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 7	99.61 7	99.77 72	99.38 268	99.37 121	99.58 129	99.62 50	99.41 20	99.87 47	99.92 17	98.81 48	100.00 1	99.97 2	99.93 32	99.94 17

test_fmvsm_n_1920		99.69 5	99.66 4	99.78 69	99.84 37	99.44 114	99.58 129	99.69 21	99.43 16	99.98 12	99.91 25	98.62 75	100.00 1	99.97 2	99.95 22	99.90 25

test_vis1_n_1920		98.63 209	98.40 217	99.31 189	99.86 24	97.94 291	99.67 74	99.62 50	99.43 16	99.99 2	99.91 25	87.29 423	100.00 1	99.92 23	99.92 38	99.98 2

fmvsm_s_conf0.5_n_10		99.41 58	99.24 77	99.92 1	99.83 46	99.84 20	99.53 173	99.56 89	99.45 11	99.99 2	99.92 17	94.92 249	99.99 4	99.97 2	99.97 8	99.95 11

fmvsm_l_conf0.5_n_9		99.58 15	99.47 23	99.92 1	99.85 30	99.82 28	99.47 227	99.63 45	99.45 11	99.98 12	99.89 40	97.02 146	99.99 4	99.98 1	99.96 16	99.95 11

NormalMVS		99.27 87	99.19 87	99.52 137	99.89 8	98.83 215	99.65 87	99.52 128	99.10 46	99.84 54	99.76 179	95.80 210	99.99 4	99.30 88	99.84 100	99.74 112

SymmetryMVS		99.15 112	99.02 120	99.52 137	99.72 109	98.83 215	99.65 87	99.34 302	99.10 46	99.84 54	99.76 179	95.80 210	99.99 4	99.30 88	98.72 252	99.73 121

fmvsm_s_conf0.5_n_5		99.37 67	99.21 83	99.86 33	99.80 61	99.68 62	99.42 254	99.61 59	99.37 23	99.97 24	99.86 70	94.96 244	99.99 4	99.97 2	99.93 32	99.92 23

fmvsm_l_conf0.5_n_3		99.61 9	99.51 17	99.92 1	99.84 37	99.82 28	99.54 164	99.66 31	99.46 7	99.98 12	99.89 40	97.27 132	99.99 4	99.97 2	99.95 22	99.95 11

fmvsm_l_conf0.5_n_a		99.71 2	99.67 1	99.85 42	99.86 24	99.61 83	99.56 144	99.63 45	99.48 3	99.98 12	99.83 97	98.75 59	99.99 4	99.97 2	99.96 16	99.94 17

fmvsm_l_conf0.5_n		99.71 2	99.67 1	99.85 42	99.84 37	99.63 80	99.56 144	99.63 45	99.47 4	99.98 12	99.82 109	98.75 59	99.99 4	99.97 2	99.97 8	99.94 17

test_fmvsmconf_n		99.70 4	99.64 5	99.87 21	99.80 61	99.66 69	99.48 217	99.64 41	99.45 11	99.92 29	99.92 17	98.62 75	99.99 4	99.96 13	99.99 1	99.96 7

patch_mono-2		99.26 90	99.62 6	98.16 351	99.81 55	94.59 424	99.52 175	99.64 41	99.33 27	99.73 95	99.90 32	99.00 23	99.99 4	99.69 34	99.98 4	99.89 29

h-mvs33		97.70 323	97.28 346	98.97 237	99.70 120	97.27 319	99.36 284	99.45 238	98.94 76	99.66 120	99.64 244	94.93 247	99.99 4	99.48 63	84.36 459	99.65 165

xiu_mvs_v1_base_debu		99.29 83	99.27 72	99.34 181	99.63 161	98.97 181	99.12 361	99.51 147	98.86 82	99.84 54	99.47 311	98.18 103	99.99 4	99.50 56	99.31 189	99.08 290

xiu_mvs_v1_base		99.29 83	99.27 72	99.34 181	99.63 161	98.97 181	99.12 361	99.51 147	98.86 82	99.84 54	99.47 311	98.18 103	99.99 4	99.50 56	99.31 189	99.08 290

xiu_mvs_v1_base_debi		99.29 83	99.27 72	99.34 181	99.63 161	98.97 181	99.12 361	99.51 147	98.86 82	99.84 54	99.47 311	98.18 103	99.99 4	99.50 56	99.31 189	99.08 290

EPNet		98.86 174	98.71 181	99.30 194	97.20 450	98.18 271	99.62 105	98.91 393	99.28 30	98.63 354	99.81 124	95.96 198	99.99 4	99.24 98	99.72 146	99.73 121
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 23	99.42 31	99.89 11	99.83 46	99.74 53	99.51 184	99.62 50	99.46 7	99.99 2	99.90 32	96.60 169	99.98 19	99.95 15	99.95 22	99.96 7

MM		99.40 63	99.28 68	99.74 78	99.67 132	99.31 133	99.52 175	98.87 400	99.55 1	99.74 93	99.80 142	96.47 176	99.98 19	99.97 2	99.97 8	99.94 17

test_cas_vis1_n_1920		99.16 108	99.01 125	99.61 107	99.81 55	98.86 209	99.65 87	99.64 41	99.39 21	99.97 24	99.94 6	93.20 324	99.98 19	99.55 49	99.91 45	99.99 1

test_vis1_n		97.92 281	97.44 322	99.34 181	99.53 210	98.08 278	99.74 47	99.49 182	99.15 36	100.00 1	99.94 6	79.51 459	99.98 19	99.88 25	99.76 138	99.97 4

xiu_mvs_v2_base		99.26 90	99.25 76	99.29 197	99.53 210	98.91 200	99.02 385	99.45 238	98.80 92	99.71 103	99.26 370	98.94 33	99.98 19	99.34 80	99.23 198	98.98 304

PS-MVSNAJ		99.32 78	99.32 53	99.30 194	99.57 194	98.94 195	98.97 399	99.46 227	98.92 79	99.71 103	99.24 372	99.01 19	99.98 19	99.35 75	99.66 157	98.97 305

QAPM		98.67 204	98.30 224	99.80 63	99.20 317	99.67 66	99.77 34	99.72 13	94.74 419	98.73 334	99.90 32	95.78 212	99.98 19	96.96 351	99.88 74	99.76 106

3Dnovator	97.25 9	99.24 95	99.05 109	99.81 59	99.12 339	99.66 69	99.84 12	99.74 12	99.09 53	98.92 307	99.90 32	95.94 201	99.98 19	98.95 137	99.92 38	99.79 91

OpenMVS	96.50 16	98.47 215	98.12 236	99.52 137	99.04 358	99.53 99	99.82 16	99.72 13	94.56 422	98.08 389	99.88 51	94.73 264	99.98 19	97.47 318	99.76 138	99.06 296

fmvsm_s_conf0.5_n_3		99.37 67	99.20 85	99.87 21	99.75 90	99.70 59	99.48 217	99.66 31	99.45 11	99.99 2	99.93 10	94.64 273	99.97 28	99.94 20	99.97 8	99.95 11

reproduce_model		99.63 8	99.54 12	99.90 8	99.78 68	99.88 10	99.56 144	99.55 98	99.15 36	99.90 33	99.90 32	99.00 23	99.97 28	99.11 114	99.91 45	99.86 42

test_fmvsmconf0.1_n		99.55 22	99.45 29	99.86 33	99.44 250	99.65 73	99.50 194	99.61 59	99.45 11	99.87 47	99.92 17	97.31 129	99.97 28	99.95 15	99.99 1	99.97 4

test_fmvs1_n		98.41 221	98.14 233	99.21 210	99.82 51	97.71 304	99.74 47	99.49 182	99.32 28	99.99 2	99.95 3	85.32 437	99.97 28	99.82 28	99.84 100	99.96 7

CANet_DTU		98.97 162	98.87 158	99.25 204	99.33 281	98.42 263	99.08 370	99.30 329	99.16 35	99.43 187	99.75 184	95.27 232	99.97 28	98.56 206	99.95 22	99.36 262

MGCNet		99.15 112	98.96 136	99.73 81	98.92 376	99.37 121	99.37 278	96.92 457	99.51 2	99.66 120	99.78 166	96.69 165	99.97 28	99.84 27	99.97 8	99.84 53

MTAPA		99.52 27	99.39 39	99.89 11	99.90 4	99.86 18	99.66 81	99.47 216	98.79 93	99.68 109	99.81 124	98.43 88	99.97 28	98.88 147	99.90 56	99.83 63

PGM-MVS		99.45 45	99.31 59	99.86 33	99.87 19	99.78 46	99.58 129	99.65 38	97.84 230	99.71 103	99.80 142	99.12 14	99.97 28	98.33 231	99.87 77	99.83 63

mPP-MVS		99.44 49	99.30 61	99.86 33	99.88 13	99.79 40	99.69 62	99.48 194	98.12 182	99.50 171	99.75 184	98.78 52	99.97 28	98.57 203	99.89 67	99.83 63

CP-MVS		99.45 45	99.32 53	99.85 42	99.83 46	99.75 50	99.69 62	99.52 128	98.07 193	99.53 166	99.63 250	98.93 37	99.97 28	98.74 174	99.91 45	99.83 63

SteuartSystems-ACMMP		99.54 23	99.42 31	99.87 21	99.82 51	99.81 33	99.59 119	99.51 147	98.62 110	99.79 74	99.83 97	99.28 5	99.97 28	98.48 213	99.90 56	99.84 53
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 102	98.97 132	99.82 56	99.17 331	99.68 62	99.81 20	99.51 147	99.20 32	98.72 335	99.89 40	95.68 216	99.97 28	98.86 155	99.86 85	99.81 78

fmvsm_s_conf0.5_n_9		99.41 58	99.28 68	99.81 59	99.84 37	99.52 103	99.48 217	99.62 50	99.46 7	99.99 2	99.92 17	95.24 236	99.96 40	99.97 2	99.97 8	99.96 7

lecture		99.60 13	99.50 18	99.89 11	99.89 8	99.90 3	99.75 42	99.59 72	99.06 59	99.88 41	99.85 77	98.41 92	99.96 40	99.28 91	99.84 100	99.83 63

KinetiMVS		99.12 125	98.92 145	99.70 85	99.67 132	99.40 119	99.67 74	99.63 45	98.73 100	99.94 27	99.81 124	94.54 279	99.96 40	98.40 222	99.93 32	99.74 112

fmvsm_s_conf0.5_n_7		99.34 74	99.29 65	99.48 151	99.70 120	98.63 236	99.42 254	99.63 45	99.46 7	99.98 12	99.88 51	95.59 219	99.96 40	99.97 2	99.98 4	99.85 46

fmvsm_s_conf0.5_n_2		99.32 78	99.13 93	99.89 11	99.80 61	99.77 47	99.44 241	99.58 77	99.47 4	99.99 2	99.93 10	94.04 300	99.96 40	99.96 13	99.93 32	99.93 22

reproduce-ours		99.61 9	99.52 13	99.90 8	99.76 80	99.88 10	99.52 175	99.54 107	99.13 39	99.89 38	99.89 40	98.96 26	99.96 40	99.04 123	99.90 56	99.85 46

our_new_method		99.61 9	99.52 13	99.90 8	99.76 80	99.88 10	99.52 175	99.54 107	99.13 39	99.89 38	99.89 40	98.96 26	99.96 40	99.04 123	99.90 56	99.85 46

fmvsm_s_conf0.5_n_a		99.56 20	99.47 23	99.85 42	99.83 46	99.64 79	99.52 175	99.65 38	99.10 46	99.98 12	99.92 17	97.35 128	99.96 40	99.94 20	99.92 38	99.95 11

fmvsm_s_conf0.5_n		99.51 28	99.40 37	99.85 42	99.84 37	99.65 73	99.51 184	99.67 26	99.13 39	99.98 12	99.92 17	96.60 169	99.96 40	99.95 15	99.96 16	99.95 11

mvsany_test1		99.50 30	99.46 27	99.62 106	99.61 179	99.09 163	98.94 405	99.48 194	99.10 46	99.96 26	99.91 25	98.85 43	99.96 40	99.72 31	99.58 167	99.82 71

test_fmvs1		98.88 168	98.79 172	99.16 215	99.69 125	97.61 308	99.55 159	99.49 182	99.32 28	99.98 12	99.91 25	91.41 372	99.96 40	99.82 28	99.92 38	99.90 25

DVP-MVS++		99.59 14	99.50 18	99.88 15	99.51 219	99.88 10	99.87 8	99.51 147	98.99 67	99.88 41	99.81 124	99.27 6	99.96 40	98.85 157	99.80 123	99.81 78

MSC_two_6792asdad				99.87 21	99.51 219	99.76 48		99.33 310					99.96 40	98.87 150	99.84 100	99.89 29

No_MVS				99.87 21	99.51 219	99.76 48		99.33 310					99.96 40	98.87 150	99.84 100	99.89 29

ZD-MVS					99.71 115	99.79 40		99.61 59	96.84 337	99.56 157	99.54 284	98.58 77	99.96 40	96.93 354	99.75 140

SED-MVS		99.61 9	99.52 13	99.88 15	99.84 37	99.90 3	99.60 112	99.48 194	99.08 54	99.91 30	99.81 124	99.20 8	99.96 40	98.91 144	99.85 92	99.79 91

test_241102_TWO								99.48 194	99.08 54	99.88 41	99.81 124	98.94 33	99.96 40	98.91 144	99.84 100	99.88 35

ZNCC-MVS		99.47 39	99.33 51	99.87 21	99.87 19	99.81 33	99.64 94	99.67 26	98.08 192	99.55 163	99.64 244	98.91 38	99.96 40	98.72 177	99.90 56	99.82 71

DVP-MVS		99.57 19	99.47 23	99.88 15	99.85 30	99.89 6	99.57 137	99.37 289	99.10 46	99.81 67	99.80 142	98.94 33	99.96 40	98.93 141	99.86 85	99.81 78
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 67	99.81 67	99.80 142	99.09 15	99.96 40	98.85 157	99.90 56	99.88 35

test_0728_SECOND				99.91 6	99.84 37	99.89 6	99.57 137	99.51 147					99.96 40	98.93 141	99.86 85	99.88 35

SR-MVS		99.43 52	99.29 65	99.86 33	99.75 90	99.83 22	99.59 119	99.62 50	98.21 166	99.73 95	99.79 159	98.68 69	99.96 40	98.44 219	99.77 135	99.79 91

DPE-MVS		99.46 41	99.32 53	99.91 6	99.78 68	99.88 10	99.36 284	99.51 147	98.73 100	99.88 41	99.84 92	98.72 66	99.96 40	98.16 246	99.87 77	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 54	99.29 65	99.80 63	99.62 169	99.55 94	99.50 194	99.70 17	98.79 93	99.77 83	99.96 1	97.45 123	99.96 40	98.92 143	99.90 56	99.89 29

HFP-MVS		99.49 32	99.37 43	99.86 33	99.87 19	99.80 37	99.66 81	99.67 26	98.15 173	99.68 109	99.69 217	99.06 17	99.96 40	98.69 182	99.87 77	99.84 53

region2R		99.48 36	99.35 47	99.87 21	99.88 13	99.80 37	99.65 87	99.66 31	98.13 180	99.66 120	99.68 225	98.96 26	99.96 40	98.62 191	99.87 77	99.84 53

HPM-MVS++		99.39 65	99.23 81	99.87 21	99.75 90	99.84 20	99.43 247	99.51 147	98.68 107	99.27 236	99.53 288	98.64 74	99.96 40	98.44 219	99.80 123	99.79 91

APDe-MVS		99.66 6	99.57 9	99.92 1	99.77 76	99.89 6	99.75 42	99.56 89	99.02 60	99.88 41	99.85 77	99.18 11	99.96 40	99.22 99	99.92 38	99.90 25
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 32	99.36 45	99.86 33	99.87 19	99.79 40	99.66 81	99.67 26	98.15 173	99.67 115	99.69 217	98.95 31	99.96 40	98.69 182	99.87 77	99.84 53

MP-MVS		99.33 76	99.15 91	99.87 21	99.88 13	99.82 28	99.66 81	99.46 227	98.09 188	99.48 175	99.74 189	98.29 98	99.96 40	97.93 268	99.87 77	99.82 71
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 131	98.90 150	99.74 78	99.80 61	99.46 112	99.59 119	99.49 182	97.03 324	99.63 137	99.69 217	97.27 132	99.96 40	97.82 279	99.84 100	99.81 78

PVSNet_Blended_VisFu		99.36 71	99.28 68	99.61 107	99.86 24	99.07 168	99.47 227	99.93 2	97.66 255	99.71 103	99.86 70	97.73 118	99.96 40	99.47 65	99.82 115	99.79 91

UGNet		98.87 171	98.69 183	99.40 171	99.22 314	98.72 228	99.44 241	99.68 23	99.24 31	99.18 261	99.42 322	92.74 334	99.96 40	99.34 80	99.94 30	99.53 215
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 78	99.32 53	99.32 187	99.85 30	98.29 266	99.71 57	99.66 31	98.11 184	99.41 195	99.80 142	98.37 95	99.96 40	98.99 129	99.96 16	99.72 130

ACMMP		99.45 45	99.32 53	99.82 56	99.89 8	99.67 66	99.62 105	99.69 21	98.12 182	99.63 137	99.84 92	98.73 65	99.96 40	98.55 209	99.83 111	99.81 78
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 25	99.90 33	99.83 97		99.95 75	98.83 163	99.89 67	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 25	99.90 33	99.83 97	99.30 4	99.95 75	99.32 83	99.89 67	99.90 25

fmvsm_s_conf0.5_n_6		99.54 23	99.44 30	99.85 42	99.51 219	99.67 66	99.50 194	99.64 41	99.43 16	99.98 12	99.78 166	97.26 134	99.95 75	99.95 15	99.93 32	99.92 23

fmvsm_s_conf0.5_n_4		99.36 71	99.24 77	99.73 81	99.78 68	99.53 99	99.49 211	99.60 66	99.42 19	99.99 2	99.86 70	95.15 239	99.95 75	99.95 15	99.89 67	99.73 121

fmvsm_s_conf0.1_n_2		99.37 67	99.22 82	99.81 59	99.77 76	99.75 50	99.46 231	99.60 66	99.47 4	99.98 12	99.94 6	94.98 243	99.95 75	99.97 2	99.79 130	99.73 121

test_fmvsmconf0.01_n		99.22 98	99.03 114	99.79 66	98.42 430	99.48 109	99.55 159	99.51 147	99.39 21	99.78 79	99.93 10	94.80 256	99.95 75	99.93 22	99.95 22	99.94 17

SR-MVS-dyc-post		99.45 45	99.31 59	99.85 42	99.76 80	99.82 28	99.63 100	99.52 128	98.38 135	99.76 89	99.82 109	98.53 81	99.95 75	98.61 194	99.81 118	99.77 99

GST-MVS		99.40 63	99.24 77	99.85 42	99.86 24	99.79 40	99.60 112	99.67 26	97.97 214	99.63 137	99.68 225	98.52 82	99.95 75	98.38 224	99.86 85	99.81 78

CANet		99.25 94	99.14 92	99.59 111	99.41 258	99.16 153	99.35 289	99.57 84	98.82 87	99.51 170	99.61 259	96.46 177	99.95 75	99.59 44	99.98 4	99.65 165

MP-MVS-pluss		99.37 67	99.20 85	99.88 15	99.90 4	99.87 17	99.30 303	99.52 128	97.18 306	99.60 149	99.79 159	98.79 51	99.95 75	98.83 163	99.91 45	99.83 63
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 54	99.27 72	99.88 15	99.89 8	99.80 37	99.67 74	99.50 170	98.70 104	99.77 83	99.49 302	98.21 101	99.95 75	98.46 217	99.77 135	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 75	96.67 366

APD-MVS_3200maxsize		99.48 36	99.35 47	99.85 42	99.76 80	99.83 22	99.63 100	99.54 107	98.36 139	99.79 74	99.82 109	98.86 42	99.95 75	98.62 191	99.81 118	99.78 97

RPMNet		96.72 375	95.90 388	99.19 212	99.18 323	98.49 255	99.22 341	99.52 128	88.72 456	99.56 157	97.38 453	94.08 299	99.95 75	86.87 461	98.58 259	99.14 282

sss		99.17 106	99.05 109	99.53 131	99.62 169	98.97 181	99.36 284	99.62 50	97.83 231	99.67 115	99.65 238	97.37 127	99.95 75	99.19 102	99.19 201	99.68 151

MVSMamba_PlusPlus		99.46 41	99.41 36	99.64 99	99.68 130	99.50 106	99.75 42	99.50 170	98.27 150	99.87 47	99.92 17	98.09 107	99.94 90	99.65 40	99.95 22	99.47 239

fmvsm_s_conf0.1_n_a		99.26 90	99.06 107	99.85 42	99.52 216	99.62 81	99.54 164	99.62 50	98.69 105	99.99 2	99.96 1	94.47 283	99.94 90	99.88 25	99.92 38	99.98 2

fmvsm_s_conf0.1_n		99.29 83	99.10 97	99.86 33	99.70 120	99.65 73	99.53 173	99.62 50	98.74 99	99.99 2	99.95 3	94.53 281	99.94 90	99.89 24	99.96 16	99.97 4

TSAR-MVS + MP.		99.58 15	99.50 18	99.81 59	99.91 1	99.66 69	99.63 100	99.39 273	98.91 80	99.78 79	99.85 77	99.36 2	99.94 90	98.84 160	99.88 74	99.82 71
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 166	98.75 175	99.39 176	99.46 243	98.61 240	99.76 37	99.50 170	98.06 197	99.81 67	99.88 51	93.91 307	99.94 90	99.11 114	99.27 192	99.61 182

mamv4		99.33 76	99.42 31	99.07 223	99.67 132	97.73 299	99.42 254	99.60 66	98.15 173	99.94 27	99.91 25	98.42 90	99.94 90	99.72 31	99.96 16	99.54 209

XVS		99.53 26	99.42 31	99.87 21	99.85 30	99.83 22	99.69 62	99.68 23	98.98 70	99.37 206	99.74 189	98.81 48	99.94 90	98.79 170	99.86 85	99.84 53

X-MVStestdata		96.55 378	95.45 397	99.87 21	99.85 30	99.83 22	99.69 62	99.68 23	98.98 70	99.37 206	64.01 476	98.81 48	99.94 90	98.79 170	99.86 85	99.84 53

旧先验2							98.96 400		96.70 344	99.47 176			99.94 90	98.19 242

新几何1				99.75 75	99.75 90	99.59 86		99.54 107	96.76 340	99.29 229	99.64 244	98.43 88	99.94 90	96.92 356	99.66 157	99.72 130

testdata				99.54 123	99.75 90	98.95 191		99.51 147	97.07 318	99.43 187	99.70 206	98.87 41	99.94 90	97.76 288	99.64 160	99.72 130

HPM-MVS		99.42 54	99.28 68	99.83 55	99.90 4	99.72 55	99.81 20	99.54 107	97.59 261	99.68 109	99.63 250	98.91 38	99.94 90	98.58 200	99.91 45	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 99	99.10 97	99.45 159	99.89 8	98.52 250	99.39 271	99.94 1	98.73 100	99.11 270	99.89 40	95.50 222	99.94 90	99.50 56	99.97 8	99.89 29

APD-MVS		99.27 87	99.08 103	99.84 54	99.75 90	99.79 40	99.50 194	99.50 170	97.16 308	99.77 83	99.82 109	98.78 52	99.94 90	97.56 309	99.86 85	99.80 87
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 36	99.42 31	99.65 93	99.72 109	99.40 119	99.05 377	99.66 31	99.14 38	99.57 156	99.80 142	98.46 86	99.94 90	99.57 47	99.84 100	99.60 185
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		99.06 144	98.88 157	99.61 107	99.62 169	99.16 153	99.37 278	99.56 89	98.04 206	99.53 166	99.62 255	96.84 157	99.94 90	98.85 157	98.49 267	99.72 130

DeepC-MVS	98.35 2	99.30 81	99.19 87	99.64 99	99.82 51	99.23 146	99.62 105	99.55 98	98.94 76	99.63 137	99.95 3	95.82 208	99.94 90	99.37 74	99.97 8	99.73 121
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 87	99.12 95	99.74 78	99.18 323	99.75 50	99.56 144	99.57 84	98.45 128	99.49 174	99.85 77	97.77 117	99.94 90	98.33 231	99.84 100	99.52 216

ME-MVS		99.56 20	99.46 27	99.86 33	99.80 61	99.81 33	99.37 278	99.70 17	99.18 33	99.83 62	99.83 97	98.74 64	99.93 108	98.83 163	99.89 67	99.83 63

GDP-MVS		99.08 139	98.89 154	99.64 99	99.53 210	99.34 125	99.64 94	99.48 194	98.32 145	99.77 83	99.66 236	95.14 240	99.93 108	98.97 135	99.50 174	99.64 172

SDMVSNet		99.11 131	98.90 150	99.75 75	99.81 55	99.59 86	99.81 20	99.65 38	98.78 96	99.64 134	99.88 51	94.56 276	99.93 108	99.67 36	98.26 282	99.72 130

FE-MVS		98.48 214	98.17 229	99.40 171	99.54 209	98.96 185	99.68 71	98.81 407	95.54 403	99.62 141	99.70 206	93.82 310	99.93 108	97.35 327	99.46 176	99.32 268

SF-MVS		99.38 66	99.24 77	99.79 66	99.79 66	99.68 62	99.57 137	99.54 107	97.82 236	99.71 103	99.80 142	98.95 31	99.93 108	98.19 242	99.84 100	99.74 112

dcpmvs_2		99.23 96	99.58 8	98.16 351	99.83 46	94.68 421	99.76 37	99.52 128	99.07 56	99.98 12	99.88 51	98.56 79	99.93 108	99.67 36	99.98 4	99.87 40

Anonymous20240529		98.09 251	97.68 289	99.34 181	99.66 145	98.44 260	99.40 267	99.43 258	93.67 429	99.22 248	99.89 40	90.23 389	99.93 108	99.26 97	98.33 274	99.66 159

ACMMP_NAP		99.47 39	99.34 49	99.88 15	99.87 19	99.86 18	99.47 227	99.48 194	98.05 199	99.76 89	99.86 70	98.82 47	99.93 108	98.82 169	99.91 45	99.84 53

EI-MVSNet-UG-set		99.58 15	99.57 9	99.64 99	99.78 68	99.14 158	99.60 112	99.45 238	99.01 62	99.90 33	99.83 97	98.98 25	99.93 108	99.59 44	99.95 22	99.86 42

无先验							98.99 393	99.51 147	96.89 334				99.93 108	97.53 312		99.72 130

VDDNet		97.55 338	97.02 360	99.16 215	99.49 233	98.12 277	99.38 276	99.30 329	95.35 405	99.68 109	99.90 32	82.62 450	99.93 108	99.31 85	98.13 294	99.42 251

ab-mvs		98.86 174	98.63 193	99.54 123	99.64 157	99.19 148	99.44 241	99.54 107	97.77 240	99.30 226	99.81 124	94.20 293	99.93 108	99.17 108	98.82 246	99.49 230

F-COLMAP		99.19 99	99.04 111	99.64 99	99.78 68	99.27 141	99.42 254	99.54 107	97.29 297	99.41 195	99.59 264	98.42 90	99.93 108	98.19 242	99.69 151	99.73 121

BP-MVS1		99.12 125	98.94 142	99.65 93	99.51 219	99.30 136	99.67 74	98.92 388	98.48 124	99.84 54	99.69 217	94.96 244	99.92 121	99.62 43	99.79 130	99.71 139

Anonymous202405211		98.30 232	97.98 253	99.26 203	99.57 194	98.16 272	99.41 259	98.55 432	96.03 397	99.19 257	99.74 189	91.87 359	99.92 121	99.16 109	98.29 281	99.70 142

EI-MVSNet-Vis-set		99.58 15	99.56 11	99.64 99	99.78 68	99.15 157	99.61 111	99.45 238	99.01 62	99.89 38	99.82 109	99.01 19	99.92 121	99.56 48	99.95 22	99.85 46

VDD-MVS		97.73 317	97.35 334	98.88 259	99.47 241	97.12 327	99.34 292	98.85 402	98.19 168	99.67 115	99.85 77	82.98 448	99.92 121	99.49 60	98.32 278	99.60 185

VNet		99.11 131	98.90 150	99.73 81	99.52 216	99.56 92	99.41 259	99.39 273	99.01 62	99.74 93	99.78 166	95.56 220	99.92 121	99.52 54	98.18 290	99.72 130

XVG-OURS-SEG-HR		98.69 202	98.62 198	98.89 256	99.71 115	97.74 298	99.12 361	99.54 107	98.44 131	99.42 190	99.71 202	94.20 293	99.92 121	98.54 210	98.90 240	99.00 301

mvsmamba		99.06 144	98.96 136	99.36 178	99.47 241	98.64 235	99.70 58	99.05 372	97.61 260	99.65 129	99.83 97	96.54 173	99.92 121	99.19 102	99.62 163	99.51 225

HPM-MVS_fast		99.51 28	99.40 37	99.85 42	99.91 1	99.79 40	99.76 37	99.56 89	97.72 246	99.76 89	99.75 184	99.13 13	99.92 121	99.07 120	99.92 38	99.85 46

HY-MVS	97.30 7	98.85 183	98.64 192	99.47 156	99.42 253	99.08 166	99.62 105	99.36 290	97.39 289	99.28 230	99.68 225	96.44 179	99.92 121	98.37 226	98.22 285	99.40 256

DP-MVS		99.16 108	98.95 140	99.78 69	99.77 76	99.53 99	99.41 259	99.50 170	97.03 324	99.04 287	99.88 51	97.39 124	99.92 121	98.66 186	99.90 56	99.87 40

IB-MVS	95.67 18	96.22 384	95.44 398	98.57 301	99.21 315	96.70 361	98.65 434	97.74 451	96.71 343	97.27 415	98.54 427	86.03 431	99.92 121	98.47 216	86.30 457	99.10 285
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 32	99.39 39	99.77 72	99.63 161	99.59 86	99.36 284	99.46 227	99.07 56	99.79 74	99.82 109	98.85 43	99.92 121	98.68 184	99.87 77	99.82 71
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 96	99.10 97	99.61 107	99.35 275	99.31 133	99.46 231	99.13 360	98.61 111	99.86 51	99.89 40	96.41 182	99.91 133	99.67 36	99.51 172	99.63 177

balanced_conf03		99.46 41	99.39 39	99.67 88	99.55 202	99.58 91	99.74 47	99.51 147	98.42 132	99.87 47	99.84 92	98.05 110	99.91 133	99.58 46	99.94 30	99.52 216

9.14			99.10 97		99.72 109		99.40 267	99.51 147	97.53 271	99.64 134	99.78 166	98.84 45	99.91 133	97.63 300	99.82 115

SMA-MVS		99.44 49	99.30 61	99.85 42	99.73 105	99.83 22	99.56 144	99.47 216	97.45 280	99.78 79	99.82 109	99.18 11	99.91 133	98.79 170	99.89 67	99.81 78
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					99.67 132	99.65 73	99.05 377	99.41 263	96.22 382	98.95 303	99.49 302	98.77 55	99.91 133

train_agg		99.02 152	98.77 173	99.77 72	99.67 132	99.65 73	99.05 377	99.41 263	96.28 376	98.95 303	99.49 302	98.76 56	99.91 133	97.63 300	99.72 146	99.75 108

test_8					99.67 132	99.61 83	99.03 382	99.41 263	96.28 376	98.93 306	99.48 308	98.76 56	99.91 133

agg_prior					99.67 132	99.62 81		99.40 270		98.87 316			99.91 133

原ACMM1				99.65 93	99.73 105	99.33 128		99.47 216	97.46 277	99.12 268	99.66 236	98.67 71	99.91 133	97.70 297	99.69 151	99.71 139

LFMVS		97.90 284	97.35 334	99.54 123	99.52 216	99.01 175	99.39 271	98.24 440	97.10 316	99.65 129	99.79 159	84.79 440	99.91 133	99.28 91	98.38 271	99.69 145

XVG-OURS		98.73 200	98.68 184	98.88 259	99.70 120	97.73 299	98.92 407	99.55 98	98.52 120	99.45 179	99.84 92	95.27 232	99.91 133	98.08 257	98.84 244	99.00 301

PLC	97.94 4	99.02 152	98.85 164	99.53 131	99.66 145	99.01 175	99.24 334	99.52 128	96.85 336	99.27 236	99.48 308	98.25 100	99.91 133	97.76 288	99.62 163	99.65 165
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 331	97.06 359	99.47 156	99.61 179	99.09 163	98.04 460	99.25 341	91.24 447	98.51 365	99.70 206	94.55 278	99.91 133	92.76 436	99.85 92	99.42 251
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 168	98.65 190	99.58 114	99.58 189	99.34 125	99.65 87	99.52 128	98.26 153	99.83 62	99.87 62	93.37 318	99.90 146	97.81 281	99.91 45	99.49 230

StellarMVS		98.88 168	98.65 190	99.58 114	99.58 189	99.34 125	99.65 87	99.52 128	98.26 153	99.83 62	99.87 62	93.37 318	99.90 146	97.81 281	99.91 45	99.49 230

AstraMVS		99.09 137	99.03 114	99.25 204	99.66 145	98.13 275	99.57 137	98.24 440	98.82 87	99.91 30	99.88 51	95.81 209	99.90 146	99.72 31	99.67 156	99.74 112

mmtdpeth		96.95 370	96.71 369	97.67 390	99.33 281	94.90 416	99.89 2	99.28 335	98.15 173	99.72 100	98.57 426	86.56 428	99.90 146	99.82 28	89.02 452	98.20 421

UWE-MVS		97.58 337	97.29 345	98.48 314	99.09 347	96.25 381	99.01 390	96.61 463	97.86 224	99.19 257	99.01 397	88.72 404	99.90 146	97.38 325	98.69 253	99.28 271

test_vis1_rt		95.81 394	95.65 393	96.32 424	99.67 132	91.35 452	99.49 211	96.74 461	98.25 158	95.24 439	98.10 445	74.96 460	99.90 146	99.53 52	98.85 243	97.70 445

FA-MVS(test-final)		98.75 197	98.53 209	99.41 170	99.55 202	99.05 171	99.80 25	99.01 377	96.59 358	99.58 153	99.59 264	95.39 226	99.90 146	97.78 284	99.49 175	99.28 271

MCST-MVS		99.43 52	99.30 61	99.82 56	99.79 66	99.74 53	99.29 308	99.40 270	98.79 93	99.52 168	99.62 255	98.91 38	99.90 146	98.64 188	99.75 140	99.82 71

CDPH-MVS		99.13 118	98.91 148	99.80 63	99.75 90	99.71 57	99.15 355	99.41 263	96.60 356	99.60 149	99.55 279	98.83 46	99.90 146	97.48 316	99.83 111	99.78 97

NCCC		99.34 74	99.19 87	99.79 66	99.61 179	99.65 73	99.30 303	99.48 194	98.86 82	99.21 251	99.63 250	98.72 66	99.90 146	98.25 238	99.63 162	99.80 87

114514_t		98.93 164	98.67 185	99.72 84	99.85 30	99.53 99	99.62 105	99.59 72	92.65 442	99.71 103	99.78 166	98.06 109	99.90 146	98.84 160	99.91 45	99.74 112

1112_ss		98.98 160	98.77 173	99.59 111	99.68 130	99.02 173	99.25 329	99.48 194	97.23 303	99.13 266	99.58 268	96.93 151	99.90 146	98.87 150	98.78 249	99.84 53

PHI-MVS		99.30 81	99.17 90	99.70 85	99.56 198	99.52 103	99.58 129	99.80 10	97.12 312	99.62 141	99.73 195	98.58 77	99.90 146	98.61 194	99.91 45	99.68 151

AdaColmap		99.01 156	98.80 169	99.66 89	99.56 198	99.54 96	99.18 350	99.70 17	98.18 171	99.35 215	99.63 250	96.32 184	99.90 146	97.48 316	99.77 135	99.55 207

COLMAP_ROB	97.56 6	98.86 174	98.75 175	99.17 214	99.88 13	98.53 246	99.34 292	99.59 72	97.55 267	98.70 342	99.89 40	95.83 207	99.90 146	98.10 252	99.90 56	99.08 290
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 228	98.03 248	99.31 189	99.63 161	98.56 243	99.54 164	96.75 460	97.53 271	99.73 95	99.65 238	91.25 377	99.89 161	98.62 191	99.56 168	99.48 233

tttt0517		98.42 219	98.14 233	99.28 201	99.66 145	98.38 264	99.74 47	96.85 458	97.68 252	99.79 74	99.74 189	91.39 373	99.89 161	98.83 163	99.56 168	99.57 203

test12				99.75 75	99.64 157	99.61 83		99.29 333		99.21 251		98.38 94	99.89 161		99.74 143	99.74 112

Test_1112_low_res		98.89 167	98.66 188	99.57 118	99.69 125	98.95 191	99.03 382	99.47 216	96.98 326	99.15 264	99.23 373	96.77 162	99.89 161	98.83 163	98.78 249	99.86 42

CNLPA		99.14 116	98.99 128	99.59 111	99.58 189	99.41 118	99.16 352	99.44 247	98.45 128	99.19 257	99.49 302	98.08 108	99.89 161	97.73 292	99.75 140	99.48 233

diffmvs_AUTHOR		99.19 99	99.10 97	99.48 151	99.64 157	98.85 210	99.32 297	99.48 194	98.50 122	99.81 67	99.81 124	96.82 158	99.88 166	99.40 70	99.12 211	99.71 139

guyue		99.16 108	99.04 111	99.52 137	99.69 125	98.92 199	99.59 119	98.81 407	98.73 100	99.90 33	99.87 62	95.34 229	99.88 166	99.66 39	99.81 118	99.74 112

sd_testset		98.75 197	98.57 205	99.29 197	99.81 55	98.26 268	99.56 144	99.62 50	98.78 96	99.64 134	99.88 51	92.02 356	99.88 166	99.54 50	98.26 282	99.72 130

APD_test1		95.87 392	96.49 374	94.00 432	99.53 210	84.01 461	99.54 164	99.32 320	95.91 399	97.99 394	99.85 77	85.49 435	99.88 166	91.96 439	98.84 244	98.12 425

diffmvs		99.14 116	99.02 120	99.51 142	99.61 179	98.96 185	99.28 313	99.49 182	98.46 126	99.72 100	99.71 202	96.50 175	99.88 166	99.31 85	99.11 213	99.67 155
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		98.86 174	98.80 169	99.03 229	99.76 80	98.79 221	99.28 313	99.91 3	97.42 286	99.67 115	99.37 340	97.53 121	99.88 166	98.98 130	97.29 342	98.42 406

PVSNet_Blended		99.08 139	98.97 132	99.42 169	99.76 80	98.79 221	98.78 421	99.91 3	96.74 341	99.67 115	99.49 302	97.53 121	99.88 166	98.98 130	99.85 92	99.60 185

viewdifsd2359ckpt07		99.11 131	99.00 127	99.43 167	99.63 161	98.73 226	99.45 234	99.54 107	98.33 143	99.62 141	99.81 124	96.17 189	99.87 173	99.27 94	99.14 206	99.69 145

viewdifsd2359ckpt11		98.78 192	98.74 177	98.89 256	99.67 132	97.04 337	99.50 194	99.58 77	98.26 153	99.56 157	99.90 32	94.36 286	99.87 173	99.49 60	98.32 278	99.77 99

viewmsd2359difaftdt		98.78 192	98.74 177	98.90 252	99.67 132	97.04 337	99.50 194	99.58 77	98.26 153	99.56 157	99.90 32	94.36 286	99.87 173	99.49 60	98.32 278	99.77 99

MVS		97.28 359	96.55 372	99.48 151	98.78 397	98.95 191	99.27 318	99.39 273	83.53 463	98.08 389	99.54 284	96.97 149	99.87 173	94.23 417	99.16 202	99.63 177

MG-MVS		99.13 118	99.02 120	99.45 159	99.57 194	98.63 236	99.07 371	99.34 302	98.99 67	99.61 146	99.82 109	97.98 112	99.87 173	97.00 347	99.80 123	99.85 46

MSDG		98.98 160	98.80 169	99.53 131	99.76 80	99.19 148	98.75 424	99.55 98	97.25 300	99.47 176	99.77 175	97.82 115	99.87 173	96.93 354	99.90 56	99.54 209

ETV-MVS		99.26 90	99.21 83	99.40 171	99.46 243	99.30 136	99.56 144	99.52 128	98.52 120	99.44 184	99.27 368	98.41 92	99.86 179	99.10 117	99.59 166	99.04 297

thisisatest0515		98.14 246	97.79 272	99.19 212	99.50 231	98.50 254	98.61 436	96.82 459	96.95 330	99.54 164	99.43 320	91.66 368	99.86 179	98.08 257	99.51 172	99.22 279

thres600view7		97.86 290	97.51 308	98.92 246	99.72 109	97.95 289	99.59 119	98.74 417	97.94 216	99.27 236	98.62 423	91.75 362	99.86 179	93.73 423	98.19 289	98.96 307

lupinMVS		99.13 118	99.01 125	99.46 158	99.51 219	98.94 195	99.05 377	99.16 356	97.86 224	99.80 72	99.56 276	97.39 124	99.86 179	98.94 138	99.85 92	99.58 200

PVSNet	96.02 17	98.85 183	98.84 166	98.89 256	99.73 105	97.28 318	98.32 452	99.60 66	97.86 224	99.50 171	99.57 273	96.75 163	99.86 179	98.56 206	99.70 150	99.54 209

MAR-MVS		98.86 174	98.63 193	99.54 123	99.37 271	99.66 69	99.45 234	99.54 107	96.61 353	99.01 290	99.40 330	97.09 141	99.86 179	97.68 299	99.53 171	99.10 285
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		99.08 139	98.96 136	99.44 164	99.62 169	98.88 202	99.25 329	99.47 216	98.05 199	99.37 206	99.81 124	96.85 153	99.85 185	98.98 130	99.25 195	99.60 185

SSM_0404		99.16 108	99.06 107	99.44 164	99.65 153	98.96 185	99.49 211	99.50 170	98.14 178	99.62 141	99.85 77	96.85 153	99.85 185	99.19 102	99.26 194	99.52 216

testing91		97.44 351	97.02 360	98.71 288	99.18 323	96.89 355	99.19 348	99.04 373	97.78 239	98.31 376	98.29 437	85.41 436	99.85 185	98.01 263	97.95 299	99.39 257

test2506		96.81 374	96.65 370	97.29 405	99.74 98	92.21 449	99.60 112	85.06 480	99.13 39	99.77 83	99.93 10	87.82 421	99.85 185	99.38 73	99.38 181	99.80 87

AllTest		98.87 171	98.72 179	99.31 189	99.86 24	98.48 257	99.56 144	99.61 59	97.85 227	99.36 212	99.85 77	95.95 199	99.85 185	96.66 367	99.83 111	99.59 196

TestCases				99.31 189	99.86 24	98.48 257		99.61 59	97.85 227	99.36 212	99.85 77	95.95 199	99.85 185	96.66 367	99.83 111	99.59 196

jason		99.13 118	99.03 114	99.45 159	99.46 243	98.87 206	99.12 361	99.26 339	98.03 208	99.79 74	99.65 238	97.02 146	99.85 185	99.02 127	99.90 56	99.65 165
jason: jason.
CNVR-MVS		99.42 54	99.30 61	99.78 69	99.62 169	99.71 57	99.26 327	99.52 128	98.82 87	99.39 202	99.71 202	98.96 26	99.85 185	98.59 199	99.80 123	99.77 99

PAPM_NR		99.04 149	98.84 166	99.66 89	99.74 98	99.44 114	99.39 271	99.38 281	97.70 250	99.28 230	99.28 365	98.34 96	99.85 185	96.96 351	99.45 177	99.69 145

viewcassd2359sk11		99.18 102	99.08 103	99.49 150	99.65 153	98.95 191	99.48 217	99.51 147	98.10 187	99.72 100	99.87 62	97.13 137	99.84 194	99.13 111	99.14 206	99.69 145

testing99		97.36 354	96.94 363	98.63 294	99.18 323	96.70 361	99.30 303	98.93 385	97.71 247	98.23 381	98.26 438	84.92 439	99.84 194	98.04 262	97.85 306	99.35 263

testing222		97.16 364	96.50 373	99.16 215	99.16 333	98.47 259	99.27 318	98.66 428	97.71 247	98.23 381	98.15 441	82.28 453	99.84 194	97.36 326	97.66 312	99.18 281

test1111		98.04 261	98.11 237	97.83 380	99.74 98	93.82 433	99.58 129	95.40 467	99.12 44	99.65 129	99.93 10	90.73 382	99.84 194	99.43 68	99.38 181	99.82 71

ECVR-MVS		98.04 261	98.05 246	98.00 364	99.74 98	94.37 428	99.59 119	94.98 468	99.13 39	99.66 120	99.93 10	90.67 383	99.84 194	99.40 70	99.38 181	99.80 87

test_yl		98.86 174	98.63 193	99.54 123	99.49 233	99.18 150	99.50 194	99.07 369	98.22 164	99.61 146	99.51 296	95.37 227	99.84 194	98.60 197	98.33 274	99.59 196

DCV-MVSNet		98.86 174	98.63 193	99.54 123	99.49 233	99.18 150	99.50 194	99.07 369	98.22 164	99.61 146	99.51 296	95.37 227	99.84 194	98.60 197	98.33 274	99.59 196

Fast-Effi-MVS+		98.70 201	98.43 214	99.51 142	99.51 219	99.28 139	99.52 175	99.47 216	96.11 392	99.01 290	99.34 350	96.20 188	99.84 194	97.88 271	98.82 246	99.39 257

TSAR-MVS + GP.		99.36 71	99.36 45	99.36 178	99.67 132	98.61 240	99.07 371	99.33 310	99.00 65	99.82 66	99.81 124	99.06 17	99.84 194	99.09 118	99.42 179	99.65 165

tpmrst		98.33 229	98.48 212	97.90 373	99.16 333	94.78 417	99.31 301	99.11 362	97.27 298	99.45 179	99.59 264	95.33 230	99.84 194	98.48 213	98.61 256	99.09 289

Vis-MVSNet		99.12 125	98.97 132	99.56 120	99.78 68	99.10 162	99.68 71	99.66 31	98.49 123	99.86 51	99.87 62	94.77 261	99.84 194	99.19 102	99.41 180	99.74 112
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 209	98.34 220	99.51 142	99.40 263	99.03 172	98.80 419	99.36 290	96.33 373	99.00 294	99.12 387	98.46 86	99.84 194	95.23 403	99.37 188	99.66 159

PatchMatch-RL		98.84 186	98.62 198	99.52 137	99.71 115	99.28 139	99.06 375	99.77 11	97.74 245	99.50 171	99.53 288	95.41 225	99.84 194	97.17 340	99.64 160	99.44 249

EPP-MVSNet		99.13 118	98.99 128	99.53 131	99.65 153	99.06 169	99.81 20	99.33 310	97.43 284	99.60 149	99.88 51	97.14 136	99.84 194	99.13 111	98.94 231	99.69 145

SSM_0407		99.13 118	99.03 114	99.43 167	99.62 169	98.88 202	99.51 184	99.50 170	98.14 178	99.37 206	99.85 77	96.85 153	99.83 208	99.19 102	99.25 195	99.60 185

testing3-2		97.84 295	97.70 287	98.24 346	99.53 210	95.37 405	99.55 159	98.67 427	98.46 126	99.27 236	99.34 350	86.58 427	99.83 208	99.32 83	98.63 255	99.52 216

testing11		97.50 344	97.10 357	98.71 288	99.20 317	96.91 353	99.29 308	98.82 405	97.89 221	98.21 384	98.40 432	85.63 434	99.83 208	98.45 218	98.04 297	99.37 261

thres100view900		97.76 309	97.45 317	98.69 290	99.72 109	97.86 295	99.59 119	98.74 417	97.93 217	99.26 241	98.62 423	91.75 362	99.83 208	93.22 428	98.18 290	98.37 412

tfpn200view9		97.72 319	97.38 330	98.72 285	99.69 125	97.96 286	99.50 194	98.73 423	97.83 231	99.17 262	98.45 430	91.67 366	99.83 208	93.22 428	98.18 290	98.37 412

test_prior				99.68 87	99.67 132	99.48 109		99.56 89					99.83 208			99.74 112

1314		98.68 203	98.54 208	99.11 221	98.89 380	98.65 233	99.27 318	99.49 182	96.89 334	97.99 394	99.56 276	97.72 119	99.83 208	97.74 291	99.27 192	98.84 313

thres400		97.77 308	97.38 330	98.92 246	99.69 125	97.96 286	99.50 194	98.73 423	97.83 231	99.17 262	98.45 430	91.67 366	99.83 208	93.22 428	98.18 290	98.96 307

casdiffmvs		99.13 118	98.98 131	99.56 120	99.65 153	99.16 153	99.56 144	99.50 170	98.33 143	99.41 195	99.86 70	95.92 202	99.83 208	99.45 67	99.16 202	99.70 142
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 32	99.48 21	99.54 123	99.78 68	99.30 136	99.89 2	99.58 77	98.56 116	99.73 95	99.69 217	98.55 80	99.82 217	99.69 34	99.85 92	99.48 233

MVS_Test		99.10 136	98.97 132	99.48 151	99.49 233	99.14 158	99.67 74	99.34 302	97.31 295	99.58 153	99.76 179	97.65 120	99.82 217	98.87 150	99.07 222	99.46 244

dp		97.75 313	97.80 271	97.59 396	99.10 344	93.71 436	99.32 297	98.88 398	96.48 365	99.08 278	99.55 279	92.67 340	99.82 217	96.52 371	98.58 259	99.24 277

RPSCF		98.22 236	98.62 198	96.99 411	99.82 51	91.58 451	99.72 53	99.44 247	96.61 353	99.66 120	99.89 40	95.92 202	99.82 217	97.46 319	99.10 219	99.57 203

PMMVS		98.80 190	98.62 198	99.34 181	99.27 299	98.70 229	98.76 423	99.31 324	97.34 292	99.21 251	99.07 389	97.20 135	99.82 217	98.56 206	98.87 241	99.52 216

UBG		97.85 291	97.48 311	98.95 240	99.25 306	97.64 306	99.24 334	98.74 417	97.90 220	98.64 352	98.20 440	88.65 408	99.81 222	98.27 236	98.40 269	99.42 251

EIA-MVS		99.18 102	99.09 102	99.45 159	99.49 233	99.18 150	99.67 74	99.53 123	97.66 255	99.40 200	99.44 318	98.10 106	99.81 222	98.94 138	99.62 163	99.35 263

Effi-MVS+		98.81 187	98.59 204	99.48 151	99.46 243	99.12 161	98.08 459	99.50 170	97.50 275	99.38 204	99.41 326	96.37 183	99.81 222	99.11 114	98.54 264	99.51 225

thres200		97.61 335	97.28 346	98.62 295	99.64 157	98.03 280	99.26 327	98.74 417	97.68 252	99.09 276	98.32 436	91.66 368	99.81 222	92.88 433	98.22 285	98.03 431

tpmvs		97.98 272	98.02 250	97.84 379	99.04 358	94.73 418	99.31 301	99.20 351	96.10 396	98.76 332	99.42 322	94.94 246	99.81 222	96.97 350	98.45 268	98.97 305

casdiffmvs_mvg		99.15 112	99.02 120	99.55 122	99.66 145	99.09 163	99.64 94	99.56 89	98.26 153	99.45 179	99.87 62	96.03 195	99.81 222	99.54 50	99.15 205	99.73 121
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	98.81 187	99.37 43	97.12 409	99.60 185	91.75 450	98.61 436	99.44 247	99.35 24	99.83 62	99.85 77	98.70 68	99.81 222	99.02 127	99.91 45	99.81 78

viewmacassd2359aftdt		99.08 139	98.94 142	99.50 147	99.66 145	98.96 185	99.51 184	99.54 107	98.27 150	99.42 190	99.89 40	95.88 206	99.80 229	99.20 101	99.11 213	99.76 106

viewmanbaseed2359cas		99.18 102	99.07 106	99.50 147	99.62 169	99.01 175	99.50 194	99.52 128	98.25 158	99.68 109	99.82 109	96.93 151	99.80 229	99.15 110	99.11 213	99.70 142

IMVS_0403		98.86 174	98.89 154	98.78 280	99.55 202	96.93 348	99.58 129	99.44 247	98.05 199	99.68 109	99.80 142	96.81 159	99.80 229	98.15 248	98.92 234	99.60 185

DPM-MVS		98.95 163	98.71 181	99.66 89	99.63 161	99.55 94	98.64 435	99.10 363	97.93 217	99.42 190	99.55 279	98.67 71	99.80 229	95.80 388	99.68 154	99.61 182

DP-MVS Recon		99.12 125	98.95 140	99.65 93	99.74 98	99.70 59	99.27 318	99.57 84	96.40 372	99.42 190	99.68 225	98.75 59	99.80 229	97.98 265	99.72 146	99.44 249

MVS_111021_LR		99.41 58	99.33 51	99.65 93	99.77 76	99.51 105	98.94 405	99.85 8	98.82 87	99.65 129	99.74 189	98.51 83	99.80 229	98.83 163	99.89 67	99.64 172

viewmambaseed2359dif		99.01 156	98.90 150	99.32 187	99.58 189	98.51 252	99.33 294	99.54 107	97.85 227	99.44 184	99.85 77	96.01 196	99.79 235	99.41 69	99.13 209	99.67 155

CS-MVS		99.50 30	99.48 21	99.54 123	99.76 80	99.42 116	99.90 1	99.55 98	98.56 116	99.78 79	99.70 206	98.65 73	99.79 235	99.65 40	99.78 132	99.41 254

Fast-Effi-MVS+-dtu		98.77 196	98.83 168	98.60 296	99.41 258	96.99 343	99.52 175	99.49 182	98.11 184	99.24 243	99.34 350	96.96 150	99.79 235	97.95 267	99.45 177	99.02 300

baseline1		98.31 230	97.95 257	99.38 177	99.50 231	98.74 225	99.59 119	98.93 385	98.41 133	99.14 265	99.60 262	94.59 274	99.79 235	98.48 213	93.29 425	99.61 182

baseline		99.15 112	99.02 120	99.53 131	99.66 145	99.14 158	99.72 53	99.48 194	98.35 140	99.42 190	99.84 92	96.07 192	99.79 235	99.51 55	99.14 206	99.67 155

PVSNet_0	94.43 19	96.09 389	95.47 396	97.94 369	99.31 289	94.34 430	97.81 461	99.70 17	97.12 312	97.46 409	98.75 420	89.71 394	99.79 235	97.69 298	81.69 463	99.68 151

API-MVS		99.04 149	99.03 114	99.06 225	99.40 263	99.31 133	99.55 159	99.56 89	98.54 118	99.33 220	99.39 334	98.76 56	99.78 241	96.98 349	99.78 132	98.07 428

OMC-MVS		99.08 139	99.04 111	99.20 211	99.67 132	98.22 270	99.28 313	99.52 128	98.07 193	99.66 120	99.81 124	97.79 116	99.78 241	97.79 283	99.81 118	99.60 185

GeoE		98.85 183	98.62 198	99.53 131	99.61 179	99.08 166	99.80 25	99.51 147	97.10 316	99.31 222	99.78 166	95.23 237	99.77 243	98.21 240	99.03 225	99.75 108

alignmvs		98.81 187	98.56 207	99.58 114	99.43 251	99.42 116	99.51 184	98.96 383	98.61 111	99.35 215	98.92 410	94.78 258	99.77 243	99.35 75	98.11 295	99.54 209

tpm cat1		97.39 353	97.36 332	97.50 399	99.17 331	93.73 435	99.43 247	99.31 324	91.27 446	98.71 336	99.08 388	94.31 291	99.77 243	96.41 376	98.50 266	99.00 301

CostFormer		97.72 319	97.73 284	97.71 388	99.15 337	94.02 432	99.54 164	99.02 376	94.67 420	99.04 287	99.35 346	92.35 352	99.77 243	98.50 212	97.94 300	99.34 266

MGCFI-Net		99.01 156	98.85 164	99.50 147	99.42 253	99.26 142	99.82 16	99.48 194	98.60 113	99.28 230	98.81 415	97.04 145	99.76 247	99.29 90	97.87 304	99.47 239

test_241102_ONE					99.84 37	99.90 3		99.48 194	99.07 56	99.91 30	99.74 189	99.20 8	99.76 247

MDTV_nov1_ep13			98.32 222		99.11 341	94.44 426	99.27 318	98.74 417	97.51 274	99.40 200	99.62 255	94.78 258	99.76 247	97.59 303	98.81 248

viewdifsd2359ckpt09		99.01 156	98.87 158	99.40 171	99.62 169	98.79 221	99.44 241	99.51 147	97.76 241	99.35 215	99.69 217	96.42 181	99.75 250	98.97 135	99.11 213	99.66 159

sasdasda		99.02 152	98.86 161	99.51 142	99.42 253	99.32 129	99.80 25	99.48 194	98.63 108	99.31 222	98.81 415	97.09 141	99.75 250	99.27 94	97.90 301	99.47 239

canonicalmvs		99.02 152	98.86 161	99.51 142	99.42 253	99.32 129	99.80 25	99.48 194	98.63 108	99.31 222	98.81 415	97.09 141	99.75 250	99.27 94	97.90 301	99.47 239

Effi-MVS+-dtu		98.78 192	98.89 154	98.47 319	99.33 281	96.91 353	99.57 137	99.30 329	98.47 125	99.41 195	98.99 400	96.78 161	99.74 253	98.73 176	99.38 181	98.74 329

patchmatchnet-post											98.70 421	94.79 257	99.74 253

SCA		98.19 240	98.16 230	98.27 345	99.30 290	95.55 396	99.07 371	98.97 381	97.57 264	99.43 187	99.57 273	92.72 335	99.74 253	97.58 304	99.20 200	99.52 216

BH-untuned		98.42 219	98.36 218	98.59 297	99.49 233	96.70 361	99.27 318	99.13 360	97.24 302	98.80 327	99.38 337	95.75 213	99.74 253	97.07 345	99.16 202	99.33 267

BH-RMVSNet		98.41 221	98.08 242	99.40 171	99.41 258	98.83 215	99.30 303	98.77 413	97.70 250	98.94 305	99.65 238	92.91 330	99.74 253	96.52 371	99.55 170	99.64 172

MVS_111021_HR		99.41 58	99.32 53	99.66 89	99.72 109	99.47 111	98.95 403	99.85 8	98.82 87	99.54 164	99.73 195	98.51 83	99.74 253	98.91 144	99.88 74	99.77 99

test_post											65.99 474	94.65 272	99.73 259

XVG-ACMP-BASELINE		97.83 298	97.71 286	98.20 348	99.11 341	96.33 377	99.41 259	99.52 128	98.06 197	99.05 286	99.50 299	89.64 396	99.73 259	97.73 292	97.38 339	98.53 394

HyFIR lowres test		99.11 131	98.92 145	99.65 93	99.90 4	99.37 121	99.02 385	99.91 3	97.67 254	99.59 152	99.75 184	95.90 204	99.73 259	99.53 52	99.02 227	99.86 42

DeepMVS_CX				93.34 435	99.29 294	82.27 464		99.22 347	85.15 461	96.33 431	99.05 392	90.97 380	99.73 259	93.57 425	97.77 309	98.01 432

Patchmatch-test		97.93 278	97.65 292	98.77 281	99.18 323	97.07 332	99.03 382	99.14 359	96.16 387	98.74 333	99.57 273	94.56 276	99.72 263	93.36 427	99.11 213	99.52 216

LPG-MVS_test		98.22 236	98.13 235	98.49 312	99.33 281	97.05 334	99.58 129	99.55 98	97.46 277	99.24 243	99.83 97	92.58 342	99.72 263	98.09 253	97.51 325	98.68 347

LGP-MVS_train				98.49 312	99.33 281	97.05 334		99.55 98	97.46 277	99.24 243	99.83 97	92.58 342	99.72 263	98.09 253	97.51 325	98.68 347

BH-w/o		98.00 270	97.89 266	98.32 337	99.35 275	96.20 383	99.01 390	98.90 395	96.42 370	98.38 372	99.00 398	95.26 234	99.72 263	96.06 381	98.61 256	99.03 298

ACMP	97.20 11	98.06 255	97.94 259	98.45 322	99.37 271	97.01 341	99.44 241	99.49 182	97.54 270	98.45 369	99.79 159	91.95 358	99.72 263	97.91 269	97.49 330	98.62 377
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 265	97.90 262	98.40 330	99.23 310	96.80 359	99.70 58	99.60 66	97.12 312	98.18 386	99.70 206	91.73 364	99.72 263	98.39 223	97.45 332	98.68 347
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		99.06 144	98.93 144	99.45 159	99.63 161	98.96 185	99.50 194	99.51 147	97.83 231	99.28 230	99.80 142	96.68 167	99.71 269	99.05 122	99.12 211	99.68 151

test_post1							99.23 337				65.14 475	94.18 296	99.71 269	97.58 304

ADS-MVSNet		98.20 239	98.08 242	98.56 305	99.33 281	96.48 372	99.23 337	99.15 357	96.24 380	99.10 273	99.67 231	94.11 297	99.71 269	96.81 359	99.05 223	99.48 233

JIA-IIPM		97.50 344	97.02 360	98.93 244	98.73 406	97.80 297	99.30 303	98.97 381	91.73 445	98.91 308	94.86 463	95.10 241	99.71 269	97.58 304	97.98 298	99.28 271

EPMVS		97.82 301	97.65 292	98.35 334	98.88 381	95.98 387	99.49 211	94.71 470	97.57 264	99.26 241	99.48 308	92.46 349	99.71 269	97.87 273	99.08 221	99.35 263

TDRefinement		95.42 400	94.57 408	97.97 366	89.83 473	96.11 386	99.48 217	98.75 414	96.74 341	96.68 428	99.88 51	88.65 408	99.71 269	98.37 226	82.74 462	98.09 427

ACMM	97.58 5	98.37 227	98.34 220	98.48 314	99.41 258	97.10 328	99.56 144	99.45 238	98.53 119	99.04 287	99.85 77	93.00 326	99.71 269	98.74 174	97.45 332	98.64 368
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 275	97.77 277	98.57 301	99.59 187	96.61 368	99.45 234	99.08 366	98.21 166	98.88 313	99.80 142	88.66 407	99.70 276	98.58 200	97.72 310	99.39 257

CHOSEN 280x420		99.12 125	99.13 93	99.08 222	99.66 145	97.89 292	98.43 446	99.71 15	98.88 81	99.62 141	99.76 179	96.63 168	99.70 276	99.46 66	99.99 1	99.66 159

EC-MVSNet		99.44 49	99.39 39	99.58 114	99.56 198	99.49 107	99.88 4	99.58 77	98.38 135	99.73 95	99.69 217	98.20 102	99.70 276	99.64 42	99.82 115	99.54 209

PatchmatchNet		98.31 230	98.36 218	98.19 349	99.16 333	95.32 406	99.27 318	98.92 388	97.37 290	99.37 206	99.58 268	94.90 251	99.70 276	97.43 322	99.21 199	99.54 209
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 250	97.99 252	98.44 325	99.41 258	96.96 347	99.60 112	99.56 89	98.09 188	98.15 387	99.91 25	90.87 381	99.70 276	98.88 147	97.45 332	98.67 355
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 344	96.90 364	99.29 197	99.23 310	98.78 224	99.32 297	98.90 395	97.52 273	98.56 362	98.09 446	84.72 441	99.69 281	97.86 274	97.88 303	99.39 257

HQP_MVS		98.27 235	98.22 228	98.44 325	99.29 294	96.97 345	99.39 271	99.47 216	98.97 73	99.11 270	99.61 259	92.71 337	99.69 281	97.78 284	97.63 313	98.67 355

plane_prior5								99.47 216					99.69 281	97.78 284	97.63 313	98.67 355

D2MVS		98.41 221	98.50 211	98.15 354	99.26 302	96.62 367	99.40 267	99.61 59	97.71 247	98.98 297	99.36 343	96.04 194	99.67 284	98.70 179	97.41 337	98.15 424

IS-MVSNet		99.05 148	98.87 158	99.57 118	99.73 105	99.32 129	99.75 42	99.20 351	98.02 211	99.56 157	99.86 70	96.54 173	99.67 284	98.09 253	99.13 209	99.73 121

CLD-MVS		98.16 244	98.10 238	98.33 335	99.29 294	96.82 358	98.75 424	99.44 247	97.83 231	99.13 266	99.55 279	92.92 328	99.67 284	98.32 233	97.69 311	98.48 398
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 361	97.30 343	97.09 410	99.43 251	93.31 442	99.73 51	98.87 400	98.83 86	99.28 230	99.80 142	84.45 442	99.66 287	97.88 271	97.45 332	98.30 414

AUN-MVS		96.88 372	96.31 378	98.59 297	99.48 240	97.04 337	99.27 318	99.22 347	97.44 283	98.51 365	99.41 326	91.97 357	99.66 287	97.71 295	83.83 460	99.07 295

UniMVSNet_ETH3D		97.32 358	96.81 366	98.87 263	99.40 263	97.46 312	99.51 184	99.53 123	95.86 400	98.54 364	99.77 175	82.44 451	99.66 287	98.68 184	97.52 324	99.50 229

OPM-MVS		98.19 240	98.10 238	98.45 322	98.88 381	97.07 332	99.28 313	99.38 281	98.57 115	99.22 248	99.81 124	92.12 354	99.66 287	98.08 257	97.54 322	98.61 386
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 281	97.78 275	98.32 337	99.46 243	96.68 365	99.56 144	99.54 107	98.41 133	97.79 405	99.87 62	90.18 390	99.66 287	98.05 261	97.18 347	98.62 377

IMVS_0407		98.86 174	98.91 148	98.72 285	99.55 202	96.93 348	99.50 194	99.44 247	98.05 199	99.66 120	99.80 142	97.13 137	99.65 292	98.15 248	98.92 234	99.60 185

hse-mvs2		97.50 344	97.14 354	98.59 297	99.49 233	97.05 334	99.28 313	99.22 347	98.94 76	99.66 120	99.42 322	94.93 247	99.65 292	99.48 63	83.80 461	99.08 290

VPA-MVSNet		98.29 233	97.95 257	99.30 194	99.16 333	99.54 96	99.50 194	99.58 77	98.27 150	99.35 215	99.37 340	92.53 344	99.65 292	99.35 75	94.46 406	98.72 331

TR-MVS		97.76 309	97.41 328	98.82 272	99.06 353	97.87 293	98.87 413	98.56 431	96.63 352	98.68 344	99.22 374	92.49 345	99.65 292	95.40 399	97.79 308	98.95 309

reproduce_monomvs		97.89 285	97.87 267	97.96 368	99.51 219	95.45 401	99.60 112	99.25 341	99.17 34	98.85 321	99.49 302	89.29 399	99.64 296	99.35 75	96.31 363	98.78 317

gm-plane-assit					98.54 426	92.96 444			94.65 421		99.15 382		99.64 296	97.56 309

HQP4-MVS										98.66 345			99.64 296			98.64 368

HQP-MVS		98.02 265	97.90 262	98.37 333	99.19 320	96.83 356	98.98 396	99.39 273	98.24 160	98.66 345	99.40 330	92.47 346	99.64 296	97.19 337	97.58 318	98.64 368

PAPM		97.59 336	97.09 358	99.07 223	99.06 353	98.26 268	98.30 453	99.10 363	94.88 415	98.08 389	99.34 350	96.27 186	99.64 296	89.87 447	98.92 234	99.31 269

TAPA-MVS	97.07 15	97.74 315	97.34 337	98.94 242	99.70 120	97.53 309	99.25 329	99.51 147	91.90 444	99.30 226	99.63 250	98.78 52	99.64 296	88.09 454	99.87 77	99.65 165
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 225	98.09 241	99.24 207	99.26 302	99.32 129	99.56 144	99.55 98	97.45 280	98.71 336	99.83 97	93.23 321	99.63 302	98.88 147	96.32 362	98.76 323

ITE_SJBPF				98.08 357	99.29 294	96.37 375		98.92 388	98.34 141	98.83 322	99.75 184	91.09 378	99.62 303	95.82 386	97.40 338	98.25 418

LF4IMVS		97.52 341	97.46 316	97.70 389	98.98 369	95.55 396	99.29 308	98.82 405	98.07 193	98.66 345	99.64 244	89.97 391	99.61 304	97.01 346	96.68 352	97.94 439

tpm		97.67 330	97.55 301	98.03 359	99.02 360	95.01 413	99.43 247	98.54 433	96.44 368	99.12 268	99.34 350	91.83 361	99.60 305	97.75 290	96.46 358	99.48 233

tpm2		97.44 351	97.34 337	97.74 387	99.15 337	94.36 429	99.45 234	98.94 384	93.45 434	98.90 310	99.44 318	91.35 374	99.59 306	97.31 328	98.07 296	99.29 270

SSM_04072		99.06 144	98.96 136	99.35 180	99.62 169	98.88 202	99.25 329	99.47 216	98.05 199	99.37 206	99.81 124	96.85 153	99.58 307	98.98 130	99.25 195	99.60 185

SD_0403		97.55 338	97.53 305	97.62 392	99.61 179	93.64 439	99.72 53	99.44 247	98.03 208	98.62 357	99.39 334	96.06 193	99.57 308	87.88 456	99.01 228	99.66 159

baseline2		97.87 288	97.55 301	98.82 272	99.18 323	98.02 281	99.41 259	96.58 464	96.97 327	96.51 429	99.17 379	93.43 316	99.57 308	97.71 295	99.03 225	98.86 311

MS-PatchMatch		97.24 363	97.32 341	96.99 411	98.45 429	93.51 441	98.82 417	99.32 320	97.41 287	98.13 388	99.30 361	88.99 401	99.56 310	95.68 392	99.80 123	97.90 442

TinyColmap		97.12 366	96.89 365	97.83 380	99.07 351	95.52 399	98.57 439	98.74 417	97.58 263	97.81 404	99.79 159	88.16 415	99.56 310	95.10 404	97.21 345	98.39 410

USDC		97.34 356	97.20 351	97.75 385	99.07 351	95.20 408	98.51 443	99.04 373	97.99 212	98.31 376	99.86 70	89.02 400	99.55 312	95.67 393	97.36 340	98.49 397

MSLP-MVS++		99.46 41	99.47 23	99.44 164	99.60 185	99.16 153	99.41 259	99.71 15	98.98 70	99.45 179	99.78 166	99.19 10	99.54 313	99.28 91	99.84 100	99.63 177

UWE-MVS-28		97.36 354	97.24 350	97.75 385	98.84 390	94.44 426	99.24 334	97.58 453	97.98 213	99.00 294	99.00 398	91.35 374	99.53 314	93.75 422	98.39 270	99.27 275

TAMVS		99.12 125	99.08 103	99.24 207	99.46 243	98.55 244	99.51 184	99.46 227	98.09 188	99.45 179	99.82 109	98.34 96	99.51 315	98.70 179	98.93 232	99.67 155

EPNet_dtu		98.03 263	97.96 255	98.23 347	98.27 432	95.54 398	99.23 337	98.75 414	99.02 60	97.82 403	99.71 202	96.11 191	99.48 316	93.04 431	99.65 159	99.69 145
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 376	96.22 380	97.97 366	97.00 454	96.28 379	98.66 433	99.03 375	96.61 353	96.93 426	99.79 159	87.20 424	99.47 317	96.65 369	94.13 413	98.16 423

EG-PatchMatch MVS		95.97 391	95.69 392	96.81 418	97.78 439	92.79 445	99.16 352	98.93 385	96.16 387	94.08 447	99.22 374	82.72 449	99.47 317	95.67 393	97.50 327	98.17 422

myMVS_eth3d28		97.69 324	97.34 337	98.73 283	99.27 299	97.52 310	99.33 294	98.78 412	98.03 208	98.82 324	98.49 428	86.64 426	99.46 319	98.44 219	98.24 284	99.23 278

MVP-Stereo		97.81 303	97.75 282	97.99 365	97.53 443	96.60 369	98.96 400	98.85 402	97.22 304	97.23 416	99.36 343	95.28 231	99.46 319	95.51 395	99.78 132	97.92 441
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 211	98.67 185	98.30 339	99.35 275	95.59 395	99.50 194	99.55 98	98.60 113	99.39 202	99.83 97	94.48 282	99.45 321	98.75 173	98.56 262	99.85 46

test-LLR		98.06 255	97.90 262	98.55 307	98.79 394	97.10 328	98.67 430	97.75 449	97.34 292	98.61 358	98.85 412	94.45 284	99.45 321	97.25 331	99.38 181	99.10 285

TESTMET0.1,1		97.55 338	97.27 349	98.40 330	98.93 374	96.53 370	98.67 430	97.61 452	96.96 328	98.64 352	99.28 365	88.63 410	99.45 321	97.30 329	99.38 181	99.21 280

test-mter		97.49 349	97.13 356	98.55 307	98.79 394	97.10 328	98.67 430	97.75 449	96.65 348	98.61 358	98.85 412	88.23 414	99.45 321	97.25 331	99.38 181	99.10 285

mvs_anonymous		99.03 151	98.99 128	99.16 215	99.38 268	98.52 250	99.51 184	99.38 281	97.79 237	99.38 204	99.81 124	97.30 130	99.45 321	99.35 75	98.99 229	99.51 225

tfpnnormal		97.84 295	97.47 314	98.98 235	99.20 317	99.22 147	99.64 94	99.61 59	96.32 374	98.27 380	99.70 206	93.35 320	99.44 326	95.69 391	95.40 389	98.27 416

v7n		97.87 288	97.52 306	98.92 246	98.76 404	98.58 242	99.84 12	99.46 227	96.20 383	98.91 308	99.70 206	94.89 252	99.44 326	96.03 382	93.89 418	98.75 325

jajsoiax		98.43 218	98.28 225	98.88 259	98.60 421	98.43 261	99.82 16	99.53 123	98.19 168	98.63 354	99.80 142	93.22 323	99.44 326	99.22 99	97.50 327	98.77 321

mvs_tets		98.40 224	98.23 227	98.91 250	98.67 414	98.51 252	99.66 81	99.53 123	98.19 168	98.65 351	99.81 124	92.75 332	99.44 326	99.31 85	97.48 331	98.77 321

sc_t1		95.75 395	95.05 402	97.87 375	98.83 391	94.61 423	99.21 343	99.45 238	87.45 457	97.97 396	99.85 77	81.19 456	99.43 330	98.27 236	93.20 427	99.57 203

Vis-MVSNet (Re-imp)		98.87 171	98.72 179	99.31 189	99.71 115	98.88 202	99.80 25	99.44 247	97.91 219	99.36 212	99.78 166	95.49 223	99.43 330	97.91 269	99.11 213	99.62 180

OPU-MVS				99.64 99	99.56 198	99.72 55	99.60 112				99.70 206	99.27 6	99.42 332	98.24 239	99.80 123	99.79 91

Anonymous20231211		97.88 286	97.54 304	98.90 252	99.71 115	98.53 246	99.48 217	99.57 84	94.16 425	98.81 325	99.68 225	93.23 321	99.42 332	98.84 160	94.42 408	98.76 323

ttmdpeth		97.80 305	97.63 296	98.29 340	98.77 402	97.38 315	99.64 94	99.36 290	98.78 96	96.30 432	99.58 268	92.34 353	99.39 334	98.36 228	95.58 384	98.10 426

VPNet		97.84 295	97.44 322	99.01 231	99.21 315	98.94 195	99.48 217	99.57 84	98.38 135	99.28 230	99.73 195	88.89 402	99.39 334	99.19 102	93.27 426	98.71 333

nrg030		98.64 208	98.42 215	99.28 201	99.05 356	99.69 61	99.81 20	99.46 227	98.04 206	99.01 290	99.82 109	96.69 165	99.38 336	99.34 80	94.59 405	98.78 317

GA-MVS		97.85 291	97.47 314	99.00 233	99.38 268	97.99 283	98.57 439	99.15 357	97.04 323	98.90 310	99.30 361	89.83 393	99.38 336	96.70 364	98.33 274	99.62 180

UniMVSNet (Re)		98.29 233	98.00 251	99.13 220	99.00 363	99.36 124	99.49 211	99.51 147	97.95 215	98.97 299	99.13 384	96.30 185	99.38 336	98.36 228	93.34 424	98.66 364

FIs		98.78 192	98.63 193	99.23 209	99.18 323	99.54 96	99.83 15	99.59 72	98.28 148	98.79 329	99.81 124	96.75 163	99.37 339	99.08 119	96.38 360	98.78 317

PS-MVSNAJss		98.92 165	98.92 145	98.90 252	98.78 397	98.53 246	99.78 32	99.54 107	98.07 193	99.00 294	99.76 179	99.01 19	99.37 339	99.13 111	97.23 344	98.81 314

CDS-MVSNet		99.09 137	99.03 114	99.25 204	99.42 253	98.73 226	99.45 234	99.46 227	98.11 184	99.46 178	99.77 175	98.01 111	99.37 339	98.70 179	98.92 234	99.66 159
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 395	95.16 400	97.51 398	99.30 290	93.69 437	98.88 411	95.78 465	85.09 462	98.78 330	92.65 465	91.29 376	99.37 339	94.85 409	99.85 92	99.46 244

v1192		97.81 303	97.44 322	98.91 250	98.88 381	98.68 230	99.51 184	99.34 302	96.18 385	99.20 254	99.34 350	94.03 301	99.36 343	95.32 401	95.18 393	98.69 342

EI-MVSNet		98.67 204	98.67 185	98.68 291	99.35 275	97.97 284	99.50 194	99.38 281	96.93 333	99.20 254	99.83 97	97.87 113	99.36 343	98.38 224	97.56 320	98.71 333

MVSTER		98.49 213	98.32 222	99.00 233	99.35 275	99.02 173	99.54 164	99.38 281	97.41 287	99.20 254	99.73 195	93.86 309	99.36 343	98.87 150	97.56 320	98.62 377

gg-mvs-nofinetune		96.17 387	95.32 399	98.73 283	98.79 394	98.14 274	99.38 276	94.09 471	91.07 449	98.07 392	91.04 469	89.62 397	99.35 346	96.75 361	99.09 220	98.68 347

pm-mvs1		97.68 327	97.28 346	98.88 259	99.06 353	98.62 238	99.50 194	99.45 238	96.32 374	97.87 401	99.79 159	92.47 346	99.35 346	97.54 311	93.54 422	98.67 355

OurMVSNet-221017-0		97.88 286	97.77 277	98.19 349	98.71 410	96.53 370	99.88 4	99.00 378	97.79 237	98.78 330	99.94 6	91.68 365	99.35 346	97.21 333	96.99 351	98.69 342

EGC-MVSNET		82.80 433	77.86 439	97.62 392	97.91 436	96.12 385	99.33 294	99.28 335	8.40 477	25.05 478	99.27 368	84.11 443	99.33 349	89.20 449	98.22 285	97.42 451

pmmvs6		96.53 379	96.09 384	97.82 382	98.69 412	95.47 400	99.37 278	99.47 216	93.46 433	97.41 410	99.78 166	87.06 425	99.33 349	96.92 356	92.70 434	98.65 366

V42		98.06 255	97.79 272	98.86 266	98.98 369	98.84 212	99.69 62	99.34 302	96.53 360	99.30 226	99.37 340	94.67 269	99.32 351	97.57 308	94.66 403	98.42 406

lessismore_v0				97.79 384	98.69 412	95.44 403		94.75 469		95.71 438	99.87 62	88.69 406	99.32 351	95.89 385	94.93 400	98.62 377

OpenMVS_ROB	92.34 20	94.38 412	93.70 418	96.41 423	97.38 445	93.17 443	99.06 375	98.75 414	86.58 460	94.84 445	98.26 438	81.53 454	99.32 351	89.01 450	97.87 304	96.76 454

v8		97.95 277	97.63 296	98.93 244	98.95 373	98.81 220	99.80 25	99.41 263	96.03 397	99.10 273	99.42 322	94.92 249	99.30 354	96.94 353	94.08 415	98.66 364

v1921920		97.80 305	97.45 317	98.84 270	98.80 393	98.53 246	99.52 175	99.34 302	96.15 389	99.24 243	99.47 311	93.98 303	99.29 355	95.40 399	95.13 395	98.69 342

anonymousdsp		98.44 217	98.28 225	98.94 242	98.50 427	98.96 185	99.77 34	99.50 170	97.07 318	98.87 316	99.77 175	94.76 262	99.28 356	98.66 186	97.60 316	98.57 392

MVSFormer		99.17 106	99.12 95	99.29 197	99.51 219	98.94 195	99.88 4	99.46 227	97.55 267	99.80 72	99.65 238	97.39 124	99.28 356	99.03 125	99.85 92	99.65 165

test_djsdf		98.67 204	98.57 205	98.98 235	98.70 411	98.91 200	99.88 4	99.46 227	97.55 267	99.22 248	99.88 51	95.73 214	99.28 356	99.03 125	97.62 315	98.75 325

VortexMVS		98.67 204	98.66 188	98.68 291	99.62 169	97.96 286	99.59 119	99.41 263	98.13 180	99.31 222	99.70 206	95.48 224	99.27 359	99.40 70	97.32 341	98.79 315

SSC-MVS3.2		97.34 356	97.15 353	97.93 370	99.02 360	95.76 392	99.48 217	99.58 77	97.62 259	99.09 276	99.53 288	87.95 417	99.27 359	96.42 374	95.66 382	98.75 325

cascas		97.69 324	97.43 326	98.48 314	98.60 421	97.30 317	98.18 457	99.39 273	92.96 438	98.41 370	98.78 419	93.77 312	99.27 359	98.16 246	98.61 256	98.86 311

v144192		97.92 281	97.60 299	98.87 263	98.83 391	98.65 233	99.55 159	99.34 302	96.20 383	99.32 221	99.40 330	94.36 286	99.26 362	96.37 378	95.03 397	98.70 338

dmvs_re		98.08 253	98.16 230	97.85 377	99.55 202	94.67 422	99.70 58	98.92 388	98.15 173	99.06 284	99.35 346	93.67 315	99.25 363	97.77 287	97.25 343	99.64 172

v2v482		98.06 255	97.77 277	98.92 246	98.90 379	98.82 218	99.57 137	99.36 290	96.65 348	99.19 257	99.35 346	94.20 293	99.25 363	97.72 294	94.97 398	98.69 342

v1240		97.69 324	97.32 341	98.79 278	98.85 388	98.43 261	99.48 217	99.36 290	96.11 392	99.27 236	99.36 343	93.76 313	99.24 365	94.46 413	95.23 392	98.70 338

WBMVS		97.74 315	97.50 309	98.46 320	99.24 308	97.43 313	99.21 343	99.42 260	97.45 280	98.96 301	99.41 326	88.83 403	99.23 366	98.94 138	96.02 368	98.71 333

v1144		97.98 272	97.69 288	98.85 269	98.87 384	98.66 232	99.54 164	99.35 297	96.27 378	99.23 247	99.35 346	94.67 269	99.23 366	96.73 362	95.16 394	98.68 347

v10		97.85 291	97.52 306	98.86 266	98.99 366	98.67 231	99.75 42	99.41 263	95.70 401	98.98 297	99.41 326	94.75 263	99.23 366	96.01 384	94.63 404	98.67 355

WR-MVS_H		98.13 247	97.87 267	98.90 252	99.02 360	98.84 212	99.70 58	99.59 72	97.27 298	98.40 371	99.19 378	95.53 221	99.23 366	98.34 230	93.78 420	98.61 386

miper_enhance_ethall		98.16 244	98.08 242	98.41 328	98.96 372	97.72 301	98.45 445	99.32 320	96.95 330	98.97 299	99.17 379	97.06 144	99.22 370	97.86 274	95.99 371	98.29 415

GG-mvs-BLEND				98.45 322	98.55 425	98.16 272	99.43 247	93.68 472		97.23 416	98.46 429	89.30 398	99.22 370	95.43 398	98.22 285	97.98 437

FC-MVSNet-test		98.75 197	98.62 198	99.15 219	99.08 350	99.45 113	99.86 11	99.60 66	98.23 163	98.70 342	99.82 109	96.80 160	99.22 370	99.07 120	96.38 360	98.79 315

UniMVSNet_NR-MVSNet		98.22 236	97.97 254	98.96 238	98.92 376	98.98 178	99.48 217	99.53 123	97.76 241	98.71 336	99.46 315	96.43 180	99.22 370	98.57 203	92.87 432	98.69 342

DU-MVS		98.08 253	97.79 272	98.96 238	98.87 384	98.98 178	99.41 259	99.45 238	97.87 223	98.71 336	99.50 299	94.82 254	99.22 370	98.57 203	92.87 432	98.68 347

cl____		98.01 268	97.84 270	98.55 307	99.25 306	97.97 284	98.71 428	99.34 302	96.47 367	98.59 361	99.54 284	95.65 217	99.21 375	97.21 333	95.77 377	98.46 403

WR-MVS		98.06 255	97.73 284	99.06 225	98.86 387	99.25 144	99.19 348	99.35 297	97.30 296	98.66 345	99.43 320	93.94 304	99.21 375	98.58 200	94.28 410	98.71 333

test_0402		96.64 377	96.24 379	97.85 377	98.85 388	96.43 374	99.44 241	99.26 339	93.52 431	96.98 424	99.52 292	88.52 411	99.20 377	92.58 438	97.50 327	97.93 440

icg_test_0407_2		98.79 191	98.86 161	98.57 301	99.55 202	96.93 348	99.07 371	99.44 247	98.05 199	99.66 120	99.80 142	97.13 137	99.18 378	98.15 248	98.92 234	99.60 185

SixPastTwentyTwo		97.50 344	97.33 340	98.03 359	98.65 415	96.23 382	99.77 34	98.68 426	97.14 309	97.90 399	99.93 10	90.45 384	99.18 378	97.00 347	96.43 359	98.67 355

cl22		97.85 291	97.64 295	98.48 314	99.09 347	97.87 293	98.60 438	99.33 310	97.11 315	98.87 316	99.22 374	92.38 351	99.17 380	98.21 240	95.99 371	98.42 406

tt0320		95.71 397	95.07 401	97.62 392	99.05 356	95.02 412	99.25 329	99.52 128	86.81 458	97.97 396	99.72 199	83.58 446	99.15 381	96.38 377	93.35 423	98.68 347

WB-MVSnew		97.65 332	97.65 292	97.63 391	98.78 397	97.62 307	99.13 358	98.33 437	97.36 291	99.07 279	98.94 406	95.64 218	99.15 381	92.95 432	98.68 254	96.12 461

IterMVS-SCA-FT		97.82 301	97.75 282	98.06 358	99.57 194	96.36 376	99.02 385	99.49 182	97.18 306	98.71 336	99.72 199	92.72 335	99.14 383	97.44 321	95.86 376	98.67 355

pmmvs5		97.52 341	97.30 343	98.16 351	98.57 424	96.73 360	99.27 318	98.90 395	96.14 390	98.37 373	99.53 288	91.54 371	99.14 383	97.51 313	95.87 375	98.63 375

v148		97.79 307	97.55 301	98.50 311	98.74 405	97.72 301	99.54 164	99.33 310	96.26 379	98.90 310	99.51 296	94.68 268	99.14 383	97.83 278	93.15 429	98.63 375

IMVS_0404		98.53 212	98.52 210	98.55 307	99.55 202	96.93 348	99.20 346	99.44 247	98.05 199	98.96 301	99.80 142	94.66 271	99.13 386	98.15 248	98.92 234	99.60 185

miper_ehance_all_eth		98.18 242	98.10 238	98.41 328	99.23 310	97.72 301	98.72 427	99.31 324	96.60 356	98.88 313	99.29 363	97.29 131	99.13 386	97.60 302	95.99 371	98.38 411

NR-MVSNet		97.97 275	97.61 298	99.02 230	98.87 384	99.26 142	99.47 227	99.42 260	97.63 257	97.08 422	99.50 299	95.07 242	99.13 386	97.86 274	93.59 421	98.68 347

IterMVS		97.83 298	97.77 277	98.02 361	99.58 189	96.27 380	99.02 385	99.48 194	97.22 304	98.71 336	99.70 206	92.75 332	99.13 386	97.46 319	96.00 370	98.67 355
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 413	94.90 404	91.84 440	97.24 449	80.01 470	98.52 442	99.48 194	89.01 454	91.99 457	99.67 231	85.67 433	99.13 386	95.44 397	97.03 350	96.39 458
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 260	97.96 255	98.33 335	99.26 302	97.38 315	98.56 441	99.31 324	96.65 348	98.88 313	99.52 292	96.58 171	99.12 391	97.39 324	95.53 387	98.47 400

pmmvs4		98.13 247	97.90 262	98.81 275	98.61 420	98.87 206	98.99 393	99.21 350	96.44 368	99.06 284	99.58 268	95.90 204	99.11 392	97.18 339	96.11 367	98.46 403

TransMVSNet (Re)		97.15 365	96.58 371	98.86 266	99.12 339	98.85 210	99.49 211	98.91 393	95.48 404	97.16 420	99.80 142	93.38 317	99.11 392	94.16 419	91.73 439	98.62 377

ambc				93.06 438	92.68 469	82.36 463	98.47 444	98.73 423		95.09 443	97.41 452	55.55 469	99.10 394	96.42 374	91.32 440	97.71 443

Baseline_NR-MVSNet		97.76 309	97.45 317	98.68 291	99.09 347	98.29 266	99.41 259	98.85 402	95.65 402	98.63 354	99.67 231	94.82 254	99.10 394	98.07 260	92.89 431	98.64 368

test_vis3_rt		87.04 429	85.81 432	90.73 444	93.99 468	81.96 465	99.76 37	90.23 479	92.81 440	81.35 467	91.56 467	40.06 475	99.07 396	94.27 416	88.23 454	91.15 467

CP-MVSNet		98.09 251	97.78 275	99.01 231	98.97 371	99.24 145	99.67 74	99.46 227	97.25 300	98.48 368	99.64 244	93.79 311	99.06 397	98.63 190	94.10 414	98.74 329

PS-CasMVS		97.93 278	97.59 300	98.95 240	98.99 366	99.06 169	99.68 71	99.52 128	97.13 310	98.31 376	99.68 225	92.44 350	99.05 398	98.51 211	94.08 415	98.75 325

K. test v3		97.10 367	96.79 367	98.01 362	98.72 408	96.33 377	99.87 8	97.05 456	97.59 261	96.16 434	99.80 142	88.71 405	99.04 399	96.69 365	96.55 357	98.65 366

new_pmnet		96.38 383	96.03 385	97.41 401	98.13 435	95.16 411	99.05 377	99.20 351	93.94 426	97.39 413	98.79 418	91.61 370	99.04 399	90.43 445	95.77 377	98.05 430

DIV-MVS_self_test		98.01 268	97.85 269	98.48 314	99.24 308	97.95 289	98.71 428	99.35 297	96.50 361	98.60 360	99.54 284	95.72 215	99.03 401	97.21 333	95.77 377	98.46 403

IterMVS-LS		98.46 216	98.42 215	98.58 300	99.59 187	98.00 282	99.37 278	99.43 258	96.94 332	99.07 279	99.59 264	97.87 113	99.03 401	98.32 233	95.62 383	98.71 333
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 332	97.68 289	97.55 397	98.62 418	94.97 414	98.84 415	99.30 329	96.83 339	98.19 385	99.34 350	97.01 148	99.02 403	95.00 407	96.01 369	98.64 368

Patchmtry		97.75 313	97.40 329	98.81 275	99.10 344	98.87 206	99.11 367	99.33 310	94.83 417	98.81 325	99.38 337	94.33 289	99.02 403	96.10 380	95.57 385	98.53 394

N_pmnet		94.95 407	95.83 390	92.31 439	98.47 428	79.33 471	99.12 361	92.81 477	93.87 427	97.68 406	99.13 384	93.87 308	99.01 405	91.38 442	96.19 365	98.59 390

CR-MVSNet		98.17 243	97.93 260	98.87 263	99.18 323	98.49 255	99.22 341	99.33 310	96.96 328	99.56 157	99.38 337	94.33 289	99.00 406	94.83 410	98.58 259	99.14 282

c3_l		98.12 249	98.04 247	98.38 332	99.30 290	97.69 305	98.81 418	99.33 310	96.67 346	98.83 322	99.34 350	97.11 140	98.99 407	97.58 304	95.34 390	98.48 398

test0.0.03 1		97.71 322	97.42 327	98.56 305	98.41 431	97.82 296	98.78 421	98.63 429	97.34 292	98.05 393	98.98 402	94.45 284	98.98 408	95.04 406	97.15 348	98.89 310

PatchT		97.03 369	96.44 375	98.79 278	98.99 366	98.34 265	99.16 352	99.07 369	92.13 443	99.52 168	97.31 456	94.54 279	98.98 408	88.54 452	98.73 251	99.03 298

GBi-Net		97.68 327	97.48 311	98.29 340	99.51 219	97.26 321	99.43 247	99.48 194	96.49 362	99.07 279	99.32 358	90.26 386	98.98 408	97.10 341	96.65 353	98.62 377

test1		97.68 327	97.48 311	98.29 340	99.51 219	97.26 321	99.43 247	99.48 194	96.49 362	99.07 279	99.32 358	90.26 386	98.98 408	97.10 341	96.65 353	98.62 377

FMVSNet3		98.03 263	97.76 281	98.84 270	99.39 266	98.98 178	99.40 267	99.38 281	96.67 346	99.07 279	99.28 365	92.93 327	98.98 408	97.10 341	96.65 353	98.56 393

FMVSNet2		97.72 319	97.36 332	98.80 277	99.51 219	98.84 212	99.45 234	99.42 260	96.49 362	98.86 320	99.29 363	90.26 386	98.98 408	96.44 373	96.56 356	98.58 391

FMVSNet1		96.84 373	96.36 377	98.29 340	99.32 288	97.26 321	99.43 247	99.48 194	95.11 409	98.55 363	99.32 358	83.95 444	98.98 408	95.81 387	96.26 364	98.62 377

ppachtmachnet_test		97.49 349	97.45 317	97.61 395	98.62 418	95.24 407	98.80 419	99.46 227	96.11 392	98.22 383	99.62 255	96.45 178	98.97 415	93.77 421	95.97 374	98.61 386

TranMVSNet+NR-MVSNet		97.93 278	97.66 291	98.76 282	98.78 397	98.62 238	99.65 87	99.49 182	97.76 241	98.49 367	99.60 262	94.23 292	98.97 415	98.00 264	92.90 430	98.70 338

MVStest1		96.08 390	95.48 395	97.89 374	98.93 374	96.70 361	99.56 144	99.35 297	92.69 441	91.81 458	99.46 315	89.90 392	98.96 417	95.00 407	92.61 435	98.00 435

tt0320-xc		95.31 403	94.59 407	97.45 400	98.92 376	94.73 418	99.20 346	99.31 324	86.74 459	97.23 416	99.72 199	81.14 457	98.95 418	97.08 344	91.98 438	98.67 355

test_method		91.10 424	91.36 426	90.31 445	95.85 457	73.72 478	94.89 467	99.25 341	68.39 469	95.82 437	99.02 396	80.50 458	98.95 418	93.64 424	94.89 402	98.25 418

ADS-MVSNet2		98.02 265	98.07 245	97.87 375	99.33 281	95.19 409	99.23 337	99.08 366	96.24 380	99.10 273	99.67 231	94.11 297	98.93 420	96.81 359	99.05 223	99.48 233

ET-MVSNet_ETH3D		96.49 380	95.64 394	99.05 227	99.53 210	98.82 218	98.84 415	97.51 454	97.63 257	84.77 463	99.21 377	92.09 355	98.91 421	98.98 130	92.21 437	99.41 254

miper_lstm_enhance		98.00 270	97.91 261	98.28 344	99.34 280	97.43 313	98.88 411	99.36 290	96.48 365	98.80 327	99.55 279	95.98 197	98.91 421	97.27 330	95.50 388	98.51 396

MonoMVSNet		98.38 225	98.47 213	98.12 356	98.59 423	96.19 384	99.72 53	98.79 411	97.89 221	99.44 184	99.52 292	96.13 190	98.90 423	98.64 188	97.54 322	99.28 271

PEN-MVS		97.76 309	97.44 322	98.72 285	98.77 402	98.54 245	99.78 32	99.51 147	97.06 320	98.29 379	99.64 244	92.63 341	98.89 424	98.09 253	93.16 428	98.72 331

testing3		97.28 359	96.76 368	98.82 272	99.37 271	98.07 279	99.45 234	99.36 290	97.56 266	97.89 400	98.95 405	83.70 445	98.82 425	96.03 382	98.56 262	99.58 200

testgi		97.65 332	97.50 309	98.13 355	99.36 274	96.45 373	99.42 254	99.48 194	97.76 241	97.87 401	99.45 317	91.09 378	98.81 426	94.53 412	98.52 265	99.13 284

testf1		90.42 427	90.68 428	89.65 448	97.78 439	73.97 476	99.13 358	98.81 407	89.62 451	91.80 459	98.93 407	62.23 467	98.80 427	86.61 462	91.17 441	96.19 459

APD_test2		90.42 427	90.68 428	89.65 448	97.78 439	73.97 476	99.13 358	98.81 407	89.62 451	91.80 459	98.93 407	62.23 467	98.80 427	86.61 462	91.17 441	96.19 459

MIMVSNet		97.73 317	97.45 317	98.57 301	99.45 249	97.50 311	99.02 385	98.98 380	96.11 392	99.41 195	99.14 383	90.28 385	98.74 429	95.74 389	98.93 232	99.47 239

LCM-MVSNet-Re		97.83 298	98.15 232	96.87 417	99.30 290	92.25 448	99.59 119	98.26 438	97.43 284	96.20 433	99.13 384	96.27 186	98.73 430	98.17 245	98.99 229	99.64 172

Syy-MVS		97.09 368	97.14 354	96.95 414	99.00 363	92.73 446	99.29 308	99.39 273	97.06 320	97.41 410	98.15 441	93.92 306	98.68 431	91.71 440	98.34 272	99.45 247

myMVS_eth3d		96.89 371	96.37 376	98.43 327	99.00 363	97.16 325	99.29 308	99.39 273	97.06 320	97.41 410	98.15 441	83.46 447	98.68 431	95.27 402	98.34 272	99.45 247

DTE-MVSNet		97.51 343	97.19 352	98.46 320	98.63 417	98.13 275	99.84 12	99.48 194	96.68 345	97.97 396	99.67 231	92.92 328	98.56 433	96.88 358	92.60 436	98.70 338

PC_three_1452									98.18 171	99.84 54	99.70 206	99.31 3	98.52 434	98.30 235	99.80 123	99.81 78

mvsany_test3		93.77 416	93.45 419	94.74 430	95.78 458	88.01 456	99.64 94	98.25 439	98.28 148	94.31 446	97.97 448	68.89 463	98.51 435	97.50 314	90.37 446	97.71 443

UnsupCasMVSNet_bld		93.53 417	92.51 423	96.58 422	97.38 445	93.82 433	98.24 454	99.48 194	91.10 448	93.10 452	96.66 458	74.89 461	98.37 436	94.03 420	87.71 455	97.56 448

Anonymous20240521		96.20 386	95.89 389	97.13 408	97.72 442	94.96 415	99.79 31	99.29 333	93.01 437	97.20 419	99.03 394	89.69 395	98.36 437	91.16 443	96.13 366	98.07 428

test_f		91.90 423	91.26 427	93.84 433	95.52 462	85.92 458	99.69 62	98.53 434	95.31 406	93.87 448	96.37 460	55.33 470	98.27 438	95.70 390	90.98 444	97.32 452

MDA-MVSNet_test_wron		95.45 399	94.60 406	98.01 362	98.16 434	97.21 324	99.11 367	99.24 344	93.49 432	80.73 469	98.98 402	93.02 325	98.18 439	94.22 418	94.45 407	98.64 368

UnsupCasMVSNet_eth		96.44 381	96.12 382	97.40 402	98.65 415	95.65 393	99.36 284	99.51 147	97.13 310	96.04 436	98.99 400	88.40 412	98.17 440	96.71 363	90.27 447	98.40 409

KD-MVS_2432*1600		94.62 408	93.72 416	97.31 403	97.19 451	95.82 390	98.34 449	99.20 351	95.00 413	97.57 407	98.35 434	87.95 417	98.10 441	92.87 434	77.00 467	98.01 432

miper_refine_blended		94.62 408	93.72 416	97.31 403	97.19 451	95.82 390	98.34 449	99.20 351	95.00 413	97.57 407	98.35 434	87.95 417	98.10 441	92.87 434	77.00 467	98.01 432

YYNet1		95.36 401	94.51 409	97.92 371	97.89 437	97.10 328	99.10 369	99.23 345	93.26 435	80.77 468	99.04 393	92.81 331	98.02 443	94.30 414	94.18 412	98.64 368

EU-MVSNet		97.98 272	98.03 248	97.81 383	98.72 408	96.65 366	99.66 81	99.66 31	98.09 188	98.35 374	99.82 109	95.25 235	98.01 444	97.41 323	95.30 391	98.78 317

Gipuma		90.99 425	90.15 430	93.51 434	98.73 406	90.12 454	93.98 468	99.45 238	79.32 465	92.28 455	94.91 462	69.61 462	97.98 445	87.42 458	95.67 381	92.45 465
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 402	94.73 405	97.15 406	95.53 461	95.94 388	99.35 289	99.10 363	95.13 407	93.55 450	97.54 451	88.15 416	97.91 446	94.58 411	89.69 451	97.61 446

PM-MVS		92.96 420	92.23 424	95.14 429	95.61 459	89.98 455	99.37 278	98.21 442	94.80 418	95.04 444	97.69 449	65.06 464	97.90 447	94.30 414	89.98 449	97.54 449

MDA-MVSNet-bldmvs		94.96 406	93.98 413	97.92 371	98.24 433	97.27 319	99.15 355	99.33 310	93.80 428	80.09 470	99.03 394	88.31 413	97.86 448	93.49 426	94.36 409	98.62 377

Patchmatch-RL test		95.84 393	95.81 391	95.95 427	95.61 459	90.57 453	98.24 454	98.39 435	95.10 411	95.20 441	98.67 422	94.78 258	97.77 449	96.28 379	90.02 448	99.51 225

Anonymous20231206		96.22 384	96.03 385	96.79 419	97.31 448	94.14 431	99.63 100	99.08 366	96.17 386	97.04 423	99.06 391	93.94 304	97.76 450	86.96 460	95.06 396	98.47 400

SD-MVS		99.41 58	99.52 13	99.05 227	99.74 98	99.68 62	99.46 231	99.52 128	99.11 45	99.88 41	99.91 25	99.43 1	97.70 451	98.72 177	99.93 32	99.77 99
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		97.25 361	97.35 334	96.95 414	97.84 438	93.61 440	99.57 137	96.63 462	96.13 391	98.87 316	98.61 425	94.59 274	97.70 451	95.08 405	98.86 242	99.55 207

dongtai		93.26 418	92.93 422	94.25 431	99.39 266	85.68 459	97.68 463	93.27 473	92.87 439	96.85 427	99.39 334	82.33 452	97.48 453	76.78 467	97.80 307	99.58 200

pmmvs3		94.09 414	93.25 421	96.60 421	94.76 466	94.49 425	98.92 407	98.18 444	89.66 450	96.48 430	98.06 447	86.28 430	97.33 454	89.68 448	87.20 456	97.97 438

KD-MVS_self_test		95.00 405	94.34 410	96.96 413	97.07 453	95.39 404	99.56 144	99.44 247	95.11 409	97.13 421	97.32 455	91.86 360	97.27 455	90.35 446	81.23 464	98.23 420

FMVSNet5		96.43 382	96.19 381	97.15 406	99.11 341	95.89 389	99.32 297	99.52 128	94.47 424	98.34 375	99.07 389	87.54 422	97.07 456	92.61 437	95.72 380	98.47 400

new-patchmatchnet		94.48 411	94.08 412	95.67 428	95.08 464	92.41 447	99.18 350	99.28 335	94.55 423	93.49 451	97.37 454	87.86 420	97.01 457	91.57 441	88.36 453	97.61 446

LCM-MVSNet		86.80 431	85.22 435	91.53 442	87.81 474	80.96 468	98.23 456	98.99 379	71.05 467	90.13 462	96.51 459	48.45 474	96.88 458	90.51 444	85.30 458	96.76 454

CL-MVSNet_self_test		94.49 410	93.97 414	96.08 426	96.16 456	93.67 438	98.33 451	99.38 281	95.13 407	97.33 414	98.15 441	92.69 339	96.57 459	88.67 451	79.87 465	97.99 436

MIMVSNet1		95.51 398	95.04 403	96.92 416	97.38 445	95.60 394	99.52 175	99.50 170	93.65 430	96.97 425	99.17 379	85.28 438	96.56 460	88.36 453	95.55 386	98.60 389

FE-MVSNET		94.07 415	93.36 420	96.22 425	94.05 467	94.71 420	99.56 144	98.36 436	93.15 436	93.76 449	97.55 450	86.47 429	96.49 461	87.48 457	89.83 450	97.48 450

test20.03		96.12 388	95.96 387	96.63 420	97.44 444	95.45 401	99.51 184	99.38 281	96.55 359	96.16 434	99.25 371	93.76 313	96.17 462	87.35 459	94.22 411	98.27 416

tmp_tt		82.80 433	81.52 436	86.66 450	66.61 480	68.44 479	92.79 470	97.92 446	68.96 468	80.04 471	99.85 77	85.77 432	96.15 463	97.86 274	43.89 473	95.39 463

test_fmvs3		92.10 422	91.77 425	93.08 437	96.19 455	86.25 457	99.82 16	98.62 430	96.65 348	95.19 442	96.90 457	55.05 471	95.93 464	96.63 370	90.92 445	97.06 453

kuosan		90.92 426	90.11 431	93.34 435	98.78 397	85.59 460	98.15 458	93.16 475	89.37 453	92.07 456	98.38 433	81.48 455	95.19 465	62.54 474	97.04 349	99.25 276

dmvs_testset		95.02 404	96.12 382	91.72 441	99.10 344	80.43 469	99.58 129	97.87 448	97.47 276	95.22 440	98.82 414	93.99 302	95.18 466	88.09 454	94.91 401	99.56 206

PMMVS2		86.87 430	85.37 434	91.35 443	90.21 472	83.80 462	98.89 410	97.45 455	83.13 464	91.67 461	95.03 461	48.49 473	94.70 467	85.86 464	77.62 466	95.54 462

PMVS	70.75 22	75.98 439	74.97 440	79.01 456	70.98 479	55.18 481	93.37 469	98.21 442	65.08 473	61.78 474	93.83 464	21.74 480	92.53 468	78.59 466	91.12 443	89.34 469
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 432	85.65 433	82.75 454	86.77 475	63.39 480	98.35 448	98.92 388	74.11 466	83.39 465	98.98 402	50.85 472	92.40 469	84.54 465	94.97 398	92.46 464

WB-MVS		93.10 419	94.10 411	90.12 446	95.51 463	81.88 466	99.73 51	99.27 338	95.05 412	93.09 453	98.91 411	94.70 267	91.89 470	76.62 468	94.02 417	96.58 456

SSC-MVS		92.73 421	93.73 415	89.72 447	95.02 465	81.38 467	99.76 37	99.23 345	94.87 416	92.80 454	98.93 407	94.71 266	91.37 471	74.49 470	93.80 419	96.42 457

MVE	76.82 21	76.91 438	74.31 442	84.70 451	85.38 477	76.05 475	96.88 466	93.17 474	67.39 470	71.28 472	89.01 471	21.66 481	87.69 472	71.74 471	72.29 469	90.35 468
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 435	79.88 437	82.81 453	90.75 471	76.38 474	97.69 462	95.76 466	66.44 471	83.52 464	92.25 466	62.54 466	87.16 473	68.53 472	61.40 470	84.89 471

EMVS		80.02 436	79.22 438	82.43 455	91.19 470	76.40 473	97.55 465	92.49 478	66.36 472	83.01 466	91.27 468	64.63 465	85.79 474	65.82 473	60.65 471	85.08 470

ANet_high		77.30 437	74.86 441	84.62 452	75.88 478	77.61 472	97.63 464	93.15 476	88.81 455	64.27 473	89.29 470	36.51 476	83.93 475	75.89 469	52.31 472	92.33 466

wuyk23d		40.18 440	41.29 445	36.84 457	86.18 476	49.12 482	79.73 471	22.81 482	27.64 474	25.46 477	28.45 477	21.98 479	48.89 476	55.80 475	23.56 476	12.51 474

test123		39.01 442	42.50 444	28.53 458	39.17 481	20.91 483	98.75 424	19.17 483	19.83 476	38.57 475	66.67 473	33.16 477	15.42 477	37.50 477	29.66 475	49.26 472

testmvs		39.17 441	43.78 443	25.37 459	36.04 482	16.84 484	98.36 447	26.56 481	20.06 475	38.51 476	67.32 472	29.64 478	15.30 478	37.59 476	39.90 474	43.98 473

mmdepth		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

monomultidepth		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

test_blank		0.13 446	0.17 449	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	1.57 478	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet_test		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

DCPMVS		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

cdsmvs_eth3d_5k		24.64 443	32.85 446	0.00 460	0.00 483	0.00 485	0.00 472	99.51 147	0.00 478	0.00 479	99.56 276	96.58 171	0.00 479	0.00 478	0.00 477	0.00 475

pcd_1.5k_mvsjas		8.27 445	11.03 448	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	99.01 19	0.00 479	0.00 478	0.00 477	0.00 475

sosnet-low-res		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

sosnet		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uncertanet		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

Regformer		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

ab-mvs-re		8.30 444	11.06 447	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	99.58 268	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

uanet		0.02 447	0.03 450	0.00 460	0.00 483	0.00 485	0.00 472	0.00 484	0.00 478	0.00 479	0.27 479	0.00 482	0.00 479	0.00 478	0.00 477	0.00 475

TestfortrainingZip							99.69 62

WAC-MVS						97.16 325								95.47 396

FOURS1					99.91 1	99.93 1	99.87 8	99.56 89	99.10 46	99.81 67

test_one_0601					99.81 55	99.88 10		99.49 182	98.97 73	99.65 129	99.81 124	99.09 15

eth-test2					0.00 483

eth-test					0.00 483

RE-MVS-def			99.34 49		99.76 80	99.82 28	99.63 100	99.52 128	98.38 135	99.76 89	99.82 109	98.75 59		98.61 194	99.81 118	99.77 99

IU-MVS					99.84 37	99.88 10		99.32 320	98.30 147	99.84 54				98.86 155	99.85 92	99.89 29

save fliter					99.76 80	99.59 86	99.14 357	99.40 270	99.00 65

test0726					99.85 30	99.89 6	99.62 105	99.50 170	99.10 46	99.86 51	99.82 109	98.94 33

GSMVS																99.52 216

test_part2					99.81 55	99.83 22				99.77 83

sam_mvs1												94.86 253				99.52 216

sam_mvs												94.72 265

MTGPA								99.47 216

MTMP							99.54 164	98.88 398

test9_res														97.49 315	99.72 146	99.75 108

agg_prior2														97.21 333	99.73 145	99.75 108

test_prior4						99.56 92	98.99 393

test_prior2							98.96 400		98.34 141	99.01 290	99.52 292	98.68 69		97.96 266	99.74 143

新几何2							99.01 390

旧先验1					99.74 98	99.59 86		99.54 107			99.69 217	98.47 85			99.68 154	99.73 121

原ACMM2							98.95 403

test222					99.75 90	99.49 107	98.91 409	99.49 182	96.42 370	99.34 219	99.65 238	98.28 99			99.69 151	99.72 130

segment_acmp												98.96 26

testdata1							98.85 414		98.32 145

plane_prior7					99.29 294	97.03 340

plane_prior6					99.27 299	96.98 344						92.71 337

plane_prior4											99.61 259

plane_prior3						97.00 342			98.69 105	99.11 270

plane_prior2							99.39 271		98.97 73

plane_prior1					99.26 302

plane_prior						96.97 345	99.21 343		98.45 128						97.60 316

n2								0.00 484

nn								0.00 484

door-mid								98.05 445

test11								99.35 297

door								97.92 446

HQP5-MVS						96.83 356

HQP-NCC					99.19 320		98.98 396		98.24 160	98.66 345

ACMP_Plane					99.19 320		98.98 396		98.24 160	98.66 345

BP-MVS														97.19 337

HQP3-MVS								99.39 273							97.58 318

HQP2-MVS												92.47 346

NP-MVS					99.23 310	96.92 352					99.40 330

MDTV_nov1_ep13_2view						95.18 410	99.35 289		96.84 337	99.58 153		95.19 238		97.82 279		99.46 244

ACMMP++_ref															97.19 346

ACMMP++															97.43 336

Test By Simon												98.75 59

High-resolution multi-view benchmark