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 6	99.61 6	99.77 55	99.38 211	99.37 100	99.58 109	99.62 41	99.41 9	99.87 25	99.92 14	98.81 44	100.00 1	99.97 1	99.93 22	99.94 11

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 52	99.84 32	99.44 94	99.58 109	99.69 18	99.43 7	99.98 6	99.91 20	98.62 70	100.00 1	99.97 1	99.95 16	99.90 17

test_vis1_n_1920		98.63 159	98.40 166	99.31 143	99.86 20	97.94 247	99.67 64	99.62 41	99.43 7	99.99 2	99.91 20	87.29 364	100.00 1	99.92 12	99.92 24	99.98 2

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 28	99.86 20	99.61 67	99.56 122	99.63 39	99.48 3	99.98 6	99.83 68	98.75 55	99.99 4	99.97 1	99.96 12	99.94 11

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 28	99.84 32	99.63 64	99.56 122	99.63 39	99.47 4	99.98 6	99.82 76	98.75 55	99.99 4	99.97 1	99.97 7	99.94 11

test_fmvsmconf_n		99.70 3	99.64 4	99.87 11	99.80 52	99.66 53	99.48 178	99.64 36	99.45 5	99.92 15	99.92 14	98.62 70	99.99 4	99.96 7	99.99 1	99.96 7

patch_mono-2		99.26 68	99.62 5	98.16 291	99.81 46	94.59 354	99.52 148	99.64 36	99.33 13	99.73 62	99.90 26	99.00 22	99.99 4	99.69 19	99.98 4	99.89 20

h-mvs33		97.70 267	97.28 287	98.97 191	99.70 101	97.27 270	99.36 230	99.45 193	98.94 54	99.66 83	99.64 192	94.93 204	99.99 4	99.48 41	84.36 385	99.65 129

xiu_mvs_v1_base_debu		99.29 62	99.27 57	99.34 136	99.63 130	98.97 153	99.12 291	99.51 115	98.86 60	99.84 29	99.47 255	98.18 96	99.99 4	99.50 36	99.31 157	99.08 222

xiu_mvs_v1_base		99.29 62	99.27 57	99.34 136	99.63 130	98.97 153	99.12 291	99.51 115	98.86 60	99.84 29	99.47 255	98.18 96	99.99 4	99.50 36	99.31 157	99.08 222

xiu_mvs_v1_base_debi		99.29 62	99.27 57	99.34 136	99.63 130	98.97 153	99.12 291	99.51 115	98.86 60	99.84 29	99.47 255	98.18 96	99.99 4	99.50 36	99.31 157	99.08 222

EPNet		98.86 127	98.71 131	99.30 148	97.20 377	98.18 229	99.62 88	98.91 332	99.28 16	98.63 294	99.81 90	95.96 167	99.99 4	99.24 68	99.72 118	99.73 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM				99.74 61		99.31 107	99.52 148	98.87 338	99.55 1	99.74 60	99.80 103	96.47 151	99.98 13	99.97 1	99.97 7	99.94 11

test_cas_vis1_n_1920		99.16 82	99.01 94	99.61 84	99.81 46	98.86 175	99.65 75	99.64 36	99.39 10	99.97 13	99.94 6	93.20 273	99.98 13	99.55 29	99.91 31	99.99 1

test_vis1_n		97.92 230	97.44 265	99.34 136	99.53 162	98.08 235	99.74 44	99.49 143	99.15 20	100.00 1	99.94 6	79.51 386	99.98 13	99.88 14	99.76 110	99.97 4

xiu_mvs_v2_base		99.26 68	99.25 61	99.29 151	99.53 162	98.91 169	99.02 314	99.45 193	98.80 69	99.71 68	99.26 309	98.94 29	99.98 13	99.34 55	99.23 161	98.98 236

PS-MVSNAJ		99.32 58	99.32 40	99.30 148	99.57 151	98.94 165	98.97 327	99.46 182	98.92 57	99.71 68	99.24 311	99.01 18	99.98 13	99.35 51	99.66 128	98.97 237

QAPM		98.67 155	98.30 173	99.80 46	99.20 255	99.67 51	99.77 34	99.72 11	94.74 352	98.73 275	99.90 26	95.78 177	99.98 13	96.96 286	99.88 51	99.76 87

3Dnovator	97.25 9	99.24 73	99.05 82	99.81 44	99.12 274	99.66 53	99.84 13	99.74 10	99.09 32	98.92 250	99.90 26	95.94 170	99.98 13	98.95 93	99.92 24	99.79 74

OpenMVS	96.50 16	98.47 165	98.12 185	99.52 111	99.04 292	99.53 82	99.82 17	99.72 11	94.56 355	98.08 324	99.88 36	94.73 221	99.98 13	97.47 255	99.76 110	99.06 228

test_fmvsmconf0.1_n		99.55 14	99.45 21	99.86 21	99.44 196	99.65 57	99.50 163	99.61 48	99.45 5	99.87 25	99.92 14	97.31 121	99.97 21	99.95 8	99.99 1	99.97 4

test_fmvs1_n		98.41 171	98.14 182	99.21 162	99.82 42	97.71 259	99.74 44	99.49 143	99.32 14	99.99 2	99.95 3	85.32 371	99.97 21	99.82 16	99.84 77	99.96 7

CANet_DTU		98.97 117	98.87 114	99.25 157	99.33 224	98.42 221	99.08 300	99.30 275	99.16 19	99.43 140	99.75 138	95.27 195	99.97 21	98.56 158	99.95 16	99.36 200

MTAPA		99.52 17	99.39 27	99.89 4	99.90 4	99.86 13	99.66 69	99.47 173	98.79 70	99.68 74	99.81 90	98.43 83	99.97 21	98.88 102	99.90 39	99.83 49

PGM-MVS		99.45 33	99.31 47	99.86 21	99.87 15	99.78 36	99.58 109	99.65 33	97.84 171	99.71 68	99.80 103	99.12 13	99.97 21	98.33 179	99.87 54	99.83 49

mPP-MVS		99.44 37	99.30 49	99.86 21	99.88 11	99.79 30	99.69 55	99.48 155	98.12 138	99.50 126	99.75 138	98.78 48	99.97 21	98.57 155	99.89 48	99.83 49

CP-MVS		99.45 33	99.32 40	99.85 28	99.83 39	99.75 39	99.69 55	99.52 101	98.07 148	99.53 121	99.63 198	98.93 33	99.97 21	98.74 127	99.91 31	99.83 49

SteuartSystems-ACMMP		99.54 15	99.42 22	99.87 11	99.82 42	99.81 25	99.59 101	99.51 115	98.62 83	99.79 42	99.83 68	99.28 4	99.97 21	98.48 165	99.90 39	99.84 40
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 78	98.97 100	99.82 41	99.17 266	99.68 48	99.81 20	99.51 115	99.20 18	98.72 276	99.89 30	95.68 182	99.97 21	98.86 110	99.86 62	99.81 61

fmvsm_s_conf0.5_n_a		99.56 13	99.47 17	99.85 28	99.83 39	99.64 63	99.52 148	99.65 33	99.10 27	99.98 6	99.92 14	97.35 120	99.96 30	99.94 10	99.92 24	99.95 9

fmvsm_s_conf0.5_n		99.51 18	99.40 25	99.85 28	99.84 32	99.65 57	99.51 156	99.67 23	99.13 22	99.98 6	99.92 14	96.60 146	99.96 30	99.95 8	99.96 12	99.95 9

mvsany_test1		99.50 20	99.46 20	99.62 83	99.61 140	99.09 136	98.94 333	99.48 155	99.10 27	99.96 14	99.91 20	98.85 39	99.96 30	99.72 18	99.58 137	99.82 54

test_fmvs1		98.88 123	98.79 125	99.16 167	99.69 106	97.61 262	99.55 134	99.49 143	99.32 14	99.98 6	99.91 20	91.41 320	99.96 30	99.82 16	99.92 24	99.90 17

DVP-MVS++		99.59 8	99.50 13	99.88 5	99.51 169	99.88 8	99.87 9	99.51 115	98.99 45	99.88 20	99.81 90	99.27 5	99.96 30	98.85 112	99.80 97	99.81 61

MSC_two_6792asdad				99.87 11	99.51 169	99.76 37		99.33 257					99.96 30	98.87 105	99.84 77	99.89 20

No_MVS				99.87 11	99.51 169	99.76 37		99.33 257					99.96 30	98.87 105	99.84 77	99.89 20

ZD-MVS					99.71 96	99.79 30		99.61 48	96.84 271	99.56 114	99.54 231	98.58 72	99.96 30	96.93 289	99.75 112

SED-MVS		99.61 7	99.52 11	99.88 5	99.84 32	99.90 2	99.60 95	99.48 155	99.08 33	99.91 16	99.81 90	99.20 7	99.96 30	98.91 99	99.85 69	99.79 74

test_241102_TWO								99.48 155	99.08 33	99.88 20	99.81 90	98.94 29	99.96 30	98.91 99	99.84 77	99.88 26

ZNCC-MVS		99.47 29	99.33 38	99.87 11	99.87 15	99.81 25	99.64 78	99.67 23	98.08 147	99.55 118	99.64 192	98.91 34	99.96 30	98.72 130	99.90 39	99.82 54

DVP-MVS		99.57 12	99.47 17	99.88 5	99.85 26	99.89 4	99.57 116	99.37 239	99.10 27	99.81 37	99.80 103	98.94 29	99.96 30	98.93 96	99.86 62	99.81 61
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 45	99.81 37	99.80 103	99.09 14	99.96 30	98.85 112	99.90 39	99.88 26

test_0728_SECOND				99.91 2	99.84 32	99.89 4	99.57 116	99.51 115					99.96 30	98.93 96	99.86 62	99.88 26

SR-MVS		99.43 40	99.29 53	99.86 21	99.75 73	99.83 16	99.59 101	99.62 41	98.21 124	99.73 62	99.79 115	98.68 64	99.96 30	98.44 170	99.77 107	99.79 74

DPE-MVS		99.46 31	99.32 40	99.91 2	99.78 56	99.88 8	99.36 230	99.51 115	98.73 76	99.88 20	99.84 64	98.72 61	99.96 30	98.16 192	99.87 54	99.88 26
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MVS_0304		99.42 42	99.32 40	99.72 65	99.70 101	99.27 113	99.52 148	97.57 383	99.51 2	99.82 35	99.78 121	98.09 100	99.96 30	99.97 1	99.97 7	99.94 11

UA-Net		99.42 42	99.29 53	99.80 46	99.62 136	99.55 77	99.50 163	99.70 15	98.79 70	99.77 51	99.96 1	97.45 115	99.96 30	98.92 98	99.90 39	99.89 20

HFP-MVS		99.49 22	99.37 30	99.86 21	99.87 15	99.80 27	99.66 69	99.67 23	98.15 133	99.68 74	99.69 168	99.06 16	99.96 30	98.69 135	99.87 54	99.84 40

region2R		99.48 26	99.35 34	99.87 11	99.88 11	99.80 27	99.65 75	99.66 28	98.13 137	99.66 83	99.68 174	98.96 24	99.96 30	98.62 143	99.87 54	99.84 40

HPM-MVS++		99.39 51	99.23 64	99.87 11	99.75 73	99.84 15	99.43 198	99.51 115	98.68 81	99.27 184	99.53 235	98.64 69	99.96 30	98.44 170	99.80 97	99.79 74

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 62	99.89 4	99.75 41	99.56 69	99.02 38	99.88 20	99.85 54	99.18 10	99.96 30	99.22 69	99.92 24	99.90 17
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 22	99.36 32	99.86 21	99.87 15	99.79 30	99.66 69	99.67 23	98.15 133	99.67 78	99.69 168	98.95 27	99.96 30	98.69 135	99.87 54	99.84 40

MP-MVS		99.33 57	99.15 70	99.87 11	99.88 11	99.82 22	99.66 69	99.46 182	98.09 143	99.48 130	99.74 143	98.29 91	99.96 30	97.93 208	99.87 54	99.82 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 98	98.90 109	99.74 61	99.80 52	99.46 92	99.59 101	99.49 143	97.03 258	99.63 96	99.69 168	97.27 124	99.96 30	97.82 218	99.84 77	99.81 61

PVSNet_Blended_VisFu		99.36 54	99.28 55	99.61 84	99.86 20	99.07 141	99.47 184	99.93 2	97.66 193	99.71 68	99.86 49	97.73 110	99.96 30	99.47 43	99.82 90	99.79 74

UGNet		98.87 124	98.69 133	99.40 130	99.22 252	98.72 188	99.44 194	99.68 20	99.24 17	99.18 207	99.42 265	92.74 283	99.96 30	99.34 55	99.94 21	99.53 166
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 58	99.32 40	99.32 142	99.85 26	98.29 224	99.71 51	99.66 28	98.11 140	99.41 147	99.80 103	98.37 88	99.96 30	98.99 89	99.96 12	99.72 103

ACMMP		99.45 33	99.32 40	99.82 41	99.89 8	99.67 51	99.62 88	99.69 18	98.12 138	99.63 96	99.84 64	98.73 60	99.96 30	98.55 161	99.83 86	99.81 61
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 75	99.03 86	99.79 49	98.42 357	99.48 89	99.55 134	99.51 115	99.39 10	99.78 47	99.93 9	94.80 213	99.95 59	99.93 11	99.95 16	99.94 11

SR-MVS-dyc-post		99.45 33	99.31 47	99.85 28	99.76 65	99.82 22	99.63 82	99.52 101	98.38 102	99.76 56	99.82 76	98.53 76	99.95 59	98.61 146	99.81 93	99.77 82

GST-MVS		99.40 50	99.24 62	99.85 28	99.86 20	99.79 30	99.60 95	99.67 23	97.97 159	99.63 96	99.68 174	98.52 77	99.95 59	98.38 173	99.86 62	99.81 61

CANet		99.25 72	99.14 71	99.59 87	99.41 202	99.16 125	99.35 235	99.57 64	98.82 65	99.51 125	99.61 207	96.46 152	99.95 59	99.59 25	99.98 4	99.65 129

MP-MVS-pluss		99.37 53	99.20 66	99.88 5	99.90 4	99.87 12	99.30 245	99.52 101	97.18 240	99.60 106	99.79 115	98.79 47	99.95 59	98.83 118	99.91 31	99.83 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 42	99.27 57	99.88 5	99.89 8	99.80 27	99.67 64	99.50 135	98.70 78	99.77 51	99.49 247	98.21 94	99.95 59	98.46 169	99.77 107	99.88 26
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 59	96.67 301

APD-MVS_3200maxsize		99.48 26	99.35 34	99.85 28	99.76 65	99.83 16	99.63 82	99.54 85	98.36 106	99.79 42	99.82 76	98.86 38	99.95 59	98.62 143	99.81 93	99.78 80

RPMNet		96.72 309	95.90 321	99.19 164	99.18 260	98.49 212	99.22 276	99.52 101	88.72 385	99.56 114	97.38 379	94.08 251	99.95 59	86.87 389	98.58 206	99.14 214

sss		99.17 80	99.05 82	99.53 105	99.62 136	98.97 153	99.36 230	99.62 41	97.83 172	99.67 78	99.65 186	97.37 119	99.95 59	99.19 71	99.19 164	99.68 119

fmvsm_s_conf0.1_n_a		99.26 68	99.06 81	99.85 28	99.52 166	99.62 65	99.54 139	99.62 41	98.69 79	99.99 2	99.96 1	94.47 237	99.94 69	99.88 14	99.92 24	99.98 2

fmvsm_s_conf0.1_n		99.29 62	99.10 75	99.86 21	99.70 101	99.65 57	99.53 147	99.62 41	98.74 75	99.99 2	99.95 3	94.53 235	99.94 69	99.89 13	99.96 12	99.97 4

TSAR-MVS + MP.		99.58 9	99.50 13	99.81 44	99.91 1	99.66 53	99.63 82	99.39 223	98.91 58	99.78 47	99.85 54	99.36 2	99.94 69	98.84 115	99.88 51	99.82 54
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 16	99.42 22	99.87 11	99.85 26	99.83 16	99.69 55	99.68 20	98.98 48	99.37 160	99.74 143	98.81 44	99.94 69	98.79 123	99.86 62	99.84 40

X-MVStestdata		96.55 311	95.45 329	99.87 11	99.85 26	99.83 16	99.69 55	99.68 20	98.98 48	99.37 160	64.01 402	98.81 44	99.94 69	98.79 123	99.86 62	99.84 40

旧先验2							98.96 328		96.70 278	99.47 131			99.94 69	98.19 188

新几何1				99.75 58	99.75 73	99.59 70		99.54 85	96.76 274	99.29 179	99.64 192	98.43 83	99.94 69	96.92 291	99.66 128	99.72 103

testdata				99.54 97	99.75 73	98.95 162		99.51 115	97.07 252	99.43 140	99.70 158	98.87 37	99.94 69	97.76 225	99.64 131	99.72 103

HPM-MVS		99.42 42	99.28 55	99.83 40	99.90 4	99.72 42	99.81 20	99.54 85	97.59 197	99.68 74	99.63 198	98.91 34	99.94 69	98.58 152	99.91 31	99.84 40
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 76	99.10 75	99.45 123	99.89 8	98.52 208	99.39 219	99.94 1	98.73 76	99.11 216	99.89 30	95.50 187	99.94 69	99.50 36	99.97 7	99.89 20

APD-MVS		99.27 66	99.08 79	99.84 39	99.75 73	99.79 30	99.50 163	99.50 135	97.16 242	99.77 51	99.82 76	98.78 48	99.94 69	97.56 246	99.86 62	99.80 70
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 26	99.42 22	99.65 73	99.72 91	99.40 99	99.05 306	99.66 28	99.14 21	99.57 113	99.80 103	98.46 81	99.94 69	99.57 27	99.84 77	99.60 146
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		99.06 106	98.88 113	99.61 84	99.62 136	99.16 125	99.37 226	99.56 69	98.04 154	99.53 121	99.62 203	96.84 138	99.94 69	98.85 112	98.49 214	99.72 103

DeepC-MVS	98.35 2	99.30 60	99.19 67	99.64 78	99.82 42	99.23 118	99.62 88	99.55 77	98.94 54	99.63 96	99.95 3	95.82 176	99.94 69	99.37 50	99.97 7	99.73 97
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 66	99.12 73	99.74 61	99.18 260	99.75 39	99.56 122	99.57 64	98.45 96	99.49 129	99.85 54	97.77 109	99.94 69	98.33 179	99.84 77	99.52 167

SDMVSNet		99.11 98	98.90 109	99.75 58	99.81 46	99.59 70	99.81 20	99.65 33	98.78 73	99.64 93	99.88 36	94.56 231	99.93 84	99.67 21	98.26 225	99.72 103

FE-MVS		98.48 164	98.17 178	99.40 130	99.54 161	98.96 157	99.68 61	98.81 344	95.54 336	99.62 100	99.70 158	93.82 260	99.93 84	97.35 263	99.46 144	99.32 205

SF-MVS		99.38 52	99.24 62	99.79 49	99.79 54	99.68 48	99.57 116	99.54 85	97.82 176	99.71 68	99.80 103	98.95 27	99.93 84	98.19 188	99.84 77	99.74 92

dcpmvs_2		99.23 74	99.58 7	98.16 291	99.83 39	94.68 352	99.76 37	99.52 101	99.07 35	99.98 6	99.88 36	98.56 74	99.93 84	99.67 21	99.98 4	99.87 31

Anonymous20240529		98.09 200	97.68 236	99.34 136	99.66 119	98.44 218	99.40 215	99.43 207	93.67 362	99.22 195	99.89 30	90.23 336	99.93 84	99.26 67	98.33 219	99.66 125

ACMMP_NAP		99.47 29	99.34 36	99.88 5	99.87 15	99.86 13	99.47 184	99.48 155	98.05 153	99.76 56	99.86 49	98.82 43	99.93 84	98.82 122	99.91 31	99.84 40

EI-MVSNet-UG-set		99.58 9	99.57 8	99.64 78	99.78 56	99.14 131	99.60 95	99.45 193	99.01 40	99.90 18	99.83 68	98.98 23	99.93 84	99.59 25	99.95 16	99.86 33

无先验							98.99 321	99.51 115	96.89 268				99.93 84	97.53 249		99.72 103

VDDNet		97.55 280	97.02 298	99.16 167	99.49 180	98.12 234	99.38 224	99.30 275	95.35 338	99.68 74	99.90 26	82.62 381	99.93 84	99.31 58	98.13 236	99.42 193

ab-mvs		98.86 127	98.63 141	99.54 97	99.64 127	99.19 120	99.44 194	99.54 85	97.77 179	99.30 176	99.81 90	94.20 245	99.93 84	99.17 74	98.82 196	99.49 177

F-COLMAP		99.19 76	99.04 84	99.64 78	99.78 56	99.27 113	99.42 205	99.54 85	97.29 231	99.41 147	99.59 212	98.42 85	99.93 84	98.19 188	99.69 123	99.73 97

Anonymous202405211		98.30 181	97.98 202	99.26 156	99.57 151	98.16 230	99.41 207	98.55 364	96.03 330	99.19 204	99.74 143	91.87 307	99.92 95	99.16 75	98.29 224	99.70 113

EI-MVSNet-Vis-set		99.58 9	99.56 10	99.64 78	99.78 56	99.15 130	99.61 94	99.45 193	99.01 40	99.89 19	99.82 76	99.01 18	99.92 95	99.56 28	99.95 16	99.85 36

VDD-MVS		97.73 261	97.35 277	98.88 210	99.47 189	97.12 278	99.34 238	98.85 340	98.19 127	99.67 78	99.85 54	82.98 379	99.92 95	99.49 40	98.32 223	99.60 146

VNet		99.11 98	98.90 109	99.73 64	99.52 166	99.56 75	99.41 207	99.39 223	99.01 40	99.74 60	99.78 121	95.56 185	99.92 95	99.52 34	98.18 232	99.72 103

XVG-OURS-SEG-HR		98.69 152	98.62 146	98.89 208	99.71 96	97.74 254	99.12 291	99.54 85	98.44 99	99.42 143	99.71 154	94.20 245	99.92 95	98.54 162	98.90 190	99.00 233

HPM-MVS_fast		99.51 18	99.40 25	99.85 28	99.91 1	99.79 30	99.76 37	99.56 69	97.72 185	99.76 56	99.75 138	99.13 12	99.92 95	99.07 83	99.92 24	99.85 36

HY-MVS	97.30 7	98.85 134	98.64 140	99.47 120	99.42 199	99.08 139	99.62 88	99.36 240	97.39 223	99.28 180	99.68 174	96.44 154	99.92 95	98.37 175	98.22 227	99.40 197

DP-MVS		99.16 82	98.95 104	99.78 52	99.77 62	99.53 82	99.41 207	99.50 135	97.03 258	99.04 232	99.88 36	97.39 116	99.92 95	98.66 139	99.90 39	99.87 31

IB-MVS	95.67 18	96.22 317	95.44 330	98.57 247	99.21 253	96.70 304	98.65 361	97.74 381	96.71 277	97.27 348	98.54 361	86.03 367	99.92 95	98.47 168	86.30 383	99.10 217
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 22	99.39 27	99.77 55	99.63 130	99.59 70	99.36 230	99.46 182	99.07 35	99.79 42	99.82 76	98.85 39	99.92 95	98.68 137	99.87 54	99.82 54
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 75		99.72 91		99.40 215	99.51 115	97.53 207	99.64 93	99.78 121	98.84 41	99.91 105	97.63 237	99.82 90

SMA-MVS		99.44 37	99.30 49	99.85 28	99.73 87	99.83 16	99.56 122	99.47 173	97.45 215	99.78 47	99.82 76	99.18 10	99.91 105	98.79 123	99.89 48	99.81 61
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					99.67 111	99.65 57	99.05 306	99.41 212	96.22 315	98.95 245	99.49 247	98.77 51	99.91 105

train_agg		99.02 111	98.77 126	99.77 55	99.67 111	99.65 57	99.05 306	99.41 212	96.28 309	98.95 245	99.49 247	98.76 52	99.91 105	97.63 237	99.72 118	99.75 88

test_8					99.67 111	99.61 67	99.03 311	99.41 212	96.28 309	98.93 249	99.48 252	98.76 52	99.91 105

agg_prior					99.67 111	99.62 65		99.40 220		98.87 259			99.91 105

原ACMM1				99.65 73	99.73 87	99.33 103		99.47 173	97.46 212	99.12 214	99.66 185	98.67 66	99.91 105	97.70 234	99.69 123	99.71 112

LFMVS		97.90 233	97.35 277	99.54 97	99.52 166	99.01 148	99.39 219	98.24 371	97.10 250	99.65 89	99.79 115	84.79 373	99.91 105	99.28 63	98.38 216	99.69 115

XVG-OURS		98.73 148	98.68 134	98.88 210	99.70 101	97.73 255	98.92 335	99.55 77	98.52 91	99.45 134	99.84 64	95.27 195	99.91 105	98.08 199	98.84 194	99.00 233

PLC	97.94 4	99.02 111	98.85 118	99.53 105	99.66 119	99.01 148	99.24 271	99.52 101	96.85 270	99.27 184	99.48 252	98.25 93	99.91 105	97.76 225	99.62 134	99.65 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 274	97.06 297	99.47 120	99.61 140	99.09 136	98.04 386	99.25 287	91.24 377	98.51 303	99.70 158	94.55 233	99.91 105	92.76 366	99.85 69	99.42 193
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
test_vis1_rt		95.81 326	95.65 326	96.32 353	99.67 111	91.35 380	99.49 174	96.74 390	98.25 117	95.24 368	98.10 373	74.96 387	99.90 116	99.53 32	98.85 193	97.70 372

FA-MVS(test-final)		98.75 145	98.53 159	99.41 129	99.55 159	99.05 144	99.80 25	99.01 318	96.59 291	99.58 110	99.59 212	95.39 190	99.90 116	97.78 221	99.49 143	99.28 208

MCST-MVS		99.43 40	99.30 49	99.82 41	99.79 54	99.74 41	99.29 249	99.40 220	98.79 70	99.52 123	99.62 203	98.91 34	99.90 116	98.64 141	99.75 112	99.82 54

CDPH-MVS		99.13 88	98.91 108	99.80 46	99.75 73	99.71 44	99.15 285	99.41 212	96.60 289	99.60 106	99.55 226	98.83 42	99.90 116	97.48 253	99.83 86	99.78 80

NCCC		99.34 56	99.19 67	99.79 49	99.61 140	99.65 57	99.30 245	99.48 155	98.86 60	99.21 198	99.63 198	98.72 61	99.90 116	98.25 184	99.63 133	99.80 70

114514_t		98.93 119	98.67 135	99.72 65	99.85 26	99.53 82	99.62 88	99.59 57	92.65 372	99.71 68	99.78 121	98.06 102	99.90 116	98.84 115	99.91 31	99.74 92

1112_ss		98.98 115	98.77 126	99.59 87	99.68 110	99.02 146	99.25 269	99.48 155	97.23 237	99.13 212	99.58 216	96.93 137	99.90 116	98.87 105	98.78 199	99.84 40

PHI-MVS		99.30 60	99.17 69	99.70 67	99.56 155	99.52 85	99.58 109	99.80 8	97.12 246	99.62 100	99.73 149	98.58 72	99.90 116	98.61 146	99.91 31	99.68 119

AdaColmap		99.01 114	98.80 122	99.66 69	99.56 155	99.54 79	99.18 280	99.70 15	98.18 131	99.35 167	99.63 198	96.32 157	99.90 116	97.48 253	99.77 107	99.55 159

COLMAP_ROB	97.56 6	98.86 127	98.75 128	99.17 166	99.88 11	98.53 204	99.34 238	99.59 57	97.55 203	98.70 283	99.89 30	95.83 175	99.90 116	98.10 194	99.90 39	99.08 222
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 177	98.03 197	99.31 143	99.63 130	98.56 201	99.54 139	96.75 389	97.53 207	99.73 62	99.65 186	91.25 324	99.89 126	98.62 143	99.56 138	99.48 178

tttt0517		98.42 169	98.14 182	99.28 154	99.66 119	98.38 222	99.74 44	96.85 387	97.68 190	99.79 42	99.74 143	91.39 321	99.89 126	98.83 118	99.56 138	99.57 156

test12				99.75 58	99.64 127	99.61 67		99.29 279		99.21 198		98.38 87	99.89 126		99.74 115	99.74 92

Test_1112_low_res		98.89 122	98.66 138	99.57 92	99.69 106	98.95 162	99.03 311	99.47 173	96.98 260	99.15 210	99.23 312	96.77 141	99.89 126	98.83 118	98.78 199	99.86 33

CNLPA		99.14 86	98.99 96	99.59 87	99.58 149	99.41 98	99.16 282	99.44 201	98.45 96	99.19 204	99.49 247	98.08 101	99.89 126	97.73 229	99.75 112	99.48 178

sd_testset		98.75 145	98.57 155	99.29 151	99.81 46	98.26 226	99.56 122	99.62 41	98.78 73	99.64 93	99.88 36	92.02 304	99.88 131	99.54 30	98.26 225	99.72 103

APD_test1		95.87 324	96.49 308	94.00 359	99.53 162	84.01 387	99.54 139	99.32 267	95.91 332	97.99 329	99.85 54	85.49 370	99.88 131	91.96 369	98.84 194	98.12 354

diffmvs		99.14 86	99.02 90	99.51 113	99.61 140	98.96 157	99.28 253	99.49 143	98.46 95	99.72 67	99.71 154	96.50 150	99.88 131	99.31 58	99.11 171	99.67 122
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		98.86 127	98.80 122	99.03 181	99.76 65	98.79 184	99.28 253	99.91 3	97.42 220	99.67 78	99.37 280	97.53 113	99.88 131	98.98 90	97.29 278	98.42 337

PVSNet_Blended		99.08 104	98.97 100	99.42 128	99.76 65	98.79 184	98.78 349	99.91 3	96.74 275	99.67 78	99.49 247	97.53 113	99.88 131	98.98 90	99.85 69	99.60 146

MVS		97.28 294	96.55 306	99.48 117	98.78 327	98.95 162	99.27 258	99.39 223	83.53 389	98.08 324	99.54 231	96.97 135	99.87 136	94.23 348	99.16 165	99.63 140

MG-MVS		99.13 88	99.02 90	99.45 123	99.57 151	98.63 195	99.07 301	99.34 250	98.99 45	99.61 103	99.82 76	97.98 104	99.87 136	97.00 282	99.80 97	99.85 36

MSDG		98.98 115	98.80 122	99.53 105	99.76 65	99.19 120	98.75 352	99.55 77	97.25 234	99.47 131	99.77 129	97.82 107	99.87 136	96.93 289	99.90 39	99.54 161

ETV-MVS		99.26 68	99.21 65	99.40 130	99.46 190	99.30 109	99.56 122	99.52 101	98.52 91	99.44 139	99.27 307	98.41 86	99.86 139	99.10 79	99.59 136	99.04 229

thisisatest0515		98.14 195	97.79 220	99.19 164	99.50 178	98.50 211	98.61 363	96.82 388	96.95 264	99.54 119	99.43 263	91.66 316	99.86 139	98.08 199	99.51 142	99.22 211

thres600view7		97.86 238	97.51 253	98.92 199	99.72 91	97.95 245	99.59 101	98.74 351	97.94 161	99.27 184	98.62 358	91.75 310	99.86 139	93.73 353	98.19 231	98.96 239

lupinMVS		99.13 88	99.01 94	99.46 122	99.51 169	98.94 165	99.05 306	99.16 301	97.86 167	99.80 40	99.56 223	97.39 116	99.86 139	98.94 94	99.85 69	99.58 154

PVSNet	96.02 17	98.85 134	98.84 119	98.89 208	99.73 87	97.28 269	98.32 379	99.60 54	97.86 167	99.50 126	99.57 220	96.75 142	99.86 139	98.56 158	99.70 122	99.54 161

MAR-MVS		98.86 127	98.63 141	99.54 97	99.37 214	99.66 53	99.45 188	99.54 85	96.61 287	99.01 235	99.40 272	97.09 129	99.86 139	97.68 236	99.53 141	99.10 217
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		96.81 308	96.65 304	97.29 334	99.74 80	92.21 377	99.60 95	85.06 406	99.13 22	99.77 51	99.93 9	87.82 362	99.85 145	99.38 48	99.38 149	99.80 70

AllTest		98.87 124	98.72 129	99.31 143	99.86 20	98.48 214	99.56 122	99.61 48	97.85 169	99.36 164	99.85 54	95.95 168	99.85 145	96.66 302	99.83 86	99.59 150

TestCases				99.31 143	99.86 20	98.48 214		99.61 48	97.85 169	99.36 164	99.85 54	95.95 168	99.85 145	96.66 302	99.83 86	99.59 150

jason		99.13 88	99.03 86	99.45 123	99.46 190	98.87 172	99.12 291	99.26 285	98.03 156	99.79 42	99.65 186	97.02 132	99.85 145	99.02 87	99.90 39	99.65 129
jason: jason.
CNVR-MVS		99.42 42	99.30 49	99.78 52	99.62 136	99.71 44	99.26 267	99.52 101	98.82 65	99.39 155	99.71 154	98.96 24	99.85 145	98.59 151	99.80 97	99.77 82

PAPM_NR		99.04 108	98.84 119	99.66 69	99.74 80	99.44 94	99.39 219	99.38 231	97.70 188	99.28 180	99.28 304	98.34 89	99.85 145	96.96 286	99.45 145	99.69 115

testing222		97.16 299	96.50 307	99.16 167	99.16 268	98.47 216	99.27 258	98.66 360	97.71 186	98.23 318	98.15 369	82.28 383	99.84 151	97.36 262	97.66 247	99.18 213

test1111		98.04 210	98.11 186	97.83 314	99.74 80	93.82 362	99.58 109	95.40 395	99.12 25	99.65 89	99.93 9	90.73 329	99.84 151	99.43 46	99.38 149	99.82 54

ECVR-MVS		98.04 210	98.05 195	98.00 303	99.74 80	94.37 357	99.59 101	94.98 396	99.13 22	99.66 83	99.93 9	90.67 330	99.84 151	99.40 47	99.38 149	99.80 70

test_yl		98.86 127	98.63 141	99.54 97	99.49 180	99.18 122	99.50 163	99.07 313	98.22 122	99.61 103	99.51 241	95.37 191	99.84 151	98.60 149	98.33 219	99.59 150

DCV-MVSNet		98.86 127	98.63 141	99.54 97	99.49 180	99.18 122	99.50 163	99.07 313	98.22 122	99.61 103	99.51 241	95.37 191	99.84 151	98.60 149	98.33 219	99.59 150

Fast-Effi-MVS+		98.70 150	98.43 163	99.51 113	99.51 169	99.28 111	99.52 148	99.47 173	96.11 325	99.01 235	99.34 290	96.20 161	99.84 151	97.88 211	98.82 196	99.39 198

TSAR-MVS + GP.		99.36 54	99.36 32	99.36 135	99.67 111	98.61 198	99.07 301	99.33 257	99.00 43	99.82 35	99.81 90	99.06 16	99.84 151	99.09 80	99.42 147	99.65 129

tpmrst		98.33 178	98.48 161	97.90 309	99.16 268	94.78 350	99.31 243	99.11 306	97.27 232	99.45 134	99.59 212	95.33 193	99.84 151	98.48 165	98.61 203	99.09 221

Vis-MVSNet		99.12 94	98.97 100	99.56 94	99.78 56	99.10 135	99.68 61	99.66 28	98.49 93	99.86 27	99.87 44	94.77 218	99.84 151	99.19 71	99.41 148	99.74 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 159	98.34 169	99.51 113	99.40 207	99.03 145	98.80 347	99.36 240	96.33 306	99.00 239	99.12 326	98.46 81	99.84 151	95.23 335	99.37 156	99.66 125

PatchMatch-RL		98.84 137	98.62 146	99.52 111	99.71 96	99.28 111	99.06 304	99.77 9	97.74 184	99.50 126	99.53 235	95.41 189	99.84 151	97.17 276	99.64 131	99.44 191

EPP-MVSNet		99.13 88	98.99 96	99.53 105	99.65 125	99.06 142	99.81 20	99.33 257	97.43 218	99.60 106	99.88 36	97.14 126	99.84 151	99.13 76	98.94 185	99.69 115

thres100view900		97.76 254	97.45 260	98.69 238	99.72 91	97.86 251	99.59 101	98.74 351	97.93 162	99.26 188	98.62 358	91.75 310	99.83 163	93.22 358	98.18 232	98.37 343

tfpn200view9		97.72 263	97.38 273	98.72 236	99.69 106	97.96 243	99.50 163	98.73 356	97.83 172	99.17 208	98.45 363	91.67 314	99.83 163	93.22 358	98.18 232	98.37 343

test_prior				99.68 68	99.67 111	99.48 89		99.56 69					99.83 163			99.74 92

1314		98.68 154	98.54 158	99.11 173	98.89 311	98.65 193	99.27 258	99.49 143	96.89 268	97.99 329	99.56 223	97.72 111	99.83 163	97.74 228	99.27 160	98.84 245

thres400		97.77 253	97.38 273	98.92 199	99.69 106	97.96 243	99.50 163	98.73 356	97.83 172	99.17 208	98.45 363	91.67 314	99.83 163	93.22 358	98.18 232	98.96 239

casdiffmvs		99.13 88	98.98 99	99.56 94	99.65 125	99.16 125	99.56 122	99.50 135	98.33 110	99.41 147	99.86 49	95.92 171	99.83 163	99.45 45	99.16 165	99.70 113
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 22	99.48 15	99.54 97	99.78 56	99.30 109	99.89 2	99.58 61	98.56 87	99.73 62	99.69 168	98.55 75	99.82 169	99.69 19	99.85 69	99.48 178

MVS_Test		99.10 102	98.97 100	99.48 117	99.49 180	99.14 131	99.67 64	99.34 250	97.31 229	99.58 110	99.76 135	97.65 112	99.82 169	98.87 105	99.07 177	99.46 186

dp		97.75 258	97.80 219	97.59 326	99.10 279	93.71 365	99.32 241	98.88 336	96.48 298	99.08 223	99.55 226	92.67 289	99.82 169	96.52 305	98.58 206	99.24 210

RPSCF		98.22 185	98.62 146	96.99 340	99.82 42	91.58 379	99.72 49	99.44 201	96.61 287	99.66 83	99.89 30	95.92 171	99.82 169	97.46 256	99.10 174	99.57 156

PMMVS		98.80 141	98.62 146	99.34 136	99.27 241	98.70 189	98.76 351	99.31 271	97.34 226	99.21 198	99.07 328	97.20 125	99.82 169	98.56 158	98.87 191	99.52 167

EIA-MVS		99.18 78	99.09 78	99.45 123	99.49 180	99.18 122	99.67 64	99.53 96	97.66 193	99.40 152	99.44 261	98.10 99	99.81 174	98.94 94	99.62 134	99.35 201

Effi-MVS+		98.81 138	98.59 153	99.48 117	99.46 190	99.12 134	98.08 385	99.50 135	97.50 210	99.38 158	99.41 269	96.37 156	99.81 174	99.11 78	98.54 211	99.51 173

thres200		97.61 278	97.28 287	98.62 241	99.64 127	98.03 237	99.26 267	98.74 351	97.68 190	99.09 222	98.32 367	91.66 316	99.81 174	92.88 363	98.22 227	98.03 359

tpmvs		97.98 221	98.02 199	97.84 313	99.04 292	94.73 351	99.31 243	99.20 296	96.10 329	98.76 273	99.42 265	94.94 203	99.81 174	96.97 285	98.45 215	98.97 237

casdiffmvs_mvg		99.15 84	99.02 90	99.55 96	99.66 119	99.09 136	99.64 78	99.56 69	98.26 116	99.45 134	99.87 44	96.03 165	99.81 174	99.54 30	99.15 168	99.73 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepPCF-MVS	98.18 3	98.81 138	99.37 30	97.12 338	99.60 145	91.75 378	98.61 363	99.44 201	99.35 12	99.83 34	99.85 54	98.70 63	99.81 174	99.02 87	99.91 31	99.81 61

DPM-MVS		98.95 118	98.71 131	99.66 69	99.63 130	99.55 77	98.64 362	99.10 307	97.93 162	99.42 143	99.55 226	98.67 66	99.80 180	95.80 320	99.68 126	99.61 144

DP-MVS Recon		99.12 94	98.95 104	99.65 73	99.74 80	99.70 46	99.27 258	99.57 64	96.40 305	99.42 143	99.68 174	98.75 55	99.80 180	97.98 205	99.72 118	99.44 191

MVS_111021_LR		99.41 47	99.33 38	99.65 73	99.77 62	99.51 86	98.94 333	99.85 6	98.82 65	99.65 89	99.74 143	98.51 78	99.80 180	98.83 118	99.89 48	99.64 136

CS-MVS		99.50 20	99.48 15	99.54 97	99.76 65	99.42 96	99.90 1	99.55 77	98.56 87	99.78 47	99.70 158	98.65 68	99.79 183	99.65 23	99.78 104	99.41 195

Fast-Effi-MVS+-dtu		98.77 144	98.83 121	98.60 242	99.41 202	96.99 292	99.52 148	99.49 143	98.11 140	99.24 190	99.34 290	96.96 136	99.79 183	97.95 207	99.45 145	99.02 232

baseline1		98.31 179	97.95 206	99.38 134	99.50 178	98.74 186	99.59 101	98.93 326	98.41 100	99.14 211	99.60 210	94.59 229	99.79 183	98.48 165	93.29 356	99.61 144

baseline		99.15 84	99.02 90	99.53 105	99.66 119	99.14 131	99.72 49	99.48 155	98.35 107	99.42 143	99.84 64	96.07 163	99.79 183	99.51 35	99.14 169	99.67 122

PVSNet_0	94.43 19	96.09 322	95.47 328	97.94 306	99.31 231	94.34 359	97.81 387	99.70 15	97.12 246	97.46 342	98.75 355	89.71 340	99.79 183	97.69 235	81.69 389	99.68 119

API-MVS		99.04 108	99.03 86	99.06 177	99.40 207	99.31 107	99.55 134	99.56 69	98.54 89	99.33 171	99.39 276	98.76 52	99.78 188	96.98 284	99.78 104	98.07 356

OMC-MVS		99.08 104	99.04 84	99.20 163	99.67 111	98.22 228	99.28 253	99.52 101	98.07 148	99.66 83	99.81 90	97.79 108	99.78 188	97.79 220	99.81 93	99.60 146

GeoE		98.85 134	98.62 146	99.53 105	99.61 140	99.08 139	99.80 25	99.51 115	97.10 250	99.31 174	99.78 121	95.23 199	99.77 190	98.21 186	99.03 180	99.75 88

alignmvs		98.81 138	98.56 157	99.58 90	99.43 197	99.42 96	99.51 156	98.96 324	98.61 84	99.35 167	98.92 347	94.78 215	99.77 190	99.35 51	98.11 237	99.54 161

tpm cat1		97.39 291	97.36 275	97.50 329	99.17 266	93.73 364	99.43 198	99.31 271	91.27 376	98.71 277	99.08 327	94.31 243	99.77 190	96.41 309	98.50 213	99.00 233

CostFormer		97.72 263	97.73 232	97.71 321	99.15 272	94.02 361	99.54 139	99.02 317	94.67 353	99.04 232	99.35 286	92.35 301	99.77 190	98.50 164	97.94 240	99.34 203

test_241102_ONE					99.84 32	99.90 2		99.48 155	99.07 35	99.91 16	99.74 143	99.20 7	99.76 194

MDTV_nov1_ep13			98.32 171		99.11 276	94.44 356	99.27 258	98.74 351	97.51 209	99.40 152	99.62 203	94.78 215	99.76 194	97.59 240	98.81 198

canonicalmvs		99.02 111	98.86 117	99.51 113	99.42 199	99.32 104	99.80 25	99.48 155	98.63 82	99.31 174	98.81 352	97.09 129	99.75 196	99.27 66	97.90 241	99.47 184

Effi-MVS+-dtu		98.78 142	98.89 112	98.47 262	99.33 224	96.91 298	99.57 116	99.30 275	98.47 94	99.41 147	98.99 337	96.78 140	99.74 197	98.73 129	99.38 149	98.74 259

patchmatchnet-post											98.70 356	94.79 214	99.74 197

SCA		98.19 189	98.16 179	98.27 286	99.30 232	95.55 333	99.07 301	98.97 322	97.57 200	99.43 140	99.57 220	92.72 284	99.74 197	97.58 241	99.20 163	99.52 167

BH-untuned		98.42 169	98.36 167	98.59 243	99.49 180	96.70 304	99.27 258	99.13 305	97.24 236	98.80 268	99.38 277	95.75 178	99.74 197	97.07 280	99.16 165	99.33 204

BH-RMVSNet		98.41 171	98.08 191	99.40 130	99.41 202	98.83 180	99.30 245	98.77 347	97.70 188	98.94 247	99.65 186	92.91 279	99.74 197	96.52 305	99.55 140	99.64 136

MVS_111021_HR		99.41 47	99.32 40	99.66 69	99.72 91	99.47 91	98.95 331	99.85 6	98.82 65	99.54 119	99.73 149	98.51 78	99.74 197	98.91 99	99.88 51	99.77 82

test_post											65.99 400	94.65 228	99.73 203

XVG-ACMP-BASELINE		97.83 244	97.71 234	98.20 288	99.11 276	96.33 318	99.41 207	99.52 101	98.06 152	99.05 231	99.50 244	89.64 342	99.73 203	97.73 229	97.38 276	98.53 325

HyFIR lowres test		99.11 98	98.92 106	99.65 73	99.90 4	99.37 100	99.02 314	99.91 3	97.67 192	99.59 109	99.75 138	95.90 173	99.73 203	99.53 32	99.02 182	99.86 33

DeepMVS_CX				93.34 362	99.29 236	82.27 390		99.22 292	85.15 387	96.33 361	99.05 331	90.97 327	99.73 203	93.57 355	97.77 244	98.01 360

Patchmatch-test		97.93 227	97.65 239	98.77 233	99.18 260	97.07 283	99.03 311	99.14 304	96.16 320	98.74 274	99.57 220	94.56 231	99.72 207	93.36 357	99.11 171	99.52 167

LPG-MVS_test		98.22 185	98.13 184	98.49 256	99.33 224	97.05 285	99.58 109	99.55 77	97.46 212	99.24 190	99.83 68	92.58 291	99.72 207	98.09 195	97.51 260	98.68 278

LGP-MVS_train				98.49 256	99.33 224	97.05 285		99.55 77	97.46 212	99.24 190	99.83 68	92.58 291	99.72 207	98.09 195	97.51 260	98.68 278

BH-w/o		98.00 219	97.89 215	98.32 279	99.35 218	96.20 322	99.01 319	98.90 334	96.42 303	98.38 310	99.00 336	95.26 197	99.72 207	96.06 313	98.61 203	99.03 230

ACMP	97.20 11	98.06 204	97.94 208	98.45 264	99.37 214	97.01 290	99.44 194	99.49 143	97.54 206	98.45 307	99.79 115	91.95 306	99.72 207	97.91 209	97.49 265	98.62 308
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 214	97.90 211	98.40 272	99.23 249	96.80 302	99.70 52	99.60 54	97.12 246	98.18 321	99.70 158	91.73 312	99.72 207	98.39 172	97.45 268	98.68 278
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							99.23 272				65.14 401	94.18 248	99.71 213	97.58 241

ADS-MVSNet		98.20 188	98.08 191	98.56 250	99.33 224	96.48 313	99.23 272	99.15 302	96.24 313	99.10 219	99.67 180	94.11 249	99.71 213	96.81 294	99.05 178	99.48 178

JIA-IIPM		97.50 285	97.02 298	98.93 197	98.73 334	97.80 253	99.30 245	98.97 322	91.73 375	98.91 251	94.86 389	95.10 201	99.71 213	97.58 241	97.98 239	99.28 208

EPMVS		97.82 247	97.65 239	98.35 276	98.88 312	95.98 325	99.49 174	94.71 398	97.57 200	99.26 188	99.48 252	92.46 298	99.71 213	97.87 213	99.08 176	99.35 201

TDRefinement		95.42 330	94.57 337	97.97 305	89.83 398	96.11 324	99.48 178	98.75 348	96.74 275	96.68 358	99.88 36	88.65 351	99.71 213	98.37 175	82.74 388	98.09 355

ACMM	97.58 5	98.37 176	98.34 169	98.48 258	99.41 202	97.10 279	99.56 122	99.45 193	98.53 90	99.04 232	99.85 54	93.00 275	99.71 213	98.74 127	97.45 268	98.64 297
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 224	97.77 225	98.57 247	99.59 147	96.61 309	99.45 188	99.08 310	98.21 124	98.88 256	99.80 103	88.66 350	99.70 219	98.58 152	97.72 245	99.39 198

CHOSEN 280x420		99.12 94	99.13 72	99.08 174	99.66 119	97.89 248	98.43 373	99.71 13	98.88 59	99.62 100	99.76 135	96.63 145	99.70 219	99.46 44	99.99 1	99.66 125

EC-MVSNet		99.44 37	99.39 27	99.58 90	99.56 155	99.49 87	99.88 4	99.58 61	98.38 102	99.73 62	99.69 168	98.20 95	99.70 219	99.64 24	99.82 90	99.54 161

PatchmatchNet		98.31 179	98.36 167	98.19 289	99.16 268	95.32 341	99.27 258	98.92 328	97.37 224	99.37 160	99.58 216	94.90 207	99.70 219	97.43 259	99.21 162	99.54 161
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 199	97.99 201	98.44 267	99.41 202	96.96 296	99.60 95	99.56 69	98.09 143	98.15 322	99.91 20	90.87 328	99.70 219	98.88 102	97.45 268	98.67 285
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
HQP_MVS		98.27 184	98.22 177	98.44 267	99.29 236	96.97 294	99.39 219	99.47 173	98.97 51	99.11 216	99.61 207	92.71 286	99.69 224	97.78 221	97.63 248	98.67 285

plane_prior5								99.47 173					99.69 224	97.78 221	97.63 248	98.67 285

D2MVS		98.41 171	98.50 160	98.15 294	99.26 243	96.62 308	99.40 215	99.61 48	97.71 186	98.98 241	99.36 283	96.04 164	99.67 226	98.70 132	97.41 273	98.15 353

IS-MVSNet		99.05 107	98.87 114	99.57 92	99.73 87	99.32 104	99.75 41	99.20 296	98.02 157	99.56 114	99.86 49	96.54 149	99.67 226	98.09 195	99.13 170	99.73 97

CLD-MVS		98.16 193	98.10 187	98.33 277	99.29 236	96.82 301	98.75 352	99.44 201	97.83 172	99.13 212	99.55 226	92.92 277	99.67 226	98.32 181	97.69 246	98.48 329
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 296	97.30 285	97.09 339	99.43 197	93.31 370	99.73 47	98.87 338	98.83 64	99.28 180	99.80 103	84.45 374	99.66 229	97.88 211	97.45 268	98.30 345

AUN-MVS		96.88 306	96.31 312	98.59 243	99.48 188	97.04 288	99.27 258	99.22 292	97.44 217	98.51 303	99.41 269	91.97 305	99.66 229	97.71 232	83.83 386	99.07 227

UniMVSNet_ETH3D		97.32 293	96.81 301	98.87 214	99.40 207	97.46 265	99.51 156	99.53 96	95.86 333	98.54 302	99.77 129	82.44 382	99.66 229	98.68 137	97.52 258	99.50 176

OPM-MVS		98.19 189	98.10 187	98.45 264	98.88 312	97.07 283	99.28 253	99.38 231	98.57 86	99.22 195	99.81 90	92.12 302	99.66 229	98.08 199	97.54 257	98.61 317
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 230	97.78 223	98.32 279	99.46 190	96.68 306	99.56 122	99.54 85	98.41 100	97.79 338	99.87 44	90.18 337	99.66 229	98.05 203	97.18 284	98.62 308

hse-mvs2		97.50 285	97.14 293	98.59 243	99.49 180	97.05 285	99.28 253	99.22 292	98.94 54	99.66 83	99.42 265	94.93 204	99.65 234	99.48 41	83.80 387	99.08 222

VPA-MVSNet		98.29 182	97.95 206	99.30 148	99.16 268	99.54 79	99.50 163	99.58 61	98.27 115	99.35 167	99.37 280	92.53 293	99.65 234	99.35 51	94.46 339	98.72 262

TR-MVS		97.76 254	97.41 271	98.82 225	99.06 288	97.87 249	98.87 341	98.56 363	96.63 286	98.68 285	99.22 313	92.49 294	99.65 234	95.40 331	97.79 243	98.95 241

gm-plane-assit					98.54 353	92.96 372			94.65 354		99.15 321		99.64 237	97.56 246

HQP4-MVS										98.66 286			99.64 237			98.64 297

HQP-MVS		98.02 214	97.90 211	98.37 275	99.19 257	96.83 299	98.98 324	99.39 223	98.24 118	98.66 286	99.40 272	92.47 295	99.64 237	97.19 273	97.58 253	98.64 297

PAPM		97.59 279	97.09 296	99.07 176	99.06 288	98.26 226	98.30 380	99.10 307	94.88 348	98.08 324	99.34 290	96.27 159	99.64 237	89.87 377	98.92 188	99.31 206

TAPA-MVS	97.07 15	97.74 260	97.34 280	98.94 195	99.70 101	97.53 263	99.25 269	99.51 115	91.90 374	99.30 176	99.63 198	98.78 48	99.64 237	88.09 384	99.87 54	99.65 129
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 175	98.09 190	99.24 159	99.26 243	99.32 104	99.56 122	99.55 77	97.45 215	98.71 277	99.83 68	93.23 270	99.63 242	98.88 102	96.32 299	98.76 254

ITE_SJBPF				98.08 296	99.29 236	96.37 316		98.92 328	98.34 108	98.83 264	99.75 138	91.09 325	99.62 243	95.82 318	97.40 274	98.25 349

LF4IMVS		97.52 282	97.46 259	97.70 322	98.98 302	95.55 333	99.29 249	98.82 343	98.07 148	98.66 286	99.64 192	89.97 338	99.61 244	97.01 281	96.68 289	97.94 366

tpm		97.67 273	97.55 247	98.03 298	99.02 294	95.01 347	99.43 198	98.54 365	96.44 301	99.12 214	99.34 290	91.83 309	99.60 245	97.75 227	96.46 295	99.48 178

tpm2		97.44 290	97.34 280	97.74 320	99.15 272	94.36 358	99.45 188	98.94 325	93.45 367	98.90 253	99.44 261	91.35 322	99.59 246	97.31 264	98.07 238	99.29 207

baseline2		97.87 236	97.55 247	98.82 225	99.18 260	98.02 238	99.41 207	96.58 392	96.97 261	96.51 359	99.17 318	93.43 267	99.57 247	97.71 232	99.03 180	98.86 243

MS-PatchMatch		97.24 298	97.32 283	96.99 340	98.45 356	93.51 369	98.82 345	99.32 267	97.41 221	98.13 323	99.30 300	88.99 346	99.56 248	95.68 324	99.80 97	97.90 369

TinyColmap		97.12 301	96.89 300	97.83 314	99.07 285	95.52 336	98.57 366	98.74 351	97.58 199	97.81 337	99.79 115	88.16 357	99.56 248	95.10 336	97.21 282	98.39 341

USDC		97.34 292	97.20 291	97.75 319	99.07 285	95.20 343	98.51 370	99.04 316	97.99 158	98.31 314	99.86 49	89.02 345	99.55 250	95.67 325	97.36 277	98.49 328

MSLP-MVS++		99.46 31	99.47 17	99.44 127	99.60 145	99.16 125	99.41 207	99.71 13	98.98 48	99.45 134	99.78 121	99.19 9	99.54 251	99.28 63	99.84 77	99.63 140

TAMVS		99.12 94	99.08 79	99.24 159	99.46 190	98.55 202	99.51 156	99.46 182	98.09 143	99.45 134	99.82 76	98.34 89	99.51 252	98.70 132	98.93 186	99.67 122

EPNet_dtu		98.03 212	97.96 204	98.23 287	98.27 359	95.54 335	99.23 272	98.75 348	99.02 38	97.82 336	99.71 154	96.11 162	99.48 253	93.04 361	99.65 130	99.69 115
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		95.97 323	95.69 325	96.81 347	97.78 366	92.79 373	99.16 282	98.93 326	96.16 320	94.08 376	99.22 313	82.72 380	99.47 254	95.67 325	97.50 262	98.17 352

MVP-Stereo		97.81 249	97.75 230	97.99 304	97.53 370	96.60 310	98.96 328	98.85 340	97.22 238	97.23 349	99.36 283	95.28 194	99.46 255	95.51 327	99.78 104	97.92 368
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 161	98.67 135	98.30 281	99.35 218	95.59 332	99.50 163	99.55 77	98.60 85	99.39 155	99.83 68	94.48 236	99.45 256	98.75 126	98.56 209	99.85 36

test-LLR		98.06 204	97.90 211	98.55 252	98.79 324	97.10 279	98.67 358	97.75 379	97.34 226	98.61 297	98.85 349	94.45 238	99.45 256	97.25 267	99.38 149	99.10 217

TESTMET0.1,1		97.55 280	97.27 290	98.40 272	98.93 307	96.53 311	98.67 358	97.61 382	96.96 262	98.64 293	99.28 304	88.63 352	99.45 256	97.30 265	99.38 149	99.21 212

test-mter		97.49 288	97.13 295	98.55 252	98.79 324	97.10 279	98.67 358	97.75 379	96.65 282	98.61 297	98.85 349	88.23 356	99.45 256	97.25 267	99.38 149	99.10 217

mvs_anonymous		99.03 110	98.99 96	99.16 167	99.38 211	98.52 208	99.51 156	99.38 231	97.79 177	99.38 158	99.81 90	97.30 122	99.45 256	99.35 51	98.99 183	99.51 173

tfpnnormal		97.84 242	97.47 257	98.98 189	99.20 255	99.22 119	99.64 78	99.61 48	96.32 307	98.27 317	99.70 158	93.35 269	99.44 261	95.69 323	95.40 322	98.27 347

v7n		97.87 236	97.52 251	98.92 199	98.76 332	98.58 200	99.84 13	99.46 182	96.20 316	98.91 251	99.70 158	94.89 208	99.44 261	96.03 314	93.89 350	98.75 256

jajsoiax		98.43 168	98.28 174	98.88 210	98.60 349	98.43 219	99.82 17	99.53 96	98.19 127	98.63 294	99.80 103	93.22 272	99.44 261	99.22 69	97.50 262	98.77 252

mvs_tets		98.40 174	98.23 176	98.91 203	98.67 342	98.51 210	99.66 69	99.53 96	98.19 127	98.65 292	99.81 90	92.75 281	99.44 261	99.31 58	97.48 266	98.77 252

Vis-MVSNet (Re-imp)		98.87 124	98.72 129	99.31 143	99.71 96	98.88 171	99.80 25	99.44 201	97.91 164	99.36 164	99.78 121	95.49 188	99.43 265	97.91 209	99.11 171	99.62 142

OPU-MVS				99.64 78	99.56 155	99.72 42	99.60 95				99.70 158	99.27 5	99.42 266	98.24 185	99.80 97	99.79 74

Anonymous20231211		97.88 234	97.54 250	98.90 205	99.71 96	98.53 204	99.48 178	99.57 64	94.16 358	98.81 266	99.68 174	93.23 270	99.42 266	98.84 115	94.42 341	98.76 254

VPNet		97.84 242	97.44 265	99.01 183	99.21 253	98.94 165	99.48 178	99.57 64	98.38 102	99.28 180	99.73 149	88.89 347	99.39 268	99.19 71	93.27 357	98.71 264

iter_conf_final		98.71 149	98.61 152	98.99 187	99.49 180	98.96 157	99.63 82	99.41 212	98.19 127	99.39 155	99.77 129	94.82 210	99.38 269	99.30 61	97.52 258	98.64 297

nrg030		98.64 158	98.42 164	99.28 154	99.05 291	99.69 47	99.81 20	99.46 182	98.04 154	99.01 235	99.82 76	96.69 144	99.38 269	99.34 55	94.59 338	98.78 249

iter_conf05		98.55 162	98.44 162	98.87 214	99.34 222	98.60 199	99.55 134	99.42 209	98.21 124	99.37 160	99.77 129	93.55 266	99.38 269	99.30 61	97.48 266	98.63 305

GA-MVS		97.85 239	97.47 257	99.00 185	99.38 211	97.99 240	98.57 366	99.15 302	97.04 257	98.90 253	99.30 300	89.83 339	99.38 269	96.70 299	98.33 219	99.62 142

UniMVSNet (Re)		98.29 182	98.00 200	99.13 172	99.00 296	99.36 102	99.49 174	99.51 115	97.95 160	98.97 243	99.13 323	96.30 158	99.38 269	98.36 177	93.34 355	98.66 293

FIs		98.78 142	98.63 141	99.23 161	99.18 260	99.54 79	99.83 16	99.59 57	98.28 113	98.79 270	99.81 90	96.75 142	99.37 274	99.08 82	96.38 297	98.78 249

PS-MVSNAJss		98.92 120	98.92 106	98.90 205	98.78 327	98.53 204	99.78 32	99.54 85	98.07 148	99.00 239	99.76 135	99.01 18	99.37 274	99.13 76	97.23 281	98.81 246

CDS-MVSNet		99.09 103	99.03 86	99.25 157	99.42 199	98.73 187	99.45 188	99.46 182	98.11 140	99.46 133	99.77 129	98.01 103	99.37 274	98.70 132	98.92 188	99.66 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 327	95.16 332	97.51 328	99.30 232	93.69 366	98.88 339	95.78 393	85.09 388	98.78 271	92.65 391	91.29 323	99.37 274	94.85 340	99.85 69	99.46 186

v1192		97.81 249	97.44 265	98.91 203	98.88 312	98.68 190	99.51 156	99.34 250	96.18 318	99.20 201	99.34 290	94.03 252	99.36 278	95.32 333	95.18 326	98.69 273

EI-MVSNet		98.67 155	98.67 135	98.68 239	99.35 218	97.97 241	99.50 163	99.38 231	96.93 267	99.20 201	99.83 68	97.87 105	99.36 278	98.38 173	97.56 255	98.71 264

MVSTER		98.49 163	98.32 171	99.00 185	99.35 218	99.02 146	99.54 139	99.38 231	97.41 221	99.20 201	99.73 149	93.86 259	99.36 278	98.87 105	97.56 255	98.62 308

gg-mvs-nofinetune		96.17 320	95.32 331	98.73 235	98.79 324	98.14 232	99.38 224	94.09 399	91.07 379	98.07 327	91.04 395	89.62 343	99.35 281	96.75 296	99.09 175	98.68 278

pm-mvs1		97.68 270	97.28 287	98.88 210	99.06 288	98.62 196	99.50 163	99.45 193	96.32 307	97.87 334	99.79 115	92.47 295	99.35 281	97.54 248	93.54 354	98.67 285

OurMVSNet-221017-0		97.88 234	97.77 225	98.19 289	98.71 338	96.53 311	99.88 4	99.00 319	97.79 177	98.78 271	99.94 6	91.68 313	99.35 281	97.21 269	96.99 288	98.69 273

EGC-MVSNET		82.80 359	77.86 365	97.62 324	97.91 363	96.12 323	99.33 240	99.28 281	8.40 403	25.05 404	99.27 307	84.11 375	99.33 284	89.20 379	98.22 227	97.42 377

pmmvs6		96.53 312	96.09 317	97.82 316	98.69 340	95.47 337	99.37 226	99.47 173	93.46 366	97.41 343	99.78 121	87.06 365	99.33 284	96.92 291	92.70 364	98.65 295

mvsmamba		98.92 120	98.87 114	99.08 174	99.07 285	99.16 125	99.88 4	99.51 115	98.15 133	99.40 152	99.89 30	97.12 127	99.33 284	99.38 48	97.40 274	98.73 261

V42		98.06 204	97.79 220	98.86 218	98.98 302	98.84 177	99.69 55	99.34 250	96.53 293	99.30 176	99.37 280	94.67 226	99.32 287	97.57 245	94.66 336	98.42 337

lessismore_v0				97.79 318	98.69 340	95.44 339		94.75 397		95.71 367	99.87 44	88.69 349	99.32 287	95.89 317	94.93 333	98.62 308

OpenMVS_ROB	92.34 20	94.38 341	93.70 347	96.41 352	97.38 372	93.17 371	99.06 304	98.75 348	86.58 386	94.84 374	98.26 368	81.53 384	99.32 287	89.01 380	97.87 242	96.76 380

bld_raw_dy_0_64		98.69 152	98.58 154	98.99 187	98.88 312	98.96 157	99.80 25	99.41 212	97.91 164	99.32 172	99.87 44	95.70 181	99.31 290	99.09 80	97.27 279	98.71 264

v8		97.95 226	97.63 243	98.93 197	98.95 306	98.81 183	99.80 25	99.41 212	96.03 330	99.10 219	99.42 265	94.92 206	99.30 291	96.94 288	94.08 347	98.66 293

v1921920		97.80 251	97.45 260	98.84 222	98.80 323	98.53 204	99.52 148	99.34 250	96.15 322	99.24 190	99.47 255	93.98 254	99.29 292	95.40 331	95.13 328	98.69 273

anonymousdsp		98.44 167	98.28 174	98.94 195	98.50 354	98.96 157	99.77 34	99.50 135	97.07 252	98.87 259	99.77 129	94.76 219	99.28 293	98.66 139	97.60 251	98.57 323

MVSFormer		99.17 80	99.12 73	99.29 151	99.51 169	98.94 165	99.88 4	99.46 182	97.55 203	99.80 40	99.65 186	97.39 116	99.28 293	99.03 85	99.85 69	99.65 129

test_djsdf		98.67 155	98.57 155	98.98 189	98.70 339	98.91 169	99.88 4	99.46 182	97.55 203	99.22 195	99.88 36	95.73 179	99.28 293	99.03 85	97.62 250	98.75 256

cascas		97.69 268	97.43 269	98.48 258	98.60 349	97.30 268	98.18 384	99.39 223	92.96 370	98.41 308	98.78 354	93.77 262	99.27 296	98.16 192	98.61 203	98.86 243

v144192		97.92 230	97.60 245	98.87 214	98.83 322	98.65 193	99.55 134	99.34 250	96.20 316	99.32 172	99.40 272	94.36 240	99.26 297	96.37 310	95.03 330	98.70 269

dmvs_re		98.08 202	98.16 179	97.85 311	99.55 159	94.67 353	99.70 52	98.92 328	98.15 133	99.06 229	99.35 286	93.67 265	99.25 298	97.77 224	97.25 280	99.64 136

RRT_MVS		98.70 150	98.66 138	98.83 224	98.90 309	98.45 217	99.89 2	99.28 281	97.76 180	98.94 247	99.92 14	96.98 134	99.25 298	99.28 63	97.00 287	98.80 247

v2v482		98.06 204	97.77 225	98.92 199	98.90 309	98.82 181	99.57 116	99.36 240	96.65 282	99.19 204	99.35 286	94.20 245	99.25 298	97.72 231	94.97 331	98.69 273

v1240		97.69 268	97.32 283	98.79 231	98.85 320	98.43 219	99.48 178	99.36 240	96.11 325	99.27 184	99.36 283	93.76 263	99.24 301	94.46 344	95.23 325	98.70 269

v1144		97.98 221	97.69 235	98.85 221	98.87 316	98.66 192	99.54 139	99.35 246	96.27 311	99.23 194	99.35 286	94.67 226	99.23 302	96.73 297	95.16 327	98.68 278

v10		97.85 239	97.52 251	98.86 218	98.99 299	98.67 191	99.75 41	99.41 212	95.70 334	98.98 241	99.41 269	94.75 220	99.23 302	96.01 316	94.63 337	98.67 285

WR-MVS_H		98.13 196	97.87 216	98.90 205	99.02 294	98.84 177	99.70 52	99.59 57	97.27 232	98.40 309	99.19 317	95.53 186	99.23 302	98.34 178	93.78 352	98.61 317

miper_enhance_ethall		98.16 193	98.08 191	98.41 270	98.96 305	97.72 256	98.45 372	99.32 267	96.95 264	98.97 243	99.17 318	97.06 131	99.22 305	97.86 214	95.99 306	98.29 346

GG-mvs-BLEND				98.45 264	98.55 352	98.16 230	99.43 198	93.68 400		97.23 349	98.46 362	89.30 344	99.22 305	95.43 330	98.22 227	97.98 364

FC-MVSNet-test		98.75 145	98.62 146	99.15 171	99.08 284	99.45 93	99.86 12	99.60 54	98.23 121	98.70 283	99.82 76	96.80 139	99.22 305	99.07 83	96.38 297	98.79 248

UniMVSNet_NR-MVSNet		98.22 185	97.97 203	98.96 192	98.92 308	98.98 150	99.48 178	99.53 96	97.76 180	98.71 277	99.46 259	96.43 155	99.22 305	98.57 155	92.87 362	98.69 273

DU-MVS		98.08 202	97.79 220	98.96 192	98.87 316	98.98 150	99.41 207	99.45 193	97.87 166	98.71 277	99.50 244	94.82 210	99.22 305	98.57 155	92.87 362	98.68 278

cl____		98.01 217	97.84 218	98.55 252	99.25 247	97.97 241	98.71 356	99.34 250	96.47 300	98.59 300	99.54 231	95.65 183	99.21 310	97.21 269	95.77 312	98.46 334

WR-MVS		98.06 204	97.73 232	99.06 177	98.86 319	99.25 116	99.19 279	99.35 246	97.30 230	98.66 286	99.43 263	93.94 255	99.21 310	98.58 152	94.28 343	98.71 264

test_0402		96.64 310	96.24 313	97.85 311	98.85 320	96.43 315	99.44 194	99.26 285	93.52 364	96.98 356	99.52 238	88.52 353	99.20 312	92.58 368	97.50 262	97.93 367

SixPastTwentyTwo		97.50 285	97.33 282	98.03 298	98.65 343	96.23 321	99.77 34	98.68 359	97.14 243	97.90 332	99.93 9	90.45 331	99.18 313	97.00 282	96.43 296	98.67 285

cl22		97.85 239	97.64 242	98.48 258	99.09 282	97.87 249	98.60 365	99.33 257	97.11 249	98.87 259	99.22 313	92.38 300	99.17 314	98.21 186	95.99 306	98.42 337

WB-MVSnew		97.65 275	97.65 239	97.63 323	98.78 327	97.62 261	99.13 288	98.33 368	97.36 225	99.07 224	98.94 343	95.64 184	99.15 315	92.95 362	98.68 202	96.12 387

IterMVS-SCA-FT		97.82 247	97.75 230	98.06 297	99.57 151	96.36 317	99.02 314	99.49 143	97.18 240	98.71 277	99.72 153	92.72 284	99.14 316	97.44 258	95.86 311	98.67 285

pmmvs5		97.52 282	97.30 285	98.16 291	98.57 351	96.73 303	99.27 258	98.90 334	96.14 323	98.37 311	99.53 235	91.54 319	99.14 316	97.51 250	95.87 310	98.63 305

v148		97.79 252	97.55 247	98.50 255	98.74 333	97.72 256	99.54 139	99.33 257	96.26 312	98.90 253	99.51 241	94.68 225	99.14 316	97.83 217	93.15 359	98.63 305

miper_ehance_all_eth		98.18 191	98.10 187	98.41 270	99.23 249	97.72 256	98.72 355	99.31 271	96.60 289	98.88 256	99.29 302	97.29 123	99.13 319	97.60 239	95.99 306	98.38 342

NR-MVSNet		97.97 224	97.61 244	99.02 182	98.87 316	99.26 115	99.47 184	99.42 209	97.63 195	97.08 354	99.50 244	95.07 202	99.13 319	97.86 214	93.59 353	98.68 278

IterMVS		97.83 244	97.77 225	98.02 300	99.58 149	96.27 320	99.02 314	99.48 155	97.22 238	98.71 277	99.70 158	92.75 281	99.13 319	97.46 256	96.00 305	98.67 285
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 342	94.90 334	91.84 366	97.24 376	80.01 396	98.52 369	99.48 155	89.01 383	91.99 384	99.67 180	85.67 369	99.13 319	95.44 329	97.03 286	96.39 384
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 209	97.96 204	98.33 277	99.26 243	97.38 267	98.56 368	99.31 271	96.65 282	98.88 256	99.52 238	96.58 147	99.12 323	97.39 261	95.53 320	98.47 331

pmmvs4		98.13 196	97.90 211	98.81 228	98.61 348	98.87 172	98.99 321	99.21 295	96.44 301	99.06 229	99.58 216	95.90 173	99.11 324	97.18 275	96.11 303	98.46 334

TransMVSNet (Re)		97.15 300	96.58 305	98.86 218	99.12 274	98.85 176	99.49 174	98.91 332	95.48 337	97.16 352	99.80 103	93.38 268	99.11 324	94.16 350	91.73 367	98.62 308

ambc				93.06 364	92.68 394	82.36 389	98.47 371	98.73 356		95.09 372	97.41 378	55.55 396	99.10 326	96.42 308	91.32 368	97.71 370

Baseline_NR-MVSNet		97.76 254	97.45 260	98.68 239	99.09 282	98.29 224	99.41 207	98.85 340	95.65 335	98.63 294	99.67 180	94.82 210	99.10 326	98.07 202	92.89 361	98.64 297

test_vis3_rt		87.04 355	85.81 358	90.73 370	93.99 393	81.96 391	99.76 37	90.23 405	92.81 371	81.35 393	91.56 393	40.06 402	99.07 328	94.27 347	88.23 380	91.15 393

CP-MVSNet		98.09 200	97.78 223	99.01 183	98.97 304	99.24 117	99.67 64	99.46 182	97.25 234	98.48 306	99.64 192	93.79 261	99.06 329	98.63 142	94.10 346	98.74 259

PS-CasMVS		97.93 227	97.59 246	98.95 194	98.99 299	99.06 142	99.68 61	99.52 101	97.13 244	98.31 314	99.68 174	92.44 299	99.05 330	98.51 163	94.08 347	98.75 256

K. test v3		97.10 302	96.79 302	98.01 301	98.72 336	96.33 318	99.87 9	97.05 386	97.59 197	96.16 363	99.80 103	88.71 348	99.04 331	96.69 300	96.55 294	98.65 295

new_pmnet		96.38 316	96.03 318	97.41 330	98.13 362	95.16 346	99.05 306	99.20 296	93.94 359	97.39 346	98.79 353	91.61 318	99.04 331	90.43 375	95.77 312	98.05 358

DIV-MVS_self_test		98.01 217	97.85 217	98.48 258	99.24 248	97.95 245	98.71 356	99.35 246	96.50 294	98.60 299	99.54 231	95.72 180	99.03 333	97.21 269	95.77 312	98.46 334

IterMVS-LS		98.46 166	98.42 164	98.58 246	99.59 147	98.00 239	99.37 226	99.43 207	96.94 266	99.07 224	99.59 212	97.87 105	99.03 333	98.32 181	95.62 317	98.71 264
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 275	97.68 236	97.55 327	98.62 346	94.97 348	98.84 343	99.30 275	96.83 273	98.19 320	99.34 290	97.01 133	99.02 335	95.00 339	96.01 304	98.64 297

Patchmtry		97.75 258	97.40 272	98.81 228	99.10 279	98.87 172	99.11 297	99.33 257	94.83 350	98.81 266	99.38 277	94.33 241	99.02 335	96.10 312	95.57 318	98.53 325

N_pmnet		94.95 336	95.83 323	92.31 365	98.47 355	79.33 397	99.12 291	92.81 403	93.87 360	97.68 339	99.13 323	93.87 258	99.01 337	91.38 372	96.19 301	98.59 321

CR-MVSNet		98.17 192	97.93 209	98.87 214	99.18 260	98.49 212	99.22 276	99.33 257	96.96 262	99.56 114	99.38 277	94.33 241	99.00 338	94.83 341	98.58 206	99.14 214

c3_l		98.12 198	98.04 196	98.38 274	99.30 232	97.69 260	98.81 346	99.33 257	96.67 280	98.83 264	99.34 290	97.11 128	98.99 339	97.58 241	95.34 323	98.48 329

test0.0.03 1		97.71 266	97.42 270	98.56 250	98.41 358	97.82 252	98.78 349	98.63 361	97.34 226	98.05 328	98.98 339	94.45 238	98.98 340	95.04 338	97.15 285	98.89 242

PatchT		97.03 304	96.44 309	98.79 231	98.99 299	98.34 223	99.16 282	99.07 313	92.13 373	99.52 123	97.31 382	94.54 234	98.98 340	88.54 382	98.73 201	99.03 230

GBi-Net		97.68 270	97.48 255	98.29 282	99.51 169	97.26 272	99.43 198	99.48 155	96.49 295	99.07 224	99.32 297	90.26 333	98.98 340	97.10 277	96.65 290	98.62 308

test1		97.68 270	97.48 255	98.29 282	99.51 169	97.26 272	99.43 198	99.48 155	96.49 295	99.07 224	99.32 297	90.26 333	98.98 340	97.10 277	96.65 290	98.62 308

FMVSNet3		98.03 212	97.76 229	98.84 222	99.39 210	98.98 150	99.40 215	99.38 231	96.67 280	99.07 224	99.28 304	92.93 276	98.98 340	97.10 277	96.65 290	98.56 324

FMVSNet2		97.72 263	97.36 275	98.80 230	99.51 169	98.84 177	99.45 188	99.42 209	96.49 295	98.86 263	99.29 302	90.26 333	98.98 340	96.44 307	96.56 293	98.58 322

FMVSNet1		96.84 307	96.36 311	98.29 282	99.32 230	97.26 272	99.43 198	99.48 155	95.11 342	98.55 301	99.32 297	83.95 376	98.98 340	95.81 319	96.26 300	98.62 308

ppachtmachnet_test		97.49 288	97.45 260	97.61 325	98.62 346	95.24 342	98.80 347	99.46 182	96.11 325	98.22 319	99.62 203	96.45 153	98.97 347	93.77 352	95.97 309	98.61 317

TranMVSNet+NR-MVSNet		97.93 227	97.66 238	98.76 234	98.78 327	98.62 196	99.65 75	99.49 143	97.76 180	98.49 305	99.60 210	94.23 244	98.97 347	98.00 204	92.90 360	98.70 269

test_method		91.10 351	91.36 353	90.31 371	95.85 383	73.72 404	94.89 392	99.25 287	68.39 395	95.82 366	99.02 335	80.50 385	98.95 349	93.64 354	94.89 335	98.25 349

ADS-MVSNet2		98.02 214	98.07 194	97.87 310	99.33 224	95.19 344	99.23 272	99.08 310	96.24 313	99.10 219	99.67 180	94.11 249	98.93 350	96.81 294	99.05 178	99.48 178

ET-MVSNet_ETH3D		96.49 313	95.64 327	99.05 179	99.53 162	98.82 181	98.84 343	97.51 384	97.63 195	84.77 389	99.21 316	92.09 303	98.91 351	98.98 90	92.21 366	99.41 195

miper_lstm_enhance		98.00 219	97.91 210	98.28 285	99.34 222	97.43 266	98.88 339	99.36 240	96.48 298	98.80 268	99.55 226	95.98 166	98.91 351	97.27 266	95.50 321	98.51 327

PEN-MVS		97.76 254	97.44 265	98.72 236	98.77 331	98.54 203	99.78 32	99.51 115	97.06 254	98.29 316	99.64 192	92.63 290	98.89 353	98.09 195	93.16 358	98.72 262

testing3		97.28 294	96.76 303	98.82 225	99.37 214	98.07 236	99.45 188	99.36 240	97.56 202	97.89 333	98.95 342	83.70 377	98.82 354	96.03 314	98.56 209	99.58 154

testgi		97.65 275	97.50 254	98.13 295	99.36 217	96.45 314	99.42 205	99.48 155	97.76 180	97.87 334	99.45 260	91.09 325	98.81 355	94.53 343	98.52 212	99.13 216

testf1		90.42 353	90.68 355	89.65 374	97.78 366	73.97 402	99.13 288	98.81 344	89.62 381	91.80 385	98.93 344	62.23 394	98.80 356	86.61 390	91.17 369	96.19 385

APD_test2		90.42 353	90.68 355	89.65 374	97.78 366	73.97 402	99.13 288	98.81 344	89.62 381	91.80 385	98.93 344	62.23 394	98.80 356	86.61 390	91.17 369	96.19 385

MIMVSNet		97.73 261	97.45 260	98.57 247	99.45 195	97.50 264	99.02 314	98.98 321	96.11 325	99.41 147	99.14 322	90.28 332	98.74 358	95.74 321	98.93 186	99.47 184

LCM-MVSNet-Re		97.83 244	98.15 181	96.87 346	99.30 232	92.25 376	99.59 101	98.26 369	97.43 218	96.20 362	99.13 323	96.27 159	98.73 359	98.17 191	98.99 183	99.64 136

Syy-MVS		97.09 303	97.14 293	96.95 343	99.00 296	92.73 374	99.29 249	99.39 223	97.06 254	97.41 343	98.15 369	93.92 257	98.68 360	91.71 370	98.34 217	99.45 189

myMVS_eth3d		96.89 305	96.37 310	98.43 269	99.00 296	97.16 276	99.29 249	99.39 223	97.06 254	97.41 343	98.15 369	83.46 378	98.68 360	95.27 334	98.34 217	99.45 189

DTE-MVSNet		97.51 284	97.19 292	98.46 263	98.63 345	98.13 233	99.84 13	99.48 155	96.68 279	97.97 331	99.67 180	92.92 277	98.56 362	96.88 293	92.60 365	98.70 269

PC_three_1452									98.18 131	99.84 29	99.70 158	99.31 3	98.52 363	98.30 183	99.80 97	99.81 61

mvsany_test3		93.77 344	93.45 348	94.74 358	95.78 384	88.01 384	99.64 78	98.25 370	98.28 113	94.31 375	97.97 375	68.89 390	98.51 364	97.50 251	90.37 374	97.71 370

UnsupCasMVSNet_bld		93.53 345	92.51 350	96.58 351	97.38 372	93.82 362	98.24 381	99.48 155	91.10 378	93.10 380	96.66 384	74.89 388	98.37 365	94.03 351	87.71 381	97.56 375

Anonymous20240521		96.20 319	95.89 322	97.13 337	97.72 369	94.96 349	99.79 31	99.29 279	93.01 369	97.20 351	99.03 333	89.69 341	98.36 366	91.16 373	96.13 302	98.07 356

test_f		91.90 350	91.26 354	93.84 360	95.52 388	85.92 386	99.69 55	98.53 366	95.31 339	93.87 377	96.37 386	55.33 397	98.27 367	95.70 322	90.98 372	97.32 378

MDA-MVSNet_test_wron		95.45 329	94.60 336	98.01 301	98.16 361	97.21 275	99.11 297	99.24 289	93.49 365	80.73 395	98.98 339	93.02 274	98.18 368	94.22 349	94.45 340	98.64 297

UnsupCasMVSNet_eth		96.44 314	96.12 315	97.40 331	98.65 343	95.65 330	99.36 230	99.51 115	97.13 244	96.04 365	98.99 337	88.40 354	98.17 369	96.71 298	90.27 375	98.40 340

KD-MVS_2432*1600		94.62 337	93.72 345	97.31 332	97.19 378	95.82 328	98.34 376	99.20 296	95.00 346	97.57 340	98.35 365	87.95 359	98.10 370	92.87 364	77.00 393	98.01 360

miper_refine_blended		94.62 337	93.72 345	97.31 332	97.19 378	95.82 328	98.34 376	99.20 296	95.00 346	97.57 340	98.35 365	87.95 359	98.10 370	92.87 364	77.00 393	98.01 360

YYNet1		95.36 331	94.51 338	97.92 307	97.89 364	97.10 279	99.10 299	99.23 290	93.26 368	80.77 394	99.04 332	92.81 280	98.02 372	94.30 345	94.18 345	98.64 297

EU-MVSNet		97.98 221	98.03 197	97.81 317	98.72 336	96.65 307	99.66 69	99.66 28	98.09 143	98.35 312	99.82 76	95.25 198	98.01 373	97.41 260	95.30 324	98.78 249

Gipuma		90.99 352	90.15 357	93.51 361	98.73 334	90.12 382	93.98 393	99.45 193	79.32 391	92.28 383	94.91 388	69.61 389	97.98 374	87.42 386	95.67 316	92.45 391
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 332	94.73 335	97.15 335	95.53 387	95.94 326	99.35 235	99.10 307	95.13 340	93.55 378	97.54 377	88.15 358	97.91 375	94.58 342	89.69 378	97.61 373

PM-MVS		92.96 347	92.23 351	95.14 357	95.61 385	89.98 383	99.37 226	98.21 372	94.80 351	95.04 373	97.69 376	65.06 391	97.90 376	94.30 345	89.98 377	97.54 376

MDA-MVSNet-bldmvs		94.96 335	93.98 342	97.92 307	98.24 360	97.27 270	99.15 285	99.33 257	93.80 361	80.09 396	99.03 333	88.31 355	97.86 377	93.49 356	94.36 342	98.62 308

Patchmatch-RL test		95.84 325	95.81 324	95.95 355	95.61 385	90.57 381	98.24 381	98.39 367	95.10 344	95.20 370	98.67 357	94.78 215	97.77 378	96.28 311	90.02 376	99.51 173

Anonymous20231206		96.22 317	96.03 318	96.79 348	97.31 375	94.14 360	99.63 82	99.08 310	96.17 319	97.04 355	99.06 330	93.94 255	97.76 379	86.96 388	95.06 329	98.47 331

SD-MVS		99.41 47	99.52 11	99.05 179	99.74 80	99.68 48	99.46 187	99.52 101	99.11 26	99.88 20	99.91 20	99.43 1	97.70 380	98.72 130	99.93 22	99.77 82
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		97.25 296	97.35 277	96.95 343	97.84 365	93.61 368	99.57 116	96.63 391	96.13 324	98.87 259	98.61 360	94.59 229	97.70 380	95.08 337	98.86 192	99.55 159

pmmvs3		94.09 343	93.25 349	96.60 350	94.76 392	94.49 355	98.92 335	98.18 374	89.66 380	96.48 360	98.06 374	86.28 366	97.33 382	89.68 378	87.20 382	97.97 365

KD-MVS_self_test		95.00 334	94.34 339	96.96 342	97.07 380	95.39 340	99.56 122	99.44 201	95.11 342	97.13 353	97.32 381	91.86 308	97.27 383	90.35 376	81.23 390	98.23 351

FMVSNet5		96.43 315	96.19 314	97.15 335	99.11 276	95.89 327	99.32 241	99.52 101	94.47 357	98.34 313	99.07 328	87.54 363	97.07 384	92.61 367	95.72 315	98.47 331

new-patchmatchnet		94.48 340	94.08 341	95.67 356	95.08 390	92.41 375	99.18 280	99.28 281	94.55 356	93.49 379	97.37 380	87.86 361	97.01 385	91.57 371	88.36 379	97.61 373

LCM-MVSNet		86.80 357	85.22 361	91.53 368	87.81 399	80.96 394	98.23 383	98.99 320	71.05 393	90.13 388	96.51 385	48.45 401	96.88 386	90.51 374	85.30 384	96.76 380

CL-MVSNet_self_test		94.49 339	93.97 343	96.08 354	96.16 382	93.67 367	98.33 378	99.38 231	95.13 340	97.33 347	98.15 369	92.69 288	96.57 387	88.67 381	79.87 391	97.99 363

MIMVSNet1		95.51 328	95.04 333	96.92 345	97.38 372	95.60 331	99.52 148	99.50 135	93.65 363	96.97 357	99.17 318	85.28 372	96.56 388	88.36 383	95.55 319	98.60 320

test20.03		96.12 321	95.96 320	96.63 349	97.44 371	95.45 338	99.51 156	99.38 231	96.55 292	96.16 363	99.25 310	93.76 263	96.17 389	87.35 387	94.22 344	98.27 347

tmp_tt		82.80 359	81.52 362	86.66 376	66.61 405	68.44 405	92.79 395	97.92 376	68.96 394	80.04 397	99.85 54	85.77 368	96.15 390	97.86 214	43.89 399	95.39 389

test_fmvs3		92.10 349	91.77 352	93.08 363	96.19 381	86.25 385	99.82 17	98.62 362	96.65 282	95.19 371	96.90 383	55.05 398	95.93 391	96.63 304	90.92 373	97.06 379

dmvs_testset		95.02 333	96.12 315	91.72 367	99.10 279	80.43 395	99.58 109	97.87 378	97.47 211	95.22 369	98.82 351	93.99 253	95.18 392	88.09 384	94.91 334	99.56 158

PMMVS2		86.87 356	85.37 360	91.35 369	90.21 397	83.80 388	98.89 338	97.45 385	83.13 390	91.67 387	95.03 387	48.49 400	94.70 393	85.86 392	77.62 392	95.54 388

PMVS	70.75 22	75.98 365	74.97 366	79.01 382	70.98 404	55.18 407	93.37 394	98.21 372	65.08 399	61.78 400	93.83 390	21.74 407	92.53 394	78.59 394	91.12 371	89.34 395
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 358	85.65 359	82.75 380	86.77 400	63.39 406	98.35 375	98.92 328	74.11 392	83.39 391	98.98 339	50.85 399	92.40 395	84.54 393	94.97 331	92.46 390

WB-MVS		93.10 346	94.10 340	90.12 372	95.51 389	81.88 392	99.73 47	99.27 284	95.05 345	93.09 381	98.91 348	94.70 224	91.89 396	76.62 395	94.02 349	96.58 382

SSC-MVS		92.73 348	93.73 344	89.72 373	95.02 391	81.38 393	99.76 37	99.23 290	94.87 349	92.80 382	98.93 344	94.71 223	91.37 397	74.49 397	93.80 351	96.42 383

MVE	76.82 21	76.91 364	74.31 368	84.70 377	85.38 402	76.05 401	96.88 391	93.17 401	67.39 396	71.28 398	89.01 397	21.66 408	87.69 398	71.74 398	72.29 395	90.35 394
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 361	79.88 363	82.81 379	90.75 396	76.38 400	97.69 388	95.76 394	66.44 397	83.52 390	92.25 392	62.54 393	87.16 399	68.53 399	61.40 396	84.89 397

EMVS		80.02 362	79.22 364	82.43 381	91.19 395	76.40 399	97.55 390	92.49 404	66.36 398	83.01 392	91.27 394	64.63 392	85.79 400	65.82 400	60.65 397	85.08 396

ANet_high		77.30 363	74.86 367	84.62 378	75.88 403	77.61 398	97.63 389	93.15 402	88.81 384	64.27 399	89.29 396	36.51 403	83.93 401	75.89 396	52.31 398	92.33 392

wuyk23d		40.18 366	41.29 371	36.84 383	86.18 401	49.12 408	79.73 396	22.81 408	27.64 400	25.46 403	28.45 403	21.98 406	48.89 402	55.80 401	23.56 402	12.51 400

test123		39.01 368	42.50 370	28.53 384	39.17 406	20.91 409	98.75 352	19.17 409	19.83 402	38.57 401	66.67 399	33.16 404	15.42 403	37.50 403	29.66 401	49.26 398

testmvs		39.17 367	43.78 369	25.37 385	36.04 407	16.84 410	98.36 374	26.56 407	20.06 401	38.51 402	67.32 398	29.64 405	15.30 404	37.59 402	39.90 400	43.98 399

test_blank		0.13 372	0.17 375	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	1.57 404	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

uanet_test		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

DCPMVS		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

cdsmvs_eth3d_5k		24.64 369	32.85 372	0.00 386	0.00 408	0.00 411	0.00 397	99.51 115	0.00 404	0.00 405	99.56 223	96.58 147	0.00 405	0.00 404	0.00 403	0.00 401

pcd_1.5k_mvsjas		8.27 371	11.03 374	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	99.01 18	0.00 405	0.00 404	0.00 403	0.00 401

sosnet-low-res		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

sosnet		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

uncertanet		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

Regformer		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

ab-mvs-re		8.30 370	11.06 373	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	99.58 216	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

uanet		0.02 373	0.03 376	0.00 386	0.00 408	0.00 411	0.00 397	0.00 410	0.00 404	0.00 405	0.27 405	0.00 409	0.00 405	0.00 404	0.00 403	0.00 401

WAC-MVS						97.16 276								95.47 328

FOURS1					99.91 1	99.93 1	99.87 9	99.56 69	99.10 27	99.81 37

test_one_0601					99.81 46	99.88 8		99.49 143	98.97 51	99.65 89	99.81 90	99.09 14

eth-test2					0.00 408

eth-test					0.00 408

RE-MVS-def			99.34 36		99.76 65	99.82 22	99.63 82	99.52 101	98.38 102	99.76 56	99.82 76	98.75 55		98.61 146	99.81 93	99.77 82

IU-MVS					99.84 32	99.88 8		99.32 267	98.30 112	99.84 29				98.86 110	99.85 69	99.89 20

save fliter					99.76 65	99.59 70	99.14 287	99.40 220	99.00 43

test0726					99.85 26	99.89 4	99.62 88	99.50 135	99.10 27	99.86 27	99.82 76	98.94 29

GSMVS																99.52 167

test_part2					99.81 46	99.83 16				99.77 51

sam_mvs1												94.86 209				99.52 167

sam_mvs												94.72 222

MTGPA								99.47 173

MTMP							99.54 139	98.88 336

test9_res														97.49 252	99.72 118	99.75 88

agg_prior2														97.21 269	99.73 117	99.75 88

test_prior4						99.56 75	98.99 321

test_prior2							98.96 328		98.34 108	99.01 235	99.52 238	98.68 64		97.96 206	99.74 115

新几何2							99.01 319

旧先验1					99.74 80	99.59 70		99.54 85			99.69 168	98.47 80			99.68 126	99.73 97

原ACMM2							98.95 331

test222					99.75 73	99.49 87	98.91 337	99.49 143	96.42 303	99.34 170	99.65 186	98.28 92			99.69 123	99.72 103

segment_acmp												98.96 24

testdata1							98.85 342		98.32 111

plane_prior7					99.29 236	97.03 289

plane_prior6					99.27 241	96.98 293						92.71 286

plane_prior4											99.61 207

plane_prior3						97.00 291			98.69 79	99.11 216

plane_prior2							99.39 219		98.97 51

plane_prior1					99.26 243

plane_prior						96.97 294	99.21 278		98.45 96						97.60 251

n2								0.00 410

nn								0.00 410

door-mid								98.05 375

test11								99.35 246

door								97.92 376

HQP5-MVS						96.83 299

HQP-NCC					99.19 257		98.98 324		98.24 118	98.66 286

ACMP_Plane					99.19 257		98.98 324		98.24 118	98.66 286

BP-MVS														97.19 273

HQP3-MVS								99.39 223							97.58 253

HQP2-MVS												92.47 295

NP-MVS					99.23 249	96.92 297					99.40 272

MDTV_nov1_ep13_2view						95.18 345	99.35 235		96.84 271	99.58 110		95.19 200		97.82 218		99.46 186

ACMMP++_ref															97.19 283

ACMMP++															97.43 272

Test By Simon												98.75 55

High-resolution multi-view benchmark