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 11	98.26 1	96.26 98	95.09 1	99.15 4	96.98 30	93.39 10	96.45 18	98.79 8	90.17 10	99.99 1	89.33 108	99.25 6	99.70 3

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 9	98.94 16	97.10 26	95.17 2	92.11 66	98.46 22	87.33 24	99.97 2	97.21 17	99.31 4	99.63 7

CNVR-MVS		96.30 1	96.54 1	95.55 13	99.31 5	87.69 20	99.06 10	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

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 32	99.10 9	99.00 26

API-MVS		90.18 97	88.97 108	93.80 47	98.66 28	82.95 95	97.50 80	95.63 148	75.16 289	86.31 136	97.69 58	72.49 173	99.90 5	81.26 179	96.07 95	98.56 46

DeepC-MVS_fast	89.06 2	94.48 19	94.30 23	95.02 18	98.86 21	85.68 42	98.06 43	96.64 70	93.64 9	91.74 71	98.54 18	80.17 64	99.90 5	92.28 70	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 64	90.85 73	94.34 32	99.50 1	85.00 61	98.51 25	95.96 130	80.57 216	88.08 122	97.63 66	76.84 107	99.89 7	85.67 138	94.88 106	98.13 72

CANet		94.89 13	94.64 17	95.63 11	97.55 75	88.12 14	99.06 10	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

DeepPCF-MVS	89.82 1	94.61 17	96.17 5	89.91 180	97.09 90	70.21 309	98.99 15	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

HPM-MVS++		95.32 9	95.48 12	94.85 22	98.62 34	86.04 34	97.81 56	96.93 35	92.45 13	95.69 23	98.50 20	85.38 31	99.85 10	94.75 40	99.18 7	98.65 42

PHI-MVS		93.59 31	93.63 29	93.48 63	98.05 58	81.76 118	98.64 21	97.13 23	82.60 188	94.09 45	98.49 21	80.35 59	99.85 10	94.74 41	98.62 32	98.83 31

DVP-MVS++		96.05 4	96.41 3	94.96 20	99.05 9	85.34 47	98.13 37	96.77 50	88.38 59	97.70 6	98.77 10	92.06 3	99.84 12	97.47 14	99.37 1	99.70 3

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

test_0728_SECOND				95.14 16	99.04 14	86.14 33	99.06 10	96.77 50					99.84 12	97.90 9	98.85 21	99.45 10

SMA-MVS		94.70 16	94.68 16	94.76 24	98.02 59	85.94 37	97.47 81	96.77 50	85.32 118	97.92 3	98.70 15	83.09 47	99.84 12	95.79 29	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
patch_mono-2		95.14 11	96.08 7	92.33 102	98.44 43	77.84 221	98.43 26	97.21 20	92.58 12	97.68 8	97.65 64	86.88 26	99.83 16	98.25 3	97.60 64	99.33 17

ACMMP_NAP		93.46 32	93.23 37	94.17 39	97.16 88	84.28 72	96.82 134	96.65 67	86.24 101	94.27 42	97.99 44	77.94 89	99.83 16	93.39 55	98.57 33	98.39 55

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 52	97.79 4	98.91 2	88.48 17	99.82 18	98.15 4	98.97 17	99.74 1

test_241102_TWO								96.78 44	88.72 52	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 52	97.79 4	98.90 5	88.48 17	99.82 18

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 22	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

ZNCC-MVS		92.75 41	92.60 46	93.23 70	98.24 51	81.82 116	97.63 68	96.50 87	85.00 128	91.05 82	97.74 57	78.38 83	99.80 24	90.48 90	98.34 46	98.07 75

DVP-MVS		95.58 8	95.91 9	94.57 28	99.05 9	85.18 52	99.06 10	96.46 91	88.75 50	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_THIRD									88.38 59	96.69 13	98.76 12	89.64 13	99.76 25	97.47 14	98.84 23	99.38 14

GST-MVS		92.43 54	92.22 54	93.04 77	98.17 54	81.64 122	97.40 90	96.38 102	84.71 134	90.90 85	97.40 77	77.55 97	99.76 25	89.75 102	97.74 61	97.72 102

MTAPA		92.45 53	92.31 50	92.86 83	97.90 61	80.85 135	92.88 276	96.33 106	87.92 69	90.20 94	98.18 30	76.71 111	99.76 25	92.57 69	98.09 51	97.96 87

PAPR		92.74 42	92.17 55	94.45 30	98.89 20	84.87 64	97.20 99	96.20 115	87.73 74	88.40 117	98.12 35	78.71 80	99.76 25	87.99 121	96.28 92	98.74 34

PAPM_NR		91.46 70	90.82 74	93.37 66	98.50 40	81.81 117	95.03 227	96.13 119	84.65 136	86.10 139	97.65 64	79.24 72	99.75 30	83.20 167	96.88 83	98.56 46

MAR-MVS		90.63 88	90.22 86	91.86 120	98.47 42	78.20 209	97.18 101	96.61 73	83.87 159	88.18 121	98.18 30	68.71 202	99.75 30	83.66 161	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
DPE-MVS		95.32 9	95.55 10	94.64 27	98.79 23	84.87 64	97.77 58	96.74 55	86.11 103	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
MP-MVS-pluss		92.58 51	92.35 49	93.29 67	97.30 86	82.53 100	96.44 157	96.04 127	84.68 135	89.12 107	98.37 24	77.48 98	99.74 32	93.31 59	98.38 43	97.59 113
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
QAPM		86.88 160	84.51 181	93.98 42	94.04 160	85.89 38	97.19 100	96.05 126	73.62 300	75.12 265	95.62 128	62.02 242	99.74 32	70.88 271	96.06 96	96.30 165

AdaColmap		88.81 123	87.61 134	92.39 100	99.33 4	79.95 156	96.70 144	95.58 149	77.51 269	83.05 173	96.69 108	61.90 245	99.72 35	84.29 148	93.47 124	97.50 119

HFP-MVS		92.89 39	92.86 41	92.98 79	98.71 25	81.12 129	97.58 72	96.70 60	85.20 123	91.75 70	97.97 48	78.47 82	99.71 36	90.95 81	98.41 41	98.12 73

DeepC-MVS	86.58 3	91.53 69	91.06 72	92.94 81	94.52 145	81.89 112	95.95 184	95.98 129	90.76 26	83.76 165	96.76 104	73.24 167	99.71 36	91.67 77	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
MP-MVS		92.61 50	92.67 44	92.42 99	98.13 56	79.73 165	97.33 93	96.20 115	85.63 112	90.53 89	97.66 60	78.14 87	99.70 38	92.12 72	98.30 48	97.85 93
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MVS		90.60 89	88.64 113	96.50 5	94.25 153	90.53 8	93.33 264	97.21 20	77.59 268	78.88 217	97.31 79	71.52 185	99.69 39	89.60 103	98.03 54	99.27 20

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 73	97.08 91	83.32 45	99.69 39	92.83 65	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
mPP-MVS		91.88 60	91.82 59	92.07 112	98.38 44	78.63 193	97.29 94	96.09 122	85.12 125	88.45 116	97.66 60	75.53 130	99.68 41	89.83 100	98.02 55	97.88 89

3Dnovator	82.32 10	89.33 111	87.64 131	94.42 31	93.73 167	85.70 41	97.73 62	96.75 54	86.73 99	76.21 250	95.93 118	62.17 239	99.68 41	81.67 177	97.81 59	97.88 89

region2R		92.72 45	92.70 43	92.79 85	98.68 26	80.53 145	97.53 76	96.51 85	85.22 121	91.94 68	97.98 46	77.26 100	99.67 43	90.83 85	98.37 44	98.18 67

ACMMPR		92.69 47	92.67 44	92.75 86	98.66 28	80.57 141	97.58 72	96.69 62	85.20 123	91.57 72	97.92 49	77.01 105	99.67 43	90.95 81	98.41 41	98.00 82

OpenMVS	79.58 14	86.09 173	83.62 197	93.50 61	90.95 241	86.71 30	97.44 84	95.83 138	75.35 286	72.64 284	95.72 123	57.42 276	99.64 45	71.41 265	95.85 100	94.13 203

ACMMP		90.39 93	89.97 92	91.64 128	97.58 73	78.21 208	96.78 137	96.72 58	84.73 133	84.72 152	97.23 84	71.22 187	99.63 46	88.37 119	92.41 137	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
CHOSEN 1792x2688		91.07 80	90.21 87	93.64 53	95.18 126	83.53 85	96.26 169	96.13 119	88.92 49	84.90 149	93.10 184	72.86 169	99.62 47	88.86 111	95.67 102	97.79 98

SD-MVS		94.84 14	95.02 14	94.29 34	97.87 64	84.61 67	97.76 60	96.19 117	89.59 42	96.66 15	98.17 33	84.33 36	99.60 48	96.09 24	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_vis1_n_1920		89.95 101	90.59 77	88.03 217	92.36 204	68.98 319	99.12 6	94.34 218	93.86 8	93.64 49	97.01 94	51.54 302	99.59 49	96.76 21	96.71 89	95.53 179

XVS		92.69 47	92.71 42	92.63 92	98.52 37	80.29 148	97.37 91	96.44 93	87.04 91	91.38 74	97.83 54	77.24 102	99.59 49	90.46 91	98.07 52	98.02 77

X-MVStestdata		86.26 171	84.14 190	92.63 92	98.52 37	80.29 148	97.37 91	96.44 93	87.04 91	91.38 74	20.73 376	77.24 102	99.59 49	90.46 91	98.07 52	98.02 77

PVSNet_BlendedMVS		90.05 99	89.96 93	90.33 167	97.47 76	83.86 77	98.02 46	96.73 56	87.98 67	89.53 103	89.61 233	76.42 114	99.57 52	94.29 45	79.59 232	87.57 300

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 25	89.53 103	96.21 113	76.42 114	99.57 52	94.29 45	95.81 101	97.29 131

PGM-MVS		91.93 59	91.80 60	92.32 104	98.27 50	79.74 164	95.28 211	97.27 18	83.83 160	90.89 86	97.78 56	76.12 120	99.56 54	88.82 112	97.93 58	97.66 107

MVS_111021_HR		93.41 33	93.39 35	93.47 65	97.34 85	82.83 96	97.56 74	98.27 6	89.16 47	89.71 98	97.14 87	79.77 67	99.56 54	93.65 53	97.94 56	98.02 77

无先验							96.87 130	96.78 44	77.39 270				99.52 56	79.95 191		98.43 53

CSCG		92.02 58	91.65 63	93.12 73	98.53 36	80.59 140	97.47 81	97.18 22	77.06 277	84.64 154	97.98 46	83.98 41	99.52 56	90.72 87	97.33 73	99.23 21

新几何1				93.12 73	97.44 78	81.60 123		96.71 59	74.54 294	91.22 80	97.57 67	79.13 74	99.51 58	77.40 217	98.46 38	98.26 65

3Dnovator+	82.88 8	89.63 106	87.85 126	94.99 19	94.49 149	86.76 29	97.84 53	95.74 142	86.10 104	75.47 262	96.02 117	65.00 225	99.51 58	82.91 171	97.07 79	98.72 39

CANet_DTU		90.98 81	90.04 91	93.83 46	94.76 139	86.23 32	96.32 166	93.12 277	93.11 11	93.71 47	96.82 102	63.08 235	99.48 60	84.29 148	95.12 105	95.77 174

testdata2													99.48 60	76.45 226

SteuartSystems-ACMMP		94.13 26	94.44 21	93.20 71	95.41 119	81.35 126	99.02 14	96.59 77	89.50 43	94.18 44	98.36 25	83.68 44	99.45 62	94.77 39	98.45 39	98.81 32
Skip Steuart: Steuart Systems R&D Blog.
TSAR-MVS + GP.		94.35 20	94.50 18	93.89 45	97.38 84	83.04 94	98.10 39	95.29 169	91.57 18	93.81 46	97.45 72	86.64 27	99.43 63	96.28 23	94.01 116	99.20 22

1314		88.94 118	87.20 144	94.17 39	93.21 180	85.73 40	93.33 264	96.64 70	82.89 181	75.98 253	96.36 111	66.83 213	99.39 64	83.52 165	96.02 97	97.39 126

SF-MVS		94.17 24	94.05 26	94.55 29	97.56 74	85.95 35	97.73 62	96.43 95	84.02 152	95.07 31	98.74 14	82.93 48	99.38 65	95.42 35	98.51 34	98.32 58

DP-MVS		81.47 246	78.28 262	91.04 145	98.14 55	78.48 195	95.09 226	86.97 340	61.14 350	71.12 293	92.78 189	59.59 255	99.38 65	53.11 345	86.61 180	95.27 187

9.14			94.26 24		98.10 57		98.14 34	96.52 84	84.74 132	94.83 36	98.80 7	82.80 50	99.37 67	95.95 27	98.42 40

TEST9					98.64 31	83.71 80	97.82 54	96.65 67	84.29 147	95.16 27	98.09 37	84.39 35	99.36 68

train_agg		94.28 21	94.45 20	93.74 49	98.64 31	83.71 80	97.82 54	96.65 67	84.50 140	95.16 27	98.09 37	84.33 36	99.36 68	95.91 28	98.96 19	98.16 69

sss		90.87 85	89.96 93	93.60 56	94.15 156	83.84 79	97.14 107	98.13 7	85.93 108	89.68 99	96.09 116	71.67 182	99.30 70	87.69 124	89.16 158	97.66 107

PVSNet_Blended_VisFu		91.24 76	90.77 75	92.66 90	95.09 128	82.40 104	97.77 58	95.87 137	88.26 62	86.39 135	93.94 173	76.77 109	99.27 71	88.80 113	94.00 117	96.31 164

PLC	83.97 7	88.00 145	87.38 141	89.83 183	98.02 59	76.46 245	97.16 105	94.43 215	79.26 248	81.98 187	96.28 112	69.36 200	99.27 71	77.71 211	92.25 139	93.77 210
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 83	97.81 56	96.63 72	84.50 140	95.10 29	98.11 36	84.33 36	99.23 73

test12				94.25 35	98.34 46	85.55 44		96.35 105		92.36 61		80.84 56	99.22 74		98.31 47	97.98 84

MSLP-MVS++		94.28 21	94.39 22	93.97 43	98.30 49	84.06 75	98.64 21	96.93 35	90.71 27	93.08 56	98.70 15	79.98 65	99.21 75	94.12 48	99.07 11	98.63 43

CDPH-MVS		93.12 35	92.91 39	93.74 49	98.65 30	83.88 76	97.67 67	96.26 110	83.00 179	93.22 54	98.24 28	81.31 54	99.21 75	89.12 109	98.74 29	98.14 71

CP-MVS		92.54 52	92.60 46	92.34 101	98.50 40	79.90 158	98.40 27	96.40 99	84.75 131	90.48 91	98.09 37	77.40 99	99.21 75	91.15 80	98.23 50	97.92 88

LS3D		82.22 237	79.94 250	89.06 192	97.43 79	74.06 276	93.20 270	92.05 291	61.90 344	73.33 277	95.21 138	59.35 258	99.21 75	54.54 341	92.48 136	93.90 208

PCF-MVS	84.09 5	86.77 164	85.00 175	92.08 111	92.06 222	83.07 93	92.14 284	94.47 212	79.63 239	76.90 236	94.78 154	71.15 188	99.20 79	72.87 256	91.05 148	93.98 206
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
MVS_111021_LR		91.60 68	91.64 64	91.47 134	95.74 111	78.79 190	96.15 176	96.77 50	88.49 57	88.64 114	97.07 92	72.33 175	99.19 80	93.13 63	96.48 91	96.43 158

APDe-MVS		94.56 18	94.75 15	93.96 44	98.84 22	83.40 88	98.04 45	96.41 97	85.79 110	95.00 32	98.28 27	84.32 39	99.18 81	97.35 16	98.77 27	99.28 19

PS-MVSNAJ		94.17 24	93.52 32	96.10 8	95.65 113	92.35 2	98.21 32	95.79 140	92.42 14	96.24 19	98.18 30	71.04 190	99.17 82	96.77 20	97.39 72	96.79 147

agg_prior					98.59 35	83.13 92		96.56 81		94.19 43			99.16 83

ZD-MVS					99.09 8	83.22 91		96.60 76	82.88 182	93.61 50	98.06 42	82.93 48	99.14 84	95.51 34	98.49 37

EI-MVSNet-Vis-set		91.84 61	91.77 61	92.04 114	97.60 71	81.17 128	96.61 146	96.87 38	88.20 63	89.19 106	97.55 71	78.69 81	99.14 84	90.29 97	90.94 149	95.80 173

EI-MVSNet-UG-set		91.35 74	91.22 68	91.73 125	97.39 82	80.68 138	96.47 154	96.83 41	87.92 69	88.30 120	97.36 78	77.84 92	99.13 86	89.43 107	89.45 156	95.37 183

EPNet		94.06 27	94.15 25	93.76 48	97.27 87	84.35 70	98.29 29	97.64 13	94.57 4	95.36 25	96.88 98	79.96 66	99.12 87	91.30 78	96.11 94	97.82 96
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 83	98.31 48	80.10 155	97.42 88	96.78 44	92.20 15	97.11 11	98.29 26	93.46 1	99.10 88	96.01 25	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		87.73 150	86.55 156	91.27 139	95.16 127	79.11 181	96.35 164	96.23 112	88.14 64	87.83 124	90.48 220	50.65 304	99.09 89	80.13 190	94.03 114	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
test_prior				93.09 75	98.68 26	81.91 111		96.40 99					99.06 90			98.29 62

WTY-MVS		92.65 49	91.68 62	95.56 12	96.00 105	88.90 11	98.23 31	97.65 12	88.57 55	89.82 97	97.22 85	79.29 70	99.06 90	89.57 104	88.73 164	98.73 38

HY-MVS	84.06 6	91.63 66	90.37 84	95.39 15	96.12 102	88.25 13	90.22 301	97.58 14	88.33 61	90.50 90	91.96 196	79.26 71	99.06 90	90.29 97	89.07 159	98.88 30

MG-MVS		94.25 23	93.72 27	95.85 10	99.38 3	89.35 10	97.98 47	98.09 8	89.99 37	92.34 62	96.97 95	81.30 55	98.99 93	88.54 114	98.88 20	99.20 22

原ACMM1				91.22 141	97.77 65	78.10 211		96.61 73	81.05 207	91.28 79	97.42 76	77.92 91	98.98 94	79.85 193	98.51 34	96.59 154

Anonymous202405211		84.41 201	81.93 220	91.85 122	96.78 93	78.41 199	97.44 84	91.34 303	70.29 323	84.06 157	94.26 164	41.09 338	98.96 95	79.46 195	82.65 217	98.17 68

xiu_mvs_v2_base		93.92 28	93.26 36	95.91 9	95.07 130	92.02 6	98.19 33	95.68 145	92.06 16	96.01 22	98.14 34	70.83 193	98.96 95	96.74 22	96.57 90	96.76 150

VNet		92.11 57	91.22 68	94.79 23	96.91 91	86.98 25	97.91 49	97.96 9	86.38 100	93.65 48	95.74 122	70.16 198	98.95 97	93.39 55	88.87 162	98.43 53

CNLPA		86.96 158	85.37 167	91.72 126	97.59 72	79.34 175	97.21 97	91.05 308	74.22 295	78.90 216	96.75 106	67.21 210	98.95 97	74.68 242	90.77 150	96.88 145

ab-mvs		87.08 157	84.94 176	93.48 63	93.34 179	83.67 82	88.82 309	95.70 144	81.18 205	84.55 155	90.14 228	62.72 236	98.94 99	85.49 140	82.54 218	97.85 93

HPM-MVS		91.62 67	91.53 65	91.89 119	97.88 63	79.22 177	96.99 118	95.73 143	82.07 196	89.50 105	97.19 86	75.59 129	98.93 100	90.91 83	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
PVSNet	82.34 9	89.02 116	87.79 128	92.71 89	95.49 117	81.50 124	97.70 64	97.29 17	87.76 73	85.47 143	95.12 145	56.90 279	98.90 101	80.33 185	94.02 115	97.71 104

h-mvs33		89.30 112	88.95 110	90.36 166	95.07 130	76.04 252	96.96 124	97.11 25	90.39 32	92.22 64	95.10 146	74.70 147	98.86 102	93.14 61	65.89 323	96.16 166

MSDG		80.62 257	77.77 266	89.14 191	93.43 178	77.24 233	91.89 287	90.18 317	69.86 326	68.02 307	91.94 198	52.21 301	98.84 103	59.32 324	83.12 208	91.35 223

Anonymous20240529		83.15 220	80.60 239	90.80 153	95.74 111	78.27 203	96.81 135	94.92 182	60.10 354	81.89 189	92.54 190	45.82 322	98.82 104	79.25 198	78.32 248	95.31 185

test_yl		91.46 70	90.53 79	94.24 36	97.41 80	85.18 52	98.08 40	97.72 10	80.94 208	89.85 95	96.14 114	75.61 127	98.81 105	90.42 95	88.56 166	98.74 34

DCV-MVSNet		91.46 70	90.53 79	94.24 36	97.41 80	85.18 52	98.08 40	97.72 10	80.94 208	89.85 95	96.14 114	75.61 127	98.81 105	90.42 95	88.56 166	98.74 34

HPM-MVS_fast		90.38 95	90.17 89	91.03 146	97.61 70	77.35 232	97.15 106	95.48 155	79.51 241	88.79 111	96.90 96	71.64 184	98.81 105	87.01 132	97.44 69	96.94 140

APD-MVS		93.61 30	93.59 30	93.69 52	98.76 24	83.26 90	97.21 97	96.09 122	82.41 190	94.65 38	98.21 29	81.96 53	98.81 105	94.65 42	98.36 45	99.01 25
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SR-MVS		92.16 56	92.27 51	91.83 123	98.37 45	78.41 199	96.67 145	95.76 141	82.19 194	91.97 67	98.07 41	76.44 113	98.64 109	93.71 52	97.27 75	98.45 52

SR-MVS-dyc-post		91.29 75	91.45 66	90.80 153	97.76 67	76.03 253	96.20 174	95.44 159	80.56 217	90.72 87	97.84 52	75.76 126	98.61 110	91.99 74	96.79 86	97.75 100

alignmvs		92.97 38	92.26 52	95.12 17	95.54 116	87.77 18	98.67 19	96.38 102	88.04 66	93.01 57	97.45 72	79.20 73	98.60 111	93.25 60	88.76 163	98.99 28

OMC-MVS		88.80 124	88.16 122	90.72 156	95.30 122	77.92 218	94.81 232	94.51 209	86.80 96	84.97 148	96.85 99	67.53 206	98.60 111	85.08 142	87.62 173	95.63 176

canonicalmvs		92.27 55	91.22 68	95.41 14	95.80 110	88.31 12	97.09 114	94.64 202	88.49 57	92.99 58	97.31 79	72.68 171	98.57 113	93.38 57	88.58 165	99.36 16

APD-MVS_3200maxsize		91.23 77	91.35 67	90.89 151	97.89 62	76.35 248	96.30 167	95.52 153	79.82 235	91.03 83	97.88 51	74.70 147	98.54 114	92.11 73	96.89 82	97.77 99

IB-MVS	85.34 4	88.67 127	87.14 147	93.26 68	93.12 186	84.32 71	98.76 17	97.27 18	87.19 89	79.36 214	90.45 221	83.92 42	98.53 115	84.41 147	69.79 291	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
114514_t		88.79 125	87.57 135	92.45 97	98.21 53	81.74 119	96.99 118	95.45 158	75.16 289	82.48 176	95.69 125	68.59 203	98.50 116	80.33 185	95.18 104	97.10 137

FA-MVS(test-final)		87.71 151	86.23 158	92.17 109	94.19 155	80.55 142	87.16 324	96.07 125	82.12 195	85.98 140	88.35 248	72.04 180	98.49 117	80.26 187	89.87 153	97.48 121

TSAR-MVS + MP.		94.79 15	95.17 13	93.64 53	97.66 69	84.10 74	95.85 192	96.42 96	91.26 21	97.49 10	96.80 103	86.50 28	98.49 117	95.54 33	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
VDD-MVS		88.28 139	87.02 150	92.06 113	95.09 128	80.18 154	97.55 75	94.45 214	83.09 175	89.10 108	95.92 120	47.97 314	98.49 117	93.08 64	86.91 178	97.52 118

test_fmvs1_n		86.34 169	86.72 154	85.17 273	87.54 291	63.64 338	96.91 128	92.37 288	87.49 79	91.33 77	95.58 130	40.81 340	98.46 120	95.00 38	93.49 123	93.41 217

PatchMatch-RL		85.00 192	83.66 195	89.02 194	95.86 108	74.55 271	92.49 280	93.60 257	79.30 246	79.29 215	91.47 202	58.53 265	98.45 121	70.22 276	92.17 141	94.07 205

F-COLMAP		84.50 200	83.44 201	87.67 222	95.22 124	72.22 288	95.95 184	93.78 248	75.74 284	76.30 247	95.18 141	59.50 257	98.45 121	72.67 258	86.59 181	92.35 221

test_fmvs1		87.79 149	88.52 116	85.62 266	92.98 192	64.31 333	97.88 51	92.42 286	87.95 68	92.24 63	95.82 121	47.94 315	98.44 123	95.31 36	94.09 113	94.09 204

RPMNet		79.85 261	75.92 280	91.64 128	90.16 256	79.75 162	79.02 351	95.44 159	58.43 358	82.27 183	72.55 355	73.03 168	98.41 124	46.10 359	86.25 184	96.75 151

FE-MVS		86.06 174	84.15 189	91.78 124	94.33 152	79.81 159	84.58 337	96.61 73	76.69 279	85.00 147	87.38 261	70.71 194	98.37 125	70.39 275	91.70 145	97.17 135

xiu_mvs_v1_base_debu		90.54 90	89.54 100	93.55 58	92.31 205	87.58 21	96.99 118	94.87 185	87.23 86	93.27 51	97.56 68	57.43 273	98.32 126	92.72 66	93.46 125	94.74 193

xiu_mvs_v1_base		90.54 90	89.54 100	93.55 58	92.31 205	87.58 21	96.99 118	94.87 185	87.23 86	93.27 51	97.56 68	57.43 273	98.32 126	92.72 66	93.46 125	94.74 193

xiu_mvs_v1_base_debi		90.54 90	89.54 100	93.55 58	92.31 205	87.58 21	96.99 118	94.87 185	87.23 86	93.27 51	97.56 68	57.43 273	98.32 126	92.72 66	93.46 125	94.74 193

CPTT-MVS		89.72 104	89.87 97	89.29 190	98.33 47	73.30 280	97.70 64	95.35 166	75.68 285	87.40 126	97.44 75	70.43 195	98.25 129	89.56 105	96.90 81	96.33 163

LFMVS		89.27 113	87.64 131	94.16 41	97.16 88	85.52 45	97.18 101	94.66 199	79.17 249	89.63 101	96.57 109	55.35 290	98.22 130	89.52 106	89.54 155	98.74 34

PVSNet_0	77.72 15	81.70 243	78.95 259	89.94 179	90.77 247	76.72 243	95.96 183	96.95 33	85.01 127	70.24 300	88.53 246	52.32 300	98.20 131	86.68 135	44.08 364	94.89 189

TAPA-MVS	81.61 12	85.02 191	83.67 194	89.06 192	96.79 92	73.27 282	95.92 186	94.79 192	74.81 292	80.47 202	96.83 100	71.07 189	98.19 132	49.82 353	92.57 133	95.71 175
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
UA-Net		88.92 119	88.48 117	90.24 169	94.06 159	77.18 236	93.04 272	94.66 199	87.39 82	91.09 81	93.89 174	74.92 145	98.18 133	75.83 233	91.43 146	95.35 184

dcpmvs_2		93.10 36	93.46 34	92.02 115	97.77 65	79.73 165	94.82 231	93.86 241	86.91 93	91.33 77	96.76 104	85.20 32	98.06 134	96.90 19	97.60 64	98.27 64

thres200		88.92 119	87.65 130	92.73 88	96.30 96	85.62 43	97.85 52	98.86 1	84.38 144	84.82 150	93.99 172	75.12 143	98.01 135	70.86 272	86.67 179	94.56 198

cascas		86.50 166	84.48 183	92.55 95	92.64 200	85.95 35	97.04 117	95.07 177	75.32 287	80.50 201	91.02 211	54.33 297	97.98 136	86.79 134	87.62 173	93.71 211

thres100view900		88.30 138	86.95 151	92.33 102	96.10 103	84.90 63	97.14 107	98.85 2	82.69 186	83.41 167	93.66 178	75.43 134	97.93 137	69.04 280	86.24 186	94.17 200

tfpn200view9		88.48 132	87.15 145	92.47 96	96.21 99	85.30 50	97.44 84	98.85 2	83.37 169	83.99 159	93.82 175	75.36 137	97.93 137	69.04 280	86.24 186	94.17 200

gm-plane-assit					92.27 209	79.64 168			84.47 142		95.15 143		97.93 137	85.81 137

testdata				90.13 172	95.92 107	74.17 274		96.49 90	73.49 303	94.82 37	97.99 44	78.80 79	97.93 137	83.53 164	97.52 66	98.29 62

thres400		88.42 135	87.15 145	92.23 106	96.21 99	85.30 50	97.44 84	98.85 2	83.37 169	83.99 159	93.82 175	75.36 137	97.93 137	69.04 280	86.24 186	93.45 215

VDDNet		86.44 167	84.51 181	92.22 107	91.56 231	81.83 115	97.10 113	94.64 202	69.50 327	87.84 123	95.19 140	48.01 313	97.92 142	89.82 101	86.92 177	96.89 144

thisisatest0515		90.95 83	90.26 85	93.01 78	94.03 162	84.27 73	97.91 49	96.67 64	83.18 172	86.87 133	95.51 132	88.66 16	97.85 143	80.46 184	89.01 160	96.92 143

thres600view7		88.06 143	86.70 155	92.15 110	96.10 103	85.17 56	97.14 107	98.85 2	82.70 185	83.41 167	93.66 178	75.43 134	97.82 144	67.13 290	85.88 190	93.45 215

MVS_Test		90.29 96	89.18 105	93.62 55	95.23 123	84.93 62	94.41 238	94.66 199	84.31 145	90.37 93	91.02 211	75.13 142	97.82 144	83.11 169	94.42 111	98.12 73

旧先验2							96.97 123		74.06 298	96.10 20			97.76 146	88.38 118

EIA-MVS		91.73 62	92.05 57	90.78 155	94.52 145	76.40 247	98.06 43	95.34 167	89.19 46	88.90 110	97.28 83	77.56 96	97.73 147	90.77 86	96.86 85	98.20 66

thisisatest0530		89.65 105	89.02 107	91.53 132	93.46 177	80.78 136	96.52 151	96.67 64	81.69 201	83.79 164	94.90 152	88.85 15	97.68 148	77.80 207	87.49 176	96.14 167

BH-RMVSNet		86.84 161	85.28 168	91.49 133	95.35 121	80.26 151	96.95 125	92.21 289	82.86 183	81.77 191	95.46 133	59.34 259	97.64 149	69.79 278	93.81 120	96.57 155

1112_ss		88.60 130	87.47 139	92.00 116	93.21 180	80.97 132	96.47 154	92.46 285	83.64 166	80.86 198	97.30 81	80.24 62	97.62 150	77.60 212	85.49 194	97.40 125

casdiffmvs_mvg		91.13 79	90.45 81	93.17 72	92.99 191	83.58 84	97.46 83	94.56 207	87.69 75	87.19 130	94.98 151	74.50 152	97.60 151	91.88 76	92.79 131	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
Test_1112_low_res		88.03 144	86.73 153	91.94 118	93.15 183	80.88 134	96.44 157	92.41 287	83.59 168	80.74 200	91.16 209	80.18 63	97.59 152	77.48 215	85.40 195	97.36 127

tttt0517		88.57 131	88.19 121	89.71 187	93.00 188	75.99 256	95.67 197	96.67 64	80.78 211	81.82 190	94.40 161	88.97 14	97.58 153	76.05 231	86.31 183	95.57 178

ECVR-MVS		88.35 137	87.25 143	91.65 127	93.54 171	79.40 172	96.56 150	90.78 313	86.78 97	85.57 142	95.25 135	57.25 277	97.56 154	84.73 146	94.80 107	97.98 84

lupinMVS		93.87 29	93.58 31	94.75 25	93.00 188	88.08 15	99.15 4	95.50 154	91.03 24	94.90 33	97.66 60	78.84 77	97.56 154	94.64 43	97.46 67	98.62 44

XVG-OURS		85.18 188	84.38 185	87.59 226	90.42 252	71.73 299	91.06 297	94.07 232	82.00 198	83.29 169	95.08 147	56.42 284	97.55 156	83.70 160	83.42 206	93.49 214

TR-MVS		86.30 170	84.93 177	90.42 163	94.63 141	77.58 227	96.57 148	93.82 243	80.30 225	82.42 178	95.16 142	58.74 263	97.55 156	74.88 240	87.82 172	96.13 168

test_vis1_rt		73.96 300	72.40 302	78.64 325	83.91 333	61.16 347	95.63 200	68.18 371	76.32 280	60.09 344	74.77 347	29.01 360	97.54 158	87.74 123	75.94 255	77.22 357

casdiffmvs		90.95 83	90.39 82	92.63 92	92.82 195	82.53 100	96.83 132	94.47 212	87.69 75	88.47 115	95.56 131	74.04 157	97.54 158	90.90 84	92.74 132	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
XVG-OURS-SEG-HR		85.74 180	85.16 172	87.49 231	90.22 254	71.45 302	91.29 294	94.09 231	81.37 203	83.90 163	95.22 137	60.30 252	97.53 160	85.58 139	84.42 201	93.50 213

baseline		90.76 86	90.10 90	92.74 87	92.90 194	82.56 99	94.60 235	94.56 207	87.69 75	89.06 109	95.67 126	73.76 160	97.51 161	90.43 94	92.23 140	98.16 69

test2506		90.96 82	90.39 82	92.65 91	93.54 171	82.46 103	96.37 162	97.35 16	86.78 97	87.55 125	95.25 135	77.83 93	97.50 162	84.07 150	94.80 107	97.98 84

ETV-MVS		92.72 45	92.87 40	92.28 105	94.54 144	81.89 112	97.98 47	95.21 172	89.77 41	93.11 55	96.83 100	77.23 104	97.50 162	95.74 30	95.38 103	97.44 122

Effi-MVS+		90.70 87	89.90 96	93.09 75	93.61 168	83.48 86	95.20 217	92.79 282	83.22 171	91.82 69	95.70 124	71.82 181	97.48 164	91.25 79	93.67 121	98.32 58

baseline2		90.39 93	90.21 87	90.93 148	90.86 244	80.99 131	95.20 217	97.41 15	86.03 106	80.07 210	94.61 157	90.58 6	97.47 165	87.29 128	89.86 154	94.35 199

diffmvs		91.17 78	90.74 76	92.44 98	93.11 187	82.50 102	96.25 170	93.62 256	87.79 72	90.40 92	95.93 118	73.44 165	97.42 166	93.62 54	92.55 134	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
tpmvs		83.04 223	80.77 234	89.84 182	95.43 118	77.96 215	85.59 334	95.32 168	75.31 288	76.27 248	83.70 314	73.89 158	97.41 167	59.53 321	81.93 220	94.14 202

tt0805		81.20 251	79.06 258	87.61 224	86.50 298	72.97 285	93.66 255	95.48 155	74.11 296	76.23 249	91.99 194	41.36 337	97.40 168	77.44 216	74.78 262	92.45 219

test1111		88.11 142	87.04 149	91.35 135	93.15 183	78.79 190	96.57 148	90.78 313	86.88 95	85.04 146	95.20 139	57.23 278	97.39 169	83.88 153	94.59 109	97.87 91

PMMVS		89.46 109	89.92 95	88.06 215	94.64 140	69.57 316	96.22 171	94.95 180	87.27 85	91.37 76	96.54 110	65.88 217	97.39 169	88.54 114	93.89 118	97.23 132

PAPM		92.87 40	92.40 48	94.30 33	92.25 212	87.85 17	96.40 161	96.38 102	91.07 23	88.72 113	96.90 96	82.11 52	97.37 171	90.05 99	97.70 62	97.67 106

HQP4-MVS										82.30 179			97.32 172			91.13 224

HQP-MVS		87.91 148	87.55 136	88.98 195	92.08 219	78.48 195	97.63 68	94.80 190	90.52 29	82.30 179	94.56 158	65.40 221	97.32 172	87.67 125	83.01 210	91.13 224

HQP_MVS		87.50 154	87.09 148	88.74 200	91.86 228	77.96 215	97.18 101	94.69 195	89.89 39	81.33 193	94.15 168	64.77 227	97.30 174	87.08 129	82.82 214	90.96 226

plane_prior5								94.69 195					97.30 174	87.08 129	82.82 214	90.96 226

jason		92.73 43	92.23 53	94.21 38	90.50 250	87.30 24	98.65 20	95.09 175	90.61 28	92.76 60	97.13 88	75.28 140	97.30 174	93.32 58	96.75 88	98.02 77
jason: jason.
CLD-MVS		87.97 146	87.48 138	89.44 188	92.16 217	80.54 144	98.14 34	94.92 182	91.41 19	79.43 213	95.40 134	62.34 238	97.27 177	90.60 89	82.90 213	90.50 233
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
OPM-MVS		85.84 177	85.10 174	88.06 215	88.34 280	77.83 222	95.72 195	94.20 224	87.89 71	80.45 203	94.05 170	58.57 264	97.26 178	83.88 153	82.76 216	89.09 264
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BH-w/o		88.24 140	87.47 139	90.54 161	95.03 133	78.54 194	97.41 89	93.82 243	84.08 150	78.23 224	94.51 160	69.34 201	97.21 179	80.21 189	94.58 110	95.87 172

Vis-MVSNet		88.67 127	87.82 127	91.24 140	92.68 196	78.82 187	96.95 125	93.85 242	87.55 78	87.07 132	95.13 144	63.43 233	97.21 179	77.58 213	96.15 93	97.70 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
test_vis1_n		85.60 182	85.70 162	85.33 270	84.79 323	64.98 331	96.83 132	91.61 299	87.36 83	91.00 84	94.84 153	36.14 346	97.18 181	95.66 31	93.03 129	93.82 209

AllTest		75.92 292	73.06 299	84.47 284	92.18 215	67.29 324	91.07 296	84.43 351	67.63 330	63.48 327	90.18 225	38.20 343	97.16 182	57.04 332	73.37 268	88.97 272

TestCases				84.47 284	92.18 215	67.29 324		84.43 351	67.63 330	63.48 327	90.18 225	38.20 343	97.16 182	57.04 332	73.37 268	88.97 272

ACMH	75.40 17	77.99 277	74.96 284	87.10 240	90.67 248	76.41 246	93.19 271	91.64 298	72.47 312	63.44 329	87.61 259	43.34 328	97.16 182	58.34 326	73.94 265	87.72 294
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
CS-MVS-test		92.98 37	93.67 28	90.90 150	96.52 94	76.87 239	98.68 18	94.73 194	90.36 34	94.84 35	97.89 50	77.94 89	97.15 185	94.28 47	97.80 60	98.70 40

ACMM	80.70 13	83.72 211	82.85 208	86.31 253	91.19 237	72.12 291	95.88 189	94.29 221	80.44 220	77.02 234	91.96 196	55.24 291	97.14 186	79.30 197	80.38 226	89.67 250
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EPP-MVSNet		89.76 103	89.72 99	89.87 181	93.78 164	76.02 255	97.22 95	96.51 85	79.35 243	85.11 145	95.01 149	84.82 34	97.10 187	87.46 127	88.21 170	96.50 156

tpm cat1		83.63 212	81.38 228	90.39 164	93.53 176	78.19 210	85.56 335	95.09 175	70.78 321	78.51 221	83.28 317	74.80 146	97.03 188	66.77 291	84.05 202	95.95 169

CS-MVS		92.73 43	93.48 33	90.48 162	96.27 97	75.93 258	98.55 24	94.93 181	89.32 44	94.54 40	97.67 59	78.91 76	97.02 189	93.80 50	97.32 74	98.49 49

BH-untuned		86.95 159	85.94 160	89.99 175	94.52 145	77.46 229	96.78 137	93.37 268	81.80 199	76.62 240	93.81 177	66.64 214	97.02 189	76.06 230	93.88 119	95.48 181

LTVRE_ROB	73.68 18	77.99 277	75.74 281	84.74 277	90.45 251	72.02 293	86.41 330	91.12 305	72.57 311	66.63 316	87.27 263	54.95 294	96.98 191	56.29 336	75.98 254	85.21 329
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		89.83 102	89.34 103	91.31 136	92.54 202	80.19 153	97.11 110	96.57 79	86.15 102	86.85 134	91.83 200	79.32 69	96.95 192	81.30 178	92.35 138	96.77 149

LPG-MVS_test		84.20 204	83.49 200	86.33 250	90.88 242	73.06 283	95.28 211	94.13 228	82.20 192	76.31 245	93.20 181	54.83 295	96.95 192	83.72 158	80.83 223	88.98 270

LGP-MVS_train				86.33 250	90.88 242	73.06 283		94.13 228	82.20 192	76.31 245	93.20 181	54.83 295	96.95 192	83.72 158	80.83 223	88.98 270

COLMAP_ROB	73.24 19	75.74 294	73.00 300	83.94 290	92.38 203	69.08 318	91.85 288	86.93 341	61.48 347	65.32 322	90.27 224	42.27 333	96.93 195	50.91 350	75.63 258	85.80 326
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
baseline1		88.85 122	87.49 137	92.93 82	95.21 125	86.85 27	95.47 205	94.61 204	87.29 84	83.11 172	94.99 150	80.70 57	96.89 196	82.28 173	73.72 266	95.05 188

ACMP	81.66 11	84.00 205	83.22 204	86.33 250	91.53 234	72.95 286	95.91 188	93.79 247	83.70 165	73.79 272	92.22 192	54.31 298	96.89 196	83.98 151	79.74 231	89.16 261
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
CostFormer		89.08 115	88.39 118	91.15 143	93.13 185	79.15 180	88.61 312	96.11 121	83.14 173	89.58 102	86.93 270	83.83 43	96.87 198	88.22 120	85.92 189	97.42 123

DROMVSNet		91.73 62	92.11 56	90.58 159	93.54 171	77.77 223	98.07 42	94.40 216	87.44 80	92.99 58	97.11 90	74.59 151	96.87 198	93.75 51	97.08 78	97.11 136

USDC		78.65 272	76.25 277	85.85 259	87.58 289	74.60 270	89.58 304	90.58 316	84.05 151	63.13 331	88.23 250	40.69 341	96.86 200	66.57 294	75.81 257	86.09 321

MS-PatchMatch		83.05 222	81.82 222	86.72 248	89.64 265	79.10 182	94.88 230	94.59 206	79.70 238	70.67 296	89.65 232	50.43 306	96.82 201	70.82 274	95.99 98	84.25 335

HyFIR lowres test		89.36 110	88.60 114	91.63 130	94.91 136	80.76 137	95.60 201	95.53 151	82.56 189	84.03 158	91.24 208	78.03 88	96.81 202	87.07 131	88.41 168	97.32 128

RPSCF		77.73 280	76.63 275	81.06 314	88.66 278	55.76 358	87.77 319	87.88 337	64.82 339	74.14 271	92.79 188	49.22 310	96.81 202	67.47 288	76.88 252	90.62 230

test-LLR		88.48 132	87.98 124	89.98 176	92.26 210	77.23 234	97.11 110	95.96 130	83.76 163	86.30 137	91.38 204	72.30 176	96.78 204	80.82 181	91.92 142	95.94 170

test-mter		88.95 117	88.60 114	89.98 176	92.26 210	77.23 234	97.11 110	95.96 130	85.32 118	86.30 137	91.38 204	76.37 116	96.78 204	80.82 181	91.92 142	95.94 170

tpmrst		88.36 136	87.38 141	91.31 136	94.36 151	79.92 157	87.32 322	95.26 171	85.32 118	88.34 118	86.13 286	80.60 58	96.70 206	83.78 155	85.34 197	97.30 130

Fast-Effi-MVS+		87.93 147	86.94 152	90.92 149	94.04 160	79.16 179	98.26 30	93.72 252	81.29 204	83.94 162	92.90 185	69.83 199	96.68 207	76.70 223	91.74 144	96.93 141

AUN-MVS		86.25 172	85.57 163	88.26 210	93.57 170	73.38 278	95.45 206	95.88 135	83.94 156	85.47 143	94.21 166	73.70 163	96.67 208	83.54 163	64.41 327	94.73 196

hse-mvs2		88.22 141	88.21 120	88.25 211	93.54 171	73.41 277	95.41 208	95.89 134	90.39 32	92.22 64	94.22 165	74.70 147	96.66 209	93.14 61	64.37 328	94.69 197

MDTV_nov1_ep13			83.69 193		94.09 158	81.01 130	86.78 327	96.09 122	83.81 161	84.75 151	84.32 309	74.44 153	96.54 210	63.88 306	85.07 198

XXY-MVS		83.84 208	82.00 219	89.35 189	87.13 294	81.38 125	95.72 195	94.26 222	80.15 229	75.92 255	90.63 218	61.96 244	96.52 211	78.98 201	73.28 271	90.14 239

ACMH+	76.62 16	77.47 283	74.94 285	85.05 274	91.07 240	71.58 301	93.26 268	90.01 318	71.80 316	64.76 324	88.55 244	41.62 335	96.48 212	62.35 313	71.00 279	87.09 308

GA-MVS		85.79 179	84.04 191	91.02 147	89.47 269	80.27 150	96.90 129	94.84 188	85.57 113	80.88 197	89.08 236	56.56 283	96.47 213	77.72 210	85.35 196	96.34 161

tpm2		87.35 156	86.26 157	90.62 158	92.93 193	78.67 192	88.06 317	95.99 128	79.33 244	87.40 126	86.43 281	80.28 61	96.40 214	80.23 188	85.73 193	96.79 147

dp		84.30 203	82.31 215	90.28 168	94.24 154	77.97 214	86.57 328	95.53 151	79.94 234	80.75 199	85.16 300	71.49 186	96.39 215	63.73 307	83.36 207	96.48 157

nrg030		86.79 163	85.43 165	90.87 152	88.76 274	85.34 47	97.06 116	94.33 219	84.31 145	80.45 203	91.98 195	72.36 174	96.36 216	88.48 117	71.13 278	90.93 228

CMPMVS	54.94 21	75.71 295	74.56 290	79.17 323	79.69 345	55.98 355	89.59 303	93.30 270	60.28 352	53.85 356	89.07 237	47.68 318	96.33 217	76.55 224	81.02 221	85.22 328
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
VPA-MVSNet		85.32 186	83.83 192	89.77 186	90.25 253	82.63 98	96.36 163	97.07 27	83.03 178	81.21 195	89.02 238	61.58 246	96.31 218	85.02 144	70.95 280	90.36 234

XVG-ACMP-BASELINE		79.38 268	77.90 265	83.81 291	84.98 322	67.14 328	89.03 308	93.18 274	80.26 228	72.87 282	88.15 252	38.55 342	96.26 219	76.05 231	78.05 249	88.02 290

EPMVS		87.47 155	85.90 161	92.18 108	95.41 119	82.26 107	87.00 325	96.28 109	85.88 109	84.23 156	85.57 292	75.07 144	96.26 219	71.14 270	92.50 135	98.03 76

IS-MVSNet		88.67 127	88.16 122	90.20 171	93.61 168	76.86 240	96.77 139	93.07 278	84.02 152	83.62 166	95.60 129	74.69 150	96.24 221	78.43 206	93.66 122	97.49 120

GG-mvs-BLEND				93.49 62	94.94 134	86.26 31	81.62 345	97.00 29		88.32 119	94.30 163	91.23 5	96.21 222	88.49 116	97.43 70	98.00 82

GeoE		86.36 168	85.20 169	89.83 183	93.17 182	76.13 250	97.53 76	92.11 290	79.58 240	80.99 196	94.01 171	66.60 215	96.17 223	73.48 254	89.30 157	97.20 134

gg-mvs-nofinetune		85.48 185	82.90 207	93.24 69	94.51 148	85.82 39	79.22 349	96.97 31	61.19 349	87.33 128	53.01 365	90.58 6	96.07 224	86.07 136	97.23 76	97.81 97

iter_conf_final		89.51 107	89.21 104	90.39 164	95.60 114	84.44 69	97.22 95	89.09 327	89.11 48	82.07 186	92.80 186	87.03 25	96.03 225	89.10 110	80.89 222	90.70 229

iter_conf05		90.14 98	89.79 98	91.17 142	95.85 109	86.93 26	97.68 66	88.67 334	89.93 38	81.73 192	92.80 186	90.37 8	96.03 225	90.44 93	80.65 225	90.56 231

v2v482		83.46 214	81.86 221	88.25 211	86.19 304	79.65 167	96.34 165	94.02 234	81.56 202	77.32 230	88.23 250	65.62 218	96.03 225	77.77 208	69.72 293	89.09 264

V42		83.04 223	81.53 226	87.57 228	86.27 303	79.09 183	95.87 190	94.11 230	80.35 224	77.22 232	86.79 273	65.32 223	96.02 228	77.74 209	70.14 285	87.61 299

VPNet		84.69 196	82.92 206	90.01 174	89.01 273	83.45 87	96.71 142	95.46 157	85.71 111	79.65 212	92.18 193	56.66 282	96.01 229	83.05 170	67.84 311	90.56 231

test_post											33.80 372	76.17 119	95.97 230

EI-MVSNet		85.80 178	85.20 169	87.59 226	91.55 232	77.41 230	95.13 221	95.36 164	80.43 222	80.33 205	94.71 155	73.72 161	95.97 230	76.96 221	78.64 241	89.39 252

MVSTER		89.25 114	88.92 111	90.24 169	95.98 106	84.66 66	96.79 136	95.36 164	87.19 89	80.33 205	90.61 219	90.02 12	95.97 230	85.38 141	78.64 241	90.09 243

PatchmatchNet		86.83 162	85.12 173	91.95 117	94.12 157	82.27 106	86.55 329	95.64 147	84.59 138	82.98 174	84.99 304	77.26 100	95.96 233	68.61 284	91.34 147	97.64 109
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
TinyColmap		72.41 309	68.99 317	82.68 305	88.11 283	69.59 315	88.41 313	85.20 348	65.55 336	57.91 349	84.82 306	30.80 358	95.94 234	51.38 347	68.70 300	82.49 346

v1144		82.90 226	81.27 230	87.78 221	86.29 302	79.07 184	96.14 177	93.93 236	80.05 231	77.38 228	86.80 272	65.50 219	95.93 235	75.21 238	70.13 286	88.33 285

v144192		82.43 232	80.73 236	87.54 229	85.81 311	78.22 205	95.98 182	93.78 248	79.09 251	77.11 233	86.49 277	64.66 229	95.91 236	74.20 248	69.42 294	88.49 279

mvsmamba		85.17 189	84.54 180	87.05 241	87.94 285	75.11 266	96.22 171	87.79 338	86.91 93	78.55 220	91.77 201	64.93 226	95.91 236	86.94 133	79.80 228	90.12 240

v1192		82.31 236	80.55 240	87.60 225	85.94 308	78.47 198	95.85 192	93.80 246	79.33 244	76.97 235	86.51 276	63.33 234	95.87 238	73.11 255	70.13 286	88.46 281

v1240		81.70 243	79.83 252	87.30 236	85.50 314	77.70 226	95.48 204	93.44 262	78.46 260	76.53 241	86.44 279	60.85 249	95.84 239	71.59 264	70.17 284	88.35 284

v1921920		82.02 240	80.23 244	87.41 232	85.62 313	77.92 218	95.79 194	93.69 253	78.86 255	76.67 238	86.44 279	62.50 237	95.83 240	72.69 257	69.77 292	88.47 280

v8		81.88 241	80.06 248	87.32 234	86.63 297	79.04 185	94.41 238	93.65 255	78.77 256	73.19 279	85.57 292	66.87 212	95.81 241	73.84 252	67.61 313	87.11 307

D2MVS		82.67 229	81.55 225	86.04 258	87.77 287	76.47 244	95.21 216	96.58 78	82.66 187	70.26 299	85.46 295	60.39 251	95.80 242	76.40 227	79.18 236	85.83 325

PS-MVSNAJss		84.91 193	84.30 186	86.74 244	85.89 310	74.40 273	94.95 228	94.16 227	83.93 157	76.45 243	90.11 229	71.04 190	95.77 243	83.16 168	79.02 238	90.06 245

MVP-Stereo		82.65 230	81.67 224	85.59 267	86.10 307	78.29 202	93.33 264	92.82 281	77.75 266	69.17 306	87.98 254	59.28 260	95.76 244	71.77 262	96.88 83	82.73 343
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tfpnnormal		78.14 276	75.42 282	86.31 253	88.33 281	79.24 176	94.41 238	96.22 113	73.51 301	69.81 302	85.52 294	55.43 289	95.75 245	47.65 357	67.86 310	83.95 338

v148		82.41 235	80.89 232	86.99 242	86.18 305	76.81 241	96.27 168	93.82 243	80.49 219	75.28 264	86.11 287	67.32 209	95.75 245	75.48 236	67.03 319	88.42 283

v10		81.43 247	79.53 254	87.11 239	86.38 299	78.87 186	94.31 243	93.43 263	77.88 264	73.24 278	85.26 296	65.44 220	95.75 245	72.14 261	67.71 312	86.72 311

TAMVS		88.48 132	87.79 128	90.56 160	91.09 239	79.18 178	96.45 156	95.88 135	83.64 166	83.12 171	93.33 180	75.94 123	95.74 248	82.40 172	88.27 169	96.75 151

cl22		85.11 190	84.17 188	87.92 218	95.06 132	78.82 187	95.51 203	94.22 223	79.74 237	76.77 237	87.92 255	75.96 122	95.68 249	79.93 192	72.42 273	89.27 258

UniMVSNet_ETH3D		80.86 255	78.75 260	87.22 238	86.31 301	72.02 293	91.95 285	93.76 251	73.51 301	75.06 266	90.16 227	43.04 331	95.66 250	76.37 228	78.55 245	93.98 206

Anonymous20231211		79.72 263	77.19 270	87.33 233	95.59 115	77.16 237	95.18 220	94.18 226	59.31 356	72.57 285	86.20 285	47.89 316	95.66 250	74.53 246	69.24 297	89.18 260

CHOSEN 280x420		91.71 65	91.85 58	91.29 138	94.94 134	82.69 97	87.89 318	96.17 118	85.94 107	87.27 129	94.31 162	90.27 9	95.65 252	94.04 49	95.86 99	95.53 179

CDS-MVSNet		89.50 108	88.96 109	91.14 144	91.94 227	80.93 133	97.09 114	95.81 139	84.26 148	84.72 152	94.20 167	80.31 60	95.64 253	83.37 166	88.96 161	96.85 146
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		71.36 314	67.00 319	84.46 286	90.58 249	69.74 314	79.15 350	87.74 339	46.09 362	61.96 337	50.50 366	45.14 323	95.64 253	53.74 343	88.11 171	88.00 291

v7n		79.32 269	77.34 268	85.28 271	84.05 332	72.89 287	93.38 262	93.87 240	75.02 291	70.68 295	84.37 308	59.58 256	95.62 255	67.60 286	67.50 314	87.32 306

Effi-MVS+-dtu		84.61 197	84.90 178	83.72 295	91.96 225	63.14 340	94.95 228	93.34 269	85.57 113	79.79 211	87.12 267	61.99 243	95.61 256	83.55 162	85.83 191	92.41 220

JIA-IIPM		79.00 271	77.20 269	84.40 287	89.74 264	64.06 336	75.30 359	95.44 159	62.15 343	81.90 188	59.08 363	78.92 75	95.59 257	66.51 295	85.78 192	93.54 212

Fast-Effi-MVS+-dtu		83.33 216	82.60 212	85.50 268	89.55 267	69.38 317	96.09 180	91.38 300	82.30 191	75.96 254	91.41 203	56.71 280	95.58 258	75.13 239	84.90 199	91.54 222

EG-PatchMatch MVS		74.92 297	72.02 303	83.62 296	83.76 335	73.28 281	93.62 257	92.04 292	68.57 329	58.88 346	83.80 313	31.87 356	95.57 259	56.97 334	78.67 240	82.00 349

UniMVSNet (Re)		85.31 187	84.23 187	88.55 203	89.75 262	80.55 142	96.72 140	96.89 37	85.42 116	78.40 222	88.93 239	75.38 136	95.52 260	78.58 204	68.02 308	89.57 251

OpenMVS_ROB	68.52 20	73.02 307	69.57 313	83.37 300	80.54 343	71.82 297	93.60 258	88.22 335	62.37 342	61.98 336	83.15 318	35.31 350	95.47 261	45.08 360	75.88 256	82.82 341

miper_enhance_ethall		85.95 176	85.20 169	88.19 214	94.85 137	79.76 161	96.00 181	94.06 233	82.98 180	77.74 227	88.76 241	79.42 68	95.46 262	80.58 183	72.42 273	89.36 257

patchmatchnet-post											77.09 344	77.78 94	95.39 263

SCA		85.63 181	83.64 196	91.60 131	92.30 208	81.86 114	92.88 276	95.56 150	84.85 129	82.52 175	85.12 302	58.04 268	95.39 263	73.89 250	87.58 175	97.54 114

jajsoiax		82.12 239	81.15 231	85.03 275	84.19 329	70.70 305	94.22 248	93.95 235	83.07 176	73.48 274	89.75 231	49.66 309	95.37 265	82.24 174	79.76 229	89.02 268

mvs_anonymous		88.68 126	87.62 133	91.86 120	94.80 138	81.69 121	93.53 260	94.92 182	82.03 197	78.87 218	90.43 222	75.77 125	95.34 266	85.04 143	93.16 128	98.55 48

ITE_SJBPF				82.38 307	87.00 295	65.59 330		89.55 321	79.99 233	69.37 304	91.30 206	41.60 336	95.33 267	62.86 312	74.63 264	86.24 318

eth_miper_zixun_eth		83.12 221	82.01 218	86.47 249	91.85 230	74.80 268	94.33 242	93.18 274	79.11 250	75.74 260	87.25 265	72.71 170	95.32 268	76.78 222	67.13 317	89.27 258

mvs_tets		81.74 242	80.71 237	84.84 276	84.22 328	70.29 308	93.91 252	93.78 248	82.77 184	73.37 275	89.46 234	47.36 319	95.31 269	81.99 175	79.55 234	88.92 274

FIs		86.73 165	86.10 159	88.61 202	90.05 258	80.21 152	96.14 177	96.95 33	85.56 115	78.37 223	92.30 191	76.73 110	95.28 270	79.51 194	79.27 235	90.35 235

pm-mvs1		80.05 260	78.02 264	86.15 256	85.42 315	75.81 260	95.11 223	92.69 284	77.13 274	70.36 298	87.43 260	58.44 266	95.27 271	71.36 266	64.25 329	87.36 305

miper_ehance_all_eth		84.57 198	83.60 198	87.50 230	92.64 200	78.25 204	95.40 209	93.47 261	79.28 247	76.41 244	87.64 258	76.53 112	95.24 272	78.58 204	72.42 273	89.01 269

ADS-MVSNet		81.26 249	78.36 261	89.96 178	93.78 164	79.78 160	79.48 347	93.60 257	73.09 306	80.14 207	79.99 334	62.15 240	95.24 272	59.49 322	83.52 204	94.85 190

cl____		83.27 217	82.12 216	86.74 244	92.20 213	75.95 257	95.11 223	93.27 271	78.44 261	74.82 267	87.02 269	74.19 155	95.19 274	74.67 243	69.32 295	89.09 264

DIV-MVS_self_test		83.27 217	82.12 216	86.74 244	92.19 214	75.92 259	95.11 223	93.26 272	78.44 261	74.81 268	87.08 268	74.19 155	95.19 274	74.66 244	69.30 296	89.11 263

IterMVS-LS		83.93 206	82.80 209	87.31 235	91.46 235	77.39 231	95.66 198	93.43 263	80.44 220	75.51 261	87.26 264	73.72 161	95.16 276	76.99 219	70.72 282	89.39 252
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
UniMVSNet_NR-MVSNet		85.49 184	84.59 179	88.21 213	89.44 270	79.36 173	96.71 142	96.41 97	85.22 121	78.11 225	90.98 213	76.97 106	95.14 277	79.14 199	68.30 305	90.12 240

DU-MVS		84.57 198	83.33 202	88.28 209	88.76 274	79.36 173	96.43 159	95.41 163	85.42 116	78.11 225	90.82 215	67.61 204	95.14 277	79.14 199	68.30 305	90.33 236

c3_l		83.80 209	82.65 211	87.25 237	92.10 218	77.74 225	95.25 214	93.04 279	78.58 258	76.01 252	87.21 266	75.25 141	95.11 279	77.54 214	68.89 299	88.91 275

MVSFormer		91.36 73	90.57 78	93.73 51	93.00 188	88.08 15	94.80 233	94.48 210	80.74 212	94.90 33	97.13 88	78.84 77	95.10 280	83.77 156	97.46 67	98.02 77

test_djsdf		83.00 225	82.45 214	84.64 281	84.07 331	69.78 313	94.80 233	94.48 210	80.74 212	75.41 263	87.70 257	61.32 248	95.10 280	83.77 156	79.76 229	89.04 267

RRT_MVS		83.88 207	83.27 203	85.71 262	87.53 292	72.12 291	95.35 210	94.33 219	83.81 161	75.86 256	91.28 207	60.55 250	95.09 282	83.93 152	76.76 253	89.90 248

test_post1							85.88 333				30.24 375	73.77 159	95.07 283	73.89 250

pmmvs4		82.54 231	80.79 233	87.79 220	86.11 306	80.49 146	93.55 259	93.18 274	77.29 272	73.35 276	89.40 235	65.26 224	95.05 284	75.32 237	73.61 267	87.83 293

anonymousdsp		80.98 254	79.97 249	84.01 289	81.73 339	70.44 307	92.49 280	93.58 259	77.10 276	72.98 281	86.31 283	57.58 272	94.90 285	79.32 196	78.63 243	86.69 312

NR-MVSNet		83.35 215	81.52 227	88.84 197	88.76 274	81.31 127	94.45 237	95.16 173	84.65 136	67.81 308	90.82 215	70.36 196	94.87 286	74.75 241	66.89 320	90.33 236

WR-MVS		84.32 202	82.96 205	88.41 205	89.38 271	80.32 147	96.59 147	96.25 111	83.97 154	76.63 239	90.36 223	67.53 206	94.86 287	75.82 234	70.09 289	90.06 245

pmmvs6		74.65 299	71.67 304	83.60 297	79.13 347	69.94 310	93.31 267	90.88 312	61.05 351	65.83 320	84.15 311	43.43 327	94.83 288	66.62 292	60.63 338	86.02 322

FC-MVSNet-test		85.96 175	85.39 166	87.66 223	89.38 271	78.02 212	95.65 199	96.87 38	85.12 125	77.34 229	91.94 198	76.28 118	94.74 289	77.09 218	78.82 239	90.21 238

Vis-MVSNet (Re-imp)		88.88 121	88.87 112	88.91 196	93.89 163	74.43 272	96.93 127	94.19 225	84.39 143	83.22 170	95.67 126	78.24 85	94.70 290	78.88 202	94.40 112	97.61 112

tpm		85.55 183	84.47 184	88.80 199	90.19 255	75.39 263	88.79 310	94.69 195	84.83 130	83.96 161	85.21 298	78.22 86	94.68 291	76.32 229	78.02 250	96.34 161

TranMVSNet+NR-MVSNet		83.24 219	81.71 223	87.83 219	87.71 288	78.81 189	96.13 179	94.82 189	84.52 139	76.18 251	90.78 217	64.07 230	94.60 292	74.60 245	66.59 322	90.09 243

bld_raw_dy_0_64		82.13 238	80.76 235	86.24 255	85.78 312	75.03 267	94.40 241	82.62 358	83.12 174	76.46 242	90.96 214	53.83 299	94.55 293	81.04 180	78.60 244	89.14 262

Patchmatch-test		78.25 275	74.72 288	88.83 198	91.20 236	74.10 275	73.91 362	88.70 333	59.89 355	66.82 314	85.12 302	78.38 83	94.54 294	48.84 355	79.58 233	97.86 92

mvsany_test1		87.58 153	88.22 119	85.67 264	89.78 261	67.18 326	95.25 214	87.93 336	83.96 155	88.79 111	97.06 93	72.52 172	94.53 295	92.21 71	86.45 182	95.30 186

FMVSNet3		84.71 195	82.71 210	90.70 157	94.55 143	87.71 19	95.92 186	94.67 198	81.73 200	75.82 257	88.08 253	66.99 211	94.47 296	71.23 267	75.38 259	89.91 247

pmmvs5		81.34 248	79.54 253	86.73 247	85.02 321	76.91 238	96.22 171	91.65 297	77.65 267	73.55 273	88.61 243	55.70 288	94.43 297	74.12 249	73.35 270	88.86 276

Baseline_NR-MVSNet		81.22 250	80.07 247	84.68 279	85.32 319	75.12 265	96.48 153	88.80 330	76.24 283	77.28 231	86.40 282	67.61 204	94.39 298	75.73 235	66.73 321	84.54 332

FMVSNet2		82.79 227	80.44 241	89.83 183	92.66 197	85.43 46	95.42 207	94.35 217	79.06 252	74.46 269	87.28 262	56.38 285	94.31 299	69.72 279	74.68 263	89.76 249

SixPastTwentyTwo		76.04 291	74.32 292	81.22 313	84.54 325	61.43 346	91.16 295	89.30 325	77.89 263	64.04 326	86.31 283	48.23 311	94.29 300	63.54 309	63.84 331	87.93 292

TDRefinement		69.20 319	65.78 323	79.48 321	66.04 367	62.21 342	88.21 314	86.12 345	62.92 341	61.03 341	85.61 291	33.23 353	94.16 301	55.82 339	53.02 351	82.08 348

TransMVSNet (Re)		76.94 287	74.38 291	84.62 282	85.92 309	75.25 264	95.28 211	89.18 326	73.88 299	67.22 309	86.46 278	59.64 254	94.10 302	59.24 325	52.57 353	84.50 333

OurMVSNet-221017-0		77.18 286	76.06 278	80.55 317	83.78 334	60.00 350	90.35 300	91.05 308	77.01 278	66.62 317	87.92 255	47.73 317	94.03 303	71.63 263	68.44 303	87.62 298

EPNet_dtu		87.65 152	87.89 125	86.93 243	94.57 142	71.37 303	96.72 140	96.50 87	88.56 56	87.12 131	95.02 148	75.91 124	94.01 304	66.62 292	90.00 152	95.42 182
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
lessismore_v0				79.98 319	80.59 342	58.34 353		80.87 360		58.49 347	83.46 316	43.10 330	93.89 305	63.11 311	48.68 357	87.72 294

GBi-Net		82.42 233	80.43 242	88.39 206	92.66 197	81.95 108	94.30 244	93.38 265	79.06 252	75.82 257	85.66 288	56.38 285	93.84 306	71.23 267	75.38 259	89.38 254

test1		82.42 233	80.43 242	88.39 206	92.66 197	81.95 108	94.30 244	93.38 265	79.06 252	75.82 257	85.66 288	56.38 285	93.84 306	71.23 267	75.38 259	89.38 254

FMVSNet1		79.50 266	76.54 276	88.39 206	88.47 279	81.95 108	94.30 244	93.38 265	73.14 305	72.04 289	85.66 288	43.86 325	93.84 306	65.48 299	72.53 272	89.38 254

test_0402		72.68 308	69.54 314	82.09 310	88.67 277	71.81 298	92.72 278	86.77 343	61.52 346	62.21 335	83.91 312	43.22 329	93.76 309	34.60 365	72.23 276	80.72 353

CR-MVSNet		83.53 213	81.36 229	90.06 173	90.16 256	79.75 162	79.02 351	91.12 305	84.24 149	82.27 183	80.35 331	75.45 132	93.67 310	63.37 310	86.25 184	96.75 151

ET-MVSNet_ETH3D		90.01 100	89.03 106	92.95 80	94.38 150	86.77 28	98.14 34	96.31 108	89.30 45	63.33 330	96.72 107	90.09 11	93.63 311	90.70 88	82.29 219	98.46 51

Patchmtry		77.36 284	74.59 289	85.67 264	89.75 262	75.75 261	77.85 354	91.12 305	60.28 352	71.23 291	80.35 331	75.45 132	93.56 312	57.94 327	67.34 316	87.68 296

test_fmvs2		79.59 264	79.90 251	78.67 324	82.86 337	55.82 357	95.20 217	89.55 321	81.09 206	80.12 209	89.80 230	34.31 351	93.51 313	87.82 122	78.36 247	86.69 312

miper_lstm_enhance		81.66 245	80.66 238	84.67 280	91.19 237	71.97 295	91.94 286	93.19 273	77.86 265	72.27 287	85.26 296	73.46 164	93.42 314	73.71 253	67.05 318	88.61 277

PatchT		79.75 262	76.85 273	88.42 204	89.55 267	75.49 262	77.37 355	94.61 204	63.07 340	82.46 177	73.32 353	75.52 131	93.41 315	51.36 348	84.43 200	96.36 159

ppachtmachnet_test		77.19 285	74.22 293	86.13 257	85.39 316	78.22 205	93.98 251	91.36 302	71.74 317	67.11 311	84.87 305	56.67 281	93.37 316	52.21 346	64.59 326	86.80 310

MVS_0304		78.43 273	76.70 274	83.60 297	88.22 282	69.81 312	92.91 275	95.10 174	72.32 313	78.71 219	80.29 333	33.78 352	93.37 316	68.77 283	80.23 227	87.63 297

our_test_3		77.90 279	75.37 283	85.48 269	85.39 316	76.74 242	93.63 256	91.67 296	73.39 304	65.72 321	84.65 307	58.20 267	93.13 318	57.82 328	67.87 309	86.57 314

LCM-MVSNet-Re		83.75 210	83.54 199	84.39 288	93.54 171	64.14 335	92.51 279	84.03 353	83.90 158	66.14 319	86.59 275	67.36 208	92.68 319	84.89 145	92.87 130	96.35 160

WR-MVS_H		81.02 252	80.09 245	83.79 292	88.08 284	71.26 304	94.46 236	96.54 82	80.08 230	72.81 283	86.82 271	70.36 196	92.65 320	64.18 304	67.50 314	87.46 304

ambc				76.02 333	68.11 364	51.43 361	64.97 367	89.59 320		60.49 342	74.49 349	17.17 366	92.46 321	61.50 316	52.85 352	84.17 336

PEN-MVS		79.47 267	78.26 263	83.08 302	86.36 300	68.58 320	93.85 253	94.77 193	79.76 236	71.37 290	88.55 244	59.79 253	92.46 321	64.50 303	65.40 324	88.19 287

CP-MVSNet		81.01 253	80.08 246	83.79 292	87.91 286	70.51 306	94.29 247	95.65 146	80.83 210	72.54 286	88.84 240	63.71 231	92.32 323	68.58 285	68.36 304	88.55 278

LF4IMVS		72.36 310	70.82 307	76.95 329	79.18 346	56.33 354	86.12 331	86.11 346	69.30 328	63.06 332	86.66 274	33.03 354	92.25 324	65.33 300	68.64 301	82.28 347

PS-CasMVS		80.27 259	79.18 255	83.52 299	87.56 290	69.88 311	94.08 250	95.29 169	80.27 227	72.08 288	88.51 247	59.22 261	92.23 325	67.49 287	68.15 307	88.45 282

DTE-MVSNet		78.37 274	77.06 271	82.32 309	85.22 320	67.17 327	93.40 261	93.66 254	78.71 257	70.53 297	88.29 249	59.06 262	92.23 325	61.38 317	63.28 333	87.56 301

UnsupCasMVSNet_bld		68.60 321	64.50 325	80.92 315	74.63 360	67.80 322	83.97 339	92.94 280	65.12 338	54.63 355	68.23 359	35.97 347	92.17 327	60.13 320	44.83 362	82.78 342

KD-MVS_2432*1600		77.63 281	74.92 286	85.77 260	90.86 244	79.44 170	88.08 315	93.92 237	76.26 281	67.05 312	82.78 319	72.15 178	91.92 328	61.53 314	41.62 367	85.94 323

miper_refine_blended		77.63 281	74.92 286	85.77 260	90.86 244	79.44 170	88.08 315	93.92 237	76.26 281	67.05 312	82.78 319	72.15 178	91.92 328	61.53 314	41.62 367	85.94 323

test_vis3_rt		54.10 330	51.04 333	63.27 348	58.16 370	46.08 369	84.17 338	49.32 381	56.48 360	36.56 365	49.48 368	8.03 377	91.91 330	67.29 289	49.87 355	51.82 367

N_pmnet		61.30 326	60.20 329	64.60 345	84.32 327	17.00 383	91.67 292	10.98 382	61.77 345	58.45 348	78.55 338	49.89 308	91.83 331	42.27 362	63.94 330	84.97 330

K. test v3		73.62 301	71.59 305	79.69 320	82.98 336	59.85 351	90.85 299	88.83 329	77.13 274	58.90 345	82.11 321	43.62 326	91.72 332	65.83 298	54.10 348	87.50 303

Patchmatch-RL test		76.65 289	74.01 296	84.55 283	77.37 353	64.23 334	78.49 353	82.84 357	78.48 259	64.63 325	73.40 352	76.05 121	91.70 333	76.99 219	57.84 342	97.72 102

IterMVS-SCA-FT		80.51 258	79.10 257	84.73 278	89.63 266	74.66 269	92.98 273	91.81 295	80.05 231	71.06 294	85.18 299	58.04 268	91.40 334	72.48 260	70.70 283	88.12 289

IterMVS		80.67 256	79.16 256	85.20 272	89.79 260	76.08 251	92.97 274	91.86 293	80.28 226	71.20 292	85.14 301	57.93 271	91.34 335	72.52 259	70.74 281	88.18 288
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
MDA-MVSNet-bldmvs		71.45 313	67.94 318	81.98 311	85.33 318	68.50 321	92.35 283	88.76 331	70.40 322	42.99 361	81.96 322	46.57 320	91.31 336	48.75 356	54.39 347	86.11 320

pmmvs-eth3d		73.59 302	70.66 308	82.38 307	76.40 357	73.38 278	89.39 307	89.43 323	72.69 310	60.34 343	77.79 340	46.43 321	91.26 337	66.42 296	57.06 343	82.51 344

PM-MVS		69.32 318	66.93 320	76.49 331	73.60 361	55.84 356	85.91 332	79.32 364	74.72 293	61.09 340	78.18 339	21.76 363	91.10 338	70.86 272	56.90 344	82.51 344

Anonymous20240521		72.06 312	69.91 312	78.50 326	77.11 354	61.67 345	91.62 293	90.97 310	65.52 337	62.37 334	79.05 337	36.32 345	90.96 339	57.75 329	68.52 302	82.87 340

Anonymous20231206		75.29 296	73.64 297	80.22 318	80.75 340	63.38 339	93.36 263	90.71 315	73.09 306	67.12 310	83.70 314	50.33 307	90.85 340	53.63 344	70.10 288	86.44 315

MIMVSNet		79.18 270	75.99 279	88.72 201	87.37 293	80.66 139	79.96 346	91.82 294	77.38 271	74.33 270	81.87 323	41.78 334	90.74 341	66.36 297	83.10 209	94.76 192

UnsupCasMVSNet_eth		73.25 305	70.57 309	81.30 312	77.53 351	66.33 329	87.24 323	93.89 239	80.38 223	57.90 350	81.59 324	42.91 332	90.56 342	65.18 301	48.51 358	87.01 309

YYNet1		73.53 304	70.43 310	82.85 304	84.52 326	71.73 299	91.69 291	91.37 301	67.63 330	46.79 359	81.21 327	55.04 293	90.43 343	55.93 337	59.70 340	86.38 316

MDA-MVSNet_test_wron		73.54 303	70.43 310	82.86 303	84.55 324	71.85 296	91.74 290	91.32 304	67.63 330	46.73 360	81.09 328	55.11 292	90.42 344	55.91 338	59.76 339	86.31 317

CVMVSNet		84.83 194	85.57 163	82.63 306	91.55 232	60.38 348	95.13 221	95.03 178	80.60 215	82.10 185	94.71 155	66.40 216	90.19 345	74.30 247	90.32 151	97.31 129

ADS-MVSNet2		79.57 265	77.53 267	85.71 262	93.78 164	72.13 290	79.48 347	86.11 346	73.09 306	80.14 207	79.99 334	62.15 240	90.14 346	59.49 322	83.52 204	94.85 190

CL-MVSNet_self_test		75.81 293	74.14 295	80.83 316	78.33 349	67.79 323	94.22 248	93.52 260	77.28 273	69.82 301	81.54 325	61.47 247	89.22 347	57.59 330	53.51 349	85.48 327

test0.0.03 1		82.79 227	82.48 213	83.74 294	86.81 296	72.22 288	96.52 151	95.03 178	83.76 163	73.00 280	93.20 181	72.30 176	88.88 348	64.15 305	77.52 251	90.12 240

testgi		74.88 298	73.40 298	79.32 322	80.13 344	61.75 343	93.21 269	86.64 344	79.49 242	66.56 318	91.06 210	35.51 349	88.67 349	56.79 335	71.25 277	87.56 301

KD-MVS_self_test		70.97 315	69.31 315	75.95 335	76.24 359	55.39 359	87.45 320	90.94 311	70.20 324	62.96 333	77.48 341	44.01 324	88.09 350	61.25 318	53.26 350	84.37 334

new_pmnet		66.18 323	63.18 326	75.18 337	76.27 358	61.74 344	83.79 340	84.66 350	56.64 359	51.57 357	71.85 358	31.29 357	87.93 351	49.98 352	62.55 334	75.86 358

mvsany_test3		67.19 322	65.34 324	72.72 338	63.08 368	48.57 363	83.12 342	78.09 365	72.07 314	61.21 339	77.11 343	22.94 362	87.78 352	78.59 203	51.88 354	81.80 350

FMVSNet5		76.46 290	74.16 294	83.35 301	90.05 258	76.17 249	89.58 304	89.85 319	71.39 319	65.29 323	80.42 330	50.61 305	87.70 353	61.05 319	69.24 297	86.18 319

EU-MVSNet		76.92 288	76.95 272	76.83 330	84.10 330	54.73 360	91.77 289	92.71 283	72.74 309	69.57 303	88.69 242	58.03 270	87.43 354	64.91 302	70.00 290	88.33 285

new-patchmatchnet		68.85 320	65.93 322	77.61 328	73.57 362	63.94 337	90.11 302	88.73 332	71.62 318	55.08 354	73.60 351	40.84 339	87.22 355	51.35 349	48.49 359	81.67 352

DSMNet-mixed		73.13 306	72.45 301	75.19 336	77.51 352	46.82 365	85.09 336	82.01 359	67.61 334	69.27 305	81.33 326	50.89 303	86.28 356	54.54 341	83.80 203	92.46 218

pmmvs3		65.75 324	62.18 327	76.45 332	67.12 366	64.54 332	88.68 311	85.05 349	54.77 361	57.54 352	73.79 350	29.40 359	86.21 357	55.49 340	47.77 360	78.62 355

MIMVSNet1		69.44 317	66.65 321	77.84 327	76.48 356	62.84 341	87.42 321	88.97 328	66.96 335	57.75 351	79.72 336	32.77 355	85.83 358	46.32 358	63.42 332	84.85 331

test20.03		72.36 310	71.15 306	75.98 334	77.79 350	59.16 352	92.40 282	89.35 324	74.09 297	61.50 338	84.32 309	48.09 312	85.54 359	50.63 351	62.15 336	83.24 339

test_f		64.01 325	62.13 328	69.65 340	63.00 369	45.30 370	83.66 341	80.68 361	61.30 348	55.70 353	72.62 354	14.23 369	84.64 360	69.84 277	58.11 341	79.00 354

EGC-MVSNET		52.46 332	47.56 335	67.15 341	81.98 338	60.11 349	82.54 344	72.44 369	0.11 379	0.70 380	74.59 348	25.11 361	83.26 361	29.04 367	61.51 337	58.09 364

test_fmvs3		69.56 316	69.19 316	70.67 339	69.01 363	47.05 364	90.87 298	86.81 342	71.31 320	66.79 315	77.15 342	16.40 367	83.17 362	81.84 176	62.51 335	81.79 351

APD_test1		56.56 328	53.58 331	65.50 342	67.93 365	46.51 367	77.24 357	72.95 368	38.09 364	42.75 362	75.17 346	13.38 370	82.78 363	40.19 363	54.53 346	67.23 363

DeepMVS_CX				64.06 346	78.53 348	43.26 371		68.11 373	69.94 325	38.55 363	76.14 345	18.53 365	79.34 364	43.72 361	41.62 367	69.57 361

FPMVS		55.09 329	52.93 332	61.57 349	55.98 371	40.51 374	83.11 343	83.41 356	37.61 365	34.95 366	71.95 356	14.40 368	76.95 365	29.81 366	65.16 325	67.25 362

LCM-MVSNet		52.52 331	48.24 334	65.35 343	47.63 378	41.45 372	72.55 363	83.62 355	31.75 366	37.66 364	57.92 364	9.19 376	76.76 366	49.26 354	44.60 363	77.84 356

Gipuma		45.11 337	42.05 339	54.30 353	80.69 341	51.30 362	35.80 371	83.81 354	28.13 367	27.94 371	34.53 371	11.41 374	76.70 367	21.45 371	54.65 345	34.90 371
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMMVS2		50.90 333	46.31 336	64.67 344	55.53 372	46.67 366	77.30 356	71.02 370	40.89 363	34.16 367	59.32 362	9.83 375	76.14 368	40.09 364	28.63 370	71.21 359

PMVS	34.80 23	39.19 339	35.53 342	50.18 354	29.72 381	30.30 378	59.60 369	66.20 374	26.06 370	17.91 374	49.53 367	3.12 380	74.09 369	18.19 373	49.40 356	46.14 368
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testf1		45.70 335	42.41 337	55.58 351	53.29 375	40.02 375	68.96 365	62.67 375	27.45 368	29.85 368	61.58 360	5.98 378	73.83 370	28.49 369	43.46 365	52.90 365

APD_test2		45.70 335	42.41 337	55.58 351	53.29 375	40.02 375	68.96 365	62.67 375	27.45 368	29.85 368	61.58 360	5.98 378	73.83 370	28.49 369	43.46 365	52.90 365

ANet_high		46.22 334	41.28 341	61.04 350	39.91 380	46.25 368	70.59 364	76.18 366	58.87 357	23.09 372	48.00 369	12.58 372	66.54 372	28.65 368	13.62 373	70.35 360

test_method		56.77 327	54.53 330	63.49 347	76.49 355	40.70 373	75.68 358	74.24 367	19.47 373	48.73 358	71.89 357	19.31 364	65.80 373	57.46 331	47.51 361	83.97 337

MVE	35.65 22	33.85 340	29.49 345	46.92 355	41.86 379	36.28 377	50.45 370	56.52 378	18.75 374	18.28 373	37.84 370	2.41 381	58.41 374	18.71 372	20.62 371	46.06 369
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		32.70 341	32.39 343	33.65 357	53.35 374	25.70 380	74.07 361	53.33 379	21.08 371	17.17 375	33.63 373	11.85 373	54.84 375	12.98 374	14.04 372	20.42 372

EMVS		31.70 342	31.45 344	32.48 358	50.72 377	23.95 381	74.78 360	52.30 380	20.36 372	16.08 376	31.48 374	12.80 371	53.60 376	11.39 375	13.10 375	19.88 373

tmp_tt		41.54 338	41.93 340	40.38 356	20.10 382	26.84 379	61.93 368	59.09 377	14.81 375	28.51 370	80.58 329	35.53 348	48.33 377	63.70 308	13.11 374	45.96 370

wuyk23d		14.10 344	13.89 347	14.72 359	55.23 373	22.91 382	33.83 372	3.56 383	4.94 376	4.11 377	2.28 379	2.06 382	19.66 378	10.23 376	8.74 376	1.59 376

test123		9.07 346	11.73 349	1.11 360	0.50 384	0.77 384	89.44 306	0.20 385	0.34 378	2.15 379	10.72 378	0.34 383	0.32 379	1.79 378	0.08 378	2.23 374

testmvs		9.92 345	12.94 348	0.84 361	0.65 383	0.29 385	93.78 254	0.39 384	0.42 377	2.85 378	15.84 377	0.17 384	0.30 380	2.18 377	0.21 377	1.91 375

test_blank		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet_test		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

DCPMVS		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

cdsmvs_eth3d_5k		21.43 343	28.57 346	0.00 362	0.00 385	0.00 386	0.00 373	95.93 133	0.00 380	0.00 381	97.66 60	63.57 232	0.00 381	0.00 379	0.00 379	0.00 377

pcd_1.5k_mvsjas		5.92 348	7.89 351	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	71.04 190	0.00 381	0.00 379	0.00 379	0.00 377

sosnet-low-res		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

sosnet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uncertanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

Regformer		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

ab-mvs-re		8.11 347	10.81 350	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	97.30 81	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

uanet		0.00 349	0.00 352	0.00 362	0.00 385	0.00 386	0.00 373	0.00 386	0.00 380	0.00 381	0.00 380	0.00 385	0.00 381	0.00 379	0.00 379	0.00 377

FOURS1					98.51 39	78.01 213	98.13 37	96.21 114	83.04 177	94.39 41

test_one_0601					98.91 18	84.56 68		96.70 60	88.06 65	96.57 16	98.77 10	88.04 20

eth-test2					0.00 385

eth-test					0.00 385

RE-MVS-def			91.18 71		97.76 67	76.03 253	96.20 174	95.44 159	80.56 217	90.72 87	97.84 52	73.36 166		91.99 74	96.79 86	97.75 100

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

save fliter					98.24 51	83.34 89	98.61 23	96.57 79	91.32 20

test0726					99.05 9	85.18 52	99.11 9	96.78 44	88.75 50	97.65 9	98.91 2	87.69 22

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

MTMP							97.53 76	68.16 372

test9_res														96.00 26	99.03 13	98.31 60

agg_prior2														94.30 44	99.00 15	98.57 45

test_prior4						82.34 105	97.75 61

test_prior2							98.37 28		86.08 105	94.57 39	98.02 43	83.14 46		95.05 37	98.79 26

新几何2							96.42 160

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ACMM2							96.84 131

test222					96.15 101	78.41 199	95.87 190	96.46 91	71.97 315	89.66 100	97.45 72	76.33 117			98.24 49	98.30 61

segment_acmp												82.69 51

testdata1							95.57 202		87.44 80

plane_prior7					91.86 228	77.55 228

plane_prior6					91.98 224	77.92 218						64.77 227

plane_prior4											94.15 168

plane_prior3						77.75 224			90.17 36	81.33 193

plane_prior2							97.18 101		89.89 39

plane_prior1					91.95 226

plane_prior						77.96 215	97.52 79		90.36 34						82.96 212

n2								0.00 386

nn								0.00 386

door-mid								79.75 363

test11								96.50 87

door								80.13 362

HQP5-MVS						78.48 195

HQP-NCC					92.08 219		97.63 68		90.52 29	82.30 179

ACMP_Plane					92.08 219		97.63 68		90.52 29	82.30 179

BP-MVS														87.67 125

HQP3-MVS								94.80 190							83.01 210

HQP2-MVS												65.40 221

NP-MVS					92.04 223	78.22 205					94.56 158

MDTV_nov1_ep13_2view						81.74 119	86.80 326		80.65 214	85.65 141		74.26 154		76.52 225		96.98 139

ACMMP++_ref															78.45 246

ACMMP++															79.05 237

Test By Simon												71.65 183

High-resolution multi-view benchmark