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.

DPM-MVS		96.21 2	95.53 12	98.26 1	96.26 98	95.09 1	99.15 7	96.98 34	93.39 14	96.45 24	98.79 8	90.17 10	99.99 1	89.33 123	99.25 6	99.70 3

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 23	97.10 30	95.17 3	92.11 78	98.46 26	87.33 24	99.97 2	97.21 28	99.31 4	99.63 7

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 22	99.06 16	97.12 28	94.66 5	96.79 16	98.78 9	86.42 29	99.95 3	97.59 23	99.18 7	99.00 27

NCCC		95.63 6	95.94 8	94.69 28	99.21 6	85.15 59	99.16 6	96.96 37	94.11 9	95.59 32	98.64 17	85.07 33	99.91 4	95.61 45	99.10 9	99.00 27

API-MVS		90.18 109	88.97 121	93.80 50	98.66 28	82.95 100	97.50 94	95.63 160	75.16 310	86.31 150	97.69 70	72.49 187	99.90 5	81.26 194	96.07 102	98.56 47

DeepC-MVS_fast	89.06 2	94.48 23	94.30 28	95.02 20	98.86 21	85.68 44	98.06 55	96.64 75	93.64 12	91.74 84	98.54 20	80.17 69	99.90 5	92.28 84	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
DP-MVS Recon		91.72 75	90.85 84	94.34 34	99.50 1	85.00 63	98.51 35	95.96 141	80.57 237	88.08 135	97.63 78	76.84 115	99.89 7	85.67 153	94.88 116	98.13 74

CANet		94.89 15	94.64 21	95.63 13	97.55 75	88.12 16	99.06 16	96.39 106	94.07 10	95.34 34	97.80 67	76.83 117	99.87 8	97.08 30	97.64 66	98.89 30

DeepPCF-MVS	89.82 1	94.61 21	96.17 5	89.91 194	97.09 90	70.21 326	98.99 22	96.69 67	95.57 2	95.08 40	99.23 1	86.40 30	99.87 8	97.84 20	98.66 31	99.65 6

HPM-MVS++		95.32 10	95.48 13	94.85 24	98.62 34	86.04 36	97.81 70	96.93 40	92.45 20	95.69 31	98.50 24	85.38 31	99.85 10	94.75 54	99.18 7	98.65 43

PHI-MVS		93.59 37	93.63 36	93.48 67	98.05 58	81.76 125	98.64 31	97.13 26	82.60 206	94.09 55	98.49 25	80.35 64	99.85 10	94.74 55	98.62 32	98.83 32

DVP-MVS++		96.05 4	96.41 3	94.96 22	99.05 9	85.34 49	98.13 49	96.77 55	88.38 73	97.70 8	98.77 10	92.06 3	99.84 12	97.47 24	99.37 1	99.70 3

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 11				98.54 20	92.06 3	99.84 12	99.11 2	99.37 1	99.74 1

test_0728_SECOND				95.14 18	99.04 14	86.14 35	99.06 16	96.77 55					99.84 12	97.90 17	98.85 21	99.45 10

SMA-MVS		94.70 20	94.68 20	94.76 26	98.02 59	85.94 39	97.47 95	96.77 55	85.32 132	97.92 3	98.70 15	83.09 49	99.84 12	95.79 42	99.08 10	98.49 51
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
patch_mono-2		95.14 12	96.08 7	92.33 110	98.44 43	77.84 235	98.43 36	97.21 22	92.58 19	97.68 10	97.65 76	86.88 26	99.83 16	98.25 9	97.60 67	99.33 17

ACMMP_NAP		93.46 38	93.23 44	94.17 41	97.16 88	84.28 76	96.82 149	96.65 72	86.24 115	94.27 52	97.99 52	77.94 96	99.83 16	93.39 69	98.57 33	98.39 57

SED-MVS		95.88 5	96.22 4	94.87 23	99.03 15	85.03 61	99.12 11	96.78 49	88.72 66	97.79 6	98.91 2	88.48 17	99.82 18	98.15 11	98.97 17	99.74 1

test_241102_TWO								96.78 49	88.72 66	97.70 8	98.91 2	87.86 21	99.82 18	98.15 11	99.00 15	99.47 9

test_241102_ONE					99.03 15	85.03 61		96.78 49	88.72 66	97.79 6	98.90 5	88.48 17	99.82 18

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 46					99.81 21	98.08 14	98.81 24	99.43 11

PC_three_1452									91.12 35	98.33 2	98.42 28	92.51 2	99.81 21	98.96 3	99.37 1	99.70 3

No_MVS				97.14 3	99.05 9	92.19 4		96.83 46					99.81 21	98.08 14	98.81 24	99.43 11

MVS_0304		95.36 9	95.20 16	95.85 11	94.89 138	89.22 12	98.83 25	97.88 11	94.68 4	95.14 38	97.99 52	80.80 60	99.81 21	98.60 6	97.95 57	98.50 50

fmvsm_s_conf0.5_n		93.69 35	94.13 31	92.34 108	94.56 145	82.01 113	99.07 15	97.13 26	92.09 23	96.25 25	98.53 22	76.47 122	99.80 25	98.39 8	94.71 119	95.22 197

MM				96.15 8		89.50 9	99.18 5	98.10 8	95.68 1	96.64 20	97.92 58	80.72 61	99.80 25	99.16 1	97.96 56	99.15 24

ZNCC-MVS		92.75 50	92.60 55	93.23 74	98.24 51	81.82 123	97.63 82	96.50 92	85.00 143	91.05 95	97.74 69	78.38 89	99.80 25	90.48 104	98.34 46	98.07 77

test_fmvsm_n_1920		94.81 18	95.60 10	92.45 103	95.29 123	80.96 144	99.29 2	97.21 22	94.50 7	97.29 13	98.44 27	82.15 54	99.78 28	98.56 7	97.68 65	96.61 161

fmvsm_l_conf0.5_n_a		94.91 14	95.30 14	93.72 55	94.50 152	84.30 75	99.14 9	96.00 137	91.94 28	97.91 5	98.60 18	84.78 35	99.77 29	98.84 4	96.03 104	97.08 144

fmvsm_s_conf0.5_n_a		93.34 40	93.71 34	92.22 117	93.38 186	81.71 128	98.86 24	96.98 34	91.64 29	96.85 15	98.55 19	75.58 140	99.77 29	97.88 19	93.68 133	95.18 198

DVP-MVS		95.58 8	95.91 9	94.57 30	99.05 9	85.18 54	99.06 16	96.46 96	88.75 64	96.69 17	98.76 12	87.69 22	99.76 31	97.90 17	98.85 21	98.77 34
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_THIRD									88.38 73	96.69 17	98.76 12	89.64 13	99.76 31	97.47 24	98.84 23	99.38 14

GST-MVS		92.43 63	92.22 64	93.04 81	98.17 54	81.64 130	97.40 104	96.38 107	84.71 149	90.90 98	97.40 90	77.55 104	99.76 31	89.75 117	97.74 63	97.72 105

MTAPA		92.45 62	92.31 60	92.86 87	97.90 61	80.85 147	92.88 293	96.33 112	87.92 83	90.20 107	98.18 38	76.71 120	99.76 31	92.57 83	98.09 51	97.96 89

PAPR		92.74 51	92.17 65	94.45 32	98.89 20	84.87 66	97.20 113	96.20 122	87.73 88	88.40 130	98.12 43	78.71 86	99.76 31	87.99 136	96.28 97	98.74 35

PAPM_NR		91.46 81	90.82 85	93.37 70	98.50 40	81.81 124	95.03 242	96.13 127	84.65 151	86.10 153	97.65 76	79.24 77	99.75 36	83.20 182	96.88 86	98.56 47

MAR-MVS		90.63 100	90.22 98	91.86 133	98.47 42	78.20 223	97.18 115	96.61 78	83.87 176	88.18 134	98.18 38	68.71 216	99.75 36	83.66 176	97.15 80	97.63 113
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
fmvsm_l_conf0.5_n		94.89 15	95.24 15	93.86 48	94.42 154	84.61 69	99.13 10	96.15 126	92.06 25	97.92 3	98.52 23	84.52 36	99.74 38	98.76 5	95.67 110	97.22 137

fmvsm_s_conf0.1_n		92.93 47	93.16 46	92.24 115	90.52 264	81.92 117	98.42 37	96.24 118	91.17 34	96.02 29	98.35 31	75.34 151	99.74 38	97.84 20	94.58 121	95.05 199

DPE-MVS		95.32 10	95.55 11	94.64 29	98.79 23	84.87 66	97.77 72	96.74 60	86.11 117	96.54 23	98.89 6	88.39 19	99.74 38	97.67 22	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
MP-MVS-pluss		92.58 60	92.35 59	93.29 71	97.30 86	82.53 105	96.44 172	96.04 135	84.68 150	89.12 120	98.37 29	77.48 105	99.74 38	93.31 73	98.38 43	97.59 116
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
QAPM		86.88 174	84.51 195	93.98 44	94.04 167	85.89 40	97.19 114	96.05 134	73.62 321	75.12 281	95.62 142	62.02 257	99.74 38	70.88 288	96.06 103	96.30 173

test_fmvsmvis_n_1920		92.12 67	92.10 67	92.17 120	90.87 257	81.04 140	98.34 40	93.90 256	92.71 18	87.24 143	97.90 61	74.83 158	99.72 43	96.96 31	96.20 98	95.76 183

AdaColmap		88.81 136	87.61 147	92.39 107	99.33 4	79.95 170	96.70 159	95.58 161	77.51 290	83.05 187	96.69 121	61.90 260	99.72 43	84.29 163	93.47 137	97.50 123

fmvsm_s_conf0.1_n_a		92.38 64	92.49 57	92.06 125	88.08 300	81.62 131	97.97 61	96.01 136	90.62 41	96.58 21	98.33 32	74.09 170	99.71 45	97.23 27	93.46 138	94.86 203

HFP-MVS		92.89 48	92.86 50	92.98 83	98.71 25	81.12 138	97.58 86	96.70 65	85.20 137	91.75 83	97.97 57	78.47 88	99.71 45	90.95 95	98.41 41	98.12 75

DeepC-MVS	86.58 3	91.53 80	91.06 83	92.94 85	94.52 148	81.89 119	95.95 199	95.98 139	90.76 39	83.76 179	96.76 117	73.24 181	99.71 45	91.67 91	96.96 83	97.22 137
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MP-MVS		92.61 59	92.67 53	92.42 106	98.13 56	79.73 179	97.33 107	96.20 122	85.63 126	90.53 102	97.66 72	78.14 94	99.70 48	92.12 86	98.30 48	97.85 95
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVS		90.60 101	88.64 126	96.50 5	94.25 158	90.53 8	93.33 282	97.21 22	77.59 289	78.88 233	97.31 92	71.52 199	99.69 49	89.60 118	98.03 54	99.27 20

DELS-MVS		94.98 13	94.49 23	96.44 6	96.42 95	90.59 7	99.21 4	97.02 32	94.40 8	91.46 86	97.08 104	83.32 47	99.69 49	92.83 79	98.70 30	99.04 25
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
mPP-MVS		91.88 71	91.82 70	92.07 124	98.38 44	78.63 207	97.29 108	96.09 130	85.12 139	88.45 129	97.66 72	75.53 141	99.68 51	89.83 115	98.02 55	97.88 91

3Dnovator	82.32 10	89.33 124	87.64 144	94.42 33	93.73 174	85.70 43	97.73 76	96.75 59	86.73 113	76.21 266	95.93 132	62.17 254	99.68 51	81.67 192	97.81 61	97.88 91

region2R		92.72 54	92.70 52	92.79 90	98.68 26	80.53 158	97.53 90	96.51 90	85.22 135	91.94 81	97.98 55	77.26 107	99.67 53	90.83 99	98.37 44	98.18 69

ACMMPR		92.69 56	92.67 53	92.75 91	98.66 28	80.57 154	97.58 86	96.69 67	85.20 137	91.57 85	97.92 58	77.01 112	99.67 53	90.95 95	98.41 41	98.00 84

test_fmvsmconf_n		93.99 32	94.36 27	92.86 87	92.82 203	81.12 138	99.26 3	96.37 110	93.47 13	95.16 35	98.21 36	79.00 80	99.64 55	98.21 10	96.73 92	97.83 97

OpenMVS	79.58 14	86.09 187	83.62 211	93.50 65	90.95 254	86.71 32	97.44 98	95.83 149	75.35 307	72.64 302	95.72 137	57.42 295	99.64 55	71.41 282	95.85 108	94.13 217

ACMMP		90.39 105	89.97 105	91.64 141	97.58 73	78.21 222	96.78 152	96.72 63	84.73 148	84.72 166	97.23 97	71.22 201	99.63 57	88.37 134	92.41 151	97.08 144
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
CHOSEN 1792x2688		91.07 92	90.21 99	93.64 57	95.18 127	83.53 89	96.26 184	96.13 127	88.92 63	84.90 163	93.10 202	72.86 183	99.62 58	88.86 126	95.67 110	97.79 101

SD-MVS		94.84 17	95.02 18	94.29 36	97.87 64	84.61 69	97.76 74	96.19 124	89.59 56	96.66 19	98.17 41	84.33 38	99.60 59	96.09 37	98.50 36	98.66 42
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		93.08 44	93.22 45	92.65 96	88.45 296	80.81 148	99.00 21	95.11 186	93.21 15	94.00 56	97.91 60	76.84 115	99.59 60	97.91 16	96.55 95	97.54 117

test_vis1_n_1920		89.95 113	90.59 89	88.03 233	92.36 213	68.98 335	99.12 11	94.34 232	93.86 11	93.64 60	97.01 107	51.54 323	99.59 60	96.76 34	96.71 93	95.53 188

XVS		92.69 56	92.71 51	92.63 98	98.52 37	80.29 161	97.37 105	96.44 98	87.04 105	91.38 87	97.83 66	77.24 109	99.59 60	90.46 105	98.07 52	98.02 79

X-MVStestdata		86.26 185	84.14 204	92.63 98	98.52 37	80.29 161	97.37 105	96.44 98	87.04 105	91.38 87	20.73 398	77.24 109	99.59 60	90.46 105	98.07 52	98.02 79

PVSNet_BlendedMVS		90.05 111	89.96 106	90.33 181	97.47 76	83.86 81	98.02 58	96.73 61	87.98 81	89.53 116	89.61 254	76.42 124	99.57 64	94.29 59	79.59 251	87.57 319

PVSNet_Blended		93.13 41	92.98 47	93.57 61	97.47 76	83.86 81	99.32 1	96.73 61	91.02 38	89.53 116	96.21 127	76.42 124	99.57 64	94.29 59	95.81 109	97.29 135

PGM-MVS		91.93 70	91.80 71	92.32 112	98.27 50	79.74 178	95.28 226	97.27 20	83.83 177	90.89 99	97.78 68	76.12 130	99.56 66	88.82 127	97.93 60	97.66 110

MVS_111021_HR		93.41 39	93.39 42	93.47 69	97.34 85	82.83 101	97.56 88	98.27 6	89.16 61	89.71 111	97.14 100	79.77 72	99.56 66	93.65 67	97.94 58	98.02 79

test_fmvsmconf0.01_n		91.08 91	90.68 88	92.29 113	82.43 356	80.12 168	97.94 62	93.93 252	92.07 24	91.97 79	97.60 79	67.56 220	99.53 68	97.09 29	95.56 112	97.21 139

无先验							96.87 145	96.78 49	77.39 291				99.52 69	79.95 206		98.43 55

CSCG		92.02 69	91.65 74	93.12 77	98.53 36	80.59 153	97.47 95	97.18 25	77.06 298	84.64 168	97.98 55	83.98 43	99.52 69	90.72 101	97.33 76	99.23 21

新几何1				93.12 77	97.44 78	81.60 132		96.71 64	74.54 315	91.22 93	97.57 80	79.13 79	99.51 71	77.40 233	98.46 38	98.26 67

3Dnovator+	82.88 8	89.63 119	87.85 139	94.99 21	94.49 153	86.76 31	97.84 67	95.74 154	86.10 118	75.47 278	96.02 131	65.00 240	99.51 71	82.91 186	97.07 82	98.72 40

CANet_DTU		90.98 93	90.04 103	93.83 49	94.76 141	86.23 34	96.32 181	93.12 296	93.11 16	93.71 58	96.82 115	63.08 250	99.48 73	84.29 163	95.12 115	95.77 182

testdata2													99.48 73	76.45 242

SteuartSystems-ACMMP		94.13 30	94.44 25	93.20 75	95.41 119	81.35 135	99.02 20	96.59 82	89.50 57	94.18 54	98.36 30	83.68 46	99.45 75	94.77 53	98.45 39	98.81 33
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + GP.		94.35 24	94.50 22	93.89 47	97.38 84	83.04 99	98.10 51	95.29 181	91.57 30	93.81 57	97.45 85	86.64 27	99.43 76	96.28 36	94.01 128	99.20 22

1314		88.94 131	87.20 157	94.17 41	93.21 188	85.73 42	93.33 282	96.64 75	82.89 198	75.98 269	96.36 124	66.83 228	99.39 77	83.52 180	96.02 105	97.39 130

SF-MVS		94.17 28	94.05 32	94.55 31	97.56 74	85.95 37	97.73 76	96.43 100	84.02 169	95.07 41	98.74 14	82.93 50	99.38 78	95.42 49	98.51 34	98.32 60

DP-MVS		81.47 263	78.28 280	91.04 159	98.14 55	78.48 209	95.09 241	86.97 359	61.14 370	71.12 312	92.78 207	59.59 271	99.38 78	53.11 361	86.61 194	95.27 196

9.14			94.26 29		98.10 57		98.14 46	96.52 89	84.74 147	94.83 46	98.80 7	82.80 52	99.37 80	95.95 40	98.42 40

TEST9					98.64 31	83.71 84	97.82 68	96.65 72	84.29 164	95.16 35	98.09 45	84.39 37	99.36 81

train_agg		94.28 25	94.45 24	93.74 52	98.64 31	83.71 84	97.82 68	96.65 72	84.50 155	95.16 35	98.09 45	84.33 38	99.36 81	95.91 41	98.96 19	98.16 71

sss		90.87 97	89.96 106	93.60 60	94.15 161	83.84 83	97.14 122	98.13 7	85.93 122	89.68 112	96.09 130	71.67 196	99.30 83	87.69 139	89.16 172	97.66 110

PVSNet_Blended_VisFu		91.24 87	90.77 86	92.66 95	95.09 129	82.40 109	97.77 72	95.87 148	88.26 76	86.39 149	93.94 187	76.77 118	99.27 84	88.80 128	94.00 129	96.31 172

PLC	83.97 7	88.00 158	87.38 154	89.83 197	98.02 59	76.46 260	97.16 119	94.43 227	79.26 269	81.98 201	96.28 126	69.36 214	99.27 84	77.71 226	92.25 153	93.77 224
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test_8					98.63 33	83.64 87	97.81 70	96.63 77	84.50 155	95.10 39	98.11 44	84.33 38	99.23 86

test12				94.25 37	98.34 46	85.55 46		96.35 111		92.36 73		80.84 59	99.22 87		98.31 47	97.98 86

MSLP-MVS++		94.28 25	94.39 26	93.97 45	98.30 49	84.06 79	98.64 31	96.93 40	90.71 40	93.08 67	98.70 15	79.98 70	99.21 88	94.12 62	99.07 11	98.63 44

CDPH-MVS		93.12 42	92.91 48	93.74 52	98.65 30	83.88 80	97.67 81	96.26 116	83.00 196	93.22 65	98.24 35	81.31 57	99.21 88	89.12 124	98.74 29	98.14 73

CP-MVS		92.54 61	92.60 55	92.34 108	98.50 40	79.90 172	98.40 38	96.40 104	84.75 146	90.48 104	98.09 45	77.40 106	99.21 88	91.15 94	98.23 50	97.92 90

LS3D		82.22 253	79.94 268	89.06 208	97.43 79	74.06 292	93.20 288	92.05 310	61.90 364	73.33 295	95.21 152	59.35 274	99.21 88	54.54 357	92.48 150	93.90 222

PCF-MVS	84.09 5	86.77 178	85.00 189	92.08 123	92.06 233	83.07 98	92.14 301	94.47 224	79.63 260	76.90 252	94.78 168	71.15 202	99.20 92	72.87 273	91.05 162	93.98 220
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS_111021_LR		91.60 79	91.64 75	91.47 147	95.74 111	78.79 204	96.15 191	96.77 55	88.49 71	88.64 127	97.07 105	72.33 189	99.19 93	93.13 77	96.48 96	96.43 166

APDe-MVS		94.56 22	94.75 19	93.96 46	98.84 22	83.40 92	98.04 57	96.41 102	85.79 124	95.00 42	98.28 34	84.32 41	99.18 94	97.35 26	98.77 27	99.28 19
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
PS-MVSNAJ		94.17 28	93.52 39	96.10 9	95.65 113	92.35 2	98.21 44	95.79 151	92.42 21	96.24 26	98.18 38	71.04 204	99.17 95	96.77 33	97.39 75	96.79 154

agg_prior					98.59 35	83.13 97		96.56 86		94.19 53			99.16 96

ZD-MVS					99.09 8	83.22 96		96.60 81	82.88 199	93.61 61	98.06 50	82.93 50	99.14 97	95.51 48	98.49 37

EI-MVSNet-Vis-set		91.84 72	91.77 72	92.04 127	97.60 71	81.17 137	96.61 161	96.87 43	88.20 77	89.19 119	97.55 84	78.69 87	99.14 97	90.29 111	90.94 163	95.80 181

EI-MVSNet-UG-set		91.35 85	91.22 79	91.73 138	97.39 82	80.68 151	96.47 169	96.83 46	87.92 83	88.30 133	97.36 91	77.84 99	99.13 99	89.43 122	89.45 170	95.37 192

EPNet		94.06 31	94.15 30	93.76 51	97.27 87	84.35 73	98.29 41	97.64 15	94.57 6	95.36 33	96.88 111	79.96 71	99.12 100	91.30 92	96.11 101	97.82 99
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSP-MVS		95.62 7	96.54 1	92.86 87	98.31 48	80.10 169	97.42 102	96.78 49	92.20 22	97.11 14	98.29 33	93.46 1	99.10 101	96.01 38	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
UGNet		87.73 163	86.55 169	91.27 152	95.16 128	79.11 195	96.35 179	96.23 119	88.14 78	87.83 137	90.48 241	50.65 326	99.09 102	80.13 205	94.03 126	95.60 186
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
test_cas_vis1_n_1920		89.90 114	90.02 104	89.54 202	90.14 273	74.63 285	98.71 27	94.43 227	93.04 17	92.40 72	96.35 125	53.41 319	99.08 103	95.59 46	96.16 99	94.90 201

test_prior				93.09 79	98.68 26	81.91 118		96.40 104					99.06 104			98.29 64

WTY-MVS		92.65 58	91.68 73	95.56 14	96.00 105	88.90 13	98.23 43	97.65 14	88.57 69	89.82 110	97.22 98	79.29 75	99.06 104	89.57 119	88.73 178	98.73 39

HY-MVS	84.06 6	91.63 77	90.37 96	95.39 17	96.12 102	88.25 15	90.22 320	97.58 16	88.33 75	90.50 103	91.96 217	79.26 76	99.06 104	90.29 111	89.07 173	98.88 31

MG-MVS		94.25 27	93.72 33	95.85 11	99.38 3	89.35 11	97.98 59	98.09 9	89.99 51	92.34 74	96.97 108	81.30 58	98.99 107	88.54 129	98.88 20	99.20 22

原ACMM1				91.22 155	97.77 65	78.10 225		96.61 78	81.05 227	91.28 92	97.42 89	77.92 98	98.98 108	79.85 208	98.51 34	96.59 162

Anonymous202405211		84.41 216	81.93 237	91.85 135	96.78 93	78.41 213	97.44 98	91.34 322	70.29 343	84.06 171	94.26 178	41.09 361	98.96 109	79.46 210	82.65 231	98.17 70

xiu_mvs_v2_base		93.92 33	93.26 43	95.91 10	95.07 131	92.02 6	98.19 45	95.68 157	92.06 25	96.01 30	98.14 42	70.83 207	98.96 109	96.74 35	96.57 94	96.76 157

VNet		92.11 68	91.22 79	94.79 25	96.91 91	86.98 27	97.91 63	97.96 10	86.38 114	93.65 59	95.74 136	70.16 212	98.95 111	93.39 69	88.87 176	98.43 55

CNLPA		86.96 172	85.37 181	91.72 139	97.59 72	79.34 189	97.21 111	91.05 327	74.22 316	78.90 232	96.75 119	67.21 225	98.95 111	74.68 259	90.77 164	96.88 152

ab-mvs		87.08 170	84.94 190	93.48 67	93.34 187	83.67 86	88.82 328	95.70 156	81.18 225	84.55 169	90.14 249	62.72 251	98.94 113	85.49 155	82.54 232	97.85 95

HPM-MVS		91.62 78	91.53 76	91.89 132	97.88 63	79.22 191	96.99 133	95.73 155	82.07 216	89.50 118	97.19 99	75.59 139	98.93 114	90.91 97	97.94 58	97.54 117
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
PVSNet	82.34 9	89.02 129	87.79 141	92.71 94	95.49 117	81.50 133	97.70 78	97.29 19	87.76 87	85.47 157	95.12 159	56.90 298	98.90 115	80.33 200	94.02 127	97.71 107

h-mvs33		89.30 125	88.95 123	90.36 180	95.07 131	76.04 267	96.96 139	97.11 29	90.39 46	92.22 76	95.10 160	74.70 160	98.86 116	93.14 75	65.89 343	96.16 174

MSDG		80.62 275	77.77 285	89.14 207	93.43 185	77.24 248	91.89 304	90.18 336	69.86 346	68.02 326	91.94 219	52.21 322	98.84 117	59.32 340	83.12 222	91.35 240

Anonymous20240529		83.15 236	80.60 257	90.80 167	95.74 111	78.27 217	96.81 150	94.92 194	60.10 374	81.89 203	92.54 208	45.82 345	98.82 118	79.25 213	78.32 267	95.31 194

test_yl		91.46 81	90.53 91	94.24 38	97.41 80	85.18 54	98.08 52	97.72 12	80.94 228	89.85 108	96.14 128	75.61 137	98.81 119	90.42 109	88.56 180	98.74 35

DCV-MVSNet		91.46 81	90.53 91	94.24 38	97.41 80	85.18 54	98.08 52	97.72 12	80.94 228	89.85 108	96.14 128	75.61 137	98.81 119	90.42 109	88.56 180	98.74 35

HPM-MVS_fast		90.38 107	90.17 101	91.03 160	97.61 70	77.35 247	97.15 121	95.48 167	79.51 262	88.79 124	96.90 109	71.64 198	98.81 119	87.01 147	97.44 72	96.94 147

APD-MVS		93.61 36	93.59 37	93.69 56	98.76 24	83.26 95	97.21 111	96.09 130	82.41 210	94.65 48	98.21 36	81.96 56	98.81 119	94.65 56	98.36 45	99.01 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS		92.16 66	92.27 61	91.83 136	98.37 45	78.41 213	96.67 160	95.76 152	82.19 214	91.97 79	98.07 49	76.44 123	98.64 123	93.71 66	97.27 78	98.45 54

SR-MVS-dyc-post		91.29 86	91.45 77	90.80 167	97.76 67	76.03 268	96.20 189	95.44 171	80.56 238	90.72 100	97.84 64	75.76 136	98.61 124	91.99 88	96.79 89	97.75 103

alignmvs		92.97 46	92.26 62	95.12 19	95.54 116	87.77 20	98.67 29	96.38 107	88.04 80	93.01 68	97.45 85	79.20 78	98.60 125	93.25 74	88.76 177	98.99 29

OMC-MVS		88.80 137	88.16 135	90.72 170	95.30 122	77.92 232	94.81 247	94.51 221	86.80 110	84.97 162	96.85 112	67.53 221	98.60 125	85.08 157	87.62 187	95.63 185

canonicalmvs		92.27 65	91.22 79	95.41 16	95.80 110	88.31 14	97.09 129	94.64 214	88.49 71	92.99 69	97.31 92	72.68 185	98.57 127	93.38 71	88.58 179	99.36 16

APD-MVS_3200maxsize		91.23 88	91.35 78	90.89 165	97.89 62	76.35 263	96.30 182	95.52 165	79.82 256	91.03 96	97.88 63	74.70 160	98.54 128	92.11 87	96.89 85	97.77 102

IB-MVS	85.34 4	88.67 140	87.14 160	93.26 72	93.12 194	84.32 74	98.76 26	97.27 20	87.19 103	79.36 230	90.45 242	83.92 44	98.53 129	84.41 162	69.79 311	96.93 148
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
114514_t		88.79 138	87.57 148	92.45 103	98.21 53	81.74 126	96.99 133	95.45 170	75.16 310	82.48 190	95.69 139	68.59 217	98.50 130	80.33 200	95.18 114	97.10 143

FA-MVS(test-final)		87.71 164	86.23 171	92.17 120	94.19 160	80.55 155	87.16 343	96.07 133	82.12 215	85.98 154	88.35 269	72.04 194	98.49 131	80.26 202	89.87 167	97.48 125

TSAR-MVS + MP.		94.79 19	95.17 17	93.64 57	97.66 69	84.10 78	95.85 207	96.42 101	91.26 33	97.49 12	96.80 116	86.50 28	98.49 131	95.54 47	99.03 13	98.33 59
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
VDD-MVS		88.28 152	87.02 163	92.06 125	95.09 129	80.18 167	97.55 89	94.45 226	83.09 192	89.10 121	95.92 134	47.97 337	98.49 131	93.08 78	86.91 192	97.52 122

test_fmvs1_n		86.34 183	86.72 167	85.17 290	87.54 308	63.64 356	96.91 143	92.37 307	87.49 93	91.33 90	95.58 144	40.81 363	98.46 134	95.00 52	93.49 136	93.41 232

PatchMatch-RL		85.00 206	83.66 209	89.02 210	95.86 108	74.55 287	92.49 297	93.60 275	79.30 267	79.29 231	91.47 223	58.53 281	98.45 135	70.22 293	92.17 155	94.07 219

F-COLMAP		84.50 215	83.44 215	87.67 239	95.22 125	72.22 305	95.95 199	93.78 266	75.74 305	76.30 263	95.18 155	59.50 273	98.45 135	72.67 275	86.59 195	92.35 238

test_fmvs1		87.79 162	88.52 129	85.62 283	92.98 200	64.31 351	97.88 65	92.42 305	87.95 82	92.24 75	95.82 135	47.94 338	98.44 137	95.31 50	94.09 125	94.09 218

RPMNet		79.85 279	75.92 298	91.64 141	90.16 271	79.75 176	79.02 373	95.44 171	58.43 379	82.27 197	72.55 376	73.03 182	98.41 138	46.10 377	86.25 198	96.75 158

FE-MVS		86.06 188	84.15 203	91.78 137	94.33 157	79.81 173	84.58 359	96.61 78	76.69 300	85.00 161	87.38 282	70.71 208	98.37 139	70.39 292	91.70 159	97.17 141

xiu_mvs_v1_base_debu		90.54 102	89.54 113	93.55 62	92.31 214	87.58 23	96.99 133	94.87 197	87.23 100	93.27 62	97.56 81	57.43 292	98.32 140	92.72 80	93.46 138	94.74 207

xiu_mvs_v1_base		90.54 102	89.54 113	93.55 62	92.31 214	87.58 23	96.99 133	94.87 197	87.23 100	93.27 62	97.56 81	57.43 292	98.32 140	92.72 80	93.46 138	94.74 207

xiu_mvs_v1_base_debi		90.54 102	89.54 113	93.55 62	92.31 214	87.58 23	96.99 133	94.87 197	87.23 100	93.27 62	97.56 81	57.43 292	98.32 140	92.72 80	93.46 138	94.74 207

CPTT-MVS		89.72 117	89.87 110	89.29 205	98.33 47	73.30 296	97.70 78	95.35 178	75.68 306	87.40 139	97.44 88	70.43 209	98.25 143	89.56 120	96.90 84	96.33 171

LFMVS		89.27 126	87.64 144	94.16 43	97.16 88	85.52 47	97.18 115	94.66 211	79.17 270	89.63 114	96.57 122	55.35 309	98.22 144	89.52 121	89.54 169	98.74 35

PVSNet_0	77.72 15	81.70 260	78.95 277	89.94 193	90.77 261	76.72 258	95.96 198	96.95 38	85.01 142	70.24 319	88.53 267	52.32 320	98.20 145	86.68 150	44.08 384	94.89 202

TAPA-MVS	81.61 12	85.02 205	83.67 208	89.06 208	96.79 92	73.27 299	95.92 201	94.79 204	74.81 313	80.47 216	96.83 113	71.07 203	98.19 146	49.82 370	92.57 147	95.71 184
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UA-Net		88.92 132	88.48 130	90.24 183	94.06 166	77.18 251	93.04 290	94.66 211	87.39 96	91.09 94	93.89 188	74.92 157	98.18 147	75.83 249	91.43 160	95.35 193

dcpmvs_2		93.10 43	93.46 41	92.02 128	97.77 65	79.73 179	94.82 246	93.86 259	86.91 107	91.33 90	96.76 117	85.20 32	98.06 148	96.90 32	97.60 67	98.27 66

thres200		88.92 132	87.65 143	92.73 93	96.30 96	85.62 45	97.85 66	98.86 1	84.38 159	84.82 164	93.99 186	75.12 155	98.01 149	70.86 289	86.67 193	94.56 212

cascas		86.50 180	84.48 197	92.55 101	92.64 209	85.95 37	97.04 132	95.07 189	75.32 308	80.50 215	91.02 232	54.33 316	97.98 150	86.79 149	87.62 187	93.71 225

thres100view900		88.30 151	86.95 164	92.33 110	96.10 103	84.90 65	97.14 122	98.85 2	82.69 204	83.41 181	93.66 193	75.43 145	97.93 151	69.04 297	86.24 200	94.17 214

tfpn200view9		88.48 145	87.15 158	92.47 102	96.21 99	85.30 52	97.44 98	98.85 2	83.37 186	83.99 173	93.82 189	75.36 148	97.93 151	69.04 297	86.24 200	94.17 214

gm-plane-assit					92.27 218	79.64 182			84.47 157		95.15 157		97.93 151	85.81 152

testdata				90.13 186	95.92 107	74.17 290		96.49 95	73.49 324	94.82 47	97.99 52	78.80 85	97.93 151	83.53 179	97.52 69	98.29 64

thres400		88.42 148	87.15 158	92.23 116	96.21 99	85.30 52	97.44 98	98.85 2	83.37 186	83.99 173	93.82 189	75.36 148	97.93 151	69.04 297	86.24 200	93.45 230

VDDNet		86.44 181	84.51 195	92.22 117	91.56 242	81.83 122	97.10 128	94.64 214	69.50 347	87.84 136	95.19 154	48.01 336	97.92 156	89.82 116	86.92 191	96.89 151

thisisatest0515		90.95 95	90.26 97	93.01 82	94.03 169	84.27 77	97.91 63	96.67 69	83.18 189	86.87 147	95.51 146	88.66 16	97.85 157	80.46 199	89.01 174	96.92 150

thres600view7		88.06 156	86.70 168	92.15 122	96.10 103	85.17 58	97.14 122	98.85 2	82.70 203	83.41 181	93.66 193	75.43 145	97.82 158	67.13 306	85.88 204	93.45 230

MVS_Test		90.29 108	89.18 118	93.62 59	95.23 124	84.93 64	94.41 253	94.66 211	84.31 160	90.37 106	91.02 232	75.13 154	97.82 158	83.11 184	94.42 123	98.12 75

旧先验2							96.97 138		74.06 319	96.10 27			97.76 160	88.38 133

EIA-MVS		91.73 73	92.05 68	90.78 169	94.52 148	76.40 262	98.06 55	95.34 179	89.19 60	88.90 123	97.28 96	77.56 103	97.73 161	90.77 100	96.86 88	98.20 68

SDMVSNet		87.02 171	85.61 176	91.24 153	94.14 162	83.30 94	93.88 270	95.98 139	84.30 162	79.63 227	92.01 213	58.23 283	97.68 162	90.28 113	82.02 236	92.75 233

thisisatest0530		89.65 118	89.02 120	91.53 145	93.46 184	80.78 149	96.52 166	96.67 69	81.69 221	83.79 178	94.90 166	88.85 15	97.68 162	77.80 222	87.49 190	96.14 175

BH-RMVSNet		86.84 175	85.28 182	91.49 146	95.35 121	80.26 164	96.95 140	92.21 308	82.86 200	81.77 205	95.46 147	59.34 275	97.64 164	69.79 295	93.81 132	96.57 163

1112_ss		88.60 143	87.47 152	92.00 129	93.21 188	80.97 143	96.47 169	92.46 304	83.64 183	80.86 212	97.30 94	80.24 67	97.62 165	77.60 228	85.49 208	97.40 129

casdiffmvs_mvg		91.13 90	90.45 93	93.17 76	92.99 199	83.58 88	97.46 97	94.56 219	87.69 89	87.19 144	94.98 165	74.50 165	97.60 166	91.88 90	92.79 145	98.34 58
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
Test_1112_low_res		88.03 157	86.73 166	91.94 131	93.15 191	80.88 146	96.44 172	92.41 306	83.59 185	80.74 214	91.16 230	80.18 68	97.59 167	77.48 231	85.40 209	97.36 131

tttt0517		88.57 144	88.19 134	89.71 201	93.00 196	75.99 271	95.67 212	96.67 69	80.78 232	81.82 204	94.40 175	88.97 14	97.58 168	76.05 247	86.31 197	95.57 187

ECVR-MVS		88.35 150	87.25 156	91.65 140	93.54 178	79.40 186	96.56 165	90.78 332	86.78 111	85.57 156	95.25 149	57.25 296	97.56 169	84.73 161	94.80 117	97.98 86

lupinMVS		93.87 34	93.58 38	94.75 27	93.00 196	88.08 17	99.15 7	95.50 166	91.03 37	94.90 43	97.66 72	78.84 83	97.56 169	94.64 57	97.46 70	98.62 45

XVG-OURS		85.18 202	84.38 199	87.59 243	90.42 267	71.73 316	91.06 315	94.07 248	82.00 218	83.29 183	95.08 161	56.42 303	97.55 171	83.70 175	83.42 220	93.49 229

TR-MVS		86.30 184	84.93 191	90.42 177	94.63 143	77.58 242	96.57 163	93.82 261	80.30 246	82.42 192	95.16 156	58.74 279	97.55 171	74.88 257	87.82 186	96.13 176

test_vis1_rt		73.96 318	72.40 321	78.64 343	83.91 350	61.16 366	95.63 215	68.18 393	76.32 301	60.09 364	74.77 367	29.01 382	97.54 173	87.74 138	75.94 274	77.22 377

casdiffmvs		90.95 95	90.39 94	92.63 98	92.82 203	82.53 105	96.83 147	94.47 224	87.69 89	88.47 128	95.56 145	74.04 171	97.54 173	90.90 98	92.74 146	97.83 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XVG-OURS-SEG-HR		85.74 194	85.16 186	87.49 248	90.22 269	71.45 319	91.29 312	94.09 247	81.37 223	83.90 177	95.22 151	60.30 268	97.53 175	85.58 154	84.42 215	93.50 228

baseline		90.76 98	90.10 102	92.74 92	92.90 202	82.56 104	94.60 250	94.56 219	87.69 89	89.06 122	95.67 140	73.76 174	97.51 176	90.43 108	92.23 154	98.16 71

test2506		90.96 94	90.39 94	92.65 96	93.54 178	82.46 108	96.37 177	97.35 18	86.78 111	87.55 138	95.25 149	77.83 100	97.50 177	84.07 165	94.80 117	97.98 86

ETV-MVS		92.72 54	92.87 49	92.28 114	94.54 147	81.89 119	97.98 59	95.21 184	89.77 55	93.11 66	96.83 113	77.23 111	97.50 177	95.74 43	95.38 113	97.44 126

Effi-MVS+		90.70 99	89.90 109	93.09 79	93.61 175	83.48 90	95.20 232	92.79 301	83.22 188	91.82 82	95.70 138	71.82 195	97.48 179	91.25 93	93.67 134	98.32 60

baseline2		90.39 105	90.21 99	90.93 162	90.86 258	80.99 142	95.20 232	97.41 17	86.03 120	80.07 224	94.61 171	90.58 6	97.47 180	87.29 143	89.86 168	94.35 213

diffmvs		91.17 89	90.74 87	92.44 105	93.11 195	82.50 107	96.25 185	93.62 274	87.79 86	90.40 105	95.93 132	73.44 179	97.42 181	93.62 68	92.55 148	97.41 128
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tpmvs		83.04 239	80.77 252	89.84 196	95.43 118	77.96 229	85.59 354	95.32 180	75.31 309	76.27 264	83.70 335	73.89 172	97.41 182	59.53 337	81.93 238	94.14 216

tt0805		81.20 268	79.06 276	87.61 241	86.50 315	72.97 302	93.66 273	95.48 167	74.11 317	76.23 265	91.99 215	41.36 360	97.40 183	77.44 232	74.78 281	92.45 236

test1111		88.11 155	87.04 162	91.35 148	93.15 191	78.79 204	96.57 163	90.78 332	86.88 109	85.04 160	95.20 153	57.23 297	97.39 184	83.88 168	94.59 120	97.87 93

PMMVS		89.46 122	89.92 108	88.06 231	94.64 142	69.57 332	96.22 186	94.95 192	87.27 99	91.37 89	96.54 123	65.88 232	97.39 184	88.54 129	93.89 130	97.23 136

PAPM		92.87 49	92.40 58	94.30 35	92.25 221	87.85 19	96.40 176	96.38 107	91.07 36	88.72 126	96.90 109	82.11 55	97.37 186	90.05 114	97.70 64	97.67 109

HQP4-MVS										82.30 193			97.32 187			91.13 241

HQP-MVS		87.91 161	87.55 149	88.98 211	92.08 230	78.48 209	97.63 82	94.80 202	90.52 43	82.30 193	94.56 172	65.40 236	97.32 187	87.67 140	83.01 224	91.13 241

HQP_MVS		87.50 167	87.09 161	88.74 216	91.86 239	77.96 229	97.18 115	94.69 207	89.89 53	81.33 207	94.15 182	64.77 242	97.30 189	87.08 144	82.82 228	90.96 243

plane_prior5								94.69 207					97.30 189	87.08 144	82.82 228	90.96 243

jason		92.73 52	92.23 63	94.21 40	90.50 265	87.30 26	98.65 30	95.09 187	90.61 42	92.76 71	97.13 101	75.28 152	97.30 189	93.32 72	96.75 91	98.02 79
jason: jason.
CLD-MVS		87.97 159	87.48 151	89.44 203	92.16 226	80.54 157	98.14 46	94.92 194	91.41 31	79.43 229	95.40 148	62.34 253	97.27 192	90.60 103	82.90 227	90.50 250
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OPM-MVS		85.84 191	85.10 188	88.06 231	88.34 297	77.83 236	95.72 210	94.20 240	87.89 85	80.45 217	94.05 184	58.57 280	97.26 193	83.88 168	82.76 230	89.09 282
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-w/o		88.24 153	87.47 152	90.54 175	95.03 134	78.54 208	97.41 103	93.82 261	84.08 167	78.23 239	94.51 174	69.34 215	97.21 194	80.21 204	94.58 121	95.87 180

Vis-MVSNet		88.67 140	87.82 140	91.24 153	92.68 205	78.82 201	96.95 140	93.85 260	87.55 92	87.07 146	95.13 158	63.43 248	97.21 194	77.58 229	96.15 100	97.70 108
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_vis1_n		85.60 196	85.70 175	85.33 287	84.79 340	64.98 349	96.83 147	91.61 318	87.36 97	91.00 97	94.84 167	36.14 369	97.18 196	95.66 44	93.03 143	93.82 223

AllTest		75.92 310	73.06 318	84.47 301	92.18 224	67.29 340	91.07 314	84.43 370	67.63 350	63.48 346	90.18 246	38.20 366	97.16 197	57.04 348	73.37 287	88.97 290

TestCases				84.47 301	92.18 224	67.29 340		84.43 370	67.63 350	63.48 346	90.18 246	38.20 366	97.16 197	57.04 348	73.37 287	88.97 290

ACMH	75.40 17	77.99 294	74.96 302	87.10 257	90.67 262	76.41 261	93.19 289	91.64 317	72.47 333	63.44 348	87.61 280	43.34 351	97.16 197	58.34 342	73.94 284	87.72 314
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS-test		92.98 45	93.67 35	90.90 164	96.52 94	76.87 254	98.68 28	94.73 206	90.36 48	94.84 45	97.89 62	77.94 96	97.15 200	94.28 61	97.80 62	98.70 41

ACMM	80.70 13	83.72 227	82.85 224	86.31 270	91.19 249	72.12 308	95.88 204	94.29 235	80.44 241	77.02 250	91.96 217	55.24 310	97.14 201	79.30 212	80.38 245	89.67 267
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		89.76 116	89.72 112	89.87 195	93.78 171	76.02 270	97.22 109	96.51 90	79.35 264	85.11 159	95.01 163	84.82 34	97.10 202	87.46 142	88.21 184	96.50 164

tpm cat1		83.63 228	81.38 245	90.39 178	93.53 183	78.19 224	85.56 355	95.09 187	70.78 341	78.51 236	83.28 338	74.80 159	97.03 203	66.77 307	84.05 216	95.95 177

CS-MVS		92.73 52	93.48 40	90.48 176	96.27 97	75.93 273	98.55 34	94.93 193	89.32 58	94.54 50	97.67 71	78.91 82	97.02 204	93.80 64	97.32 77	98.49 51

BH-untuned		86.95 173	85.94 173	89.99 189	94.52 148	77.46 244	96.78 152	93.37 286	81.80 219	76.62 256	93.81 191	66.64 229	97.02 204	76.06 246	93.88 131	95.48 190

sd_testset		84.62 211	83.11 219	89.17 206	94.14 162	77.78 237	91.54 311	94.38 230	84.30 162	79.63 227	92.01 213	52.28 321	96.98 206	77.67 227	82.02 236	92.75 233

LTVRE_ROB	73.68 18	77.99 294	75.74 299	84.74 294	90.45 266	72.02 310	86.41 349	91.12 324	72.57 332	66.63 335	87.27 284	54.95 313	96.98 206	56.29 352	75.98 273	85.21 349
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
TESTMET0.1,1		89.83 115	89.34 116	91.31 149	92.54 211	80.19 166	97.11 125	96.57 84	86.15 116	86.85 148	91.83 221	79.32 74	96.95 208	81.30 193	92.35 152	96.77 156

LPG-MVS_test		84.20 219	83.49 214	86.33 267	90.88 255	73.06 300	95.28 226	94.13 244	82.20 212	76.31 261	93.20 198	54.83 314	96.95 208	83.72 173	80.83 242	88.98 288

LGP-MVS_train				86.33 267	90.88 255	73.06 300		94.13 244	82.20 212	76.31 261	93.20 198	54.83 314	96.95 208	83.72 173	80.83 242	88.98 288

COLMAP_ROB	73.24 19	75.74 312	73.00 319	83.94 307	92.38 212	69.08 334	91.85 305	86.93 360	61.48 367	65.32 341	90.27 245	42.27 356	96.93 211	50.91 366	75.63 277	85.80 346
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
baseline1		88.85 135	87.49 150	92.93 86	95.21 126	86.85 29	95.47 220	94.61 216	87.29 98	83.11 186	94.99 164	80.70 62	96.89 212	82.28 188	73.72 285	95.05 199

ACMP	81.66 11	84.00 221	83.22 218	86.33 267	91.53 245	72.95 303	95.91 203	93.79 265	83.70 182	73.79 288	92.22 211	54.31 317	96.89 212	83.98 166	79.74 249	89.16 279
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CostFormer		89.08 128	88.39 131	91.15 157	93.13 193	79.15 194	88.61 331	96.11 129	83.14 190	89.58 115	86.93 291	83.83 45	96.87 214	88.22 135	85.92 203	97.42 127

EC-MVSNet		91.73 73	92.11 66	90.58 173	93.54 178	77.77 238	98.07 54	94.40 229	87.44 94	92.99 69	97.11 103	74.59 164	96.87 214	93.75 65	97.08 81	97.11 142

USDC		78.65 290	76.25 295	85.85 276	87.58 306	74.60 286	89.58 323	90.58 335	84.05 168	63.13 350	88.23 271	40.69 364	96.86 216	66.57 310	75.81 276	86.09 341

MS-PatchMatch		83.05 238	81.82 239	86.72 265	89.64 281	79.10 196	94.88 245	94.59 218	79.70 259	70.67 315	89.65 253	50.43 328	96.82 217	70.82 291	95.99 106	84.25 355

HyFIR lowres test		89.36 123	88.60 127	91.63 143	94.91 137	80.76 150	95.60 216	95.53 163	82.56 207	84.03 172	91.24 229	78.03 95	96.81 218	87.07 146	88.41 182	97.32 132

RPSCF		77.73 298	76.63 293	81.06 331	88.66 294	55.76 378	87.77 338	87.88 356	64.82 359	74.14 287	92.79 206	49.22 333	96.81 218	67.47 304	76.88 271	90.62 247

test-LLR		88.48 145	87.98 137	89.98 190	92.26 219	77.23 249	97.11 125	95.96 141	83.76 180	86.30 151	91.38 225	72.30 190	96.78 220	80.82 196	91.92 156	95.94 178

test-mter		88.95 130	88.60 127	89.98 190	92.26 219	77.23 249	97.11 125	95.96 141	85.32 132	86.30 151	91.38 225	76.37 126	96.78 220	80.82 196	91.92 156	95.94 178

tpmrst		88.36 149	87.38 154	91.31 149	94.36 156	79.92 171	87.32 341	95.26 183	85.32 132	88.34 131	86.13 307	80.60 63	96.70 222	83.78 170	85.34 211	97.30 134

Fast-Effi-MVS+		87.93 160	86.94 165	90.92 163	94.04 167	79.16 193	98.26 42	93.72 270	81.29 224	83.94 176	92.90 203	69.83 213	96.68 223	76.70 239	91.74 158	96.93 148

AUN-MVS		86.25 186	85.57 177	88.26 226	93.57 177	73.38 294	95.45 221	95.88 146	83.94 173	85.47 157	94.21 180	73.70 177	96.67 224	83.54 178	64.41 347	94.73 210

hse-mvs2		88.22 154	88.21 133	88.25 227	93.54 178	73.41 293	95.41 223	95.89 145	90.39 46	92.22 76	94.22 179	74.70 160	96.66 225	93.14 75	64.37 348	94.69 211

MDTV_nov1_ep13			83.69 207		94.09 165	81.01 141	86.78 346	96.09 130	83.81 178	84.75 165	84.32 330	74.44 166	96.54 226	63.88 322	85.07 212

XXY-MVS		83.84 224	82.00 236	89.35 204	87.13 311	81.38 134	95.72 210	94.26 236	80.15 250	75.92 271	90.63 239	61.96 259	96.52 227	78.98 216	73.28 290	90.14 256

ACMH+	76.62 16	77.47 301	74.94 303	85.05 291	91.07 253	71.58 318	93.26 286	90.01 337	71.80 336	64.76 343	88.55 265	41.62 358	96.48 228	62.35 329	71.00 299	87.09 328

GA-MVS		85.79 193	84.04 205	91.02 161	89.47 285	80.27 163	96.90 144	94.84 200	85.57 127	80.88 211	89.08 257	56.56 302	96.47 229	77.72 225	85.35 210	96.34 169

tpm2		87.35 169	86.26 170	90.62 172	92.93 201	78.67 206	88.06 336	95.99 138	79.33 265	87.40 139	86.43 302	80.28 66	96.40 230	80.23 203	85.73 207	96.79 154

dp		84.30 218	82.31 231	90.28 182	94.24 159	77.97 228	86.57 347	95.53 163	79.94 255	80.75 213	85.16 321	71.49 200	96.39 231	63.73 323	83.36 221	96.48 165

nrg030		86.79 177	85.43 179	90.87 166	88.76 290	85.34 49	97.06 131	94.33 233	84.31 160	80.45 217	91.98 216	72.36 188	96.36 232	88.48 132	71.13 298	90.93 245

CMPMVS	54.94 21	75.71 313	74.56 308	79.17 341	79.69 364	55.98 375	89.59 322	93.30 288	60.28 372	53.85 376	89.07 258	47.68 341	96.33 233	76.55 240	81.02 239	85.22 348
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VPA-MVSNet		85.32 200	83.83 206	89.77 200	90.25 268	82.63 103	96.36 178	97.07 31	83.03 195	81.21 209	89.02 259	61.58 261	96.31 234	85.02 159	70.95 300	90.36 251

XVG-ACMP-BASELINE		79.38 286	77.90 284	83.81 308	84.98 339	67.14 346	89.03 327	93.18 293	80.26 249	72.87 300	88.15 273	38.55 365	96.26 235	76.05 247	78.05 268	88.02 310

EPMVS		87.47 168	85.90 174	92.18 119	95.41 119	82.26 112	87.00 344	96.28 115	85.88 123	84.23 170	85.57 313	75.07 156	96.26 235	71.14 287	92.50 149	98.03 78

IS-MVSNet		88.67 140	88.16 135	90.20 185	93.61 175	76.86 255	96.77 154	93.07 297	84.02 169	83.62 180	95.60 143	74.69 163	96.24 237	78.43 221	93.66 135	97.49 124

GG-mvs-BLEND				93.49 66	94.94 135	86.26 33	81.62 367	97.00 33		88.32 132	94.30 177	91.23 5	96.21 238	88.49 131	97.43 73	98.00 84

dmvs_re		84.10 220	82.90 222	87.70 238	91.41 247	73.28 297	90.59 318	93.19 291	85.02 141	77.96 242	93.68 192	57.92 290	96.18 239	75.50 252	80.87 241	93.63 226

GeoE		86.36 182	85.20 183	89.83 197	93.17 190	76.13 265	97.53 90	92.11 309	79.58 261	80.99 210	94.01 185	66.60 230	96.17 240	73.48 271	89.30 171	97.20 140

gg-mvs-nofinetune		85.48 199	82.90 222	93.24 73	94.51 151	85.82 41	79.22 371	96.97 36	61.19 369	87.33 141	53.01 387	90.58 6	96.07 241	86.07 151	97.23 79	97.81 100

iter_conf_final		89.51 120	89.21 117	90.39 178	95.60 114	84.44 72	97.22 109	89.09 346	89.11 62	82.07 200	92.80 204	87.03 25	96.03 242	89.10 125	80.89 240	90.70 246

iter_conf05		90.14 110	89.79 111	91.17 156	95.85 109	86.93 28	97.68 80	88.67 353	89.93 52	81.73 206	92.80 204	90.37 8	96.03 242	90.44 107	80.65 244	90.56 248

v2v482		83.46 230	81.86 238	88.25 227	86.19 321	79.65 181	96.34 180	94.02 250	81.56 222	77.32 246	88.23 271	65.62 233	96.03 242	77.77 223	69.72 313	89.09 282

V42		83.04 239	81.53 243	87.57 245	86.27 320	79.09 197	95.87 205	94.11 246	80.35 245	77.22 248	86.79 294	65.32 238	96.02 245	77.74 224	70.14 305	87.61 318

VPNet		84.69 210	82.92 221	90.01 188	89.01 289	83.45 91	96.71 157	95.46 169	85.71 125	79.65 226	92.18 212	56.66 301	96.01 246	83.05 185	67.84 331	90.56 248

test_post											33.80 394	76.17 129	95.97 247

EI-MVSNet		85.80 192	85.20 183	87.59 243	91.55 243	77.41 245	95.13 236	95.36 176	80.43 243	80.33 219	94.71 169	73.72 175	95.97 247	76.96 237	78.64 260	89.39 269

MVSTER		89.25 127	88.92 124	90.24 183	95.98 106	84.66 68	96.79 151	95.36 176	87.19 103	80.33 219	90.61 240	90.02 12	95.97 247	85.38 156	78.64 260	90.09 260

PatchmatchNet		86.83 176	85.12 187	91.95 130	94.12 164	82.27 111	86.55 348	95.64 159	84.59 153	82.98 188	84.99 325	77.26 107	95.96 250	68.61 300	91.34 161	97.64 112
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		72.41 327	68.99 336	82.68 321	88.11 299	69.59 331	88.41 332	85.20 367	65.55 356	57.91 369	84.82 327	30.80 380	95.94 251	51.38 363	68.70 320	82.49 366

v1144		82.90 242	81.27 247	87.78 237	86.29 319	79.07 198	96.14 192	93.93 252	80.05 252	77.38 244	86.80 293	65.50 234	95.93 252	75.21 255	70.13 306	88.33 305

v144192		82.43 248	80.73 254	87.54 246	85.81 328	78.22 219	95.98 197	93.78 266	79.09 272	77.11 249	86.49 298	64.66 244	95.91 253	74.20 265	69.42 314	88.49 299

mvsmamba		85.17 203	84.54 194	87.05 258	87.94 302	75.11 281	96.22 186	87.79 357	86.91 107	78.55 235	91.77 222	64.93 241	95.91 253	86.94 148	79.80 246	90.12 257

v1192		82.31 252	80.55 258	87.60 242	85.94 325	78.47 212	95.85 207	93.80 264	79.33 265	76.97 251	86.51 297	63.33 249	95.87 255	73.11 272	70.13 306	88.46 301

v1240		81.70 260	79.83 270	87.30 253	85.50 331	77.70 241	95.48 219	93.44 280	78.46 281	76.53 257	86.44 300	60.85 265	95.84 256	71.59 281	70.17 304	88.35 304

v1921920		82.02 256	80.23 262	87.41 249	85.62 330	77.92 232	95.79 209	93.69 271	78.86 276	76.67 254	86.44 300	62.50 252	95.83 257	72.69 274	69.77 312	88.47 300

v8		81.88 258	80.06 266	87.32 251	86.63 314	79.04 199	94.41 253	93.65 273	78.77 277	73.19 297	85.57 313	66.87 227	95.81 258	73.84 269	67.61 333	87.11 327

D2MVS		82.67 245	81.55 242	86.04 275	87.77 304	76.47 259	95.21 231	96.58 83	82.66 205	70.26 318	85.46 316	60.39 267	95.80 259	76.40 243	79.18 255	85.83 345

PS-MVSNAJss		84.91 207	84.30 200	86.74 261	85.89 327	74.40 289	94.95 243	94.16 243	83.93 174	76.45 259	90.11 250	71.04 204	95.77 260	83.16 183	79.02 257	90.06 262

MVP-Stereo		82.65 246	81.67 241	85.59 284	86.10 324	78.29 216	93.33 282	92.82 300	77.75 287	69.17 325	87.98 275	59.28 276	95.76 261	71.77 279	96.88 86	82.73 363
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tfpnnormal		78.14 293	75.42 300	86.31 270	88.33 298	79.24 190	94.41 253	96.22 120	73.51 322	69.81 321	85.52 315	55.43 308	95.75 262	47.65 375	67.86 330	83.95 358

v148		82.41 251	80.89 250	86.99 259	86.18 322	76.81 256	96.27 183	93.82 261	80.49 240	75.28 280	86.11 308	67.32 224	95.75 262	75.48 253	67.03 339	88.42 303

v10		81.43 264	79.53 272	87.11 256	86.38 316	78.87 200	94.31 258	93.43 281	77.88 285	73.24 296	85.26 317	65.44 235	95.75 262	72.14 278	67.71 332	86.72 331

TAMVS		88.48 145	87.79 141	90.56 174	91.09 252	79.18 192	96.45 171	95.88 146	83.64 183	83.12 185	93.33 197	75.94 133	95.74 265	82.40 187	88.27 183	96.75 158

cl22		85.11 204	84.17 202	87.92 234	95.06 133	78.82 201	95.51 218	94.22 239	79.74 258	76.77 253	87.92 276	75.96 132	95.68 266	79.93 207	72.42 292	89.27 276

UniMVSNet_ETH3D		80.86 272	78.75 278	87.22 255	86.31 318	72.02 310	91.95 302	93.76 269	73.51 322	75.06 282	90.16 248	43.04 354	95.66 267	76.37 244	78.55 264	93.98 220

Anonymous20231211		79.72 281	77.19 289	87.33 250	95.59 115	77.16 252	95.18 235	94.18 242	59.31 377	72.57 303	86.20 306	47.89 339	95.66 267	74.53 263	69.24 317	89.18 278

CHOSEN 280x420		91.71 76	91.85 69	91.29 151	94.94 135	82.69 102	87.89 337	96.17 125	85.94 121	87.27 142	94.31 176	90.27 9	95.65 269	94.04 63	95.86 107	95.53 188

CDS-MVSNet		89.50 121	88.96 122	91.14 158	91.94 238	80.93 145	97.09 129	95.81 150	84.26 165	84.72 166	94.20 181	80.31 65	95.64 270	83.37 181	88.96 175	96.85 153
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		71.36 333	67.00 338	84.46 303	90.58 263	69.74 330	79.15 372	87.74 358	46.09 384	61.96 357	50.50 388	45.14 346	95.64 270	53.74 359	88.11 185	88.00 311

v7n		79.32 287	77.34 287	85.28 288	84.05 349	72.89 304	93.38 280	93.87 258	75.02 312	70.68 314	84.37 329	59.58 272	95.62 272	67.60 302	67.50 334	87.32 326

Effi-MVS+-dtu		84.61 212	84.90 192	83.72 312	91.96 236	63.14 359	94.95 243	93.34 287	85.57 127	79.79 225	87.12 288	61.99 258	95.61 273	83.55 177	85.83 205	92.41 237

JIA-IIPM		79.00 289	77.20 288	84.40 304	89.74 280	64.06 354	75.30 381	95.44 171	62.15 363	81.90 202	59.08 385	78.92 81	95.59 274	66.51 311	85.78 206	93.54 227

Fast-Effi-MVS+-dtu		83.33 232	82.60 228	85.50 285	89.55 283	69.38 333	96.09 195	91.38 319	82.30 211	75.96 270	91.41 224	56.71 299	95.58 275	75.13 256	84.90 213	91.54 239

EG-PatchMatch MVS		74.92 315	72.02 322	83.62 313	83.76 353	73.28 297	93.62 275	92.04 311	68.57 349	58.88 366	83.80 334	31.87 378	95.57 276	56.97 350	78.67 259	82.00 369

UniMVSNet (Re)		85.31 201	84.23 201	88.55 219	89.75 278	80.55 155	96.72 155	96.89 42	85.42 130	78.40 237	88.93 260	75.38 147	95.52 277	78.58 219	68.02 328	89.57 268

OpenMVS_ROB	68.52 20	73.02 325	69.57 332	83.37 316	80.54 362	71.82 314	93.60 276	88.22 354	62.37 362	61.98 356	83.15 339	35.31 373	95.47 278	45.08 378	75.88 275	82.82 361

miper_enhance_ethall		85.95 190	85.20 183	88.19 230	94.85 139	79.76 175	96.00 196	94.06 249	82.98 197	77.74 243	88.76 262	79.42 73	95.46 279	80.58 198	72.42 292	89.36 274

patchmatchnet-post											77.09 364	77.78 101	95.39 280

SCA		85.63 195	83.64 210	91.60 144	92.30 217	81.86 121	92.88 293	95.56 162	84.85 144	82.52 189	85.12 323	58.04 285	95.39 280	73.89 267	87.58 189	97.54 117

jajsoiax		82.12 255	81.15 249	85.03 292	84.19 346	70.70 322	94.22 263	93.95 251	83.07 193	73.48 290	89.75 252	49.66 332	95.37 282	82.24 189	79.76 247	89.02 286

mvs_anonymous		88.68 139	87.62 146	91.86 133	94.80 140	81.69 129	93.53 278	94.92 194	82.03 217	78.87 234	90.43 243	75.77 135	95.34 283	85.04 158	93.16 142	98.55 49

ITE_SJBPF				82.38 323	87.00 312	65.59 348		89.55 340	79.99 254	69.37 323	91.30 227	41.60 359	95.33 284	62.86 328	74.63 283	86.24 338

eth_miper_zixun_eth		83.12 237	82.01 235	86.47 266	91.85 241	74.80 283	94.33 257	93.18 293	79.11 271	75.74 276	87.25 286	72.71 184	95.32 285	76.78 238	67.13 337	89.27 276

mvs_tets		81.74 259	80.71 255	84.84 293	84.22 345	70.29 325	93.91 269	93.78 266	82.77 202	73.37 293	89.46 255	47.36 342	95.31 286	81.99 190	79.55 253	88.92 292

FIs		86.73 179	86.10 172	88.61 218	90.05 274	80.21 165	96.14 192	96.95 38	85.56 129	78.37 238	92.30 210	76.73 119	95.28 287	79.51 209	79.27 254	90.35 252

pm-mvs1		80.05 278	78.02 283	86.15 273	85.42 332	75.81 275	95.11 238	92.69 303	77.13 295	70.36 317	87.43 281	58.44 282	95.27 288	71.36 283	64.25 349	87.36 325

miper_ehance_all_eth		84.57 213	83.60 212	87.50 247	92.64 209	78.25 218	95.40 224	93.47 279	79.28 268	76.41 260	87.64 279	76.53 121	95.24 289	78.58 219	72.42 292	89.01 287

ADS-MVSNet		81.26 266	78.36 279	89.96 192	93.78 171	79.78 174	79.48 369	93.60 275	73.09 327	80.14 221	79.99 354	62.15 255	95.24 289	59.49 338	83.52 218	94.85 204

cl____		83.27 233	82.12 233	86.74 261	92.20 222	75.95 272	95.11 238	93.27 289	78.44 282	74.82 283	87.02 290	74.19 168	95.19 291	74.67 260	69.32 315	89.09 282

DIV-MVS_self_test		83.27 233	82.12 233	86.74 261	92.19 223	75.92 274	95.11 238	93.26 290	78.44 282	74.81 284	87.08 289	74.19 168	95.19 291	74.66 261	69.30 316	89.11 281

IterMVS-LS		83.93 222	82.80 225	87.31 252	91.46 246	77.39 246	95.66 213	93.43 281	80.44 241	75.51 277	87.26 285	73.72 175	95.16 293	76.99 235	70.72 302	89.39 269
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_NR-MVSNet		85.49 198	84.59 193	88.21 229	89.44 286	79.36 187	96.71 157	96.41 102	85.22 135	78.11 240	90.98 234	76.97 114	95.14 294	79.14 214	68.30 325	90.12 257

DU-MVS		84.57 213	83.33 216	88.28 225	88.76 290	79.36 187	96.43 174	95.41 175	85.42 130	78.11 240	90.82 236	67.61 218	95.14 294	79.14 214	68.30 325	90.33 253

c3_l		83.80 225	82.65 227	87.25 254	92.10 229	77.74 240	95.25 229	93.04 298	78.58 279	76.01 268	87.21 287	75.25 153	95.11 296	77.54 230	68.89 319	88.91 293

MVSFormer		91.36 84	90.57 90	93.73 54	93.00 196	88.08 17	94.80 248	94.48 222	80.74 233	94.90 43	97.13 101	78.84 83	95.10 297	83.77 171	97.46 70	98.02 79

test_djsdf		83.00 241	82.45 230	84.64 298	84.07 348	69.78 329	94.80 248	94.48 222	80.74 233	75.41 279	87.70 278	61.32 264	95.10 297	83.77 171	79.76 247	89.04 285

RRT_MVS		83.88 223	83.27 217	85.71 279	87.53 309	72.12 308	95.35 225	94.33 233	83.81 178	75.86 272	91.28 228	60.55 266	95.09 299	83.93 167	76.76 272	89.90 265

test_post1							85.88 353				30.24 397	73.77 173	95.07 300	73.89 267

pmmvs4		82.54 247	80.79 251	87.79 236	86.11 323	80.49 159	93.55 277	93.18 293	77.29 293	73.35 294	89.40 256	65.26 239	95.05 301	75.32 254	73.61 286	87.83 313

anonymousdsp		80.98 271	79.97 267	84.01 306	81.73 358	70.44 324	92.49 297	93.58 277	77.10 297	72.98 299	86.31 304	57.58 291	94.90 302	79.32 211	78.63 262	86.69 332

NR-MVSNet		83.35 231	81.52 244	88.84 213	88.76 290	81.31 136	94.45 252	95.16 185	84.65 151	67.81 327	90.82 236	70.36 210	94.87 303	74.75 258	66.89 340	90.33 253

WR-MVS		84.32 217	82.96 220	88.41 221	89.38 287	80.32 160	96.59 162	96.25 117	83.97 171	76.63 255	90.36 244	67.53 221	94.86 304	75.82 250	70.09 309	90.06 262

pmmvs6		74.65 317	71.67 323	83.60 314	79.13 366	69.94 327	93.31 285	90.88 331	61.05 371	65.83 339	84.15 332	43.43 350	94.83 305	66.62 308	60.63 358	86.02 342

FC-MVSNet-test		85.96 189	85.39 180	87.66 240	89.38 287	78.02 226	95.65 214	96.87 43	85.12 139	77.34 245	91.94 219	76.28 128	94.74 306	77.09 234	78.82 258	90.21 255

Vis-MVSNet (Re-imp)		88.88 134	88.87 125	88.91 212	93.89 170	74.43 288	96.93 142	94.19 241	84.39 158	83.22 184	95.67 140	78.24 91	94.70 307	78.88 217	94.40 124	97.61 115

tpm		85.55 197	84.47 198	88.80 215	90.19 270	75.39 278	88.79 329	94.69 207	84.83 145	83.96 175	85.21 319	78.22 92	94.68 308	76.32 245	78.02 269	96.34 169

TranMVSNet+NR-MVSNet		83.24 235	81.71 240	87.83 235	87.71 305	78.81 203	96.13 194	94.82 201	84.52 154	76.18 267	90.78 238	64.07 245	94.60 309	74.60 262	66.59 342	90.09 260

bld_raw_dy_0_64		82.13 254	80.76 253	86.24 272	85.78 329	75.03 282	94.40 256	82.62 377	83.12 191	76.46 258	90.96 235	53.83 318	94.55 310	81.04 195	78.60 263	89.14 280

Patchmatch-test		78.25 292	74.72 306	88.83 214	91.20 248	74.10 291	73.91 384	88.70 352	59.89 375	66.82 333	85.12 323	78.38 89	94.54 311	48.84 373	79.58 252	97.86 94

mvsany_test1		87.58 166	88.22 132	85.67 281	89.78 277	67.18 342	95.25 229	87.93 355	83.96 172	88.79 124	97.06 106	72.52 186	94.53 312	92.21 85	86.45 196	95.30 195

FMVSNet3		84.71 209	82.71 226	90.70 171	94.55 146	87.71 21	95.92 201	94.67 210	81.73 220	75.82 273	88.08 274	66.99 226	94.47 313	71.23 284	75.38 278	89.91 264

pmmvs5		81.34 265	79.54 271	86.73 264	85.02 338	76.91 253	96.22 186	91.65 316	77.65 288	73.55 289	88.61 264	55.70 307	94.43 314	74.12 266	73.35 289	88.86 294

Baseline_NR-MVSNet		81.22 267	80.07 265	84.68 296	85.32 336	75.12 280	96.48 168	88.80 349	76.24 304	77.28 247	86.40 303	67.61 218	94.39 315	75.73 251	66.73 341	84.54 352

FMVSNet2		82.79 243	80.44 259	89.83 197	92.66 206	85.43 48	95.42 222	94.35 231	79.06 273	74.46 285	87.28 283	56.38 304	94.31 316	69.72 296	74.68 282	89.76 266

SixPastTwentyTwo		76.04 309	74.32 310	81.22 329	84.54 342	61.43 365	91.16 313	89.30 344	77.89 284	64.04 345	86.31 304	48.23 334	94.29 317	63.54 325	63.84 351	87.93 312

TDRefinement		69.20 338	65.78 342	79.48 338	66.04 388	62.21 361	88.21 333	86.12 364	62.92 361	61.03 361	85.61 312	33.23 375	94.16 318	55.82 355	53.02 371	82.08 368

TransMVSNet (Re)		76.94 305	74.38 309	84.62 299	85.92 326	75.25 279	95.28 226	89.18 345	73.88 320	67.22 328	86.46 299	59.64 270	94.10 319	59.24 341	52.57 373	84.50 353

OurMVSNet-221017-0		77.18 304	76.06 296	80.55 334	83.78 352	60.00 369	90.35 319	91.05 327	77.01 299	66.62 336	87.92 276	47.73 340	94.03 320	71.63 280	68.44 323	87.62 317

EPNet_dtu		87.65 165	87.89 138	86.93 260	94.57 144	71.37 320	96.72 155	96.50 92	88.56 70	87.12 145	95.02 162	75.91 134	94.01 321	66.62 308	90.00 166	95.42 191
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lessismore_v0				79.98 336	80.59 361	58.34 372		80.87 379		58.49 367	83.46 337	43.10 353	93.89 322	63.11 327	48.68 377	87.72 314

GBi-Net		82.42 249	80.43 260	88.39 222	92.66 206	81.95 114	94.30 259	93.38 283	79.06 273	75.82 273	85.66 309	56.38 304	93.84 323	71.23 284	75.38 278	89.38 271

test1		82.42 249	80.43 260	88.39 222	92.66 206	81.95 114	94.30 259	93.38 283	79.06 273	75.82 273	85.66 309	56.38 304	93.84 323	71.23 284	75.38 278	89.38 271

FMVSNet1		79.50 284	76.54 294	88.39 222	88.47 295	81.95 114	94.30 259	93.38 283	73.14 326	72.04 307	85.66 309	43.86 348	93.84 323	65.48 315	72.53 291	89.38 271

test_0402		72.68 326	69.54 333	82.09 326	88.67 293	71.81 315	92.72 295	86.77 362	61.52 366	62.21 355	83.91 333	43.22 352	93.76 326	34.60 385	72.23 295	80.72 373

CR-MVSNet		83.53 229	81.36 246	90.06 187	90.16 271	79.75 176	79.02 373	91.12 324	84.24 166	82.27 197	80.35 352	75.45 143	93.67 327	63.37 326	86.25 198	96.75 158

ET-MVSNet_ETH3D		90.01 112	89.03 119	92.95 84	94.38 155	86.77 30	98.14 46	96.31 114	89.30 59	63.33 349	96.72 120	90.09 11	93.63 328	90.70 102	82.29 235	98.46 53

Patchmtry		77.36 302	74.59 307	85.67 281	89.75 278	75.75 276	77.85 376	91.12 324	60.28 372	71.23 310	80.35 352	75.45 143	93.56 329	57.94 343	67.34 336	87.68 316

test_fmvs2		79.59 282	79.90 269	78.67 342	82.86 355	55.82 377	95.20 232	89.55 340	81.09 226	80.12 223	89.80 251	34.31 374	93.51 330	87.82 137	78.36 266	86.69 332

miper_lstm_enhance		81.66 262	80.66 256	84.67 297	91.19 249	71.97 312	91.94 303	93.19 291	77.86 286	72.27 305	85.26 317	73.46 178	93.42 331	73.71 270	67.05 338	88.61 295

PatchT		79.75 280	76.85 292	88.42 220	89.55 283	75.49 277	77.37 377	94.61 216	63.07 360	82.46 191	73.32 373	75.52 142	93.41 332	51.36 364	84.43 214	96.36 167

ppachtmachnet_test		77.19 303	74.22 311	86.13 274	85.39 333	78.22 219	93.98 266	91.36 321	71.74 337	67.11 330	84.87 326	56.67 300	93.37 333	52.21 362	64.59 346	86.80 330

our_test_3		77.90 297	75.37 301	85.48 286	85.39 333	76.74 257	93.63 274	91.67 315	73.39 325	65.72 340	84.65 328	58.20 284	93.13 334	57.82 344	67.87 329	86.57 334

LCM-MVSNet-Re		83.75 226	83.54 213	84.39 305	93.54 178	64.14 353	92.51 296	84.03 372	83.90 175	66.14 338	86.59 296	67.36 223	92.68 335	84.89 160	92.87 144	96.35 168

WR-MVS_H		81.02 269	80.09 263	83.79 309	88.08 300	71.26 321	94.46 251	96.54 87	80.08 251	72.81 301	86.82 292	70.36 210	92.65 336	64.18 320	67.50 334	87.46 324

ambc				76.02 352	68.11 385	51.43 381	64.97 389	89.59 339		60.49 362	74.49 369	17.17 388	92.46 337	61.50 332	52.85 372	84.17 356

PEN-MVS		79.47 285	78.26 281	83.08 318	86.36 317	68.58 336	93.85 271	94.77 205	79.76 257	71.37 308	88.55 265	59.79 269	92.46 337	64.50 319	65.40 344	88.19 307

CP-MVSNet		81.01 270	80.08 264	83.79 309	87.91 303	70.51 323	94.29 262	95.65 158	80.83 230	72.54 304	88.84 261	63.71 246	92.32 339	68.58 301	68.36 324	88.55 296

LF4IMVS		72.36 328	70.82 326	76.95 348	79.18 365	56.33 374	86.12 351	86.11 365	69.30 348	63.06 351	86.66 295	33.03 376	92.25 340	65.33 316	68.64 321	82.28 367

PS-CasMVS		80.27 277	79.18 273	83.52 315	87.56 307	69.88 328	94.08 265	95.29 181	80.27 248	72.08 306	88.51 268	59.22 277	92.23 341	67.49 303	68.15 327	88.45 302

DTE-MVSNet		78.37 291	77.06 290	82.32 325	85.22 337	67.17 345	93.40 279	93.66 272	78.71 278	70.53 316	88.29 270	59.06 278	92.23 341	61.38 333	63.28 353	87.56 320

UnsupCasMVSNet_bld		68.60 340	64.50 344	80.92 332	74.63 379	67.80 338	83.97 361	92.94 299	65.12 358	54.63 375	68.23 381	35.97 370	92.17 343	60.13 336	44.83 382	82.78 362

KD-MVS_2432*1600		77.63 299	74.92 304	85.77 277	90.86 258	79.44 184	88.08 334	93.92 254	76.26 302	67.05 331	82.78 340	72.15 192	91.92 344	61.53 330	41.62 387	85.94 343

miper_refine_blended		77.63 299	74.92 304	85.77 277	90.86 258	79.44 184	88.08 334	93.92 254	76.26 302	67.05 331	82.78 340	72.15 192	91.92 344	61.53 330	41.62 387	85.94 343

test_vis3_rt		54.10 351	51.04 354	63.27 368	58.16 391	46.08 389	84.17 360	49.32 403	56.48 382	36.56 387	49.48 390	8.03 399	91.91 346	67.29 305	49.87 375	51.82 389

N_pmnet		61.30 345	60.20 348	64.60 365	84.32 344	17.00 406	91.67 309	10.98 404	61.77 365	58.45 368	78.55 358	49.89 331	91.83 347	42.27 381	63.94 350	84.97 350

K. test v3		73.62 319	71.59 324	79.69 337	82.98 354	59.85 370	90.85 317	88.83 348	77.13 295	58.90 365	82.11 342	43.62 349	91.72 348	65.83 314	54.10 368	87.50 323

Patchmatch-RL test		76.65 307	74.01 314	84.55 300	77.37 372	64.23 352	78.49 375	82.84 376	78.48 280	64.63 344	73.40 372	76.05 131	91.70 349	76.99 235	57.84 362	97.72 105

IterMVS-SCA-FT		80.51 276	79.10 275	84.73 295	89.63 282	74.66 284	92.98 291	91.81 314	80.05 252	71.06 313	85.18 320	58.04 285	91.40 350	72.48 277	70.70 303	88.12 309

IterMVS		80.67 274	79.16 274	85.20 289	89.79 276	76.08 266	92.97 292	91.86 312	80.28 247	71.20 311	85.14 322	57.93 289	91.34 351	72.52 276	70.74 301	88.18 308
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDA-MVSNet-bldmvs		71.45 332	67.94 337	81.98 327	85.33 335	68.50 337	92.35 300	88.76 350	70.40 342	42.99 383	81.96 343	46.57 343	91.31 352	48.75 374	54.39 367	86.11 340

pmmvs-eth3d		73.59 320	70.66 327	82.38 323	76.40 376	73.38 294	89.39 326	89.43 342	72.69 331	60.34 363	77.79 360	46.43 344	91.26 353	66.42 312	57.06 363	82.51 364

PM-MVS		69.32 337	66.93 339	76.49 350	73.60 380	55.84 376	85.91 352	79.32 383	74.72 314	61.09 360	78.18 359	21.76 385	91.10 354	70.86 289	56.90 364	82.51 364

Anonymous20240521		72.06 330	69.91 331	78.50 344	77.11 373	61.67 364	91.62 310	90.97 329	65.52 357	62.37 354	79.05 357	36.32 368	90.96 355	57.75 345	68.52 322	82.87 360

Anonymous20231206		75.29 314	73.64 315	80.22 335	80.75 359	63.38 358	93.36 281	90.71 334	73.09 327	67.12 329	83.70 335	50.33 329	90.85 356	53.63 360	70.10 308	86.44 335

MIMVSNet		79.18 288	75.99 297	88.72 217	87.37 310	80.66 152	79.96 368	91.82 313	77.38 292	74.33 286	81.87 344	41.78 357	90.74 357	66.36 313	83.10 223	94.76 206

UnsupCasMVSNet_eth		73.25 323	70.57 328	81.30 328	77.53 370	66.33 347	87.24 342	93.89 257	80.38 244	57.90 370	81.59 345	42.91 355	90.56 358	65.18 317	48.51 378	87.01 329

YYNet1		73.53 322	70.43 329	82.85 320	84.52 343	71.73 316	91.69 308	91.37 320	67.63 350	46.79 379	81.21 348	55.04 312	90.43 359	55.93 353	59.70 360	86.38 336

MDA-MVSNet_test_wron		73.54 321	70.43 329	82.86 319	84.55 341	71.85 313	91.74 307	91.32 323	67.63 350	46.73 380	81.09 349	55.11 311	90.42 360	55.91 354	59.76 359	86.31 337

CVMVSNet		84.83 208	85.57 177	82.63 322	91.55 243	60.38 367	95.13 236	95.03 190	80.60 236	82.10 199	94.71 169	66.40 231	90.19 361	74.30 264	90.32 165	97.31 133

ADS-MVSNet2		79.57 283	77.53 286	85.71 279	93.78 171	72.13 307	79.48 369	86.11 365	73.09 327	80.14 221	79.99 354	62.15 255	90.14 362	59.49 338	83.52 218	94.85 204

CL-MVSNet_self_test		75.81 311	74.14 313	80.83 333	78.33 368	67.79 339	94.22 263	93.52 278	77.28 294	69.82 320	81.54 346	61.47 263	89.22 363	57.59 346	53.51 369	85.48 347

test0.0.03 1		82.79 243	82.48 229	83.74 311	86.81 313	72.22 305	96.52 166	95.03 190	83.76 180	73.00 298	93.20 198	72.30 190	88.88 364	64.15 321	77.52 270	90.12 257

testgi		74.88 316	73.40 316	79.32 340	80.13 363	61.75 362	93.21 287	86.64 363	79.49 263	66.56 337	91.06 231	35.51 372	88.67 365	56.79 351	71.25 297	87.56 320

KD-MVS_self_test		70.97 334	69.31 334	75.95 354	76.24 378	55.39 379	87.45 339	90.94 330	70.20 344	62.96 353	77.48 361	44.01 347	88.09 366	61.25 334	53.26 370	84.37 354

new_pmnet		66.18 342	63.18 345	75.18 356	76.27 377	61.74 363	83.79 362	84.66 369	56.64 381	51.57 377	71.85 379	31.29 379	87.93 367	49.98 369	62.55 354	75.86 378

Syy-MVS		77.97 296	78.05 282	77.74 346	92.13 227	56.85 373	93.97 267	94.23 237	82.43 208	73.39 291	93.57 195	57.95 288	87.86 368	32.40 386	82.34 233	88.51 297

myMVS_eth3d		81.93 257	82.18 232	81.18 330	92.13 227	67.18 342	93.97 267	94.23 237	82.43 208	73.39 291	93.57 195	76.98 113	87.86 368	50.53 368	82.34 233	88.51 297

mvsany_test3		67.19 341	65.34 343	72.72 357	63.08 389	48.57 383	83.12 364	78.09 384	72.07 334	61.21 359	77.11 363	22.94 384	87.78 370	78.59 218	51.88 374	81.80 370

FMVSNet5		76.46 308	74.16 312	83.35 317	90.05 274	76.17 264	89.58 323	89.85 338	71.39 339	65.29 342	80.42 351	50.61 327	87.70 371	61.05 335	69.24 317	86.18 339

EU-MVSNet		76.92 306	76.95 291	76.83 349	84.10 347	54.73 380	91.77 306	92.71 302	72.74 330	69.57 322	88.69 263	58.03 287	87.43 372	64.91 318	70.00 310	88.33 305

testing3		80.74 273	81.17 248	79.44 339	91.15 251	63.48 357	97.16 119	95.76 152	80.83 230	71.36 309	93.15 201	78.22 92	87.30 373	43.19 380	79.67 250	87.55 322

new-patchmatchnet		68.85 339	65.93 341	77.61 347	73.57 381	63.94 355	90.11 321	88.73 351	71.62 338	55.08 374	73.60 371	40.84 362	87.22 374	51.35 365	48.49 379	81.67 372

DSMNet-mixed		73.13 324	72.45 320	75.19 355	77.51 371	46.82 385	85.09 357	82.01 378	67.61 354	69.27 324	81.33 347	50.89 325	86.28 375	54.54 357	83.80 217	92.46 235

pmmvs3		65.75 343	62.18 346	76.45 351	67.12 387	64.54 350	88.68 330	85.05 368	54.77 383	57.54 372	73.79 370	29.40 381	86.21 376	55.49 356	47.77 380	78.62 375

MIMVSNet1		69.44 336	66.65 340	77.84 345	76.48 375	62.84 360	87.42 340	88.97 347	66.96 355	57.75 371	79.72 356	32.77 377	85.83 377	46.32 376	63.42 352	84.85 351

test20.03		72.36 328	71.15 325	75.98 353	77.79 369	59.16 371	92.40 299	89.35 343	74.09 318	61.50 358	84.32 330	48.09 335	85.54 378	50.63 367	62.15 356	83.24 359

test_f		64.01 344	62.13 347	69.65 359	63.00 390	45.30 390	83.66 363	80.68 380	61.30 368	55.70 373	72.62 375	14.23 391	84.64 379	69.84 294	58.11 361	79.00 374

EGC-MVSNET		52.46 353	47.56 356	67.15 361	81.98 357	60.11 368	82.54 366	72.44 389	0.11 401	0.70 402	74.59 368	25.11 383	83.26 380	29.04 388	61.51 357	58.09 386

test_fmvs3		69.56 335	69.19 335	70.67 358	69.01 383	47.05 384	90.87 316	86.81 361	71.31 340	66.79 334	77.15 362	16.40 389	83.17 381	81.84 191	62.51 355	81.79 371

APD_test1		56.56 348	53.58 352	65.50 362	67.93 386	46.51 387	77.24 379	72.95 388	38.09 386	42.75 384	75.17 366	13.38 392	82.78 382	40.19 383	54.53 366	67.23 383

dmvs_testset		72.00 331	73.36 317	67.91 360	83.83 351	31.90 400	85.30 356	77.12 385	82.80 201	63.05 352	92.46 209	61.54 262	82.55 383	42.22 382	71.89 296	89.29 275

DeepMVS_CX				64.06 366	78.53 367	43.26 391		68.11 395	69.94 345	38.55 385	76.14 365	18.53 387	79.34 384	43.72 379	41.62 387	69.57 381

WB-MVS		57.26 346	56.22 349	60.39 371	69.29 382	35.91 398	86.39 350	70.06 391	59.84 376	46.46 381	72.71 374	51.18 324	78.11 385	15.19 395	34.89 390	67.14 384

SSC-MVS		56.01 349	54.96 350	59.17 372	68.42 384	34.13 399	84.98 358	69.23 392	58.08 380	45.36 382	71.67 380	50.30 330	77.46 386	14.28 396	32.33 391	65.91 385

FPMVS		55.09 350	52.93 353	61.57 369	55.98 392	40.51 394	83.11 365	83.41 375	37.61 387	34.95 388	71.95 377	14.40 390	76.95 387	29.81 387	65.16 345	67.25 382

LCM-MVSNet		52.52 352	48.24 355	65.35 363	47.63 399	41.45 392	72.55 385	83.62 374	31.75 388	37.66 386	57.92 386	9.19 398	76.76 388	49.26 371	44.60 383	77.84 376

Gipuma		45.11 358	42.05 360	54.30 375	80.69 360	51.30 382	35.80 393	83.81 373	28.13 389	27.94 393	34.53 393	11.41 396	76.70 389	21.45 392	54.65 365	34.90 393
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		50.90 354	46.31 357	64.67 364	55.53 393	46.67 386	77.30 378	71.02 390	40.89 385	34.16 389	59.32 384	9.83 397	76.14 390	40.09 384	28.63 392	71.21 379

PMVS	34.80 23	39.19 360	35.53 363	50.18 376	29.72 402	30.30 401	59.60 391	66.20 396	26.06 392	17.91 396	49.53 389	3.12 402	74.09 391	18.19 394	49.40 376	46.14 390
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 356	42.41 358	55.58 373	53.29 396	40.02 395	68.96 387	62.67 397	27.45 390	29.85 390	61.58 382	5.98 400	73.83 392	28.49 390	43.46 385	52.90 387

APD_test2		45.70 356	42.41 358	55.58 373	53.29 396	40.02 395	68.96 387	62.67 397	27.45 390	29.85 390	61.58 382	5.98 400	73.83 392	28.49 390	43.46 385	52.90 387

ANet_high		46.22 355	41.28 362	61.04 370	39.91 401	46.25 388	70.59 386	76.18 386	58.87 378	23.09 394	48.00 391	12.58 394	66.54 394	28.65 389	13.62 395	70.35 380

test_method		56.77 347	54.53 351	63.49 367	76.49 374	40.70 393	75.68 380	74.24 387	19.47 395	48.73 378	71.89 378	19.31 386	65.80 395	57.46 347	47.51 381	83.97 357

MVE	35.65 22	33.85 361	29.49 366	46.92 377	41.86 400	36.28 397	50.45 392	56.52 400	18.75 396	18.28 395	37.84 392	2.41 403	58.41 396	18.71 393	20.62 393	46.06 391
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 362	32.39 364	33.65 379	53.35 395	25.70 403	74.07 383	53.33 401	21.08 393	17.17 397	33.63 395	11.85 395	54.84 397	12.98 397	14.04 394	20.42 394

EMVS		31.70 363	31.45 365	32.48 380	50.72 398	23.95 404	74.78 382	52.30 402	20.36 394	16.08 398	31.48 396	12.80 393	53.60 398	11.39 398	13.10 397	19.88 395

tmp_tt		41.54 359	41.93 361	40.38 378	20.10 403	26.84 402	61.93 390	59.09 399	14.81 397	28.51 392	80.58 350	35.53 371	48.33 399	63.70 324	13.11 396	45.96 392

wuyk23d		14.10 365	13.89 368	14.72 381	55.23 394	22.91 405	33.83 394	3.56 405	4.94 398	4.11 399	2.28 401	2.06 404	19.66 400	10.23 399	8.74 398	1.59 398

test123		9.07 367	11.73 370	1.11 382	0.50 405	0.77 407	89.44 325	0.20 407	0.34 400	2.15 401	10.72 400	0.34 405	0.32 401	1.79 401	0.08 400	2.23 396

testmvs		9.92 366	12.94 369	0.84 383	0.65 404	0.29 408	93.78 272	0.39 406	0.42 399	2.85 400	15.84 399	0.17 406	0.30 402	2.18 400	0.21 399	1.91 397

test_blank		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet_test		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

DCPMVS		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

cdsmvs_eth3d_5k		21.43 364	28.57 367	0.00 384	0.00 406	0.00 409	0.00 395	95.93 144	0.00 402	0.00 403	97.66 72	63.57 247	0.00 403	0.00 402	0.00 401	0.00 399

pcd_1.5k_mvsjas		5.92 369	7.89 372	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	71.04 204	0.00 403	0.00 402	0.00 401	0.00 399

sosnet-low-res		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

sosnet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uncertanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

Regformer		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

ab-mvs-re		8.11 368	10.81 371	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	97.30 94	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

uanet		0.00 370	0.00 373	0.00 384	0.00 406	0.00 409	0.00 395	0.00 408	0.00 402	0.00 403	0.00 402	0.00 407	0.00 403	0.00 402	0.00 401	0.00 399

WAC-MVS						67.18 342								49.00 372

FOURS1					98.51 39	78.01 227	98.13 49	96.21 121	83.04 194	94.39 51

test_one_0601					98.91 18	84.56 71		96.70 65	88.06 79	96.57 22	98.77 10	88.04 20

eth-test2					0.00 406

eth-test					0.00 406

RE-MVS-def			91.18 82		97.76 67	76.03 268	96.20 189	95.44 171	80.56 238	90.72 100	97.84 64	73.36 180		91.99 88	96.79 89	97.75 103

IU-MVS					99.03 15	85.34 49		96.86 45	92.05 27	98.74 1				98.15 11	98.97 17	99.42 13

save fliter					98.24 51	83.34 93	98.61 33	96.57 84	91.32 32

test0726					99.05 9	85.18 54	99.11 14	96.78 49	88.75 64	97.65 11	98.91 2	87.69 22

GSMVS																97.54 117

test_part2					98.90 19	85.14 60				96.07 28

sam_mvs1												77.59 102				97.54 117

sam_mvs												75.35 150

MTGPA								96.33 112

MTMP							97.53 90	68.16 394

test9_res														96.00 39	99.03 13	98.31 62

agg_prior2														94.30 58	99.00 15	98.57 46

test_prior4						82.34 110	97.75 75

test_prior2							98.37 39		86.08 119	94.57 49	98.02 51	83.14 48		95.05 51	98.79 26

新几何2							96.42 175

旧先验1					97.39 82	79.58 183		96.54 87			98.08 48	84.00 42			97.42 74	97.62 114

原ACMM2							96.84 146

test222					96.15 101	78.41 213	95.87 205	96.46 96	71.97 335	89.66 113	97.45 85	76.33 127			98.24 49	98.30 63

segment_acmp												82.69 53

testdata1							95.57 217		87.44 94

plane_prior7					91.86 239	77.55 243

plane_prior6					91.98 235	77.92 232						64.77 242

plane_prior4											94.15 182

plane_prior3						77.75 239			90.17 50	81.33 207

plane_prior2							97.18 115		89.89 53

plane_prior1					91.95 237

plane_prior						77.96 229	97.52 93		90.36 48						82.96 226

n2								0.00 408

nn								0.00 408

door-mid								79.75 382

test11								96.50 92

door								80.13 381

HQP5-MVS						78.48 209

HQP-NCC					92.08 230		97.63 82		90.52 43	82.30 193

ACMP_Plane					92.08 230		97.63 82		90.52 43	82.30 193

BP-MVS														87.67 140

HQP3-MVS								94.80 202							83.01 224

HQP2-MVS												65.40 236

NP-MVS					92.04 234	78.22 219					94.56 172

MDTV_nov1_ep13_2view						81.74 126	86.80 345		80.65 235	85.65 155		74.26 167		76.52 241		96.98 146

ACMMP++_ref															78.45 265

ACMMP++															79.05 256

Test By Simon												71.65 197

High-resolution multi-view benchmark