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 71	99.27 1	99.54 1

mamv4		95.37 2	94.51 2	97.96 1	96.31 10	98.41 1	91.05 50	97.23 2	95.32 2	99.01 2	97.26 9	80.16 147	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 49	91.91 18	84.21 181	96.51 7	57.84 365	88.93 95	92.84 103	91.92 4	96.16 4	96.23 24	86.95 54	95.99 12	79.05 146	98.57 15	98.80 6

PS-CasMVS		90.06 45	91.92 16	84.47 172	96.56 6	58.83 357	89.04 93	92.74 107	91.40 6	96.12 5	96.06 29	87.23 50	95.57 43	79.42 142	98.74 6	99.00 2

LCM-MVSNet-Re		83.48 193	85.06 146	78.75 308	85.94 301	55.75 382	80.05 297	94.27 25	76.47 147	96.09 6	94.54 71	83.31 95	89.75 264	59.95 366	94.89 180	90.75 273

PEN-MVS		90.03 47	91.88 19	84.48 171	96.57 5	58.88 354	88.95 94	93.19 84	91.62 5	96.01 7	96.16 27	87.02 53	95.60 42	78.69 150	98.72 9	98.97 3

CP-MVSNet		89.27 65	90.91 45	84.37 173	96.34 8	58.61 360	88.66 102	92.06 129	90.78 7	95.67 8	95.17 51	81.80 127	95.54 46	79.00 147	98.69 10	98.95 4

reproduce_model		92.89 5	93.18 8	92.01 13	94.20 53	88.23 9	92.87 13	94.32 22	90.25 11	95.65 9	95.74 33	87.75 43	95.72 38	89.60 5	98.27 28	92.08 232

LTVRE_ROB	86.10 1	93.04 4	93.44 4	91.82 22	93.73 68	85.72 34	96.79 1	95.51 10	88.86 16	95.63 10	96.99 13	84.81 79	93.16 149	91.10 2	97.53 80	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 53	91.31 34	85.71 137	96.32 9	62.39 299	89.54 83	93.31 78	90.21 12	95.57 11	95.66 37	81.42 132	95.90 17	80.94 121	98.80 3	98.84 5

reproduce-ours		92.86 6	93.22 6	91.76 23	94.39 46	87.71 11	92.40 28	94.38 20	89.82 13	95.51 12	95.49 42	89.64 22	95.82 28	89.13 7	98.26 30	91.76 243

our_new_method		92.86 6	93.22 6	91.76 23	94.39 46	87.71 11	92.40 28	94.38 20	89.82 13	95.51 12	95.49 42	89.64 22	95.82 28	89.13 7	98.26 30	91.76 243

OurMVSNet-221017-0		90.01 48	89.74 59	90.83 36	93.16 85	80.37 74	91.91 40	93.11 88	81.10 88	95.32 14	97.24 10	72.94 250	94.85 75	85.07 71	97.78 59	97.26 16

anonymousdsp		89.73 56	88.88 76	92.27 8	89.82 183	86.67 18	90.51 58	90.20 199	69.87 254	95.06 15	96.14 28	84.28 84	93.07 153	87.68 24	96.34 114	97.09 20

wuyk23d		75.13 327	79.30 277	62.63 436	75.56 436	75.18 133	80.89 286	73.10 404	75.06 170	94.76 16	95.32 45	87.73 45	52.85 468	34.16 466	97.11 90	59.85 464

ACMH	76.49 14	89.34 62	91.14 36	83.96 188	92.50 102	70.36 197	89.55 81	93.84 55	81.89 80	94.70 17	95.44 44	90.69 9	88.31 294	83.33 92	98.30 27	93.20 166
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
SixPastTwentyTwo		87.20 95	87.45 95	86.45 117	92.52 101	69.19 215	87.84 116	88.05 245	81.66 82	94.64 18	96.53 20	65.94 301	94.75 79	83.02 98	96.83 97	95.41 58

mvs_tets		89.78 55	89.27 66	91.30 29	93.51 72	84.79 44	89.89 72	90.63 178	70.00 253	94.55 19	96.67 17	87.94 41	93.59 131	84.27 85	95.97 132	95.52 56

lecture		92.43 9	93.50 3	89.21 66	94.43 44	79.31 84	92.69 19	95.72 8	88.48 22	94.43 20	95.73 34	91.34 4	94.68 81	90.26 4	98.44 20	93.63 144

jajsoiax		89.41 60	88.81 79	91.19 32	93.38 78	84.72 45	89.70 75	90.29 196	69.27 261	94.39 21	96.38 21	86.02 68	93.52 136	83.96 87	95.92 138	95.34 60

test_0402		88.65 74	89.58 63	85.88 133	92.55 100	72.22 169	84.01 199	89.44 220	88.63 20	94.38 22	95.77 32	86.38 64	93.59 131	79.84 133	95.21 165	91.82 241

UniMVSNet_ETH3D		89.12 68	90.72 49	84.31 179	97.00 2	64.33 270	89.67 78	88.38 237	88.84 17	94.29 23	97.57 7	90.48 14	91.26 203	72.57 248	97.65 69	97.34 15

v7n		90.13 41	90.96 43	87.65 98	91.95 121	71.06 188	89.99 68	93.05 92	86.53 35	94.29 23	96.27 23	82.69 100	94.08 108	86.25 53	97.63 70	97.82 8

test_djsdf		89.62 57	89.01 70	91.45 26	92.36 106	82.98 57	91.98 38	90.08 202	71.54 232	94.28 25	96.54 19	81.57 130	94.27 95	86.26 51	96.49 108	97.09 20

PS-MVSNAJss		88.31 78	87.90 89	89.56 60	93.31 80	77.96 99	87.94 114	91.97 132	70.73 244	94.19 26	96.67 17	76.94 189	94.57 87	83.07 96	96.28 116	96.15 38

SED-MVS		90.46 38	91.64 22	86.93 108	94.18 54	72.65 155	90.47 59	93.69 61	83.77 58	94.11 27	94.27 83	90.28 15	95.84 26	86.03 57	97.92 52	92.29 221

test_241102_ONE					94.18 54	72.65 155		93.69 61	83.62 61	94.11 27	93.78 114	90.28 15	95.50 51

DPE-MVS		90.53 37	91.08 38	88.88 71	93.38 78	78.65 90	89.15 92	94.05 42	84.68 49	93.90 29	94.11 95	88.13 37	96.30 5	84.51 83	97.81 58	91.70 247
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 68	92.97 89	78.04 96	92.84 16	94.14 37	83.33 65	93.90 29	95.73 34	88.77 28	96.41 3	87.60 27	97.98 48	92.98 182
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 82	93.00 88	76.26 122	89.65 79	95.55 9	87.72 27	93.89 31	94.94 56	91.62 3	93.44 140	78.35 154	98.76 4	95.61 55

ACMM	79.39 9	90.65 33	90.99 42	89.63 58	95.03 34	83.53 51	89.62 80	93.35 74	79.20 113	93.83 32	93.60 122	90.81 8	92.96 156	85.02 74	98.45 19	92.41 209
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 59	88.95 6	92.87 13	94.16 33	88.75 18	93.79 33	94.43 76	88.83 27	95.51 49	87.16 38	97.60 74	92.73 189

RE-MVS-def			92.61 9		94.13 59	88.95 6	92.87 13	94.16 33	88.75 18	93.79 33	94.43 76	90.64 11		87.16 38	97.60 74	92.73 189

DVP-MVS		90.06 45	91.32 33	86.29 120	94.16 57	72.56 161	90.54 56	91.01 168	83.61 62	93.75 35	94.65 65	89.76 19	95.78 34	86.42 47	97.97 49	90.55 284
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 48	95.78 34	87.41 31	98.21 34	92.98 182

test0726					94.16 57	72.56 161	90.63 53	93.90 49	83.61 62	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 66	94.27 25	82.35 75	93.67 38	94.82 60	91.18 5	95.52 47	85.36 67	98.73 7	95.23 66

LGP-MVS_train				90.82 37	94.75 41	81.69 63		94.27 25	82.35 75	93.67 38	94.82 60	91.18 5	95.52 47	85.36 67	98.73 7	95.23 66

DVP-MVS++		90.07 44	91.09 37	87.00 106	91.55 138	72.64 157	96.19 2	94.10 40	85.33 42	93.49 40	94.64 68	81.12 135	95.88 18	87.41 31	95.94 136	92.48 205

test_241102_TWO								93.71 59	83.77 58	93.49 40	94.27 83	89.27 24	95.84 26	86.03 57	97.82 57	92.04 234

test_one_0601					93.85 66	73.27 147		94.11 39	86.57 34	93.47 42	94.64 68	88.42 29

MED-MVS test				88.50 80	94.38 48	76.12 126	92.12 33	93.85 53	77.53 139	93.24 43	93.18 131		95.85 24	84.99 75	97.69 65	93.54 154

TestfortrainingZip a		89.97 51	90.77 48	87.58 99	94.38 48	73.21 149	92.12 33	93.85 53	77.53 139	93.24 43	93.18 131	87.06 52	95.85 24	87.89 19	97.69 65	93.68 138

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 40	86.82 43	97.34 84	92.19 227

APD-MVS_3200maxsize		92.05 13	92.24 13	91.48 25	93.02 87	85.17 39	92.47 27	95.05 15	87.65 28	93.21 46	94.39 81	90.09 18	95.08 69	86.67 45	97.60 74	94.18 112

testf1		89.30 63	89.12 67	89.84 53	88.67 213	85.64 35	90.61 54	93.17 85	86.02 38	93.12 47	95.30 46	84.94 76	89.44 269	74.12 217	96.10 127	94.45 97

APD_test2		89.30 63	89.12 67	89.84 53	88.67 213	85.64 35	90.61 54	93.17 85	86.02 38	93.12 47	95.30 46	84.94 76	89.44 269	74.12 217	96.10 127	94.45 97

Anonymous20231211		88.40 76	89.62 62	84.73 163	90.46 168	65.27 259	88.86 96	93.02 96	87.15 30	93.05 49	97.10 11	82.28 113	92.02 182	76.70 178	97.99 46	96.88 26

MP-MVS-pluss		90.81 31	91.08 38	89.99 50	95.97 14	79.88 77	88.13 109	94.51 19	75.79 158	92.94 50	94.96 55	88.36 31	95.01 71	90.70 3	98.40 22	95.09 73
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SD-MVS		88.96 70	89.88 56	86.22 124	91.63 132	77.07 112	89.82 73	93.77 57	78.90 117	92.88 51	92.29 173	86.11 66	90.22 243	86.24 54	97.24 87	91.36 256
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 52	90.35 45	94.36 50	80.98 69	89.16 91	94.05 42	79.03 116	92.87 52	93.74 117	90.60 12	95.21 64	82.87 100	98.76 4	94.87 78
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 53	96.29 22	88.16 36	94.17 105	86.07 56	98.48 18	97.22 18

SMA-MVS		90.31 39	90.48 53	89.83 55	95.31 30	79.52 83	90.98 51	93.24 82	75.37 167	92.84 54	95.28 48	85.58 71	96.09 8	87.92 18	97.76 60	93.88 126
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 65	77.77 101				92.84 54

v10		86.54 107	87.10 101	84.84 157	88.16 228	63.28 281	86.64 139	92.20 124	75.42 166	92.81 56	94.50 72	74.05 230	94.06 109	83.88 88	96.28 116	97.17 19

dcpmvs_2		84.23 166	85.14 144	81.50 259	88.61 217	61.98 307	82.90 240	93.11 88	68.66 273	92.77 57	92.39 165	78.50 162	87.63 308	76.99 177	92.30 266	94.90 76

v8		86.22 113	86.83 109	84.36 175	87.82 236	62.35 301	86.42 143	91.33 155	76.78 146	92.73 58	94.48 74	73.41 242	93.72 122	83.10 95	95.41 157	97.01 23

nrg030		87.85 87	88.49 81	85.91 131	90.07 178	69.73 205	87.86 115	94.20 31	74.04 184	92.70 59	94.66 64	85.88 69	91.50 194	79.72 135	97.32 85	96.50 34

SteuartSystems-ACMMP		91.16 28	91.36 29	90.55 41	93.91 64	80.97 70	91.49 44	93.48 71	82.82 72	92.60 60	93.97 102	88.19 34	96.29 6	87.61 26	98.20 36	94.39 103
Skip Steuart: Steuart Systems R&D Blog.
OPM-MVS		89.80 54	89.97 55	89.27 64	94.76 40	79.86 78	86.76 136	92.78 106	78.78 119	92.51 61	93.64 121	88.13 37	93.84 119	84.83 79	97.55 77	94.10 117
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 61	95.13 52	90.65 10	95.34 58	88.06 16	98.15 39	95.95 46

K. test v3		85.14 137	84.73 154	86.37 118	91.13 154	69.63 207	85.45 163	76.68 377	84.06 56	92.44 63	96.99 13	62.03 328	94.65 83	80.58 127	93.24 238	94.83 83

ME-MVS		90.09 42	90.66 50	88.38 84	92.82 96	76.12 126	89.40 89	93.70 60	83.72 60	92.39 64	93.18 131	88.02 40	95.47 52	84.99 75	97.69 65	93.54 154

ACMMP		91.91 15	91.87 20	92.03 12	95.53 27	85.91 28	93.35 11	94.16 33	82.52 74	92.39 64	94.14 93	89.15 26	95.62 41	87.35 33	98.24 32	94.56 90
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 78	92.86 93	77.09 111	91.19 48	95.74 6	81.38 85	92.28 66	93.80 112	86.89 55	94.64 84	85.52 66	97.51 81	94.30 108

COLMAP_ROB	83.01 3	91.97 14	91.95 15	92.04 11	93.68 69	86.15 24	93.37 10	95.10 14	90.28 10	92.11 67	95.03 54	89.75 21	94.93 73	79.95 132	98.27 28	95.04 74
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 49	89.84 57	90.41 43	94.91 37	84.50 48	89.49 85	93.98 44	79.68 105	92.09 68	93.89 110	83.80 88	93.10 152	82.67 104	98.04 41	93.64 143

TranMVSNet+NR-MVSNet		87.86 86	88.76 80	85.18 149	94.02 62	64.13 271	84.38 191	91.29 156	84.88 48	92.06 69	93.84 111	86.45 61	93.73 121	73.22 239	98.66 11	97.69 9

MTAPA		91.52 19	91.60 23	91.29 30	96.59 4	86.29 21	92.02 37	91.81 140	84.07 55	92.00 70	94.40 80	86.63 57	95.28 61	88.59 11	98.31 26	92.30 219

ACMMP_NAP		90.65 33	91.07 40	89.42 62	95.93 16	79.54 82	89.95 70	93.68 63	77.65 135	91.97 71	94.89 57	88.38 30	95.45 54	89.27 6	97.87 56	93.27 162

FC-MVSNet-test		85.93 121	87.05 103	82.58 232	92.25 110	56.44 376	85.75 156	93.09 90	77.33 141	91.94 72	94.65 65	74.78 216	93.41 142	75.11 204	98.58 14	97.88 7

sc_t1		87.70 90	88.94 73	83.99 186	93.47 73	67.15 236	85.05 173	88.21 244	86.81 32	91.87 73	97.65 5	85.51 73	87.91 300	74.22 212	97.63 70	96.92 25

lessismore_v0				85.95 130	91.10 155	70.99 189		70.91 421		91.79 74	94.42 78	61.76 329	92.93 158	79.52 141	93.03 245	93.93 123

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 71	91.77 75	93.94 108	90.55 13	95.73 37	88.50 12	98.23 33	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 66	93.90 49	80.32 97	91.74 76	94.41 79	88.17 35	95.98 13	86.37 49	97.99 46	93.96 122

mPP-MVS		91.69 16	91.47 27	92.37 6	96.04 13	88.48 8	92.72 18	92.60 113	83.09 68	91.54 77	94.25 87	87.67 46	95.51 49	87.21 37	98.11 40	93.12 172

HFP-MVS		91.30 24	91.39 28	91.02 33	95.43 29	84.66 47	92.58 23	93.29 80	81.99 77	91.47 78	93.96 105	88.35 32	95.56 44	87.74 22	97.74 62	92.85 186

ACMMPR		91.49 20	91.35 31	91.92 16	95.74 20	85.88 30	92.58 23	93.25 81	81.99 77	91.40 79	94.17 92	87.51 47	95.87 20	87.74 22	97.76 60	93.99 120

GST-MVS		90.96 30	91.01 41	90.82 37	95.45 28	82.73 59	91.75 42	93.74 58	80.98 90	91.38 80	93.80 112	87.20 51	95.80 30	87.10 40	97.69 65	93.93 123

test_fmvsmvis_n_1920		85.22 132	85.36 140	84.81 159	85.80 304	76.13 125	85.15 171	92.32 121	61.40 359	91.33 81	90.85 232	83.76 90	86.16 337	84.31 84	93.28 236	92.15 230

ANet_high		83.17 201	85.68 133	75.65 356	81.24 382	45.26 444	79.94 299	92.91 100	83.83 57	91.33 81	96.88 16	80.25 146	85.92 341	68.89 290	95.89 141	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	80.14 100	91.29 83	93.97 102	87.93 42	95.87 20	88.65 10	97.96 51	94.12 116

casdiffmvs_mvg		86.72 102	87.51 94	84.36 175	87.09 263	65.22 260	84.16 195	94.23 28	77.89 131	91.28 84	93.66 120	84.35 83	92.71 162	80.07 129	94.87 183	95.16 71
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 59	89.63 61	89.26 65	92.57 99	81.34 68	90.19 65	93.08 91	80.87 92	91.13 85	93.19 130	86.22 65	95.97 14	82.23 110	97.18 89	90.45 286
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
9.14			89.29 65		91.84 128		88.80 98	95.32 13	75.14 169	91.07 86	92.89 148	87.27 49	93.78 120	83.69 91	97.55 77

CP-MVS		91.67 17	91.58 24	91.96 14	95.29 31	87.62 13	93.38 9	93.36 73	83.16 67	91.06 87	94.00 101	88.26 33	95.71 39	87.28 36	98.39 23	92.55 202

FIs		85.35 131	86.27 116	82.60 231	91.86 125	57.31 369	85.10 172	93.05 92	75.83 157	91.02 88	93.97 102	73.57 238	92.91 160	73.97 221	98.02 44	97.58 12

UniMVSNet_NR-MVSNet		86.84 100	87.06 102	86.17 127	92.86 93	67.02 240	82.55 249	91.56 146	83.08 69	90.92 89	91.82 188	78.25 165	93.99 110	74.16 215	98.35 24	97.49 13

DU-MVS		86.80 101	86.99 105	86.21 125	93.24 83	67.02 240	83.16 232	92.21 123	81.73 81	90.92 89	91.97 181	77.20 183	93.99 110	74.16 215	98.35 24	97.61 10

tt0805		88.09 82	89.79 58	82.98 219	93.26 82	63.94 274	91.10 49	89.64 214	85.07 45	90.91 91	91.09 218	89.16 25	91.87 187	82.03 111	95.87 142	93.13 169

V42		83.47 194	83.37 192	83.75 195	83.16 364	63.33 280	81.31 278	90.23 198	69.51 258	90.91 91	90.81 234	74.16 226	92.29 176	80.06 130	90.22 325	95.62 54

tt0320-xc		86.67 104	88.41 83	81.44 261	93.45 74	60.44 331	83.96 201	88.50 233	87.26 29	90.90 93	97.90 3	85.61 70	86.40 331	70.14 274	98.01 45	97.47 14

region2R		91.44 23	91.30 35	91.87 19	95.75 19	85.90 29	92.63 22	93.30 79	81.91 79	90.88 94	94.21 88	87.75 43	95.87 20	87.60 27	97.71 63	93.83 129

APD_test1		88.40 76	87.91 88	89.88 52	89.50 189	86.65 20	89.98 69	91.91 135	84.26 53	90.87 95	93.92 109	82.18 115	89.29 273	73.75 225	94.81 184	93.70 137

tt0320		86.63 106	88.36 84	81.41 262	93.57 71	60.73 328	84.37 192	88.61 232	87.00 31	90.75 96	97.98 2	85.54 72	86.45 329	69.75 279	97.70 64	97.06 22

WR-MVS		83.56 190	84.40 169	81.06 269	93.43 77	54.88 389	78.67 325	85.02 307	81.24 86	90.74 97	91.56 198	72.85 251	91.08 209	68.00 300	98.04 41	97.23 17

v1240		84.30 162	84.51 165	83.65 198	87.65 243	61.26 315	82.85 241	91.54 147	67.94 285	90.68 98	90.65 243	71.71 268	93.64 125	82.84 101	94.78 185	96.07 41

Elysia		88.71 72	88.89 74	88.19 89	91.26 148	72.96 151	88.10 110	93.59 67	84.31 51	90.42 99	94.10 96	74.07 227	94.82 76	88.19 14	95.92 138	96.80 27

StellarMVS		88.71 72	88.89 74	88.19 89	91.26 148	72.96 151	88.10 110	93.59 67	84.31 51	90.42 99	94.10 96	74.07 227	94.82 76	88.19 14	95.92 138	96.80 27

ZD-MVS					92.22 112	80.48 71		91.85 136	71.22 238	90.38 101	92.98 142	86.06 67	96.11 7	81.99 113	96.75 100

MIMVSNet1		83.63 187	84.59 160	80.74 275	94.06 61	62.77 288	82.72 243	84.53 317	77.57 137	90.34 102	95.92 31	76.88 195	85.83 348	61.88 353	97.42 82	93.62 145

LS3D		90.60 35	90.34 54	91.38 28	89.03 202	84.23 49	93.58 6	94.68 18	90.65 8	90.33 103	93.95 107	84.50 81	95.37 57	80.87 122	95.50 156	94.53 94

KD-MVS_self_test		81.93 231	83.14 199	78.30 317	84.75 327	52.75 404	80.37 294	89.42 221	70.24 251	90.26 104	93.39 126	74.55 223	86.77 323	68.61 295	96.64 102	95.38 59

PMVS	80.48 6	90.08 43	90.66 50	88.34 86	96.71 3	92.97 2	90.31 63	89.57 217	88.51 21	90.11 105	95.12 53	90.98 7	88.92 277	77.55 168	97.07 91	83.13 404
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PC_three_1452									58.96 382	90.06 106	91.33 207	80.66 141	93.03 155	75.78 195	95.94 136	92.48 205

v1921920		84.23 166	84.37 170	83.79 193	87.64 244	61.71 309	82.91 239	91.20 162	67.94 285	90.06 106	90.34 252	72.04 263	93.59 131	82.32 108	94.91 178	96.07 41

ITE_SJBPF				90.11 49	90.72 163	84.97 41		90.30 194	81.56 83	90.02 108	91.20 215	82.40 106	90.81 222	73.58 232	94.66 190	94.56 90

XVS		91.54 18	91.36 29	92.08 9	95.64 24	86.25 22	92.64 20	93.33 75	85.07 45	89.99 109	94.03 99	86.57 58	95.80 30	87.35 33	97.62 72	94.20 109

X-MVStestdata		85.04 141	82.70 210	92.08 9	95.64 24	86.25 22	92.64 20	93.33 75	85.07 45	89.99 109	16.05 473	86.57 58	95.80 30	87.35 33	97.62 72	94.20 109

v1192		84.57 153	84.69 159	84.21 181	87.75 238	62.88 285	83.02 235	91.43 150	69.08 265	89.98 111	90.89 229	72.70 254	93.62 129	82.41 107	94.97 177	96.13 39

Anonymous20240529		86.20 114	87.13 100	83.42 207	90.19 173	64.55 267	84.55 186	90.71 175	85.85 40	89.94 112	95.24 50	82.13 116	90.40 238	69.19 286	96.40 113	95.31 62

fmvsm_s_conf0.5_n_9		87.04 96	87.02 104	87.08 104	89.67 185	75.87 128	84.60 184	89.74 209	74.40 181	89.92 113	93.41 125	80.45 143	90.63 230	86.66 46	94.37 199	94.73 87

pmmvs6		86.52 108	88.06 87	81.90 247	92.22 112	62.28 302	84.66 183	89.15 224	83.54 64	89.85 114	97.32 8	88.08 39	86.80 322	70.43 271	97.30 86	96.62 31

v144192		84.24 165	84.41 168	83.71 197	87.59 245	61.57 310	82.95 238	91.03 167	67.82 289	89.80 115	90.49 249	73.28 246	93.51 137	81.88 116	94.89 180	96.04 43

v1144		84.54 156	84.72 156	84.00 185	87.67 242	62.55 292	82.97 237	90.93 171	70.32 249	89.80 115	90.99 222	73.50 239	93.48 138	81.69 117	94.65 191	95.97 44

DeepC-MVS	82.31 4	89.15 67	89.08 69	89.37 63	93.64 70	79.07 86	88.54 105	94.20 31	73.53 192	89.71 117	94.82 60	85.09 75	95.77 36	84.17 86	98.03 43	93.26 164
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 84	86.93 107	91.22 31	90.08 176	89.30 5	89.68 77	91.11 164	79.26 112	89.68 118	94.81 63	82.44 104	87.74 305	76.54 183	88.74 348	96.61 32

IU-MVS					94.18 54	72.64 157		90.82 173	56.98 399	89.67 119				85.78 64	97.92 52	93.28 161

FMVSNet1		84.55 155	85.45 137	81.85 249	90.27 172	61.05 319	86.83 133	88.27 241	78.57 123	89.66 120	95.64 38	75.43 206	90.68 227	69.09 287	95.33 160	93.82 130

IterMVS-LS		84.73 150	84.98 148	83.96 188	87.35 251	63.66 275	83.25 227	89.88 207	76.06 150	89.62 121	92.37 169	73.40 244	92.52 167	78.16 159	94.77 187	95.69 51
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		88.60 75	89.01 70	87.36 101	91.30 145	77.50 104	87.55 118	92.97 99	87.95 26	89.62 121	92.87 149	84.56 80	93.89 116	77.65 166	96.62 103	90.70 276

UniMVSNet (Re)		86.87 98	86.98 106	86.55 115	93.11 86	68.48 225	83.80 209	92.87 101	80.37 95	89.61 123	91.81 189	77.72 172	94.18 103	75.00 205	98.53 16	96.99 24

IS-MVSNet		86.66 105	86.82 110	86.17 127	92.05 118	66.87 244	91.21 47	88.64 230	86.30 37	89.60 124	92.59 158	69.22 282	94.91 74	73.89 222	97.89 55	96.72 29

v2v482		84.09 169	84.24 174	83.62 199	87.13 258	61.40 312	82.71 244	89.71 212	72.19 226	89.55 125	91.41 204	70.70 274	93.20 147	81.02 120	93.76 218	96.25 37

Baseline_NR-MVSNet		84.00 175	85.90 125	78.29 318	91.47 143	53.44 400	82.29 259	87.00 274	79.06 115	89.55 125	95.72 36	77.20 183	86.14 338	72.30 250	98.51 17	95.28 63

CSCG		86.26 111	86.47 113	85.60 139	90.87 160	74.26 138	87.98 113	91.85 136	80.35 96	89.54 127	88.01 300	79.09 156	92.13 178	75.51 198	95.06 172	90.41 287

ambc				82.98 219	90.55 167	64.86 263	88.20 107	89.15 224		89.40 128	93.96 105	71.67 269	91.38 201	78.83 148	96.55 105	92.71 192

DeepPCF-MVS	81.24 5	87.28 94	86.21 118	90.49 42	91.48 142	84.90 42	83.41 222	92.38 118	70.25 250	89.35 129	90.68 239	82.85 99	94.57 87	79.55 139	95.95 135	92.00 236

LuminaMVS		83.94 178	83.51 186	85.23 147	89.78 184	71.74 175	84.76 179	87.27 259	72.60 217	89.31 130	90.60 247	64.04 314	90.95 213	79.08 145	94.11 207	92.99 180

MVStest1		70.05 379	69.26 382	72.41 385	58.62 476	55.59 383	76.61 360	65.58 444	53.44 416	89.28 131	93.32 127	22.91 475	71.44 430	74.08 219	89.52 335	90.21 294

test_fmvsmconf0.01_n		86.68 103	86.52 112	87.18 102	85.94 301	78.30 92	86.93 129	92.20 124	65.94 308	89.16 132	93.16 135	83.10 96	89.89 258	87.81 21	94.43 197	93.35 157

MSP-MVS		89.08 69	88.16 86	91.83 20	95.76 18	86.14 25	92.75 17	93.90 49	78.43 124	89.16 132	92.25 175	72.03 264	96.36 4	88.21 13	90.93 304	92.98 182
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 66	88.83 78	90.23 47	94.28 51	86.11 26	85.91 151	93.60 66	80.16 99	89.13 134	93.44 124	83.82 87	90.98 212	83.86 89	95.30 164	93.60 147

fmvsm_s_conf0.5_n_10		85.20 134	85.25 143	85.02 154	86.01 299	71.31 184	84.96 174	91.76 142	69.10 264	88.90 135	92.56 161	73.84 234	90.63 230	86.88 41	93.26 237	93.13 169

MDA-MVSNet-bldmvs		77.47 299	76.90 306	79.16 304	79.03 410	64.59 264	66.58 441	75.67 383	73.15 205	88.86 136	88.99 286	66.94 293	81.23 386	64.71 329	88.22 358	91.64 249

EG-PatchMatch MVS		84.08 170	84.11 176	83.98 187	92.22 112	72.61 160	82.20 265	87.02 271	72.63 216	88.86 136	91.02 221	78.52 161	91.11 208	73.41 234	91.09 298	88.21 330

3Dnovator+	83.92 2	89.97 51	89.66 60	90.92 35	91.27 147	81.66 66	91.25 46	94.13 38	88.89 15	88.83 138	94.26 86	77.55 176	95.86 23	84.88 77	95.87 142	95.24 65

fmvsm_s_conf0.5_n_5		84.56 154	84.71 157	84.11 184	87.92 233	72.09 171	84.80 175	88.64 230	64.43 333	88.77 139	91.78 191	78.07 166	87.95 299	85.85 63	92.18 273	92.30 219

EI-MVSNet-UG-set		85.04 141	84.44 167	86.85 110	83.87 345	72.52 163	83.82 207	85.15 303	80.27 98	88.75 140	85.45 354	79.95 150	91.90 185	81.92 115	90.80 311	96.13 39

EI-MVSNet-Vis-set		85.12 139	84.53 164	86.88 109	84.01 341	72.76 154	83.91 205	85.18 302	80.44 93	88.75 140	85.49 352	80.08 148	91.92 184	82.02 112	90.85 309	95.97 44

balanced_conf03		84.80 147	85.40 138	83.00 218	88.95 205	61.44 311	90.42 62	92.37 120	71.48 234	88.72 142	93.13 136	70.16 278	95.15 66	79.26 144	94.11 207	92.41 209

OMC-MVS		88.19 79	87.52 93	90.19 48	91.94 123	81.68 65	87.49 121	93.17 85	76.02 152	88.64 143	91.22 213	84.24 85	93.37 143	77.97 164	97.03 92	95.52 56

RRT-MVS		82.97 204	83.44 188	81.57 257	85.06 321	58.04 363	87.20 123	90.37 188	77.88 132	88.59 144	93.70 119	63.17 322	93.05 154	76.49 184	88.47 350	93.62 145

test_fmvsmconf0.1_n		86.18 116	85.88 126	87.08 104	85.26 317	78.25 93	85.82 155	91.82 138	65.33 323	88.55 145	92.35 172	82.62 103	89.80 260	86.87 42	94.32 201	93.18 168

UA-Net		91.49 20	91.53 25	91.39 27	94.98 35	82.95 58	93.52 7	92.79 105	88.22 23	88.53 146	97.64 6	83.45 93	94.55 89	86.02 60	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 95	82.59 73	88.52 147	94.37 82	86.74 56	95.41 56	86.32 50	98.21 34	93.19 167
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
sasdasda		85.50 125	86.14 119	83.58 201	87.97 230	67.13 237	87.55 118	94.32 22	73.44 195	88.47 148	87.54 316	86.45 61	91.06 210	75.76 196	93.76 218	92.54 203

canonicalmvs		85.50 125	86.14 119	83.58 201	87.97 230	67.13 237	87.55 118	94.32 22	73.44 195	88.47 148	87.54 316	86.45 61	91.06 210	75.76 196	93.76 218	92.54 203

NR-MVSNet		86.00 118	86.22 117	85.34 146	93.24 83	64.56 266	82.21 263	90.46 184	80.99 89	88.42 150	91.97 181	77.56 175	93.85 117	72.46 249	98.65 12	97.61 10

alignmvs		83.94 178	83.98 179	83.80 192	87.80 237	67.88 232	84.54 188	91.42 152	73.27 203	88.41 151	87.96 301	72.33 257	90.83 221	76.02 193	94.11 207	92.69 193

TransMVSNet (Re)		84.02 174	85.74 132	78.85 306	91.00 157	55.20 388	82.29 259	87.26 260	79.65 106	88.38 152	95.52 41	83.00 97	86.88 320	67.97 301	96.60 104	94.45 97

PM-MVS		80.20 268	79.00 279	83.78 194	88.17 227	86.66 19	81.31 278	66.81 441	69.64 256	88.33 153	90.19 259	64.58 308	83.63 372	71.99 252	90.03 328	81.06 432

fmvsm_s_conf0.5_n_3		86.19 115	87.27 98	82.95 221	86.91 271	70.38 196	85.31 167	92.61 112	75.59 162	88.32 154	92.87 149	82.22 114	88.63 286	88.80 9	92.82 253	89.83 300

tttt0517		81.07 247	79.58 273	85.52 141	88.99 204	66.45 249	87.03 128	75.51 385	73.76 188	88.32 154	90.20 258	37.96 446	94.16 107	79.36 143	95.13 168	95.93 47

casdiffmvs		85.21 133	85.85 127	83.31 210	86.17 293	62.77 288	83.03 234	93.93 47	74.69 174	88.21 156	92.68 157	82.29 112	91.89 186	77.87 165	93.75 221	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		71.42 365	70.67 367	73.64 372	69.66 464	70.46 194	66.97 440	89.73 210	42.68 461	88.20 157	83.04 383	43.77 430	60.07 462	65.35 324	86.66 380	90.39 288

SSC-MVS		77.55 298	81.64 229	65.29 430	90.46 168	20.33 477	73.56 393	68.28 431	85.44 41	88.18 158	94.64 68	70.93 272	81.33 385	71.25 258	92.03 276	94.20 109

MVSMamba_PlusPlus		87.53 92	88.86 77	83.54 205	92.03 119	62.26 303	91.49 44	92.62 111	88.07 25	88.07 159	96.17 26	72.24 259	95.79 33	84.85 78	94.16 206	92.58 200

MGCFI-Net		85.04 141	85.95 123	82.31 240	87.52 247	63.59 277	86.23 147	93.96 45	73.46 193	88.07 159	87.83 311	86.46 60	90.87 220	76.17 190	93.89 214	92.47 207

v148		82.31 216	82.48 216	81.81 252	85.59 310	59.66 342	81.47 275	86.02 286	72.85 211	88.05 161	90.65 243	70.73 273	90.91 217	75.15 203	91.79 282	94.87 78

AstraMVS		81.67 235	81.40 239	82.48 237	87.06 266	66.47 248	81.41 276	81.68 343	68.78 270	88.00 162	90.95 227	65.70 303	87.86 304	76.66 179	92.38 263	93.12 172

AllTest		87.97 85	87.40 97	89.68 56	91.59 133	83.40 52	89.50 84	95.44 11	79.47 107	88.00 162	93.03 140	82.66 101	91.47 195	70.81 262	96.14 124	94.16 113

TestCases				89.68 56	91.59 133	83.40 52		95.44 11	79.47 107	88.00 162	93.03 140	82.66 101	91.47 195	70.81 262	96.14 124	94.16 113

fmvsm_s_conf0.1_n_2		83.82 181	83.49 187	84.84 157	85.99 300	70.19 199	80.93 285	87.58 255	67.26 298	87.94 165	92.37 169	71.40 270	88.01 296	86.03 57	91.87 281	96.31 36

fmvsm_s_conf0.5_n_8		85.48 127	85.75 131	84.68 166	87.10 261	69.98 201	84.28 193	92.68 108	74.77 172	87.90 166	92.36 171	73.94 231	90.41 237	85.95 62	92.74 255	93.66 139

viewdifsd2359ckpt11		82.46 214	82.98 203	80.88 272	83.53 348	61.00 322	79.46 309	85.97 288	69.48 259	87.89 167	91.31 209	82.10 117	88.61 287	74.28 210	92.86 250	93.02 176

viewmsd2359difaftdt		82.46 214	82.99 202	80.88 272	83.52 349	61.00 322	79.46 309	85.97 288	69.48 259	87.89 167	91.31 209	82.10 117	88.61 287	74.28 210	92.86 250	93.02 176

pm-mvs1		83.69 184	84.95 150	79.91 292	90.04 180	59.66 342	82.43 255	87.44 256	75.52 164	87.85 169	95.26 49	81.25 134	85.65 351	68.74 293	96.04 129	94.42 101

PCF-MVS	74.62 15	82.15 224	80.92 251	85.84 134	89.43 191	72.30 167	80.53 292	91.82 138	57.36 395	87.81 170	89.92 267	77.67 173	93.63 126	58.69 371	95.08 171	91.58 251
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
fmvsm_s_conf0.5_n_2		83.62 188	83.29 193	84.62 167	85.43 314	70.18 200	80.61 291	87.24 261	67.14 299	87.79 171	91.87 183	71.79 267	87.98 298	86.00 61	91.77 284	95.71 50

guyue		81.57 237	81.37 241	82.15 242	86.39 281	66.13 252	81.54 274	83.21 327	69.79 255	87.77 172	89.95 265	65.36 306	87.64 307	75.88 194	92.49 261	92.67 194

KinetiMVS		85.95 120	86.10 121	85.50 143	87.56 246	69.78 203	83.70 212	89.83 208	80.42 94	87.76 173	93.24 129	73.76 236	91.54 193	85.03 73	93.62 227	95.19 68

mvs5depth		83.82 181	84.54 163	81.68 255	82.23 370	68.65 223	86.89 130	89.90 206	80.02 102	87.74 174	97.86 4	64.19 313	82.02 381	76.37 185	95.63 154	94.35 104

test_fmvsmconf_n		85.88 122	85.51 136	86.99 107	84.77 326	78.21 94	85.40 165	91.39 153	65.32 324	87.72 175	91.81 189	82.33 108	89.78 261	86.68 44	94.20 204	92.99 180

FMVSNet2		81.31 242	81.61 231	80.41 284	86.38 283	58.75 358	83.93 204	86.58 277	72.43 218	87.65 176	92.98 142	63.78 318	90.22 243	66.86 305	93.92 213	92.27 223

viewdifsd2359ckpt07		83.41 198	84.35 171	80.56 281	85.84 303	58.93 353	79.47 308	91.28 157	73.01 208	87.59 177	92.07 178	85.24 74	88.68 284	73.59 231	91.11 296	94.09 118

GeoE		85.45 129	85.81 128	84.37 173	90.08 176	67.07 239	85.86 154	91.39 153	72.33 223	87.59 177	90.25 257	84.85 78	92.37 172	78.00 162	91.94 280	93.66 139

VPA-MVSNet		83.47 194	84.73 154	79.69 297	90.29 171	57.52 368	81.30 280	88.69 229	76.29 148	87.58 179	94.44 75	80.60 142	87.20 314	66.60 310	96.82 98	94.34 105

CPTT-MVS		89.39 61	88.98 72	90.63 40	95.09 33	86.95 16	92.09 36	92.30 122	79.74 104	87.50 180	92.38 166	81.42 132	93.28 145	83.07 96	97.24 87	91.67 248

VDDNet		84.35 160	85.39 139	81.25 264	95.13 32	59.32 345	85.42 164	81.11 348	86.41 36	87.41 181	96.21 25	73.61 237	90.61 232	66.33 312	96.85 95	93.81 133

VortexMVS		80.51 257	80.63 254	80.15 290	83.36 357	61.82 308	80.63 290	88.00 247	67.11 300	87.23 182	89.10 284	63.98 315	88.00 297	73.63 230	92.63 258	90.64 281

c3_l		81.64 236	81.59 232	81.79 254	80.86 388	59.15 350	78.61 326	90.18 200	68.36 276	87.20 183	87.11 328	69.39 280	91.62 191	78.16 159	94.43 197	94.60 89

VDD-MVS		84.23 166	84.58 161	83.20 213	91.17 153	65.16 262	83.25 227	84.97 310	79.79 103	87.18 184	94.27 83	74.77 217	90.89 218	69.24 283	96.54 106	93.55 153

MSLP-MVS++		85.00 144	86.03 122	81.90 247	91.84 128	71.56 182	86.75 137	93.02 96	75.95 155	87.12 185	89.39 277	77.98 167	89.40 272	77.46 169	94.78 185	84.75 376

baseline		85.20 134	85.93 124	83.02 217	86.30 288	62.37 300	84.55 186	93.96 45	74.48 178	87.12 185	92.03 180	82.30 110	91.94 183	78.39 152	94.21 203	94.74 86

YYNet1		70.06 378	70.44 371	68.90 407	73.76 447	53.42 401	58.99 459	67.20 437	58.42 385	87.10 187	85.39 356	59.82 342	67.32 447	59.79 367	83.50 416	85.96 361

MDA-MVSNet_test_wron		70.05 379	70.44 371	68.88 408	73.84 446	53.47 399	58.93 460	67.28 436	58.43 384	87.09 188	85.40 355	59.80 343	67.25 448	59.66 368	83.54 415	85.92 363

test_fmvs3		75.72 323	75.20 324	77.27 334	75.01 443	69.47 209	78.93 318	84.88 311	46.67 445	87.08 189	87.84 310	50.44 394	71.62 428	77.42 172	88.53 349	90.72 274

CNVR-MVS		87.81 88	87.68 91	88.21 88	92.87 91	77.30 110	85.25 168	91.23 161	77.31 142	87.07 190	91.47 203	82.94 98	94.71 80	84.67 81	96.27 118	92.62 197

EPP-MVSNet		85.47 128	85.04 147	86.77 112	91.52 141	69.37 210	91.63 43	87.98 248	81.51 84	87.05 191	91.83 187	66.18 300	95.29 59	70.75 265	96.89 94	95.64 53

TinyColmap		81.25 243	82.34 218	77.99 324	85.33 315	60.68 329	82.32 258	88.33 239	71.26 237	86.97 192	92.22 177	77.10 186	86.98 318	62.37 347	95.17 167	86.31 359

eth_miper_zixun_eth		80.84 251	80.22 264	82.71 229	81.41 380	60.98 324	77.81 337	90.14 201	67.31 297	86.95 193	87.24 325	64.26 311	92.31 174	75.23 202	91.61 288	94.85 82

Anonymous20240521		80.18 269	81.25 243	76.95 338	83.15 365	60.84 326	82.46 252	85.99 287	68.76 271	86.78 194	93.73 118	59.13 347	77.44 407	73.71 226	97.55 77	92.56 201

Patchmatch-RL test		74.48 336	73.68 336	76.89 341	84.83 324	66.54 246	72.29 403	69.16 430	57.70 391	86.76 195	86.33 338	45.79 415	82.59 376	69.63 280	90.65 321	81.54 423

XVG-OURS-SEG-HR		89.59 58	89.37 64	90.28 46	94.47 43	85.95 27	86.84 132	93.91 48	80.07 101	86.75 196	93.26 128	93.64 2	90.93 215	84.60 82	90.75 312	93.97 121

fmvsm_l_conf0.5_n_9		83.98 176	84.46 166	82.53 235	86.11 296	70.65 193	82.45 254	89.17 223	67.72 291	86.74 197	91.49 200	79.20 154	85.86 347	84.71 80	92.60 259	91.07 262

h-mvs33		84.25 164	82.76 209	88.72 75	91.82 130	82.60 60	84.00 200	84.98 309	71.27 235	86.70 198	90.55 248	63.04 325	93.92 115	78.26 157	94.20 204	89.63 302

hse-mvs2		83.47 194	81.81 226	88.47 81	91.03 156	82.27 61	82.61 245	83.69 323	71.27 235	86.70 198	86.05 344	63.04 325	92.41 170	78.26 157	93.62 227	90.71 275

HPM-MVS++		88.93 71	88.45 82	90.38 44	94.92 36	85.85 31	89.70 75	91.27 160	78.20 127	86.69 200	92.28 174	80.36 145	95.06 70	86.17 55	96.49 108	90.22 290

TSAR-MVS + MP.		88.14 80	87.82 90	89.09 69	95.72 22	76.74 115	92.49 26	91.19 163	67.85 288	86.63 201	94.84 59	79.58 153	95.96 15	87.62 25	94.50 193	94.56 90
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SSM_0404		85.16 136	85.09 145	85.36 145	90.14 175	69.52 208	86.17 148	91.58 144	74.41 179	86.55 202	91.49 200	78.54 159	93.97 112	73.71 226	93.21 241	92.59 199

EI-MVSNet		82.61 209	82.42 217	83.20 213	83.25 361	63.66 275	83.50 219	85.07 304	76.06 150	86.55 202	85.10 360	73.41 242	90.25 240	78.15 161	90.67 318	95.68 52

HQP_MVS		87.75 89	87.43 96	88.70 77	93.45 74	76.42 119	89.45 86	93.61 64	79.44 109	86.55 202	92.95 146	74.84 214	95.22 62	80.78 124	95.83 144	94.46 95

plane_prior3						76.85 114			77.79 134	86.55 202

BH-untuned		80.96 249	80.99 249	80.84 274	88.55 219	68.23 226	80.33 295	88.46 234	72.79 214	86.55 202	86.76 332	74.72 218	91.77 190	61.79 354	88.99 343	82.52 412

MVSTER		77.09 304	75.70 318	81.25 264	75.27 440	61.08 318	77.49 345	85.07 304	60.78 369	86.55 202	88.68 290	43.14 435	90.25 240	73.69 229	90.67 318	92.42 208

旧先验2							81.73 270		56.88 400	86.54 208			84.90 357	72.81 246

IterMVS-SCA-FT		80.64 255	79.41 274	84.34 177	83.93 343	69.66 206	76.28 365	81.09 349	72.43 218	86.47 209	90.19 259	60.46 335	93.15 150	77.45 170	86.39 384	90.22 290

WB-MVS		76.06 319	80.01 270	64.19 433	89.96 182	20.58 476	72.18 404	68.19 432	83.21 66	86.46 210	93.49 123	70.19 277	78.97 401	65.96 314	90.46 324	93.02 176

test_fmvsm_n_1920		83.60 189	82.89 205	85.74 136	85.22 318	77.74 102	84.12 197	90.48 182	59.87 379	86.45 211	91.12 217	75.65 204	85.89 345	82.28 109	90.87 307	93.58 149

fmvsm_s_conf0.5_n_4		84.38 158	84.27 173	84.74 162	87.25 254	70.84 190	83.55 217	88.45 235	68.64 274	86.29 212	91.31 209	74.97 212	88.42 290	87.87 20	90.07 327	94.95 75

DIV-MVS_self_test		80.43 259	80.23 262	81.02 270	79.99 398	59.25 347	77.07 351	87.02 271	67.38 294	86.19 213	89.22 280	63.09 323	90.16 246	76.32 186	95.80 146	93.66 139

CDPH-MVS		86.17 117	85.54 135	88.05 93	92.25 110	75.45 131	83.85 206	92.01 130	65.91 310	86.19 213	91.75 193	83.77 89	94.98 72	77.43 171	96.71 101	93.73 136

cl____		80.42 260	80.23 262	81.02 270	79.99 398	59.25 347	77.07 351	87.02 271	67.37 295	86.18 215	89.21 281	63.08 324	90.16 246	76.31 187	95.80 146	93.65 142

MVS_111021_LR		84.28 163	83.76 183	85.83 135	89.23 196	83.07 55	80.99 284	83.56 325	72.71 215	86.07 216	89.07 285	81.75 129	86.19 336	77.11 175	93.36 232	88.24 329

viewmacassd2359aftdt		84.04 173	84.78 153	81.81 252	86.43 280	60.32 333	81.95 267	92.82 104	71.56 231	86.06 217	92.98 142	81.79 128	90.28 239	76.18 189	93.24 238	94.82 84

GBi-Net		82.02 228	82.07 219	81.85 249	86.38 283	61.05 319	86.83 133	88.27 241	72.43 218	86.00 218	95.64 38	63.78 318	90.68 227	65.95 315	93.34 233	93.82 130

test1		82.02 228	82.07 219	81.85 249	86.38 283	61.05 319	86.83 133	88.27 241	72.43 218	86.00 218	95.64 38	63.78 318	90.68 227	65.95 315	93.34 233	93.82 130

FMVSNet3		78.80 282	78.55 287	79.57 299	82.89 368	56.89 374	81.76 269	85.77 291	69.04 266	86.00 218	90.44 250	51.75 387	90.09 252	65.95 315	93.34 233	91.72 245

miper_ehance_all_eth		80.34 263	80.04 269	81.24 266	79.82 401	58.95 352	77.66 339	89.66 213	65.75 315	85.99 221	85.11 359	68.29 287	91.42 199	76.03 192	92.03 276	93.33 158

tfpnnormal		81.79 234	82.95 204	78.31 316	88.93 206	55.40 384	80.83 288	82.85 332	76.81 145	85.90 222	94.14 93	74.58 221	86.51 327	66.82 308	95.68 152	93.01 179

TAPA-MVS	77.73 12	85.71 124	84.83 152	88.37 85	88.78 212	79.72 79	87.15 126	93.50 70	69.17 262	85.80 223	89.56 273	80.76 139	92.13 178	73.21 244	95.51 155	93.25 165
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
mamba_0408		83.44 197	82.88 206	85.11 150	89.13 198	68.97 218	72.73 400	91.28 157	72.90 209	85.68 224	90.61 245	76.78 196	93.97 112	73.37 236	93.47 229	92.38 214

SSM_04072		81.44 240	82.88 206	77.10 336	89.13 198	68.97 218	72.73 400	91.28 157	72.90 209	85.68 224	90.61 245	76.78 196	69.94 433	73.37 236	93.47 229	92.38 214

SSM_0407		84.89 146	84.85 151	85.01 155	89.13 198	68.97 218	85.60 160	91.58 144	74.41 179	85.68 224	91.49 200	78.54 159	93.69 123	73.71 226	93.47 229	92.38 214

TSAR-MVS + GP.		83.95 177	82.69 211	87.72 96	89.27 195	81.45 67	83.72 211	81.58 346	74.73 173	85.66 227	86.06 343	72.56 256	92.69 164	75.44 200	95.21 165	89.01 323

EU-MVSNet		75.12 328	74.43 331	77.18 335	83.11 366	59.48 344	85.71 158	82.43 336	39.76 465	85.64 228	88.76 288	44.71 428	87.88 302	73.86 223	85.88 390	84.16 387

MonoMVSNet		76.66 310	77.26 302	74.86 362	79.86 400	54.34 393	86.26 146	86.08 283	71.08 240	85.59 229	88.68 290	53.95 377	85.93 340	63.86 336	80.02 436	84.32 382

LF4IMVS		82.75 208	81.93 224	85.19 148	82.08 371	80.15 76	85.53 161	88.76 228	68.01 282	85.58 230	87.75 312	71.80 266	86.85 321	74.02 220	93.87 215	88.58 326

Patchmtry		76.56 313	77.46 298	73.83 370	79.37 407	46.60 437	82.41 256	76.90 374	73.81 187	85.56 231	92.38 166	48.07 401	83.98 369	63.36 341	95.31 163	90.92 268

MVS_111021_HR		84.63 151	84.34 172	85.49 144	90.18 174	75.86 129	79.23 316	87.13 265	73.35 197	85.56 231	89.34 278	83.60 92	90.50 234	76.64 180	94.05 211	90.09 296

testdata				79.54 300	92.87 91	72.34 166		80.14 355	59.91 378	85.47 233	91.75 193	67.96 289	85.24 353	68.57 297	92.18 273	81.06 432

FE-MVSNET		78.46 288	79.36 276	75.75 354	86.53 277	54.53 391	78.03 331	85.35 298	69.01 267	85.41 234	90.68 239	64.27 310	85.73 349	62.59 346	92.35 265	87.00 352

viewcassd2359sk11		83.53 192	83.96 180	82.25 241	86.97 270	61.13 317	80.80 289	93.22 83	70.97 241	85.36 235	91.08 219	81.84 126	91.29 202	74.79 207	90.58 323	94.33 106

mvsmamba		80.30 265	78.87 280	84.58 169	88.12 229	67.55 234	92.35 30	84.88 311	63.15 340	85.33 236	90.91 228	50.71 391	95.20 65	66.36 311	87.98 360	90.99 265

test1111		78.53 287	78.85 282	77.56 330	92.22 112	47.49 433	82.61 245	69.24 429	72.43 218	85.28 237	94.20 89	51.91 385	90.07 254	65.36 323	96.45 111	95.11 72

thisisatest0530		79.07 277	77.33 301	84.26 180	87.13 258	64.58 265	83.66 214	75.95 380	68.86 269	85.22 238	87.36 322	38.10 443	93.57 134	75.47 199	94.28 202	94.62 88

BP-MVS1		82.81 206	81.67 228	86.23 122	87.88 235	68.53 224	86.06 150	84.36 318	75.65 160	85.14 239	90.19 259	45.84 414	94.42 92	85.18 69	94.72 189	95.75 49

NormalMVS		86.47 109	85.32 141	89.94 51	94.43 44	80.42 72	88.63 103	93.59 67	74.56 176	85.12 240	90.34 252	66.19 298	94.20 100	76.57 181	98.44 20	95.19 68

SymmetryMVS		84.79 149	83.54 185	88.55 79	92.44 104	80.42 72	88.63 103	82.37 337	74.56 176	85.12 240	90.34 252	66.19 298	94.20 100	76.57 181	95.68 152	91.03 264

EC-MVSNet		88.01 83	88.32 85	87.09 103	89.28 194	72.03 172	90.31 63	96.31 4	80.88 91	85.12 240	89.67 272	84.47 82	95.46 53	82.56 105	96.26 119	93.77 135

CLD-MVS		83.18 200	82.64 212	84.79 160	89.05 201	67.82 233	77.93 335	92.52 114	68.33 277	85.07 243	81.54 402	82.06 119	92.96 156	69.35 282	97.91 54	93.57 150
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		82.58 211	81.93 224	84.50 170	87.68 241	73.35 144	86.14 149	77.70 366	61.64 357	85.02 244	91.62 195	77.75 170	86.24 333	82.79 102	87.07 373	93.91 125

FA-MVS(test-final)		83.13 202	83.02 201	83.43 206	86.16 295	66.08 253	88.00 112	88.36 238	75.55 163	85.02 244	92.75 155	65.12 307	92.50 168	74.94 206	91.30 294	91.72 245

viewdifsd2359ckpt09		83.64 186	83.18 197	85.03 153	87.26 253	66.99 242	85.32 166	93.83 56	65.57 318	84.99 246	89.40 276	77.30 179	93.57 134	71.16 261	93.80 217	94.54 93

DeepC-MVS_fast	80.27 8	86.23 112	85.65 134	87.96 94	91.30 145	76.92 113	87.19 124	91.99 131	70.56 245	84.96 247	90.69 238	80.01 149	95.14 67	78.37 153	95.78 148	91.82 241
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	84.80 147	84.71 157	85.06 152	86.36 286	74.71 134	88.77 99	90.00 204	75.65 160	84.96 247	93.17 134	74.06 229	91.19 205	78.28 156	91.09 298	89.29 310

QAPM		82.59 210	82.59 214	82.58 232	86.44 279	66.69 245	89.94 71	90.36 189	67.97 284	84.94 249	92.58 160	72.71 253	92.18 177	70.63 268	87.73 365	88.85 324

fmvsm_l_conf0.5_n_3		85.11 140	84.96 149	85.56 140	87.49 249	75.69 130	84.71 181	90.61 180	67.64 292	84.88 250	92.05 179	82.30 110	88.36 292	83.84 90	91.10 297	92.62 197

VPNet		80.25 266	81.68 227	75.94 352	92.46 103	47.98 431	76.70 356	81.67 344	73.45 194	84.87 251	92.82 151	74.66 220	86.51 327	61.66 356	96.85 95	93.33 158

NCCC		87.36 93	86.87 108	88.83 72	92.32 109	78.84 89	86.58 140	91.09 166	78.77 120	84.85 252	90.89 229	80.85 138	95.29 59	81.14 119	95.32 161	92.34 217

viewmanbaseed2359cas		82.95 205	83.43 189	81.52 258	85.18 319	60.03 338	81.36 277	92.38 118	69.55 257	84.84 253	91.38 205	79.85 152	90.09 252	74.22 212	92.09 275	94.43 100

PHI-MVS		86.38 110	85.81 128	88.08 91	88.44 222	77.34 108	89.35 90	93.05 92	73.15 205	84.76 254	87.70 313	78.87 158	94.18 103	80.67 126	96.29 115	92.73 189

pmmvs-eth3d		78.42 291	77.04 304	82.57 234	87.44 250	74.41 137	80.86 287	79.67 357	55.68 404	84.69 255	90.31 256	60.91 333	85.42 352	62.20 349	91.59 289	87.88 340

test_prior2							83.37 223		75.43 165	84.58 256	91.57 197	81.92 124		79.54 140	96.97 93

fmvsm_s_conf0.5_n_6		84.05 171	84.14 175	83.81 191	87.75 238	71.17 186	83.42 221	91.10 165	67.90 287	84.53 257	90.70 237	73.01 249	88.73 283	85.09 70	93.72 223	91.53 253

fmvsm_s_conf0.5_n_a		82.21 220	81.51 237	84.32 178	86.56 276	73.35 144	85.46 162	77.30 370	61.81 353	84.51 258	90.88 231	77.36 178	86.21 335	82.72 103	86.97 378	93.38 156

TEST9					92.34 107	79.70 80	83.94 202	90.32 191	65.41 322	84.49 259	90.97 223	82.03 120	93.63 126

train_agg		85.98 119	85.28 142	88.07 92	92.34 107	79.70 80	83.94 202	90.32 191	65.79 312	84.49 259	90.97 223	81.93 122	93.63 126	81.21 118	96.54 106	90.88 270

fmvsm_s_conf0.1_n		82.17 222	81.59 232	83.94 190	86.87 274	71.57 181	85.19 170	77.42 369	62.27 351	84.47 261	91.33 207	76.43 199	85.91 343	83.14 93	87.14 371	94.33 106

Gipuma		84.44 157	86.33 115	78.78 307	84.20 338	73.57 142	89.55 81	90.44 185	84.24 54	84.38 262	94.89 57	76.35 202	80.40 393	76.14 191	96.80 99	82.36 414
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
test_f		64.31 418	65.85 406	59.67 445	66.54 469	62.24 305	57.76 462	70.96 420	40.13 463	84.36 263	82.09 395	46.93 403	51.67 469	61.99 352	81.89 426	65.12 460

test_8					92.09 116	78.87 88	83.82 207	90.31 193	65.79 312	84.36 263	90.96 225	81.93 122	93.44 140

cl22		78.97 278	78.21 293	81.24 266	77.74 415	59.01 351	77.46 346	87.13 265	65.79 312	84.32 265	85.10 360	58.96 349	90.88 219	75.36 201	92.03 276	93.84 128

CS-MVS		88.14 80	87.67 92	89.54 61	89.56 187	79.18 85	90.47 59	94.77 17	79.37 111	84.32 265	89.33 279	83.87 86	94.53 90	82.45 106	94.89 180	94.90 76

agg_prior					91.58 136	77.69 103		90.30 194		84.32 265			93.18 148

Anonymous202405211		80.51 257	81.19 247	78.49 313	88.48 220	57.26 370	76.63 358	82.49 335	81.21 87	84.30 268	92.24 176	67.99 288	86.24 333	62.22 348	95.13 168	91.98 238

LFMVS		80.15 270	80.56 256	78.89 305	89.19 197	55.93 378	85.22 169	73.78 397	82.96 70	84.28 269	92.72 156	57.38 359	90.07 254	63.80 337	95.75 149	90.68 277

Vis-MVSNet		86.86 99	86.58 111	87.72 96	92.09 116	77.43 107	87.35 122	92.09 128	78.87 118	84.27 270	94.05 98	78.35 164	93.65 124	80.54 128	91.58 290	92.08 232
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
ECVR-MVS		78.44 290	78.63 286	77.88 326	91.85 126	48.95 427	83.68 213	69.91 425	72.30 224	84.26 271	94.20 89	51.89 386	89.82 259	63.58 338	96.02 130	94.87 78

FE-MVS		79.98 273	78.86 281	83.36 208	86.47 278	66.45 249	89.73 74	84.74 315	72.80 213	84.22 272	91.38 205	44.95 426	93.60 130	63.93 335	91.50 291	90.04 297

ETV-MVS		84.31 161	83.91 182	85.52 141	88.58 218	70.40 195	84.50 190	93.37 72	78.76 121	84.07 273	78.72 427	80.39 144	95.13 68	73.82 224	92.98 247	91.04 263

fmvsm_s_conf0.5_n		81.91 232	81.30 242	83.75 195	86.02 298	71.56 182	84.73 180	77.11 373	62.44 348	84.00 274	90.68 239	76.42 200	85.89 345	83.14 93	87.11 372	93.81 133

MCST-MVS		84.36 159	83.93 181	85.63 138	91.59 133	71.58 180	83.52 218	92.13 126	61.82 352	83.96 275	89.75 270	79.93 151	93.46 139	78.33 155	94.34 200	91.87 240

新几何1				82.95 221	93.96 63	78.56 91		80.24 354	55.45 405	83.93 276	91.08 219	71.19 271	88.33 293	65.84 318	93.07 244	81.95 419

mmtdpeth		85.13 138	85.78 130	83.17 215	84.65 328	74.71 134	85.87 153	90.35 190	77.94 130	83.82 277	96.96 15	77.75 170	80.03 396	78.44 151	96.21 120	94.79 85

fmvsm_l_conf0.5_n		82.06 226	81.54 236	83.60 200	83.94 342	73.90 140	83.35 224	86.10 282	58.97 381	83.80 278	90.36 251	74.23 224	86.94 319	82.90 99	90.22 325	89.94 298

GDP-MVS		82.17 222	80.85 253	86.15 129	88.65 215	68.95 221	85.65 159	93.02 96	68.42 275	83.73 279	89.54 274	45.07 425	94.31 94	79.66 137	93.87 215	95.19 68

viewdifsd2359ckpt13		82.22 219	81.98 223	82.95 221	85.48 313	64.44 268	83.17 231	92.11 127	65.97 307	83.72 280	89.73 271	77.60 174	90.80 223	70.61 269	89.42 336	93.59 148

BH-RMVSNet		80.53 256	80.22 264	81.49 260	87.19 257	66.21 251	77.79 338	86.23 280	74.21 183	83.69 281	88.50 294	73.25 247	90.75 224	63.18 343	87.90 361	87.52 344

USDC		76.63 311	76.73 309	76.34 348	83.46 352	57.20 371	80.02 298	88.04 246	52.14 427	83.65 282	91.25 212	63.24 321	86.65 325	54.66 399	94.11 207	85.17 371

miper_enhance_ethall		77.83 294	76.93 305	80.51 282	76.15 432	58.01 364	75.47 377	88.82 226	58.05 389	83.59 283	80.69 406	64.41 309	91.20 204	73.16 245	92.03 276	92.33 218

MM		87.64 91	87.15 99	89.09 69	89.51 188	76.39 121	88.68 101	86.76 275	84.54 50	83.58 284	93.78 114	73.36 245	96.48 2	87.98 17	96.21 120	94.41 102

Effi-MVS+-dtu		85.82 123	83.38 191	93.14 4	87.13 258	91.15 3	87.70 117	88.42 236	74.57 175	83.56 285	85.65 348	78.49 163	94.21 99	72.04 251	92.88 249	94.05 119

CNLPA		83.55 191	83.10 200	84.90 156	89.34 193	83.87 50	84.54 188	88.77 227	79.09 114	83.54 286	88.66 293	74.87 213	81.73 383	66.84 307	92.29 268	89.11 316

SDMVSNet		81.90 233	83.17 198	78.10 321	88.81 210	62.45 298	76.08 369	86.05 285	73.67 189	83.41 287	93.04 138	82.35 107	80.65 390	70.06 276	95.03 173	91.21 258

sd_testset		79.95 274	81.39 240	75.64 357	88.81 210	58.07 362	76.16 368	82.81 333	73.67 189	83.41 287	93.04 138	80.96 137	77.65 406	58.62 372	95.03 173	91.21 258

diffmvs_AUTHOR		81.24 244	81.55 235	80.30 286	80.61 393	60.22 334	77.98 334	90.48 182	67.77 290	83.34 289	89.50 275	74.69 219	87.42 310	78.78 149	90.81 310	93.27 162

OpenMVS_ROB	70.19 17	77.77 297	77.46 298	78.71 309	84.39 334	61.15 316	81.18 282	82.52 334	62.45 347	83.34 289	87.37 321	66.20 297	88.66 285	64.69 330	85.02 400	86.32 358

thres100view900		75.45 324	75.05 325	76.66 344	87.27 252	51.88 412	81.07 283	73.26 402	75.68 159	83.25 291	86.37 337	45.54 416	88.80 278	51.98 415	90.99 300	89.31 308

miper_lstm_enhance		76.45 315	76.10 314	77.51 331	76.72 426	60.97 325	64.69 445	85.04 306	63.98 336	83.20 292	88.22 297	56.67 363	78.79 403	73.22 239	93.12 243	92.78 188

IterMVS		76.91 306	76.34 312	78.64 310	80.91 386	64.03 272	76.30 364	79.03 360	64.88 331	83.11 293	89.16 282	59.90 341	84.46 362	68.61 295	85.15 398	87.42 345
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
thres600view7		75.97 320	75.35 323	77.85 328	87.01 267	51.84 413	80.45 293	73.26 402	75.20 168	83.10 294	86.31 340	45.54 416	89.05 274	55.03 397	92.24 270	92.66 195

mvs_anonymous		78.13 292	78.76 284	76.23 351	79.24 408	50.31 423	78.69 324	84.82 313	61.60 358	83.09 295	92.82 151	73.89 233	87.01 315	68.33 299	86.41 383	91.37 255

fmvsm_l_conf0.5_n_a		81.46 239	80.87 252	83.25 211	83.73 347	73.21 149	83.00 236	85.59 295	58.22 387	82.96 296	90.09 264	72.30 258	86.65 325	81.97 114	89.95 330	89.88 299

test_fmvs2		73.57 345	72.80 347	75.90 353	72.74 457	68.84 222	77.07 351	84.32 320	45.14 451	82.89 297	84.22 372	48.37 399	70.36 432	73.40 235	87.03 375	88.52 327

MVS_Test		82.47 213	83.22 194	80.22 288	82.62 369	57.75 367	82.54 250	91.96 133	71.16 239	82.89 297	92.52 163	77.41 177	90.50 234	80.04 131	87.84 364	92.40 211

reproduce_monomvs		74.09 340	73.23 342	76.65 345	76.52 427	54.54 390	77.50 344	81.40 347	65.85 311	82.86 299	86.67 333	27.38 469	84.53 361	70.24 273	90.66 320	90.89 269

test12				86.57 114	90.74 162	72.63 159		90.69 176		82.76 300		79.20 154	94.80 78		95.32 161	92.27 223

原ACMM1				84.60 168	92.81 97	74.01 139		91.50 148	62.59 343	82.73 301	90.67 242	76.53 198	94.25 97	69.24 283	95.69 151	85.55 367

test_yl		78.71 285	78.51 288	79.32 302	84.32 335	58.84 355	78.38 327	85.33 299	75.99 153	82.49 302	86.57 334	58.01 353	90.02 256	62.74 344	92.73 256	89.10 317

DCV-MVSNet		78.71 285	78.51 288	79.32 302	84.32 335	58.84 355	78.38 327	85.33 299	75.99 153	82.49 302	86.57 334	58.01 353	90.02 256	62.74 344	92.73 256	89.10 317

diffmvs		80.40 261	80.48 259	80.17 289	79.02 411	60.04 336	77.54 342	90.28 197	66.65 305	82.40 304	87.33 323	73.50 239	87.35 312	77.98 163	89.62 334	93.13 169
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
viewmambaseed2359dif		78.80 282	78.47 290	79.78 293	80.26 397	59.28 346	77.31 348	87.13 265	60.42 373	82.37 305	88.67 292	74.58 221	87.87 303	67.78 303	87.73 365	92.19 227

test222					93.31 80	76.54 116	79.38 311	77.79 365	52.59 422	82.36 306	90.84 233	66.83 295			91.69 286	81.25 427

D2MVS		76.84 307	75.67 319	80.34 285	80.48 395	62.16 306	73.50 394	84.80 314	57.61 393	82.24 307	87.54 316	51.31 388	87.65 306	70.40 272	93.19 242	91.23 257

VNet		79.31 276	80.27 261	76.44 346	87.92 233	53.95 396	75.58 375	84.35 319	74.39 182	82.23 308	90.72 236	72.84 252	84.39 364	60.38 364	93.98 212	90.97 266

Vis-MVSNet (Re-imp)		77.82 295	77.79 296	77.92 325	88.82 209	51.29 417	83.28 225	71.97 413	74.04 184	82.23 308	89.78 269	57.38 359	89.41 271	57.22 380	95.41 157	93.05 175

API-MVS		82.28 217	82.61 213	81.30 263	86.29 289	69.79 202	88.71 100	87.67 254	78.42 125	82.15 310	84.15 374	77.98 167	91.59 192	65.39 322	92.75 254	82.51 413

icg_test_0407_2		78.46 288	79.68 272	74.78 364	85.76 305	62.46 294	68.51 429	87.91 249	65.23 325	82.12 311	87.92 305	77.27 181	72.67 423	71.67 253	90.74 313	89.20 311

IMVS_0407		81.08 246	81.23 245	80.62 280	85.76 305	62.46 294	82.46 252	87.91 249	65.23 325	82.12 311	87.92 305	77.27 181	90.18 245	71.67 253	90.74 313	89.20 311

IMVS_0403		80.93 250	81.00 248	80.72 277	85.76 305	62.46 294	81.82 268	87.91 249	65.23 325	82.07 313	87.92 305	75.91 203	90.50 234	71.67 253	90.74 313	89.20 311

DP-MVS Recon		84.05 171	83.22 194	86.52 116	91.73 131	75.27 132	83.23 229	92.40 116	72.04 228	82.04 314	88.33 296	77.91 169	93.95 114	66.17 313	95.12 170	90.34 289

MSDG		80.06 272	79.99 271	80.25 287	83.91 344	68.04 231	77.51 343	89.19 222	77.65 135	81.94 315	83.45 380	76.37 201	86.31 332	63.31 342	86.59 381	86.41 357

test2506		74.12 339	73.39 340	76.28 349	91.85 126	44.20 447	84.06 198	48.20 472	72.30 224	81.90 316	94.20 89	27.22 471	89.77 262	64.81 328	96.02 130	94.87 78

Fast-Effi-MVS+		81.04 248	80.57 255	82.46 238	87.50 248	63.22 282	78.37 329	89.63 215	68.01 282	81.87 317	82.08 396	82.31 109	92.65 165	67.10 304	88.30 357	91.51 254

testgi		72.36 355	74.61 327	65.59 427	80.56 394	42.82 452	68.29 430	73.35 401	66.87 303	81.84 318	89.93 266	72.08 262	66.92 450	46.05 444	92.54 260	87.01 351

tfpn200view9		74.86 332	74.23 332	76.74 343	86.24 290	52.12 409	79.24 314	73.87 395	73.34 198	81.82 319	84.60 369	46.02 409	88.80 278	51.98 415	90.99 300	89.31 308

thres400		75.14 326	74.23 332	77.86 327	86.24 290	52.12 409	79.24 314	73.87 395	73.34 198	81.82 319	84.60 369	46.02 409	88.80 278	51.98 415	90.99 300	92.66 195

CL-MVSNet_self_test		76.81 308	77.38 300	75.12 360	86.90 272	51.34 415	73.20 397	80.63 353	68.30 278	81.80 321	88.40 295	66.92 294	80.90 387	55.35 394	94.90 179	93.12 172

OpenMVS	76.72 13	81.98 230	82.00 222	81.93 246	84.42 333	68.22 227	88.50 106	89.48 218	66.92 302	81.80 321	91.86 184	72.59 255	90.16 246	71.19 260	91.25 295	87.40 346

MGCNet		85.37 130	84.58 161	87.75 95	85.28 316	73.36 143	86.54 142	85.71 292	77.56 138	81.78 323	92.47 164	70.29 276	96.02 11	85.59 65	95.96 133	93.87 127

AdaColmap		83.66 185	83.69 184	83.57 203	90.05 179	72.26 168	86.29 145	90.00 204	78.19 128	81.65 324	87.16 326	83.40 94	94.24 98	61.69 355	94.76 188	84.21 386

SPE-MVS-test		87.00 97	86.43 114	88.71 76	89.46 190	77.46 105	89.42 88	95.73 7	77.87 133	81.64 325	87.25 324	82.43 105	94.53 90	77.65 166	96.46 110	94.14 115

DELS-MVS		81.44 240	81.25 243	82.03 244	84.27 337	62.87 286	76.47 363	92.49 115	70.97 241	81.64 325	83.83 375	75.03 210	92.70 163	74.29 209	92.22 272	90.51 285
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		83.10 203	82.54 215	84.77 161	92.90 90	69.10 217	86.65 138	90.62 179	54.66 411	81.46 327	90.81 234	76.98 188	94.38 93	72.62 247	96.18 122	90.82 272

TR-MVS		76.77 309	75.79 316	79.72 296	86.10 297	65.79 256	77.14 349	83.02 330	65.20 329	81.40 328	82.10 394	66.30 296	90.73 226	55.57 391	85.27 394	82.65 407

TAMVS		78.08 293	76.36 311	83.23 212	90.62 165	72.87 153	79.08 317	80.01 356	61.72 355	81.35 329	86.92 331	63.96 317	88.78 281	50.61 420	93.01 246	88.04 335

Effi-MVS+		83.90 180	84.01 178	83.57 203	87.22 256	65.61 258	86.55 141	92.40 116	78.64 122	81.34 330	84.18 373	83.65 91	92.93 158	74.22 212	87.87 362	92.17 229

testing3		71.53 364	70.79 366	73.77 371	88.89 208	41.86 454	76.60 361	59.12 461	72.83 212	80.97 331	82.08 396	19.80 477	87.33 313	65.12 325	91.68 287	92.13 231

new-patchmatchnet		70.10 377	73.37 341	60.29 444	81.23 383	16.95 479	59.54 456	74.62 388	62.93 341	80.97 331	87.93 304	62.83 327	71.90 426	55.24 395	95.01 176	92.00 236

PVSNet_Blended_VisFu		81.55 238	80.49 258	84.70 165	91.58 136	73.24 148	84.21 194	91.67 143	62.86 342	80.94 333	87.16 326	67.27 292	92.87 161	69.82 278	88.94 345	87.99 336

BH-w/o		76.57 312	76.07 315	78.10 321	86.88 273	65.92 255	77.63 340	86.33 278	65.69 316	80.89 334	79.95 415	68.97 285	90.74 225	53.01 410	85.25 395	77.62 443

PAPM_NR		83.23 199	83.19 196	83.33 209	90.90 159	65.98 254	88.19 108	90.78 174	78.13 129	80.87 335	87.92 305	73.49 241	92.42 169	70.07 275	88.40 351	91.60 250

ab-mvs		79.67 275	80.56 256	76.99 337	88.48 220	56.93 372	84.70 182	86.06 284	68.95 268	80.78 336	93.08 137	75.30 208	84.62 359	56.78 381	90.90 305	89.43 306

XXY-MVS		74.44 338	76.19 313	69.21 405	84.61 329	52.43 408	71.70 407	77.18 372	60.73 370	80.60 337	90.96 225	75.44 205	69.35 436	56.13 386	88.33 353	85.86 364

HQP4-MVS										80.56 338			94.61 85			93.56 151

HQP-NCC					91.19 150		84.77 176		73.30 200	80.55 339

ACMP_Plane					91.19 150		84.77 176		73.30 200	80.55 339

HQP-MVS		84.61 152	84.06 177	86.27 121	91.19 150	70.66 191	84.77 176	92.68 108	73.30 200	80.55 339	90.17 262	72.10 260	94.61 85	77.30 173	94.47 195	93.56 151

test_cas_vis1_n_1920		69.20 390	69.12 383	69.43 404	73.68 448	62.82 287	70.38 420	77.21 371	46.18 448	80.46 342	78.95 424	52.03 384	65.53 455	65.77 320	77.45 450	79.95 438

AUN-MVS		81.18 245	78.78 283	88.39 83	90.93 158	82.14 62	82.51 251	83.67 324	64.69 332	80.29 343	85.91 347	51.07 389	92.38 171	76.29 188	93.63 226	90.65 280

HyFIR lowres test		75.12 328	72.66 350	82.50 236	91.44 144	65.19 261	72.47 402	87.31 258	46.79 444	80.29 343	84.30 371	52.70 382	92.10 181	51.88 419	86.73 379	90.22 290

test20.03		73.75 344	74.59 329	71.22 391	81.11 384	51.12 419	70.15 421	72.10 412	70.42 246	80.28 345	91.50 199	64.21 312	74.72 419	46.96 440	94.58 192	87.82 342

mvsany_test3		65.48 412	62.97 421	73.03 377	69.99 463	76.17 124	64.83 443	43.71 474	43.68 456	80.25 346	87.05 330	52.83 381	63.09 461	51.92 418	72.44 456	79.84 439

F-COLMAP		84.97 145	83.42 190	89.63 58	92.39 105	83.40 52	88.83 97	91.92 134	73.19 204	80.18 347	89.15 283	77.04 187	93.28 145	65.82 319	92.28 269	92.21 226

GA-MVS		75.83 321	74.61 327	79.48 301	81.87 373	59.25 347	73.42 395	82.88 331	68.68 272	79.75 348	81.80 399	50.62 392	89.46 267	66.85 306	85.64 391	89.72 301

xiu_mvs_v1_base_debu		80.84 251	80.14 266	82.93 224	88.31 223	71.73 176	79.53 304	87.17 262	65.43 319	79.59 349	82.73 390	76.94 189	90.14 249	73.22 239	88.33 353	86.90 353

xiu_mvs_v1_base		80.84 251	80.14 266	82.93 224	88.31 223	71.73 176	79.53 304	87.17 262	65.43 319	79.59 349	82.73 390	76.94 189	90.14 249	73.22 239	88.33 353	86.90 353

xiu_mvs_v1_base_debi		80.84 251	80.14 266	82.93 224	88.31 223	71.73 176	79.53 304	87.17 262	65.43 319	79.59 349	82.73 390	76.94 189	90.14 249	73.22 239	88.33 353	86.90 353

test_fmvs1_n		70.94 369	70.41 373	72.53 383	73.92 445	66.93 243	75.99 370	84.21 322	43.31 458	79.40 352	79.39 420	43.47 431	68.55 441	69.05 288	84.91 403	82.10 417

patch_mono-2		78.89 279	79.39 275	77.41 333	84.78 325	68.11 229	75.60 373	83.11 329	60.96 367	79.36 353	89.89 268	75.18 209	72.97 422	73.32 238	92.30 266	91.15 260

UnsupCasMVSNet_eth		71.63 363	72.30 355	69.62 402	76.47 429	52.70 406	70.03 422	80.97 350	59.18 380	79.36 353	88.21 298	60.50 334	69.12 437	58.33 375	77.62 448	87.04 350

ppachtmachnet_test		74.73 335	74.00 334	76.90 340	80.71 391	56.89 374	71.53 410	78.42 362	58.24 386	79.32 355	82.92 387	57.91 356	84.26 366	65.60 321	91.36 293	89.56 303

MG-MVS		80.32 264	80.94 250	78.47 314	88.18 226	52.62 407	82.29 259	85.01 308	72.01 229	79.24 356	92.54 162	69.36 281	93.36 144	70.65 267	89.19 341	89.45 304

Fast-Effi-MVS+-dtu		82.54 212	81.41 238	85.90 132	85.60 309	76.53 118	83.07 233	89.62 216	73.02 207	79.11 357	83.51 378	80.74 140	90.24 242	68.76 292	89.29 338	90.94 267

SSC-MVS3.2		73.90 342	75.67 319	68.61 413	84.11 340	41.28 455	64.17 447	72.83 405	72.09 227	79.08 358	87.94 302	70.31 275	73.89 421	55.99 387	94.49 194	90.67 279

CDS-MVSNet		77.32 301	75.40 321	83.06 216	89.00 203	72.48 164	77.90 336	82.17 339	60.81 368	78.94 359	83.49 379	59.30 345	88.76 282	54.64 400	92.37 264	87.93 339
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
baseline1		73.26 347	73.54 338	72.43 384	84.92 323	47.79 432	79.89 300	74.00 393	65.93 309	78.81 360	86.28 341	56.36 365	81.63 384	56.63 382	79.04 443	87.87 341

ttmdpeth		71.72 361	70.67 367	74.86 362	73.08 454	55.88 379	77.41 347	69.27 428	55.86 403	78.66 361	93.77 116	38.01 445	75.39 416	60.12 365	89.87 331	93.31 160

EIA-MVS		82.19 221	81.23 245	85.10 151	87.95 232	69.17 216	83.22 230	93.33 75	70.42 246	78.58 362	79.77 418	77.29 180	94.20 100	71.51 257	88.96 344	91.93 239

thres200		72.34 356	71.55 362	74.70 366	83.48 351	51.60 414	75.02 380	73.71 398	70.14 252	78.56 363	80.57 409	46.20 407	88.20 295	46.99 439	89.29 338	84.32 382

fmvsm_s_conf0.5_n_7		82.04 227	82.05 221	82.01 245	86.98 269	71.07 187	78.70 323	89.45 219	68.07 281	78.14 364	91.61 196	74.19 225	85.92 341	79.61 138	91.73 285	89.05 320

our_test_3		71.85 359	71.59 359	72.62 381	80.71 391	53.78 397	69.72 424	71.71 417	58.80 383	78.03 365	80.51 411	56.61 364	78.84 402	62.20 349	86.04 389	85.23 370

KD-MVS_2432*1600		66.87 401	65.81 408	70.04 396	67.50 466	47.49 433	62.56 450	79.16 358	61.21 365	77.98 366	80.61 407	25.29 473	82.48 377	53.02 408	84.92 401	80.16 436

miper_refine_blended		66.87 401	65.81 408	70.04 396	67.50 466	47.49 433	62.56 450	79.16 358	61.21 365	77.98 366	80.61 407	25.29 473	82.48 377	53.02 408	84.92 401	80.16 436

jason		77.42 300	75.75 317	82.43 239	87.10 261	69.27 211	77.99 333	81.94 341	51.47 431	77.84 368	85.07 363	60.32 337	89.00 275	70.74 266	89.27 340	89.03 321
jason: jason.
MAR-MVS		80.24 267	78.74 285	84.73 163	86.87 274	78.18 95	85.75 156	87.81 253	65.67 317	77.84 368	78.50 428	73.79 235	90.53 233	61.59 357	90.87 307	85.49 369
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		72.29 357	72.00 356	73.14 375	88.63 216	85.00 40	74.65 384	67.39 435	71.94 230	77.80 370	87.66 314	50.48 393	75.83 413	49.95 423	79.51 437	58.58 466

test_fmvs1		69.57 385	69.05 385	71.14 393	69.15 465	65.77 257	73.98 389	83.32 326	42.83 460	77.77 371	78.27 430	43.39 434	68.50 442	68.39 298	84.38 410	79.15 440

pmmvs4		74.92 331	72.98 346	80.73 276	84.95 322	71.71 179	76.23 366	77.59 367	52.83 421	77.73 372	86.38 336	56.35 366	84.97 356	57.72 379	87.05 374	85.51 368

ET-MVSNet_ETH3D		75.28 325	72.77 348	82.81 228	83.03 367	68.11 229	77.09 350	76.51 378	60.67 371	77.60 373	80.52 410	38.04 444	91.15 207	70.78 264	90.68 317	89.17 315

testing3-2		70.72 372	70.97 365	69.95 398	88.93 206	34.80 468	69.85 423	66.59 442	78.42 125	77.58 374	85.55 349	31.83 458	82.08 380	46.28 441	93.73 222	92.98 182

UnsupCasMVSNet_bld		69.21 389	69.68 380	67.82 416	79.42 405	51.15 418	67.82 434	75.79 381	54.15 413	77.47 375	85.36 358	59.26 346	70.64 431	48.46 433	79.35 439	81.66 421

WBMVS		68.76 392	68.43 392	69.75 401	83.29 359	40.30 458	67.36 436	72.21 411	57.09 398	77.05 376	85.53 351	33.68 453	80.51 391	48.79 431	90.90 305	88.45 328

Anonymous20231206		71.38 366	71.88 357	69.88 399	86.31 287	54.37 392	70.39 419	74.62 388	52.57 423	76.73 377	88.76 288	59.94 340	72.06 425	44.35 448	93.23 240	83.23 402

CMPMVS	59.41 20	75.12 328	73.57 337	79.77 294	75.84 435	67.22 235	81.21 281	82.18 338	50.78 436	76.50 378	87.66 314	55.20 373	82.99 375	62.17 351	90.64 322	89.09 319
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		72.10 358	71.69 358	73.32 373	81.57 378	53.02 403	76.77 355	78.37 363	63.31 337	76.37 379	91.85 185	36.68 448	78.98 400	47.87 436	92.45 262	87.95 337

CVMVSNet		72.62 353	71.41 363	76.28 349	83.25 361	60.34 332	83.50 219	79.02 361	37.77 469	76.33 380	85.10 360	49.60 397	87.41 311	70.54 270	77.54 449	81.08 430

PLC	73.85 16	82.09 225	80.31 260	87.45 100	90.86 161	80.29 75	85.88 152	90.65 177	68.17 280	76.32 381	86.33 338	73.12 248	92.61 166	61.40 358	90.02 329	89.44 305
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MVSFormer		82.23 218	81.57 234	84.19 183	85.54 311	69.26 212	91.98 38	90.08 202	71.54 232	76.23 382	85.07 363	58.69 350	94.27 95	86.26 51	88.77 346	89.03 321

lupinMVS		76.37 316	74.46 330	82.09 243	85.54 311	69.26 212	76.79 354	80.77 352	50.68 438	76.23 382	82.82 388	58.69 350	88.94 276	69.85 277	88.77 346	88.07 332

UWE-MVS		66.43 405	65.56 411	69.05 406	84.15 339	40.98 456	73.06 399	64.71 448	54.84 409	76.18 384	79.62 419	29.21 464	80.50 392	38.54 460	89.75 332	85.66 366

PatchMatch-RL		74.48 336	73.22 343	78.27 319	87.70 240	85.26 38	75.92 371	70.09 423	64.34 334	76.09 385	81.25 404	65.87 302	78.07 405	53.86 402	83.82 413	71.48 452

thisisatest0515		73.00 351	70.52 370	80.46 283	81.45 379	59.90 340	73.16 398	74.31 392	57.86 390	76.08 386	77.78 432	37.60 447	92.12 180	65.00 326	91.45 292	89.35 307

MS-PatchMatch		70.93 370	70.22 374	73.06 376	81.85 374	62.50 293	73.82 392	77.90 364	52.44 424	75.92 387	81.27 403	55.67 370	81.75 382	55.37 393	77.70 447	74.94 448

CHOSEN 1792x2688		72.45 354	70.56 369	78.13 320	90.02 181	63.08 283	68.72 428	83.16 328	42.99 459	75.92 387	85.46 353	57.22 361	85.18 355	49.87 425	81.67 427	86.14 360

CR-MVSNet		74.00 341	73.04 345	76.85 342	79.58 402	62.64 290	82.58 247	76.90 374	50.50 439	75.72 389	92.38 166	48.07 401	84.07 368	68.72 294	82.91 420	83.85 391

RPMNet		78.88 280	78.28 292	80.68 279	79.58 402	62.64 290	82.58 247	94.16 33	74.80 171	75.72 389	92.59 158	48.69 398	95.56 44	73.48 233	82.91 420	83.85 391

DPM-MVS		80.10 271	79.18 278	82.88 227	90.71 164	69.74 204	78.87 321	90.84 172	60.29 375	75.64 391	85.92 346	67.28 291	93.11 151	71.24 259	91.79 282	85.77 365

test_vis1_n		70.29 374	69.99 378	71.20 392	75.97 434	66.50 247	76.69 357	80.81 351	44.22 454	75.43 392	77.23 439	50.00 395	68.59 440	66.71 309	82.85 422	78.52 442

PVSNet_BlendedMVS		78.80 282	77.84 295	81.65 256	84.43 331	63.41 278	79.49 307	90.44 185	61.70 356	75.43 392	87.07 329	69.11 283	91.44 197	60.68 362	92.24 270	90.11 295

PVSNet_Blended		76.49 314	75.40 321	79.76 295	84.43 331	63.41 278	75.14 379	90.44 185	57.36 395	75.43 392	78.30 429	69.11 283	91.44 197	60.68 362	87.70 367	84.42 381

PAPR		78.84 281	78.10 294	81.07 268	85.17 320	60.22 334	82.21 263	90.57 181	62.51 344	75.32 395	84.61 368	74.99 211	92.30 175	59.48 369	88.04 359	90.68 277

N_pmnet		70.20 375	68.80 390	74.38 367	80.91 386	84.81 43	59.12 458	76.45 379	55.06 407	75.31 396	82.36 393	55.74 369	54.82 467	47.02 438	87.24 370	83.52 395

cascas		76.29 317	74.81 326	80.72 277	84.47 330	62.94 284	73.89 391	87.34 257	55.94 402	75.16 397	76.53 445	63.97 316	91.16 206	65.00 326	90.97 303	88.06 334

SD_0403		76.08 318	76.77 307	73.98 368	87.08 265	49.45 426	83.62 215	84.68 316	63.31 337	75.13 398	87.47 319	71.85 265	84.56 360	49.97 422	87.86 363	87.94 338

SCA		73.32 346	72.57 352	75.58 358	81.62 377	55.86 380	78.89 320	71.37 418	61.73 354	74.93 399	83.42 381	60.46 335	87.01 315	58.11 377	82.63 425	83.88 388

test_vis1_n_1920		71.30 367	71.58 361	70.47 394	77.58 418	59.99 339	74.25 385	84.22 321	51.06 433	74.85 400	79.10 422	55.10 374	68.83 439	68.86 291	79.20 442	82.58 409

xiu_mvs_v2_base		77.19 303	76.75 308	78.52 312	87.01 267	61.30 314	75.55 376	87.12 269	61.24 364	74.45 401	78.79 426	77.20 183	90.93 215	64.62 332	84.80 407	83.32 400

CANet		83.79 183	82.85 208	86.63 113	86.17 293	72.21 170	83.76 210	91.43 150	77.24 143	74.39 402	87.45 320	75.36 207	95.42 55	77.03 176	92.83 252	92.25 225

PS-MVSNAJ		77.04 305	76.53 310	78.56 311	87.09 263	61.40 312	75.26 378	87.13 265	61.25 363	74.38 403	77.22 440	76.94 189	90.94 214	64.63 331	84.83 406	83.35 399

MVP-Stereo		75.81 322	73.51 339	82.71 229	89.35 192	73.62 141	80.06 296	85.20 301	60.30 374	73.96 404	87.94 302	57.89 357	89.45 268	52.02 414	74.87 454	85.06 373
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
WB-MVSnew		68.72 393	69.01 386	67.85 415	83.22 363	43.98 448	74.93 381	65.98 443	55.09 406	73.83 405	79.11 421	65.63 304	71.89 427	38.21 461	85.04 399	87.69 343

UGNet		82.78 207	81.64 229	86.21 125	86.20 292	76.24 123	86.86 131	85.68 293	77.07 144	73.76 406	92.82 151	69.64 279	91.82 189	69.04 289	93.69 224	90.56 283
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		74.82 333	73.74 335	78.04 323	89.57 186	60.04 336	76.49 362	87.09 270	54.31 412	73.66 407	79.80 416	60.25 338	86.76 324	58.37 373	84.15 411	87.32 347

Test_1112_low_res		73.90 342	73.08 344	76.35 347	90.35 170	55.95 377	73.40 396	86.17 281	50.70 437	73.14 408	85.94 345	58.31 352	85.90 344	56.51 383	83.22 417	87.20 349

1314		73.22 348	72.56 353	75.20 359	80.41 396	57.84 365	81.64 272	85.36 297	51.68 430	73.10 409	76.65 444	61.45 330	85.19 354	63.54 339	79.21 441	82.59 408

test_vis1_rt		65.64 411	64.09 415	70.31 395	66.09 470	70.20 198	61.16 453	81.60 345	38.65 466	72.87 410	69.66 459	52.84 380	60.04 463	56.16 385	77.77 446	80.68 434

Patchmatch-test		65.91 408	67.38 397	61.48 441	75.51 437	43.21 451	68.84 427	63.79 450	62.48 345	72.80 411	83.42 381	44.89 427	59.52 464	48.27 435	86.45 382	81.70 420

PatchmatchNet		69.71 384	68.83 389	72.33 386	77.66 417	53.60 398	79.29 312	69.99 424	57.66 392	72.53 412	82.93 386	46.45 406	80.08 395	60.91 361	72.09 457	83.31 401
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpm		67.95 395	68.08 396	67.55 417	78.74 413	43.53 450	75.60 373	67.10 440	54.92 408	72.23 413	88.10 299	42.87 436	75.97 412	52.21 413	80.95 435	83.15 403

IMVS_0404		77.24 302	77.75 297	75.73 355	85.76 305	62.46 294	70.84 415	87.91 249	65.23 325	72.21 414	87.92 305	67.48 290	75.53 415	71.67 253	90.74 313	89.20 311

pmmvs5		70.73 371	70.07 375	72.72 379	77.03 423	52.73 405	74.14 386	75.65 384	50.36 440	72.17 415	85.37 357	55.42 372	80.67 389	52.86 411	87.59 368	84.77 375

PatchT		70.52 373	72.76 349	63.79 435	79.38 406	33.53 469	77.63 340	65.37 446	73.61 191	71.77 416	92.79 154	44.38 429	75.65 414	64.53 333	85.37 393	82.18 416

MVS		73.21 349	72.59 351	75.06 361	80.97 385	60.81 327	81.64 272	85.92 290	46.03 449	71.68 417	77.54 435	68.47 286	89.77 262	55.70 390	85.39 392	74.60 449

MIMVSNet		71.09 368	71.59 359	69.57 403	87.23 255	50.07 424	78.91 319	71.83 414	60.20 377	71.26 418	91.76 192	55.08 375	76.09 411	41.06 453	87.02 376	82.54 411

WTY-MVS		67.91 396	68.35 393	66.58 423	80.82 389	48.12 430	65.96 442	72.60 406	53.67 415	71.20 419	81.68 401	58.97 348	69.06 438	48.57 432	81.67 427	82.55 410

test0.0.03 1		64.66 415	64.36 414	65.57 428	75.03 442	46.89 436	64.69 445	61.58 458	62.43 349	71.18 420	77.54 435	43.41 432	68.47 443	40.75 455	82.65 423	81.35 424

CostFormer		69.98 381	68.68 391	73.87 369	77.14 421	50.72 421	79.26 313	74.51 390	51.94 429	70.97 421	84.75 366	45.16 424	87.49 309	55.16 396	79.23 440	83.40 398

Syy-MVS		69.40 387	70.03 377	67.49 418	81.72 375	38.94 460	71.00 412	61.99 452	61.38 360	70.81 422	72.36 456	61.37 331	79.30 398	64.50 334	85.18 396	84.22 384

myMVS_eth3d		64.66 415	63.89 416	66.97 421	81.72 375	37.39 463	71.00 412	61.99 452	61.38 360	70.81 422	72.36 456	20.96 476	79.30 398	49.59 426	85.18 396	84.22 384

testing91		69.94 382	68.99 387	72.80 378	83.81 346	45.89 440	71.57 409	73.64 400	68.24 279	70.77 424	77.82 431	34.37 451	84.44 363	53.64 404	87.00 377	88.07 332

testing99		69.27 388	68.15 395	72.63 380	83.29 359	45.45 442	71.15 411	71.08 419	67.34 296	70.43 425	77.77 433	32.24 457	84.35 365	53.72 403	86.33 385	88.10 331

tpmvs		70.16 376	69.56 381	71.96 387	74.71 444	48.13 429	79.63 302	75.45 386	65.02 330	70.26 426	81.88 398	45.34 421	85.68 350	58.34 374	75.39 453	82.08 418

sss		66.92 400	67.26 398	65.90 425	77.23 420	51.10 420	64.79 444	71.72 416	52.12 428	70.13 427	80.18 413	57.96 355	65.36 456	50.21 421	81.01 433	81.25 427

tpm2		68.45 394	66.83 401	73.30 374	78.93 412	48.50 428	79.76 301	71.76 415	47.50 443	69.92 428	83.60 377	42.07 437	88.40 291	48.44 434	79.51 437	83.01 405

myMVS_eth3d28		65.83 410	65.85 406	65.78 426	83.42 354	35.71 466	67.29 437	68.01 433	67.58 293	69.80 429	77.72 434	32.29 456	74.30 420	37.49 462	89.06 342	87.32 347

testing222		66.93 399	65.30 412	71.81 388	83.38 355	45.83 441	72.06 405	67.50 434	64.12 335	69.68 430	76.37 446	27.34 470	83.00 374	38.88 457	88.38 352	86.62 356

HY-MVS	64.64 18	73.03 350	72.47 354	74.71 365	83.36 357	54.19 394	82.14 266	81.96 340	56.76 401	69.57 431	86.21 342	60.03 339	84.83 358	49.58 427	82.65 423	85.11 372

dmvs_re		66.81 403	66.98 399	66.28 424	76.87 424	58.68 359	71.66 408	72.24 409	60.29 375	69.52 432	73.53 453	52.38 383	64.40 458	44.90 446	81.44 430	75.76 446

ETVMVS		64.67 414	63.34 420	68.64 410	83.44 353	41.89 453	69.56 426	61.70 457	61.33 362	68.74 433	75.76 448	28.76 465	79.35 397	34.65 465	86.16 388	84.67 377

tpm cat1		66.76 404	65.21 413	71.42 390	77.09 422	50.62 422	78.01 332	73.68 399	44.89 452	68.64 434	79.00 423	45.51 418	82.42 379	49.91 424	70.15 460	81.23 429

IB-MVS	62.13 19	71.64 362	68.97 388	79.66 298	80.80 390	62.26 303	73.94 390	76.90 374	63.27 339	68.63 435	76.79 442	33.83 452	91.84 188	59.28 370	87.26 369	84.88 374
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		80.37 262	78.41 291	86.23 122	76.75 425	73.28 146	87.18 125	77.45 368	76.24 149	68.14 436	88.93 287	65.41 305	93.85 117	69.47 281	96.12 126	91.55 252
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet	58.17 21	66.41 406	65.63 410	68.75 409	81.96 372	49.88 425	62.19 452	72.51 408	51.03 434	68.04 437	75.34 450	50.84 390	74.77 417	45.82 445	82.96 418	81.60 422

tpmrst		66.28 407	66.69 403	65.05 431	72.82 456	39.33 459	78.20 330	70.69 422	53.16 419	67.88 438	80.36 412	48.18 400	74.75 418	58.13 376	70.79 459	81.08 430

CANet_DTU		77.81 296	77.05 303	80.09 291	81.37 381	59.90 340	83.26 226	88.29 240	69.16 263	67.83 439	83.72 376	60.93 332	89.47 266	69.22 285	89.70 333	90.88 270

EPMVS		62.47 419	62.63 423	62.01 437	70.63 462	38.74 461	74.76 382	52.86 468	53.91 414	67.71 440	80.01 414	39.40 441	66.60 451	55.54 392	68.81 465	80.68 434

UBG		64.34 417	63.35 419	67.30 419	83.50 350	40.53 457	67.46 435	65.02 447	54.77 410	67.54 441	74.47 452	32.99 455	78.50 404	40.82 454	83.58 414	82.88 406

MDTV_nov1_ep13			68.29 394		78.03 414	43.87 449	74.12 387	72.22 410	52.17 425	67.02 442	85.54 350	45.36 420	80.85 388	55.73 388	84.42 409

testing11		67.38 397	65.93 405	71.73 389	83.37 356	46.60 437	70.95 414	69.40 427	62.47 346	66.14 443	76.66 443	31.22 459	84.10 367	49.10 429	84.10 412	84.49 378

pmmvs3		62.47 419	60.02 432	69.80 400	71.58 460	64.00 273	70.52 418	58.44 464	39.77 464	66.05 444	75.84 447	27.10 472	72.28 424	46.15 443	84.77 408	73.11 450

ADS-MVSNet2		65.87 409	63.64 418	72.55 382	73.16 452	56.92 373	67.10 438	74.81 387	49.74 441	66.04 445	82.97 384	46.71 404	77.26 408	42.29 450	69.96 461	83.46 396

ADS-MVSNet		61.90 421	62.19 425	61.03 442	73.16 452	36.42 465	67.10 438	61.75 455	49.74 441	66.04 445	82.97 384	46.71 404	63.21 459	42.29 450	69.96 461	83.46 396

mvsany_test1		58.48 431	56.47 437	64.50 432	65.90 472	68.21 228	56.95 463	42.11 475	38.30 467	65.69 447	77.19 441	56.96 362	59.35 465	46.16 442	58.96 468	65.93 459

dmvs_testset		60.59 429	62.54 424	54.72 450	77.26 419	27.74 473	74.05 388	61.00 459	60.48 372	65.62 448	67.03 463	55.93 368	68.23 445	32.07 469	69.46 464	68.17 457

DSMNet-mixed		60.98 427	61.61 427	59.09 447	72.88 455	45.05 445	74.70 383	46.61 473	26.20 471	65.34 449	90.32 255	55.46 371	63.12 460	41.72 452	81.30 432	69.09 456

JIA-IIPM		69.41 386	66.64 404	77.70 329	73.19 451	71.24 185	75.67 372	65.56 445	70.42 246	65.18 450	92.97 145	33.64 454	83.06 373	53.52 406	69.61 463	78.79 441

test-LLR		67.21 398	66.74 402	68.63 411	76.45 430	55.21 386	67.89 431	67.14 438	62.43 349	65.08 451	72.39 454	43.41 432	69.37 434	61.00 359	84.89 404	81.31 425

test-mter		65.00 413	63.79 417	68.63 411	76.45 430	55.21 386	67.89 431	67.14 438	50.98 435	65.08 451	72.39 454	28.27 467	69.37 434	61.00 359	84.89 404	81.31 425

PMMVS2		55.64 435	59.27 433	44.74 452	64.30 474	12.32 480	40.60 468	49.79 470	53.19 418	65.06 453	84.81 365	53.60 379	49.76 470	32.68 468	89.41 337	72.15 451

baseline2		69.77 383	66.89 400	78.41 315	79.51 404	58.09 361	76.23 366	69.57 426	57.50 394	64.82 454	77.45 437	46.02 409	88.44 289	53.08 407	77.83 445	88.70 325

gg-mvs-nofinetune		68.96 391	69.11 384	68.52 414	76.12 433	45.32 443	83.59 216	55.88 466	86.68 33	64.62 455	97.01 12	30.36 462	83.97 370	44.78 447	82.94 419	76.26 445

PAPM		71.77 360	70.06 376	76.92 339	86.39 281	53.97 395	76.62 359	86.62 276	53.44 416	63.97 456	84.73 367	57.79 358	92.34 173	39.65 456	81.33 431	84.45 380

new_pmnet		55.69 434	57.66 435	49.76 451	75.47 438	30.59 471	59.56 455	51.45 469	43.62 457	62.49 457	75.48 449	40.96 439	49.15 471	37.39 463	72.52 455	69.55 455

UWE-MVS-28		58.44 432	57.71 434	60.65 443	73.58 449	31.23 470	69.68 425	48.80 471	53.12 420	61.79 458	78.83 425	30.98 460	68.40 444	21.58 472	80.99 434	82.33 415

MDTV_nov1_ep13_2view						27.60 474	70.76 417		46.47 447	61.27 459		45.20 422		49.18 428		83.75 393

dp		60.70 428	60.29 431	61.92 439	72.04 459	38.67 462	70.83 416	64.08 449	51.28 432	60.75 460	77.28 438	36.59 449	71.58 429	47.41 437	62.34 467	75.52 447

TESTMET0.1,1		61.29 424	60.32 430	64.19 433	72.06 458	51.30 416	67.89 431	62.09 451	45.27 450	60.65 461	69.01 460	27.93 468	64.74 457	56.31 384	81.65 429	76.53 444

PMMVS		61.65 422	60.38 429	65.47 429	65.40 473	69.26 212	63.97 448	61.73 456	36.80 470	60.11 462	68.43 461	59.42 344	66.35 452	48.97 430	78.57 444	60.81 463

PVSNet_0	51.08 22	56.10 433	54.97 438	59.48 446	75.12 441	53.28 402	55.16 464	61.89 454	44.30 453	59.16 463	62.48 466	54.22 376	65.91 454	35.40 464	47.01 469	59.25 465

MVS-HIRNet		61.16 425	62.92 422	55.87 448	79.09 409	35.34 467	71.83 406	57.98 465	46.56 446	59.05 464	91.14 216	49.95 396	76.43 410	38.74 458	71.92 458	55.84 467

E-PMN		61.59 423	61.62 426	61.49 440	66.81 468	55.40 384	53.77 465	60.34 460	66.80 304	58.90 465	65.50 464	40.48 440	66.12 453	55.72 389	86.25 386	62.95 462

GG-mvs-BLEND				67.16 420	73.36 450	46.54 439	84.15 196	55.04 467		58.64 466	61.95 467	29.93 463	83.87 371	38.71 459	76.92 451	71.07 453

EPNet_dtu		72.87 352	71.33 364	77.49 332	77.72 416	60.55 330	82.35 257	75.79 381	66.49 306	58.39 467	81.06 405	53.68 378	85.98 339	53.55 405	92.97 248	85.95 362
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
dongtai		41.90 437	42.65 440	39.67 453	70.86 461	21.11 475	61.01 454	21.42 480	57.36 395	57.97 468	50.06 469	16.40 478	58.73 466	21.03 473	27.69 473	39.17 469

EMVS		61.10 426	60.81 428	61.99 438	65.96 471	55.86 380	53.10 466	58.97 463	67.06 301	56.89 469	63.33 465	40.98 438	67.03 449	54.79 398	86.18 387	63.08 461

CHOSEN 280x420		59.08 430	56.52 436	66.76 422	76.51 428	64.39 269	49.62 467	59.00 462	43.86 455	55.66 470	68.41 462	35.55 450	68.21 446	43.25 449	76.78 452	67.69 458

MVE	40.22 23	51.82 436	50.47 439	55.87 448	62.66 475	51.91 411	31.61 470	39.28 476	40.65 462	50.76 471	74.98 451	56.24 367	44.67 472	33.94 467	64.11 466	71.04 454
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
kuosan		30.83 438	32.17 441	26.83 455	53.36 477	19.02 478	57.90 461	20.44 481	38.29 468	38.01 472	37.82 471	15.18 479	33.45 474	7.74 475	20.76 474	28.03 470

DeepMVS_CX				24.13 456	32.95 478	29.49 472		21.63 479	12.07 472	37.95 473	45.07 470	30.84 461	19.21 475	17.94 474	33.06 472	23.69 471

tmp_tt		20.25 441	24.50 444	7.49 457	4.47 480	8.70 481	34.17 469	25.16 478	1.00 475	32.43 474	18.49 472	39.37 442	9.21 476	21.64 471	43.75 470	4.57 472

test_method		30.46 439	29.60 442	33.06 454	17.99 479	3.84 482	13.62 471	73.92 394	2.79 473	18.29 475	53.41 468	28.53 466	43.25 473	22.56 470	35.27 471	52.11 468

EGC-MVSNET		74.79 334	69.99 378	89.19 67	94.89 38	87.00 15	91.89 41	86.28 279	1.09 474	2.23 476	95.98 30	81.87 125	89.48 265	79.76 134	95.96 133	91.10 261

testmvs		5.91 445	7.65 448	0.72 459	1.20 481	0.37 484	59.14 457	0.67 483	0.49 477	1.11 477	2.76 476	0.94 481	0.24 478	1.02 477	1.47 475	1.55 474

test123		6.27 444	8.08 447	0.84 458	1.11 482	0.57 483	62.90 449	0.82 482	0.54 476	1.07 478	2.75 477	1.26 480	0.30 477	1.04 476	1.26 476	1.66 473

mmdepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet_test		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

cdsmvs_eth3d_5k		20.81 440	27.75 443	0.00 460	0.00 483	0.00 485	0.00 472	85.44 296	0.00 478	0.00 479	82.82 388	81.46 131	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		6.41 443	8.55 446	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	76.94 189	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

ab-mvs-re		6.65 442	8.87 445	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	79.80 416	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		0.00 446	0.00 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.00 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

TestfortrainingZip							92.12 33

WAC-MVS						37.39 463								52.61 412

MSC_two_6792asdad				88.81 73	91.55 138	77.99 97		91.01 168					96.05 9	87.45 29	98.17 37	92.40 211

No_MVS				88.81 73	91.55 138	77.99 97		91.01 168					96.05 9	87.45 29	98.17 37	92.40 211

eth-test2					0.00 483

eth-test					0.00 483

OPU-MVS				88.27 87	91.89 124	77.83 100	90.47 59				91.22 213	81.12 135	94.68 81	74.48 208	95.35 159	92.29 221

save fliter					93.75 67	77.44 106	86.31 144	89.72 211	70.80 243

test_0728_SECOND				86.79 111	94.25 52	72.45 165	90.54 56	94.10 40					95.88 18	86.42 47	97.97 49	92.02 235

GSMVS																83.88 388

sam_mvs1												46.11 408				83.88 388

sam_mvs												45.92 413

MTGPA								91.81 140

test_post1							78.85 322				3.13 474	45.19 423	80.13 394	58.11 377

test_post											3.10 475	45.43 419	77.22 409

patchmatchnet-post											81.71 400	45.93 412	87.01 315

MTMP							90.66 52	33.14 477

gm-plane-assit					75.42 439	44.97 446			52.17 425		72.36 456		87.90 301	54.10 401

test9_res														80.83 123	96.45 111	90.57 282

agg_prior2														79.68 136	96.16 123	90.22 290

test_prior4						78.97 87	84.59 185

test_prior				86.32 119	90.59 166	71.99 173		92.85 102					94.17 105			92.80 187

新几何2							81.72 271

旧先验1					91.97 120	71.77 174		81.78 342			91.84 186	73.92 232			93.65 225	83.61 394

无先验							82.81 242	85.62 294	58.09 388				91.41 200	67.95 302		84.48 379

原ACMM2							82.26 262

testdata2													86.43 330	63.52 340

segment_acmp												81.94 121

testdata1							79.62 303		73.95 186

plane_prior7					93.45 74	77.31 109

plane_prior6					92.61 98	76.54 116						74.84 214

plane_prior5								93.61 64					95.22 62	80.78 124	95.83 144	94.46 95

plane_prior4											92.95 146

plane_prior2							89.45 86		79.44 109

plane_prior1					92.83 95

plane_prior						76.42 119	87.15 126		75.94 156						95.03 173

n2								0.00 484

nn								0.00 484

door-mid								74.45 391

test11								91.46 149

door								72.57 407

HQP5-MVS						70.66 191

BP-MVS														77.30 173

HQP3-MVS								92.68 108							94.47 195

HQP2-MVS												72.10 260

NP-MVS					91.95 121	74.55 136					90.17 262

ACMMP++_ref															95.74 150

ACMMP++															97.35 83

Test By Simon												79.09 156

High-resolution multi-view benchmark