26 77	77.55 145	95.86 21	84.88 55	95.87 129	95.24 58

EI-MVSNet-UG-set		85.04 116	84.44 135	86.85 95	83.87 278	72.52 143	83.82 167	85.15 243	80.27 83	88.75 124	85.45 278	79.95 127	91.90 166	81.92 84	90.80 256	96.13 34

EI-MVSNet-Vis-set		85.12 115	84.53 133	86.88 94	84.01 275	72.76 134	83.91 165	85.18 242	80.44 79	88.75 124	85.49 276	80.08 125	91.92 165	82.02 82	90.85 255	95.97 39

OMC-MVS		88.19 71	87.52 81	90.19 44	91.94 112	81.68 61	87.49 107	93.17 70	76.02 131	88.64 126	91.22 169	84.24 73	93.37 125	77.97 128	97.03 83	95.52 49

UA-Net		91.49 15	91.53 20	91.39 23	94.98 34	82.95 54	93.52 7	92.79 88	88.22 18	88.53 127	97.64 2	83.45 81	94.55 77	86.02 44	98.60 12	96.67 27

MP-MVS		91.14 24	90.91 40	91.83 18	96.18 10	86.88 13	92.20 27	93.03 80	82.59 58	88.52 128	94.37 73	86.74 50	95.41 49	86.32 35	98.21 29	93.19 135
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
canonicalmvs		85.50 107	86.14 104	83.58 165	87.97 204	67.13 194	87.55 105	94.32 18	73.44 165	88.47 129	87.54 245	86.45 54	91.06 189	75.76 153	93.76 193	92.54 158

NR-MVSNet		86.00 102	86.22 102	85.34 127	93.24 74	64.56 220	82.21 214	90.46 150	80.99 75	88.42 130	91.97 150	77.56 144	93.85 101	72.46 193	98.65 11	97.61 10

alignmvs		83.94 145	83.98 145	83.80 158	87.80 208	67.88 191	84.54 150	91.42 125	73.27 172	88.41 131	87.96 236	72.33 205	90.83 197	76.02 151	94.11 187	92.69 152

TransMVSNet (Re)		84.02 142	85.74 112	78.85 244	91.00 144	55.20 321	82.29 210	87.26 209	79.65 90	88.38 132	95.52 33	83.00 84	86.88 268	67.97 235	96.60 95	94.45 82

PM-MVS		80.20 206	79.00 213	83.78 160	88.17 202	86.66 15	81.31 224	66.81 362	69.64 216	88.33 133	90.19 202	64.58 243	83.63 304	71.99 196	90.03 264	81.06 343

tttt0517		81.07 187	79.58 208	85.52 124	88.99 183	66.45 203	87.03 113	75.51 316	73.76 159	88.32 134	90.20 201	37.96 371	94.16 93	79.36 111	95.13 154	95.93 42

casdiffmvs		85.21 112	85.85 109	83.31 172	86.17 247	62.77 240	83.03 188	93.93 40	74.69 150	88.21 135	92.68 133	82.29 96	91.89 167	77.87 129	93.75 195	95.27 57
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test_vis3_rt		71.42 292	70.67 294	73.64 301	69.66 375	70.46 165	66.97 351	89.73 171	42.68 371	88.20 136	83.04 307	43.77 356	60.07 373	65.35 255	86.66 300	90.39 224

v148		82.31 169	82.48 170	81.81 204	85.59 254	59.66 280	81.47 223	86.02 231	72.85 177	88.05 137	90.65 192	70.73 216	90.91 194	75.15 159	91.79 234	94.87 67

AllTest		87.97 77	87.40 85	89.68 53	91.59 122	83.40 48	89.50 75	95.44 9	79.47 91	88.00 138	93.03 118	82.66 88	91.47 175	70.81 200	96.14 114	94.16 93

TestCases				89.68 53	91.59 122	83.40 48		95.44 9	79.47 91	88.00 138	93.03 118	82.66 88	91.47 175	70.81 200	96.14 114	94.16 93

pm-mvs1		83.69 148	84.95 124	79.91 231	90.04 165	59.66 280	82.43 206	87.44 206	75.52 141	87.85 140	95.26 39	81.25 113	85.65 288	68.74 227	96.04 119	94.42 85

PCF-MVS	74.62 15	82.15 173	80.92 191	85.84 118	89.43 172	72.30 147	80.53 234	91.82 115	57.36 313	87.81 141	89.92 207	77.67 143	93.63 109	58.69 297	95.08 157	91.58 194
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
FMVSNet2		81.31 184	81.61 180	80.41 225	86.38 236	58.75 294	83.93 164	86.58 223	72.43 183	87.65 142	92.98 120	63.78 249	90.22 213	66.86 238	93.92 191	92.27 171

GeoE		85.45 109	85.81 110	84.37 144	90.08 161	67.07 195	85.86 131	91.39 126	72.33 188	87.59 143	90.25 200	84.85 66	92.37 153	78.00 126	91.94 233	93.66 116

VPA-MVSNet		83.47 155	84.73 126	79.69 235	90.29 157	57.52 303	81.30 226	88.69 189	76.29 127	87.58 144	94.44 66	80.60 121	87.20 263	66.60 243	96.82 89	94.34 88

CPTT-MVS		89.39 54	88.98 65	90.63 36	95.09 32	86.95 12	92.09 29	92.30 100	79.74 88	87.50 145	92.38 140	81.42 111	93.28 127	83.07 69	97.24 77	91.67 191

VDDNet		84.35 130	85.39 117	81.25 210	95.13 31	59.32 283	85.42 137	81.11 283	86.41 27	87.41 146	96.21 19	73.61 187	90.61 205	66.33 244	96.85 86	93.81 112

c3_l		81.64 181	81.59 181	81.79 205	80.86 306	59.15 287	78.61 264	90.18 164	68.36 228	87.20 147	87.11 255	69.39 219	91.62 172	78.16 123	94.43 181	94.60 75

VDD-MVS		84.23 136	84.58 132	83.20 175	91.17 140	65.16 216	83.25 182	84.97 250	79.79 87	87.18 148	94.27 74	74.77 176	90.89 195	69.24 217	96.54 97	93.55 126

MSLP-MVS++		85.00 118	86.03 105	81.90 199	91.84 117	71.56 159	86.75 121	93.02 81	75.95 134	87.12 149	89.39 215	77.98 139	89.40 237	77.46 133	94.78 171	84.75 294

baseline		85.20 113	85.93 106	83.02 178	86.30 241	62.37 248	84.55 148	93.96 39	74.48 152	87.12 149	92.03 149	82.30 95	91.94 164	78.39 116	94.21 185	94.74 73

YYNet1		70.06 304	70.44 297	68.90 328	73.76 361	53.42 331	58.99 368	67.20 358	58.42 304	87.10 151	85.39 280	59.82 271	67.32 358	59.79 293	83.50 329	85.96 280

MDA-MVSNet_test_wron		70.05 305	70.44 297	68.88 329	73.84 360	53.47 329	58.93 369	67.28 357	58.43 303	87.09 152	85.40 279	59.80 272	67.25 359	59.66 294	83.54 328	85.92 282

test_fmvs3		75.72 254	75.20 254	77.27 272	75.01 357	69.47 174	78.93 257	84.88 251	46.67 355	87.08 153	87.84 240	50.44 322	71.62 342	77.42 136	88.53 279	90.72 212

CNVR-MVS		87.81 81	87.68 79	88.21 80	92.87 82	77.30 100	85.25 138	91.23 130	77.31 121	87.07 154	91.47 164	82.94 85	94.71 69	84.67 57	96.27 110	92.62 155

EPP-MVSNet		85.47 108	85.04 122	86.77 97	91.52 130	69.37 175	91.63 36	87.98 203	81.51 69	87.05 155	91.83 155	66.18 236	95.29 52	70.75 203	96.89 85	95.64 46

TinyColmap		81.25 185	82.34 172	77.99 262	85.33 257	60.68 271	82.32 209	88.33 196	71.26 199	86.97 156	92.22 148	77.10 151	86.98 267	62.37 274	95.17 153	86.31 278

eth_miper_zixun_eth		80.84 190	80.22 201	82.71 187	81.41 298	60.98 266	77.81 273	90.14 165	67.31 242	86.95 157	87.24 252	64.26 245	92.31 155	75.23 158	91.61 237	94.85 71

Anonymous20240521		80.18 207	81.25 185	76.95 275	83.15 285	60.84 268	82.46 205	85.99 232	68.76 225	86.78 158	93.73 106	59.13 276	77.44 327	73.71 176	97.55 67	92.56 156

Patchmatch-RL test		74.48 267	73.68 266	76.89 278	84.83 262	66.54 201	72.29 329	69.16 355	57.70 309	86.76 159	86.33 264	45.79 342	82.59 307	69.63 214	90.65 261	81.54 334

XVG-OURS-SEG-HR		89.59 51	89.37 57	90.28 42	94.47 42	85.95 23	86.84 116	93.91 41	80.07 86	86.75 160	93.26 112	93.64 2	90.93 192	84.60 58	90.75 257	93.97 102

h-mvs33		84.25 134	82.76 163	88.72 70	91.82 119	82.60 56	84.00 161	84.98 249	71.27 197	86.70 161	90.55 194	63.04 255	93.92 99	78.26 121	94.20 186	89.63 234

hse-mvs2		83.47 155	81.81 177	88.47 74	91.03 143	82.27 57	82.61 198	83.69 260	71.27 197	86.70 161	86.05 270	63.04 255	92.41 151	78.26 121	93.62 199	90.71 213

HPM-MVS++		88.93 64	88.45 71	90.38 40	94.92 35	85.85 27	89.70 66	91.27 129	78.20 110	86.69 163	92.28 145	80.36 123	95.06 61	86.17 40	96.49 100	90.22 226

TSAR-MVS + MP.		88.14 72	87.82 78	89.09 65	95.72 21	76.74 105	92.49 24	91.19 132	67.85 238	86.63 164	94.84 51	79.58 129	95.96 12	87.62 14	94.50 178	94.56 76
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 165	82.42 171	83.20 175	83.25 282	63.66 228	83.50 176	85.07 244	76.06 129	86.55 165	85.10 284	73.41 192	90.25 210	78.15 125	90.67 259	95.68 45

HQP_MVS		87.75 82	87.43 84	88.70 72	93.45 66	76.42 110	89.45 77	93.61 53	79.44 93	86.55 165	92.95 123	74.84 173	95.22 55	80.78 93	95.83 131	94.46 80

plane_prior3						76.85 104			77.79 115	86.55 165

BH-untuned		80.96 189	80.99 189	80.84 218	88.55 194	68.23 185	80.33 237	88.46 191	72.79 179	86.55 165	86.76 259	74.72 177	91.77 171	61.79 281	88.99 273	82.52 324

MVSTER		77.09 238	75.70 249	81.25 210	75.27 354	61.08 262	77.49 280	85.07 244	60.78 290	86.55 165	88.68 227	43.14 361	90.25 210	73.69 177	90.67 259	92.42 161

旧先验2							81.73 219		56.88 316	86.54 170			84.90 294	72.81 190

IterMVS-SCA-FT		80.64 194	79.41 209	84.34 148	83.93 276	69.66 172	76.28 296	81.09 284	72.43 183	86.47 171	90.19 202	60.46 264	93.15 132	77.45 134	86.39 304	90.22 226

test_fmvsm_n_1920		83.60 151	82.89 161	85.74 120	85.22 258	77.74 92	84.12 157	90.48 149	59.87 299	86.45 172	91.12 173	75.65 164	85.89 285	82.28 79	90.87 253	93.58 122

DIV-MVS_self_test		80.43 197	80.23 199	81.02 216	79.99 314	59.25 284	77.07 284	87.02 218	67.38 240	86.19 173	89.22 218	63.09 253	90.16 215	76.32 146	95.80 134	93.66 116

CDPH-MVS		86.17 101	85.54 115	88.05 83	92.25 100	75.45 118	83.85 166	92.01 106	65.91 250	86.19 173	91.75 159	83.77 77	94.98 63	77.43 135	96.71 92	93.73 114

cl____		80.42 198	80.23 199	81.02 216	79.99 314	59.25 284	77.07 284	87.02 218	67.37 241	86.18 175	89.21 219	63.08 254	90.16 215	76.31 147	95.80 134	93.65 118

MVS_111021_LR		84.28 133	83.76 148	85.83 119	89.23 177	83.07 51	80.99 230	83.56 263	72.71 180	86.07 176	89.07 222	81.75 108	86.19 279	77.11 139	93.36 200	88.24 255

GBi-Net		82.02 175	82.07 173	81.85 201	86.38 236	61.05 263	86.83 117	88.27 198	72.43 183	86.00 177	95.64 30	63.78 249	90.68 202	65.95 246	93.34 201	93.82 109

test1		82.02 175	82.07 173	81.85 201	86.38 236	61.05 263	86.83 117	88.27 198	72.43 183	86.00 177	95.64 30	63.78 249	90.68 202	65.95 246	93.34 201	93.82 109

FMVSNet3		78.80 221	78.55 221	79.57 237	82.89 289	56.89 309	81.76 218	85.77 234	69.04 222	86.00 177	90.44 196	51.75 316	90.09 221	65.95 246	93.34 201	91.72 188

miper_ehance_all_eth		80.34 202	80.04 206	81.24 212	79.82 316	58.95 289	77.66 275	89.66 174	65.75 254	85.99 180	85.11 283	68.29 226	91.42 179	76.03 150	92.03 230	93.33 128

tfpnnormal		81.79 180	82.95 160	78.31 254	88.93 184	55.40 317	80.83 233	82.85 269	76.81 124	85.90 181	94.14 84	74.58 179	86.51 274	66.82 241	95.68 140	93.01 141

TAPA-MVS	77.73 12	85.71 106	84.83 125	88.37 77	88.78 188	79.72 73	87.15 111	93.50 56	69.17 219	85.80 182	89.56 212	80.76 118	92.13 159	73.21 188	95.51 141	93.25 133
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 144	82.69 165	87.72 85	89.27 176	81.45 63	83.72 171	81.58 282	74.73 149	85.66 183	86.06 269	72.56 204	92.69 145	75.44 156	95.21 151	89.01 250

EU-MVSNet		75.12 259	74.43 261	77.18 273	83.11 286	59.48 282	85.71 134	82.43 273	39.76 375	85.64 184	88.76 225	44.71 354	87.88 256	73.86 173	85.88 308	84.16 300

LF4IMVS		82.75 164	81.93 176	85.19 128	82.08 291	80.15 70	85.53 135	88.76 188	68.01 233	85.58 185	87.75 241	71.80 211	86.85 269	74.02 170	93.87 192	88.58 253

Patchmtry		76.56 246	77.46 230	73.83 300	79.37 322	46.60 366	82.41 207	76.90 305	73.81 158	85.56 186	92.38 140	48.07 329	83.98 301	63.36 269	95.31 149	90.92 207

MVS_111021_HR		84.63 123	84.34 140	85.49 126	90.18 160	75.86 116	79.23 255	87.13 213	73.35 166	85.56 186	89.34 216	83.60 80	90.50 207	76.64 143	94.05 189	90.09 231

testdata				79.54 238	92.87 82	72.34 146		80.14 290	59.91 298	85.47 188	91.75 159	67.96 228	85.24 290	68.57 231	92.18 229	81.06 343

test1111		78.53 225	78.85 216	77.56 268	92.22 102	47.49 362	82.61 198	69.24 354	72.43 183	85.28 189	94.20 80	51.91 314	90.07 222	65.36 254	96.45 103	95.11 62

thisisatest0530		79.07 215	77.33 234	84.26 150	87.13 222	64.58 219	83.66 173	75.95 311	68.86 224	85.22 190	87.36 249	38.10 369	93.57 117	75.47 155	94.28 184	94.62 74

EC-MVSNet		88.01 75	88.32 72	87.09 91	89.28 175	72.03 151	90.31 54	96.31 3	80.88 77	85.12 191	89.67 211	84.47 70	95.46 46	82.56 75	96.26 111	93.77 113

CLD-MVS		83.18 159	82.64 166	84.79 135	89.05 180	67.82 192	77.93 271	92.52 94	68.33 229	85.07 192	81.54 325	82.06 100	92.96 137	69.35 216	97.91 48	93.57 123
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
FA-MVS(test-final)		83.13 161	83.02 159	83.43 168	86.16 249	66.08 207	88.00 99	88.36 194	75.55 140	85.02 193	92.75 131	65.12 242	92.50 149	74.94 162	91.30 243	91.72 188

DeepC-MVS_fast	80.27 8	86.23 98	85.65 114	87.96 84	91.30 134	76.92 103	87.19 109	91.99 107	70.56 205	84.96 194	90.69 189	80.01 126	95.14 58	78.37 117	95.78 136	91.82 186
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
3Dnovator	80.37 7	84.80 121	84.71 129	85.06 131	86.36 239	74.71 122	88.77 89	90.00 168	75.65 139	84.96 194	93.17 114	74.06 182	91.19 184	78.28 120	91.09 245	89.29 242

QAPM		82.59 166	82.59 168	82.58 190	86.44 234	66.69 200	89.94 62	90.36 154	67.97 235	84.94 196	92.58 136	72.71 201	92.18 158	70.63 206	87.73 291	88.85 251

VPNet		80.25 204	81.68 178	75.94 288	92.46 93	47.98 360	76.70 289	81.67 280	73.45 164	84.87 197	92.82 127	74.66 178	86.51 274	61.66 283	96.85 86	93.33 128

NCCC		87.36 83	86.87 94	88.83 67	92.32 98	78.84 82	86.58 124	91.09 134	78.77 104	84.85 198	90.89 182	80.85 117	95.29 52	81.14 88	95.32 147	92.34 166

PHI-MVS		86.38 95	85.81 110	88.08 81	88.44 197	77.34 98	89.35 80	93.05 77	73.15 174	84.76 199	87.70 242	78.87 133	94.18 89	80.67 95	96.29 107	92.73 148

pmmvs-eth3d		78.42 227	77.04 236	82.57 192	87.44 216	74.41 124	80.86 232	79.67 292	55.68 319	84.69 200	90.31 199	60.91 262	85.42 289	62.20 276	91.59 238	87.88 263

test_prior2							83.37 179		75.43 142	84.58 201	91.57 161	81.92 105		79.54 108	96.97 84

TEST9					92.34 96	79.70 74	83.94 162	90.32 155	65.41 260	84.49 202	90.97 178	82.03 101	93.63 109

train_agg		85.98 103	85.28 119	88.07 82	92.34 96	79.70 74	83.94 162	90.32 155	65.79 251	84.49 202	90.97 178	81.93 103	93.63 109	81.21 87	96.54 97	90.88 208

Gipuma		84.44 128	86.33 100	78.78 245	84.20 274	73.57 128	89.55 72	90.44 151	84.24 41	84.38 204	94.89 49	76.35 163	80.40 319	76.14 149	96.80 90	82.36 326
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 331	65.85 325	59.67 356	66.54 380	62.24 252	57.76 370	70.96 347	40.13 373	84.36 205	82.09 319	46.93 331	51.67 379	61.99 279	81.89 339	65.12 371

test_8					92.09 106	78.87 81	83.82 167	90.31 157	65.79 251	84.36 205	90.96 180	81.93 103	93.44 122

cl22		78.97 216	78.21 226	81.24 212	77.74 330	59.01 288	77.46 281	87.13 213	65.79 251	84.32 207	85.10 284	58.96 278	90.88 196	75.36 157	92.03 230	93.84 107

CS-MVS		88.14 72	87.67 80	89.54 58	89.56 169	79.18 78	90.47 51	94.77 15	79.37 95	84.32 207	89.33 217	83.87 74	94.53 78	82.45 76	94.89 166	94.90 65

agg_prior					91.58 125	77.69 93		90.30 158		84.32 207			93.18 130

Anonymous202405211		80.51 196	81.19 188	78.49 251	88.48 195	57.26 305	76.63 291	82.49 272	81.21 73	84.30 210	92.24 147	67.99 227	86.24 278	62.22 275	95.13 154	91.98 183

LFMVS		80.15 208	80.56 193	78.89 243	89.19 179	55.93 313	85.22 139	73.78 328	82.96 55	84.28 211	92.72 132	57.38 288	90.07 222	63.80 265	95.75 137	90.68 215

Vis-MVSNet		86.86 88	86.58 97	87.72 85	92.09 106	77.43 97	87.35 108	92.09 104	78.87 102	84.27 212	94.05 88	78.35 137	93.65 107	80.54 97	91.58 239	92.08 178
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 226	78.63 220	77.88 264	91.85 115	48.95 356	83.68 172	69.91 352	72.30 189	84.26 213	94.20 80	51.89 315	89.82 226	63.58 266	96.02 120	94.87 67

iter_conf05		78.81 220	77.35 233	83.21 174	82.98 288	60.75 270	84.09 158	88.34 195	63.12 269	84.25 214	89.48 213	31.41 379	94.51 80	76.64 143	95.83 131	94.38 87

FE-MVS		79.98 211	78.86 215	83.36 170	86.47 233	66.45 203	89.73 65	84.74 254	72.80 178	84.22 215	91.38 166	44.95 352	93.60 113	63.93 264	91.50 240	90.04 232

ETV-MVS		84.31 131	83.91 147	85.52 124	88.58 193	70.40 166	84.50 152	93.37 58	78.76 105	84.07 216	78.72 347	80.39 122	95.13 59	73.82 174	92.98 212	91.04 204

MCST-MVS		84.36 129	83.93 146	85.63 122	91.59 122	71.58 158	83.52 175	92.13 103	61.82 278	83.96 217	89.75 210	79.93 128	93.46 121	78.33 119	94.34 182	91.87 185

新几何1				82.95 181	93.96 55	78.56 84		80.24 289	55.45 320	83.93 218	91.08 175	71.19 215	88.33 252	65.84 249	93.07 209	81.95 330

BH-RMVSNet		80.53 195	80.22 201	81.49 208	87.19 221	66.21 206	77.79 274	86.23 227	74.21 154	83.69 219	88.50 229	73.25 196	90.75 199	63.18 271	87.90 288	87.52 266

USDC		76.63 244	76.73 240	76.34 284	83.46 280	57.20 306	80.02 240	88.04 202	52.14 337	83.65 220	91.25 168	63.24 252	86.65 273	54.66 324	94.11 187	85.17 289

miper_enhance_ethall		77.83 230	76.93 237	80.51 223	76.15 346	58.01 299	75.47 308	88.82 186	58.05 307	83.59 221	80.69 329	64.41 244	91.20 183	73.16 189	92.03 230	92.33 167

Effi-MVS+-dtu		85.82 105	83.38 151	93.14 3	87.13 222	91.15 2	87.70 104	88.42 192	74.57 151	83.56 222	85.65 274	78.49 136	94.21 87	72.04 195	92.88 214	94.05 99

CNLPA		83.55 153	83.10 158	84.90 132	89.34 174	83.87 46	84.54 150	88.77 187	79.09 98	83.54 223	88.66 228	74.87 172	81.73 312	66.84 240	92.29 224	89.11 244

SDMVSNet		81.90 179	83.17 156	78.10 259	88.81 186	62.45 246	76.08 300	86.05 230	73.67 160	83.41 224	93.04 116	82.35 93	80.65 318	70.06 211	95.03 159	91.21 200

sd_testset		79.95 212	81.39 184	75.64 291	88.81 186	58.07 298	76.16 299	82.81 270	73.67 160	83.41 224	93.04 116	80.96 116	77.65 326	58.62 298	95.03 159	91.21 200

OpenMVS_ROB	70.19 17	77.77 233	77.46 230	78.71 247	84.39 270	61.15 261	81.18 228	82.52 271	62.45 275	83.34 226	87.37 248	66.20 235	88.66 249	64.69 260	85.02 315	86.32 277

thres100view900		75.45 255	75.05 255	76.66 281	87.27 218	51.88 342	81.07 229	73.26 332	75.68 138	83.25 227	86.37 263	45.54 343	88.80 244	51.98 337	90.99 247	89.31 240

miper_lstm_enhance		76.45 248	76.10 245	77.51 269	76.72 341	60.97 267	64.69 356	85.04 246	63.98 266	83.20 228	88.22 232	56.67 292	78.79 324	73.22 183	93.12 208	92.78 147

IterMVS		76.91 240	76.34 243	78.64 248	80.91 304	64.03 225	76.30 295	79.03 295	64.88 263	83.11 229	89.16 220	59.90 270	84.46 297	68.61 229	85.15 314	87.42 267
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 251	75.35 253	77.85 266	87.01 228	51.84 343	80.45 235	73.26 332	75.20 145	83.10 230	86.31 266	45.54 343	89.05 240	55.03 322	92.24 226	92.66 153

mvs_anonymous		78.13 228	78.76 218	76.23 287	79.24 323	50.31 353	78.69 262	84.82 252	61.60 282	83.09 231	92.82 127	73.89 185	87.01 264	68.33 233	86.41 303	91.37 197

test_fmvs2		73.57 274	72.80 276	75.90 289	72.74 369	68.84 183	77.07 284	84.32 257	45.14 361	82.89 232	84.22 296	48.37 327	70.36 345	73.40 181	87.03 297	88.52 254

MVS_Test		82.47 168	83.22 153	80.22 228	82.62 290	57.75 302	82.54 203	91.96 109	71.16 201	82.89 232	92.52 138	77.41 146	90.50 207	80.04 100	87.84 290	92.40 163

test12				86.57 99	90.74 149	72.63 139		90.69 144		82.76 234		79.20 130	94.80 67		95.32 147	92.27 171

原ACMM1				84.60 141	92.81 87	74.01 126		91.50 121	62.59 272	82.73 235	90.67 191	76.53 161	94.25 85	69.24 217	95.69 139	85.55 285

test_yl		78.71 223	78.51 222	79.32 240	84.32 271	58.84 291	78.38 265	85.33 239	75.99 132	82.49 236	86.57 260	58.01 282	90.02 224	62.74 272	92.73 217	89.10 245

DCV-MVSNet		78.71 223	78.51 222	79.32 240	84.32 271	58.84 291	78.38 265	85.33 239	75.99 132	82.49 236	86.57 260	58.01 282	90.02 224	62.74 272	92.73 217	89.10 245

diffmvs		80.40 199	80.48 196	80.17 229	79.02 326	60.04 275	77.54 278	90.28 161	66.65 247	82.40 238	87.33 250	73.50 189	87.35 262	77.98 127	89.62 267	93.13 136
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
test222					93.31 71	76.54 106	79.38 250	77.79 300	52.59 332	82.36 239	90.84 185	66.83 233			91.69 236	81.25 338

D2MVS		76.84 241	75.67 250	80.34 226	80.48 312	62.16 253	73.50 323	84.80 253	57.61 311	82.24 240	87.54 245	51.31 317	87.65 258	70.40 209	93.19 207	91.23 199

VNet		79.31 214	80.27 198	76.44 282	87.92 206	53.95 326	75.58 306	84.35 256	74.39 153	82.23 241	90.72 188	72.84 200	84.39 298	60.38 291	93.98 190	90.97 205

Vis-MVSNet (Re-imp)		77.82 231	77.79 229	77.92 263	88.82 185	51.29 347	83.28 180	71.97 341	74.04 155	82.23 241	89.78 209	57.38 288	89.41 236	57.22 306	95.41 143	93.05 140

API-MVS		82.28 170	82.61 167	81.30 209	86.29 242	69.79 169	88.71 90	87.67 205	78.42 109	82.15 243	84.15 298	77.98 139	91.59 173	65.39 253	92.75 216	82.51 325

iter_conf_final		80.36 201	78.88 214	84.79 135	86.29 242	66.36 205	86.95 114	86.25 226	68.16 232	82.09 244	89.48 213	36.59 374	94.51 80	79.83 103	94.30 183	93.50 127

DP-MVS Recon		84.05 141	83.22 153	86.52 101	91.73 120	75.27 119	83.23 184	92.40 96	72.04 192	82.04 245	88.33 231	77.91 141	93.95 98	66.17 245	95.12 156	90.34 225

MSDG		80.06 210	79.99 207	80.25 227	83.91 277	68.04 190	77.51 279	89.19 182	77.65 116	81.94 246	83.45 304	76.37 162	86.31 277	63.31 270	86.59 301	86.41 276

test2506		74.12 270	73.39 270	76.28 285	91.85 115	44.20 372	84.06 159	48.20 383	72.30 189	81.90 247	94.20 80	27.22 386	89.77 227	64.81 258	96.02 120	94.87 67

Fast-Effi-MVS+		81.04 188	80.57 192	82.46 194	87.50 215	63.22 234	78.37 267	89.63 176	68.01 233	81.87 248	82.08 320	82.31 94	92.65 146	67.10 237	88.30 285	91.51 196

testgi		72.36 284	74.61 257	65.59 341	80.56 311	42.82 376	68.29 344	73.35 331	66.87 245	81.84 249	89.93 206	72.08 208	66.92 361	46.05 361	92.54 219	87.01 272

tfpn200view9		74.86 263	74.23 262	76.74 280	86.24 244	52.12 339	79.24 253	73.87 326	73.34 167	81.82 250	84.60 293	46.02 337	88.80 244	51.98 337	90.99 247	89.31 240

thres400		75.14 257	74.23 262	77.86 265	86.24 244	52.12 339	79.24 253	73.87 326	73.34 167	81.82 250	84.60 293	46.02 337	88.80 244	51.98 337	90.99 247	92.66 153

CL-MVSNet_self_test		76.81 242	77.38 232	75.12 294	86.90 230	51.34 345	73.20 326	80.63 288	68.30 230	81.80 252	88.40 230	66.92 232	80.90 315	55.35 319	94.90 165	93.12 138

OpenMVS	76.72 13	81.98 177	82.00 175	81.93 198	84.42 269	68.22 186	88.50 94	89.48 179	66.92 244	81.80 252	91.86 152	72.59 203	90.16 215	71.19 199	91.25 244	87.40 268

AdaColmap		83.66 149	83.69 149	83.57 166	90.05 164	72.26 148	86.29 128	90.00 168	78.19 111	81.65 254	87.16 253	83.40 82	94.24 86	61.69 282	94.76 174	84.21 299

CS-MVS-test		87.00 86	86.43 99	88.71 71	89.46 171	77.46 95	89.42 79	95.73 6	77.87 114	81.64 255	87.25 251	82.43 91	94.53 78	77.65 130	96.46 102	94.14 95

DELS-MVS		81.44 183	81.25 185	82.03 197	84.27 273	62.87 238	76.47 294	92.49 95	70.97 202	81.64 255	83.83 299	75.03 170	92.70 144	74.29 164	92.22 228	90.51 221
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
114514_t		83.10 162	82.54 169	84.77 137	92.90 81	69.10 182	86.65 122	90.62 147	54.66 323	81.46 257	90.81 186	76.98 153	94.38 82	72.62 191	96.18 112	90.82 210

TR-MVS		76.77 243	75.79 247	79.72 234	86.10 250	65.79 210	77.14 282	83.02 267	65.20 261	81.40 258	82.10 318	66.30 234	90.73 201	55.57 316	85.27 312	82.65 319

TAMVS		78.08 229	76.36 242	83.23 173	90.62 152	72.87 133	79.08 256	80.01 291	61.72 280	81.35 259	86.92 258	63.96 248	88.78 247	50.61 342	93.01 211	88.04 259

Effi-MVS+		83.90 146	84.01 144	83.57 166	87.22 220	65.61 212	86.55 125	92.40 96	78.64 106	81.34 260	84.18 297	83.65 79	92.93 139	74.22 165	87.87 289	92.17 176

new-patchmatchnet		70.10 303	73.37 271	60.29 355	81.23 301	16.95 387	59.54 365	74.62 319	62.93 270	80.97 261	87.93 238	62.83 257	71.90 341	55.24 320	95.01 162	92.00 181

PVSNet_Blended_VisFu		81.55 182	80.49 195	84.70 140	91.58 125	73.24 131	84.21 154	91.67 118	62.86 271	80.94 262	87.16 253	67.27 230	92.87 142	69.82 213	88.94 275	87.99 260

BH-w/o		76.57 245	76.07 246	78.10 259	86.88 231	65.92 209	77.63 276	86.33 224	65.69 255	80.89 263	79.95 338	68.97 224	90.74 200	53.01 333	85.25 313	77.62 354

MVS_0304		86.35 96	85.92 107	87.66 87	89.21 178	73.16 132	88.40 95	83.63 262	81.27 71	80.87 264	94.12 86	71.49 214	95.71 31	87.79 10	96.50 99	94.11 97

PAPM_NR		83.23 158	83.19 155	83.33 171	90.90 146	65.98 208	88.19 97	90.78 142	78.13 112	80.87 264	87.92 239	73.49 191	92.42 150	70.07 210	88.40 280	91.60 193

ab-mvs		79.67 213	80.56 193	76.99 274	88.48 195	56.93 307	84.70 145	86.06 229	68.95 223	80.78 266	93.08 115	75.30 168	84.62 296	56.78 307	90.90 252	89.43 238

XXY-MVS		74.44 269	76.19 244	69.21 327	84.61 265	52.43 338	71.70 331	77.18 304	60.73 291	80.60 267	90.96 180	75.44 165	69.35 348	56.13 312	88.33 281	85.86 283

HQP4-MVS										80.56 268			94.61 73			93.56 124

HQP-NCC					91.19 137		84.77 142		73.30 169	80.55 269

ACMP_Plane					91.19 137		84.77 142		73.30 169	80.55 269

HQP-MVS		84.61 124	84.06 143	86.27 106	91.19 137	70.66 163	84.77 142	92.68 91	73.30 169	80.55 269	90.17 204	72.10 206	94.61 73	77.30 137	94.47 179	93.56 124

test_cas_vis1_n_1920		69.20 312	69.12 307	69.43 326	73.68 362	62.82 239	70.38 338	77.21 303	46.18 358	80.46 272	78.95 345	52.03 313	65.53 366	65.77 251	77.45 361	79.95 349

AUN-MVS		81.18 186	78.78 217	88.39 76	90.93 145	82.14 58	82.51 204	83.67 261	64.69 264	80.29 273	85.91 273	51.07 318	92.38 152	76.29 148	93.63 198	90.65 217

HyFIR lowres test		75.12 259	72.66 279	82.50 193	91.44 133	65.19 215	72.47 328	87.31 208	46.79 354	80.29 273	84.30 295	52.70 311	92.10 162	51.88 341	86.73 299	90.22 226

test20.03		73.75 273	74.59 259	71.22 315	81.11 302	51.12 349	70.15 339	72.10 340	70.42 207	80.28 275	91.50 163	64.21 246	74.72 337	46.96 358	94.58 177	87.82 265

mvsany_test3		65.48 328	62.97 334	73.03 306	69.99 374	76.17 114	64.83 354	43.71 385	43.68 366	80.25 276	87.05 257	52.83 310	63.09 372	51.92 340	72.44 367	79.84 350

F-COLMAP		84.97 119	83.42 150	89.63 55	92.39 94	83.40 48	88.83 87	91.92 110	73.19 173	80.18 277	89.15 221	77.04 152	93.28 127	65.82 250	92.28 225	92.21 174

GA-MVS		75.83 252	74.61 257	79.48 239	81.87 293	59.25 284	73.42 324	82.88 268	68.68 226	79.75 278	81.80 322	50.62 320	89.46 232	66.85 239	85.64 309	89.72 233

xiu_mvs_v1_base_debu		80.84 190	80.14 203	82.93 182	88.31 198	71.73 154	79.53 246	87.17 210	65.43 257	79.59 279	82.73 314	76.94 154	90.14 218	73.22 183	88.33 281	86.90 273

xiu_mvs_v1_base		80.84 190	80.14 203	82.93 182	88.31 198	71.73 154	79.53 246	87.17 210	65.43 257	79.59 279	82.73 314	76.94 154	90.14 218	73.22 183	88.33 281	86.90 273

xiu_mvs_v1_base_debi		80.84 190	80.14 203	82.93 182	88.31 198	71.73 154	79.53 246	87.17 210	65.43 257	79.59 279	82.73 314	76.94 154	90.14 218	73.22 183	88.33 281	86.90 273

test_fmvs1_n		70.94 296	70.41 299	72.53 310	73.92 359	66.93 198	75.99 301	84.21 259	43.31 368	79.40 282	79.39 342	43.47 357	68.55 353	69.05 222	84.91 318	82.10 328

patch_mono-2		78.89 217	79.39 210	77.41 271	84.78 263	68.11 188	75.60 304	83.11 266	60.96 288	79.36 283	89.89 208	75.18 169	72.97 338	73.32 182	92.30 222	91.15 202

UnsupCasMVSNet_eth		71.63 291	72.30 284	69.62 324	76.47 343	52.70 336	70.03 340	80.97 285	59.18 300	79.36 283	88.21 233	60.50 263	69.12 349	58.33 301	77.62 359	87.04 271

ppachtmachnet_test		74.73 266	74.00 264	76.90 277	80.71 309	56.89 309	71.53 333	78.42 297	58.24 305	79.32 285	82.92 311	57.91 285	84.26 299	65.60 252	91.36 242	89.56 235

MG-MVS		80.32 203	80.94 190	78.47 252	88.18 201	52.62 337	82.29 210	85.01 248	72.01 193	79.24 286	92.54 137	69.36 220	93.36 126	70.65 205	89.19 272	89.45 236

Fast-Effi-MVS+-dtu		82.54 167	81.41 183	85.90 116	85.60 253	76.53 108	83.07 187	89.62 177	73.02 176	79.11 287	83.51 302	80.74 119	90.24 212	68.76 226	89.29 269	90.94 206

CDS-MVSNet		77.32 236	75.40 251	83.06 177	89.00 182	72.48 144	77.90 272	82.17 275	60.81 289	78.94 288	83.49 303	59.30 274	88.76 248	54.64 325	92.37 221	87.93 262
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 276	73.54 268	72.43 311	84.92 261	47.79 361	79.89 242	74.00 324	65.93 249	78.81 289	86.28 267	56.36 295	81.63 313	56.63 308	79.04 354	87.87 264

EIA-MVS		82.19 172	81.23 187	85.10 130	87.95 205	69.17 181	83.22 185	93.33 61	70.42 207	78.58 290	79.77 341	77.29 147	94.20 88	71.51 197	88.96 274	91.93 184

thres200		72.34 285	71.55 291	74.70 297	83.48 279	51.60 344	75.02 311	73.71 329	70.14 213	78.56 291	80.57 332	46.20 335	88.20 254	46.99 357	89.29 269	84.32 298

our_test_3		71.85 288	71.59 288	72.62 308	80.71 309	53.78 327	69.72 341	71.71 345	58.80 302	78.03 292	80.51 334	56.61 294	78.84 323	62.20 276	86.04 307	85.23 288

KD-MVS_2432*1600		66.87 319	65.81 326	70.04 320	67.50 377	47.49 362	62.56 360	79.16 293	61.21 286	77.98 293	80.61 330	25.29 388	82.48 308	53.02 331	84.92 316	80.16 347

miper_refine_blended		66.87 319	65.81 326	70.04 320	67.50 377	47.49 362	62.56 360	79.16 293	61.21 286	77.98 293	80.61 330	25.29 388	82.48 308	53.02 331	84.92 316	80.16 347

jason		77.42 235	75.75 248	82.43 195	87.10 225	69.27 176	77.99 270	81.94 277	51.47 341	77.84 295	85.07 287	60.32 266	89.00 241	70.74 204	89.27 271	89.03 248
jason: jason.
MAR-MVS		80.24 205	78.74 219	84.73 138	86.87 232	78.18 85	85.75 132	87.81 204	65.67 256	77.84 295	78.50 348	73.79 186	90.53 206	61.59 284	90.87 253	85.49 287
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
FPMVS		72.29 286	72.00 285	73.14 304	88.63 191	85.00 36	74.65 314	67.39 356	71.94 194	77.80 297	87.66 243	50.48 321	75.83 333	49.95 344	79.51 348	58.58 377

test_fmvs1		69.57 309	69.05 309	71.14 317	69.15 376	65.77 211	73.98 319	83.32 264	42.83 370	77.77 298	78.27 350	43.39 360	68.50 354	68.39 232	84.38 325	79.15 351

pmmvs4		74.92 262	72.98 275	80.73 220	84.95 260	71.71 157	76.23 297	77.59 301	52.83 331	77.73 299	86.38 262	56.35 296	84.97 293	57.72 305	87.05 296	85.51 286

ET-MVSNet_ETH3D		75.28 256	72.77 277	82.81 186	83.03 287	68.11 188	77.09 283	76.51 309	60.67 292	77.60 300	80.52 333	38.04 370	91.15 186	70.78 202	90.68 258	89.17 243

UnsupCasMVSNet_bld		69.21 311	69.68 305	67.82 334	79.42 320	51.15 348	67.82 348	75.79 312	54.15 325	77.47 301	85.36 282	59.26 275	70.64 344	48.46 351	79.35 350	81.66 332

Anonymous20231206		71.38 293	71.88 286	69.88 322	86.31 240	54.37 323	70.39 337	74.62 319	52.57 333	76.73 302	88.76 225	59.94 269	72.06 340	44.35 365	93.23 206	83.23 315

CMPMVS	59.41 20	75.12 259	73.57 267	79.77 232	75.84 349	67.22 193	81.21 227	82.18 274	50.78 346	76.50 303	87.66 243	55.20 303	82.99 306	62.17 278	90.64 262	89.09 247
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 287	71.69 287	73.32 302	81.57 296	53.02 333	76.77 288	78.37 298	63.31 267	76.37 304	91.85 153	36.68 373	78.98 322	47.87 354	92.45 220	87.95 261

CVMVSNet		72.62 282	71.41 292	76.28 285	83.25 282	60.34 273	83.50 176	79.02 296	37.77 378	76.33 305	85.10 284	49.60 325	87.41 261	70.54 207	77.54 360	81.08 341

PLC	73.85 16	82.09 174	80.31 197	87.45 89	90.86 148	80.29 69	85.88 130	90.65 145	68.17 231	76.32 306	86.33 264	73.12 197	92.61 147	61.40 285	90.02 265	89.44 237
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 171	81.57 182	84.19 153	85.54 255	69.26 177	91.98 31	90.08 166	71.54 195	76.23 307	85.07 287	58.69 279	94.27 83	86.26 36	88.77 276	89.03 248

lupinMVS		76.37 249	74.46 260	82.09 196	85.54 255	69.26 177	76.79 287	80.77 287	50.68 348	76.23 307	82.82 312	58.69 279	88.94 242	69.85 212	88.77 276	88.07 257

PatchMatch-RL		74.48 267	73.22 272	78.27 257	87.70 210	85.26 34	75.92 302	70.09 350	64.34 265	76.09 309	81.25 327	65.87 239	78.07 325	53.86 327	83.82 327	71.48 363

thisisatest0515		73.00 280	70.52 296	80.46 224	81.45 297	59.90 278	73.16 327	74.31 323	57.86 308	76.08 310	77.78 351	37.60 372	92.12 161	65.00 256	91.45 241	89.35 239

MS-PatchMatch		70.93 297	70.22 300	73.06 305	81.85 294	62.50 245	73.82 322	77.90 299	52.44 334	75.92 311	81.27 326	55.67 300	81.75 311	55.37 318	77.70 358	74.94 359

CHOSEN 1792x2688		72.45 283	70.56 295	78.13 258	90.02 166	63.08 235	68.72 343	83.16 265	42.99 369	75.92 311	85.46 277	57.22 290	85.18 292	49.87 346	81.67 340	86.14 279

CR-MVSNet		74.00 271	73.04 274	76.85 279	79.58 317	62.64 242	82.58 200	76.90 305	50.50 349	75.72 313	92.38 140	48.07 329	84.07 300	68.72 228	82.91 333	83.85 304

RPMNet		78.88 218	78.28 225	80.68 222	79.58 317	62.64 242	82.58 200	94.16 27	74.80 148	75.72 313	92.59 134	48.69 326	95.56 38	73.48 179	82.91 333	83.85 304

DPM-MVS		80.10 209	79.18 212	82.88 185	90.71 151	69.74 170	78.87 260	90.84 140	60.29 295	75.64 315	85.92 272	67.28 229	93.11 133	71.24 198	91.79 234	85.77 284

test_vis1_n		70.29 300	69.99 303	71.20 316	75.97 348	66.50 202	76.69 290	80.81 286	44.22 364	75.43 316	77.23 356	50.00 323	68.59 352	66.71 242	82.85 335	78.52 353

PVSNet_BlendedMVS		78.80 221	77.84 228	81.65 206	84.43 267	63.41 230	79.49 249	90.44 151	61.70 281	75.43 316	87.07 256	69.11 222	91.44 177	60.68 289	92.24 226	90.11 230

PVSNet_Blended		76.49 247	75.40 251	79.76 233	84.43 267	63.41 230	75.14 310	90.44 151	57.36 313	75.43 316	78.30 349	69.11 222	91.44 177	60.68 289	87.70 292	84.42 297

PAPR		78.84 219	78.10 227	81.07 214	85.17 259	60.22 274	82.21 214	90.57 148	62.51 273	75.32 319	84.61 292	74.99 171	92.30 156	59.48 295	88.04 287	90.68 215

N_pmnet		70.20 301	68.80 312	74.38 298	80.91 304	84.81 39	59.12 367	76.45 310	55.06 321	75.31 320	82.36 317	55.74 299	54.82 377	47.02 356	87.24 295	83.52 308

cascas		76.29 250	74.81 256	80.72 221	84.47 266	62.94 236	73.89 321	87.34 207	55.94 318	75.16 321	76.53 361	63.97 247	91.16 185	65.00 256	90.97 250	88.06 258

SCA		73.32 275	72.57 281	75.58 292	81.62 295	55.86 314	78.89 259	71.37 346	61.73 279	74.93 322	83.42 305	60.46 264	87.01 264	58.11 303	82.63 338	83.88 301

test_vis1_n_1920		71.30 294	71.58 290	70.47 318	77.58 333	59.99 277	74.25 315	84.22 258	51.06 343	74.85 323	79.10 343	55.10 304	68.83 351	68.86 225	79.20 353	82.58 321

xiu_mvs_v2_base		77.19 237	76.75 239	78.52 250	87.01 228	61.30 259	75.55 307	87.12 216	61.24 285	74.45 324	78.79 346	77.20 148	90.93 192	64.62 262	84.80 322	83.32 313

CANet		83.79 147	82.85 162	86.63 98	86.17 247	72.21 150	83.76 170	91.43 123	77.24 122	74.39 325	87.45 247	75.36 167	95.42 48	77.03 140	92.83 215	92.25 173

PS-MVSNAJ		77.04 239	76.53 241	78.56 249	87.09 226	61.40 257	75.26 309	87.13 213	61.25 284	74.38 326	77.22 357	76.94 154	90.94 191	64.63 261	84.83 321	83.35 312

MVP-Stereo		75.81 253	73.51 269	82.71 187	89.35 173	73.62 127	80.06 238	85.20 241	60.30 294	73.96 327	87.94 237	57.89 286	89.45 233	52.02 336	74.87 365	85.06 291
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
UGNet		82.78 163	81.64 179	86.21 109	86.20 246	76.24 113	86.86 115	85.68 235	77.07 123	73.76 328	92.82 127	69.64 218	91.82 170	69.04 223	93.69 196	90.56 219
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
1112_ss		74.82 264	73.74 265	78.04 261	89.57 168	60.04 275	76.49 293	87.09 217	54.31 324	73.66 329	79.80 339	60.25 267	86.76 272	58.37 299	84.15 326	87.32 269

Test_1112_low_res		73.90 272	73.08 273	76.35 283	90.35 156	55.95 312	73.40 325	86.17 228	50.70 347	73.14 330	85.94 271	58.31 281	85.90 284	56.51 309	83.22 330	87.20 270

1314		73.22 277	72.56 282	75.20 293	80.41 313	57.84 300	81.64 221	85.36 238	51.68 340	73.10 331	76.65 360	61.45 260	85.19 291	63.54 267	79.21 352	82.59 320

test_vis1_rt		65.64 327	64.09 331	70.31 319	66.09 381	70.20 168	61.16 363	81.60 281	38.65 376	72.87 332	69.66 370	52.84 309	60.04 374	56.16 311	77.77 357	80.68 345

Patchmatch-test		65.91 325	67.38 317	61.48 353	75.51 351	43.21 375	68.84 342	63.79 366	62.48 274	72.80 333	83.42 305	44.89 353	59.52 375	48.27 353	86.45 302	81.70 331

PatchmatchNet		69.71 308	68.83 311	72.33 312	77.66 332	53.60 328	79.29 251	69.99 351	57.66 310	72.53 334	82.93 310	46.45 334	80.08 321	60.91 288	72.09 368	83.31 314
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 315	68.08 316	67.55 335	78.74 328	43.53 374	75.60 304	67.10 361	54.92 322	72.23 335	88.10 234	42.87 362	75.97 332	52.21 335	80.95 347	83.15 316

pmmvs5		70.73 298	70.07 301	72.72 307	77.03 338	52.73 335	74.14 316	75.65 315	50.36 350	72.17 336	85.37 281	55.42 302	80.67 317	52.86 334	87.59 293	84.77 293

PatchT		70.52 299	72.76 278	63.79 347	79.38 321	33.53 382	77.63 276	65.37 364	73.61 162	71.77 337	92.79 130	44.38 355	75.65 334	64.53 263	85.37 311	82.18 327

MVS		73.21 278	72.59 280	75.06 295	80.97 303	60.81 269	81.64 221	85.92 233	46.03 359	71.68 338	77.54 352	68.47 225	89.77 227	55.70 315	85.39 310	74.60 360

MIMVSNet		71.09 295	71.59 288	69.57 325	87.23 219	50.07 354	78.91 258	71.83 342	60.20 297	71.26 339	91.76 158	55.08 305	76.09 331	41.06 370	87.02 298	82.54 323

WTY-MVS		67.91 316	68.35 314	66.58 338	80.82 307	48.12 359	65.96 353	72.60 335	53.67 327	71.20 340	81.68 324	58.97 277	69.06 350	48.57 350	81.67 340	82.55 322

test0.0.03 1		64.66 330	64.36 330	65.57 342	75.03 356	46.89 365	64.69 356	61.58 371	62.43 276	71.18 341	77.54 352	43.41 358	68.47 355	40.75 371	82.65 336	81.35 335

CostFormer		69.98 306	68.68 313	73.87 299	77.14 336	50.72 351	79.26 252	74.51 321	51.94 339	70.97 342	84.75 290	45.16 351	87.49 260	55.16 321	79.23 351	83.40 311

tpmvs		70.16 302	69.56 306	71.96 313	74.71 358	48.13 358	79.63 244	75.45 317	65.02 262	70.26 343	81.88 321	45.34 348	85.68 287	58.34 300	75.39 364	82.08 329

sss		66.92 318	67.26 318	65.90 340	77.23 335	51.10 350	64.79 355	71.72 344	52.12 338	70.13 344	80.18 336	57.96 284	65.36 367	50.21 343	81.01 346	81.25 338

tpm2		68.45 314	66.83 321	73.30 303	78.93 327	48.50 357	79.76 243	71.76 343	47.50 353	69.92 345	83.60 301	42.07 363	88.40 251	48.44 352	79.51 348	83.01 318

HY-MVS	64.64 18	73.03 279	72.47 283	74.71 296	83.36 281	54.19 324	82.14 217	81.96 276	56.76 317	69.57 346	86.21 268	60.03 268	84.83 295	49.58 347	82.65 336	85.11 290

dmvs_re		66.81 321	66.98 319	66.28 339	76.87 339	58.68 295	71.66 332	72.24 338	60.29 295	69.52 347	73.53 366	52.38 312	64.40 369	44.90 363	81.44 343	75.76 357

tpm cat1		66.76 322	65.21 329	71.42 314	77.09 337	50.62 352	78.01 269	73.68 330	44.89 362	68.64 348	79.00 344	45.51 345	82.42 310	49.91 345	70.15 371	81.23 340

IB-MVS	62.13 19	71.64 290	68.97 310	79.66 236	80.80 308	62.26 251	73.94 320	76.90 305	63.27 268	68.63 349	76.79 359	33.83 377	91.84 169	59.28 296	87.26 294	84.88 292
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
EPNet		80.37 200	78.41 224	86.23 107	76.75 340	73.28 129	87.18 110	77.45 302	76.24 128	68.14 350	88.93 224	65.41 240	93.85 101	69.47 215	96.12 116	91.55 195
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 323	65.63 328	68.75 330	81.96 292	49.88 355	62.19 362	72.51 337	51.03 344	68.04 351	75.34 364	50.84 319	74.77 335	45.82 362	82.96 331	81.60 333

tpmrst		66.28 324	66.69 323	65.05 344	72.82 368	39.33 377	78.20 268	70.69 349	53.16 330	67.88 352	80.36 335	48.18 328	74.75 336	58.13 302	70.79 370	81.08 341

CANet_DTU		77.81 232	77.05 235	80.09 230	81.37 299	59.90 278	83.26 181	88.29 197	69.16 220	67.83 353	83.72 300	60.93 261	89.47 231	69.22 219	89.70 266	90.88 208

EPMVS		62.47 332	62.63 336	62.01 349	70.63 373	38.74 378	74.76 312	52.86 380	53.91 326	67.71 354	80.01 337	39.40 367	66.60 362	55.54 317	68.81 376	80.68 345

MDTV_nov1_ep13			68.29 315		78.03 329	43.87 373	74.12 317	72.22 339	52.17 335	67.02 355	85.54 275	45.36 347	80.85 316	55.73 313	84.42 324

pmmvs3		62.47 332	60.02 345	69.80 323	71.58 372	64.00 226	70.52 336	58.44 376	39.77 374	66.05 356	75.84 362	27.10 387	72.28 339	46.15 360	84.77 323	73.11 361

ADS-MVSNet2		65.87 326	63.64 333	72.55 309	73.16 365	56.92 308	67.10 349	74.81 318	49.74 351	66.04 357	82.97 308	46.71 332	77.26 328	42.29 367	69.96 372	83.46 309

ADS-MVSNet		61.90 334	62.19 338	61.03 354	73.16 365	36.42 380	67.10 349	61.75 369	49.74 351	66.04 357	82.97 308	46.71 332	63.21 370	42.29 367	69.96 372	83.46 309

mvsany_test1		58.48 344	56.47 349	64.50 345	65.90 383	68.21 187	56.95 371	42.11 386	38.30 377	65.69 359	77.19 358	56.96 291	59.35 376	46.16 359	58.96 379	65.93 370

dmvs_testset		60.59 342	62.54 337	54.72 361	77.26 334	27.74 385	74.05 318	61.00 372	60.48 293	65.62 360	67.03 374	55.93 298	68.23 356	32.07 380	69.46 375	68.17 368

DSMNet-mixed		60.98 340	61.61 340	59.09 358	72.88 367	45.05 370	74.70 313	46.61 384	26.20 380	65.34 361	90.32 198	55.46 301	63.12 371	41.72 369	81.30 345	69.09 367

JIA-IIPM		69.41 310	66.64 324	77.70 267	73.19 364	71.24 160	75.67 303	65.56 363	70.42 207	65.18 362	92.97 122	33.64 378	83.06 305	53.52 329	69.61 374	78.79 352

test-LLR		67.21 317	66.74 322	68.63 331	76.45 344	55.21 319	67.89 345	67.14 359	62.43 276	65.08 363	72.39 367	43.41 358	69.37 346	61.00 286	84.89 319	81.31 336

test-mter		65.00 329	63.79 332	68.63 331	76.45 344	55.21 319	67.89 345	67.14 359	50.98 345	65.08 363	72.39 367	28.27 384	69.37 346	61.00 286	84.89 319	81.31 336

PMMVS2		55.64 347	59.27 346	44.74 363	64.30 385	12.32 388	40.60 376	49.79 382	53.19 329	65.06 365	84.81 289	53.60 308	49.76 380	32.68 379	89.41 268	72.15 362

baseline2		69.77 307	66.89 320	78.41 253	79.51 319	58.09 297	76.23 297	69.57 353	57.50 312	64.82 366	77.45 354	46.02 337	88.44 250	53.08 330	77.83 356	88.70 252

gg-mvs-nofinetune		68.96 313	69.11 308	68.52 333	76.12 347	45.32 368	83.59 174	55.88 378	86.68 24	64.62 367	97.01 7	30.36 381	83.97 302	44.78 364	82.94 332	76.26 356

PAPM		71.77 289	70.06 302	76.92 276	86.39 235	53.97 325	76.62 292	86.62 222	53.44 328	63.97 368	84.73 291	57.79 287	92.34 154	39.65 372	81.33 344	84.45 296

new_pmnet		55.69 346	57.66 347	49.76 362	75.47 352	30.59 383	59.56 364	51.45 381	43.62 367	62.49 369	75.48 363	40.96 365	49.15 381	37.39 375	72.52 366	69.55 366

MDTV_nov1_ep13_2view						27.60 386	70.76 335		46.47 357	61.27 370		45.20 349		49.18 348		83.75 306

dp		60.70 341	60.29 344	61.92 351	72.04 371	38.67 379	70.83 334	64.08 365	51.28 342	60.75 371	77.28 355	36.59 374	71.58 343	47.41 355	62.34 378	75.52 358

TESTMET0.1,1		61.29 337	60.32 343	64.19 346	72.06 370	51.30 346	67.89 345	62.09 367	45.27 360	60.65 372	69.01 371	27.93 385	64.74 368	56.31 310	81.65 342	76.53 355

PMMVS		61.65 335	60.38 342	65.47 343	65.40 384	69.26 177	63.97 358	61.73 370	36.80 379	60.11 373	68.43 372	59.42 273	66.35 363	48.97 349	78.57 355	60.81 374

PVSNet_0	51.08 22	56.10 345	54.97 350	59.48 357	75.12 355	53.28 332	55.16 372	61.89 368	44.30 363	59.16 374	62.48 377	54.22 306	65.91 365	35.40 376	47.01 380	59.25 376

MVS-HIRNet		61.16 338	62.92 335	55.87 359	79.09 324	35.34 381	71.83 330	57.98 377	46.56 356	59.05 375	91.14 172	49.95 324	76.43 330	38.74 373	71.92 369	55.84 378

E-PMN		61.59 336	61.62 339	61.49 352	66.81 379	55.40 317	53.77 373	60.34 373	66.80 246	58.90 376	65.50 375	40.48 366	66.12 364	55.72 314	86.25 305	62.95 373

GG-mvs-BLEND				67.16 336	73.36 363	46.54 367	84.15 156	55.04 379		58.64 377	61.95 378	29.93 382	83.87 303	38.71 374	76.92 362	71.07 364

EPNet_dtu		72.87 281	71.33 293	77.49 270	77.72 331	60.55 272	82.35 208	75.79 312	66.49 248	58.39 378	81.06 328	53.68 307	85.98 282	53.55 328	92.97 213	85.95 281
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EMVS		61.10 339	60.81 341	61.99 350	65.96 382	55.86 314	53.10 374	58.97 375	67.06 243	56.89 379	63.33 376	40.98 364	67.03 360	54.79 323	86.18 306	63.08 372

CHOSEN 280x420		59.08 343	56.52 348	66.76 337	76.51 342	64.39 222	49.62 375	59.00 374	43.86 365	55.66 380	68.41 373	35.55 376	68.21 357	43.25 366	76.78 363	67.69 369

MVE	40.22 23	51.82 348	50.47 351	55.87 359	62.66 386	51.91 341	31.61 378	39.28 387	40.65 372	50.76 381	74.98 365	56.24 297	44.67 382	33.94 378	64.11 377	71.04 365
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
DeepMVS_CX				24.13 365	32.95 387	29.49 384		21.63 390	12.07 381	37.95 382	45.07 380	30.84 380	19.21 384	17.94 383	33.06 383	23.69 380

tmp_tt		20.25 351	24.50 354	7.49 366	4.47 389	8.70 389	34.17 377	25.16 389	1.00 384	32.43 383	18.49 381	39.37 368	9.21 385	21.64 382	43.75 381	4.57 381

test_method		30.46 349	29.60 352	33.06 364	17.99 388	3.84 390	13.62 379	73.92 325	2.79 382	18.29 384	53.41 379	28.53 383	43.25 383	22.56 381	35.27 382	52.11 379

EGC-MVSNET		74.79 265	69.99 303	89.19 63	94.89 37	87.00 11	91.89 34	86.28 225	1.09 383	2.23 385	95.98 23	81.87 106	89.48 230	79.76 104	95.96 123	91.10 203

testmvs		5.91 355	7.65 358	0.72 368	1.20 390	0.37 392	59.14 366	0.67 392	0.49 386	1.11 386	2.76 385	0.94 391	0.24 387	1.02 385	1.47 384	1.55 383

test123		6.27 354	8.08 357	0.84 367	1.11 391	0.57 391	62.90 359	0.82 391	0.54 385	1.07 387	2.75 386	1.26 390	0.30 386	1.04 384	1.26 385	1.66 382

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

cdsmvs_eth3d_5k		20.81 350	27.75 353	0.00 369	0.00 392	0.00 393	0.00 380	85.44 237	0.00 387	0.00 388	82.82 312	81.46 110	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		6.41 353	8.55 356	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	76.94 154	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

ab-mvs-re		6.65 352	8.87 355	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	79.80 339	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

MSC_two_6792asdad				88.81 68	91.55 127	77.99 87		91.01 136					96.05 7	87.45 18	98.17 32	92.40 163

No_MVS				88.81 68	91.55 127	77.99 87		91.01 136					96.05 7	87.45 18	98.17 32	92.40 163

eth-test2					0.00 392

eth-test					0.00 392

OPU-MVS				88.27 79	91.89 113	77.83 90	90.47 51				91.22 169	81.12 114	94.68 70	74.48 163	95.35 145	92.29 169

save fliter					93.75 59	77.44 96	86.31 127	89.72 172	70.80 203

test_0728_SECOND				86.79 96	94.25 45	72.45 145	90.54 48	94.10 34					95.88 16	86.42 32	97.97 43	92.02 180

GSMVS																83.88 301

sam_mvs1												46.11 336				83.88 301

sam_mvs												45.92 341

MTGPA								91.81 116

test_post1							78.85 261				3.13 383	45.19 350	80.13 320	58.11 303

test_post											3.10 384	45.43 346	77.22 329

patchmatchnet-post											81.71 323	45.93 340	87.01 264

MTMP							90.66 44	33.14 388

gm-plane-assit					75.42 353	44.97 371			52.17 335		72.36 369		87.90 255	54.10 326

test9_res														80.83 92	96.45 103	90.57 218

agg_prior2														79.68 106	96.16 113	90.22 226

test_prior4						78.97 80	84.59 147

test_prior				86.32 104	90.59 153	71.99 152		92.85 86					94.17 91			92.80 146

新几何2							81.72 220

旧先验1					91.97 109	71.77 153		81.78 279			91.84 154	73.92 184			93.65 197	83.61 307

无先验							82.81 195	85.62 236	58.09 306				91.41 180	67.95 236		84.48 295

原ACMM2							82.26 213

testdata2													86.43 276	63.52 268

segment_acmp												81.94 102

testdata1							79.62 245		73.95 157

plane_prior7					93.45 66	77.31 99

plane_prior6					92.61 88	76.54 106						74.84 173

plane_prior5								93.61 53					95.22 55	80.78 93	95.83 131	94.46 80

plane_prior4											92.95 123

plane_prior2							89.45 77		79.44 93

plane_prior1					92.83 86

plane_prior						76.42 110	87.15 111		75.94 135						95.03 159

n2								0.00 393

nn								0.00 393

door-mid								74.45 322

test11								91.46 122

door								72.57 336

HQP5-MVS						70.66 163

BP-MVS														77.30 137

HQP3-MVS								92.68 91							94.47 179

HQP2-MVS												72.10 206

NP-MVS					91.95 110	74.55 123					90.17 204

ACMMP++_ref															95.74 138

ACMMP++															97.35 73

Test By Simon												79.09 131

High-resolution multi-view benchmark