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 57	95.06 1	94.23 3	78.38 33	92.78 4	95.74 6	82.45 3	97.49 4	89.42 9	96.68 2	94.95 10

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 113	91.30 15

CP-MVS		87.11 29	86.92 31	87.68 34	94.20 34	73.86 7	93.98 3	92.82 58	76.62 70	83.68 82	94.46 25	67.93 88	95.95 52	84.20 53	94.39 53	93.23 87

APDe-MVS		89.15 6	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 89	91.06 16	96.03 1	76.84 14	97.03 17	89.09 11	95.65 27	94.47 31
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		88.72 10	88.86 10	88.32 9	92.14 69	72.96 25	93.73 5	93.67 20	80.19 12	88.10 25	94.80 17	73.76 33	97.11 15	87.51 29	95.82 21	94.90 13
Skip Steuart: Steuart Systems R&D Blog.
test0726					95.27 5	71.25 57	93.60 6	94.11 6	77.33 48	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 63	93.57 7	94.06 10	77.24 50	93.10 1	95.72 8	82.99 1	97.44 6	89.07 14	96.63 4	94.88 14

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 44	82.45 3	96.87 20	83.77 56	96.48 8	94.88 14

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 57	93.49 9	92.73 59	77.33 48	92.12 9	95.78 4	80.98 9	97.40 8	89.08 12	96.41 12	93.33 84
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 56	93.49 9	94.23 3					97.49 4	89.08 12	96.41 12	94.21 42

3Dnovator+	77.84 4	85.48 53	84.47 67	88.51 7	91.08 81	73.49 16	93.18 11	93.78 18	80.79 8	76.66 193	93.37 60	60.40 186	96.75 26	77.20 115	93.73 62	95.29 5

HFP-MVS		87.58 21	87.47 23	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 65	84.91 57	94.44 28	70.78 58	96.61 32	84.53 47	94.89 41	93.66 65

ACMMPR		87.44 22	87.23 26	88.08 14	94.64 13	73.59 12	93.04 12	93.20 34	76.78 65	84.66 64	94.52 21	68.81 82	96.65 30	84.53 47	94.90 40	94.00 50

ZNCC-MVS		87.94 18	87.85 19	88.20 12	94.39 24	73.33 19	93.03 14	93.81 17	76.81 63	85.24 51	94.32 31	71.76 47	96.93 19	85.53 37	95.79 22	94.32 38

region2R		87.42 24	87.20 27	88.09 13	94.63 14	73.55 13	93.03 14	93.12 37	76.73 68	84.45 68	94.52 21	69.09 76	96.70 27	84.37 49	94.83 44	94.03 49

MSP-MVS		89.51 4	89.91 5	88.30 10	94.28 30	73.46 17	92.90 16	94.11 6	80.27 10	91.35 14	94.16 37	78.35 13	96.77 24	89.59 8	94.22 58	94.67 24
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 34	86.95 30	85.90 63	90.76 90	67.57 138	92.83 17	93.30 32	79.67 17	84.57 67	92.27 84	71.47 52	95.02 86	84.24 52	93.46 63	95.13 6

XVS		87.18 28	86.91 32	88.00 17	94.42 20	73.33 19	92.78 18	92.99 45	79.14 21	83.67 83	94.17 36	67.45 93	96.60 33	83.06 61	94.50 50	94.07 47

X-MVStestdata		80.37 142	77.83 179	88.00 17	94.42 20	73.33 19	92.78 18	92.99 45	79.14 21	83.67 83	12.47 394	67.45 93	96.60 33	83.06 61	94.50 50	94.07 47

mPP-MVS		86.67 36	86.32 38	87.72 30	94.41 22	73.55 13	92.74 20	92.22 80	76.87 62	82.81 95	94.25 34	66.44 103	96.24 41	82.88 65	94.28 56	93.38 81

ACMMP		85.89 47	85.39 53	87.38 39	93.59 45	72.63 33	92.74 20	93.18 36	76.78 65	80.73 119	93.82 53	64.33 123	96.29 39	82.67 71	90.69 94	93.23 87
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
MP-MVS		87.71 19	87.64 21	87.93 21	94.36 26	73.88 6	92.71 22	92.65 64	77.57 41	83.84 80	94.40 30	72.24 43	96.28 40	85.65 36	95.30 35	93.62 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MM				88.97 4		73.65 10	92.66 23	91.17 116	86.57 1	87.39 33	94.97 16	71.70 49	97.68 1	92.19 1	95.63 28	95.57 1

SF-MVS		88.46 11	88.74 11	87.64 35	92.78 61	71.95 50	92.40 24	94.74 2	75.71 87	89.16 19	95.10 14	75.65 21	96.19 43	87.07 32	96.01 17	94.79 21

SMA-MVS		89.08 7	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 107	92.29 7	95.97 2	74.28 29	97.24 12	88.58 20	96.91 1	94.87 16
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 24	87.26 24	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 61	84.68 61	93.99 48	70.67 60	96.82 22	84.18 54	95.01 37	93.90 55

HPM-MVS++		89.02 8	89.15 8	88.63 5	95.01 9	76.03 1	92.38 27	92.85 54	80.26 11	87.78 28	94.27 32	75.89 19	96.81 23	87.45 30	96.44 9	93.05 96

SR-MVS		86.73 33	86.67 34	86.91 46	94.11 37	72.11 47	92.37 28	92.56 67	74.50 112	86.84 40	94.65 20	67.31 95	95.77 54	84.80 44	92.85 67	92.84 103

CS-MVS-test		86.29 41	86.48 36	85.71 65	91.02 83	67.21 150	92.36 29	93.78 18	78.97 28	83.51 86	91.20 109	70.65 61	95.15 77	81.96 74	94.89 41	94.77 22

EC-MVSNet		86.01 42	86.38 37	84.91 88	89.31 130	66.27 164	92.32 30	93.63 21	79.37 20	84.17 74	91.88 91	69.04 80	95.43 65	83.93 55	93.77 61	93.01 99

EPP-MVSNet		83.40 81	83.02 81	84.57 96	90.13 100	64.47 205	92.32 30	90.73 128	74.45 115	79.35 133	91.10 112	69.05 79	95.12 78	72.78 161	87.22 136	94.13 44

PHI-MVS		86.43 38	86.17 42	87.24 41	90.88 87	70.96 65	92.27 32	94.07 9	72.45 152	85.22 52	91.90 90	69.47 72	96.42 37	83.28 60	95.94 19	94.35 36

MVS_0304		88.08 13	88.08 16	88.08 14	89.67 113	72.04 48	92.26 33	89.26 173	84.19 2	85.01 53	95.18 13	69.93 67	97.20 14	91.63 2	95.60 29	94.99 9

HPM-MVS		87.11 29	86.98 29	87.50 38	93.88 39	72.16 45	92.19 34	93.33 31	76.07 82	83.81 81	93.95 51	69.77 70	96.01 48	85.15 38	94.66 46	94.32 38
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MTMP							92.18 35	32.83 399

HPM-MVS_fast		85.35 57	84.95 62	86.57 53	93.69 42	70.58 75	92.15 36	91.62 103	73.89 126	82.67 97	94.09 40	62.60 142	95.54 60	80.93 81	92.93 66	93.57 74

CPTT-MVS		83.73 71	83.33 77	84.92 87	93.28 49	70.86 69	92.09 37	90.38 137	68.75 231	79.57 130	92.83 74	60.60 182	93.04 178	80.92 82	91.56 84	90.86 165

APD-MVS_3200maxsize		85.97 44	85.88 47	86.22 57	92.69 63	69.53 89	91.93 38	92.99 45	73.54 135	85.94 43	94.51 24	65.80 113	95.61 57	83.04 63	92.51 71	93.53 78

SR-MVS-dyc-post		85.77 48	85.61 51	86.23 56	93.06 55	70.63 73	91.88 39	92.27 76	73.53 136	85.69 47	94.45 26	65.00 121	95.56 58	82.75 66	91.87 79	92.50 114

RE-MVS-def			85.48 52		93.06 55	70.63 73	91.88 39	92.27 76	73.53 136	85.69 47	94.45 26	63.87 127		82.75 66	91.87 79	92.50 114

APD-MVS		87.44 22	87.52 22	87.19 42	94.24 32	72.39 39	91.86 41	92.83 55	73.01 149	88.58 21	94.52 21	73.36 34	96.49 36	84.26 50	95.01 37	92.70 105
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		88.06 14	88.50 13	86.71 51	92.60 66	72.71 29	91.81 42	93.19 35	77.87 36	90.32 17	94.00 46	74.83 23	93.78 136	87.63 28	94.27 57	93.65 69
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
DPE-MVS		89.48 5	89.98 4	88.01 16	94.80 11	72.69 31	91.59 43	94.10 8	75.90 85	92.29 7	95.66 10	81.67 6	97.38 10	87.44 31	96.34 15	93.95 52
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
QAPM		80.88 123	79.50 139	85.03 81	88.01 179	68.97 103	91.59 43	92.00 87	66.63 257	75.15 233	92.16 86	57.70 200	95.45 63	63.52 238	88.76 119	90.66 172

IS-MVSNet		83.15 85	82.81 85	84.18 115	89.94 109	63.30 230	91.59 43	88.46 204	79.04 25	79.49 131	92.16 86	65.10 118	94.28 112	67.71 207	91.86 81	94.95 10

9.14			88.26 14		92.84 60		91.52 46	94.75 1	73.93 125	88.57 22	94.67 19	75.57 22	95.79 53	86.77 33	95.76 23

TSAR-MVS + MP.		88.02 17	88.11 15	87.72 30	93.68 43	72.13 46	91.41 47	92.35 74	74.62 111	88.90 20	93.85 52	75.75 20	96.00 49	87.80 26	94.63 47	95.04 7
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
mvsmamba		81.69 108	80.74 114	84.56 97	87.45 199	66.72 157	91.26 48	85.89 249	74.66 109	78.23 157	90.56 125	54.33 225	94.91 88	80.73 86	83.54 189	92.04 132

DeepC-MVS_fast	79.65 3	86.91 32	86.62 35	87.76 27	93.52 46	72.37 41	91.26 48	93.04 38	76.62 70	84.22 72	93.36 61	71.44 53	96.76 25	80.82 83	95.33 34	94.16 43
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 74	83.14 78	85.14 77	90.08 102	68.71 111	91.25 50	92.44 69	79.12 23	78.92 139	91.00 118	60.42 184	95.38 69	78.71 100	86.32 149	91.33 147

plane_prior2							91.25 50		79.12 23

NCCC		88.06 14	88.01 18	88.24 11	94.41 22	73.62 11	91.22 52	92.83 55	81.50 5	85.79 46	93.47 59	73.02 39	97.00 18	84.90 40	94.94 39	94.10 45

API-MVS		81.99 102	81.23 106	84.26 113	90.94 85	70.18 82	91.10 53	89.32 169	71.51 169	78.66 145	88.28 184	65.26 116	95.10 83	64.74 234	91.23 88	87.51 270

RRT_MVS		80.35 143	79.22 148	83.74 138	87.63 193	65.46 183	91.08 54	88.92 191	73.82 127	76.44 201	90.03 134	49.05 288	94.25 117	76.84 119	79.20 244	91.51 141

EPNet		83.72 72	82.92 84	86.14 59	84.22 257	69.48 91	91.05 55	85.27 255	81.30 6	76.83 188	91.65 95	66.09 108	95.56 58	76.00 130	93.85 60	93.38 81
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		88.05 16	88.08 16	87.94 19	93.70 41	73.05 22	90.86 56	93.59 23	76.27 79	88.14 24	95.09 15	71.06 56	96.67 29	87.67 27	96.37 14	94.09 46

CSCG		86.41 40	86.19 41	87.07 45	92.91 58	72.48 37	90.81 57	93.56 24	73.95 123	83.16 89	91.07 114	75.94 18	95.19 75	79.94 92	94.38 54	93.55 76

MSLP-MVS++		85.43 55	85.76 49	84.45 103	91.93 72	70.24 76	90.71 58	92.86 53	77.46 47	84.22 72	92.81 76	67.16 97	92.94 180	80.36 88	94.35 55	90.16 191

3Dnovator	76.31 5	83.38 82	82.31 92	86.59 52	87.94 180	72.94 28	90.64 59	92.14 84	77.21 52	75.47 218	92.83 74	58.56 193	94.72 99	73.24 157	92.71 69	92.13 128

OpenMVS	72.83 10	79.77 153	78.33 168	84.09 120	85.17 237	69.91 84	90.57 60	90.97 121	66.70 251	72.17 267	91.91 89	54.70 222	93.96 124	61.81 258	90.95 91	88.41 255

CNVR-MVS		88.93 9	89.13 9	88.33 8	94.77 12	73.82 8	90.51 61	93.00 43	80.90 7	88.06 26	94.06 42	76.43 16	96.84 21	88.48 23	95.99 18	94.34 37

MVSFormer		82.85 91	82.05 96	85.24 75	87.35 200	70.21 77	90.50 62	90.38 137	68.55 234	81.32 110	89.47 149	61.68 157	93.46 153	78.98 97	90.26 100	92.05 130

test_djsdf		80.30 144	79.32 144	83.27 151	83.98 263	65.37 187	90.50 62	90.38 137	68.55 234	76.19 206	88.70 170	56.44 211	93.46 153	78.98 97	80.14 232	90.97 162

save fliter					93.80 40	72.35 42	90.47 64	91.17 116	74.31 116

nrg030		83.88 68	83.53 72	84.96 84	86.77 216	69.28 98	90.46 65	92.67 61	74.79 106	82.95 90	91.33 106	72.70 41	93.09 174	80.79 85	79.28 242	92.50 114

canonicalmvs		85.91 46	85.87 48	86.04 60	89.84 111	69.44 95	90.45 66	93.00 43	76.70 69	88.01 27	91.23 107	73.28 36	93.91 131	81.50 77	88.80 118	94.77 22

plane_prior						68.71 111	90.38 67		77.62 39						86.16 153

DeepC-MVS	79.81 2	87.08 31	86.88 33	87.69 33	91.16 80	72.32 43	90.31 68	93.94 14	77.12 55	82.82 94	94.23 35	72.13 45	97.09 16	84.83 43	95.37 32	93.65 69
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 79	82.80 86	85.43 71	90.25 98	68.74 109	90.30 69	90.13 148	76.33 78	80.87 118	92.89 72	61.00 174	94.20 118	72.45 166	90.97 90	93.35 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PGM-MVS		86.68 35	86.27 39	87.90 22	94.22 33	73.38 18	90.22 70	93.04 38	75.53 91	83.86 79	94.42 29	67.87 90	96.64 31	82.70 70	94.57 49	93.66 65

LPG-MVS_test		82.08 99	81.27 105	84.50 99	89.23 134	68.76 107	90.22 70	91.94 91	75.37 94	76.64 194	91.51 100	54.29 226	94.91 88	78.44 102	83.78 179	89.83 212

Anonymous20231211		78.97 176	77.69 187	82.81 174	90.54 93	64.29 209	90.11 72	91.51 107	65.01 275	76.16 210	88.13 193	50.56 267	93.03 179	69.68 190	77.56 259	91.11 154

ACMM	73.20 8	80.78 131	79.84 132	83.58 141	89.31 130	68.37 119	89.99 73	91.60 104	70.28 193	77.25 178	89.66 142	53.37 235	93.53 149	74.24 146	82.85 198	88.85 243
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	74.13 6	81.51 115	80.57 117	84.36 106	89.42 122	68.69 114	89.97 74	91.50 110	74.46 114	75.04 237	90.41 128	53.82 231	94.54 104	77.56 111	82.91 197	89.86 211
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
iter_conf_final		80.63 133	79.35 143	84.46 102	89.36 126	67.70 135	89.85 75	84.49 265	73.19 145	78.30 155	88.94 163	45.98 309	94.56 102	79.59 94	84.48 172	91.11 154

LFMVS		81.82 105	81.23 106	83.57 142	91.89 73	63.43 228	89.84 76	81.85 305	77.04 58	83.21 87	93.10 65	52.26 243	93.43 155	71.98 167	89.95 107	93.85 57

MCST-MVS		87.37 26	87.25 25	87.73 28	94.53 17	72.46 38	89.82 77	93.82 16	73.07 147	84.86 60	92.89 72	76.22 17	96.33 38	84.89 42	95.13 36	94.40 34

MAR-MVS		81.84 104	80.70 115	85.27 74	91.32 79	71.53 54	89.82 77	90.92 122	69.77 206	78.50 149	86.21 243	62.36 148	94.52 106	65.36 228	92.05 77	89.77 215
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 20	87.72 20	87.54 36	93.64 44	72.04 48	89.80 79	93.50 25	75.17 100	86.34 42	95.29 12	70.86 57	96.00 49	88.78 18	96.04 16	94.58 27
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
UA-Net		85.08 61	84.96 61	85.45 70	92.07 70	68.07 127	89.78 80	90.86 126	82.48 3	84.60 66	93.20 64	69.35 73	95.22 74	71.39 172	90.88 92	93.07 95

alignmvs		85.48 53	85.32 56	85.96 62	89.51 119	69.47 92	89.74 81	92.47 68	76.17 80	87.73 32	91.46 103	70.32 63	93.78 136	81.51 76	88.95 115	94.63 26

VDDNet		81.52 113	80.67 116	84.05 126	90.44 95	64.13 212	89.73 82	85.91 248	71.11 175	83.18 88	93.48 57	50.54 268	93.49 150	73.40 154	88.25 126	94.54 30

CANet		86.45 37	86.10 44	87.51 37	90.09 101	70.94 67	89.70 83	92.59 66	81.78 4	81.32 110	91.43 104	70.34 62	97.23 13	84.26 50	93.36 64	94.37 35

test_fmvsmconf0.1_n		85.61 52	85.65 50	85.50 69	82.99 288	69.39 96	89.65 84	90.29 144	73.31 141	87.77 29	94.15 38	71.72 48	93.23 161	90.31 4	90.67 95	93.89 56

114514_t		80.68 132	79.51 138	84.20 114	94.09 38	67.27 147	89.64 85	91.11 119	58.75 335	74.08 248	90.72 122	58.10 196	95.04 85	69.70 189	89.42 113	90.30 187

test_fmvsmconf_n		85.92 45	86.04 46	85.57 68	85.03 244	69.51 90	89.62 86	90.58 131	73.42 138	87.75 30	94.02 44	72.85 40	93.24 160	90.37 3	90.75 93	93.96 51

DeepPCF-MVS	80.84 1	88.10 12	88.56 12	86.73 50	92.24 68	69.03 99	89.57 87	93.39 30	77.53 45	89.79 18	94.12 39	78.98 12	96.58 35	85.66 35	95.72 24	94.58 27

test_fmvsmconf0.01_n		84.73 65	84.52 66	85.34 72	80.25 328	69.03 99	89.47 88	89.65 161	73.24 144	86.98 38	94.27 32	66.62 99	93.23 161	90.26 5	89.95 107	93.78 62

fmvsm_s_conf0.5_n		83.80 70	83.71 71	84.07 122	86.69 218	67.31 145	89.46 89	83.07 290	71.09 176	86.96 39	93.70 55	69.02 81	91.47 231	88.79 17	84.62 168	93.44 80

fmvsm_s_conf0.5_n_a		83.63 75	83.41 74	84.28 111	86.14 224	68.12 125	89.43 90	82.87 294	70.27 194	87.27 35	93.80 54	69.09 76	91.58 222	88.21 24	83.65 185	93.14 93

UGNet		80.83 125	79.59 137	84.54 98	88.04 177	68.09 126	89.42 91	88.16 206	76.95 59	76.22 205	89.46 151	49.30 283	93.94 127	68.48 202	90.31 98	91.60 138
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		78.73 180	77.83 179	81.43 203	85.17 237	60.30 271	89.41 92	90.90 123	71.21 173	77.17 184	88.73 169	46.38 303	93.21 163	72.57 164	78.96 245	90.79 166

fmvsm_s_conf0.1_n		83.56 77	83.38 75	84.10 117	84.86 246	67.28 146	89.40 93	83.01 291	70.67 184	87.08 36	93.96 50	68.38 85	91.45 232	88.56 21	84.50 169	93.56 75

AdaColmap		80.58 137	79.42 140	84.06 124	93.09 54	68.91 104	89.36 94	88.97 188	69.27 215	75.70 215	89.69 141	57.20 207	95.77 54	63.06 243	88.41 125	87.50 271

fmvsm_s_conf0.1_n_a		83.32 83	82.99 82	84.28 111	83.79 266	68.07 127	89.34 95	82.85 295	69.80 204	87.36 34	94.06 42	68.34 86	91.56 224	87.95 25	83.46 191	93.21 90

PS-MVSNAJss		82.07 100	81.31 104	84.34 108	86.51 220	67.27 147	89.27 96	91.51 107	71.75 161	79.37 132	90.22 132	63.15 136	94.27 113	77.69 110	82.36 205	91.49 144

jajsoiax		79.29 167	77.96 174	83.27 151	84.68 249	66.57 160	89.25 97	90.16 147	69.20 219	75.46 220	89.49 148	45.75 314	93.13 172	76.84 119	80.80 222	90.11 195

mvs_tets		79.13 171	77.77 183	83.22 155	84.70 248	66.37 162	89.17 98	90.19 146	69.38 213	75.40 223	89.46 151	44.17 322	93.15 170	76.78 122	80.70 224	90.14 192

HQP-NCC					89.33 127		89.17 98		76.41 72	77.23 180

ACMP_Plane					89.33 127		89.17 98		76.41 72	77.23 180

HQP-MVS		82.61 94	82.02 97	84.37 105	89.33 127	66.98 153	89.17 98	92.19 82	76.41 72	77.23 180	90.23 131	60.17 187	95.11 80	77.47 112	85.99 156	91.03 159

LS3D		76.95 223	74.82 236	83.37 148	90.45 94	67.36 144	89.15 102	86.94 234	61.87 310	69.52 295	90.61 124	51.71 256	94.53 105	46.38 355	86.71 144	88.21 257

OPM-MVS		83.50 78	82.95 83	85.14 77	88.79 151	70.95 66	89.13 103	91.52 106	77.55 44	80.96 117	91.75 93	60.71 177	94.50 107	79.67 93	86.51 147	89.97 207
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
TSAR-MVS + GP.		85.71 50	85.33 55	86.84 47	91.34 78	72.50 36	89.07 104	87.28 228	76.41 72	85.80 45	90.22 132	74.15 31	95.37 72	81.82 75	91.88 78	92.65 109

test_prior4						72.60 34	89.01 105

GeoE		81.71 107	81.01 111	83.80 137	89.51 119	64.45 206	88.97 106	88.73 199	71.27 172	78.63 146	89.76 140	66.32 105	93.20 166	69.89 187	86.02 155	93.74 63

Anonymous20240529		80.19 147	78.89 155	84.10 117	90.60 91	64.75 199	88.95 107	90.90 123	65.97 265	80.59 120	91.17 111	49.97 273	93.73 142	69.16 195	82.70 202	93.81 60

VDD-MVS		83.01 90	82.36 91	84.96 84	91.02 83	66.40 161	88.91 108	88.11 207	77.57 41	84.39 70	93.29 62	52.19 244	93.91 131	77.05 117	88.70 120	94.57 29

Effi-MVS+		83.62 76	83.08 79	85.24 75	88.38 166	67.45 140	88.89 109	89.15 179	75.50 92	82.27 98	88.28 184	69.61 71	94.45 109	77.81 109	87.84 128	93.84 59

ACMH+	68.96 14	76.01 237	74.01 245	82.03 191	88.60 158	65.31 188	88.86 110	87.55 222	70.25 195	67.75 309	87.47 206	41.27 339	93.19 168	58.37 287	75.94 282	87.60 267

test_prior2							88.85 111		75.41 93	84.91 57	93.54 56	74.28 29		83.31 59	95.86 20

iter_conf05		80.00 151	78.70 157	83.91 135	87.84 183	65.83 173	88.84 112	84.92 260	71.61 166	78.70 142	88.94 163	43.88 324	94.56 102	79.28 95	84.28 175	91.33 147

DP-MVS Recon		83.11 88	82.09 95	86.15 58	94.44 19	70.92 68	88.79 113	92.20 81	70.53 188	79.17 135	91.03 117	64.12 125	96.03 46	68.39 204	90.14 102	91.50 143

Effi-MVS+-dtu		80.03 149	78.57 161	84.42 104	85.13 241	68.74 109	88.77 114	88.10 208	74.99 102	74.97 238	83.49 294	57.27 206	93.36 156	73.53 151	80.88 220	91.18 152

TEST9					93.26 50	72.96 25	88.75 115	91.89 93	68.44 237	85.00 55	93.10 65	74.36 28	95.41 67

train_agg		86.43 38	86.20 40	87.13 44	93.26 50	72.96 25	88.75 115	91.89 93	68.69 232	85.00 55	93.10 65	74.43 26	95.41 67	84.97 39	95.71 25	93.02 98

ETV-MVS		84.90 64	84.67 64	85.59 67	89.39 124	68.66 115	88.74 117	92.64 65	79.97 15	84.10 75	85.71 252	69.32 74	95.38 69	80.82 83	91.37 86	92.72 104

PVSNet_Blended_VisFu		82.62 93	81.83 101	84.96 84	90.80 89	69.76 87	88.74 117	91.70 102	69.39 212	78.96 137	88.46 179	65.47 115	94.87 94	74.42 143	88.57 121	90.24 189

casdiffmvs_mvg		85.99 43	86.09 45	85.70 66	87.65 192	67.22 149	88.69 119	93.04 38	79.64 18	85.33 50	92.54 81	73.30 35	94.50 107	83.49 57	91.14 89	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 52	72.57 35	88.68 120	91.84 97	68.69 232	84.87 59	93.10 65	74.43 26	95.16 76

test_fmvsm_n_1920		85.29 58	85.34 54	85.13 79	86.12 225	69.93 83	88.65 121	90.78 127	69.97 200	88.27 23	93.98 49	71.39 54	91.54 226	88.49 22	90.45 97	93.91 53

ACMH	67.68 16	75.89 238	73.93 246	81.77 196	88.71 155	66.61 159	88.62 122	89.01 185	69.81 203	66.78 321	86.70 228	41.95 338	91.51 229	55.64 308	78.14 254	87.17 278
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		85.76 49	85.29 58	87.17 43	93.49 47	71.08 61	88.58 123	92.42 72	68.32 239	84.61 65	93.48 57	72.32 42	96.15 45	79.00 96	95.43 31	94.28 40

DP-MVS		76.78 225	74.57 238	83.42 145	93.29 48	69.46 94	88.55 124	83.70 277	63.98 289	70.20 283	88.89 166	54.01 230	94.80 96	46.66 352	81.88 210	86.01 303

WR-MVS_H		78.51 186	78.49 162	78.56 263	88.02 178	56.38 318	88.43 125	92.67 61	77.14 54	73.89 249	87.55 203	66.25 106	89.24 272	58.92 281	73.55 315	90.06 201

F-COLMAP		76.38 233	74.33 243	82.50 184	89.28 132	66.95 156	88.41 126	89.03 183	64.05 287	66.83 320	88.61 174	46.78 301	92.89 181	57.48 294	78.55 247	87.67 265

GBi-Net		78.40 187	77.40 192	81.40 205	87.60 194	63.01 236	88.39 127	89.28 170	71.63 163	75.34 225	87.28 208	54.80 218	91.11 240	62.72 245	79.57 236	90.09 197

test1		78.40 187	77.40 192	81.40 205	87.60 194	63.01 236	88.39 127	89.28 170	71.63 163	75.34 225	87.28 208	54.80 218	91.11 240	62.72 245	79.57 236	90.09 197

FMVSNet1		77.44 213	76.12 219	81.40 205	86.81 215	63.01 236	88.39 127	89.28 170	70.49 189	74.39 245	87.28 208	49.06 287	91.11 240	60.91 265	78.52 248	90.09 197

tttt0517		79.40 164	77.91 176	83.90 136	88.10 174	63.84 216	88.37 130	84.05 273	71.45 170	76.78 190	89.12 159	49.93 276	94.89 92	70.18 183	83.18 195	92.96 101

v7n		78.97 176	77.58 190	83.14 158	83.45 273	65.51 180	88.32 131	91.21 114	73.69 130	72.41 264	86.32 242	57.93 197	93.81 135	69.18 194	75.65 285	90.11 195

COLMAP_ROB	66.92 17	73.01 268	70.41 280	80.81 223	87.13 210	65.63 178	88.30 132	84.19 272	62.96 297	63.80 346	87.69 198	38.04 352	92.56 189	46.66 352	74.91 302	84.24 326
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FIs		82.07 100	82.42 88	81.04 217	88.80 150	58.34 286	88.26 133	93.49 26	76.93 60	78.47 151	91.04 115	69.92 68	92.34 199	69.87 188	84.97 163	92.44 118

EIA-MVS		83.31 84	82.80 86	84.82 90	89.59 115	65.59 179	88.21 134	92.68 60	74.66 109	78.96 137	86.42 239	69.06 78	95.26 73	75.54 136	90.09 103	93.62 72

PLC	70.83 11	78.05 198	76.37 217	83.08 161	91.88 74	67.80 132	88.19 135	89.46 165	64.33 283	69.87 292	88.38 181	53.66 232	93.58 144	58.86 282	82.73 200	87.86 262
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MG-MVS		83.41 80	83.45 73	83.28 150	92.74 62	62.28 246	88.17 136	89.50 164	75.22 96	81.49 109	92.74 80	66.75 98	95.11 80	72.85 160	91.58 83	92.45 117

TAPA-MVS	73.13 9	79.15 170	77.94 175	82.79 177	89.59 115	62.99 239	88.16 137	91.51 107	65.77 266	77.14 185	91.09 113	60.91 175	93.21 163	50.26 335	87.05 138	92.17 127
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvsmvis_n_1920		84.02 67	83.87 69	84.49 101	84.12 259	69.37 97	88.15 138	87.96 212	70.01 198	83.95 78	93.23 63	68.80 83	91.51 229	88.61 19	89.96 106	92.57 110

h-mvs33		83.15 85	82.19 93	86.02 61	90.56 92	70.85 70	88.15 138	89.16 178	76.02 83	84.67 62	91.39 105	61.54 160	95.50 61	82.71 68	75.48 289	91.72 137

bld_raw_dy_0_64		77.29 218	75.98 220	81.22 211	85.04 243	65.47 182	88.14 140	77.56 338	69.20 219	73.77 250	89.40 157	42.24 335	88.85 282	76.78 122	81.64 212	89.33 225

PS-CasMVS		78.01 200	78.09 172	77.77 275	87.71 189	54.39 338	88.02 141	91.22 113	77.50 46	73.26 254	88.64 173	60.73 176	88.41 287	61.88 256	73.88 312	90.53 178

OMC-MVS		82.69 92	81.97 99	84.85 89	88.75 153	67.42 141	87.98 142	90.87 125	74.92 103	79.72 128	91.65 95	62.19 152	93.96 124	75.26 138	86.42 148	93.16 92

v8		79.97 152	79.02 153	82.80 175	84.09 260	64.50 204	87.96 143	90.29 144	74.13 122	75.24 231	86.81 221	62.88 141	93.89 133	74.39 144	75.40 294	90.00 203

FC-MVSNet-test		81.52 113	82.02 97	80.03 238	88.42 165	55.97 323	87.95 144	93.42 29	77.10 56	77.38 175	90.98 120	69.96 66	91.79 217	68.46 203	84.50 169	92.33 119

CP-MVSNet		78.22 191	78.34 167	77.84 273	87.83 184	54.54 336	87.94 145	91.17 116	77.65 38	73.48 252	88.49 178	62.24 151	88.43 286	62.19 252	74.07 308	90.55 177

PAPM_NR		83.02 89	82.41 89	84.82 90	92.47 67	66.37 162	87.93 146	91.80 98	73.82 127	77.32 177	90.66 123	67.90 89	94.90 91	70.37 181	89.48 112	93.19 91

PEN-MVS		77.73 206	77.69 187	77.84 273	87.07 211	53.91 341	87.91 147	91.18 115	77.56 43	73.14 256	88.82 168	61.23 169	89.17 273	59.95 271	72.37 323	90.43 181

ECVR-MVS		79.61 155	79.26 146	80.67 226	90.08 102	54.69 334	87.89 148	77.44 341	74.88 104	80.27 122	92.79 77	48.96 290	92.45 192	68.55 201	92.50 72	94.86 17

v10		79.74 154	78.67 158	82.97 168	84.06 261	64.95 194	87.88 149	90.62 130	73.11 146	75.11 234	86.56 235	61.46 163	94.05 123	73.68 149	75.55 287	89.90 209

test2506		77.30 217	76.49 213	79.74 244	90.08 102	52.02 350	87.86 150	63.10 382	74.88 104	80.16 125	92.79 77	38.29 351	92.35 198	68.74 200	92.50 72	94.86 17

casdiffmvs		85.11 60	85.14 59	85.01 82	87.20 208	65.77 177	87.75 151	92.83 55	77.84 37	84.36 71	92.38 83	72.15 44	93.93 130	81.27 79	90.48 96	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		80.84 124	80.31 123	82.42 185	87.85 182	62.33 244	87.74 152	91.33 112	80.55 9	77.99 165	89.86 137	65.23 117	92.62 186	67.05 216	75.24 299	92.30 121

EI-MVSNet-Vis-set		84.19 66	83.81 70	85.31 73	88.18 171	67.85 131	87.66 153	89.73 159	80.05 14	82.95 90	89.59 146	70.74 59	94.82 95	80.66 87	84.72 166	93.28 86

UniMVSNet (Re)		81.60 112	81.11 108	83.09 160	88.38 166	64.41 207	87.60 154	93.02 42	78.42 32	78.56 148	88.16 188	69.78 69	93.26 159	69.58 191	76.49 271	91.60 138

CNLPA		78.08 196	76.79 206	81.97 193	90.40 96	71.07 62	87.59 155	84.55 264	66.03 264	72.38 265	89.64 143	57.56 202	86.04 305	59.61 274	83.35 192	88.79 246

DTE-MVSNet		76.99 221	76.80 205	77.54 280	86.24 222	53.06 349	87.52 156	90.66 129	77.08 57	72.50 262	88.67 172	60.48 183	89.52 267	57.33 297	70.74 334	90.05 202

无先验							87.48 157	88.98 186	60.00 322				94.12 121	67.28 212		88.97 238

FMVSNet2		78.20 193	77.21 196	81.20 212	87.60 194	62.89 240	87.47 158	89.02 184	71.63 163	75.29 230	87.28 208	54.80 218	91.10 243	62.38 250	79.38 240	89.61 219

EI-MVSNet-UG-set		83.81 69	83.38 75	85.09 80	87.87 181	67.53 139	87.44 159	89.66 160	79.74 16	82.23 99	89.41 155	70.24 64	94.74 98	79.95 91	83.92 178	92.99 100

thisisatest0530		79.40 164	77.76 184	84.31 109	87.69 191	65.10 192	87.36 160	84.26 271	70.04 197	77.42 174	88.26 186	49.94 274	94.79 97	70.20 182	84.70 167	93.03 97

CANet_DTU		80.61 134	79.87 131	82.83 172	85.60 232	63.17 235	87.36 160	88.65 200	76.37 76	75.88 212	88.44 180	53.51 234	93.07 175	73.30 155	89.74 110	92.25 123

test1111		79.43 162	79.18 150	80.15 236	89.99 107	53.31 347	87.33 162	77.05 344	75.04 101	80.23 124	92.77 79	48.97 289	92.33 200	68.87 198	92.40 74	94.81 20

baseline		84.93 62	84.98 60	84.80 92	87.30 206	65.39 186	87.30 163	92.88 52	77.62 39	84.04 77	92.26 85	71.81 46	93.96 124	81.31 78	90.30 99	95.03 8

UniMVSNet_ETH3D		79.10 172	78.24 170	81.70 197	86.85 213	60.24 272	87.28 164	88.79 193	74.25 118	76.84 187	90.53 127	49.48 279	91.56 224	67.98 205	82.15 206	93.29 85

anonymousdsp		78.60 184	77.15 197	82.98 167	80.51 326	67.08 151	87.24 165	89.53 163	65.66 268	75.16 232	87.19 214	52.52 238	92.25 202	77.17 116	79.34 241	89.61 219

UniMVSNet_NR-MVSNet		81.88 103	81.54 103	82.92 169	88.46 163	63.46 226	87.13 166	92.37 73	80.19 12	78.38 152	89.14 158	71.66 51	93.05 176	70.05 184	76.46 272	92.25 123

DPM-MVS		84.93 62	84.29 68	86.84 47	90.20 99	73.04 23	87.12 167	93.04 38	69.80 204	82.85 93	91.22 108	73.06 38	96.02 47	76.72 124	94.63 47	91.46 146

v1144		80.03 149	79.03 152	83.01 165	83.78 267	64.51 202	87.11 168	90.57 133	71.96 160	78.08 163	86.20 244	61.41 164	93.94 127	74.93 139	77.23 260	90.60 175

v2v482		80.23 145	79.29 145	83.05 163	83.62 269	64.14 211	87.04 169	89.97 152	73.61 132	78.18 160	87.22 212	61.10 172	93.82 134	76.11 127	76.78 269	91.18 152

DU-MVS		81.12 120	80.52 119	82.90 170	87.80 185	63.46 226	87.02 170	91.87 95	79.01 26	78.38 152	89.07 160	65.02 119	93.05 176	70.05 184	76.46 272	92.20 125

v144192		79.47 160	78.37 166	82.78 178	83.35 274	63.96 214	86.96 171	90.36 140	69.99 199	77.50 172	85.67 255	60.66 179	93.77 138	74.27 145	76.58 270	90.62 173

Fast-Effi-MVS+-dtu		78.02 199	76.49 213	82.62 182	83.16 282	66.96 155	86.94 172	87.45 226	72.45 152	71.49 274	84.17 283	54.79 221	91.58 222	67.61 208	80.31 229	89.30 226

v1192		79.59 157	78.43 165	83.07 162	83.55 271	64.52 201	86.93 173	90.58 131	70.83 180	77.78 168	85.90 248	59.15 190	93.94 127	73.96 148	77.19 262	90.76 168

EPNet_dtu		75.46 244	74.86 235	77.23 284	82.57 297	54.60 335	86.89 174	83.09 289	71.64 162	66.25 330	85.86 250	55.99 212	88.04 291	54.92 310	86.55 146	89.05 233
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM2							86.86 175

VPA-MVSNet		80.60 135	80.55 118	80.76 224	88.07 176	60.80 263	86.86 175	91.58 105	75.67 90	80.24 123	89.45 153	63.34 130	90.25 257	70.51 180	79.22 243	91.23 151

v1921920		79.22 168	78.03 173	82.80 175	83.30 276	63.94 215	86.80 177	90.33 141	69.91 202	77.48 173	85.53 258	58.44 194	93.75 140	73.60 150	76.85 267	90.71 171

IterMVS-LS		80.06 148	79.38 141	82.11 189	85.89 227	63.20 233	86.79 178	89.34 168	74.19 119	75.45 221	86.72 224	66.62 99	92.39 195	72.58 163	76.86 266	90.75 169
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		75.39 247	74.56 239	77.86 272	85.50 234	57.10 306	86.78 179	86.09 247	72.17 158	71.53 273	87.34 207	63.01 140	89.31 271	56.84 302	61.83 360	87.17 278

Baseline_NR-MVSNet		78.15 195	78.33 168	77.61 278	85.79 228	56.21 321	86.78 179	85.76 251	73.60 133	77.93 166	87.57 201	65.02 119	88.99 276	67.14 215	75.33 296	87.63 266

PAPR		81.66 111	80.89 113	83.99 131	90.27 97	64.00 213	86.76 181	91.77 101	68.84 230	77.13 186	89.50 147	67.63 91	94.88 93	67.55 209	88.52 123	93.09 94

Vis-MVSNet (Re-imp)		78.36 189	78.45 163	78.07 271	88.64 157	51.78 354	86.70 182	79.63 327	74.14 121	75.11 234	90.83 121	61.29 168	89.75 263	58.10 290	91.60 82	92.69 107

pmmvs6		74.69 250	73.39 252	78.61 261	81.38 315	57.48 301	86.64 183	87.95 213	64.99 276	70.18 284	86.61 231	50.43 269	89.52 267	62.12 254	70.18 336	88.83 244

v1240		78.99 175	77.78 182	82.64 181	83.21 278	63.54 223	86.62 184	90.30 143	69.74 209	77.33 176	85.68 254	57.04 208	93.76 139	73.13 158	76.92 264	90.62 173

MTAPA		87.23 27	87.00 28	87.90 22	94.18 35	74.25 5	86.58 185	92.02 85	79.45 19	85.88 44	94.80 17	68.07 87	96.21 42	86.69 34	95.34 33	93.23 87

旧先验2							86.56 186		58.10 339	87.04 37			88.98 277	74.07 147

FMVSNet3		77.88 203	76.85 204	80.97 220	86.84 214	62.36 243	86.52 187	88.77 194	71.13 174	75.34 225	86.66 230	54.07 229	91.10 243	62.72 245	79.57 236	89.45 222

dcpmvs_2		85.63 51	86.15 43	84.06 124	91.71 75	64.94 195	86.47 188	91.87 95	73.63 131	86.60 41	93.02 70	76.57 15	91.87 216	83.36 58	92.15 75	95.35 3

pm-mvs1		77.25 219	76.68 211	78.93 257	84.22 257	58.62 284	86.41 189	88.36 205	71.37 171	73.31 253	88.01 194	61.22 170	89.15 274	64.24 236	73.01 320	89.03 234

EI-MVSNet		80.52 138	79.98 128	82.12 188	84.28 255	63.19 234	86.41 189	88.95 189	74.18 120	78.69 143	87.54 204	66.62 99	92.43 193	72.57 164	80.57 226	90.74 170

CVMVSNet		72.99 269	72.58 259	74.25 310	84.28 255	50.85 360	86.41 189	83.45 283	44.56 372	73.23 255	87.54 204	49.38 281	85.70 307	65.90 224	78.44 250	86.19 298

NR-MVSNet		80.23 145	79.38 141	82.78 178	87.80 185	63.34 229	86.31 192	91.09 120	79.01 26	72.17 267	89.07 160	67.20 96	92.81 185	66.08 223	75.65 285	92.20 125

v148		78.72 181	77.80 181	81.47 202	82.73 293	61.96 250	86.30 193	88.08 209	73.26 142	76.18 207	85.47 260	62.46 146	92.36 197	71.92 168	73.82 313	90.09 197

新几何2							86.29 194

test_yl		81.17 118	80.47 120	83.24 153	89.13 138	63.62 219	86.21 195	89.95 153	72.43 155	81.78 106	89.61 144	57.50 203	93.58 144	70.75 176	86.90 140	92.52 112

DCV-MVSNet		81.17 118	80.47 120	83.24 153	89.13 138	63.62 219	86.21 195	89.95 153	72.43 155	81.78 106	89.61 144	57.50 203	93.58 144	70.75 176	86.90 140	92.52 112

PVSNet_BlendedMVS		80.60 135	80.02 127	82.36 187	88.85 145	65.40 184	86.16 197	92.00 87	69.34 214	78.11 161	86.09 247	66.02 110	94.27 113	71.52 169	82.06 207	87.39 272

MVS_Test		83.15 85	83.06 80	83.41 147	86.86 212	63.21 232	86.11 198	92.00 87	74.31 116	82.87 92	89.44 154	70.03 65	93.21 163	77.39 114	88.50 124	93.81 60

BH-untuned		79.47 160	78.60 160	82.05 190	89.19 136	65.91 171	86.07 199	88.52 203	72.18 157	75.42 222	87.69 198	61.15 171	93.54 148	60.38 268	86.83 142	86.70 291

MVS_111021_HR		85.14 59	84.75 63	86.32 55	91.65 76	72.70 30	85.98 200	90.33 141	76.11 81	82.08 100	91.61 98	71.36 55	94.17 120	81.02 80	92.58 70	92.08 129

jason		81.39 116	80.29 124	84.70 94	86.63 219	69.90 85	85.95 201	86.77 236	63.24 292	81.07 116	89.47 149	61.08 173	92.15 205	78.33 105	90.07 105	92.05 130
jason: jason.
test_0402		72.79 271	70.44 279	79.84 242	88.13 172	65.99 169	85.93 202	84.29 269	65.57 269	67.40 315	85.49 259	46.92 300	92.61 187	35.88 376	74.38 307	80.94 355

OurMVSNet-221017-0		74.26 253	72.42 261	79.80 243	83.76 268	59.59 279	85.92 203	86.64 237	66.39 259	66.96 318	87.58 200	39.46 345	91.60 221	65.76 226	69.27 339	88.22 256

hse-mvs2		81.72 106	80.94 112	84.07 122	88.72 154	67.68 136	85.87 204	87.26 229	76.02 83	84.67 62	88.22 187	61.54 160	93.48 151	82.71 68	73.44 317	91.06 157

EG-PatchMatch MVS		74.04 256	71.82 265	80.71 225	84.92 245	67.42 141	85.86 205	88.08 209	66.04 263	64.22 342	83.85 287	35.10 360	92.56 189	57.44 295	80.83 221	82.16 349

AUN-MVS		79.21 169	77.60 189	84.05 126	88.71 155	67.61 137	85.84 206	87.26 229	69.08 223	77.23 180	88.14 192	53.20 237	93.47 152	75.50 137	73.45 316	91.06 157

thres100view900		76.50 228	75.55 226	79.33 252	89.52 118	56.99 307	85.83 207	83.23 286	73.94 124	76.32 203	87.12 216	51.89 253	91.95 211	48.33 343	83.75 181	89.07 228

CLD-MVS		82.31 96	81.65 102	84.29 110	88.47 162	67.73 134	85.81 208	92.35 74	75.78 86	78.33 154	86.58 234	64.01 126	94.35 110	76.05 129	87.48 133	90.79 166
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
SixPastTwentyTwo		73.37 262	71.26 272	79.70 245	85.08 242	57.89 294	85.57 209	83.56 280	71.03 178	65.66 332	85.88 249	42.10 336	92.57 188	59.11 279	63.34 358	88.65 250

xiu_mvs_v1_base_debu		80.80 128	79.72 134	84.03 128	87.35 200	70.19 79	85.56 210	88.77 194	69.06 224	81.83 102	88.16 188	50.91 262	92.85 182	78.29 106	87.56 130	89.06 230

xiu_mvs_v1_base		80.80 128	79.72 134	84.03 128	87.35 200	70.19 79	85.56 210	88.77 194	69.06 224	81.83 102	88.16 188	50.91 262	92.85 182	78.29 106	87.56 130	89.06 230

xiu_mvs_v1_base_debi		80.80 128	79.72 134	84.03 128	87.35 200	70.19 79	85.56 210	88.77 194	69.06 224	81.83 102	88.16 188	50.91 262	92.85 182	78.29 106	87.56 130	89.06 230

V42		79.38 166	78.24 170	82.83 172	81.10 320	65.50 181	85.55 213	89.82 155	71.57 168	78.21 158	86.12 246	60.66 179	93.18 169	75.64 133	75.46 291	89.81 214

lupinMVS		81.39 116	80.27 125	84.76 93	87.35 200	70.21 77	85.55 213	86.41 240	62.85 299	81.32 110	88.61 174	61.68 157	92.24 203	78.41 104	90.26 100	91.83 134

Fast-Effi-MVS+		80.81 126	79.92 129	83.47 143	88.85 145	64.51 202	85.53 215	89.39 167	70.79 181	78.49 150	85.06 270	67.54 92	93.58 144	67.03 217	86.58 145	92.32 120

thres600view7		76.50 228	75.44 227	79.68 246	89.40 123	57.16 304	85.53 215	83.23 286	73.79 129	76.26 204	87.09 217	51.89 253	91.89 214	48.05 348	83.72 184	90.00 203

DELS-MVS		85.41 56	85.30 57	85.77 64	88.49 161	67.93 130	85.52 217	93.44 27	78.70 29	83.63 85	89.03 162	74.57 24	95.71 56	80.26 90	94.04 59	93.66 65
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
tfpn200view9		76.42 231	75.37 231	79.55 251	89.13 138	57.65 298	85.17 218	83.60 278	73.41 139	76.45 198	86.39 240	52.12 245	91.95 211	48.33 343	83.75 181	89.07 228

thres400		76.50 228	75.37 231	79.86 241	89.13 138	57.65 298	85.17 218	83.60 278	73.41 139	76.45 198	86.39 240	52.12 245	91.95 211	48.33 343	83.75 181	90.00 203

MVS_111021_LR		82.61 94	82.11 94	84.11 116	88.82 148	71.58 53	85.15 220	86.16 245	74.69 108	80.47 121	91.04 115	62.29 149	90.55 254	80.33 89	90.08 104	90.20 190

baseline1		76.98 222	76.75 209	77.66 276	88.13 172	55.66 326	85.12 221	81.89 303	73.04 148	76.79 189	88.90 165	62.43 147	87.78 294	63.30 242	71.18 332	89.55 221

WR-MVS		79.49 159	79.22 148	80.27 234	88.79 151	58.35 285	85.06 222	88.61 202	78.56 30	77.65 170	88.34 182	63.81 129	90.66 253	64.98 232	77.22 261	91.80 136

ET-MVSNet_ETH3D		78.63 183	76.63 212	84.64 95	86.73 217	69.47 92	85.01 223	84.61 263	69.54 210	66.51 328	86.59 232	50.16 271	91.75 218	76.26 126	84.24 176	92.69 107

OpenMVS_ROB	64.09 19	70.56 288	68.19 294	77.65 277	80.26 327	59.41 281	85.01 223	82.96 293	58.76 334	65.43 334	82.33 308	37.63 354	91.23 239	45.34 360	76.03 281	82.32 346

BH-RMVSNet		79.61 155	78.44 164	83.14 158	89.38 125	65.93 170	84.95 225	87.15 231	73.56 134	78.19 159	89.79 139	56.67 210	93.36 156	59.53 275	86.74 143	90.13 193

BH-w/o		78.21 192	77.33 195	80.84 222	88.81 149	65.13 191	84.87 226	87.85 217	69.75 207	74.52 244	84.74 275	61.34 166	93.11 173	58.24 289	85.84 158	84.27 325

TDRefinement		67.49 311	64.34 321	76.92 286	73.47 369	61.07 259	84.86 227	82.98 292	59.77 324	58.30 364	85.13 268	26.06 374	87.89 292	47.92 349	60.59 365	81.81 351

Anonymous202405211		78.25 190	77.01 199	81.99 192	91.03 82	60.67 265	84.77 228	83.90 275	70.65 187	80.00 126	91.20 109	41.08 341	91.43 233	65.21 229	85.26 161	93.85 57

TAMVS		78.89 178	77.51 191	83.03 164	87.80 185	67.79 133	84.72 229	85.05 258	67.63 243	76.75 191	87.70 197	62.25 150	90.82 249	58.53 286	87.13 137	90.49 179

1314		76.53 227	75.30 233	80.21 235	83.93 264	62.32 245	84.66 230	88.81 192	60.23 320	70.16 286	84.07 285	55.30 215	90.73 252	67.37 211	83.21 194	87.59 269

MVS		78.19 194	76.99 201	81.78 195	85.66 230	66.99 152	84.66 230	90.47 135	55.08 355	72.02 269	85.27 263	63.83 128	94.11 122	66.10 222	89.80 109	84.24 326

tfpnnormal		74.39 251	73.16 255	78.08 270	86.10 226	58.05 289	84.65 232	87.53 223	70.32 192	71.22 276	85.63 256	54.97 216	89.86 261	43.03 364	75.02 301	86.32 295

TR-MVS		77.44 213	76.18 218	81.20 212	88.24 170	63.24 231	84.61 233	86.40 241	67.55 245	77.81 167	86.48 238	54.10 228	93.15 170	57.75 293	82.72 201	87.20 277

AllTest		70.96 282	68.09 297	79.58 249	85.15 239	63.62 219	84.58 234	79.83 324	62.31 306	60.32 357	86.73 222	32.02 364	88.96 279	50.28 333	71.57 330	86.15 299

FA-MVS(test-final)		80.96 122	79.91 130	84.10 117	88.30 169	65.01 193	84.55 235	90.01 151	73.25 143	79.61 129	87.57 201	58.35 195	94.72 99	71.29 173	86.25 151	92.56 111

EU-MVSNet		68.53 306	67.61 307	71.31 332	78.51 347	47.01 370	84.47 236	84.27 270	42.27 375	66.44 329	84.79 274	40.44 343	83.76 322	58.76 284	68.54 344	83.17 337

VNet		82.21 97	82.41 89	81.62 198	90.82 88	60.93 260	84.47 236	89.78 156	76.36 77	84.07 76	91.88 91	64.71 122	90.26 256	70.68 178	88.89 116	93.66 65

xiu_mvs_v2_base		81.69 108	81.05 109	83.60 140	89.15 137	68.03 129	84.46 238	90.02 150	70.67 184	81.30 113	86.53 237	63.17 135	94.19 119	75.60 135	88.54 122	88.57 252

VPNet		78.69 182	78.66 159	78.76 259	88.31 168	55.72 325	84.45 239	86.63 238	76.79 64	78.26 156	90.55 126	59.30 189	89.70 265	66.63 218	77.05 263	90.88 164

PVSNet_Blended		80.98 121	80.34 122	82.90 170	88.85 145	65.40 184	84.43 240	92.00 87	67.62 244	78.11 161	85.05 271	66.02 110	94.27 113	71.52 169	89.50 111	89.01 235

MVP-Stereo		76.12 235	74.46 242	81.13 215	85.37 235	69.79 86	84.42 241	87.95 213	65.03 274	67.46 313	85.33 262	53.28 236	91.73 220	58.01 291	83.27 193	81.85 350
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		79.07 173	77.70 186	83.17 157	87.60 194	68.23 123	84.40 242	86.20 244	67.49 246	76.36 202	86.54 236	61.54 160	90.79 250	61.86 257	87.33 134	90.49 179
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
K. test v3		71.19 279	68.51 291	79.21 255	83.04 285	57.78 297	84.35 243	76.91 345	72.90 151	62.99 349	82.86 302	39.27 346	91.09 245	61.65 259	52.66 376	88.75 247

PS-MVSNAJ		81.69 108	81.02 110	83.70 139	89.51 119	68.21 124	84.28 244	90.09 149	70.79 181	81.26 114	85.62 257	63.15 136	94.29 111	75.62 134	88.87 117	88.59 251

patch_mono-2		83.65 73	84.54 65	80.99 218	90.06 106	65.83 173	84.21 245	88.74 198	71.60 167	85.01 53	92.44 82	74.51 25	83.50 325	82.15 73	92.15 75	93.64 71

test222					91.50 77	68.26 122	84.16 246	83.20 288	54.63 356	79.74 127	91.63 97	58.97 191			91.42 85	86.77 289

testdata1							84.14 247		75.71 87

c3_l		78.75 179	77.91 176	81.26 209	82.89 290	61.56 255	84.09 248	89.13 181	69.97 200	75.56 216	84.29 282	66.36 104	92.09 207	73.47 153	75.48 289	90.12 194

MVSTER		79.01 174	77.88 178	82.38 186	83.07 283	64.80 198	84.08 249	88.95 189	69.01 227	78.69 143	87.17 215	54.70 222	92.43 193	74.69 140	80.57 226	89.89 210

ab-mvs		79.51 158	78.97 154	81.14 214	88.46 163	60.91 261	83.84 250	89.24 175	70.36 190	79.03 136	88.87 167	63.23 134	90.21 258	65.12 230	82.57 203	92.28 122

PAPM		77.68 210	76.40 216	81.51 201	87.29 207	61.85 251	83.78 251	89.59 162	64.74 277	71.23 275	88.70 170	62.59 143	93.66 143	52.66 321	87.03 139	89.01 235

diffmvs		82.10 98	81.88 100	82.76 180	83.00 286	63.78 218	83.68 252	89.76 157	72.94 150	82.02 101	89.85 138	65.96 112	90.79 250	82.38 72	87.30 135	93.71 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
miper_ehance_all_eth		78.59 185	77.76 184	81.08 216	82.66 295	61.56 255	83.65 253	89.15 179	68.87 229	75.55 217	83.79 290	66.49 102	92.03 208	73.25 156	76.39 274	89.64 218

1112_ss		77.40 215	76.43 215	80.32 233	89.11 142	60.41 270	83.65 253	87.72 220	62.13 308	73.05 257	86.72 224	62.58 144	89.97 260	62.11 255	80.80 222	90.59 176

PCF-MVS	73.52 7	80.38 140	78.84 156	85.01 82	87.71 189	68.99 102	83.65 253	91.46 111	63.00 296	77.77 169	90.28 129	66.10 107	95.09 84	61.40 261	88.22 127	90.94 163
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVG-ACMP-BASELINE		76.11 236	74.27 244	81.62 198	83.20 279	64.67 200	83.60 256	89.75 158	69.75 207	71.85 270	87.09 217	32.78 363	92.11 206	69.99 186	80.43 228	88.09 258

cl22		78.07 197	77.01 199	81.23 210	82.37 302	61.83 252	83.55 257	87.98 211	68.96 228	75.06 236	83.87 286	61.40 165	91.88 215	73.53 151	76.39 274	89.98 206

XVG-OURS-SEG-HR		80.81 126	79.76 133	83.96 133	85.60 232	68.78 106	83.54 258	90.50 134	70.66 186	76.71 192	91.66 94	60.69 178	91.26 237	76.94 118	81.58 213	91.83 134

IB-MVS	68.01 15	75.85 239	73.36 253	83.31 149	84.76 247	66.03 166	83.38 259	85.06 257	70.21 196	69.40 296	81.05 319	45.76 313	94.66 101	65.10 231	75.49 288	89.25 227
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	77.95 201	77.15 197	80.36 231	87.57 198	60.21 273	83.37 260	87.78 219	66.11 261	75.37 224	87.06 219	63.27 132	90.48 255	61.38 262	82.43 204	90.40 183

test_vis1_n_1920		75.52 243	75.78 221	74.75 306	79.84 334	57.44 302	83.26 261	85.52 253	62.83 300	79.34 134	86.17 245	45.10 318	79.71 343	78.75 99	81.21 217	87.10 284

Anonymous20240521		68.80 302	67.22 311	73.55 314	74.33 362	54.11 339	83.18 262	85.61 252	58.15 338	61.68 352	80.94 322	30.71 369	81.27 338	57.00 300	73.34 319	85.28 312

eth_miper_zixun_eth		77.92 202	76.69 210	81.61 200	83.00 286	61.98 249	83.15 263	89.20 177	69.52 211	74.86 240	84.35 281	61.76 156	92.56 189	71.50 171	72.89 321	90.28 188

FE-MVS		77.78 205	75.68 223	84.08 121	88.09 175	66.00 168	83.13 264	87.79 218	68.42 238	78.01 164	85.23 265	45.50 316	95.12 78	59.11 279	85.83 159	91.11 154

cl____		77.72 207	76.76 207	80.58 227	82.49 299	60.48 268	83.09 265	87.87 215	69.22 217	74.38 246	85.22 266	62.10 153	91.53 227	71.09 174	75.41 293	89.73 217

DIV-MVS_self_test		77.72 207	76.76 207	80.58 227	82.48 300	60.48 268	83.09 265	87.86 216	69.22 217	74.38 246	85.24 264	62.10 153	91.53 227	71.09 174	75.40 294	89.74 216

thres200		75.55 242	74.47 241	78.82 258	87.78 188	57.85 295	83.07 267	83.51 281	72.44 154	75.84 213	84.42 277	52.08 248	91.75 218	47.41 350	83.64 186	86.86 287

testing3		68.56 305	67.67 306	71.22 333	87.33 205	42.87 381	83.06 268	71.54 363	70.36 190	69.08 300	84.38 279	30.33 370	85.69 308	37.50 375	75.45 292	85.09 318

XVG-OURS		80.41 139	79.23 147	83.97 132	85.64 231	69.02 101	83.03 269	90.39 136	71.09 176	77.63 171	91.49 102	54.62 224	91.35 235	75.71 132	83.47 190	91.54 140

miper_enhance_ethall		77.87 204	76.86 203	80.92 221	81.65 309	61.38 257	82.68 270	88.98 186	65.52 270	75.47 218	82.30 309	65.76 114	92.00 210	72.95 159	76.39 274	89.39 223

mvs_anonymous		79.42 163	79.11 151	80.34 232	84.45 254	57.97 292	82.59 271	87.62 221	67.40 247	76.17 209	88.56 177	68.47 84	89.59 266	70.65 179	86.05 154	93.47 79

baseline2		75.70 240	73.83 249	81.30 208	83.26 277	61.79 253	82.57 272	80.65 314	66.81 248	66.88 319	83.42 295	57.86 199	92.19 204	63.47 239	79.57 236	89.91 208

cascas		76.72 226	74.64 237	82.99 166	85.78 229	65.88 172	82.33 273	89.21 176	60.85 316	72.74 259	81.02 320	47.28 297	93.75 140	67.48 210	85.02 162	89.34 224

RPSCF		73.23 266	71.46 267	78.54 264	82.50 298	59.85 275	82.18 274	82.84 296	58.96 332	71.15 277	89.41 155	45.48 317	84.77 317	58.82 283	71.83 328	91.02 161

thisisatest0515		77.33 216	75.38 230	83.18 156	85.27 236	63.80 217	82.11 275	83.27 285	65.06 273	75.91 211	83.84 288	49.54 278	94.27 113	67.24 213	86.19 152	91.48 145

pmmvs-eth3d		70.50 289	67.83 302	78.52 265	77.37 351	66.18 165	81.82 276	81.51 307	58.90 333	63.90 345	80.42 327	42.69 330	86.28 304	58.56 285	65.30 354	83.11 339

MS-PatchMatch		73.83 258	72.67 258	77.30 283	83.87 265	66.02 167	81.82 276	84.66 262	61.37 314	68.61 304	82.82 303	47.29 296	88.21 288	59.27 276	84.32 174	77.68 364

pmmvs5		71.55 277	70.20 283	75.61 295	77.83 348	56.39 317	81.74 278	80.89 310	57.76 341	67.46 313	84.49 276	49.26 284	85.32 313	57.08 299	75.29 297	85.11 317

Test_1112_low_res		76.40 232	75.44 227	79.27 253	89.28 132	58.09 288	81.69 279	87.07 232	59.53 327	72.48 263	86.67 229	61.30 167	89.33 270	60.81 267	80.15 231	90.41 182

IterMVS		74.29 252	72.94 257	78.35 267	81.53 312	63.49 225	81.58 280	82.49 298	68.06 241	69.99 289	83.69 292	51.66 257	85.54 309	65.85 225	71.64 329	86.01 303
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		75.43 245	73.87 248	80.11 237	82.69 294	64.85 197	81.57 281	83.47 282	69.16 221	70.49 280	84.15 284	51.95 251	88.15 289	69.23 193	72.14 326	87.34 274

test_vis1_n		69.85 296	69.21 287	71.77 326	72.66 374	55.27 330	81.48 282	76.21 348	52.03 362	75.30 229	83.20 298	28.97 371	76.22 363	74.60 141	78.41 252	83.81 332

pmmvs4		74.03 257	71.91 264	80.39 230	81.96 305	68.32 120	81.45 283	82.14 301	59.32 328	69.87 292	85.13 268	52.40 241	88.13 290	60.21 270	74.74 304	84.73 322

GA-MVS		76.87 224	75.17 234	81.97 193	82.75 292	62.58 241	81.44 284	86.35 243	72.16 159	74.74 241	82.89 301	46.20 308	92.02 209	68.85 199	81.09 218	91.30 150

test_fmvs1_n		70.86 284	70.24 282	72.73 321	72.51 375	55.28 329	81.27 285	79.71 326	51.49 365	78.73 141	84.87 272	27.54 373	77.02 355	76.06 128	79.97 234	85.88 306

test_fmvs1		70.93 283	70.52 277	72.16 324	73.71 365	55.05 331	80.82 286	78.77 332	51.21 366	78.58 147	84.41 278	31.20 368	76.94 356	75.88 131	80.12 233	84.47 324

CostFormer		75.24 248	73.90 247	79.27 253	82.65 296	58.27 287	80.80 287	82.73 297	61.57 311	75.33 228	83.13 299	55.52 213	91.07 246	64.98 232	78.34 253	88.45 253

MIMVSNet1		68.58 304	66.78 314	73.98 312	80.07 331	51.82 353	80.77 288	84.37 266	64.40 281	59.75 360	82.16 312	36.47 356	83.63 324	42.73 365	70.33 335	86.48 294

CL-MVSNet_self_test		72.37 274	71.46 267	75.09 301	79.49 341	53.53 343	80.76 289	85.01 259	69.12 222	70.51 279	82.05 313	57.92 198	84.13 320	52.27 323	66.00 352	87.60 267

MSDG		73.36 264	70.99 273	80.49 229	84.51 253	65.80 175	80.71 290	86.13 246	65.70 267	65.46 333	83.74 291	44.60 319	90.91 248	51.13 328	76.89 265	84.74 321

tpm2		73.26 265	71.46 267	78.63 260	83.34 275	56.71 312	80.65 291	80.40 319	56.63 349	73.55 251	82.02 314	51.80 255	91.24 238	56.35 306	78.42 251	87.95 259

XXY-MVS		75.41 246	75.56 225	74.96 302	83.59 270	57.82 296	80.59 292	83.87 276	66.54 258	74.93 239	88.31 183	63.24 133	80.09 342	62.16 253	76.85 267	86.97 285

test_cas_vis1_n_1920		73.76 259	73.74 250	73.81 313	75.90 355	59.77 276	80.51 293	82.40 299	58.30 337	81.62 108	85.69 253	44.35 321	76.41 361	76.29 125	78.61 246	85.23 313

EGC-MVSNET		52.07 348	47.05 352	67.14 350	83.51 272	60.71 264	80.50 294	67.75 373	0.07 397	0.43 398	75.85 361	24.26 377	81.54 336	28.82 382	62.25 359	59.16 382

SDMVSNet		80.38 140	80.18 126	80.99 218	89.03 143	64.94 195	80.45 295	89.40 166	75.19 98	76.61 196	89.98 135	60.61 181	87.69 295	76.83 121	83.55 187	90.33 185

HyFIR lowres test		77.53 212	75.40 229	83.94 134	89.59 115	66.62 158	80.36 296	88.64 201	56.29 351	76.45 198	85.17 267	57.64 201	93.28 158	61.34 263	83.10 196	91.91 133

D2MVS		74.82 249	73.21 254	79.64 248	79.81 335	62.56 242	80.34 297	87.35 227	64.37 282	68.86 301	82.66 305	46.37 304	90.10 259	67.91 206	81.24 216	86.25 296

TinyColmap		67.30 314	64.81 319	74.76 305	81.92 307	56.68 313	80.29 298	81.49 308	60.33 318	56.27 371	83.22 296	24.77 376	87.66 296	45.52 358	69.47 338	79.95 359

LCM-MVSNet-Re		77.05 220	76.94 202	77.36 281	87.20 208	51.60 355	80.06 299	80.46 318	75.20 97	67.69 310	86.72 224	62.48 145	88.98 277	63.44 240	89.25 114	91.51 141

test_fmvs2		68.35 308	67.48 309	70.98 335	69.50 378	51.95 352	80.05 300	76.38 347	49.33 368	74.65 243	84.38 279	23.30 379	75.40 370	74.51 142	75.17 300	85.60 308

FMVSNet5		69.50 297	67.96 298	74.15 311	82.97 289	55.35 328	80.01 301	82.12 302	62.56 304	63.02 347	81.53 316	36.92 355	81.92 334	48.42 342	74.06 309	85.17 316

SCA		74.22 254	72.33 262	79.91 240	84.05 262	62.17 247	79.96 302	79.29 330	66.30 260	72.38 265	80.13 329	51.95 251	88.60 284	59.25 277	77.67 258	88.96 239

tpmrst		72.39 272	72.13 263	73.18 319	80.54 325	49.91 364	79.91 303	79.08 331	63.11 294	71.69 272	79.95 331	55.32 214	82.77 330	65.66 227	73.89 311	86.87 286

PatchmatchNet		73.12 267	71.33 270	78.49 266	83.18 280	60.85 262	79.63 304	78.57 333	64.13 284	71.73 271	79.81 334	51.20 260	85.97 306	57.40 296	76.36 279	88.66 249
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PatchMatch-RL		72.38 273	70.90 274	76.80 288	88.60 158	67.38 143	79.53 305	76.17 349	62.75 302	69.36 297	82.00 315	45.51 315	84.89 316	53.62 316	80.58 225	78.12 363

CMPMVS	51.72 21	70.19 292	68.16 295	76.28 290	73.15 371	57.55 300	79.47 306	83.92 274	48.02 369	56.48 370	84.81 273	43.13 327	86.42 303	62.67 248	81.81 211	84.89 319
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
GG-mvs-BLEND				75.38 299	81.59 311	55.80 324	79.32 307	69.63 368		67.19 316	73.67 366	43.24 326	88.90 281	50.41 330	84.50 169	81.45 352

LTVRE_ROB	69.57 13	76.25 234	74.54 240	81.41 204	88.60 158	64.38 208	79.24 308	89.12 182	70.76 183	69.79 294	87.86 195	49.09 286	93.20 166	56.21 307	80.16 230	86.65 292
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		72.37 274	71.71 266	74.35 309	82.19 303	52.00 351	79.22 309	77.29 342	64.56 279	72.95 258	83.68 293	51.35 258	83.26 328	58.33 288	75.80 283	87.81 263

ppachtmachnet_test		70.04 293	67.34 310	78.14 269	79.80 336	61.13 258	79.19 310	80.59 315	59.16 330	65.27 335	79.29 337	46.75 302	87.29 297	49.33 339	66.72 347	86.00 305

USDC		70.33 290	68.37 292	76.21 291	80.60 324	56.23 320	79.19 310	86.49 239	60.89 315	61.29 353	85.47 260	31.78 366	89.47 269	53.37 318	76.21 280	82.94 343

sd_testset		77.70 209	77.40 192	78.60 262	89.03 143	60.02 274	79.00 312	85.83 250	75.19 98	76.61 196	89.98 135	54.81 217	85.46 311	62.63 249	83.55 187	90.33 185

PM-MVS		66.41 320	64.14 322	73.20 318	73.92 364	56.45 315	78.97 313	64.96 380	63.88 291	64.72 339	80.24 328	19.84 382	83.44 326	66.24 219	64.52 356	79.71 360

tpmvs		71.09 281	69.29 286	76.49 289	82.04 304	56.04 322	78.92 314	81.37 309	64.05 287	67.18 317	78.28 346	49.74 277	89.77 262	49.67 338	72.37 323	83.67 333

test_post1							78.90 315				5.43 396	48.81 292	85.44 312	59.25 277

CHOSEN 1792x2688		77.63 211	75.69 222	83.44 144	89.98 108	68.58 117	78.70 316	87.50 224	56.38 350	75.80 214	86.84 220	58.67 192	91.40 234	61.58 260	85.75 160	90.34 184

Syy-MVS		68.05 309	67.85 300	68.67 346	84.68 249	40.97 387	78.62 317	73.08 360	66.65 255	66.74 322	79.46 335	52.11 247	82.30 332	32.89 379	76.38 277	82.75 344

myMVS_eth3d		67.02 315	66.29 316	69.21 341	84.68 249	42.58 382	78.62 317	73.08 360	66.65 255	66.74 322	79.46 335	31.53 367	82.30 332	39.43 372	76.38 277	82.75 344

test-LLR		72.94 270	72.43 260	74.48 307	81.35 316	58.04 290	78.38 319	77.46 339	66.66 252	69.95 290	79.00 340	48.06 293	79.24 344	66.13 220	84.83 164	86.15 299

TESTMET0.1,1		69.89 295	69.00 289	72.55 322	79.27 344	56.85 308	78.38 319	74.71 355	57.64 342	68.09 307	77.19 353	37.75 353	76.70 357	63.92 237	84.09 177	84.10 329

test-mter		71.41 278	70.39 281	74.48 307	81.35 316	58.04 290	78.38 319	77.46 339	60.32 319	69.95 290	79.00 340	36.08 358	79.24 344	66.13 220	84.83 164	86.15 299

Anonymous20231206		68.60 303	67.80 303	71.02 334	80.23 329	50.75 361	78.30 322	80.47 317	56.79 348	66.11 331	82.63 306	46.35 305	78.95 346	43.62 363	75.70 284	83.36 336

tpm cat1		70.57 287	68.31 293	77.35 282	82.41 301	57.95 293	78.08 323	80.22 322	52.04 361	68.54 305	77.66 351	52.00 250	87.84 293	51.77 324	72.07 327	86.25 296

our_test_3		69.14 299	67.00 312	75.57 296	79.80 336	58.80 282	77.96 324	77.81 336	59.55 326	62.90 350	78.25 347	47.43 295	83.97 321	51.71 325	67.58 346	83.93 331

KD-MVS_self_test		68.81 301	67.59 308	72.46 323	74.29 363	45.45 372	77.93 325	87.00 233	63.12 293	63.99 344	78.99 342	42.32 332	84.77 317	56.55 305	64.09 357	87.16 280

WTY-MVS		75.65 241	75.68 223	75.57 296	86.40 221	56.82 309	77.92 326	82.40 299	65.10 272	76.18 207	87.72 196	63.13 139	80.90 339	60.31 269	81.96 208	89.00 237

test20.03		67.45 312	66.95 313	68.94 342	75.48 359	44.84 377	77.50 327	77.67 337	66.66 252	63.01 348	83.80 289	47.02 299	78.40 348	42.53 366	68.86 343	83.58 334

EPMVS		69.02 300	68.16 295	71.59 327	79.61 339	49.80 366	77.40 328	66.93 374	62.82 301	70.01 287	79.05 338	45.79 312	77.86 352	56.58 304	75.26 298	87.13 281

test_fmvs3		63.36 331	61.82 334	67.98 348	62.51 385	46.96 371	77.37 329	74.03 357	45.24 371	67.50 312	78.79 343	12.16 390	72.98 378	72.77 162	66.02 351	83.99 330

gg-mvs-nofinetune		69.95 294	67.96 298	75.94 292	83.07 283	54.51 337	77.23 330	70.29 366	63.11 294	70.32 282	62.33 377	43.62 325	88.69 283	53.88 315	87.76 129	84.62 323

MDTV_nov1_ep13			69.97 284		83.18 280	53.48 344	77.10 331	80.18 323	60.45 317	69.33 298	80.44 326	48.89 291	86.90 299	51.60 326	78.51 249

LF4IMVS		64.02 329	62.19 333	69.50 340	70.90 376	53.29 348	76.13 332	77.18 343	52.65 360	58.59 362	80.98 321	23.55 378	76.52 359	53.06 320	66.66 348	78.68 362

sss		73.60 260	73.64 251	73.51 315	82.80 291	55.01 332	76.12 333	81.69 306	62.47 305	74.68 242	85.85 251	57.32 205	78.11 350	60.86 266	80.93 219	87.39 272

testgi		66.67 318	66.53 315	67.08 351	75.62 358	41.69 386	75.93 334	76.50 346	66.11 261	65.20 338	86.59 232	35.72 359	74.71 372	43.71 362	73.38 318	84.84 320

CR-MVSNet		73.37 262	71.27 271	79.67 247	81.32 318	65.19 189	75.92 335	80.30 320	59.92 323	72.73 260	81.19 317	52.50 239	86.69 300	59.84 272	77.71 256	87.11 282

RPMNet		73.51 261	70.49 278	82.58 183	81.32 318	65.19 189	75.92 335	92.27 76	57.60 343	72.73 260	76.45 356	52.30 242	95.43 65	48.14 347	77.71 256	87.11 282

MIMVSNet		70.69 286	69.30 285	74.88 303	84.52 252	56.35 319	75.87 337	79.42 328	64.59 278	67.76 308	82.41 307	41.10 340	81.54 336	46.64 354	81.34 214	86.75 290

test0.0.03 1		68.00 310	67.69 305	68.90 343	77.55 349	47.43 368	75.70 338	72.95 362	66.66 252	66.56 324	82.29 310	48.06 293	75.87 365	44.97 361	74.51 306	83.41 335

dmvs_re		71.14 280	70.58 276	72.80 320	81.96 305	59.68 277	75.60 339	79.34 329	68.55 234	69.27 299	80.72 325	49.42 280	76.54 358	52.56 322	77.79 255	82.19 348

dmvs_testset		62.63 332	64.11 323	58.19 361	78.55 346	24.76 397	75.28 340	65.94 377	67.91 242	60.34 356	76.01 358	53.56 233	73.94 376	31.79 380	67.65 345	75.88 368

PMMVS		69.34 298	68.67 290	71.35 331	75.67 357	62.03 248	75.17 341	73.46 358	50.00 367	68.68 302	79.05 338	52.07 249	78.13 349	61.16 264	82.77 199	73.90 370

UnsupCasMVSNet_eth		67.33 313	65.99 317	71.37 329	73.48 368	51.47 357	75.16 342	85.19 256	65.20 271	60.78 355	80.93 324	42.35 331	77.20 354	57.12 298	53.69 375	85.44 310

MDTV_nov1_ep13_2view						37.79 389	75.16 342		55.10 354	66.53 325		49.34 282		53.98 314		87.94 260

pmmvs3		57.79 338	54.26 343	68.37 347	64.02 384	56.72 311	75.12 344	65.17 378	40.20 377	52.93 375	69.86 374	20.36 381	75.48 368	45.45 359	55.25 374	72.90 372

dp		66.80 316	65.43 318	70.90 336	79.74 338	48.82 367	75.12 344	74.77 353	59.61 325	64.08 343	77.23 352	42.89 328	80.72 340	48.86 341	66.58 349	83.16 338

Patchmtry		70.74 285	69.16 288	75.49 298	80.72 322	54.07 340	74.94 346	80.30 320	58.34 336	70.01 287	81.19 317	52.50 239	86.54 301	53.37 318	71.09 333	85.87 307

PVSNet	64.34 18	72.08 276	70.87 275	75.69 294	86.21 223	56.44 316	74.37 347	80.73 313	62.06 309	70.17 285	82.23 311	42.86 329	83.31 327	54.77 311	84.45 173	87.32 275

WB-MVS		54.94 340	54.72 342	55.60 367	73.50 367	20.90 399	74.27 348	61.19 384	59.16 330	50.61 377	74.15 364	47.19 298	75.78 366	17.31 391	35.07 386	70.12 374

MDA-MVSNet-bldmvs		66.68 317	63.66 326	75.75 293	79.28 343	60.56 267	73.92 349	78.35 334	64.43 280	50.13 378	79.87 333	44.02 323	83.67 323	46.10 356	56.86 368	83.03 341

SSC-MVS		53.88 343	53.59 344	54.75 369	72.87 372	19.59 400	73.84 350	60.53 386	57.58 344	49.18 379	73.45 367	46.34 306	75.47 369	16.20 394	32.28 388	69.20 375

UnsupCasMVSNet_bld		63.70 330	61.53 336	70.21 338	73.69 366	51.39 358	72.82 351	81.89 303	55.63 353	57.81 366	71.80 370	38.67 348	78.61 347	49.26 340	52.21 377	80.63 356

PatchT		68.46 307	67.85 300	70.29 337	80.70 323	43.93 379	72.47 352	74.88 352	60.15 321	70.55 278	76.57 355	49.94 274	81.59 335	50.58 329	74.83 303	85.34 311

miper_lstm_enhance		74.11 255	73.11 256	77.13 285	80.11 330	59.62 278	72.23 353	86.92 235	66.76 250	70.40 281	82.92 300	56.93 209	82.92 329	69.06 196	72.63 322	88.87 242

MVS-HIRNet		59.14 337	57.67 340	63.57 355	81.65 309	43.50 380	71.73 354	65.06 379	39.59 379	51.43 376	57.73 383	38.34 350	82.58 331	39.53 370	73.95 310	64.62 379

APD_test1		53.31 345	49.93 350	63.42 356	65.68 382	50.13 363	71.59 355	66.90 375	34.43 384	40.58 383	71.56 371	8.65 395	76.27 362	34.64 378	55.36 373	63.86 380

Patchmatch-RL test		70.24 291	67.78 304	77.61 278	77.43 350	59.57 280	71.16 356	70.33 365	62.94 298	68.65 303	72.77 368	50.62 266	85.49 310	69.58 191	66.58 349	87.77 264

test123		6.12 365	8.11 368	0.14 380	0.06 403	0.09 405	71.05 357	0.03 405	0.04 399	0.25 400	1.30 399	0.05 403	0.03 400	0.21 399	0.01 398	0.29 395

ANet_high		50.57 350	46.10 354	63.99 354	48.67 396	39.13 388	70.99 358	80.85 311	61.39 313	31.18 386	57.70 384	17.02 385	73.65 377	31.22 381	15.89 394	79.18 361

KD-MVS_2432*1600		66.22 322	63.89 324	73.21 316	75.47 360	53.42 345	70.76 359	84.35 267	64.10 285	66.52 326	78.52 344	34.55 361	84.98 314	50.40 331	50.33 379	81.23 353

miper_refine_blended		66.22 322	63.89 324	73.21 316	75.47 360	53.42 345	70.76 359	84.35 267	64.10 285	66.52 326	78.52 344	34.55 361	84.98 314	50.40 331	50.33 379	81.23 353

test_vis1_rt		60.28 336	58.42 339	65.84 352	67.25 381	55.60 327	70.44 361	60.94 385	44.33 373	59.00 361	66.64 375	24.91 375	68.67 383	62.80 244	69.48 337	73.25 371

testmvs		6.04 366	8.02 369	0.10 381	0.08 402	0.03 406	69.74 362	0.04 404	0.05 398	0.31 399	1.68 398	0.02 404	0.04 399	0.24 398	0.02 397	0.25 396

N_pmnet		52.79 346	53.26 345	51.40 371	78.99 345	7.68 403	69.52 363	3.89 402	51.63 364	57.01 368	74.98 363	40.83 342	65.96 386	37.78 374	64.67 355	80.56 358

FPMVS		53.68 344	51.64 346	59.81 360	65.08 383	51.03 359	69.48 364	69.58 369	41.46 376	40.67 382	72.32 369	16.46 386	70.00 382	24.24 388	65.42 353	58.40 384

DSMNet-mixed		57.77 339	56.90 341	60.38 359	67.70 380	35.61 390	69.18 365	53.97 391	32.30 387	57.49 367	79.88 332	40.39 344	68.57 384	38.78 373	72.37 323	76.97 365

new-patchmatchnet		61.73 334	61.73 335	61.70 357	72.74 373	24.50 398	69.16 366	78.03 335	61.40 312	56.72 369	75.53 362	38.42 349	76.48 360	45.95 357	57.67 367	84.13 328

YYNet1		65.03 325	62.91 330	71.38 328	75.85 356	56.60 314	69.12 367	74.66 356	57.28 346	54.12 373	77.87 349	45.85 311	74.48 373	49.95 336	61.52 362	83.05 340

MDA-MVSNet_test_wron		65.03 325	62.92 329	71.37 329	75.93 354	56.73 310	69.09 368	74.73 354	57.28 346	54.03 374	77.89 348	45.88 310	74.39 374	49.89 337	61.55 361	82.99 342

PVSNet_0	57.27 20	61.67 335	59.27 338	68.85 344	79.61 339	57.44 302	68.01 369	73.44 359	55.93 352	58.54 363	70.41 373	44.58 320	77.55 353	47.01 351	35.91 385	71.55 373

ADS-MVSNet2		66.20 324	63.33 327	74.82 304	79.92 332	58.75 283	67.55 370	75.19 351	53.37 358	65.25 336	75.86 359	42.32 332	80.53 341	41.57 367	68.91 341	85.18 314

ADS-MVSNet		64.36 328	62.88 331	68.78 345	79.92 332	47.17 369	67.55 370	71.18 364	53.37 358	65.25 336	75.86 359	42.32 332	73.99 375	41.57 367	68.91 341	85.18 314

mvsany_test1		62.30 333	61.26 337	65.41 353	69.52 377	54.86 333	66.86 372	49.78 393	46.65 370	68.50 306	83.21 297	49.15 285	66.28 385	56.93 301	60.77 363	75.11 369

LCM-MVSNet		54.25 341	49.68 351	67.97 349	53.73 393	45.28 375	66.85 373	80.78 312	35.96 383	39.45 384	62.23 379	8.70 394	78.06 351	48.24 346	51.20 378	80.57 357

test_vis3_rt		49.26 351	47.02 353	56.00 364	54.30 390	45.27 376	66.76 374	48.08 394	36.83 381	44.38 381	53.20 386	7.17 397	64.07 387	56.77 303	55.66 371	58.65 383

testf1		45.72 352	41.96 355	57.00 362	56.90 387	45.32 373	66.14 375	59.26 387	26.19 388	30.89 387	60.96 381	4.14 398	70.64 380	26.39 386	46.73 383	55.04 385

APD_test2		45.72 352	41.96 355	57.00 362	56.90 387	45.32 373	66.14 375	59.26 387	26.19 388	30.89 387	60.96 381	4.14 398	70.64 380	26.39 386	46.73 383	55.04 385

JIA-IIPM		66.32 321	62.82 332	76.82 287	77.09 352	61.72 254	65.34 377	75.38 350	58.04 340	64.51 340	62.32 378	42.05 337	86.51 302	51.45 327	69.22 340	82.21 347

PMVS	37.38 22	44.16 355	40.28 358	55.82 366	40.82 398	42.54 384	65.12 378	63.99 381	34.43 384	24.48 390	57.12 385	3.92 400	76.17 364	17.10 392	55.52 372	48.75 387
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		50.91 349	50.29 349	52.78 370	68.58 379	34.94 392	63.71 379	56.63 390	39.73 378	44.95 380	65.47 376	21.93 380	58.48 389	34.98 377	56.62 369	64.92 378

mvsany_test3		53.99 342	51.45 347	61.61 358	55.51 389	44.74 378	63.52 380	45.41 397	43.69 374	58.11 365	76.45 356	17.99 383	63.76 388	54.77 311	47.59 381	76.34 367

Patchmatch-test		64.82 327	63.24 328	69.57 339	79.42 342	49.82 365	63.49 381	69.05 371	51.98 363	59.95 359	80.13 329	50.91 262	70.98 379	40.66 369	73.57 314	87.90 261

ambc				75.24 300	73.16 370	50.51 362	63.05 382	87.47 225		64.28 341	77.81 350	17.80 384	89.73 264	57.88 292	60.64 364	85.49 309

test_f		52.09 347	50.82 348	55.90 365	53.82 392	42.31 385	59.42 383	58.31 389	36.45 382	56.12 372	70.96 372	12.18 389	57.79 390	53.51 317	56.57 370	67.60 376

CHOSEN 280x420		66.51 319	64.71 320	71.90 325	81.45 313	63.52 224	57.98 384	68.95 372	53.57 357	62.59 351	76.70 354	46.22 307	75.29 371	55.25 309	79.68 235	76.88 366

E-PMN		31.77 357	30.64 360	35.15 375	52.87 394	27.67 394	57.09 385	47.86 395	24.64 390	16.40 395	33.05 391	11.23 391	54.90 392	14.46 395	18.15 392	22.87 391

EMVS		30.81 359	29.65 361	34.27 376	50.96 395	25.95 396	56.58 386	46.80 396	24.01 391	15.53 396	30.68 392	12.47 388	54.43 393	12.81 396	17.05 393	22.43 392

PMMVS2		40.82 356	38.86 359	46.69 372	53.84 391	16.45 401	48.61 387	49.92 392	37.49 380	31.67 385	60.97 380	8.14 396	56.42 391	28.42 383	30.72 389	67.19 377

wuyk23d		16.82 363	15.94 366	19.46 378	58.74 386	31.45 393	39.22 388	3.74 403	6.84 394	6.04 397	2.70 397	1.27 402	24.29 397	10.54 397	14.40 396	2.63 394

tmp_tt		18.61 362	21.40 365	10.23 379	4.82 401	10.11 402	34.70 389	30.74 400	1.48 396	23.91 392	26.07 393	28.42 372	13.41 398	27.12 384	15.35 395	7.17 393

Gipuma		45.18 354	41.86 357	55.16 368	77.03 353	51.52 356	32.50 390	80.52 316	32.46 386	27.12 389	35.02 390	9.52 393	75.50 367	22.31 389	60.21 366	38.45 389
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	26.22 23	30.37 360	25.89 364	43.81 373	44.55 397	35.46 391	28.87 391	39.07 398	18.20 392	18.58 394	40.18 389	2.68 401	47.37 395	17.07 393	23.78 391	48.60 388
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		31.52 358	29.28 362	38.23 374	27.03 400	6.50 404	20.94 392	62.21 383	4.05 395	22.35 393	52.50 387	13.33 387	47.58 394	27.04 385	34.04 387	60.62 381

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

cdsmvs_eth3d_5k		19.96 361	26.61 363	0.00 382	0.00 404	0.00 407	0.00 393	89.26 173	0.00 400	0.00 401	88.61 174	61.62 159	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		5.26 367	7.02 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	63.15 136	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

ab-mvs-re		7.23 364	9.64 367	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	86.72 224	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

WAC-MVS						42.58 382								39.46 371

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 45					97.53 2	89.67 6	96.44 9	94.41 32

PC_three_1452									68.21 240	92.02 12	94.00 46	82.09 5	95.98 51	84.58 46	96.68 2	94.95 10

No_MVS				89.16 1	94.34 27	75.53 2		92.99 45					97.53 2	89.67 6	96.44 9	94.41 32

test_one_0601					95.07 7	71.46 55		94.14 5	78.27 35	92.05 11	95.74 6	80.83 11

eth-test2					0.00 404

eth-test					0.00 404

ZD-MVS					94.38 25	72.22 44		92.67 61	70.98 179	87.75 30	94.07 41	74.01 32	96.70 27	84.66 45	94.84 43

IU-MVS					95.30 2	71.25 57		92.95 51	66.81 248	92.39 6				88.94 16	96.63 4	94.85 19

test_241102_TWO								94.06 10	77.24 50	92.78 4	95.72 8	81.26 8	97.44 6	89.07 14	96.58 6	94.26 41

test_241102_ONE					95.30 2	70.98 63		94.06 10	77.17 53	93.10 1	95.39 11	82.99 1	97.27 11

test_0728_THIRD									78.38 33	92.12 9	95.78 4	81.46 7	97.40 8	89.42 9	96.57 7	94.67 24

GSMVS																88.96 239

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 259				88.96 239

sam_mvs												50.01 272

MTGPA								92.02 85

test_post											5.46 395	50.36 270	84.24 319

patchmatchnet-post											74.00 365	51.12 261	88.60 284

gm-plane-assit					81.40 314	53.83 342			62.72 303		80.94 322		92.39 195	63.40 241

test9_res														84.90 40	95.70 26	92.87 102

agg_prior2														82.91 64	95.45 30	92.70 105

agg_prior					92.85 59	71.94 51		91.78 100		84.41 69			94.93 87

TestCases				79.58 249	85.15 239	63.62 219		79.83 324	62.31 306	60.32 357	86.73 222	32.02 364	88.96 279	50.28 333	71.57 330	86.15 299

test_prior				86.33 54	92.61 65	69.59 88		92.97 50					95.48 62			93.91 53

新几何1				83.42 145	93.13 52	70.71 71		85.48 254	57.43 345	81.80 105	91.98 88	63.28 131	92.27 201	64.60 235	92.99 65	87.27 276

旧先验1					91.96 71	65.79 176		86.37 242			93.08 69	69.31 75			92.74 68	88.74 248

原ACMM1				84.35 107	93.01 57	68.79 105		92.44 69	63.96 290	81.09 115	91.57 99	66.06 109	95.45 63	67.19 214	94.82 45	88.81 245

testdata2													91.01 247	62.37 251

segment_acmp												73.08 37

testdata				79.97 239	90.90 86	64.21 210		84.71 261	59.27 329	85.40 49	92.91 71	62.02 155	89.08 275	68.95 197	91.37 86	86.63 293

test12				86.80 49	92.63 64	70.70 72		91.79 99		82.71 96		71.67 50	96.16 44		94.50 50	93.54 77

plane_prior7					90.08 102	68.51 118

plane_prior6					89.84 111	68.70 113						60.42 184

plane_prior5								92.44 69					95.38 69	78.71 100	86.32 149	91.33 147

plane_prior4											91.00 118

plane_prior3						68.60 116			78.44 31	78.92 139

plane_prior1					89.90 110

n2								0.00 406

nn								0.00 406

door-mid								69.98 367

lessismore_v0				78.97 256	81.01 321	57.15 305		65.99 376		61.16 354	82.82 303	39.12 347	91.34 236	59.67 273	46.92 382	88.43 254

LGP-MVS_train				84.50 99	89.23 134	68.76 107		91.94 91	75.37 94	76.64 194	91.51 100	54.29 226	94.91 88	78.44 102	83.78 179	89.83 212

test11								92.23 79

door								69.44 370

HQP5-MVS						66.98 153

BP-MVS														77.47 112

HQP4-MVS										77.24 179			95.11 80			91.03 159

HQP3-MVS								92.19 82							85.99 156

HQP2-MVS												60.17 187

NP-MVS					89.62 114	68.32 120					90.24 130

ACMMP++_ref															81.95 209

ACMMP++															81.25 215

Test By Simon												64.33 123

ITE_SJBPF				78.22 268	81.77 308	60.57 266		83.30 284	69.25 216	67.54 311	87.20 213	36.33 357	87.28 298	54.34 313	74.62 305	86.80 288

DeepMVS_CX				27.40 377	40.17 399	26.90 395		24.59 401	17.44 393	23.95 391	48.61 388	9.77 392	26.48 396	18.06 390	24.47 390	28.83 390

High-resolution multi-view benchmark