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.

PVSNet_Blended		93.13 34	92.98 38	93.57 57	97.47 76	83.86 77	99.32 1	96.73 56	91.02 24	89.53 102	96.21 112	76.42 114	99.57 51	94.29 44	95.81 100	97.29 131

DELS-MVS		94.98 12	94.49 19	96.44 6	96.42 95	90.59 7	99.21 2	97.02 28	94.40 5	91.46 72	97.08 91	83.32 45	99.69 39	92.83 64	98.70 30	99.04 24
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
NCCC		95.63 6	95.94 8	94.69 26	99.21 6	85.15 57	99.16 3	96.96 32	94.11 6	95.59 24	98.64 17	85.07 33	99.91 4	95.61 31	99.10 9	99.00 26

DPM-MVS		96.21 2	95.53 11	98.26 1	96.26 98	95.09 1	99.15 4	96.98 30	93.39 9	96.45 18	98.79 8	90.17 10	99.99 1	89.33 107	99.25 6	99.70 3

lupinMVS		93.87 29	93.58 31	94.75 25	93.00 188	88.08 15	99.15 4	95.50 154	91.03 23	94.90 33	97.66 60	78.84 77	97.56 153	94.64 42	97.46 67	98.62 44

SED-MVS		95.88 5	96.22 4	94.87 21	99.03 15	85.03 59	99.12 6	96.78 44	88.72 51	97.79 4	98.91 2	88.48 17	99.82 18	98.15 4	98.97 17	99.74 1

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 6				98.54 18	92.06 3	99.84 12	99.11 1	99.37 1	99.74 1

test0726					99.05 9	85.18 52	99.11 8	96.78 44	88.75 49	97.65 9	98.91 2	87.69 22

DVP-MVS		95.58 8	95.91 9	94.57 28	99.05 9	85.18 52	99.06 9	96.46 91	88.75 49	96.69 13	98.76 12	87.69 22	99.76 25	97.90 9	98.85 21	98.77 33
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				95.14 16	99.04 14	86.14 33	99.06 9	96.77 50					99.84 12	97.90 9	98.85 21	99.45 10

CANet		94.89 13	94.64 17	95.63 11	97.55 75	88.12 14	99.06 9	96.39 101	94.07 7	95.34 26	97.80 55	76.83 108	99.87 8	97.08 18	97.64 63	98.89 29

CNVR-MVS		96.30 1	96.54 1	95.55 13	99.31 5	87.69 20	99.06 9	97.12 24	94.66 3	96.79 12	98.78 9	86.42 29	99.95 3	97.59 13	99.18 7	99.00 26

SteuartSystems-ACMMP		94.13 26	94.44 21	93.20 71	95.41 119	81.35 126	99.02 13	96.59 77	89.50 42	94.18 44	98.36 25	83.68 44	99.45 61	94.77 38	98.45 39	98.81 32
Skip Steuart: Steuart Systems R&D Blog.
DeepPCF-MVS	89.82 1	94.61 17	96.17 5	89.91 180	97.09 90	70.21 309	98.99 14	96.69 62	95.57 1	95.08 30	99.23 1	86.40 30	99.87 8	97.84 11	98.66 31	99.65 6

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 9	98.94 15	97.10 26	95.17 2	92.11 65	98.46 22	87.33 24	99.97 2	97.21 17	99.31 4	99.63 7

IB-MVS	85.34 4	88.67 126	87.14 146	93.26 68	93.12 186	84.32 71	98.76 16	97.27 18	87.19 88	79.36 213	90.45 220	83.92 42	98.53 114	84.41 146	69.79 290	96.93 141
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
CS-MVS-test		92.98 37	93.67 28	90.90 150	96.52 94	76.87 239	98.68 17	94.73 194	90.36 33	94.84 35	97.89 50	77.94 89	97.15 184	94.28 46	97.80 60	98.70 40

alignmvs		92.97 38	92.26 52	95.12 17	95.54 116	87.77 18	98.67 18	96.38 102	88.04 65	93.01 56	97.45 72	79.20 73	98.60 110	93.25 59	88.76 162	98.99 28

jason		92.73 43	92.23 53	94.21 38	90.50 249	87.30 24	98.65 19	95.09 175	90.61 27	92.76 59	97.13 88	75.28 140	97.30 173	93.32 57	96.75 88	98.02 77
jason: jason.
MSLP-MVS++		94.28 21	94.39 22	93.97 43	98.30 49	84.06 75	98.64 20	96.93 35	90.71 26	93.08 55	98.70 15	79.98 65	99.21 74	94.12 47	99.07 11	98.63 43

PHI-MVS		93.59 31	93.63 29	93.48 63	98.05 58	81.76 118	98.64 20	97.13 23	82.60 187	94.09 45	98.49 21	80.35 59	99.85 10	94.74 40	98.62 32	98.83 31

save fliter					98.24 51	83.34 89	98.61 22	96.57 79	91.32 19

CS-MVS		92.73 43	93.48 33	90.48 162	96.27 97	75.93 258	98.55 23	94.93 181	89.32 43	94.54 40	97.67 59	78.91 76	97.02 188	93.80 49	97.32 74	98.49 49

DP-MVS Recon		91.72 64	90.85 73	94.34 32	99.50 1	85.00 61	98.51 24	95.96 130	80.57 215	88.08 121	97.63 66	76.84 107	99.89 7	85.67 137	94.88 105	98.13 72

patch_mono-2		95.14 11	96.08 7	92.33 102	98.44 43	77.84 221	98.43 25	97.21 20	92.58 11	97.68 8	97.65 64	86.88 26	99.83 16	98.25 3	97.60 64	99.33 17

CP-MVS		92.54 52	92.60 46	92.34 101	98.50 40	79.90 158	98.40 26	96.40 99	84.75 130	90.48 90	98.09 37	77.40 99	99.21 74	91.15 79	98.23 50	97.92 88

test_prior2							98.37 27		86.08 104	94.57 39	98.02 43	83.14 46		95.05 36	98.79 26

EPNet		94.06 27	94.15 25	93.76 48	97.27 87	84.35 70	98.29 28	97.64 13	94.57 4	95.36 25	96.88 97	79.96 66	99.12 86	91.30 77	96.11 93	97.82 96
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Fast-Effi-MVS+		87.93 146	86.94 151	90.92 149	94.04 160	79.16 179	98.26 29	93.72 251	81.29 203	83.94 161	92.90 184	69.83 199	96.68 206	76.70 222	91.74 143	96.93 141

WTY-MVS		92.65 49	91.68 62	95.56 12	96.00 105	88.90 11	98.23 30	97.65 12	88.57 54	89.82 96	97.22 85	79.29 70	99.06 89	89.57 103	88.73 163	98.73 38

PS-MVSNAJ		94.17 24	93.52 32	96.10 8	95.65 113	92.35 2	98.21 31	95.79 140	92.42 13	96.24 19	98.18 30	71.04 190	99.17 81	96.77 20	97.39 72	96.79 147

xiu_mvs_v2_base		93.92 28	93.26 36	95.91 9	95.07 130	92.02 6	98.19 32	95.68 145	92.06 15	96.01 22	98.14 34	70.83 193	98.96 94	96.74 21	96.57 89	96.76 150

9.14			94.26 24		98.10 57		98.14 33	96.52 84	84.74 131	94.83 36	98.80 7	82.80 50	99.37 66	95.95 26	98.42 40

ET-MVSNet_ETH3D		90.01 100	89.03 105	92.95 80	94.38 150	86.77 28	98.14 33	96.31 108	89.30 44	63.33 329	96.72 106	90.09 11	93.63 310	90.70 87	82.29 218	98.46 51

CLD-MVS		87.97 145	87.48 137	89.44 188	92.16 216	80.54 144	98.14 33	94.92 182	91.41 18	79.43 212	95.40 133	62.34 238	97.27 176	90.60 88	82.90 212	90.50 232
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
DVP-MVS++		96.05 4	96.41 3	94.96 20	99.05 9	85.34 47	98.13 36	96.77 50	88.38 58	97.70 6	98.77 10	92.06 3	99.84 12	97.47 14	99.37 1	99.70 3

FOURS1					98.51 39	78.01 213	98.13 36	96.21 114	83.04 176	94.39 41

TSAR-MVS + GP.		94.35 20	94.50 18	93.89 45	97.38 84	83.04 94	98.10 38	95.29 169	91.57 17	93.81 46	97.45 72	86.64 27	99.43 62	96.28 22	94.01 115	99.20 22

test_yl		91.46 70	90.53 78	94.24 36	97.41 80	85.18 52	98.08 39	97.72 10	80.94 207	89.85 94	96.14 113	75.61 127	98.81 104	90.42 94	88.56 165	98.74 34

DCV-MVSNet		91.46 70	90.53 78	94.24 36	97.41 80	85.18 52	98.08 39	97.72 10	80.94 207	89.85 94	96.14 113	75.61 127	98.81 104	90.42 94	88.56 165	98.74 34

DROMVSNet		91.73 62	92.11 56	90.58 159	93.54 171	77.77 223	98.07 41	94.40 216	87.44 79	92.99 57	97.11 90	74.59 151	96.87 197	93.75 50	97.08 78	97.11 136

EIA-MVS		91.73 62	92.05 57	90.78 155	94.52 145	76.40 247	98.06 42	95.34 167	89.19 45	88.90 109	97.28 83	77.56 96	97.73 146	90.77 85	96.86 85	98.20 66

DeepC-MVS_fast	89.06 2	94.48 19	94.30 23	95.02 18	98.86 21	85.68 42	98.06 42	96.64 70	93.64 8	91.74 70	98.54 18	80.17 64	99.90 5	92.28 69	98.75 28	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
APDe-MVS		94.56 18	94.75 15	93.96 44	98.84 22	83.40 88	98.04 44	96.41 97	85.79 109	95.00 32	98.28 27	84.32 39	99.18 80	97.35 16	98.77 27	99.28 19

PVSNet_BlendedMVS		90.05 99	89.96 92	90.33 167	97.47 76	83.86 77	98.02 45	96.73 56	87.98 66	89.53 102	89.61 232	76.42 114	99.57 51	94.29 44	79.59 231	87.57 299

ETV-MVS		92.72 45	92.87 40	92.28 105	94.54 144	81.89 112	97.98 46	95.21 172	89.77 40	93.11 54	96.83 99	77.23 104	97.50 161	95.74 29	95.38 102	97.44 122

MG-MVS		94.25 23	93.72 27	95.85 10	99.38 3	89.35 10	97.98 46	98.09 8	89.99 36	92.34 61	96.97 94	81.30 55	98.99 92	88.54 113	98.88 20	99.20 22

thisisatest0515		90.95 83	90.26 84	93.01 78	94.03 162	84.27 73	97.91 48	96.67 64	83.18 171	86.87 132	95.51 131	88.66 16	97.85 142	80.46 183	89.01 159	96.92 143

VNet		92.11 57	91.22 68	94.79 23	96.91 91	86.98 25	97.91 48	97.96 9	86.38 99	93.65 48	95.74 121	70.16 198	98.95 96	93.39 54	88.87 161	98.43 53

test_fmvs1		87.79 148	88.52 115	85.62 265	92.98 192	64.31 332	97.88 50	92.42 285	87.95 67	92.24 62	95.82 120	47.94 314	98.44 122	95.31 35	94.09 112	94.09 203

thres200		88.92 118	87.65 129	92.73 88	96.30 96	85.62 43	97.85 51	98.86 1	84.38 143	84.82 149	93.99 171	75.12 143	98.01 134	70.86 271	86.67 178	94.56 197

3Dnovator+	82.88 8	89.63 105	87.85 125	94.99 19	94.49 149	86.76 29	97.84 52	95.74 142	86.10 103	75.47 261	96.02 116	65.00 225	99.51 57	82.91 170	97.07 79	98.72 39

TEST9					98.64 31	83.71 80	97.82 53	96.65 67	84.29 146	95.16 27	98.09 37	84.39 35	99.36 67

train_agg		94.28 21	94.45 20	93.74 49	98.64 31	83.71 80	97.82 53	96.65 67	84.50 139	95.16 27	98.09 37	84.33 36	99.36 67	95.91 27	98.96 19	98.16 69

test_8					98.63 33	83.64 83	97.81 55	96.63 72	84.50 139	95.10 29	98.11 36	84.33 36	99.23 72

HPM-MVS++		95.32 9	95.48 12	94.85 22	98.62 34	86.04 34	97.81 55	96.93 35	92.45 12	95.69 23	98.50 20	85.38 31	99.85 10	94.75 39	99.18 7	98.65 42

DPE-MVS		95.32 9	95.55 10	94.64 27	98.79 23	84.87 64	97.77 57	96.74 55	86.11 102	96.54 17	98.89 6	88.39 19	99.74 32	97.67 12	99.05 12	99.31 18
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
PVSNet_Blended_VisFu		91.24 76	90.77 75	92.66 90	95.09 128	82.40 104	97.77 57	95.87 137	88.26 61	86.39 134	93.94 172	76.77 109	99.27 70	88.80 112	94.00 116	96.31 164

SD-MVS		94.84 14	95.02 14	94.29 34	97.87 64	84.61 67	97.76 59	96.19 117	89.59 41	96.66 15	98.17 33	84.33 36	99.60 48	96.09 23	98.50 36	98.66 41
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_prior4						82.34 105	97.75 60

SF-MVS		94.17 24	94.05 26	94.55 29	97.56 74	85.95 35	97.73 61	96.43 95	84.02 151	95.07 31	98.74 14	82.93 48	99.38 64	95.42 34	98.51 34	98.32 58

3Dnovator	82.32 10	89.33 110	87.64 130	94.42 31	93.73 167	85.70 41	97.73 61	96.75 54	86.73 98	76.21 249	95.93 117	62.17 239	99.68 41	81.67 176	97.81 59	97.88 89

CPTT-MVS		89.72 103	89.87 96	89.29 190	98.33 47	73.30 280	97.70 63	95.35 166	75.68 284	87.40 125	97.44 75	70.43 195	98.25 128	89.56 104	96.90 81	96.33 163

PVSNet	82.34 9	89.02 115	87.79 127	92.71 89	95.49 117	81.50 124	97.70 63	97.29 17	87.76 72	85.47 142	95.12 144	56.90 279	98.90 100	80.33 184	94.02 114	97.71 104

iter_conf05		90.14 98	89.79 97	91.17 142	95.85 109	86.93 26	97.68 65	88.67 333	89.93 37	81.73 191	92.80 185	90.37 8	96.03 224	90.44 92	80.65 224	90.56 230

CDPH-MVS		93.12 35	92.91 39	93.74 49	98.65 30	83.88 76	97.67 66	96.26 110	83.00 178	93.22 53	98.24 28	81.31 54	99.21 74	89.12 108	98.74 29	98.14 71

ZNCC-MVS		92.75 41	92.60 46	93.23 70	98.24 51	81.82 116	97.63 67	96.50 87	85.00 127	91.05 81	97.74 57	78.38 83	99.80 24	90.48 89	98.34 46	98.07 75

HQP-NCC					92.08 218		97.63 67		90.52 28	82.30 178

ACMP_Plane					92.08 218		97.63 67		90.52 28	82.30 178

HQP-MVS		87.91 147	87.55 135	88.98 195	92.08 218	78.48 195	97.63 67	94.80 190	90.52 28	82.30 178	94.56 157	65.40 221	97.32 171	87.67 124	83.01 209	91.13 223

HFP-MVS		92.89 39	92.86 41	92.98 79	98.71 25	81.12 129	97.58 71	96.70 60	85.20 122	91.75 69	97.97 48	78.47 82	99.71 36	90.95 80	98.41 41	98.12 73

ACMMPR		92.69 47	92.67 44	92.75 86	98.66 28	80.57 141	97.58 71	96.69 62	85.20 122	91.57 71	97.92 49	77.01 105	99.67 43	90.95 80	98.41 41	98.00 82

MVS_111021_HR		93.41 33	93.39 35	93.47 65	97.34 85	82.83 96	97.56 73	98.27 6	89.16 46	89.71 97	97.14 87	79.77 67	99.56 53	93.65 52	97.94 56	98.02 77

VDD-MVS		88.28 138	87.02 149	92.06 113	95.09 128	80.18 154	97.55 74	94.45 214	83.09 174	89.10 107	95.92 119	47.97 313	98.49 116	93.08 63	86.91 177	97.52 118

GeoE		86.36 167	85.20 168	89.83 183	93.17 182	76.13 250	97.53 75	92.11 289	79.58 239	80.99 195	94.01 170	66.60 215	96.17 222	73.48 253	89.30 156	97.20 134

MTMP							97.53 75	68.16 371

region2R		92.72 45	92.70 43	92.79 85	98.68 26	80.53 145	97.53 75	96.51 85	85.22 120	91.94 67	97.98 46	77.26 100	99.67 43	90.83 84	98.37 44	98.18 67

plane_prior						77.96 215	97.52 78		90.36 33						82.96 211

API-MVS		90.18 97	88.97 107	93.80 47	98.66 28	82.95 95	97.50 79	95.63 148	75.16 288	86.31 135	97.69 58	72.49 173	99.90 5	81.26 178	96.07 94	98.56 46

SMA-MVS		94.70 16	94.68 16	94.76 24	98.02 59	85.94 37	97.47 80	96.77 50	85.32 117	97.92 3	98.70 15	83.09 47	99.84 12	95.79 28	99.08 10	98.49 49
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
CSCG		92.02 58	91.65 63	93.12 73	98.53 36	80.59 140	97.47 80	97.18 22	77.06 276	84.64 153	97.98 46	83.98 41	99.52 55	90.72 86	97.33 73	99.23 21

casdiffmvs_mvg		91.13 79	90.45 80	93.17 72	92.99 191	83.58 84	97.46 82	94.56 207	87.69 74	87.19 129	94.98 150	74.50 152	97.60 150	91.88 75	92.79 130	98.34 56
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Anonymous202405211		84.41 200	81.93 219	91.85 122	96.78 93	78.41 199	97.44 83	91.34 302	70.29 322	84.06 156	94.26 163	41.09 337	98.96 94	79.46 194	82.65 216	98.17 68

tfpn200view9		88.48 131	87.15 144	92.47 96	96.21 99	85.30 50	97.44 83	98.85 2	83.37 168	83.99 158	93.82 174	75.36 137	97.93 136	69.04 279	86.24 185	94.17 199

thres400		88.42 134	87.15 144	92.23 106	96.21 99	85.30 50	97.44 83	98.85 2	83.37 168	83.99 158	93.82 174	75.36 137	97.93 136	69.04 279	86.24 185	93.45 214

OpenMVS	79.58 14	86.09 172	83.62 196	93.50 61	90.95 240	86.71 30	97.44 83	95.83 138	75.35 285	72.64 283	95.72 122	57.42 276	99.64 45	71.41 264	95.85 99	94.13 202

MSP-MVS		95.62 7	96.54 1	92.86 83	98.31 48	80.10 155	97.42 87	96.78 44	92.20 14	97.11 11	98.29 26	93.46 1	99.10 87	96.01 24	99.30 5	99.38 14
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
BH-w/o		88.24 139	87.47 138	90.54 161	95.03 133	78.54 194	97.41 88	93.82 242	84.08 149	78.23 223	94.51 159	69.34 201	97.21 178	80.21 188	94.58 109	95.87 172

GST-MVS		92.43 54	92.22 54	93.04 77	98.17 54	81.64 122	97.40 89	96.38 102	84.71 133	90.90 84	97.40 77	77.55 97	99.76 25	89.75 101	97.74 61	97.72 102

XVS		92.69 47	92.71 42	92.63 92	98.52 37	80.29 148	97.37 90	96.44 93	87.04 90	91.38 73	97.83 54	77.24 102	99.59 49	90.46 90	98.07 52	98.02 77

X-MVStestdata		86.26 170	84.14 189	92.63 92	98.52 37	80.29 148	97.37 90	96.44 93	87.04 90	91.38 73	20.73 375	77.24 102	99.59 49	90.46 90	98.07 52	98.02 77

MP-MVS		92.61 50	92.67 44	92.42 99	98.13 56	79.73 165	97.33 92	96.20 115	85.63 111	90.53 88	97.66 60	78.14 87	99.70 38	92.12 71	98.30 48	97.85 93
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
mPP-MVS		91.88 60	91.82 59	92.07 112	98.38 44	78.63 193	97.29 93	96.09 122	85.12 124	88.45 115	97.66 60	75.53 130	99.68 41	89.83 99	98.02 55	97.88 89

iter_conf_final		89.51 106	89.21 103	90.39 164	95.60 114	84.44 69	97.22 94	89.09 326	89.11 47	82.07 185	92.80 185	87.03 25	96.03 224	89.10 109	80.89 221	90.70 228

EPP-MVSNet		89.76 102	89.72 98	89.87 181	93.78 164	76.02 255	97.22 94	96.51 85	79.35 242	85.11 144	95.01 148	84.82 34	97.10 186	87.46 126	88.21 169	96.50 156

APD-MVS		93.61 30	93.59 30	93.69 52	98.76 24	83.26 90	97.21 96	96.09 122	82.41 189	94.65 38	98.21 29	81.96 53	98.81 104	94.65 41	98.36 45	99.01 25
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
CNLPA		86.96 157	85.37 166	91.72 126	97.59 72	79.34 175	97.21 96	91.05 307	74.22 294	78.90 215	96.75 105	67.21 210	98.95 96	74.68 241	90.77 149	96.88 145

PAPR		92.74 42	92.17 55	94.45 30	98.89 20	84.87 64	97.20 98	96.20 115	87.73 73	88.40 116	98.12 35	78.71 80	99.76 25	87.99 120	96.28 91	98.74 34

QAPM		86.88 159	84.51 180	93.98 42	94.04 160	85.89 38	97.19 99	96.05 126	73.62 299	75.12 264	95.62 127	62.02 242	99.74 32	70.88 270	96.06 95	96.30 165

LFMVS		89.27 112	87.64 130	94.16 41	97.16 88	85.52 45	97.18 100	94.66 199	79.17 248	89.63 100	96.57 108	55.35 290	98.22 129	89.52 105	89.54 154	98.74 34

HQP_MVS		87.50 153	87.09 147	88.74 200	91.86 227	77.96 215	97.18 100	94.69 195	89.89 38	81.33 192	94.15 167	64.77 227	97.30 173	87.08 128	82.82 213	90.96 225

plane_prior2							97.18 100		89.89 38

MAR-MVS		90.63 88	90.22 85	91.86 120	98.47 42	78.20 209	97.18 100	96.61 73	83.87 158	88.18 120	98.18 30	68.71 202	99.75 30	83.66 160	97.15 77	97.63 110
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
PLC	83.97 7	88.00 144	87.38 140	89.83 183	98.02 59	76.46 245	97.16 104	94.43 215	79.26 247	81.98 186	96.28 111	69.36 200	99.27 70	77.71 210	92.25 138	93.77 209
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HPM-MVS_fast		90.38 95	90.17 88	91.03 146	97.61 70	77.35 232	97.15 105	95.48 155	79.51 240	88.79 110	96.90 95	71.64 184	98.81 104	87.01 131	97.44 69	96.94 140

thres100view900		88.30 137	86.95 150	92.33 102	96.10 103	84.90 63	97.14 106	98.85 2	82.69 185	83.41 166	93.66 177	75.43 134	97.93 136	69.04 279	86.24 185	94.17 199

thres600view7		88.06 142	86.70 154	92.15 110	96.10 103	85.17 56	97.14 106	98.85 2	82.70 184	83.41 166	93.66 177	75.43 134	97.82 143	67.13 289	85.88 189	93.45 214

sss		90.87 85	89.96 92	93.60 56	94.15 156	83.84 79	97.14 106	98.13 7	85.93 107	89.68 98	96.09 115	71.67 182	99.30 69	87.69 123	89.16 157	97.66 107

test-LLR		88.48 131	87.98 123	89.98 176	92.26 209	77.23 234	97.11 109	95.96 130	83.76 162	86.30 136	91.38 203	72.30 176	96.78 203	80.82 180	91.92 141	95.94 170

TESTMET0.1,1		89.83 101	89.34 102	91.31 136	92.54 202	80.19 153	97.11 109	96.57 79	86.15 101	86.85 133	91.83 199	79.32 69	96.95 191	81.30 177	92.35 137	96.77 149

test-mter		88.95 116	88.60 113	89.98 176	92.26 209	77.23 234	97.11 109	95.96 130	85.32 117	86.30 136	91.38 203	76.37 116	96.78 203	80.82 180	91.92 141	95.94 170

VDDNet		86.44 166	84.51 180	92.22 107	91.56 230	81.83 115	97.10 112	94.64 202	69.50 326	87.84 122	95.19 139	48.01 312	97.92 141	89.82 100	86.92 176	96.89 144

canonicalmvs		92.27 55	91.22 68	95.41 14	95.80 110	88.31 12	97.09 113	94.64 202	88.49 56	92.99 57	97.31 79	72.68 171	98.57 112	93.38 56	88.58 164	99.36 16

CDS-MVSNet		89.50 107	88.96 108	91.14 144	91.94 226	80.93 133	97.09 113	95.81 139	84.26 147	84.72 151	94.20 166	80.31 60	95.64 252	83.37 165	88.96 160	96.85 146
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
nrg030		86.79 162	85.43 164	90.87 152	88.76 273	85.34 47	97.06 115	94.33 218	84.31 144	80.45 202	91.98 194	72.36 174	96.36 215	88.48 116	71.13 277	90.93 227

cascas		86.50 165	84.48 182	92.55 95	92.64 200	85.95 35	97.04 116	95.07 177	75.32 286	80.50 200	91.02 210	54.33 297	97.98 135	86.79 133	87.62 172	93.71 210

xiu_mvs_v1_base_debu		90.54 90	89.54 99	93.55 58	92.31 204	87.58 21	96.99 117	94.87 185	87.23 85	93.27 50	97.56 68	57.43 273	98.32 125	92.72 65	93.46 124	94.74 192

xiu_mvs_v1_base		90.54 90	89.54 99	93.55 58	92.31 204	87.58 21	96.99 117	94.87 185	87.23 85	93.27 50	97.56 68	57.43 273	98.32 125	92.72 65	93.46 124	94.74 192

xiu_mvs_v1_base_debi		90.54 90	89.54 99	93.55 58	92.31 204	87.58 21	96.99 117	94.87 185	87.23 85	93.27 50	97.56 68	57.43 273	98.32 125	92.72 65	93.46 124	94.74 192

HPM-MVS		91.62 67	91.53 65	91.89 119	97.88 63	79.22 177	96.99 117	95.73 143	82.07 195	89.50 104	97.19 86	75.59 129	98.93 99	90.91 82	97.94 56	97.54 114
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
114514_t		88.79 124	87.57 134	92.45 97	98.21 53	81.74 119	96.99 117	95.45 158	75.16 288	82.48 175	95.69 124	68.59 203	98.50 115	80.33 184	95.18 103	97.10 137

旧先验2							96.97 122		74.06 297	96.10 20			97.76 145	88.38 117

h-mvs33		89.30 111	88.95 109	90.36 166	95.07 130	76.04 252	96.96 123	97.11 25	90.39 31	92.22 63	95.10 145	74.70 147	98.86 101	93.14 60	65.89 322	96.16 166

BH-RMVSNet		86.84 160	85.28 167	91.49 133	95.35 121	80.26 151	96.95 124	92.21 288	82.86 182	81.77 190	95.46 132	59.34 259	97.64 148	69.79 277	93.81 119	96.57 155

Vis-MVSNet		88.67 126	87.82 126	91.24 140	92.68 196	78.82 187	96.95 124	93.85 241	87.55 77	87.07 131	95.13 143	63.43 233	97.21 178	77.58 212	96.15 92	97.70 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
Vis-MVSNet (Re-imp)		88.88 120	88.87 111	88.91 196	93.89 163	74.43 272	96.93 126	94.19 224	84.39 142	83.22 169	95.67 125	78.24 85	94.70 289	78.88 201	94.40 111	97.61 112

test_fmvs1_n		86.34 168	86.72 153	85.17 272	87.54 290	63.64 337	96.91 127	92.37 287	87.49 78	91.33 76	95.58 129	40.81 339	98.46 119	95.00 37	93.49 122	93.41 216

GA-MVS		85.79 178	84.04 190	91.02 147	89.47 268	80.27 150	96.90 128	94.84 188	85.57 112	80.88 196	89.08 235	56.56 283	96.47 212	77.72 209	85.35 195	96.34 161

无先验							96.87 129	96.78 44	77.39 269				99.52 55	79.95 190		98.43 53

原ACMM2							96.84 130

test_vis1_n		85.60 181	85.70 161	85.33 269	84.79 322	64.98 330	96.83 131	91.61 298	87.36 82	91.00 83	94.84 152	36.14 345	97.18 180	95.66 30	93.03 128	93.82 208

casdiffmvs		90.95 83	90.39 81	92.63 92	92.82 195	82.53 100	96.83 131	94.47 212	87.69 74	88.47 114	95.56 130	74.04 157	97.54 157	90.90 83	92.74 131	97.83 95
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMMP_NAP		93.46 32	93.23 37	94.17 39	97.16 88	84.28 72	96.82 133	96.65 67	86.24 100	94.27 42	97.99 44	77.94 89	99.83 16	93.39 54	98.57 33	98.39 55

Anonymous20240529		83.15 219	80.60 238	90.80 153	95.74 111	78.27 203	96.81 134	94.92 182	60.10 353	81.89 188	92.54 189	45.82 321	98.82 103	79.25 197	78.32 247	95.31 184

MVSTER		89.25 113	88.92 110	90.24 169	95.98 106	84.66 66	96.79 135	95.36 164	87.19 88	80.33 204	90.61 218	90.02 12	95.97 229	85.38 140	78.64 240	90.09 242

BH-untuned		86.95 158	85.94 159	89.99 175	94.52 145	77.46 229	96.78 136	93.37 267	81.80 198	76.62 239	93.81 176	66.64 214	97.02 188	76.06 229	93.88 118	95.48 180

ACMMP		90.39 93	89.97 91	91.64 128	97.58 73	78.21 208	96.78 136	96.72 58	84.73 132	84.72 151	97.23 84	71.22 187	99.63 46	88.37 118	92.41 136	97.08 138
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
IS-MVSNet		88.67 126	88.16 121	90.20 171	93.61 168	76.86 240	96.77 138	93.07 277	84.02 151	83.62 165	95.60 128	74.69 150	96.24 220	78.43 205	93.66 121	97.49 120

UniMVSNet (Re)		85.31 186	84.23 186	88.55 203	89.75 261	80.55 142	96.72 139	96.89 37	85.42 115	78.40 221	88.93 238	75.38 136	95.52 259	78.58 203	68.02 307	89.57 250

EPNet_dtu		87.65 151	87.89 124	86.93 242	94.57 142	71.37 303	96.72 139	96.50 87	88.56 55	87.12 130	95.02 147	75.91 124	94.01 303	66.62 291	90.00 151	95.42 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
VPNet		84.69 195	82.92 205	90.01 174	89.01 272	83.45 87	96.71 141	95.46 157	85.71 110	79.65 211	92.18 192	56.66 282	96.01 228	83.05 169	67.84 310	90.56 230

UniMVSNet_NR-MVSNet		85.49 183	84.59 178	88.21 213	89.44 269	79.36 173	96.71 141	96.41 97	85.22 120	78.11 224	90.98 212	76.97 106	95.14 276	79.14 198	68.30 304	90.12 239

AdaColmap		88.81 122	87.61 133	92.39 100	99.33 4	79.95 156	96.70 143	95.58 149	77.51 268	83.05 172	96.69 107	61.90 245	99.72 35	84.29 147	93.47 123	97.50 119

SR-MVS		92.16 56	92.27 51	91.83 123	98.37 45	78.41 199	96.67 144	95.76 141	82.19 193	91.97 66	98.07 41	76.44 113	98.64 108	93.71 51	97.27 75	98.45 52

EI-MVSNet-Vis-set		91.84 61	91.77 61	92.04 114	97.60 71	81.17 128	96.61 145	96.87 38	88.20 62	89.19 105	97.55 71	78.69 81	99.14 83	90.29 96	90.94 148	95.80 173

WR-MVS		84.32 201	82.96 204	88.41 205	89.38 270	80.32 147	96.59 146	96.25 111	83.97 153	76.63 238	90.36 222	67.53 206	94.86 286	75.82 233	70.09 288	90.06 244

test1111		88.11 141	87.04 148	91.35 135	93.15 183	78.79 190	96.57 147	90.78 312	86.88 94	85.04 145	95.20 138	57.23 278	97.39 168	83.88 152	94.59 108	97.87 91

TR-MVS		86.30 169	84.93 176	90.42 163	94.63 141	77.58 227	96.57 147	93.82 242	80.30 224	82.42 177	95.16 141	58.74 263	97.55 155	74.88 239	87.82 171	96.13 168

ECVR-MVS		88.35 136	87.25 142	91.65 127	93.54 171	79.40 172	96.56 149	90.78 312	86.78 96	85.57 141	95.25 134	57.25 277	97.56 153	84.73 145	94.80 106	97.98 84

thisisatest0530		89.65 104	89.02 106	91.53 132	93.46 177	80.78 136	96.52 150	96.67 64	81.69 200	83.79 163	94.90 151	88.85 15	97.68 147	77.80 206	87.49 175	96.14 167

test0.0.03 1		82.79 226	82.48 212	83.74 293	86.81 295	72.22 288	96.52 150	95.03 178	83.76 162	73.00 279	93.20 180	72.30 176	88.88 347	64.15 304	77.52 250	90.12 239

Baseline_NR-MVSNet		81.22 249	80.07 246	84.68 278	85.32 318	75.12 265	96.48 152	88.80 329	76.24 282	77.28 230	86.40 281	67.61 204	94.39 297	75.73 234	66.73 320	84.54 331

EI-MVSNet-UG-set		91.35 74	91.22 68	91.73 125	97.39 82	80.68 138	96.47 153	96.83 41	87.92 68	88.30 119	97.36 78	77.84 92	99.13 85	89.43 106	89.45 155	95.37 182

1112_ss		88.60 129	87.47 138	92.00 116	93.21 180	80.97 132	96.47 153	92.46 284	83.64 165	80.86 197	97.30 81	80.24 62	97.62 149	77.60 211	85.49 193	97.40 125

TAMVS		88.48 131	87.79 127	90.56 160	91.09 238	79.18 178	96.45 155	95.88 135	83.64 165	83.12 170	93.33 179	75.94 123	95.74 247	82.40 171	88.27 168	96.75 151

MP-MVS-pluss		92.58 51	92.35 49	93.29 67	97.30 86	82.53 100	96.44 156	96.04 127	84.68 134	89.12 106	98.37 24	77.48 98	99.74 32	93.31 58	98.38 43	97.59 113
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
Test_1112_low_res		88.03 143	86.73 152	91.94 118	93.15 183	80.88 134	96.44 156	92.41 286	83.59 167	80.74 199	91.16 208	80.18 63	97.59 151	77.48 214	85.40 194	97.36 127

DU-MVS		84.57 197	83.33 201	88.28 209	88.76 273	79.36 173	96.43 158	95.41 163	85.42 115	78.11 224	90.82 214	67.61 204	95.14 276	79.14 198	68.30 304	90.33 235

新几何2							96.42 159

PAPM		92.87 40	92.40 48	94.30 33	92.25 211	87.85 17	96.40 160	96.38 102	91.07 22	88.72 112	96.90 95	82.11 52	97.37 170	90.05 98	97.70 62	97.67 106

test2506		90.96 82	90.39 81	92.65 91	93.54 171	82.46 103	96.37 161	97.35 16	86.78 96	87.55 124	95.25 134	77.83 93	97.50 161	84.07 149	94.80 106	97.98 84

VPA-MVSNet		85.32 185	83.83 191	89.77 186	90.25 252	82.63 98	96.36 162	97.07 27	83.03 177	81.21 194	89.02 237	61.58 246	96.31 217	85.02 143	70.95 279	90.36 233

UGNet		87.73 149	86.55 155	91.27 139	95.16 127	79.11 181	96.35 163	96.23 112	88.14 63	87.83 123	90.48 219	50.65 303	99.09 88	80.13 189	94.03 113	95.60 177
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
v2v482		83.46 213	81.86 220	88.25 211	86.19 303	79.65 167	96.34 164	94.02 233	81.56 201	77.32 229	88.23 249	65.62 218	96.03 224	77.77 207	69.72 292	89.09 263

CANet_DTU		90.98 81	90.04 90	93.83 46	94.76 139	86.23 32	96.32 165	93.12 276	93.11 10	93.71 47	96.82 101	63.08 235	99.48 59	84.29 147	95.12 104	95.77 174

APD-MVS_3200maxsize		91.23 77	91.35 67	90.89 151	97.89 62	76.35 248	96.30 166	95.52 153	79.82 234	91.03 82	97.88 51	74.70 147	98.54 113	92.11 72	96.89 82	97.77 99

v148		82.41 234	80.89 231	86.99 241	86.18 304	76.81 241	96.27 167	93.82 242	80.49 218	75.28 263	86.11 286	67.32 209	95.75 244	75.48 235	67.03 318	88.42 282

CHOSEN 1792x2688		91.07 80	90.21 86	93.64 53	95.18 126	83.53 85	96.26 168	96.13 119	88.92 48	84.90 148	93.10 183	72.86 169	99.62 47	88.86 110	95.67 101	97.79 98

diffmvs		91.17 78	90.74 76	92.44 98	93.11 187	82.50 102	96.25 169	93.62 255	87.79 71	90.40 91	95.93 117	73.44 165	97.42 165	93.62 53	92.55 133	97.41 124
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
pmmvs5		81.34 247	79.54 252	86.73 246	85.02 320	76.91 238	96.22 170	91.65 296	77.65 266	73.55 272	88.61 242	55.70 288	94.43 296	74.12 248	73.35 269	88.86 275

mvsmamba		85.17 188	84.54 179	87.05 240	87.94 284	75.11 266	96.22 170	87.79 337	86.91 92	78.55 219	91.77 200	64.93 226	95.91 235	86.94 132	79.80 227	90.12 239

PMMVS		89.46 108	89.92 94	88.06 215	94.64 140	69.57 316	96.22 170	94.95 180	87.27 84	91.37 75	96.54 109	65.88 217	97.39 168	88.54 113	93.89 117	97.23 132

SR-MVS-dyc-post		91.29 75	91.45 66	90.80 153	97.76 67	76.03 253	96.20 173	95.44 159	80.56 216	90.72 86	97.84 52	75.76 126	98.61 109	91.99 73	96.79 86	97.75 100

RE-MVS-def			91.18 71		97.76 67	76.03 253	96.20 173	95.44 159	80.56 216	90.72 86	97.84 52	73.36 166		91.99 73	96.79 86	97.75 100

MVS_111021_LR		91.60 68	91.64 64	91.47 134	95.74 111	78.79 190	96.15 175	96.77 50	88.49 56	88.64 113	97.07 92	72.33 175	99.19 79	93.13 62	96.48 90	96.43 158

FIs		86.73 164	86.10 158	88.61 202	90.05 257	80.21 152	96.14 176	96.95 33	85.56 114	78.37 222	92.30 190	76.73 110	95.28 269	79.51 193	79.27 234	90.35 234

v1144		82.90 225	81.27 229	87.78 220	86.29 301	79.07 184	96.14 176	93.93 235	80.05 230	77.38 227	86.80 271	65.50 219	95.93 234	75.21 237	70.13 285	88.33 284

TranMVSNet+NR-MVSNet		83.24 218	81.71 222	87.83 218	87.71 287	78.81 189	96.13 178	94.82 189	84.52 138	76.18 250	90.78 216	64.07 230	94.60 291	74.60 244	66.59 321	90.09 242

Fast-Effi-MVS+-dtu		83.33 215	82.60 211	85.50 267	89.55 266	69.38 317	96.09 179	91.38 299	82.30 190	75.96 253	91.41 202	56.71 280	95.58 257	75.13 238	84.90 198	91.54 221

miper_enhance_ethall		85.95 175	85.20 168	88.19 214	94.85 137	79.76 161	96.00 180	94.06 232	82.98 179	77.74 226	88.76 240	79.42 68	95.46 261	80.58 182	72.42 272	89.36 256

v144192		82.43 231	80.73 235	87.54 228	85.81 310	78.22 205	95.98 181	93.78 247	79.09 250	77.11 232	86.49 276	64.66 229	95.91 235	74.20 247	69.42 293	88.49 278

PVSNet_0	77.72 15	81.70 242	78.95 258	89.94 179	90.77 246	76.72 243	95.96 182	96.95 33	85.01 126	70.24 299	88.53 245	52.32 300	98.20 130	86.68 134	44.08 363	94.89 188

F-COLMAP		84.50 199	83.44 200	87.67 221	95.22 124	72.22 288	95.95 183	93.78 247	75.74 283	76.30 246	95.18 140	59.50 257	98.45 120	72.67 257	86.59 180	92.35 220

DeepC-MVS	86.58 3	91.53 69	91.06 72	92.94 81	94.52 145	81.89 112	95.95 183	95.98 129	90.76 25	83.76 164	96.76 103	73.24 167	99.71 36	91.67 76	96.96 80	97.22 133
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
FMVSNet3		84.71 194	82.71 209	90.70 157	94.55 143	87.71 19	95.92 185	94.67 198	81.73 199	75.82 256	88.08 252	66.99 211	94.47 295	71.23 266	75.38 258	89.91 246

TAPA-MVS	81.61 12	85.02 190	83.67 193	89.06 192	96.79 92	73.27 282	95.92 185	94.79 192	74.81 291	80.47 201	96.83 99	71.07 189	98.19 131	49.82 352	92.57 132	95.71 175
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
ACMP	81.66 11	84.00 204	83.22 203	86.33 249	91.53 233	72.95 286	95.91 187	93.79 246	83.70 164	73.79 271	92.22 191	54.31 298	96.89 195	83.98 150	79.74 230	89.16 260
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMM	80.70 13	83.72 210	82.85 207	86.31 252	91.19 236	72.12 291	95.88 188	94.29 220	80.44 219	77.02 233	91.96 195	55.24 291	97.14 185	79.30 196	80.38 225	89.67 249
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test222					96.15 101	78.41 199	95.87 189	96.46 91	71.97 314	89.66 99	97.45 72	76.33 117			98.24 49	98.30 61

V42		83.04 222	81.53 225	87.57 227	86.27 302	79.09 183	95.87 189	94.11 229	80.35 223	77.22 231	86.79 272	65.32 223	96.02 227	77.74 208	70.14 284	87.61 298

TSAR-MVS + MP.		94.79 15	95.17 13	93.64 53	97.66 69	84.10 74	95.85 191	96.42 96	91.26 20	97.49 10	96.80 102	86.50 28	98.49 116	95.54 32	99.03 13	98.33 57
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
v1192		82.31 235	80.55 239	87.60 224	85.94 307	78.47 198	95.85 191	93.80 245	79.33 243	76.97 234	86.51 275	63.33 234	95.87 237	73.11 254	70.13 285	88.46 280

v1921920		82.02 239	80.23 243	87.41 231	85.62 312	77.92 218	95.79 193	93.69 252	78.86 254	76.67 237	86.44 278	62.50 237	95.83 239	72.69 256	69.77 291	88.47 279

OPM-MVS		85.84 176	85.10 173	88.06 215	88.34 279	77.83 222	95.72 194	94.20 223	87.89 70	80.45 202	94.05 169	58.57 264	97.26 177	83.88 152	82.76 215	89.09 263
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
XXY-MVS		83.84 207	82.00 218	89.35 189	87.13 293	81.38 125	95.72 194	94.26 221	80.15 228	75.92 254	90.63 217	61.96 244	96.52 210	78.98 200	73.28 270	90.14 238

tttt0517		88.57 130	88.19 120	89.71 187	93.00 188	75.99 256	95.67 196	96.67 64	80.78 210	81.82 189	94.40 160	88.97 14	97.58 152	76.05 230	86.31 182	95.57 178

IterMVS-LS		83.93 205	82.80 208	87.31 234	91.46 234	77.39 231	95.66 197	93.43 262	80.44 219	75.51 260	87.26 263	73.72 161	95.16 275	76.99 218	70.72 281	89.39 251
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
FC-MVSNet-test		85.96 174	85.39 165	87.66 222	89.38 270	78.02 212	95.65 198	96.87 38	85.12 124	77.34 228	91.94 197	76.28 118	94.74 288	77.09 217	78.82 238	90.21 237

test_vis1_rt		73.96 299	72.40 301	78.64 324	83.91 332	61.16 346	95.63 199	68.18 370	76.32 279	60.09 343	74.77 346	29.01 359	97.54 157	87.74 122	75.94 254	77.22 356

HyFIR lowres test		89.36 109	88.60 113	91.63 130	94.91 136	80.76 137	95.60 200	95.53 151	82.56 188	84.03 157	91.24 207	78.03 88	96.81 201	87.07 130	88.41 167	97.32 128

testdata1							95.57 201		87.44 79

cl22		85.11 189	84.17 187	87.92 217	95.06 132	78.82 187	95.51 202	94.22 222	79.74 236	76.77 236	87.92 254	75.96 122	95.68 248	79.93 191	72.42 272	89.27 257

v1240		81.70 242	79.83 251	87.30 235	85.50 313	77.70 226	95.48 203	93.44 261	78.46 259	76.53 240	86.44 278	60.85 249	95.84 238	71.59 263	70.17 283	88.35 283

baseline1		88.85 121	87.49 136	92.93 82	95.21 125	86.85 27	95.47 204	94.61 204	87.29 83	83.11 171	94.99 149	80.70 57	96.89 195	82.28 172	73.72 265	95.05 187

AUN-MVS		86.25 171	85.57 162	88.26 210	93.57 170	73.38 278	95.45 205	95.88 135	83.94 155	85.47 142	94.21 165	73.70 163	96.67 207	83.54 162	64.41 326	94.73 195

FMVSNet2		82.79 226	80.44 240	89.83 183	92.66 197	85.43 46	95.42 206	94.35 217	79.06 251	74.46 268	87.28 261	56.38 285	94.31 298	69.72 278	74.68 262	89.76 248

hse-mvs2		88.22 140	88.21 119	88.25 211	93.54 171	73.41 277	95.41 207	95.89 134	90.39 31	92.22 63	94.22 164	74.70 147	96.66 208	93.14 60	64.37 327	94.69 196

miper_ehance_all_eth		84.57 197	83.60 197	87.50 229	92.64 200	78.25 204	95.40 208	93.47 260	79.28 246	76.41 243	87.64 257	76.53 112	95.24 271	78.58 203	72.42 272	89.01 268

RRT_MVS		83.88 206	83.27 202	85.71 261	87.53 291	72.12 291	95.35 209	94.33 218	83.81 160	75.86 255	91.28 206	60.55 250	95.09 281	83.93 151	76.76 252	89.90 247

PGM-MVS		91.93 59	91.80 60	92.32 104	98.27 50	79.74 164	95.28 210	97.27 18	83.83 159	90.89 85	97.78 56	76.12 120	99.56 53	88.82 111	97.93 58	97.66 107

TransMVSNet (Re)		76.94 286	74.38 290	84.62 281	85.92 308	75.25 264	95.28 210	89.18 325	73.88 298	67.22 308	86.46 277	59.64 254	94.10 301	59.24 324	52.57 352	84.50 332

LPG-MVS_test		84.20 203	83.49 199	86.33 249	90.88 241	73.06 283	95.28 210	94.13 227	82.20 191	76.31 244	93.20 180	54.83 295	96.95 191	83.72 157	80.83 222	88.98 269

mvsany_test1		87.58 152	88.22 118	85.67 263	89.78 260	67.18 325	95.25 213	87.93 335	83.96 154	88.79 110	97.06 93	72.52 172	94.53 294	92.21 70	86.45 181	95.30 185

c3_l		83.80 208	82.65 210	87.25 236	92.10 217	77.74 225	95.25 213	93.04 278	78.58 257	76.01 251	87.21 265	75.25 141	95.11 278	77.54 213	68.89 298	88.91 274

D2MVS		82.67 228	81.55 224	86.04 257	87.77 286	76.47 244	95.21 215	96.58 78	82.66 186	70.26 298	85.46 294	60.39 251	95.80 241	76.40 226	79.18 235	85.83 324

test_fmvs2		79.59 263	79.90 250	78.67 323	82.86 336	55.82 356	95.20 216	89.55 320	81.09 205	80.12 208	89.80 229	34.31 350	93.51 312	87.82 121	78.36 246	86.69 311

Effi-MVS+		90.70 87	89.90 95	93.09 75	93.61 168	83.48 86	95.20 216	92.79 281	83.22 170	91.82 68	95.70 123	71.82 181	97.48 163	91.25 78	93.67 120	98.32 58

baseline2		90.39 93	90.21 86	90.93 148	90.86 243	80.99 131	95.20 216	97.41 15	86.03 105	80.07 209	94.61 156	90.58 6	97.47 164	87.29 127	89.86 153	94.35 198

Anonymous20231211		79.72 262	77.19 269	87.33 232	95.59 115	77.16 237	95.18 219	94.18 225	59.31 355	72.57 284	86.20 284	47.89 315	95.66 249	74.53 245	69.24 296	89.18 259

EI-MVSNet		85.80 177	85.20 168	87.59 225	91.55 231	77.41 230	95.13 220	95.36 164	80.43 221	80.33 204	94.71 154	73.72 161	95.97 229	76.96 220	78.64 240	89.39 251

CVMVSNet		84.83 193	85.57 162	82.63 305	91.55 231	60.38 347	95.13 220	95.03 178	80.60 214	82.10 184	94.71 154	66.40 216	90.19 344	74.30 246	90.32 150	97.31 129

cl____		83.27 216	82.12 215	86.74 243	92.20 212	75.95 257	95.11 222	93.27 270	78.44 260	74.82 266	87.02 268	74.19 155	95.19 273	74.67 242	69.32 294	89.09 263

DIV-MVS_self_test		83.27 216	82.12 215	86.74 243	92.19 213	75.92 259	95.11 222	93.26 271	78.44 260	74.81 267	87.08 267	74.19 155	95.19 273	74.66 243	69.30 295	89.11 262

pm-mvs1		80.05 259	78.02 263	86.15 255	85.42 314	75.81 260	95.11 222	92.69 283	77.13 273	70.36 297	87.43 259	58.44 266	95.27 270	71.36 265	64.25 328	87.36 304

DP-MVS		81.47 245	78.28 261	91.04 145	98.14 55	78.48 195	95.09 225	86.97 339	61.14 349	71.12 292	92.78 188	59.59 255	99.38 64	53.11 344	86.61 179	95.27 186

PAPM_NR		91.46 70	90.82 74	93.37 66	98.50 40	81.81 117	95.03 226	96.13 119	84.65 135	86.10 138	97.65 64	79.24 72	99.75 30	83.20 166	96.88 83	98.56 46

Effi-MVS+-dtu		84.61 196	84.90 177	83.72 294	91.96 224	63.14 339	94.95 227	93.34 268	85.57 112	79.79 210	87.12 266	61.99 243	95.61 255	83.55 161	85.83 190	92.41 219

PS-MVSNAJss		84.91 192	84.30 185	86.74 243	85.89 309	74.40 273	94.95 227	94.16 226	83.93 156	76.45 242	90.11 228	71.04 190	95.77 242	83.16 167	79.02 237	90.06 244

MS-PatchMatch		83.05 221	81.82 221	86.72 247	89.64 264	79.10 182	94.88 229	94.59 206	79.70 237	70.67 295	89.65 231	50.43 305	96.82 200	70.82 273	95.99 97	84.25 334

dcpmvs_2		93.10 36	93.46 34	92.02 115	97.77 65	79.73 165	94.82 230	93.86 240	86.91 92	91.33 76	96.76 103	85.20 32	98.06 133	96.90 19	97.60 64	98.27 64

OMC-MVS		88.80 123	88.16 121	90.72 156	95.30 122	77.92 218	94.81 231	94.51 209	86.80 95	84.97 147	96.85 98	67.53 206	98.60 110	85.08 141	87.62 172	95.63 176

MVSFormer		91.36 73	90.57 77	93.73 51	93.00 188	88.08 15	94.80 232	94.48 210	80.74 211	94.90 33	97.13 88	78.84 77	95.10 279	83.77 155	97.46 67	98.02 77

test_djsdf		83.00 224	82.45 213	84.64 280	84.07 330	69.78 313	94.80 232	94.48 210	80.74 211	75.41 262	87.70 256	61.32 248	95.10 279	83.77 155	79.76 228	89.04 266

baseline		90.76 86	90.10 89	92.74 87	92.90 194	82.56 99	94.60 234	94.56 207	87.69 74	89.06 108	95.67 125	73.76 160	97.51 160	90.43 93	92.23 139	98.16 69

WR-MVS_H		81.02 251	80.09 244	83.79 291	88.08 283	71.26 304	94.46 235	96.54 82	80.08 229	72.81 282	86.82 270	70.36 196	92.65 319	64.18 303	67.50 313	87.46 303

NR-MVSNet		83.35 214	81.52 226	88.84 197	88.76 273	81.31 127	94.45 236	95.16 173	84.65 135	67.81 307	90.82 214	70.36 196	94.87 285	74.75 240	66.89 319	90.33 235

tfpnnormal		78.14 275	75.42 281	86.31 252	88.33 280	79.24 176	94.41 237	96.22 113	73.51 300	69.81 301	85.52 293	55.43 289	95.75 244	47.65 356	67.86 309	83.95 337

v8		81.88 240	80.06 247	87.32 233	86.63 296	79.04 185	94.41 237	93.65 254	78.77 255	73.19 278	85.57 291	66.87 212	95.81 240	73.84 251	67.61 312	87.11 306

MVS_Test		90.29 96	89.18 104	93.62 55	95.23 123	84.93 62	94.41 237	94.66 199	84.31 144	90.37 92	91.02 210	75.13 142	97.82 143	83.11 168	94.42 110	98.12 73

bld_raw_dy_0_64		82.13 237	80.76 234	86.24 254	85.78 311	75.03 267	94.40 240	82.62 357	83.12 173	76.46 241	90.96 213	53.83 299	94.55 292	81.04 179	78.60 243	89.14 261

eth_miper_zixun_eth		83.12 220	82.01 217	86.47 248	91.85 229	74.80 268	94.33 241	93.18 273	79.11 249	75.74 259	87.25 264	72.71 170	95.32 267	76.78 221	67.13 316	89.27 257

v10		81.43 246	79.53 253	87.11 238	86.38 298	78.87 186	94.31 242	93.43 262	77.88 263	73.24 277	85.26 295	65.44 220	95.75 244	72.14 260	67.71 311	86.72 310

GBi-Net		82.42 232	80.43 241	88.39 206	92.66 197	81.95 108	94.30 243	93.38 264	79.06 251	75.82 256	85.66 287	56.38 285	93.84 305	71.23 266	75.38 258	89.38 253

test1		82.42 232	80.43 241	88.39 206	92.66 197	81.95 108	94.30 243	93.38 264	79.06 251	75.82 256	85.66 287	56.38 285	93.84 305	71.23 266	75.38 258	89.38 253

FMVSNet1		79.50 265	76.54 275	88.39 206	88.47 278	81.95 108	94.30 243	93.38 264	73.14 304	72.04 288	85.66 287	43.86 324	93.84 305	65.48 298	72.53 271	89.38 253

CP-MVSNet		81.01 252	80.08 245	83.79 291	87.91 285	70.51 306	94.29 246	95.65 146	80.83 209	72.54 285	88.84 239	63.71 231	92.32 322	68.58 284	68.36 303	88.55 277

CL-MVSNet_self_test		75.81 292	74.14 294	80.83 315	78.33 348	67.79 322	94.22 247	93.52 259	77.28 272	69.82 300	81.54 324	61.47 247	89.22 346	57.59 329	53.51 348	85.48 326

jajsoiax		82.12 238	81.15 230	85.03 274	84.19 328	70.70 305	94.22 247	93.95 234	83.07 175	73.48 273	89.75 230	49.66 308	95.37 264	82.24 173	79.76 228	89.02 267

PS-CasMVS		80.27 258	79.18 254	83.52 298	87.56 289	69.88 311	94.08 249	95.29 169	80.27 226	72.08 287	88.51 246	59.22 261	92.23 324	67.49 286	68.15 306	88.45 281

ppachtmachnet_test		77.19 284	74.22 292	86.13 256	85.39 315	78.22 205	93.98 250	91.36 301	71.74 316	67.11 310	84.87 304	56.67 281	93.37 315	52.21 345	64.59 325	86.80 309

mvs_tets		81.74 241	80.71 236	84.84 275	84.22 327	70.29 308	93.91 251	93.78 247	82.77 183	73.37 274	89.46 233	47.36 318	95.31 268	81.99 174	79.55 233	88.92 273

PEN-MVS		79.47 266	78.26 262	83.08 301	86.36 299	68.58 319	93.85 252	94.77 193	79.76 235	71.37 289	88.55 243	59.79 253	92.46 320	64.50 302	65.40 323	88.19 286

testmvs		9.92 344	12.94 347	0.84 360	0.65 382	0.29 384	93.78 253	0.39 383	0.42 376	2.85 377	15.84 376	0.17 383	0.30 379	2.18 376	0.21 376	1.91 374

tt0805		81.20 250	79.06 257	87.61 223	86.50 297	72.97 285	93.66 254	95.48 155	74.11 295	76.23 248	91.99 193	41.36 336	97.40 167	77.44 215	74.78 261	92.45 218

our_test_3		77.90 278	75.37 282	85.48 268	85.39 315	76.74 242	93.63 255	91.67 295	73.39 303	65.72 320	84.65 306	58.20 267	93.13 317	57.82 327	67.87 308	86.57 313

EG-PatchMatch MVS		74.92 296	72.02 302	83.62 295	83.76 334	73.28 281	93.62 256	92.04 291	68.57 328	58.88 345	83.80 312	31.87 355	95.57 258	56.97 333	78.67 239	82.00 348

OpenMVS_ROB	68.52 20	73.02 306	69.57 312	83.37 299	80.54 342	71.82 297	93.60 257	88.22 334	62.37 341	61.98 335	83.15 317	35.31 349	95.47 260	45.08 359	75.88 255	82.82 340

pmmvs4		82.54 230	80.79 232	87.79 219	86.11 305	80.49 146	93.55 258	93.18 273	77.29 271	73.35 275	89.40 234	65.26 224	95.05 283	75.32 236	73.61 266	87.83 292

mvs_anonymous		88.68 125	87.62 132	91.86 120	94.80 138	81.69 121	93.53 259	94.92 182	82.03 196	78.87 217	90.43 221	75.77 125	95.34 265	85.04 142	93.16 127	98.55 48

DTE-MVSNet		78.37 273	77.06 270	82.32 308	85.22 319	67.17 326	93.40 260	93.66 253	78.71 256	70.53 296	88.29 248	59.06 262	92.23 324	61.38 316	63.28 332	87.56 300

v7n		79.32 268	77.34 267	85.28 270	84.05 331	72.89 287	93.38 261	93.87 239	75.02 290	70.68 294	84.37 307	59.58 256	95.62 254	67.60 285	67.50 313	87.32 305

Anonymous20231206		75.29 295	73.64 296	80.22 317	80.75 339	63.38 338	93.36 262	90.71 314	73.09 305	67.12 309	83.70 313	50.33 306	90.85 339	53.63 343	70.10 287	86.44 314

MVP-Stereo		82.65 229	81.67 223	85.59 266	86.10 306	78.29 202	93.33 263	92.82 280	77.75 265	69.17 305	87.98 253	59.28 260	95.76 243	71.77 261	96.88 83	82.73 342
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
1314		88.94 117	87.20 143	94.17 39	93.21 180	85.73 40	93.33 263	96.64 70	82.89 180	75.98 252	96.36 110	66.83 213	99.39 63	83.52 164	96.02 96	97.39 126

MVS		90.60 89	88.64 112	96.50 5	94.25 153	90.53 8	93.33 263	97.21 20	77.59 267	78.88 216	97.31 79	71.52 185	99.69 39	89.60 102	98.03 54	99.27 20

pmmvs6		74.65 298	71.67 303	83.60 296	79.13 346	69.94 310	93.31 266	90.88 311	61.05 350	65.83 319	84.15 310	43.43 326	94.83 287	66.62 291	60.63 337	86.02 321

ACMH+	76.62 16	77.47 282	74.94 284	85.05 273	91.07 239	71.58 301	93.26 267	90.01 317	71.80 315	64.76 323	88.55 243	41.62 334	96.48 211	62.35 312	71.00 278	87.09 307

testgi		74.88 297	73.40 297	79.32 321	80.13 343	61.75 342	93.21 268	86.64 343	79.49 241	66.56 317	91.06 209	35.51 348	88.67 348	56.79 334	71.25 276	87.56 300

LS3D		82.22 236	79.94 249	89.06 192	97.43 79	74.06 276	93.20 269	92.05 290	61.90 343	73.33 276	95.21 137	59.35 258	99.21 74	54.54 340	92.48 135	93.90 207

ACMH	75.40 17	77.99 276	74.96 283	87.10 239	90.67 247	76.41 246	93.19 270	91.64 297	72.47 311	63.44 328	87.61 258	43.34 327	97.16 181	58.34 325	73.94 264	87.72 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UA-Net		88.92 118	88.48 116	90.24 169	94.06 159	77.18 236	93.04 271	94.66 199	87.39 81	91.09 80	93.89 173	74.92 145	98.18 132	75.83 232	91.43 145	95.35 183

IterMVS-SCA-FT		80.51 257	79.10 256	84.73 277	89.63 265	74.66 269	92.98 272	91.81 294	80.05 230	71.06 293	85.18 298	58.04 268	91.40 333	72.48 259	70.70 282	88.12 288

IterMVS		80.67 255	79.16 255	85.20 271	89.79 259	76.08 251	92.97 273	91.86 292	80.28 225	71.20 291	85.14 300	57.93 271	91.34 334	72.52 258	70.74 280	88.18 287
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MVS_0304		78.43 272	76.70 273	83.60 296	88.22 281	69.81 312	92.91 274	95.10 174	72.32 312	78.71 218	80.29 332	33.78 351	93.37 315	68.77 282	80.23 226	87.63 296

MTAPA		92.45 53	92.31 50	92.86 83	97.90 61	80.85 135	92.88 275	96.33 106	87.92 68	90.20 93	98.18 30	76.71 111	99.76 25	92.57 68	98.09 51	97.96 87

SCA		85.63 180	83.64 195	91.60 131	92.30 207	81.86 114	92.88 275	95.56 150	84.85 128	82.52 174	85.12 301	58.04 268	95.39 262	73.89 249	87.58 174	97.54 114

test_0402		72.68 307	69.54 313	82.09 309	88.67 276	71.81 298	92.72 277	86.77 342	61.52 345	62.21 334	83.91 311	43.22 328	93.76 308	34.60 364	72.23 275	80.72 352

LCM-MVSNet-Re		83.75 209	83.54 198	84.39 287	93.54 171	64.14 334	92.51 278	84.03 352	83.90 157	66.14 318	86.59 274	67.36 208	92.68 318	84.89 144	92.87 129	96.35 160

anonymousdsp		80.98 253	79.97 248	84.01 288	81.73 338	70.44 307	92.49 279	93.58 258	77.10 275	72.98 280	86.31 282	57.58 272	94.90 284	79.32 195	78.63 242	86.69 311

PatchMatch-RL		85.00 191	83.66 194	89.02 194	95.86 108	74.55 271	92.49 279	93.60 256	79.30 245	79.29 214	91.47 201	58.53 265	98.45 120	70.22 275	92.17 140	94.07 204

test20.03		72.36 309	71.15 305	75.98 333	77.79 349	59.16 351	92.40 281	89.35 323	74.09 296	61.50 337	84.32 308	48.09 311	85.54 358	50.63 350	62.15 335	83.24 338

MDA-MVSNet-bldmvs		71.45 312	67.94 317	81.98 310	85.33 317	68.50 320	92.35 282	88.76 330	70.40 321	42.99 360	81.96 321	46.57 319	91.31 335	48.75 355	54.39 346	86.11 319

PCF-MVS	84.09 5	86.77 163	85.00 174	92.08 111	92.06 221	83.07 93	92.14 283	94.47 212	79.63 238	76.90 235	94.78 153	71.15 188	99.20 78	72.87 255	91.05 147	93.98 205
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UniMVSNet_ETH3D		80.86 254	78.75 259	87.22 237	86.31 300	72.02 293	91.95 284	93.76 250	73.51 300	75.06 265	90.16 226	43.04 330	95.66 249	76.37 227	78.55 244	93.98 205

miper_lstm_enhance		81.66 244	80.66 237	84.67 279	91.19 236	71.97 295	91.94 285	93.19 272	77.86 264	72.27 286	85.26 295	73.46 164	93.42 313	73.71 252	67.05 317	88.61 276

MSDG		80.62 256	77.77 265	89.14 191	93.43 178	77.24 233	91.89 286	90.18 316	69.86 325	68.02 306	91.94 197	52.21 301	98.84 102	59.32 323	83.12 207	91.35 222

COLMAP_ROB	73.24 19	75.74 293	73.00 299	83.94 289	92.38 203	69.08 318	91.85 287	86.93 340	61.48 346	65.32 321	90.27 223	42.27 332	96.93 194	50.91 349	75.63 257	85.80 325
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EU-MVSNet		76.92 287	76.95 271	76.83 329	84.10 329	54.73 359	91.77 288	92.71 282	72.74 308	69.57 302	88.69 241	58.03 270	87.43 353	64.91 301	70.00 289	88.33 284

MDA-MVSNet_test_wron		73.54 302	70.43 309	82.86 302	84.55 323	71.85 296	91.74 289	91.32 303	67.63 329	46.73 359	81.09 327	55.11 292	90.42 343	55.91 337	59.76 338	86.31 316

YYNet1		73.53 303	70.43 309	82.85 303	84.52 325	71.73 299	91.69 290	91.37 300	67.63 329	46.79 358	81.21 326	55.04 293	90.43 342	55.93 336	59.70 339	86.38 315

N_pmnet		61.30 325	60.20 328	64.60 344	84.32 326	17.00 382	91.67 291	10.98 381	61.77 344	58.45 347	78.55 337	49.89 307	91.83 330	42.27 361	63.94 329	84.97 329

Anonymous20240521		72.06 311	69.91 311	78.50 325	77.11 353	61.67 344	91.62 292	90.97 309	65.52 336	62.37 333	79.05 336	36.32 344	90.96 338	57.75 328	68.52 301	82.87 339

XVG-OURS-SEG-HR		85.74 179	85.16 171	87.49 230	90.22 253	71.45 302	91.29 293	94.09 230	81.37 202	83.90 162	95.22 136	60.30 252	97.53 159	85.58 138	84.42 200	93.50 212

SixPastTwentyTwo		76.04 290	74.32 291	81.22 312	84.54 324	61.43 345	91.16 294	89.30 324	77.89 262	64.04 325	86.31 282	48.23 310	94.29 299	63.54 308	63.84 330	87.93 291

AllTest		75.92 291	73.06 298	84.47 283	92.18 214	67.29 323	91.07 295	84.43 350	67.63 329	63.48 326	90.18 224	38.20 342	97.16 181	57.04 331	73.37 267	88.97 271

XVG-OURS		85.18 187	84.38 184	87.59 225	90.42 251	71.73 299	91.06 296	94.07 231	82.00 197	83.29 168	95.08 146	56.42 284	97.55 155	83.70 159	83.42 205	93.49 213

test_fmvs3		69.56 315	69.19 315	70.67 338	69.01 362	47.05 363	90.87 297	86.81 341	71.31 319	66.79 314	77.15 341	16.40 366	83.17 361	81.84 175	62.51 334	81.79 350

K. test v3		73.62 300	71.59 304	79.69 319	82.98 335	59.85 350	90.85 298	88.83 328	77.13 273	58.90 344	82.11 320	43.62 325	91.72 331	65.83 297	54.10 347	87.50 302

OurMVSNet-221017-0		77.18 285	76.06 277	80.55 316	83.78 333	60.00 349	90.35 299	91.05 307	77.01 277	66.62 316	87.92 254	47.73 316	94.03 302	71.63 262	68.44 302	87.62 297

HY-MVS	84.06 6	91.63 66	90.37 83	95.39 15	96.12 102	88.25 13	90.22 300	97.58 14	88.33 60	90.50 89	91.96 195	79.26 71	99.06 89	90.29 96	89.07 158	98.88 30

new-patchmatchnet		68.85 319	65.93 321	77.61 327	73.57 361	63.94 336	90.11 301	88.73 331	71.62 317	55.08 353	73.60 350	40.84 338	87.22 354	51.35 348	48.49 358	81.67 351

CMPMVS	54.94 21	75.71 294	74.56 289	79.17 322	79.69 344	55.98 354	89.59 302	93.30 269	60.28 351	53.85 355	89.07 236	47.68 317	96.33 216	76.55 223	81.02 220	85.22 327
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
FMVSNet5		76.46 289	74.16 293	83.35 300	90.05 257	76.17 249	89.58 303	89.85 318	71.39 318	65.29 322	80.42 329	50.61 304	87.70 352	61.05 318	69.24 296	86.18 318

USDC		78.65 271	76.25 276	85.85 258	87.58 288	74.60 270	89.58 303	90.58 315	84.05 150	63.13 330	88.23 249	40.69 340	96.86 199	66.57 293	75.81 256	86.09 320

test123		9.07 345	11.73 348	1.11 359	0.50 383	0.77 383	89.44 305	0.20 384	0.34 377	2.15 378	10.72 377	0.34 382	0.32 378	1.79 377	0.08 377	2.23 373

pmmvs-eth3d		73.59 301	70.66 307	82.38 306	76.40 356	73.38 278	89.39 306	89.43 322	72.69 309	60.34 342	77.79 339	46.43 320	91.26 336	66.42 295	57.06 342	82.51 343

XVG-ACMP-BASELINE		79.38 267	77.90 264	83.81 290	84.98 321	67.14 327	89.03 307	93.18 273	80.26 227	72.87 281	88.15 251	38.55 341	96.26 218	76.05 230	78.05 248	88.02 289

ab-mvs		87.08 156	84.94 175	93.48 63	93.34 179	83.67 82	88.82 308	95.70 144	81.18 204	84.55 154	90.14 227	62.72 236	98.94 98	85.49 139	82.54 217	97.85 93

tpm		85.55 182	84.47 183	88.80 199	90.19 254	75.39 263	88.79 309	94.69 195	84.83 129	83.96 160	85.21 297	78.22 86	94.68 290	76.32 228	78.02 249	96.34 161

pmmvs3		65.75 323	62.18 326	76.45 331	67.12 365	64.54 331	88.68 310	85.05 348	54.77 360	57.54 351	73.79 349	29.40 358	86.21 356	55.49 339	47.77 359	78.62 354

CostFormer		89.08 114	88.39 117	91.15 143	93.13 185	79.15 180	88.61 311	96.11 121	83.14 172	89.58 101	86.93 269	83.83 43	96.87 197	88.22 119	85.92 188	97.42 123

TinyColmap		72.41 308	68.99 316	82.68 304	88.11 282	69.59 315	88.41 312	85.20 347	65.55 335	57.91 348	84.82 305	30.80 357	95.94 233	51.38 346	68.70 299	82.49 345

TDRefinement		69.20 318	65.78 322	79.48 320	66.04 366	62.21 341	88.21 313	86.12 344	62.92 340	61.03 340	85.61 290	33.23 352	94.16 300	55.82 338	53.02 350	82.08 347

KD-MVS_2432*1600		77.63 280	74.92 285	85.77 259	90.86 243	79.44 170	88.08 314	93.92 236	76.26 280	67.05 311	82.78 318	72.15 178	91.92 327	61.53 313	41.62 366	85.94 322

miper_refine_blended		77.63 280	74.92 285	85.77 259	90.86 243	79.44 170	88.08 314	93.92 236	76.26 280	67.05 311	82.78 318	72.15 178	91.92 327	61.53 313	41.62 366	85.94 322

tpm2		87.35 155	86.26 156	90.62 158	92.93 193	78.67 192	88.06 316	95.99 128	79.33 243	87.40 125	86.43 280	80.28 61	96.40 213	80.23 187	85.73 192	96.79 147

CHOSEN 280x420		91.71 65	91.85 58	91.29 138	94.94 134	82.69 97	87.89 317	96.17 118	85.94 106	87.27 128	94.31 161	90.27 9	95.65 251	94.04 48	95.86 98	95.53 179

RPSCF		77.73 279	76.63 274	81.06 313	88.66 277	55.76 357	87.77 318	87.88 336	64.82 338	74.14 270	92.79 187	49.22 309	96.81 201	67.47 287	76.88 251	90.62 229

KD-MVS_self_test		70.97 314	69.31 314	75.95 334	76.24 358	55.39 358	87.45 319	90.94 310	70.20 323	62.96 332	77.48 340	44.01 323	88.09 349	61.25 317	53.26 349	84.37 333

MIMVSNet1		69.44 316	66.65 320	77.84 326	76.48 355	62.84 340	87.42 320	88.97 327	66.96 334	57.75 350	79.72 335	32.77 354	85.83 357	46.32 357	63.42 331	84.85 330

tpmrst		88.36 135	87.38 140	91.31 136	94.36 151	79.92 157	87.32 321	95.26 171	85.32 117	88.34 117	86.13 285	80.60 58	96.70 205	83.78 154	85.34 196	97.30 130

UnsupCasMVSNet_eth		73.25 304	70.57 308	81.30 311	77.53 350	66.33 328	87.24 322	93.89 238	80.38 222	57.90 349	81.59 323	42.91 331	90.56 341	65.18 300	48.51 357	87.01 308

FA-MVS(test-final)		87.71 150	86.23 157	92.17 109	94.19 155	80.55 142	87.16 323	96.07 125	82.12 194	85.98 139	88.35 247	72.04 180	98.49 116	80.26 186	89.87 152	97.48 121

EPMVS		87.47 154	85.90 160	92.18 108	95.41 119	82.26 107	87.00 324	96.28 109	85.88 108	84.23 155	85.57 291	75.07 144	96.26 218	71.14 269	92.50 134	98.03 76

MDTV_nov1_ep13_2view						81.74 119	86.80 325		80.65 213	85.65 140		74.26 154		76.52 224		96.98 139

MDTV_nov1_ep13			83.69 192		94.09 158	81.01 130	86.78 326	96.09 122	83.81 160	84.75 150	84.32 308	74.44 153	96.54 209	63.88 305	85.07 197

dp		84.30 202	82.31 214	90.28 168	94.24 154	77.97 214	86.57 327	95.53 151	79.94 233	80.75 198	85.16 299	71.49 186	96.39 214	63.73 306	83.36 206	96.48 157

PatchmatchNet		86.83 161	85.12 172	91.95 117	94.12 157	82.27 106	86.55 328	95.64 147	84.59 137	82.98 173	84.99 303	77.26 100	95.96 232	68.61 283	91.34 146	97.64 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
LTVRE_ROB	73.68 18	77.99 276	75.74 280	84.74 276	90.45 250	72.02 293	86.41 329	91.12 304	72.57 310	66.63 315	87.27 262	54.95 294	96.98 190	56.29 335	75.98 253	85.21 328
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
LF4IMVS		72.36 309	70.82 306	76.95 328	79.18 345	56.33 353	86.12 330	86.11 345	69.30 327	63.06 331	86.66 273	33.03 353	92.25 323	65.33 299	68.64 300	82.28 346

PM-MVS		69.32 317	66.93 319	76.49 330	73.60 360	55.84 355	85.91 331	79.32 363	74.72 292	61.09 339	78.18 338	21.76 362	91.10 337	70.86 271	56.90 343	82.51 343

test_post1							85.88 332				30.24 374	73.77 159	95.07 282	73.89 249

tpmvs		83.04 222	80.77 233	89.84 182	95.43 118	77.96 215	85.59 333	95.32 168	75.31 287	76.27 247	83.70 313	73.89 158	97.41 166	59.53 320	81.93 219	94.14 201

tpm cat1		83.63 211	81.38 227	90.39 164	93.53 176	78.19 210	85.56 334	95.09 175	70.78 320	78.51 220	83.28 316	74.80 146	97.03 187	66.77 290	84.05 201	95.95 169

DSMNet-mixed		73.13 305	72.45 300	75.19 335	77.51 351	46.82 364	85.09 335	82.01 358	67.61 333	69.27 304	81.33 325	50.89 302	86.28 355	54.54 340	83.80 202	92.46 217

FE-MVS		86.06 173	84.15 188	91.78 124	94.33 152	79.81 159	84.58 336	96.61 73	76.69 278	85.00 146	87.38 260	70.71 194	98.37 124	70.39 274	91.70 144	97.17 135

test_vis3_rt		54.10 329	51.04 332	63.27 347	58.16 369	46.08 368	84.17 337	49.32 380	56.48 359	36.56 364	49.48 367	8.03 376	91.91 329	67.29 288	49.87 354	51.82 366

UnsupCasMVSNet_bld		68.60 320	64.50 324	80.92 314	74.63 359	67.80 321	83.97 338	92.94 279	65.12 337	54.63 354	68.23 358	35.97 346	92.17 326	60.13 319	44.83 361	82.78 341

new_pmnet		66.18 322	63.18 325	75.18 336	76.27 357	61.74 343	83.79 339	84.66 349	56.64 358	51.57 356	71.85 357	31.29 356	87.93 350	49.98 351	62.55 333	75.86 357

test_f		64.01 324	62.13 327	69.65 339	63.00 368	45.30 369	83.66 340	80.68 360	61.30 347	55.70 352	72.62 353	14.23 368	84.64 359	69.84 276	58.11 340	79.00 353

mvsany_test3		67.19 321	65.34 323	72.72 337	63.08 367	48.57 362	83.12 341	78.09 364	72.07 313	61.21 338	77.11 342	22.94 361	87.78 351	78.59 202	51.88 353	81.80 349

FPMVS		55.09 328	52.93 331	61.57 348	55.98 370	40.51 373	83.11 342	83.41 355	37.61 364	34.95 365	71.95 355	14.40 367	76.95 364	29.81 365	65.16 324	67.25 361

EGC-MVSNET		52.46 331	47.56 334	67.15 340	81.98 337	60.11 348	82.54 343	72.44 368	0.11 378	0.70 379	74.59 347	25.11 360	83.26 360	29.04 366	61.51 336	58.09 363

GG-mvs-BLEND				93.49 62	94.94 134	86.26 31	81.62 344	97.00 29		88.32 118	94.30 162	91.23 5	96.21 221	88.49 115	97.43 70	98.00 82

MIMVSNet		79.18 269	75.99 278	88.72 201	87.37 292	80.66 139	79.96 345	91.82 293	77.38 270	74.33 269	81.87 322	41.78 333	90.74 340	66.36 296	83.10 208	94.76 191

ADS-MVSNet2		79.57 264	77.53 266	85.71 261	93.78 164	72.13 290	79.48 346	86.11 345	73.09 305	80.14 206	79.99 333	62.15 240	90.14 345	59.49 321	83.52 203	94.85 189

ADS-MVSNet		81.26 248	78.36 260	89.96 178	93.78 164	79.78 160	79.48 346	93.60 256	73.09 305	80.14 206	79.99 333	62.15 240	95.24 271	59.49 321	83.52 203	94.85 189

gg-mvs-nofinetune		85.48 184	82.90 206	93.24 69	94.51 148	85.82 39	79.22 348	96.97 31	61.19 348	87.33 127	53.01 364	90.58 6	96.07 223	86.07 135	97.23 76	97.81 97

MVS-HIRNet		71.36 313	67.00 318	84.46 285	90.58 248	69.74 314	79.15 349	87.74 338	46.09 361	61.96 336	50.50 365	45.14 322	95.64 252	53.74 342	88.11 170	88.00 290

CR-MVSNet		83.53 212	81.36 228	90.06 173	90.16 255	79.75 162	79.02 350	91.12 304	84.24 148	82.27 182	80.35 330	75.45 132	93.67 309	63.37 309	86.25 183	96.75 151

RPMNet		79.85 260	75.92 279	91.64 128	90.16 255	79.75 162	79.02 350	95.44 159	58.43 357	82.27 182	72.55 354	73.03 168	98.41 123	46.10 358	86.25 183	96.75 151

Patchmatch-RL test		76.65 288	74.01 295	84.55 282	77.37 352	64.23 333	78.49 352	82.84 356	78.48 258	64.63 324	73.40 351	76.05 121	91.70 332	76.99 218	57.84 341	97.72 102

Patchmtry		77.36 283	74.59 288	85.67 263	89.75 261	75.75 261	77.85 353	91.12 304	60.28 351	71.23 290	80.35 330	75.45 132	93.56 311	57.94 326	67.34 315	87.68 295

PatchT		79.75 261	76.85 272	88.42 204	89.55 266	75.49 262	77.37 354	94.61 204	63.07 339	82.46 176	73.32 352	75.52 131	93.41 314	51.36 347	84.43 199	96.36 159

PMMVS2		50.90 332	46.31 335	64.67 343	55.53 371	46.67 365	77.30 355	71.02 369	40.89 362	34.16 366	59.32 361	9.83 374	76.14 367	40.09 363	28.63 369	71.21 358

APD_test1		56.56 327	53.58 330	65.50 341	67.93 364	46.51 366	77.24 356	72.95 367	38.09 363	42.75 361	75.17 345	13.38 369	82.78 362	40.19 362	54.53 345	67.23 362

test_method		56.77 326	54.53 329	63.49 346	76.49 354	40.70 372	75.68 357	74.24 366	19.47 372	48.73 357	71.89 356	19.31 363	65.80 372	57.46 330	47.51 360	83.97 336

JIA-IIPM		79.00 270	77.20 268	84.40 286	89.74 263	64.06 335	75.30 358	95.44 159	62.15 342	81.90 187	59.08 362	78.92 75	95.59 256	66.51 294	85.78 191	93.54 211

EMVS		31.70 341	31.45 343	32.48 357	50.72 376	23.95 380	74.78 359	52.30 379	20.36 371	16.08 375	31.48 373	12.80 370	53.60 375	11.39 374	13.10 374	19.88 372

E-PMN		32.70 340	32.39 342	33.65 356	53.35 373	25.70 379	74.07 360	53.33 378	21.08 370	17.17 374	33.63 372	11.85 372	54.84 374	12.98 373	14.04 371	20.42 371

Patchmatch-test		78.25 274	74.72 287	88.83 198	91.20 235	74.10 275	73.91 361	88.70 332	59.89 354	66.82 313	85.12 301	78.38 83	94.54 293	48.84 354	79.58 232	97.86 92

LCM-MVSNet		52.52 330	48.24 333	65.35 342	47.63 377	41.45 371	72.55 362	83.62 354	31.75 365	37.66 363	57.92 363	9.19 375	76.76 365	49.26 353	44.60 362	77.84 355

ANet_high		46.22 333	41.28 340	61.04 349	39.91 379	46.25 367	70.59 363	76.18 365	58.87 356	23.09 371	48.00 368	12.58 371	66.54 371	28.65 367	13.62 372	70.35 359

testf1		45.70 334	42.41 336	55.58 350	53.29 374	40.02 374	68.96 364	62.67 374	27.45 367	29.85 367	61.58 359	5.98 377	73.83 369	28.49 368	43.46 364	52.90 364

APD_test2		45.70 334	42.41 336	55.58 350	53.29 374	40.02 374	68.96 364	62.67 374	27.45 367	29.85 367	61.58 359	5.98 377	73.83 369	28.49 368	43.46 364	52.90 364

ambc				76.02 332	68.11 363	51.43 360	64.97 366	89.59 319		60.49 341	74.49 348	17.17 365	92.46 320	61.50 315	52.85 351	84.17 335

tmp_tt		41.54 337	41.93 339	40.38 355	20.10 381	26.84 378	61.93 367	59.09 376	14.81 374	28.51 369	80.58 328	35.53 347	48.33 376	63.70 307	13.11 373	45.96 369

PMVS	34.80 23	39.19 338	35.53 341	50.18 353	29.72 380	30.30 377	59.60 368	66.20 373	26.06 369	17.91 373	49.53 366	3.12 379	74.09 368	18.19 372	49.40 355	46.14 367
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	35.65 22	33.85 339	29.49 344	46.92 354	41.86 378	36.28 376	50.45 369	56.52 377	18.75 373	18.28 372	37.84 369	2.41 380	58.41 373	18.71 371	20.62 370	46.06 368
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
Gipuma		45.11 336	42.05 338	54.30 352	80.69 340	51.30 361	35.80 370	83.81 353	28.13 366	27.94 370	34.53 370	11.41 373	76.70 366	21.45 370	54.65 344	34.90 370
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
wuyk23d		14.10 343	13.89 346	14.72 358	55.23 372	22.91 381	33.83 371	3.56 382	4.94 375	4.11 376	2.28 378	2.06 381	19.66 377	10.23 375	8.74 375	1.59 375

test_blank		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet_test		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

DCPMVS		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

cdsmvs_eth3d_5k		21.43 342	28.57 345	0.00 361	0.00 384	0.00 385	0.00 372	95.93 133	0.00 379	0.00 380	97.66 60	63.57 232	0.00 380	0.00 378	0.00 378	0.00 376

pcd_1.5k_mvsjas		5.92 347	7.89 350	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	71.04 190	0.00 380	0.00 378	0.00 378	0.00 376

sosnet-low-res		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

sosnet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uncertanet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

Regformer		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

ab-mvs-re		8.11 346	10.81 349	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	97.30 81	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

uanet		0.00 348	0.00 351	0.00 361	0.00 384	0.00 385	0.00 372	0.00 385	0.00 379	0.00 380	0.00 379	0.00 384	0.00 380	0.00 378	0.00 378	0.00 376

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 41					99.81 21	98.08 7	98.81 24	99.43 11

PC_three_1452									91.12 21	98.33 2	98.42 23	92.51 2	99.81 21	98.96 2	99.37 1	99.70 3

No_MVS				97.14 3	99.05 9	92.19 4		96.83 41					99.81 21	98.08 7	98.81 24	99.43 11

test_one_0601					98.91 18	84.56 68		96.70 60	88.06 64	96.57 16	98.77 10	88.04 20

eth-test2					0.00 384

eth-test					0.00 384

ZD-MVS					99.09 8	83.22 91		96.60 76	82.88 181	93.61 49	98.06 42	82.93 48	99.14 83	95.51 33	98.49 37

IU-MVS					99.03 15	85.34 47		96.86 40	92.05 16	98.74 1				98.15 4	98.97 17	99.42 13

test_241102_TWO								96.78 44	88.72 51	97.70 6	98.91 2	87.86 21	99.82 18	98.15 4	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 59		96.78 44	88.72 51	97.79 4	98.90 5	88.48 17	99.82 18

test_0728_THIRD									88.38 58	96.69 13	98.76 12	89.64 13	99.76 25	97.47 14	98.84 23	99.38 14

GSMVS																97.54 114

test_part2					98.90 19	85.14 58				96.07 21

sam_mvs1												77.59 95				97.54 114

sam_mvs												75.35 139

MTGPA								96.33 106

test_post											33.80 371	76.17 119	95.97 229

patchmatchnet-post											77.09 343	77.78 94	95.39 262

gm-plane-assit					92.27 208	79.64 168			84.47 141		95.15 142		97.93 136	85.81 136

test9_res														96.00 25	99.03 13	98.31 60

agg_prior2														94.30 43	99.00 15	98.57 45

agg_prior					98.59 35	83.13 92		96.56 81		94.19 43			99.16 82

TestCases				84.47 283	92.18 214	67.29 323		84.43 350	67.63 329	63.48 326	90.18 224	38.20 342	97.16 181	57.04 331	73.37 267	88.97 271

test_prior				93.09 75	98.68 26	81.91 111		96.40 99					99.06 89			98.29 62

新几何1				93.12 73	97.44 78	81.60 123		96.71 59	74.54 293	91.22 79	97.57 67	79.13 74	99.51 57	77.40 216	98.46 38	98.26 65

旧先验1					97.39 82	79.58 169		96.54 82			98.08 40	84.00 40			97.42 71	97.62 111

原ACMM1				91.22 141	97.77 65	78.10 211		96.61 73	81.05 206	91.28 78	97.42 76	77.92 91	98.98 93	79.85 192	98.51 34	96.59 154

testdata2													99.48 59	76.45 225

segment_acmp												82.69 51

testdata				90.13 172	95.92 107	74.17 274		96.49 90	73.49 302	94.82 37	97.99 44	78.80 79	97.93 136	83.53 163	97.52 66	98.29 62

test12				94.25 35	98.34 46	85.55 44		96.35 105		92.36 60		80.84 56	99.22 73		98.31 47	97.98 84

plane_prior7					91.86 227	77.55 228

plane_prior6					91.98 223	77.92 218						64.77 227

plane_prior5								94.69 195					97.30 173	87.08 128	82.82 213	90.96 225

plane_prior4											94.15 167

plane_prior3						77.75 224			90.17 35	81.33 192

plane_prior1					91.95 225

n2								0.00 385

nn								0.00 385

door-mid								79.75 362

lessismore_v0				79.98 318	80.59 341	58.34 352		80.87 359		58.49 346	83.46 315	43.10 329	93.89 304	63.11 310	48.68 356	87.72 293

LGP-MVS_train				86.33 249	90.88 241	73.06 283		94.13 227	82.20 191	76.31 244	93.20 180	54.83 295	96.95 191	83.72 157	80.83 222	88.98 269

test11								96.50 87

door								80.13 361

HQP5-MVS						78.48 195

BP-MVS														87.67 124

HQP4-MVS										82.30 178			97.32 171			91.13 223

HQP3-MVS								94.80 190							83.01 209

HQP2-MVS												65.40 221

NP-MVS					92.04 222	78.22 205					94.56 157

ACMMP++_ref															78.45 245

ACMMP++															79.05 236

Test By Simon												71.65 183

ITE_SJBPF				82.38 306	87.00 294	65.59 329		89.55 320	79.99 232	69.37 303	91.30 205	41.60 335	95.33 266	62.86 311	74.63 263	86.24 317

DeepMVS_CX				64.06 345	78.53 347	43.26 370		68.11 372	69.94 324	38.55 362	76.14 344	18.53 364	79.34 363	43.72 360	41.62 366	69.57 360

High-resolution multi-view benchmark