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 59	95.06 1	94.23 3	78.38 34	92.78 4	95.74 6	82.45 3	97.49 4	89.42 15	96.68 2	94.95 11

FOURS1					95.00 10	72.39 39	95.06 1	93.84 15	74.49 128	91.30 15

CP-MVS		87.11 33	86.92 37	87.68 34	94.20 34	73.86 7	93.98 3	92.82 63	76.62 76	83.68 100	94.46 28	67.93 103	95.95 57	84.20 68	94.39 55	93.23 99

APDe-MVS		89.15 7	89.63 6	87.73 28	94.49 18	71.69 52	93.83 4	93.96 13	75.70 96	91.06 16	96.03 1	76.84 14	97.03 17	89.09 17	95.65 27	94.47 38
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 72	72.96 25	93.73 5	93.67 20	80.19 12	88.10 33	94.80 20	73.76 33	97.11 15	87.51 38	95.82 21	94.90 14
Skip Steuart: Steuart Systems R&D Blog.
test0726					95.27 5	71.25 59	93.60 6	94.11 6	77.33 52	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 66	93.57 7	94.06 10	77.24 55	93.10 1	95.72 8	82.99 1	97.44 7	89.07 20	96.63 4	94.88 15

OPU-MVS				89.06 3	94.62 15	75.42 4	93.57 7				94.02 51	82.45 3	96.87 20	83.77 72	96.48 8	94.88 15

DVP-MVS		89.60 3	90.35 3	87.33 40	95.27 5	71.25 59	93.49 9	92.73 64	77.33 52	92.12 9	95.78 4	80.98 9	97.40 9	89.08 18	96.41 12	93.33 96
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 58	93.49 9	94.23 3					97.49 4	89.08 18	96.41 12	94.21 49

3Dnovator+	77.84 4	85.48 63	84.47 81	88.51 7	91.08 86	73.49 16	93.18 11	93.78 18	80.79 8	76.66 211	93.37 73	60.40 204	96.75 26	77.20 133	93.73 64	95.29 5

HFP-MVS		87.58 22	87.47 26	87.94 19	94.58 16	73.54 15	93.04 12	93.24 33	76.78 70	84.91 72	94.44 31	70.78 68	96.61 32	84.53 62	94.89 42	93.66 76

ACMMPR		87.44 25	87.23 31	88.08 15	94.64 13	73.59 12	93.04 12	93.20 34	76.78 70	84.66 79	94.52 24	68.81 94	96.65 30	84.53 62	94.90 41	94.00 59

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 68	85.24 67	94.32 36	71.76 53	96.93 19	85.53 51	95.79 22	94.32 45

region2R		87.42 27	87.20 32	88.09 14	94.63 14	73.55 13	93.03 14	93.12 40	76.73 73	84.45 84	94.52 24	69.09 88	96.70 27	84.37 64	94.83 45	94.03 57

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 44	78.35 13	96.77 24	89.59 13	94.22 60	94.67 28
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 39	86.95 36	85.90 71	90.76 96	67.57 148	92.83 17	93.30 32	79.67 17	84.57 83	92.27 97	71.47 58	95.02 93	84.24 67	93.46 67	95.13 8

XVS		87.18 32	86.91 38	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 101	94.17 43	67.45 108	96.60 33	83.06 77	94.50 51	94.07 55

X-MVStestdata		80.37 162	77.83 198	88.00 17	94.42 20	73.33 19	92.78 18	92.99 49	79.14 22	83.67 101	12.47 432	67.45 108	96.60 33	83.06 77	94.50 51	94.07 55

mPP-MVS		86.67 41	86.32 44	87.72 30	94.41 22	73.55 13	92.74 20	92.22 88	76.87 67	82.81 113	94.25 40	66.44 119	96.24 44	82.88 82	94.28 58	93.38 92

ACMMP		85.89 56	85.39 66	87.38 39	93.59 45	72.63 33	92.74 20	93.18 39	76.78 70	80.73 138	93.82 62	64.33 139	96.29 42	82.67 88	90.69 104	93.23 99
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 70	77.57 44	83.84 97	94.40 33	72.24 47	96.28 43	85.65 49	95.30 35	93.62 83
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 95	73.65 10	92.66 23	91.17 126	86.57 1	87.39 48	94.97 19	71.70 55	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 64	71.95 49	92.40 24	94.74 2	75.71 94	89.16 20	95.10 16	75.65 21	96.19 46	87.07 41	96.01 17	94.79 22

SMA-MVS		89.08 8	89.23 7	88.61 6	94.25 31	73.73 9	92.40 24	93.63 21	74.77 122	92.29 7	95.97 2	74.28 29	97.24 13	88.58 28	96.91 1	94.87 17
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 27	87.26 29	87.89 24	94.12 36	72.97 24	92.39 26	93.43 28	76.89 66	84.68 76	93.99 55	70.67 70	96.82 22	84.18 69	95.01 37	93.90 65

HPM-MVS++		89.02 9	89.15 9	88.63 5	95.01 9	76.03 1	92.38 27	92.85 59	80.26 11	87.78 39	94.27 38	75.89 19	96.81 23	87.45 39	96.44 9	93.05 112

SR-MVS		86.73 38	86.67 40	86.91 49	94.11 37	72.11 47	92.37 28	92.56 75	74.50 127	86.84 55	94.65 23	67.31 110	95.77 59	84.80 58	92.85 72	92.84 120

SPE-MVS-test		86.29 47	86.48 42	85.71 73	91.02 88	67.21 162	92.36 29	93.78 18	78.97 29	83.51 104	91.20 128	70.65 71	95.15 84	81.96 91	94.89 42	94.77 24

EC-MVSNet		86.01 49	86.38 43	84.91 97	89.31 139	66.27 175	92.32 30	93.63 21	79.37 21	84.17 90	91.88 105	69.04 92	95.43 70	83.93 71	93.77 63	93.01 115

EPP-MVSNet		83.40 100	83.02 100	84.57 105	90.13 107	64.47 220	92.32 30	90.73 138	74.45 130	79.35 153	91.10 131	69.05 91	95.12 85	72.78 180	87.22 158	94.13 52

PHI-MVS		86.43 43	86.17 50	87.24 41	90.88 92	70.96 68	92.27 32	94.07 9	72.45 174	85.22 68	91.90 104	69.47 83	96.42 40	83.28 76	95.94 19	94.35 43

HPM-MVS		87.11 33	86.98 35	87.50 38	93.88 39	72.16 45	92.19 33	93.33 31	76.07 89	83.81 98	93.95 58	69.77 80	96.01 53	85.15 52	94.66 47	94.32 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
MTMP							92.18 34	32.83 437

HPM-MVS_fast		85.35 68	84.95 75	86.57 56	93.69 42	70.58 78	92.15 35	91.62 112	73.89 144	82.67 115	94.09 47	62.60 158	95.54 65	80.93 100	92.93 71	93.57 85

CPTT-MVS		83.73 89	83.33 96	84.92 96	93.28 49	70.86 72	92.09 36	90.38 148	68.75 256	79.57 150	92.83 87	60.60 200	93.04 185	80.92 101	91.56 92	90.86 184

APD-MVS_3200maxsize		85.97 52	85.88 56	86.22 60	92.69 66	69.53 92	91.93 37	92.99 49	73.54 153	85.94 59	94.51 27	65.80 129	95.61 62	83.04 79	92.51 77	93.53 89

SR-MVS-dyc-post		85.77 57	85.61 62	86.23 59	93.06 58	70.63 76	91.88 38	92.27 84	73.53 154	85.69 63	94.45 29	65.00 137	95.56 63	82.75 83	91.87 85	92.50 131

RE-MVS-def			85.48 65		93.06 58	70.63 76	91.88 38	92.27 84	73.53 154	85.69 63	94.45 29	63.87 143		82.75 83	91.87 85	92.50 131

APD-MVS		87.44 25	87.52 25	87.19 42	94.24 32	72.39 39	91.86 40	92.83 60	73.01 168	88.58 25	94.52 24	73.36 34	96.49 38	84.26 65	95.01 37	92.70 122
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SD-MVS		88.06 14	88.50 14	86.71 54	92.60 69	72.71 29	91.81 41	93.19 35	77.87 38	90.32 17	94.00 53	74.83 23	93.78 141	87.63 37	94.27 59	93.65 80
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
reproduce_model		87.28 30	87.39 28	86.95 48	93.10 56	71.24 63	91.60 42	93.19 35	74.69 123	88.80 24	95.61 11	70.29 74	96.44 39	86.20 47	93.08 69	93.16 105

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 92	92.29 7	95.66 10	81.67 6	97.38 11	87.44 40	96.34 15	93.95 62
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
QAPM		80.88 143	79.50 159	85.03 90	88.01 194	68.97 107	91.59 43	92.00 95	66.63 285	75.15 255	92.16 99	57.70 218	95.45 68	63.52 260	88.76 135	90.66 193

IS-MVSNet		83.15 105	82.81 104	84.18 126	89.94 116	63.30 245	91.59 43	88.46 219	79.04 26	79.49 151	92.16 99	65.10 134	94.28 117	67.71 227	91.86 87	94.95 11

reproduce-ours		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 114	88.96 21	95.54 12	71.20 63	96.54 36	86.28 45	93.49 65	93.06 110

our_new_method		87.47 23	87.61 22	87.07 45	93.27 50	71.60 53	91.56 46	93.19 35	74.98 114	88.96 21	95.54 12	71.20 63	96.54 36	86.28 45	93.49 65	93.06 110

9.14			88.26 15		92.84 63		91.52 48	94.75 1	73.93 143	88.57 26	94.67 22	75.57 22	95.79 58	86.77 42	95.76 23

MVS_0304		87.69 20	87.55 24	88.12 13	89.45 130	71.76 51	91.47 49	89.54 178	82.14 3	86.65 56	94.28 37	68.28 100	97.46 6	90.81 4	95.31 34	95.15 7

TSAR-MVS + MP.		88.02 17	88.11 16	87.72 30	93.68 43	72.13 46	91.41 50	92.35 82	74.62 126	88.90 23	93.85 61	75.75 20	96.00 54	87.80 35	94.63 48	95.04 9
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 36	86.62 41	87.76 27	93.52 46	72.37 41	91.26 51	93.04 41	76.62 76	84.22 88	93.36 74	71.44 59	96.76 25	80.82 102	95.33 33	94.16 50
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 92	83.14 97	85.14 85	90.08 109	68.71 116	91.25 52	92.44 77	79.12 24	78.92 159	91.00 138	60.42 202	95.38 75	78.71 118	86.32 171	91.33 168

plane_prior2							91.25 52		79.12 24

NCCC		88.06 14	88.01 18	88.24 11	94.41 22	73.62 11	91.22 54	92.83 60	81.50 5	85.79 62	93.47 70	73.02 41	97.00 18	84.90 54	94.94 40	94.10 53

API-MVS		81.99 123	81.23 127	84.26 123	90.94 90	70.18 85	91.10 55	89.32 185	71.51 191	78.66 164	88.28 201	65.26 132	95.10 90	64.74 254	91.23 96	87.51 299

EPNet		83.72 90	82.92 103	86.14 65	84.22 287	69.48 94	91.05 56	85.27 276	81.30 6	76.83 206	91.65 111	66.09 124	95.56 63	76.00 147	93.85 62	93.38 92
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
ACMMP_NAP		88.05 16	88.08 17	87.94 19	93.70 41	73.05 22	90.86 57	93.59 23	76.27 86	88.14 32	95.09 17	71.06 65	96.67 29	87.67 36	96.37 14	94.09 54

CSCG		86.41 45	86.19 49	87.07 45	92.91 61	72.48 37	90.81 58	93.56 24	73.95 141	83.16 107	91.07 133	75.94 18	95.19 82	79.94 111	94.38 56	93.55 87

MSLP-MVS++		85.43 65	85.76 59	84.45 110	91.93 75	70.24 79	90.71 59	92.86 58	77.46 50	84.22 88	92.81 89	67.16 112	92.94 187	80.36 106	94.35 57	90.16 213

3Dnovator	76.31 5	83.38 101	82.31 112	86.59 55	87.94 196	72.94 28	90.64 60	92.14 92	77.21 57	75.47 237	92.83 87	58.56 211	94.72 105	73.24 176	92.71 75	92.13 149

OpenMVS	72.83 10	79.77 171	78.33 186	84.09 132	85.17 267	69.91 87	90.57 61	90.97 131	66.70 279	72.17 299	91.91 103	54.70 243	93.96 128	61.81 281	90.95 101	88.41 282

balanced_conf03		86.78 37	86.99 34	86.15 63	91.24 83	67.61 146	90.51 62	92.90 56	77.26 54	87.44 47	91.63 113	71.27 62	96.06 49	85.62 50	95.01 37	94.78 23

CNVR-MVS		88.93 10	89.13 10	88.33 8	94.77 12	73.82 8	90.51 62	93.00 46	80.90 7	88.06 34	94.06 49	76.43 16	96.84 21	88.48 31	95.99 18	94.34 44

MVSFormer		82.85 111	82.05 117	85.24 83	87.35 217	70.21 80	90.50 64	90.38 148	68.55 259	81.32 129	89.47 168	61.68 174	93.46 158	78.98 115	90.26 111	92.05 151

test_djsdf		80.30 163	79.32 164	83.27 166	83.98 293	65.37 197	90.50 64	90.38 148	68.55 259	76.19 224	88.70 187	56.44 231	93.46 158	78.98 115	80.14 260	90.97 181

save fliter					93.80 40	72.35 42	90.47 66	91.17 126	74.31 133

nrg030		83.88 85	83.53 91	84.96 93	86.77 236	69.28 102	90.46 67	92.67 67	74.79 121	82.95 108	91.33 124	72.70 45	93.09 180	80.79 104	79.28 270	92.50 131

sasdasda		85.91 54	85.87 57	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 36	91.23 125	73.28 36	93.91 135	81.50 94	88.80 133	94.77 24

canonicalmvs		85.91 54	85.87 57	86.04 67	89.84 118	69.44 98	90.45 68	93.00 46	76.70 74	88.01 36	91.23 125	73.28 36	93.91 135	81.50 94	88.80 133	94.77 24

plane_prior						68.71 116	90.38 70		77.62 42						86.16 175

DeepC-MVS	79.81 2	87.08 35	86.88 39	87.69 33	91.16 84	72.32 43	90.31 71	93.94 14	77.12 60	82.82 112	94.23 41	72.13 49	97.09 16	84.83 57	95.37 31	93.65 80
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 98	82.80 105	85.43 79	90.25 105	68.74 114	90.30 72	90.13 160	76.33 85	80.87 137	92.89 85	61.00 191	94.20 122	72.45 185	90.97 100	93.35 95
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PGM-MVS		86.68 40	86.27 46	87.90 22	94.22 33	73.38 18	90.22 73	93.04 41	75.53 98	83.86 96	94.42 32	67.87 105	96.64 31	82.70 87	94.57 50	93.66 76

LPG-MVS_test		82.08 120	81.27 126	84.50 107	89.23 143	68.76 112	90.22 73	91.94 99	75.37 103	76.64 212	91.51 117	54.29 246	94.91 95	78.44 120	83.78 205	89.83 234

Anonymous20231211		78.97 194	77.69 206	82.81 190	90.54 99	64.29 224	90.11 75	91.51 116	65.01 305	76.16 228	88.13 210	50.56 291	93.03 186	69.68 210	77.56 289	91.11 174

ACMM	73.20 8	80.78 151	79.84 152	83.58 156	89.31 139	68.37 127	89.99 76	91.60 113	70.28 217	77.25 195	89.66 161	53.37 256	93.53 154	74.24 165	82.85 225	88.85 266
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMP	74.13 6	81.51 135	80.57 137	84.36 113	89.42 131	68.69 119	89.97 77	91.50 119	74.46 129	75.04 259	90.41 147	53.82 251	94.54 109	77.56 129	82.91 224	89.86 233
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LFMVS		81.82 126	81.23 127	83.57 157	91.89 76	63.43 243	89.84 78	81.85 328	77.04 63	83.21 105	93.10 78	52.26 265	93.43 160	71.98 186	89.95 118	93.85 67

MCST-MVS		87.37 29	87.25 30	87.73 28	94.53 17	72.46 38	89.82 79	93.82 16	73.07 166	84.86 75	92.89 85	76.22 17	96.33 41	84.89 56	95.13 36	94.40 41

MAR-MVS		81.84 125	80.70 135	85.27 82	91.32 82	71.53 56	89.82 79	90.92 132	69.77 231	78.50 168	86.21 261	62.36 164	94.52 111	65.36 248	92.05 83	89.77 237
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 21	87.72 20	87.54 36	93.64 44	72.04 48	89.80 81	93.50 25	75.17 111	86.34 58	95.29 15	70.86 67	96.00 54	88.78 26	96.04 16	94.58 33
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
UA-Net		85.08 73	84.96 74	85.45 78	92.07 73	68.07 135	89.78 82	90.86 136	82.48 2	84.60 82	93.20 77	69.35 84	95.22 81	71.39 191	90.88 102	93.07 109

alignmvs		85.48 63	85.32 69	85.96 70	89.51 127	69.47 95	89.74 83	92.47 76	76.17 87	87.73 43	91.46 120	70.32 73	93.78 141	81.51 93	88.95 130	94.63 32

VDDNet		81.52 133	80.67 136	84.05 139	90.44 101	64.13 227	89.73 84	85.91 270	71.11 198	83.18 106	93.48 68	50.54 292	93.49 155	73.40 173	88.25 144	94.54 36

CANet		86.45 42	86.10 52	87.51 37	90.09 108	70.94 70	89.70 85	92.59 74	81.78 4	81.32 129	91.43 121	70.34 72	97.23 14	84.26 65	93.36 68	94.37 42

test_fmvsmconf0.1_n		85.61 61	85.65 61	85.50 77	82.99 320	69.39 100	89.65 86	90.29 155	73.31 160	87.77 40	94.15 45	71.72 54	93.23 167	90.31 6	90.67 105	93.89 66

114514_t		80.68 152	79.51 158	84.20 125	94.09 38	67.27 158	89.64 87	91.11 129	58.75 369	74.08 273	90.72 142	58.10 214	95.04 92	69.70 209	89.42 125	90.30 209

MVSMamba_PlusPlus		85.99 50	85.96 55	86.05 66	91.09 85	67.64 145	89.63 88	92.65 70	72.89 171	84.64 80	91.71 109	71.85 51	96.03 50	84.77 59	94.45 54	94.49 37

test_fmvsmconf_n		85.92 53	86.04 54	85.57 76	85.03 273	69.51 93	89.62 89	90.58 141	73.42 157	87.75 41	94.02 51	72.85 43	93.24 166	90.37 5	90.75 103	93.96 60

fmvsm_l_conf0.5_n_3		86.02 48	86.32 44	85.14 85	87.20 226	68.54 123	89.57 90	90.44 146	75.31 105	87.49 45	94.39 34	72.86 42	92.72 193	89.04 22	90.56 106	94.16 50

DeepPCF-MVS	80.84 1	88.10 13	88.56 13	86.73 53	92.24 71	69.03 103	89.57 90	93.39 30	77.53 48	89.79 19	94.12 46	78.98 12	96.58 35	85.66 48	95.72 24	94.58 33

test_fmvsmconf0.01_n		84.73 78	84.52 80	85.34 80	80.25 361	69.03 103	89.47 92	89.65 175	73.24 164	86.98 53	94.27 38	66.62 115	93.23 167	90.26 7	89.95 118	93.78 73

fmvsm_s_conf0.5_n		83.80 87	83.71 89	84.07 134	86.69 239	67.31 156	89.46 93	83.07 311	71.09 199	86.96 54	93.70 65	69.02 93	91.47 247	88.79 25	84.62 192	93.44 91

MGCFI-Net		85.06 74	85.51 64	83.70 152	89.42 131	63.01 251	89.43 94	92.62 73	76.43 78	87.53 44	91.34 123	72.82 44	93.42 161	81.28 97	88.74 136	94.66 31

fmvsm_s_conf0.5_n_a		83.63 93	83.41 93	84.28 119	86.14 248	68.12 133	89.43 94	82.87 316	70.27 218	87.27 50	93.80 63	69.09 88	91.58 238	88.21 33	83.65 212	93.14 107

UGNet		80.83 145	79.59 157	84.54 106	88.04 191	68.09 134	89.42 96	88.16 221	76.95 64	76.22 223	89.46 170	49.30 307	93.94 131	68.48 222	90.31 109	91.60 158
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		78.73 198	77.83 198	81.43 219	85.17 267	60.30 289	89.41 97	90.90 133	71.21 196	77.17 202	88.73 186	46.38 327	93.21 169	72.57 183	78.96 272	90.79 186

fmvsm_s_conf0.1_n		83.56 95	83.38 94	84.10 128	84.86 275	67.28 157	89.40 98	83.01 312	70.67 207	87.08 51	93.96 57	68.38 98	91.45 248	88.56 29	84.50 193	93.56 86

BP-MVS1		84.32 80	83.71 89	86.17 61	87.84 201	67.85 139	89.38 99	89.64 176	77.73 40	83.98 94	92.12 101	56.89 228	95.43 70	84.03 70	91.75 88	95.24 6

AdaColmap		80.58 157	79.42 160	84.06 136	93.09 57	68.91 108	89.36 100	88.97 204	69.27 240	75.70 233	89.69 160	57.20 225	95.77 59	63.06 265	88.41 143	87.50 300

fmvsm_s_conf0.1_n_a		83.32 103	82.99 101	84.28 119	83.79 297	68.07 135	89.34 101	82.85 317	69.80 229	87.36 49	94.06 49	68.34 99	91.56 240	87.95 34	83.46 218	93.21 102

PS-MVSNAJss		82.07 121	81.31 125	84.34 115	86.51 242	67.27 158	89.27 102	91.51 116	71.75 184	79.37 152	90.22 152	63.15 152	94.27 118	77.69 128	82.36 232	91.49 164

jajsoiax		79.29 185	77.96 193	83.27 166	84.68 278	66.57 171	89.25 103	90.16 159	69.20 245	75.46 239	89.49 167	45.75 338	93.13 178	76.84 138	80.80 250	90.11 217

fmvsm_s_conf0.5_n_5		85.22 70	85.55 63	84.25 124	86.26 244	67.40 153	89.18 104	89.31 186	72.50 173	88.31 28	93.86 60	69.66 81	91.96 223	89.81 9	91.05 98	93.38 92

mvs_tets		79.13 189	77.77 202	83.22 170	84.70 277	66.37 173	89.17 105	90.19 158	69.38 238	75.40 242	89.46 170	44.17 350	93.15 176	76.78 140	80.70 252	90.14 214

HQP-NCC					89.33 136		89.17 105		76.41 79	77.23 197

ACMP_Plane					89.33 136		89.17 105		76.41 79	77.23 197

HQP-MVS		82.61 114	82.02 118	84.37 112	89.33 136	66.98 165	89.17 105	92.19 90	76.41 79	77.23 197	90.23 151	60.17 205	95.11 87	77.47 130	85.99 179	91.03 178

LS3D		76.95 240	74.82 258	83.37 163	90.45 100	67.36 155	89.15 109	86.94 252	61.87 344	69.52 328	90.61 144	51.71 279	94.53 110	46.38 386	86.71 166	88.21 285

GDP-MVS		83.52 96	82.64 107	86.16 62	88.14 185	68.45 125	89.13 110	92.69 65	72.82 172	83.71 99	91.86 107	55.69 233	95.35 79	80.03 109	89.74 121	94.69 27

OPM-MVS		83.50 97	82.95 102	85.14 85	88.79 160	70.95 69	89.13 110	91.52 115	77.55 47	80.96 136	91.75 108	60.71 194	94.50 112	79.67 113	86.51 169	89.97 229
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
fmvsm_s_conf0.5_n_3		86.36 46	87.46 27	83.09 175	87.08 230	65.21 199	89.09 112	90.21 157	79.67 17	89.98 18	95.02 18	73.17 38	91.71 235	91.30 2	91.60 89	92.34 137

TSAR-MVS + GP.		85.71 59	85.33 68	86.84 50	91.34 81	72.50 36	89.07 113	87.28 243	76.41 79	85.80 61	90.22 152	74.15 31	95.37 78	81.82 92	91.88 84	92.65 126

test_prior4						72.60 34	89.01 114

GeoE		81.71 128	81.01 132	83.80 151	89.51 127	64.45 221	88.97 115	88.73 214	71.27 195	78.63 165	89.76 159	66.32 121	93.20 172	69.89 207	86.02 178	93.74 74

Anonymous20240529		80.19 166	78.89 174	84.10 128	90.60 97	64.75 214	88.95 116	90.90 133	65.97 293	80.59 139	91.17 130	49.97 297	93.73 147	69.16 215	82.70 229	93.81 71

VDD-MVS		83.01 110	82.36 111	84.96 93	91.02 88	66.40 172	88.91 117	88.11 222	77.57 44	84.39 86	93.29 75	52.19 266	93.91 135	77.05 136	88.70 137	94.57 35

Effi-MVS+		83.62 94	83.08 98	85.24 83	88.38 176	67.45 150	88.89 118	89.15 195	75.50 99	82.27 116	88.28 201	69.61 82	94.45 114	77.81 127	87.84 148	93.84 69

fmvsm_s_conf0.5_n_6		85.55 62	86.20 47	83.60 154	87.32 223	65.13 202	88.86 119	91.63 111	75.41 101	88.23 31	93.45 71	68.56 96	92.47 203	89.52 14	92.78 73	93.20 103

ACMH+	68.96 14	76.01 258	74.01 268	82.03 207	88.60 167	65.31 198	88.86 119	87.55 237	70.25 219	67.75 342	87.47 224	41.27 368	93.19 174	58.37 312	75.94 312	87.60 296

test_prior2							88.85 121		75.41 101	84.91 72	93.54 66	74.28 29		83.31 75	95.86 20

DP-MVS Recon		83.11 108	82.09 116	86.15 63	94.44 19	70.92 71	88.79 122	92.20 89	70.53 212	79.17 155	91.03 136	64.12 141	96.03 50	68.39 224	90.14 113	91.50 163

fmvsm_s_conf0.5_n_4		85.39 67	85.75 60	84.30 117	86.70 238	65.83 184	88.77 123	89.78 169	75.46 100	88.35 27	93.73 64	69.19 87	93.06 182	91.30 2	88.44 142	94.02 58

Effi-MVS+-dtu		80.03 168	78.57 179	84.42 111	85.13 271	68.74 114	88.77 123	88.10 223	74.99 113	74.97 260	83.49 324	57.27 224	93.36 162	73.53 170	80.88 248	91.18 172

TEST9					93.26 52	72.96 25	88.75 125	91.89 101	68.44 262	85.00 70	93.10 78	74.36 28	95.41 73

train_agg		86.43 43	86.20 47	87.13 44	93.26 52	72.96 25	88.75 125	91.89 101	68.69 257	85.00 70	93.10 78	74.43 26	95.41 73	84.97 53	95.71 25	93.02 114

ETV-MVS		84.90 77	84.67 77	85.59 75	89.39 134	68.66 120	88.74 127	92.64 72	79.97 15	84.10 91	85.71 270	69.32 85	95.38 75	80.82 102	91.37 94	92.72 121

PVSNet_Blended_VisFu		82.62 113	81.83 122	84.96 93	90.80 94	69.76 90	88.74 127	91.70 110	69.39 237	78.96 157	88.46 196	65.47 131	94.87 100	74.42 162	88.57 138	90.24 211

casdiffmvs_mvg		85.99 50	86.09 53	85.70 74	87.65 211	67.22 161	88.69 129	93.04 41	79.64 19	85.33 66	92.54 94	73.30 35	94.50 112	83.49 73	91.14 97	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 54	72.57 35	88.68 130	91.84 105	68.69 257	84.87 74	93.10 78	74.43 26	95.16 83

test_fmvsm_n_1920		85.29 69	85.34 67	85.13 88	86.12 249	69.93 86	88.65 131	90.78 137	69.97 225	88.27 29	93.98 56	71.39 60	91.54 242	88.49 30	90.45 108	93.91 63

ACMH	67.68 16	75.89 259	73.93 270	81.77 212	88.71 164	66.61 170	88.62 132	89.01 201	69.81 228	66.78 354	86.70 246	41.95 366	91.51 245	55.64 334	78.14 281	87.17 307
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CDPH-MVS		85.76 58	85.29 71	87.17 43	93.49 47	71.08 64	88.58 133	92.42 80	68.32 264	84.61 81	93.48 68	72.32 46	96.15 48	79.00 114	95.43 30	94.28 47

DP-MVS		76.78 243	74.57 260	83.42 160	93.29 48	69.46 97	88.55 134	83.70 297	63.98 320	70.20 316	88.89 183	54.01 250	94.80 102	46.66 383	81.88 238	86.01 332

fmvsm_l_conf0.5_n		84.47 79	84.54 78	84.27 121	85.42 262	68.81 109	88.49 135	87.26 245	68.08 266	88.03 35	93.49 67	72.04 50	91.77 231	88.90 24	89.14 129	92.24 144

WR-MVS_H		78.51 204	78.49 180	78.56 282	88.02 192	56.38 338	88.43 136	92.67 67	77.14 59	73.89 275	87.55 221	66.25 122	89.24 292	58.92 305	73.55 345	90.06 223

F-COLMAP		76.38 253	74.33 266	82.50 200	89.28 141	66.95 168	88.41 137	89.03 199	64.05 318	66.83 353	88.61 191	46.78 324	92.89 188	57.48 319	78.55 274	87.67 294

GBi-Net		78.40 205	77.40 211	81.40 221	87.60 212	63.01 251	88.39 138	89.28 187	71.63 186	75.34 245	87.28 226	54.80 239	91.11 256	62.72 267	79.57 264	90.09 219

test1		78.40 205	77.40 211	81.40 221	87.60 212	63.01 251	88.39 138	89.28 187	71.63 186	75.34 245	87.28 226	54.80 239	91.11 256	62.72 267	79.57 264	90.09 219

FMVSNet1		77.44 231	76.12 238	81.40 221	86.81 235	63.01 251	88.39 138	89.28 187	70.49 213	74.39 270	87.28 226	49.06 311	91.11 256	60.91 288	78.52 275	90.09 219

tttt0517		79.40 182	77.91 195	83.90 148	88.10 188	63.84 231	88.37 141	84.05 293	71.45 192	76.78 208	89.12 177	49.93 300	94.89 98	70.18 203	83.18 222	92.96 118

fmvsm_l_conf0.5_n_a		84.13 82	84.16 83	84.06 136	85.38 263	68.40 126	88.34 142	86.85 255	67.48 273	87.48 46	93.40 72	70.89 66	91.61 236	88.38 32	89.22 127	92.16 148

v7n		78.97 194	77.58 209	83.14 173	83.45 305	65.51 192	88.32 143	91.21 124	73.69 148	72.41 295	86.32 260	57.93 215	93.81 140	69.18 214	75.65 315	90.11 217

COLMAP_ROB	66.92 17	73.01 298	70.41 313	80.81 239	87.13 229	65.63 190	88.30 144	84.19 292	62.96 329	63.80 380	87.69 216	38.04 385	92.56 199	46.66 383	74.91 332	84.24 359
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FIs		82.07 121	82.42 108	81.04 233	88.80 159	58.34 305	88.26 145	93.49 26	76.93 65	78.47 170	91.04 134	69.92 78	92.34 211	69.87 208	84.97 187	92.44 135

EIA-MVS		83.31 104	82.80 105	84.82 99	89.59 123	65.59 191	88.21 146	92.68 66	74.66 125	78.96 157	86.42 257	69.06 90	95.26 80	75.54 153	90.09 114	93.62 83

PLC	70.83 11	78.05 216	76.37 236	83.08 177	91.88 77	67.80 141	88.19 147	89.46 181	64.33 313	69.87 325	88.38 198	53.66 252	93.58 149	58.86 306	82.73 227	87.86 291
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MG-MVS		83.41 99	83.45 92	83.28 165	92.74 65	62.28 263	88.17 148	89.50 180	75.22 106	81.49 128	92.74 93	66.75 113	95.11 87	72.85 179	91.58 91	92.45 134

TAPA-MVS	73.13 9	79.15 188	77.94 194	82.79 193	89.59 123	62.99 255	88.16 149	91.51 116	65.77 294	77.14 203	91.09 132	60.91 192	93.21 169	50.26 365	87.05 160	92.17 147
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test_fmvsmvis_n_1920		84.02 84	83.87 86	84.49 109	84.12 289	69.37 101	88.15 150	87.96 227	70.01 223	83.95 95	93.23 76	68.80 95	91.51 245	88.61 27	89.96 117	92.57 127

h-mvs33		83.15 105	82.19 113	86.02 69	90.56 98	70.85 73	88.15 150	89.16 194	76.02 90	84.67 77	91.39 122	61.54 177	95.50 66	82.71 85	75.48 319	91.72 157

PS-CasMVS		78.01 218	78.09 191	77.77 297	87.71 208	54.39 363	88.02 152	91.22 123	77.50 49	73.26 283	88.64 190	60.73 193	88.41 308	61.88 279	73.88 342	90.53 199

OMC-MVS		82.69 112	81.97 120	84.85 98	88.75 162	67.42 151	87.98 153	90.87 135	74.92 117	79.72 148	91.65 111	62.19 168	93.96 128	75.26 157	86.42 170	93.16 105

v8		79.97 170	79.02 172	82.80 191	84.09 290	64.50 219	87.96 154	90.29 155	74.13 140	75.24 252	86.81 239	62.88 157	93.89 138	74.39 163	75.40 324	90.00 225

FC-MVSNet-test		81.52 133	82.02 118	80.03 254	88.42 175	55.97 344	87.95 155	93.42 29	77.10 61	77.38 192	90.98 140	69.96 77	91.79 230	68.46 223	84.50 193	92.33 138

CP-MVSNet		78.22 209	78.34 185	77.84 295	87.83 202	54.54 361	87.94 156	91.17 126	77.65 41	73.48 281	88.49 195	62.24 167	88.43 307	62.19 275	74.07 338	90.55 198

PAPM_NR		83.02 109	82.41 109	84.82 99	92.47 70	66.37 173	87.93 157	91.80 106	73.82 145	77.32 194	90.66 143	67.90 104	94.90 97	70.37 201	89.48 124	93.19 104

PEN-MVS		77.73 224	77.69 206	77.84 295	87.07 231	53.91 366	87.91 158	91.18 125	77.56 46	73.14 285	88.82 185	61.23 186	89.17 293	59.95 294	72.37 353	90.43 203

ECVR-MVS		79.61 173	79.26 166	80.67 242	90.08 109	54.69 359	87.89 159	77.44 371	74.88 118	80.27 141	92.79 90	48.96 313	92.45 204	68.55 221	92.50 78	94.86 18

v10		79.74 172	78.67 176	82.97 184	84.06 291	64.95 208	87.88 160	90.62 140	73.11 165	75.11 256	86.56 253	61.46 180	94.05 127	73.68 168	75.55 317	89.90 231

test2506		77.30 235	76.49 232	79.74 260	90.08 109	52.02 376	87.86 161	63.10 418	74.88 118	80.16 144	92.79 90	38.29 384	92.35 210	68.74 220	92.50 78	94.86 18

casdiffmvs		85.11 72	85.14 72	85.01 91	87.20 226	65.77 188	87.75 162	92.83 60	77.84 39	84.36 87	92.38 96	72.15 48	93.93 134	81.27 98	90.48 107	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		80.84 144	80.31 143	82.42 201	87.85 200	62.33 261	87.74 163	91.33 121	80.55 9	77.99 182	89.86 156	65.23 133	92.62 194	67.05 236	75.24 329	92.30 140

EI-MVSNet-Vis-set		84.19 81	83.81 87	85.31 81	88.18 182	67.85 139	87.66 164	89.73 173	80.05 14	82.95 108	89.59 165	70.74 69	94.82 101	80.66 105	84.72 190	93.28 98

UniMVSNet (Re)		81.60 132	81.11 129	83.09 175	88.38 176	64.41 222	87.60 165	93.02 45	78.42 33	78.56 167	88.16 205	69.78 79	93.26 165	69.58 211	76.49 301	91.60 158

CNLPA		78.08 214	76.79 225	81.97 209	90.40 102	71.07 65	87.59 166	84.55 285	66.03 292	72.38 296	89.64 162	57.56 220	86.04 331	59.61 298	83.35 219	88.79 269

DTE-MVSNet		76.99 238	76.80 224	77.54 303	86.24 245	53.06 375	87.52 167	90.66 139	77.08 62	72.50 293	88.67 189	60.48 201	89.52 286	57.33 322	70.74 365	90.05 224

无先验							87.48 168	88.98 202	60.00 356				94.12 125	67.28 232		88.97 261

mvsmamba		80.60 154	79.38 161	84.27 121	89.74 121	67.24 160	87.47 169	86.95 251	70.02 222	75.38 243	88.93 181	51.24 283	92.56 199	75.47 155	89.22 127	93.00 116

FMVSNet2		78.20 211	77.21 215	81.20 228	87.60 212	62.89 257	87.47 169	89.02 200	71.63 186	75.29 251	87.28 226	54.80 239	91.10 259	62.38 272	79.38 268	89.61 241

RRT-MVS		82.60 116	82.10 115	84.10 128	87.98 195	62.94 256	87.45 171	91.27 122	77.42 51	79.85 146	90.28 148	56.62 230	94.70 107	79.87 112	88.15 146	94.67 28

EI-MVSNet-UG-set		83.81 86	83.38 94	85.09 89	87.87 199	67.53 149	87.44 172	89.66 174	79.74 16	82.23 117	89.41 174	70.24 75	94.74 104	79.95 110	83.92 204	92.99 117

thisisatest0530		79.40 182	77.76 203	84.31 116	87.69 210	65.10 205	87.36 173	84.26 291	70.04 221	77.42 191	88.26 203	49.94 298	94.79 103	70.20 202	84.70 191	93.03 113

CANet_DTU		80.61 153	79.87 151	82.83 188	85.60 259	63.17 250	87.36 173	88.65 215	76.37 83	75.88 230	88.44 197	53.51 254	93.07 181	73.30 174	89.74 121	92.25 142

test1111		79.43 180	79.18 169	80.15 252	89.99 114	53.31 372	87.33 175	77.05 375	75.04 112	80.23 143	92.77 92	48.97 312	92.33 212	68.87 218	92.40 80	94.81 21

baseline		84.93 75	84.98 73	84.80 101	87.30 224	65.39 196	87.30 176	92.88 57	77.62 42	84.04 93	92.26 98	71.81 52	93.96 128	81.31 96	90.30 110	95.03 10

UniMVSNet_ETH3D		79.10 190	78.24 188	81.70 213	86.85 233	60.24 290	87.28 177	88.79 208	74.25 136	76.84 205	90.53 146	49.48 303	91.56 240	67.98 225	82.15 233	93.29 97

anonymousdsp		78.60 202	77.15 216	82.98 183	80.51 359	67.08 163	87.24 178	89.53 179	65.66 296	75.16 254	87.19 232	52.52 260	92.25 214	77.17 134	79.34 269	89.61 241

UniMVSNet_NR-MVSNet		81.88 124	81.54 124	82.92 185	88.46 172	63.46 241	87.13 179	92.37 81	80.19 12	78.38 171	89.14 176	71.66 57	93.05 183	70.05 204	76.46 302	92.25 142

DPM-MVS		84.93 75	84.29 82	86.84 50	90.20 106	73.04 23	87.12 180	93.04 41	69.80 229	82.85 111	91.22 127	73.06 40	96.02 52	76.72 141	94.63 48	91.46 167

v1144		80.03 168	79.03 171	83.01 181	83.78 298	64.51 217	87.11 181	90.57 143	71.96 183	78.08 180	86.20 262	61.41 181	93.94 131	74.93 158	77.23 290	90.60 196

v2v482		80.23 164	79.29 165	83.05 179	83.62 301	64.14 226	87.04 182	89.97 164	73.61 150	78.18 177	87.22 230	61.10 189	93.82 139	76.11 144	76.78 299	91.18 172

fmvsm_s_conf0.1_n_2		83.80 87	83.79 88	83.83 149	85.62 258	64.94 209	87.03 183	86.62 259	74.32 132	87.97 38	94.33 35	60.67 196	92.60 196	89.72 10	87.79 149	93.96 60

DU-MVS		81.12 140	80.52 139	82.90 186	87.80 203	63.46 241	87.02 184	91.87 103	79.01 27	78.38 171	89.07 178	65.02 135	93.05 183	70.05 204	76.46 302	92.20 145

fmvsm_s_conf0.5_n_2		84.04 83	84.11 84	83.81 150	86.17 247	65.00 207	86.96 185	87.28 243	74.35 131	88.25 30	94.23 41	61.82 172	92.60 196	89.85 8	88.09 147	93.84 69

v144192		79.47 178	78.37 184	82.78 194	83.35 306	63.96 229	86.96 185	90.36 151	69.99 224	77.50 189	85.67 273	60.66 197	93.77 143	74.27 164	76.58 300	90.62 194

Fast-Effi-MVS+-dtu		78.02 217	76.49 232	82.62 198	83.16 314	66.96 167	86.94 187	87.45 241	72.45 174	71.49 307	84.17 309	54.79 242	91.58 238	67.61 228	80.31 257	89.30 249

v1192		79.59 175	78.43 183	83.07 178	83.55 303	64.52 216	86.93 188	90.58 141	70.83 203	77.78 185	85.90 266	59.15 208	93.94 131	73.96 167	77.19 292	90.76 188

EPNet_dtu		75.46 265	74.86 257	77.23 307	82.57 329	54.60 360	86.89 189	83.09 310	71.64 185	66.25 363	85.86 268	55.99 232	88.04 312	54.92 337	86.55 168	89.05 256
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
原ACMM2							86.86 190

VPA-MVSNet		80.60 154	80.55 138	80.76 240	88.07 190	60.80 281	86.86 190	91.58 114	75.67 97	80.24 142	89.45 172	63.34 146	90.25 273	70.51 200	79.22 271	91.23 171

v1921920		79.22 186	78.03 192	82.80 191	83.30 308	63.94 230	86.80 192	90.33 152	69.91 227	77.48 190	85.53 277	58.44 212	93.75 145	73.60 169	76.85 297	90.71 192

IterMVS-LS		80.06 167	79.38 161	82.11 205	85.89 252	63.20 248	86.79 193	89.34 184	74.19 137	75.45 240	86.72 242	66.62 115	92.39 207	72.58 182	76.86 296	90.75 189
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
TransMVSNet (Re)		75.39 269	74.56 261	77.86 294	85.50 261	57.10 326	86.78 194	86.09 269	72.17 180	71.53 306	87.34 225	63.01 156	89.31 290	56.84 328	61.83 392	87.17 307

Baseline_NR-MVSNet		78.15 213	78.33 186	77.61 300	85.79 253	56.21 342	86.78 194	85.76 272	73.60 151	77.93 183	87.57 219	65.02 135	88.99 296	67.14 235	75.33 326	87.63 295

PAPR		81.66 131	80.89 134	83.99 144	90.27 104	64.00 228	86.76 196	91.77 109	68.84 255	77.13 204	89.50 166	67.63 106	94.88 99	67.55 229	88.52 140	93.09 108

Vis-MVSNet (Re-imp)		78.36 207	78.45 181	78.07 293	88.64 166	51.78 382	86.70 197	79.63 354	74.14 139	75.11 256	90.83 141	61.29 185	89.75 282	58.10 315	91.60 89	92.69 124

pmmvs6		74.69 274	73.39 277	78.61 279	81.38 348	57.48 321	86.64 198	87.95 228	64.99 306	70.18 317	86.61 249	50.43 293	89.52 286	62.12 277	70.18 368	88.83 267

v1240		78.99 193	77.78 201	82.64 197	83.21 310	63.54 238	86.62 199	90.30 154	69.74 234	77.33 193	85.68 272	57.04 226	93.76 144	73.13 177	76.92 294	90.62 194

MTAPA		87.23 31	87.00 33	87.90 22	94.18 35	74.25 5	86.58 200	92.02 93	79.45 20	85.88 60	94.80 20	68.07 101	96.21 45	86.69 43	95.34 32	93.23 99

旧先验2							86.56 201		58.10 373	87.04 52			88.98 297	74.07 166

FMVSNet3		77.88 221	76.85 223	80.97 236	86.84 234	62.36 260	86.52 202	88.77 209	71.13 197	75.34 245	86.66 248	54.07 249	91.10 259	62.72 267	79.57 264	89.45 245

dcpmvs_2		85.63 60	86.15 51	84.06 136	91.71 78	64.94 209	86.47 203	91.87 103	73.63 149	86.60 57	93.02 83	76.57 15	91.87 229	83.36 74	92.15 81	95.35 3

pm-mvs1		77.25 236	76.68 230	78.93 275	84.22 287	58.62 302	86.41 204	88.36 220	71.37 193	73.31 282	88.01 211	61.22 187	89.15 294	64.24 258	73.01 350	89.03 257

EI-MVSNet		80.52 158	79.98 148	82.12 204	84.28 285	63.19 249	86.41 204	88.95 205	74.18 138	78.69 162	87.54 222	66.62 115	92.43 205	72.57 183	80.57 254	90.74 190

CVMVSNet		72.99 299	72.58 288	74.25 338	84.28 285	50.85 390	86.41 204	83.45 303	44.56 409	73.23 284	87.54 222	49.38 305	85.70 334	65.90 244	78.44 277	86.19 327

MonoMVSNet		76.49 250	75.80 239	78.58 281	81.55 344	58.45 303	86.36 207	86.22 265	74.87 120	74.73 264	83.73 318	51.79 278	88.73 302	70.78 195	72.15 356	88.55 279

NR-MVSNet		80.23 164	79.38 161	82.78 194	87.80 203	63.34 244	86.31 208	91.09 130	79.01 27	72.17 299	89.07 178	67.20 111	92.81 192	66.08 243	75.65 315	92.20 145

v148		78.72 199	77.80 200	81.47 218	82.73 325	61.96 267	86.30 209	88.08 224	73.26 162	76.18 225	85.47 279	62.46 162	92.36 209	71.92 187	73.82 343	90.09 219

新几何2							86.29 210

test_yl		81.17 138	80.47 140	83.24 168	89.13 147	63.62 234	86.21 211	89.95 165	72.43 177	81.78 125	89.61 163	57.50 221	93.58 149	70.75 196	86.90 162	92.52 129

DCV-MVSNet		81.17 138	80.47 140	83.24 168	89.13 147	63.62 234	86.21 211	89.95 165	72.43 177	81.78 125	89.61 163	57.50 221	93.58 149	70.75 196	86.90 162	92.52 129

PVSNet_BlendedMVS		80.60 154	80.02 147	82.36 203	88.85 154	65.40 194	86.16 213	92.00 95	69.34 239	78.11 178	86.09 265	66.02 126	94.27 118	71.52 188	82.06 235	87.39 301

MVS_Test		83.15 105	83.06 99	83.41 162	86.86 232	63.21 247	86.11 214	92.00 95	74.31 133	82.87 110	89.44 173	70.03 76	93.21 169	77.39 132	88.50 141	93.81 71

BH-untuned		79.47 178	78.60 178	82.05 206	89.19 145	65.91 182	86.07 215	88.52 218	72.18 179	75.42 241	87.69 216	61.15 188	93.54 153	60.38 291	86.83 164	86.70 320

MVS_111021_HR		85.14 71	84.75 76	86.32 58	91.65 79	72.70 30	85.98 216	90.33 152	76.11 88	82.08 119	91.61 115	71.36 61	94.17 124	81.02 99	92.58 76	92.08 150

jason		81.39 136	80.29 144	84.70 103	86.63 241	69.90 88	85.95 217	86.77 256	63.24 324	81.07 135	89.47 168	61.08 190	92.15 217	78.33 123	90.07 116	92.05 151
jason: jason.
test_0402		72.79 301	70.44 312	79.84 258	88.13 186	65.99 180	85.93 218	84.29 289	65.57 297	67.40 348	85.49 278	46.92 323	92.61 195	35.88 411	74.38 337	80.94 390

OurMVSNet-221017-0		74.26 277	72.42 290	79.80 259	83.76 299	59.59 297	85.92 219	86.64 257	66.39 287	66.96 351	87.58 218	39.46 376	91.60 237	65.76 246	69.27 371	88.22 284

hse-mvs2		81.72 127	80.94 133	84.07 134	88.72 163	67.68 144	85.87 220	87.26 245	76.02 90	84.67 77	88.22 204	61.54 177	93.48 156	82.71 85	73.44 347	91.06 176

EG-PatchMatch MVS		74.04 281	71.82 295	80.71 241	84.92 274	67.42 151	85.86 221	88.08 224	66.04 291	64.22 375	83.85 313	35.10 393	92.56 199	57.44 320	80.83 249	82.16 384

AUN-MVS		79.21 187	77.60 208	84.05 139	88.71 164	67.61 146	85.84 222	87.26 245	69.08 248	77.23 197	88.14 209	53.20 258	93.47 157	75.50 154	73.45 346	91.06 176

thres100view900		76.50 247	75.55 246	79.33 268	89.52 126	56.99 327	85.83 223	83.23 306	73.94 142	76.32 221	87.12 234	51.89 275	91.95 224	48.33 374	83.75 208	89.07 251

CLD-MVS		82.31 117	81.65 123	84.29 118	88.47 171	67.73 143	85.81 224	92.35 82	75.78 93	78.33 173	86.58 252	64.01 142	94.35 115	76.05 146	87.48 154	90.79 186
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
SixPastTwentyTwo		73.37 290	71.26 304	79.70 261	85.08 272	57.89 313	85.57 225	83.56 300	71.03 201	65.66 365	85.88 267	42.10 364	92.57 198	59.11 303	63.34 390	88.65 275

xiu_mvs_v1_base_debu		80.80 148	79.72 154	84.03 141	87.35 217	70.19 82	85.56 226	88.77 209	69.06 249	81.83 121	88.16 205	50.91 286	92.85 189	78.29 124	87.56 151	89.06 253

xiu_mvs_v1_base		80.80 148	79.72 154	84.03 141	87.35 217	70.19 82	85.56 226	88.77 209	69.06 249	81.83 121	88.16 205	50.91 286	92.85 189	78.29 124	87.56 151	89.06 253

xiu_mvs_v1_base_debi		80.80 148	79.72 154	84.03 141	87.35 217	70.19 82	85.56 226	88.77 209	69.06 249	81.83 121	88.16 205	50.91 286	92.85 189	78.29 124	87.56 151	89.06 253

V42		79.38 184	78.24 188	82.83 188	81.10 353	65.50 193	85.55 229	89.82 168	71.57 190	78.21 175	86.12 264	60.66 197	93.18 175	75.64 150	75.46 321	89.81 236

lupinMVS		81.39 136	80.27 145	84.76 102	87.35 217	70.21 80	85.55 229	86.41 261	62.85 331	81.32 129	88.61 191	61.68 174	92.24 215	78.41 122	90.26 111	91.83 154

Fast-Effi-MVS+		80.81 146	79.92 149	83.47 158	88.85 154	64.51 217	85.53 231	89.39 183	70.79 204	78.49 169	85.06 289	67.54 107	93.58 149	67.03 237	86.58 167	92.32 139

thres600view7		76.50 247	75.44 247	79.68 262	89.40 133	57.16 324	85.53 231	83.23 306	73.79 146	76.26 222	87.09 235	51.89 275	91.89 227	48.05 379	83.72 211	90.00 225

DELS-MVS		85.41 66	85.30 70	85.77 72	88.49 170	67.93 138	85.52 233	93.44 27	78.70 30	83.63 103	89.03 180	74.57 24	95.71 61	80.26 108	94.04 61	93.66 76
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		83.34 102	84.03 85	81.28 225	85.73 255	65.13 202	85.40 234	89.90 167	74.96 116	82.13 118	93.89 59	66.65 114	87.92 313	86.56 44	91.05 98	90.80 185

tfpn200view9		76.42 251	75.37 251	79.55 267	89.13 147	57.65 318	85.17 235	83.60 298	73.41 158	76.45 217	86.39 258	52.12 267	91.95 224	48.33 374	83.75 208	89.07 251

thres400		76.50 247	75.37 251	79.86 257	89.13 147	57.65 318	85.17 235	83.60 298	73.41 158	76.45 217	86.39 258	52.12 267	91.95 224	48.33 374	83.75 208	90.00 225

MVS_111021_LR		82.61 114	82.11 114	84.11 127	88.82 157	71.58 55	85.15 237	86.16 267	74.69 123	80.47 140	91.04 134	62.29 165	90.55 270	80.33 107	90.08 115	90.20 212

baseline1		76.98 239	76.75 228	77.66 298	88.13 186	55.66 349	85.12 238	81.89 326	73.04 167	76.79 207	88.90 182	62.43 163	87.78 316	63.30 264	71.18 363	89.55 243

mmtdpeth		74.16 279	73.01 283	77.60 302	83.72 300	61.13 275	85.10 239	85.10 278	72.06 182	77.21 201	80.33 363	43.84 352	85.75 333	77.14 135	52.61 410	85.91 335

WR-MVS		79.49 177	79.22 168	80.27 250	88.79 160	58.35 304	85.06 240	88.61 217	78.56 31	77.65 187	88.34 199	63.81 145	90.66 269	64.98 252	77.22 291	91.80 156

ET-MVSNet_ETH3D		78.63 201	76.63 231	84.64 104	86.73 237	69.47 95	85.01 241	84.61 284	69.54 235	66.51 361	86.59 250	50.16 295	91.75 232	76.26 143	84.24 201	92.69 124

OpenMVS_ROB	64.09 19	70.56 321	68.19 327	77.65 299	80.26 360	59.41 299	85.01 241	82.96 315	58.76 368	65.43 367	82.33 343	37.63 387	91.23 255	45.34 393	76.03 311	82.32 381

BH-RMVSNet		79.61 173	78.44 182	83.14 173	89.38 135	65.93 181	84.95 243	87.15 248	73.56 152	78.19 176	89.79 158	56.67 229	93.36 162	59.53 299	86.74 165	90.13 215

BH-w/o		78.21 210	77.33 214	80.84 238	88.81 158	65.13 202	84.87 244	87.85 232	69.75 232	74.52 268	84.74 296	61.34 183	93.11 179	58.24 314	85.84 181	84.27 358

TDRefinement		67.49 345	64.34 356	76.92 309	73.47 404	61.07 277	84.86 245	82.98 314	59.77 358	58.30 399	85.13 287	26.06 408	87.89 314	47.92 380	60.59 397	81.81 386

Anonymous202405211		78.25 208	77.01 218	81.99 208	91.03 87	60.67 283	84.77 246	83.90 295	70.65 211	80.00 145	91.20 128	41.08 370	91.43 249	65.21 249	85.26 185	93.85 67

TAMVS		78.89 196	77.51 210	83.03 180	87.80 203	67.79 142	84.72 247	85.05 280	67.63 269	76.75 209	87.70 215	62.25 166	90.82 265	58.53 310	87.13 159	90.49 201

1314		76.53 246	75.30 253	80.21 251	83.93 294	62.32 262	84.66 248	88.81 207	60.23 354	70.16 319	84.07 311	55.30 236	90.73 268	67.37 231	83.21 221	87.59 298

MVS		78.19 212	76.99 220	81.78 211	85.66 256	66.99 164	84.66 248	90.47 145	55.08 389	72.02 301	85.27 282	63.83 144	94.11 126	66.10 242	89.80 120	84.24 359

tfpnnormal		74.39 275	73.16 281	78.08 292	86.10 251	58.05 308	84.65 250	87.53 238	70.32 216	71.22 309	85.63 274	54.97 237	89.86 279	43.03 397	75.02 331	86.32 324

TR-MVS		77.44 231	76.18 237	81.20 228	88.24 180	63.24 246	84.61 251	86.40 262	67.55 271	77.81 184	86.48 256	54.10 248	93.15 176	57.75 318	82.72 228	87.20 306

AllTest		70.96 315	68.09 330	79.58 265	85.15 269	63.62 234	84.58 252	79.83 351	62.31 338	60.32 392	86.73 240	32.02 398	88.96 299	50.28 363	71.57 361	86.15 328

FA-MVS(test-final)		80.96 142	79.91 150	84.10 128	88.30 179	65.01 206	84.55 253	90.01 163	73.25 163	79.61 149	87.57 219	58.35 213	94.72 105	71.29 192	86.25 173	92.56 128

EU-MVSNet		68.53 340	67.61 340	71.31 365	78.51 381	47.01 403	84.47 254	84.27 290	42.27 412	66.44 362	84.79 295	40.44 373	83.76 351	58.76 308	68.54 376	83.17 371

VNet		82.21 118	82.41 109	81.62 214	90.82 93	60.93 278	84.47 254	89.78 169	76.36 84	84.07 92	91.88 105	64.71 138	90.26 272	70.68 198	88.89 131	93.66 76

xiu_mvs_v2_base		81.69 129	81.05 130	83.60 154	89.15 146	68.03 137	84.46 256	90.02 162	70.67 207	81.30 132	86.53 255	63.17 151	94.19 123	75.60 152	88.54 139	88.57 278

VPNet		78.69 200	78.66 177	78.76 277	88.31 178	55.72 348	84.45 257	86.63 258	76.79 69	78.26 174	90.55 145	59.30 207	89.70 284	66.63 238	77.05 293	90.88 183

PVSNet_Blended		80.98 141	80.34 142	82.90 186	88.85 154	65.40 194	84.43 258	92.00 95	67.62 270	78.11 178	85.05 290	66.02 126	94.27 118	71.52 188	89.50 123	89.01 258

MVP-Stereo		76.12 255	74.46 264	81.13 231	85.37 264	69.79 89	84.42 259	87.95 228	65.03 304	67.46 346	85.33 281	53.28 257	91.73 234	58.01 316	83.27 220	81.85 385
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CDS-MVSNet		79.07 191	77.70 205	83.17 172	87.60 212	68.23 131	84.40 260	86.20 266	67.49 272	76.36 220	86.54 254	61.54 177	90.79 266	61.86 280	87.33 156	90.49 201
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
K. test v3		71.19 312	68.51 324	79.21 271	83.04 317	57.78 317	84.35 261	76.91 376	72.90 170	62.99 383	82.86 336	39.27 377	91.09 261	61.65 282	52.66 409	88.75 271

PS-MVSNAJ		81.69 129	81.02 131	83.70 152	89.51 127	68.21 132	84.28 262	90.09 161	70.79 204	81.26 133	85.62 275	63.15 152	94.29 116	75.62 151	88.87 132	88.59 277

patch_mono-2		83.65 91	84.54 78	80.99 234	90.06 113	65.83 184	84.21 263	88.74 213	71.60 189	85.01 69	92.44 95	74.51 25	83.50 355	82.15 90	92.15 81	93.64 82

test222					91.50 80	68.26 130	84.16 264	83.20 309	54.63 390	79.74 147	91.63 113	58.97 209			91.42 93	86.77 318

testdata1							84.14 265		75.71 94

c3_l		78.75 197	77.91 195	81.26 226	82.89 322	61.56 272	84.09 266	89.13 197	69.97 225	75.56 235	84.29 304	66.36 120	92.09 219	73.47 172	75.48 319	90.12 216

MVSTER		79.01 192	77.88 197	82.38 202	83.07 315	64.80 213	84.08 267	88.95 205	69.01 252	78.69 162	87.17 233	54.70 243	92.43 205	74.69 159	80.57 254	89.89 232

ab-mvs		79.51 176	78.97 173	81.14 230	88.46 172	60.91 279	83.84 268	89.24 191	70.36 214	79.03 156	88.87 184	63.23 150	90.21 274	65.12 250	82.57 230	92.28 141

reproduce_monomvs		75.40 268	74.38 265	78.46 287	83.92 295	57.80 316	83.78 269	86.94 252	73.47 156	72.25 298	84.47 298	38.74 380	89.27 291	75.32 156	70.53 366	88.31 283

PAPM		77.68 228	76.40 235	81.51 217	87.29 225	61.85 268	83.78 269	89.59 177	64.74 307	71.23 308	88.70 187	62.59 159	93.66 148	52.66 349	87.03 161	89.01 258

diffmvs		82.10 119	81.88 121	82.76 196	83.00 318	63.78 233	83.68 271	89.76 171	72.94 169	82.02 120	89.85 157	65.96 128	90.79 266	82.38 89	87.30 157	93.71 75
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		78.59 203	77.76 203	81.08 232	82.66 327	61.56 272	83.65 272	89.15 195	68.87 254	75.55 236	83.79 316	66.49 118	92.03 220	73.25 175	76.39 304	89.64 240

1112_ss		77.40 233	76.43 234	80.32 249	89.11 151	60.41 288	83.65 272	87.72 235	62.13 341	73.05 286	86.72 242	62.58 160	89.97 278	62.11 278	80.80 250	90.59 197

PCF-MVS	73.52 7	80.38 160	78.84 175	85.01 91	87.71 208	68.99 106	83.65 272	91.46 120	63.00 328	77.77 186	90.28 148	66.10 123	95.09 91	61.40 284	88.22 145	90.94 182
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
XVG-ACMP-BASELINE		76.11 256	74.27 267	81.62 214	83.20 311	64.67 215	83.60 275	89.75 172	69.75 232	71.85 302	87.09 235	32.78 397	92.11 218	69.99 206	80.43 256	88.09 287

cl22		78.07 215	77.01 218	81.23 227	82.37 334	61.83 269	83.55 276	87.98 226	68.96 253	75.06 258	83.87 312	61.40 182	91.88 228	73.53 170	76.39 304	89.98 228

XVG-OURS-SEG-HR		80.81 146	79.76 153	83.96 146	85.60 259	68.78 111	83.54 277	90.50 144	70.66 210	76.71 210	91.66 110	60.69 195	91.26 253	76.94 137	81.58 240	91.83 154

IB-MVS	68.01 15	75.85 260	73.36 279	83.31 164	84.76 276	66.03 177	83.38 278	85.06 279	70.21 220	69.40 329	81.05 354	45.76 337	94.66 108	65.10 251	75.49 318	89.25 250
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	77.95 219	77.15 216	80.36 247	87.57 216	60.21 291	83.37 279	87.78 234	66.11 289	75.37 244	87.06 237	63.27 148	90.48 271	61.38 285	82.43 231	90.40 205

test_vis1_n_1920		75.52 264	75.78 240	74.75 334	79.84 367	57.44 322	83.26 280	85.52 274	62.83 332	79.34 154	86.17 263	45.10 343	79.71 375	78.75 117	81.21 244	87.10 313

Anonymous20240521		68.80 336	67.22 345	73.55 344	74.33 396	54.11 364	83.18 281	85.61 273	58.15 372	61.68 387	80.94 357	30.71 403	81.27 369	57.00 326	73.34 349	85.28 344

eth_miper_zixun_eth		77.92 220	76.69 229	81.61 216	83.00 318	61.98 266	83.15 282	89.20 193	69.52 236	74.86 262	84.35 303	61.76 173	92.56 199	71.50 190	72.89 351	90.28 210

FE-MVS		77.78 223	75.68 242	84.08 133	88.09 189	66.00 179	83.13 283	87.79 233	68.42 263	78.01 181	85.23 284	45.50 341	95.12 85	59.11 303	85.83 182	91.11 174

cl____		77.72 225	76.76 226	80.58 243	82.49 331	60.48 286	83.09 284	87.87 230	69.22 243	74.38 271	85.22 285	62.10 169	91.53 243	71.09 193	75.41 323	89.73 239

DIV-MVS_self_test		77.72 225	76.76 226	80.58 243	82.48 332	60.48 286	83.09 284	87.86 231	69.22 243	74.38 271	85.24 283	62.10 169	91.53 243	71.09 193	75.40 324	89.74 238

thres200		75.55 263	74.47 263	78.82 276	87.78 206	57.85 314	83.07 286	83.51 301	72.44 176	75.84 231	84.42 299	52.08 270	91.75 232	47.41 381	83.64 213	86.86 316

testing3		68.56 339	67.67 339	71.22 366	87.33 222	42.87 416	83.06 287	71.54 396	70.36 214	69.08 333	84.38 301	30.33 404	85.69 335	37.50 409	75.45 322	85.09 350

XVG-OURS		80.41 159	79.23 167	83.97 145	85.64 257	69.02 105	83.03 288	90.39 147	71.09 199	77.63 188	91.49 119	54.62 245	91.35 251	75.71 149	83.47 217	91.54 161

miper_enhance_ethall		77.87 222	76.86 222	80.92 237	81.65 341	61.38 274	82.68 289	88.98 202	65.52 298	75.47 237	82.30 344	65.76 130	92.00 222	72.95 178	76.39 304	89.39 246

mvs_anonymous		79.42 181	79.11 170	80.34 248	84.45 284	57.97 311	82.59 290	87.62 236	67.40 274	76.17 227	88.56 194	68.47 97	89.59 285	70.65 199	86.05 177	93.47 90

baseline2		75.70 261	73.83 273	81.30 224	83.26 309	61.79 270	82.57 291	80.65 340	66.81 276	66.88 352	83.42 325	57.86 217	92.19 216	63.47 261	79.57 264	89.91 230

cascas		76.72 244	74.64 259	82.99 182	85.78 254	65.88 183	82.33 292	89.21 192	60.85 350	72.74 289	81.02 355	47.28 320	93.75 145	67.48 230	85.02 186	89.34 248

WB-MVSnew		71.96 309	71.65 297	72.89 351	84.67 281	51.88 380	82.29 293	77.57 368	62.31 338	73.67 279	83.00 332	53.49 255	81.10 370	45.75 390	82.13 234	85.70 338

RPSCF		73.23 295	71.46 299	78.54 283	82.50 330	59.85 293	82.18 294	82.84 318	58.96 366	71.15 310	89.41 174	45.48 342	84.77 346	58.82 307	71.83 359	91.02 180

thisisatest0515		77.33 234	75.38 250	83.18 171	85.27 266	63.80 232	82.11 295	83.27 305	65.06 303	75.91 229	83.84 314	49.54 302	94.27 118	67.24 233	86.19 174	91.48 165

pmmvs-eth3d		70.50 322	67.83 335	78.52 285	77.37 385	66.18 176	81.82 296	81.51 331	58.90 367	63.90 379	80.42 362	42.69 359	86.28 329	58.56 309	65.30 386	83.11 373

MS-PatchMatch		73.83 284	72.67 286	77.30 306	83.87 296	66.02 178	81.82 296	84.66 283	61.37 348	68.61 337	82.82 337	47.29 319	88.21 309	59.27 300	84.32 200	77.68 400

pmmvs5		71.55 310	70.20 316	75.61 319	77.83 382	56.39 337	81.74 298	80.89 336	57.76 375	67.46 346	84.49 297	49.26 308	85.32 341	57.08 324	75.29 327	85.11 349

Test_1112_low_res		76.40 252	75.44 247	79.27 269	89.28 141	58.09 307	81.69 299	87.07 249	59.53 361	72.48 294	86.67 247	61.30 184	89.33 289	60.81 290	80.15 259	90.41 204

IterMVS		74.29 276	72.94 284	78.35 288	81.53 345	63.49 240	81.58 300	82.49 320	68.06 267	69.99 322	83.69 320	51.66 280	85.54 337	65.85 245	71.64 360	86.01 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		75.43 266	73.87 272	80.11 253	82.69 326	64.85 212	81.57 301	83.47 302	69.16 246	70.49 313	84.15 310	51.95 273	88.15 310	69.23 213	72.14 357	87.34 303

test_vis1_n		69.85 329	69.21 320	71.77 359	72.66 410	55.27 355	81.48 302	76.21 380	52.03 397	75.30 250	83.20 329	28.97 405	76.22 395	74.60 160	78.41 279	83.81 365

pmmvs4		74.03 283	71.91 294	80.39 246	81.96 337	68.32 128	81.45 303	82.14 323	59.32 362	69.87 325	85.13 287	52.40 263	88.13 311	60.21 293	74.74 334	84.73 355

GA-MVS		76.87 241	75.17 255	81.97 209	82.75 324	62.58 258	81.44 304	86.35 264	72.16 181	74.74 263	82.89 335	46.20 332	92.02 221	68.85 219	81.09 245	91.30 170

UWE-MVS		72.13 307	71.49 298	74.03 340	86.66 240	47.70 399	81.40 305	76.89 377	63.60 323	75.59 234	84.22 308	39.94 375	85.62 336	48.98 371	86.13 176	88.77 270

test_fmvs1_n		70.86 317	70.24 315	72.73 353	72.51 411	55.28 354	81.27 306	79.71 353	51.49 400	78.73 161	84.87 292	27.54 407	77.02 387	76.06 145	79.97 262	85.88 336

testing91		76.54 245	75.66 244	79.18 272	88.43 174	55.89 345	81.08 307	83.00 313	73.76 147	75.34 245	84.29 304	46.20 332	90.07 276	64.33 256	84.50 193	91.58 160

testing222		74.04 281	72.66 287	78.19 290	87.89 198	55.36 352	81.06 308	79.20 359	71.30 194	74.65 266	83.57 323	39.11 379	88.67 304	51.43 357	85.75 183	90.53 199

test_fmvs1		70.93 316	70.52 310	72.16 357	73.71 400	55.05 356	80.82 309	78.77 361	51.21 401	78.58 166	84.41 300	31.20 402	76.94 388	75.88 148	80.12 261	84.47 357

CostFormer		75.24 270	73.90 271	79.27 269	82.65 328	58.27 306	80.80 310	82.73 319	61.57 345	75.33 249	83.13 330	55.52 234	91.07 262	64.98 252	78.34 280	88.45 280

testing99		76.09 257	75.12 256	79.00 273	88.16 183	55.50 351	80.79 311	81.40 333	73.30 161	75.17 253	84.27 307	44.48 347	90.02 277	64.28 257	84.22 202	91.48 165

MIMVSNet1		68.58 338	66.78 348	73.98 341	80.07 364	51.82 381	80.77 312	84.37 286	64.40 311	59.75 395	82.16 347	36.47 389	83.63 353	42.73 398	70.33 367	86.48 323

CL-MVSNet_self_test		72.37 304	71.46 299	75.09 328	79.49 374	53.53 368	80.76 313	85.01 281	69.12 247	70.51 312	82.05 348	57.92 216	84.13 349	52.27 351	66.00 384	87.60 296

testing11		75.14 271	74.01 268	78.53 284	88.16 183	56.38 338	80.74 314	80.42 345	70.67 207	72.69 292	83.72 319	43.61 354	89.86 279	62.29 274	83.76 207	89.36 247

MSDG		73.36 292	70.99 306	80.49 245	84.51 283	65.80 186	80.71 315	86.13 268	65.70 295	65.46 366	83.74 317	44.60 345	90.91 264	51.13 358	76.89 295	84.74 354

tpm2		73.26 294	71.46 299	78.63 278	83.34 307	56.71 332	80.65 316	80.40 346	56.63 383	73.55 280	82.02 349	51.80 277	91.24 254	56.35 332	78.42 278	87.95 288

XXY-MVS		75.41 267	75.56 245	74.96 329	83.59 302	57.82 315	80.59 317	83.87 296	66.54 286	74.93 261	88.31 200	63.24 149	80.09 374	62.16 276	76.85 297	86.97 314

test_cas_vis1_n_1920		73.76 285	73.74 274	73.81 343	75.90 389	59.77 294	80.51 318	82.40 321	58.30 371	81.62 127	85.69 271	44.35 349	76.41 393	76.29 142	78.61 273	85.23 345

EGC-MVSNET		52.07 385	47.05 389	67.14 385	83.51 304	60.71 282	80.50 319	67.75 407	0.07 435	0.43 436	75.85 397	24.26 413	81.54 367	28.82 418	62.25 391	59.16 418

SDMVSNet		80.38 160	80.18 146	80.99 234	89.03 152	64.94 209	80.45 320	89.40 182	75.19 109	76.61 214	89.98 154	60.61 199	87.69 317	76.83 139	83.55 214	90.33 207

HyFIR lowres test		77.53 230	75.40 249	83.94 147	89.59 123	66.62 169	80.36 321	88.64 216	56.29 385	76.45 217	85.17 286	57.64 219	93.28 164	61.34 286	83.10 223	91.91 153

D2MVS		74.82 273	73.21 280	79.64 264	79.81 368	62.56 259	80.34 322	87.35 242	64.37 312	68.86 334	82.66 339	46.37 328	90.10 275	67.91 226	81.24 243	86.25 325

testing3-2		75.12 272	75.19 254	74.91 330	90.40 102	45.09 411	80.29 323	78.42 363	78.37 36	76.54 216	87.75 213	44.36 348	87.28 320	57.04 325	83.49 216	92.37 136

TinyColmap		67.30 348	64.81 354	74.76 333	81.92 339	56.68 333	80.29 323	81.49 332	60.33 352	56.27 406	83.22 327	24.77 412	87.66 318	45.52 391	69.47 370	79.95 395

LCM-MVSNet-Re		77.05 237	76.94 221	77.36 304	87.20 226	51.60 383	80.06 325	80.46 344	75.20 108	67.69 343	86.72 242	62.48 161	88.98 297	63.44 262	89.25 126	91.51 162

test_fmvs2		68.35 342	67.48 342	70.98 368	69.50 414	51.95 378	80.05 326	76.38 379	49.33 403	74.65 266	84.38 301	23.30 416	75.40 404	74.51 161	75.17 330	85.60 339

FMVSNet5		69.50 330	67.96 331	74.15 339	82.97 321	55.35 353	80.01 327	82.12 324	62.56 336	63.02 381	81.53 351	36.92 388	81.92 365	48.42 373	74.06 339	85.17 348

SCA		74.22 278	72.33 291	79.91 256	84.05 292	62.17 264	79.96 328	79.29 358	66.30 288	72.38 296	80.13 365	51.95 273	88.60 305	59.25 301	77.67 288	88.96 262

tpmrst		72.39 302	72.13 293	73.18 350	80.54 358	49.91 394	79.91 329	79.08 360	63.11 326	71.69 304	79.95 367	55.32 235	82.77 360	65.66 247	73.89 341	86.87 315

PatchmatchNet		73.12 296	71.33 302	78.49 286	83.18 312	60.85 280	79.63 330	78.57 362	64.13 314	71.73 303	79.81 370	51.20 284	85.97 332	57.40 321	76.36 309	88.66 274
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PatchMatch-RL		72.38 303	70.90 307	76.80 311	88.60 167	67.38 154	79.53 331	76.17 381	62.75 334	69.36 330	82.00 350	45.51 340	84.89 345	53.62 344	80.58 253	78.12 399

CMPMVS	51.72 21	70.19 325	68.16 328	76.28 313	73.15 407	57.55 320	79.47 332	83.92 294	48.02 405	56.48 405	84.81 294	43.13 356	86.42 328	62.67 270	81.81 239	84.89 352
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
ETVMVS		72.25 306	71.05 305	75.84 316	87.77 207	51.91 379	79.39 333	74.98 384	69.26 241	73.71 277	82.95 333	40.82 372	86.14 330	46.17 387	84.43 198	89.47 244

GG-mvs-BLEND				75.38 325	81.59 343	55.80 347	79.32 334	69.63 401		67.19 349	73.67 402	43.24 355	88.90 301	50.41 360	84.50 193	81.45 387

LTVRE_ROB	69.57 13	76.25 254	74.54 262	81.41 220	88.60 167	64.38 223	79.24 335	89.12 198	70.76 206	69.79 327	87.86 212	49.09 310	93.20 172	56.21 333	80.16 258	86.65 321
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		72.37 304	71.71 296	74.35 337	82.19 335	52.00 377	79.22 336	77.29 373	64.56 309	72.95 288	83.68 321	51.35 281	83.26 358	58.33 313	75.80 313	87.81 292

mvs5depth		69.45 331	67.45 343	75.46 324	73.93 398	55.83 346	79.19 337	83.23 306	66.89 275	71.63 305	83.32 326	33.69 396	85.09 342	59.81 296	55.34 406	85.46 341

ppachtmachnet_test		70.04 326	67.34 344	78.14 291	79.80 369	61.13 275	79.19 337	80.59 341	59.16 364	65.27 368	79.29 373	46.75 325	87.29 319	49.33 369	66.72 379	86.00 334

USDC		70.33 323	68.37 325	76.21 314	80.60 357	56.23 341	79.19 337	86.49 260	60.89 349	61.29 388	85.47 279	31.78 400	89.47 288	53.37 346	76.21 310	82.94 377

sd_testset		77.70 227	77.40 211	78.60 280	89.03 152	60.02 292	79.00 340	85.83 271	75.19 109	76.61 214	89.98 154	54.81 238	85.46 339	62.63 271	83.55 214	90.33 207

PM-MVS		66.41 354	64.14 357	73.20 349	73.92 399	56.45 335	78.97 341	64.96 415	63.88 322	64.72 372	80.24 364	19.84 420	83.44 356	66.24 239	64.52 388	79.71 396

tpmvs		71.09 314	69.29 319	76.49 312	82.04 336	56.04 343	78.92 342	81.37 334	64.05 318	67.18 350	78.28 382	49.74 301	89.77 281	49.67 368	72.37 353	83.67 367

test_post1							78.90 343				5.43 434	48.81 315	85.44 340	59.25 301

mamv4		76.81 242	78.23 190	72.54 355	86.12 249	65.75 189	78.76 344	82.07 325	64.12 315	72.97 287	91.02 137	67.97 102	68.08 420	83.04 79	78.02 282	83.80 366

CHOSEN 1792x2688		77.63 229	75.69 241	83.44 159	89.98 115	68.58 122	78.70 345	87.50 239	56.38 384	75.80 232	86.84 238	58.67 210	91.40 250	61.58 283	85.75 183	90.34 206

Syy-MVS		68.05 343	67.85 333	68.67 379	84.68 278	40.97 422	78.62 346	73.08 393	66.65 283	66.74 355	79.46 371	52.11 269	82.30 362	32.89 414	76.38 307	82.75 378

myMVS_eth3d		67.02 349	66.29 350	69.21 374	84.68 278	42.58 417	78.62 346	73.08 393	66.65 283	66.74 355	79.46 371	31.53 401	82.30 362	39.43 406	76.38 307	82.75 378

WBMVS		73.43 289	72.81 285	75.28 326	87.91 197	50.99 389	78.59 348	81.31 335	65.51 300	74.47 269	84.83 293	46.39 326	86.68 324	58.41 311	77.86 283	88.17 286

test-LLR		72.94 300	72.43 289	74.48 335	81.35 349	58.04 309	78.38 349	77.46 369	66.66 280	69.95 323	79.00 376	48.06 316	79.24 376	66.13 240	84.83 188	86.15 328

TESTMET0.1,1		69.89 328	69.00 322	72.55 354	79.27 377	56.85 328	78.38 349	74.71 388	57.64 376	68.09 340	77.19 389	37.75 386	76.70 389	63.92 259	84.09 203	84.10 362

test-mter		71.41 311	70.39 314	74.48 335	81.35 349	58.04 309	78.38 349	77.46 369	60.32 353	69.95 323	79.00 376	36.08 391	79.24 376	66.13 240	84.83 188	86.15 328

UBG		73.08 297	72.27 292	75.51 322	88.02 192	51.29 387	78.35 352	77.38 372	65.52 298	73.87 276	82.36 342	45.55 339	86.48 327	55.02 336	84.39 199	88.75 271

Anonymous20231206		68.60 337	67.80 336	71.02 367	80.23 362	50.75 391	78.30 353	80.47 343	56.79 382	66.11 364	82.63 340	46.35 329	78.95 378	43.62 396	75.70 314	83.36 370

tpm cat1		70.57 320	68.31 326	77.35 305	82.41 333	57.95 312	78.08 354	80.22 349	52.04 396	68.54 338	77.66 387	52.00 272	87.84 315	51.77 352	72.07 358	86.25 325

myMVS_eth3d28		73.62 286	73.53 276	73.90 342	88.20 181	47.41 401	78.06 355	79.37 356	74.29 135	73.98 274	84.29 304	44.67 344	83.54 354	51.47 355	87.39 155	90.74 190

our_test_3		69.14 333	67.00 346	75.57 320	79.80 369	58.80 300	77.96 356	77.81 366	59.55 360	62.90 384	78.25 383	47.43 318	83.97 350	51.71 353	67.58 378	83.93 364

KD-MVS_self_test		68.81 335	67.59 341	72.46 356	74.29 397	45.45 406	77.93 357	87.00 250	63.12 325	63.99 378	78.99 378	42.32 361	84.77 346	56.55 331	64.09 389	87.16 309

WTY-MVS		75.65 262	75.68 242	75.57 320	86.40 243	56.82 329	77.92 358	82.40 321	65.10 302	76.18 225	87.72 214	63.13 155	80.90 371	60.31 292	81.96 236	89.00 260

UWE-MVS-28		65.32 359	64.93 353	66.49 387	78.70 379	38.55 424	77.86 359	64.39 416	62.00 343	64.13 376	83.60 322	41.44 367	76.00 397	31.39 416	80.89 247	84.92 351

test20.03		67.45 346	66.95 347	68.94 375	75.48 393	44.84 412	77.50 360	77.67 367	66.66 280	63.01 382	83.80 315	47.02 322	78.40 380	42.53 400	68.86 375	83.58 368

EPMVS		69.02 334	68.16 328	71.59 360	79.61 372	49.80 396	77.40 361	66.93 409	62.82 333	70.01 320	79.05 374	45.79 336	77.86 384	56.58 330	75.26 328	87.13 310

test_fmvs3		63.36 366	61.82 369	67.98 383	62.51 423	46.96 404	77.37 362	74.03 390	45.24 408	67.50 345	78.79 379	12.16 428	72.98 412	72.77 181	66.02 383	83.99 363

gg-mvs-nofinetune		69.95 327	67.96 331	75.94 315	83.07 315	54.51 362	77.23 363	70.29 399	63.11 326	70.32 315	62.33 413	43.62 353	88.69 303	53.88 343	87.76 150	84.62 356

MDTV_nov1_ep13			69.97 317		83.18 312	53.48 369	77.10 364	80.18 350	60.45 351	69.33 331	80.44 361	48.89 314	86.90 322	51.60 354	78.51 276

LF4IMVS		64.02 364	62.19 368	69.50 373	70.90 412	53.29 373	76.13 365	77.18 374	52.65 395	58.59 397	80.98 356	23.55 415	76.52 391	53.06 348	66.66 380	78.68 398

sss		73.60 287	73.64 275	73.51 345	82.80 323	55.01 357	76.12 366	81.69 329	62.47 337	74.68 265	85.85 269	57.32 223	78.11 382	60.86 289	80.93 246	87.39 301

testgi		66.67 352	66.53 349	67.08 386	75.62 392	41.69 421	75.93 367	76.50 378	66.11 289	65.20 371	86.59 250	35.72 392	74.71 406	43.71 395	73.38 348	84.84 353

CR-MVSNet		73.37 290	71.27 303	79.67 263	81.32 351	65.19 200	75.92 368	80.30 347	59.92 357	72.73 290	81.19 352	52.50 261	86.69 323	59.84 295	77.71 285	87.11 311

RPMNet		73.51 288	70.49 311	82.58 199	81.32 351	65.19 200	75.92 368	92.27 84	57.60 377	72.73 290	76.45 392	52.30 264	95.43 70	48.14 378	77.71 285	87.11 311

MIMVSNet		70.69 319	69.30 318	74.88 331	84.52 282	56.35 340	75.87 370	79.42 355	64.59 308	67.76 341	82.41 341	41.10 369	81.54 367	46.64 385	81.34 241	86.75 319

test0.0.03 1		68.00 344	67.69 338	68.90 376	77.55 383	47.43 400	75.70 371	72.95 395	66.66 280	66.56 357	82.29 345	48.06 316	75.87 399	44.97 394	74.51 336	83.41 369

dmvs_re		71.14 313	70.58 309	72.80 352	81.96 337	59.68 295	75.60 372	79.34 357	68.55 259	69.27 332	80.72 360	49.42 304	76.54 390	52.56 350	77.79 284	82.19 383

dmvs_testset		62.63 367	64.11 358	58.19 397	78.55 380	24.76 435	75.28 373	65.94 412	67.91 268	60.34 391	76.01 394	53.56 253	73.94 410	31.79 415	67.65 377	75.88 404

PMMVS		69.34 332	68.67 323	71.35 364	75.67 391	62.03 265	75.17 374	73.46 391	50.00 402	68.68 335	79.05 374	52.07 271	78.13 381	61.16 287	82.77 226	73.90 406

UnsupCasMVSNet_eth		67.33 347	65.99 351	71.37 362	73.48 403	51.47 385	75.16 375	85.19 277	65.20 301	60.78 390	80.93 359	42.35 360	77.20 386	57.12 323	53.69 408	85.44 342

MDTV_nov1_ep13_2view						37.79 425	75.16 375		55.10 388	66.53 358		49.34 306		53.98 342		87.94 289

pmmvs3		57.79 374	54.26 379	68.37 380	64.02 422	56.72 331	75.12 377	65.17 413	40.20 414	52.93 410	69.86 410	20.36 419	75.48 402	45.45 392	55.25 407	72.90 408

dp		66.80 350	65.43 352	70.90 369	79.74 371	48.82 398	75.12 377	74.77 386	59.61 359	64.08 377	77.23 388	42.89 357	80.72 372	48.86 372	66.58 381	83.16 372

Patchmtry		70.74 318	69.16 321	75.49 323	80.72 355	54.07 365	74.94 379	80.30 347	58.34 370	70.01 320	81.19 352	52.50 261	86.54 325	53.37 346	71.09 364	85.87 337

ttmdpeth		59.91 372	57.10 376	68.34 381	67.13 418	46.65 405	74.64 380	67.41 408	48.30 404	62.52 386	85.04 291	20.40 418	75.93 398	42.55 399	45.90 419	82.44 380

SSC-MVS3.2		73.35 293	73.39 277	73.23 346	85.30 265	49.01 397	74.58 381	81.57 330	75.21 107	73.68 278	85.58 276	52.53 259	82.05 364	54.33 341	77.69 287	88.63 276

PVSNet	64.34 18	72.08 308	70.87 308	75.69 318	86.21 246	56.44 336	74.37 382	80.73 339	62.06 342	70.17 318	82.23 346	42.86 358	83.31 357	54.77 338	84.45 197	87.32 304

WB-MVS		54.94 377	54.72 378	55.60 403	73.50 402	20.90 437	74.27 383	61.19 420	59.16 364	50.61 412	74.15 400	47.19 321	75.78 400	17.31 428	35.07 422	70.12 410

MDA-MVSNet-bldmvs		66.68 351	63.66 361	75.75 317	79.28 376	60.56 285	73.92 384	78.35 364	64.43 310	50.13 414	79.87 369	44.02 351	83.67 352	46.10 388	56.86 400	83.03 375

SSC-MVS		53.88 380	53.59 380	54.75 405	72.87 408	19.59 438	73.84 385	60.53 422	57.58 378	49.18 416	73.45 403	46.34 330	75.47 403	16.20 431	32.28 424	69.20 411

UnsupCasMVSNet_bld		63.70 365	61.53 371	70.21 371	73.69 401	51.39 386	72.82 386	81.89 326	55.63 387	57.81 401	71.80 406	38.67 381	78.61 379	49.26 370	52.21 411	80.63 392

PatchT		68.46 341	67.85 333	70.29 370	80.70 356	43.93 414	72.47 387	74.88 385	60.15 355	70.55 311	76.57 391	49.94 298	81.59 366	50.58 359	74.83 333	85.34 343

miper_lstm_enhance		74.11 280	73.11 282	77.13 308	80.11 363	59.62 296	72.23 388	86.92 254	66.76 278	70.40 314	82.92 334	56.93 227	82.92 359	69.06 216	72.63 352	88.87 265

MVS-HIRNet		59.14 373	57.67 375	63.57 391	81.65 341	43.50 415	71.73 389	65.06 414	39.59 416	51.43 411	57.73 419	38.34 383	82.58 361	39.53 404	73.95 340	64.62 415

MVStest1		56.63 376	52.76 382	68.25 382	61.67 424	53.25 374	71.67 390	68.90 406	38.59 417	50.59 413	83.05 331	25.08 410	70.66 414	36.76 410	38.56 420	80.83 391

APD_test1		53.31 382	49.93 387	63.42 392	65.68 419	50.13 393	71.59 391	66.90 410	34.43 422	40.58 421	71.56 407	8.65 433	76.27 394	34.64 413	55.36 405	63.86 416

Patchmatch-RL test		70.24 324	67.78 337	77.61 300	77.43 384	59.57 298	71.16 392	70.33 398	62.94 330	68.65 336	72.77 404	50.62 290	85.49 338	69.58 211	66.58 381	87.77 293

test123		6.12 404	8.11 407	0.14 418	0.06 442	0.09 443	71.05 393	0.03 443	0.04 437	0.25 438	1.30 437	0.05 441	0.03 438	0.21 437	0.01 436	0.29 433

ANet_high		50.57 387	46.10 391	63.99 390	48.67 435	39.13 423	70.99 394	80.85 337	61.39 347	31.18 424	57.70 420	17.02 423	73.65 411	31.22 417	15.89 432	79.18 397

KD-MVS_2432*1600		66.22 356	63.89 359	73.21 347	75.47 394	53.42 370	70.76 395	84.35 287	64.10 316	66.52 359	78.52 380	34.55 394	84.98 343	50.40 361	50.33 413	81.23 388

miper_refine_blended		66.22 356	63.89 359	73.21 347	75.47 394	53.42 370	70.76 395	84.35 287	64.10 316	66.52 359	78.52 380	34.55 394	84.98 343	50.40 361	50.33 413	81.23 388

test_vis1_rt		60.28 371	58.42 374	65.84 388	67.25 417	55.60 350	70.44 397	60.94 421	44.33 410	59.00 396	66.64 411	24.91 411	68.67 418	62.80 266	69.48 369	73.25 407

testmvs		6.04 405	8.02 408	0.10 419	0.08 441	0.03 444	69.74 398	0.04 442	0.05 436	0.31 437	1.68 436	0.02 442	0.04 437	0.24 436	0.02 435	0.25 434

N_pmnet		52.79 383	53.26 381	51.40 407	78.99 378	7.68 441	69.52 399	3.89 440	51.63 399	57.01 403	74.98 399	40.83 371	65.96 422	37.78 408	64.67 387	80.56 394

FPMVS		53.68 381	51.64 383	59.81 396	65.08 420	51.03 388	69.48 400	69.58 402	41.46 413	40.67 420	72.32 405	16.46 424	70.00 417	24.24 424	65.42 385	58.40 420

DSMNet-mixed		57.77 375	56.90 377	60.38 395	67.70 416	35.61 426	69.18 401	53.97 427	32.30 425	57.49 402	79.88 368	40.39 374	68.57 419	38.78 407	72.37 353	76.97 401

new-patchmatchnet		61.73 369	61.73 370	61.70 393	72.74 409	24.50 436	69.16 402	78.03 365	61.40 346	56.72 404	75.53 398	38.42 382	76.48 392	45.95 389	57.67 399	84.13 361

YYNet1		65.03 360	62.91 365	71.38 361	75.85 390	56.60 334	69.12 403	74.66 389	57.28 380	54.12 408	77.87 385	45.85 335	74.48 407	49.95 366	61.52 394	83.05 374

MDA-MVSNet_test_wron		65.03 360	62.92 364	71.37 362	75.93 388	56.73 330	69.09 404	74.73 387	57.28 380	54.03 409	77.89 384	45.88 334	74.39 408	49.89 367	61.55 393	82.99 376

PVSNet_0	57.27 20	61.67 370	59.27 373	68.85 377	79.61 372	57.44 322	68.01 405	73.44 392	55.93 386	58.54 398	70.41 409	44.58 346	77.55 385	47.01 382	35.91 421	71.55 409

dongtai		45.42 391	45.38 392	45.55 409	73.36 405	26.85 433	67.72 406	34.19 435	54.15 391	49.65 415	56.41 422	25.43 409	62.94 425	19.45 426	28.09 426	46.86 425

ADS-MVSNet2		66.20 358	63.33 362	74.82 332	79.92 365	58.75 301	67.55 407	75.19 383	53.37 393	65.25 369	75.86 395	42.32 361	80.53 373	41.57 401	68.91 373	85.18 346

ADS-MVSNet		64.36 363	62.88 366	68.78 378	79.92 365	47.17 402	67.55 407	71.18 397	53.37 393	65.25 369	75.86 395	42.32 361	73.99 409	41.57 401	68.91 373	85.18 346

mvsany_test1		62.30 368	61.26 372	65.41 389	69.52 413	54.86 358	66.86 409	49.78 429	46.65 406	68.50 339	83.21 328	49.15 309	66.28 421	56.93 327	60.77 395	75.11 405

LCM-MVSNet		54.25 378	49.68 388	67.97 384	53.73 432	45.28 409	66.85 410	80.78 338	35.96 421	39.45 422	62.23 415	8.70 432	78.06 383	48.24 377	51.20 412	80.57 393

test_vis3_rt		49.26 388	47.02 390	56.00 400	54.30 429	45.27 410	66.76 411	48.08 430	36.83 419	44.38 418	53.20 423	7.17 435	64.07 423	56.77 329	55.66 403	58.65 419

testf1		45.72 389	41.96 393	57.00 398	56.90 426	45.32 407	66.14 412	59.26 423	26.19 426	30.89 425	60.96 417	4.14 436	70.64 415	26.39 422	46.73 417	55.04 421

APD_test2		45.72 389	41.96 393	57.00 398	56.90 426	45.32 407	66.14 412	59.26 423	26.19 426	30.89 425	60.96 417	4.14 436	70.64 415	26.39 422	46.73 417	55.04 421

kuosan		39.70 395	40.40 396	37.58 412	64.52 421	26.98 431	65.62 414	33.02 436	46.12 407	42.79 419	48.99 425	24.10 414	46.56 433	12.16 434	26.30 427	39.20 426

JIA-IIPM		66.32 355	62.82 367	76.82 310	77.09 386	61.72 271	65.34 415	75.38 382	58.04 374	64.51 373	62.32 414	42.05 365	86.51 326	51.45 356	69.22 372	82.21 382

PMVS	37.38 22	44.16 393	40.28 397	55.82 402	40.82 437	42.54 419	65.12 416	63.99 417	34.43 422	24.48 428	57.12 421	3.92 438	76.17 396	17.10 429	55.52 404	48.75 423
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
new_pmnet		50.91 386	50.29 386	52.78 406	68.58 415	34.94 428	63.71 417	56.63 426	39.73 415	44.95 417	65.47 412	21.93 417	58.48 426	34.98 412	56.62 401	64.92 414

mvsany_test3		53.99 379	51.45 384	61.61 394	55.51 428	44.74 413	63.52 418	45.41 433	43.69 411	58.11 400	76.45 392	17.99 421	63.76 424	54.77 338	47.59 415	76.34 403

Patchmatch-test		64.82 362	63.24 363	69.57 372	79.42 375	49.82 395	63.49 419	69.05 404	51.98 398	59.95 394	80.13 365	50.91 286	70.98 413	40.66 403	73.57 344	87.90 290

ambc				75.24 327	73.16 406	50.51 392	63.05 420	87.47 240		64.28 374	77.81 386	17.80 422	89.73 283	57.88 317	60.64 396	85.49 340

test_f		52.09 384	50.82 385	55.90 401	53.82 431	42.31 420	59.42 421	58.31 425	36.45 420	56.12 407	70.96 408	12.18 427	57.79 427	53.51 345	56.57 402	67.60 412

CHOSEN 280x420		66.51 353	64.71 355	71.90 358	81.45 346	63.52 239	57.98 422	68.95 405	53.57 392	62.59 385	76.70 390	46.22 331	75.29 405	55.25 335	79.68 263	76.88 402

E-PMN		31.77 396	30.64 399	35.15 413	52.87 433	27.67 430	57.09 423	47.86 431	24.64 428	16.40 433	33.05 429	11.23 429	54.90 429	14.46 432	18.15 430	22.87 429

EMVS		30.81 398	29.65 400	34.27 414	50.96 434	25.95 434	56.58 424	46.80 432	24.01 429	15.53 434	30.68 430	12.47 426	54.43 430	12.81 433	17.05 431	22.43 430

PMMVS2		40.82 394	38.86 398	46.69 408	53.84 430	16.45 439	48.61 425	49.92 428	37.49 418	31.67 423	60.97 416	8.14 434	56.42 428	28.42 419	30.72 425	67.19 413

wuyk23d		16.82 402	15.94 405	19.46 416	58.74 425	31.45 429	39.22 426	3.74 441	6.84 432	6.04 435	2.70 435	1.27 440	24.29 435	10.54 435	14.40 434	2.63 432

tmp_tt		18.61 401	21.40 404	10.23 417	4.82 440	10.11 440	34.70 427	30.74 438	1.48 434	23.91 430	26.07 431	28.42 406	13.41 436	27.12 420	15.35 433	7.17 431

Gipuma		45.18 392	41.86 395	55.16 404	77.03 387	51.52 384	32.50 428	80.52 342	32.46 424	27.12 427	35.02 428	9.52 431	75.50 401	22.31 425	60.21 398	38.45 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
MVE	26.22 23	30.37 399	25.89 403	43.81 410	44.55 436	35.46 427	28.87 429	39.07 434	18.20 430	18.58 432	40.18 427	2.68 439	47.37 432	17.07 430	23.78 429	48.60 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
test_method		31.52 397	29.28 401	38.23 411	27.03 439	6.50 442	20.94 430	62.21 419	4.05 433	22.35 431	52.50 424	13.33 425	47.58 431	27.04 421	34.04 423	60.62 417

mmdepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

monomultidepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

test_blank		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet_test		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

DCPMVS		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

cdsmvs_eth3d_5k		19.96 400	26.61 402	0.00 420	0.00 443	0.00 445	0.00 431	89.26 190	0.00 438	0.00 439	88.61 191	61.62 176	0.00 439	0.00 438	0.00 437	0.00 435

pcd_1.5k_mvsjas		5.26 406	7.02 409	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	63.15 152	0.00 439	0.00 438	0.00 437	0.00 435

sosnet-low-res		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uncertanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

Regformer		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

ab-mvs-re		7.23 403	9.64 406	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	86.72 242	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

WAC-MVS						42.58 417								39.46 405

MSC_two_6792asdad				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 11	96.44 9	94.41 39

PC_three_1452									68.21 265	92.02 12	94.00 53	82.09 5	95.98 56	84.58 61	96.68 2	94.95 11

No_MVS				89.16 1	94.34 27	75.53 2		92.99 49					97.53 2	89.67 11	96.44 9	94.41 39

test_one_0601					95.07 7	71.46 57		94.14 5	78.27 37	92.05 11	95.74 6	80.83 11

eth-test2					0.00 443

eth-test					0.00 443

ZD-MVS					94.38 25	72.22 44		92.67 67	70.98 202	87.75 41	94.07 48	74.01 32	96.70 27	84.66 60	94.84 44

IU-MVS					95.30 2	71.25 59		92.95 55	66.81 276	92.39 6				88.94 23	96.63 4	94.85 20

test_241102_TWO								94.06 10	77.24 55	92.78 4	95.72 8	81.26 8	97.44 7	89.07 20	96.58 6	94.26 48

test_241102_ONE					95.30 2	70.98 66		94.06 10	77.17 58	93.10 1	95.39 14	82.99 1	97.27 12

test_0728_THIRD									78.38 34	92.12 9	95.78 4	81.46 7	97.40 9	89.42 15	96.57 7	94.67 28

GSMVS																88.96 262

test_part2					95.06 8	72.65 32				91.80 13

sam_mvs1												51.32 282				88.96 262

sam_mvs												50.01 296

MTGPA								92.02 93

test_post											5.46 433	50.36 294	84.24 348

patchmatchnet-post											74.00 401	51.12 285	88.60 305

gm-plane-assit					81.40 347	53.83 367			62.72 335		80.94 357		92.39 207	63.40 263

test9_res														84.90 54	95.70 26	92.87 119

agg_prior2														82.91 81	95.45 29	92.70 122

agg_prior					92.85 62	71.94 50		91.78 108		84.41 85			94.93 94

TestCases				79.58 265	85.15 269	63.62 234		79.83 351	62.31 338	60.32 392	86.73 240	32.02 398	88.96 299	50.28 363	71.57 361	86.15 328

test_prior				86.33 57	92.61 68	69.59 91		92.97 54					95.48 67			93.91 63

新几何1				83.42 160	93.13 54	70.71 74		85.48 275	57.43 379	81.80 124	91.98 102	63.28 147	92.27 213	64.60 255	92.99 70	87.27 305

旧先验1					91.96 74	65.79 187		86.37 263			93.08 82	69.31 86			92.74 74	88.74 273

原ACMM1				84.35 114	93.01 60	68.79 110		92.44 77	63.96 321	81.09 134	91.57 116	66.06 125	95.45 68	67.19 234	94.82 46	88.81 268

testdata2													91.01 263	62.37 273

segment_acmp												73.08 39

testdata				79.97 255	90.90 91	64.21 225		84.71 282	59.27 363	85.40 65	92.91 84	62.02 171	89.08 295	68.95 217	91.37 94	86.63 322

test12				86.80 52	92.63 67	70.70 75		91.79 107		82.71 114		71.67 56	96.16 47		94.50 51	93.54 88

plane_prior7					90.08 109	68.51 124

plane_prior6					89.84 118	68.70 118						60.42 202

plane_prior5								92.44 77					95.38 75	78.71 118	86.32 171	91.33 168

plane_prior4											91.00 138

plane_prior3						68.60 121			78.44 32	78.92 159

plane_prior1					89.90 117

n2								0.00 444

nn								0.00 444

door-mid								69.98 400

lessismore_v0				78.97 274	81.01 354	57.15 325		65.99 411		61.16 389	82.82 337	39.12 378	91.34 252	59.67 297	46.92 416	88.43 281

LGP-MVS_train				84.50 107	89.23 143	68.76 112		91.94 99	75.37 103	76.64 212	91.51 117	54.29 246	94.91 95	78.44 120	83.78 205	89.83 234

test11								92.23 87

door								69.44 403

HQP5-MVS						66.98 165

BP-MVS														77.47 130

HQP4-MVS										77.24 196			95.11 87			91.03 178

HQP3-MVS								92.19 90							85.99 179

HQP2-MVS												60.17 205

NP-MVS					89.62 122	68.32 128					90.24 150

ACMMP++_ref															81.95 237

ACMMP++															81.25 242

Test By Simon												64.33 139

ITE_SJBPF				78.22 289	81.77 340	60.57 284		83.30 304	69.25 242	67.54 344	87.20 231	36.33 390	87.28 320	54.34 340	74.62 335	86.80 317

DeepMVS_CX				27.40 415	40.17 438	26.90 432		24.59 439	17.44 431	23.95 429	48.61 426	9.77 430	26.48 434	18.06 427	24.47 428	28.83 428

High-resolution multi-view benchmark