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 8	99.61 7	99.77 74	99.38 274	99.37 123	99.58 130	99.62 51	99.41 21	99.87 49	99.92 18	98.81 49	100.00 1	99.97 2	99.93 33	99.94 17

test_fmvsm_n_1920		99.69 5	99.66 4	99.78 71	99.84 38	99.44 116	99.58 130	99.69 22	99.43 17	99.98 13	99.91 26	98.62 76	100.00 1	99.97 2	99.95 23	99.90 25

test_vis1_n_1920		98.63 215	98.40 223	99.31 195	99.86 25	97.94 298	99.67 75	99.62 51	99.43 17	99.99 2	99.91 26	87.29 430	100.00 1	99.92 24	99.92 39	99.98 2

fmvsm_s_conf0.5_n_11		99.32 79	99.16 92	99.80 64	99.83 47	99.70 60	99.57 138	99.56 90	99.45 11	99.99 2	99.93 10	94.18 302	99.99 4	99.96 13	99.98 4	99.73 123

fmvsm_s_conf0.5_n_10		99.41 59	99.24 78	99.92 1	99.83 47	99.84 20	99.53 175	99.56 90	99.45 11	99.99 2	99.92 18	94.92 254	99.99 4	99.97 2	99.97 9	99.95 11

fmvsm_l_conf0.5_n_9		99.58 16	99.47 24	99.92 1	99.85 31	99.82 28	99.47 233	99.63 46	99.45 11	99.98 13	99.89 42	97.02 148	99.99 4	99.98 1	99.96 17	99.95 11

NormalMVS		99.27 89	99.19 88	99.52 139	99.89 8	98.83 222	99.65 88	99.52 130	99.10 48	99.84 56	99.76 185	95.80 215	99.99 4	99.30 89	99.84 102	99.74 114

SymmetryMVS		99.15 115	99.02 125	99.52 139	99.72 111	98.83 222	99.65 88	99.34 310	99.10 48	99.84 56	99.76 185	95.80 215	99.99 4	99.30 89	98.72 258	99.73 123

fmvsm_s_conf0.5_n_5		99.37 68	99.21 84	99.86 34	99.80 63	99.68 64	99.42 261	99.61 60	99.37 24	99.97 25	99.86 74	94.96 249	99.99 4	99.97 2	99.93 33	99.92 23

fmvsm_l_conf0.5_n_3		99.61 10	99.51 18	99.92 1	99.84 38	99.82 28	99.54 166	99.66 32	99.46 7	99.98 13	99.89 42	97.27 133	99.99 4	99.97 2	99.95 23	99.95 11

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 43	99.86 25	99.61 85	99.56 146	99.63 46	99.48 3	99.98 13	99.83 102	98.75 60	99.99 4	99.97 2	99.96 17	99.94 17

fmvsm_l_conf0.5_n		99.71 2	99.67 1	99.85 43	99.84 38	99.63 82	99.56 146	99.63 46	99.47 4	99.98 13	99.82 115	98.75 60	99.99 4	99.97 2	99.97 9	99.94 17

test_fmvsmconf_n		99.70 4	99.64 5	99.87 21	99.80 63	99.66 71	99.48 223	99.64 42	99.45 11	99.92 30	99.92 18	98.62 76	99.99 4	99.96 13	99.99 1	99.96 7

patch_mono-2		99.26 92	99.62 6	98.16 358	99.81 57	94.59 432	99.52 177	99.64 42	99.33 28	99.73 97	99.90 33	99.00 24	99.99 4	99.69 35	99.98 4	99.89 29

h-mvs33		97.70 330	97.28 353	98.97 243	99.70 122	97.27 326	99.36 291	99.45 245	98.94 78	99.66 126	99.64 250	94.93 252	99.99 4	99.48 64	84.36 467	99.65 171

xiu_mvs_v1_base_debu		99.29 85	99.27 73	99.34 187	99.63 165	98.97 183	99.12 368	99.51 152	98.86 84	99.84 56	99.47 317	98.18 104	99.99 4	99.50 57	99.31 191	99.08 296

xiu_mvs_v1_base		99.29 85	99.27 73	99.34 187	99.63 165	98.97 183	99.12 368	99.51 152	98.86 84	99.84 56	99.47 317	98.18 104	99.99 4	99.50 57	99.31 191	99.08 296

xiu_mvs_v1_base_debi		99.29 85	99.27 73	99.34 187	99.63 165	98.97 183	99.12 368	99.51 152	98.86 84	99.84 56	99.47 317	98.18 104	99.99 4	99.50 57	99.31 191	99.08 296

EPNet		98.86 180	98.71 187	99.30 200	97.20 457	98.18 278	99.62 106	98.91 401	99.28 31	98.63 361	99.81 130	95.96 203	99.99 4	99.24 99	99.72 148	99.73 123
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 24	99.42 32	99.89 11	99.83 47	99.74 54	99.51 187	99.62 51	99.46 7	99.99 2	99.90 33	96.60 172	99.98 20	99.95 16	99.95 23	99.96 7

MM		99.40 64	99.28 69	99.74 80	99.67 135	99.31 135	99.52 177	98.87 408	99.55 1	99.74 95	99.80 148	96.47 180	99.98 20	99.97 2	99.97 9	99.94 17

test_cas_vis1_n_1920		99.16 111	99.01 130	99.61 109	99.81 57	98.86 216	99.65 88	99.64 42	99.39 22	99.97 25	99.94 6	93.20 331	99.98 20	99.55 50	99.91 46	99.99 1

test_vis1_n		97.92 288	97.44 329	99.34 187	99.53 216	98.08 285	99.74 47	99.49 188	99.15 38	100.00 1	99.94 6	79.51 467	99.98 20	99.88 26	99.76 140	99.97 4

xiu_mvs_v2_base		99.26 92	99.25 77	99.29 203	99.53 216	98.91 204	99.02 392	99.45 245	98.80 94	99.71 108	99.26 376	98.94 34	99.98 20	99.34 81	99.23 200	98.98 310

PS-MVSNAJ		99.32 79	99.32 54	99.30 200	99.57 200	98.94 197	98.97 406	99.46 234	98.92 81	99.71 108	99.24 378	99.01 20	99.98 20	99.35 76	99.66 159	98.97 311

QAPM		98.67 210	98.30 230	99.80 64	99.20 323	99.67 68	99.77 34	99.72 14	94.74 427	98.73 341	99.90 33	95.78 217	99.98 20	96.96 358	99.88 76	99.76 107

3Dnovator	97.25 9	99.24 97	99.05 112	99.81 60	99.12 345	99.66 71	99.84 12	99.74 13	99.09 55	98.92 313	99.90 33	95.94 206	99.98 20	98.95 142	99.92 39	99.79 92

OpenMVS	96.50 16	98.47 221	98.12 242	99.52 139	99.04 364	99.53 101	99.82 16	99.72 14	94.56 430	98.08 396	99.88 53	94.73 270	99.98 20	97.47 324	99.76 140	99.06 302

fmvsm_s_conf0.5_n_3		99.37 68	99.20 86	99.87 21	99.75 92	99.70 60	99.48 223	99.66 32	99.45 11	99.99 2	99.93 10	94.64 279	99.97 29	99.94 21	99.97 9	99.95 11

reproduce_model		99.63 9	99.54 13	99.90 8	99.78 70	99.88 10	99.56 146	99.55 100	99.15 38	99.90 34	99.90 33	99.00 24	99.97 29	99.11 118	99.91 46	99.86 42

test_fmvsmconf0.1_n		99.55 23	99.45 30	99.86 34	99.44 256	99.65 75	99.50 198	99.61 60	99.45 11	99.87 49	99.92 18	97.31 130	99.97 29	99.95 16	99.99 1	99.97 4

test_fmvs1_n		98.41 227	98.14 239	99.21 216	99.82 53	97.71 311	99.74 47	99.49 188	99.32 29	99.99 2	99.95 3	85.32 445	99.97 29	99.82 29	99.84 102	99.96 7

CANet_DTU		98.97 168	98.87 164	99.25 210	99.33 287	98.42 270	99.08 377	99.30 337	99.16 37	99.43 193	99.75 190	95.27 237	99.97 29	98.56 212	99.95 23	99.36 268

MGCNet		99.15 115	98.96 142	99.73 83	98.92 382	99.37 123	99.37 285	96.92 465	99.51 2	99.66 126	99.78 172	96.69 167	99.97 29	99.84 28	99.97 9	99.84 53

MTAPA		99.52 28	99.39 40	99.89 11	99.90 4	99.86 18	99.66 82	99.47 222	98.79 95	99.68 115	99.81 130	98.43 89	99.97 29	98.88 152	99.90 57	99.83 63

PGM-MVS		99.45 46	99.31 60	99.86 34	99.87 20	99.78 47	99.58 130	99.65 39	97.84 236	99.71 108	99.80 148	99.12 15	99.97 29	98.33 237	99.87 79	99.83 63

mPP-MVS		99.44 50	99.30 62	99.86 34	99.88 13	99.79 41	99.69 62	99.48 200	98.12 187	99.50 177	99.75 190	98.78 53	99.97 29	98.57 209	99.89 68	99.83 63

CP-MVS		99.45 46	99.32 54	99.85 43	99.83 47	99.75 51	99.69 62	99.52 130	98.07 198	99.53 172	99.63 256	98.93 38	99.97 29	98.74 180	99.91 46	99.83 63

SteuartSystems-ACMMP		99.54 24	99.42 32	99.87 21	99.82 53	99.81 33	99.59 120	99.51 152	98.62 112	99.79 76	99.83 102	99.28 6	99.97 29	98.48 219	99.90 57	99.84 53
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 104	98.97 138	99.82 57	99.17 337	99.68 64	99.81 20	99.51 152	99.20 33	98.72 342	99.89 42	95.68 221	99.97 29	98.86 160	99.86 87	99.81 79

fmvsm_s_conf0.5_n_9		99.41 59	99.28 69	99.81 60	99.84 38	99.52 105	99.48 223	99.62 51	99.46 7	99.99 2	99.92 18	95.24 241	99.96 41	99.97 2	99.97 9	99.96 7

lecture		99.60 14	99.50 19	99.89 11	99.89 8	99.90 3	99.75 42	99.59 73	99.06 61	99.88 43	99.85 81	98.41 93	99.96 41	99.28 92	99.84 102	99.83 63

KinetiMVS		99.12 131	98.92 151	99.70 87	99.67 135	99.40 121	99.67 75	99.63 46	98.73 102	99.94 28	99.81 130	94.54 285	99.96 41	98.40 228	99.93 33	99.74 114

fmvsm_s_conf0.5_n_7		99.34 75	99.29 66	99.48 156	99.70 122	98.63 243	99.42 261	99.63 46	99.46 7	99.98 13	99.88 53	95.59 224	99.96 41	99.97 2	99.98 4	99.85 46

fmvsm_s_conf0.5_n_2		99.32 79	99.13 95	99.89 11	99.80 63	99.77 48	99.44 248	99.58 78	99.47 4	99.99 2	99.93 10	94.04 307	99.96 41	99.96 13	99.93 33	99.93 22

reproduce-ours		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 177	99.54 109	99.13 41	99.89 40	99.89 42	98.96 27	99.96 41	99.04 128	99.90 57	99.85 46

our_new_method		99.61 10	99.52 14	99.90 8	99.76 82	99.88 10	99.52 177	99.54 109	99.13 41	99.89 40	99.89 42	98.96 27	99.96 41	99.04 128	99.90 57	99.85 46

fmvsm_s_conf0.5_n_a		99.56 21	99.47 24	99.85 43	99.83 47	99.64 81	99.52 177	99.65 39	99.10 48	99.98 13	99.92 18	97.35 129	99.96 41	99.94 21	99.92 39	99.95 11

fmvsm_s_conf0.5_n		99.51 29	99.40 38	99.85 43	99.84 38	99.65 75	99.51 187	99.67 27	99.13 41	99.98 13	99.92 18	96.60 172	99.96 41	99.95 16	99.96 17	99.95 11

mvsany_test1		99.50 31	99.46 28	99.62 108	99.61 185	99.09 165	98.94 412	99.48 200	99.10 48	99.96 27	99.91 26	98.85 44	99.96 41	99.72 32	99.58 169	99.82 72

test_fmvs1		98.88 174	98.79 178	99.16 221	99.69 127	97.61 315	99.55 161	99.49 188	99.32 29	99.98 13	99.91 26	91.41 379	99.96 41	99.82 29	99.92 39	99.90 25

DVP-MVS++		99.59 15	99.50 19	99.88 15	99.51 225	99.88 10	99.87 8	99.51 152	98.99 69	99.88 43	99.81 130	99.27 7	99.96 41	98.85 162	99.80 125	99.81 79

MSC_two_6792asdad				99.87 21	99.51 225	99.76 49		99.33 318					99.96 41	98.87 155	99.84 102	99.89 29

No_MVS				99.87 21	99.51 225	99.76 49		99.33 318					99.96 41	98.87 155	99.84 102	99.89 29

ZD-MVS					99.71 117	99.79 41		99.61 60	96.84 343	99.56 163	99.54 290	98.58 78	99.96 41	96.93 361	99.75 142

SED-MVS		99.61 10	99.52 14	99.88 15	99.84 38	99.90 3	99.60 113	99.48 200	99.08 56	99.91 31	99.81 130	99.20 9	99.96 41	98.91 149	99.85 94	99.79 92

test_241102_TWO								99.48 200	99.08 56	99.88 43	99.81 130	98.94 34	99.96 41	98.91 149	99.84 102	99.88 35

ZNCC-MVS		99.47 40	99.33 52	99.87 21	99.87 20	99.81 33	99.64 95	99.67 27	98.08 197	99.55 169	99.64 250	98.91 39	99.96 41	98.72 183	99.90 57	99.82 72

DVP-MVS		99.57 20	99.47 24	99.88 15	99.85 31	99.89 6	99.57 138	99.37 296	99.10 48	99.81 69	99.80 148	98.94 34	99.96 41	98.93 146	99.86 87	99.81 79
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 69	99.81 69	99.80 148	99.09 16	99.96 41	98.85 162	99.90 57	99.88 35

test_0728_SECOND				99.91 6	99.84 38	99.89 6	99.57 138	99.51 152					99.96 41	98.93 146	99.86 87	99.88 35

SR-MVS		99.43 53	99.29 66	99.86 34	99.75 92	99.83 22	99.59 120	99.62 51	98.21 168	99.73 97	99.79 165	98.68 70	99.96 41	98.44 225	99.77 137	99.79 92

DPE-MVS		99.46 42	99.32 54	99.91 6	99.78 70	99.88 10	99.36 291	99.51 152	98.73 102	99.88 43	99.84 96	98.72 67	99.96 41	98.16 252	99.87 79	99.88 35
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 55	99.29 66	99.80 64	99.62 174	99.55 96	99.50 198	99.70 18	98.79 95	99.77 85	99.96 1	97.45 124	99.96 41	98.92 148	99.90 57	99.89 29

HFP-MVS		99.49 33	99.37 44	99.86 34	99.87 20	99.80 38	99.66 82	99.67 27	98.15 175	99.68 115	99.69 223	99.06 18	99.96 41	98.69 188	99.87 79	99.84 53

region2R		99.48 37	99.35 48	99.87 21	99.88 13	99.80 38	99.65 88	99.66 32	98.13 183	99.66 126	99.68 231	98.96 27	99.96 41	98.62 197	99.87 79	99.84 53

HPM-MVS++		99.39 66	99.23 82	99.87 21	99.75 92	99.84 20	99.43 254	99.51 152	98.68 109	99.27 242	99.53 294	98.64 75	99.96 41	98.44 225	99.80 125	99.79 92

APDe-MVS		99.66 6	99.57 10	99.92 1	99.77 78	99.89 6	99.75 42	99.56 90	99.02 62	99.88 43	99.85 81	99.18 12	99.96 41	99.22 100	99.92 39	99.90 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 33	99.36 46	99.86 34	99.87 20	99.79 41	99.66 82	99.67 27	98.15 175	99.67 121	99.69 223	98.95 32	99.96 41	98.69 188	99.87 79	99.84 53

MP-MVS		99.33 77	99.15 93	99.87 21	99.88 13	99.82 28	99.66 82	99.46 234	98.09 193	99.48 181	99.74 195	98.29 99	99.96 41	97.93 274	99.87 79	99.82 72
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 137	98.90 156	99.74 80	99.80 63	99.46 114	99.59 120	99.49 188	97.03 330	99.63 143	99.69 223	97.27 133	99.96 41	97.82 285	99.84 102	99.81 79

PVSNet_Blended_VisFu		99.36 72	99.28 69	99.61 109	99.86 25	99.07 170	99.47 233	99.93 2	97.66 261	99.71 108	99.86 74	97.73 119	99.96 41	99.47 66	99.82 117	99.79 92

UGNet		98.87 177	98.69 189	99.40 177	99.22 320	98.72 235	99.44 248	99.68 24	99.24 32	99.18 267	99.42 328	92.74 341	99.96 41	99.34 81	99.94 31	99.53 221
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 79	99.32 54	99.32 193	99.85 31	98.29 273	99.71 57	99.66 32	98.11 189	99.41 201	99.80 148	98.37 96	99.96 41	98.99 134	99.96 17	99.72 133

ACMMP		99.45 46	99.32 54	99.82 57	99.89 8	99.67 68	99.62 106	99.69 22	98.12 187	99.63 143	99.84 96	98.73 66	99.96 41	98.55 215	99.83 113	99.81 79
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
MED-MVS test				99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.34 26	99.90 34	99.83 102		99.95 76	98.83 168	99.89 68	99.83 63

MED-MVS		99.66 6	99.60 8	99.87 21	99.88 13	99.81 33	99.69 62	99.87 6	99.18 34	99.90 34	99.83 102	99.30 4	99.95 76	98.83 168	99.89 68	99.83 63

TestfortrainingZip a		99.73 1	99.67 1	99.92 1	99.88 13	99.91 2	99.69 62	99.87 6	99.34 26	99.90 34	99.83 102	99.30 4	99.95 76	99.32 84	99.89 68	99.90 25

fmvsm_s_conf0.5_n_6		99.54 24	99.44 31	99.85 43	99.51 225	99.67 68	99.50 198	99.64 42	99.43 17	99.98 13	99.78 172	97.26 136	99.95 76	99.95 16	99.93 33	99.92 23

fmvsm_s_conf0.5_n_4		99.36 72	99.24 78	99.73 83	99.78 70	99.53 101	99.49 215	99.60 67	99.42 20	99.99 2	99.86 74	95.15 244	99.95 76	99.95 16	99.89 68	99.73 123

fmvsm_s_conf0.1_n_2		99.37 68	99.22 83	99.81 60	99.77 78	99.75 51	99.46 237	99.60 67	99.47 4	99.98 13	99.94 6	94.98 248	99.95 76	99.97 2	99.79 132	99.73 123

test_fmvsmconf0.01_n		99.22 100	99.03 117	99.79 68	98.42 437	99.48 111	99.55 161	99.51 152	99.39 22	99.78 81	99.93 10	94.80 261	99.95 76	99.93 23	99.95 23	99.94 17

SR-MVS-dyc-post		99.45 46	99.31 60	99.85 43	99.76 82	99.82 28	99.63 101	99.52 130	98.38 137	99.76 91	99.82 115	98.53 82	99.95 76	98.61 200	99.81 120	99.77 100

GST-MVS		99.40 64	99.24 78	99.85 43	99.86 25	99.79 41	99.60 113	99.67 27	97.97 220	99.63 143	99.68 231	98.52 83	99.95 76	98.38 230	99.86 87	99.81 79

CANet		99.25 96	99.14 94	99.59 113	99.41 264	99.16 155	99.35 296	99.57 85	98.82 89	99.51 176	99.61 265	96.46 181	99.95 76	99.59 45	99.98 4	99.65 171

MP-MVS-pluss		99.37 68	99.20 86	99.88 15	99.90 4	99.87 17	99.30 310	99.52 130	97.18 312	99.60 155	99.79 165	98.79 52	99.95 76	98.83 168	99.91 46	99.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 55	99.27 73	99.88 15	99.89 8	99.80 38	99.67 75	99.50 175	98.70 106	99.77 85	99.49 308	98.21 102	99.95 76	98.46 223	99.77 137	99.88 35
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 76	96.67 373

APD-MVS_3200maxsize		99.48 37	99.35 48	99.85 43	99.76 82	99.83 22	99.63 101	99.54 109	98.36 141	99.79 76	99.82 115	98.86 43	99.95 76	98.62 197	99.81 120	99.78 98

RPMNet		96.72 382	95.90 395	99.19 218	99.18 329	98.49 262	99.22 348	99.52 130	88.72 464	99.56 163	97.38 461	94.08 306	99.95 76	86.87 469	98.58 265	99.14 288

sss		99.17 109	99.05 112	99.53 133	99.62 174	98.97 183	99.36 291	99.62 51	97.83 237	99.67 121	99.65 244	97.37 128	99.95 76	99.19 104	99.19 203	99.68 156

MVSMamba_PlusPlus		99.46 42	99.41 37	99.64 101	99.68 132	99.50 108	99.75 42	99.50 175	98.27 152	99.87 49	99.92 18	98.09 108	99.94 92	99.65 41	99.95 23	99.47 245

fmvsm_s_conf0.1_n_a		99.26 92	99.06 110	99.85 43	99.52 222	99.62 83	99.54 166	99.62 51	98.69 107	99.99 2	99.96 1	94.47 289	99.94 92	99.88 26	99.92 39	99.98 2

fmvsm_s_conf0.1_n		99.29 85	99.10 99	99.86 34	99.70 122	99.65 75	99.53 175	99.62 51	98.74 101	99.99 2	99.95 3	94.53 287	99.94 92	99.89 25	99.96 17	99.97 4

TSAR-MVS + MP.		99.58 16	99.50 19	99.81 60	99.91 1	99.66 71	99.63 101	99.39 280	98.91 82	99.78 81	99.85 81	99.36 2	99.94 92	98.84 165	99.88 76	99.82 72
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 172	98.75 181	99.39 182	99.46 249	98.61 247	99.76 37	99.50 175	98.06 202	99.81 69	99.88 53	93.91 314	99.94 92	99.11 118	99.27 194	99.61 188

mamv4		99.33 77	99.42 32	99.07 229	99.67 135	97.73 306	99.42 261	99.60 67	98.15 175	99.94 28	99.91 26	98.42 91	99.94 92	99.72 32	99.96 17	99.54 215

XVS		99.53 27	99.42 32	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 212	99.74 195	98.81 49	99.94 92	98.79 176	99.86 87	99.84 53

X-MVStestdata		96.55 385	95.45 404	99.87 21	99.85 31	99.83 22	99.69 62	99.68 24	98.98 72	99.37 212	64.01 484	98.81 49	99.94 92	98.79 176	99.86 87	99.84 53

旧先验2							98.96 407		96.70 351	99.47 182			99.94 92	98.19 248

新几何1				99.75 77	99.75 92	99.59 88		99.54 109	96.76 347	99.29 235	99.64 250	98.43 89	99.94 92	96.92 363	99.66 159	99.72 133

testdata				99.54 125	99.75 92	98.95 193		99.51 152	97.07 324	99.43 193	99.70 212	98.87 42	99.94 92	97.76 294	99.64 162	99.72 133

HPM-MVS		99.42 55	99.28 69	99.83 56	99.90 4	99.72 56	99.81 20	99.54 109	97.59 267	99.68 115	99.63 256	98.91 39	99.94 92	98.58 206	99.91 46	99.84 53
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 101	99.10 99	99.45 165	99.89 8	98.52 257	99.39 278	99.94 1	98.73 102	99.11 276	99.89 42	95.50 227	99.94 92	99.50 57	99.97 9	99.89 29

APD-MVS		99.27 89	99.08 105	99.84 55	99.75 92	99.79 41	99.50 198	99.50 175	97.16 314	99.77 85	99.82 115	98.78 53	99.94 92	97.56 315	99.86 87	99.80 88
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 37	99.42 32	99.65 95	99.72 111	99.40 121	99.05 384	99.66 32	99.14 40	99.57 162	99.80 148	98.46 87	99.94 92	99.57 48	99.84 102	99.60 191
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		99.06 150	98.88 163	99.61 109	99.62 174	99.16 155	99.37 285	99.56 90	98.04 212	99.53 172	99.62 261	96.84 159	99.94 92	98.85 162	98.49 273	99.72 133

DeepC-MVS	98.35 2	99.30 83	99.19 88	99.64 101	99.82 53	99.23 148	99.62 106	99.55 100	98.94 78	99.63 143	99.95 3	95.82 213	99.94 92	99.37 75	99.97 9	99.73 123
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 89	99.12 97	99.74 80	99.18 329	99.75 51	99.56 146	99.57 85	98.45 130	99.49 180	99.85 81	97.77 118	99.94 92	98.33 237	99.84 102	99.52 222

ME-MVS		99.56 21	99.46 28	99.86 34	99.80 63	99.81 33	99.37 285	99.70 18	99.18 34	99.83 64	99.83 102	98.74 65	99.93 110	98.83 168	99.89 68	99.83 63

GDP-MVS		99.08 145	98.89 160	99.64 101	99.53 216	99.34 127	99.64 95	99.48 200	98.32 147	99.77 85	99.66 242	95.14 245	99.93 110	98.97 140	99.50 176	99.64 178

SDMVSNet		99.11 137	98.90 156	99.75 77	99.81 57	99.59 88	99.81 20	99.65 39	98.78 98	99.64 140	99.88 53	94.56 282	99.93 110	99.67 37	98.26 288	99.72 133

FE-MVS		98.48 220	98.17 235	99.40 177	99.54 215	98.96 187	99.68 72	98.81 415	95.54 410	99.62 147	99.70 212	93.82 317	99.93 110	97.35 334	99.46 178	99.32 274

SF-MVS		99.38 67	99.24 78	99.79 68	99.79 68	99.68 64	99.57 138	99.54 109	97.82 242	99.71 108	99.80 148	98.95 32	99.93 110	98.19 248	99.84 102	99.74 114

dcpmvs_2		99.23 98	99.58 9	98.16 358	99.83 47	94.68 429	99.76 37	99.52 130	99.07 58	99.98 13	99.88 53	98.56 80	99.93 110	99.67 37	99.98 4	99.87 40

Anonymous20240529		98.09 257	97.68 296	99.34 187	99.66 148	98.44 267	99.40 274	99.43 265	93.67 437	99.22 254	99.89 42	90.23 396	99.93 110	99.26 98	98.33 280	99.66 165

ACMMP_NAP		99.47 40	99.34 50	99.88 15	99.87 20	99.86 18	99.47 233	99.48 200	98.05 205	99.76 91	99.86 74	98.82 48	99.93 110	98.82 175	99.91 46	99.84 53

EI-MVSNet-UG-set		99.58 16	99.57 10	99.64 101	99.78 70	99.14 160	99.60 113	99.45 245	99.01 64	99.90 34	99.83 102	98.98 26	99.93 110	99.59 45	99.95 23	99.86 42

无先验							98.99 400	99.51 152	96.89 340				99.93 110	97.53 318		99.72 133

VDDNet		97.55 345	97.02 367	99.16 221	99.49 239	98.12 284	99.38 283	99.30 337	95.35 412	99.68 115	99.90 33	82.62 458	99.93 110	99.31 86	98.13 300	99.42 257

ab-mvs		98.86 180	98.63 199	99.54 125	99.64 161	99.19 150	99.44 248	99.54 109	97.77 246	99.30 232	99.81 130	94.20 299	99.93 110	99.17 110	98.82 252	99.49 236

F-COLMAP		99.19 101	99.04 114	99.64 101	99.78 70	99.27 143	99.42 261	99.54 109	97.29 303	99.41 201	99.59 270	98.42 91	99.93 110	98.19 248	99.69 153	99.73 123

BP-MVS1		99.12 131	98.94 148	99.65 95	99.51 225	99.30 138	99.67 75	98.92 396	98.48 126	99.84 56	99.69 223	94.96 249	99.92 123	99.62 44	99.79 132	99.71 144

Anonymous202405211		98.30 238	97.98 259	99.26 209	99.57 200	98.16 279	99.41 266	98.55 440	96.03 404	99.19 263	99.74 195	91.87 366	99.92 123	99.16 113	98.29 287	99.70 147

EI-MVSNet-Vis-set		99.58 16	99.56 12	99.64 101	99.78 70	99.15 159	99.61 112	99.45 245	99.01 64	99.89 40	99.82 115	99.01 20	99.92 123	99.56 49	99.95 23	99.85 46

VDD-MVS		97.73 324	97.35 341	98.88 266	99.47 247	97.12 334	99.34 299	98.85 410	98.19 170	99.67 121	99.85 81	82.98 456	99.92 123	99.49 61	98.32 284	99.60 191

VNet		99.11 137	98.90 156	99.73 83	99.52 222	99.56 94	99.41 266	99.39 280	99.01 64	99.74 95	99.78 172	95.56 225	99.92 123	99.52 55	98.18 296	99.72 133

XVG-OURS-SEG-HR		98.69 208	98.62 204	98.89 262	99.71 117	97.74 305	99.12 368	99.54 109	98.44 133	99.42 196	99.71 208	94.20 299	99.92 123	98.54 216	98.90 246	99.00 307

mvsmamba		99.06 150	98.96 142	99.36 184	99.47 247	98.64 242	99.70 58	99.05 380	97.61 266	99.65 135	99.83 102	96.54 177	99.92 123	99.19 104	99.62 165	99.51 231

HPM-MVS_fast		99.51 29	99.40 38	99.85 43	99.91 1	99.79 41	99.76 37	99.56 90	97.72 252	99.76 91	99.75 190	99.13 14	99.92 123	99.07 125	99.92 39	99.85 46

HY-MVS	97.30 7	98.85 189	98.64 198	99.47 162	99.42 259	99.08 168	99.62 106	99.36 298	97.39 295	99.28 236	99.68 231	96.44 183	99.92 123	98.37 232	98.22 291	99.40 262

DP-MVS		99.16 111	98.95 146	99.78 71	99.77 78	99.53 101	99.41 266	99.50 175	97.03 330	99.04 293	99.88 53	97.39 125	99.92 123	98.66 192	99.90 57	99.87 40

IB-MVS	95.67 18	96.22 391	95.44 405	98.57 308	99.21 321	96.70 368	98.65 441	97.74 459	96.71 350	97.27 422	98.54 434	86.03 439	99.92 123	98.47 222	86.30 465	99.10 291
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 33	99.39 40	99.77 74	99.63 165	99.59 88	99.36 291	99.46 234	99.07 58	99.79 76	99.82 115	98.85 44	99.92 123	98.68 190	99.87 79	99.82 72
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LuminaMVS		99.23 98	99.10 99	99.61 109	99.35 281	99.31 135	99.46 237	99.13 368	98.61 113	99.86 53	99.89 42	96.41 186	99.91 135	99.67 37	99.51 174	99.63 183

balanced_conf03		99.46 42	99.39 40	99.67 90	99.55 208	99.58 93	99.74 47	99.51 152	98.42 134	99.87 49	99.84 96	98.05 111	99.91 135	99.58 47	99.94 31	99.52 222

9.14			99.10 99		99.72 111		99.40 274	99.51 152	97.53 277	99.64 140	99.78 172	98.84 46	99.91 135	97.63 306	99.82 117

SMA-MVS		99.44 50	99.30 62	99.85 43	99.73 107	99.83 22	99.56 146	99.47 222	97.45 286	99.78 81	99.82 115	99.18 12	99.91 135	98.79 176	99.89 68	99.81 79
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					99.67 135	99.65 75	99.05 384	99.41 270	96.22 389	98.95 309	99.49 308	98.77 56	99.91 135

train_agg		99.02 158	98.77 179	99.77 74	99.67 135	99.65 75	99.05 384	99.41 270	96.28 383	98.95 309	99.49 308	98.76 57	99.91 135	97.63 306	99.72 148	99.75 109

test_8					99.67 135	99.61 85	99.03 389	99.41 270	96.28 383	98.93 312	99.48 314	98.76 57	99.91 135

agg_prior					99.67 135	99.62 83		99.40 277		98.87 322			99.91 135

原ACMM1				99.65 95	99.73 107	99.33 130		99.47 222	97.46 283	99.12 274	99.66 242	98.67 72	99.91 135	97.70 303	99.69 153	99.71 144

LFMVS		97.90 291	97.35 341	99.54 125	99.52 222	99.01 177	99.39 278	98.24 448	97.10 322	99.65 135	99.79 165	84.79 448	99.91 135	99.28 92	98.38 277	99.69 150

XVG-OURS		98.73 206	98.68 190	98.88 266	99.70 122	97.73 306	98.92 414	99.55 100	98.52 122	99.45 185	99.84 96	95.27 237	99.91 135	98.08 263	98.84 250	99.00 307

PLC	97.94 4	99.02 158	98.85 170	99.53 133	99.66 148	99.01 177	99.24 341	99.52 130	96.85 342	99.27 242	99.48 314	98.25 101	99.91 135	97.76 294	99.62 165	99.65 171
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 338	97.06 366	99.47 162	99.61 185	99.09 165	98.04 468	99.25 349	91.24 455	98.51 372	99.70 212	94.55 284	99.91 135	92.76 444	99.85 94	99.42 257
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 174	98.65 196	99.58 116	99.58 195	99.34 127	99.65 88	99.52 130	98.26 155	99.83 64	99.87 66	93.37 325	99.90 148	97.81 287	99.91 46	99.49 236

StellarMVS		98.88 174	98.65 196	99.58 116	99.58 195	99.34 127	99.65 88	99.52 130	98.26 155	99.83 64	99.87 66	93.37 325	99.90 148	97.81 287	99.91 46	99.49 236

AstraMVS		99.09 143	99.03 117	99.25 210	99.66 148	98.13 282	99.57 138	98.24 448	98.82 89	99.91 31	99.88 53	95.81 214	99.90 148	99.72 32	99.67 158	99.74 114

mmtdpeth		96.95 377	96.71 376	97.67 397	99.33 287	94.90 424	99.89 2	99.28 343	98.15 175	99.72 102	98.57 433	86.56 435	99.90 148	99.82 29	89.02 460	98.20 428

UWE-MVS		97.58 344	97.29 352	98.48 321	99.09 353	96.25 388	99.01 397	96.61 471	97.86 230	99.19 263	99.01 404	88.72 411	99.90 148	97.38 332	98.69 259	99.28 277

test_vis1_rt		95.81 401	95.65 400	96.32 432	99.67 135	91.35 460	99.49 215	96.74 469	98.25 160	95.24 446	98.10 452	74.96 468	99.90 148	99.53 53	98.85 249	97.70 452

FA-MVS(test-final)		98.75 203	98.53 215	99.41 176	99.55 208	99.05 173	99.80 25	99.01 385	96.59 365	99.58 159	99.59 270	95.39 231	99.90 148	97.78 290	99.49 177	99.28 277

MCST-MVS		99.43 53	99.30 62	99.82 57	99.79 68	99.74 54	99.29 315	99.40 277	98.79 95	99.52 174	99.62 261	98.91 39	99.90 148	98.64 194	99.75 142	99.82 72

CDPH-MVS		99.13 123	98.91 154	99.80 64	99.75 92	99.71 58	99.15 362	99.41 270	96.60 363	99.60 155	99.55 285	98.83 47	99.90 148	97.48 322	99.83 113	99.78 98

NCCC		99.34 75	99.19 88	99.79 68	99.61 185	99.65 75	99.30 310	99.48 200	98.86 84	99.21 257	99.63 256	98.72 67	99.90 148	98.25 244	99.63 164	99.80 88

114514_t		98.93 170	98.67 191	99.72 86	99.85 31	99.53 101	99.62 106	99.59 73	92.65 450	99.71 108	99.78 172	98.06 110	99.90 148	98.84 165	99.91 46	99.74 114

1112_ss		98.98 166	98.77 179	99.59 113	99.68 132	99.02 175	99.25 336	99.48 200	97.23 309	99.13 272	99.58 274	96.93 153	99.90 148	98.87 155	98.78 255	99.84 53

PHI-MVS		99.30 83	99.17 91	99.70 87	99.56 204	99.52 105	99.58 130	99.80 11	97.12 318	99.62 147	99.73 201	98.58 78	99.90 148	98.61 200	99.91 46	99.68 156

AdaColmap		99.01 162	98.80 175	99.66 91	99.56 204	99.54 98	99.18 357	99.70 18	98.18 173	99.35 221	99.63 256	96.32 188	99.90 148	97.48 322	99.77 137	99.55 213

COLMAP_ROB	97.56 6	98.86 180	98.75 181	99.17 220	99.88 13	98.53 253	99.34 299	99.59 73	97.55 273	98.70 349	99.89 42	95.83 212	99.90 148	98.10 258	99.90 57	99.08 296
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 234	98.03 254	99.31 195	99.63 165	98.56 250	99.54 166	96.75 468	97.53 277	99.73 97	99.65 244	91.25 384	99.89 163	98.62 197	99.56 170	99.48 239

tttt0517		98.42 225	98.14 239	99.28 207	99.66 148	98.38 271	99.74 47	96.85 466	97.68 258	99.79 76	99.74 195	91.39 380	99.89 163	98.83 168	99.56 170	99.57 209

test12				99.75 77	99.64 161	99.61 85		99.29 341		99.21 257		98.38 95	99.89 163		99.74 145	99.74 114

Test_1112_low_res		98.89 173	98.66 194	99.57 120	99.69 127	98.95 193	99.03 389	99.47 222	96.98 332	99.15 270	99.23 379	96.77 164	99.89 163	98.83 168	98.78 255	99.86 42

CNLPA		99.14 121	98.99 134	99.59 113	99.58 195	99.41 120	99.16 359	99.44 254	98.45 130	99.19 263	99.49 308	98.08 109	99.89 163	97.73 298	99.75 142	99.48 239

diffmvs_AUTHOR		99.19 101	99.10 99	99.48 156	99.64 161	98.85 217	99.32 304	99.48 200	98.50 124	99.81 69	99.81 130	96.82 160	99.88 168	99.40 71	99.12 216	99.71 144

guyue		99.16 111	99.04 114	99.52 139	99.69 127	98.92 203	99.59 120	98.81 415	98.73 102	99.90 34	99.87 66	95.34 234	99.88 168	99.66 40	99.81 120	99.74 114

sd_testset		98.75 203	98.57 211	99.29 203	99.81 57	98.26 275	99.56 146	99.62 51	98.78 98	99.64 140	99.88 53	92.02 363	99.88 168	99.54 51	98.26 288	99.72 133

APD_test1		95.87 399	96.49 381	94.00 440	99.53 216	84.01 469	99.54 166	99.32 328	95.91 406	97.99 401	99.85 81	85.49 443	99.88 168	91.96 447	98.84 250	98.12 432

diffmvs		99.14 121	99.02 125	99.51 144	99.61 185	98.96 187	99.28 320	99.49 188	98.46 128	99.72 102	99.71 208	96.50 179	99.88 168	99.31 86	99.11 218	99.67 160
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		98.86 180	98.80 175	99.03 235	99.76 82	98.79 228	99.28 320	99.91 3	97.42 292	99.67 121	99.37 346	97.53 122	99.88 168	98.98 135	97.29 348	98.42 413

PVSNet_Blended		99.08 145	98.97 138	99.42 175	99.76 82	98.79 228	98.78 428	99.91 3	96.74 348	99.67 121	99.49 308	97.53 122	99.88 168	98.98 135	99.85 94	99.60 191

viewdifsd2359ckpt07		99.11 137	99.00 133	99.43 173	99.63 165	98.73 233	99.45 241	99.54 109	98.33 145	99.62 147	99.81 130	96.17 194	99.87 175	99.27 95	99.14 208	99.69 150

viewdifsd2359ckpt11		98.78 198	98.74 183	98.89 262	99.67 135	97.04 344	99.50 198	99.58 78	98.26 155	99.56 163	99.90 33	94.36 292	99.87 175	99.49 61	98.32 284	99.77 100

viewmsd2359difaftdt		98.78 198	98.74 183	98.90 258	99.67 135	97.04 344	99.50 198	99.58 78	98.26 155	99.56 163	99.90 33	94.36 292	99.87 175	99.49 61	98.32 284	99.77 100

MVS		97.28 366	96.55 379	99.48 156	98.78 403	98.95 193	99.27 325	99.39 280	83.53 471	98.08 396	99.54 290	96.97 151	99.87 175	94.23 424	99.16 204	99.63 183

MG-MVS		99.13 123	99.02 125	99.45 165	99.57 200	98.63 243	99.07 378	99.34 310	98.99 69	99.61 152	99.82 115	97.98 113	99.87 175	97.00 354	99.80 125	99.85 46

MSDG		98.98 166	98.80 175	99.53 133	99.76 82	99.19 150	98.75 431	99.55 100	97.25 306	99.47 182	99.77 181	97.82 116	99.87 175	96.93 361	99.90 57	99.54 215

ETV-MVS		99.26 92	99.21 84	99.40 177	99.46 249	99.30 138	99.56 146	99.52 130	98.52 122	99.44 190	99.27 374	98.41 93	99.86 181	99.10 121	99.59 168	99.04 303

thisisatest0515		98.14 252	97.79 279	99.19 218	99.50 237	98.50 261	98.61 443	96.82 467	96.95 336	99.54 170	99.43 326	91.66 375	99.86 181	98.08 263	99.51 174	99.22 285

thres600view7		97.86 297	97.51 315	98.92 252	99.72 111	97.95 296	99.59 120	98.74 425	97.94 222	99.27 242	98.62 430	91.75 369	99.86 181	93.73 430	98.19 295	98.96 313

lupinMVS		99.13 123	99.01 130	99.46 164	99.51 225	98.94 197	99.05 384	99.16 364	97.86 230	99.80 74	99.56 282	97.39 125	99.86 181	98.94 143	99.85 94	99.58 206

PVSNet	96.02 17	98.85 189	98.84 172	98.89 262	99.73 107	97.28 325	98.32 460	99.60 67	97.86 230	99.50 177	99.57 279	96.75 165	99.86 181	98.56 212	99.70 152	99.54 215

MAR-MVS		98.86 180	98.63 199	99.54 125	99.37 277	99.66 71	99.45 241	99.54 109	96.61 360	99.01 296	99.40 336	97.09 143	99.86 181	97.68 305	99.53 173	99.10 291
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
mamba_0408		99.08 145	98.96 142	99.44 170	99.62 174	98.88 209	99.25 336	99.47 222	98.05 205	99.37 212	99.81 130	96.85 155	99.85 187	98.98 135	99.25 197	99.60 191

SSM_0404		99.16 111	99.06 110	99.44 170	99.65 156	98.96 187	99.49 215	99.50 175	98.14 180	99.62 147	99.85 81	96.85 155	99.85 187	99.19 104	99.26 196	99.52 222

testing91		97.44 358	97.02 367	98.71 295	99.18 329	96.89 362	99.19 355	99.04 381	97.78 245	98.31 383	98.29 444	85.41 444	99.85 187	98.01 269	97.95 305	99.39 263

test2506		96.81 381	96.65 377	97.29 412	99.74 100	92.21 457	99.60 113	85.06 488	99.13 41	99.77 85	99.93 10	87.82 428	99.85 187	99.38 74	99.38 183	99.80 88

AllTest		98.87 177	98.72 185	99.31 195	99.86 25	98.48 264	99.56 146	99.61 60	97.85 233	99.36 218	99.85 81	95.95 204	99.85 187	96.66 374	99.83 113	99.59 202

TestCases				99.31 195	99.86 25	98.48 264		99.61 60	97.85 233	99.36 218	99.85 81	95.95 204	99.85 187	96.66 374	99.83 113	99.59 202

jason		99.13 123	99.03 117	99.45 165	99.46 249	98.87 213	99.12 368	99.26 347	98.03 214	99.79 76	99.65 244	97.02 148	99.85 187	99.02 132	99.90 57	99.65 171
jason: jason.
CNVR-MVS		99.42 55	99.30 62	99.78 71	99.62 174	99.71 58	99.26 334	99.52 130	98.82 89	99.39 208	99.71 208	98.96 27	99.85 187	98.59 205	99.80 125	99.77 100

PAPM_NR		99.04 155	98.84 172	99.66 91	99.74 100	99.44 116	99.39 278	99.38 288	97.70 256	99.28 236	99.28 371	98.34 97	99.85 187	96.96 358	99.45 179	99.69 150

E4		99.13 123	99.01 130	99.49 152	99.68 132	98.90 207	99.52 177	99.52 130	98.13 183	99.71 108	99.90 33	96.32 188	99.84 196	99.21 102	99.11 218	99.75 109

E3new		99.18 104	99.08 105	99.48 156	99.63 165	98.94 197	99.46 237	99.50 175	98.06 202	99.72 102	99.84 96	97.27 133	99.84 196	99.10 121	99.13 211	99.67 160

E2		99.15 115	99.03 117	99.49 152	99.65 156	98.93 202	99.49 215	99.52 130	98.14 180	99.72 102	99.88 53	96.57 176	99.84 196	99.17 110	99.13 211	99.72 133

E3		99.15 115	99.03 117	99.49 152	99.62 174	98.91 204	99.49 215	99.52 130	98.13 183	99.72 102	99.88 53	96.61 171	99.84 196	99.17 110	99.13 211	99.72 133

viewcassd2359sk11		99.18 104	99.08 105	99.49 152	99.65 156	98.95 193	99.48 223	99.51 152	98.10 192	99.72 102	99.87 66	97.13 139	99.84 196	99.13 115	99.14 208	99.69 150

testing99		97.36 361	96.94 370	98.63 301	99.18 329	96.70 368	99.30 310	98.93 393	97.71 253	98.23 388	98.26 445	84.92 447	99.84 196	98.04 268	97.85 312	99.35 269

testing222		97.16 371	96.50 380	99.16 221	99.16 339	98.47 266	99.27 325	98.66 436	97.71 253	98.23 388	98.15 448	82.28 461	99.84 196	97.36 333	97.66 318	99.18 287

test1111		98.04 268	98.11 243	97.83 387	99.74 100	93.82 441	99.58 130	95.40 475	99.12 46	99.65 135	99.93 10	90.73 389	99.84 196	99.43 69	99.38 183	99.82 72

ECVR-MVS		98.04 268	98.05 252	98.00 371	99.74 100	94.37 436	99.59 120	94.98 476	99.13 41	99.66 126	99.93 10	90.67 390	99.84 196	99.40 71	99.38 183	99.80 88

test_yl		98.86 180	98.63 199	99.54 125	99.49 239	99.18 152	99.50 198	99.07 377	98.22 166	99.61 152	99.51 302	95.37 232	99.84 196	98.60 203	98.33 280	99.59 202

DCV-MVSNet		98.86 180	98.63 199	99.54 125	99.49 239	99.18 152	99.50 198	99.07 377	98.22 166	99.61 152	99.51 302	95.37 232	99.84 196	98.60 203	98.33 280	99.59 202

Fast-Effi-MVS+		98.70 207	98.43 220	99.51 144	99.51 225	99.28 141	99.52 177	99.47 222	96.11 399	99.01 296	99.34 356	96.20 193	99.84 196	97.88 277	98.82 252	99.39 263

TSAR-MVS + GP.		99.36 72	99.36 46	99.36 184	99.67 135	98.61 247	99.07 378	99.33 318	99.00 67	99.82 68	99.81 130	99.06 18	99.84 196	99.09 123	99.42 181	99.65 171

tpmrst		98.33 235	98.48 218	97.90 380	99.16 339	94.78 425	99.31 308	99.11 370	97.27 304	99.45 185	99.59 270	95.33 235	99.84 196	98.48 219	98.61 262	99.09 295

Vis-MVSNet		99.12 131	98.97 138	99.56 122	99.78 70	99.10 164	99.68 72	99.66 32	98.49 125	99.86 53	99.87 66	94.77 266	99.84 196	99.19 104	99.41 182	99.74 114
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 215	98.34 226	99.51 144	99.40 269	99.03 174	98.80 426	99.36 298	96.33 380	99.00 300	99.12 393	98.46 87	99.84 196	95.23 410	99.37 190	99.66 165

PatchMatch-RL		98.84 192	98.62 204	99.52 139	99.71 117	99.28 141	99.06 382	99.77 12	97.74 251	99.50 177	99.53 294	95.41 230	99.84 196	97.17 347	99.64 162	99.44 255

EPP-MVSNet		99.13 123	98.99 134	99.53 133	99.65 156	99.06 171	99.81 20	99.33 318	97.43 290	99.60 155	99.88 53	97.14 138	99.84 196	99.13 115	98.94 237	99.69 150

SSM_0407		99.13 123	99.03 117	99.43 173	99.62 174	98.88 209	99.51 187	99.50 175	98.14 180	99.37 212	99.85 81	96.85 155	99.83 214	99.19 104	99.25 197	99.60 191

testing3-2		97.84 302	97.70 294	98.24 353	99.53 216	95.37 413	99.55 161	98.67 435	98.46 128	99.27 242	99.34 356	86.58 434	99.83 214	99.32 84	98.63 261	99.52 222

testing11		97.50 351	97.10 364	98.71 295	99.20 323	96.91 360	99.29 315	98.82 413	97.89 227	98.21 391	98.40 439	85.63 442	99.83 214	98.45 224	98.04 303	99.37 267

thres100view900		97.76 316	97.45 324	98.69 297	99.72 111	97.86 302	99.59 120	98.74 425	97.93 223	99.26 247	98.62 430	91.75 369	99.83 214	93.22 436	98.18 296	98.37 419

tfpn200view9		97.72 326	97.38 337	98.72 292	99.69 127	97.96 293	99.50 198	98.73 431	97.83 237	99.17 268	98.45 437	91.67 373	99.83 214	93.22 436	98.18 296	98.37 419

test_prior				99.68 89	99.67 135	99.48 111		99.56 90					99.83 214			99.74 114

1314		98.68 209	98.54 214	99.11 227	98.89 386	98.65 240	99.27 325	99.49 188	96.89 340	97.99 401	99.56 282	97.72 120	99.83 214	97.74 297	99.27 194	98.84 319

thres400		97.77 315	97.38 337	98.92 252	99.69 127	97.96 293	99.50 198	98.73 431	97.83 237	99.17 268	98.45 437	91.67 373	99.83 214	93.22 436	98.18 296	98.96 313

casdiffmvs		99.13 123	98.98 137	99.56 122	99.65 156	99.16 155	99.56 146	99.50 175	98.33 145	99.41 201	99.86 74	95.92 207	99.83 214	99.45 68	99.16 204	99.70 147
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
SPE-MVS-test		99.49 33	99.48 22	99.54 125	99.78 70	99.30 138	99.89 2	99.58 78	98.56 118	99.73 97	99.69 223	98.55 81	99.82 223	99.69 35	99.85 94	99.48 239

MVS_Test		99.10 142	98.97 138	99.48 156	99.49 239	99.14 160	99.67 75	99.34 310	97.31 301	99.58 159	99.76 185	97.65 121	99.82 223	98.87 155	99.07 228	99.46 250

dp		97.75 320	97.80 278	97.59 403	99.10 350	93.71 444	99.32 304	98.88 406	96.48 372	99.08 284	99.55 285	92.67 347	99.82 223	96.52 378	98.58 265	99.24 283

RPSCF		98.22 242	98.62 204	96.99 419	99.82 53	91.58 459	99.72 53	99.44 254	96.61 360	99.66 126	99.89 42	95.92 207	99.82 223	97.46 325	99.10 225	99.57 209

PMMVS		98.80 196	98.62 204	99.34 187	99.27 305	98.70 236	98.76 430	99.31 332	97.34 298	99.21 257	99.07 395	97.20 137	99.82 223	98.56 212	98.87 247	99.52 222

UBG		97.85 298	97.48 318	98.95 246	99.25 312	97.64 313	99.24 341	98.74 425	97.90 226	98.64 359	98.20 447	88.65 415	99.81 228	98.27 242	98.40 275	99.42 257

EIA-MVS		99.18 104	99.09 104	99.45 165	99.49 239	99.18 152	99.67 75	99.53 125	97.66 261	99.40 206	99.44 324	98.10 107	99.81 228	98.94 143	99.62 165	99.35 269

Effi-MVS+		98.81 193	98.59 210	99.48 156	99.46 249	99.12 163	98.08 467	99.50 175	97.50 281	99.38 210	99.41 332	96.37 187	99.81 228	99.11 118	98.54 270	99.51 231

thres200		97.61 342	97.28 353	98.62 302	99.64 161	98.03 287	99.26 334	98.74 425	97.68 258	99.09 282	98.32 443	91.66 375	99.81 228	92.88 441	98.22 291	98.03 438

tpmvs		97.98 279	98.02 256	97.84 386	99.04 364	94.73 426	99.31 308	99.20 359	96.10 403	98.76 339	99.42 328	94.94 251	99.81 228	96.97 357	98.45 274	98.97 311

casdiffmvs_mvg		99.15 115	99.02 125	99.55 124	99.66 148	99.09 165	99.64 95	99.56 90	98.26 155	99.45 185	99.87 66	96.03 200	99.81 228	99.54 51	99.15 207	99.73 123
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	98.81 193	99.37 44	97.12 416	99.60 191	91.75 458	98.61 443	99.44 254	99.35 25	99.83 64	99.85 81	98.70 69	99.81 228	99.02 132	99.91 46	99.81 79

viewmacassd2359aftdt		99.08 145	98.94 148	99.50 149	99.66 148	98.96 187	99.51 187	99.54 109	98.27 152	99.42 196	99.89 42	95.88 211	99.80 235	99.20 103	99.11 218	99.76 107

viewmanbaseed2359cas		99.18 104	99.07 109	99.50 149	99.62 174	99.01 177	99.50 198	99.52 130	98.25 160	99.68 115	99.82 115	96.93 153	99.80 235	99.15 114	99.11 218	99.70 147

IMVS_0403		98.86 180	98.89 160	98.78 287	99.55 208	96.93 355	99.58 130	99.44 254	98.05 205	99.68 115	99.80 148	96.81 161	99.80 235	98.15 254	98.92 240	99.60 191

DPM-MVS		98.95 169	98.71 187	99.66 91	99.63 165	99.55 96	98.64 442	99.10 371	97.93 223	99.42 196	99.55 285	98.67 72	99.80 235	95.80 395	99.68 156	99.61 188

DP-MVS Recon		99.12 131	98.95 146	99.65 95	99.74 100	99.70 60	99.27 325	99.57 85	96.40 379	99.42 196	99.68 231	98.75 60	99.80 235	97.98 271	99.72 148	99.44 255

MVS_111021_LR		99.41 59	99.33 52	99.65 95	99.77 78	99.51 107	98.94 412	99.85 9	98.82 89	99.65 135	99.74 195	98.51 84	99.80 235	98.83 168	99.89 68	99.64 178

viewmambaseed2359dif		99.01 162	98.90 156	99.32 193	99.58 195	98.51 259	99.33 301	99.54 109	97.85 233	99.44 190	99.85 81	96.01 201	99.79 241	99.41 70	99.13 211	99.67 160

CS-MVS		99.50 31	99.48 22	99.54 125	99.76 82	99.42 118	99.90 1	99.55 100	98.56 118	99.78 81	99.70 212	98.65 74	99.79 241	99.65 41	99.78 134	99.41 260

Fast-Effi-MVS+-dtu		98.77 202	98.83 174	98.60 303	99.41 264	96.99 350	99.52 177	99.49 188	98.11 189	99.24 249	99.34 356	96.96 152	99.79 241	97.95 273	99.45 179	99.02 306

baseline1		98.31 236	97.95 263	99.38 183	99.50 237	98.74 232	99.59 120	98.93 393	98.41 135	99.14 271	99.60 268	94.59 280	99.79 241	98.48 219	93.29 432	99.61 188

baseline		99.15 115	99.02 125	99.53 133	99.66 148	99.14 160	99.72 53	99.48 200	98.35 142	99.42 196	99.84 96	96.07 197	99.79 241	99.51 56	99.14 208	99.67 160

PVSNet_0	94.43 19	96.09 396	95.47 403	97.94 376	99.31 295	94.34 438	97.81 469	99.70 18	97.12 318	97.46 416	98.75 427	89.71 401	99.79 241	97.69 304	81.69 471	99.68 156

API-MVS		99.04 155	99.03 117	99.06 231	99.40 269	99.31 135	99.55 161	99.56 90	98.54 120	99.33 226	99.39 340	98.76 57	99.78 247	96.98 356	99.78 134	98.07 435

OMC-MVS		99.08 145	99.04 114	99.20 217	99.67 135	98.22 277	99.28 320	99.52 130	98.07 198	99.66 126	99.81 130	97.79 117	99.78 247	97.79 289	99.81 120	99.60 191

GeoE		98.85 189	98.62 204	99.53 133	99.61 185	99.08 168	99.80 25	99.51 152	97.10 322	99.31 228	99.78 172	95.23 242	99.77 249	98.21 246	99.03 231	99.75 109

alignmvs		98.81 193	98.56 213	99.58 116	99.43 257	99.42 118	99.51 187	98.96 391	98.61 113	99.35 221	98.92 417	94.78 263	99.77 249	99.35 76	98.11 301	99.54 215

tpm cat1		97.39 360	97.36 339	97.50 406	99.17 337	93.73 443	99.43 254	99.31 332	91.27 454	98.71 343	99.08 394	94.31 297	99.77 249	96.41 383	98.50 272	99.00 307

CostFormer		97.72 326	97.73 291	97.71 395	99.15 343	94.02 440	99.54 166	99.02 384	94.67 428	99.04 293	99.35 352	92.35 359	99.77 249	98.50 218	97.94 306	99.34 272

MGCFI-Net		99.01 162	98.85 170	99.50 149	99.42 259	99.26 144	99.82 16	99.48 200	98.60 115	99.28 236	98.81 422	97.04 147	99.76 253	99.29 91	97.87 310	99.47 245

test_241102_ONE					99.84 38	99.90 3		99.48 200	99.07 58	99.91 31	99.74 195	99.20 9	99.76 253

MDTV_nov1_ep13			98.32 228		99.11 347	94.44 434	99.27 325	98.74 425	97.51 280	99.40 206	99.62 261	94.78 263	99.76 253	97.59 309	98.81 254

viewdifsd2359ckpt09		99.01 162	98.87 164	99.40 177	99.62 174	98.79 228	99.44 248	99.51 152	97.76 247	99.35 221	99.69 223	96.42 185	99.75 256	98.97 140	99.11 218	99.66 165

sasdasda		99.02 158	98.86 167	99.51 144	99.42 259	99.32 131	99.80 25	99.48 200	98.63 110	99.31 228	98.81 422	97.09 143	99.75 256	99.27 95	97.90 307	99.47 245

canonicalmvs		99.02 158	98.86 167	99.51 144	99.42 259	99.32 131	99.80 25	99.48 200	98.63 110	99.31 228	98.81 422	97.09 143	99.75 256	99.27 95	97.90 307	99.47 245

Effi-MVS+-dtu		98.78 198	98.89 160	98.47 326	99.33 287	96.91 360	99.57 138	99.30 337	98.47 127	99.41 201	98.99 407	96.78 163	99.74 259	98.73 182	99.38 183	98.74 335

patchmatchnet-post											98.70 428	94.79 262	99.74 259

SCA		98.19 246	98.16 236	98.27 352	99.30 296	95.55 404	99.07 378	98.97 389	97.57 270	99.43 193	99.57 279	92.72 342	99.74 259	97.58 310	99.20 202	99.52 222

BH-untuned		98.42 225	98.36 224	98.59 304	99.49 239	96.70 368	99.27 325	99.13 368	97.24 308	98.80 334	99.38 343	95.75 218	99.74 259	97.07 352	99.16 204	99.33 273

BH-RMVSNet		98.41 227	98.08 248	99.40 177	99.41 264	98.83 222	99.30 310	98.77 421	97.70 256	98.94 311	99.65 244	92.91 337	99.74 259	96.52 378	99.55 172	99.64 178

MVS_111021_HR		99.41 59	99.32 54	99.66 91	99.72 111	99.47 113	98.95 410	99.85 9	98.82 89	99.54 170	99.73 201	98.51 84	99.74 259	98.91 149	99.88 76	99.77 100

test_post											65.99 482	94.65 278	99.73 265

XVG-ACMP-BASELINE		97.83 305	97.71 293	98.20 355	99.11 347	96.33 384	99.41 266	99.52 130	98.06 202	99.05 292	99.50 305	89.64 403	99.73 265	97.73 298	97.38 345	98.53 400

HyFIR lowres test		99.11 137	98.92 151	99.65 95	99.90 4	99.37 123	99.02 392	99.91 3	97.67 260	99.59 158	99.75 190	95.90 209	99.73 265	99.53 53	99.02 233	99.86 42

DeepMVS_CX				93.34 443	99.29 300	82.27 472		99.22 355	85.15 469	96.33 438	99.05 398	90.97 387	99.73 265	93.57 432	97.77 315	98.01 439

Patchmatch-test		97.93 285	97.65 299	98.77 288	99.18 329	97.07 339	99.03 389	99.14 367	96.16 394	98.74 340	99.57 279	94.56 282	99.72 269	93.36 434	99.11 218	99.52 222

LPG-MVS_test		98.22 242	98.13 241	98.49 319	99.33 287	97.05 341	99.58 130	99.55 100	97.46 283	99.24 249	99.83 102	92.58 349	99.72 269	98.09 259	97.51 331	98.68 353

LGP-MVS_train				98.49 319	99.33 287	97.05 341		99.55 100	97.46 283	99.24 249	99.83 102	92.58 349	99.72 269	98.09 259	97.51 331	98.68 353

BH-w/o		98.00 277	97.89 272	98.32 344	99.35 281	96.20 390	99.01 397	98.90 403	96.42 377	98.38 379	99.00 405	95.26 239	99.72 269	96.06 388	98.61 262	99.03 304

ACMP	97.20 11	98.06 262	97.94 265	98.45 329	99.37 277	97.01 348	99.44 248	99.49 188	97.54 276	98.45 376	99.79 165	91.95 365	99.72 269	97.91 275	97.49 336	98.62 383
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 272	97.90 268	98.40 337	99.23 316	96.80 366	99.70 58	99.60 67	97.12 318	98.18 393	99.70 212	91.73 371	99.72 269	98.39 229	97.45 338	98.68 353
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
viewdifsd2359ckpt13		99.06 150	98.93 150	99.45 165	99.63 165	98.96 187	99.50 198	99.51 152	97.83 237	99.28 236	99.80 148	96.68 169	99.71 275	99.05 127	99.12 216	99.68 156

test_post1							99.23 344				65.14 483	94.18 302	99.71 275	97.58 310

ADS-MVSNet		98.20 245	98.08 248	98.56 312	99.33 287	96.48 379	99.23 344	99.15 365	96.24 387	99.10 279	99.67 237	94.11 304	99.71 275	96.81 366	99.05 229	99.48 239

JIA-IIPM		97.50 351	97.02 367	98.93 250	98.73 412	97.80 304	99.30 310	98.97 389	91.73 453	98.91 314	94.86 471	95.10 246	99.71 275	97.58 310	97.98 304	99.28 277

EPMVS		97.82 308	97.65 299	98.35 341	98.88 387	95.98 394	99.49 215	94.71 478	97.57 270	99.26 247	99.48 314	92.46 356	99.71 275	97.87 279	99.08 227	99.35 269

TDRefinement		95.42 407	94.57 415	97.97 373	89.83 481	96.11 393	99.48 223	98.75 422	96.74 348	96.68 435	99.88 53	88.65 415	99.71 275	98.37 232	82.74 470	98.09 434

ACMM	97.58 5	98.37 233	98.34 226	98.48 321	99.41 264	97.10 335	99.56 146	99.45 245	98.53 121	99.04 293	99.85 81	93.00 333	99.71 275	98.74 180	97.45 338	98.64 374
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 282	97.77 284	98.57 308	99.59 193	96.61 375	99.45 241	99.08 374	98.21 168	98.88 319	99.80 148	88.66 414	99.70 282	98.58 206	97.72 316	99.39 263

CHOSEN 280x420		99.12 131	99.13 95	99.08 228	99.66 148	97.89 299	98.43 454	99.71 16	98.88 83	99.62 147	99.76 185	96.63 170	99.70 282	99.46 67	99.99 1	99.66 165

EC-MVSNet		99.44 50	99.39 40	99.58 116	99.56 204	99.49 109	99.88 4	99.58 78	98.38 137	99.73 97	99.69 223	98.20 103	99.70 282	99.64 43	99.82 117	99.54 215

PatchmatchNet		98.31 236	98.36 224	98.19 356	99.16 339	95.32 414	99.27 325	98.92 396	97.37 296	99.37 212	99.58 274	94.90 256	99.70 282	97.43 329	99.21 201	99.54 215
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 256	97.99 258	98.44 332	99.41 264	96.96 354	99.60 113	99.56 90	98.09 193	98.15 394	99.91 26	90.87 388	99.70 282	98.88 152	97.45 338	98.67 361
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 351	96.90 371	99.29 203	99.23 316	98.78 231	99.32 304	98.90 403	97.52 279	98.56 369	98.09 453	84.72 449	99.69 287	97.86 280	97.88 309	99.39 263

HQP_MVS		98.27 241	98.22 234	98.44 332	99.29 300	96.97 352	99.39 278	99.47 222	98.97 75	99.11 276	99.61 265	92.71 344	99.69 287	97.78 290	97.63 319	98.67 361

plane_prior5								99.47 222					99.69 287	97.78 290	97.63 319	98.67 361

D2MVS		98.41 227	98.50 217	98.15 361	99.26 308	96.62 374	99.40 274	99.61 60	97.71 253	98.98 303	99.36 349	96.04 199	99.67 290	98.70 185	97.41 343	98.15 431

IS-MVSNet		99.05 154	98.87 164	99.57 120	99.73 107	99.32 131	99.75 42	99.20 359	98.02 217	99.56 163	99.86 74	96.54 177	99.67 290	98.09 259	99.13 211	99.73 123

CLD-MVS		98.16 250	98.10 244	98.33 342	99.29 300	96.82 365	98.75 431	99.44 254	97.83 237	99.13 272	99.55 285	92.92 335	99.67 290	98.32 239	97.69 317	98.48 405
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 368	97.30 350	97.09 417	99.43 257	93.31 450	99.73 51	98.87 408	98.83 88	99.28 236	99.80 148	84.45 450	99.66 293	97.88 277	97.45 338	98.30 421

AUN-MVS		96.88 379	96.31 385	98.59 304	99.48 246	97.04 344	99.27 325	99.22 355	97.44 289	98.51 372	99.41 332	91.97 364	99.66 293	97.71 301	83.83 468	99.07 301

UniMVSNet_ETH3D		97.32 365	96.81 373	98.87 270	99.40 269	97.46 319	99.51 187	99.53 125	95.86 407	98.54 371	99.77 181	82.44 459	99.66 293	98.68 190	97.52 330	99.50 235

OPM-MVS		98.19 246	98.10 244	98.45 329	98.88 387	97.07 339	99.28 320	99.38 288	98.57 117	99.22 254	99.81 130	92.12 361	99.66 293	98.08 263	97.54 328	98.61 392
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 288	97.78 282	98.32 344	99.46 249	96.68 372	99.56 146	99.54 109	98.41 135	97.79 412	99.87 66	90.18 397	99.66 293	98.05 267	97.18 353	98.62 383

IMVS_0407		98.86 180	98.91 154	98.72 292	99.55 208	96.93 355	99.50 198	99.44 254	98.05 205	99.66 126	99.80 148	97.13 139	99.65 298	98.15 254	98.92 240	99.60 191

hse-mvs2		97.50 351	97.14 361	98.59 304	99.49 239	97.05 341	99.28 320	99.22 355	98.94 78	99.66 126	99.42 328	94.93 252	99.65 298	99.48 64	83.80 469	99.08 296

VPA-MVSNet		98.29 239	97.95 263	99.30 200	99.16 339	99.54 98	99.50 198	99.58 78	98.27 152	99.35 221	99.37 346	92.53 351	99.65 298	99.35 76	94.46 413	98.72 337

TR-MVS		97.76 316	97.41 335	98.82 279	99.06 359	97.87 300	98.87 420	98.56 439	96.63 359	98.68 351	99.22 380	92.49 352	99.65 298	95.40 406	97.79 314	98.95 315

reproduce_monomvs		97.89 292	97.87 273	97.96 375	99.51 225	95.45 409	99.60 113	99.25 349	99.17 36	98.85 328	99.49 308	89.29 406	99.64 302	99.35 76	96.31 370	98.78 323

gm-plane-assit					98.54 433	92.96 452			94.65 429		99.15 388		99.64 302	97.56 315

HQP4-MVS										98.66 352			99.64 302			98.64 374

HQP-MVS		98.02 272	97.90 268	98.37 340	99.19 326	96.83 363	98.98 403	99.39 280	98.24 162	98.66 352	99.40 336	92.47 353	99.64 302	97.19 344	97.58 324	98.64 374

PAPM		97.59 343	97.09 365	99.07 229	99.06 359	98.26 275	98.30 461	99.10 371	94.88 423	98.08 396	99.34 356	96.27 191	99.64 302	89.87 455	98.92 240	99.31 275

TAPA-MVS	97.07 15	97.74 322	97.34 344	98.94 248	99.70 122	97.53 316	99.25 336	99.51 152	91.90 452	99.30 232	99.63 256	98.78 53	99.64 302	88.09 462	99.87 79	99.65 171
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 231	98.09 247	99.24 213	99.26 308	99.32 131	99.56 146	99.55 100	97.45 286	98.71 343	99.83 102	93.23 328	99.63 308	98.88 152	96.32 369	98.76 329

ITE_SJBPF				98.08 364	99.29 300	96.37 382		98.92 396	98.34 143	98.83 329	99.75 190	91.09 385	99.62 309	95.82 393	97.40 344	98.25 425

LF4IMVS		97.52 348	97.46 323	97.70 396	98.98 375	95.55 404	99.29 315	98.82 413	98.07 198	98.66 352	99.64 250	89.97 398	99.61 310	97.01 353	96.68 359	97.94 446

tpm		97.67 337	97.55 308	98.03 366	99.02 366	95.01 421	99.43 254	98.54 441	96.44 375	99.12 274	99.34 356	91.83 368	99.60 311	97.75 296	96.46 365	99.48 239

tpm2		97.44 358	97.34 344	97.74 394	99.15 343	94.36 437	99.45 241	98.94 392	93.45 442	98.90 316	99.44 324	91.35 381	99.59 312	97.31 335	98.07 302	99.29 276

SSM_04072		99.06 150	98.96 142	99.35 186	99.62 174	98.88 209	99.25 336	99.47 222	98.05 205	99.37 212	99.81 130	96.85 155	99.58 313	98.98 135	99.25 197	99.60 191

SD_0403		97.55 345	97.53 312	97.62 399	99.61 185	93.64 447	99.72 53	99.44 254	98.03 214	98.62 364	99.39 340	96.06 198	99.57 314	87.88 464	99.01 234	99.66 165

baseline2		97.87 295	97.55 308	98.82 279	99.18 329	98.02 288	99.41 266	96.58 472	96.97 333	96.51 436	99.17 385	93.43 323	99.57 314	97.71 301	99.03 231	98.86 317

MS-PatchMatch		97.24 370	97.32 348	96.99 419	98.45 436	93.51 449	98.82 424	99.32 328	97.41 293	98.13 395	99.30 367	88.99 408	99.56 316	95.68 399	99.80 125	97.90 449

TinyColmap		97.12 373	96.89 372	97.83 387	99.07 357	95.52 407	98.57 446	98.74 425	97.58 269	97.81 411	99.79 165	88.16 422	99.56 316	95.10 411	97.21 351	98.39 417

USDC		97.34 363	97.20 358	97.75 392	99.07 357	95.20 416	98.51 451	99.04 381	97.99 218	98.31 383	99.86 74	89.02 407	99.55 318	95.67 400	97.36 346	98.49 404

MSLP-MVS++		99.46 42	99.47 24	99.44 170	99.60 191	99.16 155	99.41 266	99.71 16	98.98 72	99.45 185	99.78 172	99.19 11	99.54 319	99.28 92	99.84 102	99.63 183

UWE-MVS-28		97.36 361	97.24 357	97.75 392	98.84 396	94.44 434	99.24 341	97.58 461	97.98 219	99.00 300	99.00 405	91.35 381	99.53 320	93.75 429	98.39 276	99.27 281

TAMVS		99.12 131	99.08 105	99.24 213	99.46 249	98.55 251	99.51 187	99.46 234	98.09 193	99.45 185	99.82 115	98.34 97	99.51 321	98.70 185	98.93 238	99.67 160

EPNet_dtu		98.03 270	97.96 261	98.23 354	98.27 439	95.54 406	99.23 344	98.75 422	99.02 62	97.82 410	99.71 208	96.11 196	99.48 322	93.04 439	99.65 161	99.69 150
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 383	96.22 387	97.97 373	97.00 461	96.28 386	98.66 440	99.03 383	96.61 360	96.93 433	99.79 165	87.20 431	99.47 323	96.65 376	94.13 420	98.16 430

EG-PatchMatch MVS		95.97 398	95.69 399	96.81 426	97.78 446	92.79 453	99.16 359	98.93 393	96.16 394	94.08 455	99.22 380	82.72 457	99.47 323	95.67 400	97.50 333	98.17 429

myMVS_eth3d28		97.69 331	97.34 344	98.73 290	99.27 305	97.52 317	99.33 301	98.78 420	98.03 214	98.82 331	98.49 435	86.64 433	99.46 325	98.44 225	98.24 290	99.23 284

MVP-Stereo		97.81 310	97.75 289	97.99 372	97.53 450	96.60 376	98.96 407	98.85 410	97.22 310	97.23 423	99.36 349	95.28 236	99.46 325	95.51 402	99.78 134	97.92 448
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 217	98.67 191	98.30 346	99.35 281	95.59 403	99.50 198	99.55 100	98.60 115	99.39 208	99.83 102	94.48 288	99.45 327	98.75 179	98.56 268	99.85 46

test-LLR		98.06 262	97.90 268	98.55 314	98.79 400	97.10 335	98.67 437	97.75 457	97.34 298	98.61 365	98.85 419	94.45 290	99.45 327	97.25 338	99.38 183	99.10 291

TESTMET0.1,1		97.55 345	97.27 356	98.40 337	98.93 380	96.53 377	98.67 437	97.61 460	96.96 334	98.64 359	99.28 371	88.63 417	99.45 327	97.30 336	99.38 183	99.21 286

test-mter		97.49 356	97.13 363	98.55 314	98.79 400	97.10 335	98.67 437	97.75 457	96.65 355	98.61 365	98.85 419	88.23 421	99.45 327	97.25 338	99.38 183	99.10 291

mvs_anonymous		99.03 157	98.99 134	99.16 221	99.38 274	98.52 257	99.51 187	99.38 288	97.79 243	99.38 210	99.81 130	97.30 131	99.45 327	99.35 76	98.99 235	99.51 231

tfpnnormal		97.84 302	97.47 321	98.98 241	99.20 323	99.22 149	99.64 95	99.61 60	96.32 381	98.27 387	99.70 212	93.35 327	99.44 332	95.69 398	95.40 396	98.27 423

v7n		97.87 295	97.52 313	98.92 252	98.76 410	98.58 249	99.84 12	99.46 234	96.20 390	98.91 314	99.70 212	94.89 257	99.44 332	96.03 389	93.89 425	98.75 331

jajsoiax		98.43 224	98.28 231	98.88 266	98.60 428	98.43 268	99.82 16	99.53 125	98.19 170	98.63 361	99.80 148	93.22 330	99.44 332	99.22 100	97.50 333	98.77 327

mvs_tets		98.40 230	98.23 233	98.91 256	98.67 421	98.51 259	99.66 82	99.53 125	98.19 170	98.65 358	99.81 130	92.75 339	99.44 332	99.31 86	97.48 337	98.77 327

sc_t1		95.75 402	95.05 409	97.87 382	98.83 397	94.61 431	99.21 350	99.45 245	87.45 465	97.97 403	99.85 81	81.19 464	99.43 336	98.27 242	93.20 434	99.57 209

Vis-MVSNet (Re-imp)		98.87 177	98.72 185	99.31 195	99.71 117	98.88 209	99.80 25	99.44 254	97.91 225	99.36 218	99.78 172	95.49 228	99.43 336	97.91 275	99.11 218	99.62 186

OPU-MVS				99.64 101	99.56 204	99.72 56	99.60 113				99.70 212	99.27 7	99.42 338	98.24 245	99.80 125	99.79 92

Anonymous20231211		97.88 293	97.54 311	98.90 258	99.71 117	98.53 253	99.48 223	99.57 85	94.16 433	98.81 332	99.68 231	93.23 328	99.42 338	98.84 165	94.42 415	98.76 329

ttmdpeth		97.80 312	97.63 303	98.29 347	98.77 408	97.38 322	99.64 95	99.36 298	98.78 98	96.30 439	99.58 274	92.34 360	99.39 340	98.36 234	95.58 391	98.10 433

VPNet		97.84 302	97.44 329	99.01 237	99.21 321	98.94 197	99.48 223	99.57 85	98.38 137	99.28 236	99.73 201	88.89 409	99.39 340	99.19 104	93.27 433	98.71 339

nrg030		98.64 214	98.42 221	99.28 207	99.05 362	99.69 63	99.81 20	99.46 234	98.04 212	99.01 296	99.82 115	96.69 167	99.38 342	99.34 81	94.59 412	98.78 323

GA-MVS		97.85 298	97.47 321	99.00 239	99.38 274	97.99 290	98.57 446	99.15 365	97.04 329	98.90 316	99.30 367	89.83 400	99.38 342	96.70 371	98.33 280	99.62 186

UniMVSNet (Re)		98.29 239	98.00 257	99.13 226	99.00 369	99.36 126	99.49 215	99.51 152	97.95 221	98.97 305	99.13 390	96.30 190	99.38 342	98.36 234	93.34 431	98.66 370

FIs		98.78 198	98.63 199	99.23 215	99.18 329	99.54 98	99.83 15	99.59 73	98.28 150	98.79 336	99.81 130	96.75 165	99.37 345	99.08 124	96.38 367	98.78 323

PS-MVSNAJss		98.92 171	98.92 151	98.90 258	98.78 403	98.53 253	99.78 32	99.54 109	98.07 198	99.00 300	99.76 185	99.01 20	99.37 345	99.13 115	97.23 350	98.81 320

CDS-MVSNet		99.09 143	99.03 117	99.25 210	99.42 259	98.73 233	99.45 241	99.46 234	98.11 189	99.46 184	99.77 181	98.01 112	99.37 345	98.70 185	98.92 240	99.66 165
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 402	95.16 407	97.51 405	99.30 296	93.69 445	98.88 418	95.78 473	85.09 470	98.78 337	92.65 473	91.29 383	99.37 345	94.85 416	99.85 94	99.46 250

v1192		97.81 310	97.44 329	98.91 256	98.88 387	98.68 237	99.51 187	99.34 310	96.18 392	99.20 260	99.34 356	94.03 308	99.36 349	95.32 408	95.18 400	98.69 348

EI-MVSNet		98.67 210	98.67 191	98.68 298	99.35 281	97.97 291	99.50 198	99.38 288	96.93 339	99.20 260	99.83 102	97.87 114	99.36 349	98.38 230	97.56 326	98.71 339

MVSTER		98.49 219	98.32 228	99.00 239	99.35 281	99.02 175	99.54 166	99.38 288	97.41 293	99.20 260	99.73 201	93.86 316	99.36 349	98.87 155	97.56 326	98.62 383

gg-mvs-nofinetune		96.17 394	95.32 406	98.73 290	98.79 400	98.14 281	99.38 283	94.09 479	91.07 457	98.07 399	91.04 477	89.62 404	99.35 352	96.75 368	99.09 226	98.68 353

pm-mvs1		97.68 334	97.28 353	98.88 266	99.06 359	98.62 245	99.50 198	99.45 245	96.32 381	97.87 408	99.79 165	92.47 353	99.35 352	97.54 317	93.54 429	98.67 361

OurMVSNet-221017-0		97.88 293	97.77 284	98.19 356	98.71 416	96.53 377	99.88 4	99.00 386	97.79 243	98.78 337	99.94 6	91.68 372	99.35 352	97.21 340	96.99 357	98.69 348

EGC-MVSNET		82.80 441	77.86 447	97.62 399	97.91 443	96.12 392	99.33 301	99.28 343	8.40 485	25.05 486	99.27 374	84.11 451	99.33 355	89.20 457	98.22 291	97.42 459

pmmvs6		96.53 386	96.09 391	97.82 389	98.69 419	95.47 408	99.37 285	99.47 222	93.46 441	97.41 417	99.78 172	87.06 432	99.33 355	96.92 363	92.70 441	98.65 372

V42		98.06 262	97.79 279	98.86 273	98.98 375	98.84 219	99.69 62	99.34 310	96.53 367	99.30 232	99.37 346	94.67 275	99.32 357	97.57 314	94.66 410	98.42 413

lessismore_v0				97.79 391	98.69 419	95.44 411		94.75 477		95.71 445	99.87 66	88.69 413	99.32 357	95.89 392	94.93 407	98.62 383

OpenMVS_ROB	92.34 20	94.38 420	93.70 426	96.41 431	97.38 452	93.17 451	99.06 382	98.75 422	86.58 468	94.84 452	98.26 445	81.53 462	99.32 357	89.01 458	97.87 310	96.76 462

v8		97.95 284	97.63 303	98.93 250	98.95 379	98.81 227	99.80 25	99.41 270	96.03 404	99.10 279	99.42 328	94.92 254	99.30 360	96.94 360	94.08 422	98.66 370

v1921920		97.80 312	97.45 324	98.84 277	98.80 399	98.53 253	99.52 177	99.34 310	96.15 396	99.24 249	99.47 317	93.98 310	99.29 361	95.40 406	95.13 402	98.69 348

anonymousdsp		98.44 223	98.28 231	98.94 248	98.50 434	98.96 187	99.77 34	99.50 175	97.07 324	98.87 322	99.77 181	94.76 267	99.28 362	98.66 192	97.60 322	98.57 398

MVSFormer		99.17 109	99.12 97	99.29 203	99.51 225	98.94 197	99.88 4	99.46 234	97.55 273	99.80 74	99.65 244	97.39 125	99.28 362	99.03 130	99.85 94	99.65 171

test_djsdf		98.67 210	98.57 211	98.98 241	98.70 417	98.91 204	99.88 4	99.46 234	97.55 273	99.22 254	99.88 53	95.73 219	99.28 362	99.03 130	97.62 321	98.75 331

VortexMVS		98.67 210	98.66 194	98.68 298	99.62 174	97.96 293	99.59 120	99.41 270	98.13 183	99.31 228	99.70 212	95.48 229	99.27 365	99.40 71	97.32 347	98.79 321

SSC-MVS3.2		97.34 363	97.15 360	97.93 377	99.02 366	95.76 400	99.48 223	99.58 78	97.62 265	99.09 282	99.53 294	87.95 424	99.27 365	96.42 381	95.66 389	98.75 331

cascas		97.69 331	97.43 333	98.48 321	98.60 428	97.30 324	98.18 465	99.39 280	92.96 446	98.41 377	98.78 426	93.77 319	99.27 365	98.16 252	98.61 262	98.86 317

v144192		97.92 288	97.60 306	98.87 270	98.83 397	98.65 240	99.55 161	99.34 310	96.20 390	99.32 227	99.40 336	94.36 292	99.26 368	96.37 385	95.03 404	98.70 344

dmvs_re		98.08 260	98.16 236	97.85 384	99.55 208	94.67 430	99.70 58	98.92 396	98.15 175	99.06 290	99.35 352	93.67 322	99.25 369	97.77 293	97.25 349	99.64 178

v2v482		98.06 262	97.77 284	98.92 252	98.90 385	98.82 225	99.57 138	99.36 298	96.65 355	99.19 263	99.35 352	94.20 299	99.25 369	97.72 300	94.97 405	98.69 348

v1240		97.69 331	97.32 348	98.79 285	98.85 394	98.43 268	99.48 223	99.36 298	96.11 399	99.27 242	99.36 349	93.76 320	99.24 371	94.46 420	95.23 399	98.70 344

FE-MVSNET3		98.09 257	97.82 277	98.89 262	98.70 417	98.90 207	98.57 446	99.47 222	96.78 346	98.87 322	99.05 398	94.75 268	99.23 372	97.45 327	96.74 358	98.53 400

WBMVS		97.74 322	97.50 316	98.46 327	99.24 314	97.43 320	99.21 350	99.42 267	97.45 286	98.96 307	99.41 332	88.83 410	99.23 372	98.94 143	96.02 375	98.71 339

v1144		97.98 279	97.69 295	98.85 276	98.87 390	98.66 239	99.54 166	99.35 305	96.27 385	99.23 253	99.35 352	94.67 275	99.23 372	96.73 369	95.16 401	98.68 353

v10		97.85 298	97.52 313	98.86 273	98.99 372	98.67 238	99.75 42	99.41 270	95.70 408	98.98 303	99.41 332	94.75 268	99.23 372	96.01 391	94.63 411	98.67 361

WR-MVS_H		98.13 253	97.87 273	98.90 258	99.02 366	98.84 219	99.70 58	99.59 73	97.27 304	98.40 378	99.19 384	95.53 226	99.23 372	98.34 236	93.78 427	98.61 392

miper_enhance_ethall		98.16 250	98.08 248	98.41 335	98.96 378	97.72 308	98.45 453	99.32 328	96.95 336	98.97 305	99.17 385	97.06 146	99.22 377	97.86 280	95.99 378	98.29 422

GG-mvs-BLEND				98.45 329	98.55 432	98.16 279	99.43 254	93.68 480		97.23 423	98.46 436	89.30 405	99.22 377	95.43 405	98.22 291	97.98 444

FC-MVSNet-test		98.75 203	98.62 204	99.15 225	99.08 356	99.45 115	99.86 11	99.60 67	98.23 165	98.70 349	99.82 115	96.80 162	99.22 377	99.07 125	96.38 367	98.79 321

UniMVSNet_NR-MVSNet		98.22 242	97.97 260	98.96 244	98.92 382	98.98 180	99.48 223	99.53 125	97.76 247	98.71 343	99.46 321	96.43 184	99.22 377	98.57 209	92.87 439	98.69 348

DU-MVS		98.08 260	97.79 279	98.96 244	98.87 390	98.98 180	99.41 266	99.45 245	97.87 229	98.71 343	99.50 305	94.82 259	99.22 377	98.57 209	92.87 439	98.68 353

cl____		98.01 275	97.84 276	98.55 314	99.25 312	97.97 291	98.71 435	99.34 310	96.47 374	98.59 368	99.54 290	95.65 222	99.21 382	97.21 340	95.77 384	98.46 410

WR-MVS		98.06 262	97.73 291	99.06 231	98.86 393	99.25 146	99.19 355	99.35 305	97.30 302	98.66 352	99.43 326	93.94 311	99.21 382	98.58 206	94.28 417	98.71 339

test_0402		96.64 384	96.24 386	97.85 384	98.85 394	96.43 381	99.44 248	99.26 347	93.52 439	96.98 431	99.52 298	88.52 418	99.20 384	92.58 446	97.50 333	97.93 447

icg_test_0407_2		98.79 197	98.86 167	98.57 308	99.55 208	96.93 355	99.07 378	99.44 254	98.05 205	99.66 126	99.80 148	97.13 139	99.18 385	98.15 254	98.92 240	99.60 191

SixPastTwentyTwo		97.50 351	97.33 347	98.03 366	98.65 422	96.23 389	99.77 34	98.68 434	97.14 315	97.90 406	99.93 10	90.45 391	99.18 385	97.00 354	96.43 366	98.67 361

cl22		97.85 298	97.64 302	98.48 321	99.09 353	97.87 300	98.60 445	99.33 318	97.11 321	98.87 322	99.22 380	92.38 358	99.17 387	98.21 246	95.99 378	98.42 413

tt0320		95.71 404	95.07 408	97.62 399	99.05 362	95.02 420	99.25 336	99.52 130	86.81 466	97.97 403	99.72 205	83.58 454	99.15 388	96.38 384	93.35 430	98.68 353

WB-MVSnew		97.65 339	97.65 299	97.63 398	98.78 403	97.62 314	99.13 365	98.33 445	97.36 297	99.07 285	98.94 413	95.64 223	99.15 388	92.95 440	98.68 260	96.12 469

IterMVS-SCA-FT		97.82 308	97.75 289	98.06 365	99.57 200	96.36 383	99.02 392	99.49 188	97.18 312	98.71 343	99.72 205	92.72 342	99.14 390	97.44 328	95.86 383	98.67 361

pmmvs5		97.52 348	97.30 350	98.16 358	98.57 431	96.73 367	99.27 325	98.90 403	96.14 397	98.37 380	99.53 294	91.54 378	99.14 390	97.51 319	95.87 382	98.63 381

v148		97.79 314	97.55 308	98.50 318	98.74 411	97.72 308	99.54 166	99.33 318	96.26 386	98.90 316	99.51 302	94.68 274	99.14 390	97.83 284	93.15 436	98.63 381

IMVS_0404		98.53 218	98.52 216	98.55 314	99.55 208	96.93 355	99.20 353	99.44 254	98.05 205	98.96 307	99.80 148	94.66 277	99.13 393	98.15 254	98.92 240	99.60 191

miper_ehance_all_eth		98.18 248	98.10 244	98.41 335	99.23 316	97.72 308	98.72 434	99.31 332	96.60 363	98.88 319	99.29 369	97.29 132	99.13 393	97.60 308	95.99 378	98.38 418

NR-MVSNet		97.97 282	97.61 305	99.02 236	98.87 390	99.26 144	99.47 233	99.42 267	97.63 263	97.08 429	99.50 305	95.07 247	99.13 393	97.86 280	93.59 428	98.68 353

IterMVS		97.83 305	97.77 284	98.02 368	99.58 195	96.27 387	99.02 392	99.48 200	97.22 310	98.71 343	99.70 212	92.75 339	99.13 393	97.46 325	96.00 377	98.67 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 421	94.90 411	91.84 448	97.24 456	80.01 478	98.52 450	99.48 200	89.01 462	91.99 465	99.67 237	85.67 441	99.13 393	95.44 404	97.03 356	96.39 466
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 267	97.96 261	98.33 342	99.26 308	97.38 322	98.56 449	99.31 332	96.65 355	98.88 319	99.52 298	96.58 174	99.12 398	97.39 331	95.53 394	98.47 407

pmmvs4		98.13 253	97.90 268	98.81 282	98.61 427	98.87 213	98.99 400	99.21 358	96.44 375	99.06 290	99.58 274	95.90 209	99.11 399	97.18 346	96.11 374	98.46 410

TransMVSNet (Re)		97.15 372	96.58 378	98.86 273	99.12 345	98.85 217	99.49 215	98.91 401	95.48 411	97.16 427	99.80 148	93.38 324	99.11 399	94.16 426	91.73 446	98.62 383

ambc				93.06 446	92.68 477	82.36 471	98.47 452	98.73 431		95.09 450	97.41 460	55.55 477	99.10 401	96.42 381	91.32 447	97.71 450

Baseline_NR-MVSNet		97.76 316	97.45 324	98.68 298	99.09 353	98.29 273	99.41 266	98.85 410	95.65 409	98.63 361	99.67 237	94.82 259	99.10 401	98.07 266	92.89 438	98.64 374

test_vis3_rt		87.04 437	85.81 440	90.73 452	93.99 476	81.96 473	99.76 37	90.23 487	92.81 448	81.35 475	91.56 475	40.06 483	99.07 403	94.27 423	88.23 462	91.15 475

CP-MVSNet		98.09 257	97.78 282	99.01 237	98.97 377	99.24 147	99.67 75	99.46 234	97.25 306	98.48 375	99.64 250	93.79 318	99.06 404	98.63 196	94.10 421	98.74 335

PS-CasMVS		97.93 285	97.59 307	98.95 246	98.99 372	99.06 171	99.68 72	99.52 130	97.13 316	98.31 383	99.68 231	92.44 357	99.05 405	98.51 217	94.08 422	98.75 331

K. test v3		97.10 374	96.79 374	98.01 369	98.72 414	96.33 384	99.87 8	97.05 464	97.59 267	96.16 441	99.80 148	88.71 412	99.04 406	96.69 372	96.55 364	98.65 372

new_pmnet		96.38 390	96.03 392	97.41 408	98.13 442	95.16 419	99.05 384	99.20 359	93.94 434	97.39 420	98.79 425	91.61 377	99.04 406	90.43 453	95.77 384	98.05 437

DIV-MVS_self_test		98.01 275	97.85 275	98.48 321	99.24 314	97.95 296	98.71 435	99.35 305	96.50 368	98.60 367	99.54 290	95.72 220	99.03 408	97.21 340	95.77 384	98.46 410

IterMVS-LS		98.46 222	98.42 221	98.58 307	99.59 193	98.00 289	99.37 285	99.43 265	96.94 338	99.07 285	99.59 270	97.87 114	99.03 408	98.32 239	95.62 390	98.71 339
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 339	97.68 296	97.55 404	98.62 425	94.97 422	98.84 422	99.30 337	96.83 345	98.19 392	99.34 356	97.01 150	99.02 410	95.00 414	96.01 376	98.64 374

Patchmtry		97.75 320	97.40 336	98.81 282	99.10 350	98.87 213	99.11 374	99.33 318	94.83 425	98.81 332	99.38 343	94.33 295	99.02 410	96.10 387	95.57 392	98.53 400

N_pmnet		94.95 415	95.83 397	92.31 447	98.47 435	79.33 479	99.12 368	92.81 485	93.87 435	97.68 413	99.13 390	93.87 315	99.01 412	91.38 450	96.19 372	98.59 396

CR-MVSNet		98.17 249	97.93 266	98.87 270	99.18 329	98.49 262	99.22 348	99.33 318	96.96 334	99.56 163	99.38 343	94.33 295	99.00 413	94.83 417	98.58 265	99.14 288

c3_l		98.12 255	98.04 253	98.38 339	99.30 296	97.69 312	98.81 425	99.33 318	96.67 353	98.83 329	99.34 356	97.11 142	98.99 414	97.58 310	95.34 397	98.48 405

test0.0.03 1		97.71 329	97.42 334	98.56 312	98.41 438	97.82 303	98.78 428	98.63 437	97.34 298	98.05 400	98.98 409	94.45 290	98.98 415	95.04 413	97.15 354	98.89 316

PatchT		97.03 376	96.44 382	98.79 285	98.99 372	98.34 272	99.16 359	99.07 377	92.13 451	99.52 174	97.31 464	94.54 285	98.98 415	88.54 460	98.73 257	99.03 304

GBi-Net		97.68 334	97.48 318	98.29 347	99.51 225	97.26 328	99.43 254	99.48 200	96.49 369	99.07 285	99.32 364	90.26 393	98.98 415	97.10 348	96.65 360	98.62 383

test1		97.68 334	97.48 318	98.29 347	99.51 225	97.26 328	99.43 254	99.48 200	96.49 369	99.07 285	99.32 364	90.26 393	98.98 415	97.10 348	96.65 360	98.62 383

FMVSNet3		98.03 270	97.76 288	98.84 277	99.39 272	98.98 180	99.40 274	99.38 288	96.67 353	99.07 285	99.28 371	92.93 334	98.98 415	97.10 348	96.65 360	98.56 399

FMVSNet2		97.72 326	97.36 339	98.80 284	99.51 225	98.84 219	99.45 241	99.42 267	96.49 369	98.86 327	99.29 369	90.26 393	98.98 415	96.44 380	96.56 363	98.58 397

FMVSNet1		96.84 380	96.36 384	98.29 347	99.32 294	97.26 328	99.43 254	99.48 200	95.11 416	98.55 370	99.32 364	83.95 452	98.98 415	95.81 394	96.26 371	98.62 383

ppachtmachnet_test		97.49 356	97.45 324	97.61 402	98.62 425	95.24 415	98.80 426	99.46 234	96.11 399	98.22 390	99.62 261	96.45 182	98.97 422	93.77 428	95.97 381	98.61 392

TranMVSNet+NR-MVSNet		97.93 285	97.66 298	98.76 289	98.78 403	98.62 245	99.65 88	99.49 188	97.76 247	98.49 374	99.60 268	94.23 298	98.97 422	98.00 270	92.90 437	98.70 344

MVStest1		96.08 397	95.48 402	97.89 381	98.93 380	96.70 368	99.56 146	99.35 305	92.69 449	91.81 466	99.46 321	89.90 399	98.96 424	95.00 414	92.61 442	98.00 442

tt0320-xc		95.31 410	94.59 414	97.45 407	98.92 382	94.73 426	99.20 353	99.31 332	86.74 467	97.23 423	99.72 205	81.14 465	98.95 425	97.08 351	91.98 445	98.67 361

test_method		91.10 432	91.36 434	90.31 453	95.85 464	73.72 486	94.89 475	99.25 349	68.39 477	95.82 444	99.02 403	80.50 466	98.95 425	93.64 431	94.89 409	98.25 425

ADS-MVSNet2		98.02 272	98.07 251	97.87 382	99.33 287	95.19 417	99.23 344	99.08 374	96.24 387	99.10 279	99.67 237	94.11 304	98.93 427	96.81 366	99.05 229	99.48 239

ET-MVSNet_ETH3D		96.49 387	95.64 401	99.05 233	99.53 216	98.82 225	98.84 422	97.51 462	97.63 263	84.77 471	99.21 383	92.09 362	98.91 428	98.98 135	92.21 444	99.41 260

miper_lstm_enhance		98.00 277	97.91 267	98.28 351	99.34 286	97.43 320	98.88 418	99.36 298	96.48 372	98.80 334	99.55 285	95.98 202	98.91 428	97.27 337	95.50 395	98.51 403

MonoMVSNet		98.38 231	98.47 219	98.12 363	98.59 430	96.19 391	99.72 53	98.79 419	97.89 227	99.44 190	99.52 298	96.13 195	98.90 430	98.64 194	97.54 328	99.28 277

PEN-MVS		97.76 316	97.44 329	98.72 292	98.77 408	98.54 252	99.78 32	99.51 152	97.06 326	98.29 386	99.64 250	92.63 348	98.89 431	98.09 259	93.16 435	98.72 337

testing3		97.28 366	96.76 375	98.82 279	99.37 277	98.07 286	99.45 241	99.36 298	97.56 272	97.89 407	98.95 412	83.70 453	98.82 432	96.03 389	98.56 268	99.58 206

testgi		97.65 339	97.50 316	98.13 362	99.36 280	96.45 380	99.42 261	99.48 200	97.76 247	97.87 408	99.45 323	91.09 385	98.81 433	94.53 419	98.52 271	99.13 290

testf1		90.42 435	90.68 436	89.65 456	97.78 446	73.97 484	99.13 365	98.81 415	89.62 459	91.80 467	98.93 414	62.23 475	98.80 434	86.61 470	91.17 448	96.19 467

APD_test2		90.42 435	90.68 436	89.65 456	97.78 446	73.97 484	99.13 365	98.81 415	89.62 459	91.80 467	98.93 414	62.23 475	98.80 434	86.61 470	91.17 448	96.19 467

MIMVSNet		97.73 324	97.45 324	98.57 308	99.45 255	97.50 318	99.02 392	98.98 388	96.11 399	99.41 201	99.14 389	90.28 392	98.74 436	95.74 396	98.93 238	99.47 245

LCM-MVSNet-Re		97.83 305	98.15 238	96.87 425	99.30 296	92.25 456	99.59 120	98.26 446	97.43 290	96.20 440	99.13 390	96.27 191	98.73 437	98.17 251	98.99 235	99.64 178

Syy-MVS		97.09 375	97.14 361	96.95 422	99.00 369	92.73 454	99.29 315	99.39 280	97.06 326	97.41 417	98.15 448	93.92 313	98.68 438	91.71 448	98.34 278	99.45 253

myMVS_eth3d		96.89 378	96.37 383	98.43 334	99.00 369	97.16 332	99.29 315	99.39 280	97.06 326	97.41 417	98.15 448	83.46 455	98.68 438	95.27 409	98.34 278	99.45 253

DTE-MVSNet		97.51 350	97.19 359	98.46 327	98.63 424	98.13 282	99.84 12	99.48 200	96.68 352	97.97 403	99.67 237	92.92 335	98.56 440	96.88 365	92.60 443	98.70 344

PC_three_1452									98.18 173	99.84 56	99.70 212	99.31 3	98.52 441	98.30 241	99.80 125	99.81 79

mvsany_test3		93.77 424	93.45 427	94.74 438	95.78 465	88.01 464	99.64 95	98.25 447	98.28 150	94.31 453	97.97 455	68.89 471	98.51 442	97.50 320	90.37 453	97.71 450

UnsupCasMVSNet_bld		93.53 425	92.51 431	96.58 430	97.38 452	93.82 441	98.24 462	99.48 200	91.10 456	93.10 460	96.66 466	74.89 469	98.37 443	94.03 427	87.71 463	97.56 456

Anonymous20240521		96.20 393	95.89 396	97.13 415	97.72 449	94.96 423	99.79 31	99.29 341	93.01 445	97.20 426	99.03 401	89.69 402	98.36 444	91.16 451	96.13 373	98.07 435

test_f		91.90 431	91.26 435	93.84 441	95.52 469	85.92 466	99.69 62	98.53 442	95.31 413	93.87 456	96.37 468	55.33 478	98.27 445	95.70 397	90.98 451	97.32 460

MDA-MVSNet_test_wron		95.45 406	94.60 413	98.01 369	98.16 441	97.21 331	99.11 374	99.24 352	93.49 440	80.73 477	98.98 409	93.02 332	98.18 446	94.22 425	94.45 414	98.64 374

UnsupCasMVSNet_eth		96.44 388	96.12 389	97.40 409	98.65 422	95.65 401	99.36 291	99.51 152	97.13 316	96.04 443	98.99 407	88.40 419	98.17 447	96.71 370	90.27 454	98.40 416

KD-MVS_2432*1600		94.62 416	93.72 424	97.31 410	97.19 458	95.82 398	98.34 457	99.20 359	95.00 421	97.57 414	98.35 441	87.95 424	98.10 448	92.87 442	77.00 475	98.01 439

miper_refine_blended		94.62 416	93.72 424	97.31 410	97.19 458	95.82 398	98.34 457	99.20 359	95.00 421	97.57 414	98.35 441	87.95 424	98.10 448	92.87 442	77.00 475	98.01 439

YYNet1		95.36 408	94.51 416	97.92 378	97.89 444	97.10 335	99.10 376	99.23 353	93.26 443	80.77 476	99.04 400	92.81 338	98.02 450	94.30 421	94.18 419	98.64 374

EU-MVSNet		97.98 279	98.03 254	97.81 390	98.72 414	96.65 373	99.66 82	99.66 32	98.09 193	98.35 381	99.82 115	95.25 240	98.01 451	97.41 330	95.30 398	98.78 323

Gipuma		90.99 433	90.15 438	93.51 442	98.73 412	90.12 462	93.98 476	99.45 245	79.32 473	92.28 463	94.91 470	69.61 470	97.98 452	87.42 466	95.67 388	92.45 473
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 409	94.73 412	97.15 413	95.53 468	95.94 396	99.35 296	99.10 371	95.13 414	93.55 458	97.54 459	88.15 423	97.91 453	94.58 418	89.69 459	97.61 453

PM-MVS		92.96 428	92.23 432	95.14 437	95.61 466	89.98 463	99.37 285	98.21 450	94.80 426	95.04 451	97.69 456	65.06 472	97.90 454	94.30 421	89.98 456	97.54 457

MDA-MVSNet-bldmvs		94.96 414	93.98 421	97.92 378	98.24 440	97.27 326	99.15 362	99.33 318	93.80 436	80.09 478	99.03 401	88.31 420	97.86 455	93.49 433	94.36 416	98.62 383

Patchmatch-RL test		95.84 400	95.81 398	95.95 435	95.61 466	90.57 461	98.24 462	98.39 443	95.10 418	95.20 448	98.67 429	94.78 263	97.77 456	96.28 386	90.02 455	99.51 231

Anonymous20231206		96.22 391	96.03 392	96.79 427	97.31 455	94.14 439	99.63 101	99.08 374	96.17 393	97.04 430	99.06 397	93.94 311	97.76 457	86.96 468	95.06 403	98.47 407

SD-MVS		99.41 59	99.52 14	99.05 233	99.74 100	99.68 64	99.46 237	99.52 130	99.11 47	99.88 43	99.91 26	99.43 1	97.70 458	98.72 183	99.93 33	99.77 100
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		97.25 368	97.35 341	96.95 422	97.84 445	93.61 448	99.57 138	96.63 470	96.13 398	98.87 322	98.61 432	94.59 280	97.70 458	95.08 412	98.86 248	99.55 213

FE-MVSNET2		95.10 411	94.44 417	97.08 418	95.08 471	95.97 395	99.51 187	99.37 296	95.02 420	94.10 454	97.57 457	86.18 438	97.66 460	93.28 435	89.86 457	97.61 453

dongtai		93.26 426	92.93 430	94.25 439	99.39 272	85.68 467	97.68 471	93.27 481	92.87 447	96.85 434	99.39 340	82.33 460	97.48 461	76.78 475	97.80 313	99.58 206

pmmvs3		94.09 422	93.25 429	96.60 429	94.76 474	94.49 433	98.92 414	98.18 452	89.66 458	96.48 437	98.06 454	86.28 437	97.33 462	89.68 456	87.20 464	97.97 445

KD-MVS_self_test		95.00 413	94.34 418	96.96 421	97.07 460	95.39 412	99.56 146	99.44 254	95.11 416	97.13 428	97.32 463	91.86 367	97.27 463	90.35 454	81.23 472	98.23 427

FMVSNet5		96.43 389	96.19 388	97.15 413	99.11 347	95.89 397	99.32 304	99.52 130	94.47 432	98.34 382	99.07 395	87.54 429	97.07 464	92.61 445	95.72 387	98.47 407

new-patchmatchnet		94.48 419	94.08 420	95.67 436	95.08 471	92.41 455	99.18 357	99.28 343	94.55 431	93.49 459	97.37 462	87.86 427	97.01 465	91.57 449	88.36 461	97.61 453

LCM-MVSNet		86.80 439	85.22 443	91.53 450	87.81 482	80.96 476	98.23 464	98.99 387	71.05 475	90.13 470	96.51 467	48.45 482	96.88 466	90.51 452	85.30 466	96.76 462

CL-MVSNet_self_test		94.49 418	93.97 422	96.08 434	96.16 463	93.67 446	98.33 459	99.38 288	95.13 414	97.33 421	98.15 448	92.69 346	96.57 467	88.67 459	79.87 473	97.99 443

MIMVSNet1		95.51 405	95.04 410	96.92 424	97.38 452	95.60 402	99.52 177	99.50 175	93.65 438	96.97 432	99.17 385	85.28 446	96.56 468	88.36 461	95.55 393	98.60 395

FE-MVSNET		94.07 423	93.36 428	96.22 433	94.05 475	94.71 428	99.56 146	98.36 444	93.15 444	93.76 457	97.55 458	86.47 436	96.49 469	87.48 465	89.83 458	97.48 458

test20.03		96.12 395	95.96 394	96.63 428	97.44 451	95.45 409	99.51 187	99.38 288	96.55 366	96.16 441	99.25 377	93.76 320	96.17 470	87.35 467	94.22 418	98.27 423

tmp_tt		82.80 441	81.52 444	86.66 458	66.61 488	68.44 487	92.79 478	97.92 454	68.96 476	80.04 479	99.85 81	85.77 440	96.15 471	97.86 280	43.89 481	95.39 471

test_fmvs3		92.10 430	91.77 433	93.08 445	96.19 462	86.25 465	99.82 16	98.62 438	96.65 355	95.19 449	96.90 465	55.05 479	95.93 472	96.63 377	90.92 452	97.06 461

kuosan		90.92 434	90.11 439	93.34 443	98.78 403	85.59 468	98.15 466	93.16 483	89.37 461	92.07 464	98.38 440	81.48 463	95.19 473	62.54 482	97.04 355	99.25 282

dmvs_testset		95.02 412	96.12 389	91.72 449	99.10 350	80.43 477	99.58 130	97.87 456	97.47 282	95.22 447	98.82 421	93.99 309	95.18 474	88.09 462	94.91 408	99.56 212

PMMVS2		86.87 438	85.37 442	91.35 451	90.21 480	83.80 470	98.89 417	97.45 463	83.13 472	91.67 469	95.03 469	48.49 481	94.70 475	85.86 472	77.62 474	95.54 470

PMVS	70.75 22	75.98 447	74.97 448	79.01 464	70.98 487	55.18 489	93.37 477	98.21 450	65.08 481	61.78 482	93.83 472	21.74 488	92.53 476	78.59 474	91.12 450	89.34 477
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 440	85.65 441	82.75 462	86.77 483	63.39 488	98.35 456	98.92 396	74.11 474	83.39 473	98.98 409	50.85 480	92.40 477	84.54 473	94.97 405	92.46 472

WB-MVS		93.10 427	94.10 419	90.12 454	95.51 470	81.88 474	99.73 51	99.27 346	95.05 419	93.09 461	98.91 418	94.70 273	91.89 478	76.62 476	94.02 424	96.58 464

SSC-MVS		92.73 429	93.73 423	89.72 455	95.02 473	81.38 475	99.76 37	99.23 353	94.87 424	92.80 462	98.93 414	94.71 272	91.37 479	74.49 478	93.80 426	96.42 465

MVE	76.82 21	76.91 446	74.31 450	84.70 459	85.38 485	76.05 483	96.88 474	93.17 482	67.39 478	71.28 480	89.01 479	21.66 489	87.69 480	71.74 479	72.29 477	90.35 476
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 443	79.88 445	82.81 461	90.75 479	76.38 482	97.69 470	95.76 474	66.44 479	83.52 472	92.25 474	62.54 474	87.16 481	68.53 480	61.40 478	84.89 479

EMVS		80.02 444	79.22 446	82.43 463	91.19 478	76.40 481	97.55 473	92.49 486	66.36 480	83.01 474	91.27 476	64.63 473	85.79 482	65.82 481	60.65 479	85.08 478

ANet_high		77.30 445	74.86 449	84.62 460	75.88 486	77.61 480	97.63 472	93.15 484	88.81 463	64.27 481	89.29 478	36.51 484	83.93 483	75.89 477	52.31 480	92.33 474

wuyk23d		40.18 448	41.29 453	36.84 465	86.18 484	49.12 490	79.73 479	22.81 490	27.64 482	25.46 485	28.45 485	21.98 487	48.89 484	55.80 483	23.56 484	12.51 482

test123		39.01 450	42.50 452	28.53 466	39.17 489	20.91 491	98.75 431	19.17 491	19.83 484	38.57 483	66.67 481	33.16 485	15.42 485	37.50 485	29.66 483	49.26 480

testmvs		39.17 449	43.78 451	25.37 467	36.04 490	16.84 492	98.36 455	26.56 489	20.06 483	38.51 484	67.32 480	29.64 486	15.30 486	37.59 484	39.90 482	43.98 481

mmdepth		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

monomultidepth		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

test_blank		0.13 454	0.17 457	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	1.57 486	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uanet_test		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

DCPMVS		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

cdsmvs_eth3d_5k		24.64 451	32.85 454	0.00 468	0.00 491	0.00 493	0.00 480	99.51 152	0.00 486	0.00 487	99.56 282	96.58 174	0.00 487	0.00 486	0.00 485	0.00 483

pcd_1.5k_mvsjas		8.27 453	11.03 456	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	99.01 20	0.00 487	0.00 486	0.00 485	0.00 483

sosnet-low-res		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

sosnet		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uncertanet		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

Regformer		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

ab-mvs-re		8.30 452	11.06 455	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	99.58 274	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

uanet		0.02 455	0.03 458	0.00 468	0.00 491	0.00 493	0.00 480	0.00 492	0.00 486	0.00 487	0.27 487	0.00 490	0.00 487	0.00 486	0.00 485	0.00 483

TestfortrainingZip							99.69 62

WAC-MVS						97.16 332								95.47 403

FOURS1					99.91 1	99.93 1	99.87 8	99.56 90	99.10 48	99.81 69

test_one_0601					99.81 57	99.88 10		99.49 188	98.97 75	99.65 135	99.81 130	99.09 16

eth-test2					0.00 491

eth-test					0.00 491

RE-MVS-def			99.34 50		99.76 82	99.82 28	99.63 101	99.52 130	98.38 137	99.76 91	99.82 115	98.75 60		98.61 200	99.81 120	99.77 100

IU-MVS					99.84 38	99.88 10		99.32 328	98.30 149	99.84 56				98.86 160	99.85 94	99.89 29

save fliter					99.76 82	99.59 88	99.14 364	99.40 277	99.00 67

test0726					99.85 31	99.89 6	99.62 106	99.50 175	99.10 48	99.86 53	99.82 115	98.94 34

GSMVS																99.52 222

test_part2					99.81 57	99.83 22				99.77 85

sam_mvs1												94.86 258				99.52 222

sam_mvs												94.72 271

MTGPA								99.47 222

MTMP							99.54 166	98.88 406

test9_res														97.49 321	99.72 148	99.75 109

agg_prior2														97.21 340	99.73 147	99.75 109

test_prior4						99.56 94	98.99 400

test_prior2							98.96 407		98.34 143	99.01 296	99.52 298	98.68 70		97.96 272	99.74 145

新几何2							99.01 397

旧先验1					99.74 100	99.59 88		99.54 109			99.69 223	98.47 86			99.68 156	99.73 123

原ACMM2							98.95 410

test222					99.75 92	99.49 109	98.91 416	99.49 188	96.42 377	99.34 225	99.65 244	98.28 100			99.69 153	99.72 133

segment_acmp												98.96 27

testdata1							98.85 421		98.32 147

plane_prior7					99.29 300	97.03 347

plane_prior6					99.27 305	96.98 351						92.71 344

plane_prior4											99.61 265

plane_prior3						97.00 349			98.69 107	99.11 276

plane_prior2							99.39 278		98.97 75

plane_prior1					99.26 308

plane_prior						96.97 352	99.21 350		98.45 130						97.60 322

n2								0.00 492

nn								0.00 492

door-mid								98.05 453

test11								99.35 305

door								97.92 454

HQP5-MVS						96.83 363

HQP-NCC					99.19 326		98.98 403		98.24 162	98.66 352

ACMP_Plane					99.19 326		98.98 403		98.24 162	98.66 352

BP-MVS														97.19 344

HQP3-MVS								99.39 280							97.58 324

HQP2-MVS												92.47 353

NP-MVS					99.23 316	96.92 359					99.40 336

MDTV_nov1_ep13_2view						95.18 418	99.35 296		96.84 343	99.58 159		95.19 243		97.82 285		99.46 250

ACMMP++_ref															97.19 352

ACMMP++															97.43 342

Test By Simon												98.75 60

High-resolution multi-view benchmark