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++		95.98 1	96.36 1	94.82 31	97.78 54	86.00 50	98.29 1	97.49 6	90.75 19	97.62 5	98.06 14	92.59 2	99.61 4	95.64 19	99.02 12	98.86 11

FOURS1					98.86 1	85.54 67	98.29 1	97.49 6	89.79 50	96.29 18

CS-MVS		94.12 40	94.44 25	93.17 84	96.55 88	83.08 137	97.63 3	96.95 57	91.71 11	93.50 65	96.21 89	85.61 52	98.24 146	93.64 43	98.17 62	98.19 64

CP-MVS		94.34 29	94.21 37	94.74 37	98.39 23	86.64 32	97.60 4	97.24 32	88.53 92	92.73 85	97.23 43	85.20 59	99.32 41	92.15 77	98.83 22	98.25 61

SPE-MVS-test		94.02 42	94.29 31	93.24 81	96.69 81	83.24 127	97.49 5	96.92 60	92.14 5	92.90 75	95.77 113	85.02 63	98.33 141	93.03 54	98.62 46	98.13 68

APDe-MVS		95.46 5	95.64 5	94.91 21	98.26 28	86.29 46	97.46 6	97.40 20	89.03 75	96.20 19	98.10 8	89.39 16	99.34 37	95.88 16	99.03 11	99.10 4
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
SteuartSystems-ACMMP		95.20 8	95.32 9	94.85 25	96.99 75	86.33 42	97.33 7	97.30 29	91.38 12	95.39 31	97.46 32	88.98 19	99.40 30	94.12 37	98.89 18	98.82 16
Skip Steuart: Steuart Systems R&D Blog.
EPP-MVSNet		91.70 95	91.56 92	92.13 139	95.88 117	80.50 208	97.33 7	95.25 200	86.15 157	89.76 141	95.60 119	83.42 82	98.32 143	87.37 147	93.25 176	97.56 106

EC-MVSNet		93.44 59	93.71 55	92.63 116	95.21 146	82.43 158	97.27 9	96.71 85	90.57 26	92.88 76	95.80 111	83.16 84	98.16 152	93.68 42	98.14 65	97.31 112

HPM-MVS		94.02 42	93.88 47	94.43 47	98.39 23	85.78 63	97.25 10	97.07 48	86.90 139	92.62 89	96.80 68	84.85 68	99.17 50	92.43 65	98.65 44	98.33 44
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
test0726					98.78 3	85.93 55	97.19 11	97.47 11	90.27 32	97.64 4	98.13 4	91.47 8

3Dnovator	86.66 5	91.73 94	90.82 106	94.44 45	94.59 179	86.37 41	97.18 12	97.02 50	89.20 67	84.31 271	96.66 72	73.74 208	99.17 50	86.74 155	97.96 73	97.79 93

HPM-MVS_fast		93.40 64	93.22 65	93.94 61	98.36 25	84.83 79	97.15 13	96.80 74	85.77 165	92.47 93	97.13 51	82.38 95	99.07 56	90.51 112	98.40 54	97.92 84

SED-MVS		95.91 2	96.28 2	94.80 33	98.77 5	85.99 52	97.13 14	97.44 15	90.31 29	97.71 1	98.07 12	92.31 4	99.58 10	95.66 17	99.13 3	98.84 14

OPU-MVS				96.21 3	98.00 42	90.85 3	97.13 14				97.08 52	92.59 2	98.94 81	92.25 73	98.99 14	98.84 14

DVP-MVS		95.67 3	96.02 3	94.64 39	98.78 3	85.93 55	97.09 16	96.73 82	90.27 32	97.04 11	98.05 16	91.47 8	99.55 16	95.62 21	99.08 7	98.45 36
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				95.01 17	98.79 2	86.43 39	97.09 16	97.49 6					99.61 4	95.62 21	99.08 7	98.99 9

3Dnovator+	87.14 4	92.42 84	91.37 94	95.55 7	95.63 129	88.73 6	97.07 18	96.77 77	90.84 16	84.02 276	96.62 77	75.95 171	99.34 37	87.77 140	97.68 83	98.59 24

IS-MVSNet		91.43 98	91.09 101	92.46 124	95.87 119	81.38 184	96.95 19	93.69 271	89.72 53	89.50 145	95.98 101	78.57 145	97.77 183	83.02 202	96.50 109	98.22 63

HFP-MVS		94.52 22	94.40 26	94.86 24	98.61 10	86.81 25	96.94 20	97.34 23	88.63 87	93.65 59	97.21 44	86.10 48	99.49 26	92.35 70	98.77 28	98.30 49

ACMMPR		94.43 26	94.28 32	94.91 21	98.63 9	86.69 28	96.94 20	97.32 27	88.63 87	93.53 64	97.26 42	85.04 62	99.54 20	92.35 70	98.78 26	98.50 27

XVS		94.45 24	94.32 28	94.85 25	98.54 13	86.60 34	96.93 22	97.19 35	90.66 24	92.85 77	97.16 50	85.02 63	99.49 26	91.99 84	98.56 50	98.47 33

X-MVStestdata		88.31 182	86.13 229	94.85 25	98.54 13	86.60 34	96.93 22	97.19 35	90.66 24	92.85 77	23.41 420	85.02 63	99.49 26	91.99 84	98.56 50	98.47 33

region2R		94.43 26	94.27 34	94.92 20	98.65 8	86.67 30	96.92 24	97.23 34	88.60 90	93.58 61	97.27 40	85.22 58	99.54 20	92.21 74	98.74 31	98.56 25

MSP-MVS		95.42 6	95.56 6	94.98 19	98.49 17	86.52 36	96.91 25	97.47 11	91.73 10	96.10 20	96.69 69	89.90 12	99.30 43	94.70 31	98.04 71	99.13 2
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
mPP-MVS		93.99 44	93.78 51	94.63 40	98.50 16	85.90 60	96.87 26	96.91 61	88.70 85	91.83 111	97.17 49	83.96 77	99.55 16	91.44 97	98.64 45	98.43 38

ACMMP		93.24 68	92.88 72	94.30 53	98.09 38	85.33 72	96.86 27	97.45 14	88.33 96	90.15 137	97.03 56	81.44 112	99.51 24	90.85 108	95.74 120	98.04 76
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
ZNCC-MVS		94.47 23	94.28 32	95.03 16	98.52 15	86.96 20	96.85 28	97.32 27	88.24 100	93.15 69	97.04 55	86.17 47	99.62 2	92.40 67	98.81 23	98.52 26

QAPM		89.51 145	88.15 169	93.59 75	94.92 161	84.58 85	96.82 29	96.70 86	78.43 320	83.41 291	96.19 93	73.18 216	99.30 43	77.11 292	96.54 107	96.89 139

CPTT-MVS		91.99 88	91.80 88	92.55 120	98.24 31	81.98 168	96.76 30	96.49 101	81.89 262	90.24 132	96.44 84	78.59 144	98.61 113	89.68 118	97.85 77	97.06 127

MP-MVS		94.25 31	94.07 42	94.77 35	98.47 18	86.31 44	96.71 31	96.98 52	89.04 73	91.98 102	97.19 47	85.43 56	99.56 12	92.06 83	98.79 24	98.44 37
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
PHI-MVS		93.89 47	93.65 58	94.62 41	96.84 78	86.43 39	96.69 32	97.49 6	85.15 181	93.56 63	96.28 87	85.60 53	99.31 42	92.45 64	98.79 24	98.12 71

MM		95.10 11	94.91 16	95.68 5	96.09 106	88.34 9	96.68 33	94.37 244	95.08 1	94.68 40	97.72 26	82.94 88	99.64 1	97.85 1	98.76 29	99.06 7

SF-MVS		94.97 12	94.90 18	95.20 12	97.84 50	87.76 10	96.65 34	97.48 10	87.76 120	95.71 27	97.70 27	88.28 23	99.35 36	93.89 41	98.78 26	98.48 30

OpenMVS	83.78 11	88.74 171	87.29 188	93.08 90	92.70 261	85.39 71	96.57 35	96.43 103	78.74 315	80.85 323	96.07 97	69.64 259	99.01 66	78.01 283	96.65 106	94.83 224

GST-MVS		94.21 34	93.97 46	94.90 23	98.41 22	86.82 24	96.54 36	97.19 35	88.24 100	93.26 66	96.83 64	85.48 55	99.59 8	91.43 98	98.40 54	98.30 49

nrg030		91.08 106	90.39 110	93.17 84	93.07 249	86.91 22	96.41 37	96.26 118	88.30 98	88.37 163	94.85 151	82.19 103	97.64 194	91.09 100	82.95 305	94.96 217

SR-MVS		94.23 33	94.17 40	94.43 47	98.21 32	85.78 63	96.40 38	96.90 62	88.20 103	94.33 44	97.40 35	84.75 69	99.03 61	93.35 49	97.99 72	98.48 30

sasdasda		93.27 66	92.75 74	94.85 25	95.70 125	87.66 12	96.33 39	96.41 105	90.00 38	94.09 49	94.60 162	82.33 97	98.62 111	92.40 67	92.86 183	98.27 56

canonicalmvs		93.27 66	92.75 74	94.85 25	95.70 125	87.66 12	96.33 39	96.41 105	90.00 38	94.09 49	94.60 162	82.33 97	98.62 111	92.40 67	92.86 183	98.27 56

VDDNet		89.56 144	88.49 160	92.76 108	95.07 152	82.09 165	96.30 41	93.19 279	81.05 285	91.88 107	96.86 62	61.16 342	98.33 141	88.43 133	92.49 192	97.84 90

APD-MVS_3200maxsize		93.78 49	93.77 52	93.80 67	97.92 43	84.19 101	96.30 41	96.87 65	86.96 135	93.92 55	97.47 31	83.88 78	98.96 80	92.71 61	97.87 76	98.26 60

SR-MVS-dyc-post		93.82 48	93.82 48	93.82 65	97.92 43	84.57 86	96.28 43	96.76 78	87.46 125	93.75 57	97.43 33	84.24 74	99.01 66	92.73 58	97.80 79	97.88 86

RE-MVS-def			93.68 56		97.92 43	84.57 86	96.28 43	96.76 78	87.46 125	93.75 57	97.43 33	82.94 88		92.73 58	97.80 79	97.88 86

balanced_conf03		93.98 45	94.22 35	93.26 80	96.13 101	83.29 126	96.27 45	96.52 98	89.82 44	95.56 30	95.51 122	84.50 71	98.79 94	94.83 30	98.86 19	97.72 96

SMA-MVS		95.20 8	95.07 11	95.59 6	98.14 35	88.48 8	96.26 46	97.28 31	85.90 162	97.67 3	98.10 8	88.41 20	99.56 12	94.66 32	99.19 1	98.71 20
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
test2506		87.21 226	86.28 224	90.02 233	95.62 130	73.64 334	96.25 47	71.38 418	87.89 114	90.45 129	96.65 73	55.29 372	98.09 164	86.03 165	96.94 96	98.33 44

CSCG		93.23 69	93.05 68	93.76 69	98.04 40	84.07 103	96.22 48	97.37 21	84.15 204	90.05 138	95.66 117	87.77 26	99.15 53	89.91 117	98.27 58	98.07 73

fmvsm_s_conf0.5_n_a		93.57 54	93.76 53	93.00 95	95.02 153	83.67 113	96.19 49	96.10 134	87.27 129	95.98 24	98.05 16	83.07 87	98.45 129	96.68 11	95.51 124	96.88 140

SD-MVS		94.96 13	95.33 8	93.88 62	97.25 72	86.69 28	96.19 49	97.11 46	90.42 27	96.95 13	97.27 40	89.53 14	96.91 261	94.38 35	98.85 20	98.03 77
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
test_fmvsmconf0.1_n		94.20 36	94.31 30	93.88 62	92.46 266	84.80 80	96.18 51	96.82 71	89.29 64	95.68 28	98.11 6	85.10 60	98.99 73	97.38 3	97.75 82	97.86 88

ECVR-MVS		89.09 160	88.53 156	90.77 201	95.62 130	75.89 308	96.16 52	84.22 396	87.89 114	90.20 134	96.65 73	63.19 322	98.10 156	85.90 166	96.94 96	98.33 44

MTMP							96.16 52	60.64 422

test_fmvsmconf_n		94.60 21	94.81 19	93.98 58	94.62 178	84.96 77	96.15 54	97.35 22	89.37 61	96.03 23	98.11 6	86.36 44	99.01 66	97.45 2	97.83 78	97.96 80

test_fmvsm_n_1920		94.71 20	95.11 10	93.50 76	95.79 120	84.62 84	96.15 54	97.64 2	89.85 43	97.19 8	97.89 22	86.28 46	98.71 102	97.11 6	98.08 70	97.17 120

fmvsm_s_conf0.5_n		93.76 50	94.06 44	92.86 103	95.62 130	83.17 130	96.14 56	96.12 132	88.13 106	95.82 26	98.04 19	83.43 80	98.48 121	96.97 9	96.23 113	96.92 137

Anonymous20231211		86.59 249	85.13 263	90.98 196	96.52 91	81.50 177	96.14 56	96.16 127	73.78 366	83.65 285	92.15 247	63.26 321	97.37 226	82.82 207	81.74 324	94.06 260

Vis-MVSNet		91.75 93	91.23 97	93.29 78	95.32 139	83.78 110	96.14 56	95.98 144	89.89 40	90.45 129	96.58 79	75.09 183	98.31 144	84.75 180	96.90 98	97.78 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
TSAR-MVS + MP.		94.85 14	94.94 14	94.58 42	98.25 29	86.33 42	96.11 59	96.62 91	88.14 105	96.10 20	96.96 58	89.09 18	98.94 81	94.48 34	98.68 37	98.48 30
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MGCFI-Net		93.03 73	92.63 77	94.23 56	95.62 130	85.92 57	96.08 60	96.33 111	89.86 42	93.89 56	94.66 159	82.11 104	98.50 119	92.33 72	92.82 186	98.27 56

test1111		89.10 158	88.64 153	90.48 211	95.53 135	74.97 318	96.08 60	84.89 394	88.13 106	90.16 136	96.65 73	63.29 320	98.10 156	86.14 161	96.90 98	98.39 39

9.14			94.47 23		97.79 52		96.08 60	97.44 15	86.13 160	95.10 37	97.40 35	88.34 22	99.22 47	93.25 50	98.70 34

LFMVS		90.08 128	89.13 141	92.95 99	96.71 80	82.32 163	96.08 60	89.91 363	86.79 140	92.15 99	96.81 66	62.60 324	98.34 139	87.18 149	93.90 160	98.19 64

MVSMamba_PlusPlus		93.44 59	93.54 60	93.14 86	96.58 87	83.05 138	96.06 64	96.50 100	84.42 201	94.09 49	95.56 121	85.01 66	98.69 103	94.96 29	98.66 41	97.67 99

test_fmvsmconf0.01_n		93.19 70	93.02 69	93.71 72	89.25 360	84.42 97	96.06 64	96.29 113	89.06 71	94.68 40	98.13 4	79.22 136	98.98 77	97.22 4	97.24 90	97.74 95

API-MVS		90.66 116	90.07 118	92.45 125	96.36 95	84.57 86	96.06 64	95.22 203	82.39 245	89.13 150	94.27 175	80.32 120	98.46 125	80.16 258	96.71 104	94.33 248

EPNet		91.79 91	91.02 102	94.10 57	90.10 347	85.25 73	96.03 67	92.05 310	92.83 2	87.39 184	95.78 112	79.39 134	99.01 66	88.13 136	97.48 85	98.05 75
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.1_n_a		93.19 70	93.26 63	92.97 97	92.49 264	83.62 116	96.02 68	95.72 167	86.78 141	96.04 22	98.19 1	82.30 99	98.43 133	96.38 13	95.42 130	96.86 141

fmvsm_s_conf0.1_n		93.46 57	93.66 57	92.85 104	93.75 227	83.13 132	96.02 68	95.74 164	87.68 122	95.89 25	98.17 2	82.78 91	98.46 125	96.71 10	96.17 114	96.98 133

Anonymous20240529		88.09 188	86.59 211	92.58 119	96.53 90	81.92 170	95.99 70	95.84 157	74.11 363	89.06 153	95.21 135	61.44 334	98.81 92	83.67 196	87.47 265	97.01 131

alignmvs		93.08 72	92.50 80	94.81 32	95.62 130	87.61 15	95.99 70	96.07 137	89.77 51	94.12 48	94.87 148	80.56 118	98.66 104	92.42 66	93.10 179	98.15 67

MVS_0304		94.18 39	93.80 49	95.34 9	94.91 163	87.62 14	95.97 72	93.01 284	92.58 3	94.22 45	97.20 46	80.56 118	99.59 8	97.04 8	98.68 37	98.81 17

MVSFormer		91.68 96	91.30 95	92.80 106	93.86 221	83.88 108	95.96 73	95.90 152	84.66 197	91.76 112	94.91 145	77.92 152	97.30 228	89.64 119	97.11 91	97.24 116

test_djsdf		89.03 163	88.64 153	90.21 222	90.74 333	79.28 245	95.96 73	95.90 152	84.66 197	85.33 243	92.94 222	74.02 202	97.30 228	89.64 119	88.53 246	94.05 261

reproduce_model		94.76 18	94.92 15	94.29 54	97.92 43	85.18 74	95.95 75	97.19 35	89.67 54	95.27 34	98.16 3	86.53 43	99.36 35	95.42 24	98.15 64	98.33 44

HPM-MVS++		95.14 10	94.91 16	95.83 4	98.25 29	89.65 4	95.92 76	96.96 55	91.75 9	94.02 53	96.83 64	88.12 24	99.55 16	93.41 48	98.94 16	98.28 54

BP-MVS1		92.48 82	92.07 85	93.72 71	94.50 187	84.39 98	95.90 77	94.30 247	90.39 28	92.67 87	95.94 103	74.46 192	98.65 106	93.14 52	97.35 89	98.13 68

APD-MVS		94.24 32	94.07 42	94.75 36	98.06 39	86.90 23	95.88 78	96.94 58	85.68 168	95.05 38	97.18 48	87.31 35	99.07 56	91.90 90	98.61 48	98.28 54
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
reproduce-ours		94.82 15	94.97 12	94.38 50	97.91 47	85.46 68	95.86 79	97.15 41	89.82 44	95.23 35	98.10 8	87.09 37	99.37 33	95.30 25	98.25 60	98.30 49

our_new_method		94.82 15	94.97 12	94.38 50	97.91 47	85.46 68	95.86 79	97.15 41	89.82 44	95.23 35	98.10 8	87.09 37	99.37 33	95.30 25	98.25 60	98.30 49

HQP_MVS		90.60 120	90.19 114	91.82 157	94.70 174	82.73 150	95.85 81	96.22 123	90.81 17	86.91 190	94.86 149	74.23 196	98.12 154	88.15 134	89.99 220	94.63 229

plane_prior2							95.85 81		90.81 17

test_fmvsmvis_n_1920		93.44 59	93.55 59	93.10 88	93.67 231	84.26 100	95.83 83	96.14 128	89.00 77	92.43 94	97.50 30	83.37 83	98.72 100	96.61 12	97.44 86	96.32 159

GeoE		90.05 129	89.43 133	91.90 153	95.16 149	80.37 211	95.80 84	94.65 237	83.90 209	87.55 180	94.75 154	78.18 150	97.62 196	81.28 238	93.63 164	97.71 97

MSLP-MVS++		93.72 52	94.08 41	92.65 115	97.31 68	83.43 121	95.79 85	97.33 25	90.03 37	93.58 61	96.96 58	84.87 67	97.76 184	92.19 76	98.66 41	96.76 144

FC-MVSNet-test		90.27 124	90.18 115	90.53 206	93.71 228	79.85 230	95.77 86	97.59 3	89.31 63	86.27 208	94.67 158	81.93 110	97.01 254	84.26 186	88.09 256	94.71 228

FIs		90.51 121	90.35 111	90.99 194	93.99 217	80.98 194	95.73 87	97.54 4	89.15 69	86.72 197	94.68 157	81.83 111	97.24 236	85.18 173	88.31 253	94.76 227

VDD-MVS		90.74 112	89.92 124	93.20 83	96.27 97	83.02 140	95.73 87	93.86 265	88.42 95	92.53 90	96.84 63	62.09 326	98.64 108	90.95 105	92.62 188	97.93 83

UGNet		89.95 133	88.95 145	92.95 99	94.51 186	83.31 125	95.70 89	95.23 201	89.37 61	87.58 178	93.94 187	64.00 315	98.78 95	83.92 191	96.31 112	96.74 146
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
fmvsm_l_conf0.5_n		94.29 30	94.46 24	93.79 68	95.28 141	85.43 70	95.68 90	96.43 103	86.56 146	96.84 14	97.81 25	87.56 32	98.77 96	97.14 5	96.82 102	97.16 124

ACMMP_NAP		94.74 19	94.56 22	95.28 10	98.02 41	87.70 11	95.68 90	97.34 23	88.28 99	95.30 33	97.67 28	85.90 50	99.54 20	93.91 40	98.95 15	98.60 23

MAR-MVS		90.30 123	89.37 135	93.07 92	96.61 84	84.48 91	95.68 90	95.67 170	82.36 247	87.85 172	92.85 223	76.63 165	98.80 93	80.01 259	96.68 105	95.91 180
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
UA-Net		92.83 76	92.54 79	93.68 73	96.10 105	84.71 82	95.66 93	96.39 107	91.92 7	93.22 68	96.49 82	83.16 84	98.87 85	84.47 184	95.47 127	97.45 110

NCCC		94.81 17	94.69 21	95.17 14	97.83 51	87.46 17	95.66 93	96.93 59	92.34 4	93.94 54	96.58 79	87.74 27	99.44 29	92.83 57	98.40 54	98.62 22

DeepC-MVS_fast	89.43 2	94.04 41	93.79 50	94.80 33	97.48 64	86.78 26	95.65 95	96.89 63	89.40 60	92.81 80	96.97 57	85.37 57	99.24 46	90.87 107	98.69 35	98.38 41
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
tt0805		86.92 236	85.74 250	90.48 211	92.22 271	79.98 226	95.63 96	94.88 223	83.83 212	84.74 254	92.80 228	57.61 361	97.67 189	85.48 172	84.42 289	93.79 274

fmvsm_l_conf0.5_n_a		94.20 36	94.40 26	93.60 74	95.29 140	84.98 76	95.61 97	96.28 116	86.31 152	96.75 16	97.86 24	87.40 33	98.74 99	97.07 7	97.02 95	97.07 126

WR-MVS_H		87.80 195	87.37 186	89.10 266	93.23 243	78.12 268	95.61 97	97.30 29	87.90 112	83.72 282	92.01 257	79.65 133	96.01 310	76.36 299	80.54 343	93.16 305

Vis-MVSNet (Re-imp)		89.59 143	89.44 132	90.03 231	95.74 122	75.85 309	95.61 97	90.80 347	87.66 124	87.83 173	95.40 127	76.79 161	96.46 289	78.37 276	96.73 103	97.80 92

GDP-MVS		92.04 87	91.46 93	93.75 70	94.55 184	84.69 83	95.60 100	96.56 96	87.83 117	93.07 73	95.89 106	73.44 212	98.65 106	90.22 115	96.03 117	97.91 85

DPE-MVS		95.57 4	95.67 4	95.25 11	98.36 25	87.28 18	95.56 101	97.51 5	89.13 70	97.14 9	97.91 21	91.64 7	99.62 2	94.61 33	99.17 2	98.86 11
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
VPA-MVSNet		89.62 141	88.96 144	91.60 165	93.86 221	82.89 145	95.46 102	97.33 25	87.91 111	88.43 162	93.31 208	74.17 199	97.40 222	87.32 148	82.86 310	94.52 237

h-mvs33		90.80 110	90.15 116	92.75 109	96.01 110	82.66 154	95.43 103	95.53 182	89.80 47	93.08 71	95.64 118	75.77 172	99.00 71	92.07 80	78.05 362	96.60 150

EIA-MVS		91.95 89	91.94 86	91.98 144	95.16 149	80.01 224	95.36 104	96.73 82	88.44 93	89.34 147	92.16 246	83.82 79	98.45 129	89.35 121	97.06 93	97.48 108

tttt0517		88.61 174	87.78 177	91.11 186	94.96 158	77.81 277	95.35 105	89.69 367	85.09 183	88.05 169	94.59 164	66.93 290	98.48 121	83.27 199	92.13 195	97.03 130

PS-CasMVS		87.32 219	86.88 197	88.63 280	92.99 255	76.33 304	95.33 106	96.61 92	88.22 102	83.30 295	93.07 219	73.03 218	95.79 323	78.36 277	81.00 337	93.75 281

jajsoiax		88.24 184	87.50 182	90.48 211	90.89 327	80.14 216	95.31 107	95.65 174	84.97 186	84.24 272	94.02 182	65.31 308	97.42 214	88.56 131	88.52 247	93.89 265

ACMM	84.12 9	89.14 157	88.48 161	91.12 183	94.65 177	81.22 188	95.31 107	96.12 132	85.31 177	85.92 215	94.34 168	70.19 252	98.06 168	85.65 169	88.86 243	94.08 259
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
PGM-MVS		93.96 46	93.72 54	94.68 38	98.43 20	86.22 47	95.30 109	97.78 1	87.45 127	93.26 66	97.33 38	84.62 70	99.51 24	90.75 109	98.57 49	98.32 48

LPG-MVS_test		89.45 148	88.90 148	91.12 183	94.47 188	81.49 179	95.30 109	96.14 128	86.73 143	85.45 232	95.16 138	69.89 255	98.10 156	87.70 141	89.23 238	93.77 279

CP-MVSNet		87.63 203	87.26 191	88.74 277	93.12 246	76.59 299	95.29 111	96.58 94	88.43 94	83.49 290	92.98 221	75.28 181	95.83 319	78.97 272	81.15 331	93.79 274

CNVR-MVS		95.40 7	95.37 7	95.50 8	98.11 36	88.51 7	95.29 111	96.96 55	92.09 6	95.32 32	97.08 52	89.49 15	99.33 40	95.10 28	98.85 20	98.66 21

pm-mvs1		86.61 247	85.54 252	89.82 241	91.44 299	80.18 214	95.28 113	94.85 225	83.84 211	81.66 313	92.62 232	72.45 226	96.48 286	79.67 263	78.06 361	92.82 318

mvsmamba		90.33 122	89.69 127	92.25 137	95.17 148	81.64 174	95.27 114	93.36 276	84.88 188	89.51 143	94.27 175	69.29 268	97.42 214	89.34 122	96.12 116	97.68 98

PS-MVSNAJss		89.97 132	89.62 128	91.02 191	91.90 284	80.85 199	95.26 115	95.98 144	86.26 154	86.21 210	94.29 172	79.70 129	97.65 192	88.87 129	88.10 254	94.57 234

LS3D		87.89 192	86.32 222	92.59 118	96.07 108	82.92 144	95.23 116	94.92 220	75.66 346	82.89 298	95.98 101	72.48 224	99.21 48	68.43 355	95.23 136	95.64 193

mvs_tets		88.06 190	87.28 189	90.38 218	90.94 323	79.88 228	95.22 117	95.66 172	85.10 182	84.21 273	93.94 187	63.53 318	97.40 222	88.50 132	88.40 251	93.87 269

save fliter					97.85 49	85.63 66	95.21 118	96.82 71	89.44 58

plane_prior						82.73 150	95.21 118		89.66 55						89.88 225

PEN-MVS		86.80 240	86.27 225	88.40 283	92.32 270	75.71 312	95.18 120	96.38 108	87.97 109	82.82 299	93.15 215	73.39 214	95.92 314	76.15 303	79.03 360	93.59 286

TransMVSNet (Re)		84.43 294	83.06 301	88.54 281	91.72 291	78.44 259	95.18 120	92.82 290	82.73 241	79.67 341	92.12 249	73.49 210	95.96 312	71.10 338	68.73 391	91.21 355

114514_t		89.51 145	88.50 158	92.54 121	98.11 36	81.99 167	95.16 122	96.36 109	70.19 390	85.81 217	95.25 132	76.70 163	98.63 110	82.07 223	96.86 101	97.00 132

GBi-Net		87.26 220	85.98 237	91.08 187	94.01 213	83.10 133	95.14 123	94.94 215	83.57 217	84.37 264	91.64 267	66.59 297	96.34 297	78.23 280	85.36 282	93.79 274

test1		87.26 220	85.98 237	91.08 187	94.01 213	83.10 133	95.14 123	94.94 215	83.57 217	84.37 264	91.64 267	66.59 297	96.34 297	78.23 280	85.36 282	93.79 274

FMVSNet1		85.85 266	84.11 283	91.08 187	92.81 259	83.10 133	95.14 123	94.94 215	81.64 270	82.68 300	91.64 267	59.01 355	96.34 297	75.37 308	83.78 295	93.79 274

ETV-MVS		92.74 78	92.66 76	92.97 97	95.20 147	84.04 105	95.07 126	96.51 99	90.73 22	92.96 74	91.19 282	84.06 75	98.34 139	91.72 93	96.54 107	96.54 155

v7n		86.81 239	85.76 248	89.95 236	90.72 334	79.25 247	95.07 126	95.92 149	84.45 200	82.29 304	90.86 293	72.60 223	97.53 201	79.42 269	80.52 345	93.08 309

ACMP	84.23 8	89.01 165	88.35 162	90.99 194	94.73 171	81.27 185	95.07 126	95.89 154	86.48 147	83.67 284	94.30 171	69.33 264	97.99 173	87.10 154	88.55 245	93.72 283
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
thres100view900		87.63 203	86.71 204	90.38 218	96.12 102	78.55 255	95.03 129	91.58 325	87.15 130	88.06 168	92.29 243	68.91 274	98.10 156	70.13 345	91.10 203	94.48 243

MCST-MVS		94.45 24	94.20 38	95.19 13	98.46 19	87.50 16	95.00 130	97.12 44	87.13 131	92.51 92	96.30 86	89.24 17	99.34 37	93.46 45	98.62 46	98.73 18

casdiffmvs_mvg		92.96 75	92.83 73	93.35 77	94.59 179	83.40 123	95.00 130	96.34 110	90.30 31	92.05 100	96.05 98	83.43 80	98.15 153	92.07 80	95.67 121	98.49 29
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
pmmvs6		83.42 307	81.60 311	88.87 272	88.01 375	77.87 275	94.96 132	94.24 251	74.67 358	78.80 349	91.09 289	60.17 347	96.49 285	77.06 294	75.40 375	92.23 335

CANet		93.54 55	93.20 66	94.55 43	95.65 128	85.73 65	94.94 133	96.69 87	91.89 8	90.69 127	95.88 107	81.99 109	99.54 20	93.14 52	97.95 74	98.39 39

DTE-MVSNet		86.11 261	85.48 254	87.98 297	91.65 296	74.92 319	94.93 134	95.75 163	87.36 128	82.26 305	93.04 220	72.85 219	95.82 320	74.04 319	77.46 366	93.20 303

TranMVSNet+NR-MVSNet		88.84 167	87.95 173	91.49 169	92.68 262	83.01 141	94.92 135	96.31 112	89.88 41	85.53 226	93.85 194	76.63 165	96.96 257	81.91 227	79.87 352	94.50 240

DeepC-MVS	88.79 3	93.31 65	92.99 70	94.26 55	96.07 108	85.83 61	94.89 136	96.99 51	89.02 76	89.56 142	97.37 37	82.51 94	99.38 31	92.20 75	98.30 57	97.57 105
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
thres600view7		87.65 200	86.67 206	90.59 203	96.08 107	78.72 251	94.88 137	91.58 325	87.06 133	88.08 167	92.30 242	68.91 274	98.10 156	70.05 348	91.10 203	94.96 217

Anonymous202405211		87.68 198	86.13 229	92.31 132	96.66 82	80.74 202	94.87 138	91.49 329	80.47 290	89.46 146	95.44 124	54.72 375	98.23 147	82.19 219	89.89 224	97.97 79

PVSNet_Blended_VisFu		91.38 99	90.91 104	92.80 106	96.39 94	83.17 130	94.87 138	96.66 88	83.29 227	89.27 149	94.46 167	80.29 121	99.17 50	87.57 143	95.37 131	96.05 177

RRT-MVS		90.85 109	90.70 108	91.30 177	94.25 201	76.83 294	94.85 140	96.13 131	89.04 73	90.23 133	94.88 147	70.15 253	98.72 100	91.86 91	94.88 140	98.34 42

VNet		92.24 86	91.91 87	93.24 81	96.59 85	83.43 121	94.84 141	96.44 102	89.19 68	94.08 52	95.90 105	77.85 155	98.17 151	88.90 127	93.38 173	98.13 68

MP-MVS-pluss		94.21 34	94.00 45	94.85 25	98.17 33	86.65 31	94.82 142	97.17 40	86.26 154	92.83 79	97.87 23	85.57 54	99.56 12	94.37 36	98.92 17	98.34 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
DP-MVS		87.25 222	85.36 258	92.90 101	97.65 58	83.24 127	94.81 143	92.00 312	74.99 354	81.92 312	95.00 143	72.66 221	99.05 58	66.92 367	92.33 193	96.40 157

FMVSNet2		87.19 228	85.82 244	91.30 177	94.01 213	83.67 113	94.79 144	94.94 215	83.57 217	83.88 279	92.05 256	66.59 297	96.51 284	77.56 287	85.01 285	93.73 282

UniMVSNet (Re)		89.80 138	89.07 142	92.01 140	93.60 234	84.52 89	94.78 145	97.47 11	89.26 65	86.44 204	92.32 241	82.10 105	97.39 225	84.81 179	80.84 339	94.12 255

NR-MVSNet		88.58 177	87.47 184	91.93 148	93.04 252	84.16 102	94.77 146	96.25 120	89.05 72	80.04 336	93.29 210	79.02 138	97.05 252	81.71 234	80.05 349	94.59 232

UniMVSNet_ETH3D		87.53 209	86.37 219	91.00 193	92.44 267	78.96 250	94.74 147	95.61 176	84.07 206	85.36 242	94.52 166	59.78 350	97.34 227	82.93 203	87.88 259	96.71 147

F-COLMAP		87.95 191	86.80 201	91.40 173	96.35 96	80.88 198	94.73 148	95.45 188	79.65 300	82.04 310	94.61 161	71.13 235	98.50 119	76.24 302	91.05 208	94.80 226

ACMH	80.38 17	85.36 275	83.68 290	90.39 216	94.45 191	80.63 204	94.73 148	94.85 225	82.09 252	77.24 358	92.65 231	60.01 348	97.58 197	72.25 330	84.87 286	92.96 312
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis1_n_1920		89.39 153	89.84 125	88.04 296	92.97 256	72.64 348	94.71 150	96.03 142	86.18 156	91.94 106	96.56 81	61.63 330	95.74 325	93.42 47	95.11 137	95.74 189

test_vis1_n		86.56 250	86.49 217	86.78 332	88.51 366	72.69 345	94.68 151	93.78 269	79.55 301	90.70 126	95.31 129	48.75 391	93.28 368	93.15 51	93.99 158	94.38 247

anonymousdsp		87.84 193	87.09 192	90.12 227	89.13 361	80.54 207	94.67 152	95.55 179	82.05 253	83.82 280	92.12 249	71.47 233	97.15 241	87.15 150	87.80 263	92.67 320

DP-MVS Recon		91.95 89	91.28 96	93.96 60	98.33 27	85.92 57	94.66 153	96.66 88	82.69 242	90.03 139	95.82 110	82.30 99	99.03 61	84.57 182	96.48 110	96.91 138

thisisatest0530		88.67 172	87.61 180	91.86 154	94.87 165	80.07 219	94.63 154	89.90 364	84.00 207	88.46 161	93.78 196	66.88 292	98.46 125	83.30 198	92.65 187	97.06 127

Effi-MVS+		91.59 97	91.11 99	93.01 94	94.35 199	83.39 124	94.60 155	95.10 208	87.10 132	90.57 128	93.10 218	81.43 113	98.07 167	89.29 123	94.48 152	97.59 104

tfpn200view9		87.58 207	86.64 207	90.41 215	95.99 114	78.64 253	94.58 156	91.98 314	86.94 137	88.09 165	91.77 263	69.18 270	98.10 156	70.13 345	91.10 203	94.48 243

thres400		87.62 205	86.64 207	90.57 204	95.99 114	78.64 253	94.58 156	91.98 314	86.94 137	88.09 165	91.77 263	69.18 270	98.10 156	70.13 345	91.10 203	94.96 217

test_fmvs1_n		87.03 234	87.04 195	86.97 325	89.74 355	71.86 355	94.55 158	94.43 241	78.47 318	91.95 105	95.50 123	51.16 386	93.81 360	93.02 55	94.56 149	95.26 205

casdiffmvs		92.51 81	92.43 81	92.74 110	94.41 194	81.98 168	94.54 159	96.23 122	89.57 56	91.96 104	96.17 94	82.58 93	98.01 171	90.95 105	95.45 129	98.23 62
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
v8		87.50 212	86.71 204	89.89 238	91.37 304	79.40 238	94.50 160	95.38 194	84.81 192	83.60 287	91.33 277	76.05 168	97.42 214	82.84 206	80.51 346	92.84 317

tfpnnormal		84.72 291	83.23 297	89.20 263	92.79 260	80.05 221	94.48 161	95.81 158	82.38 246	81.08 321	91.21 281	69.01 273	96.95 258	61.69 386	80.59 342	90.58 368

EI-MVSNet-Vis-set		93.01 74	92.92 71	93.29 78	95.01 154	83.51 120	94.48 161	95.77 161	90.87 15	92.52 91	96.67 71	84.50 71	99.00 71	91.99 84	94.44 154	97.36 111

v10		87.25 222	86.38 218	89.85 239	91.19 310	79.50 235	94.48 161	95.45 188	83.79 213	83.62 286	91.19 282	75.13 182	97.42 214	81.94 226	80.60 341	92.63 322

Effi-MVS+-dtu		88.65 173	88.35 162	89.54 254	93.33 241	76.39 302	94.47 164	94.36 245	87.70 121	85.43 235	89.56 331	73.45 211	97.26 234	85.57 171	91.28 202	94.97 214

DU-MVS		89.34 155	88.50 158	91.85 156	93.04 252	83.72 111	94.47 164	96.59 93	89.50 57	86.46 201	93.29 210	77.25 157	97.23 237	84.92 176	81.02 335	94.59 232

ACMH+	81.04 14	85.05 283	83.46 293	89.82 241	94.66 176	79.37 239	94.44 166	94.12 257	82.19 251	78.04 353	92.82 226	58.23 358	97.54 200	73.77 323	82.90 309	92.54 323

UniMVSNet_NR-MVSNet		89.92 135	89.29 138	91.81 159	93.39 240	83.72 111	94.43 167	97.12 44	89.80 47	86.46 201	93.32 207	83.16 84	97.23 237	84.92 176	81.02 335	94.49 242

AdaColmap		89.89 136	89.07 142	92.37 129	97.41 65	83.03 139	94.42 168	95.92 149	82.81 239	86.34 207	94.65 160	73.89 204	99.02 64	80.69 249	95.51 124	95.05 212

EI-MVSNet-UG-set		92.74 78	92.62 78	93.12 87	94.86 166	83.20 129	94.40 169	95.74 164	90.71 23	92.05 100	96.60 78	84.00 76	98.99 73	91.55 95	93.63 164	97.17 120

TSAR-MVS + GP.		93.66 53	93.41 61	94.41 49	96.59 85	86.78 26	94.40 169	93.93 261	89.77 51	94.21 46	95.59 120	87.35 34	98.61 113	92.72 60	96.15 115	97.83 91

HQP-NCC					94.17 205		94.39 171		88.81 79	85.43 235

ACMP_Plane					94.17 205		94.39 171		88.81 79	85.43 235

HQP-MVS		89.80 138	89.28 139	91.34 176	94.17 205	81.56 175	94.39 171	96.04 140	88.81 79	85.43 235	93.97 186	73.83 206	97.96 175	87.11 152	89.77 229	94.50 240

TAPA-MVS	84.62 6	88.16 186	87.01 196	91.62 164	96.64 83	80.65 203	94.39 171	96.21 126	76.38 339	86.19 211	95.44 124	79.75 127	98.08 166	62.75 384	95.29 133	96.13 169
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
mmtdpeth		85.04 285	84.15 282	87.72 304	93.11 247	75.74 311	94.37 175	92.83 288	84.98 185	89.31 148	86.41 373	61.61 332	97.14 244	92.63 63	62.11 401	90.29 369

PAPM_NR		91.22 103	90.78 107	92.52 122	97.60 59	81.46 181	94.37 175	96.24 121	86.39 151	87.41 181	94.80 153	82.06 107	98.48 121	82.80 208	95.37 131	97.61 102

MTAPA		94.42 28	94.22 35	95.00 18	98.42 21	86.95 21	94.36 177	96.97 53	91.07 13	93.14 70	97.56 29	84.30 73	99.56 12	93.43 46	98.75 30	98.47 33

PLC	84.53 7	89.06 162	88.03 171	92.15 138	97.27 71	82.69 153	94.29 178	95.44 190	79.71 299	84.01 277	94.18 178	76.68 164	98.75 97	77.28 289	93.41 172	95.02 213
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
baseline1		88.10 187	87.28 189	90.57 204	94.96 158	80.07 219	94.27 179	91.29 334	86.74 142	87.41 181	94.00 184	76.77 162	96.20 302	80.77 247	79.31 358	95.44 198

dcpmvs_2		93.49 56	94.19 39	91.38 174	97.69 57	76.78 295	94.25 180	96.29 113	88.33 96	94.46 42	96.88 61	88.07 25	98.64 108	93.62 44	98.09 68	98.73 18

COLMAP_ROB	80.39 16	83.96 300	82.04 309	89.74 245	95.28 141	79.75 231	94.25 180	92.28 303	75.17 352	78.02 354	93.77 197	58.60 357	97.84 181	65.06 376	85.92 278	91.63 345
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
V42		87.68 198	86.86 198	90.15 225	90.58 338	80.14 216	94.24 182	95.28 199	83.66 215	85.67 221	91.33 277	74.73 189	97.41 220	84.43 185	81.83 321	92.89 315

Baseline_NR-MVSNet		87.07 232	86.63 209	88.40 283	91.44 299	77.87 275	94.23 183	92.57 296	84.12 205	85.74 220	92.08 253	77.25 157	96.04 307	82.29 217	79.94 350	91.30 353

FMVSNet3		87.40 215	86.11 231	91.30 177	93.79 226	83.64 115	94.20 184	94.81 229	83.89 210	84.37 264	91.87 262	68.45 280	96.56 280	78.23 280	85.36 282	93.70 284

OPM-MVS		90.12 127	89.56 130	91.82 157	93.14 245	83.90 107	94.16 185	95.74 164	88.96 78	87.86 171	95.43 126	72.48 224	97.91 179	88.10 138	90.18 219	93.65 285
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
baseline		92.39 85	92.29 83	92.69 114	94.46 190	81.77 172	94.14 186	96.27 117	89.22 66	91.88 107	96.00 99	82.35 96	97.99 173	91.05 101	95.27 135	98.30 49

MonoMVSNet		86.89 238	86.55 213	87.92 300	89.46 359	73.75 331	94.12 187	93.10 280	87.82 118	85.10 246	90.76 299	69.59 260	94.94 345	86.47 159	82.50 312	95.07 211

test_prior2							94.12 187		87.67 123	92.63 88	96.39 85	86.62 40		91.50 96	98.67 40

test_yl		90.69 114	90.02 122	92.71 111	95.72 123	82.41 161	94.11 189	95.12 206	85.63 169	91.49 117	94.70 155	74.75 187	98.42 134	86.13 163	92.53 190	97.31 112

DCV-MVSNet		90.69 114	90.02 122	92.71 111	95.72 123	82.41 161	94.11 189	95.12 206	85.63 169	91.49 117	94.70 155	74.75 187	98.42 134	86.13 163	92.53 190	97.31 112

test_prior4						85.96 54	94.11 189

EPNet_dtu		86.49 255	85.94 240	88.14 294	90.24 345	72.82 343	94.11 189	92.20 306	86.66 145	79.42 344	92.36 240	73.52 209	95.81 321	71.26 333	93.66 163	95.80 187
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CNLPA		89.07 161	87.98 172	92.34 130	96.87 77	84.78 81	94.08 193	93.24 277	81.41 276	84.46 261	95.13 140	75.57 179	96.62 272	77.21 290	93.84 162	95.61 196

TEST9					97.53 61	86.49 37	94.07 194	96.78 75	81.61 272	92.77 82	96.20 90	87.71 28	99.12 54

train_agg		93.44 59	93.08 67	94.52 44	97.53 61	86.49 37	94.07 194	96.78 75	81.86 263	92.77 82	96.20 90	87.63 29	99.12 54	92.14 78	98.69 35	97.94 81

CDPH-MVS		92.83 76	92.30 82	94.44 45	97.79 52	86.11 49	94.06 196	96.66 88	80.09 294	92.77 82	96.63 76	86.62 40	99.04 60	87.40 145	98.66 41	98.17 66

VPNet		88.20 185	87.47 184	90.39 216	93.56 235	79.46 236	94.04 197	95.54 181	88.67 86	86.96 187	94.58 165	69.33 264	97.15 241	84.05 189	80.53 344	94.56 235

Fast-Effi-MVS+-dtu		87.44 213	86.72 203	89.63 252	92.04 278	77.68 283	94.03 198	93.94 260	85.81 163	82.42 303	91.32 279	70.33 250	97.06 250	80.33 256	90.23 218	94.14 254

test_8					97.49 63	86.30 45	94.02 199	96.76 78	81.86 263	92.70 86	96.20 90	87.63 29	99.02 64

test_fmvs1		87.34 217	87.56 181	86.68 333	90.59 337	71.80 357	94.01 200	94.04 259	78.30 322	91.97 103	95.22 133	56.28 366	93.71 362	92.89 56	94.71 143	94.52 237

OurMVSNet-221017-0		85.35 276	84.64 275	87.49 310	90.77 331	72.59 350	94.01 200	94.40 243	84.72 195	79.62 343	93.17 214	61.91 328	96.72 266	81.99 225	81.16 329	93.16 305

v2v482		87.84 193	87.06 193	90.17 223	90.99 319	79.23 248	94.00 202	95.13 205	84.87 189	85.53 226	92.07 255	74.45 193	97.45 209	84.71 181	81.75 323	93.85 272

DeepPCF-MVS	89.96 1	94.20 36	94.77 20	92.49 123	96.52 91	80.00 225	94.00 202	97.08 47	90.05 36	95.65 29	97.29 39	89.66 13	98.97 78	93.95 39	98.71 32	98.50 27

v1144		87.61 206	86.79 202	90.06 230	91.01 318	79.34 241	93.95 204	95.42 193	83.36 226	85.66 222	91.31 280	74.98 185	97.42 214	83.37 197	82.06 317	93.42 294

hse-mvs2		89.88 137	89.34 136	91.51 168	94.83 168	81.12 191	93.94 205	93.91 264	89.80 47	93.08 71	93.60 201	75.77 172	97.66 191	92.07 80	77.07 369	95.74 189

test_fmvs2		83.98 299	84.03 284	83.83 362	87.16 380	67.53 388	93.93 206	92.89 286	77.62 328	86.89 193	93.53 202	47.18 395	92.02 380	90.54 110	86.51 275	91.93 340

v144192		87.19 228	86.35 220	89.74 245	90.64 336	78.24 266	93.92 207	95.43 191	81.93 258	85.51 228	91.05 290	74.21 198	97.45 209	82.86 205	81.56 325	93.53 288

PVSNet_BlendedMVS		89.98 131	89.70 126	90.82 199	96.12 102	81.25 186	93.92 207	96.83 69	83.49 221	89.10 151	92.26 244	81.04 116	98.85 89	86.72 157	87.86 260	92.35 332

AUN-MVS		87.78 196	86.54 214	91.48 170	94.82 169	81.05 192	93.91 209	93.93 261	83.00 234	86.93 188	93.53 202	69.50 262	97.67 189	86.14 161	77.12 368	95.73 191

test_cas_vis1_n_1920		88.83 170	88.85 151	88.78 273	91.15 314	76.72 296	93.85 210	94.93 219	83.23 230	92.81 80	96.00 99	61.17 341	94.45 347	91.67 94	94.84 141	95.17 208

v1921920		86.97 235	86.06 234	89.69 249	90.53 341	78.11 269	93.80 211	95.43 191	81.90 260	85.33 243	91.05 290	72.66 221	97.41 220	82.05 224	81.80 322	93.53 288

v1192		87.25 222	86.33 221	90.00 235	90.76 332	79.04 249	93.80 211	95.48 184	82.57 243	85.48 230	91.18 284	73.38 215	97.42 214	82.30 216	82.06 317	93.53 288

XXY-MVS		87.65 200	86.85 199	90.03 231	92.14 274	80.60 206	93.76 213	95.23 201	82.94 236	84.60 256	94.02 182	74.27 195	95.49 335	81.04 241	83.68 298	94.01 263

MVSTER		88.84 167	88.29 166	90.51 209	92.95 257	80.44 209	93.73 214	95.01 212	84.66 197	87.15 185	93.12 217	72.79 220	97.21 239	87.86 139	87.36 268	93.87 269

IterMVS-LS		88.36 181	87.91 175	89.70 248	93.80 224	78.29 265	93.73 214	95.08 210	85.73 166	84.75 253	91.90 261	79.88 125	96.92 260	83.83 192	82.51 311	93.89 265
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v148		87.04 233	86.32 222	89.21 262	90.94 323	77.26 288	93.71 216	94.43 241	84.84 191	84.36 267	90.80 297	76.04 169	97.05 252	82.12 220	79.60 355	93.31 296

EI-MVSNet		89.10 158	88.86 150	89.80 244	91.84 286	78.30 264	93.70 217	95.01 212	85.73 166	87.15 185	95.28 130	79.87 126	97.21 239	83.81 193	87.36 268	93.88 268

CVMVSNet		84.69 292	84.79 272	84.37 357	91.84 286	64.92 395	93.70 217	91.47 330	66.19 397	86.16 212	95.28 130	67.18 288	93.33 367	80.89 246	90.42 216	94.88 222

v1240		86.78 241	85.85 243	89.56 253	90.45 342	77.79 279	93.61 219	95.37 196	81.65 269	85.43 235	91.15 286	71.50 232	97.43 213	81.47 237	82.05 319	93.47 292

MG-MVS		91.77 92	91.70 91	92.00 143	97.08 74	80.03 223	93.60 220	95.18 204	87.85 116	90.89 125	96.47 83	82.06 107	98.36 136	85.07 174	97.04 94	97.62 101

Fast-Effi-MVS+		89.41 150	88.64 153	91.71 162	94.74 170	80.81 200	93.54 221	95.10 208	83.11 231	86.82 196	90.67 303	79.74 128	97.75 187	80.51 253	93.55 166	96.57 153

OMC-MVS		91.23 102	90.62 109	93.08 90	96.27 97	84.07 103	93.52 222	95.93 148	86.95 136	89.51 143	96.13 96	78.50 146	98.35 138	85.84 168	92.90 182	96.83 143

CANet_DTU		90.26 125	89.41 134	92.81 105	93.46 238	83.01 141	93.48 223	94.47 240	89.43 59	87.76 176	94.23 177	70.54 248	99.03 61	84.97 175	96.39 111	96.38 158

SixPastTwentyTwo		83.91 302	82.90 304	86.92 327	90.99 319	70.67 372	93.48 223	91.99 313	85.54 172	77.62 357	92.11 251	60.59 344	96.87 263	76.05 304	77.75 363	93.20 303

MVS_Test		91.31 101	91.11 99	91.93 148	94.37 195	80.14 216	93.46 225	95.80 159	86.46 149	91.35 121	93.77 197	82.21 102	98.09 164	87.57 143	94.95 139	97.55 107

reproduce_monomvs		86.37 258	85.87 242	87.87 301	93.66 232	73.71 332	93.44 226	95.02 211	88.61 89	82.64 302	91.94 259	57.88 360	96.68 269	89.96 116	79.71 354	93.22 301

patch_mono-2		93.74 51	94.32 28	92.01 140	97.54 60	78.37 262	93.40 227	97.19 35	88.02 108	94.99 39	97.21 44	88.35 21	98.44 131	94.07 38	98.09 68	99.23 1

旧先验2							93.36 228		71.25 385	94.37 43			97.13 245	86.74 155

testing3		80.46 336	79.59 333	83.06 365	93.44 239	64.64 396	93.33 229	85.47 391	84.34 202	79.93 338	90.84 295	44.35 401	92.39 376	57.06 399	87.56 264	92.16 337

xiu_mvs_v1_base_debu		90.64 117	90.05 119	92.40 126	93.97 218	84.46 92	93.32 230	95.46 185	85.17 178	92.25 95	94.03 179	70.59 244	98.57 116	90.97 102	94.67 144	94.18 251

xiu_mvs_v1_base		90.64 117	90.05 119	92.40 126	93.97 218	84.46 92	93.32 230	95.46 185	85.17 178	92.25 95	94.03 179	70.59 244	98.57 116	90.97 102	94.67 144	94.18 251

xiu_mvs_v1_base_debi		90.64 117	90.05 119	92.40 126	93.97 218	84.46 92	93.32 230	95.46 185	85.17 178	92.25 95	94.03 179	70.59 244	98.57 116	90.97 102	94.67 144	94.18 251

EU-MVSNet		81.32 328	80.95 316	82.42 370	88.50 368	63.67 399	93.32 230	91.33 332	64.02 400	80.57 328	92.83 225	61.21 339	92.27 378	76.34 300	80.38 347	91.32 352

TAMVS		89.21 156	88.29 166	91.96 146	93.71 228	82.62 156	93.30 234	94.19 252	82.22 250	87.78 175	93.94 187	78.83 139	96.95 258	77.70 285	92.98 181	96.32 159

BH-untuned		88.60 175	88.13 170	90.01 234	95.24 145	78.50 258	93.29 235	94.15 254	84.75 194	84.46 261	93.40 204	75.76 174	97.40 222	77.59 286	94.52 151	94.12 255

无先验							93.28 236	96.26 118	73.95 365				99.05 58	80.56 252		96.59 151

thres200		87.21 226	86.24 226	90.12 227	95.36 138	78.53 256	93.26 237	92.10 308	86.42 150	88.00 170	91.11 288	69.24 269	98.00 172	69.58 349	91.04 209	93.83 273

WR-MVS		88.38 179	87.67 179	90.52 208	93.30 242	80.18 214	93.26 237	95.96 147	88.57 91	85.47 231	92.81 227	76.12 167	96.91 261	81.24 239	82.29 315	94.47 245

MVS_111021_HR		93.45 58	93.31 62	93.84 64	96.99 75	84.84 78	93.24 239	97.24 32	88.76 82	91.60 116	95.85 108	86.07 49	98.66 104	91.91 88	98.16 63	98.03 77

LCM-MVSNet-Re		88.30 183	88.32 165	88.27 289	94.71 173	72.41 353	93.15 240	90.98 341	87.77 119	79.25 345	91.96 258	78.35 148	95.75 324	83.04 201	95.62 122	96.65 149

AllTest		83.42 307	81.39 313	89.52 255	95.01 154	77.79 279	93.12 241	90.89 345	77.41 330	76.12 366	93.34 205	54.08 378	97.51 203	68.31 356	84.27 291	93.26 297

TDRefinement		79.81 343	77.34 348	87.22 320	79.24 408	75.48 314	93.12 241	92.03 311	76.45 338	75.01 373	91.58 273	49.19 390	96.44 290	70.22 344	69.18 388	89.75 374

新几何2							93.11 243

jason		90.80 110	90.10 117	92.90 101	93.04 252	83.53 119	93.08 244	94.15 254	80.22 291	91.41 119	94.91 145	76.87 159	97.93 178	90.28 114	96.90 98	97.24 116
jason: jason.
MVS_111021_LR		92.47 83	92.29 83	92.98 96	95.99 114	84.43 95	93.08 244	96.09 135	88.20 103	91.12 123	95.72 116	81.33 114	97.76 184	91.74 92	97.37 88	96.75 145

DELS-MVS		93.43 63	93.25 64	93.97 59	95.42 137	85.04 75	93.06 246	97.13 43	90.74 21	91.84 109	95.09 141	86.32 45	99.21 48	91.22 99	98.45 52	97.65 100
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
CDS-MVSNet		89.45 148	88.51 157	92.29 134	93.62 233	83.61 118	93.01 247	94.68 236	81.95 257	87.82 174	93.24 212	78.69 142	96.99 255	80.34 255	93.23 177	96.28 162
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
test_0402		81.30 329	79.17 339	87.67 305	93.19 244	78.17 267	92.98 248	91.71 319	75.25 351	76.02 368	90.31 310	59.23 353	96.37 294	50.22 404	83.63 299	88.47 389

1112_ss		88.42 178	87.33 187	91.72 161	94.92 161	80.98 194	92.97 249	94.54 238	78.16 326	83.82 280	93.88 192	78.78 141	97.91 179	79.45 266	89.41 233	96.26 163

原ACMM2							92.94 250

mamv4		90.92 107	91.78 89	88.33 288	95.67 127	70.75 371	92.92 251	96.02 143	81.90 260	88.11 164	95.34 128	85.88 51	96.97 256	95.22 27	95.01 138	97.26 115

SDMVSNet		90.19 126	89.61 129	91.93 148	96.00 111	83.09 136	92.89 252	95.98 144	88.73 83	86.85 194	95.20 136	72.09 228	97.08 247	88.90 127	89.85 226	95.63 194

BH-RMVSNet		88.37 180	87.48 183	91.02 191	95.28 141	79.45 237	92.89 252	93.07 282	85.45 174	86.91 190	94.84 152	70.35 249	97.76 184	73.97 320	94.59 148	95.85 183

Anonymous20240521		80.44 337	79.21 337	84.11 360	85.75 389	67.89 383	92.86 254	93.23 278	75.61 348	75.59 371	87.47 363	50.03 387	94.33 351	71.14 337	81.21 328	90.12 371

lupinMVS		90.92 107	90.21 113	93.03 93	93.86 221	83.88 108	92.81 255	93.86 265	79.84 297	91.76 112	94.29 172	77.92 152	98.04 169	90.48 113	97.11 91	97.17 120

EG-PatchMatch MVS		82.37 315	80.34 321	88.46 282	90.27 344	79.35 240	92.80 256	94.33 246	77.14 334	73.26 383	90.18 315	47.47 394	96.72 266	70.25 342	87.32 270	89.30 378

PAPR		90.02 130	89.27 140	92.29 134	95.78 121	80.95 196	92.68 257	96.22 123	81.91 259	86.66 198	93.75 199	82.23 101	98.44 131	79.40 270	94.79 142	97.48 108

DPM-MVS		92.58 80	91.74 90	95.08 15	96.19 99	89.31 5	92.66 258	96.56 96	83.44 222	91.68 115	95.04 142	86.60 42	98.99 73	85.60 170	97.92 75	96.93 136

1314		87.51 210	86.57 212	90.34 220	92.42 268	79.74 232	92.63 259	95.35 198	78.35 321	80.14 333	91.62 271	74.05 201	97.15 241	81.05 240	93.53 167	94.12 255

MVS		87.44 213	86.10 232	91.44 172	92.61 263	83.62 116	92.63 259	95.66 172	67.26 395	81.47 315	92.15 247	77.95 151	98.22 149	79.71 262	95.48 126	92.47 326

K. test v3		81.59 323	80.15 325	85.91 343	89.89 353	69.42 379	92.57 261	87.71 380	85.56 171	73.44 382	89.71 328	55.58 367	95.52 331	77.17 291	69.76 385	92.78 319

PVSNet_Blended		90.73 113	90.32 112	91.98 144	96.12 102	81.25 186	92.55 262	96.83 69	82.04 255	89.10 151	92.56 234	81.04 116	98.85 89	86.72 157	95.91 118	95.84 184

TR-MVS		86.78 241	85.76 248	89.82 241	94.37 195	78.41 260	92.47 263	92.83 288	81.11 284	86.36 205	92.40 238	68.73 277	97.48 205	73.75 324	89.85 226	93.57 287

pmmvs5		84.21 296	82.84 306	88.34 287	88.95 363	76.94 292	92.41 264	91.91 318	75.63 347	80.28 330	91.18 284	64.59 312	95.57 329	77.09 293	83.47 301	92.53 324

BH-w/o		87.57 208	87.05 194	89.12 265	94.90 164	77.90 273	92.41 264	93.51 273	82.89 238	83.70 283	91.34 276	75.75 175	97.07 249	75.49 306	93.49 169	92.39 330

WTY-MVS		89.60 142	88.92 146	91.67 163	95.47 136	81.15 190	92.38 266	94.78 231	83.11 231	89.06 153	94.32 170	78.67 143	96.61 275	81.57 235	90.89 210	97.24 116

diffmvs		91.37 100	91.23 97	91.77 160	93.09 248	80.27 212	92.36 267	95.52 183	87.03 134	91.40 120	94.93 144	80.08 123	97.44 212	92.13 79	94.56 149	97.61 102
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
sd_testset		88.59 176	87.85 176	90.83 198	96.00 111	80.42 210	92.35 268	94.71 234	88.73 83	86.85 194	95.20 136	67.31 284	96.43 291	79.64 264	89.85 226	95.63 194

test_fmvs3		77.67 355	77.16 352	79.22 377	79.52 407	61.14 403	92.34 269	91.64 324	73.98 364	78.86 346	86.59 370	27.38 413	87.03 401	88.12 137	75.97 373	89.50 375

ET-MVSNet_ETH3D		87.51 210	85.91 241	92.32 131	93.70 230	83.93 106	92.33 270	90.94 343	84.16 203	72.09 386	92.52 235	69.90 254	95.85 318	89.20 124	88.36 252	97.17 120

OpenMVS_ROB	74.94 19	79.51 346	77.03 353	86.93 326	87.00 381	76.23 305	92.33 270	90.74 348	68.93 392	74.52 377	88.23 353	49.58 389	96.62 272	57.64 397	84.29 290	87.94 392

LTVRE_ROB	82.13 13	86.26 260	84.90 269	90.34 220	94.44 192	81.50 177	92.31 272	94.89 221	83.03 233	79.63 342	92.67 230	69.69 258	97.79 182	71.20 334	86.26 277	91.72 343
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
xiu_mvs_v2_base		91.13 105	90.89 105	91.86 154	94.97 157	82.42 159	92.24 273	95.64 175	86.11 161	91.74 114	93.14 216	79.67 132	98.89 84	89.06 126	95.46 128	94.28 250

test222					96.55 88	81.70 173	92.22 274	95.01 212	68.36 393	90.20 134	96.14 95	80.26 122			97.80 79	96.05 177

ab-mvs		89.41 150	88.35 162	92.60 117	95.15 151	82.65 155	92.20 275	95.60 177	83.97 208	88.55 159	93.70 200	74.16 200	98.21 150	82.46 213	89.37 234	96.94 135

testdata1							92.15 276		87.94 110

CLD-MVS		89.47 147	88.90 148	91.18 182	94.22 203	82.07 166	92.13 277	96.09 135	87.90 112	85.37 241	92.45 237	74.38 194	97.56 199	87.15 150	90.43 215	93.93 264
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVP-Stereo		85.97 263	84.86 270	89.32 260	90.92 325	82.19 164	92.11 278	94.19 252	78.76 314	78.77 350	91.63 270	68.38 281	96.56 280	75.01 313	93.95 159	89.20 381
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
PS-MVSNAJ		91.18 104	90.92 103	91.96 146	95.26 144	82.60 157	92.09 279	95.70 168	86.27 153	91.84 109	92.46 236	79.70 129	98.99 73	89.08 125	95.86 119	94.29 249

HY-MVS	83.01 12	89.03 163	87.94 174	92.29 134	94.86 166	82.77 146	92.08 280	94.49 239	81.52 275	86.93 188	92.79 229	78.32 149	98.23 147	79.93 260	90.55 213	95.88 182

WB-MVSnew		83.77 304	83.28 295	85.26 351	91.48 298	71.03 367	91.89 281	87.98 377	78.91 308	84.78 252	90.22 312	69.11 272	94.02 356	64.70 377	90.44 214	90.71 363

baseline2		86.50 253	85.39 256	89.84 240	91.12 315	76.70 297	91.88 282	88.58 374	82.35 248	79.95 337	90.95 292	73.42 213	97.63 195	80.27 257	89.95 223	95.19 207

XVG-OURS-SEG-HR		89.95 133	89.45 131	91.47 171	94.00 216	81.21 189	91.87 283	96.06 139	85.78 164	88.55 159	95.73 115	74.67 191	97.27 232	88.71 130	89.64 231	95.91 180

D2MVS		85.90 264	85.09 264	88.35 285	90.79 330	77.42 286	91.83 284	95.70 168	80.77 287	80.08 335	90.02 320	66.74 295	96.37 294	81.88 228	87.97 258	91.26 354

Test_1112_low_res		87.65 200	86.51 215	91.08 187	94.94 160	79.28 245	91.77 285	94.30 247	76.04 344	83.51 289	92.37 239	77.86 154	97.73 188	78.69 275	89.13 240	96.22 164

IB-MVS	80.51 15	85.24 280	83.26 296	91.19 181	92.13 275	79.86 229	91.75 286	91.29 334	83.28 228	80.66 326	88.49 348	61.28 336	98.46 125	80.99 244	79.46 356	95.25 206
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
sss		88.93 166	88.26 168	90.94 197	94.05 211	80.78 201	91.71 287	95.38 194	81.55 274	88.63 158	93.91 191	75.04 184	95.47 336	82.47 212	91.61 198	96.57 153

XVG-ACMP-BASELINE		86.00 262	84.84 271	89.45 258	91.20 309	78.00 270	91.70 288	95.55 179	85.05 184	82.97 297	92.25 245	54.49 376	97.48 205	82.93 203	87.45 267	92.89 315

RPSCF		85.07 282	84.27 279	87.48 311	92.91 258	70.62 373	91.69 289	92.46 297	76.20 343	82.67 301	95.22 133	63.94 316	97.29 231	77.51 288	85.80 279	94.53 236

mvs_anonymous		89.37 154	89.32 137	89.51 257	93.47 237	74.22 327	91.65 290	94.83 227	82.91 237	85.45 232	93.79 195	81.23 115	96.36 296	86.47 159	94.09 157	97.94 81

MIMVSNet1		79.38 347	77.28 349	85.69 345	86.35 383	73.67 333	91.61 291	92.75 292	78.11 327	72.64 385	88.12 354	48.16 392	91.97 382	60.32 389	77.49 365	91.43 351

testing91		87.11 231	86.18 227	89.92 237	94.43 193	75.38 317	91.53 292	92.27 304	86.48 147	86.50 199	90.24 311	61.19 340	97.53 201	82.10 221	90.88 211	96.84 142

FMVSNet5		81.52 325	79.60 332	87.27 315	91.17 311	77.95 271	91.49 293	92.26 305	76.87 335	76.16 365	87.91 358	51.67 384	92.34 377	67.74 360	81.16 329	91.52 348

Anonymous20231206		81.03 331	79.77 330	84.82 354	87.85 378	70.26 375	91.42 294	92.08 309	73.67 367	77.75 355	89.25 334	62.43 325	93.08 371	61.50 387	82.00 320	91.12 358

FA-MVS(test-final)		89.66 140	88.91 147	91.93 148	94.57 182	80.27 212	91.36 295	94.74 233	84.87 189	89.82 140	92.61 233	74.72 190	98.47 124	83.97 190	93.53 167	97.04 129

testing99		86.72 245	85.73 251	89.69 249	94.23 202	74.91 320	91.35 296	90.97 342	86.14 158	86.36 205	90.22 312	59.41 352	97.48 205	82.24 218	90.66 212	96.69 148

testing11		86.44 256	85.35 259	89.69 249	94.29 200	75.40 316	91.30 297	90.53 350	84.76 193	85.06 247	90.13 317	58.95 356	97.45 209	82.08 222	91.09 207	96.21 166

testgi		80.94 334	80.20 324	83.18 363	87.96 376	66.29 389	91.28 298	90.70 349	83.70 214	78.12 352	92.84 224	51.37 385	90.82 390	63.34 381	82.46 313	92.43 328

XVG-OURS		89.40 152	88.70 152	91.52 167	94.06 210	81.46 181	91.27 299	96.07 137	86.14 158	88.89 155	95.77 113	68.73 277	97.26 234	87.39 146	89.96 222	95.83 185

MS-PatchMatch		85.05 283	84.16 281	87.73 303	91.42 302	78.51 257	91.25 300	93.53 272	77.50 329	80.15 332	91.58 273	61.99 327	95.51 332	75.69 305	94.35 155	89.16 382

ETVMVS		84.43 294	82.92 303	88.97 271	94.37 195	74.67 321	91.23 301	88.35 376	83.37 225	86.06 214	89.04 337	55.38 370	95.67 327	67.12 363	91.34 201	96.58 152

c3_l		87.14 230	86.50 216	89.04 268	92.20 272	77.26 288	91.22 302	94.70 235	82.01 256	84.34 268	90.43 308	78.81 140	96.61 275	83.70 195	81.09 332	93.25 299

SCA		86.32 259	85.18 262	89.73 247	92.15 273	76.60 298	91.12 303	91.69 321	83.53 220	85.50 229	88.81 342	66.79 293	96.48 286	76.65 295	90.35 217	96.12 170

testing222		84.84 289	83.32 294	89.43 259	94.15 208	75.94 307	91.09 304	89.41 372	84.90 187	85.78 218	89.44 332	52.70 383	96.28 300	70.80 340	91.57 199	96.07 174

test20.03		79.95 342	79.08 341	82.55 367	85.79 388	67.74 386	91.09 304	91.08 337	81.23 282	74.48 378	89.96 323	61.63 330	90.15 392	60.08 390	76.38 371	89.76 373

KD-MVS_self_test		80.20 339	79.24 336	83.07 364	85.64 390	65.29 393	91.01 306	93.93 261	78.71 316	76.32 364	86.40 374	59.20 354	92.93 373	72.59 328	69.35 386	91.00 362

UWE-MVS		83.69 306	83.09 299	85.48 346	93.06 250	65.27 394	90.92 307	86.14 386	79.90 296	86.26 209	90.72 302	57.17 363	95.81 321	71.03 339	92.62 188	95.35 203

miper_ehance_all_eth		87.22 225	86.62 210	89.02 269	92.13 275	77.40 287	90.91 308	94.81 229	81.28 279	84.32 269	90.08 319	79.26 135	96.62 272	83.81 193	82.94 306	93.04 310

cl22		86.78 241	85.98 237	89.18 264	92.34 269	77.62 284	90.84 309	94.13 256	81.33 278	83.97 278	90.15 316	73.96 203	96.60 277	84.19 187	82.94 306	93.33 295

cl____		86.52 252	85.78 245	88.75 275	92.03 279	76.46 300	90.74 310	94.30 247	81.83 265	83.34 293	90.78 298	75.74 177	96.57 278	81.74 232	81.54 326	93.22 301

DIV-MVS_self_test		86.53 251	85.78 245	88.75 275	92.02 280	76.45 301	90.74 310	94.30 247	81.83 265	83.34 293	90.82 296	75.75 175	96.57 278	81.73 233	81.52 327	93.24 300

thisisatest0515		87.33 218	85.99 236	91.37 175	93.49 236	79.55 234	90.63 312	89.56 371	80.17 292	87.56 179	90.86 293	67.07 289	98.28 145	81.50 236	93.02 180	96.29 161

PatchMatch-RL		86.77 244	85.54 252	90.47 214	95.88 117	82.71 152	90.54 313	92.31 302	79.82 298	84.32 269	91.57 275	68.77 276	96.39 293	73.16 326	93.48 171	92.32 333

eth_miper_zixun_eth		86.50 253	85.77 247	88.68 278	91.94 281	75.81 310	90.47 314	94.89 221	82.05 253	84.05 275	90.46 307	75.96 170	96.77 265	82.76 209	79.36 357	93.46 293

GA-MVS		86.61 247	85.27 261	90.66 202	91.33 307	78.71 252	90.40 315	93.81 268	85.34 176	85.12 245	89.57 330	61.25 337	97.11 246	80.99 244	89.59 232	96.15 167

FE-MVS		87.40 215	86.02 235	91.57 166	94.56 183	79.69 233	90.27 316	93.72 270	80.57 288	88.80 156	91.62 271	65.32 307	98.59 115	74.97 314	94.33 156	96.44 156

pmmvs4		85.43 273	83.86 288	90.16 224	90.02 350	82.97 143	90.27 316	92.67 294	75.93 345	80.73 324	91.74 265	71.05 236	95.73 326	78.85 274	83.46 302	91.78 342

test_vis1_rt		77.96 354	76.46 354	82.48 369	85.89 387	71.74 359	90.25 318	78.89 408	71.03 387	71.30 390	81.35 397	42.49 403	91.05 389	84.55 183	82.37 314	84.65 395

CL-MVSNet_self_test		81.74 320	80.53 318	85.36 348	85.96 386	72.45 352	90.25 318	93.07 282	81.24 281	79.85 340	87.29 365	70.93 239	92.52 375	66.95 364	69.23 387	91.11 359

test0.0.03 1		82.41 314	81.69 310	84.59 355	88.23 372	72.89 342	90.24 320	87.83 379	83.41 223	79.86 339	89.78 326	67.25 286	88.99 399	65.18 374	83.42 303	91.90 341

cascas		86.43 257	84.98 266	90.80 200	92.10 277	80.92 197	90.24 320	95.91 151	73.10 373	83.57 288	88.39 349	65.15 309	97.46 208	84.90 178	91.43 200	94.03 262

miper_enhance_ethall		86.90 237	86.18 227	89.06 267	91.66 295	77.58 285	90.22 322	94.82 228	79.16 306	84.48 260	89.10 336	79.19 137	96.66 270	84.06 188	82.94 306	92.94 313

WBMVS		84.97 286	84.18 280	87.34 313	94.14 209	71.62 362	90.20 323	92.35 299	81.61 272	84.06 274	90.76 299	61.82 329	96.52 283	78.93 273	83.81 294	93.89 265

IterMVS-SCA-FT		85.45 272	84.53 278	88.18 293	91.71 292	76.87 293	90.19 324	92.65 295	85.40 175	81.44 316	90.54 304	66.79 293	95.00 344	81.04 241	81.05 333	92.66 321

IterMVS		84.88 287	83.98 287	87.60 306	91.44 299	76.03 306	90.18 325	92.41 298	83.24 229	81.06 322	90.42 309	66.60 296	94.28 353	79.46 265	80.98 338	92.48 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
pmmvs-eth3d		80.97 333	78.72 345	87.74 302	84.99 393	79.97 227	90.11 326	91.65 323	75.36 349	73.51 381	86.03 376	59.45 351	93.96 359	75.17 310	72.21 380	89.29 380

UBG		85.51 271	84.57 277	88.35 285	94.21 204	71.78 358	90.07 327	89.66 369	82.28 249	85.91 216	89.01 338	61.30 335	97.06 250	76.58 298	92.06 196	96.22 164

dmvs_re		84.20 297	83.22 298	87.14 323	91.83 288	77.81 277	90.04 328	90.19 355	84.70 196	81.49 314	89.17 335	64.37 314	91.13 388	71.58 332	85.65 281	92.46 327

CHOSEN 1792x2688		88.84 167	87.69 178	92.30 133	96.14 100	81.42 183	90.01 329	95.86 156	74.52 359	87.41 181	93.94 187	75.46 180	98.36 136	80.36 254	95.53 123	97.12 125

HyFIR lowres test		88.09 188	86.81 200	91.93 148	96.00 111	80.63 204	90.01 329	95.79 160	73.42 370	87.68 177	92.10 252	73.86 205	97.96 175	80.75 248	91.70 197	97.19 119

CMPMVS	59.16 21	80.52 335	79.20 338	84.48 356	83.98 395	67.63 387	89.95 331	93.84 267	64.79 399	66.81 397	91.14 287	57.93 359	95.17 339	76.25 301	88.10 254	90.65 364
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
PAPM		86.68 246	85.39 256	90.53 206	93.05 251	79.33 244	89.79 332	94.77 232	78.82 312	81.95 311	93.24 212	76.81 160	97.30 228	66.94 365	93.16 178	94.95 220

ttmdpeth		76.55 358	74.64 363	82.29 372	82.25 402	67.81 385	89.76 333	85.69 389	70.35 389	75.76 369	91.69 266	46.88 396	89.77 394	66.16 370	63.23 400	89.30 378

Syy-MVS		80.07 340	79.78 328	80.94 374	91.92 282	59.93 405	89.75 334	87.40 383	81.72 267	78.82 347	87.20 366	66.29 301	91.29 386	47.06 406	87.84 261	91.60 346

myMVS_eth3d		79.67 345	78.79 344	82.32 371	91.92 282	64.08 397	89.75 334	87.40 383	81.72 267	78.82 347	87.20 366	45.33 399	91.29 386	59.09 394	87.84 261	91.60 346

test-LLR		85.87 265	85.41 255	87.25 317	90.95 321	71.67 360	89.55 336	89.88 365	83.41 223	84.54 258	87.95 356	67.25 286	95.11 341	81.82 229	93.37 174	94.97 214

TESTMET0.1,1		83.74 305	82.85 305	86.42 337	89.96 351	71.21 365	89.55 336	87.88 378	77.41 330	83.37 292	87.31 364	56.71 364	93.65 364	80.62 251	92.85 185	94.40 246

test-mter		84.54 293	83.64 291	87.25 317	90.95 321	71.67 360	89.55 336	89.88 365	79.17 305	84.54 258	87.95 356	55.56 368	95.11 341	81.82 229	93.37 174	94.97 214

TinyColmap		79.76 344	77.69 347	85.97 340	91.71 292	73.12 339	89.55 336	90.36 353	75.03 353	72.03 387	90.19 314	46.22 398	96.19 304	63.11 382	81.03 334	88.59 388

CostFormer		85.77 268	84.94 268	88.26 290	91.16 313	72.58 351	89.47 340	91.04 340	76.26 342	86.45 203	89.97 322	70.74 242	96.86 264	82.35 215	87.07 273	95.34 204

LF4IMVS		80.37 338	79.07 342	84.27 359	86.64 382	69.87 378	89.39 341	91.05 339	76.38 339	74.97 374	90.00 321	47.85 393	94.25 354	74.55 318	80.82 340	88.69 387

USDC		82.76 310	81.26 315	87.26 316	91.17 311	74.55 323	89.27 342	93.39 275	78.26 324	75.30 372	92.08 253	54.43 377	96.63 271	71.64 331	85.79 280	90.61 365

PCF-MVS	84.11 10	87.74 197	86.08 233	92.70 113	94.02 212	84.43 95	89.27 342	95.87 155	73.62 368	84.43 263	94.33 169	78.48 147	98.86 87	70.27 341	94.45 153	94.81 225
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
tpm2		84.08 298	82.94 302	87.48 311	91.39 303	71.27 363	89.23 344	90.37 352	71.95 382	84.64 255	89.33 333	67.30 285	96.55 282	75.17 310	87.09 272	94.63 229

MSDG		84.86 288	83.09 299	90.14 226	93.80 224	80.05 221	89.18 345	93.09 281	78.89 310	78.19 351	91.91 260	65.86 306	97.27 232	68.47 354	88.45 249	93.11 307

EGC-MVSNET		61.97 375	56.37 380	78.77 379	89.63 357	73.50 335	89.12 346	82.79 399	0.21 425	1.24 426	84.80 383	39.48 404	90.04 393	44.13 408	75.94 374	72.79 407

tpm		84.73 290	84.02 285	86.87 330	90.33 343	68.90 380	89.06 347	89.94 362	80.85 286	85.75 219	89.86 324	68.54 279	95.97 311	77.76 284	84.05 293	95.75 188

ppachtmachnet_test		81.84 318	80.07 326	87.15 322	88.46 369	74.43 326	89.04 348	92.16 307	75.33 350	77.75 355	88.99 339	66.20 302	95.37 337	65.12 375	77.60 364	91.65 344

PM-MVS		78.11 353	76.12 357	84.09 361	83.54 397	70.08 376	88.97 349	85.27 393	79.93 295	74.73 376	86.43 372	34.70 409	93.48 365	79.43 268	72.06 381	88.72 386

MDA-MVSNet-bldmvs		78.85 350	76.31 355	86.46 334	89.76 354	73.88 330	88.79 350	90.42 351	79.16 306	59.18 405	88.33 351	60.20 346	94.04 355	62.00 385	68.96 389	91.48 350

tpmrst		85.35 276	84.99 265	86.43 336	90.88 328	67.88 384	88.71 351	91.43 331	80.13 293	86.08 213	88.80 344	73.05 217	96.02 309	82.48 211	83.40 304	95.40 200

PMMVS		85.71 269	84.96 267	87.95 298	88.90 364	77.09 290	88.68 352	90.06 359	72.32 380	86.47 200	90.76 299	72.15 227	94.40 349	81.78 231	93.49 169	92.36 331

EPMVS		83.90 303	82.70 307	87.51 308	90.23 346	72.67 346	88.62 353	81.96 402	81.37 277	85.01 249	88.34 350	66.31 300	94.45 347	75.30 309	87.12 271	95.43 199

PatchmatchNet		85.85 266	84.70 273	89.29 261	91.76 290	75.54 313	88.49 354	91.30 333	81.63 271	85.05 248	88.70 346	71.71 229	96.24 301	74.61 317	89.05 241	96.08 173
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
our_test_3		81.93 317	80.46 320	86.33 338	88.46 369	73.48 336	88.46 355	91.11 336	76.46 337	76.69 362	88.25 352	66.89 291	94.36 350	68.75 352	79.08 359	91.14 357

UnsupCasMVSNet_eth		80.07 340	78.27 346	85.46 347	85.24 392	72.63 349	88.45 356	94.87 224	82.99 235	71.64 389	88.07 355	56.34 365	91.75 383	73.48 325	63.36 399	92.01 339

tpmvs		83.35 309	82.07 308	87.20 321	91.07 317	71.00 369	88.31 357	91.70 320	78.91 308	80.49 329	87.18 368	69.30 267	97.08 247	68.12 359	83.56 300	93.51 291

MVStest1		72.91 364	69.70 369	82.54 368	78.14 409	73.05 340	88.21 358	86.21 385	60.69 403	64.70 398	90.53 305	46.44 397	85.70 406	58.78 395	53.62 408	88.87 385

N_pmnet		68.89 369	68.44 371	70.23 389	89.07 362	28.79 428	88.06 359	19.50 428	69.47 391	71.86 388	84.93 382	61.24 338	91.75 383	54.70 401	77.15 367	90.15 370

WB-MVS		67.92 370	67.49 372	69.21 392	81.09 403	41.17 422	88.03 360	78.00 412	73.50 369	62.63 401	83.11 392	63.94 316	86.52 403	25.66 418	51.45 410	79.94 403

test_post1							88.00 361				9.81 422	69.31 266	95.53 330	76.65 295

GG-mvs-BLEND				87.94 299	89.73 356	77.91 272	87.80 362	78.23 411		80.58 327	83.86 386	59.88 349	95.33 338	71.20 334	92.22 194	90.60 367

mvs5depth		80.98 332	79.15 340	86.45 335	84.57 394	73.29 338	87.79 363	91.67 322	80.52 289	82.20 308	89.72 327	55.14 373	95.93 313	73.93 322	66.83 393	90.12 371

DSMNet-mixed		76.94 357	76.29 356	78.89 378	83.10 399	56.11 414	87.78 364	79.77 406	60.65 404	75.64 370	88.71 345	61.56 333	88.34 400	60.07 391	89.29 237	92.21 336

SSC-MVS		67.06 371	66.56 373	68.56 394	80.54 404	40.06 424	87.77 365	77.37 415	72.38 379	61.75 403	82.66 394	63.37 319	86.45 404	24.48 419	48.69 413	79.16 405

MDTV_nov1_ep13			83.56 292		91.69 294	69.93 377	87.75 366	91.54 327	78.60 317	84.86 251	88.90 341	69.54 261	96.03 308	70.25 342	88.93 242

miper_lstm_enhance		85.27 279	84.59 276	87.31 314	91.28 308	74.63 322	87.69 367	94.09 258	81.20 283	81.36 318	89.85 325	74.97 186	94.30 352	81.03 243	79.84 353	93.01 311

new-patchmatchnet		76.41 359	75.17 361	80.13 375	82.65 401	59.61 406	87.66 368	91.08 337	78.23 325	69.85 393	83.22 389	54.76 374	91.63 385	64.14 380	64.89 397	89.16 382

MDTV_nov1_ep13_2view						55.91 415	87.62 369		73.32 371	84.59 257		70.33 250		74.65 316		95.50 197

mvsany_test1		85.42 274	85.30 260	85.77 344	87.95 377	75.41 315	87.61 370	80.97 404	76.82 336	88.68 157	95.83 109	77.44 156	90.82 390	85.90 166	86.51 275	91.08 361

tpm cat1		81.96 316	80.27 322	87.01 324	91.09 316	71.02 368	87.38 371	91.53 328	66.25 396	80.17 331	86.35 375	68.22 282	96.15 305	69.16 350	82.29 315	93.86 271

test_vis3_rt		65.12 373	62.60 375	72.69 386	71.44 415	60.71 404	87.17 372	65.55 419	63.80 401	53.22 409	65.65 412	14.54 423	89.44 397	76.65 295	65.38 395	67.91 410

PVSNet	78.82 18	85.55 270	84.65 274	88.23 292	94.72 172	71.93 354	87.12 373	92.75 292	78.80 313	84.95 250	90.53 305	64.43 313	96.71 268	74.74 315	93.86 161	96.06 176

dmvs_testset		74.57 362	75.81 360	70.86 388	87.72 379	40.47 423	87.05 374	77.90 413	82.75 240	71.15 391	85.47 381	67.98 283	84.12 410	45.26 407	76.98 370	88.00 391

pmmvs3		71.81 367	68.71 370	81.11 373	75.86 411	70.42 374	86.74 375	83.66 397	58.95 406	68.64 396	80.89 398	36.93 407	89.52 396	63.10 383	63.59 398	83.39 396

dp		81.47 326	80.23 323	85.17 352	89.92 352	65.49 392	86.74 375	90.10 358	76.30 341	81.10 320	87.12 369	62.81 323	95.92 314	68.13 358	79.88 351	94.09 258

MIMVSNet		82.59 313	80.53 318	88.76 274	91.51 297	78.32 263	86.57 377	90.13 357	79.32 302	80.70 325	88.69 347	52.98 382	93.07 372	66.03 371	88.86 243	94.90 221

gg-mvs-nofinetune		81.77 319	79.37 334	88.99 270	90.85 329	77.73 282	86.29 378	79.63 407	74.88 357	83.19 296	69.05 409	60.34 345	96.11 306	75.46 307	94.64 147	93.11 307

testmvs		8.92 391	11.52 394	1.12 407	1.06 429	0.46 432	86.02 379	0.65 430	0.62 423	2.74 424	9.52 423	0.31 430	0.45 426	2.38 424	0.39 423	2.46 422

YYNet1		79.22 348	77.20 350	85.28 350	88.20 374	72.66 347	85.87 380	90.05 361	74.33 361	62.70 400	87.61 361	66.09 304	92.03 379	66.94 365	72.97 378	91.15 356

MDA-MVSNet_test_wron		79.21 349	77.19 351	85.29 349	88.22 373	72.77 344	85.87 380	90.06 359	74.34 360	62.62 402	87.56 362	66.14 303	91.99 381	66.90 368	73.01 377	91.10 360

test123		8.76 392	11.22 395	1.39 406	0.85 430	0.97 431	85.76 382	0.35 431	0.54 424	2.45 425	8.14 424	0.60 429	0.48 425	2.16 425	0.17 424	2.71 421

UnsupCasMVSNet_bld		76.23 360	73.27 364	85.09 353	83.79 396	72.92 341	85.65 383	93.47 274	71.52 383	68.84 395	79.08 400	49.77 388	93.21 369	66.81 369	60.52 403	89.13 384

mvsany_test3		74.95 361	73.26 365	80.02 376	74.61 412	63.16 401	85.53 384	78.42 409	74.16 362	74.89 375	86.46 371	36.02 408	89.09 398	82.39 214	66.91 392	87.82 393

APD_test1		69.04 368	66.26 374	77.36 383	80.51 405	62.79 402	85.46 385	83.51 398	54.11 409	59.14 406	84.79 384	23.40 416	89.61 395	55.22 400	70.24 384	79.68 404

CR-MVSNet		85.35 276	83.76 289	90.12 227	90.58 338	79.34 241	85.24 386	91.96 316	78.27 323	85.55 224	87.87 359	71.03 237	95.61 328	73.96 321	89.36 235	95.40 200

RPMNet		83.95 301	81.53 312	91.21 180	90.58 338	79.34 241	85.24 386	96.76 78	71.44 384	85.55 224	82.97 393	70.87 240	98.91 83	61.01 388	89.36 235	95.40 200

test_f		71.95 366	70.87 367	75.21 384	74.21 414	59.37 407	85.07 388	85.82 388	65.25 398	70.42 392	83.13 390	23.62 414	82.93 412	78.32 278	71.94 382	83.33 397

KD-MVS_2432*1600		78.50 351	76.02 358	85.93 341	86.22 384	74.47 324	84.80 389	92.33 300	79.29 303	76.98 360	85.92 377	53.81 380	93.97 357	67.39 361	57.42 406	89.36 376

miper_refine_blended		78.50 351	76.02 358	85.93 341	86.22 384	74.47 324	84.80 389	92.33 300	79.29 303	76.98 360	85.92 377	53.81 380	93.97 357	67.39 361	57.42 406	89.36 376

Patchmtry		82.71 311	80.93 317	88.06 295	90.05 349	76.37 303	84.74 391	91.96 316	72.28 381	81.32 319	87.87 359	71.03 237	95.50 334	68.97 351	80.15 348	92.32 333

FPMVS		64.63 374	62.55 376	70.88 387	70.80 416	56.71 409	84.42 392	84.42 395	51.78 410	49.57 410	81.61 396	23.49 415	81.48 413	40.61 413	76.25 372	74.46 406

PatchT		82.68 312	81.27 314	86.89 329	90.09 348	70.94 370	84.06 393	90.15 356	74.91 355	85.63 223	83.57 388	69.37 263	94.87 346	65.19 373	88.50 248	94.84 223

new_pmnet		72.15 365	70.13 368	78.20 380	82.95 400	65.68 390	83.91 394	82.40 401	62.94 402	64.47 399	79.82 399	42.85 402	86.26 405	57.41 398	74.44 376	82.65 400

LCM-MVSNet		66.00 372	62.16 377	77.51 382	64.51 422	58.29 408	83.87 395	90.90 344	48.17 411	54.69 408	73.31 406	16.83 422	86.75 402	65.47 372	61.67 402	87.48 394

ADS-MVSNet2		81.66 322	79.71 331	87.50 309	91.35 305	74.19 328	83.33 396	88.48 375	72.90 375	82.24 306	85.77 379	64.98 310	93.20 370	64.57 378	83.74 296	95.12 209

ADS-MVSNet		81.56 324	79.78 328	86.90 328	91.35 305	71.82 356	83.33 396	89.16 373	72.90 375	82.24 306	85.77 379	64.98 310	93.76 361	64.57 378	83.74 296	95.12 209

PVSNet_0	73.20 20	77.22 356	74.83 362	84.37 357	90.70 335	71.10 366	83.09 398	89.67 368	72.81 377	73.93 380	83.13 390	60.79 343	93.70 363	68.54 353	50.84 411	88.30 390

MVS-HIRNet		73.70 363	72.20 366	78.18 381	91.81 289	56.42 413	82.94 399	82.58 400	55.24 407	68.88 394	66.48 410	55.32 371	95.13 340	58.12 396	88.42 250	83.01 398

dongtai		58.82 380	58.24 378	60.56 397	83.13 398	45.09 421	82.32 400	48.22 427	67.61 394	61.70 404	69.15 408	38.75 405	76.05 416	32.01 415	41.31 415	60.55 412

Patchmatch-RL test		81.67 321	79.96 327	86.81 331	85.42 391	71.23 364	82.17 401	87.50 382	78.47 318	77.19 359	82.50 395	70.81 241	93.48 365	82.66 210	72.89 379	95.71 192

JIA-IIPM		81.04 330	78.98 343	87.25 317	88.64 365	73.48 336	81.75 402	89.61 370	73.19 372	82.05 309	73.71 405	66.07 305	95.87 317	71.18 336	84.60 288	92.41 329

Patchmatch-test		81.37 327	79.30 335	87.58 307	90.92 325	74.16 329	80.99 403	87.68 381	70.52 388	76.63 363	88.81 342	71.21 234	92.76 374	60.01 392	86.93 274	95.83 185

ANet_high		58.88 379	54.22 384	72.86 385	56.50 425	56.67 410	80.75 404	86.00 387	73.09 374	37.39 417	64.63 413	22.17 417	79.49 415	43.51 409	23.96 419	82.43 401

testf1		59.54 377	56.11 381	69.85 390	69.28 417	56.61 411	80.37 405	76.55 416	42.58 414	45.68 413	75.61 401	11.26 424	84.18 408	43.20 410	60.44 404	68.75 408

APD_test2		59.54 377	56.11 381	69.85 390	69.28 417	56.61 411	80.37 405	76.55 416	42.58 414	45.68 413	75.61 401	11.26 424	84.18 408	43.20 410	60.44 404	68.75 408

kuosan		53.51 382	53.30 385	54.13 401	76.06 410	45.36 420	80.11 407	48.36 426	59.63 405	54.84 407	63.43 414	37.41 406	62.07 421	20.73 421	39.10 416	54.96 415

CHOSEN 280x420		85.15 281	83.99 286	88.65 279	92.47 265	78.40 261	79.68 408	92.76 291	74.90 356	81.41 317	89.59 329	69.85 257	95.51 332	79.92 261	95.29 133	92.03 338

ambc				83.06 365	79.99 406	63.51 400	77.47 409	92.86 287		74.34 379	84.45 385	28.74 410	95.06 343	73.06 327	68.89 390	90.61 365

EMVS		42.07 387	41.12 389	44.92 403	63.45 423	35.56 427	73.65 410	63.48 421	33.05 418	26.88 422	45.45 419	21.27 418	67.14 419	19.80 422	23.02 420	32.06 418

E-PMN		43.23 386	42.29 388	46.03 402	65.58 421	37.41 425	73.51 411	64.62 420	33.99 417	28.47 421	47.87 418	19.90 420	67.91 418	22.23 420	24.45 418	32.77 417

PMVS	47.18 22	52.22 383	48.46 387	63.48 396	45.72 427	46.20 419	73.41 412	78.31 410	41.03 416	30.06 419	65.68 411	6.05 426	83.43 411	30.04 416	65.86 394	60.80 411
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
PMMVS2		59.60 376	56.40 379	69.21 392	68.83 419	46.58 418	73.02 413	77.48 414	55.07 408	49.21 411	72.95 407	17.43 421	80.04 414	49.32 405	44.33 414	80.99 402

tmp_tt		35.64 388	39.24 390	24.84 404	14.87 428	23.90 429	62.71 414	51.51 425	6.58 422	36.66 418	62.08 415	44.37 400	30.34 424	52.40 403	22.00 421	20.27 419

MVE	39.65 23	43.39 385	38.59 391	57.77 398	56.52 424	48.77 417	55.38 415	58.64 423	29.33 419	28.96 420	52.65 416	4.68 427	64.62 420	28.11 417	33.07 417	59.93 413
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		57.99 381	54.91 383	67.24 395	88.51 366	65.59 391	52.21 416	90.33 354	43.58 413	42.84 416	51.18 417	20.29 419	85.07 407	34.77 414	70.45 383	51.05 416
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
wuyk23d		21.27 390	20.48 393	23.63 405	68.59 420	36.41 426	49.57 417	6.85 429	9.37 421	7.89 423	4.46 425	4.03 428	31.37 423	17.47 423	16.07 422	3.12 420

test_method		50.52 384	48.47 386	56.66 399	52.26 426	18.98 430	41.51 418	81.40 403	10.10 420	44.59 415	75.01 404	28.51 411	68.16 417	53.54 402	49.31 412	82.83 399

mmdepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

monomultidepth		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

test_blank		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet_test		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

DCPMVS		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

cdsmvs_eth3d_5k		22.14 389	29.52 392	0.00 408	0.00 431	0.00 433	0.00 419	95.76 162	0.00 426	0.00 427	94.29 172	75.66 178	0.00 427	0.00 426	0.00 425	0.00 423

pcd_1.5k_mvsjas		6.64 394	8.86 397	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	79.70 129	0.00 427	0.00 426	0.00 425	0.00 423

sosnet-low-res		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

sosnet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uncertanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

Regformer		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

ab-mvs-re		7.82 393	10.43 396	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	93.88 192	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

uanet		0.00 395	0.00 398	0.00 408	0.00 431	0.00 433	0.00 419	0.00 432	0.00 426	0.00 427	0.00 426	0.00 431	0.00 427	0.00 426	0.00 425	0.00 423

WAC-MVS						64.08 397								59.14 393

MSC_two_6792asdad				96.52 1	97.78 54	90.86 1		96.85 66					99.61 4	96.03 14	99.06 9	99.07 5

PC_three_1452									82.47 244	97.09 10	97.07 54	92.72 1	98.04 169	92.70 62	99.02 12	98.86 11

No_MVS				96.52 1	97.78 54	90.86 1		96.85 66					99.61 4	96.03 14	99.06 9	99.07 5

test_one_0601					98.58 11	85.83 61		97.44 15	91.05 14	96.78 15	98.06 14	91.45 11

eth-test2					0.00 431

eth-test					0.00 431

ZD-MVS					98.15 34	86.62 33		97.07 48	83.63 216	94.19 47	96.91 60	87.57 31	99.26 45	91.99 84	98.44 53

IU-MVS					98.77 5	86.00 50		96.84 68	81.26 280	97.26 7				95.50 23	99.13 3	99.03 8

test_241102_TWO								97.44 15	90.31 29	97.62 5	98.07 12	91.46 10	99.58 10	95.66 17	99.12 6	98.98 10

test_241102_ONE					98.77 5	85.99 52		97.44 15	90.26 34	97.71 1	97.96 20	92.31 4	99.38 31

test_0728_THIRD									90.75 19	97.04 11	98.05 16	92.09 6	99.55 16	95.64 19	99.13 3	99.13 2

GSMVS																96.12 170

test_part2					98.55 12	87.22 19				96.40 17

sam_mvs1												71.70 230				96.12 170

sam_mvs												70.60 243

MTGPA								96.97 53

test_post											10.29 421	70.57 247	95.91 316

patchmatchnet-post											83.76 387	71.53 231	96.48 286

gm-plane-assit					89.60 358	68.00 382			77.28 333		88.99 339		97.57 198	79.44 267

test9_res														91.91 88	98.71 32	98.07 73

agg_prior2														90.54 110	98.68 37	98.27 56

agg_prior					97.38 66	85.92 57		96.72 84		92.16 98			98.97 78

TestCases				89.52 255	95.01 154	77.79 279		90.89 345	77.41 330	76.12 366	93.34 205	54.08 378	97.51 203	68.31 356	84.27 291	93.26 297

test_prior				93.82 65	97.29 70	84.49 90		96.88 64					98.87 85			98.11 72

新几何1				93.10 88	97.30 69	84.35 99		95.56 178	71.09 386	91.26 122	96.24 88	82.87 90	98.86 87	79.19 271	98.10 67	96.07 174

旧先验1					96.79 79	81.81 171		95.67 170			96.81 66	86.69 39			97.66 84	96.97 134

原ACMM1				92.01 140	97.34 67	81.05 192		96.81 73	78.89 310	90.45 129	95.92 104	82.65 92	98.84 91	80.68 250	98.26 59	96.14 168

testdata2													98.75 97	78.30 279

segment_acmp												87.16 36

testdata				90.49 210	96.40 93	77.89 274		95.37 196	72.51 378	93.63 60	96.69 69	82.08 106	97.65 192	83.08 200	97.39 87	95.94 179

test12				94.34 52	97.13 73	86.15 48		96.29 113		91.04 124		85.08 61	99.01 66		98.13 66	97.86 88

plane_prior7					94.70 174	82.74 149

plane_prior6					94.52 185	82.75 147						74.23 196

plane_prior5								96.22 123					98.12 154	88.15 134	89.99 220	94.63 229

plane_prior4											94.86 149

plane_prior3						82.75 147			90.26 34	86.91 190

plane_prior1					94.59 179

n2								0.00 432

nn								0.00 432

door-mid								85.49 390

lessismore_v0				86.04 339	88.46 369	68.78 381		80.59 405		73.01 384	90.11 318	55.39 369	96.43 291	75.06 312	65.06 396	92.90 314

LGP-MVS_train				91.12 183	94.47 188	81.49 179		96.14 128	86.73 143	85.45 232	95.16 138	69.89 255	98.10 156	87.70 141	89.23 238	93.77 279

test11								96.57 95

door								85.33 392

HQP5-MVS						81.56 175

BP-MVS														87.11 152

HQP4-MVS										85.43 235			97.96 175			94.51 239

HQP3-MVS								96.04 140							89.77 229

HQP2-MVS												73.83 206

NP-MVS					94.37 195	82.42 159					93.98 185

ACMMP++_ref															87.47 265

ACMMP++															88.01 257

Test By Simon												80.02 124

ITE_SJBPF				88.24 291	91.88 285	77.05 291		92.92 285	85.54 172	80.13 334	93.30 209	57.29 362	96.20 302	72.46 329	84.71 287	91.49 349

DeepMVS_CX				56.31 400	74.23 413	51.81 416		56.67 424	44.85 412	48.54 412	75.16 403	27.87 412	58.74 422	40.92 412	52.22 409	58.39 414

High-resolution multi-view benchmark