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 3	98.67 1	85.39 37	95.54 5	97.36 1	96.97 1	99.04 1	99.05 1	96.61 1	95.92 16	85.07 63	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 46	97.23 2	95.32 2	99.01 2	97.26 6	80.16 135	98.99 1	95.15 1	99.14 2	96.47 30

FOURS1					96.08 12	87.41 14	96.19 2	95.83 5	92.95 3	96.57 3

DTE-MVSNet		89.98 47	91.91 17	84.21 164	96.51 7	57.84 325	88.93 90	92.84 94	91.92 4	96.16 4	96.23 21	86.95 51	95.99 12	79.05 132	98.57 15	98.80 6

PS-CasMVS		90.06 43	91.92 15	84.47 155	96.56 6	58.83 317	89.04 88	92.74 97	91.40 6	96.12 5	96.06 26	87.23 48	95.57 41	79.42 129	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 171	85.06 132	78.75 271	85.94 271	55.75 342	80.05 265	94.27 24	76.47 137	96.09 6	94.54 67	83.31 88	89.75 241	59.95 325	94.89 169	90.75 239

PEN-MVS		90.03 45	91.88 18	84.48 154	96.57 5	58.88 314	88.95 89	93.19 75	91.62 5	96.01 7	96.16 24	87.02 50	95.60 40	78.69 135	98.72 9	98.97 3

CP-MVSNet		89.27 62	90.91 44	84.37 156	96.34 8	58.61 320	88.66 97	92.06 116	90.78 7	95.67 8	95.17 47	81.80 117	95.54 44	79.00 133	98.69 10	98.95 4

reproduce_model		92.89 5	93.18 7	92.01 13	94.20 49	88.23 9	92.87 13	94.32 21	90.25 11	95.65 9	95.74 30	87.75 41	95.72 36	89.60 4	98.27 26	92.08 201

LTVRE_ROB	86.10 1	93.04 4	93.44 3	91.82 22	93.73 64	85.72 34	96.79 1	95.51 9	88.86 16	95.63 10	96.99 10	84.81 72	93.16 137	91.10 2	97.53 72	96.58 28
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 50	91.31 33	85.71 128	96.32 9	62.39 270	89.54 79	93.31 70	90.21 12	95.57 11	95.66 33	81.42 121	95.90 17	80.94 109	98.80 3	98.84 5

reproduce-ours		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 212

our_new_method		92.86 6	93.22 5	91.76 23	94.39 44	87.71 11	92.40 27	94.38 19	89.82 13	95.51 12	95.49 38	89.64 21	95.82 26	89.13 6	98.26 28	91.76 212

OurMVSNet-221017-0		90.01 46	89.74 56	90.83 36	93.16 78	80.37 72	91.91 36	93.11 79	81.10 81	95.32 14	97.24 7	72.94 218	94.85 72	85.07 63	97.78 56	97.26 15

anonymousdsp		89.73 53	88.88 70	92.27 8	89.82 171	86.67 18	90.51 54	90.20 178	69.87 232	95.06 15	96.14 25	84.28 77	93.07 141	87.68 20	96.34 106	97.09 19

wuyk23d		75.13 286	79.30 239	62.63 394	75.56 394	75.18 127	80.89 256	73.10 362	75.06 160	94.76 16	95.32 41	87.73 43	52.85 426	34.16 424	97.11 82	59.85 422

ACMH	76.49 14	89.34 59	91.14 35	83.96 170	92.50 94	70.36 183	89.55 77	93.84 52	81.89 73	94.70 17	95.44 40	90.69 8	88.31 267	83.33 80	98.30 25	93.20 146
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 89	87.45 87	86.45 108	92.52 93	69.19 198	87.84 107	88.05 217	81.66 75	94.64 18	96.53 17	65.94 265	94.75 74	83.02 86	96.83 89	95.41 53

mvs_tets		89.78 52	89.27 63	91.30 29	93.51 67	84.79 44	89.89 68	90.63 158	70.00 231	94.55 19	96.67 14	87.94 39	93.59 120	84.27 73	95.97 124	95.52 51

jajsoiax		89.41 57	88.81 73	91.19 32	93.38 71	84.72 45	89.70 71	90.29 175	69.27 235	94.39 20	96.38 18	86.02 65	93.52 124	83.96 75	95.92 130	95.34 55

test_0402		88.65 69	89.58 60	85.88 124	92.55 92	72.22 160	84.01 181	89.44 196	88.63 20	94.38 21	95.77 29	86.38 61	93.59 120	79.84 121	95.21 154	91.82 210

UniMVSNet_ETH3D		89.12 65	90.72 47	84.31 162	97.00 2	64.33 245	89.67 74	88.38 210	88.84 17	94.29 22	97.57 4	90.48 13	91.26 189	72.57 217	97.65 62	97.34 14

v7n		90.13 40	90.96 42	87.65 91	91.95 112	71.06 175	89.99 64	93.05 83	86.53 31	94.29 22	96.27 20	82.69 93	94.08 100	86.25 47	97.63 63	97.82 8

test_djsdf		89.62 54	89.01 67	91.45 26	92.36 97	82.98 57	91.98 34	90.08 181	71.54 211	94.28 24	96.54 16	81.57 119	94.27 89	86.26 45	96.49 100	97.09 19

PS-MVSNAJss		88.31 73	87.90 81	89.56 59	93.31 73	77.96 96	87.94 105	91.97 119	70.73 222	94.19 25	96.67 14	76.94 169	94.57 81	83.07 84	96.28 108	96.15 33

SED-MVS		90.46 37	91.64 21	86.93 99	94.18 50	72.65 146	90.47 55	93.69 56	83.77 52	94.11 26	94.27 79	90.28 14	95.84 24	86.03 51	97.92 49	92.29 191

test_241102_ONE					94.18 50	72.65 146		93.69 56	83.62 54	94.11 26	93.78 108	90.28 14	95.50 49

DPE-MVS		90.53 36	91.08 37	88.88 69	93.38 71	78.65 87	89.15 87	94.05 41	84.68 45	93.90 28	94.11 91	88.13 36	96.30 5	84.51 71	97.81 55	91.70 216
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		91.22 25	91.92 15	89.14 66	92.97 82	78.04 93	92.84 16	94.14 36	83.33 58	93.90 28	95.73 31	88.77 27	96.41 3	87.60 23	97.98 45	92.98 157
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMH+	77.89 11	90.73 31	91.50 25	88.44 78	93.00 81	76.26 119	89.65 75	95.55 8	87.72 26	93.89 30	94.94 52	91.62 3	93.44 128	78.35 139	98.76 4	95.61 50

ACMM	79.39 9	90.65 32	90.99 41	89.63 57	95.03 34	83.53 51	89.62 76	93.35 66	79.20 105	93.83 31	93.60 116	90.81 7	92.96 144	85.02 65	98.45 19	92.41 182
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		92.41 9	92.41 10	92.39 5	94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	88.83 26	95.51 47	87.16 34	97.60 66	92.73 164

RE-MVS-def			92.61 8		94.13 55	88.95 6	92.87 13	94.16 32	88.75 18	93.79 32	94.43 72	90.64 10		87.16 34	97.60 66	92.73 164

DVP-MVS		90.06 43	91.32 32	86.29 111	94.16 53	72.56 152	90.54 52	91.01 148	83.61 55	93.75 34	94.65 61	89.76 18	95.78 32	86.42 41	97.97 46	90.55 249
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 38	93.75 34	94.65 61	87.44 46	95.78 32	87.41 27	98.21 32	92.98 157

test0726					94.16 53	72.56 152	90.63 49	93.90 48	83.61 55	93.75 34	94.49 69	89.76 18

LPG-MVS_test		91.47 21	91.68 20	90.82 37	94.75 41	81.69 63	90.00 62	94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 60	98.73 7	95.23 61

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 24	82.35 68	93.67 37	94.82 56	91.18 4	95.52 45	85.36 60	98.73 7	95.23 61

DVP-MVS++		90.07 42	91.09 36	87.00 97	91.55 129	72.64 148	96.19 2	94.10 39	85.33 38	93.49 39	94.64 64	81.12 124	95.88 18	87.41 27	95.94 128	92.48 178

test_241102_TWO								93.71 55	83.77 52	93.49 39	94.27 79	89.27 23	95.84 24	86.03 51	97.82 54	92.04 203

test_one_0601					93.85 62	73.27 141		94.11 38	86.57 30	93.47 41	94.64 64	88.42 28

SR-MVS		92.23 10	92.34 11	91.91 17	94.89 38	87.85 10	92.51 24	93.87 51	88.20 23	93.24 42	94.02 94	90.15 16	95.67 38	86.82 38	97.34 76	92.19 197

APD-MVS_3200maxsize		92.05 12	92.24 12	91.48 25	93.02 80	85.17 39	92.47 26	95.05 14	87.65 27	93.21 43	94.39 77	90.09 17	95.08 66	86.67 40	97.60 66	94.18 100

testf1		89.30 60	89.12 64	89.84 52	88.67 196	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 192	96.10 119	94.45 87

APD_test2		89.30 60	89.12 64	89.84 52	88.67 196	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 192	96.10 119	94.45 87

Anonymous20231211		88.40 71	89.62 59	84.73 147	90.46 157	65.27 235	88.86 91	93.02 87	87.15 28	93.05 46	97.10 8	82.28 106	92.02 170	76.70 163	97.99 43	96.88 23

MP-MVS-pluss		90.81 30	91.08 37	89.99 50	95.97 14	79.88 75	88.13 102	94.51 18	75.79 148	92.94 47	94.96 51	88.36 30	95.01 68	90.70 3	98.40 20	95.09 66
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 67	89.88 53	86.22 115	91.63 123	77.07 109	89.82 69	93.77 53	78.90 109	92.88 48	92.29 159	86.11 63	90.22 222	86.24 48	97.24 79	91.36 224
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 35	90.60 49	90.35 45	94.36 46	80.98 69	89.16 86	94.05 41	79.03 108	92.87 49	93.74 111	90.60 11	95.21 61	82.87 88	98.76 4	94.87 71
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TDRefinement		93.52 3	93.39 4	93.88 2	95.94 15	90.26 4	95.70 4	96.46 3	90.58 9	92.86 50	96.29 19	88.16 35	94.17 97	86.07 50	98.48 18	97.22 17

SMA-MVS		90.31 38	90.48 50	89.83 54	95.31 30	79.52 81	90.98 47	93.24 74	75.37 157	92.84 51	95.28 44	85.58 67	96.09 8	87.92 15	97.76 57	93.88 113
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 61	77.77 98				92.84 51

v10		86.54 98	87.10 93	84.84 141	88.16 211	63.28 256	86.64 130	92.20 112	75.42 156	92.81 53	94.50 68	74.05 202	94.06 101	83.88 76	96.28 108	97.17 18

dcpmvs_2		84.23 150	85.14 131	81.50 232	88.61 200	61.98 278	82.90 217	93.11 79	68.66 244	92.77 54	92.39 152	78.50 146	87.63 276	76.99 162	92.30 236	94.90 69

v8		86.22 103	86.83 100	84.36 158	87.82 219	62.35 272	86.42 134	91.33 139	76.78 136	92.73 55	94.48 70	73.41 211	93.72 112	83.10 83	95.41 146	97.01 21

nrg030		87.85 82	88.49 75	85.91 122	90.07 166	69.73 189	87.86 106	94.20 30	74.04 168	92.70 56	94.66 60	85.88 66	91.50 181	79.72 123	97.32 77	96.50 29

SteuartSystems-ACMMP		91.16 27	91.36 28	90.55 41	93.91 60	80.97 70	91.49 40	93.48 63	82.82 65	92.60 57	93.97 96	88.19 33	96.29 6	87.61 22	98.20 34	94.39 92
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 51	89.97 52	89.27 63	94.76 40	79.86 76	86.76 127	92.78 96	78.78 111	92.51 58	93.64 115	88.13 36	93.84 109	84.83 68	97.55 69	94.10 105
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HPM-MVS_fast		92.50 8	92.54 9	92.37 6	95.93 16	85.81 33	92.99 12	94.23 27	85.21 40	92.51 58	95.13 48	90.65 9	95.34 55	88.06 13	98.15 37	95.95 41

K. test v3		85.14 123	84.73 138	86.37 109	91.13 143	69.63 191	85.45 152	76.68 335	84.06 50	92.44 60	96.99 10	62.03 287	94.65 77	80.58 115	93.24 218	94.83 76

ACMMP		91.91 14	91.87 19	92.03 12	95.53 27	85.91 28	93.35 11	94.16 32	82.52 67	92.39 61	94.14 89	89.15 25	95.62 39	87.35 29	98.24 30	94.56 81
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 39	90.80 46	88.68 76	92.86 86	77.09 108	91.19 44	95.74 6	81.38 78	92.28 62	93.80 106	86.89 52	94.64 78	85.52 59	97.51 73	94.30 96

COLMAP_ROB	83.01 3	91.97 13	91.95 14	92.04 11	93.68 65	86.15 24	93.37 10	95.10 13	90.28 10	92.11 63	95.03 50	89.75 20	94.93 70	79.95 120	98.27 26	95.04 67
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 47	89.84 54	90.41 43	94.91 37	84.50 48	89.49 81	93.98 43	79.68 97	92.09 64	93.89 104	83.80 81	93.10 140	82.67 92	98.04 39	93.64 128

TranMVSNet+NR-MVSNet		87.86 81	88.76 74	85.18 137	94.02 58	64.13 246	84.38 175	91.29 140	84.88 44	92.06 65	93.84 105	86.45 58	93.73 111	73.22 208	98.66 11	97.69 9

MTAPA		91.52 18	91.60 22	91.29 30	96.59 4	86.29 21	92.02 33	91.81 127	84.07 49	92.00 66	94.40 76	86.63 54	95.28 58	88.59 10	98.31 24	92.30 189

ACMMP_NAP		90.65 32	91.07 39	89.42 61	95.93 16	79.54 80	89.95 66	93.68 58	77.65 127	91.97 67	94.89 53	88.38 29	95.45 51	89.27 5	97.87 53	93.27 143

FC-MVSNet-test		85.93 110	87.05 95	82.58 212	92.25 101	56.44 336	85.75 146	93.09 81	77.33 131	91.94 68	94.65 61	74.78 193	93.41 130	75.11 184	98.58 14	97.88 7

lessismore_v0				85.95 121	91.10 144	70.99 176		70.91 379		91.79 69	94.42 74	61.76 288	92.93 146	79.52 128	93.03 223	93.93 110

HPM-MVS		92.13 11	92.20 13	91.91 17	95.58 26	84.67 46	93.51 8	94.85 15	82.88 64	91.77 70	93.94 102	90.55 12	95.73 35	88.50 11	98.23 31	95.33 56
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PGM-MVS		91.20 26	90.95 43	91.93 15	95.67 23	85.85 31	90.00 62	93.90 48	80.32 89	91.74 71	94.41 75	88.17 34	95.98 13	86.37 43	97.99 43	93.96 109

mPP-MVS		91.69 15	91.47 26	92.37 6	96.04 13	88.48 8	92.72 18	92.60 102	83.09 61	91.54 72	94.25 83	87.67 44	95.51 47	87.21 33	98.11 38	93.12 151

HFP-MVS		91.30 23	91.39 27	91.02 33	95.43 29	84.66 47	92.58 22	93.29 72	81.99 70	91.47 73	93.96 99	88.35 31	95.56 42	87.74 18	97.74 59	92.85 161

ACMMPR		91.49 19	91.35 30	91.92 16	95.74 20	85.88 30	92.58 22	93.25 73	81.99 70	91.40 74	94.17 88	87.51 45	95.87 20	87.74 18	97.76 57	93.99 107

GST-MVS		90.96 29	91.01 40	90.82 37	95.45 28	82.73 59	91.75 38	93.74 54	80.98 83	91.38 75	93.80 106	87.20 49	95.80 28	87.10 36	97.69 61	93.93 110

test_fmvsmvis_n_1920		85.22 120	85.36 129	84.81 143	85.80 273	76.13 122	85.15 159	92.32 109	61.40 318	91.33 76	90.85 208	83.76 83	86.16 302	84.31 72	93.28 217	92.15 199

ANet_high		83.17 177	85.68 122	75.65 316	81.24 342	45.26 402	79.94 267	92.91 91	83.83 51	91.33 76	96.88 13	80.25 134	85.92 306	68.89 251	95.89 131	95.76 43

ZNCC-MVS		91.26 24	91.34 31	91.01 34	95.73 21	83.05 56	92.18 31	94.22 29	80.14 92	91.29 78	93.97 96	87.93 40	95.87 20	88.65 9	97.96 48	94.12 104

casdiffmvs_mvg		86.72 95	87.51 86	84.36 158	87.09 242	65.22 236	84.16 177	94.23 27	77.89 123	91.28 79	93.66 114	84.35 76	92.71 150	80.07 117	94.87 172	95.16 64
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 56	89.63 58	89.26 64	92.57 91	81.34 68	90.19 61	93.08 82	80.87 85	91.13 80	93.19 122	86.22 62	95.97 14	82.23 98	97.18 81	90.45 251
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 62		91.84 119		88.80 93	95.32 12	75.14 159	91.07 81	92.89 136	87.27 47	93.78 110	83.69 79	97.55 69

CP-MVS		91.67 16	91.58 23	91.96 14	95.29 31	87.62 13	93.38 9	93.36 65	83.16 60	91.06 82	94.00 95	88.26 32	95.71 37	87.28 32	98.39 21	92.55 175

FIs		85.35 119	86.27 107	82.60 211	91.86 116	57.31 329	85.10 160	93.05 83	75.83 147	91.02 83	93.97 96	73.57 207	92.91 148	73.97 196	98.02 42	97.58 12

UniMVSNet_NR-MVSNet		86.84 93	87.06 94	86.17 118	92.86 86	67.02 219	82.55 226	91.56 130	83.08 62	90.92 84	91.82 173	78.25 149	93.99 102	74.16 190	98.35 22	97.49 13

DU-MVS		86.80 94	86.99 96	86.21 116	93.24 76	67.02 219	83.16 209	92.21 111	81.73 74	90.92 84	91.97 166	77.20 163	93.99 102	74.16 190	98.35 22	97.61 10

tt0805		88.09 77	89.79 55	82.98 200	93.26 75	63.94 249	91.10 45	89.64 191	85.07 41	90.91 86	91.09 196	89.16 24	91.87 175	82.03 99	95.87 132	93.13 149

V42		83.47 172	83.37 169	83.75 176	83.16 324	63.33 255	81.31 248	90.23 177	69.51 234	90.91 86	90.81 210	74.16 200	92.29 164	80.06 118	90.22 286	95.62 49

region2R		91.44 22	91.30 34	91.87 19	95.75 19	85.90 29	92.63 21	93.30 71	81.91 72	90.88 88	94.21 84	87.75 41	95.87 20	87.60 23	97.71 60	93.83 116

APD_test1		88.40 71	87.91 80	89.88 51	89.50 175	86.65 20	89.98 65	91.91 122	84.26 47	90.87 89	93.92 103	82.18 108	89.29 250	73.75 200	94.81 173	93.70 124

WR-MVS		83.56 169	84.40 152	81.06 240	93.43 70	54.88 349	78.67 289	85.02 269	81.24 79	90.74 90	91.56 182	72.85 219	91.08 195	68.00 261	98.04 39	97.23 16

v1240		84.30 146	84.51 149	83.65 179	87.65 225	61.26 285	82.85 218	91.54 131	67.94 255	90.68 91	90.65 217	71.71 235	93.64 114	82.84 89	94.78 174	96.07 36

ZD-MVS					92.22 103	80.48 71		91.85 123	71.22 217	90.38 92	92.98 131	86.06 64	96.11 7	81.99 101	96.75 92

MIMVSNet1		83.63 166	84.59 144	80.74 244	94.06 57	62.77 263	82.72 220	84.53 278	77.57 129	90.34 93	95.92 28	76.88 175	85.83 311	61.88 312	97.42 74	93.62 129

LS3D		90.60 34	90.34 51	91.38 28	89.03 185	84.23 49	93.58 6	94.68 17	90.65 8	90.33 94	93.95 101	84.50 74	95.37 54	80.87 110	95.50 145	94.53 84

KD-MVS_self_test		81.93 202	83.14 175	78.30 280	84.75 290	52.75 363	80.37 262	89.42 197	70.24 229	90.26 95	93.39 119	74.55 198	86.77 290	68.61 256	96.64 94	95.38 54

PMVS	80.48 6	90.08 41	90.66 48	88.34 81	96.71 3	92.97 2	90.31 59	89.57 194	88.51 21	90.11 96	95.12 49	90.98 6	88.92 254	77.55 153	97.07 83	83.13 362
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 340	90.06 97	91.33 187	80.66 130	93.03 143	75.78 175	95.94 128	92.48 178

v1921920		84.23 150	84.37 153	83.79 174	87.64 226	61.71 279	82.91 216	91.20 143	67.94 255	90.06 97	90.34 223	72.04 231	93.59 120	82.32 96	94.91 167	96.07 36

ITE_SJBPF				90.11 49	90.72 152	84.97 41		90.30 173	81.56 76	90.02 99	91.20 193	82.40 99	90.81 207	73.58 203	94.66 179	94.56 81

XVS		91.54 17	91.36 28	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	94.03 93	86.57 55	95.80 28	87.35 29	97.62 64	94.20 97

X-MVStestdata		85.04 127	82.70 182	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	16.05 431	86.57 55	95.80 28	87.35 29	97.62 64	94.20 97

v1192		84.57 137	84.69 143	84.21 164	87.75 221	62.88 260	83.02 212	91.43 134	69.08 238	89.98 102	90.89 205	72.70 222	93.62 118	82.41 95	94.97 166	96.13 34

Anonymous20240529		86.20 104	87.13 92	83.42 188	90.19 162	64.55 243	84.55 170	90.71 155	85.85 36	89.94 103	95.24 46	82.13 109	90.40 218	69.19 247	96.40 105	95.31 57

pmmvs6		86.52 99	88.06 79	81.90 222	92.22 103	62.28 273	84.66 168	89.15 199	83.54 57	89.85 104	97.32 5	88.08 38	86.80 289	70.43 234	97.30 78	96.62 26

v144192		84.24 149	84.41 151	83.71 178	87.59 227	61.57 280	82.95 215	91.03 147	67.82 258	89.80 105	90.49 220	73.28 215	93.51 125	81.88 104	94.89 169	96.04 38

v1144		84.54 140	84.72 140	84.00 168	87.67 224	62.55 267	82.97 214	90.93 151	70.32 227	89.80 105	90.99 199	73.50 208	93.48 126	81.69 105	94.65 180	95.97 39

DeepC-MVS	82.31 4	89.15 64	89.08 66	89.37 62	93.64 66	79.07 83	88.54 98	94.20 30	73.53 176	89.71 107	94.82 56	85.09 68	95.77 34	84.17 74	98.03 41	93.26 144
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 79	86.93 98	91.22 31	90.08 164	89.30 5	89.68 73	91.11 145	79.26 104	89.68 108	94.81 59	82.44 97	87.74 274	76.54 165	88.74 308	96.61 27

IU-MVS					94.18 50	72.64 148		90.82 153	56.98 357	89.67 109				85.78 57	97.92 49	93.28 142

FMVSNet1		84.55 139	85.45 126	81.85 224	90.27 161	61.05 288	86.83 124	88.27 214	78.57 115	89.66 110	95.64 34	75.43 183	90.68 211	69.09 248	95.33 149	93.82 117

IterMVS-LS		84.73 134	84.98 134	83.96 170	87.35 232	63.66 250	83.25 205	89.88 186	76.06 140	89.62 111	92.37 156	73.40 213	92.52 155	78.16 144	94.77 176	95.69 46
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 70	89.01 67	87.36 93	91.30 136	77.50 101	87.55 109	92.97 90	87.95 25	89.62 111	92.87 137	84.56 73	93.89 106	77.65 151	96.62 95	90.70 242

UniMVSNet (Re)		86.87 91	86.98 97	86.55 106	93.11 79	68.48 205	83.80 190	92.87 92	80.37 87	89.61 113	91.81 174	77.72 156	94.18 95	75.00 185	98.53 16	96.99 22

IS-MVSNet		86.66 97	86.82 101	86.17 118	92.05 109	66.87 222	91.21 43	88.64 205	86.30 33	89.60 114	92.59 146	69.22 249	94.91 71	73.89 197	97.89 52	96.72 24

v2v482		84.09 153	84.24 156	83.62 180	87.13 238	61.40 282	82.71 221	89.71 189	72.19 206	89.55 115	91.41 185	70.70 241	93.20 135	81.02 108	93.76 204	96.25 32

Baseline_NR-MVSNet		84.00 157	85.90 115	78.29 281	91.47 134	53.44 359	82.29 234	87.00 239	79.06 107	89.55 115	95.72 32	77.20 163	86.14 303	72.30 219	98.51 17	95.28 58

CSCG		86.26 101	86.47 104	85.60 130	90.87 149	74.26 132	87.98 104	91.85 123	80.35 88	89.54 117	88.01 263	79.09 142	92.13 166	75.51 178	95.06 161	90.41 252

ambc				82.98 200	90.55 156	64.86 239	88.20 100	89.15 199		89.40 118	93.96 99	71.67 236	91.38 188	78.83 134	96.55 97	92.71 167

DeepPCF-MVS	81.24 5	87.28 88	86.21 109	90.49 42	91.48 133	84.90 42	83.41 200	92.38 107	70.25 228	89.35 119	90.68 214	82.85 92	94.57 81	79.55 126	95.95 127	92.00 205

MVStest1		70.05 338	69.26 341	72.41 343	58.62 434	55.59 343	76.61 321	65.58 402	53.44 374	89.28 120	93.32 120	22.91 434	71.44 389	74.08 194	89.52 296	90.21 259

test_fmvsmconf0.01_n		86.68 96	86.52 103	87.18 94	85.94 271	78.30 89	86.93 120	92.20 112	65.94 273	89.16 121	93.16 124	83.10 89	89.89 235	87.81 17	94.43 186	93.35 138

MSP-MVS		89.08 66	88.16 78	91.83 20	95.76 18	86.14 25	92.75 17	93.90 48	78.43 116	89.16 121	92.25 161	72.03 232	96.36 4	88.21 12	90.93 271	92.98 157
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 63	88.83 72	90.23 47	94.28 47	86.11 26	85.91 141	93.60 61	80.16 91	89.13 123	93.44 118	83.82 80	90.98 198	83.86 77	95.30 153	93.60 131

MDA-MVSNet-bldmvs		77.47 260	76.90 266	79.16 267	79.03 368	64.59 240	66.58 398	75.67 341	73.15 189	88.86 124	88.99 250	66.94 259	81.23 347	64.71 289	88.22 318	91.64 218

EG-PatchMatch MVS		84.08 154	84.11 157	83.98 169	92.22 103	72.61 151	82.20 240	87.02 236	72.63 197	88.86 124	91.02 198	78.52 145	91.11 194	73.41 205	91.09 265	88.21 290

3Dnovator+	83.92 2	89.97 49	89.66 57	90.92 35	91.27 138	81.66 66	91.25 42	94.13 37	88.89 15	88.83 126	94.26 82	77.55 159	95.86 23	84.88 66	95.87 132	95.24 60

fmvsm_s_conf0.5_n_5		84.56 138	84.71 141	84.11 167	87.92 216	72.09 162	84.80 161	88.64 205	64.43 293	88.77 127	91.78 176	78.07 150	87.95 271	85.85 56	92.18 243	92.30 189

EI-MVSNet-UG-set		85.04 127	84.44 150	86.85 101	83.87 308	72.52 154	83.82 188	85.15 265	80.27 90	88.75 128	85.45 312	79.95 138	91.90 173	81.92 103	90.80 277	96.13 34

EI-MVSNet-Vis-set		85.12 125	84.53 148	86.88 100	84.01 304	72.76 145	83.91 186	85.18 264	80.44 86	88.75 128	85.49 310	80.08 136	91.92 172	82.02 100	90.85 276	95.97 39

balanced_conf03		84.80 132	85.40 127	83.00 199	88.95 188	61.44 281	90.42 58	92.37 108	71.48 213	88.72 130	93.13 125	70.16 245	95.15 63	79.26 131	94.11 195	92.41 182

OMC-MVS		88.19 74	87.52 85	90.19 48	91.94 114	81.68 65	87.49 112	93.17 76	76.02 142	88.64 131	91.22 191	84.24 78	93.37 131	77.97 149	97.03 84	95.52 51

RRT-MVS		82.97 180	83.44 166	81.57 231	85.06 284	58.04 323	87.20 114	90.37 167	77.88 124	88.59 132	93.70 113	63.17 281	93.05 142	76.49 166	88.47 310	93.62 129

test_fmvsmconf0.1_n		86.18 106	85.88 116	87.08 96	85.26 281	78.25 90	85.82 145	91.82 125	65.33 287	88.55 133	92.35 158	82.62 96	89.80 237	86.87 37	94.32 189	93.18 148

UA-Net		91.49 19	91.53 24	91.39 27	94.98 35	82.95 58	93.52 7	92.79 95	88.22 22	88.53 134	97.64 3	83.45 86	94.55 83	86.02 54	98.60 13	96.67 25

MP-MVS		91.14 28	90.91 44	91.83 20	96.18 11	86.88 17	92.20 30	93.03 86	82.59 66	88.52 135	94.37 78	86.74 53	95.41 53	86.32 44	98.21 32	93.19 147
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
sasdasda		85.50 114	86.14 110	83.58 182	87.97 213	67.13 216	87.55 109	94.32 21	73.44 179	88.47 136	87.54 275	86.45 58	91.06 196	75.76 176	93.76 204	92.54 176

canonicalmvs		85.50 114	86.14 110	83.58 182	87.97 213	67.13 216	87.55 109	94.32 21	73.44 179	88.47 136	87.54 275	86.45 58	91.06 196	75.76 176	93.76 204	92.54 176

NR-MVSNet		86.00 108	86.22 108	85.34 135	93.24 76	64.56 242	82.21 238	90.46 163	80.99 82	88.42 138	91.97 166	77.56 158	93.85 107	72.46 218	98.65 12	97.61 10

alignmvs		83.94 159	83.98 160	83.80 173	87.80 220	67.88 212	84.54 172	91.42 136	73.27 187	88.41 139	87.96 264	72.33 225	90.83 206	76.02 174	94.11 195	92.69 168

TransMVSNet (Re)		84.02 156	85.74 121	78.85 269	91.00 146	55.20 348	82.29 234	87.26 226	79.65 98	88.38 140	95.52 37	83.00 90	86.88 287	67.97 262	96.60 96	94.45 87

PM-MVS		80.20 232	79.00 241	83.78 175	88.17 210	86.66 19	81.31 248	66.81 399	69.64 233	88.33 141	90.19 228	64.58 270	83.63 333	71.99 221	90.03 289	81.06 390

fmvsm_s_conf0.5_n_3		86.19 105	87.27 90	82.95 202	86.91 246	70.38 182	85.31 155	92.61 101	75.59 152	88.32 142	92.87 137	82.22 107	88.63 261	88.80 8	92.82 229	89.83 265

tttt0517		81.07 213	79.58 236	85.52 132	88.99 187	66.45 226	87.03 119	75.51 343	73.76 172	88.32 142	90.20 227	37.96 405	94.16 99	79.36 130	95.13 157	95.93 42

casdiffmvs		85.21 121	85.85 117	83.31 191	86.17 265	62.77 263	83.03 211	93.93 46	74.69 163	88.21 144	92.68 145	82.29 105	91.89 174	77.87 150	93.75 207	95.27 59
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		71.42 324	70.67 326	73.64 330	69.66 422	70.46 180	66.97 397	89.73 187	42.68 419	88.20 145	83.04 341	43.77 389	60.07 420	65.35 284	86.66 338	90.39 253

SSC-MVS		77.55 259	81.64 199	65.29 388	90.46 157	20.33 435	73.56 354	68.28 389	85.44 37	88.18 146	94.64 64	70.93 239	81.33 346	71.25 223	92.03 245	94.20 97

MVSMamba_PlusPlus		87.53 86	88.86 71	83.54 186	92.03 110	62.26 274	91.49 40	92.62 100	88.07 24	88.07 147	96.17 23	72.24 227	95.79 31	84.85 67	94.16 194	92.58 173

MGCFI-Net		85.04 127	85.95 113	82.31 218	87.52 228	63.59 252	86.23 138	93.96 44	73.46 177	88.07 147	87.83 270	86.46 57	90.87 205	76.17 171	93.89 201	92.47 180

v148		82.31 189	82.48 188	81.81 227	85.59 275	59.66 304	81.47 247	86.02 251	72.85 192	88.05 149	90.65 217	70.73 240	90.91 202	75.15 183	91.79 251	94.87 71

AllTest		87.97 80	87.40 89	89.68 55	91.59 124	83.40 52	89.50 80	95.44 10	79.47 99	88.00 150	93.03 129	82.66 94	91.47 182	70.81 226	96.14 116	94.16 101

TestCases				89.68 55	91.59 124	83.40 52		95.44 10	79.47 99	88.00 150	93.03 129	82.66 94	91.47 182	70.81 226	96.14 116	94.16 101

fmvsm_s_conf0.1_n_2		83.82 161	83.49 165	84.84 141	85.99 270	70.19 185	80.93 255	87.58 222	67.26 265	87.94 152	92.37 156	71.40 237	88.01 269	86.03 51	91.87 250	96.31 31

pm-mvs1		83.69 164	84.95 136	79.91 256	90.04 168	59.66 304	82.43 230	87.44 223	75.52 154	87.85 153	95.26 45	81.25 123	85.65 313	68.74 254	96.04 121	94.42 90

PCF-MVS	74.62 15	82.15 196	80.92 216	85.84 125	89.43 177	72.30 158	80.53 260	91.82 125	57.36 353	87.81 154	89.92 235	77.67 157	93.63 115	58.69 330	95.08 160	91.58 220
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 167	83.29 170	84.62 150	85.43 278	70.18 186	80.61 259	87.24 227	67.14 266	87.79 155	91.87 168	71.79 234	87.98 270	86.00 55	91.77 253	95.71 45

mvs5depth		83.82 161	84.54 147	81.68 229	82.23 330	68.65 203	86.89 121	89.90 185	80.02 94	87.74 156	97.86 2	64.19 274	82.02 342	76.37 167	95.63 143	94.35 93

test_fmvsmconf_n		85.88 111	85.51 125	86.99 98	84.77 289	78.21 91	85.40 154	91.39 137	65.32 288	87.72 157	91.81 174	82.33 101	89.78 238	86.68 39	94.20 192	92.99 156

FMVSNet2		81.31 210	81.61 201	80.41 250	86.38 255	58.75 318	83.93 185	86.58 242	72.43 198	87.65 158	92.98 131	63.78 277	90.22 222	66.86 265	93.92 200	92.27 193

GeoE		85.45 117	85.81 118	84.37 156	90.08 164	67.07 218	85.86 144	91.39 137	72.33 203	87.59 159	90.25 226	84.85 71	92.37 160	78.00 147	91.94 249	93.66 125

VPA-MVSNet		83.47 172	84.73 138	79.69 260	90.29 160	57.52 328	81.30 250	88.69 204	76.29 138	87.58 160	94.44 71	80.60 131	87.20 281	66.60 270	96.82 90	94.34 94

CPTT-MVS		89.39 58	88.98 69	90.63 40	95.09 33	86.95 16	92.09 32	92.30 110	79.74 96	87.50 161	92.38 153	81.42 121	93.28 133	83.07 84	97.24 79	91.67 217

VDDNet		84.35 144	85.39 128	81.25 235	95.13 32	59.32 307	85.42 153	81.11 306	86.41 32	87.41 162	96.21 22	73.61 206	90.61 214	66.33 272	96.85 87	93.81 120

c3_l		81.64 206	81.59 202	81.79 228	80.86 348	59.15 311	78.61 290	90.18 179	68.36 247	87.20 163	87.11 286	69.39 247	91.62 179	78.16 144	94.43 186	94.60 80

VDD-MVS		84.23 150	84.58 145	83.20 194	91.17 142	65.16 238	83.25 205	84.97 272	79.79 95	87.18 164	94.27 79	74.77 194	90.89 203	69.24 244	96.54 98	93.55 136

MSLP-MVS++		85.00 130	86.03 112	81.90 222	91.84 119	71.56 172	86.75 128	93.02 87	75.95 145	87.12 165	89.39 242	77.98 151	89.40 249	77.46 154	94.78 174	84.75 334

baseline		85.20 122	85.93 114	83.02 198	86.30 260	62.37 271	84.55 170	93.96 44	74.48 165	87.12 165	92.03 165	82.30 103	91.94 171	78.39 137	94.21 191	94.74 78

YYNet1		70.06 337	70.44 330	68.90 365	73.76 405	53.42 360	58.99 416	67.20 395	58.42 343	87.10 167	85.39 314	59.82 301	67.32 405	59.79 326	83.50 374	85.96 319

MDA-MVSNet_test_wron		70.05 338	70.44 330	68.88 366	73.84 404	53.47 358	58.93 417	67.28 394	58.43 342	87.09 168	85.40 313	59.80 302	67.25 406	59.66 327	83.54 373	85.92 321

test_fmvs3		75.72 282	75.20 283	77.27 297	75.01 401	69.47 192	78.93 283	84.88 273	46.67 403	87.08 169	87.84 269	50.44 353	71.62 387	77.42 157	88.53 309	90.72 240

CNVR-MVS		87.81 83	87.68 83	88.21 83	92.87 84	77.30 107	85.25 156	91.23 142	77.31 132	87.07 170	91.47 184	82.94 91	94.71 75	84.67 69	96.27 110	92.62 171

EPP-MVSNet		85.47 116	85.04 133	86.77 103	91.52 132	69.37 193	91.63 39	87.98 219	81.51 77	87.05 171	91.83 172	66.18 264	95.29 56	70.75 229	96.89 86	95.64 48

TinyColmap		81.25 211	82.34 190	77.99 287	85.33 279	60.68 295	82.32 233	88.33 212	71.26 216	86.97 172	92.22 163	77.10 166	86.98 285	62.37 306	95.17 156	86.31 317

eth_miper_zixun_eth		80.84 216	80.22 228	82.71 209	81.41 340	60.98 291	77.81 299	90.14 180	67.31 264	86.95 173	87.24 283	64.26 272	92.31 162	75.23 182	91.61 256	94.85 75

Anonymous20240521		80.18 233	81.25 210	76.95 300	83.15 325	60.84 293	82.46 229	85.99 252	68.76 242	86.78 174	93.73 112	59.13 306	77.44 368	73.71 201	97.55 69	92.56 174

Patchmatch-RL test		74.48 295	73.68 295	76.89 303	84.83 287	66.54 224	72.29 362	69.16 388	57.70 349	86.76 175	86.33 296	45.79 374	82.59 337	69.63 241	90.65 283	81.54 381

XVG-OURS-SEG-HR		89.59 55	89.37 61	90.28 46	94.47 43	85.95 27	86.84 123	93.91 47	80.07 93	86.75 176	93.26 121	93.64 2	90.93 200	84.60 70	90.75 278	93.97 108

h-mvs33		84.25 148	82.76 181	88.72 73	91.82 121	82.60 60	84.00 182	84.98 271	71.27 214	86.70 177	90.55 219	63.04 284	93.92 105	78.26 142	94.20 192	89.63 267

hse-mvs2		83.47 172	81.81 196	88.47 77	91.03 145	82.27 61	82.61 222	83.69 284	71.27 214	86.70 177	86.05 302	63.04 284	92.41 158	78.26 142	93.62 212	90.71 241

HPM-MVS++		88.93 68	88.45 76	90.38 44	94.92 36	85.85 31	89.70 71	91.27 141	78.20 119	86.69 179	92.28 160	80.36 133	95.06 67	86.17 49	96.49 100	90.22 255

TSAR-MVS + MP.		88.14 75	87.82 82	89.09 67	95.72 22	76.74 112	92.49 25	91.19 144	67.85 257	86.63 180	94.84 55	79.58 140	95.96 15	87.62 21	94.50 182	94.56 81
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 184	82.42 189	83.20 194	83.25 321	63.66 250	83.50 198	85.07 266	76.06 140	86.55 181	85.10 318	73.41 211	90.25 219	78.15 146	90.67 280	95.68 47

HQP_MVS		87.75 84	87.43 88	88.70 75	93.45 68	76.42 116	89.45 82	93.61 59	79.44 101	86.55 181	92.95 134	74.84 191	95.22 59	80.78 112	95.83 134	94.46 85

plane_prior3						76.85 111			77.79 126	86.55 181

BH-untuned		80.96 215	80.99 214	80.84 243	88.55 202	68.23 206	80.33 263	88.46 207	72.79 195	86.55 181	86.76 290	74.72 195	91.77 178	61.79 313	88.99 303	82.52 370

MVSTER		77.09 264	75.70 277	81.25 235	75.27 398	61.08 287	77.49 307	85.07 266	60.78 328	86.55 181	88.68 254	43.14 394	90.25 219	73.69 202	90.67 280	92.42 181

旧先验2							81.73 243		56.88 358	86.54 186			84.90 319	72.81 215

IterMVS-SCA-FT		80.64 220	79.41 237	84.34 160	83.93 306	69.66 190	76.28 326	81.09 307	72.43 198	86.47 187	90.19 228	60.46 294	93.15 138	77.45 155	86.39 342	90.22 255

WB-MVS		76.06 278	80.01 234	64.19 391	89.96 170	20.58 434	72.18 363	68.19 390	83.21 59	86.46 188	93.49 117	70.19 244	78.97 362	65.96 274	90.46 285	93.02 154

test_fmvsm_n_1920		83.60 168	82.89 179	85.74 127	85.22 282	77.74 99	84.12 179	90.48 162	59.87 337	86.45 189	91.12 195	75.65 181	85.89 309	82.28 97	90.87 274	93.58 132

fmvsm_s_conf0.5_n_4		84.38 142	84.27 155	84.74 146	87.25 234	70.84 177	83.55 196	88.45 208	68.64 245	86.29 190	91.31 189	74.97 189	88.42 263	87.87 16	90.07 288	94.95 68

DIV-MVS_self_test		80.43 223	80.23 226	81.02 241	79.99 356	59.25 308	77.07 312	87.02 236	67.38 261	86.19 191	89.22 245	63.09 282	90.16 224	76.32 168	95.80 136	93.66 125

CDPH-MVS		86.17 107	85.54 124	88.05 86	92.25 101	75.45 125	83.85 187	92.01 117	65.91 275	86.19 191	91.75 178	83.77 82	94.98 69	77.43 156	96.71 93	93.73 123

cl____		80.42 224	80.23 226	81.02 241	79.99 356	59.25 308	77.07 312	87.02 236	67.37 262	86.18 193	89.21 246	63.08 283	90.16 224	76.31 169	95.80 136	93.65 127

MVS_111021_LR		84.28 147	83.76 163	85.83 126	89.23 182	83.07 55	80.99 254	83.56 286	72.71 196	86.07 194	89.07 249	81.75 118	86.19 301	77.11 160	93.36 213	88.24 289

GBi-Net		82.02 199	82.07 191	81.85 224	86.38 255	61.05 288	86.83 124	88.27 214	72.43 198	86.00 195	95.64 34	63.78 277	90.68 211	65.95 275	93.34 214	93.82 117

test1		82.02 199	82.07 191	81.85 224	86.38 255	61.05 288	86.83 124	88.27 214	72.43 198	86.00 195	95.64 34	63.78 277	90.68 211	65.95 275	93.34 214	93.82 117

FMVSNet3		78.80 246	78.55 249	79.57 262	82.89 328	56.89 334	81.76 242	85.77 254	69.04 239	86.00 195	90.44 221	51.75 346	90.09 230	65.95 275	93.34 214	91.72 214

miper_ehance_all_eth		80.34 227	80.04 233	81.24 237	79.82 359	58.95 313	77.66 301	89.66 190	65.75 280	85.99 198	85.11 317	68.29 254	91.42 186	76.03 173	92.03 245	93.33 139

tfpnnormal		81.79 205	82.95 178	78.31 279	88.93 189	55.40 344	80.83 258	82.85 292	76.81 135	85.90 199	94.14 89	74.58 197	86.51 294	66.82 268	95.68 142	93.01 155

TAPA-MVS	77.73 12	85.71 113	84.83 137	88.37 80	88.78 195	79.72 77	87.15 117	93.50 62	69.17 236	85.80 200	89.56 240	80.76 128	92.13 166	73.21 213	95.51 144	93.25 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 158	82.69 183	87.72 89	89.27 181	81.45 67	83.72 192	81.58 304	74.73 162	85.66 201	86.06 301	72.56 224	92.69 152	75.44 180	95.21 154	89.01 283

EU-MVSNet		75.12 287	74.43 290	77.18 298	83.11 326	59.48 306	85.71 148	82.43 296	39.76 423	85.64 202	88.76 252	44.71 387	87.88 273	73.86 198	85.88 348	84.16 345

MonoMVSNet		76.66 270	77.26 262	74.86 322	79.86 358	54.34 352	86.26 137	86.08 248	71.08 219	85.59 203	88.68 254	53.95 336	85.93 305	63.86 296	80.02 394	84.32 340

LF4IMVS		82.75 183	81.93 194	85.19 136	82.08 331	80.15 74	85.53 150	88.76 203	68.01 252	85.58 204	87.75 271	71.80 233	86.85 288	74.02 195	93.87 202	88.58 286

Patchmtry		76.56 273	77.46 258	73.83 328	79.37 365	46.60 395	82.41 231	76.90 332	73.81 171	85.56 205	92.38 153	48.07 360	83.98 330	63.36 301	95.31 152	90.92 234

MVS_111021_HR		84.63 135	84.34 154	85.49 134	90.18 163	75.86 123	79.23 281	87.13 231	73.35 181	85.56 205	89.34 243	83.60 85	90.50 216	76.64 164	94.05 198	90.09 261

testdata				79.54 263	92.87 84	72.34 157		80.14 313	59.91 336	85.47 207	91.75 178	67.96 256	85.24 315	68.57 258	92.18 243	81.06 390

mvsmamba		80.30 229	78.87 242	84.58 152	88.12 212	67.55 214	92.35 29	84.88 273	63.15 299	85.33 208	90.91 204	50.71 350	95.20 62	66.36 271	87.98 320	90.99 231

test1111		78.53 250	78.85 244	77.56 293	92.22 103	47.49 391	82.61 222	69.24 387	72.43 198	85.28 209	94.20 85	51.91 344	90.07 231	65.36 283	96.45 103	95.11 65

thisisatest0530		79.07 241	77.33 261	84.26 163	87.13 238	64.58 241	83.66 194	75.95 338	68.86 241	85.22 210	87.36 280	38.10 402	93.57 123	75.47 179	94.28 190	94.62 79

BP-MVS1		82.81 181	81.67 198	86.23 113	87.88 218	68.53 204	86.06 140	84.36 279	75.65 150	85.14 211	90.19 228	45.84 373	94.42 86	85.18 62	94.72 178	95.75 44

EC-MVSNet		88.01 78	88.32 77	87.09 95	89.28 180	72.03 163	90.31 59	96.31 4	80.88 84	85.12 212	89.67 239	84.47 75	95.46 50	82.56 93	96.26 111	93.77 122

CLD-MVS		83.18 176	82.64 184	84.79 144	89.05 184	67.82 213	77.93 297	92.52 103	68.33 248	85.07 213	81.54 360	82.06 110	92.96 144	69.35 243	97.91 51	93.57 133
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
fmvsm_s_conf0.1_n_a		82.58 186	81.93 194	84.50 153	87.68 223	73.35 138	86.14 139	77.70 324	61.64 316	85.02 214	91.62 180	77.75 154	86.24 298	82.79 90	87.07 331	93.91 112

FA-MVS(test-final)		83.13 178	83.02 177	83.43 187	86.16 267	66.08 229	88.00 103	88.36 211	75.55 153	85.02 214	92.75 143	65.12 269	92.50 156	74.94 186	91.30 262	91.72 214

DeepC-MVS_fast	80.27 8	86.23 102	85.65 123	87.96 87	91.30 136	76.92 110	87.19 115	91.99 118	70.56 223	84.96 216	90.69 213	80.01 137	95.14 64	78.37 138	95.78 138	91.82 210
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	84.80 132	84.71 141	85.06 139	86.36 258	74.71 128	88.77 94	90.00 183	75.65 150	84.96 216	93.17 123	74.06 201	91.19 191	78.28 141	91.09 265	89.29 275

QAPM		82.59 185	82.59 186	82.58 212	86.44 253	66.69 223	89.94 67	90.36 168	67.97 254	84.94 218	92.58 148	72.71 221	92.18 165	70.63 232	87.73 324	88.85 284

fmvsm_l_conf0.5_n_3		85.11 126	84.96 135	85.56 131	87.49 230	75.69 124	84.71 166	90.61 160	67.64 259	84.88 219	92.05 164	82.30 103	88.36 265	83.84 78	91.10 264	92.62 171

VPNet		80.25 230	81.68 197	75.94 314	92.46 95	47.98 389	76.70 317	81.67 302	73.45 178	84.87 220	92.82 139	74.66 196	86.51 294	61.66 315	96.85 87	93.33 139

NCCC		87.36 87	86.87 99	88.83 70	92.32 100	78.84 86	86.58 131	91.09 146	78.77 112	84.85 221	90.89 205	80.85 127	95.29 56	81.14 107	95.32 150	92.34 187

PHI-MVS		86.38 100	85.81 118	88.08 84	88.44 205	77.34 105	89.35 85	93.05 83	73.15 189	84.76 222	87.70 272	78.87 144	94.18 95	80.67 114	96.29 107	92.73 164

pmmvs-eth3d		78.42 252	77.04 264	82.57 214	87.44 231	74.41 131	80.86 257	79.67 315	55.68 362	84.69 223	90.31 225	60.91 292	85.42 314	62.20 308	91.59 257	87.88 299

test_prior2							83.37 201		75.43 155	84.58 224	91.57 181	81.92 115		79.54 127	96.97 85

fmvsm_s_conf0.5_n_a		82.21 192	81.51 206	84.32 161	86.56 251	73.35 138	85.46 151	77.30 328	61.81 312	84.51 225	90.88 207	77.36 161	86.21 300	82.72 91	86.97 336	93.38 137

TEST9					92.34 98	79.70 78	83.94 183	90.32 170	65.41 286	84.49 226	90.97 200	82.03 111	93.63 115

train_agg		85.98 109	85.28 130	88.07 85	92.34 98	79.70 78	83.94 183	90.32 170	65.79 277	84.49 226	90.97 200	81.93 113	93.63 115	81.21 106	96.54 98	90.88 236

fmvsm_s_conf0.1_n		82.17 194	81.59 202	83.94 172	86.87 249	71.57 171	85.19 158	77.42 327	62.27 310	84.47 228	91.33 187	76.43 177	85.91 307	83.14 81	87.14 329	94.33 95

Gipuma		84.44 141	86.33 106	78.78 270	84.20 301	73.57 136	89.55 77	90.44 164	84.24 48	84.38 229	94.89 53	76.35 180	80.40 354	76.14 172	96.80 91	82.36 372
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 377	65.85 365	59.67 403	66.54 427	62.24 276	57.76 419	70.96 378	40.13 421	84.36 230	82.09 353	46.93 362	51.67 427	61.99 311	81.89 384	65.12 418

test_8					92.09 107	78.87 85	83.82 188	90.31 172	65.79 277	84.36 230	90.96 202	81.93 113	93.44 128

cl22		78.97 242	78.21 254	81.24 237	77.74 373	59.01 312	77.46 308	87.13 231	65.79 277	84.32 232	85.10 318	58.96 308	90.88 204	75.36 181	92.03 245	93.84 115

CS-MVS		88.14 75	87.67 84	89.54 60	89.56 173	79.18 82	90.47 55	94.77 16	79.37 103	84.32 232	89.33 244	83.87 79	94.53 84	82.45 94	94.89 169	94.90 69

agg_prior					91.58 127	77.69 100		90.30 173		84.32 232			93.18 136

Anonymous202405211		80.51 222	81.19 213	78.49 276	88.48 203	57.26 330	76.63 319	82.49 295	81.21 80	84.30 235	92.24 162	67.99 255	86.24 298	62.22 307	95.13 157	91.98 207

LFMVS		80.15 234	80.56 220	78.89 268	89.19 183	55.93 338	85.22 157	73.78 355	82.96 63	84.28 236	92.72 144	57.38 318	90.07 231	63.80 297	95.75 139	90.68 243

Vis-MVSNet		86.86 92	86.58 102	87.72 89	92.09 107	77.43 104	87.35 113	92.09 115	78.87 110	84.27 237	94.05 92	78.35 148	93.65 113	80.54 116	91.58 258	92.08 201
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 251	78.63 248	77.88 289	91.85 117	48.95 385	83.68 193	69.91 383	72.30 204	84.26 238	94.20 85	51.89 345	89.82 236	63.58 298	96.02 122	94.87 71

FE-MVS		79.98 237	78.86 243	83.36 189	86.47 252	66.45 226	89.73 70	84.74 277	72.80 194	84.22 239	91.38 186	44.95 385	93.60 119	63.93 295	91.50 259	90.04 262

ETV-MVS		84.31 145	83.91 162	85.52 132	88.58 201	70.40 181	84.50 174	93.37 64	78.76 113	84.07 240	78.72 385	80.39 132	95.13 65	73.82 199	92.98 225	91.04 230

fmvsm_s_conf0.5_n		81.91 203	81.30 209	83.75 176	86.02 269	71.56 172	84.73 165	77.11 331	62.44 307	84.00 241	90.68 214	76.42 178	85.89 309	83.14 81	87.11 330	93.81 120

MCST-MVS		84.36 143	83.93 161	85.63 129	91.59 124	71.58 170	83.52 197	92.13 114	61.82 311	83.96 242	89.75 238	79.93 139	93.46 127	78.33 140	94.34 188	91.87 209

新几何1				82.95 202	93.96 59	78.56 88		80.24 312	55.45 363	83.93 243	91.08 197	71.19 238	88.33 266	65.84 278	93.07 222	81.95 377

mmtdpeth		85.13 124	85.78 120	83.17 196	84.65 291	74.71 128	85.87 143	90.35 169	77.94 122	83.82 244	96.96 12	77.75 154	80.03 357	78.44 136	96.21 112	94.79 77

fmvsm_l_conf0.5_n		82.06 198	81.54 205	83.60 181	83.94 305	73.90 134	83.35 202	86.10 247	58.97 339	83.80 245	90.36 222	74.23 199	86.94 286	82.90 87	90.22 286	89.94 263

GDP-MVS		82.17 194	80.85 218	86.15 120	88.65 198	68.95 201	85.65 149	93.02 87	68.42 246	83.73 246	89.54 241	45.07 384	94.31 88	79.66 125	93.87 202	95.19 63

BH-RMVSNet		80.53 221	80.22 228	81.49 233	87.19 237	66.21 228	77.79 300	86.23 245	74.21 167	83.69 247	88.50 257	73.25 216	90.75 208	63.18 303	87.90 321	87.52 303

USDC		76.63 271	76.73 268	76.34 310	83.46 313	57.20 331	80.02 266	88.04 218	52.14 385	83.65 248	91.25 190	63.24 280	86.65 292	54.66 358	94.11 195	85.17 329

miper_enhance_ethall		77.83 255	76.93 265	80.51 248	76.15 390	58.01 324	75.47 338	88.82 201	58.05 347	83.59 249	80.69 364	64.41 271	91.20 190	73.16 214	92.03 245	92.33 188

MM		87.64 85	87.15 91	89.09 67	89.51 174	76.39 118	88.68 96	86.76 240	84.54 46	83.58 250	93.78 108	73.36 214	96.48 2	87.98 14	96.21 112	94.41 91

Effi-MVS+-dtu		85.82 112	83.38 168	93.14 4	87.13 238	91.15 3	87.70 108	88.42 209	74.57 164	83.56 251	85.65 306	78.49 147	94.21 93	72.04 220	92.88 227	94.05 106

CNLPA		83.55 170	83.10 176	84.90 140	89.34 179	83.87 50	84.54 172	88.77 202	79.09 106	83.54 252	88.66 256	74.87 190	81.73 344	66.84 267	92.29 238	89.11 277

SDMVSNet		81.90 204	83.17 174	78.10 284	88.81 193	62.45 269	76.08 330	86.05 250	73.67 173	83.41 253	93.04 127	82.35 100	80.65 351	70.06 238	95.03 162	91.21 226

sd_testset		79.95 238	81.39 208	75.64 317	88.81 193	58.07 322	76.16 329	82.81 293	73.67 173	83.41 253	93.04 127	80.96 126	77.65 367	58.62 331	95.03 162	91.21 226

OpenMVS_ROB	70.19 17	77.77 258	77.46 258	78.71 272	84.39 297	61.15 286	81.18 252	82.52 294	62.45 306	83.34 255	87.37 279	66.20 263	88.66 260	64.69 290	85.02 358	86.32 316

thres100view900		75.45 283	75.05 284	76.66 306	87.27 233	51.88 371	81.07 253	73.26 360	75.68 149	83.25 256	86.37 295	45.54 375	88.80 255	51.98 374	90.99 267	89.31 273

miper_lstm_enhance		76.45 275	76.10 273	77.51 294	76.72 384	60.97 292	64.69 402	85.04 268	63.98 296	83.20 257	88.22 260	56.67 322	78.79 364	73.22 208	93.12 221	92.78 163

IterMVS		76.91 266	76.34 271	78.64 273	80.91 346	64.03 247	76.30 325	79.03 318	64.88 291	83.11 258	89.16 247	59.90 300	84.46 323	68.61 256	85.15 356	87.42 304
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 279	75.35 282	77.85 291	87.01 244	51.84 372	80.45 261	73.26 360	75.20 158	83.10 259	86.31 298	45.54 375	89.05 251	55.03 356	92.24 240	92.66 169

mvs_anonymous		78.13 253	78.76 246	76.23 313	79.24 366	50.31 382	78.69 288	84.82 275	61.60 317	83.09 260	92.82 139	73.89 204	87.01 282	68.33 260	86.41 341	91.37 223

fmvsm_l_conf0.5_n_a		81.46 208	80.87 217	83.25 192	83.73 310	73.21 143	83.00 213	85.59 258	58.22 345	82.96 261	90.09 233	72.30 226	86.65 292	81.97 102	89.95 291	89.88 264

test_fmvs2		73.57 304	72.80 306	75.90 315	72.74 415	68.84 202	77.07 312	84.32 281	45.14 409	82.89 262	84.22 330	48.37 358	70.36 391	73.40 206	87.03 333	88.52 287

MVS_Test		82.47 188	83.22 171	80.22 253	82.62 329	57.75 327	82.54 227	91.96 120	71.16 218	82.89 262	92.52 150	77.41 160	90.50 216	80.04 119	87.84 323	92.40 184

reproduce_monomvs		74.09 299	73.23 301	76.65 307	76.52 385	54.54 350	77.50 306	81.40 305	65.85 276	82.86 264	86.67 291	27.38 428	84.53 322	70.24 236	90.66 282	90.89 235

test12				86.57 105	90.74 151	72.63 150		90.69 156		82.76 265		79.20 141	94.80 73		95.32 150	92.27 193

原ACMM1				84.60 151	92.81 89	74.01 133		91.50 132	62.59 302	82.73 266	90.67 216	76.53 176	94.25 91	69.24 244	95.69 141	85.55 325

test_yl		78.71 248	78.51 250	79.32 265	84.32 298	58.84 315	78.38 291	85.33 261	75.99 143	82.49 267	86.57 292	58.01 312	90.02 233	62.74 304	92.73 231	89.10 278

DCV-MVSNet		78.71 248	78.51 250	79.32 265	84.32 298	58.84 315	78.38 291	85.33 261	75.99 143	82.49 267	86.57 292	58.01 312	90.02 233	62.74 304	92.73 231	89.10 278

diffmvs		80.40 225	80.48 223	80.17 254	79.02 369	60.04 299	77.54 304	90.28 176	66.65 271	82.40 269	87.33 281	73.50 208	87.35 279	77.98 148	89.62 295	93.13 149
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 73	76.54 113	79.38 276	77.79 323	52.59 380	82.36 270	90.84 209	66.83 261			91.69 254	81.25 385

D2MVS		76.84 267	75.67 278	80.34 251	80.48 354	62.16 277	73.50 355	84.80 276	57.61 351	82.24 271	87.54 275	51.31 347	87.65 275	70.40 235	93.19 220	91.23 225

VNet		79.31 240	80.27 225	76.44 308	87.92 216	53.95 355	75.58 336	84.35 280	74.39 166	82.23 272	90.72 212	72.84 220	84.39 325	60.38 323	93.98 199	90.97 232

Vis-MVSNet (Re-imp)		77.82 256	77.79 257	77.92 288	88.82 192	51.29 376	83.28 203	71.97 371	74.04 168	82.23 272	89.78 237	57.38 318	89.41 248	57.22 339	95.41 146	93.05 153

API-MVS		82.28 190	82.61 185	81.30 234	86.29 261	69.79 187	88.71 95	87.67 221	78.42 117	82.15 274	84.15 332	77.98 151	91.59 180	65.39 282	92.75 230	82.51 371

DP-MVS Recon		84.05 155	83.22 171	86.52 107	91.73 122	75.27 126	83.23 207	92.40 105	72.04 208	82.04 275	88.33 259	77.91 153	93.95 104	66.17 273	95.12 159	90.34 254

MSDG		80.06 236	79.99 235	80.25 252	83.91 307	68.04 211	77.51 305	89.19 198	77.65 127	81.94 276	83.45 338	76.37 179	86.31 297	63.31 302	86.59 339	86.41 315

test2506		74.12 298	73.39 299	76.28 311	91.85 117	44.20 405	84.06 180	48.20 430	72.30 204	81.90 277	94.20 85	27.22 430	89.77 239	64.81 288	96.02 122	94.87 71

Fast-Effi-MVS+		81.04 214	80.57 219	82.46 216	87.50 229	63.22 257	78.37 293	89.63 192	68.01 252	81.87 278	82.08 354	82.31 102	92.65 153	67.10 264	88.30 317	91.51 222

testgi		72.36 314	74.61 286	65.59 385	80.56 353	42.82 410	68.29 387	73.35 359	66.87 269	81.84 279	89.93 234	72.08 230	66.92 408	46.05 402	92.54 233	87.01 310

tfpn200view9		74.86 291	74.23 291	76.74 305	86.24 262	52.12 368	79.24 279	73.87 353	73.34 182	81.82 280	84.60 327	46.02 368	88.80 255	51.98 374	90.99 267	89.31 273

thres400		75.14 285	74.23 291	77.86 290	86.24 262	52.12 368	79.24 279	73.87 353	73.34 182	81.82 280	84.60 327	46.02 368	88.80 255	51.98 374	90.99 267	92.66 169

CL-MVSNet_self_test		76.81 268	77.38 260	75.12 320	86.90 247	51.34 374	73.20 358	80.63 311	68.30 249	81.80 282	88.40 258	66.92 260	80.90 348	55.35 353	94.90 168	93.12 151

OpenMVS	76.72 13	81.98 201	82.00 193	81.93 221	84.42 296	68.22 207	88.50 99	89.48 195	66.92 268	81.80 282	91.86 169	72.59 223	90.16 224	71.19 225	91.25 263	87.40 305

MVS_0304		85.37 118	84.58 145	87.75 88	85.28 280	73.36 137	86.54 133	85.71 255	77.56 130	81.78 284	92.47 151	70.29 243	96.02 11	85.59 58	95.96 125	93.87 114

AdaColmap		83.66 165	83.69 164	83.57 184	90.05 167	72.26 159	86.29 136	90.00 183	78.19 120	81.65 285	87.16 284	83.40 87	94.24 92	61.69 314	94.76 177	84.21 344

SPE-MVS-test		87.00 90	86.43 105	88.71 74	89.46 176	77.46 102	89.42 84	95.73 7	77.87 125	81.64 286	87.25 282	82.43 98	94.53 84	77.65 151	96.46 102	94.14 103

DELS-MVS		81.44 209	81.25 210	82.03 220	84.27 300	62.87 261	76.47 324	92.49 104	70.97 220	81.64 286	83.83 333	75.03 187	92.70 151	74.29 188	92.22 242	90.51 250
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		83.10 179	82.54 187	84.77 145	92.90 83	69.10 200	86.65 129	90.62 159	54.66 369	81.46 288	90.81 210	76.98 168	94.38 87	72.62 216	96.18 114	90.82 238

TR-MVS		76.77 269	75.79 275	79.72 259	86.10 268	65.79 232	77.14 310	83.02 290	65.20 289	81.40 289	82.10 352	66.30 262	90.73 210	55.57 350	85.27 352	82.65 365

TAMVS		78.08 254	76.36 270	83.23 193	90.62 154	72.87 144	79.08 282	80.01 314	61.72 314	81.35 290	86.92 289	63.96 276	88.78 258	50.61 379	93.01 224	88.04 295

Effi-MVS+		83.90 160	84.01 159	83.57 184	87.22 236	65.61 234	86.55 132	92.40 105	78.64 114	81.34 291	84.18 331	83.65 84	92.93 146	74.22 189	87.87 322	92.17 198

testing3		71.53 323	70.79 325	73.77 329	88.89 191	41.86 412	76.60 322	59.12 419	72.83 193	80.97 292	82.08 354	19.80 436	87.33 280	65.12 285	91.68 255	92.13 200

new-patchmatchnet		70.10 336	73.37 300	60.29 402	81.23 343	16.95 437	59.54 413	74.62 346	62.93 300	80.97 292	87.93 267	62.83 286	71.90 385	55.24 354	95.01 165	92.00 205

PVSNet_Blended_VisFu		81.55 207	80.49 222	84.70 149	91.58 127	73.24 142	84.21 176	91.67 129	62.86 301	80.94 294	87.16 284	67.27 258	92.87 149	69.82 240	88.94 305	87.99 296

BH-w/o		76.57 272	76.07 274	78.10 284	86.88 248	65.92 231	77.63 302	86.33 243	65.69 281	80.89 295	79.95 373	68.97 252	90.74 209	53.01 369	85.25 353	77.62 401

PAPM_NR		83.23 175	83.19 173	83.33 190	90.90 148	65.98 230	88.19 101	90.78 154	78.13 121	80.87 296	87.92 268	73.49 210	92.42 157	70.07 237	88.40 311	91.60 219

ab-mvs		79.67 239	80.56 220	76.99 299	88.48 203	56.93 332	84.70 167	86.06 249	68.95 240	80.78 297	93.08 126	75.30 185	84.62 321	56.78 340	90.90 272	89.43 271

XXY-MVS		74.44 297	76.19 272	69.21 363	84.61 292	52.43 367	71.70 366	77.18 330	60.73 329	80.60 298	90.96 202	75.44 182	69.35 394	56.13 345	88.33 313	85.86 322

HQP4-MVS										80.56 299			94.61 79			93.56 134

HQP-NCC					91.19 139		84.77 162		73.30 184	80.55 300

ACMP_Plane					91.19 139		84.77 162		73.30 184	80.55 300

HQP-MVS		84.61 136	84.06 158	86.27 112	91.19 139	70.66 178	84.77 162	92.68 98	73.30 184	80.55 300	90.17 231	72.10 228	94.61 79	77.30 158	94.47 184	93.56 134

test_cas_vis1_n_1920		69.20 349	69.12 342	69.43 362	73.68 406	62.82 262	70.38 378	77.21 329	46.18 406	80.46 303	78.95 382	52.03 343	65.53 413	65.77 280	77.45 408	79.95 396

AUN-MVS		81.18 212	78.78 245	88.39 79	90.93 147	82.14 62	82.51 228	83.67 285	64.69 292	80.29 304	85.91 305	51.07 348	92.38 159	76.29 170	93.63 211	90.65 246

HyFIR lowres test		75.12 287	72.66 309	82.50 215	91.44 135	65.19 237	72.47 361	87.31 225	46.79 402	80.29 304	84.30 329	52.70 341	92.10 169	51.88 378	86.73 337	90.22 255

test20.03		73.75 303	74.59 288	71.22 349	81.11 344	51.12 378	70.15 379	72.10 370	70.42 224	80.28 306	91.50 183	64.21 273	74.72 379	46.96 398	94.58 181	87.82 301

mvsany_test3		65.48 371	62.97 380	73.03 335	69.99 421	76.17 121	64.83 400	43.71 432	43.68 414	80.25 307	87.05 288	52.83 340	63.09 419	51.92 377	72.44 414	79.84 397

F-COLMAP		84.97 131	83.42 167	89.63 57	92.39 96	83.40 52	88.83 92	91.92 121	73.19 188	80.18 308	89.15 248	77.04 167	93.28 133	65.82 279	92.28 239	92.21 196

GA-MVS		75.83 280	74.61 286	79.48 264	81.87 333	59.25 308	73.42 356	82.88 291	68.68 243	79.75 309	81.80 357	50.62 351	89.46 244	66.85 266	85.64 349	89.72 266

xiu_mvs_v1_base_debu		80.84 216	80.14 230	82.93 204	88.31 206	71.73 166	79.53 272	87.17 228	65.43 283	79.59 310	82.73 348	76.94 169	90.14 227	73.22 208	88.33 313	86.90 311

xiu_mvs_v1_base		80.84 216	80.14 230	82.93 204	88.31 206	71.73 166	79.53 272	87.17 228	65.43 283	79.59 310	82.73 348	76.94 169	90.14 227	73.22 208	88.33 313	86.90 311

xiu_mvs_v1_base_debi		80.84 216	80.14 230	82.93 204	88.31 206	71.73 166	79.53 272	87.17 228	65.43 283	79.59 310	82.73 348	76.94 169	90.14 227	73.22 208	88.33 313	86.90 311

test_fmvs1_n		70.94 328	70.41 332	72.53 341	73.92 403	66.93 221	75.99 331	84.21 283	43.31 416	79.40 313	79.39 378	43.47 390	68.55 399	69.05 249	84.91 361	82.10 375

patch_mono-2		78.89 243	79.39 238	77.41 296	84.78 288	68.11 209	75.60 334	83.11 289	60.96 326	79.36 314	89.89 236	75.18 186	72.97 382	73.32 207	92.30 236	91.15 228

UnsupCasMVSNet_eth		71.63 322	72.30 314	69.62 360	76.47 387	52.70 365	70.03 380	80.97 308	59.18 338	79.36 314	88.21 261	60.50 293	69.12 395	58.33 334	77.62 406	87.04 309

ppachtmachnet_test		74.73 294	74.00 293	76.90 302	80.71 351	56.89 334	71.53 369	78.42 320	58.24 344	79.32 316	82.92 345	57.91 315	84.26 327	65.60 281	91.36 261	89.56 268

MG-MVS		80.32 228	80.94 215	78.47 277	88.18 209	52.62 366	82.29 234	85.01 270	72.01 209	79.24 317	92.54 149	69.36 248	93.36 132	70.65 231	89.19 301	89.45 269

Fast-Effi-MVS+-dtu		82.54 187	81.41 207	85.90 123	85.60 274	76.53 115	83.07 210	89.62 193	73.02 191	79.11 318	83.51 336	80.74 129	90.24 221	68.76 253	89.29 298	90.94 233

SSC-MVS3.2		73.90 301	75.67 278	68.61 371	84.11 303	41.28 413	64.17 404	72.83 363	72.09 207	79.08 319	87.94 265	70.31 242	73.89 381	55.99 346	94.49 183	90.67 245

CDS-MVSNet		77.32 262	75.40 280	83.06 197	89.00 186	72.48 155	77.90 298	82.17 298	60.81 327	78.94 320	83.49 337	59.30 304	88.76 259	54.64 359	92.37 235	87.93 298
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 306	73.54 297	72.43 342	84.92 286	47.79 390	79.89 268	74.00 351	65.93 274	78.81 321	86.28 299	56.36 324	81.63 345	56.63 341	79.04 401	87.87 300

ttmdpeth		71.72 320	70.67 326	74.86 322	73.08 412	55.88 339	77.41 309	69.27 386	55.86 361	78.66 322	93.77 110	38.01 404	75.39 376	60.12 324	89.87 292	93.31 141

EIA-MVS		82.19 193	81.23 212	85.10 138	87.95 215	69.17 199	83.22 208	93.33 67	70.42 224	78.58 323	79.77 376	77.29 162	94.20 94	71.51 222	88.96 304	91.93 208

thres200		72.34 315	71.55 321	74.70 325	83.48 312	51.60 373	75.02 341	73.71 356	70.14 230	78.56 324	80.57 367	46.20 366	88.20 268	46.99 397	89.29 298	84.32 340

our_test_3		71.85 318	71.59 318	72.62 339	80.71 351	53.78 356	69.72 382	71.71 375	58.80 341	78.03 325	80.51 369	56.61 323	78.84 363	62.20 308	86.04 347	85.23 328

KD-MVS_2432*1600		66.87 360	65.81 367	70.04 354	67.50 424	47.49 391	62.56 407	79.16 316	61.21 324	77.98 326	80.61 365	25.29 432	82.48 338	53.02 367	84.92 359	80.16 394

miper_refine_blended		66.87 360	65.81 367	70.04 354	67.50 424	47.49 391	62.56 407	79.16 316	61.21 324	77.98 326	80.61 365	25.29 432	82.48 338	53.02 367	84.92 359	80.16 394

jason		77.42 261	75.75 276	82.43 217	87.10 241	69.27 194	77.99 296	81.94 300	51.47 389	77.84 328	85.07 321	60.32 296	89.00 252	70.74 230	89.27 300	89.03 281
jason: jason.
MAR-MVS		80.24 231	78.74 247	84.73 147	86.87 249	78.18 92	85.75 146	87.81 220	65.67 282	77.84 328	78.50 386	73.79 205	90.53 215	61.59 316	90.87 274	85.49 327
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		72.29 316	72.00 315	73.14 333	88.63 199	85.00 40	74.65 345	67.39 393	71.94 210	77.80 330	87.66 273	50.48 352	75.83 374	49.95 381	79.51 395	58.58 424

test_fmvs1		69.57 344	69.05 344	71.14 351	69.15 423	65.77 233	73.98 350	83.32 287	42.83 418	77.77 331	78.27 388	43.39 393	68.50 400	68.39 259	84.38 368	79.15 398

pmmvs4		74.92 290	72.98 305	80.73 245	84.95 285	71.71 169	76.23 327	77.59 325	52.83 379	77.73 332	86.38 294	56.35 325	84.97 318	57.72 338	87.05 332	85.51 326

ET-MVSNet_ETH3D		75.28 284	72.77 307	82.81 208	83.03 327	68.11 209	77.09 311	76.51 336	60.67 330	77.60 333	80.52 368	38.04 403	91.15 193	70.78 228	90.68 279	89.17 276

testing3-2		70.72 331	70.97 324	69.95 356	88.93 189	34.80 426	69.85 381	66.59 400	78.42 117	77.58 334	85.55 307	31.83 417	82.08 341	46.28 399	93.73 208	92.98 157

UnsupCasMVSNet_bld		69.21 348	69.68 339	67.82 374	79.42 363	51.15 377	67.82 391	75.79 339	54.15 371	77.47 335	85.36 316	59.26 305	70.64 390	48.46 391	79.35 397	81.66 379

WBMVS		68.76 351	68.43 351	69.75 359	83.29 319	40.30 416	67.36 393	72.21 369	57.09 356	77.05 336	85.53 309	33.68 412	80.51 352	48.79 389	90.90 272	88.45 288

Anonymous20231206		71.38 325	71.88 316	69.88 357	86.31 259	54.37 351	70.39 377	74.62 346	52.57 381	76.73 337	88.76 252	59.94 299	72.06 384	44.35 406	93.23 219	83.23 360

CMPMVS	59.41 20	75.12 287	73.57 296	79.77 257	75.84 393	67.22 215	81.21 251	82.18 297	50.78 394	76.50 338	87.66 273	55.20 332	82.99 336	62.17 310	90.64 284	89.09 280
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 317	71.69 317	73.32 331	81.57 338	53.02 362	76.77 316	78.37 321	63.31 297	76.37 339	91.85 170	36.68 407	78.98 361	47.87 394	92.45 234	87.95 297

CVMVSNet		72.62 312	71.41 322	76.28 311	83.25 321	60.34 297	83.50 198	79.02 319	37.77 427	76.33 340	85.10 318	49.60 356	87.41 278	70.54 233	77.54 407	81.08 388

PLC	73.85 16	82.09 197	80.31 224	87.45 92	90.86 150	80.29 73	85.88 142	90.65 157	68.17 251	76.32 341	86.33 296	73.12 217	92.61 154	61.40 317	90.02 290	89.44 270
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 191	81.57 204	84.19 166	85.54 276	69.26 195	91.98 34	90.08 181	71.54 211	76.23 342	85.07 321	58.69 309	94.27 89	86.26 45	88.77 306	89.03 281

lupinMVS		76.37 276	74.46 289	82.09 219	85.54 276	69.26 195	76.79 315	80.77 310	50.68 396	76.23 342	82.82 346	58.69 309	88.94 253	69.85 239	88.77 306	88.07 292

UWE-MVS		66.43 364	65.56 370	69.05 364	84.15 302	40.98 414	73.06 360	64.71 406	54.84 367	76.18 344	79.62 377	29.21 423	80.50 353	38.54 418	89.75 293	85.66 324

PatchMatch-RL		74.48 295	73.22 302	78.27 282	87.70 222	85.26 38	75.92 332	70.09 381	64.34 294	76.09 345	81.25 362	65.87 266	78.07 366	53.86 361	83.82 371	71.48 410

thisisatest0515		73.00 310	70.52 329	80.46 249	81.45 339	59.90 302	73.16 359	74.31 350	57.86 348	76.08 346	77.78 390	37.60 406	92.12 168	65.00 286	91.45 260	89.35 272

MS-PatchMatch		70.93 329	70.22 333	73.06 334	81.85 334	62.50 268	73.82 353	77.90 322	52.44 382	75.92 347	81.27 361	55.67 329	81.75 343	55.37 352	77.70 405	74.94 406

CHOSEN 1792x2688		72.45 313	70.56 328	78.13 283	90.02 169	63.08 258	68.72 386	83.16 288	42.99 417	75.92 347	85.46 311	57.22 320	85.18 317	49.87 383	81.67 385	86.14 318

CR-MVSNet		74.00 300	73.04 304	76.85 304	79.58 360	62.64 265	82.58 224	76.90 332	50.50 397	75.72 349	92.38 153	48.07 360	84.07 329	68.72 255	82.91 378	83.85 349

RPMNet		78.88 244	78.28 253	80.68 247	79.58 360	62.64 265	82.58 224	94.16 32	74.80 161	75.72 349	92.59 146	48.69 357	95.56 42	73.48 204	82.91 378	83.85 349

DPM-MVS		80.10 235	79.18 240	82.88 207	90.71 153	69.74 188	78.87 286	90.84 152	60.29 333	75.64 351	85.92 304	67.28 257	93.11 139	71.24 224	91.79 251	85.77 323

test_vis1_n		70.29 333	69.99 337	71.20 350	75.97 392	66.50 225	76.69 318	80.81 309	44.22 412	75.43 352	77.23 397	50.00 354	68.59 398	66.71 269	82.85 380	78.52 400

PVSNet_BlendedMVS		78.80 246	77.84 256	81.65 230	84.43 294	63.41 253	79.49 275	90.44 164	61.70 315	75.43 352	87.07 287	69.11 250	91.44 184	60.68 321	92.24 240	90.11 260

PVSNet_Blended		76.49 274	75.40 280	79.76 258	84.43 294	63.41 253	75.14 340	90.44 164	57.36 353	75.43 352	78.30 387	69.11 250	91.44 184	60.68 321	87.70 325	84.42 339

PAPR		78.84 245	78.10 255	81.07 239	85.17 283	60.22 298	82.21 238	90.57 161	62.51 303	75.32 355	84.61 326	74.99 188	92.30 163	59.48 328	88.04 319	90.68 243

N_pmnet		70.20 334	68.80 349	74.38 326	80.91 346	84.81 43	59.12 415	76.45 337	55.06 365	75.31 356	82.36 351	55.74 328	54.82 425	47.02 396	87.24 328	83.52 353

cascas		76.29 277	74.81 285	80.72 246	84.47 293	62.94 259	73.89 352	87.34 224	55.94 360	75.16 357	76.53 403	63.97 275	91.16 192	65.00 286	90.97 270	88.06 294

SCA		73.32 305	72.57 311	75.58 318	81.62 337	55.86 340	78.89 285	71.37 376	61.73 313	74.93 358	83.42 339	60.46 294	87.01 282	58.11 336	82.63 383	83.88 346

test_vis1_n_1920		71.30 326	71.58 320	70.47 352	77.58 376	59.99 301	74.25 346	84.22 282	51.06 391	74.85 359	79.10 380	55.10 333	68.83 397	68.86 252	79.20 400	82.58 367

xiu_mvs_v2_base		77.19 263	76.75 267	78.52 275	87.01 244	61.30 284	75.55 337	87.12 234	61.24 323	74.45 360	78.79 384	77.20 163	90.93 200	64.62 292	84.80 365	83.32 358

CANet		83.79 163	82.85 180	86.63 104	86.17 265	72.21 161	83.76 191	91.43 134	77.24 133	74.39 361	87.45 278	75.36 184	95.42 52	77.03 161	92.83 228	92.25 195

PS-MVSNAJ		77.04 265	76.53 269	78.56 274	87.09 242	61.40 282	75.26 339	87.13 231	61.25 322	74.38 362	77.22 398	76.94 169	90.94 199	64.63 291	84.83 364	83.35 357

MVP-Stereo		75.81 281	73.51 298	82.71 209	89.35 178	73.62 135	80.06 264	85.20 263	60.30 332	73.96 363	87.94 265	57.89 316	89.45 245	52.02 373	74.87 412	85.06 331
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 352	69.01 345	67.85 373	83.22 323	43.98 406	74.93 342	65.98 401	55.09 364	73.83 364	79.11 379	65.63 267	71.89 386	38.21 419	85.04 357	87.69 302

UGNet		82.78 182	81.64 199	86.21 116	86.20 264	76.24 120	86.86 122	85.68 256	77.07 134	73.76 365	92.82 139	69.64 246	91.82 177	69.04 250	93.69 209	90.56 248
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		74.82 292	73.74 294	78.04 286	89.57 172	60.04 299	76.49 323	87.09 235	54.31 370	73.66 366	79.80 374	60.25 297	86.76 291	58.37 332	84.15 369	87.32 306

Test_1112_low_res		73.90 301	73.08 303	76.35 309	90.35 159	55.95 337	73.40 357	86.17 246	50.70 395	73.14 367	85.94 303	58.31 311	85.90 308	56.51 342	83.22 375	87.20 308

1314		73.22 307	72.56 312	75.20 319	80.41 355	57.84 325	81.64 245	85.36 260	51.68 388	73.10 368	76.65 402	61.45 289	85.19 316	63.54 299	79.21 399	82.59 366

test_vis1_rt		65.64 370	64.09 374	70.31 353	66.09 428	70.20 184	61.16 410	81.60 303	38.65 424	72.87 369	69.66 417	52.84 339	60.04 421	56.16 344	77.77 404	80.68 392

Patchmatch-test		65.91 367	67.38 356	61.48 399	75.51 395	43.21 409	68.84 385	63.79 408	62.48 304	72.80 370	83.42 339	44.89 386	59.52 422	48.27 393	86.45 340	81.70 378

PatchmatchNet		69.71 343	68.83 348	72.33 344	77.66 375	53.60 357	79.29 277	69.99 382	57.66 350	72.53 371	82.93 344	46.45 365	80.08 356	60.91 320	72.09 415	83.31 359
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 354	68.08 355	67.55 375	78.74 371	43.53 408	75.60 334	67.10 398	54.92 366	72.23 372	88.10 262	42.87 395	75.97 373	52.21 372	80.95 393	83.15 361

pmmvs5		70.73 330	70.07 334	72.72 337	77.03 381	52.73 364	74.14 347	75.65 342	50.36 398	72.17 373	85.37 315	55.42 331	80.67 350	52.86 370	87.59 326	84.77 333

PatchT		70.52 332	72.76 308	63.79 393	79.38 364	33.53 427	77.63 302	65.37 404	73.61 175	71.77 374	92.79 142	44.38 388	75.65 375	64.53 293	85.37 351	82.18 374

MVS		73.21 308	72.59 310	75.06 321	80.97 345	60.81 294	81.64 245	85.92 253	46.03 407	71.68 375	77.54 393	68.47 253	89.77 239	55.70 349	85.39 350	74.60 407

MIMVSNet		71.09 327	71.59 318	69.57 361	87.23 235	50.07 383	78.91 284	71.83 372	60.20 335	71.26 376	91.76 177	55.08 334	76.09 372	41.06 411	87.02 334	82.54 369

WTY-MVS		67.91 355	68.35 352	66.58 381	80.82 349	48.12 388	65.96 399	72.60 364	53.67 373	71.20 377	81.68 359	58.97 307	69.06 396	48.57 390	81.67 385	82.55 368

test0.0.03 1		64.66 374	64.36 373	65.57 386	75.03 400	46.89 394	64.69 402	61.58 416	62.43 308	71.18 378	77.54 393	43.41 391	68.47 401	40.75 413	82.65 381	81.35 382

CostFormer		69.98 340	68.68 350	73.87 327	77.14 379	50.72 380	79.26 278	74.51 348	51.94 387	70.97 379	84.75 324	45.16 383	87.49 277	55.16 355	79.23 398	83.40 356

Syy-MVS		69.40 346	70.03 336	67.49 376	81.72 335	38.94 418	71.00 371	61.99 410	61.38 319	70.81 380	72.36 414	61.37 290	79.30 359	64.50 294	85.18 354	84.22 342

myMVS_eth3d		64.66 374	63.89 375	66.97 379	81.72 335	37.39 421	71.00 371	61.99 410	61.38 319	70.81 380	72.36 414	20.96 435	79.30 359	49.59 384	85.18 354	84.22 342

testing91		69.94 341	68.99 346	72.80 336	83.81 309	45.89 398	71.57 368	73.64 358	68.24 250	70.77 382	77.82 389	34.37 410	84.44 324	53.64 363	87.00 335	88.07 292

testing99		69.27 347	68.15 354	72.63 338	83.29 319	45.45 400	71.15 370	71.08 377	67.34 263	70.43 383	77.77 391	32.24 416	84.35 326	53.72 362	86.33 343	88.10 291

tpmvs		70.16 335	69.56 340	71.96 345	74.71 402	48.13 387	79.63 270	75.45 344	65.02 290	70.26 384	81.88 356	45.34 380	85.68 312	58.34 333	75.39 411	82.08 376

sss		66.92 359	67.26 357	65.90 383	77.23 378	51.10 379	64.79 401	71.72 374	52.12 386	70.13 385	80.18 371	57.96 314	65.36 414	50.21 380	81.01 391	81.25 385

tpm2		68.45 353	66.83 360	73.30 332	78.93 370	48.50 386	79.76 269	71.76 373	47.50 401	69.92 386	83.60 335	42.07 396	88.40 264	48.44 392	79.51 395	83.01 363

myMVS_eth3d28		65.83 369	65.85 365	65.78 384	83.42 315	35.71 424	67.29 394	68.01 391	67.58 260	69.80 387	77.72 392	32.29 415	74.30 380	37.49 420	89.06 302	87.32 306

testing222		66.93 358	65.30 371	71.81 346	83.38 316	45.83 399	72.06 364	67.50 392	64.12 295	69.68 388	76.37 404	27.34 429	83.00 335	38.88 415	88.38 312	86.62 314

HY-MVS	64.64 18	73.03 309	72.47 313	74.71 324	83.36 318	54.19 353	82.14 241	81.96 299	56.76 359	69.57 389	86.21 300	60.03 298	84.83 320	49.58 385	82.65 381	85.11 330

dmvs_re		66.81 362	66.98 358	66.28 382	76.87 382	58.68 319	71.66 367	72.24 367	60.29 333	69.52 390	73.53 411	52.38 342	64.40 416	44.90 404	81.44 388	75.76 404

ETVMVS		64.67 373	63.34 379	68.64 368	83.44 314	41.89 411	69.56 384	61.70 415	61.33 321	68.74 391	75.76 406	28.76 424	79.35 358	34.65 423	86.16 346	84.67 335

tpm cat1		66.76 363	65.21 372	71.42 348	77.09 380	50.62 381	78.01 295	73.68 357	44.89 410	68.64 392	79.00 381	45.51 377	82.42 340	49.91 382	70.15 418	81.23 387

IB-MVS	62.13 19	71.64 321	68.97 347	79.66 261	80.80 350	62.26 274	73.94 351	76.90 332	63.27 298	68.63 393	76.79 400	33.83 411	91.84 176	59.28 329	87.26 327	84.88 332
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		80.37 226	78.41 252	86.23 113	76.75 383	73.28 140	87.18 116	77.45 326	76.24 139	68.14 394	88.93 251	65.41 268	93.85 107	69.47 242	96.12 118	91.55 221
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 365	65.63 369	68.75 367	81.96 332	49.88 384	62.19 409	72.51 366	51.03 392	68.04 395	75.34 408	50.84 349	74.77 377	45.82 403	82.96 376	81.60 380

tpmrst		66.28 366	66.69 362	65.05 389	72.82 414	39.33 417	78.20 294	70.69 380	53.16 377	67.88 396	80.36 370	48.18 359	74.75 378	58.13 335	70.79 417	81.08 388

CANet_DTU		77.81 257	77.05 263	80.09 255	81.37 341	59.90 302	83.26 204	88.29 213	69.16 237	67.83 397	83.72 334	60.93 291	89.47 243	69.22 246	89.70 294	90.88 236

EPMVS		62.47 378	62.63 382	62.01 395	70.63 420	38.74 419	74.76 343	52.86 426	53.91 372	67.71 398	80.01 372	39.40 400	66.60 409	55.54 351	68.81 423	80.68 392

UBG		64.34 376	63.35 378	67.30 377	83.50 311	40.53 415	67.46 392	65.02 405	54.77 368	67.54 399	74.47 410	32.99 414	78.50 365	40.82 412	83.58 372	82.88 364

MDTV_nov1_ep13			68.29 353		78.03 372	43.87 407	74.12 348	72.22 368	52.17 383	67.02 400	85.54 308	45.36 379	80.85 349	55.73 347	84.42 367

testing11		67.38 356	65.93 364	71.73 347	83.37 317	46.60 395	70.95 373	69.40 385	62.47 305	66.14 401	76.66 401	31.22 418	84.10 328	49.10 387	84.10 370	84.49 336

pmmvs3		62.47 378	60.02 391	69.80 358	71.58 418	64.00 248	70.52 376	58.44 422	39.77 422	66.05 402	75.84 405	27.10 431	72.28 383	46.15 401	84.77 366	73.11 408

ADS-MVSNet2		65.87 368	63.64 377	72.55 340	73.16 410	56.92 333	67.10 395	74.81 345	49.74 399	66.04 403	82.97 342	46.71 363	77.26 369	42.29 408	69.96 419	83.46 354

ADS-MVSNet		61.90 380	62.19 384	61.03 400	73.16 410	36.42 423	67.10 395	61.75 413	49.74 399	66.04 403	82.97 342	46.71 363	63.21 417	42.29 408	69.96 419	83.46 354

mvsany_test1		58.48 390	56.47 396	64.50 390	65.90 430	68.21 208	56.95 420	42.11 433	38.30 425	65.69 405	77.19 399	56.96 321	59.35 423	46.16 400	58.96 426	65.93 417

dmvs_testset		60.59 388	62.54 383	54.72 408	77.26 377	27.74 431	74.05 349	61.00 417	60.48 331	65.62 406	67.03 421	55.93 327	68.23 403	32.07 427	69.46 422	68.17 415

DSMNet-mixed		60.98 386	61.61 386	59.09 405	72.88 413	45.05 403	74.70 344	46.61 431	26.20 429	65.34 407	90.32 224	55.46 330	63.12 418	41.72 410	81.30 390	69.09 414

JIA-IIPM		69.41 345	66.64 363	77.70 292	73.19 409	71.24 174	75.67 333	65.56 403	70.42 224	65.18 408	92.97 133	33.64 413	83.06 334	53.52 365	69.61 421	78.79 399

test-LLR		67.21 357	66.74 361	68.63 369	76.45 388	55.21 346	67.89 388	67.14 396	62.43 308	65.08 409	72.39 412	43.41 391	69.37 392	61.00 318	84.89 362	81.31 383

test-mter		65.00 372	63.79 376	68.63 369	76.45 388	55.21 346	67.89 388	67.14 396	50.98 393	65.08 409	72.39 412	28.27 426	69.37 392	61.00 318	84.89 362	81.31 383

PMMVS2		55.64 394	59.27 392	44.74 410	64.30 432	12.32 438	40.60 425	49.79 428	53.19 376	65.06 411	84.81 323	53.60 338	49.76 428	32.68 426	89.41 297	72.15 409

baseline2		69.77 342	66.89 359	78.41 278	79.51 362	58.09 321	76.23 327	69.57 384	57.50 352	64.82 412	77.45 395	46.02 368	88.44 262	53.08 366	77.83 403	88.70 285

gg-mvs-nofinetune		68.96 350	69.11 343	68.52 372	76.12 391	45.32 401	83.59 195	55.88 424	86.68 29	64.62 413	97.01 9	30.36 421	83.97 331	44.78 405	82.94 377	76.26 403

PAPM		71.77 319	70.06 335	76.92 301	86.39 254	53.97 354	76.62 320	86.62 241	53.44 374	63.97 414	84.73 325	57.79 317	92.34 161	39.65 414	81.33 389	84.45 338

new_pmnet		55.69 393	57.66 394	49.76 409	75.47 396	30.59 429	59.56 412	51.45 427	43.62 415	62.49 415	75.48 407	40.96 398	49.15 429	37.39 421	72.52 413	69.55 413

UWE-MVS-28		58.44 391	57.71 393	60.65 401	73.58 407	31.23 428	69.68 383	48.80 429	53.12 378	61.79 416	78.83 383	30.98 419	68.40 402	21.58 430	80.99 392	82.33 373

MDTV_nov1_ep13_2view						27.60 432	70.76 375		46.47 405	61.27 417		45.20 381		49.18 386		83.75 351

dp		60.70 387	60.29 390	61.92 397	72.04 417	38.67 420	70.83 374	64.08 407	51.28 390	60.75 418	77.28 396	36.59 408	71.58 388	47.41 395	62.34 425	75.52 405

TESTMET0.1,1		61.29 383	60.32 389	64.19 391	72.06 416	51.30 375	67.89 388	62.09 409	45.27 408	60.65 419	69.01 418	27.93 427	64.74 415	56.31 343	81.65 387	76.53 402

PMMVS		61.65 381	60.38 388	65.47 387	65.40 431	69.26 195	63.97 405	61.73 414	36.80 428	60.11 420	68.43 419	59.42 303	66.35 410	48.97 388	78.57 402	60.81 421

PVSNet_0	51.08 22	56.10 392	54.97 397	59.48 404	75.12 399	53.28 361	55.16 421	61.89 412	44.30 411	59.16 421	62.48 424	54.22 335	65.91 412	35.40 422	47.01 427	59.25 423

MVS-HIRNet		61.16 384	62.92 381	55.87 406	79.09 367	35.34 425	71.83 365	57.98 423	46.56 404	59.05 422	91.14 194	49.95 355	76.43 371	38.74 416	71.92 416	55.84 425

E-PMN		61.59 382	61.62 385	61.49 398	66.81 426	55.40 344	53.77 422	60.34 418	66.80 270	58.90 423	65.50 422	40.48 399	66.12 411	55.72 348	86.25 344	62.95 420

GG-mvs-BLEND				67.16 378	73.36 408	46.54 397	84.15 178	55.04 425		58.64 424	61.95 425	29.93 422	83.87 332	38.71 417	76.92 409	71.07 411

EPNet_dtu		72.87 311	71.33 323	77.49 295	77.72 374	60.55 296	82.35 232	75.79 339	66.49 272	58.39 425	81.06 363	53.68 337	85.98 304	53.55 364	92.97 226	85.95 320
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 396	42.65 399	39.67 411	70.86 419	21.11 433	61.01 411	21.42 438	57.36 353	57.97 426	50.06 427	16.40 437	58.73 424	21.03 431	27.69 431	39.17 427

EMVS		61.10 385	60.81 387	61.99 396	65.96 429	55.86 340	53.10 423	58.97 421	67.06 267	56.89 427	63.33 423	40.98 397	67.03 407	54.79 357	86.18 345	63.08 419

CHOSEN 280x420		59.08 389	56.52 395	66.76 380	76.51 386	64.39 244	49.62 424	59.00 420	43.86 413	55.66 428	68.41 420	35.55 409	68.21 404	43.25 407	76.78 410	67.69 416

MVE	40.22 23	51.82 395	50.47 398	55.87 406	62.66 433	51.91 370	31.61 427	39.28 434	40.65 420	50.76 429	74.98 409	56.24 326	44.67 430	33.94 425	64.11 424	71.04 412
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 397	32.17 400	26.83 413	53.36 435	19.02 436	57.90 418	20.44 439	38.29 426	38.01 430	37.82 429	15.18 438	33.45 432	7.74 433	20.76 432	28.03 428

DeepMVS_CX				24.13 414	32.95 436	29.49 430		21.63 437	12.07 430	37.95 431	45.07 428	30.84 420	19.21 433	17.94 432	33.06 430	23.69 429

tmp_tt		20.25 400	24.50 403	7.49 415	4.47 438	8.70 439	34.17 426	25.16 436	1.00 433	32.43 432	18.49 430	39.37 401	9.21 434	21.64 429	43.75 428	4.57 430

test_method		30.46 398	29.60 401	33.06 412	17.99 437	3.84 440	13.62 428	73.92 352	2.79 431	18.29 433	53.41 426	28.53 425	43.25 431	22.56 428	35.27 429	52.11 426

EGC-MVSNET		74.79 293	69.99 337	89.19 65	94.89 38	87.00 15	91.89 37	86.28 244	1.09 432	2.23 434	95.98 27	81.87 116	89.48 242	79.76 122	95.96 125	91.10 229

testmvs		5.91 404	7.65 407	0.72 417	1.20 439	0.37 442	59.14 414	0.67 441	0.49 435	1.11 435	2.76 434	0.94 440	0.24 436	1.02 435	1.47 433	1.55 432

test123		6.27 403	8.08 406	0.84 416	1.11 440	0.57 441	62.90 406	0.82 440	0.54 434	1.07 436	2.75 435	1.26 439	0.30 435	1.04 434	1.26 434	1.66 431

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		20.81 399	27.75 402	0.00 418	0.00 441	0.00 443	0.00 429	85.44 259	0.00 436	0.00 437	82.82 346	81.46 120	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		6.41 402	8.55 405	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	76.94 169	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		6.65 401	8.87 404	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	79.80 374	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						37.39 421								52.61 371

MSC_two_6792asdad				88.81 71	91.55 129	77.99 94		91.01 148					96.05 9	87.45 25	98.17 35	92.40 184

No_MVS				88.81 71	91.55 129	77.99 94		91.01 148					96.05 9	87.45 25	98.17 35	92.40 184

eth-test2					0.00 441

eth-test					0.00 441

OPU-MVS				88.27 82	91.89 115	77.83 97	90.47 55				91.22 191	81.12 124	94.68 76	74.48 187	95.35 148	92.29 191

save fliter					93.75 63	77.44 103	86.31 135	89.72 188	70.80 221

test_0728_SECOND				86.79 102	94.25 48	72.45 156	90.54 52	94.10 39					95.88 18	86.42 41	97.97 46	92.02 204

GSMVS																83.88 346

sam_mvs1												46.11 367				83.88 346

sam_mvs												45.92 372

MTGPA								91.81 127

test_post1							78.85 287				3.13 432	45.19 382	80.13 355	58.11 336

test_post											3.10 433	45.43 378	77.22 370

patchmatchnet-post											81.71 358	45.93 371	87.01 282

MTMP							90.66 48	33.14 435

gm-plane-assit					75.42 397	44.97 404			52.17 383		72.36 414		87.90 272	54.10 360

test9_res														80.83 111	96.45 103	90.57 247

agg_prior2														79.68 124	96.16 115	90.22 255

test_prior4						78.97 84	84.59 169

test_prior				86.32 110	90.59 155	71.99 164		92.85 93					94.17 97			92.80 162

新几何2							81.72 244

旧先验1					91.97 111	71.77 165		81.78 301			91.84 171	73.92 203			93.65 210	83.61 352

无先验							82.81 219	85.62 257	58.09 346				91.41 187	67.95 263		84.48 337

原ACMM2							82.26 237

testdata2													86.43 296	63.52 300

segment_acmp												81.94 112

testdata1							79.62 271		73.95 170

plane_prior7					93.45 68	77.31 106

plane_prior6					92.61 90	76.54 113						74.84 191

plane_prior5								93.61 59					95.22 59	80.78 112	95.83 134	94.46 85

plane_prior4											92.95 134

plane_prior2							89.45 82		79.44 101

plane_prior1					92.83 88

plane_prior						76.42 116	87.15 117		75.94 146						95.03 162

n2								0.00 442

nn								0.00 442

door-mid								74.45 349

test11								91.46 133

door								72.57 365

HQP5-MVS						70.66 178

BP-MVS														77.30 158

HQP3-MVS								92.68 98							94.47 184

HQP2-MVS												72.10 228

NP-MVS					91.95 112	74.55 130					90.17 231

ACMMP++_ref															95.74 140

ACMMP++															97.35 75

Test By Simon												79.09 142

High-resolution multi-view benchmark