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.

test_fmvsmvis_n_1920		99.65 4	99.61 4	99.77 49	99.38 205	99.37 94	99.58 109	99.62 37	99.41 6	99.87 19	99.92 12	98.81 44	100.00 1	99.97 1	99.93 17	99.94 7

test_fmvsm_n_1920		99.69 2	99.66 1	99.78 46	99.84 31	99.44 88	99.58 109	99.69 18	99.43 4	99.98 4	99.91 16	98.62 68	100.00 1	99.97 1	99.95 11	99.90 10

test_vis1_n_1920		98.63 153	98.40 160	99.31 136	99.86 20	97.94 239	99.67 64	99.62 37	99.43 4	99.99 2	99.91 16	87.29 355	100.00 1	99.92 7	99.92 19	99.98 2

test_fmvsmconf_n		99.70 1	99.64 2	99.87 11	99.80 48	99.66 53	99.48 171	99.64 34	99.45 2	99.92 9	99.92 12	98.62 68	99.99 4	99.96 4	99.99 1	99.96 5

patch_mono-2		99.26 63	99.62 3	98.16 283	99.81 42	94.59 344	99.52 144	99.64 34	99.33 10	99.73 55	99.90 22	99.00 22	99.99 4	99.69 12	99.98 4	99.89 13

h-mvs33		97.70 261	97.28 280	98.97 183	99.70 97	97.27 261	99.36 223	99.45 187	98.94 49	99.66 76	99.64 185	94.93 198	99.99 4	99.48 34	84.36 375	99.65 122

xiu_mvs_v1_base_debu		99.29 58	99.27 53	99.34 129	99.63 125	98.97 146	99.12 281	99.51 109	98.86 55	99.84 23	99.47 248	98.18 94	99.99 4	99.50 29	99.31 150	99.08 213

xiu_mvs_v1_base		99.29 58	99.27 53	99.34 129	99.63 125	98.97 146	99.12 281	99.51 109	98.86 55	99.84 23	99.47 248	98.18 94	99.99 4	99.50 29	99.31 150	99.08 213

xiu_mvs_v1_base_debi		99.29 58	99.27 53	99.34 129	99.63 125	98.97 146	99.12 281	99.51 109	98.86 55	99.84 23	99.47 248	98.18 94	99.99 4	99.50 29	99.31 150	99.08 213

EPNet		98.86 121	98.71 125	99.30 141	97.20 368	98.18 221	99.62 88	98.91 325	99.28 13	98.63 286	99.81 84	95.96 162	99.99 4	99.24 61	99.72 111	99.73 90
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
test_cas_vis1_n_1920		99.16 76	99.01 88	99.61 77	99.81 42	98.86 168	99.65 75	99.64 34	99.39 7	99.97 7	99.94 4	93.20 264	99.98 11	99.55 22	99.91 24	99.99 1

test_vis1_n		97.92 224	97.44 258	99.34 129	99.53 157	98.08 227	99.74 44	99.49 137	99.15 17	100.00 1	99.94 4	79.51 376	99.98 11	99.88 8	99.76 103	99.97 3

xiu_mvs_v2_base		99.26 63	99.25 57	99.29 144	99.53 157	98.91 162	99.02 304	99.45 187	98.80 64	99.71 61	99.26 302	98.94 29	99.98 11	99.34 48	99.23 154	98.98 227

PS-MVSNAJ		99.32 54	99.32 36	99.30 141	99.57 146	98.94 158	98.97 317	99.46 176	98.92 52	99.71 61	99.24 304	99.01 18	99.98 11	99.35 44	99.66 121	98.97 228

QAPM		98.67 149	98.30 167	99.80 40	99.20 249	99.67 51	99.77 34	99.72 11	94.74 342	98.73 267	99.90 22	95.78 172	99.98 11	96.96 278	99.88 44	99.76 80

3Dnovator	97.25 9	99.24 67	99.05 76	99.81 38	99.12 267	99.66 53	99.84 13	99.74 10	99.09 27	98.92 242	99.90 22	95.94 165	99.98 11	98.95 86	99.92 19	99.79 67

OpenMVS	96.50 16	98.47 159	98.12 179	99.52 104	99.04 285	99.53 76	99.82 17	99.72 11	94.56 345	98.08 315	99.88 32	94.73 215	99.98 11	97.47 248	99.76 103	99.06 219

test_fmvsmconf0.1_n		99.55 11	99.45 18	99.86 21	99.44 190	99.65 57	99.50 156	99.61 42	99.45 2	99.87 19	99.92 12	97.31 118	99.97 18	99.95 5	99.99 1	99.97 3

test_fmvs1_n		98.41 165	98.14 176	99.21 155	99.82 38	97.71 251	99.74 44	99.49 137	99.32 11	99.99 2	99.95 2	85.32 362	99.97 18	99.82 9	99.84 70	99.96 5

CANet_DTU		98.97 111	98.87 108	99.25 150	99.33 218	98.42 213	99.08 290	99.30 268	99.16 16	99.43 133	99.75 131	95.27 189	99.97 18	98.56 151	99.95 11	99.36 192

MTAPA		99.52 14	99.39 23	99.89 4	99.90 4	99.86 13	99.66 69	99.47 167	98.79 65	99.68 67	99.81 84	98.43 81	99.97 18	98.88 95	99.90 32	99.83 42

PGM-MVS		99.45 29	99.31 43	99.86 21	99.87 15	99.78 36	99.58 109	99.65 32	97.84 164	99.71 61	99.80 97	99.12 13	99.97 18	98.33 172	99.87 47	99.83 42

mPP-MVS		99.44 33	99.30 45	99.86 21	99.88 11	99.79 30	99.69 55	99.48 149	98.12 131	99.50 119	99.75 131	98.78 48	99.97 18	98.57 148	99.89 41	99.83 42

CP-MVS		99.45 29	99.32 36	99.85 27	99.83 36	99.75 39	99.69 55	99.52 95	98.07 141	99.53 114	99.63 191	98.93 33	99.97 18	98.74 120	99.91 24	99.83 42

SteuartSystems-ACMMP		99.54 12	99.42 19	99.87 11	99.82 38	99.81 25	99.59 101	99.51 109	98.62 76	99.79 36	99.83 64	99.28 4	99.97 18	98.48 158	99.90 32	99.84 33
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 72	98.97 94	99.82 35	99.17 260	99.68 48	99.81 20	99.51 109	99.20 15	98.72 268	99.89 26	95.68 177	99.97 18	98.86 103	99.86 55	99.81 54

mvsany_test1		99.50 16	99.46 17	99.62 76	99.61 135	99.09 129	98.94 323	99.48 149	99.10 23	99.96 8	99.91 16	98.85 39	99.96 27	99.72 11	99.58 130	99.82 47

test_fmvs1		98.88 117	98.79 119	99.16 160	99.69 101	97.61 253	99.55 132	99.49 137	99.32 11	99.98 4	99.91 16	91.41 311	99.96 27	99.82 9	99.92 19	99.90 10

DVP-MVS++		99.59 6	99.50 11	99.88 5	99.51 163	99.88 8	99.87 9	99.51 109	98.99 40	99.88 14	99.81 84	99.27 5	99.96 27	98.85 105	99.80 90	99.81 54

MSC_two_6792asdad				99.87 11	99.51 163	99.76 37		99.33 250					99.96 27	98.87 98	99.84 70	99.89 13

No_MVS				99.87 11	99.51 163	99.76 37		99.33 250					99.96 27	98.87 98	99.84 70	99.89 13

ZD-MVS					99.71 92	99.79 30		99.61 42	96.84 261	99.56 107	99.54 224	98.58 70	99.96 27	96.93 281	99.75 105

SED-MVS		99.61 5	99.52 9	99.88 5	99.84 31	99.90 2	99.60 95	99.48 149	99.08 28	99.91 10	99.81 84	99.20 7	99.96 27	98.91 92	99.85 62	99.79 67

test_241102_TWO								99.48 149	99.08 28	99.88 14	99.81 84	98.94 29	99.96 27	98.91 92	99.84 70	99.88 19

ZNCC-MVS		99.47 25	99.33 34	99.87 11	99.87 15	99.81 25	99.64 78	99.67 23	98.08 140	99.55 111	99.64 185	98.91 34	99.96 27	98.72 123	99.90 32	99.82 47

DVP-MVS		99.57 10	99.47 15	99.88 5	99.85 25	99.89 4	99.57 116	99.37 232	99.10 23	99.81 31	99.80 97	98.94 29	99.96 27	98.93 89	99.86 55	99.81 54
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									98.99 40	99.81 31	99.80 97	99.09 14	99.96 27	98.85 105	99.90 32	99.88 19

test_0728_SECOND				99.91 2	99.84 31	99.89 4	99.57 116	99.51 109					99.96 27	98.93 89	99.86 55	99.88 19

SR-MVS		99.43 36	99.29 49	99.86 21	99.75 69	99.83 16	99.59 101	99.62 37	98.21 117	99.73 55	99.79 108	98.68 62	99.96 27	98.44 163	99.77 100	99.79 67

DPE-MVS		99.46 27	99.32 36	99.91 2	99.78 52	99.88 8	99.36 223	99.51 109	98.73 70	99.88 14	99.84 60	98.72 59	99.96 27	98.16 185	99.87 47	99.88 19
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MVS_0304		99.42 38	99.32 36	99.72 58	99.70 97	99.27 106	99.52 144	97.57 373	99.51 1	99.82 29	99.78 114	98.09 98	99.96 27	99.97 1	99.97 7	99.94 7

UA-Net		99.42 38	99.29 49	99.80 40	99.62 131	99.55 71	99.50 156	99.70 15	98.79 65	99.77 45	99.96 1	97.45 113	99.96 27	98.92 91	99.90 32	99.89 13

HFP-MVS		99.49 18	99.37 26	99.86 21	99.87 15	99.80 27	99.66 69	99.67 23	98.15 126	99.68 67	99.69 161	99.06 16	99.96 27	98.69 128	99.87 47	99.84 33

region2R		99.48 22	99.35 30	99.87 11	99.88 11	99.80 27	99.65 75	99.66 27	98.13 130	99.66 76	99.68 167	98.96 24	99.96 27	98.62 136	99.87 47	99.84 33

HPM-MVS++		99.39 47	99.23 60	99.87 11	99.75 69	99.84 15	99.43 191	99.51 109	98.68 74	99.27 177	99.53 228	98.64 67	99.96 27	98.44 163	99.80 90	99.79 67

APDe-MVS		99.66 3	99.57 6	99.92 1	99.77 58	99.89 4	99.75 41	99.56 63	99.02 33	99.88 14	99.85 50	99.18 10	99.96 27	99.22 62	99.92 19	99.90 10

ACMMPR		99.49 18	99.36 28	99.86 21	99.87 15	99.79 30	99.66 69	99.67 23	98.15 126	99.67 71	99.69 161	98.95 27	99.96 27	98.69 128	99.87 47	99.84 33

MP-MVS		99.33 53	99.15 66	99.87 11	99.88 11	99.82 22	99.66 69	99.46 176	98.09 136	99.48 123	99.74 136	98.29 89	99.96 27	97.93 201	99.87 47	99.82 47
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 92	98.90 103	99.74 55	99.80 48	99.46 86	99.59 101	99.49 137	97.03 248	99.63 89	99.69 161	97.27 121	99.96 27	97.82 211	99.84 70	99.81 54

PVSNet_Blended_VisFu		99.36 50	99.28 51	99.61 77	99.86 20	99.07 134	99.47 177	99.93 2	97.66 185	99.71 61	99.86 45	97.73 108	99.96 27	99.47 36	99.82 83	99.79 67

UGNet		98.87 118	98.69 127	99.40 123	99.22 246	98.72 181	99.44 187	99.68 20	99.24 14	99.18 200	99.42 258	92.74 274	99.96 27	99.34 48	99.94 16	99.53 159
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
CSCG		99.32 54	99.32 36	99.32 135	99.85 25	98.29 216	99.71 51	99.66 27	98.11 133	99.41 140	99.80 97	98.37 86	99.96 27	98.99 82	99.96 10	99.72 96

ACMMP		99.45 29	99.32 36	99.82 35	99.89 8	99.67 51	99.62 88	99.69 18	98.12 131	99.63 89	99.84 60	98.73 58	99.96 27	98.55 154	99.83 79	99.81 54
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
test_fmvsmconf0.01_n		99.22 69	99.03 80	99.79 43	98.42 348	99.48 83	99.55 132	99.51 109	99.39 7	99.78 41	99.93 7	94.80 207	99.95 54	99.93 6	99.95 11	99.94 7

SR-MVS-dyc-post		99.45 29	99.31 43	99.85 27	99.76 61	99.82 22	99.63 82	99.52 95	98.38 95	99.76 50	99.82 71	98.53 74	99.95 54	98.61 139	99.81 86	99.77 75

GST-MVS		99.40 46	99.24 58	99.85 27	99.86 20	99.79 30	99.60 95	99.67 23	97.97 152	99.63 89	99.68 167	98.52 75	99.95 54	98.38 166	99.86 55	99.81 54

CANet		99.25 66	99.14 67	99.59 80	99.41 196	99.16 118	99.35 228	99.57 58	98.82 60	99.51 118	99.61 200	96.46 147	99.95 54	99.59 18	99.98 4	99.65 122

MP-MVS-pluss		99.37 49	99.20 62	99.88 5	99.90 4	99.87 12	99.30 238	99.52 95	97.18 231	99.60 99	99.79 108	98.79 47	99.95 54	98.83 111	99.91 24	99.83 42
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 38	99.27 53	99.88 5	99.89 8	99.80 27	99.67 64	99.50 129	98.70 72	99.77 45	99.49 240	98.21 92	99.95 54	98.46 162	99.77 100	99.88 19
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
testdata2													99.95 54	96.67 293

APD-MVS_3200maxsize		99.48 22	99.35 30	99.85 27	99.76 61	99.83 16	99.63 82	99.54 79	98.36 99	99.79 36	99.82 71	98.86 38	99.95 54	98.62 136	99.81 86	99.78 73

RPMNet		96.72 300	95.90 312	99.19 157	99.18 254	98.49 205	99.22 267	99.52 95	88.72 375	99.56 107	97.38 369	94.08 243	99.95 54	86.87 378	98.58 198	99.14 205

sss		99.17 74	99.05 76	99.53 98	99.62 131	98.97 146	99.36 223	99.62 37	97.83 165	99.67 71	99.65 179	97.37 117	99.95 54	99.19 64	99.19 157	99.68 112

TSAR-MVS + MP.		99.58 7	99.50 11	99.81 38	99.91 1	99.66 53	99.63 82	99.39 217	98.91 53	99.78 41	99.85 50	99.36 2	99.94 64	98.84 108	99.88 44	99.82 47
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
XVS		99.53 13	99.42 19	99.87 11	99.85 25	99.83 16	99.69 55	99.68 20	98.98 43	99.37 153	99.74 136	98.81 44	99.94 64	98.79 116	99.86 55	99.84 33

X-MVStestdata		96.55 302	95.45 320	99.87 11	99.85 25	99.83 16	99.69 55	99.68 20	98.98 43	99.37 153	64.01 392	98.81 44	99.94 64	98.79 116	99.86 55	99.84 33

旧先验2							98.96 318		96.70 268	99.47 124			99.94 64	98.19 181

新几何1				99.75 52	99.75 69	99.59 64		99.54 79	96.76 264	99.29 172	99.64 185	98.43 81	99.94 64	96.92 283	99.66 121	99.72 96

testdata				99.54 90	99.75 69	98.95 155		99.51 109	97.07 243	99.43 133	99.70 151	98.87 37	99.94 64	97.76 218	99.64 124	99.72 96

HPM-MVS		99.42 38	99.28 51	99.83 34	99.90 4	99.72 42	99.81 20	99.54 79	97.59 189	99.68 67	99.63 191	98.91 34	99.94 64	98.58 145	99.91 24	99.84 33
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 70	99.10 71	99.45 116	99.89 8	98.52 201	99.39 212	99.94 1	98.73 70	99.11 209	99.89 26	95.50 181	99.94 64	99.50 29	99.97 7	99.89 13

APD-MVS		99.27 61	99.08 74	99.84 33	99.75 69	99.79 30	99.50 156	99.50 129	97.16 233	99.77 45	99.82 71	98.78 48	99.94 64	97.56 239	99.86 55	99.80 63
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 22	99.42 19	99.65 66	99.72 87	99.40 93	99.05 296	99.66 27	99.14 18	99.57 106	99.80 97	98.46 79	99.94 64	99.57 20	99.84 70	99.60 139
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
WTY-MVS		99.06 100	98.88 107	99.61 77	99.62 131	99.16 118	99.37 219	99.56 63	98.04 147	99.53 114	99.62 196	96.84 135	99.94 64	98.85 105	98.49 206	99.72 96

DeepC-MVS	98.35 2	99.30 56	99.19 63	99.64 71	99.82 38	99.23 111	99.62 88	99.55 71	98.94 49	99.63 89	99.95 2	95.82 171	99.94 64	99.37 43	99.97 7	99.73 90
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		99.27 61	99.12 69	99.74 55	99.18 254	99.75 39	99.56 122	99.57 58	98.45 89	99.49 122	99.85 50	97.77 107	99.94 64	98.33 172	99.84 70	99.52 160

SDMVSNet		99.11 92	98.90 103	99.75 52	99.81 42	99.59 64	99.81 20	99.65 32	98.78 68	99.64 86	99.88 32	94.56 225	99.93 77	99.67 14	98.26 216	99.72 96

FE-MVS		98.48 158	98.17 172	99.40 123	99.54 156	98.96 150	99.68 61	98.81 336	95.54 326	99.62 93	99.70 151	93.82 251	99.93 77	97.35 255	99.46 137	99.32 197

SF-MVS		99.38 48	99.24 58	99.79 43	99.79 50	99.68 48	99.57 116	99.54 79	97.82 169	99.71 61	99.80 97	98.95 27	99.93 77	98.19 181	99.84 70	99.74 85

dcpmvs_2		99.23 68	99.58 5	98.16 283	99.83 36	94.68 342	99.76 37	99.52 95	99.07 30	99.98 4	99.88 32	98.56 72	99.93 77	99.67 14	99.98 4	99.87 24

Anonymous20240529		98.09 194	97.68 230	99.34 129	99.66 114	98.44 210	99.40 208	99.43 201	93.67 352	99.22 188	99.89 26	90.23 327	99.93 77	99.26 60	98.33 210	99.66 118

ACMMP_NAP		99.47 25	99.34 32	99.88 5	99.87 15	99.86 13	99.47 177	99.48 149	98.05 146	99.76 50	99.86 45	98.82 43	99.93 77	98.82 115	99.91 24	99.84 33

EI-MVSNet-UG-set		99.58 7	99.57 6	99.64 71	99.78 52	99.14 124	99.60 95	99.45 187	99.01 35	99.90 12	99.83 64	98.98 23	99.93 77	99.59 18	99.95 11	99.86 26

无先验							98.99 311	99.51 109	96.89 258				99.93 77	97.53 242		99.72 96

VDDNet		97.55 273	97.02 290	99.16 160	99.49 174	98.12 226	99.38 217	99.30 268	95.35 328	99.68 67	99.90 22	82.62 372	99.93 77	99.31 51	98.13 227	99.42 185

ab-mvs		98.86 121	98.63 135	99.54 90	99.64 122	99.19 113	99.44 187	99.54 79	97.77 172	99.30 169	99.81 84	94.20 237	99.93 77	99.17 67	98.82 189	99.49 170

F-COLMAP		99.19 70	99.04 78	99.64 71	99.78 52	99.27 106	99.42 198	99.54 79	97.29 222	99.41 140	99.59 205	98.42 83	99.93 77	98.19 181	99.69 116	99.73 90

Anonymous202405211		98.30 175	97.98 196	99.26 149	99.57 146	98.16 222	99.41 200	98.55 355	96.03 320	99.19 197	99.74 136	91.87 298	99.92 88	99.16 68	98.29 215	99.70 106

EI-MVSNet-Vis-set		99.58 7	99.56 8	99.64 71	99.78 52	99.15 123	99.61 94	99.45 187	99.01 35	99.89 13	99.82 71	99.01 18	99.92 88	99.56 21	99.95 11	99.85 29

VDD-MVS		97.73 255	97.35 270	98.88 202	99.47 183	97.12 268	99.34 231	98.85 332	98.19 120	99.67 71	99.85 50	82.98 370	99.92 88	99.49 33	98.32 214	99.60 139

VNet		99.11 92	98.90 103	99.73 57	99.52 161	99.56 69	99.41 200	99.39 217	99.01 35	99.74 54	99.78 114	95.56 179	99.92 88	99.52 27	98.18 223	99.72 96

XVG-OURS-SEG-HR		98.69 146	98.62 140	98.89 200	99.71 92	97.74 246	99.12 281	99.54 79	98.44 92	99.42 136	99.71 147	94.20 237	99.92 88	98.54 155	98.90 183	99.00 224

HPM-MVS_fast		99.51 15	99.40 22	99.85 27	99.91 1	99.79 30	99.76 37	99.56 63	97.72 178	99.76 50	99.75 131	99.13 12	99.92 88	99.07 76	99.92 19	99.85 29

HY-MVS	97.30 7	98.85 128	98.64 134	99.47 113	99.42 193	99.08 132	99.62 88	99.36 233	97.39 215	99.28 173	99.68 167	96.44 149	99.92 88	98.37 168	98.22 218	99.40 189

DP-MVS		99.16 76	98.95 98	99.78 46	99.77 58	99.53 76	99.41 200	99.50 129	97.03 248	99.04 224	99.88 32	97.39 114	99.92 88	98.66 132	99.90 32	99.87 24

IB-MVS	95.67 18	96.22 308	95.44 321	98.57 239	99.21 247	96.70 294	98.65 351	97.74 371	96.71 267	97.27 338	98.54 353	86.03 358	99.92 88	98.47 161	86.30 373	99.10 208
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
DeepC-MVS_fast	98.69 1	99.49 18	99.39 23	99.77 49	99.63 125	99.59 64	99.36 223	99.46 176	99.07 30	99.79 36	99.82 71	98.85 39	99.92 88	98.68 130	99.87 47	99.82 47
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
9.14			99.10 71		99.72 87		99.40 208	99.51 109	97.53 199	99.64 86	99.78 114	98.84 41	99.91 98	97.63 230	99.82 83

SMA-MVS		99.44 33	99.30 45	99.85 27	99.73 83	99.83 16	99.56 122	99.47 167	97.45 207	99.78 41	99.82 71	99.18 10	99.91 98	98.79 116	99.89 41	99.81 54
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
TEST9					99.67 106	99.65 57	99.05 296	99.41 206	96.22 305	98.95 237	99.49 240	98.77 51	99.91 98

train_agg		99.02 105	98.77 120	99.77 49	99.67 106	99.65 57	99.05 296	99.41 206	96.28 299	98.95 237	99.49 240	98.76 52	99.91 98	97.63 230	99.72 111	99.75 81

test_8					99.67 106	99.61 62	99.03 301	99.41 206	96.28 299	98.93 241	99.48 245	98.76 52	99.91 98

agg_prior					99.67 106	99.62 61		99.40 214		98.87 251			99.91 98

原ACMM1				99.65 66	99.73 83	99.33 97		99.47 167	97.46 204	99.12 207	99.66 178	98.67 64	99.91 98	97.70 227	99.69 116	99.71 105

LFMVS		97.90 227	97.35 270	99.54 90	99.52 161	99.01 141	99.39 212	98.24 361	97.10 241	99.65 82	99.79 108	84.79 364	99.91 98	99.28 56	98.38 208	99.69 108

XVG-OURS		98.73 142	98.68 128	98.88 202	99.70 97	97.73 247	98.92 325	99.55 71	98.52 84	99.45 127	99.84 60	95.27 189	99.91 98	98.08 192	98.84 187	99.00 224

PLC	97.94 4	99.02 105	98.85 112	99.53 98	99.66 114	99.01 141	99.24 262	99.52 95	96.85 260	99.27 177	99.48 245	98.25 91	99.91 98	97.76 218	99.62 127	99.65 122
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 268	97.06 289	99.47 113	99.61 135	99.09 129	98.04 376	99.25 280	91.24 367	98.51 295	99.70 151	94.55 227	99.91 98	92.76 356	99.85 62	99.42 185
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_vis1_rt		95.81 317	95.65 317	96.32 343	99.67 106	91.35 369	99.49 167	96.74 380	98.25 110	95.24 358	98.10 363	74.96 377	99.90 109	99.53 25	98.85 186	97.70 363

FA-MVS(test-final)		98.75 139	98.53 153	99.41 122	99.55 154	99.05 137	99.80 25	99.01 311	96.59 281	99.58 103	99.59 205	95.39 184	99.90 109	97.78 214	99.49 136	99.28 200

MCST-MVS		99.43 36	99.30 45	99.82 35	99.79 50	99.74 41	99.29 242	99.40 214	98.79 65	99.52 116	99.62 196	98.91 34	99.90 109	98.64 134	99.75 105	99.82 47

CDPH-MVS		99.13 82	98.91 102	99.80 40	99.75 69	99.71 44	99.15 276	99.41 206	96.60 279	99.60 99	99.55 219	98.83 42	99.90 109	97.48 246	99.83 79	99.78 73

NCCC		99.34 52	99.19 63	99.79 43	99.61 135	99.65 57	99.30 238	99.48 149	98.86 55	99.21 191	99.63 191	98.72 59	99.90 109	98.25 177	99.63 126	99.80 63

114514_t		98.93 113	98.67 129	99.72 58	99.85 25	99.53 76	99.62 88	99.59 51	92.65 362	99.71 61	99.78 114	98.06 100	99.90 109	98.84 108	99.91 24	99.74 85

1112_ss		98.98 109	98.77 120	99.59 80	99.68 105	99.02 139	99.25 260	99.48 149	97.23 228	99.13 205	99.58 209	96.93 134	99.90 109	98.87 98	98.78 192	99.84 33

PHI-MVS		99.30 56	99.17 65	99.70 60	99.56 150	99.52 79	99.58 109	99.80 8	97.12 237	99.62 93	99.73 142	98.58 70	99.90 109	98.61 139	99.91 24	99.68 112

AdaColmap		99.01 108	98.80 116	99.66 62	99.56 150	99.54 73	99.18 271	99.70 15	98.18 124	99.35 160	99.63 191	96.32 152	99.90 109	97.48 246	99.77 100	99.55 152

COLMAP_ROB	97.56 6	98.86 121	98.75 122	99.17 159	99.88 11	98.53 197	99.34 231	99.59 51	97.55 195	98.70 275	99.89 26	95.83 170	99.90 109	98.10 187	99.90 32	99.08 213
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 171	98.03 191	99.31 136	99.63 125	98.56 194	99.54 137	96.75 379	97.53 199	99.73 55	99.65 179	91.25 315	99.89 119	98.62 136	99.56 131	99.48 171

tttt0517		98.42 163	98.14 176	99.28 147	99.66 114	98.38 214	99.74 44	96.85 377	97.68 182	99.79 36	99.74 136	91.39 312	99.89 119	98.83 111	99.56 131	99.57 149

test12				99.75 52	99.64 122	99.61 62		99.29 272		99.21 191		98.38 85	99.89 119		99.74 108	99.74 85

Test_1112_low_res		98.89 116	98.66 132	99.57 85	99.69 101	98.95 155	99.03 301	99.47 167	96.98 250	99.15 203	99.23 305	96.77 138	99.89 119	98.83 111	98.78 192	99.86 26

CNLPA		99.14 80	98.99 90	99.59 80	99.58 144	99.41 92	99.16 273	99.44 195	98.45 89	99.19 197	99.49 240	98.08 99	99.89 119	97.73 222	99.75 105	99.48 171

sd_testset		98.75 139	98.57 149	99.29 144	99.81 42	98.26 218	99.56 122	99.62 37	98.78 68	99.64 86	99.88 32	92.02 295	99.88 124	99.54 23	98.26 216	99.72 96

APD_test1		95.87 315	96.49 299	94.00 349	99.53 157	84.01 376	99.54 137	99.32 260	95.91 322	97.99 320	99.85 50	85.49 361	99.88 124	91.96 359	98.84 187	98.12 345

diffmvs		99.14 80	99.02 84	99.51 106	99.61 135	98.96 150	99.28 245	99.49 137	98.46 88	99.72 60	99.71 147	96.50 146	99.88 124	99.31 51	99.11 164	99.67 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 121	98.80 116	99.03 173	99.76 61	98.79 177	99.28 245	99.91 3	97.42 212	99.67 71	99.37 273	97.53 111	99.88 124	98.98 83	97.29 268	98.42 328

PVSNet_Blended		99.08 98	98.97 94	99.42 121	99.76 61	98.79 177	98.78 339	99.91 3	96.74 265	99.67 71	99.49 240	97.53 111	99.88 124	98.98 83	99.85 62	99.60 139

MVS		97.28 287	96.55 298	99.48 110	98.78 319	98.95 155	99.27 250	99.39 217	83.53 379	98.08 315	99.54 224	96.97 132	99.87 129	94.23 339	99.16 158	99.63 133

MG-MVS		99.13 82	99.02 84	99.45 116	99.57 146	98.63 188	99.07 291	99.34 243	98.99 40	99.61 96	99.82 71	97.98 102	99.87 129	97.00 274	99.80 90	99.85 29

MSDG		98.98 109	98.80 116	99.53 98	99.76 61	99.19 113	98.75 342	99.55 71	97.25 225	99.47 124	99.77 122	97.82 105	99.87 129	96.93 281	99.90 32	99.54 154

ETV-MVS		99.26 63	99.21 61	99.40 123	99.46 184	99.30 102	99.56 122	99.52 95	98.52 84	99.44 132	99.27 300	98.41 84	99.86 132	99.10 72	99.59 129	99.04 220

thisisatest0515		98.14 189	97.79 214	99.19 157	99.50 172	98.50 204	98.61 353	96.82 378	96.95 254	99.54 112	99.43 256	91.66 307	99.86 132	98.08 192	99.51 135	99.22 203

thres600view7		97.86 232	97.51 246	98.92 191	99.72 87	97.95 237	99.59 101	98.74 343	97.94 154	99.27 177	98.62 350	91.75 301	99.86 132	93.73 344	98.19 222	98.96 230

lupinMVS		99.13 82	99.01 88	99.46 115	99.51 163	98.94 158	99.05 296	99.16 294	97.86 160	99.80 34	99.56 216	97.39 114	99.86 132	98.94 87	99.85 62	99.58 147

PVSNet	96.02 17	98.85 128	98.84 113	98.89 200	99.73 83	97.28 260	98.32 369	99.60 48	97.86 160	99.50 119	99.57 213	96.75 139	99.86 132	98.56 151	99.70 115	99.54 154

MAR-MVS		98.86 121	98.63 135	99.54 90	99.37 208	99.66 53	99.45 181	99.54 79	96.61 277	99.01 227	99.40 265	97.09 126	99.86 132	97.68 229	99.53 134	99.10 208
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
test2506		96.81 299	96.65 296	97.29 325	99.74 76	92.21 366	99.60 95	85.06 396	99.13 19	99.77 45	99.93 7	87.82 353	99.85 138	99.38 41	99.38 142	99.80 63

AllTest		98.87 118	98.72 123	99.31 136	99.86 20	98.48 207	99.56 122	99.61 42	97.85 162	99.36 157	99.85 50	95.95 163	99.85 138	96.66 294	99.83 79	99.59 143

TestCases				99.31 136	99.86 20	98.48 207		99.61 42	97.85 162	99.36 157	99.85 50	95.95 163	99.85 138	96.66 294	99.83 79	99.59 143

jason		99.13 82	99.03 80	99.45 116	99.46 184	98.87 165	99.12 281	99.26 278	98.03 149	99.79 36	99.65 179	97.02 129	99.85 138	99.02 80	99.90 32	99.65 122
jason: jason.
CNVR-MVS		99.42 38	99.30 45	99.78 46	99.62 131	99.71 44	99.26 258	99.52 95	98.82 60	99.39 148	99.71 147	98.96 24	99.85 138	98.59 144	99.80 90	99.77 75

PAPM_NR		99.04 102	98.84 113	99.66 62	99.74 76	99.44 88	99.39 212	99.38 224	97.70 180	99.28 173	99.28 297	98.34 87	99.85 138	96.96 278	99.45 138	99.69 108

test1111		98.04 204	98.11 180	97.83 306	99.74 76	93.82 352	99.58 109	95.40 385	99.12 21	99.65 82	99.93 7	90.73 320	99.84 144	99.43 39	99.38 142	99.82 47

ECVR-MVS		98.04 204	98.05 189	98.00 295	99.74 76	94.37 347	99.59 101	94.98 386	99.13 19	99.66 76	99.93 7	90.67 321	99.84 144	99.40 40	99.38 142	99.80 63

test_yl		98.86 121	98.63 135	99.54 90	99.49 174	99.18 115	99.50 156	99.07 306	98.22 115	99.61 96	99.51 234	95.37 185	99.84 144	98.60 142	98.33 210	99.59 143

DCV-MVSNet		98.86 121	98.63 135	99.54 90	99.49 174	99.18 115	99.50 156	99.07 306	98.22 115	99.61 96	99.51 234	95.37 185	99.84 144	98.60 142	98.33 210	99.59 143

Fast-Effi-MVS+		98.70 144	98.43 157	99.51 106	99.51 163	99.28 104	99.52 144	99.47 167	96.11 315	99.01 227	99.34 283	96.20 156	99.84 144	97.88 204	98.82 189	99.39 190

TSAR-MVS + GP.		99.36 50	99.36 28	99.36 128	99.67 106	98.61 191	99.07 291	99.33 250	99.00 38	99.82 29	99.81 84	99.06 16	99.84 144	99.09 73	99.42 140	99.65 122

tpmrst		98.33 172	98.48 155	97.90 301	99.16 262	94.78 340	99.31 236	99.11 299	97.27 223	99.45 127	99.59 205	95.33 187	99.84 144	98.48 158	98.61 195	99.09 212

Vis-MVSNet		99.12 88	98.97 94	99.56 87	99.78 52	99.10 128	99.68 61	99.66 27	98.49 86	99.86 21	99.87 40	94.77 212	99.84 144	99.19 64	99.41 141	99.74 85
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 153	98.34 163	99.51 106	99.40 201	99.03 138	98.80 337	99.36 233	96.33 296	99.00 231	99.12 319	98.46 79	99.84 144	95.23 326	99.37 149	99.66 118

PatchMatch-RL		98.84 131	98.62 140	99.52 104	99.71 92	99.28 104	99.06 294	99.77 9	97.74 177	99.50 119	99.53 228	95.41 183	99.84 144	97.17 268	99.64 124	99.44 183

EPP-MVSNet		99.13 82	98.99 90	99.53 98	99.65 120	99.06 135	99.81 20	99.33 250	97.43 210	99.60 99	99.88 32	97.14 123	99.84 144	99.13 69	98.94 178	99.69 108

thres100view900		97.76 248	97.45 253	98.69 230	99.72 87	97.86 243	99.59 101	98.74 343	97.93 155	99.26 181	98.62 350	91.75 301	99.83 155	93.22 349	98.18 223	98.37 334

tfpn200view9		97.72 257	97.38 266	98.72 228	99.69 101	97.96 235	99.50 156	98.73 348	97.83 165	99.17 201	98.45 355	91.67 305	99.83 155	93.22 349	98.18 223	98.37 334

test_prior				99.68 61	99.67 106	99.48 83		99.56 63					99.83 155			99.74 85

1314		98.68 148	98.54 152	99.11 165	98.89 303	98.65 186	99.27 250	99.49 137	96.89 258	97.99 320	99.56 216	97.72 109	99.83 155	97.74 221	99.27 153	98.84 236

thres400		97.77 247	97.38 266	98.92 191	99.69 101	97.96 235	99.50 156	98.73 348	97.83 165	99.17 201	98.45 355	91.67 305	99.83 155	93.22 349	98.18 223	98.96 230

casdiffmvs		99.13 82	98.98 93	99.56 87	99.65 120	99.16 118	99.56 122	99.50 129	98.33 103	99.41 140	99.86 45	95.92 166	99.83 155	99.45 38	99.16 158	99.70 106
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS-test		99.49 18	99.48 13	99.54 90	99.78 52	99.30 102	99.89 2	99.58 55	98.56 80	99.73 55	99.69 161	98.55 73	99.82 161	99.69 12	99.85 62	99.48 171

MVS_Test		99.10 96	98.97 94	99.48 110	99.49 174	99.14 124	99.67 64	99.34 243	97.31 220	99.58 103	99.76 128	97.65 110	99.82 161	98.87 98	99.07 170	99.46 179

dp		97.75 252	97.80 213	97.59 317	99.10 272	93.71 355	99.32 234	98.88 329	96.48 288	99.08 216	99.55 219	92.67 280	99.82 161	96.52 297	98.58 198	99.24 202

RPSCF		98.22 179	98.62 140	96.99 331	99.82 38	91.58 368	99.72 49	99.44 195	96.61 277	99.66 76	99.89 26	95.92 166	99.82 161	97.46 249	99.10 167	99.57 149

PMMVS		98.80 135	98.62 140	99.34 129	99.27 235	98.70 182	98.76 341	99.31 264	97.34 217	99.21 191	99.07 321	97.20 122	99.82 161	98.56 151	98.87 184	99.52 160

EIA-MVS		99.18 72	99.09 73	99.45 116	99.49 174	99.18 115	99.67 64	99.53 90	97.66 185	99.40 145	99.44 254	98.10 97	99.81 166	98.94 87	99.62 127	99.35 193

Effi-MVS+		98.81 132	98.59 147	99.48 110	99.46 184	99.12 127	98.08 375	99.50 129	97.50 202	99.38 151	99.41 262	96.37 151	99.81 166	99.11 71	98.54 203	99.51 166

thres200		97.61 271	97.28 280	98.62 233	99.64 122	98.03 229	99.26 258	98.74 343	97.68 182	99.09 215	98.32 359	91.66 307	99.81 166	92.88 353	98.22 218	98.03 350

tpmvs		97.98 215	98.02 193	97.84 305	99.04 285	94.73 341	99.31 236	99.20 289	96.10 319	98.76 265	99.42 258	94.94 197	99.81 166	96.97 277	98.45 207	98.97 228

casdiffmvs_mvg		99.15 78	99.02 84	99.55 89	99.66 114	99.09 129	99.64 78	99.56 63	98.26 109	99.45 127	99.87 40	96.03 160	99.81 166	99.54 23	99.15 161	99.73 90
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepPCF-MVS	98.18 3	98.81 132	99.37 26	97.12 329	99.60 140	91.75 367	98.61 353	99.44 195	99.35 9	99.83 28	99.85 50	98.70 61	99.81 166	99.02 80	99.91 24	99.81 54

DPM-MVS		98.95 112	98.71 125	99.66 62	99.63 125	99.55 71	98.64 352	99.10 300	97.93 155	99.42 136	99.55 219	98.67 64	99.80 172	95.80 312	99.68 119	99.61 137

DP-MVS Recon		99.12 88	98.95 98	99.65 66	99.74 76	99.70 46	99.27 250	99.57 58	96.40 295	99.42 136	99.68 167	98.75 55	99.80 172	97.98 198	99.72 111	99.44 183

MVS_111021_LR		99.41 43	99.33 34	99.65 66	99.77 58	99.51 80	98.94 323	99.85 6	98.82 60	99.65 82	99.74 136	98.51 76	99.80 172	98.83 111	99.89 41	99.64 129

CS-MVS		99.50 16	99.48 13	99.54 90	99.76 61	99.42 90	99.90 1	99.55 71	98.56 80	99.78 41	99.70 151	98.65 66	99.79 175	99.65 16	99.78 97	99.41 187

Fast-Effi-MVS+-dtu		98.77 138	98.83 115	98.60 234	99.41 196	96.99 282	99.52 144	99.49 137	98.11 133	99.24 183	99.34 283	96.96 133	99.79 175	97.95 200	99.45 138	99.02 223

baseline1		98.31 173	97.95 200	99.38 127	99.50 172	98.74 179	99.59 101	98.93 319	98.41 93	99.14 204	99.60 203	94.59 223	99.79 175	98.48 158	93.29 346	99.61 137

baseline		99.15 78	99.02 84	99.53 98	99.66 114	99.14 124	99.72 49	99.48 149	98.35 100	99.42 136	99.84 60	96.07 158	99.79 175	99.51 28	99.14 162	99.67 115

PVSNet_0	94.43 19	96.09 313	95.47 319	97.94 298	99.31 225	94.34 349	97.81 377	99.70 15	97.12 237	97.46 333	98.75 347	89.71 331	99.79 175	97.69 228	81.69 379	99.68 112

API-MVS		99.04 102	99.03 80	99.06 169	99.40 201	99.31 101	99.55 132	99.56 63	98.54 82	99.33 164	99.39 269	98.76 52	99.78 180	96.98 276	99.78 97	98.07 347

OMC-MVS		99.08 98	99.04 78	99.20 156	99.67 106	98.22 220	99.28 245	99.52 95	98.07 141	99.66 76	99.81 84	97.79 106	99.78 180	97.79 213	99.81 86	99.60 139

GeoE		98.85 128	98.62 140	99.53 98	99.61 135	99.08 132	99.80 25	99.51 109	97.10 241	99.31 167	99.78 114	95.23 193	99.77 182	98.21 179	99.03 173	99.75 81

alignmvs		98.81 132	98.56 151	99.58 83	99.43 191	99.42 90	99.51 150	98.96 317	98.61 77	99.35 160	98.92 339	94.78 209	99.77 182	99.35 44	98.11 228	99.54 154

tpm cat1		97.39 284	97.36 268	97.50 320	99.17 260	93.73 354	99.43 191	99.31 264	91.27 366	98.71 269	99.08 320	94.31 235	99.77 182	96.41 301	98.50 205	99.00 224

CostFormer		97.72 257	97.73 226	97.71 313	99.15 265	94.02 351	99.54 137	99.02 310	94.67 343	99.04 224	99.35 279	92.35 292	99.77 182	98.50 157	97.94 231	99.34 195

test_241102_ONE					99.84 31	99.90 2		99.48 149	99.07 30	99.91 10	99.74 136	99.20 7	99.76 186

MDTV_nov1_ep13			98.32 165		99.11 269	94.44 346	99.27 250	98.74 343	97.51 201	99.40 145	99.62 196	94.78 209	99.76 186	97.59 233	98.81 191

canonicalmvs		99.02 105	98.86 111	99.51 106	99.42 193	99.32 98	99.80 25	99.48 149	98.63 75	99.31 167	98.81 344	97.09 126	99.75 188	99.27 59	97.90 232	99.47 177

Effi-MVS+-dtu		98.78 136	98.89 106	98.47 254	99.33 218	96.91 288	99.57 116	99.30 268	98.47 87	99.41 140	98.99 330	96.78 137	99.74 189	98.73 122	99.38 142	98.74 250

patchmatchnet-post											98.70 348	94.79 208	99.74 189

SCA		98.19 183	98.16 173	98.27 278	99.30 226	95.55 323	99.07 291	98.97 315	97.57 192	99.43 133	99.57 213	92.72 275	99.74 189	97.58 234	99.20 156	99.52 160

BH-untuned		98.42 163	98.36 161	98.59 235	99.49 174	96.70 294	99.27 250	99.13 298	97.24 227	98.80 260	99.38 270	95.75 173	99.74 189	97.07 272	99.16 158	99.33 196

BH-RMVSNet		98.41 165	98.08 185	99.40 123	99.41 196	98.83 173	99.30 238	98.77 339	97.70 180	98.94 239	99.65 179	92.91 270	99.74 189	96.52 297	99.55 133	99.64 129

MVS_111021_HR		99.41 43	99.32 36	99.66 62	99.72 87	99.47 85	98.95 321	99.85 6	98.82 60	99.54 112	99.73 142	98.51 76	99.74 189	98.91 92	99.88 44	99.77 75

test_post											65.99 390	94.65 222	99.73 195

XVG-ACMP-BASELINE		97.83 238	97.71 228	98.20 280	99.11 269	96.33 308	99.41 200	99.52 95	98.06 145	99.05 223	99.50 237	89.64 333	99.73 195	97.73 222	97.38 266	98.53 316

HyFIR lowres test		99.11 92	98.92 100	99.65 66	99.90 4	99.37 94	99.02 304	99.91 3	97.67 184	99.59 102	99.75 131	95.90 168	99.73 195	99.53 25	99.02 175	99.86 26

DeepMVS_CX				93.34 352	99.29 230	82.27 379		99.22 285	85.15 377	96.33 351	99.05 324	90.97 318	99.73 195	93.57 346	97.77 235	98.01 351

Patchmatch-test		97.93 221	97.65 233	98.77 225	99.18 254	97.07 273	99.03 301	99.14 297	96.16 310	98.74 266	99.57 213	94.56 225	99.72 199	93.36 348	99.11 164	99.52 160

LPG-MVS_test		98.22 179	98.13 178	98.49 248	99.33 218	97.05 275	99.58 109	99.55 71	97.46 204	99.24 183	99.83 64	92.58 282	99.72 199	98.09 188	97.51 250	98.68 269

LGP-MVS_train				98.49 248	99.33 218	97.05 275		99.55 71	97.46 204	99.24 183	99.83 64	92.58 282	99.72 199	98.09 188	97.51 250	98.68 269

BH-w/o		98.00 213	97.89 209	98.32 271	99.35 212	96.20 312	99.01 309	98.90 327	96.42 293	98.38 302	99.00 329	95.26 191	99.72 199	96.06 305	98.61 195	99.03 221

ACMP	97.20 11	98.06 198	97.94 202	98.45 256	99.37 208	97.01 280	99.44 187	99.49 137	97.54 198	98.45 299	99.79 108	91.95 297	99.72 199	97.91 202	97.49 255	98.62 299
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 208	97.90 205	98.40 264	99.23 243	96.80 292	99.70 52	99.60 48	97.12 237	98.18 312	99.70 151	91.73 303	99.72 199	98.39 165	97.45 258	98.68 269
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
test_post1							99.23 263				65.14 391	94.18 240	99.71 205	97.58 234

ADS-MVSNet		98.20 182	98.08 185	98.56 242	99.33 218	96.48 303	99.23 263	99.15 295	96.24 303	99.10 212	99.67 173	94.11 241	99.71 205	96.81 286	99.05 171	99.48 171

JIA-IIPM		97.50 278	97.02 290	98.93 189	98.73 325	97.80 245	99.30 238	98.97 315	91.73 365	98.91 243	94.86 379	95.10 195	99.71 205	97.58 234	97.98 230	99.28 200

EPMVS		97.82 241	97.65 233	98.35 268	98.88 304	95.98 315	99.49 167	94.71 388	97.57 192	99.26 181	99.48 245	92.46 289	99.71 205	97.87 206	99.08 169	99.35 193

TDRefinement		95.42 321	94.57 328	97.97 297	89.83 389	96.11 314	99.48 171	98.75 340	96.74 265	96.68 348	99.88 32	88.65 342	99.71 205	98.37 168	82.74 378	98.09 346

ACMM	97.58 5	98.37 170	98.34 163	98.48 250	99.41 196	97.10 269	99.56 122	99.45 187	98.53 83	99.04 224	99.85 50	93.00 266	99.71 205	98.74 120	97.45 258	98.64 288
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 218	97.77 219	98.57 239	99.59 142	96.61 299	99.45 181	99.08 303	98.21 117	98.88 248	99.80 97	88.66 341	99.70 211	98.58 145	97.72 236	99.39 190

CHOSEN 280x420		99.12 88	99.13 68	99.08 166	99.66 114	97.89 240	98.43 363	99.71 13	98.88 54	99.62 93	99.76 128	96.63 142	99.70 211	99.46 37	99.99 1	99.66 118

EC-MVSNet		99.44 33	99.39 23	99.58 83	99.56 150	99.49 81	99.88 4	99.58 55	98.38 95	99.73 55	99.69 161	98.20 93	99.70 211	99.64 17	99.82 83	99.54 154

PatchmatchNet		98.31 173	98.36 161	98.19 281	99.16 262	95.32 331	99.27 250	98.92 321	97.37 216	99.37 153	99.58 209	94.90 201	99.70 211	97.43 252	99.21 155	99.54 154
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 193	97.99 195	98.44 259	99.41 196	96.96 286	99.60 95	99.56 63	98.09 136	98.15 313	99.91 16	90.87 319	99.70 211	98.88 95	97.45 258	98.67 276
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP_MVS		98.27 178	98.22 171	98.44 259	99.29 230	96.97 284	99.39 212	99.47 167	98.97 46	99.11 209	99.61 200	92.71 277	99.69 216	97.78 214	97.63 238	98.67 276

plane_prior5								99.47 167					99.69 216	97.78 214	97.63 238	98.67 276

D2MVS		98.41 165	98.50 154	98.15 286	99.26 237	96.62 298	99.40 208	99.61 42	97.71 179	98.98 233	99.36 276	96.04 159	99.67 218	98.70 125	97.41 263	98.15 344

IS-MVSNet		99.05 101	98.87 108	99.57 85	99.73 83	99.32 98	99.75 41	99.20 289	98.02 150	99.56 107	99.86 45	96.54 145	99.67 218	98.09 188	99.13 163	99.73 90

CLD-MVS		98.16 187	98.10 181	98.33 269	99.29 230	96.82 291	98.75 342	99.44 195	97.83 165	99.13 205	99.55 219	92.92 268	99.67 218	98.32 174	97.69 237	98.48 320
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 289	97.30 278	97.09 330	99.43 191	93.31 360	99.73 47	98.87 331	98.83 59	99.28 173	99.80 97	84.45 365	99.66 221	97.88 204	97.45 258	98.30 336

AUN-MVS		96.88 297	96.31 303	98.59 235	99.48 182	97.04 278	99.27 250	99.22 285	97.44 209	98.51 295	99.41 262	91.97 296	99.66 221	97.71 225	83.83 376	99.07 218

UniMVSNet_ETH3D		97.32 286	96.81 293	98.87 206	99.40 201	97.46 256	99.51 150	99.53 90	95.86 323	98.54 294	99.77 122	82.44 373	99.66 221	98.68 130	97.52 248	99.50 169

OPM-MVS		98.19 183	98.10 181	98.45 256	98.88 304	97.07 273	99.28 245	99.38 224	98.57 79	99.22 188	99.81 84	92.12 293	99.66 221	98.08 192	97.54 247	98.61 308
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 224	97.78 217	98.32 271	99.46 184	96.68 296	99.56 122	99.54 79	98.41 93	97.79 329	99.87 40	90.18 328	99.66 221	98.05 196	97.18 274	98.62 299

hse-mvs2		97.50 278	97.14 286	98.59 235	99.49 174	97.05 275	99.28 245	99.22 285	98.94 49	99.66 76	99.42 258	94.93 198	99.65 226	99.48 34	83.80 377	99.08 213

VPA-MVSNet		98.29 176	97.95 200	99.30 141	99.16 262	99.54 73	99.50 156	99.58 55	98.27 108	99.35 160	99.37 273	92.53 284	99.65 226	99.35 44	94.46 329	98.72 253

TR-MVS		97.76 248	97.41 264	98.82 217	99.06 281	97.87 241	98.87 331	98.56 354	96.63 276	98.68 277	99.22 306	92.49 285	99.65 226	95.40 322	97.79 234	98.95 232

gm-plane-assit					98.54 344	92.96 362			94.65 344		99.15 314		99.64 229	97.56 239

HQP4-MVS										98.66 278			99.64 229			98.64 288

HQP-MVS		98.02 208	97.90 205	98.37 267	99.19 251	96.83 289	98.98 314	99.39 217	98.24 111	98.66 278	99.40 265	92.47 286	99.64 229	97.19 265	97.58 243	98.64 288

PAPM		97.59 272	97.09 288	99.07 168	99.06 281	98.26 218	98.30 370	99.10 300	94.88 338	98.08 315	99.34 283	96.27 154	99.64 229	89.87 366	98.92 181	99.31 198

TAPA-MVS	97.07 15	97.74 254	97.34 273	98.94 187	99.70 97	97.53 254	99.25 260	99.51 109	91.90 364	99.30 169	99.63 191	98.78 48	99.64 229	88.09 373	99.87 47	99.65 122
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 169	98.09 184	99.24 152	99.26 237	99.32 98	99.56 122	99.55 71	97.45 207	98.71 269	99.83 64	93.23 261	99.63 234	98.88 95	96.32 289	98.76 245

ITE_SJBPF				98.08 288	99.29 230	96.37 306		98.92 321	98.34 101	98.83 256	99.75 131	91.09 316	99.62 235	95.82 310	97.40 264	98.25 340

LF4IMVS		97.52 275	97.46 252	97.70 314	98.98 294	95.55 323	99.29 242	98.82 335	98.07 141	98.66 278	99.64 185	89.97 329	99.61 236	97.01 273	96.68 279	97.94 357

tpm		97.67 267	97.55 240	98.03 290	99.02 287	95.01 337	99.43 191	98.54 356	96.44 291	99.12 207	99.34 283	91.83 300	99.60 237	97.75 220	96.46 285	99.48 171

tpm2		97.44 283	97.34 273	97.74 312	99.15 265	94.36 348	99.45 181	98.94 318	93.45 357	98.90 245	99.44 254	91.35 313	99.59 238	97.31 256	98.07 229	99.29 199

baseline2		97.87 230	97.55 240	98.82 217	99.18 254	98.02 230	99.41 200	96.58 382	96.97 251	96.51 349	99.17 311	93.43 258	99.57 239	97.71 225	99.03 173	98.86 234

MS-PatchMatch		97.24 291	97.32 276	96.99 331	98.45 347	93.51 359	98.82 335	99.32 260	97.41 213	98.13 314	99.30 293	88.99 337	99.56 240	95.68 316	99.80 90	97.90 360

TinyColmap		97.12 293	96.89 292	97.83 306	99.07 278	95.52 326	98.57 356	98.74 343	97.58 191	97.81 328	99.79 108	88.16 348	99.56 240	95.10 327	97.21 272	98.39 332

USDC		97.34 285	97.20 284	97.75 311	99.07 278	95.20 333	98.51 360	99.04 309	97.99 151	98.31 306	99.86 45	89.02 336	99.55 242	95.67 317	97.36 267	98.49 319

MSLP-MVS++		99.46 27	99.47 15	99.44 120	99.60 140	99.16 118	99.41 200	99.71 13	98.98 43	99.45 127	99.78 114	99.19 9	99.54 243	99.28 56	99.84 70	99.63 133

TAMVS		99.12 88	99.08 74	99.24 152	99.46 184	98.55 195	99.51 150	99.46 176	98.09 136	99.45 127	99.82 71	98.34 87	99.51 244	98.70 125	98.93 179	99.67 115

EPNet_dtu		98.03 206	97.96 198	98.23 279	98.27 350	95.54 325	99.23 263	98.75 340	99.02 33	97.82 327	99.71 147	96.11 157	99.48 245	93.04 352	99.65 123	99.69 108
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		95.97 314	95.69 316	96.81 337	97.78 357	92.79 363	99.16 273	98.93 319	96.16 310	94.08 366	99.22 306	82.72 371	99.47 246	95.67 317	97.50 252	98.17 343

MVP-Stereo		97.81 243	97.75 224	97.99 296	97.53 361	96.60 300	98.96 318	98.85 332	97.22 229	97.23 339	99.36 276	95.28 188	99.46 247	95.51 319	99.78 97	97.92 359
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 155	98.67 129	98.30 273	99.35 212	95.59 322	99.50 156	99.55 71	98.60 78	99.39 148	99.83 64	94.48 229	99.45 248	98.75 119	98.56 201	99.85 29

test-LLR		98.06 198	97.90 205	98.55 244	98.79 316	97.10 269	98.67 348	97.75 369	97.34 217	98.61 289	98.85 341	94.45 230	99.45 248	97.25 259	99.38 142	99.10 208

TESTMET0.1,1		97.55 273	97.27 283	98.40 264	98.93 299	96.53 301	98.67 348	97.61 372	96.96 252	98.64 285	99.28 297	88.63 343	99.45 248	97.30 257	99.38 142	99.21 204

test-mter		97.49 281	97.13 287	98.55 244	98.79 316	97.10 269	98.67 348	97.75 369	96.65 272	98.61 289	98.85 341	88.23 347	99.45 248	97.25 259	99.38 142	99.10 208

mvs_anonymous		99.03 104	98.99 90	99.16 160	99.38 205	98.52 201	99.51 150	99.38 224	97.79 170	99.38 151	99.81 84	97.30 119	99.45 248	99.35 44	98.99 176	99.51 166

tfpnnormal		97.84 236	97.47 250	98.98 181	99.20 249	99.22 112	99.64 78	99.61 42	96.32 297	98.27 309	99.70 151	93.35 260	99.44 253	95.69 315	95.40 312	98.27 338

v7n		97.87 230	97.52 244	98.92 191	98.76 323	98.58 193	99.84 13	99.46 176	96.20 306	98.91 243	99.70 151	94.89 202	99.44 253	96.03 306	93.89 340	98.75 247

jajsoiax		98.43 162	98.28 168	98.88 202	98.60 340	98.43 211	99.82 17	99.53 90	98.19 120	98.63 286	99.80 97	93.22 263	99.44 253	99.22 62	97.50 252	98.77 243

mvs_tets		98.40 168	98.23 170	98.91 195	98.67 333	98.51 203	99.66 69	99.53 90	98.19 120	98.65 284	99.81 84	92.75 272	99.44 253	99.31 51	97.48 256	98.77 243

Vis-MVSNet (Re-imp)		98.87 118	98.72 123	99.31 136	99.71 92	98.88 164	99.80 25	99.44 195	97.91 157	99.36 157	99.78 114	95.49 182	99.43 257	97.91 202	99.11 164	99.62 135

OPU-MVS				99.64 71	99.56 150	99.72 42	99.60 95				99.70 151	99.27 5	99.42 258	98.24 178	99.80 90	99.79 67

Anonymous20231211		97.88 228	97.54 243	98.90 197	99.71 92	98.53 197	99.48 171	99.57 58	94.16 348	98.81 258	99.68 167	93.23 261	99.42 258	98.84 108	94.42 331	98.76 245

VPNet		97.84 236	97.44 258	99.01 175	99.21 247	98.94 158	99.48 171	99.57 58	98.38 95	99.28 173	99.73 142	88.89 338	99.39 260	99.19 64	93.27 347	98.71 255

iter_conf_final		98.71 143	98.61 146	98.99 179	99.49 174	98.96 150	99.63 82	99.41 206	98.19 120	99.39 148	99.77 122	94.82 204	99.38 261	99.30 54	97.52 248	98.64 288

nrg030		98.64 152	98.42 158	99.28 147	99.05 284	99.69 47	99.81 20	99.46 176	98.04 147	99.01 227	99.82 71	96.69 141	99.38 261	99.34 48	94.59 328	98.78 240

iter_conf05		98.55 156	98.44 156	98.87 206	99.34 216	98.60 192	99.55 132	99.42 203	98.21 117	99.37 153	99.77 122	93.55 257	99.38 261	99.30 54	97.48 256	98.63 296

GA-MVS		97.85 233	97.47 250	99.00 177	99.38 205	97.99 232	98.57 356	99.15 295	97.04 247	98.90 245	99.30 293	89.83 330	99.38 261	96.70 291	98.33 210	99.62 135

UniMVSNet (Re)		98.29 176	98.00 194	99.13 164	99.00 289	99.36 96	99.49 167	99.51 109	97.95 153	98.97 235	99.13 316	96.30 153	99.38 261	98.36 170	93.34 345	98.66 284

FIs		98.78 136	98.63 135	99.23 154	99.18 254	99.54 73	99.83 16	99.59 51	98.28 106	98.79 262	99.81 84	96.75 139	99.37 266	99.08 75	96.38 287	98.78 240

PS-MVSNAJss		98.92 114	98.92 100	98.90 197	98.78 319	98.53 197	99.78 32	99.54 79	98.07 141	99.00 231	99.76 128	99.01 18	99.37 266	99.13 69	97.23 271	98.81 237

CDS-MVSNet		99.09 97	99.03 80	99.25 150	99.42 193	98.73 180	99.45 181	99.46 176	98.11 133	99.46 126	99.77 122	98.01 101	99.37 266	98.70 125	98.92 181	99.66 118
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 318	95.16 323	97.51 319	99.30 226	93.69 356	98.88 329	95.78 383	85.09 378	98.78 263	92.65 381	91.29 314	99.37 266	94.85 331	99.85 62	99.46 179

v1192		97.81 243	97.44 258	98.91 195	98.88 304	98.68 183	99.51 150	99.34 243	96.18 308	99.20 194	99.34 283	94.03 244	99.36 270	95.32 324	95.18 316	98.69 264

EI-MVSNet		98.67 149	98.67 129	98.68 231	99.35 212	97.97 233	99.50 156	99.38 224	96.93 257	99.20 194	99.83 64	97.87 103	99.36 270	98.38 166	97.56 245	98.71 255

MVSTER		98.49 157	98.32 165	99.00 177	99.35 212	99.02 139	99.54 137	99.38 224	97.41 213	99.20 194	99.73 142	93.86 250	99.36 270	98.87 98	97.56 245	98.62 299

gg-mvs-nofinetune		96.17 311	95.32 322	98.73 227	98.79 316	98.14 224	99.38 217	94.09 389	91.07 369	98.07 318	91.04 385	89.62 334	99.35 273	96.75 288	99.09 168	98.68 269

pm-mvs1		97.68 264	97.28 280	98.88 202	99.06 281	98.62 189	99.50 156	99.45 187	96.32 297	97.87 325	99.79 108	92.47 286	99.35 273	97.54 241	93.54 344	98.67 276

OurMVSNet-221017-0		97.88 228	97.77 219	98.19 281	98.71 329	96.53 301	99.88 4	99.00 312	97.79 170	98.78 263	99.94 4	91.68 304	99.35 273	97.21 261	96.99 278	98.69 264

EGC-MVSNET		82.80 350	77.86 356	97.62 315	97.91 354	96.12 313	99.33 233	99.28 274	8.40 393	25.05 394	99.27 300	84.11 366	99.33 276	89.20 368	98.22 218	97.42 368

pmmvs6		96.53 303	96.09 308	97.82 308	98.69 331	95.47 327	99.37 219	99.47 167	93.46 356	97.41 334	99.78 114	87.06 356	99.33 276	96.92 283	92.70 354	98.65 286

mvsmamba		98.92 114	98.87 108	99.08 166	99.07 278	99.16 118	99.88 4	99.51 109	98.15 126	99.40 145	99.89 26	97.12 124	99.33 276	99.38 41	97.40 264	98.73 252

V42		98.06 198	97.79 214	98.86 210	98.98 294	98.84 170	99.69 55	99.34 243	96.53 283	99.30 169	99.37 273	94.67 220	99.32 279	97.57 238	94.66 326	98.42 328

lessismore_v0				97.79 310	98.69 331	95.44 329		94.75 387		95.71 357	99.87 40	88.69 340	99.32 279	95.89 309	94.93 323	98.62 299

OpenMVS_ROB	92.34 20	94.38 332	93.70 338	96.41 342	97.38 363	93.17 361	99.06 294	98.75 340	86.58 376	94.84 364	98.26 360	81.53 374	99.32 279	89.01 369	97.87 233	96.76 371

bld_raw_dy_0_64		98.69 146	98.58 148	98.99 179	98.88 304	98.96 150	99.80 25	99.41 206	97.91 157	99.32 165	99.87 40	95.70 176	99.31 282	99.09 73	97.27 269	98.71 255

v8		97.95 220	97.63 236	98.93 189	98.95 298	98.81 176	99.80 25	99.41 206	96.03 320	99.10 212	99.42 258	94.92 200	99.30 283	96.94 280	94.08 337	98.66 284

v1921920		97.80 245	97.45 253	98.84 214	98.80 315	98.53 197	99.52 144	99.34 243	96.15 312	99.24 183	99.47 248	93.98 246	99.29 284	95.40 322	95.13 318	98.69 264

anonymousdsp		98.44 161	98.28 168	98.94 187	98.50 345	98.96 150	99.77 34	99.50 129	97.07 243	98.87 251	99.77 122	94.76 213	99.28 285	98.66 132	97.60 241	98.57 314

MVSFormer		99.17 74	99.12 69	99.29 144	99.51 163	98.94 158	99.88 4	99.46 176	97.55 195	99.80 34	99.65 179	97.39 114	99.28 285	99.03 78	99.85 62	99.65 122

test_djsdf		98.67 149	98.57 149	98.98 181	98.70 330	98.91 162	99.88 4	99.46 176	97.55 195	99.22 188	99.88 32	95.73 174	99.28 285	99.03 78	97.62 240	98.75 247

cascas		97.69 262	97.43 262	98.48 250	98.60 340	97.30 259	98.18 374	99.39 217	92.96 360	98.41 300	98.78 346	93.77 253	99.27 288	98.16 185	98.61 195	98.86 234

v144192		97.92 224	97.60 238	98.87 206	98.83 314	98.65 186	99.55 132	99.34 243	96.20 306	99.32 165	99.40 265	94.36 232	99.26 289	96.37 302	95.03 320	98.70 260

dmvs_re		98.08 196	98.16 173	97.85 303	99.55 154	94.67 343	99.70 52	98.92 321	98.15 126	99.06 221	99.35 279	93.67 256	99.25 290	97.77 217	97.25 270	99.64 129

RRT_MVS		98.70 144	98.66 132	98.83 216	98.90 301	98.45 209	99.89 2	99.28 274	97.76 173	98.94 239	99.92 12	96.98 131	99.25 290	99.28 56	97.00 277	98.80 238

v2v482		98.06 198	97.77 219	98.92 191	98.90 301	98.82 174	99.57 116	99.36 233	96.65 272	99.19 197	99.35 279	94.20 237	99.25 290	97.72 224	94.97 321	98.69 264

v1240		97.69 262	97.32 276	98.79 223	98.85 312	98.43 211	99.48 171	99.36 233	96.11 315	99.27 177	99.36 276	93.76 254	99.24 293	94.46 335	95.23 315	98.70 260

v1144		97.98 215	97.69 229	98.85 213	98.87 308	98.66 185	99.54 137	99.35 239	96.27 301	99.23 187	99.35 279	94.67 220	99.23 294	96.73 289	95.16 317	98.68 269

v10		97.85 233	97.52 244	98.86 210	98.99 291	98.67 184	99.75 41	99.41 206	95.70 324	98.98 233	99.41 262	94.75 214	99.23 294	96.01 308	94.63 327	98.67 276

WR-MVS_H		98.13 190	97.87 210	98.90 197	99.02 287	98.84 170	99.70 52	99.59 51	97.27 223	98.40 301	99.19 310	95.53 180	99.23 294	98.34 171	93.78 342	98.61 308

miper_enhance_ethall		98.16 187	98.08 185	98.41 262	98.96 297	97.72 248	98.45 362	99.32 260	96.95 254	98.97 235	99.17 311	97.06 128	99.22 297	97.86 207	95.99 296	98.29 337

GG-mvs-BLEND				98.45 256	98.55 343	98.16 222	99.43 191	93.68 390		97.23 339	98.46 354	89.30 335	99.22 297	95.43 321	98.22 218	97.98 355

FC-MVSNet-test		98.75 139	98.62 140	99.15 163	99.08 277	99.45 87	99.86 12	99.60 48	98.23 114	98.70 275	99.82 71	96.80 136	99.22 297	99.07 76	96.38 287	98.79 239

UniMVSNet_NR-MVSNet		98.22 179	97.97 197	98.96 184	98.92 300	98.98 143	99.48 171	99.53 90	97.76 173	98.71 269	99.46 252	96.43 150	99.22 297	98.57 148	92.87 352	98.69 264

DU-MVS		98.08 196	97.79 214	98.96 184	98.87 308	98.98 143	99.41 200	99.45 187	97.87 159	98.71 269	99.50 237	94.82 204	99.22 297	98.57 148	92.87 352	98.68 269

cl____		98.01 211	97.84 212	98.55 244	99.25 241	97.97 233	98.71 346	99.34 243	96.47 290	98.59 292	99.54 224	95.65 178	99.21 302	97.21 261	95.77 302	98.46 325

WR-MVS		98.06 198	97.73 226	99.06 169	98.86 311	99.25 109	99.19 270	99.35 239	97.30 221	98.66 278	99.43 256	93.94 247	99.21 302	98.58 145	94.28 333	98.71 255

test_0402		96.64 301	96.24 304	97.85 303	98.85 312	96.43 305	99.44 187	99.26 278	93.52 354	96.98 346	99.52 231	88.52 344	99.20 304	92.58 358	97.50 252	97.93 358

SixPastTwentyTwo		97.50 278	97.33 275	98.03 290	98.65 334	96.23 311	99.77 34	98.68 351	97.14 234	97.90 323	99.93 7	90.45 322	99.18 305	97.00 274	96.43 286	98.67 276

cl22		97.85 233	97.64 235	98.48 250	99.09 275	97.87 241	98.60 355	99.33 250	97.11 240	98.87 251	99.22 306	92.38 291	99.17 306	98.21 179	95.99 296	98.42 328

IterMVS-SCA-FT		97.82 241	97.75 224	98.06 289	99.57 146	96.36 307	99.02 304	99.49 137	97.18 231	98.71 269	99.72 146	92.72 275	99.14 307	97.44 251	95.86 301	98.67 276

pmmvs5		97.52 275	97.30 278	98.16 283	98.57 342	96.73 293	99.27 250	98.90 327	96.14 313	98.37 303	99.53 228	91.54 310	99.14 307	97.51 243	95.87 300	98.63 296

v148		97.79 246	97.55 240	98.50 247	98.74 324	97.72 248	99.54 137	99.33 250	96.26 302	98.90 245	99.51 234	94.68 219	99.14 307	97.83 210	93.15 349	98.63 296

miper_ehance_all_eth		98.18 185	98.10 181	98.41 262	99.23 243	97.72 248	98.72 345	99.31 264	96.60 279	98.88 248	99.29 295	97.29 120	99.13 310	97.60 232	95.99 296	98.38 333

NR-MVSNet		97.97 218	97.61 237	99.02 174	98.87 308	99.26 108	99.47 177	99.42 203	97.63 187	97.08 344	99.50 237	95.07 196	99.13 310	97.86 207	93.59 343	98.68 269

IterMVS		97.83 238	97.77 219	98.02 292	99.58 144	96.27 310	99.02 304	99.48 149	97.22 229	98.71 269	99.70 151	92.75 272	99.13 310	97.46 249	96.00 295	98.67 276
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 333	94.90 325	91.84 356	97.24 367	80.01 385	98.52 359	99.48 149	89.01 373	91.99 374	99.67 173	85.67 360	99.13 310	95.44 320	97.03 276	96.39 375
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 203	97.96 198	98.33 269	99.26 237	97.38 258	98.56 358	99.31 264	96.65 272	98.88 248	99.52 231	96.58 143	99.12 314	97.39 254	95.53 310	98.47 322

pmmvs4		98.13 190	97.90 205	98.81 220	98.61 339	98.87 165	98.99 311	99.21 288	96.44 291	99.06 221	99.58 209	95.90 168	99.11 315	97.18 267	96.11 293	98.46 325

TransMVSNet (Re)		97.15 292	96.58 297	98.86 210	99.12 267	98.85 169	99.49 167	98.91 325	95.48 327	97.16 342	99.80 97	93.38 259	99.11 315	94.16 341	91.73 357	98.62 299

ambc				93.06 354	92.68 385	82.36 378	98.47 361	98.73 348		95.09 362	97.41 368	55.55 386	99.10 317	96.42 300	91.32 358	97.71 361

Baseline_NR-MVSNet		97.76 248	97.45 253	98.68 231	99.09 275	98.29 216	99.41 200	98.85 332	95.65 325	98.63 286	99.67 173	94.82 204	99.10 317	98.07 195	92.89 351	98.64 288

test_vis3_rt		87.04 346	85.81 349	90.73 360	93.99 384	81.96 380	99.76 37	90.23 395	92.81 361	81.35 383	91.56 383	40.06 392	99.07 319	94.27 338	88.23 370	91.15 383

CP-MVSNet		98.09 194	97.78 217	99.01 175	98.97 296	99.24 110	99.67 64	99.46 176	97.25 225	98.48 298	99.64 185	93.79 252	99.06 320	98.63 135	94.10 336	98.74 250

PS-CasMVS		97.93 221	97.59 239	98.95 186	98.99 291	99.06 135	99.68 61	99.52 95	97.13 235	98.31 306	99.68 167	92.44 290	99.05 321	98.51 156	94.08 337	98.75 247

K. test v3		97.10 294	96.79 294	98.01 293	98.72 327	96.33 308	99.87 9	97.05 376	97.59 189	96.16 353	99.80 97	88.71 339	99.04 322	96.69 292	96.55 284	98.65 286

new_pmnet		96.38 307	96.03 309	97.41 321	98.13 353	95.16 336	99.05 296	99.20 289	93.94 349	97.39 336	98.79 345	91.61 309	99.04 322	90.43 364	95.77 302	98.05 349

DIV-MVS_self_test		98.01 211	97.85 211	98.48 250	99.24 242	97.95 237	98.71 346	99.35 239	96.50 284	98.60 291	99.54 224	95.72 175	99.03 324	97.21 261	95.77 302	98.46 325

IterMVS-LS		98.46 160	98.42 158	98.58 238	99.59 142	98.00 231	99.37 219	99.43 201	96.94 256	99.07 217	99.59 205	97.87 103	99.03 324	98.32 174	95.62 307	98.71 255
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 269	97.68 230	97.55 318	98.62 337	94.97 338	98.84 333	99.30 268	96.83 263	98.19 311	99.34 283	97.01 130	99.02 326	95.00 330	96.01 294	98.64 288

Patchmtry		97.75 252	97.40 265	98.81 220	99.10 272	98.87 165	99.11 287	99.33 250	94.83 340	98.81 258	99.38 270	94.33 233	99.02 326	96.10 304	95.57 308	98.53 316

N_pmnet		94.95 327	95.83 314	92.31 355	98.47 346	79.33 386	99.12 281	92.81 393	93.87 350	97.68 330	99.13 316	93.87 249	99.01 328	91.38 361	96.19 291	98.59 312

CR-MVSNet		98.17 186	97.93 203	98.87 206	99.18 254	98.49 205	99.22 267	99.33 250	96.96 252	99.56 107	99.38 270	94.33 233	99.00 329	94.83 332	98.58 198	99.14 205

c3_l		98.12 192	98.04 190	98.38 266	99.30 226	97.69 252	98.81 336	99.33 250	96.67 270	98.83 256	99.34 283	97.11 125	98.99 330	97.58 234	95.34 313	98.48 320

test0.0.03 1		97.71 260	97.42 263	98.56 242	98.41 349	97.82 244	98.78 339	98.63 352	97.34 217	98.05 319	98.98 332	94.45 230	98.98 331	95.04 329	97.15 275	98.89 233

PatchT		97.03 295	96.44 300	98.79 223	98.99 291	98.34 215	99.16 273	99.07 306	92.13 363	99.52 116	97.31 372	94.54 228	98.98 331	88.54 371	98.73 194	99.03 221

GBi-Net		97.68 264	97.48 248	98.29 274	99.51 163	97.26 263	99.43 191	99.48 149	96.49 285	99.07 217	99.32 290	90.26 324	98.98 331	97.10 269	96.65 280	98.62 299

test1		97.68 264	97.48 248	98.29 274	99.51 163	97.26 263	99.43 191	99.48 149	96.49 285	99.07 217	99.32 290	90.26 324	98.98 331	97.10 269	96.65 280	98.62 299

FMVSNet3		98.03 206	97.76 223	98.84 214	99.39 204	98.98 143	99.40 208	99.38 224	96.67 270	99.07 217	99.28 297	92.93 267	98.98 331	97.10 269	96.65 280	98.56 315

FMVSNet2		97.72 257	97.36 268	98.80 222	99.51 163	98.84 170	99.45 181	99.42 203	96.49 285	98.86 255	99.29 295	90.26 324	98.98 331	96.44 299	96.56 283	98.58 313

FMVSNet1		96.84 298	96.36 302	98.29 274	99.32 224	97.26 263	99.43 191	99.48 149	95.11 332	98.55 293	99.32 290	83.95 367	98.98 331	95.81 311	96.26 290	98.62 299

ppachtmachnet_test		97.49 281	97.45 253	97.61 316	98.62 337	95.24 332	98.80 337	99.46 176	96.11 315	98.22 310	99.62 196	96.45 148	98.97 338	93.77 343	95.97 299	98.61 308

TranMVSNet+NR-MVSNet		97.93 221	97.66 232	98.76 226	98.78 319	98.62 189	99.65 75	99.49 137	97.76 173	98.49 297	99.60 203	94.23 236	98.97 338	98.00 197	92.90 350	98.70 260

test_method		91.10 342	91.36 344	90.31 361	95.85 374	73.72 393	94.89 382	99.25 280	68.39 385	95.82 356	99.02 328	80.50 375	98.95 340	93.64 345	94.89 325	98.25 340

ADS-MVSNet2		98.02 208	98.07 188	97.87 302	99.33 218	95.19 334	99.23 263	99.08 303	96.24 303	99.10 212	99.67 173	94.11 241	98.93 341	96.81 286	99.05 171	99.48 171

ET-MVSNet_ETH3D		96.49 304	95.64 318	99.05 171	99.53 157	98.82 174	98.84 333	97.51 374	97.63 187	84.77 379	99.21 309	92.09 294	98.91 342	98.98 83	92.21 356	99.41 187

miper_lstm_enhance		98.00 213	97.91 204	98.28 277	99.34 216	97.43 257	98.88 329	99.36 233	96.48 288	98.80 260	99.55 219	95.98 161	98.91 342	97.27 258	95.50 311	98.51 318

PEN-MVS		97.76 248	97.44 258	98.72 228	98.77 322	98.54 196	99.78 32	99.51 109	97.06 245	98.29 308	99.64 185	92.63 281	98.89 344	98.09 188	93.16 348	98.72 253

testing3		97.28 287	96.76 295	98.82 217	99.37 208	98.07 228	99.45 181	99.36 233	97.56 194	97.89 324	98.95 335	83.70 368	98.82 345	96.03 306	98.56 201	99.58 147

testgi		97.65 269	97.50 247	98.13 287	99.36 211	96.45 304	99.42 198	99.48 149	97.76 173	97.87 325	99.45 253	91.09 316	98.81 346	94.53 334	98.52 204	99.13 207

testf1		90.42 344	90.68 346	89.65 364	97.78 357	73.97 391	99.13 279	98.81 336	89.62 371	91.80 375	98.93 336	62.23 384	98.80 347	86.61 379	91.17 359	96.19 376

APD_test2		90.42 344	90.68 346	89.65 364	97.78 357	73.97 391	99.13 279	98.81 336	89.62 371	91.80 375	98.93 336	62.23 384	98.80 347	86.61 379	91.17 359	96.19 376

MIMVSNet		97.73 255	97.45 253	98.57 239	99.45 189	97.50 255	99.02 304	98.98 314	96.11 315	99.41 140	99.14 315	90.28 323	98.74 349	95.74 313	98.93 179	99.47 177

LCM-MVSNet-Re		97.83 238	98.15 175	96.87 336	99.30 226	92.25 365	99.59 101	98.26 359	97.43 210	96.20 352	99.13 316	96.27 154	98.73 350	98.17 184	98.99 176	99.64 129

myMVS_eth3d		96.89 296	96.37 301	98.43 261	99.00 289	97.16 267	99.29 242	99.39 217	97.06 245	97.41 334	98.15 361	83.46 369	98.68 351	95.27 325	98.34 209	99.45 182

DTE-MVSNet		97.51 277	97.19 285	98.46 255	98.63 336	98.13 225	99.84 13	99.48 149	96.68 269	97.97 322	99.67 173	92.92 268	98.56 352	96.88 285	92.60 355	98.70 260

PC_three_1452									98.18 124	99.84 23	99.70 151	99.31 3	98.52 353	98.30 176	99.80 90	99.81 54

mvsany_test3		93.77 335	93.45 339	94.74 348	95.78 375	88.01 373	99.64 78	98.25 360	98.28 106	94.31 365	97.97 365	68.89 380	98.51 354	97.50 244	90.37 364	97.71 361

UnsupCasMVSNet_bld		93.53 336	92.51 341	96.58 341	97.38 363	93.82 352	98.24 371	99.48 149	91.10 368	93.10 370	96.66 374	74.89 378	98.37 355	94.03 342	87.71 371	97.56 366

Anonymous20240521		96.20 310	95.89 313	97.13 328	97.72 360	94.96 339	99.79 31	99.29 272	93.01 359	97.20 341	99.03 326	89.69 332	98.36 356	91.16 362	96.13 292	98.07 347

test_f		91.90 341	91.26 345	93.84 350	95.52 379	85.92 375	99.69 55	98.53 357	95.31 329	93.87 367	96.37 376	55.33 387	98.27 357	95.70 314	90.98 362	97.32 369

MDA-MVSNet_test_wron		95.45 320	94.60 327	98.01 293	98.16 352	97.21 266	99.11 287	99.24 282	93.49 355	80.73 385	98.98 332	93.02 265	98.18 358	94.22 340	94.45 330	98.64 288

UnsupCasMVSNet_eth		96.44 305	96.12 306	97.40 322	98.65 334	95.65 320	99.36 223	99.51 109	97.13 235	96.04 355	98.99 330	88.40 345	98.17 359	96.71 290	90.27 365	98.40 331

KD-MVS_2432*1600		94.62 328	93.72 336	97.31 323	97.19 369	95.82 318	98.34 366	99.20 289	95.00 336	97.57 331	98.35 357	87.95 350	98.10 360	92.87 354	77.00 383	98.01 351

miper_refine_blended		94.62 328	93.72 336	97.31 323	97.19 369	95.82 318	98.34 366	99.20 289	95.00 336	97.57 331	98.35 357	87.95 350	98.10 360	92.87 354	77.00 383	98.01 351

YYNet1		95.36 322	94.51 329	97.92 299	97.89 355	97.10 269	99.10 289	99.23 283	93.26 358	80.77 384	99.04 325	92.81 271	98.02 362	94.30 336	94.18 335	98.64 288

EU-MVSNet		97.98 215	98.03 191	97.81 309	98.72 327	96.65 297	99.66 69	99.66 27	98.09 136	98.35 304	99.82 71	95.25 192	98.01 363	97.41 253	95.30 314	98.78 240

Gipuma		90.99 343	90.15 348	93.51 351	98.73 325	90.12 371	93.98 383	99.45 187	79.32 381	92.28 373	94.91 378	69.61 379	97.98 364	87.42 375	95.67 306	92.45 381
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 323	94.73 326	97.15 326	95.53 378	95.94 316	99.35 228	99.10 300	95.13 330	93.55 368	97.54 367	88.15 349	97.91 365	94.58 333	89.69 368	97.61 364

PM-MVS		92.96 338	92.23 342	95.14 347	95.61 376	89.98 372	99.37 219	98.21 362	94.80 341	95.04 363	97.69 366	65.06 381	97.90 366	94.30 336	89.98 367	97.54 367

MDA-MVSNet-bldmvs		94.96 326	93.98 333	97.92 299	98.24 351	97.27 261	99.15 276	99.33 250	93.80 351	80.09 386	99.03 326	88.31 346	97.86 367	93.49 347	94.36 332	98.62 299

Patchmatch-RL test		95.84 316	95.81 315	95.95 345	95.61 376	90.57 370	98.24 371	98.39 358	95.10 334	95.20 360	98.67 349	94.78 209	97.77 368	96.28 303	90.02 366	99.51 166

Anonymous20231206		96.22 308	96.03 309	96.79 338	97.31 366	94.14 350	99.63 82	99.08 303	96.17 309	97.04 345	99.06 323	93.94 247	97.76 369	86.96 377	95.06 319	98.47 322

SD-MVS		99.41 43	99.52 9	99.05 171	99.74 76	99.68 48	99.46 180	99.52 95	99.11 22	99.88 14	99.91 16	99.43 1	97.70 370	98.72 123	99.93 17	99.77 75
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
DSMNet-mixed		97.25 289	97.35 270	96.95 334	97.84 356	93.61 358	99.57 116	96.63 381	96.13 314	98.87 251	98.61 352	94.59 223	97.70 370	95.08 328	98.86 185	99.55 152

pmmvs3		94.09 334	93.25 340	96.60 340	94.76 383	94.49 345	98.92 325	98.18 364	89.66 370	96.48 350	98.06 364	86.28 357	97.33 372	89.68 367	87.20 372	97.97 356

KD-MVS_self_test		95.00 325	94.34 330	96.96 333	97.07 371	95.39 330	99.56 122	99.44 195	95.11 332	97.13 343	97.32 371	91.86 299	97.27 373	90.35 365	81.23 380	98.23 342

FMVSNet5		96.43 306	96.19 305	97.15 326	99.11 269	95.89 317	99.32 234	99.52 95	94.47 347	98.34 305	99.07 321	87.54 354	97.07 374	92.61 357	95.72 305	98.47 322

new-patchmatchnet		94.48 331	94.08 332	95.67 346	95.08 381	92.41 364	99.18 271	99.28 274	94.55 346	93.49 369	97.37 370	87.86 352	97.01 375	91.57 360	88.36 369	97.61 364

LCM-MVSNet		86.80 348	85.22 352	91.53 358	87.81 390	80.96 383	98.23 373	98.99 313	71.05 383	90.13 378	96.51 375	48.45 391	96.88 376	90.51 363	85.30 374	96.76 371

CL-MVSNet_self_test		94.49 330	93.97 334	96.08 344	96.16 373	93.67 357	98.33 368	99.38 224	95.13 330	97.33 337	98.15 361	92.69 279	96.57 377	88.67 370	79.87 381	97.99 354

MIMVSNet1		95.51 319	95.04 324	96.92 335	97.38 363	95.60 321	99.52 144	99.50 129	93.65 353	96.97 347	99.17 311	85.28 363	96.56 378	88.36 372	95.55 309	98.60 311

test20.03		96.12 312	95.96 311	96.63 339	97.44 362	95.45 328	99.51 150	99.38 224	96.55 282	96.16 353	99.25 303	93.76 254	96.17 379	87.35 376	94.22 334	98.27 338

tmp_tt		82.80 350	81.52 353	86.66 366	66.61 396	68.44 394	92.79 385	97.92 366	68.96 384	80.04 387	99.85 50	85.77 359	96.15 380	97.86 207	43.89 389	95.39 379

test_fmvs3		92.10 340	91.77 343	93.08 353	96.19 372	86.25 374	99.82 17	98.62 353	96.65 272	95.19 361	96.90 373	55.05 388	95.93 381	96.63 296	90.92 363	97.06 370

dmvs_testset		95.02 324	96.12 306	91.72 357	99.10 272	80.43 384	99.58 109	97.87 368	97.47 203	95.22 359	98.82 343	93.99 245	95.18 382	88.09 373	94.91 324	99.56 151

PMMVS2		86.87 347	85.37 351	91.35 359	90.21 388	83.80 377	98.89 328	97.45 375	83.13 380	91.67 377	95.03 377	48.49 390	94.70 383	85.86 381	77.62 382	95.54 378

PMVS	70.75 22	75.98 356	74.97 357	79.01 372	70.98 395	55.18 396	93.37 384	98.21 362	65.08 389	61.78 390	93.83 380	21.74 397	92.53 384	78.59 383	91.12 361	89.34 385
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 349	85.65 350	82.75 370	86.77 391	63.39 395	98.35 365	98.92 321	74.11 382	83.39 381	98.98 332	50.85 389	92.40 385	84.54 382	94.97 321	92.46 380

WB-MVS		93.10 337	94.10 331	90.12 362	95.51 380	81.88 381	99.73 47	99.27 277	95.05 335	93.09 371	98.91 340	94.70 218	91.89 386	76.62 384	94.02 339	96.58 373

SSC-MVS		92.73 339	93.73 335	89.72 363	95.02 382	81.38 382	99.76 37	99.23 283	94.87 339	92.80 372	98.93 336	94.71 217	91.37 387	74.49 386	93.80 341	96.42 374

MVE	76.82 21	76.91 355	74.31 359	84.70 367	85.38 393	76.05 390	96.88 381	93.17 391	67.39 386	71.28 388	89.01 387	21.66 398	87.69 388	71.74 387	72.29 385	90.35 384
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 352	79.88 354	82.81 369	90.75 387	76.38 389	97.69 378	95.76 384	66.44 387	83.52 380	92.25 382	62.54 383	87.16 389	68.53 388	61.40 386	84.89 387

EMVS		80.02 353	79.22 355	82.43 371	91.19 386	76.40 388	97.55 380	92.49 394	66.36 388	83.01 382	91.27 384	64.63 382	85.79 390	65.82 389	60.65 387	85.08 386

ANet_high		77.30 354	74.86 358	84.62 368	75.88 394	77.61 387	97.63 379	93.15 392	88.81 374	64.27 389	89.29 386	36.51 393	83.93 391	75.89 385	52.31 388	92.33 382

wuyk23d		40.18 357	41.29 362	36.84 373	86.18 392	49.12 397	79.73 386	22.81 398	27.64 390	25.46 393	28.45 393	21.98 396	48.89 392	55.80 390	23.56 392	12.51 390

test123		39.01 359	42.50 361	28.53 374	39.17 397	20.91 398	98.75 342	19.17 399	19.83 392	38.57 391	66.67 389	33.16 394	15.42 393	37.50 392	29.66 391	49.26 388

testmvs		39.17 358	43.78 360	25.37 375	36.04 398	16.84 399	98.36 364	26.56 397	20.06 391	38.51 392	67.32 388	29.64 395	15.30 394	37.59 391	39.90 390	43.98 389

test_blank		0.13 363	0.17 366	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	1.57 394	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

uanet_test		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

DCPMVS		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

cdsmvs_eth3d_5k		24.64 360	32.85 363	0.00 376	0.00 399	0.00 400	0.00 387	99.51 109	0.00 394	0.00 395	99.56 216	96.58 143	0.00 395	0.00 393	0.00 393	0.00 391

pcd_1.5k_mvsjas		8.27 362	11.03 365	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	99.01 18	0.00 395	0.00 393	0.00 393	0.00 391

sosnet-low-res		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

sosnet		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

uncertanet		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

Regformer		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

ab-mvs-re		8.30 361	11.06 364	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	99.58 209	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

uanet		0.02 364	0.03 367	0.00 376	0.00 399	0.00 400	0.00 387	0.00 400	0.00 394	0.00 395	0.27 395	0.00 399	0.00 395	0.00 393	0.00 393	0.00 391

FOURS1					99.91 1	99.93 1	99.87 9	99.56 63	99.10 23	99.81 31

test_one_0601					99.81 42	99.88 8		99.49 137	98.97 46	99.65 82	99.81 84	99.09 14

eth-test2					0.00 399

eth-test					0.00 399

RE-MVS-def			99.34 32		99.76 61	99.82 22	99.63 82	99.52 95	98.38 95	99.76 50	99.82 71	98.75 55		98.61 139	99.81 86	99.77 75

IU-MVS					99.84 31	99.88 8		99.32 260	98.30 105	99.84 23				98.86 103	99.85 62	99.89 13

save fliter					99.76 61	99.59 64	99.14 278	99.40 214	99.00 38

test0726					99.85 25	99.89 4	99.62 88	99.50 129	99.10 23	99.86 21	99.82 71	98.94 29

GSMVS																99.52 160

test_part2					99.81 42	99.83 16				99.77 45

sam_mvs1												94.86 203				99.52 160

sam_mvs												94.72 216

MTGPA								99.47 167

MTMP							99.54 137	98.88 329

test9_res														97.49 245	99.72 111	99.75 81

agg_prior2														97.21 261	99.73 110	99.75 81

test_prior4						99.56 69	98.99 311

test_prior2							98.96 318		98.34 101	99.01 227	99.52 231	98.68 62		97.96 199	99.74 108

新几何2							99.01 309

旧先验1					99.74 76	99.59 64		99.54 79			99.69 161	98.47 78			99.68 119	99.73 90

原ACMM2							98.95 321

test222					99.75 69	99.49 81	98.91 327	99.49 137	96.42 293	99.34 163	99.65 179	98.28 90			99.69 116	99.72 96

segment_acmp												98.96 24

testdata1							98.85 332		98.32 104

plane_prior7					99.29 230	97.03 279

plane_prior6					99.27 235	96.98 283						92.71 277

plane_prior4											99.61 200

plane_prior3						97.00 281			98.69 73	99.11 209

plane_prior2							99.39 212		98.97 46

plane_prior1					99.26 237

plane_prior						96.97 284	99.21 269		98.45 89						97.60 241

n2								0.00 400

nn								0.00 400

door-mid								98.05 365

test11								99.35 239

door								97.92 366

HQP5-MVS						96.83 289

HQP-NCC					99.19 251		98.98 314		98.24 111	98.66 278

ACMP_Plane					99.19 251		98.98 314		98.24 111	98.66 278

BP-MVS														97.19 265

HQP3-MVS								99.39 217							97.58 243

HQP2-MVS												92.47 286

NP-MVS					99.23 243	96.92 287					99.40 265

MDTV_nov1_ep13_2view						95.18 335	99.35 228		96.84 261	99.58 103		95.19 194		97.82 211		99.46 179

ACMMP++_ref															97.19 273

ACMMP++															97.43 262

Test By Simon												98.75 55

High-resolution multi-view benchmark