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 61	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	84.21 163	96.51 7	57.84 323	88.93 90	92.84 94	91.92 4	96.16 4	96.23 21	86.95 51	95.99 12	79.05 130	98.57 15	98.80 6

PS-CasMVS		90.06 43	91.92 15	84.47 154	96.56 6	58.83 315	89.04 88	92.74 97	91.40 6	96.12 5	96.06 26	87.23 48	95.57 41	79.42 127	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 169	85.06 132	78.75 269	85.94 268	55.75 340	80.05 263	94.27 24	76.47 136	96.09 6	94.54 67	83.31 88	89.75 241	59.95 323	94.89 169	90.75 236

PEN-MVS		90.03 45	91.88 18	84.48 153	96.57 5	58.88 312	88.95 89	93.19 75	91.62 5	96.01 7	96.16 24	87.02 50	95.60 40	78.69 133	98.72 9	98.97 3

CP-MVSNet		89.27 62	90.91 44	84.37 155	96.34 8	58.61 318	88.66 97	92.06 116	90.78 7	95.67 8	95.17 47	81.80 117	95.54 44	79.00 131	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	92.08 198

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	62.39 268	89.54 79	93.31 70	90.21 12	95.57 11	95.66 33	81.42 121	95.90 17	80.94 107	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	91.76 209

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	91.76 209

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	72.94 216	94.85 72	85.07 61	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	69.87 230	95.06 15	96.14 25	84.28 77	93.07 141	87.68 19	96.34 106	97.09 19

wuyk23d		75.13 284	79.30 237	62.63 389	75.56 389	75.18 127	80.89 254	73.10 360	75.06 159	94.76 16	95.32 41	87.73 43	52.85 420	34.16 419	97.11 82	59.85 416

ACMH	76.49 14	89.34 59	91.14 35	83.96 168	92.50 94	70.36 181	89.55 77	93.84 52	81.89 73	94.70 17	95.44 40	90.69 8	88.31 266	83.33 78	98.30 25	93.20 145
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	69.19 196	87.84 107	88.05 215	81.66 75	94.64 18	96.53 17	65.94 262	94.75 74	83.02 84	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	70.00 229	94.55 19	96.67 14	87.94 39	93.59 120	84.27 71	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	69.27 233	94.39 20	96.38 18	86.02 65	93.52 124	83.96 73	95.92 130	95.34 55

test_0402		88.65 69	89.58 60	85.88 124	92.55 92	72.22 160	84.01 180	89.44 196	88.63 20	94.38 21	95.77 29	86.38 61	93.59 120	79.84 119	95.21 154	91.82 207

UniMVSNet_ETH3D		89.12 65	90.72 47	84.31 161	97.00 2	64.33 243	89.67 74	88.38 208	88.84 17	94.29 22	97.57 4	90.48 13	91.26 189	72.57 215	97.65 62	97.34 14

v7n		90.13 40	90.96 42	87.65 91	91.95 112	71.06 174	89.99 64	93.05 83	86.53 31	94.29 22	96.27 20	82.69 93	94.08 100	86.25 46	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	71.54 209	94.28 24	96.54 16	81.57 119	94.27 89	86.26 44	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	70.73 220	94.19 25	96.67 14	76.94 168	94.57 81	83.07 82	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 50	97.92 49	92.29 188

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 69	97.81 55	91.70 213
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 22	97.98 45	92.98 156
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	78.35 137	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 63	98.45 19	92.41 180
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 33	97.60 66	92.73 162

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 33	97.60 66	92.73 162

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 40	97.97 46	90.55 245
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 26	98.21 32	92.98 156

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 58	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 58	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 26	95.94 128	92.48 176

test_241102_TWO								93.71 55	83.77 52	93.49 39	94.27 79	89.27 23	95.84 24	86.03 50	97.82 54	92.04 200

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 37	97.34 76	92.19 194

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 39	97.60 66	94.18 99

testf1		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 190	96.10 119	94.45 86

APD_test2		89.30 60	89.12 64	89.84 52	88.67 195	85.64 35	90.61 50	93.17 76	86.02 34	93.12 44	95.30 42	84.94 69	89.44 246	74.12 190	96.10 119	94.45 86

Anonymous20231211		88.40 71	89.62 59	84.73 146	90.46 157	65.27 233	88.86 91	93.02 87	87.15 28	93.05 46	97.10 8	82.28 106	92.02 170	76.70 161	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	75.79 147	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 47	97.24 79	91.36 221
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 86	98.76 4	94.87 70
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 49	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	75.37 156	92.84 51	95.28 44	85.58 67	96.09 8	87.92 15	97.76 57	93.88 112
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	88.16 210	63.28 254	86.64 130	92.20 112	75.42 155	92.81 53	94.50 68	74.05 200	94.06 101	83.88 74	96.28 108	97.17 18

dcpmvs_2		84.23 148	85.14 131	81.50 230	88.61 199	61.98 276	82.90 215	93.11 79	68.66 242	92.77 54	92.39 152	78.50 146	87.63 274	76.99 160	92.30 234	94.90 68

v8		86.22 103	86.83 100	84.36 157	87.82 217	62.35 270	86.42 134	91.33 139	76.78 135	92.73 55	94.48 70	73.41 209	93.72 112	83.10 81	95.41 146	97.01 21

nrg030		87.85 82	88.49 75	85.91 122	90.07 166	69.73 187	87.86 106	94.20 30	74.04 167	92.70 56	94.66 60	85.88 66	91.50 181	79.72 121	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 21	98.20 34	94.39 91
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 66	97.55 69	94.10 104
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	69.63 189	85.45 152	76.68 333	84.06 50	92.44 60	96.99 10	62.03 284	94.65 77	80.58 113	93.24 216	94.83 75

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 28	98.24 30	94.56 80
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 57	97.51 73	94.30 95

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	79.95 118	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 90	98.04 39	93.64 127

TranMVSNet+NR-MVSNet		87.86 81	88.76 74	85.18 137	94.02 58	64.13 244	84.38 174	91.29 140	84.88 44	92.06 65	93.84 105	86.45 58	93.73 111	73.22 206	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	92.30 187

ACMMP_NAP		90.65 32	91.07 39	89.42 61	95.93 16	79.54 80	89.95 66	93.68 58	77.65 126	91.97 67	94.89 53	88.38 29	95.45 51	89.27 5	97.87 53	93.27 142

FC-MVSNet-test		85.93 110	87.05 95	82.58 210	92.25 101	56.44 334	85.75 146	93.09 81	77.33 130	91.94 68	94.65 61	74.78 191	93.41 130	75.11 182	98.58 14	97.88 7

lessismore_v0				85.95 121	91.10 144	70.99 175		70.91 376		91.79 69	94.42 74	61.76 285	92.93 146	79.52 126	93.03 221	93.93 109

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 42	97.99 43	93.96 108

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 32	98.11 38	93.12 150

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 17	97.74 59	92.85 159

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 17	97.76 57	93.99 106

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 35	97.69 61	93.93 109

test_fmvsmvis_n_1920		85.22 120	85.36 129	84.81 143	85.80 270	76.13 122	85.15 159	92.32 109	61.40 313	91.33 76	90.85 206	83.76 83	86.16 300	84.31 70	93.28 215	92.15 196

ANet_high		83.17 175	85.68 122	75.65 314	81.24 337	45.26 400	79.94 265	92.91 91	83.83 51	91.33 76	96.88 13	80.25 134	85.92 304	68.89 249	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	94.12 103

casdiffmvs_mvg		86.72 95	87.51 86	84.36 157	87.09 239	65.22 234	84.16 176	94.23 27	77.89 122	91.28 79	93.66 114	84.35 76	92.71 150	80.07 115	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 96	97.18 81	90.45 247
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	75.14 158	91.07 81	92.89 136	87.27 47	93.78 110	83.69 77	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 31	98.39 21	92.55 173

FIs		85.35 119	86.27 107	82.60 209	91.86 116	57.31 327	85.10 160	93.05 83	75.83 146	91.02 83	93.97 96	73.57 205	92.91 148	73.97 194	98.02 42	97.58 12

UniMVSNet_NR-MVSNet		86.84 93	87.06 94	86.17 118	92.86 86	67.02 217	82.55 224	91.56 130	83.08 62	90.92 84	91.82 173	78.25 149	93.99 102	74.16 188	98.35 22	97.49 13

DU-MVS		86.80 94	86.99 96	86.21 116	93.24 76	67.02 217	83.16 207	92.21 111	81.73 74	90.92 84	91.97 166	77.20 162	93.99 102	74.16 188	98.35 22	97.61 10

tt0805		88.09 77	89.79 55	82.98 198	93.26 75	63.94 247	91.10 45	89.64 191	85.07 41	90.91 86	91.09 194	89.16 24	91.87 175	82.03 97	95.87 132	93.13 148

V42		83.47 170	83.37 167	83.75 174	83.16 319	63.33 253	81.31 246	90.23 177	69.51 232	90.91 86	90.81 208	74.16 198	92.29 164	80.06 116	90.22 283	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 22	97.71 60	93.83 115

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	73.75 198	94.81 173	93.70 123

WR-MVS		83.56 167	84.40 151	81.06 238	93.43 70	54.88 347	78.67 287	85.02 267	81.24 79	90.74 90	91.56 181	72.85 217	91.08 195	68.00 259	98.04 39	97.23 16

v1240		84.30 144	84.51 148	83.65 177	87.65 223	61.26 283	82.85 216	91.54 131	67.94 252	90.68 91	90.65 215	71.71 233	93.64 114	82.84 87	94.78 174	96.07 36

ZD-MVS					92.22 103	80.48 71		91.85 123	71.22 215	90.38 92	92.98 131	86.06 64	96.11 7	81.99 99	96.75 92

MIMVSNet1		83.63 164	84.59 143	80.74 242	94.06 57	62.77 261	82.72 218	84.53 276	77.57 128	90.34 93	95.92 28	76.88 174	85.83 309	61.88 310	97.42 74	93.62 128

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	80.87 108	95.50 145	94.53 83

KD-MVS_self_test		81.93 200	83.14 173	78.30 278	84.75 287	52.75 361	80.37 260	89.42 197	70.24 227	90.26 95	93.39 119	74.55 196	86.77 288	68.61 254	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	77.55 151	97.07 83	83.13 357
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 335	90.06 97	91.33 186	80.66 130	93.03 143	75.78 173	95.94 128	92.48 176

v1921920		84.23 148	84.37 152	83.79 172	87.64 224	61.71 277	82.91 214	91.20 143	67.94 252	90.06 97	90.34 221	72.04 229	93.59 120	82.32 94	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	91.20 191	82.40 99	90.81 207	73.58 201	94.66 179	94.56 80

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 28	97.62 64	94.20 96

X-MVStestdata		85.04 127	82.70 180	92.08 9	95.64 24	86.25 22	92.64 19	93.33 67	85.07 41	89.99 100	16.05 425	86.57 55	95.80 28	87.35 28	97.62 64	94.20 96

v1192		84.57 137	84.69 142	84.21 163	87.75 219	62.88 258	83.02 210	91.43 134	69.08 236	89.98 102	90.89 203	72.70 220	93.62 118	82.41 93	94.97 166	96.13 34

Anonymous20240529		86.20 104	87.13 92	83.42 186	90.19 162	64.55 241	84.55 169	90.71 155	85.85 36	89.94 103	95.24 46	82.13 109	90.40 218	69.19 245	96.40 105	95.31 57

pmmvs6		86.52 99	88.06 79	81.90 220	92.22 103	62.28 271	84.66 167	89.15 199	83.54 57	89.85 104	97.32 5	88.08 38	86.80 287	70.43 232	97.30 78	96.62 26

v144192		84.24 147	84.41 150	83.71 176	87.59 225	61.57 278	82.95 213	91.03 147	67.82 255	89.80 105	90.49 218	73.28 213	93.51 125	81.88 102	94.89 169	96.04 38

v1144		84.54 139	84.72 140	84.00 166	87.67 222	62.55 265	82.97 212	90.93 151	70.32 225	89.80 105	90.99 197	73.50 206	93.48 126	81.69 103	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	73.53 175	89.71 107	94.82 56	85.09 68	95.77 34	84.17 72	98.03 41	93.26 143
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	87.74 272	76.54 163	88.74 303	96.61 27

IU-MVS					94.18 50	72.64 148		90.82 153	56.98 352	89.67 109				85.78 55	97.92 49	93.28 141

FMVSNet1		84.55 138	85.45 126	81.85 222	90.27 161	61.05 286	86.83 124	88.27 212	78.57 115	89.66 110	95.64 34	75.43 182	90.68 211	69.09 246	95.33 149	93.82 116

IterMVS-LS		84.73 134	84.98 134	83.96 168	87.35 230	63.66 248	83.25 203	89.88 186	76.06 139	89.62 111	92.37 156	73.40 211	92.52 155	78.16 142	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	77.65 149	96.62 95	90.70 239

UniMVSNet (Re)		86.87 91	86.98 97	86.55 106	93.11 79	68.48 203	83.80 189	92.87 92	80.37 87	89.61 113	91.81 174	77.72 155	94.18 95	75.00 183	98.53 16	96.99 22

IS-MVSNet		86.66 97	86.82 101	86.17 118	92.05 109	66.87 220	91.21 43	88.64 205	86.30 33	89.60 114	92.59 146	69.22 246	94.91 71	73.89 195	97.89 52	96.72 24

v2v482		84.09 151	84.24 154	83.62 178	87.13 235	61.40 280	82.71 219	89.71 189	72.19 205	89.55 115	91.41 184	70.70 239	93.20 135	81.02 106	93.76 203	96.25 32

Baseline_NR-MVSNet		84.00 155	85.90 115	78.29 279	91.47 134	53.44 357	82.29 232	87.00 237	79.06 107	89.55 115	95.72 32	77.20 162	86.14 301	72.30 217	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	88.01 261	79.09 142	92.13 166	75.51 176	95.06 161	90.41 248

ambc				82.98 198	90.55 156	64.86 237	88.20 100	89.15 199		89.40 118	93.96 99	71.67 234	91.38 188	78.83 132	96.55 97	92.71 165

DeepPCF-MVS	81.24 5	87.28 88	86.21 109	90.49 42	91.48 133	84.90 42	83.41 198	92.38 107	70.25 226	89.35 119	90.68 212	82.85 92	94.57 81	79.55 124	95.95 127	92.00 202

MVStest1		70.05 334	69.26 337	72.41 341	58.62 428	55.59 341	76.61 319	65.58 397	53.44 369	89.28 120	93.32 120	22.91 428	71.44 384	74.08 192	89.52 292	90.21 255

test_fmvsmconf0.01_n		86.68 96	86.52 103	87.18 94	85.94 268	78.30 89	86.93 120	92.20 112	65.94 269	89.16 121	93.16 124	83.10 89	89.89 235	87.81 16	94.43 185	93.35 137

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	72.03 230	96.36 4	88.21 12	90.93 268	92.98 156
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 75	95.30 153	93.60 130

MDA-MVSNet-bldmvs		77.47 258	76.90 264	79.16 265	79.03 363	64.59 238	66.58 393	75.67 339	73.15 188	88.86 124	88.99 248	66.94 256	81.23 344	64.71 287	88.22 313	91.64 215

EG-PatchMatch MVS		84.08 152	84.11 155	83.98 167	92.22 103	72.61 151	82.20 238	87.02 234	72.63 196	88.86 124	91.02 196	78.52 145	91.11 194	73.41 203	91.09 262	88.21 286

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	77.55 158	95.86 23	84.88 64	95.87 132	95.24 60

EI-MVSNet-UG-set		85.04 127	84.44 149	86.85 101	83.87 304	72.52 154	83.82 187	85.15 263	80.27 90	88.75 127	85.45 308	79.95 138	91.90 173	81.92 101	90.80 274	96.13 34

EI-MVSNet-Vis-set		85.12 125	84.53 147	86.88 100	84.01 300	72.76 145	83.91 185	85.18 262	80.44 86	88.75 127	85.49 306	80.08 136	91.92 172	82.02 98	90.85 273	95.97 39

balanced_conf03		84.80 132	85.40 127	83.00 197	88.95 188	61.44 279	90.42 58	92.37 108	71.48 211	88.72 129	93.13 125	70.16 242	95.15 63	79.26 129	94.11 194	92.41 180

OMC-MVS		88.19 74	87.52 85	90.19 48	91.94 114	81.68 65	87.49 112	93.17 76	76.02 141	88.64 130	91.22 189	84.24 78	93.37 131	77.97 147	97.03 84	95.52 51

RRT-MVS		82.97 178	83.44 164	81.57 229	85.06 281	58.04 321	87.20 114	90.37 167	77.88 123	88.59 131	93.70 113	63.17 278	93.05 142	76.49 164	88.47 305	93.62 128

test_fmvsmconf0.1_n		86.18 106	85.88 116	87.08 96	85.26 278	78.25 90	85.82 145	91.82 125	65.33 283	88.55 132	92.35 158	82.62 96	89.80 237	86.87 36	94.32 188	93.18 147

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	88.53 133	97.64 3	83.45 86	94.55 83	86.02 53	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	88.52 134	94.37 78	86.74 53	95.41 53	86.32 43	98.21 32	93.19 146
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	83.58 180	87.97 212	67.13 214	87.55 109	94.32 21	73.44 178	88.47 135	87.54 272	86.45 58	91.06 196	75.76 174	93.76 203	92.54 174

canonicalmvs		85.50 114	86.14 110	83.58 180	87.97 212	67.13 214	87.55 109	94.32 21	73.44 178	88.47 135	87.54 272	86.45 58	91.06 196	75.76 174	93.76 203	92.54 174

NR-MVSNet		86.00 108	86.22 108	85.34 135	93.24 76	64.56 240	82.21 236	90.46 163	80.99 82	88.42 137	91.97 166	77.56 157	93.85 107	72.46 216	98.65 12	97.61 10

alignmvs		83.94 157	83.98 158	83.80 171	87.80 218	67.88 210	84.54 171	91.42 136	73.27 186	88.41 138	87.96 262	72.33 223	90.83 206	76.02 172	94.11 194	92.69 166

TransMVSNet (Re)		84.02 154	85.74 121	78.85 267	91.00 146	55.20 346	82.29 232	87.26 224	79.65 98	88.38 139	95.52 37	83.00 90	86.88 285	67.97 260	96.60 96	94.45 86

PM-MVS		80.20 230	79.00 239	83.78 173	88.17 209	86.66 19	81.31 246	66.81 395	69.64 231	88.33 140	90.19 226	64.58 267	83.63 331	71.99 219	90.03 285	81.06 384

fmvsm_s_conf0.5_n_3		86.19 105	87.27 90	82.95 200	86.91 243	70.38 180	85.31 155	92.61 101	75.59 151	88.32 141	92.87 137	82.22 107	88.63 261	88.80 8	92.82 227	89.83 261

tttt0517		81.07 211	79.58 234	85.52 132	88.99 187	66.45 224	87.03 119	75.51 341	73.76 171	88.32 141	90.20 225	37.96 402	94.16 99	79.36 128	95.13 157	95.93 42

casdiffmvs		85.21 121	85.85 117	83.31 189	86.17 262	62.77 261	83.03 209	93.93 46	74.69 162	88.21 143	92.68 145	82.29 105	91.89 174	77.87 148	93.75 206	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		71.42 321	70.67 322	73.64 328	69.66 416	70.46 178	66.97 392	89.73 187	42.68 413	88.20 144	83.04 337	43.77 386	60.07 414	65.35 282	86.66 333	90.39 249

SSC-MVS		77.55 257	81.64 197	65.29 383	90.46 157	20.33 429	73.56 352	68.28 386	85.44 37	88.18 145	94.64 64	70.93 237	81.33 343	71.25 221	92.03 242	94.20 96

MVSMamba_PlusPlus		87.53 86	88.86 71	83.54 184	92.03 110	62.26 272	91.49 40	92.62 100	88.07 24	88.07 146	96.17 23	72.24 225	95.79 31	84.85 65	94.16 193	92.58 171

MGCFI-Net		85.04 127	85.95 113	82.31 216	87.52 226	63.59 250	86.23 138	93.96 44	73.46 176	88.07 146	87.83 267	86.46 57	90.87 205	76.17 169	93.89 200	92.47 178

v148		82.31 187	82.48 186	81.81 225	85.59 272	59.66 302	81.47 245	86.02 249	72.85 191	88.05 148	90.65 215	70.73 238	90.91 202	75.15 181	91.79 248	94.87 70

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	88.00 149	93.03 129	82.66 94	91.47 182	70.81 224	96.14 116	94.16 100

TestCases				89.68 55	91.59 124	83.40 52		95.44 10	79.47 99	88.00 149	93.03 129	82.66 94	91.47 182	70.81 224	96.14 116	94.16 100

fmvsm_s_conf0.1_n_2		83.82 159	83.49 163	84.84 141	85.99 267	70.19 183	80.93 253	87.58 220	67.26 261	87.94 151	92.37 156	71.40 235	88.01 268	86.03 50	91.87 247	96.31 31

pm-mvs1		83.69 162	84.95 136	79.91 254	90.04 168	59.66 302	82.43 228	87.44 221	75.52 153	87.85 152	95.26 45	81.25 123	85.65 311	68.74 252	96.04 121	94.42 89

PCF-MVS	74.62 15	82.15 194	80.92 214	85.84 125	89.43 177	72.30 158	80.53 258	91.82 125	57.36 348	87.81 153	89.92 233	77.67 156	93.63 115	58.69 328	95.08 160	91.58 217
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 165	83.29 168	84.62 149	85.43 275	70.18 184	80.61 257	87.24 225	67.14 262	87.79 154	91.87 168	71.79 232	87.98 269	86.00 54	91.77 250	95.71 45

mvs5depth		83.82 159	84.54 146	81.68 227	82.23 325	68.65 201	86.89 121	89.90 185	80.02 94	87.74 155	97.86 2	64.19 271	82.02 339	76.37 165	95.63 143	94.35 92

test_fmvsmconf_n		85.88 111	85.51 125	86.99 98	84.77 286	78.21 91	85.40 154	91.39 137	65.32 284	87.72 156	91.81 174	82.33 101	89.78 238	86.68 38	94.20 191	92.99 155

FMVSNet2		81.31 208	81.61 199	80.41 248	86.38 252	58.75 316	83.93 184	86.58 240	72.43 197	87.65 157	92.98 131	63.78 274	90.22 222	66.86 263	93.92 199	92.27 190

GeoE		85.45 117	85.81 118	84.37 155	90.08 164	67.07 216	85.86 144	91.39 137	72.33 202	87.59 158	90.25 224	84.85 71	92.37 160	78.00 145	91.94 246	93.66 124

VPA-MVSNet		83.47 170	84.73 138	79.69 258	90.29 160	57.52 326	81.30 248	88.69 204	76.29 137	87.58 159	94.44 71	80.60 131	87.20 279	66.60 268	96.82 90	94.34 93

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	87.50 160	92.38 153	81.42 121	93.28 133	83.07 82	97.24 79	91.67 214

VDDNet		84.35 142	85.39 128	81.25 233	95.13 32	59.32 305	85.42 153	81.11 304	86.41 32	87.41 161	96.21 22	73.61 204	90.61 214	66.33 270	96.85 87	93.81 119

c3_l		81.64 204	81.59 200	81.79 226	80.86 343	59.15 309	78.61 288	90.18 179	68.36 244	87.20 162	87.11 283	69.39 244	91.62 179	78.16 142	94.43 185	94.60 79

VDD-MVS		84.23 148	84.58 144	83.20 192	91.17 142	65.16 236	83.25 203	84.97 270	79.79 95	87.18 163	94.27 79	74.77 192	90.89 203	69.24 242	96.54 98	93.55 135

MSLP-MVS++		85.00 130	86.03 112	81.90 220	91.84 119	71.56 171	86.75 128	93.02 87	75.95 144	87.12 164	89.39 240	77.98 150	89.40 249	77.46 152	94.78 174	84.75 329

baseline		85.20 122	85.93 114	83.02 196	86.30 257	62.37 269	84.55 169	93.96 44	74.48 164	87.12 164	92.03 165	82.30 103	91.94 171	78.39 135	94.21 190	94.74 77

YYNet1		70.06 333	70.44 326	68.90 362	73.76 400	53.42 358	58.99 410	67.20 391	58.42 338	87.10 166	85.39 310	59.82 298	67.32 399	59.79 324	83.50 369	85.96 314

MDA-MVSNet_test_wron		70.05 334	70.44 326	68.88 363	73.84 399	53.47 356	58.93 411	67.28 390	58.43 337	87.09 167	85.40 309	59.80 299	67.25 400	59.66 325	83.54 368	85.92 316

test_fmvs3		75.72 280	75.20 280	77.27 295	75.01 396	69.47 190	78.93 281	84.88 271	46.67 397	87.08 168	87.84 266	50.44 350	71.62 382	77.42 155	88.53 304	90.72 237

CNVR-MVS		87.81 83	87.68 83	88.21 83	92.87 84	77.30 107	85.25 156	91.23 142	77.31 131	87.07 169	91.47 183	82.94 91	94.71 75	84.67 67	96.27 110	92.62 169

EPP-MVSNet		85.47 116	85.04 133	86.77 103	91.52 132	69.37 191	91.63 39	87.98 217	81.51 77	87.05 170	91.83 172	66.18 261	95.29 56	70.75 227	96.89 86	95.64 48

TinyColmap		81.25 209	82.34 188	77.99 285	85.33 276	60.68 293	82.32 231	88.33 210	71.26 214	86.97 171	92.22 163	77.10 165	86.98 283	62.37 304	95.17 156	86.31 312

eth_miper_zixun_eth		80.84 214	80.22 226	82.71 207	81.41 335	60.98 289	77.81 297	90.14 180	67.31 260	86.95 172	87.24 280	64.26 269	92.31 162	75.23 180	91.61 253	94.85 74

Anonymous20240521		80.18 231	81.25 208	76.95 298	83.15 320	60.84 291	82.46 227	85.99 250	68.76 240	86.78 173	93.73 112	59.13 303	77.44 365	73.71 199	97.55 69	92.56 172

Patchmatch-RL test		74.48 293	73.68 292	76.89 301	84.83 284	66.54 222	72.29 360	69.16 385	57.70 344	86.76 174	86.33 293	45.79 371	82.59 335	69.63 239	90.65 280	81.54 375

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	86.75 175	93.26 121	93.64 2	90.93 200	84.60 68	90.75 275	93.97 107

h-mvs33		84.25 146	82.76 179	88.72 73	91.82 121	82.60 60	84.00 181	84.98 269	71.27 212	86.70 176	90.55 217	63.04 281	93.92 105	78.26 140	94.20 191	89.63 263

hse-mvs2		83.47 170	81.81 194	88.47 77	91.03 145	82.27 61	82.61 220	83.69 282	71.27 212	86.70 176	86.05 299	63.04 281	92.41 158	78.26 140	93.62 210	90.71 238

HPM-MVS++		88.93 68	88.45 76	90.38 44	94.92 36	85.85 31	89.70 71	91.27 141	78.20 118	86.69 178	92.28 160	80.36 133	95.06 67	86.17 48	96.49 100	90.22 251

TSAR-MVS + MP.		88.14 75	87.82 82	89.09 67	95.72 22	76.74 112	92.49 25	91.19 144	67.85 254	86.63 179	94.84 55	79.58 140	95.96 15	87.62 20	94.50 182	94.56 80
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 182	82.42 187	83.20 192	83.25 316	63.66 248	83.50 196	85.07 264	76.06 139	86.55 180	85.10 314	73.41 209	90.25 219	78.15 144	90.67 277	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	86.55 180	92.95 134	74.84 189	95.22 59	80.78 110	95.83 134	94.46 84

plane_prior3						76.85 111			77.79 125	86.55 180

BH-untuned		80.96 213	80.99 212	80.84 241	88.55 201	68.23 204	80.33 261	88.46 206	72.79 194	86.55 180	86.76 287	74.72 193	91.77 178	61.79 311	88.99 298	82.52 365

MVSTER		77.09 262	75.70 275	81.25 233	75.27 393	61.08 285	77.49 305	85.07 264	60.78 323	86.55 180	88.68 252	43.14 391	90.25 219	73.69 200	90.67 277	92.42 179

旧先验2							81.73 241		56.88 353	86.54 185			84.90 317	72.81 213

IterMVS-SCA-FT		80.64 218	79.41 235	84.34 159	83.93 302	69.66 188	76.28 324	81.09 305	72.43 197	86.47 186	90.19 226	60.46 291	93.15 138	77.45 153	86.39 337	90.22 251

WB-MVS		76.06 276	80.01 232	64.19 386	89.96 170	20.58 428	72.18 361	68.19 387	83.21 59	86.46 187	93.49 117	70.19 241	78.97 359	65.96 272	90.46 282	93.02 153

test_fmvsm_n_1920		83.60 166	82.89 177	85.74 127	85.22 279	77.74 99	84.12 178	90.48 162	59.87 332	86.45 188	91.12 193	75.65 180	85.89 307	82.28 95	90.87 271	93.58 131

DIV-MVS_self_test		80.43 221	80.23 224	81.02 239	79.99 351	59.25 306	77.07 310	87.02 234	67.38 257	86.19 189	89.22 243	63.09 279	90.16 224	76.32 166	95.80 136	93.66 124

CDPH-MVS		86.17 107	85.54 124	88.05 86	92.25 101	75.45 125	83.85 186	92.01 117	65.91 271	86.19 189	91.75 177	83.77 82	94.98 69	77.43 154	96.71 93	93.73 122

cl____		80.42 222	80.23 224	81.02 239	79.99 351	59.25 306	77.07 310	87.02 234	67.37 258	86.18 191	89.21 244	63.08 280	90.16 224	76.31 167	95.80 136	93.65 126

MVS_111021_LR		84.28 145	83.76 161	85.83 126	89.23 182	83.07 55	80.99 252	83.56 284	72.71 195	86.07 192	89.07 247	81.75 118	86.19 299	77.11 158	93.36 211	88.24 285

GBi-Net		82.02 197	82.07 189	81.85 222	86.38 252	61.05 286	86.83 124	88.27 212	72.43 197	86.00 193	95.64 34	63.78 274	90.68 211	65.95 273	93.34 212	93.82 116

test1		82.02 197	82.07 189	81.85 222	86.38 252	61.05 286	86.83 124	88.27 212	72.43 197	86.00 193	95.64 34	63.78 274	90.68 211	65.95 273	93.34 212	93.82 116

FMVSNet3		78.80 244	78.55 247	79.57 260	82.89 323	56.89 332	81.76 240	85.77 252	69.04 237	86.00 193	90.44 219	51.75 343	90.09 230	65.95 273	93.34 212	91.72 211

miper_ehance_all_eth		80.34 225	80.04 231	81.24 235	79.82 354	58.95 311	77.66 299	89.66 190	65.75 276	85.99 196	85.11 313	68.29 251	91.42 186	76.03 171	92.03 242	93.33 138

tfpnnormal		81.79 203	82.95 176	78.31 277	88.93 189	55.40 342	80.83 256	82.85 290	76.81 134	85.90 197	94.14 89	74.58 195	86.51 292	66.82 266	95.68 142	93.01 154

TAPA-MVS	77.73 12	85.71 113	84.83 137	88.37 80	88.78 194	79.72 77	87.15 117	93.50 62	69.17 234	85.80 198	89.56 238	80.76 128	92.13 166	73.21 211	95.51 144	93.25 144
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 156	82.69 181	87.72 89	89.27 181	81.45 67	83.72 191	81.58 302	74.73 161	85.66 199	86.06 298	72.56 222	92.69 152	75.44 178	95.21 154	89.01 279

EU-MVSNet		75.12 285	74.43 287	77.18 296	83.11 321	59.48 304	85.71 148	82.43 294	39.76 417	85.64 200	88.76 250	44.71 384	87.88 271	73.86 196	85.88 343	84.16 340

MonoMVSNet		76.66 268	77.26 260	74.86 320	79.86 353	54.34 350	86.26 137	86.08 246	71.08 217	85.59 201	88.68 252	53.95 333	85.93 303	63.86 294	80.02 388	84.32 335

LF4IMVS		82.75 181	81.93 192	85.19 136	82.08 326	80.15 74	85.53 150	88.76 203	68.01 249	85.58 202	87.75 268	71.80 231	86.85 286	74.02 193	93.87 201	88.58 282

Patchmtry		76.56 271	77.46 256	73.83 326	79.37 360	46.60 393	82.41 229	76.90 330	73.81 170	85.56 203	92.38 153	48.07 357	83.98 328	63.36 299	95.31 152	90.92 231

MVS_111021_HR		84.63 135	84.34 153	85.49 134	90.18 163	75.86 123	79.23 279	87.13 229	73.35 180	85.56 203	89.34 241	83.60 85	90.50 216	76.64 162	94.05 197	90.09 257

testdata				79.54 261	92.87 84	72.34 157		80.14 311	59.91 331	85.47 205	91.75 177	67.96 253	85.24 313	68.57 256	92.18 241	81.06 384

mvsmamba		80.30 227	78.87 240	84.58 151	88.12 211	67.55 212	92.35 29	84.88 271	63.15 294	85.33 206	90.91 202	50.71 347	95.20 62	66.36 269	87.98 315	90.99 228

test1111		78.53 248	78.85 242	77.56 291	92.22 103	47.49 389	82.61 220	69.24 384	72.43 197	85.28 207	94.20 85	51.91 341	90.07 231	65.36 281	96.45 103	95.11 65

thisisatest0530		79.07 239	77.33 259	84.26 162	87.13 235	64.58 239	83.66 193	75.95 336	68.86 239	85.22 208	87.36 277	38.10 399	93.57 123	75.47 177	94.28 189	94.62 78

BP-MVS1		82.81 179	81.67 196	86.23 113	87.88 216	68.53 202	86.06 140	84.36 277	75.65 149	85.14 209	90.19 226	45.84 370	94.42 86	85.18 60	94.72 178	95.75 44

EC-MVSNet		88.01 78	88.32 77	87.09 95	89.28 180	72.03 162	90.31 59	96.31 4	80.88 84	85.12 210	89.67 237	84.47 75	95.46 50	82.56 91	96.26 111	93.77 121

CLD-MVS		83.18 174	82.64 182	84.79 144	89.05 184	67.82 211	77.93 295	92.52 103	68.33 245	85.07 211	81.54 356	82.06 110	92.96 144	69.35 241	97.91 51	93.57 132
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		82.58 184	81.93 192	84.50 152	87.68 221	73.35 138	86.14 139	77.70 322	61.64 311	85.02 212	91.62 179	77.75 153	86.24 296	82.79 88	87.07 326	93.91 111

FA-MVS(test-final)		83.13 176	83.02 175	83.43 185	86.16 264	66.08 227	88.00 103	88.36 209	75.55 152	85.02 212	92.75 143	65.12 266	92.50 156	74.94 184	91.30 259	91.72 211

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	70.56 221	84.96 214	90.69 211	80.01 137	95.14 64	78.37 136	95.78 138	91.82 207
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	86.36 255	74.71 128	88.77 94	90.00 183	75.65 149	84.96 214	93.17 123	74.06 199	91.19 191	78.28 139	91.09 262	89.29 271

QAPM		82.59 183	82.59 184	82.58 210	86.44 250	66.69 221	89.94 67	90.36 168	67.97 251	84.94 216	92.58 148	72.71 219	92.18 165	70.63 230	87.73 319	88.85 280

fmvsm_l_conf0.5_n_3		85.11 126	84.96 135	85.56 131	87.49 228	75.69 124	84.71 165	90.61 160	67.64 256	84.88 217	92.05 164	82.30 103	88.36 264	83.84 76	91.10 261	92.62 169

VPNet		80.25 228	81.68 195	75.94 312	92.46 95	47.98 387	76.70 315	81.67 300	73.45 177	84.87 218	92.82 139	74.66 194	86.51 292	61.66 313	96.85 87	93.33 138

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	84.85 219	90.89 203	80.85 127	95.29 56	81.14 105	95.32 150	92.34 185

PHI-MVS		86.38 100	85.81 118	88.08 84	88.44 204	77.34 105	89.35 85	93.05 83	73.15 188	84.76 220	87.70 269	78.87 144	94.18 95	80.67 112	96.29 107	92.73 162

pmmvs-eth3d		78.42 250	77.04 262	82.57 212	87.44 229	74.41 131	80.86 255	79.67 313	55.68 357	84.69 221	90.31 223	60.91 289	85.42 312	62.20 306	91.59 254	87.88 295

test_prior2							83.37 199		75.43 154	84.58 222	91.57 180	81.92 115		79.54 125	96.97 85

fmvsm_s_conf0.5_n_a		82.21 190	81.51 204	84.32 160	86.56 248	73.35 138	85.46 151	77.30 326	61.81 307	84.51 223	90.88 205	77.36 160	86.21 298	82.72 89	86.97 331	93.38 136

TEST9					92.34 98	79.70 78	83.94 182	90.32 170	65.41 282	84.49 224	90.97 198	82.03 111	93.63 115

train_agg		85.98 109	85.28 130	88.07 85	92.34 98	79.70 78	83.94 182	90.32 170	65.79 273	84.49 224	90.97 198	81.93 113	93.63 115	81.21 104	96.54 98	90.88 233

fmvsm_s_conf0.1_n		82.17 192	81.59 200	83.94 170	86.87 246	71.57 170	85.19 158	77.42 325	62.27 305	84.47 226	91.33 186	76.43 176	85.91 305	83.14 79	87.14 324	94.33 94

Gipuma		84.44 140	86.33 106	78.78 268	84.20 298	73.57 136	89.55 77	90.44 164	84.24 48	84.38 227	94.89 53	76.35 179	80.40 351	76.14 170	96.80 91	82.36 367
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 372	65.85 361	59.67 397	66.54 421	62.24 274	57.76 413	70.96 375	40.13 415	84.36 228	82.09 349	46.93 359	51.67 421	61.99 309	81.89 379	65.12 412

test_8					92.09 107	78.87 85	83.82 187	90.31 172	65.79 273	84.36 228	90.96 200	81.93 113	93.44 128

cl22		78.97 240	78.21 252	81.24 235	77.74 368	59.01 310	77.46 306	87.13 229	65.79 273	84.32 230	85.10 314	58.96 305	90.88 204	75.36 179	92.03 242	93.84 114

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	84.32 230	89.33 242	83.87 79	94.53 84	82.45 92	94.89 169	94.90 68

agg_prior					91.58 127	77.69 100		90.30 173		84.32 230			93.18 136

Anonymous202405211		80.51 220	81.19 211	78.49 274	88.48 202	57.26 328	76.63 317	82.49 293	81.21 80	84.30 233	92.24 162	67.99 252	86.24 296	62.22 305	95.13 157	91.98 204

LFMVS		80.15 232	80.56 218	78.89 266	89.19 183	55.93 336	85.22 157	73.78 353	82.96 63	84.28 234	92.72 144	57.38 315	90.07 231	63.80 295	95.75 139	90.68 240

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	84.27 235	94.05 92	78.35 148	93.65 113	80.54 114	91.58 255	92.08 198
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 249	78.63 246	77.88 287	91.85 117	48.95 383	83.68 192	69.91 380	72.30 203	84.26 236	94.20 85	51.89 342	89.82 236	63.58 296	96.02 122	94.87 70

FE-MVS		79.98 235	78.86 241	83.36 187	86.47 249	66.45 224	89.73 70	84.74 275	72.80 193	84.22 237	91.38 185	44.95 382	93.60 119	63.93 293	91.50 256	90.04 258

ETV-MVS		84.31 143	83.91 160	85.52 132	88.58 200	70.40 179	84.50 173	93.37 64	78.76 113	84.07 238	78.72 380	80.39 132	95.13 65	73.82 197	92.98 223	91.04 227

fmvsm_s_conf0.5_n		81.91 201	81.30 207	83.75 174	86.02 266	71.56 171	84.73 164	77.11 329	62.44 302	84.00 239	90.68 212	76.42 177	85.89 307	83.14 79	87.11 325	93.81 119

MCST-MVS		84.36 141	83.93 159	85.63 129	91.59 124	71.58 169	83.52 195	92.13 114	61.82 306	83.96 240	89.75 236	79.93 139	93.46 127	78.33 138	94.34 187	91.87 206

新几何1				82.95 200	93.96 59	78.56 88		80.24 310	55.45 358	83.93 241	91.08 195	71.19 236	88.33 265	65.84 276	93.07 220	81.95 371

mmtdpeth		85.13 124	85.78 120	83.17 194	84.65 288	74.71 128	85.87 143	90.35 169	77.94 121	83.82 242	96.96 12	77.75 153	80.03 354	78.44 134	96.21 112	94.79 76

fmvsm_l_conf0.5_n		82.06 196	81.54 203	83.60 179	83.94 301	73.90 134	83.35 200	86.10 245	58.97 334	83.80 243	90.36 220	74.23 197	86.94 284	82.90 85	90.22 283	89.94 259

GDP-MVS		82.17 192	80.85 216	86.15 120	88.65 197	68.95 199	85.65 149	93.02 87	68.42 243	83.73 244	89.54 239	45.07 381	94.31 88	79.66 123	93.87 201	95.19 63

BH-RMVSNet		80.53 219	80.22 226	81.49 231	87.19 234	66.21 226	77.79 298	86.23 243	74.21 166	83.69 245	88.50 255	73.25 214	90.75 208	63.18 301	87.90 316	87.52 299

USDC		76.63 269	76.73 266	76.34 308	83.46 309	57.20 329	80.02 264	88.04 216	52.14 379	83.65 246	91.25 188	63.24 277	86.65 290	54.66 355	94.11 194	85.17 324

miper_enhance_ethall		77.83 253	76.93 263	80.51 246	76.15 385	58.01 322	75.47 336	88.82 201	58.05 342	83.59 247	80.69 360	64.41 268	91.20 190	73.16 212	92.03 242	92.33 186

MM		87.64 85	87.15 91	89.09 67	89.51 174	76.39 118	88.68 96	86.76 238	84.54 46	83.58 248	93.78 108	73.36 212	96.48 2	87.98 14	96.21 112	94.41 90

Effi-MVS+-dtu		85.82 112	83.38 166	93.14 4	87.13 235	91.15 3	87.70 108	88.42 207	74.57 163	83.56 249	85.65 303	78.49 147	94.21 93	72.04 218	92.88 225	94.05 105

CNLPA		83.55 168	83.10 174	84.90 140	89.34 179	83.87 50	84.54 171	88.77 202	79.09 106	83.54 250	88.66 254	74.87 188	81.73 341	66.84 265	92.29 236	89.11 273

SDMVSNet		81.90 202	83.17 172	78.10 282	88.81 192	62.45 267	76.08 328	86.05 248	73.67 172	83.41 251	93.04 127	82.35 100	80.65 348	70.06 236	95.03 162	91.21 223

sd_testset		79.95 236	81.39 206	75.64 315	88.81 192	58.07 320	76.16 327	82.81 291	73.67 172	83.41 251	93.04 127	80.96 126	77.65 364	58.62 329	95.03 162	91.21 223

OpenMVS_ROB	70.19 17	77.77 256	77.46 256	78.71 270	84.39 294	61.15 284	81.18 250	82.52 292	62.45 301	83.34 253	87.37 276	66.20 260	88.66 260	64.69 288	85.02 353	86.32 311

thres100view900		75.45 281	75.05 281	76.66 304	87.27 231	51.88 369	81.07 251	73.26 358	75.68 148	83.25 254	86.37 292	45.54 372	88.80 255	51.98 371	90.99 264	89.31 269

miper_lstm_enhance		76.45 273	76.10 271	77.51 292	76.72 379	60.97 290	64.69 397	85.04 266	63.98 291	83.20 255	88.22 258	56.67 319	78.79 361	73.22 206	93.12 219	92.78 161

IterMVS		76.91 264	76.34 269	78.64 271	80.91 341	64.03 245	76.30 323	79.03 316	64.88 287	83.11 256	89.16 245	59.90 297	84.46 321	68.61 254	85.15 351	87.42 300
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 277	75.35 279	77.85 289	87.01 241	51.84 370	80.45 259	73.26 358	75.20 157	83.10 257	86.31 295	45.54 372	89.05 251	55.03 353	92.24 238	92.66 167

mvs_anonymous		78.13 251	78.76 244	76.23 311	79.24 361	50.31 380	78.69 286	84.82 273	61.60 312	83.09 258	92.82 139	73.89 202	87.01 280	68.33 258	86.41 336	91.37 220

fmvsm_l_conf0.5_n_a		81.46 206	80.87 215	83.25 190	83.73 306	73.21 143	83.00 211	85.59 256	58.22 340	82.96 259	90.09 231	72.30 224	86.65 290	81.97 100	89.95 287	89.88 260

test_fmvs2		73.57 301	72.80 303	75.90 313	72.74 409	68.84 200	77.07 310	84.32 279	45.14 403	82.89 260	84.22 326	48.37 355	70.36 386	73.40 204	87.03 328	88.52 283

MVS_Test		82.47 186	83.22 169	80.22 251	82.62 324	57.75 325	82.54 225	91.96 120	71.16 216	82.89 260	92.52 150	77.41 159	90.50 216	80.04 117	87.84 318	92.40 182

reproduce_monomvs		74.09 297	73.23 298	76.65 305	76.52 380	54.54 348	77.50 304	81.40 303	65.85 272	82.86 262	86.67 288	27.38 422	84.53 320	70.24 234	90.66 279	90.89 232

test12				86.57 105	90.74 151	72.63 150		90.69 156		82.76 263		79.20 141	94.80 73		95.32 150	92.27 190

原ACMM1				84.60 150	92.81 89	74.01 133		91.50 132	62.59 297	82.73 264	90.67 214	76.53 175	94.25 91	69.24 242	95.69 141	85.55 320

test_yl		78.71 246	78.51 248	79.32 263	84.32 295	58.84 313	78.38 289	85.33 259	75.99 142	82.49 265	86.57 289	58.01 309	90.02 233	62.74 302	92.73 229	89.10 274

DCV-MVSNet		78.71 246	78.51 248	79.32 263	84.32 295	58.84 313	78.38 289	85.33 259	75.99 142	82.49 265	86.57 289	58.01 309	90.02 233	62.74 302	92.73 229	89.10 274

diffmvs		80.40 223	80.48 221	80.17 252	79.02 364	60.04 297	77.54 302	90.28 176	66.65 267	82.40 267	87.33 278	73.50 206	87.35 277	77.98 146	89.62 291	93.13 148
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	79.38 274	77.79 321	52.59 374	82.36 268	90.84 207	66.83 258			91.69 251	81.25 379

D2MVS		76.84 265	75.67 276	80.34 249	80.48 349	62.16 275	73.50 353	84.80 274	57.61 346	82.24 269	87.54 272	51.31 344	87.65 273	70.40 233	93.19 218	91.23 222

VNet		79.31 238	80.27 223	76.44 306	87.92 215	53.95 353	75.58 334	84.35 278	74.39 165	82.23 270	90.72 210	72.84 218	84.39 323	60.38 321	93.98 198	90.97 229

Vis-MVSNet (Re-imp)		77.82 254	77.79 255	77.92 286	88.82 191	51.29 374	83.28 201	71.97 368	74.04 167	82.23 270	89.78 235	57.38 315	89.41 248	57.22 337	95.41 146	93.05 152

API-MVS		82.28 188	82.61 183	81.30 232	86.29 258	69.79 185	88.71 95	87.67 219	78.42 117	82.15 272	84.15 328	77.98 150	91.59 180	65.39 280	92.75 228	82.51 366

DP-MVS Recon		84.05 153	83.22 169	86.52 107	91.73 122	75.27 126	83.23 205	92.40 105	72.04 206	82.04 273	88.33 257	77.91 152	93.95 104	66.17 271	95.12 159	90.34 250

MSDG		80.06 234	79.99 233	80.25 250	83.91 303	68.04 209	77.51 303	89.19 198	77.65 126	81.94 274	83.45 334	76.37 178	86.31 295	63.31 300	86.59 334	86.41 310

test2506		74.12 296	73.39 296	76.28 309	91.85 117	44.20 403	84.06 179	48.20 424	72.30 203	81.90 275	94.20 85	27.22 424	89.77 239	64.81 286	96.02 122	94.87 70

Fast-Effi-MVS+		81.04 212	80.57 217	82.46 214	87.50 227	63.22 255	78.37 291	89.63 192	68.01 249	81.87 276	82.08 350	82.31 102	92.65 153	67.10 262	88.30 312	91.51 219

testgi		72.36 311	74.61 283	65.59 380	80.56 348	42.82 408	68.29 383	73.35 357	66.87 265	81.84 277	89.93 232	72.08 228	66.92 402	46.05 398	92.54 231	87.01 305

tfpn200view9		74.86 289	74.23 288	76.74 303	86.24 259	52.12 366	79.24 277	73.87 351	73.34 181	81.82 278	84.60 323	46.02 365	88.80 255	51.98 371	90.99 264	89.31 269

thres400		75.14 283	74.23 288	77.86 288	86.24 259	52.12 366	79.24 277	73.87 351	73.34 181	81.82 278	84.60 323	46.02 365	88.80 255	51.98 371	90.99 264	92.66 167

CL-MVSNet_self_test		76.81 266	77.38 258	75.12 318	86.90 244	51.34 372	73.20 356	80.63 309	68.30 246	81.80 280	88.40 256	66.92 257	80.90 345	55.35 350	94.90 168	93.12 150

OpenMVS	76.72 13	81.98 199	82.00 191	81.93 219	84.42 293	68.22 205	88.50 99	89.48 195	66.92 264	81.80 280	91.86 169	72.59 221	90.16 224	71.19 223	91.25 260	87.40 301

MVS_0304		85.37 118	84.58 144	87.75 88	85.28 277	73.36 137	86.54 133	85.71 253	77.56 129	81.78 282	92.47 151	70.29 240	96.02 11	85.59 56	95.96 125	93.87 113

AdaColmap		83.66 163	83.69 162	83.57 182	90.05 167	72.26 159	86.29 136	90.00 183	78.19 119	81.65 283	87.16 281	83.40 87	94.24 92	61.69 312	94.76 177	84.21 339

SPE-MVS-test		87.00 90	86.43 105	88.71 74	89.46 176	77.46 102	89.42 84	95.73 7	77.87 124	81.64 284	87.25 279	82.43 98	94.53 84	77.65 149	96.46 102	94.14 102

DELS-MVS		81.44 207	81.25 208	82.03 218	84.27 297	62.87 259	76.47 322	92.49 104	70.97 218	81.64 284	83.83 329	75.03 186	92.70 151	74.29 186	92.22 240	90.51 246
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		83.10 177	82.54 185	84.77 145	92.90 83	69.10 198	86.65 129	90.62 159	54.66 364	81.46 286	90.81 208	76.98 167	94.38 87	72.62 214	96.18 114	90.82 235

TR-MVS		76.77 267	75.79 273	79.72 257	86.10 265	65.79 230	77.14 308	83.02 288	65.20 285	81.40 287	82.10 348	66.30 259	90.73 210	55.57 347	85.27 347	82.65 360

TAMVS		78.08 252	76.36 268	83.23 191	90.62 154	72.87 144	79.08 280	80.01 312	61.72 309	81.35 288	86.92 286	63.96 273	88.78 258	50.61 376	93.01 222	88.04 291

Effi-MVS+		83.90 158	84.01 157	83.57 182	87.22 233	65.61 232	86.55 132	92.40 105	78.64 114	81.34 289	84.18 327	83.65 84	92.93 146	74.22 187	87.87 317	92.17 195

testing3		71.53 320	70.79 321	73.77 327	88.89 190	41.86 410	76.60 320	59.12 414	72.83 192	80.97 290	82.08 350	19.80 430	87.33 278	65.12 283	91.68 252	92.13 197

new-patchmatchnet		70.10 332	73.37 297	60.29 396	81.23 338	16.95 431	59.54 407	74.62 344	62.93 295	80.97 290	87.93 264	62.83 283	71.90 380	55.24 351	95.01 165	92.00 202

PVSNet_Blended_VisFu		81.55 205	80.49 220	84.70 148	91.58 127	73.24 142	84.21 175	91.67 129	62.86 296	80.94 292	87.16 281	67.27 255	92.87 149	69.82 238	88.94 300	87.99 292

BH-w/o		76.57 270	76.07 272	78.10 282	86.88 245	65.92 229	77.63 300	86.33 241	65.69 277	80.89 293	79.95 369	68.97 249	90.74 209	53.01 366	85.25 348	77.62 395

PAPM_NR		83.23 173	83.19 171	83.33 188	90.90 148	65.98 228	88.19 101	90.78 154	78.13 120	80.87 294	87.92 265	73.49 208	92.42 157	70.07 235	88.40 306	91.60 216

ab-mvs		79.67 237	80.56 218	76.99 297	88.48 202	56.93 330	84.70 166	86.06 247	68.95 238	80.78 295	93.08 126	75.30 184	84.62 319	56.78 338	90.90 269	89.43 267

XXY-MVS		74.44 295	76.19 270	69.21 360	84.61 289	52.43 365	71.70 364	77.18 328	60.73 324	80.60 296	90.96 200	75.44 181	69.35 389	56.13 343	88.33 308	85.86 317

HQP4-MVS										80.56 297			94.61 79			93.56 133

HQP-NCC					91.19 139		84.77 161		73.30 183	80.55 298

ACMP_Plane					91.19 139		84.77 161		73.30 183	80.55 298

HQP-MVS		84.61 136	84.06 156	86.27 112	91.19 139	70.66 176	84.77 161	92.68 98	73.30 183	80.55 298	90.17 229	72.10 226	94.61 79	77.30 156	94.47 183	93.56 133

test_cas_vis1_n_1920		69.20 345	69.12 338	69.43 359	73.68 401	62.82 260	70.38 376	77.21 327	46.18 400	80.46 301	78.95 378	52.03 340	65.53 407	65.77 278	77.45 402	79.95 390

AUN-MVS		81.18 210	78.78 243	88.39 79	90.93 147	82.14 62	82.51 226	83.67 283	64.69 288	80.29 302	85.91 302	51.07 345	92.38 159	76.29 168	93.63 209	90.65 242

HyFIR lowres test		75.12 285	72.66 306	82.50 213	91.44 135	65.19 235	72.47 359	87.31 223	46.79 396	80.29 302	84.30 325	52.70 338	92.10 169	51.88 375	86.73 332	90.22 251

test20.03		73.75 300	74.59 285	71.22 347	81.11 339	51.12 376	70.15 377	72.10 367	70.42 222	80.28 304	91.50 182	64.21 270	74.72 376	46.96 395	94.58 181	87.82 297

mvsany_test3		65.48 366	62.97 375	73.03 333	69.99 415	76.17 121	64.83 395	43.71 426	43.68 408	80.25 305	87.05 285	52.83 337	63.09 413	51.92 374	72.44 408	79.84 391

F-COLMAP		84.97 131	83.42 165	89.63 57	92.39 96	83.40 52	88.83 92	91.92 121	73.19 187	80.18 306	89.15 246	77.04 166	93.28 133	65.82 277	92.28 237	92.21 193

GA-MVS		75.83 278	74.61 283	79.48 262	81.87 328	59.25 306	73.42 354	82.88 289	68.68 241	79.75 307	81.80 353	50.62 348	89.46 244	66.85 264	85.64 344	89.72 262

xiu_mvs_v1_base_debu		80.84 214	80.14 228	82.93 202	88.31 205	71.73 165	79.53 270	87.17 226	65.43 279	79.59 308	82.73 344	76.94 168	90.14 227	73.22 206	88.33 308	86.90 306

xiu_mvs_v1_base		80.84 214	80.14 228	82.93 202	88.31 205	71.73 165	79.53 270	87.17 226	65.43 279	79.59 308	82.73 344	76.94 168	90.14 227	73.22 206	88.33 308	86.90 306

xiu_mvs_v1_base_debi		80.84 214	80.14 228	82.93 202	88.31 205	71.73 165	79.53 270	87.17 226	65.43 279	79.59 308	82.73 344	76.94 168	90.14 227	73.22 206	88.33 308	86.90 306

test_fmvs1_n		70.94 325	70.41 328	72.53 339	73.92 398	66.93 219	75.99 329	84.21 281	43.31 410	79.40 311	79.39 374	43.47 387	68.55 394	69.05 247	84.91 356	82.10 369

patch_mono-2		78.89 241	79.39 236	77.41 294	84.78 285	68.11 207	75.60 332	83.11 287	60.96 321	79.36 312	89.89 234	75.18 185	72.97 377	73.32 205	92.30 234	91.15 225

UnsupCasMVSNet_eth		71.63 319	72.30 311	69.62 357	76.47 382	52.70 363	70.03 378	80.97 306	59.18 333	79.36 312	88.21 259	60.50 290	69.12 390	58.33 332	77.62 400	87.04 304

ppachtmachnet_test		74.73 292	74.00 290	76.90 300	80.71 346	56.89 332	71.53 367	78.42 318	58.24 339	79.32 314	82.92 341	57.91 312	84.26 325	65.60 279	91.36 258	89.56 264

MG-MVS		80.32 226	80.94 213	78.47 275	88.18 208	52.62 364	82.29 232	85.01 268	72.01 207	79.24 315	92.54 149	69.36 245	93.36 132	70.65 229	89.19 297	89.45 265

Fast-Effi-MVS+-dtu		82.54 185	81.41 205	85.90 123	85.60 271	76.53 115	83.07 208	89.62 193	73.02 190	79.11 316	83.51 332	80.74 129	90.24 221	68.76 251	89.29 294	90.94 230

CDS-MVSNet		77.32 260	75.40 277	83.06 195	89.00 186	72.48 155	77.90 296	82.17 296	60.81 322	78.94 317	83.49 333	59.30 301	88.76 259	54.64 356	92.37 233	87.93 294
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 303	73.54 294	72.43 340	84.92 283	47.79 388	79.89 266	74.00 349	65.93 270	78.81 318	86.28 296	56.36 321	81.63 342	56.63 339	79.04 395	87.87 296

ttmdpeth		71.72 317	70.67 322	74.86 320	73.08 406	55.88 337	77.41 307	69.27 383	55.86 356	78.66 319	93.77 110	38.01 401	75.39 373	60.12 322	89.87 288	93.31 140

EIA-MVS		82.19 191	81.23 210	85.10 138	87.95 214	69.17 197	83.22 206	93.33 67	70.42 222	78.58 320	79.77 372	77.29 161	94.20 94	71.51 220	88.96 299	91.93 205

thres200		72.34 312	71.55 318	74.70 323	83.48 308	51.60 371	75.02 339	73.71 354	70.14 228	78.56 321	80.57 363	46.20 363	88.20 267	46.99 394	89.29 294	84.32 335

our_test_3		71.85 315	71.59 315	72.62 337	80.71 346	53.78 354	69.72 379	71.71 372	58.80 336	78.03 322	80.51 365	56.61 320	78.84 360	62.20 306	86.04 342	85.23 323

KD-MVS_2432*1600		66.87 356	65.81 362	70.04 352	67.50 418	47.49 389	62.56 401	79.16 314	61.21 319	77.98 323	80.61 361	25.29 426	82.48 336	53.02 364	84.92 354	80.16 388

miper_refine_blended		66.87 356	65.81 362	70.04 352	67.50 418	47.49 389	62.56 401	79.16 314	61.21 319	77.98 323	80.61 361	25.29 426	82.48 336	53.02 364	84.92 354	80.16 388

jason		77.42 259	75.75 274	82.43 215	87.10 238	69.27 192	77.99 294	81.94 298	51.47 383	77.84 325	85.07 317	60.32 293	89.00 252	70.74 228	89.27 296	89.03 277
jason: jason.
MAR-MVS		80.24 229	78.74 245	84.73 146	86.87 246	78.18 92	85.75 146	87.81 218	65.67 278	77.84 325	78.50 381	73.79 203	90.53 215	61.59 314	90.87 271	85.49 322
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		72.29 313	72.00 312	73.14 331	88.63 198	85.00 40	74.65 343	67.39 389	71.94 208	77.80 327	87.66 270	50.48 349	75.83 371	49.95 378	79.51 389	58.58 418

test_fmvs1		69.57 340	69.05 340	71.14 349	69.15 417	65.77 231	73.98 348	83.32 285	42.83 412	77.77 328	78.27 383	43.39 390	68.50 395	68.39 257	84.38 363	79.15 392

pmmvs4		74.92 288	72.98 302	80.73 243	84.95 282	71.71 168	76.23 325	77.59 323	52.83 373	77.73 329	86.38 291	56.35 322	84.97 316	57.72 336	87.05 327	85.51 321

ET-MVSNet_ETH3D		75.28 282	72.77 304	82.81 206	83.03 322	68.11 207	77.09 309	76.51 334	60.67 325	77.60 330	80.52 364	38.04 400	91.15 193	70.78 226	90.68 276	89.17 272

UnsupCasMVSNet_bld		69.21 344	69.68 335	67.82 370	79.42 358	51.15 375	67.82 387	75.79 337	54.15 366	77.47 331	85.36 312	59.26 302	70.64 385	48.46 388	79.35 391	81.66 373

WBMVS		68.76 347	68.43 347	69.75 356	83.29 314	40.30 413	67.36 389	72.21 366	57.09 351	77.05 332	85.53 305	33.68 409	80.51 349	48.79 386	90.90 269	88.45 284

Anonymous20231206		71.38 322	71.88 313	69.88 354	86.31 256	54.37 349	70.39 375	74.62 344	52.57 375	76.73 333	88.76 250	59.94 296	72.06 379	44.35 402	93.23 217	83.23 355

CMPMVS	59.41 20	75.12 285	73.57 293	79.77 255	75.84 388	67.22 213	81.21 249	82.18 295	50.78 388	76.50 334	87.66 270	55.20 329	82.99 334	62.17 308	90.64 281	89.09 276
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 314	71.69 314	73.32 329	81.57 333	53.02 360	76.77 314	78.37 319	63.31 292	76.37 335	91.85 170	36.68 404	78.98 358	47.87 391	92.45 232	87.95 293

CVMVSNet		72.62 309	71.41 319	76.28 309	83.25 316	60.34 295	83.50 196	79.02 317	37.77 421	76.33 336	85.10 314	49.60 353	87.41 276	70.54 231	77.54 401	81.08 382

PLC	73.85 16	82.09 195	80.31 222	87.45 92	90.86 150	80.29 73	85.88 142	90.65 157	68.17 248	76.32 337	86.33 293	73.12 215	92.61 154	61.40 315	90.02 286	89.44 266
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 189	81.57 202	84.19 165	85.54 273	69.26 193	91.98 34	90.08 181	71.54 209	76.23 338	85.07 317	58.69 306	94.27 89	86.26 44	88.77 301	89.03 277

lupinMVS		76.37 274	74.46 286	82.09 217	85.54 273	69.26 193	76.79 313	80.77 308	50.68 390	76.23 338	82.82 342	58.69 306	88.94 253	69.85 237	88.77 301	88.07 288

UWE-MVS		66.43 360	65.56 365	69.05 361	84.15 299	40.98 411	73.06 358	64.71 401	54.84 362	76.18 340	79.62 373	29.21 417	80.50 350	38.54 414	89.75 289	85.66 319

PatchMatch-RL		74.48 293	73.22 299	78.27 280	87.70 220	85.26 38	75.92 330	70.09 378	64.34 289	76.09 341	81.25 358	65.87 263	78.07 363	53.86 358	83.82 366	71.48 404

thisisatest0515		73.00 307	70.52 325	80.46 247	81.45 334	59.90 300	73.16 357	74.31 348	57.86 343	76.08 342	77.78 385	37.60 403	92.12 168	65.00 284	91.45 257	89.35 268

MS-PatchMatch		70.93 326	70.22 329	73.06 332	81.85 329	62.50 266	73.82 351	77.90 320	52.44 376	75.92 343	81.27 357	55.67 326	81.75 340	55.37 349	77.70 399	74.94 400

CHOSEN 1792x2688		72.45 310	70.56 324	78.13 281	90.02 169	63.08 256	68.72 382	83.16 286	42.99 411	75.92 343	85.46 307	57.22 317	85.18 315	49.87 380	81.67 380	86.14 313

CR-MVSNet		74.00 298	73.04 301	76.85 302	79.58 355	62.64 263	82.58 222	76.90 330	50.50 391	75.72 345	92.38 153	48.07 357	84.07 327	68.72 253	82.91 373	83.85 344

RPMNet		78.88 242	78.28 251	80.68 245	79.58 355	62.64 263	82.58 222	94.16 32	74.80 160	75.72 345	92.59 146	48.69 354	95.56 42	73.48 202	82.91 373	83.85 344

DPM-MVS		80.10 233	79.18 238	82.88 205	90.71 153	69.74 186	78.87 284	90.84 152	60.29 328	75.64 347	85.92 301	67.28 254	93.11 139	71.24 222	91.79 248	85.77 318

test_vis1_n		70.29 329	69.99 333	71.20 348	75.97 387	66.50 223	76.69 316	80.81 307	44.22 406	75.43 348	77.23 391	50.00 351	68.59 393	66.71 267	82.85 375	78.52 394

PVSNet_BlendedMVS		78.80 244	77.84 254	81.65 228	84.43 291	63.41 251	79.49 273	90.44 164	61.70 310	75.43 348	87.07 284	69.11 247	91.44 184	60.68 319	92.24 238	90.11 256

PVSNet_Blended		76.49 272	75.40 277	79.76 256	84.43 291	63.41 251	75.14 338	90.44 164	57.36 348	75.43 348	78.30 382	69.11 247	91.44 184	60.68 319	87.70 320	84.42 334

PAPR		78.84 243	78.10 253	81.07 237	85.17 280	60.22 296	82.21 236	90.57 161	62.51 298	75.32 351	84.61 322	74.99 187	92.30 163	59.48 326	88.04 314	90.68 240

N_pmnet		70.20 330	68.80 345	74.38 324	80.91 341	84.81 43	59.12 409	76.45 335	55.06 360	75.31 352	82.36 347	55.74 325	54.82 419	47.02 393	87.24 323	83.52 348

cascas		76.29 275	74.81 282	80.72 244	84.47 290	62.94 257	73.89 350	87.34 222	55.94 355	75.16 353	76.53 397	63.97 272	91.16 192	65.00 284	90.97 267	88.06 290

SCA		73.32 302	72.57 308	75.58 316	81.62 332	55.86 338	78.89 283	71.37 373	61.73 308	74.93 354	83.42 335	60.46 291	87.01 280	58.11 334	82.63 378	83.88 341

test_vis1_n_1920		71.30 323	71.58 317	70.47 350	77.58 371	59.99 299	74.25 344	84.22 280	51.06 385	74.85 355	79.10 376	55.10 330	68.83 392	68.86 250	79.20 394	82.58 362

xiu_mvs_v2_base		77.19 261	76.75 265	78.52 273	87.01 241	61.30 282	75.55 335	87.12 232	61.24 318	74.45 356	78.79 379	77.20 162	90.93 200	64.62 290	84.80 360	83.32 353

CANet		83.79 161	82.85 178	86.63 104	86.17 262	72.21 161	83.76 190	91.43 134	77.24 132	74.39 357	87.45 275	75.36 183	95.42 52	77.03 159	92.83 226	92.25 192

PS-MVSNAJ		77.04 263	76.53 267	78.56 272	87.09 239	61.40 280	75.26 337	87.13 229	61.25 317	74.38 358	77.22 392	76.94 168	90.94 199	64.63 289	84.83 359	83.35 352

MVP-Stereo		75.81 279	73.51 295	82.71 207	89.35 178	73.62 135	80.06 262	85.20 261	60.30 327	73.96 359	87.94 263	57.89 313	89.45 245	52.02 370	74.87 406	85.06 326
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 348	69.01 341	67.85 369	83.22 318	43.98 404	74.93 340	65.98 396	55.09 359	73.83 360	79.11 375	65.63 264	71.89 381	38.21 415	85.04 352	87.69 298

UGNet		82.78 180	81.64 197	86.21 116	86.20 261	76.24 120	86.86 122	85.68 254	77.07 133	73.76 361	92.82 139	69.64 243	91.82 177	69.04 248	93.69 207	90.56 244
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		74.82 290	73.74 291	78.04 284	89.57 172	60.04 297	76.49 321	87.09 233	54.31 365	73.66 362	79.80 370	60.25 294	86.76 289	58.37 330	84.15 364	87.32 302

Test_1112_low_res		73.90 299	73.08 300	76.35 307	90.35 159	55.95 335	73.40 355	86.17 244	50.70 389	73.14 363	85.94 300	58.31 308	85.90 306	56.51 340	83.22 370	87.20 303

1314		73.22 304	72.56 309	75.20 317	80.41 350	57.84 323	81.64 243	85.36 258	51.68 382	73.10 364	76.65 396	61.45 286	85.19 314	63.54 297	79.21 393	82.59 361

test_vis1_rt		65.64 365	64.09 369	70.31 351	66.09 422	70.20 182	61.16 404	81.60 301	38.65 418	72.87 365	69.66 411	52.84 336	60.04 415	56.16 342	77.77 398	80.68 386

Patchmatch-test		65.91 363	67.38 352	61.48 394	75.51 390	43.21 407	68.84 381	63.79 403	62.48 299	72.80 366	83.42 335	44.89 383	59.52 416	48.27 390	86.45 335	81.70 372

PatchmatchNet		69.71 339	68.83 344	72.33 342	77.66 370	53.60 355	79.29 275	69.99 379	57.66 345	72.53 367	82.93 340	46.45 362	80.08 353	60.91 318	72.09 409	83.31 354
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 350	68.08 351	67.55 371	78.74 366	43.53 406	75.60 332	67.10 394	54.92 361	72.23 368	88.10 260	42.87 392	75.97 370	52.21 369	80.95 387	83.15 356

pmmvs5		70.73 327	70.07 330	72.72 335	77.03 376	52.73 362	74.14 345	75.65 340	50.36 392	72.17 369	85.37 311	55.42 328	80.67 347	52.86 367	87.59 321	84.77 328

PatchT		70.52 328	72.76 305	63.79 388	79.38 359	33.53 422	77.63 300	65.37 399	73.61 174	71.77 370	92.79 142	44.38 385	75.65 372	64.53 291	85.37 346	82.18 368

MVS		73.21 305	72.59 307	75.06 319	80.97 340	60.81 292	81.64 243	85.92 251	46.03 401	71.68 371	77.54 387	68.47 250	89.77 239	55.70 346	85.39 345	74.60 401

MIMVSNet		71.09 324	71.59 315	69.57 358	87.23 232	50.07 381	78.91 282	71.83 369	60.20 330	71.26 372	91.76 176	55.08 331	76.09 369	41.06 407	87.02 329	82.54 364

WTY-MVS		67.91 351	68.35 348	66.58 377	80.82 344	48.12 386	65.96 394	72.60 361	53.67 368	71.20 373	81.68 355	58.97 304	69.06 391	48.57 387	81.67 380	82.55 363

test0.0.03 1		64.66 369	64.36 368	65.57 381	75.03 395	46.89 392	64.69 397	61.58 411	62.43 303	71.18 374	77.54 387	43.41 388	68.47 396	40.75 409	82.65 376	81.35 376

CostFormer		69.98 336	68.68 346	73.87 325	77.14 374	50.72 378	79.26 276	74.51 346	51.94 381	70.97 375	84.75 320	45.16 380	87.49 275	55.16 352	79.23 392	83.40 351

Syy-MVS		69.40 342	70.03 332	67.49 372	81.72 330	38.94 415	71.00 369	61.99 405	61.38 314	70.81 376	72.36 408	61.37 287	79.30 356	64.50 292	85.18 349	84.22 337

myMVS_eth3d		64.66 369	63.89 370	66.97 375	81.72 330	37.39 418	71.00 369	61.99 405	61.38 314	70.81 376	72.36 408	20.96 429	79.30 356	49.59 381	85.18 349	84.22 337

testing91		69.94 337	68.99 342	72.80 334	83.81 305	45.89 396	71.57 366	73.64 356	68.24 247	70.77 378	77.82 384	34.37 407	84.44 322	53.64 360	87.00 330	88.07 288

testing99		69.27 343	68.15 350	72.63 336	83.29 314	45.45 398	71.15 368	71.08 374	67.34 259	70.43 379	77.77 386	32.24 412	84.35 324	53.72 359	86.33 338	88.10 287

tpmvs		70.16 331	69.56 336	71.96 343	74.71 397	48.13 385	79.63 268	75.45 342	65.02 286	70.26 380	81.88 352	45.34 377	85.68 310	58.34 331	75.39 405	82.08 370

sss		66.92 355	67.26 353	65.90 379	77.23 373	51.10 377	64.79 396	71.72 371	52.12 380	70.13 381	80.18 367	57.96 311	65.36 408	50.21 377	81.01 386	81.25 379

tpm2		68.45 349	66.83 356	73.30 330	78.93 365	48.50 384	79.76 267	71.76 370	47.50 395	69.92 382	83.60 331	42.07 393	88.40 263	48.44 389	79.51 389	83.01 358

testing222		66.93 354	65.30 366	71.81 344	83.38 311	45.83 397	72.06 362	67.50 388	64.12 290	69.68 383	76.37 398	27.34 423	83.00 333	38.88 411	88.38 307	86.62 309

HY-MVS	64.64 18	73.03 306	72.47 310	74.71 322	83.36 313	54.19 351	82.14 239	81.96 297	56.76 354	69.57 384	86.21 297	60.03 295	84.83 318	49.58 382	82.65 376	85.11 325

dmvs_re		66.81 358	66.98 354	66.28 378	76.87 377	58.68 317	71.66 365	72.24 364	60.29 328	69.52 385	73.53 405	52.38 339	64.40 410	44.90 400	81.44 383	75.76 398

ETVMVS		64.67 368	63.34 374	68.64 365	83.44 310	41.89 409	69.56 380	61.70 410	61.33 316	68.74 386	75.76 400	28.76 418	79.35 355	34.65 418	86.16 341	84.67 330

tpm cat1		66.76 359	65.21 367	71.42 346	77.09 375	50.62 379	78.01 293	73.68 355	44.89 404	68.64 387	79.00 377	45.51 374	82.42 338	49.91 379	70.15 412	81.23 381

IB-MVS	62.13 19	71.64 318	68.97 343	79.66 259	80.80 345	62.26 272	73.94 349	76.90 330	63.27 293	68.63 388	76.79 394	33.83 408	91.84 176	59.28 327	87.26 322	84.88 327
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		80.37 224	78.41 250	86.23 113	76.75 378	73.28 140	87.18 116	77.45 324	76.24 138	68.14 389	88.93 249	65.41 265	93.85 107	69.47 240	96.12 118	91.55 218
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 361	65.63 364	68.75 364	81.96 327	49.88 382	62.19 403	72.51 363	51.03 386	68.04 390	75.34 402	50.84 346	74.77 374	45.82 399	82.96 371	81.60 374

tpmrst		66.28 362	66.69 358	65.05 384	72.82 408	39.33 414	78.20 292	70.69 377	53.16 372	67.88 391	80.36 366	48.18 356	74.75 375	58.13 333	70.79 411	81.08 382

CANet_DTU		77.81 255	77.05 261	80.09 253	81.37 336	59.90 300	83.26 202	88.29 211	69.16 235	67.83 392	83.72 330	60.93 288	89.47 243	69.22 244	89.70 290	90.88 233

EPMVS		62.47 373	62.63 377	62.01 390	70.63 414	38.74 416	74.76 341	52.86 421	53.91 367	67.71 393	80.01 368	39.40 397	66.60 403	55.54 348	68.81 417	80.68 386

UBG		64.34 371	63.35 373	67.30 373	83.50 307	40.53 412	67.46 388	65.02 400	54.77 363	67.54 394	74.47 404	32.99 411	78.50 362	40.82 408	83.58 367	82.88 359

MDTV_nov1_ep13			68.29 349		78.03 367	43.87 405	74.12 346	72.22 365	52.17 377	67.02 395	85.54 304	45.36 376	80.85 346	55.73 344	84.42 362

testing11		67.38 352	65.93 360	71.73 345	83.37 312	46.60 393	70.95 371	69.40 382	62.47 300	66.14 396	76.66 395	31.22 413	84.10 326	49.10 384	84.10 365	84.49 331

pmmvs3		62.47 373	60.02 386	69.80 355	71.58 412	64.00 246	70.52 374	58.44 417	39.77 416	66.05 397	75.84 399	27.10 425	72.28 378	46.15 397	84.77 361	73.11 402

ADS-MVSNet2		65.87 364	63.64 372	72.55 338	73.16 404	56.92 331	67.10 390	74.81 343	49.74 393	66.04 398	82.97 338	46.71 360	77.26 366	42.29 404	69.96 413	83.46 349

ADS-MVSNet		61.90 375	62.19 379	61.03 395	73.16 404	36.42 420	67.10 390	61.75 408	49.74 393	66.04 398	82.97 338	46.71 360	63.21 411	42.29 404	69.96 413	83.46 349

mvsany_test1		58.48 385	56.47 390	64.50 385	65.90 424	68.21 206	56.95 414	42.11 427	38.30 419	65.69 400	77.19 393	56.96 318	59.35 417	46.16 396	58.96 420	65.93 411

dmvs_testset		60.59 383	62.54 378	54.72 402	77.26 372	27.74 425	74.05 347	61.00 412	60.48 326	65.62 401	67.03 415	55.93 324	68.23 397	32.07 422	69.46 416	68.17 409

DSMNet-mixed		60.98 381	61.61 381	59.09 399	72.88 407	45.05 401	74.70 342	46.61 425	26.20 423	65.34 402	90.32 222	55.46 327	63.12 412	41.72 406	81.30 385	69.09 408

JIA-IIPM		69.41 341	66.64 359	77.70 290	73.19 403	71.24 173	75.67 331	65.56 398	70.42 222	65.18 403	92.97 133	33.64 410	83.06 332	53.52 362	69.61 415	78.79 393

test-LLR		67.21 353	66.74 357	68.63 366	76.45 383	55.21 344	67.89 384	67.14 392	62.43 303	65.08 404	72.39 406	43.41 388	69.37 387	61.00 316	84.89 357	81.31 377

test-mter		65.00 367	63.79 371	68.63 366	76.45 383	55.21 344	67.89 384	67.14 392	50.98 387	65.08 404	72.39 406	28.27 420	69.37 387	61.00 316	84.89 357	81.31 377

PMMVS2		55.64 388	59.27 387	44.74 404	64.30 426	12.32 432	40.60 419	49.79 423	53.19 371	65.06 406	84.81 319	53.60 335	49.76 422	32.68 421	89.41 293	72.15 403

baseline2		69.77 338	66.89 355	78.41 276	79.51 357	58.09 319	76.23 325	69.57 381	57.50 347	64.82 407	77.45 389	46.02 365	88.44 262	53.08 363	77.83 397	88.70 281

gg-mvs-nofinetune		68.96 346	69.11 339	68.52 368	76.12 386	45.32 399	83.59 194	55.88 419	86.68 29	64.62 408	97.01 9	30.36 415	83.97 329	44.78 401	82.94 372	76.26 397

PAPM		71.77 316	70.06 331	76.92 299	86.39 251	53.97 352	76.62 318	86.62 239	53.44 369	63.97 409	84.73 321	57.79 314	92.34 161	39.65 410	81.33 384	84.45 333

new_pmnet		55.69 387	57.66 388	49.76 403	75.47 391	30.59 423	59.56 406	51.45 422	43.62 409	62.49 410	75.48 401	40.96 395	49.15 423	37.39 416	72.52 407	69.55 407

MDTV_nov1_ep13_2view						27.60 426	70.76 373		46.47 399	61.27 411		45.20 378		49.18 383		83.75 346

dp		60.70 382	60.29 385	61.92 392	72.04 411	38.67 417	70.83 372	64.08 402	51.28 384	60.75 412	77.28 390	36.59 405	71.58 383	47.41 392	62.34 419	75.52 399

TESTMET0.1,1		61.29 378	60.32 384	64.19 386	72.06 410	51.30 373	67.89 384	62.09 404	45.27 402	60.65 413	69.01 412	27.93 421	64.74 409	56.31 341	81.65 382	76.53 396

PMMVS		61.65 376	60.38 383	65.47 382	65.40 425	69.26 193	63.97 399	61.73 409	36.80 422	60.11 414	68.43 413	59.42 300	66.35 404	48.97 385	78.57 396	60.81 415

PVSNet_0	51.08 22	56.10 386	54.97 391	59.48 398	75.12 394	53.28 359	55.16 415	61.89 407	44.30 405	59.16 415	62.48 418	54.22 332	65.91 406	35.40 417	47.01 421	59.25 417

MVS-HIRNet		61.16 379	62.92 376	55.87 400	79.09 362	35.34 421	71.83 363	57.98 418	46.56 398	59.05 416	91.14 192	49.95 352	76.43 368	38.74 412	71.92 410	55.84 419

E-PMN		61.59 377	61.62 380	61.49 393	66.81 420	55.40 342	53.77 416	60.34 413	66.80 266	58.90 417	65.50 416	40.48 396	66.12 405	55.72 345	86.25 339	62.95 414

GG-mvs-BLEND				67.16 374	73.36 402	46.54 395	84.15 177	55.04 420		58.64 418	61.95 419	29.93 416	83.87 330	38.71 413	76.92 403	71.07 405

EPNet_dtu		72.87 308	71.33 320	77.49 293	77.72 369	60.55 294	82.35 230	75.79 337	66.49 268	58.39 419	81.06 359	53.68 334	85.98 302	53.55 361	92.97 224	85.95 315
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 390	42.65 393	39.67 405	70.86 413	21.11 427	61.01 405	21.42 432	57.36 348	57.97 420	50.06 421	16.40 431	58.73 418	21.03 425	27.69 425	39.17 421

EMVS		61.10 380	60.81 382	61.99 391	65.96 423	55.86 338	53.10 417	58.97 416	67.06 263	56.89 421	63.33 417	40.98 394	67.03 401	54.79 354	86.18 340	63.08 413

CHOSEN 280x420		59.08 384	56.52 389	66.76 376	76.51 381	64.39 242	49.62 418	59.00 415	43.86 407	55.66 422	68.41 414	35.55 406	68.21 398	43.25 403	76.78 404	67.69 410

MVE	40.22 23	51.82 389	50.47 392	55.87 400	62.66 427	51.91 368	31.61 421	39.28 428	40.65 414	50.76 423	74.98 403	56.24 323	44.67 424	33.94 420	64.11 418	71.04 406
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 391	32.17 394	26.83 407	53.36 429	19.02 430	57.90 412	20.44 433	38.29 420	38.01 424	37.82 423	15.18 432	33.45 426	7.74 427	20.76 426	28.03 422

DeepMVS_CX				24.13 408	32.95 430	29.49 424		21.63 431	12.07 424	37.95 425	45.07 422	30.84 414	19.21 427	17.94 426	33.06 424	23.69 423

tmp_tt		20.25 394	24.50 397	7.49 409	4.47 432	8.70 433	34.17 420	25.16 430	1.00 427	32.43 426	18.49 424	39.37 398	9.21 428	21.64 424	43.75 422	4.57 424

test_method		30.46 392	29.60 395	33.06 406	17.99 431	3.84 434	13.62 422	73.92 350	2.79 425	18.29 427	53.41 420	28.53 419	43.25 425	22.56 423	35.27 423	52.11 420

EGC-MVSNET		74.79 291	69.99 333	89.19 65	94.89 38	87.00 15	91.89 37	86.28 242	1.09 426	2.23 428	95.98 27	81.87 116	89.48 242	79.76 120	95.96 125	91.10 226

testmvs		5.91 398	7.65 401	0.72 411	1.20 433	0.37 436	59.14 408	0.67 435	0.49 429	1.11 429	2.76 428	0.94 434	0.24 430	1.02 429	1.47 427	1.55 426

test123		6.27 397	8.08 400	0.84 410	1.11 434	0.57 435	62.90 400	0.82 434	0.54 428	1.07 430	2.75 429	1.26 433	0.30 429	1.04 428	1.26 428	1.66 425

mmdepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

monomultidepth		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

test_blank		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet_test		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

DCPMVS		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

cdsmvs_eth3d_5k		20.81 393	27.75 396	0.00 412	0.00 435	0.00 437	0.00 423	85.44 257	0.00 430	0.00 431	82.82 342	81.46 120	0.00 431	0.00 430	0.00 429	0.00 427

pcd_1.5k_mvsjas		6.41 396	8.55 399	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	76.94 168	0.00 431	0.00 430	0.00 429	0.00 427

sosnet-low-res		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

sosnet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uncertanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

Regformer		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

ab-mvs-re		6.65 395	8.87 398	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	79.80 370	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

uanet		0.00 399	0.00 402	0.00 412	0.00 435	0.00 437	0.00 423	0.00 436	0.00 430	0.00 431	0.00 430	0.00 435	0.00 431	0.00 430	0.00 429	0.00 427

WAC-MVS						37.39 418								52.61 368

MSC_two_6792asdad				88.81 71	91.55 129	77.99 94		91.01 148					96.05 9	87.45 24	98.17 35	92.40 182

No_MVS				88.81 71	91.55 129	77.99 94		91.01 148					96.05 9	87.45 24	98.17 35	92.40 182

eth-test2					0.00 435

eth-test					0.00 435

OPU-MVS				88.27 82	91.89 115	77.83 97	90.47 55				91.22 189	81.12 124	94.68 76	74.48 185	95.35 148	92.29 188

save fliter					93.75 63	77.44 103	86.31 135	89.72 188	70.80 219

test_0728_SECOND				86.79 102	94.25 48	72.45 156	90.54 52	94.10 39					95.88 18	86.42 40	97.97 46	92.02 201

GSMVS																83.88 341

sam_mvs1												46.11 364				83.88 341

sam_mvs												45.92 369

MTGPA								91.81 127

test_post1							78.85 285				3.13 426	45.19 379	80.13 352	58.11 334

test_post											3.10 427	45.43 375	77.22 367

patchmatchnet-post											81.71 354	45.93 368	87.01 280

MTMP							90.66 48	33.14 429

gm-plane-assit					75.42 392	44.97 402			52.17 377		72.36 408		87.90 270	54.10 357

test9_res														80.83 109	96.45 103	90.57 243

agg_prior2														79.68 122	96.16 115	90.22 251

test_prior4						78.97 84	84.59 168

test_prior				86.32 110	90.59 155	71.99 163		92.85 93					94.17 97			92.80 160

新几何2							81.72 242

旧先验1					91.97 111	71.77 164		81.78 299			91.84 171	73.92 201			93.65 208	83.61 347

无先验							82.81 217	85.62 255	58.09 341				91.41 187	67.95 261		84.48 332

原ACMM2							82.26 235

testdata2													86.43 294	63.52 298

segment_acmp												81.94 112

testdata1							79.62 269		73.95 169

plane_prior7					93.45 68	77.31 106

plane_prior6					92.61 90	76.54 113						74.84 189

plane_prior5								93.61 59					95.22 59	80.78 110	95.83 134	94.46 84

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		75.94 145						95.03 162

n2								0.00 436

nn								0.00 436

door-mid								74.45 347

test11								91.46 133

door								72.57 362

HQP5-MVS						70.66 176

BP-MVS														77.30 156

HQP3-MVS								92.68 98							94.47 183

HQP2-MVS												72.10 226

NP-MVS					91.95 112	74.55 130					90.17 229

ACMMP++_ref															95.74 140

ACMMP++															97.35 75

Test By Simon												79.09 142

High-resolution multi-view benchmark