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.

DVP-MVS++		90.23 1	91.01 1	87.89 24	94.34 27	71.25 61	95.06 1	94.23 3	78.38 38	92.78 4	95.74 6	82.45 3	97.49 4	89.42 19	96.68 2	94.95 12

FOURS1					95.00 10	72.39 41	95.06 1	93.84 16	74.49 140	91.30 15

CP-MVS		87.11 35	86.92 40	87.68 34	94.20 34	73.86 7	93.98 3	92.82 64	76.62 82	83.68 107	94.46 32	67.93 112	95.95 58	84.20 73	94.39 57	93.23 113

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 54	93.83 4	93.96 14	75.70 104	91.06 16	96.03 1	76.84 14	97.03 17	89.09 21	95.65 27	94.47 44
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		88.72 11	88.86 11	88.32 9	92.14 74	72.96 25	93.73 5	93.67 21	80.19 12	88.10 38	94.80 23	73.76 34	97.11 15	87.51 42	95.82 21	94.90 15
Skip Steuart: Steuart Systems R&D Blog.
lecture		88.09 14	88.59 13	86.58 58	93.26 52	69.77 92	93.70 6	94.16 5	77.13 65	89.76 22	95.52 14	72.26 49	96.27 44	86.87 46	94.65 48	93.70 88

test0726					95.27 5	71.25 61	93.60 7	94.11 7	77.33 57	92.81 3	95.79 3	80.98 9

SED-MVS		90.08 2	90.85 2	87.77 26	95.30 2	70.98 68	93.57 8	94.06 11	77.24 60	93.10 1	95.72 8	82.99 1	97.44 7	89.07 24	96.63 4	94.88 16

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 8				94.02 56	82.45 3	96.87 20	83.77 77	96.48 8	94.88 16

DVP-MVS		89.60 3	90.35 3	87.33 41	95.27 5	71.25 61	93.49 10	92.73 65	77.33 57	92.12 9	95.78 4	80.98 9	97.40 9	89.08 22	96.41 12	93.33 110
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_SECOND				87.71 32	95.34 1	71.43 60	93.49 10	94.23 3					97.49 4	89.08 22	96.41 12	94.21 57

3Dnovator+	77.84 4	85.48 69	84.47 88	88.51 7	91.08 89	73.49 16	93.18 12	93.78 19	80.79 8	76.66 240	93.37 78	60.40 223	96.75 26	77.20 149	93.73 66	95.29 6

HFP-MVS		87.58 23	87.47 28	87.94 19	94.58 16	73.54 15	93.04 13	93.24 34	76.78 76	84.91 77	94.44 35	70.78 71	96.61 32	84.53 67	94.89 42	93.66 89

ACMMPR		87.44 26	87.23 33	88.08 15	94.64 13	73.59 12	93.04 13	93.20 35	76.78 76	84.66 84	94.52 28	68.81 99	96.65 30	84.53 67	94.90 41	94.00 69

ZNCC-MVS		87.94 19	87.85 21	88.20 12	94.39 24	73.33 19	93.03 15	93.81 18	76.81 74	85.24 72	94.32 40	71.76 56	96.93 19	85.53 56	95.79 22	94.32 53

region2R		87.42 28	87.20 34	88.09 14	94.63 14	73.55 13	93.03 15	93.12 41	76.73 79	84.45 89	94.52 28	69.09 93	96.70 27	84.37 69	94.83 45	94.03 67

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 17	94.11 7	80.27 10	91.35 14	94.16 49	78.35 13	96.77 24	89.59 17	94.22 62	94.67 30
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
CS-MVS		86.69 41	86.95 39	85.90 74	90.76 99	67.57 159	92.83 18	93.30 33	79.67 19	84.57 88	92.27 102	71.47 61	95.02 96	84.24 72	93.46 69	95.13 9

XVS		87.18 34	86.91 41	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 108	94.17 48	67.45 117	96.60 33	83.06 82	94.50 53	94.07 65

X-MVStestdata		80.37 186	77.83 226	88.00 17	94.42 20	73.33 19	92.78 19	92.99 50	79.14 26	83.67 108	12.47 468	67.45 117	96.60 33	83.06 82	94.50 53	94.07 65

mPP-MVS		86.67 43	86.32 49	87.72 30	94.41 22	73.55 13	92.74 21	92.22 89	76.87 73	82.81 123	94.25 45	66.44 129	96.24 45	82.88 87	94.28 60	93.38 106

ACMMP		85.89 61	85.39 72	87.38 40	93.59 45	72.63 33	92.74 21	93.18 40	76.78 76	80.73 158	93.82 67	64.33 153	96.29 42	82.67 94	90.69 111	93.23 113
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
MP-MVS		87.71 20	87.64 23	87.93 21	94.36 26	73.88 6	92.71 23	92.65 71	77.57 49	83.84 104	94.40 37	72.24 50	96.28 43	85.65 54	95.30 35	93.62 96
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MM		89.16 6	89.23 7	88.97 4	90.79 98	73.65 10	92.66 24	91.17 136	86.57 1	87.39 53	94.97 21	71.70 58	97.68 1	92.19 1	95.63 28	95.57 1

SF-MVS		88.46 12	88.74 12	87.64 35	92.78 66	71.95 51	92.40 25	94.74 2	75.71 102	89.16 25	95.10 18	75.65 21	96.19 47	87.07 45	96.01 17	94.79 23

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 25	93.63 22	74.77 134	92.29 7	95.97 2	74.28 30	97.24 13	88.58 32	96.91 1	94.87 18
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
GST-MVS		87.42 28	87.26 31	87.89 24	94.12 36	72.97 24	92.39 27	93.43 29	76.89 72	84.68 81	93.99 60	70.67 73	96.82 22	84.18 74	95.01 37	93.90 75

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 28	92.85 60	80.26 11	87.78 44	94.27 43	75.89 19	96.81 23	87.45 43	96.44 9	93.05 128

SR-MVS		86.73 40	86.67 44	86.91 51	94.11 37	72.11 49	92.37 29	92.56 76	74.50 139	86.84 60	94.65 27	67.31 119	95.77 60	84.80 63	92.85 74	92.84 140

SPE-MVS-test		86.29 51	86.48 47	85.71 76	91.02 91	67.21 175	92.36 30	93.78 19	78.97 33	83.51 111	91.20 140	70.65 74	95.15 87	81.96 97	94.89 42	94.77 25

EC-MVSNet		86.01 54	86.38 48	84.91 107	89.31 143	66.27 189	92.32 31	93.63 22	79.37 23	84.17 97	91.88 113	69.04 97	95.43 73	83.93 76	93.77 65	93.01 131

EPP-MVSNet		83.40 110	83.02 110	84.57 118	90.13 110	64.47 239	92.32 31	90.73 150	74.45 142	79.35 179	91.10 143	69.05 96	95.12 88	72.78 203	87.22 172	94.13 61

PHI-MVS		86.43 46	86.17 55	87.24 42	90.88 95	70.96 70	92.27 33	94.07 10	72.45 191	85.22 73	91.90 112	69.47 87	96.42 40	83.28 81	95.94 19	94.35 50

HPM-MVS		87.11 35	86.98 38	87.50 39	93.88 39	72.16 47	92.19 34	93.33 32	76.07 96	83.81 105	93.95 63	69.77 84	96.01 54	85.15 57	94.66 47	94.32 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MTMP							92.18 35	32.83 473

HPM-MVS_fast		85.35 75	84.95 81	86.57 59	93.69 42	70.58 80	92.15 36	91.62 121	73.89 157	82.67 125	94.09 52	62.60 175	95.54 66	80.93 106	92.93 73	93.57 99

CPTT-MVS		83.73 98	83.33 106	84.92 106	93.28 49	70.86 74	92.09 37	90.38 160	68.75 287	79.57 173	92.83 92	60.60 219	93.04 200	80.92 107	91.56 97	90.86 214

APD-MVS_3200maxsize		85.97 57	85.88 61	86.22 63	92.69 68	69.53 95	91.93 38	92.99 50	73.54 167	85.94 64	94.51 31	65.80 141	95.61 63	83.04 84	92.51 79	93.53 103

SR-MVS-dyc-post		85.77 63	85.61 68	86.23 62	93.06 60	70.63 78	91.88 39	92.27 85	73.53 168	85.69 68	94.45 33	65.00 149	95.56 64	82.75 89	91.87 90	92.50 152

RE-MVS-def			85.48 71		93.06 60	70.63 78	91.88 39	92.27 85	73.53 168	85.69 68	94.45 33	63.87 157		82.75 89	91.87 90	92.50 152

APD-MVS		87.44 26	87.52 27	87.19 43	94.24 32	72.39 41	91.86 41	92.83 61	73.01 185	88.58 30	94.52 28	73.36 35	96.49 38	84.26 70	95.01 37	92.70 142
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		88.06 15	88.50 15	86.71 56	92.60 71	72.71 29	91.81 42	93.19 36	77.87 42	90.32 19	94.00 58	74.83 23	93.78 153	87.63 41	94.27 61	93.65 93
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
NormalMVS		86.29 51	85.88 61	87.52 37	93.26 52	72.47 38	91.65 43	92.19 93	79.31 24	84.39 91	92.18 104	64.64 151	95.53 67	80.70 111	94.65 48	94.56 40

SymmetryMVS		85.38 74	84.81 82	87.07 46	91.47 83	72.47 38	91.65 43	88.06 251	79.31 24	84.39 91	92.18 104	64.64 151	95.53 67	80.70 111	90.91 108	93.21 116

reproduce_model		87.28 32	87.39 30	86.95 50	93.10 58	71.24 65	91.60 45	93.19 36	74.69 135	88.80 29	95.61 11	70.29 77	96.44 39	86.20 52	93.08 71	93.16 120

DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 46	94.10 9	75.90 99	92.29 7	95.66 10	81.67 6	97.38 11	87.44 44	96.34 15	93.95 72
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
QAPM		80.88 162	79.50 185	85.03 99	88.01 202	68.97 110	91.59 46	92.00 101	66.63 317	75.15 284	92.16 106	57.70 242	95.45 71	63.52 291	88.76 147	90.66 223

IS-MVSNet		83.15 116	82.81 114	84.18 140	89.94 119	63.30 271	91.59 46	88.46 244	79.04 30	79.49 174	92.16 106	65.10 146	94.28 125	67.71 258	91.86 92	94.95 12

reproduce-ours		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 125	88.96 26	95.54 12	71.20 66	96.54 36	86.28 50	93.49 67	93.06 126

our_new_method		87.47 24	87.61 24	87.07 46	93.27 50	71.60 55	91.56 49	93.19 36	74.98 125	88.96 26	95.54 12	71.20 66	96.54 36	86.28 50	93.49 67	93.06 126

9.14			88.26 16		92.84 65		91.52 51	94.75 1	73.93 156	88.57 31	94.67 26	75.57 22	95.79 59	86.77 47	95.76 23

MGCNet		87.69 21	87.55 26	88.12 13	89.45 134	71.76 53	91.47 52	89.54 192	82.14 3	86.65 61	94.28 42	68.28 108	97.46 6	90.81 6	95.31 34	95.15 8

TSAR-MVS + MP.		88.02 18	88.11 17	87.72 30	93.68 43	72.13 48	91.41 53	92.35 83	74.62 138	88.90 28	93.85 66	75.75 20	96.00 55	87.80 39	94.63 50	95.04 10
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
DeepC-MVS_fast	79.65 3	86.91 38	86.62 46	87.76 27	93.52 46	72.37 43	91.26 54	93.04 42	76.62 82	84.22 95	93.36 79	71.44 62	96.76 25	80.82 108	95.33 33	94.16 59
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
HQP_MVS		83.64 102	83.14 107	85.14 93	90.08 112	68.71 119	91.25 55	92.44 78	79.12 28	78.92 185	91.00 150	60.42 221	95.38 78	78.71 131	86.32 188	91.33 197

plane_prior2							91.25 55		79.12 28

NCCC		88.06 15	88.01 19	88.24 11	94.41 22	73.62 11	91.22 57	92.83 61	81.50 5	85.79 67	93.47 75	73.02 42	97.00 18	84.90 59	94.94 40	94.10 63

API-MVS		81.99 137	81.23 141	84.26 137	90.94 93	70.18 87	91.10 58	89.32 204	71.51 210	78.66 190	88.28 230	65.26 144	95.10 93	64.74 285	91.23 102	87.51 332

EPNet		83.72 99	82.92 113	86.14 68	84.22 318	69.48 97	91.05 59	85.27 307	81.30 6	76.83 235	91.65 121	66.09 136	95.56 64	76.00 167	93.85 64	93.38 106
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		88.05 17	88.08 18	87.94 19	93.70 41	73.05 22	90.86 60	93.59 24	76.27 92	88.14 37	95.09 19	71.06 68	96.67 29	87.67 40	96.37 14	94.09 64

CSCG		86.41 48	86.19 54	87.07 46	92.91 63	72.48 37	90.81 61	93.56 25	73.95 154	83.16 115	91.07 145	75.94 18	95.19 85	79.94 119	94.38 58	93.55 101

MSLP-MVS++		85.43 71	85.76 65	84.45 123	91.93 77	70.24 81	90.71 62	92.86 59	77.46 55	84.22 95	92.81 94	67.16 121	92.94 202	80.36 114	94.35 59	90.16 244

3Dnovator	76.31 5	83.38 111	82.31 124	86.59 57	87.94 204	72.94 28	90.64 63	92.14 98	77.21 62	75.47 266	92.83 92	58.56 235	94.72 110	73.24 199	92.71 77	92.13 174

OpenMVS	72.83 10	79.77 197	78.33 213	84.09 146	85.17 295	69.91 89	90.57 64	90.97 142	66.70 311	72.17 329	91.91 111	54.70 270	93.96 139	61.81 312	90.95 107	88.41 314

balanced_conf03		86.78 39	86.99 37	86.15 66	91.24 86	67.61 157	90.51 65	92.90 57	77.26 59	87.44 52	91.63 123	71.27 65	96.06 50	85.62 55	95.01 37	94.78 24

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 65	93.00 47	80.90 7	88.06 39	94.06 54	76.43 16	96.84 21	88.48 35	95.99 18	94.34 51

MVSFormer		82.85 123	82.05 131	85.24 90	87.35 227	70.21 82	90.50 67	90.38 160	68.55 290	81.32 144	89.47 193	61.68 193	93.46 171	78.98 128	90.26 118	92.05 176

test_djsdf		80.30 189	79.32 190	83.27 184	83.98 324	65.37 213	90.50 67	90.38 160	68.55 290	76.19 253	88.70 216	56.44 257	93.46 171	78.98 128	80.14 289	90.97 210

save fliter					93.80 40	72.35 44	90.47 69	91.17 136	74.31 145

nrg030		83.88 93	83.53 101	84.96 102	86.77 255	69.28 105	90.46 70	92.67 68	74.79 133	82.95 118	91.33 136	72.70 47	93.09 195	80.79 110	79.28 299	92.50 152

sasdasda		85.91 59	85.87 63	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 41	91.23 137	73.28 37	93.91 147	81.50 100	88.80 145	94.77 25

canonicalmvs		85.91 59	85.87 63	86.04 70	89.84 121	69.44 101	90.45 71	93.00 47	76.70 80	88.01 41	91.23 137	73.28 37	93.91 147	81.50 100	88.80 145	94.77 25

plane_prior						68.71 119	90.38 73		77.62 47						86.16 193

DeepC-MVS	79.81 2	87.08 37	86.88 42	87.69 33	91.16 87	72.32 45	90.31 74	93.94 15	77.12 66	82.82 122	94.23 46	72.13 52	97.09 16	84.83 62	95.37 31	93.65 93
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
Vis-MVSNet		83.46 108	82.80 115	85.43 85	90.25 108	68.74 117	90.30 75	90.13 172	76.33 91	80.87 155	92.89 90	61.00 210	94.20 131	72.45 212	90.97 106	93.35 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PGM-MVS		86.68 42	86.27 51	87.90 22	94.22 33	73.38 18	90.22 76	93.04 42	75.53 107	83.86 103	94.42 36	67.87 114	96.64 31	82.70 93	94.57 52	93.66 89

LPG-MVS_test		82.08 134	81.27 140	84.50 120	89.23 148	68.76 115	90.22 76	91.94 105	75.37 113	76.64 241	91.51 129	54.29 273	94.91 98	78.44 133	83.78 233	89.83 265

Anonymous20231211		78.97 221	77.69 234	82.81 210	90.54 102	64.29 243	90.11 78	91.51 126	65.01 337	76.16 257	88.13 239	50.56 319	93.03 201	69.68 241	77.56 320	91.11 203

ACMM	73.20 8	80.78 172	79.84 174	83.58 173	89.31 143	68.37 130	89.99 79	91.60 123	70.28 247	77.25 224	89.66 186	53.37 284	93.53 166	74.24 188	82.85 254	88.85 298
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	74.13 6	81.51 153	80.57 153	84.36 126	89.42 135	68.69 122	89.97 80	91.50 129	74.46 141	75.04 288	90.41 164	53.82 279	94.54 116	77.56 145	82.91 253	89.86 264
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LFMVS		81.82 141	81.23 141	83.57 174	91.89 78	63.43 269	89.84 81	81.85 360	77.04 69	83.21 113	93.10 83	52.26 293	93.43 173	71.98 215	89.95 125	93.85 77

MCST-MVS		87.37 31	87.25 32	87.73 28	94.53 17	72.46 40	89.82 82	93.82 17	73.07 183	84.86 80	92.89 90	76.22 17	96.33 41	84.89 61	95.13 36	94.40 47

MAR-MVS		81.84 140	80.70 150	85.27 89	91.32 85	71.53 58	89.82 82	90.92 143	69.77 261	78.50 194	86.21 292	62.36 181	94.52 118	65.36 279	92.05 88	89.77 268
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
MP-MVS-pluss		87.67 22	87.72 22	87.54 36	93.64 44	72.04 50	89.80 84	93.50 26	75.17 122	86.34 63	95.29 17	70.86 70	96.00 55	88.78 30	96.04 16	94.58 36
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
UA-Net		85.08 80	84.96 80	85.45 84	92.07 75	68.07 141	89.78 85	90.86 147	82.48 2	84.60 87	93.20 82	69.35 89	95.22 84	71.39 220	90.88 109	93.07 125

alignmvs		85.48 69	85.32 75	85.96 73	89.51 130	69.47 98	89.74 86	92.47 77	76.17 94	87.73 48	91.46 132	70.32 76	93.78 153	81.51 99	88.95 142	94.63 34

VDDNet		81.52 151	80.67 151	84.05 154	90.44 104	64.13 246	89.73 87	85.91 300	71.11 219	83.18 114	93.48 73	50.54 320	93.49 168	73.40 196	88.25 156	94.54 42

CANet		86.45 45	86.10 57	87.51 38	90.09 111	70.94 72	89.70 88	92.59 75	81.78 4	81.32 144	91.43 133	70.34 75	97.23 14	84.26 70	93.36 70	94.37 49

test_fmvsmconf0.1_n		85.61 67	85.65 67	85.50 83	82.99 354	69.39 103	89.65 89	90.29 167	73.31 175	87.77 45	94.15 50	71.72 57	93.23 182	90.31 9	90.67 112	93.89 76

114514_t		80.68 173	79.51 184	84.20 139	94.09 38	67.27 171	89.64 90	91.11 139	58.75 404	74.08 303	90.72 155	58.10 238	95.04 95	69.70 240	89.42 135	90.30 240

MVSMamba_PlusPlus		85.99 55	85.96 60	86.05 69	91.09 88	67.64 156	89.63 91	92.65 71	72.89 188	84.64 85	91.71 118	71.85 54	96.03 51	84.77 64	94.45 56	94.49 43

test_fmvsmconf_n		85.92 58	86.04 59	85.57 82	85.03 302	69.51 96	89.62 92	90.58 153	73.42 171	87.75 46	94.02 56	72.85 45	93.24 181	90.37 8	90.75 110	93.96 70

fmvsm_l_conf0.5_n_3		86.02 53	86.32 49	85.14 93	87.20 237	68.54 126	89.57 93	90.44 158	75.31 115	87.49 50	94.39 38	72.86 44	92.72 211	89.04 26	90.56 113	94.16 59

DeepPCF-MVS	80.84 1	88.10 13	88.56 14	86.73 55	92.24 73	69.03 106	89.57 93	93.39 31	77.53 53	89.79 21	94.12 51	78.98 12	96.58 35	85.66 53	95.72 24	94.58 36

fmvsm_s_conf0.5_n_10		86.38 49	86.76 43	85.24 90	87.33 232	67.30 169	89.50 95	90.98 141	76.25 93	90.56 18	94.75 25	68.38 105	94.24 130	90.80 7	92.32 84	94.19 58

test_fmvsmconf0.01_n		84.73 85	84.52 87	85.34 87	80.25 396	69.03 106	89.47 96	89.65 188	73.24 179	86.98 58	94.27 43	66.62 125	93.23 182	90.26 10	89.95 125	93.78 85

fmvsm_s_conf0.5_n		83.80 95	83.71 97	84.07 148	86.69 258	67.31 168	89.46 97	83.07 343	71.09 220	86.96 59	93.70 70	69.02 98	91.47 270	88.79 29	84.62 219	93.44 105

MGCFI-Net		85.06 81	85.51 70	83.70 169	89.42 135	63.01 277	89.43 98	92.62 74	76.43 84	87.53 49	91.34 135	72.82 46	93.42 174	81.28 103	88.74 148	94.66 33

fmvsm_s_conf0.5_n_a		83.63 103	83.41 103	84.28 133	86.14 271	68.12 139	89.43 98	82.87 348	70.27 248	87.27 55	93.80 68	69.09 93	91.58 258	88.21 37	83.65 240	93.14 123

UGNet		80.83 164	79.59 183	84.54 119	88.04 199	68.09 140	89.42 100	88.16 246	76.95 70	76.22 252	89.46 195	49.30 337	93.94 142	68.48 253	90.31 116	91.60 187
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
tt0805		78.73 226	77.83 226	81.43 246	85.17 295	60.30 321	89.41 101	90.90 144	71.21 217	77.17 231	88.73 215	46.38 359	93.21 184	72.57 206	78.96 301	90.79 216

fmvsm_s_conf0.1_n		83.56 105	83.38 104	84.10 142	84.86 304	67.28 170	89.40 102	83.01 344	70.67 232	87.08 56	93.96 62	68.38 105	91.45 271	88.56 33	84.50 220	93.56 100

BP-MVS1		84.32 87	83.71 97	86.17 64	87.84 209	67.85 150	89.38 103	89.64 189	77.73 45	83.98 101	92.12 109	56.89 253	95.43 73	84.03 75	91.75 93	95.24 7

AdaColmap		80.58 180	79.42 186	84.06 151	93.09 59	68.91 111	89.36 104	88.97 226	69.27 271	75.70 262	89.69 184	57.20 250	95.77 60	63.06 296	88.41 155	87.50 333

fmvsm_s_conf0.1_n_a		83.32 113	82.99 111	84.28 133	83.79 328	68.07 141	89.34 105	82.85 349	69.80 259	87.36 54	94.06 54	68.34 107	91.56 261	87.95 38	83.46 246	93.21 116

PS-MVSNAJss		82.07 135	81.31 139	84.34 128	86.51 263	67.27 171	89.27 106	91.51 126	71.75 203	79.37 178	90.22 172	63.15 167	94.27 126	77.69 144	82.36 261	91.49 193

jajsoiax		79.29 212	77.96 220	83.27 184	84.68 309	66.57 185	89.25 107	90.16 171	69.20 276	75.46 268	89.49 192	45.75 370	93.13 193	76.84 156	80.80 279	90.11 248

fmvsm_s_conf0.5_n_8		86.56 44	87.17 35	84.73 115	87.76 216	65.62 206	89.20 108	92.21 91	79.94 17	89.74 23	94.86 22	68.63 102	94.20 131	90.83 5	91.39 99	94.38 48

fmvsm_s_conf0.5_n_5		85.22 77	85.55 69	84.25 138	86.26 266	67.40 165	89.18 109	89.31 205	72.50 190	88.31 33	93.86 65	69.66 85	91.96 243	89.81 13	91.05 104	93.38 106

mvs_tets		79.13 216	77.77 230	83.22 188	84.70 308	66.37 187	89.17 110	90.19 170	69.38 268	75.40 271	89.46 195	44.17 382	93.15 191	76.78 160	80.70 281	90.14 245

HQP-NCC					89.33 140		89.17 110		76.41 85	77.23 226

ACMP_Plane					89.33 140		89.17 110		76.41 85	77.23 226

HQP-MVS		82.61 127	82.02 132	84.37 125	89.33 140	66.98 178	89.17 110	92.19 93	76.41 85	77.23 226	90.23 171	60.17 224	95.11 90	77.47 146	85.99 197	91.03 207

LS3D		76.95 271	74.82 289	83.37 181	90.45 103	67.36 167	89.15 114	86.94 280	61.87 377	69.52 359	90.61 160	51.71 307	94.53 117	46.38 421	86.71 183	88.21 318

GDP-MVS		83.52 106	82.64 118	86.16 65	88.14 193	68.45 128	89.13 115	92.69 66	72.82 189	83.71 106	91.86 115	55.69 260	95.35 82	80.03 117	89.74 129	94.69 29

OPM-MVS		83.50 107	82.95 112	85.14 93	88.79 168	70.95 71	89.13 115	91.52 125	77.55 52	80.96 152	91.75 117	60.71 213	94.50 119	79.67 122	86.51 186	89.97 260
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n_3		86.36 50	87.46 29	83.09 193	87.08 246	65.21 215	89.09 117	90.21 169	79.67 19	89.98 20	95.02 20	73.17 39	91.71 255	91.30 3	91.60 94	92.34 159

TSAR-MVS + GP.		85.71 65	85.33 74	86.84 52	91.34 84	72.50 36	89.07 118	87.28 271	76.41 85	85.80 66	90.22 172	74.15 32	95.37 81	81.82 98	91.88 89	92.65 146

test_prior4						72.60 34	89.01 119

GeoE		81.71 143	81.01 146	83.80 168	89.51 130	64.45 240	88.97 120	88.73 237	71.27 216	78.63 191	89.76 183	66.32 131	93.20 187	69.89 238	86.02 196	93.74 86

Anonymous20240529		80.19 192	78.89 201	84.10 142	90.60 100	64.75 231	88.95 121	90.90 144	65.97 325	80.59 160	91.17 142	49.97 327	93.73 159	69.16 246	82.70 258	93.81 81

VDD-MVS		83.01 121	82.36 123	84.96 102	91.02 91	66.40 186	88.91 122	88.11 247	77.57 49	84.39 91	93.29 80	52.19 294	93.91 147	77.05 152	88.70 149	94.57 38

Effi-MVS+		83.62 104	83.08 108	85.24 90	88.38 184	67.45 162	88.89 123	89.15 216	75.50 108	82.27 128	88.28 230	69.61 86	94.45 122	77.81 141	87.84 162	93.84 79

fmvsm_s_conf0.5_n_6		85.55 68	86.20 52	83.60 171	87.32 234	65.13 218	88.86 124	91.63 120	75.41 111	88.23 36	93.45 76	68.56 103	92.47 222	89.52 18	92.78 75	93.20 118

ACMH+	68.96 14	76.01 289	74.01 300	82.03 234	88.60 175	65.31 214	88.86 124	87.55 265	70.25 249	67.75 374	87.47 255	41.27 401	93.19 189	58.37 344	75.94 344	87.60 329

test_prior2							88.85 126		75.41 111	84.91 77	93.54 71	74.28 30		83.31 80	95.86 20

Elysia		81.53 149	80.16 164	85.62 79	85.51 286	68.25 135	88.84 127	92.19 93	71.31 213	80.50 161	89.83 178	46.89 354	94.82 104	76.85 154	89.57 131	93.80 83

StellarMVS		81.53 149	80.16 164	85.62 79	85.51 286	68.25 135	88.84 127	92.19 93	71.31 213	80.50 161	89.83 178	46.89 354	94.82 104	76.85 154	89.57 131	93.80 83

DP-MVS Recon		83.11 119	82.09 130	86.15 66	94.44 19	70.92 73	88.79 129	92.20 92	70.53 237	79.17 181	91.03 148	64.12 155	96.03 51	68.39 255	90.14 120	91.50 192

fmvsm_s_conf0.5_n_4		85.39 73	85.75 66	84.30 131	86.70 257	65.83 199	88.77 130	89.78 181	75.46 110	88.35 32	93.73 69	69.19 92	93.06 197	91.30 3	88.44 154	94.02 68

Effi-MVS+-dtu		80.03 194	78.57 206	84.42 124	85.13 299	68.74 117	88.77 130	88.10 248	74.99 124	74.97 290	83.49 357	57.27 248	93.36 175	73.53 193	80.88 277	91.18 201

TEST9					93.26 52	72.96 25	88.75 132	91.89 107	68.44 293	85.00 75	93.10 83	74.36 29	95.41 76

train_agg		86.43 46	86.20 52	87.13 45	93.26 52	72.96 25	88.75 132	91.89 107	68.69 288	85.00 75	93.10 83	74.43 27	95.41 76	84.97 58	95.71 25	93.02 130

ETV-MVS		84.90 84	84.67 84	85.59 81	89.39 138	68.66 123	88.74 134	92.64 73	79.97 16	84.10 98	85.71 301	69.32 90	95.38 78	80.82 108	91.37 100	92.72 141

PVSNet_Blended_VisFu		82.62 126	81.83 136	84.96 102	90.80 97	69.76 93	88.74 134	91.70 118	69.39 267	78.96 183	88.46 225	65.47 143	94.87 103	74.42 185	88.57 150	90.24 242

casdiffmvs_mvg		85.99 55	86.09 58	85.70 77	87.65 221	67.22 174	88.69 136	93.04 42	79.64 21	85.33 71	92.54 99	73.30 36	94.50 119	83.49 78	91.14 103	95.37 2
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_8					93.13 56	72.57 35	88.68 137	91.84 111	68.69 288	84.87 79	93.10 83	74.43 27	95.16 86

test_fmvsm_n_1920		85.29 76	85.34 73	85.13 96	86.12 272	69.93 88	88.65 138	90.78 149	69.97 255	88.27 34	93.98 61	71.39 63	91.54 265	88.49 34	90.45 115	93.91 73

ACMH	67.68 16	75.89 290	73.93 302	81.77 239	88.71 172	66.61 184	88.62 139	89.01 223	69.81 258	66.78 388	86.70 277	41.95 398	91.51 268	55.64 367	78.14 312	87.17 341
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
fmvsm_s_conf0.5_n_9		87.39 30	87.95 20	85.70 77	89.48 133	67.88 149	88.59 140	89.05 220	80.19 12	90.70 17	95.40 15	74.56 25	93.92 146	91.54 2	92.07 87	95.31 5

CDPH-MVS		85.76 64	85.29 77	87.17 44	93.49 47	71.08 66	88.58 141	92.42 81	68.32 295	84.61 86	93.48 73	72.32 48	96.15 49	79.00 127	95.43 30	94.28 55

fmvsm_l_conf0.5_n_9		85.84 62	86.63 45	83.46 176	87.12 245	66.01 193	88.56 142	89.43 196	75.59 106	89.32 24	94.32 40	72.89 43	91.21 280	90.11 11	92.33 83	93.16 120

DP-MVS		76.78 274	74.57 292	83.42 178	93.29 48	69.46 100	88.55 143	83.70 329	63.98 352	70.20 347	88.89 212	54.01 278	94.80 107	46.66 418	81.88 267	86.01 367

fmvsm_l_conf0.5_n		84.47 86	84.54 85	84.27 135	85.42 289	68.81 112	88.49 144	87.26 273	68.08 297	88.03 40	93.49 72	72.04 53	91.77 251	88.90 28	89.14 141	92.24 166

WR-MVS_H		78.51 233	78.49 207	78.56 313	88.02 200	56.38 372	88.43 145	92.67 68	77.14 64	73.89 305	87.55 252	66.25 132	89.24 320	58.92 337	73.55 377	90.06 254

F-COLMAP		76.38 284	74.33 298	82.50 224	89.28 145	66.95 181	88.41 146	89.03 221	64.05 350	66.83 387	88.61 220	46.78 356	92.89 204	57.48 351	78.55 303	87.67 327

GBi-Net		78.40 234	77.40 241	81.40 248	87.60 222	63.01 277	88.39 147	89.28 206	71.63 205	75.34 274	87.28 257	54.80 266	91.11 281	62.72 298	79.57 293	90.09 250

test1		78.40 234	77.40 241	81.40 248	87.60 222	63.01 277	88.39 147	89.28 206	71.63 205	75.34 274	87.28 257	54.80 266	91.11 281	62.72 298	79.57 293	90.09 250

FMVSNet1		77.44 261	76.12 269	81.40 248	86.81 253	63.01 277	88.39 147	89.28 206	70.49 242	74.39 300	87.28 257	49.06 341	91.11 281	60.91 319	78.52 304	90.09 250

tttt0517		79.40 208	77.91 222	83.90 164	88.10 196	63.84 252	88.37 150	84.05 325	71.45 211	76.78 237	89.12 202	49.93 330	94.89 101	70.18 234	83.18 251	92.96 134

fmvsm_l_conf0.5_n_a		84.13 89	84.16 90	84.06 151	85.38 290	68.40 129	88.34 151	86.85 283	67.48 304	87.48 51	93.40 77	70.89 69	91.61 256	88.38 36	89.22 138	92.16 173

v7n		78.97 221	77.58 237	83.14 191	83.45 338	65.51 208	88.32 152	91.21 134	73.69 162	72.41 325	86.32 291	57.93 239	93.81 152	69.18 245	75.65 347	90.11 248

COLMAP_ROB	66.92 17	73.01 330	70.41 345	80.81 266	87.13 240	65.63 205	88.30 153	84.19 324	62.96 362	63.80 415	87.69 247	38.04 419	92.56 217	46.66 418	74.91 364	84.24 394
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FIs		82.07 135	82.42 120	81.04 260	88.80 167	58.34 339	88.26 154	93.49 27	76.93 71	78.47 197	91.04 146	69.92 82	92.34 230	69.87 239	84.97 213	92.44 157

EIA-MVS		83.31 114	82.80 115	84.82 110	89.59 126	65.59 207	88.21 155	92.68 67	74.66 137	78.96 183	86.42 288	69.06 95	95.26 83	75.54 174	90.09 121	93.62 96

PLC	70.83 11	78.05 245	76.37 267	83.08 195	91.88 79	67.80 152	88.19 156	89.46 195	64.33 345	69.87 356	88.38 227	53.66 280	93.58 161	58.86 338	82.73 256	87.86 324
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MG-MVS		83.41 109	83.45 102	83.28 183	92.74 67	62.28 294	88.17 157	89.50 194	75.22 116	81.49 142	92.74 98	66.75 123	95.11 90	72.85 202	91.58 96	92.45 156

TAPA-MVS	73.13 9	79.15 215	77.94 221	82.79 214	89.59 126	62.99 281	88.16 158	91.51 126	65.77 326	77.14 232	91.09 144	60.91 211	93.21 184	50.26 399	87.05 176	92.17 172
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvsmvis_n_1920		84.02 91	83.87 93	84.49 122	84.12 320	69.37 104	88.15 159	87.96 254	70.01 253	83.95 102	93.23 81	68.80 100	91.51 268	88.61 31	89.96 124	92.57 147

h-mvs33		83.15 116	82.19 127	86.02 72	90.56 101	70.85 75	88.15 159	89.16 215	76.02 97	84.67 82	91.39 134	61.54 196	95.50 69	82.71 91	75.48 351	91.72 186

KinetiMVS		83.31 114	82.61 119	85.39 86	87.08 246	67.56 160	88.06 161	91.65 119	77.80 44	82.21 130	91.79 116	57.27 248	94.07 137	77.77 142	89.89 127	94.56 40

PS-CasMVS		78.01 247	78.09 218	77.77 331	87.71 218	54.39 397	88.02 162	91.22 133	77.50 54	73.26 313	88.64 219	60.73 212	88.41 337	61.88 310	73.88 374	90.53 229

OMC-MVS		82.69 125	81.97 134	84.85 109	88.75 170	67.42 163	87.98 163	90.87 146	74.92 128	79.72 171	91.65 121	62.19 185	93.96 139	75.26 178	86.42 187	93.16 120

v8		79.97 196	79.02 198	82.80 211	84.09 321	64.50 238	87.96 164	90.29 167	74.13 152	75.24 281	86.81 270	62.88 174	93.89 150	74.39 186	75.40 356	90.00 256

FC-MVSNet-test		81.52 151	82.02 132	80.03 283	88.42 183	55.97 378	87.95 165	93.42 30	77.10 67	77.38 221	90.98 152	69.96 81	91.79 250	68.46 254	84.50 220	92.33 160

CP-MVSNet		78.22 238	78.34 212	77.84 329	87.83 210	54.54 395	87.94 166	91.17 136	77.65 46	73.48 311	88.49 224	62.24 184	88.43 336	62.19 306	74.07 370	90.55 228

PAPM_NR		83.02 120	82.41 121	84.82 110	92.47 72	66.37 187	87.93 167	91.80 113	73.82 158	77.32 223	90.66 157	67.90 113	94.90 100	70.37 230	89.48 134	93.19 119

PEN-MVS		77.73 253	77.69 234	77.84 329	87.07 248	53.91 400	87.91 168	91.18 135	77.56 51	73.14 315	88.82 214	61.23 205	89.17 322	59.95 326	72.37 385	90.43 233

ECVR-MVS		79.61 199	79.26 192	80.67 269	90.08 112	54.69 393	87.89 169	77.44 407	74.88 130	80.27 164	92.79 95	48.96 343	92.45 223	68.55 252	92.50 80	94.86 19

v10		79.74 198	78.67 203	82.97 203	84.06 322	64.95 224	87.88 170	90.62 152	73.11 182	75.11 285	86.56 284	61.46 199	94.05 138	73.68 191	75.55 349	89.90 262

test2506		77.30 265	76.49 262	79.74 289	90.08 112	52.02 411	87.86 171	63.10 454	74.88 130	80.16 167	92.79 95	38.29 418	92.35 229	68.74 251	92.50 80	94.86 19

SSM_0404		81.91 138	80.84 149	85.13 96	89.24 147	68.26 133	87.84 172	89.25 210	71.06 222	80.62 159	90.39 165	59.57 226	94.65 114	72.45 212	87.19 173	92.47 155

casdiffmvs		85.11 79	85.14 78	85.01 100	87.20 237	65.77 203	87.75 173	92.83 61	77.84 43	84.36 94	92.38 101	72.15 51	93.93 145	81.27 104	90.48 114	95.33 4
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
TranMVSNet+NR-MVSNet		80.84 163	80.31 160	82.42 225	87.85 208	62.33 292	87.74 174	91.33 131	80.55 9	77.99 209	89.86 176	65.23 145	92.62 212	67.05 267	75.24 361	92.30 162

EI-MVSNet-Vis-set		84.19 88	83.81 94	85.31 88	88.18 190	67.85 150	87.66 175	89.73 186	80.05 15	82.95 118	89.59 190	70.74 72	94.82 104	80.66 113	84.72 217	93.28 112

UniMVSNet (Re)		81.60 147	81.11 143	83.09 193	88.38 184	64.41 241	87.60 176	93.02 46	78.42 37	78.56 193	88.16 234	69.78 83	93.26 180	69.58 242	76.49 333	91.60 187

CNLPA		78.08 243	76.79 255	81.97 236	90.40 105	71.07 67	87.59 177	84.55 317	66.03 324	72.38 326	89.64 187	57.56 244	86.04 363	59.61 330	83.35 247	88.79 301

DTE-MVSNet		76.99 269	76.80 254	77.54 337	86.24 267	53.06 409	87.52 178	90.66 151	77.08 68	72.50 323	88.67 218	60.48 220	89.52 314	57.33 354	70.74 397	90.05 255

无先验							87.48 179	88.98 224	60.00 390				94.12 135	67.28 263		88.97 293

viewdifsd2359ckpt13		82.91 122	82.29 125	84.77 113	86.96 249	66.90 182	87.47 180	91.62 121	72.19 196	81.68 140	90.71 156	66.92 122	93.28 177	75.90 168	87.15 174	94.12 62

mvsmamba		80.60 177	79.38 187	84.27 135	89.74 124	67.24 173	87.47 180	86.95 279	70.02 252	75.38 272	88.93 210	51.24 311	92.56 217	75.47 176	89.22 138	93.00 132

FMVSNet2		78.20 240	77.21 245	81.20 255	87.60 222	62.89 283	87.47 180	89.02 222	71.63 205	75.29 280	87.28 257	54.80 266	91.10 284	62.38 303	79.38 297	89.61 272

RRT-MVS		82.60 129	82.10 129	84.10 142	87.98 203	62.94 282	87.45 183	91.27 132	77.42 56	79.85 169	90.28 168	56.62 256	94.70 112	79.87 120	88.15 158	94.67 30

EI-MVSNet-UG-set		83.81 94	83.38 104	85.09 98	87.87 207	67.53 161	87.44 184	89.66 187	79.74 18	82.23 129	89.41 199	70.24 78	94.74 109	79.95 118	83.92 232	92.99 133

SSM_0407		81.58 148	80.48 156	84.87 108	88.81 163	67.96 145	87.37 185	89.25 210	71.06 222	79.48 175	90.39 165	59.57 226	94.48 121	72.45 212	85.93 199	92.18 169

thisisatest0530		79.40 208	77.76 231	84.31 130	87.69 220	65.10 221	87.36 186	84.26 323	70.04 251	77.42 220	88.26 232	49.94 328	94.79 108	70.20 233	84.70 218	93.03 129

CANet_DTU		80.61 175	79.87 173	82.83 208	85.60 284	63.17 276	87.36 186	88.65 240	76.37 89	75.88 259	88.44 226	53.51 282	93.07 196	73.30 197	89.74 129	92.25 164

test1111		79.43 206	79.18 195	80.15 281	89.99 117	53.31 406	87.33 188	77.05 411	75.04 123	80.23 166	92.77 97	48.97 342	92.33 231	68.87 249	92.40 82	94.81 22

baseline		84.93 82	84.98 79	84.80 112	87.30 235	65.39 212	87.30 189	92.88 58	77.62 47	84.04 100	92.26 103	71.81 55	93.96 139	81.31 102	90.30 117	95.03 11

UniMVSNet_ETH3D		79.10 217	78.24 215	81.70 240	86.85 251	60.24 322	87.28 190	88.79 231	74.25 148	76.84 234	90.53 163	49.48 333	91.56 261	67.98 256	82.15 262	93.29 111

anonymousdsp		78.60 230	77.15 246	82.98 202	80.51 394	67.08 176	87.24 191	89.53 193	65.66 328	75.16 283	87.19 263	52.52 288	92.25 233	77.17 150	79.34 298	89.61 272

UniMVSNet_NR-MVSNet		81.88 139	81.54 138	82.92 204	88.46 180	63.46 267	87.13 192	92.37 82	80.19 12	78.38 198	89.14 201	71.66 60	93.05 198	70.05 235	76.46 334	92.25 164

DPM-MVS		84.93 82	84.29 89	86.84 52	90.20 109	73.04 23	87.12 193	93.04 42	69.80 259	82.85 121	91.22 139	73.06 41	96.02 53	76.72 161	94.63 50	91.46 196

v1144		80.03 194	79.03 197	83.01 199	83.78 329	64.51 236	87.11 194	90.57 155	71.96 202	78.08 207	86.20 293	61.41 200	93.94 142	74.93 180	77.23 321	90.60 226

v2v482		80.23 190	79.29 191	83.05 197	83.62 334	64.14 245	87.04 195	89.97 176	73.61 164	78.18 204	87.22 261	61.10 208	93.82 151	76.11 164	76.78 330	91.18 201

fmvsm_s_conf0.1_n_2		83.80 95	83.79 95	83.83 165	85.62 283	64.94 225	87.03 196	86.62 289	74.32 144	87.97 43	94.33 39	60.67 215	92.60 214	89.72 14	87.79 163	93.96 70

DU-MVS		81.12 159	80.52 155	82.90 205	87.80 211	63.46 267	87.02 197	91.87 109	79.01 31	78.38 198	89.07 203	65.02 147	93.05 198	70.05 235	76.46 334	92.20 167

LuminaMVS		80.68 173	79.62 182	83.83 165	85.07 301	68.01 144	86.99 198	88.83 229	70.36 243	81.38 143	87.99 241	50.11 325	92.51 221	79.02 125	86.89 180	90.97 210

fmvsm_s_conf0.5_n_2		84.04 90	84.11 91	83.81 167	86.17 270	65.00 223	86.96 199	87.28 271	74.35 143	88.25 35	94.23 46	61.82 191	92.60 214	89.85 12	88.09 159	93.84 79

v144192		79.47 204	78.37 211	82.78 215	83.35 339	63.96 248	86.96 199	90.36 163	69.99 254	77.50 218	85.67 304	60.66 216	93.77 155	74.27 187	76.58 331	90.62 224

Fast-Effi-MVS+-dtu		78.02 246	76.49 262	82.62 221	83.16 348	66.96 180	86.94 201	87.45 269	72.45 191	71.49 337	84.17 341	54.79 269	91.58 258	67.61 259	80.31 286	89.30 281

v1192		79.59 201	78.43 210	83.07 196	83.55 336	64.52 235	86.93 202	90.58 153	70.83 228	77.78 214	85.90 297	59.15 230	93.94 142	73.96 190	77.19 323	90.76 218

EPNet_dtu		75.46 296	74.86 288	77.23 341	82.57 364	54.60 394	86.89 203	83.09 342	71.64 204	66.25 397	85.86 299	55.99 258	88.04 341	54.92 371	86.55 185	89.05 288
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewmacassd2359aftdt		83.76 97	83.66 99	84.07 148	86.59 261	64.56 233	86.88 204	91.82 112	75.72 101	83.34 112	92.15 108	68.24 109	92.88 205	79.05 124	89.15 140	94.77 25

原ACMM2							86.86 205

VPA-MVSNet		80.60 177	80.55 154	80.76 267	88.07 198	60.80 313	86.86 205	91.58 124	75.67 105	80.24 165	89.45 197	63.34 160	90.25 301	70.51 229	79.22 300	91.23 200

v1921920		79.22 213	78.03 219	82.80 211	83.30 341	63.94 250	86.80 207	90.33 164	69.91 257	77.48 219	85.53 308	58.44 236	93.75 157	73.60 192	76.85 328	90.71 222

IterMVS-LS		80.06 193	79.38 187	82.11 232	85.89 276	63.20 274	86.79 208	89.34 199	74.19 149	75.45 269	86.72 273	66.62 125	92.39 226	72.58 205	76.86 327	90.75 219
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		75.39 300	74.56 293	77.86 328	85.50 288	57.10 360	86.78 209	86.09 299	72.17 198	71.53 336	87.34 256	63.01 171	89.31 318	56.84 360	61.83 427	87.17 341

Baseline_NR-MVSNet		78.15 242	78.33 213	77.61 334	85.79 278	56.21 376	86.78 209	85.76 303	73.60 165	77.93 210	87.57 250	65.02 147	88.99 325	67.14 266	75.33 358	87.63 328

PAPR		81.66 146	80.89 148	83.99 160	90.27 107	64.00 247	86.76 211	91.77 116	68.84 286	77.13 233	89.50 191	67.63 115	94.88 102	67.55 260	88.52 152	93.09 124

Vis-MVSNet (Re-imp)		78.36 236	78.45 208	78.07 325	88.64 174	51.78 417	86.70 212	79.63 389	74.14 151	75.11 285	90.83 154	61.29 204	89.75 310	58.10 347	91.60 94	92.69 144

guyue		81.13 158	80.64 152	82.60 222	86.52 262	63.92 251	86.69 213	87.73 262	73.97 153	80.83 157	89.69 184	56.70 254	91.33 276	78.26 140	85.40 210	92.54 149

viewmanbaseed2359cas		83.66 100	83.55 100	84.00 159	86.81 253	64.53 234	86.65 214	91.75 117	74.89 129	83.15 116	91.68 119	68.74 101	92.83 209	79.02 125	89.24 137	94.63 34

pmmvs6		74.69 305	73.39 309	78.61 310	81.38 383	57.48 355	86.64 215	87.95 255	64.99 338	70.18 348	86.61 280	50.43 321	89.52 314	62.12 308	70.18 400	88.83 299

v1240		78.99 220	77.78 229	82.64 220	83.21 344	63.54 264	86.62 216	90.30 166	69.74 264	77.33 222	85.68 303	57.04 251	93.76 156	73.13 200	76.92 325	90.62 224

MTAPA		87.23 33	87.00 36	87.90 22	94.18 35	74.25 5	86.58 217	92.02 99	79.45 22	85.88 65	94.80 23	68.07 110	96.21 46	86.69 48	95.34 32	93.23 113

旧先验2							86.56 218		58.10 409	87.04 57			88.98 326	74.07 189

FMVSNet3		77.88 250	76.85 253	80.97 263	86.84 252	62.36 291	86.52 219	88.77 232	71.13 218	75.34 274	86.66 279	54.07 276	91.10 284	62.72 298	79.57 293	89.45 276

dcpmvs_2		85.63 66	86.15 56	84.06 151	91.71 80	64.94 225	86.47 220	91.87 109	73.63 163	86.60 62	93.02 88	76.57 15	91.87 249	83.36 79	92.15 85	95.35 3

AstraMVS		80.81 165	80.14 166	82.80 211	86.05 275	63.96 248	86.46 221	85.90 301	73.71 161	80.85 156	90.56 161	54.06 277	91.57 260	79.72 121	83.97 231	92.86 138

pm-mvs1		77.25 266	76.68 260	78.93 305	84.22 318	58.62 336	86.41 222	88.36 245	71.37 212	73.31 312	88.01 240	61.22 206	89.15 323	64.24 289	73.01 382	89.03 289

EI-MVSNet		80.52 181	79.98 169	82.12 230	84.28 316	63.19 275	86.41 222	88.95 227	74.18 150	78.69 188	87.54 253	66.62 125	92.43 224	72.57 206	80.57 283	90.74 220

CVMVSNet		72.99 331	72.58 320	74.25 373	84.28 316	50.85 425	86.41 222	83.45 335	44.56 445	73.23 314	87.54 253	49.38 335	85.70 366	65.90 275	78.44 306	86.19 362

MonoMVSNet		76.49 281	75.80 270	78.58 312	81.55 379	58.45 337	86.36 225	86.22 295	74.87 132	74.73 294	83.73 350	51.79 306	88.73 331	70.78 224	72.15 388	88.55 311

NR-MVSNet		80.23 190	79.38 187	82.78 215	87.80 211	63.34 270	86.31 226	91.09 140	79.01 31	72.17 329	89.07 203	67.20 120	92.81 210	66.08 274	75.65 347	92.20 167

viewcassd2359sk11		83.89 92	83.74 96	84.34 128	87.76 216	64.91 228	86.30 227	92.22 89	75.47 109	83.04 117	91.52 128	70.15 79	93.53 166	79.26 123	87.96 160	94.57 38

v148		78.72 227	77.80 228	81.47 245	82.73 360	61.96 298	86.30 227	88.08 249	73.26 177	76.18 254	85.47 310	62.46 179	92.36 228	71.92 216	73.82 375	90.09 250

新几何2							86.29 229

test_yl		81.17 156	80.47 157	83.24 186	89.13 152	63.62 256	86.21 230	89.95 177	72.43 194	81.78 138	89.61 188	57.50 245	93.58 161	70.75 225	86.90 178	92.52 150

DCV-MVSNet		81.17 156	80.47 157	83.24 186	89.13 152	63.62 256	86.21 230	89.95 177	72.43 194	81.78 138	89.61 188	57.50 245	93.58 161	70.75 225	86.90 178	92.52 150

PVSNet_BlendedMVS		80.60 177	80.02 168	82.36 227	88.85 159	65.40 210	86.16 232	92.00 101	69.34 269	78.11 205	86.09 296	66.02 138	94.27 126	71.52 217	82.06 264	87.39 334

MVS_Test		83.15 116	83.06 109	83.41 180	86.86 250	63.21 273	86.11 233	92.00 101	74.31 145	82.87 120	89.44 198	70.03 80	93.21 184	77.39 148	88.50 153	93.81 81

BH-untuned		79.47 204	78.60 205	82.05 233	89.19 150	65.91 197	86.07 234	88.52 243	72.18 197	75.42 270	87.69 247	61.15 207	93.54 165	60.38 323	86.83 181	86.70 355

MVS_111021_HR		85.14 78	84.75 83	86.32 61	91.65 81	72.70 30	85.98 235	90.33 164	76.11 95	82.08 132	91.61 126	71.36 64	94.17 134	81.02 105	92.58 78	92.08 175

jason		81.39 154	80.29 161	84.70 116	86.63 260	69.90 90	85.95 236	86.77 284	63.24 357	81.07 150	89.47 193	61.08 209	92.15 236	78.33 136	90.07 123	92.05 176
jason: jason.
test_0402		72.79 333	70.44 344	79.84 287	88.13 194	65.99 195	85.93 237	84.29 321	65.57 329	67.40 381	85.49 309	46.92 353	92.61 213	35.88 447	74.38 369	80.94 426

OurMVSNet-221017-0		74.26 309	72.42 322	79.80 288	83.76 330	59.59 329	85.92 238	86.64 287	66.39 319	66.96 385	87.58 249	39.46 409	91.60 257	65.76 277	69.27 403	88.22 317

hse-mvs2		81.72 142	80.94 147	84.07 148	88.72 171	67.68 155	85.87 239	87.26 273	76.02 97	84.67 82	88.22 233	61.54 196	93.48 169	82.71 91	73.44 379	91.06 205

EG-PatchMatch MVS		74.04 313	71.82 327	80.71 268	84.92 303	67.42 163	85.86 240	88.08 249	66.04 323	64.22 410	83.85 345	35.10 429	92.56 217	57.44 352	80.83 278	82.16 419

AUN-MVS		79.21 214	77.60 236	84.05 154	88.71 172	67.61 157	85.84 241	87.26 273	69.08 279	77.23 226	88.14 238	53.20 286	93.47 170	75.50 175	73.45 378	91.06 205

thres100view900		76.50 278	75.55 277	79.33 298	89.52 129	56.99 361	85.83 242	83.23 338	73.94 155	76.32 250	87.12 265	51.89 303	91.95 244	48.33 409	83.75 236	89.07 283

CLD-MVS		82.31 131	81.65 137	84.29 132	88.47 179	67.73 154	85.81 243	92.35 83	75.78 100	78.33 200	86.58 283	64.01 156	94.35 123	76.05 166	87.48 168	90.79 216
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
VortexMVS		78.57 232	77.89 224	80.59 270	85.89 276	62.76 284	85.61 244	89.62 190	72.06 200	74.99 289	85.38 312	55.94 259	90.77 295	74.99 179	76.58 331	88.23 316

SixPastTwentyTwo		73.37 322	71.26 336	79.70 290	85.08 300	57.89 347	85.57 245	83.56 332	71.03 224	65.66 400	85.88 298	42.10 396	92.57 216	59.11 335	63.34 422	88.65 307

xiu_mvs_v1_base_debu		80.80 168	79.72 179	84.03 156	87.35 227	70.19 84	85.56 246	88.77 232	69.06 280	81.83 134	88.16 234	50.91 314	92.85 206	78.29 137	87.56 165	89.06 285

xiu_mvs_v1_base		80.80 168	79.72 179	84.03 156	87.35 227	70.19 84	85.56 246	88.77 232	69.06 280	81.83 134	88.16 234	50.91 314	92.85 206	78.29 137	87.56 165	89.06 285

xiu_mvs_v1_base_debi		80.80 168	79.72 179	84.03 156	87.35 227	70.19 84	85.56 246	88.77 232	69.06 280	81.83 134	88.16 234	50.91 314	92.85 206	78.29 137	87.56 165	89.06 285

V42		79.38 210	78.24 215	82.83 208	81.10 388	65.50 209	85.55 249	89.82 180	71.57 209	78.21 202	86.12 295	60.66 216	93.18 190	75.64 171	75.46 353	89.81 267

lupinMVS		81.39 154	80.27 162	84.76 114	87.35 227	70.21 82	85.55 249	86.41 291	62.85 364	81.32 144	88.61 220	61.68 193	92.24 234	78.41 135	90.26 118	91.83 179

Fast-Effi-MVS+		80.81 165	79.92 170	83.47 175	88.85 159	64.51 236	85.53 251	89.39 198	70.79 229	78.49 195	85.06 321	67.54 116	93.58 161	67.03 268	86.58 184	92.32 161

thres600view7		76.50 278	75.44 278	79.68 291	89.40 137	57.16 358	85.53 251	83.23 338	73.79 159	76.26 251	87.09 266	51.89 303	91.89 247	48.05 414	83.72 239	90.00 256

DELS-MVS		85.41 72	85.30 76	85.77 75	88.49 178	67.93 148	85.52 253	93.44 28	78.70 34	83.63 110	89.03 205	74.57 24	95.71 62	80.26 116	94.04 63	93.66 89
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
fmvsm_s_conf0.5_n_7		83.34 112	84.03 92	81.28 252	85.73 280	65.13 218	85.40 254	89.90 179	74.96 127	82.13 131	93.89 64	66.65 124	87.92 342	86.56 49	91.05 104	90.80 215

IMVS_0407		80.61 175	79.90 172	82.75 218	87.13 240	63.59 260	85.33 255	89.33 200	70.51 238	77.82 211	89.03 205	61.84 189	92.91 203	72.56 208	85.56 206	91.74 182

IMVS_0403		80.80 168	80.12 167	82.87 207	87.13 240	63.59 260	85.19 256	89.33 200	70.51 238	78.49 195	89.03 205	63.26 163	93.27 179	72.56 208	85.56 206	91.74 182

tfpn200view9		76.42 282	75.37 282	79.55 296	89.13 152	57.65 352	85.17 257	83.60 330	73.41 172	76.45 246	86.39 289	52.12 295	91.95 244	48.33 409	83.75 236	89.07 283

thres400		76.50 278	75.37 282	79.86 286	89.13 152	57.65 352	85.17 257	83.60 330	73.41 172	76.45 246	86.39 289	52.12 295	91.95 244	48.33 409	83.75 236	90.00 256

MVS_111021_LR		82.61 127	82.11 128	84.11 141	88.82 162	71.58 57	85.15 259	86.16 297	74.69 135	80.47 163	91.04 146	62.29 182	90.55 298	80.33 115	90.08 122	90.20 243

baseline1		76.98 270	76.75 258	77.66 332	88.13 194	55.66 383	85.12 260	81.89 358	73.04 184	76.79 236	88.90 211	62.43 180	87.78 345	63.30 295	71.18 395	89.55 274

mmtdpeth		74.16 311	73.01 315	77.60 336	83.72 331	61.13 306	85.10 261	85.10 310	72.06 200	77.21 230	80.33 397	43.84 384	85.75 365	77.14 151	52.61 446	85.91 370

viewdifsd2359ckpt07		82.83 124	82.78 117	82.99 200	86.51 263	62.58 285	85.09 262	90.83 148	75.22 116	82.28 127	91.63 123	69.43 88	92.03 239	77.71 143	86.32 188	94.34 51

WR-MVS		79.49 203	79.22 194	80.27 278	88.79 168	58.35 338	85.06 263	88.61 242	78.56 35	77.65 216	88.34 228	63.81 159	90.66 297	64.98 283	77.22 322	91.80 181

ET-MVSNet_ETH3D		78.63 229	76.63 261	84.64 117	86.73 256	69.47 98	85.01 264	84.61 316	69.54 265	66.51 395	86.59 281	50.16 324	91.75 252	76.26 163	84.24 228	92.69 144

OpenMVS_ROB	64.09 19	70.56 354	68.19 360	77.65 333	80.26 395	59.41 332	85.01 264	82.96 347	58.76 403	65.43 402	82.33 376	37.63 421	91.23 279	45.34 428	76.03 343	82.32 416

BH-RMVSNet		79.61 199	78.44 209	83.14 191	89.38 139	65.93 196	84.95 266	87.15 276	73.56 166	78.19 203	89.79 182	56.67 255	93.36 175	59.53 331	86.74 182	90.13 246

BH-w/o		78.21 239	77.33 244	80.84 265	88.81 163	65.13 218	84.87 267	87.85 259	69.75 262	74.52 298	84.74 328	61.34 202	93.11 194	58.24 346	85.84 202	84.27 393

TDRefinement		67.49 380	64.34 392	76.92 343	73.47 440	61.07 309	84.86 268	82.98 346	59.77 392	58.30 435	85.13 319	26.06 444	87.89 343	47.92 415	60.59 432	81.81 422

Anonymous202405211		78.25 237	77.01 248	81.99 235	91.03 90	60.67 315	84.77 269	83.90 327	70.65 236	80.00 168	91.20 140	41.08 403	91.43 272	65.21 280	85.26 211	93.85 77

TAMVS		78.89 224	77.51 240	83.03 198	87.80 211	67.79 153	84.72 270	85.05 312	67.63 300	76.75 238	87.70 246	62.25 183	90.82 291	58.53 342	87.13 175	90.49 231

sc_t1		72.19 339	69.51 350	80.23 279	84.81 305	61.09 308	84.68 271	80.22 383	60.70 384	71.27 338	83.58 355	36.59 424	89.24 320	60.41 322	63.31 423	90.37 236

1314		76.53 277	75.30 284	80.21 280	83.93 325	62.32 293	84.66 272	88.81 230	60.23 388	70.16 350	84.07 343	55.30 263	90.73 296	67.37 262	83.21 250	87.59 331

MVS		78.19 241	76.99 250	81.78 238	85.66 281	66.99 177	84.66 272	90.47 157	55.08 425	72.02 331	85.27 314	63.83 158	94.11 136	66.10 273	89.80 128	84.24 394

tfpnnormal		74.39 307	73.16 313	78.08 324	86.10 274	58.05 342	84.65 274	87.53 266	70.32 246	71.22 340	85.63 305	54.97 264	89.86 307	43.03 433	75.02 363	86.32 359

TR-MVS		77.44 261	76.18 268	81.20 255	88.24 188	63.24 272	84.61 275	86.40 292	67.55 302	77.81 213	86.48 287	54.10 275	93.15 191	57.75 350	82.72 257	87.20 340

AllTest		70.96 348	68.09 363	79.58 294	85.15 297	63.62 256	84.58 276	79.83 386	62.31 371	60.32 428	86.73 271	32.02 434	88.96 328	50.28 397	71.57 393	86.15 363

FA-MVS(test-final)		80.96 161	79.91 171	84.10 142	88.30 187	65.01 222	84.55 277	90.01 175	73.25 178	79.61 172	87.57 250	58.35 237	94.72 110	71.29 221	86.25 191	92.56 148

EU-MVSNet		68.53 375	67.61 374	71.31 401	78.51 416	47.01 439	84.47 278	84.27 322	42.27 448	66.44 396	84.79 327	40.44 406	83.76 384	58.76 340	68.54 408	83.17 406

VNet		82.21 132	82.41 121	81.62 241	90.82 96	60.93 310	84.47 278	89.78 181	76.36 90	84.07 99	91.88 113	64.71 150	90.26 300	70.68 227	88.89 143	93.66 89

xiu_mvs_v2_base		81.69 144	81.05 144	83.60 171	89.15 151	68.03 143	84.46 280	90.02 174	70.67 232	81.30 147	86.53 286	63.17 166	94.19 133	75.60 173	88.54 151	88.57 310

VPNet		78.69 228	78.66 204	78.76 308	88.31 186	55.72 382	84.45 281	86.63 288	76.79 75	78.26 201	90.55 162	59.30 229	89.70 312	66.63 269	77.05 324	90.88 213

PVSNet_Blended		80.98 160	80.34 159	82.90 205	88.85 159	65.40 210	84.43 282	92.00 101	67.62 301	78.11 205	85.05 322	66.02 138	94.27 126	71.52 217	89.50 133	89.01 290

MVP-Stereo		76.12 286	74.46 296	81.13 258	85.37 291	69.79 91	84.42 283	87.95 255	65.03 336	67.46 378	85.33 313	53.28 285	91.73 254	58.01 348	83.27 249	81.85 421
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		79.07 218	77.70 233	83.17 190	87.60 222	68.23 137	84.40 284	86.20 296	67.49 303	76.36 249	86.54 285	61.54 196	90.79 292	61.86 311	87.33 170	90.49 231
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
K. test v3		71.19 345	68.51 357	79.21 301	83.04 351	57.78 351	84.35 285	76.91 412	72.90 187	62.99 418	82.86 369	39.27 410	91.09 286	61.65 313	52.66 445	88.75 303

PS-MVSNAJ		81.69 144	81.02 145	83.70 169	89.51 130	68.21 138	84.28 286	90.09 173	70.79 229	81.26 148	85.62 306	63.15 167	94.29 124	75.62 172	88.87 144	88.59 309

patch_mono-2		83.65 101	84.54 85	80.99 261	90.06 116	65.83 199	84.21 287	88.74 236	71.60 208	85.01 74	92.44 100	74.51 26	83.50 388	82.15 96	92.15 85	93.64 95

viewdifsd2359ckpt11		80.37 186	79.73 177	82.30 228	83.70 332	62.39 289	84.20 288	86.67 285	73.22 180	80.90 153	90.62 158	63.00 172	91.56 261	76.81 158	78.44 306	92.95 135

viewmsd2359difaftdt		80.37 186	79.73 177	82.30 228	83.70 332	62.39 289	84.20 288	86.67 285	73.22 180	80.90 153	90.62 158	63.00 172	91.56 261	76.81 158	78.44 306	92.95 135

test222					91.50 82	68.26 133	84.16 290	83.20 341	54.63 426	79.74 170	91.63 123	58.97 231			91.42 98	86.77 353

testdata1							84.14 291		75.71 102

c3_l		78.75 225	77.91 222	81.26 253	82.89 357	61.56 303	84.09 292	89.13 218	69.97 255	75.56 264	84.29 336	66.36 130	92.09 238	73.47 195	75.48 351	90.12 247

MVSTER		79.01 219	77.88 225	82.38 226	83.07 349	64.80 230	84.08 293	88.95 227	69.01 283	78.69 188	87.17 264	54.70 270	92.43 224	74.69 181	80.57 283	89.89 263

diffmvs_AUTHOR		82.38 130	82.27 126	82.73 219	83.26 342	63.80 253	83.89 294	89.76 183	73.35 174	82.37 126	90.84 153	66.25 132	90.79 292	82.77 88	87.93 161	93.59 98

ab-mvs		79.51 202	78.97 199	81.14 257	88.46 180	60.91 311	83.84 295	89.24 212	70.36 243	79.03 182	88.87 213	63.23 165	90.21 302	65.12 281	82.57 259	92.28 163

reproduce_monomvs		75.40 299	74.38 297	78.46 318	83.92 326	57.80 350	83.78 296	86.94 280	73.47 170	72.25 328	84.47 330	38.74 414	89.27 319	75.32 177	70.53 398	88.31 315

PAPM		77.68 257	76.40 266	81.51 244	87.29 236	61.85 299	83.78 296	89.59 191	64.74 339	71.23 339	88.70 216	62.59 176	93.66 160	52.66 383	87.03 177	89.01 290

SD_0403		74.65 306	74.77 290	74.29 372	86.20 269	47.42 436	83.71 298	85.12 309	69.30 270	68.50 370	87.95 242	59.40 228	86.05 362	49.38 403	83.35 247	89.40 277

diffmvs		82.10 133	81.88 135	82.76 217	83.00 352	63.78 255	83.68 299	89.76 183	72.94 186	82.02 133	89.85 177	65.96 140	90.79 292	82.38 95	87.30 171	93.71 87
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
miper_ehance_all_eth		78.59 231	77.76 231	81.08 259	82.66 362	61.56 303	83.65 300	89.15 216	68.87 285	75.55 265	83.79 348	66.49 128	92.03 239	73.25 198	76.39 336	89.64 271

1112_ss		77.40 263	76.43 264	80.32 277	89.11 156	60.41 320	83.65 300	87.72 263	62.13 374	73.05 316	86.72 273	62.58 177	89.97 306	62.11 309	80.80 279	90.59 227

PCF-MVS	73.52 7	80.38 184	78.84 202	85.01 100	87.71 218	68.99 109	83.65 300	91.46 130	63.00 361	77.77 215	90.28 168	66.10 135	95.09 94	61.40 315	88.22 157	90.94 212
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVG-ACMP-BASELINE		76.11 287	74.27 299	81.62 241	83.20 345	64.67 232	83.60 303	89.75 185	69.75 262	71.85 332	87.09 266	32.78 433	92.11 237	69.99 237	80.43 285	88.09 320

tt0320		70.49 356	68.03 364	77.89 327	84.78 306	59.12 333	83.55 304	80.44 378	58.13 408	67.43 380	80.41 396	39.26 411	87.54 348	55.12 369	63.18 424	86.99 348

cl22		78.07 244	77.01 248	81.23 254	82.37 369	61.83 300	83.55 304	87.98 253	68.96 284	75.06 287	83.87 344	61.40 201	91.88 248	73.53 193	76.39 336	89.98 259

XVG-OURS-SEG-HR		80.81 165	79.76 176	83.96 162	85.60 284	68.78 114	83.54 306	90.50 156	70.66 235	76.71 239	91.66 120	60.69 214	91.26 277	76.94 153	81.58 269	91.83 179

viewmambaseed2359dif		80.41 182	79.84 174	82.12 230	82.95 356	62.50 288	83.39 307	88.06 251	67.11 306	80.98 151	90.31 167	66.20 134	91.01 288	74.62 182	84.90 214	92.86 138

IB-MVS	68.01 15	75.85 291	73.36 311	83.31 182	84.76 307	66.03 191	83.38 308	85.06 311	70.21 250	69.40 360	81.05 387	45.76 369	94.66 113	65.10 282	75.49 350	89.25 282
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
HY-MVS	69.67 12	77.95 248	77.15 246	80.36 275	87.57 226	60.21 323	83.37 309	87.78 261	66.11 321	75.37 273	87.06 268	63.27 162	90.48 299	61.38 316	82.43 260	90.40 235

tt0320-xc		70.11 360	67.45 377	78.07 325	85.33 292	59.51 331	83.28 310	78.96 396	58.77 402	67.10 384	80.28 398	36.73 423	87.42 349	56.83 361	59.77 434	87.29 338

test_vis1_n_1920		75.52 295	75.78 271	74.75 368	79.84 402	57.44 356	83.26 311	85.52 305	62.83 365	79.34 180	86.17 294	45.10 375	79.71 410	78.75 130	81.21 273	87.10 347

Anonymous20240521		68.80 371	67.22 380	73.55 379	74.33 432	54.11 398	83.18 312	85.61 304	58.15 407	61.68 422	80.94 390	30.71 439	81.27 404	57.00 358	73.34 381	85.28 379

eth_miper_zixun_eth		77.92 249	76.69 259	81.61 243	83.00 352	61.98 297	83.15 313	89.20 214	69.52 266	74.86 292	84.35 335	61.76 192	92.56 217	71.50 219	72.89 383	90.28 241

FE-MVS		77.78 252	75.68 273	84.08 147	88.09 197	66.00 194	83.13 314	87.79 260	68.42 294	78.01 208	85.23 316	45.50 373	95.12 88	59.11 335	85.83 203	91.11 203

cl____		77.72 254	76.76 256	80.58 271	82.49 366	60.48 318	83.09 315	87.87 257	69.22 274	74.38 301	85.22 317	62.10 186	91.53 266	71.09 222	75.41 355	89.73 270

DIV-MVS_self_test		77.72 254	76.76 256	80.58 271	82.48 367	60.48 318	83.09 315	87.86 258	69.22 274	74.38 301	85.24 315	62.10 186	91.53 266	71.09 222	75.40 356	89.74 269

thres200		75.55 294	74.47 295	78.82 307	87.78 214	57.85 348	83.07 317	83.51 333	72.44 193	75.84 260	84.42 331	52.08 298	91.75 252	47.41 416	83.64 241	86.86 351

testing3		68.56 374	67.67 373	71.22 402	87.33 232	42.87 452	83.06 318	71.54 432	70.36 243	69.08 364	84.38 333	30.33 440	85.69 367	37.50 445	75.45 354	85.09 385

XVG-OURS		80.41 182	79.23 193	83.97 161	85.64 282	69.02 108	83.03 319	90.39 159	71.09 220	77.63 217	91.49 131	54.62 272	91.35 274	75.71 170	83.47 245	91.54 190

miper_enhance_ethall		77.87 251	76.86 252	80.92 264	81.65 376	61.38 305	82.68 320	88.98 224	65.52 330	75.47 266	82.30 377	65.76 142	92.00 242	72.95 201	76.39 336	89.39 278

mvs_anonymous		79.42 207	79.11 196	80.34 276	84.45 315	57.97 345	82.59 321	87.62 264	67.40 305	76.17 256	88.56 223	68.47 104	89.59 313	70.65 228	86.05 195	93.47 104

baseline2		75.70 292	73.83 305	81.30 251	83.26 342	61.79 301	82.57 322	80.65 372	66.81 308	66.88 386	83.42 358	57.86 241	92.19 235	63.47 292	79.57 293	89.91 261

cascas		76.72 275	74.64 291	82.99 200	85.78 279	65.88 198	82.33 323	89.21 213	60.85 383	72.74 319	81.02 388	47.28 350	93.75 157	67.48 261	85.02 212	89.34 280

WB-MVSnew		71.96 342	71.65 329	72.89 387	84.67 312	51.88 415	82.29 324	77.57 404	62.31 371	73.67 309	83.00 365	53.49 283	81.10 405	45.75 425	82.13 263	85.70 373

RPSCF		73.23 327	71.46 331	78.54 314	82.50 365	59.85 325	82.18 325	82.84 350	58.96 400	71.15 341	89.41 199	45.48 374	84.77 378	58.82 339	71.83 391	91.02 209

thisisatest0515		77.33 264	75.38 281	83.18 189	85.27 294	63.80 253	82.11 326	83.27 337	65.06 335	75.91 258	83.84 346	49.54 332	94.27 126	67.24 264	86.19 192	91.48 194

pmmvs-eth3d		70.50 355	67.83 369	78.52 316	77.37 420	66.18 190	81.82 327	81.51 363	58.90 401	63.90 414	80.42 395	42.69 391	86.28 360	58.56 341	65.30 418	83.11 408

MS-PatchMatch		73.83 316	72.67 318	77.30 340	83.87 327	66.02 192	81.82 327	84.66 315	61.37 381	68.61 368	82.82 370	47.29 349	88.21 338	59.27 332	84.32 227	77.68 436

pmmvs5		71.55 343	70.20 348	75.61 353	77.83 417	56.39 371	81.74 329	80.89 368	57.76 411	67.46 378	84.49 329	49.26 338	85.32 373	57.08 356	75.29 359	85.11 384

Test_1112_low_res		76.40 283	75.44 278	79.27 299	89.28 145	58.09 341	81.69 330	87.07 277	59.53 395	72.48 324	86.67 278	61.30 203	89.33 317	60.81 321	80.15 288	90.41 234

IterMVS		74.29 308	72.94 316	78.35 319	81.53 380	63.49 266	81.58 331	82.49 352	68.06 298	69.99 353	83.69 352	51.66 308	85.54 369	65.85 276	71.64 392	86.01 367
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		75.43 297	73.87 304	80.11 282	82.69 361	64.85 229	81.57 332	83.47 334	69.16 277	70.49 344	84.15 342	51.95 301	88.15 339	69.23 244	72.14 389	87.34 336

test_vis1_n		69.85 364	69.21 353	71.77 395	72.66 446	55.27 389	81.48 333	76.21 416	52.03 433	75.30 279	83.20 362	28.97 441	76.22 430	74.60 183	78.41 310	83.81 400

pmmvs4		74.03 315	71.91 326	80.39 274	81.96 372	68.32 131	81.45 334	82.14 355	59.32 396	69.87 356	85.13 319	52.40 291	88.13 340	60.21 325	74.74 366	84.73 390

GA-MVS		76.87 272	75.17 286	81.97 236	82.75 359	62.58 285	81.44 335	86.35 294	72.16 199	74.74 293	82.89 368	46.20 364	92.02 241	68.85 250	81.09 274	91.30 199

UWE-MVS		72.13 340	71.49 330	74.03 375	86.66 259	47.70 434	81.40 336	76.89 413	63.60 356	75.59 263	84.22 340	39.94 408	85.62 368	48.98 406	86.13 194	88.77 302

test_fmvs1_n		70.86 350	70.24 347	72.73 389	72.51 447	55.28 388	81.27 337	79.71 388	51.49 436	78.73 187	84.87 324	27.54 443	77.02 422	76.06 165	79.97 291	85.88 371

testing91		76.54 276	75.66 275	79.18 302	88.43 182	55.89 379	81.08 338	83.00 345	73.76 160	75.34 274	84.29 336	46.20 364	90.07 304	64.33 287	84.50 220	91.58 189

testing222		74.04 313	72.66 319	78.19 321	87.89 206	55.36 386	81.06 339	79.20 394	71.30 215	74.65 296	83.57 356	39.11 413	88.67 333	51.43 391	85.75 204	90.53 229

test_fmvs1		70.93 349	70.52 342	72.16 393	73.71 436	55.05 390	80.82 340	78.77 397	51.21 437	78.58 192	84.41 332	31.20 438	76.94 423	75.88 169	80.12 290	84.47 392

CostFormer		75.24 301	73.90 303	79.27 299	82.65 363	58.27 340	80.80 341	82.73 351	61.57 378	75.33 278	83.13 363	55.52 261	91.07 287	64.98 283	78.34 311	88.45 312

testing99		76.09 288	75.12 287	79.00 303	88.16 191	55.50 385	80.79 342	81.40 365	73.30 176	75.17 282	84.27 339	44.48 379	90.02 305	64.28 288	84.22 229	91.48 194

MIMVSNet1		68.58 373	66.78 383	73.98 376	80.07 399	51.82 416	80.77 343	84.37 318	64.40 343	59.75 431	82.16 380	36.47 425	83.63 386	42.73 434	70.33 399	86.48 358

CL-MVSNet_self_test		72.37 336	71.46 331	75.09 362	79.49 409	53.53 402	80.76 344	85.01 313	69.12 278	70.51 343	82.05 381	57.92 240	84.13 382	52.27 385	66.00 416	87.60 329

testing11		75.14 302	74.01 300	78.53 315	88.16 191	56.38 372	80.74 345	80.42 379	70.67 232	72.69 322	83.72 351	43.61 386	89.86 307	62.29 305	83.76 235	89.36 279

MSDG		73.36 324	70.99 338	80.49 273	84.51 314	65.80 201	80.71 346	86.13 298	65.70 327	65.46 401	83.74 349	44.60 377	90.91 290	51.13 392	76.89 326	84.74 389

tpm2		73.26 326	71.46 331	78.63 309	83.34 340	56.71 366	80.65 347	80.40 380	56.63 419	73.55 310	82.02 382	51.80 305	91.24 278	56.35 365	78.42 309	87.95 321

XXY-MVS		75.41 298	75.56 276	74.96 363	83.59 335	57.82 349	80.59 348	83.87 328	66.54 318	74.93 291	88.31 229	63.24 164	80.09 409	62.16 307	76.85 328	86.97 349

test_cas_vis1_n_1920		73.76 317	73.74 306	73.81 378	75.90 424	59.77 326	80.51 349	82.40 353	58.30 406	81.62 141	85.69 302	44.35 381	76.41 428	76.29 162	78.61 302	85.23 380

EGC-MVSNET		52.07 421	47.05 425	67.14 421	83.51 337	60.71 314	80.50 350	67.75 443	0.07 471	0.43 472	75.85 433	24.26 449	81.54 401	28.82 454	62.25 426	59.16 454

SDMVSNet		80.38 184	80.18 163	80.99 261	89.03 157	64.94 225	80.45 351	89.40 197	75.19 120	76.61 243	89.98 174	60.61 218	87.69 346	76.83 157	83.55 242	90.33 238

HyFIR lowres test		77.53 260	75.40 280	83.94 163	89.59 126	66.62 183	80.36 352	88.64 241	56.29 421	76.45 246	85.17 318	57.64 243	93.28 177	61.34 317	83.10 252	91.91 178

D2MVS		74.82 304	73.21 312	79.64 293	79.81 403	62.56 287	80.34 353	87.35 270	64.37 344	68.86 365	82.66 372	46.37 360	90.10 303	67.91 257	81.24 272	86.25 360

testing3-2		75.12 303	75.19 285	74.91 364	90.40 105	45.09 447	80.29 354	78.42 399	78.37 40	76.54 245	87.75 244	44.36 380	87.28 351	57.04 357	83.49 244	92.37 158

TinyColmap		67.30 383	64.81 390	74.76 367	81.92 374	56.68 367	80.29 354	81.49 364	60.33 386	56.27 442	83.22 360	24.77 448	87.66 347	45.52 426	69.47 402	79.95 431

FE-MVSNET		67.25 384	65.33 388	73.02 386	75.86 425	52.54 410	80.26 356	80.56 374	63.80 355	60.39 426	79.70 406	41.41 400	84.66 380	43.34 432	62.62 425	81.86 420

LCM-MVSNet-Re		77.05 268	76.94 251	77.36 338	87.20 237	51.60 418	80.06 357	80.46 377	75.20 119	67.69 375	86.72 273	62.48 178	88.98 326	63.44 293	89.25 136	91.51 191

test_fmvs2		68.35 377	67.48 376	70.98 404	69.50 450	51.95 413	80.05 358	76.38 415	49.33 439	74.65 296	84.38 333	23.30 452	75.40 439	74.51 184	75.17 362	85.60 374

FMVSNet5		69.50 365	67.96 365	74.15 374	82.97 355	55.35 387	80.01 359	82.12 356	62.56 369	63.02 416	81.53 384	36.92 422	81.92 399	48.42 408	74.06 371	85.17 383

SCA		74.22 310	72.33 323	79.91 285	84.05 323	62.17 295	79.96 360	79.29 393	66.30 320	72.38 326	80.13 400	51.95 301	88.60 334	59.25 333	77.67 319	88.96 294

tpmrst		72.39 334	72.13 325	73.18 385	80.54 393	49.91 429	79.91 361	79.08 395	63.11 359	71.69 334	79.95 402	55.32 262	82.77 394	65.66 278	73.89 373	86.87 350

PatchmatchNet		73.12 328	71.33 334	78.49 317	83.18 346	60.85 312	79.63 362	78.57 398	64.13 346	71.73 333	79.81 405	51.20 312	85.97 364	57.40 353	76.36 341	88.66 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PatchMatch-RL		72.38 335	70.90 339	76.80 345	88.60 175	67.38 166	79.53 363	76.17 417	62.75 367	69.36 361	82.00 383	45.51 372	84.89 377	53.62 378	80.58 282	78.12 435

CMPMVS	51.72 21	70.19 359	68.16 361	76.28 347	73.15 443	57.55 354	79.47 364	83.92 326	48.02 441	56.48 441	84.81 326	43.13 388	86.42 359	62.67 301	81.81 268	84.89 387
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ETVMVS		72.25 338	71.05 337	75.84 350	87.77 215	51.91 414	79.39 365	74.98 420	69.26 272	73.71 307	82.95 366	40.82 405	86.14 361	46.17 422	84.43 225	89.47 275

GG-mvs-BLEND				75.38 359	81.59 378	55.80 381	79.32 366	69.63 437		67.19 382	73.67 438	43.24 387	88.90 330	50.41 394	84.50 220	81.45 423

LTVRE_ROB	69.57 13	76.25 285	74.54 294	81.41 247	88.60 175	64.38 242	79.24 367	89.12 219	70.76 231	69.79 358	87.86 243	49.09 340	93.20 187	56.21 366	80.16 287	86.65 356
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
tpm		72.37 336	71.71 328	74.35 371	82.19 370	52.00 412	79.22 368	77.29 409	64.56 341	72.95 318	83.68 353	51.35 309	83.26 391	58.33 345	75.80 345	87.81 325

mvs5depth		69.45 366	67.45 377	75.46 358	73.93 434	55.83 380	79.19 369	83.23 338	66.89 307	71.63 335	83.32 359	33.69 432	85.09 374	59.81 328	55.34 442	85.46 376

ppachtmachnet_test		70.04 361	67.34 379	78.14 322	79.80 404	61.13 306	79.19 369	80.59 373	59.16 398	65.27 403	79.29 409	46.75 357	87.29 350	49.33 404	66.72 411	86.00 369

USDC		70.33 357	68.37 358	76.21 348	80.60 392	56.23 375	79.19 369	86.49 290	60.89 382	61.29 423	85.47 310	31.78 436	89.47 316	53.37 380	76.21 342	82.94 412

sd_testset		77.70 256	77.40 241	78.60 311	89.03 157	60.02 324	79.00 372	85.83 302	75.19 120	76.61 243	89.98 174	54.81 265	85.46 371	62.63 302	83.55 242	90.33 238

PM-MVS		66.41 390	64.14 393	73.20 384	73.92 435	56.45 369	78.97 373	64.96 451	63.88 354	64.72 407	80.24 399	19.84 456	83.44 389	66.24 270	64.52 420	79.71 432

tpmvs		71.09 347	69.29 352	76.49 346	82.04 371	56.04 377	78.92 374	81.37 366	64.05 350	67.18 383	78.28 418	49.74 331	89.77 309	49.67 402	72.37 385	83.67 402

test_post1							78.90 375				5.43 470	48.81 345	85.44 372	59.25 333

mamv4		76.81 273	78.23 217	72.54 391	86.12 272	65.75 204	78.76 376	82.07 357	64.12 347	72.97 317	91.02 149	67.97 111	68.08 456	83.04 84	78.02 313	83.80 401

CHOSEN 1792x2688		77.63 259	75.69 272	83.44 177	89.98 118	68.58 125	78.70 377	87.50 267	56.38 420	75.80 261	86.84 269	58.67 234	91.40 273	61.58 314	85.75 204	90.34 237

Syy-MVS		68.05 378	67.85 367	68.67 415	84.68 309	40.97 458	78.62 378	73.08 429	66.65 315	66.74 389	79.46 407	52.11 297	82.30 396	32.89 450	76.38 339	82.75 413

myMVS_eth3d		67.02 385	66.29 385	69.21 410	84.68 309	42.58 453	78.62 378	73.08 429	66.65 315	66.74 389	79.46 407	31.53 437	82.30 396	39.43 442	76.38 339	82.75 413

WBMVS		73.43 321	72.81 317	75.28 360	87.91 205	50.99 424	78.59 380	81.31 367	65.51 332	74.47 299	84.83 325	46.39 358	86.68 355	58.41 343	77.86 314	88.17 319

test-LLR		72.94 332	72.43 321	74.48 369	81.35 384	58.04 343	78.38 381	77.46 405	66.66 312	69.95 354	79.00 412	48.06 346	79.24 411	66.13 271	84.83 215	86.15 363

TESTMET0.1,1		69.89 363	69.00 355	72.55 390	79.27 412	56.85 362	78.38 381	74.71 424	57.64 412	68.09 372	77.19 425	37.75 420	76.70 424	63.92 290	84.09 230	84.10 397

test-mter		71.41 344	70.39 346	74.48 369	81.35 384	58.04 343	78.38 381	77.46 405	60.32 387	69.95 354	79.00 412	36.08 427	79.24 411	66.13 271	84.83 215	86.15 363

UBG		73.08 329	72.27 324	75.51 356	88.02 200	51.29 422	78.35 384	77.38 408	65.52 330	73.87 306	82.36 375	45.55 371	86.48 358	55.02 370	84.39 226	88.75 303

Anonymous20231206		68.60 372	67.80 370	71.02 403	80.23 397	50.75 426	78.30 385	80.47 376	56.79 418	66.11 399	82.63 373	46.35 361	78.95 413	43.62 431	75.70 346	83.36 405

tpm cat1		70.57 353	68.31 359	77.35 339	82.41 368	57.95 346	78.08 386	80.22 383	52.04 432	68.54 369	77.66 423	52.00 300	87.84 344	51.77 386	72.07 390	86.25 360

myMVS_eth3d28		73.62 318	73.53 308	73.90 377	88.20 189	47.41 437	78.06 387	79.37 391	74.29 147	73.98 304	84.29 336	44.67 376	83.54 387	51.47 389	87.39 169	90.74 220

our_test_3		69.14 368	67.00 381	75.57 354	79.80 404	58.80 334	77.96 388	77.81 402	59.55 394	62.90 419	78.25 419	47.43 348	83.97 383	51.71 387	67.58 410	83.93 399

KD-MVS_self_test		68.81 370	67.59 375	72.46 392	74.29 433	45.45 442	77.93 389	87.00 278	63.12 358	63.99 413	78.99 414	42.32 393	84.77 378	56.55 364	64.09 421	87.16 343

WTY-MVS		75.65 293	75.68 273	75.57 354	86.40 265	56.82 363	77.92 390	82.40 353	65.10 334	76.18 254	87.72 245	63.13 170	80.90 406	60.31 324	81.96 265	89.00 292

UWE-MVS-28		65.32 395	64.93 389	66.49 423	78.70 414	38.55 460	77.86 391	64.39 452	62.00 376	64.13 411	83.60 354	41.44 399	76.00 432	31.39 452	80.89 276	84.92 386

test20.03		67.45 381	66.95 382	68.94 411	75.48 429	44.84 448	77.50 392	77.67 403	66.66 312	63.01 417	83.80 347	47.02 352	78.40 415	42.53 436	68.86 407	83.58 403

EPMVS		69.02 369	68.16 361	71.59 396	79.61 407	49.80 431	77.40 393	66.93 445	62.82 366	70.01 351	79.05 410	45.79 368	77.86 419	56.58 363	75.26 360	87.13 344

test_fmvs3		63.36 402	61.82 405	67.98 419	62.51 459	46.96 440	77.37 394	74.03 426	45.24 444	67.50 377	78.79 415	12.16 464	72.98 448	72.77 204	66.02 415	83.99 398

gg-mvs-nofinetune		69.95 362	67.96 365	75.94 349	83.07 349	54.51 396	77.23 395	70.29 435	63.11 359	70.32 346	62.33 449	43.62 385	88.69 332	53.88 377	87.76 164	84.62 391

IMVS_0404		77.16 267	76.42 265	79.37 297	87.13 240	63.59 260	77.12 396	89.33 200	70.51 238	66.22 398	89.03 205	50.36 322	82.78 393	72.56 208	85.56 206	91.74 182

MDTV_nov1_ep13			69.97 349		83.18 346	53.48 403	77.10 397	80.18 385	60.45 385	69.33 362	80.44 394	48.89 344	86.90 353	51.60 388	78.51 305

icg_test_0407_2		78.92 223	78.93 200	78.90 306	87.13 240	63.59 260	76.58 398	89.33 200	70.51 238	77.82 211	89.03 205	61.84 189	81.38 403	72.56 208	85.56 206	91.74 182

LF4IMVS		64.02 400	62.19 404	69.50 409	70.90 448	53.29 407	76.13 399	77.18 410	52.65 431	58.59 433	80.98 389	23.55 451	76.52 426	53.06 382	66.66 412	78.68 434

sss		73.60 319	73.64 307	73.51 380	82.80 358	55.01 391	76.12 400	81.69 361	62.47 370	74.68 295	85.85 300	57.32 247	78.11 417	60.86 320	80.93 275	87.39 334

testgi		66.67 388	66.53 384	67.08 422	75.62 428	41.69 457	75.93 401	76.50 414	66.11 321	65.20 406	86.59 281	35.72 428	74.71 441	43.71 430	73.38 380	84.84 388

CR-MVSNet		73.37 322	71.27 335	79.67 292	81.32 386	65.19 216	75.92 402	80.30 381	59.92 391	72.73 320	81.19 385	52.50 289	86.69 354	59.84 327	77.71 316	87.11 345

RPMNet		73.51 320	70.49 343	82.58 223	81.32 386	65.19 216	75.92 402	92.27 85	57.60 413	72.73 320	76.45 428	52.30 292	95.43 73	48.14 413	77.71 316	87.11 345

MIMVSNet		70.69 352	69.30 351	74.88 365	84.52 313	56.35 374	75.87 404	79.42 390	64.59 340	67.76 373	82.41 374	41.10 402	81.54 401	46.64 420	81.34 270	86.75 354

test0.0.03 1		68.00 379	67.69 372	68.90 412	77.55 418	47.43 435	75.70 405	72.95 431	66.66 312	66.56 391	82.29 378	48.06 346	75.87 434	44.97 429	74.51 368	83.41 404

dmvs_re		71.14 346	70.58 341	72.80 388	81.96 372	59.68 327	75.60 406	79.34 392	68.55 290	69.27 363	80.72 393	49.42 334	76.54 425	52.56 384	77.79 315	82.19 418

dmvs_testset		62.63 403	64.11 394	58.19 433	78.55 415	24.76 471	75.28 407	65.94 448	67.91 299	60.34 427	76.01 430	53.56 281	73.94 446	31.79 451	67.65 409	75.88 440

PMMVS		69.34 367	68.67 356	71.35 400	75.67 427	62.03 296	75.17 408	73.46 427	50.00 438	68.68 366	79.05 410	52.07 299	78.13 416	61.16 318	82.77 255	73.90 442

UnsupCasMVSNet_eth		67.33 382	65.99 386	71.37 398	73.48 439	51.47 420	75.16 409	85.19 308	65.20 333	60.78 425	80.93 392	42.35 392	77.20 421	57.12 355	53.69 444	85.44 377

MDTV_nov1_ep13_2view						37.79 461	75.16 409		55.10 424	66.53 392		49.34 336		53.98 376		87.94 322

pmmvs3		57.79 410	54.26 415	68.37 416	64.02 458	56.72 365	75.12 411	65.17 449	40.20 450	52.93 446	69.86 446	20.36 455	75.48 437	45.45 427	55.25 443	72.90 444

dp		66.80 386	65.43 387	70.90 405	79.74 406	48.82 433	75.12 411	74.77 422	59.61 393	64.08 412	77.23 424	42.89 389	80.72 407	48.86 407	66.58 413	83.16 407

Patchmtry		70.74 351	69.16 354	75.49 357	80.72 390	54.07 399	74.94 413	80.30 381	58.34 405	70.01 351	81.19 385	52.50 289	86.54 356	53.37 380	71.09 396	85.87 372

ttmdpeth		59.91 408	57.10 412	68.34 417	67.13 454	46.65 441	74.64 414	67.41 444	48.30 440	62.52 421	85.04 323	20.40 454	75.93 433	42.55 435	45.90 455	82.44 415

SSC-MVS3.2		73.35 325	73.39 309	73.23 381	85.30 293	49.01 432	74.58 415	81.57 362	75.21 118	73.68 308	85.58 307	52.53 287	82.05 398	54.33 375	77.69 318	88.63 308

PVSNet	64.34 18	72.08 341	70.87 340	75.69 352	86.21 268	56.44 370	74.37 416	80.73 371	62.06 375	70.17 349	82.23 379	42.86 390	83.31 390	54.77 372	84.45 224	87.32 337

WB-MVS		54.94 413	54.72 414	55.60 439	73.50 438	20.90 473	74.27 417	61.19 456	59.16 398	50.61 448	74.15 436	47.19 351	75.78 435	17.31 464	35.07 458	70.12 446

MDA-MVSNet-bldmvs		66.68 387	63.66 397	75.75 351	79.28 411	60.56 317	73.92 418	78.35 400	64.43 342	50.13 450	79.87 404	44.02 383	83.67 385	46.10 423	56.86 436	83.03 410

SSC-MVS		53.88 416	53.59 416	54.75 441	72.87 444	19.59 474	73.84 419	60.53 458	57.58 414	49.18 452	73.45 439	46.34 362	75.47 438	16.20 467	32.28 460	69.20 447

UnsupCasMVSNet_bld		63.70 401	61.53 407	70.21 407	73.69 437	51.39 421	72.82 420	81.89 358	55.63 423	57.81 437	71.80 442	38.67 415	78.61 414	49.26 405	52.21 447	80.63 428

PatchT		68.46 376	67.85 367	70.29 406	80.70 391	43.93 450	72.47 421	74.88 421	60.15 389	70.55 342	76.57 427	49.94 328	81.59 400	50.58 393	74.83 365	85.34 378

miper_lstm_enhance		74.11 312	73.11 314	77.13 342	80.11 398	59.62 328	72.23 422	86.92 282	66.76 310	70.40 345	82.92 367	56.93 252	82.92 392	69.06 247	72.63 384	88.87 297

MVS-HIRNet		59.14 409	57.67 411	63.57 427	81.65 376	43.50 451	71.73 423	65.06 450	39.59 452	51.43 447	57.73 455	38.34 417	82.58 395	39.53 440	73.95 372	64.62 451

MVStest1		56.63 412	52.76 418	68.25 418	61.67 460	53.25 408	71.67 424	68.90 442	38.59 453	50.59 449	83.05 364	25.08 446	70.66 450	36.76 446	38.56 456	80.83 427

APD_test1		53.31 418	49.93 423	63.42 428	65.68 455	50.13 428	71.59 425	66.90 446	34.43 458	40.58 457	71.56 443	8.65 469	76.27 429	34.64 449	55.36 441	63.86 452

Patchmatch-RL test		70.24 358	67.78 371	77.61 334	77.43 419	59.57 330	71.16 426	70.33 434	62.94 363	68.65 367	72.77 440	50.62 318	85.49 370	69.58 242	66.58 413	87.77 326

test123		6.12 440	8.11 443	0.14 454	0.06 478	0.09 479	71.05 427	0.03 479	0.04 473	0.25 474	1.30 473	0.05 477	0.03 474	0.21 473	0.01 472	0.29 469

ANet_high		50.57 423	46.10 427	63.99 426	48.67 471	39.13 459	70.99 428	80.85 369	61.39 380	31.18 460	57.70 456	17.02 459	73.65 447	31.22 453	15.89 468	79.18 433

KD-MVS_2432*1600		66.22 392	63.89 395	73.21 382	75.47 430	53.42 404	70.76 429	84.35 319	64.10 348	66.52 393	78.52 416	34.55 430	84.98 375	50.40 395	50.33 449	81.23 424

miper_refine_blended		66.22 392	63.89 395	73.21 382	75.47 430	53.42 404	70.76 429	84.35 319	64.10 348	66.52 393	78.52 416	34.55 430	84.98 375	50.40 395	50.33 449	81.23 424

test_vis1_rt		60.28 407	58.42 410	65.84 424	67.25 453	55.60 384	70.44 431	60.94 457	44.33 446	59.00 432	66.64 447	24.91 447	68.67 454	62.80 297	69.48 401	73.25 443

testmvs		6.04 441	8.02 444	0.10 455	0.08 477	0.03 480	69.74 432	0.04 478	0.05 472	0.31 473	1.68 472	0.02 478	0.04 473	0.24 472	0.02 471	0.25 470

N_pmnet		52.79 419	53.26 417	51.40 443	78.99 413	7.68 477	69.52 433	3.89 476	51.63 435	57.01 439	74.98 435	40.83 404	65.96 458	37.78 444	64.67 419	80.56 430

FPMVS		53.68 417	51.64 419	59.81 432	65.08 456	51.03 423	69.48 434	69.58 438	41.46 449	40.67 456	72.32 441	16.46 460	70.00 453	24.24 460	65.42 417	58.40 456

DSMNet-mixed		57.77 411	56.90 413	60.38 431	67.70 452	35.61 462	69.18 435	53.97 463	32.30 461	57.49 438	79.88 403	40.39 407	68.57 455	38.78 443	72.37 385	76.97 437

new-patchmatchnet		61.73 405	61.73 406	61.70 429	72.74 445	24.50 472	69.16 436	78.03 401	61.40 379	56.72 440	75.53 434	38.42 416	76.48 427	45.95 424	57.67 435	84.13 396

YYNet1		65.03 396	62.91 401	71.38 397	75.85 426	56.60 368	69.12 437	74.66 425	57.28 416	54.12 444	77.87 421	45.85 367	74.48 442	49.95 400	61.52 429	83.05 409

MDA-MVSNet_test_wron		65.03 396	62.92 400	71.37 398	75.93 423	56.73 364	69.09 438	74.73 423	57.28 416	54.03 445	77.89 420	45.88 366	74.39 443	49.89 401	61.55 428	82.99 411

PVSNet_0	57.27 20	61.67 406	59.27 409	68.85 413	79.61 407	57.44 356	68.01 439	73.44 428	55.93 422	58.54 434	70.41 445	44.58 378	77.55 420	47.01 417	35.91 457	71.55 445

dongtai		45.42 427	45.38 428	45.55 445	73.36 441	26.85 469	67.72 440	34.19 471	54.15 427	49.65 451	56.41 458	25.43 445	62.94 461	19.45 462	28.09 462	46.86 461

ADS-MVSNet2		66.20 394	63.33 398	74.82 366	79.92 400	58.75 335	67.55 441	75.19 419	53.37 429	65.25 404	75.86 431	42.32 393	80.53 408	41.57 437	68.91 405	85.18 381

ADS-MVSNet		64.36 399	62.88 402	68.78 414	79.92 400	47.17 438	67.55 441	71.18 433	53.37 429	65.25 404	75.86 431	42.32 393	73.99 445	41.57 437	68.91 405	85.18 381

mvsany_test1		62.30 404	61.26 408	65.41 425	69.52 449	54.86 392	66.86 443	49.78 465	46.65 442	68.50 370	83.21 361	49.15 339	66.28 457	56.93 359	60.77 430	75.11 441

LCM-MVSNet		54.25 414	49.68 424	67.97 420	53.73 468	45.28 445	66.85 444	80.78 370	35.96 457	39.45 458	62.23 451	8.70 468	78.06 418	48.24 412	51.20 448	80.57 429

test_vis3_rt		49.26 424	47.02 426	56.00 436	54.30 465	45.27 446	66.76 445	48.08 466	36.83 455	44.38 454	53.20 459	7.17 471	64.07 459	56.77 362	55.66 439	58.65 455

testf1		45.72 425	41.96 429	57.00 434	56.90 462	45.32 443	66.14 446	59.26 459	26.19 462	30.89 461	60.96 453	4.14 472	70.64 451	26.39 458	46.73 453	55.04 457

APD_test2		45.72 425	41.96 429	57.00 434	56.90 462	45.32 443	66.14 446	59.26 459	26.19 462	30.89 461	60.96 453	4.14 472	70.64 451	26.39 458	46.73 453	55.04 457

kuosan		39.70 431	40.40 432	37.58 448	64.52 457	26.98 467	65.62 448	33.02 472	46.12 443	42.79 455	48.99 461	24.10 450	46.56 469	12.16 470	26.30 463	39.20 462

JIA-IIPM		66.32 391	62.82 403	76.82 344	77.09 421	61.72 302	65.34 449	75.38 418	58.04 410	64.51 408	62.32 450	42.05 397	86.51 357	51.45 390	69.22 404	82.21 417

PMVS	37.38 22	44.16 429	40.28 433	55.82 438	40.82 473	42.54 455	65.12 450	63.99 453	34.43 458	24.48 464	57.12 457	3.92 474	76.17 431	17.10 465	55.52 440	48.75 459
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
mamba_0408		79.37 211	77.52 238	84.93 105	88.81 163	67.96 145	65.03 451	88.66 238	70.96 226	79.48 175	89.80 180	58.69 232	94.65 114	70.35 231	85.93 199	92.18 169

SSM_04072		77.67 258	77.52 238	78.12 323	88.81 163	67.96 145	65.03 451	88.66 238	70.96 226	79.48 175	89.80 180	58.69 232	74.23 444	70.35 231	85.93 199	92.18 169

new_pmnet		50.91 422	50.29 422	52.78 442	68.58 451	34.94 464	63.71 453	56.63 462	39.73 451	44.95 453	65.47 448	21.93 453	58.48 462	34.98 448	56.62 437	64.92 450

mvsany_test3		53.99 415	51.45 420	61.61 430	55.51 464	44.74 449	63.52 454	45.41 469	43.69 447	58.11 436	76.45 428	17.99 457	63.76 460	54.77 372	47.59 451	76.34 439

Patchmatch-test		64.82 398	63.24 399	69.57 408	79.42 410	49.82 430	63.49 455	69.05 440	51.98 434	59.95 430	80.13 400	50.91 314	70.98 449	40.66 439	73.57 376	87.90 323

ambc				75.24 361	73.16 442	50.51 427	63.05 456	87.47 268		64.28 409	77.81 422	17.80 458	89.73 311	57.88 349	60.64 431	85.49 375

test_f		52.09 420	50.82 421	55.90 437	53.82 467	42.31 456	59.42 457	58.31 461	36.45 456	56.12 443	70.96 444	12.18 463	57.79 463	53.51 379	56.57 438	67.60 448

CHOSEN 280x420		66.51 389	64.71 391	71.90 394	81.45 381	63.52 265	57.98 458	68.95 441	53.57 428	62.59 420	76.70 426	46.22 363	75.29 440	55.25 368	79.68 292	76.88 438

E-PMN		31.77 432	30.64 435	35.15 449	52.87 469	27.67 466	57.09 459	47.86 467	24.64 464	16.40 469	33.05 465	11.23 465	54.90 465	14.46 468	18.15 466	22.87 465

EMVS		30.81 434	29.65 436	34.27 450	50.96 470	25.95 470	56.58 460	46.80 468	24.01 465	15.53 470	30.68 466	12.47 462	54.43 466	12.81 469	17.05 467	22.43 466

PMMVS2		40.82 430	38.86 434	46.69 444	53.84 466	16.45 475	48.61 461	49.92 464	37.49 454	31.67 459	60.97 452	8.14 470	56.42 464	28.42 455	30.72 461	67.19 449

wuyk23d		16.82 438	15.94 441	19.46 452	58.74 461	31.45 465	39.22 462	3.74 477	6.84 468	6.04 471	2.70 471	1.27 476	24.29 471	10.54 471	14.40 470	2.63 468

tmp_tt		18.61 437	21.40 440	10.23 453	4.82 476	10.11 476	34.70 463	30.74 474	1.48 470	23.91 466	26.07 467	28.42 442	13.41 472	27.12 456	15.35 469	7.17 467

Gipuma		45.18 428	41.86 431	55.16 440	77.03 422	51.52 419	32.50 464	80.52 375	32.46 460	27.12 463	35.02 464	9.52 467	75.50 436	22.31 461	60.21 433	38.45 463
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	26.22 23	30.37 435	25.89 439	43.81 446	44.55 472	35.46 463	28.87 465	39.07 470	18.20 466	18.58 468	40.18 463	2.68 475	47.37 468	17.07 466	23.78 465	48.60 460
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		31.52 433	29.28 437	38.23 447	27.03 475	6.50 478	20.94 466	62.21 455	4.05 469	22.35 467	52.50 460	13.33 461	47.58 467	27.04 457	34.04 459	60.62 453

mmdepth		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

monomultidepth		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

test_blank		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uanet_test		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

DCPMVS		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

cdsmvs_eth3d_5k		19.96 436	26.61 438	0.00 456	0.00 479	0.00 481	0.00 467	89.26 209	0.00 474	0.00 475	88.61 220	61.62 195	0.00 475	0.00 474	0.00 473	0.00 471

pcd_1.5k_mvsjas		5.26 442	7.02 445	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	63.15 167	0.00 475	0.00 474	0.00 473	0.00 471

sosnet-low-res		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

sosnet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uncertanet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

Regformer		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

ab-mvs-re		7.23 439	9.64 442	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	86.72 273	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

uanet		0.00 443	0.00 446	0.00 456	0.00 479	0.00 481	0.00 467	0.00 480	0.00 474	0.00 475	0.00 474	0.00 479	0.00 475	0.00 474	0.00 473	0.00 471

WAC-MVS						42.58 453								39.46 441

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 15	96.44 9	94.41 45

PC_three_1452									68.21 296	92.02 12	94.00 58	82.09 5	95.98 57	84.58 66	96.68 2	94.95 12

No_MVS				89.16 1	94.34 27	75.53 2		92.99 50					97.53 2	89.67 15	96.44 9	94.41 45

test_one_0601					95.07 7	71.46 59		94.14 6	78.27 41	92.05 11	95.74 6	80.83 11

eth-test2					0.00 479

eth-test					0.00 479

ZD-MVS					94.38 25	72.22 46		92.67 68	70.98 225	87.75 46	94.07 53	74.01 33	96.70 27	84.66 65	94.84 44

IU-MVS					95.30 2	71.25 61		92.95 56	66.81 308	92.39 6				88.94 27	96.63 4	94.85 21

test_241102_TWO								94.06 11	77.24 60	92.78 4	95.72 8	81.26 8	97.44 7	89.07 24	96.58 6	94.26 56

test_241102_ONE					95.30 2	70.98 68		94.06 11	77.17 63	93.10 1	95.39 16	82.99 1	97.27 12

test_0728_THIRD									78.38 38	92.12 9	95.78 4	81.46 7	97.40 9	89.42 19	96.57 7	94.67 30

GSMVS																88.96 294

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 310				88.96 294

sam_mvs												50.01 326

MTGPA								92.02 99

test_post											5.46 469	50.36 322	84.24 381

patchmatchnet-post											74.00 437	51.12 313	88.60 334

gm-plane-assit					81.40 382	53.83 401			62.72 368		80.94 390		92.39 226	63.40 294

test9_res														84.90 59	95.70 26	92.87 137

agg_prior2														82.91 86	95.45 29	92.70 142

agg_prior					92.85 64	71.94 52		91.78 115		84.41 90			94.93 97

TestCases				79.58 294	85.15 297	63.62 256		79.83 386	62.31 371	60.32 428	86.73 271	32.02 434	88.96 328	50.28 397	71.57 393	86.15 363

test_prior				86.33 60	92.61 70	69.59 94		92.97 55					95.48 70			93.91 73

新几何1				83.42 178	93.13 56	70.71 76		85.48 306	57.43 415	81.80 137	91.98 110	63.28 161	92.27 232	64.60 286	92.99 72	87.27 339

旧先验1					91.96 76	65.79 202		86.37 293			93.08 87	69.31 91			92.74 76	88.74 305

原ACMM1				84.35 127	93.01 62	68.79 113		92.44 78	63.96 353	81.09 149	91.57 127	66.06 137	95.45 71	67.19 265	94.82 46	88.81 300

testdata2													91.01 288	62.37 304

segment_acmp												73.08 40

testdata				79.97 284	90.90 94	64.21 244		84.71 314	59.27 397	85.40 70	92.91 89	62.02 188	89.08 324	68.95 248	91.37 100	86.63 357

test12				86.80 54	92.63 69	70.70 77		91.79 114		82.71 124		71.67 59	96.16 48		94.50 53	93.54 102

plane_prior7					90.08 112	68.51 127

plane_prior6					89.84 121	68.70 121						60.42 221

plane_prior5								92.44 78					95.38 78	78.71 131	86.32 188	91.33 197

plane_prior4											91.00 150

plane_prior3						68.60 124			78.44 36	78.92 185

plane_prior1					89.90 120

n2								0.00 480

nn								0.00 480

door-mid								69.98 436

lessismore_v0				78.97 304	81.01 389	57.15 359		65.99 447		61.16 424	82.82 370	39.12 412	91.34 275	59.67 329	46.92 452	88.43 313

LGP-MVS_train				84.50 120	89.23 148	68.76 115		91.94 105	75.37 113	76.64 241	91.51 129	54.29 273	94.91 98	78.44 133	83.78 233	89.83 265

test11								92.23 88

door								69.44 439

HQP5-MVS						66.98 178

BP-MVS														77.47 146

HQP4-MVS										77.24 225			95.11 90			91.03 207

HQP3-MVS								92.19 93							85.99 197

HQP2-MVS												60.17 224

NP-MVS					89.62 125	68.32 131					90.24 170

ACMMP++_ref															81.95 266

ACMMP++															81.25 271

Test By Simon												64.33 153

ITE_SJBPF				78.22 320	81.77 375	60.57 316		83.30 336	69.25 273	67.54 376	87.20 262	36.33 426	87.28 351	54.34 374	74.62 367	86.80 352

DeepMVS_CX				27.40 451	40.17 474	26.90 468		24.59 475	17.44 467	23.95 465	48.61 462	9.77 466	26.48 470	18.06 463	24.47 464	28.83 464

High-resolution multi-view benchmark