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 68	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 47	97.23 2	95.32 2	99.01 2	97.26 9	80.16 139	98.99 1	95.15 1	99.14 2	96.47 35

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

DTE-MVSNet		89.98 48	91.91 18	84.21 171	96.51 7	57.84 340	88.93 91	92.84 97	91.92 4	96.16 4	96.23 24	86.95 52	95.99 12	79.05 140	98.57 15	98.80 6

PS-CasMVS		90.06 44	91.92 16	84.47 162	96.56 6	58.83 332	89.04 89	92.74 100	91.40 6	96.12 5	96.06 29	87.23 49	95.57 41	79.42 136	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 182	85.06 140	78.75 286	85.94 285	55.75 357	80.05 279	94.27 25	76.47 144	96.09 6	94.54 71	83.31 92	89.75 248	59.95 340	94.89 176	90.75 252

PEN-MVS		90.03 46	91.88 19	84.48 161	96.57 5	58.88 329	88.95 90	93.19 78	91.62 5	96.01 7	96.16 27	87.02 51	95.60 40	78.69 143	98.72 9	98.97 3

CP-MVSNet		89.27 63	90.91 45	84.37 163	96.34 8	58.61 335	88.66 98	92.06 120	90.78 7	95.67 8	95.17 51	81.80 121	95.54 44	79.00 141	98.69 10	98.95 4

reproduce_model		92.89 5	93.18 8	92.01 13	94.20 50	88.23 9	92.87 13	94.32 22	90.25 11	95.65 9	95.74 33	87.75 42	95.72 36	89.60 5	98.27 27	92.08 212

LTVRE_ROB	86.10 1	93.04 4	93.44 4	91.82 22	93.73 65	85.72 34	96.79 1	95.51 10	88.86 16	95.63 10	96.99 13	84.81 76	93.16 141	91.10 2	97.53 76	96.58 33
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 51	91.31 34	85.71 132	96.32 9	62.39 282	89.54 80	93.31 73	90.21 12	95.57 11	95.66 37	81.42 125	95.90 17	80.94 115	98.80 3	98.84 5

reproduce-ours		92.86 6	93.22 6	91.76 23	94.39 45	87.71 11	92.40 28	94.38 20	89.82 13	95.51 12	95.49 42	89.64 22	95.82 26	89.13 7	98.26 29	91.76 223

our_new_method		92.86 6	93.22 6	91.76 23	94.39 45	87.71 11	92.40 28	94.38 20	89.82 13	95.51 12	95.49 42	89.64 22	95.82 26	89.13 7	98.26 29	91.76 223

OurMVSNet-221017-0		90.01 47	89.74 57	90.83 36	93.16 82	80.37 73	91.91 37	93.11 82	81.10 87	95.32 14	97.24 10	72.94 228	94.85 72	85.07 68	97.78 58	97.26 16

anonymousdsp		89.73 54	88.88 74	92.27 8	89.82 178	86.67 18	90.51 55	90.20 183	69.87 242	95.06 15	96.14 28	84.28 81	93.07 145	87.68 23	96.34 110	97.09 20

wuyk23d		75.13 301	79.30 254	62.63 409	75.56 409	75.18 129	80.89 269	73.10 377	75.06 167	94.76 16	95.32 45	87.73 44	52.85 441	34.16 439	97.11 86	59.85 437

ACMH	76.49 14	89.34 60	91.14 36	83.96 178	92.50 98	70.36 190	89.55 78	93.84 53	81.89 79	94.70 17	95.44 44	90.69 9	88.31 275	83.33 86	98.30 26	93.20 154
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 93	87.45 93	86.45 112	92.52 97	69.19 207	87.84 111	88.05 227	81.66 81	94.64 18	96.53 20	65.94 276	94.75 76	83.02 92	96.83 93	95.41 58

mvs_tets		89.78 53	89.27 64	91.30 29	93.51 69	84.79 44	89.89 69	90.63 163	70.00 241	94.55 19	96.67 17	87.94 40	93.59 124	84.27 79	95.97 128	95.52 56

lecture		92.43 9	93.50 3	89.21 65	94.43 44	79.31 83	92.69 19	95.72 8	88.48 22	94.43 20	95.73 34	91.34 4	94.68 78	90.26 4	98.44 20	93.63 136

jajsoiax		89.41 58	88.81 77	91.19 32	93.38 75	84.72 45	89.70 72	90.29 180	69.27 246	94.39 21	96.38 21	86.02 66	93.52 128	83.96 81	95.92 134	95.34 60

test_0402		88.65 72	89.58 61	85.88 128	92.55 96	72.22 164	84.01 189	89.44 203	88.63 20	94.38 22	95.77 32	86.38 62	93.59 124	79.84 127	95.21 161	91.82 221

UniMVSNet_ETH3D		89.12 66	90.72 48	84.31 169	97.00 2	64.33 257	89.67 75	88.38 219	88.84 17	94.29 23	97.57 7	90.48 14	91.26 194	72.57 230	97.65 65	97.34 15

v7n		90.13 41	90.96 43	87.65 95	91.95 117	71.06 182	89.99 65	93.05 86	86.53 35	94.29 23	96.27 23	82.69 97	94.08 104	86.25 50	97.63 66	97.82 8

test_djsdf		89.62 55	89.01 68	91.45 26	92.36 102	82.98 57	91.98 35	90.08 186	71.54 221	94.28 25	96.54 19	81.57 123	94.27 92	86.26 48	96.49 104	97.09 20

PS-MVSNAJss		88.31 76	87.90 87	89.56 59	93.31 77	77.96 98	87.94 109	91.97 123	70.73 232	94.19 26	96.67 17	76.94 173	94.57 84	83.07 90	96.28 112	96.15 38

SED-MVS		90.46 38	91.64 22	86.93 103	94.18 51	72.65 150	90.47 56	93.69 57	83.77 58	94.11 27	94.27 83	90.28 15	95.84 24	86.03 54	97.92 51	92.29 202

test_241102_ONE					94.18 51	72.65 150		93.69 57	83.62 60	94.11 27	93.78 114	90.28 15	95.50 49

DPE-MVS		90.53 37	91.08 38	88.88 70	93.38 75	78.65 89	89.15 88	94.05 42	84.68 49	93.90 29	94.11 95	88.13 37	96.30 5	84.51 77	97.81 57	91.70 227
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
APDe-MVS		91.22 26	91.92 16	89.14 67	92.97 86	78.04 95	92.84 16	94.14 37	83.33 64	93.90 29	95.73 34	88.77 28	96.41 3	87.60 26	97.98 47	92.98 167
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMH+	77.89 11	90.73 32	91.50 26	88.44 80	93.00 85	76.26 121	89.65 76	95.55 9	87.72 27	93.89 31	94.94 56	91.62 3	93.44 132	78.35 147	98.76 4	95.61 55

ACMM	79.39 9	90.65 33	90.99 42	89.63 57	95.03 34	83.53 51	89.62 77	93.35 69	79.20 112	93.83 32	93.60 122	90.81 8	92.96 148	85.02 71	98.45 19	92.41 193
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SR-MVS-dyc-post		92.41 10	92.41 11	92.39 5	94.13 56	88.95 6	92.87 13	94.16 33	88.75 18	93.79 33	94.43 76	88.83 27	95.51 47	87.16 37	97.60 70	92.73 174

RE-MVS-def			92.61 9		94.13 56	88.95 6	92.87 13	94.16 33	88.75 18	93.79 33	94.43 76	90.64 11		87.16 37	97.60 70	92.73 174

DVP-MVS		90.06 44	91.32 33	86.29 115	94.16 54	72.56 156	90.54 53	91.01 153	83.61 61	93.75 35	94.65 65	89.76 19	95.78 32	86.42 44	97.97 48	90.55 263
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 42	93.75 35	94.65 65	87.44 47	95.78 32	87.41 30	98.21 33	92.98 167

test0726					94.16 54	72.56 156	90.63 50	93.90 49	83.61 61	93.75 35	94.49 73	89.76 19

LPG-MVS_test		91.47 22	91.68 21	90.82 37	94.75 41	81.69 63	90.00 63	94.27 25	82.35 74	93.67 38	94.82 60	91.18 5	95.52 45	85.36 64	98.73 7	95.23 66

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 25	82.35 74	93.67 38	94.82 60	91.18 5	95.52 45	85.36 64	98.73 7	95.23 66

DVP-MVS++		90.07 43	91.09 37	87.00 101	91.55 134	72.64 152	96.19 2	94.10 40	85.33 42	93.49 40	94.64 68	81.12 128	95.88 18	87.41 30	95.94 132	92.48 189

test_241102_TWO								93.71 56	83.77 58	93.49 40	94.27 83	89.27 24	95.84 24	86.03 54	97.82 56	92.04 214

test_one_0601					93.85 63	73.27 143		94.11 39	86.57 34	93.47 42	94.64 68	88.42 29

SR-MVS		92.23 11	92.34 12	91.91 17	94.89 38	87.85 10	92.51 25	93.87 52	88.20 24	93.24 43	94.02 100	90.15 17	95.67 38	86.82 41	97.34 80	92.19 208

APD-MVS_3200maxsize		92.05 13	92.24 13	91.48 25	93.02 84	85.17 39	92.47 27	95.05 15	87.65 28	93.21 44	94.39 81	90.09 18	95.08 66	86.67 43	97.60 70	94.18 106

testf1		89.30 61	89.12 65	89.84 52	88.67 204	85.64 35	90.61 51	93.17 79	86.02 38	93.12 45	95.30 46	84.94 73	89.44 253	74.12 204	96.10 123	94.45 93

APD_test2		89.30 61	89.12 65	89.84 52	88.67 204	85.64 35	90.61 51	93.17 79	86.02 38	93.12 45	95.30 46	84.94 73	89.44 253	74.12 204	96.10 123	94.45 93

Anonymous20231211		88.40 74	89.62 60	84.73 153	90.46 164	65.27 247	88.86 92	93.02 90	87.15 30	93.05 47	97.10 11	82.28 110	92.02 174	76.70 171	97.99 45	96.88 26

MP-MVS-pluss		90.81 31	91.08 38	89.99 50	95.97 14	79.88 76	88.13 104	94.51 19	75.79 155	92.94 48	94.96 55	88.36 31	95.01 68	90.70 3	98.40 21	95.09 72
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 68	89.88 54	86.22 119	91.63 128	77.07 111	89.82 70	93.77 54	78.90 116	92.88 49	92.29 167	86.11 64	90.22 229	86.24 51	97.24 83	91.36 236
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 36	90.60 50	90.35 45	94.36 47	80.98 69	89.16 87	94.05 42	79.03 115	92.87 50	93.74 117	90.60 12	95.21 61	82.87 94	98.76 4	94.87 77
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
TDRefinement		93.52 3	93.39 5	93.88 2	95.94 15	90.26 4	95.70 4	96.46 3	90.58 9	92.86 51	96.29 22	88.16 36	94.17 101	86.07 53	98.48 18	97.22 18

SMA-MVS		90.31 39	90.48 51	89.83 54	95.31 30	79.52 82	90.98 48	93.24 77	75.37 164	92.84 52	95.28 48	85.58 69	96.09 8	87.92 18	97.76 59	93.88 119
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 62	77.77 100				92.84 52

v10		86.54 104	87.10 99	84.84 147	88.16 219	63.28 268	86.64 134	92.20 116	75.42 163	92.81 54	94.50 72	74.05 209	94.06 105	83.88 82	96.28 112	97.17 19

dcpmvs_2		84.23 159	85.14 139	81.50 244	88.61 208	61.98 290	82.90 228	93.11 82	68.66 256	92.77 55	92.39 159	78.50 150	87.63 288	76.99 170	92.30 250	94.90 75

v8		86.22 109	86.83 106	84.36 165	87.82 227	62.35 284	86.42 138	91.33 143	76.78 143	92.73 56	94.48 74	73.41 220	93.72 116	83.10 89	95.41 153	97.01 23

nrg030		87.85 85	88.49 79	85.91 126	90.07 173	69.73 198	87.86 110	94.20 31	74.04 177	92.70 57	94.66 64	85.88 67	91.50 186	79.72 129	97.32 81	96.50 34

SteuartSystems-ACMMP		91.16 28	91.36 29	90.55 41	93.91 61	80.97 70	91.49 41	93.48 66	82.82 71	92.60 58	93.97 102	88.19 34	96.29 6	87.61 25	98.20 35	94.39 98
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 52	89.97 53	89.27 63	94.76 40	79.86 77	86.76 131	92.78 99	78.78 118	92.51 59	93.64 121	88.13 37	93.84 113	84.83 74	97.55 73	94.10 111
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
HPM-MVS_fast		92.50 8	92.54 10	92.37 6	95.93 16	85.81 33	92.99 12	94.23 28	85.21 44	92.51 59	95.13 52	90.65 10	95.34 55	88.06 16	98.15 38	95.95 46

K. test v3		85.14 131	84.73 146	86.37 113	91.13 150	69.63 200	85.45 156	76.68 350	84.06 56	92.44 61	96.99 13	62.03 302	94.65 80	80.58 121	93.24 228	94.83 82

ACMMP		91.91 15	91.87 20	92.03 12	95.53 27	85.91 28	93.35 11	94.16 33	82.52 73	92.39 62	94.14 93	89.15 26	95.62 39	87.35 32	98.24 31	94.56 87
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 40	90.80 47	88.68 77	92.86 90	77.09 110	91.19 45	95.74 6	81.38 84	92.28 63	93.80 112	86.89 53	94.64 81	85.52 63	97.51 77	94.30 102

COLMAP_ROB	83.01 3	91.97 14	91.95 15	92.04 11	93.68 66	86.15 24	93.37 10	95.10 14	90.28 10	92.11 64	95.03 54	89.75 21	94.93 70	79.95 126	98.27 27	95.04 73
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 48	89.84 55	90.41 43	94.91 37	84.50 48	89.49 82	93.98 44	79.68 104	92.09 65	93.89 110	83.80 85	93.10 144	82.67 98	98.04 40	93.64 135

TranMVSNet+NR-MVSNet		87.86 84	88.76 78	85.18 143	94.02 59	64.13 258	84.38 181	91.29 144	84.88 48	92.06 66	93.84 111	86.45 59	93.73 115	73.22 221	98.66 11	97.69 9

MTAPA		91.52 19	91.60 23	91.29 30	96.59 4	86.29 21	92.02 34	91.81 131	84.07 55	92.00 67	94.40 80	86.63 55	95.28 58	88.59 11	98.31 25	92.30 200

ACMMP_NAP		90.65 33	91.07 40	89.42 61	95.93 16	79.54 81	89.95 67	93.68 59	77.65 134	91.97 68	94.89 57	88.38 30	95.45 51	89.27 6	97.87 55	93.27 151

FC-MVSNet-test		85.93 117	87.05 101	82.58 221	92.25 106	56.44 351	85.75 150	93.09 84	77.33 138	91.94 69	94.65 65	74.78 197	93.41 134	75.11 195	98.58 14	97.88 7

sc_t1		87.70 88	88.94 71	83.99 176	93.47 70	67.15 225	85.05 165	88.21 226	86.81 32	91.87 70	97.65 5	85.51 71	87.91 281	74.22 200	97.63 66	96.92 25

lessismore_v0				85.95 125	91.10 151	70.99 183		70.91 394		91.79 71	94.42 78	61.76 303	92.93 150	79.52 135	93.03 233	93.93 116

HPM-MVS		92.13 12	92.20 14	91.91 17	95.58 26	84.67 46	93.51 8	94.85 16	82.88 70	91.77 72	93.94 108	90.55 13	95.73 35	88.50 12	98.23 32	95.33 61
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PGM-MVS		91.20 27	90.95 44	91.93 15	95.67 23	85.85 31	90.00 63	93.90 49	80.32 96	91.74 73	94.41 79	88.17 35	95.98 13	86.37 46	97.99 45	93.96 115

mPP-MVS		91.69 16	91.47 27	92.37 6	96.04 13	88.48 8	92.72 18	92.60 106	83.09 67	91.54 74	94.25 87	87.67 45	95.51 47	87.21 36	98.11 39	93.12 159

HFP-MVS		91.30 24	91.39 28	91.02 33	95.43 29	84.66 47	92.58 23	93.29 75	81.99 76	91.47 75	93.96 105	88.35 32	95.56 42	87.74 21	97.74 61	92.85 171

ACMMPR		91.49 20	91.35 31	91.92 16	95.74 20	85.88 30	92.58 23	93.25 76	81.99 76	91.40 76	94.17 92	87.51 46	95.87 20	87.74 21	97.76 59	93.99 113

GST-MVS		90.96 30	91.01 41	90.82 37	95.45 28	82.73 59	91.75 39	93.74 55	80.98 89	91.38 77	93.80 112	87.20 50	95.80 28	87.10 39	97.69 64	93.93 116

test_fmvsmvis_n_1920		85.22 128	85.36 137	84.81 149	85.80 287	76.13 124	85.15 163	92.32 113	61.40 333	91.33 78	90.85 218	83.76 87	86.16 316	84.31 78	93.28 227	92.15 210

ANet_high		83.17 188	85.68 130	75.65 331	81.24 357	45.26 417	79.94 281	92.91 94	83.83 57	91.33 78	96.88 16	80.25 138	85.92 320	68.89 266	95.89 137	95.76 48

ZNCC-MVS		91.26 25	91.34 32	91.01 34	95.73 21	83.05 56	92.18 32	94.22 30	80.14 99	91.29 80	93.97 102	87.93 41	95.87 20	88.65 10	97.96 50	94.12 110

casdiffmvs_mvg		86.72 99	87.51 92	84.36 165	87.09 253	65.22 248	84.16 185	94.23 28	77.89 130	91.28 81	93.66 120	84.35 80	92.71 154	80.07 123	94.87 179	95.16 70
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 57	89.63 59	89.26 64	92.57 95	81.34 68	90.19 62	93.08 85	80.87 91	91.13 82	93.19 129	86.22 63	95.97 14	82.23 104	97.18 85	90.45 265
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 63		91.84 124		88.80 94	95.32 13	75.14 166	91.07 83	92.89 143	87.27 48	93.78 114	83.69 85	97.55 73

CP-MVS		91.67 17	91.58 24	91.96 14	95.29 31	87.62 13	93.38 9	93.36 68	83.16 66	91.06 84	94.00 101	88.26 33	95.71 37	87.28 35	98.39 22	92.55 186

FIs		85.35 127	86.27 113	82.60 220	91.86 121	57.31 344	85.10 164	93.05 86	75.83 154	91.02 85	93.97 102	73.57 216	92.91 152	73.97 208	98.02 43	97.58 12

UniMVSNet_NR-MVSNet		86.84 97	87.06 100	86.17 122	92.86 90	67.02 229	82.55 237	91.56 134	83.08 68	90.92 86	91.82 181	78.25 153	93.99 106	74.16 202	98.35 23	97.49 13

DU-MVS		86.80 98	86.99 102	86.21 120	93.24 80	67.02 229	83.16 220	92.21 115	81.73 80	90.92 86	91.97 174	77.20 167	93.99 106	74.16 202	98.35 23	97.61 10

tt0805		88.09 80	89.79 56	82.98 209	93.26 79	63.94 261	91.10 46	89.64 197	85.07 45	90.91 88	91.09 205	89.16 25	91.87 179	82.03 105	95.87 138	93.13 157

V42		83.47 183	83.37 180	83.75 185	83.16 339	63.33 267	81.31 261	90.23 182	69.51 245	90.91 88	90.81 220	74.16 205	92.29 168	80.06 124	90.22 301	95.62 54

tt0320-xc		86.67 101	88.41 81	81.44 246	93.45 71	60.44 311	83.96 191	88.50 215	87.26 29	90.90 90	97.90 3	85.61 68	86.40 310	70.14 250	98.01 44	97.47 14

region2R		91.44 23	91.30 35	91.87 19	95.75 19	85.90 29	92.63 22	93.30 74	81.91 78	90.88 91	94.21 88	87.75 42	95.87 20	87.60 26	97.71 62	93.83 122

APD_test1		88.40 74	87.91 86	89.88 51	89.50 183	86.65 20	89.98 66	91.91 126	84.26 53	90.87 92	93.92 109	82.18 112	89.29 257	73.75 212	94.81 180	93.70 130

tt0320		86.63 103	88.36 82	81.41 247	93.57 68	60.73 308	84.37 182	88.61 214	87.00 31	90.75 93	97.98 2	85.54 70	86.45 308	69.75 255	97.70 63	97.06 22

WR-MVS		83.56 180	84.40 160	81.06 254	93.43 74	54.88 364	78.67 304	85.02 281	81.24 85	90.74 94	91.56 191	72.85 229	91.08 200	68.00 276	98.04 40	97.23 17

v1240		84.30 155	84.51 157	83.65 188	87.65 234	61.26 298	82.85 229	91.54 135	67.94 268	90.68 95	90.65 228	71.71 245	93.64 118	82.84 95	94.78 181	96.07 41

Elysia		88.71 70	88.89 72	88.19 86	91.26 144	72.96 146	88.10 105	93.59 63	84.31 51	90.42 96	94.10 96	74.07 206	94.82 73	88.19 14	95.92 134	96.80 27

StellarMVS		88.71 70	88.89 72	88.19 86	91.26 144	72.96 146	88.10 105	93.59 63	84.31 51	90.42 96	94.10 96	74.07 206	94.82 73	88.19 14	95.92 134	96.80 27

ZD-MVS					92.22 108	80.48 71		91.85 127	71.22 227	90.38 98	92.98 138	86.06 65	96.11 7	81.99 107	96.75 96

MIMVSNet1		83.63 177	84.59 152	80.74 258	94.06 58	62.77 275	82.72 231	84.53 290	77.57 136	90.34 99	95.92 31	76.88 179	85.83 326	61.88 327	97.42 78	93.62 137

LS3D		90.60 35	90.34 52	91.38 28	89.03 193	84.23 49	93.58 6	94.68 18	90.65 8	90.33 100	93.95 107	84.50 78	95.37 54	80.87 116	95.50 152	94.53 90

KD-MVS_self_test		81.93 214	83.14 186	78.30 295	84.75 304	52.75 378	80.37 276	89.42 204	70.24 239	90.26 101	93.39 125	74.55 202	86.77 302	68.61 271	96.64 98	95.38 59

PMVS	80.48 6	90.08 42	90.66 49	88.34 83	96.71 3	92.97 2	90.31 60	89.57 200	88.51 21	90.11 102	95.12 53	90.98 7	88.92 261	77.55 161	97.07 87	83.13 377
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 355	90.06 103	91.33 196	80.66 134	93.03 147	75.78 186	95.94 132	92.48 189

v1921920		84.23 159	84.37 161	83.79 183	87.64 235	61.71 292	82.91 227	91.20 147	67.94 268	90.06 103	90.34 235	72.04 241	93.59 124	82.32 102	94.91 174	96.07 41

ITE_SJBPF				90.11 49	90.72 159	84.97 41		90.30 178	81.56 82	90.02 105	91.20 202	82.40 103	90.81 213	73.58 216	94.66 186	94.56 87

XVS		91.54 18	91.36 29	92.08 9	95.64 24	86.25 22	92.64 20	93.33 70	85.07 45	89.99 106	94.03 99	86.57 56	95.80 28	87.35 32	97.62 68	94.20 103

X-MVStestdata		85.04 135	82.70 193	92.08 9	95.64 24	86.25 22	92.64 20	93.33 70	85.07 45	89.99 106	16.05 446	86.57 56	95.80 28	87.35 32	97.62 68	94.20 103

v1192		84.57 146	84.69 151	84.21 171	87.75 229	62.88 272	83.02 223	91.43 138	69.08 249	89.98 108	90.89 215	72.70 232	93.62 122	82.41 101	94.97 173	96.13 39

Anonymous20240529		86.20 110	87.13 98	83.42 197	90.19 169	64.55 255	84.55 176	90.71 160	85.85 40	89.94 109	95.24 50	82.13 113	90.40 225	69.19 262	96.40 109	95.31 62

pmmvs6		86.52 105	88.06 85	81.90 234	92.22 108	62.28 285	84.66 174	89.15 206	83.54 63	89.85 110	97.32 8	88.08 39	86.80 301	70.43 247	97.30 82	96.62 31

v144192		84.24 158	84.41 159	83.71 187	87.59 236	61.57 293	82.95 226	91.03 152	67.82 272	89.80 111	90.49 232	73.28 224	93.51 129	81.88 110	94.89 176	96.04 43

v1144		84.54 149	84.72 148	84.00 175	87.67 233	62.55 279	82.97 225	90.93 156	70.32 237	89.80 111	90.99 208	73.50 217	93.48 130	81.69 111	94.65 187	95.97 44

DeepC-MVS	82.31 4	89.15 65	89.08 67	89.37 62	93.64 67	79.07 85	88.54 100	94.20 31	73.53 185	89.71 113	94.82 60	85.09 72	95.77 34	84.17 80	98.03 42	93.26 152
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 82	86.93 104	91.22 31	90.08 171	89.30 5	89.68 74	91.11 149	79.26 111	89.68 114	94.81 63	82.44 101	87.74 285	76.54 175	88.74 323	96.61 32

IU-MVS					94.18 51	72.64 152		90.82 158	56.98 372	89.67 115				85.78 61	97.92 51	93.28 150

FMVSNet1		84.55 148	85.45 134	81.85 236	90.27 168	61.05 301	86.83 128	88.27 223	78.57 122	89.66 116	95.64 38	75.43 187	90.68 217	69.09 263	95.33 156	93.82 123

IterMVS-LS		84.73 143	84.98 142	83.96 178	87.35 242	63.66 262	83.25 216	89.88 191	76.06 147	89.62 117	92.37 163	73.40 222	92.52 159	78.16 152	94.77 183	95.69 51
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 73	89.01 68	87.36 97	91.30 141	77.50 103	87.55 113	92.97 93	87.95 26	89.62 117	92.87 144	84.56 77	93.89 110	77.65 159	96.62 99	90.70 255

UniMVSNet (Re)		86.87 95	86.98 103	86.55 110	93.11 83	68.48 214	83.80 199	92.87 95	80.37 94	89.61 119	91.81 182	77.72 160	94.18 99	75.00 196	98.53 16	96.99 24

IS-MVSNet		86.66 102	86.82 107	86.17 122	92.05 114	66.87 232	91.21 44	88.64 212	86.30 37	89.60 120	92.59 153	69.22 259	94.91 71	73.89 209	97.89 54	96.72 29

v2v482		84.09 162	84.24 164	83.62 189	87.13 248	61.40 295	82.71 232	89.71 195	72.19 216	89.55 121	91.41 194	70.70 251	93.20 139	81.02 114	93.76 212	96.25 37

Baseline_NR-MVSNet		84.00 167	85.90 122	78.29 296	91.47 139	53.44 374	82.29 245	87.00 251	79.06 114	89.55 121	95.72 36	77.20 167	86.14 317	72.30 232	98.51 17	95.28 63

CSCG		86.26 107	86.47 110	85.60 134	90.87 156	74.26 134	87.98 108	91.85 127	80.35 95	89.54 123	88.01 278	79.09 146	92.13 170	75.51 189	95.06 168	90.41 266

ambc				82.98 209	90.55 163	64.86 251	88.20 102	89.15 206		89.40 124	93.96 105	71.67 246	91.38 193	78.83 142	96.55 101	92.71 177

DeepPCF-MVS	81.24 5	87.28 92	86.21 115	90.49 42	91.48 138	84.90 42	83.41 211	92.38 111	70.25 238	89.35 125	90.68 225	82.85 96	94.57 84	79.55 133	95.95 131	92.00 216

LuminaMVS		83.94 169	83.51 175	85.23 141	89.78 179	71.74 170	84.76 170	87.27 237	72.60 207	89.31 126	90.60 230	64.04 288	90.95 204	79.08 139	94.11 202	92.99 165

MVStest1		70.05 353	69.26 356	72.41 358	58.62 449	55.59 358	76.61 336	65.58 417	53.44 389	89.28 127	93.32 126	22.91 449	71.44 404	74.08 206	89.52 311	90.21 273

test_fmvsmconf0.01_n		86.68 100	86.52 109	87.18 98	85.94 285	78.30 91	86.93 124	92.20 116	65.94 288	89.16 128	93.16 131	83.10 93	89.89 242	87.81 20	94.43 193	93.35 146

MSP-MVS		89.08 67	88.16 84	91.83 20	95.76 18	86.14 25	92.75 17	93.90 49	78.43 123	89.16 128	92.25 169	72.03 242	96.36 4	88.21 13	90.93 286	92.98 167
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 64	88.83 76	90.23 47	94.28 48	86.11 26	85.91 145	93.60 62	80.16 98	89.13 130	93.44 124	83.82 84	90.98 203	83.86 83	95.30 160	93.60 139

MDA-MVSNet-bldmvs		77.47 275	76.90 281	79.16 282	79.03 383	64.59 252	66.58 413	75.67 356	73.15 198	88.86 131	88.99 265	66.94 269	81.23 362	64.71 304	88.22 333	91.64 229

EG-PatchMatch MVS		84.08 163	84.11 166	83.98 177	92.22 108	72.61 155	82.20 251	87.02 248	72.63 206	88.86 131	91.02 207	78.52 149	91.11 199	73.41 218	91.09 280	88.21 305

3Dnovator+	83.92 2	89.97 50	89.66 58	90.92 35	91.27 143	81.66 66	91.25 43	94.13 38	88.89 15	88.83 133	94.26 86	77.55 163	95.86 23	84.88 72	95.87 138	95.24 65

fmvsm_s_conf0.5_n_5		84.56 147	84.71 149	84.11 174	87.92 224	72.09 166	84.80 166	88.64 212	64.43 308	88.77 134	91.78 184	78.07 154	87.95 280	85.85 60	92.18 257	92.30 200

EI-MVSNet-UG-set		85.04 135	84.44 158	86.85 105	83.87 322	72.52 158	83.82 197	85.15 277	80.27 97	88.75 135	85.45 327	79.95 142	91.90 177	81.92 109	90.80 292	96.13 39

EI-MVSNet-Vis-set		85.12 133	84.53 156	86.88 104	84.01 318	72.76 149	83.91 195	85.18 276	80.44 92	88.75 135	85.49 325	80.08 140	91.92 176	82.02 106	90.85 291	95.97 44

balanced_conf03		84.80 140	85.40 135	83.00 208	88.95 196	61.44 294	90.42 59	92.37 112	71.48 223	88.72 137	93.13 132	70.16 255	95.15 63	79.26 138	94.11 202	92.41 193

OMC-MVS		88.19 77	87.52 91	90.19 48	91.94 119	81.68 65	87.49 116	93.17 79	76.02 149	88.64 138	91.22 200	84.24 82	93.37 135	77.97 157	97.03 88	95.52 56

RRT-MVS		82.97 191	83.44 177	81.57 243	85.06 298	58.04 338	87.20 118	90.37 172	77.88 131	88.59 139	93.70 119	63.17 296	93.05 146	76.49 176	88.47 325	93.62 137

test_fmvsmconf0.1_n		86.18 112	85.88 123	87.08 100	85.26 295	78.25 92	85.82 149	91.82 129	65.33 302	88.55 140	92.35 166	82.62 100	89.80 244	86.87 40	94.32 196	93.18 156

UA-Net		91.49 20	91.53 25	91.39 27	94.98 35	82.95 58	93.52 7	92.79 98	88.22 23	88.53 141	97.64 6	83.45 90	94.55 86	86.02 57	98.60 13	96.67 30

MP-MVS		91.14 29	90.91 45	91.83 20	96.18 11	86.88 17	92.20 31	93.03 89	82.59 72	88.52 142	94.37 82	86.74 54	95.41 53	86.32 47	98.21 33	93.19 155
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
sasdasda		85.50 121	86.14 116	83.58 191	87.97 221	67.13 226	87.55 113	94.32 22	73.44 188	88.47 143	87.54 290	86.45 59	91.06 201	75.76 187	93.76 212	92.54 187

canonicalmvs		85.50 121	86.14 116	83.58 191	87.97 221	67.13 226	87.55 113	94.32 22	73.44 188	88.47 143	87.54 290	86.45 59	91.06 201	75.76 187	93.76 212	92.54 187

NR-MVSNet		86.00 114	86.22 114	85.34 140	93.24 80	64.56 254	82.21 249	90.46 168	80.99 88	88.42 145	91.97 174	77.56 162	93.85 111	72.46 231	98.65 12	97.61 10

alignmvs		83.94 169	83.98 169	83.80 182	87.80 228	67.88 221	84.54 178	91.42 140	73.27 196	88.41 146	87.96 279	72.33 235	90.83 212	76.02 184	94.11 202	92.69 178

TransMVSNet (Re)		84.02 166	85.74 129	78.85 284	91.00 153	55.20 363	82.29 245	87.26 238	79.65 105	88.38 147	95.52 41	83.00 94	86.88 299	67.97 277	96.60 100	94.45 93

PM-MVS		80.20 247	79.00 256	83.78 184	88.17 218	86.66 19	81.31 261	66.81 414	69.64 244	88.33 148	90.19 241	64.58 283	83.63 348	71.99 234	90.03 304	81.06 405

fmvsm_s_conf0.5_n_3		86.19 111	87.27 96	82.95 211	86.91 259	70.38 189	85.31 159	92.61 105	75.59 159	88.32 149	92.87 144	82.22 111	88.63 269	88.80 9	92.82 239	89.83 279

tttt0517		81.07 227	79.58 251	85.52 136	88.99 195	66.45 237	87.03 123	75.51 358	73.76 181	88.32 149	90.20 240	37.96 420	94.16 103	79.36 137	95.13 164	95.93 47

casdiffmvs		85.21 129	85.85 124	83.31 200	86.17 279	62.77 275	83.03 222	93.93 47	74.69 171	88.21 151	92.68 152	82.29 109	91.89 178	77.87 158	93.75 215	95.27 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
test_vis3_rt		71.42 339	70.67 341	73.64 345	69.66 437	70.46 187	66.97 412	89.73 193	42.68 434	88.20 152	83.04 356	43.77 404	60.07 435	65.35 299	86.66 353	90.39 267

SSC-MVS		77.55 274	81.64 211	65.29 403	90.46 164	20.33 450	73.56 369	68.28 404	85.44 41	88.18 153	94.64 68	70.93 249	81.33 361	71.25 236	92.03 259	94.20 103

MVSMamba_PlusPlus		87.53 90	88.86 75	83.54 195	92.03 115	62.26 286	91.49 41	92.62 104	88.07 25	88.07 154	96.17 26	72.24 237	95.79 31	84.85 73	94.16 201	92.58 184

MGCFI-Net		85.04 135	85.95 120	82.31 228	87.52 238	63.59 264	86.23 142	93.96 45	73.46 186	88.07 154	87.83 285	86.46 58	90.87 211	76.17 181	93.89 209	92.47 191

v148		82.31 200	82.48 199	81.81 239	85.59 289	59.66 319	81.47 259	86.02 263	72.85 201	88.05 156	90.65 228	70.73 250	90.91 208	75.15 194	91.79 265	94.87 77

AstraMVS		81.67 218	81.40 220	82.48 225	87.06 255	66.47 236	81.41 260	81.68 316	68.78 253	88.00 157	90.95 213	65.70 278	87.86 284	76.66 172	92.38 248	93.12 159

AllTest		87.97 83	87.40 95	89.68 55	91.59 129	83.40 52	89.50 81	95.44 11	79.47 106	88.00 157	93.03 136	82.66 98	91.47 187	70.81 239	96.14 120	94.16 107

TestCases				89.68 55	91.59 129	83.40 52		95.44 11	79.47 106	88.00 157	93.03 136	82.66 98	91.47 187	70.81 239	96.14 120	94.16 107

fmvsm_s_conf0.1_n_2		83.82 172	83.49 176	84.84 147	85.99 284	70.19 192	80.93 268	87.58 233	67.26 279	87.94 160	92.37 163	71.40 247	88.01 277	86.03 54	91.87 264	96.31 36

fmvsm_s_conf0.5_n_8		85.48 123	85.75 128	84.68 156	87.10 251	69.98 194	84.28 183	92.68 101	74.77 169	87.90 161	92.36 165	73.94 210	90.41 224	85.95 59	92.74 241	93.66 131

pm-mvs1		83.69 175	84.95 144	79.91 271	90.04 175	59.66 319	82.43 241	87.44 234	75.52 161	87.85 162	95.26 49	81.25 127	85.65 328	68.74 269	96.04 125	94.42 96

PCF-MVS	74.62 15	82.15 207	80.92 230	85.84 129	89.43 185	72.30 162	80.53 274	91.82 129	57.36 368	87.81 163	89.92 249	77.67 161	93.63 119	58.69 345	95.08 167	91.58 231
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 178	83.29 181	84.62 157	85.43 292	70.18 193	80.61 273	87.24 239	67.14 280	87.79 164	91.87 176	71.79 244	87.98 279	86.00 58	91.77 267	95.71 50

guyue		81.57 220	81.37 222	82.15 229	86.39 267	66.13 240	81.54 258	83.21 300	69.79 243	87.77 165	89.95 247	65.36 281	87.64 287	75.88 185	92.49 246	92.67 179

KinetiMVS		85.95 116	86.10 118	85.50 138	87.56 237	69.78 196	83.70 202	89.83 192	80.42 93	87.76 166	93.24 128	73.76 214	91.54 185	85.03 70	93.62 221	95.19 68

mvs5depth		83.82 172	84.54 155	81.68 241	82.23 345	68.65 212	86.89 125	89.90 190	80.02 101	87.74 167	97.86 4	64.19 287	82.02 357	76.37 177	95.63 150	94.35 99

test_fmvsmconf_n		85.88 118	85.51 133	86.99 102	84.77 303	78.21 93	85.40 158	91.39 141	65.32 303	87.72 168	91.81 182	82.33 105	89.78 245	86.68 42	94.20 199	92.99 165

FMVSNet2		81.31 224	81.61 213	80.41 264	86.38 269	58.75 333	83.93 194	86.58 254	72.43 208	87.65 169	92.98 138	63.78 292	90.22 229	66.86 280	93.92 208	92.27 204

GeoE		85.45 125	85.81 125	84.37 163	90.08 171	67.07 228	85.86 148	91.39 141	72.33 213	87.59 170	90.25 239	84.85 75	92.37 164	78.00 155	91.94 263	93.66 131

VPA-MVSNet		83.47 183	84.73 146	79.69 275	90.29 167	57.52 343	81.30 263	88.69 211	76.29 145	87.58 171	94.44 75	80.60 135	87.20 293	66.60 285	96.82 94	94.34 100

CPTT-MVS		89.39 59	88.98 70	90.63 40	95.09 33	86.95 16	92.09 33	92.30 114	79.74 103	87.50 172	92.38 160	81.42 125	93.28 137	83.07 90	97.24 83	91.67 228

VDDNet		84.35 153	85.39 136	81.25 249	95.13 32	59.32 322	85.42 157	81.11 321	86.41 36	87.41 173	96.21 25	73.61 215	90.61 220	66.33 287	96.85 91	93.81 126

VortexMVS		80.51 236	80.63 233	80.15 269	83.36 332	61.82 291	80.63 272	88.00 229	67.11 281	87.23 174	89.10 263	63.98 289	88.00 278	73.63 215	92.63 244	90.64 260

c3_l		81.64 219	81.59 214	81.79 240	80.86 363	59.15 326	78.61 305	90.18 184	68.36 259	87.20 175	87.11 301	69.39 257	91.62 183	78.16 152	94.43 193	94.60 86

VDD-MVS		84.23 159	84.58 153	83.20 203	91.17 149	65.16 250	83.25 216	84.97 284	79.79 102	87.18 176	94.27 83	74.77 198	90.89 209	69.24 259	96.54 102	93.55 144

MSLP-MVS++		85.00 138	86.03 119	81.90 234	91.84 124	71.56 177	86.75 132	93.02 90	75.95 152	87.12 177	89.39 256	77.98 155	89.40 256	77.46 162	94.78 181	84.75 349

baseline		85.20 130	85.93 121	83.02 207	86.30 274	62.37 283	84.55 176	93.96 45	74.48 174	87.12 177	92.03 173	82.30 107	91.94 175	78.39 145	94.21 198	94.74 84

YYNet1		70.06 352	70.44 345	68.90 380	73.76 420	53.42 375	58.99 431	67.20 410	58.42 358	87.10 179	85.39 329	59.82 316	67.32 420	59.79 341	83.50 389	85.96 334

MDA-MVSNet_test_wron		70.05 353	70.44 345	68.88 381	73.84 419	53.47 373	58.93 432	67.28 409	58.43 357	87.09 180	85.40 328	59.80 317	67.25 421	59.66 342	83.54 388	85.92 336

test_fmvs3		75.72 297	75.20 298	77.27 312	75.01 416	69.47 201	78.93 297	84.88 285	46.67 418	87.08 181	87.84 284	50.44 368	71.62 402	77.42 165	88.53 324	90.72 253

CNVR-MVS		87.81 86	87.68 89	88.21 85	92.87 88	77.30 109	85.25 160	91.23 146	77.31 139	87.07 182	91.47 193	82.94 95	94.71 77	84.67 75	96.27 114	92.62 182

EPP-MVSNet		85.47 124	85.04 141	86.77 107	91.52 137	69.37 202	91.63 40	87.98 230	81.51 83	87.05 183	91.83 180	66.18 275	95.29 56	70.75 242	96.89 90	95.64 53

TinyColmap		81.25 225	82.34 201	77.99 302	85.33 293	60.68 309	82.32 244	88.33 221	71.26 226	86.97 184	92.22 171	77.10 170	86.98 297	62.37 321	95.17 163	86.31 332

eth_miper_zixun_eth		80.84 230	80.22 243	82.71 218	81.41 355	60.98 304	77.81 314	90.14 185	67.31 278	86.95 185	87.24 298	64.26 285	92.31 166	75.23 193	91.61 271	94.85 81

Anonymous20240521		80.18 248	81.25 224	76.95 315	83.15 340	60.84 306	82.46 240	85.99 264	68.76 254	86.78 186	93.73 118	59.13 321	77.44 383	73.71 213	97.55 73	92.56 185

Patchmatch-RL test		74.48 310	73.68 310	76.89 318	84.83 301	66.54 234	72.29 377	69.16 403	57.70 364	86.76 187	86.33 311	45.79 389	82.59 352	69.63 256	90.65 298	81.54 396

XVG-OURS-SEG-HR		89.59 56	89.37 62	90.28 46	94.47 43	85.95 27	86.84 127	93.91 48	80.07 100	86.75 188	93.26 127	93.64 2	90.93 206	84.60 76	90.75 293	93.97 114

h-mvs33		84.25 157	82.76 192	88.72 74	91.82 126	82.60 60	84.00 190	84.98 283	71.27 224	86.70 189	90.55 231	63.04 299	93.92 109	78.26 150	94.20 199	89.63 281

hse-mvs2		83.47 183	81.81 208	88.47 79	91.03 152	82.27 61	82.61 233	83.69 296	71.27 224	86.70 189	86.05 317	63.04 299	92.41 162	78.26 150	93.62 221	90.71 254

HPM-MVS++		88.93 69	88.45 80	90.38 44	94.92 36	85.85 31	89.70 72	91.27 145	78.20 126	86.69 191	92.28 168	80.36 137	95.06 67	86.17 52	96.49 104	90.22 269

TSAR-MVS + MP.		88.14 78	87.82 88	89.09 68	95.72 22	76.74 114	92.49 26	91.19 148	67.85 271	86.63 192	94.84 59	79.58 144	95.96 15	87.62 24	94.50 189	94.56 87
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
EI-MVSNet		82.61 195	82.42 200	83.20 203	83.25 336	63.66 262	83.50 208	85.07 278	76.06 147	86.55 193	85.10 333	73.41 220	90.25 226	78.15 154	90.67 295	95.68 52

HQP_MVS		87.75 87	87.43 94	88.70 76	93.45 71	76.42 118	89.45 83	93.61 60	79.44 108	86.55 193	92.95 141	74.84 195	95.22 59	80.78 118	95.83 140	94.46 91

plane_prior3						76.85 113			77.79 133	86.55 193

BH-untuned		80.96 229	80.99 228	80.84 257	88.55 210	68.23 215	80.33 277	88.46 216	72.79 204	86.55 193	86.76 305	74.72 199	91.77 182	61.79 328	88.99 318	82.52 385

MVSTER		77.09 279	75.70 292	81.25 249	75.27 413	61.08 300	77.49 322	85.07 278	60.78 343	86.55 193	88.68 269	43.14 409	90.25 226	73.69 214	90.67 295	92.42 192

旧先验2							81.73 254		56.88 373	86.54 198			84.90 334	72.81 228

IterMVS-SCA-FT		80.64 234	79.41 252	84.34 167	83.93 320	69.66 199	76.28 341	81.09 322	72.43 208	86.47 199	90.19 241	60.46 309	93.15 142	77.45 163	86.39 357	90.22 269

WB-MVS		76.06 293	80.01 249	64.19 406	89.96 177	20.58 449	72.18 378	68.19 405	83.21 65	86.46 200	93.49 123	70.19 254	78.97 377	65.96 289	90.46 300	93.02 163

test_fmvsm_n_1920		83.60 179	82.89 190	85.74 131	85.22 296	77.74 101	84.12 187	90.48 167	59.87 352	86.45 201	91.12 204	75.65 185	85.89 324	82.28 103	90.87 289	93.58 140

fmvsm_s_conf0.5_n_4		84.38 151	84.27 163	84.74 152	87.25 244	70.84 184	83.55 206	88.45 217	68.64 257	86.29 202	91.31 198	74.97 193	88.42 271	87.87 19	90.07 303	94.95 74

DIV-MVS_self_test		80.43 238	80.23 241	81.02 255	79.99 371	59.25 323	77.07 327	87.02 248	67.38 275	86.19 203	89.22 259	63.09 297	90.16 231	76.32 178	95.80 142	93.66 131

CDPH-MVS		86.17 113	85.54 132	88.05 90	92.25 106	75.45 127	83.85 196	92.01 121	65.91 290	86.19 203	91.75 186	83.77 86	94.98 69	77.43 164	96.71 97	93.73 129

cl____		80.42 239	80.23 241	81.02 255	79.99 371	59.25 323	77.07 327	87.02 248	67.37 276	86.18 205	89.21 260	63.08 298	90.16 231	76.31 179	95.80 142	93.65 134

MVS_111021_LR		84.28 156	83.76 172	85.83 130	89.23 190	83.07 55	80.99 267	83.56 298	72.71 205	86.07 206	89.07 264	81.75 122	86.19 315	77.11 168	93.36 223	88.24 304

GBi-Net		82.02 211	82.07 202	81.85 236	86.38 269	61.05 301	86.83 128	88.27 223	72.43 208	86.00 207	95.64 38	63.78 292	90.68 217	65.95 290	93.34 224	93.82 123

test1		82.02 211	82.07 202	81.85 236	86.38 269	61.05 301	86.83 128	88.27 223	72.43 208	86.00 207	95.64 38	63.78 292	90.68 217	65.95 290	93.34 224	93.82 123

FMVSNet3		78.80 261	78.55 264	79.57 277	82.89 343	56.89 349	81.76 253	85.77 266	69.04 250	86.00 207	90.44 233	51.75 361	90.09 237	65.95 290	93.34 224	91.72 225

miper_ehance_all_eth		80.34 242	80.04 248	81.24 251	79.82 374	58.95 328	77.66 316	89.66 196	65.75 295	85.99 210	85.11 332	68.29 264	91.42 191	76.03 183	92.03 259	93.33 147

tfpnnormal		81.79 217	82.95 189	78.31 294	88.93 197	55.40 359	80.83 271	82.85 305	76.81 142	85.90 211	94.14 93	74.58 201	86.51 306	66.82 283	95.68 148	93.01 164

TAPA-MVS	77.73 12	85.71 120	84.83 145	88.37 82	88.78 203	79.72 78	87.15 121	93.50 65	69.17 247	85.80 212	89.56 254	80.76 132	92.13 170	73.21 226	95.51 151	93.25 153
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TSAR-MVS + GP.		83.95 168	82.69 194	87.72 93	89.27 189	81.45 67	83.72 201	81.58 319	74.73 170	85.66 213	86.06 316	72.56 234	92.69 156	75.44 191	95.21 161	89.01 298

EU-MVSNet		75.12 302	74.43 305	77.18 313	83.11 341	59.48 321	85.71 152	82.43 309	39.76 438	85.64 214	88.76 267	44.71 402	87.88 283	73.86 210	85.88 363	84.16 360

MonoMVSNet		76.66 285	77.26 277	74.86 337	79.86 373	54.34 367	86.26 141	86.08 260	71.08 229	85.59 215	88.68 269	53.95 351	85.93 319	63.86 311	80.02 409	84.32 355

LF4IMVS		82.75 194	81.93 206	85.19 142	82.08 346	80.15 75	85.53 154	88.76 210	68.01 265	85.58 216	87.75 286	71.80 243	86.85 300	74.02 207	93.87 210	88.58 301

Patchmtry		76.56 288	77.46 273	73.83 343	79.37 380	46.60 410	82.41 242	76.90 347	73.81 180	85.56 217	92.38 160	48.07 375	83.98 345	63.36 316	95.31 159	90.92 247

MVS_111021_HR		84.63 144	84.34 162	85.49 139	90.18 170	75.86 125	79.23 295	87.13 243	73.35 190	85.56 217	89.34 257	83.60 89	90.50 222	76.64 173	94.05 206	90.09 275

testdata				79.54 278	92.87 88	72.34 161		80.14 328	59.91 351	85.47 219	91.75 186	67.96 266	85.24 330	68.57 273	92.18 257	81.06 405

mvsmamba		80.30 244	78.87 257	84.58 159	88.12 220	67.55 223	92.35 30	84.88 285	63.15 314	85.33 220	90.91 214	50.71 365	95.20 62	66.36 286	87.98 335	90.99 244

test1111		78.53 265	78.85 259	77.56 308	92.22 108	47.49 406	82.61 233	69.24 402	72.43 208	85.28 221	94.20 89	51.91 359	90.07 238	65.36 298	96.45 107	95.11 71

thisisatest0530		79.07 256	77.33 276	84.26 170	87.13 248	64.58 253	83.66 204	75.95 353	68.86 252	85.22 222	87.36 295	38.10 417	93.57 127	75.47 190	94.28 197	94.62 85

BP-MVS1		82.81 192	81.67 210	86.23 117	87.88 226	68.53 213	86.06 144	84.36 291	75.65 157	85.14 223	90.19 241	45.84 388	94.42 89	85.18 66	94.72 185	95.75 49

SymmetryMVS		84.79 142	83.54 174	88.55 78	92.44 100	80.42 72	88.63 99	82.37 310	74.56 173	85.12 224	90.34 235	66.19 274	94.20 97	76.57 174	95.68 148	91.03 243

EC-MVSNet		88.01 81	88.32 83	87.09 99	89.28 188	72.03 167	90.31 60	96.31 4	80.88 90	85.12 224	89.67 253	84.47 79	95.46 50	82.56 99	96.26 115	93.77 128

CLD-MVS		83.18 187	82.64 195	84.79 150	89.05 192	67.82 222	77.93 312	92.52 107	68.33 260	85.07 226	81.54 375	82.06 114	92.96 148	69.35 258	97.91 53	93.57 141
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		82.58 197	81.93 206	84.50 160	87.68 232	73.35 140	86.14 143	77.70 339	61.64 331	85.02 227	91.62 188	77.75 158	86.24 312	82.79 96	87.07 346	93.91 118

FA-MVS(test-final)		83.13 189	83.02 188	83.43 196	86.16 281	66.08 241	88.00 107	88.36 220	75.55 160	85.02 227	92.75 150	65.12 282	92.50 160	74.94 197	91.30 277	91.72 225

DeepC-MVS_fast	80.27 8	86.23 108	85.65 131	87.96 91	91.30 141	76.92 112	87.19 119	91.99 122	70.56 233	84.96 229	90.69 224	80.01 141	95.14 64	78.37 146	95.78 144	91.82 221
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	84.80 140	84.71 149	85.06 145	86.36 272	74.71 130	88.77 95	90.00 188	75.65 157	84.96 229	93.17 130	74.06 208	91.19 196	78.28 149	91.09 280	89.29 289

QAPM		82.59 196	82.59 197	82.58 221	86.44 266	66.69 233	89.94 68	90.36 173	67.97 267	84.94 231	92.58 155	72.71 231	92.18 169	70.63 245	87.73 339	88.85 299

fmvsm_l_conf0.5_n_3		85.11 134	84.96 143	85.56 135	87.49 240	75.69 126	84.71 172	90.61 165	67.64 273	84.88 232	92.05 172	82.30 107	88.36 273	83.84 84	91.10 279	92.62 182

VPNet		80.25 245	81.68 209	75.94 329	92.46 99	47.98 404	76.70 332	81.67 317	73.45 187	84.87 233	92.82 146	74.66 200	86.51 306	61.66 330	96.85 91	93.33 147

NCCC		87.36 91	86.87 105	88.83 71	92.32 105	78.84 88	86.58 135	91.09 151	78.77 119	84.85 234	90.89 215	80.85 131	95.29 56	81.14 113	95.32 157	92.34 198

PHI-MVS		86.38 106	85.81 125	88.08 88	88.44 213	77.34 107	89.35 86	93.05 86	73.15 198	84.76 235	87.70 287	78.87 148	94.18 99	80.67 120	96.29 111	92.73 174

pmmvs-eth3d		78.42 267	77.04 279	82.57 223	87.44 241	74.41 133	80.86 270	79.67 330	55.68 377	84.69 236	90.31 238	60.91 307	85.42 329	62.20 323	91.59 272	87.88 314

test_prior2							83.37 212		75.43 162	84.58 237	91.57 190	81.92 119		79.54 134	96.97 89

fmvsm_s_conf0.5_n_6		84.05 164	84.14 165	83.81 181	87.75 229	71.17 180	83.42 210	91.10 150	67.90 270	84.53 238	90.70 223	73.01 227	88.73 267	85.09 67	93.72 217	91.53 233

fmvsm_s_conf0.5_n_a		82.21 203	81.51 218	84.32 168	86.56 264	73.35 140	85.46 155	77.30 343	61.81 327	84.51 239	90.88 217	77.36 165	86.21 314	82.72 97	86.97 351	93.38 145

TEST9					92.34 103	79.70 79	83.94 192	90.32 175	65.41 301	84.49 240	90.97 209	82.03 115	93.63 119

train_agg		85.98 115	85.28 138	88.07 89	92.34 103	79.70 79	83.94 192	90.32 175	65.79 292	84.49 240	90.97 209	81.93 117	93.63 119	81.21 112	96.54 102	90.88 249

fmvsm_s_conf0.1_n		82.17 205	81.59 214	83.94 180	86.87 262	71.57 176	85.19 162	77.42 342	62.27 325	84.47 242	91.33 196	76.43 181	85.91 322	83.14 87	87.14 344	94.33 101

Gipuma		84.44 150	86.33 112	78.78 285	84.20 315	73.57 138	89.55 78	90.44 169	84.24 54	84.38 243	94.89 57	76.35 184	80.40 369	76.14 182	96.80 95	82.36 387
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 392	65.85 380	59.67 418	66.54 442	62.24 288	57.76 434	70.96 393	40.13 436	84.36 244	82.09 368	46.93 377	51.67 442	61.99 326	81.89 399	65.12 433

test_8					92.09 112	78.87 87	83.82 197	90.31 177	65.79 292	84.36 244	90.96 211	81.93 117	93.44 132

cl22		78.97 257	78.21 269	81.24 251	77.74 388	59.01 327	77.46 323	87.13 243	65.79 292	84.32 246	85.10 333	58.96 323	90.88 210	75.36 192	92.03 259	93.84 121

CS-MVS		88.14 78	87.67 90	89.54 60	89.56 181	79.18 84	90.47 56	94.77 17	79.37 110	84.32 246	89.33 258	83.87 83	94.53 87	82.45 100	94.89 176	94.90 75

agg_prior					91.58 132	77.69 102		90.30 178		84.32 246			93.18 140

Anonymous202405211		80.51 236	81.19 227	78.49 291	88.48 211	57.26 345	76.63 334	82.49 308	81.21 86	84.30 249	92.24 170	67.99 265	86.24 312	62.22 322	95.13 164	91.98 218

LFMVS		80.15 249	80.56 235	78.89 283	89.19 191	55.93 353	85.22 161	73.78 370	82.96 69	84.28 250	92.72 151	57.38 333	90.07 238	63.80 312	95.75 145	90.68 256

Vis-MVSNet		86.86 96	86.58 108	87.72 93	92.09 112	77.43 106	87.35 117	92.09 119	78.87 117	84.27 251	94.05 98	78.35 152	93.65 117	80.54 122	91.58 273	92.08 212
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 266	78.63 263	77.88 304	91.85 122	48.95 400	83.68 203	69.91 398	72.30 214	84.26 252	94.20 89	51.89 360	89.82 243	63.58 313	96.02 126	94.87 77

FE-MVS		79.98 252	78.86 258	83.36 198	86.47 265	66.45 237	89.73 71	84.74 289	72.80 203	84.22 253	91.38 195	44.95 400	93.60 123	63.93 310	91.50 274	90.04 276

ETV-MVS		84.31 154	83.91 171	85.52 136	88.58 209	70.40 188	84.50 180	93.37 67	78.76 120	84.07 254	78.72 400	80.39 136	95.13 65	73.82 211	92.98 235	91.04 242

fmvsm_s_conf0.5_n		81.91 215	81.30 223	83.75 185	86.02 283	71.56 177	84.73 171	77.11 346	62.44 322	84.00 255	90.68 225	76.42 182	85.89 324	83.14 87	87.11 345	93.81 126

MCST-MVS		84.36 152	83.93 170	85.63 133	91.59 129	71.58 175	83.52 207	92.13 118	61.82 326	83.96 256	89.75 252	79.93 143	93.46 131	78.33 148	94.34 195	91.87 220

新几何1				82.95 211	93.96 60	78.56 90		80.24 327	55.45 378	83.93 257	91.08 206	71.19 248	88.33 274	65.84 293	93.07 232	81.95 392

mmtdpeth		85.13 132	85.78 127	83.17 205	84.65 305	74.71 130	85.87 147	90.35 174	77.94 129	83.82 258	96.96 15	77.75 158	80.03 372	78.44 144	96.21 116	94.79 83

fmvsm_l_conf0.5_n		82.06 209	81.54 217	83.60 190	83.94 319	73.90 136	83.35 213	86.10 259	58.97 354	83.80 259	90.36 234	74.23 203	86.94 298	82.90 93	90.22 301	89.94 277

GDP-MVS		82.17 205	80.85 232	86.15 124	88.65 206	68.95 210	85.65 153	93.02 90	68.42 258	83.73 260	89.54 255	45.07 399	94.31 91	79.66 131	93.87 210	95.19 68

BH-RMVSNet		80.53 235	80.22 243	81.49 245	87.19 247	66.21 239	77.79 315	86.23 257	74.21 176	83.69 261	88.50 272	73.25 225	90.75 214	63.18 318	87.90 336	87.52 318

USDC		76.63 286	76.73 283	76.34 325	83.46 327	57.20 346	80.02 280	88.04 228	52.14 400	83.65 262	91.25 199	63.24 295	86.65 304	54.66 373	94.11 202	85.17 344

miper_enhance_ethall		77.83 270	76.93 280	80.51 262	76.15 405	58.01 339	75.47 353	88.82 208	58.05 362	83.59 263	80.69 379	64.41 284	91.20 195	73.16 227	92.03 259	92.33 199

MM		87.64 89	87.15 97	89.09 68	89.51 182	76.39 120	88.68 97	86.76 252	84.54 50	83.58 264	93.78 114	73.36 223	96.48 2	87.98 17	96.21 116	94.41 97

Effi-MVS+-dtu		85.82 119	83.38 179	93.14 4	87.13 248	91.15 3	87.70 112	88.42 218	74.57 172	83.56 265	85.65 321	78.49 151	94.21 96	72.04 233	92.88 237	94.05 112

CNLPA		83.55 181	83.10 187	84.90 146	89.34 187	83.87 50	84.54 178	88.77 209	79.09 113	83.54 266	88.66 271	74.87 194	81.73 359	66.84 282	92.29 252	89.11 291

SDMVSNet		81.90 216	83.17 185	78.10 299	88.81 201	62.45 281	76.08 345	86.05 262	73.67 182	83.41 267	93.04 134	82.35 104	80.65 366	70.06 252	95.03 169	91.21 238

sd_testset		79.95 253	81.39 221	75.64 332	88.81 201	58.07 337	76.16 344	82.81 306	73.67 182	83.41 267	93.04 134	80.96 130	77.65 382	58.62 346	95.03 169	91.21 238

OpenMVS_ROB	70.19 17	77.77 273	77.46 273	78.71 287	84.39 311	61.15 299	81.18 265	82.52 307	62.45 321	83.34 269	87.37 294	66.20 273	88.66 268	64.69 305	85.02 373	86.32 331

thres100view900		75.45 298	75.05 299	76.66 321	87.27 243	51.88 386	81.07 266	73.26 375	75.68 156	83.25 270	86.37 310	45.54 390	88.80 262	51.98 389	90.99 282	89.31 287

miper_lstm_enhance		76.45 290	76.10 288	77.51 309	76.72 399	60.97 305	64.69 417	85.04 280	63.98 311	83.20 271	88.22 275	56.67 337	78.79 379	73.22 221	93.12 231	92.78 173

IterMVS		76.91 281	76.34 286	78.64 288	80.91 361	64.03 259	76.30 340	79.03 333	64.88 306	83.11 272	89.16 261	59.90 315	84.46 338	68.61 271	85.15 371	87.42 319
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 294	75.35 297	77.85 306	87.01 256	51.84 387	80.45 275	73.26 375	75.20 165	83.10 273	86.31 313	45.54 390	89.05 258	55.03 371	92.24 254	92.66 180

mvs_anonymous		78.13 268	78.76 261	76.23 328	79.24 381	50.31 397	78.69 303	84.82 287	61.60 332	83.09 274	92.82 146	73.89 212	87.01 294	68.33 275	86.41 356	91.37 235

fmvsm_l_conf0.5_n_a		81.46 222	80.87 231	83.25 201	83.73 324	73.21 145	83.00 224	85.59 270	58.22 360	82.96 275	90.09 246	72.30 236	86.65 304	81.97 108	89.95 306	89.88 278

test_fmvs2		73.57 319	72.80 321	75.90 330	72.74 430	68.84 211	77.07 327	84.32 293	45.14 424	82.89 276	84.22 345	48.37 373	70.36 406	73.40 219	87.03 348	88.52 302

MVS_Test		82.47 199	83.22 182	80.22 267	82.62 344	57.75 342	82.54 238	91.96 124	71.16 228	82.89 276	92.52 157	77.41 164	90.50 222	80.04 125	87.84 338	92.40 195

reproduce_monomvs		74.09 314	73.23 316	76.65 322	76.52 400	54.54 365	77.50 321	81.40 320	65.85 291	82.86 278	86.67 306	27.38 443	84.53 337	70.24 249	90.66 297	90.89 248

test12				86.57 109	90.74 158	72.63 154		90.69 161		82.76 279		79.20 145	94.80 75		95.32 157	92.27 204

原ACMM1				84.60 158	92.81 93	74.01 135		91.50 136	62.59 317	82.73 280	90.67 227	76.53 180	94.25 94	69.24 259	95.69 147	85.55 340

test_yl		78.71 263	78.51 265	79.32 280	84.32 312	58.84 330	78.38 306	85.33 273	75.99 150	82.49 281	86.57 307	58.01 327	90.02 240	62.74 319	92.73 242	89.10 292

DCV-MVSNet		78.71 263	78.51 265	79.32 280	84.32 312	58.84 330	78.38 306	85.33 273	75.99 150	82.49 281	86.57 307	58.01 327	90.02 240	62.74 319	92.73 242	89.10 292

diffmvs		80.40 240	80.48 238	80.17 268	79.02 384	60.04 314	77.54 319	90.28 181	66.65 286	82.40 283	87.33 296	73.50 217	87.35 291	77.98 156	89.62 310	93.13 157
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 77	76.54 115	79.38 290	77.79 338	52.59 395	82.36 284	90.84 219	66.83 271			91.69 269	81.25 400

D2MVS		76.84 282	75.67 293	80.34 265	80.48 369	62.16 289	73.50 370	84.80 288	57.61 366	82.24 285	87.54 290	51.31 362	87.65 286	70.40 248	93.19 230	91.23 237

VNet		79.31 255	80.27 240	76.44 323	87.92 224	53.95 370	75.58 351	84.35 292	74.39 175	82.23 286	90.72 222	72.84 230	84.39 340	60.38 338	93.98 207	90.97 245

Vis-MVSNet (Re-imp)		77.82 271	77.79 272	77.92 303	88.82 200	51.29 391	83.28 214	71.97 386	74.04 177	82.23 286	89.78 251	57.38 333	89.41 255	57.22 354	95.41 153	93.05 162

API-MVS		82.28 201	82.61 196	81.30 248	86.29 275	69.79 195	88.71 96	87.67 232	78.42 124	82.15 288	84.15 347	77.98 155	91.59 184	65.39 297	92.75 240	82.51 386

DP-MVS Recon		84.05 164	83.22 182	86.52 111	91.73 127	75.27 128	83.23 218	92.40 109	72.04 218	82.04 289	88.33 274	77.91 157	93.95 108	66.17 288	95.12 166	90.34 268

MSDG		80.06 251	79.99 250	80.25 266	83.91 321	68.04 220	77.51 320	89.19 205	77.65 134	81.94 290	83.45 353	76.37 183	86.31 311	63.31 317	86.59 354	86.41 330

test2506		74.12 313	73.39 314	76.28 326	91.85 122	44.20 420	84.06 188	48.20 445	72.30 214	81.90 291	94.20 89	27.22 445	89.77 246	64.81 303	96.02 126	94.87 77

Fast-Effi-MVS+		81.04 228	80.57 234	82.46 226	87.50 239	63.22 269	78.37 308	89.63 198	68.01 265	81.87 292	82.08 369	82.31 106	92.65 157	67.10 279	88.30 332	91.51 234

testgi		72.36 329	74.61 301	65.59 400	80.56 368	42.82 425	68.29 402	73.35 374	66.87 284	81.84 293	89.93 248	72.08 240	66.92 423	46.05 417	92.54 245	87.01 325

tfpn200view9		74.86 306	74.23 306	76.74 320	86.24 276	52.12 383	79.24 293	73.87 368	73.34 191	81.82 294	84.60 342	46.02 383	88.80 262	51.98 389	90.99 282	89.31 287

thres400		75.14 300	74.23 306	77.86 305	86.24 276	52.12 383	79.24 293	73.87 368	73.34 191	81.82 294	84.60 342	46.02 383	88.80 262	51.98 389	90.99 282	92.66 180

CL-MVSNet_self_test		76.81 283	77.38 275	75.12 335	86.90 260	51.34 389	73.20 373	80.63 326	68.30 261	81.80 296	88.40 273	66.92 270	80.90 363	55.35 368	94.90 175	93.12 159

OpenMVS	76.72 13	81.98 213	82.00 205	81.93 233	84.42 310	68.22 216	88.50 101	89.48 201	66.92 283	81.80 296	91.86 177	72.59 233	90.16 231	71.19 238	91.25 278	87.40 320

MVS_0304		85.37 126	84.58 153	87.75 92	85.28 294	73.36 139	86.54 137	85.71 267	77.56 137	81.78 298	92.47 158	70.29 253	96.02 11	85.59 62	95.96 129	93.87 120

AdaColmap		83.66 176	83.69 173	83.57 193	90.05 174	72.26 163	86.29 140	90.00 188	78.19 127	81.65 299	87.16 299	83.40 91	94.24 95	61.69 329	94.76 184	84.21 359

SPE-MVS-test		87.00 94	86.43 111	88.71 75	89.46 184	77.46 104	89.42 85	95.73 7	77.87 132	81.64 300	87.25 297	82.43 102	94.53 87	77.65 159	96.46 106	94.14 109

DELS-MVS		81.44 223	81.25 224	82.03 231	84.27 314	62.87 273	76.47 339	92.49 108	70.97 230	81.64 300	83.83 348	75.03 191	92.70 155	74.29 199	92.22 256	90.51 264
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		83.10 190	82.54 198	84.77 151	92.90 87	69.10 209	86.65 133	90.62 164	54.66 384	81.46 302	90.81 220	76.98 172	94.38 90	72.62 229	96.18 118	90.82 251

TR-MVS		76.77 284	75.79 290	79.72 274	86.10 282	65.79 244	77.14 325	83.02 303	65.20 304	81.40 303	82.10 367	66.30 272	90.73 216	55.57 365	85.27 367	82.65 380

TAMVS		78.08 269	76.36 285	83.23 202	90.62 161	72.87 148	79.08 296	80.01 329	61.72 329	81.35 304	86.92 304	63.96 291	88.78 265	50.61 394	93.01 234	88.04 310

Effi-MVS+		83.90 171	84.01 168	83.57 193	87.22 246	65.61 246	86.55 136	92.40 109	78.64 121	81.34 305	84.18 346	83.65 88	92.93 150	74.22 200	87.87 337	92.17 209

testing3		71.53 338	70.79 340	73.77 344	88.89 199	41.86 427	76.60 337	59.12 434	72.83 202	80.97 306	82.08 369	19.80 451	87.33 292	65.12 300	91.68 270	92.13 211

new-patchmatchnet		70.10 351	73.37 315	60.29 417	81.23 358	16.95 452	59.54 428	74.62 361	62.93 315	80.97 306	87.93 282	62.83 301	71.90 400	55.24 369	95.01 172	92.00 216

PVSNet_Blended_VisFu		81.55 221	80.49 237	84.70 155	91.58 132	73.24 144	84.21 184	91.67 133	62.86 316	80.94 308	87.16 299	67.27 268	92.87 153	69.82 254	88.94 320	87.99 311

BH-w/o		76.57 287	76.07 289	78.10 299	86.88 261	65.92 243	77.63 317	86.33 255	65.69 296	80.89 309	79.95 388	68.97 262	90.74 215	53.01 384	85.25 368	77.62 416

PAPM_NR		83.23 186	83.19 184	83.33 199	90.90 155	65.98 242	88.19 103	90.78 159	78.13 128	80.87 310	87.92 283	73.49 219	92.42 161	70.07 251	88.40 326	91.60 230

ab-mvs		79.67 254	80.56 235	76.99 314	88.48 211	56.93 347	84.70 173	86.06 261	68.95 251	80.78 311	93.08 133	75.30 189	84.62 336	56.78 355	90.90 287	89.43 285

XXY-MVS		74.44 312	76.19 287	69.21 378	84.61 306	52.43 382	71.70 381	77.18 345	60.73 344	80.60 312	90.96 211	75.44 186	69.35 409	56.13 360	88.33 328	85.86 337

HQP4-MVS										80.56 313			94.61 82			93.56 142

HQP-NCC					91.19 146		84.77 167		73.30 193	80.55 314

ACMP_Plane					91.19 146		84.77 167		73.30 193	80.55 314

HQP-MVS		84.61 145	84.06 167	86.27 116	91.19 146	70.66 185	84.77 167	92.68 101	73.30 193	80.55 314	90.17 244	72.10 238	94.61 82	77.30 166	94.47 191	93.56 142

test_cas_vis1_n_1920		69.20 364	69.12 357	69.43 377	73.68 421	62.82 274	70.38 393	77.21 344	46.18 421	80.46 317	78.95 397	52.03 358	65.53 428	65.77 295	77.45 423	79.95 411

AUN-MVS		81.18 226	78.78 260	88.39 81	90.93 154	82.14 62	82.51 239	83.67 297	64.69 307	80.29 318	85.91 320	51.07 363	92.38 163	76.29 180	93.63 220	90.65 259

HyFIR lowres test		75.12 302	72.66 324	82.50 224	91.44 140	65.19 249	72.47 376	87.31 236	46.79 417	80.29 318	84.30 344	52.70 356	92.10 173	51.88 393	86.73 352	90.22 269

test20.03		73.75 318	74.59 303	71.22 364	81.11 359	51.12 393	70.15 394	72.10 385	70.42 234	80.28 320	91.50 192	64.21 286	74.72 394	46.96 413	94.58 188	87.82 316

mvsany_test3		65.48 386	62.97 395	73.03 350	69.99 436	76.17 123	64.83 415	43.71 447	43.68 429	80.25 321	87.05 303	52.83 355	63.09 434	51.92 392	72.44 429	79.84 412

F-COLMAP		84.97 139	83.42 178	89.63 57	92.39 101	83.40 52	88.83 93	91.92 125	73.19 197	80.18 322	89.15 262	77.04 171	93.28 137	65.82 294	92.28 253	92.21 207

GA-MVS		75.83 295	74.61 301	79.48 279	81.87 348	59.25 323	73.42 371	82.88 304	68.68 255	79.75 323	81.80 372	50.62 366	89.46 251	66.85 281	85.64 364	89.72 280

xiu_mvs_v1_base_debu		80.84 230	80.14 245	82.93 213	88.31 214	71.73 171	79.53 286	87.17 240	65.43 298	79.59 324	82.73 363	76.94 173	90.14 234	73.22 221	88.33 328	86.90 326

xiu_mvs_v1_base		80.84 230	80.14 245	82.93 213	88.31 214	71.73 171	79.53 286	87.17 240	65.43 298	79.59 324	82.73 363	76.94 173	90.14 234	73.22 221	88.33 328	86.90 326

xiu_mvs_v1_base_debi		80.84 230	80.14 245	82.93 213	88.31 214	71.73 171	79.53 286	87.17 240	65.43 298	79.59 324	82.73 363	76.94 173	90.14 234	73.22 221	88.33 328	86.90 326

test_fmvs1_n		70.94 343	70.41 347	72.53 356	73.92 418	66.93 231	75.99 346	84.21 295	43.31 431	79.40 327	79.39 393	43.47 405	68.55 414	69.05 264	84.91 376	82.10 390

patch_mono-2		78.89 258	79.39 253	77.41 311	84.78 302	68.11 218	75.60 349	83.11 302	60.96 341	79.36 328	89.89 250	75.18 190	72.97 397	73.32 220	92.30 250	91.15 240

UnsupCasMVSNet_eth		71.63 337	72.30 329	69.62 375	76.47 402	52.70 380	70.03 395	80.97 323	59.18 353	79.36 328	88.21 276	60.50 308	69.12 410	58.33 349	77.62 421	87.04 324

ppachtmachnet_test		74.73 309	74.00 308	76.90 317	80.71 366	56.89 349	71.53 384	78.42 335	58.24 359	79.32 330	82.92 360	57.91 330	84.26 342	65.60 296	91.36 276	89.56 282

MG-MVS		80.32 243	80.94 229	78.47 292	88.18 217	52.62 381	82.29 245	85.01 282	72.01 219	79.24 331	92.54 156	69.36 258	93.36 136	70.65 244	89.19 316	89.45 283

Fast-Effi-MVS+-dtu		82.54 198	81.41 219	85.90 127	85.60 288	76.53 117	83.07 221	89.62 199	73.02 200	79.11 332	83.51 351	80.74 133	90.24 228	68.76 268	89.29 313	90.94 246

SSC-MVS3.2		73.90 316	75.67 293	68.61 386	84.11 317	41.28 428	64.17 419	72.83 378	72.09 217	79.08 333	87.94 280	70.31 252	73.89 396	55.99 361	94.49 190	90.67 258

CDS-MVSNet		77.32 277	75.40 295	83.06 206	89.00 194	72.48 159	77.90 313	82.17 312	60.81 342	78.94 334	83.49 352	59.30 319	88.76 266	54.64 374	92.37 249	87.93 313
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 321	73.54 312	72.43 357	84.92 300	47.79 405	79.89 282	74.00 366	65.93 289	78.81 335	86.28 314	56.36 339	81.63 360	56.63 356	79.04 416	87.87 315

ttmdpeth		71.72 335	70.67 341	74.86 337	73.08 427	55.88 354	77.41 324	69.27 401	55.86 376	78.66 336	93.77 116	38.01 419	75.39 391	60.12 339	89.87 307	93.31 149

EIA-MVS		82.19 204	81.23 226	85.10 144	87.95 223	69.17 208	83.22 219	93.33 70	70.42 234	78.58 337	79.77 391	77.29 166	94.20 97	71.51 235	88.96 319	91.93 219

thres200		72.34 330	71.55 336	74.70 340	83.48 326	51.60 388	75.02 356	73.71 371	70.14 240	78.56 338	80.57 382	46.20 381	88.20 276	46.99 412	89.29 313	84.32 355

fmvsm_s_conf0.5_n_7		82.04 210	82.05 204	82.01 232	86.98 258	71.07 181	78.70 302	89.45 202	68.07 264	78.14 339	91.61 189	74.19 204	85.92 320	79.61 132	91.73 268	89.05 295

our_test_3		71.85 333	71.59 333	72.62 354	80.71 366	53.78 371	69.72 397	71.71 390	58.80 356	78.03 340	80.51 384	56.61 338	78.84 378	62.20 323	86.04 362	85.23 343

KD-MVS_2432*1600		66.87 375	65.81 382	70.04 369	67.50 439	47.49 406	62.56 422	79.16 331	61.21 339	77.98 341	80.61 380	25.29 447	82.48 353	53.02 382	84.92 374	80.16 409

miper_refine_blended		66.87 375	65.81 382	70.04 369	67.50 439	47.49 406	62.56 422	79.16 331	61.21 339	77.98 341	80.61 380	25.29 447	82.48 353	53.02 382	84.92 374	80.16 409

jason		77.42 276	75.75 291	82.43 227	87.10 251	69.27 203	77.99 311	81.94 314	51.47 404	77.84 343	85.07 336	60.32 311	89.00 259	70.74 243	89.27 315	89.03 296
jason: jason.
MAR-MVS		80.24 246	78.74 262	84.73 153	86.87 262	78.18 94	85.75 150	87.81 231	65.67 297	77.84 343	78.50 401	73.79 213	90.53 221	61.59 331	90.87 289	85.49 342
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		72.29 331	72.00 330	73.14 348	88.63 207	85.00 40	74.65 360	67.39 408	71.94 220	77.80 345	87.66 288	50.48 367	75.83 389	49.95 396	79.51 410	58.58 439

test_fmvs1		69.57 359	69.05 359	71.14 366	69.15 438	65.77 245	73.98 365	83.32 299	42.83 433	77.77 346	78.27 403	43.39 408	68.50 415	68.39 274	84.38 383	79.15 413

pmmvs4		74.92 305	72.98 320	80.73 259	84.95 299	71.71 174	76.23 342	77.59 340	52.83 394	77.73 347	86.38 309	56.35 340	84.97 333	57.72 353	87.05 347	85.51 341

ET-MVSNet_ETH3D		75.28 299	72.77 322	82.81 217	83.03 342	68.11 218	77.09 326	76.51 351	60.67 345	77.60 348	80.52 383	38.04 418	91.15 198	70.78 241	90.68 294	89.17 290

testing3-2		70.72 346	70.97 339	69.95 371	88.93 197	34.80 441	69.85 396	66.59 415	78.42 124	77.58 349	85.55 322	31.83 432	82.08 356	46.28 414	93.73 216	92.98 167

UnsupCasMVSNet_bld		69.21 363	69.68 354	67.82 389	79.42 378	51.15 392	67.82 406	75.79 354	54.15 386	77.47 350	85.36 331	59.26 320	70.64 405	48.46 406	79.35 412	81.66 394

WBMVS		68.76 366	68.43 366	69.75 374	83.29 334	40.30 431	67.36 408	72.21 384	57.09 371	77.05 351	85.53 324	33.68 427	80.51 367	48.79 404	90.90 287	88.45 303

Anonymous20231206		71.38 340	71.88 331	69.88 372	86.31 273	54.37 366	70.39 392	74.62 361	52.57 396	76.73 352	88.76 267	59.94 314	72.06 399	44.35 421	93.23 229	83.23 375

CMPMVS	59.41 20	75.12 302	73.57 311	79.77 272	75.84 408	67.22 224	81.21 264	82.18 311	50.78 409	76.50 353	87.66 288	55.20 347	82.99 351	62.17 325	90.64 299	89.09 294
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 332	71.69 332	73.32 346	81.57 353	53.02 377	76.77 331	78.37 336	63.31 312	76.37 354	91.85 178	36.68 422	78.98 376	47.87 409	92.45 247	87.95 312

CVMVSNet		72.62 327	71.41 337	76.28 326	83.25 336	60.34 312	83.50 208	79.02 334	37.77 442	76.33 355	85.10 333	49.60 371	87.41 290	70.54 246	77.54 422	81.08 403

PLC	73.85 16	82.09 208	80.31 239	87.45 96	90.86 157	80.29 74	85.88 146	90.65 162	68.17 263	76.32 356	86.33 311	73.12 226	92.61 158	61.40 332	90.02 305	89.44 284
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 202	81.57 216	84.19 173	85.54 290	69.26 204	91.98 35	90.08 186	71.54 221	76.23 357	85.07 336	58.69 324	94.27 92	86.26 48	88.77 321	89.03 296

lupinMVS		76.37 291	74.46 304	82.09 230	85.54 290	69.26 204	76.79 330	80.77 325	50.68 411	76.23 357	82.82 361	58.69 324	88.94 260	69.85 253	88.77 321	88.07 307

UWE-MVS		66.43 379	65.56 385	69.05 379	84.15 316	40.98 429	73.06 375	64.71 421	54.84 382	76.18 359	79.62 392	29.21 438	80.50 368	38.54 433	89.75 308	85.66 339

PatchMatch-RL		74.48 310	73.22 317	78.27 297	87.70 231	85.26 38	75.92 347	70.09 396	64.34 309	76.09 360	81.25 377	65.87 277	78.07 381	53.86 376	83.82 386	71.48 425

thisisatest0515		73.00 325	70.52 344	80.46 263	81.45 354	59.90 317	73.16 374	74.31 365	57.86 363	76.08 361	77.78 405	37.60 421	92.12 172	65.00 301	91.45 275	89.35 286

MS-PatchMatch		70.93 344	70.22 348	73.06 349	81.85 349	62.50 280	73.82 368	77.90 337	52.44 397	75.92 362	81.27 376	55.67 344	81.75 358	55.37 367	77.70 420	74.94 421

CHOSEN 1792x2688		72.45 328	70.56 343	78.13 298	90.02 176	63.08 270	68.72 401	83.16 301	42.99 432	75.92 362	85.46 326	57.22 335	85.18 332	49.87 398	81.67 400	86.14 333

CR-MVSNet		74.00 315	73.04 319	76.85 319	79.58 375	62.64 277	82.58 235	76.90 347	50.50 412	75.72 364	92.38 160	48.07 375	84.07 344	68.72 270	82.91 393	83.85 364

RPMNet		78.88 259	78.28 268	80.68 261	79.58 375	62.64 277	82.58 235	94.16 33	74.80 168	75.72 364	92.59 153	48.69 372	95.56 42	73.48 217	82.91 393	83.85 364

DPM-MVS		80.10 250	79.18 255	82.88 216	90.71 160	69.74 197	78.87 300	90.84 157	60.29 348	75.64 366	85.92 319	67.28 267	93.11 143	71.24 237	91.79 265	85.77 338

test_vis1_n		70.29 348	69.99 352	71.20 365	75.97 407	66.50 235	76.69 333	80.81 324	44.22 427	75.43 367	77.23 412	50.00 369	68.59 413	66.71 284	82.85 395	78.52 415

PVSNet_BlendedMVS		78.80 261	77.84 271	81.65 242	84.43 308	63.41 265	79.49 289	90.44 169	61.70 330	75.43 367	87.07 302	69.11 260	91.44 189	60.68 336	92.24 254	90.11 274

PVSNet_Blended		76.49 289	75.40 295	79.76 273	84.43 308	63.41 265	75.14 355	90.44 169	57.36 368	75.43 367	78.30 402	69.11 260	91.44 189	60.68 336	87.70 340	84.42 354

PAPR		78.84 260	78.10 270	81.07 253	85.17 297	60.22 313	82.21 249	90.57 166	62.51 318	75.32 370	84.61 341	74.99 192	92.30 167	59.48 343	88.04 334	90.68 256

N_pmnet		70.20 349	68.80 364	74.38 341	80.91 361	84.81 43	59.12 430	76.45 352	55.06 380	75.31 371	82.36 366	55.74 343	54.82 440	47.02 411	87.24 343	83.52 368

cascas		76.29 292	74.81 300	80.72 260	84.47 307	62.94 271	73.89 367	87.34 235	55.94 375	75.16 372	76.53 418	63.97 290	91.16 197	65.00 301	90.97 285	88.06 309

SCA		73.32 320	72.57 326	75.58 333	81.62 352	55.86 355	78.89 299	71.37 391	61.73 328	74.93 373	83.42 354	60.46 309	87.01 294	58.11 351	82.63 398	83.88 361

test_vis1_n_1920		71.30 341	71.58 335	70.47 367	77.58 391	59.99 316	74.25 361	84.22 294	51.06 406	74.85 374	79.10 395	55.10 348	68.83 412	68.86 267	79.20 415	82.58 382

xiu_mvs_v2_base		77.19 278	76.75 282	78.52 290	87.01 256	61.30 297	75.55 352	87.12 246	61.24 338	74.45 375	78.79 399	77.20 167	90.93 206	64.62 307	84.80 380	83.32 373

CANet		83.79 174	82.85 191	86.63 108	86.17 279	72.21 165	83.76 200	91.43 138	77.24 140	74.39 376	87.45 293	75.36 188	95.42 52	77.03 169	92.83 238	92.25 206

PS-MVSNAJ		77.04 280	76.53 284	78.56 289	87.09 253	61.40 295	75.26 354	87.13 243	61.25 337	74.38 377	77.22 413	76.94 173	90.94 205	64.63 306	84.83 379	83.35 372

MVP-Stereo		75.81 296	73.51 313	82.71 218	89.35 186	73.62 137	80.06 278	85.20 275	60.30 347	73.96 378	87.94 280	57.89 331	89.45 252	52.02 388	74.87 427	85.06 346
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 367	69.01 360	67.85 388	83.22 338	43.98 421	74.93 357	65.98 416	55.09 379	73.83 379	79.11 394	65.63 279	71.89 401	38.21 434	85.04 372	87.69 317

UGNet		82.78 193	81.64 211	86.21 120	86.20 278	76.24 122	86.86 126	85.68 268	77.07 141	73.76 380	92.82 146	69.64 256	91.82 181	69.04 265	93.69 218	90.56 262
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		74.82 307	73.74 309	78.04 301	89.57 180	60.04 314	76.49 338	87.09 247	54.31 385	73.66 381	79.80 389	60.25 312	86.76 303	58.37 347	84.15 384	87.32 321

Test_1112_low_res		73.90 316	73.08 318	76.35 324	90.35 166	55.95 352	73.40 372	86.17 258	50.70 410	73.14 382	85.94 318	58.31 326	85.90 323	56.51 357	83.22 390	87.20 323

1314		73.22 322	72.56 327	75.20 334	80.41 370	57.84 340	81.64 256	85.36 272	51.68 403	73.10 383	76.65 417	61.45 304	85.19 331	63.54 314	79.21 414	82.59 381

test_vis1_rt		65.64 385	64.09 389	70.31 368	66.09 443	70.20 191	61.16 425	81.60 318	38.65 439	72.87 384	69.66 432	52.84 354	60.04 436	56.16 359	77.77 419	80.68 407

Patchmatch-test		65.91 382	67.38 371	61.48 414	75.51 410	43.21 424	68.84 400	63.79 423	62.48 319	72.80 385	83.42 354	44.89 401	59.52 437	48.27 408	86.45 355	81.70 393

PatchmatchNet		69.71 358	68.83 363	72.33 359	77.66 390	53.60 372	79.29 291	69.99 397	57.66 365	72.53 386	82.93 359	46.45 380	80.08 371	60.91 335	72.09 430	83.31 374
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 369	68.08 370	67.55 390	78.74 386	43.53 423	75.60 349	67.10 413	54.92 381	72.23 387	88.10 277	42.87 410	75.97 388	52.21 387	80.95 408	83.15 376

pmmvs5		70.73 345	70.07 349	72.72 352	77.03 396	52.73 379	74.14 362	75.65 357	50.36 413	72.17 388	85.37 330	55.42 346	80.67 365	52.86 385	87.59 341	84.77 348

PatchT		70.52 347	72.76 323	63.79 408	79.38 379	33.53 442	77.63 317	65.37 419	73.61 184	71.77 389	92.79 149	44.38 403	75.65 390	64.53 308	85.37 366	82.18 389

MVS		73.21 323	72.59 325	75.06 336	80.97 360	60.81 307	81.64 256	85.92 265	46.03 422	71.68 390	77.54 408	68.47 263	89.77 246	55.70 364	85.39 365	74.60 422

MIMVSNet		71.09 342	71.59 333	69.57 376	87.23 245	50.07 398	78.91 298	71.83 387	60.20 350	71.26 391	91.76 185	55.08 349	76.09 387	41.06 426	87.02 349	82.54 384

WTY-MVS		67.91 370	68.35 367	66.58 396	80.82 364	48.12 403	65.96 414	72.60 379	53.67 388	71.20 392	81.68 374	58.97 322	69.06 411	48.57 405	81.67 400	82.55 383

test0.0.03 1		64.66 389	64.36 388	65.57 401	75.03 415	46.89 409	64.69 417	61.58 431	62.43 323	71.18 393	77.54 408	43.41 406	68.47 416	40.75 428	82.65 396	81.35 397

CostFormer		69.98 355	68.68 365	73.87 342	77.14 394	50.72 395	79.26 292	74.51 363	51.94 402	70.97 394	84.75 339	45.16 398	87.49 289	55.16 370	79.23 413	83.40 371

Syy-MVS		69.40 361	70.03 351	67.49 391	81.72 350	38.94 433	71.00 386	61.99 425	61.38 334	70.81 395	72.36 429	61.37 305	79.30 374	64.50 309	85.18 369	84.22 357

myMVS_eth3d		64.66 389	63.89 390	66.97 394	81.72 350	37.39 436	71.00 386	61.99 425	61.38 334	70.81 395	72.36 429	20.96 450	79.30 374	49.59 399	85.18 369	84.22 357

testing91		69.94 356	68.99 361	72.80 351	83.81 323	45.89 413	71.57 383	73.64 373	68.24 262	70.77 397	77.82 404	34.37 425	84.44 339	53.64 378	87.00 350	88.07 307

testing99		69.27 362	68.15 369	72.63 353	83.29 334	45.45 415	71.15 385	71.08 392	67.34 277	70.43 398	77.77 406	32.24 431	84.35 341	53.72 377	86.33 358	88.10 306

tpmvs		70.16 350	69.56 355	71.96 360	74.71 417	48.13 402	79.63 284	75.45 359	65.02 305	70.26 399	81.88 371	45.34 395	85.68 327	58.34 348	75.39 426	82.08 391

sss		66.92 374	67.26 372	65.90 398	77.23 393	51.10 394	64.79 416	71.72 389	52.12 401	70.13 400	80.18 386	57.96 329	65.36 429	50.21 395	81.01 406	81.25 400

tpm2		68.45 368	66.83 375	73.30 347	78.93 385	48.50 401	79.76 283	71.76 388	47.50 416	69.92 401	83.60 350	42.07 411	88.40 272	48.44 407	79.51 410	83.01 378

myMVS_eth3d28		65.83 384	65.85 380	65.78 399	83.42 329	35.71 439	67.29 409	68.01 406	67.58 274	69.80 402	77.72 407	32.29 430	74.30 395	37.49 435	89.06 317	87.32 321

testing222		66.93 373	65.30 386	71.81 361	83.38 330	45.83 414	72.06 379	67.50 407	64.12 310	69.68 403	76.37 419	27.34 444	83.00 350	38.88 430	88.38 327	86.62 329

HY-MVS	64.64 18	73.03 324	72.47 328	74.71 339	83.36 332	54.19 368	82.14 252	81.96 313	56.76 374	69.57 404	86.21 315	60.03 313	84.83 335	49.58 400	82.65 396	85.11 345

dmvs_re		66.81 377	66.98 373	66.28 397	76.87 397	58.68 334	71.66 382	72.24 382	60.29 348	69.52 405	73.53 426	52.38 357	64.40 431	44.90 419	81.44 403	75.76 419

ETVMVS		64.67 388	63.34 394	68.64 383	83.44 328	41.89 426	69.56 399	61.70 430	61.33 336	68.74 406	75.76 421	28.76 439	79.35 373	34.65 438	86.16 361	84.67 350

tpm cat1		66.76 378	65.21 387	71.42 363	77.09 395	50.62 396	78.01 310	73.68 372	44.89 425	68.64 407	79.00 396	45.51 392	82.42 355	49.91 397	70.15 433	81.23 402

IB-MVS	62.13 19	71.64 336	68.97 362	79.66 276	80.80 365	62.26 286	73.94 366	76.90 347	63.27 313	68.63 408	76.79 415	33.83 426	91.84 180	59.28 344	87.26 342	84.88 347
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		80.37 241	78.41 267	86.23 117	76.75 398	73.28 142	87.18 120	77.45 341	76.24 146	68.14 409	88.93 266	65.41 280	93.85 111	69.47 257	96.12 122	91.55 232
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 380	65.63 384	68.75 382	81.96 347	49.88 399	62.19 424	72.51 381	51.03 407	68.04 410	75.34 423	50.84 364	74.77 392	45.82 418	82.96 391	81.60 395

tpmrst		66.28 381	66.69 377	65.05 404	72.82 429	39.33 432	78.20 309	70.69 395	53.16 392	67.88 411	80.36 385	48.18 374	74.75 393	58.13 350	70.79 432	81.08 403

CANet_DTU		77.81 272	77.05 278	80.09 270	81.37 356	59.90 317	83.26 215	88.29 222	69.16 248	67.83 412	83.72 349	60.93 306	89.47 250	69.22 261	89.70 309	90.88 249

EPMVS		62.47 393	62.63 397	62.01 410	70.63 435	38.74 434	74.76 358	52.86 441	53.91 387	67.71 413	80.01 387	39.40 415	66.60 424	55.54 366	68.81 438	80.68 407

UBG		64.34 391	63.35 393	67.30 392	83.50 325	40.53 430	67.46 407	65.02 420	54.77 383	67.54 414	74.47 425	32.99 429	78.50 380	40.82 427	83.58 387	82.88 379

MDTV_nov1_ep13			68.29 368		78.03 387	43.87 422	74.12 363	72.22 383	52.17 398	67.02 415	85.54 323	45.36 394	80.85 364	55.73 362	84.42 382

testing11		67.38 371	65.93 379	71.73 362	83.37 331	46.60 410	70.95 388	69.40 400	62.47 320	66.14 416	76.66 416	31.22 433	84.10 343	49.10 402	84.10 385	84.49 351

pmmvs3		62.47 393	60.02 406	69.80 373	71.58 433	64.00 260	70.52 391	58.44 437	39.77 437	66.05 417	75.84 420	27.10 446	72.28 398	46.15 416	84.77 381	73.11 423

ADS-MVSNet2		65.87 383	63.64 392	72.55 355	73.16 425	56.92 348	67.10 410	74.81 360	49.74 414	66.04 418	82.97 357	46.71 378	77.26 384	42.29 423	69.96 434	83.46 369

ADS-MVSNet		61.90 395	62.19 399	61.03 415	73.16 425	36.42 438	67.10 410	61.75 428	49.74 414	66.04 418	82.97 357	46.71 378	63.21 432	42.29 423	69.96 434	83.46 369

mvsany_test1		58.48 405	56.47 411	64.50 405	65.90 445	68.21 217	56.95 435	42.11 448	38.30 440	65.69 420	77.19 414	56.96 336	59.35 438	46.16 415	58.96 441	65.93 432

dmvs_testset		60.59 403	62.54 398	54.72 423	77.26 392	27.74 446	74.05 364	61.00 432	60.48 346	65.62 421	67.03 436	55.93 342	68.23 418	32.07 442	69.46 437	68.17 430

DSMNet-mixed		60.98 401	61.61 401	59.09 420	72.88 428	45.05 418	74.70 359	46.61 446	26.20 444	65.34 422	90.32 237	55.46 345	63.12 433	41.72 425	81.30 405	69.09 429

JIA-IIPM		69.41 360	66.64 378	77.70 307	73.19 424	71.24 179	75.67 348	65.56 418	70.42 234	65.18 423	92.97 140	33.64 428	83.06 349	53.52 380	69.61 436	78.79 414

test-LLR		67.21 372	66.74 376	68.63 384	76.45 403	55.21 361	67.89 403	67.14 411	62.43 323	65.08 424	72.39 427	43.41 406	69.37 407	61.00 333	84.89 377	81.31 398

test-mter		65.00 387	63.79 391	68.63 384	76.45 403	55.21 361	67.89 403	67.14 411	50.98 408	65.08 424	72.39 427	28.27 441	69.37 407	61.00 333	84.89 377	81.31 398

PMMVS2		55.64 409	59.27 407	44.74 425	64.30 447	12.32 453	40.60 440	49.79 443	53.19 391	65.06 426	84.81 338	53.60 353	49.76 443	32.68 441	89.41 312	72.15 424

baseline2		69.77 357	66.89 374	78.41 293	79.51 377	58.09 336	76.23 342	69.57 399	57.50 367	64.82 427	77.45 410	46.02 383	88.44 270	53.08 381	77.83 418	88.70 300

gg-mvs-nofinetune		68.96 365	69.11 358	68.52 387	76.12 406	45.32 416	83.59 205	55.88 439	86.68 33	64.62 428	97.01 12	30.36 436	83.97 346	44.78 420	82.94 392	76.26 418

PAPM		71.77 334	70.06 350	76.92 316	86.39 267	53.97 369	76.62 335	86.62 253	53.44 389	63.97 429	84.73 340	57.79 332	92.34 165	39.65 429	81.33 404	84.45 353

new_pmnet		55.69 408	57.66 409	49.76 424	75.47 411	30.59 444	59.56 427	51.45 442	43.62 430	62.49 430	75.48 422	40.96 413	49.15 444	37.39 436	72.52 428	69.55 428

UWE-MVS-28		58.44 406	57.71 408	60.65 416	73.58 422	31.23 443	69.68 398	48.80 444	53.12 393	61.79 431	78.83 398	30.98 434	68.40 417	21.58 445	80.99 407	82.33 388

MDTV_nov1_ep13_2view						27.60 447	70.76 390		46.47 420	61.27 432		45.20 396		49.18 401		83.75 366

dp		60.70 402	60.29 405	61.92 412	72.04 432	38.67 435	70.83 389	64.08 422	51.28 405	60.75 433	77.28 411	36.59 423	71.58 403	47.41 410	62.34 440	75.52 420

TESTMET0.1,1		61.29 398	60.32 404	64.19 406	72.06 431	51.30 390	67.89 403	62.09 424	45.27 423	60.65 434	69.01 433	27.93 442	64.74 430	56.31 358	81.65 402	76.53 417

PMMVS		61.65 396	60.38 403	65.47 402	65.40 446	69.26 204	63.97 420	61.73 429	36.80 443	60.11 435	68.43 434	59.42 318	66.35 425	48.97 403	78.57 417	60.81 436

PVSNet_0	51.08 22	56.10 407	54.97 412	59.48 419	75.12 414	53.28 376	55.16 436	61.89 427	44.30 426	59.16 436	62.48 439	54.22 350	65.91 427	35.40 437	47.01 442	59.25 438

MVS-HIRNet		61.16 399	62.92 396	55.87 421	79.09 382	35.34 440	71.83 380	57.98 438	46.56 419	59.05 437	91.14 203	49.95 370	76.43 386	38.74 431	71.92 431	55.84 440

E-PMN		61.59 397	61.62 400	61.49 413	66.81 441	55.40 359	53.77 437	60.34 433	66.80 285	58.90 438	65.50 437	40.48 414	66.12 426	55.72 363	86.25 359	62.95 435

GG-mvs-BLEND				67.16 393	73.36 423	46.54 412	84.15 186	55.04 440		58.64 439	61.95 440	29.93 437	83.87 347	38.71 432	76.92 424	71.07 426

EPNet_dtu		72.87 326	71.33 338	77.49 310	77.72 389	60.55 310	82.35 243	75.79 354	66.49 287	58.39 440	81.06 378	53.68 352	85.98 318	53.55 379	92.97 236	85.95 335
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 411	42.65 414	39.67 426	70.86 434	21.11 448	61.01 426	21.42 453	57.36 368	57.97 441	50.06 442	16.40 452	58.73 439	21.03 446	27.69 446	39.17 442

EMVS		61.10 400	60.81 402	61.99 411	65.96 444	55.86 355	53.10 438	58.97 436	67.06 282	56.89 442	63.33 438	40.98 412	67.03 422	54.79 372	86.18 360	63.08 434

CHOSEN 280x420		59.08 404	56.52 410	66.76 395	76.51 401	64.39 256	49.62 439	59.00 435	43.86 428	55.66 443	68.41 435	35.55 424	68.21 419	43.25 422	76.78 425	67.69 431

MVE	40.22 23	51.82 410	50.47 413	55.87 421	62.66 448	51.91 385	31.61 442	39.28 449	40.65 435	50.76 444	74.98 424	56.24 341	44.67 445	33.94 440	64.11 439	71.04 427
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 412	32.17 415	26.83 428	53.36 450	19.02 451	57.90 433	20.44 454	38.29 441	38.01 445	37.82 444	15.18 453	33.45 447	7.74 448	20.76 447	28.03 443

DeepMVS_CX				24.13 429	32.95 451	29.49 445		21.63 452	12.07 445	37.95 446	45.07 443	30.84 435	19.21 448	17.94 447	33.06 445	23.69 444

tmp_tt		20.25 415	24.50 418	7.49 430	4.47 453	8.70 454	34.17 441	25.16 451	1.00 448	32.43 447	18.49 445	39.37 416	9.21 449	21.64 444	43.75 443	4.57 445

test_method		30.46 413	29.60 416	33.06 427	17.99 452	3.84 455	13.62 443	73.92 367	2.79 446	18.29 448	53.41 441	28.53 440	43.25 446	22.56 443	35.27 444	52.11 441

EGC-MVSNET		74.79 308	69.99 352	89.19 66	94.89 38	87.00 15	91.89 38	86.28 256	1.09 447	2.23 449	95.98 30	81.87 120	89.48 249	79.76 128	95.96 129	91.10 241

testmvs		5.91 419	7.65 422	0.72 432	1.20 454	0.37 457	59.14 429	0.67 456	0.49 450	1.11 450	2.76 449	0.94 455	0.24 451	1.02 450	1.47 448	1.55 447

test123		6.27 418	8.08 421	0.84 431	1.11 455	0.57 456	62.90 421	0.82 455	0.54 449	1.07 451	2.75 450	1.26 454	0.30 450	1.04 449	1.26 449	1.66 446

mmdepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

monomultidepth		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

test_blank		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet_test		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

DCPMVS		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

cdsmvs_eth3d_5k		20.81 414	27.75 417	0.00 433	0.00 456	0.00 458	0.00 444	85.44 271	0.00 451	0.00 452	82.82 361	81.46 124	0.00 452	0.00 451	0.00 450	0.00 448

pcd_1.5k_mvsjas		6.41 417	8.55 420	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	76.94 173	0.00 452	0.00 451	0.00 450	0.00 448

sosnet-low-res		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

sosnet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uncertanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

Regformer		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

ab-mvs-re		6.65 416	8.87 419	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	79.80 389	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

uanet		0.00 420	0.00 423	0.00 433	0.00 456	0.00 458	0.00 444	0.00 457	0.00 451	0.00 452	0.00 451	0.00 456	0.00 452	0.00 451	0.00 450	0.00 448

WAC-MVS						37.39 436								52.61 386

MSC_two_6792asdad				88.81 72	91.55 134	77.99 96		91.01 153					96.05 9	87.45 28	98.17 36	92.40 195

No_MVS				88.81 72	91.55 134	77.99 96		91.01 153					96.05 9	87.45 28	98.17 36	92.40 195

eth-test2					0.00 456

eth-test					0.00 456

OPU-MVS				88.27 84	91.89 120	77.83 99	90.47 56				91.22 200	81.12 128	94.68 78	74.48 198	95.35 155	92.29 202

save fliter					93.75 64	77.44 105	86.31 139	89.72 194	70.80 231

test_0728_SECOND				86.79 106	94.25 49	72.45 160	90.54 53	94.10 40					95.88 18	86.42 44	97.97 48	92.02 215

GSMVS																83.88 361

sam_mvs1												46.11 382				83.88 361

sam_mvs												45.92 387

MTGPA								91.81 131

test_post1							78.85 301				3.13 447	45.19 397	80.13 370	58.11 351

test_post											3.10 448	45.43 393	77.22 385

patchmatchnet-post											81.71 373	45.93 386	87.01 294

MTMP							90.66 49	33.14 450

gm-plane-assit					75.42 412	44.97 419			52.17 398		72.36 429		87.90 282	54.10 375

test9_res														80.83 117	96.45 107	90.57 261

agg_prior2														79.68 130	96.16 119	90.22 269

test_prior4						78.97 86	84.59 175

test_prior				86.32 114	90.59 162	71.99 168		92.85 96					94.17 101			92.80 172

新几何2							81.72 255

旧先验1					91.97 116	71.77 169		81.78 315			91.84 179	73.92 211			93.65 219	83.61 367

无先验							82.81 230	85.62 269	58.09 361				91.41 192	67.95 278		84.48 352

原ACMM2							82.26 248

testdata2													86.43 309	63.52 315

segment_acmp												81.94 116

testdata1							79.62 285		73.95 179

plane_prior7					93.45 71	77.31 108

plane_prior6					92.61 94	76.54 115						74.84 195

plane_prior5								93.61 60					95.22 59	80.78 118	95.83 140	94.46 91

plane_prior4											92.95 141

plane_prior2							89.45 83		79.44 108

plane_prior1					92.83 92

plane_prior						76.42 118	87.15 121		75.94 153						95.03 169

n2								0.00 457

nn								0.00 457

door-mid								74.45 364

test11								91.46 137

door								72.57 380

HQP5-MVS						70.66 185

BP-MVS														77.30 166

HQP3-MVS								92.68 101							94.47 191

HQP2-MVS												72.10 238

NP-MVS					91.95 117	74.55 132					90.17 244

ACMMP++_ref															95.74 146

ACMMP++															97.35 79

Test By Simon												79.09 146

High-resolution multi-view benchmark