High-res multi-view results

This table lists the benchmark results for the high-res multi-view scenario. The following metrics are evaluated:

Accuracy [%]: The fraction of the reconstruction which is closer to the ground truth than the evaluation threshold distance (*). Larger is better.
Completeness [%]: The fraction of the ground truth which is closer to the reconstruction than the evaluation threshold distance (*). Larger is better.
F₁ score [%]: The harmonic mean of accuracy and completeness, used to rank methods based on both metrics. Larger is better.
Time [s]: The runtime of the method. Smaller is better.

(*) For exact definitions, detailing how potentially incomplete ground truth is taken into account, see our paper.

The datasets are grouped into different categories, and result averages are computed for a category and method if results of the method are available for all datasets within the category. Note that the category "all" includes both the high-res multi-view and the low-res many-view scenarios.

Methods with suffix _ROB may participate in the Robust Vision Challenge.

Click a dataset result cell to show a visualization of the reconstruction. For training datasets, ground truth and accuracy / completeness visualizations are also available. The visualizations may not work with mobile browsers.

Method	all	high-res multi-view	indoor	outdoor	botani.	boulde.	bridge	door	exhibi.	lectur.	living.	lounge	observ.	old co.	statue	terrac.

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 68	99.38 256	99.37 117	99.58 126	99.62 47	99.41 19	99.87 44	99.92 17	98.81 47	100.00 1	99.97 2	99.93 31	99.94 16

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 65	99.84 35	99.44 110	99.58 126	99.69 18	99.43 15	99.98 11	99.91 24	98.62 73	100.00 1	99.97 2	99.95 21	99.90 24

test_vis1_n_1920		98.63 198	98.40 206	99.31 179	99.86 22	97.94 281	99.67 71	99.62 47	99.43 15	99.99 2	99.91 24	87.29 412	100.00 1	99.92 22	99.92 37	99.98 2

fmvsm_l_conf0.5_n_9		99.58 14	99.47 22	99.92 1	99.85 28	99.82 26	99.47 217	99.63 42	99.45 11	99.98 11	99.89 37	97.02 143	99.99 4	99.98 1	99.96 15	99.95 11

NormalMVS		99.27 84	99.19 84	99.52 133	99.89 8	98.83 207	99.65 84	99.52 120	99.10 42	99.84 51	99.76 168	95.80 202	99.99 4	99.30 83	99.84 96	99.74 105

SymmetryMVS		99.15 107	99.02 115	99.52 133	99.72 105	98.83 207	99.65 84	99.34 290	99.10 42	99.84 51	99.76 168	95.80 202	99.99 4	99.30 83	98.72 242	99.73 114

fmvsm_s_conf0.5_n_5		99.37 64	99.21 80	99.86 30	99.80 58	99.68 58	99.42 242	99.61 56	99.37 22	99.97 23	99.86 65	94.96 236	99.99 4	99.97 2	99.93 31	99.92 22

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 35	99.82 26	99.54 160	99.66 28	99.46 7	99.98 11	99.89 37	97.27 130	99.99 4	99.97 2	99.95 21	99.95 11

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 38	99.86 22	99.61 79	99.56 141	99.63 42	99.48 3	99.98 11	99.83 92	98.75 58	99.99 4	99.97 2	99.96 15	99.94 16

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 38	99.84 35	99.63 76	99.56 141	99.63 42	99.47 4	99.98 11	99.82 101	98.75 58	99.99 4	99.97 2	99.97 8	99.94 16

test_fmvsmconf_n		99.70 3	99.64 4	99.87 19	99.80 58	99.66 65	99.48 208	99.64 38	99.45 11	99.92 28	99.92 17	98.62 73	99.99 4	99.96 12	99.99 1	99.96 7

patch_mono-2		99.26 87	99.62 5	98.16 339	99.81 52	94.59 411	99.52 170	99.64 38	99.33 24	99.73 90	99.90 31	99.00 22	99.99 4	99.69 33	99.98 4	99.89 27

h-mvs33		97.70 312	97.28 335	98.97 227	99.70 116	97.27 309	99.36 271	99.45 226	98.94 72	99.66 114	99.64 232	94.93 239	99.99 4	99.48 60	84.36 446	99.65 153

xiu_mvs_v1_base_debu		99.29 80	99.27 70	99.34 171	99.63 152	98.97 177	99.12 347	99.51 139	98.86 78	99.84 51	99.47 299	98.18 101	99.99 4	99.50 55	99.31 185	99.08 278

xiu_mvs_v1_base		99.29 80	99.27 70	99.34 171	99.63 152	98.97 177	99.12 347	99.51 139	98.86 78	99.84 51	99.47 299	98.18 101	99.99 4	99.50 55	99.31 185	99.08 278

xiu_mvs_v1_base_debi		99.29 80	99.27 70	99.34 171	99.63 152	98.97 177	99.12 347	99.51 139	98.86 78	99.84 51	99.47 299	98.18 101	99.99 4	99.50 55	99.31 185	99.08 278

EPNet		98.86 165	98.71 170	99.30 184	97.20 438	98.18 261	99.62 102	98.91 381	99.28 27	98.63 342	99.81 116	95.96 191	99.99 4	99.24 92	99.72 142	99.73 114
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 21	99.42 29	99.89 9	99.83 44	99.74 49	99.51 179	99.62 47	99.46 7	99.99 2	99.90 31	96.60 164	99.98 18	99.95 14	99.95 21	99.96 7

MM		99.40 60	99.28 66	99.74 74	99.67 128	99.31 129	99.52 170	98.87 388	99.55 1	99.74 88	99.80 132	96.47 171	99.98 18	99.97 2	99.97 8	99.94 16

test_cas_vis1_n_1920		99.16 103	99.01 120	99.61 103	99.81 52	98.86 202	99.65 84	99.64 38	99.39 20	99.97 23	99.94 6	93.20 313	99.98 18	99.55 48	99.91 44	99.99 1

test_vis1_n		97.92 270	97.44 311	99.34 171	99.53 198	98.08 268	99.74 47	99.49 171	99.15 32	100.00 1	99.94 6	79.51 447	99.98 18	99.88 24	99.76 134	99.97 4

xiu_mvs_v2_base		99.26 87	99.25 74	99.29 187	99.53 198	98.91 193	99.02 371	99.45 226	98.80 88	99.71 97	99.26 358	98.94 32	99.98 18	99.34 76	99.23 194	98.98 292

PS-MVSNAJ		99.32 75	99.32 51	99.30 184	99.57 182	98.94 188	98.97 385	99.46 215	98.92 75	99.71 97	99.24 360	99.01 18	99.98 18	99.35 71	99.66 153	98.97 293

QAPM		98.67 193	98.30 213	99.80 59	99.20 305	99.67 62	99.77 34	99.72 11	94.74 407	98.73 322	99.90 31	95.78 204	99.98 18	96.96 339	99.88 70	99.76 100

3Dnovator	97.25 9	99.24 92	99.05 104	99.81 55	99.12 327	99.66 65	99.84 12	99.74 10	99.09 49	98.92 295	99.90 31	95.94 194	99.98 18	98.95 127	99.92 37	99.79 87

OpenMVS	96.50 16	98.47 204	98.12 225	99.52 133	99.04 346	99.53 95	99.82 16	99.72 11	94.56 410	98.08 377	99.88 47	94.73 255	99.98 18	97.47 306	99.76 134	99.06 284

fmvsm_s_conf0.5_n_3		99.37 64	99.20 82	99.87 19	99.75 86	99.70 55	99.48 208	99.66 28	99.45 11	99.99 2	99.93 10	94.64 264	99.97 27	99.94 19	99.97 8	99.95 11

reproduce_model		99.63 7	99.54 11	99.90 6	99.78 64	99.88 9	99.56 141	99.55 92	99.15 32	99.90 32	99.90 31	99.00 22	99.97 27	99.11 106	99.91 44	99.86 40

test_fmvsmconf0.1_n		99.55 20	99.45 27	99.86 30	99.44 238	99.65 69	99.50 188	99.61 56	99.45 11	99.87 44	99.92 17	97.31 127	99.97 27	99.95 14	99.99 1	99.97 4

test_fmvs1_n		98.41 210	98.14 222	99.21 200	99.82 48	97.71 294	99.74 47	99.49 171	99.32 25	99.99 2	99.95 3	85.32 425	99.97 27	99.82 27	99.84 96	99.96 7

CANet_DTU		98.97 153	98.87 150	99.25 194	99.33 269	98.42 253	99.08 356	99.30 317	99.16 31	99.43 178	99.75 173	95.27 224	99.97 27	98.56 194	99.95 21	99.36 250

MVS_0304		99.15 107	98.96 130	99.73 77	98.92 364	99.37 117	99.37 266	96.92 444	99.51 2	99.66 114	99.78 155	96.69 161	99.97 27	99.84 26	99.97 8	99.84 51

MTAPA		99.52 25	99.39 37	99.89 9	99.90 4	99.86 17	99.66 78	99.47 204	98.79 89	99.68 103	99.81 116	98.43 86	99.97 27	98.88 137	99.90 55	99.83 61

PGM-MVS		99.45 43	99.31 57	99.86 30	99.87 17	99.78 42	99.58 126	99.65 35	97.84 220	99.71 97	99.80 132	99.12 13	99.97 27	98.33 219	99.87 73	99.83 61

mPP-MVS		99.44 47	99.30 59	99.86 30	99.88 13	99.79 36	99.69 62	99.48 183	98.12 173	99.50 162	99.75 173	98.78 51	99.97 27	98.57 191	99.89 66	99.83 61

CP-MVS		99.45 43	99.32 51	99.85 38	99.83 44	99.75 46	99.69 62	99.52 120	98.07 183	99.53 157	99.63 238	98.93 36	99.97 27	98.74 162	99.91 44	99.83 61

SteuartSystems-ACMMP		99.54 21	99.42 29	99.87 19	99.82 48	99.81 31	99.59 116	99.51 139	98.62 106	99.79 69	99.83 92	99.28 4	99.97 27	98.48 201	99.90 55	99.84 51
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 98	98.97 126	99.82 52	99.17 319	99.68 58	99.81 20	99.51 139	99.20 29	98.72 323	99.89 37	95.68 208	99.97 27	98.86 145	99.86 81	99.81 74

fmvsm_s_conf0.5_n_9		99.41 56	99.28 66	99.81 55	99.84 35	99.52 99	99.48 208	99.62 47	99.46 7	99.99 2	99.92 17	95.24 228	99.96 39	99.97 2	99.97 8	99.96 7

lecture		99.60 12	99.50 17	99.89 9	99.89 8	99.90 2	99.75 42	99.59 69	99.06 55	99.88 38	99.85 72	98.41 90	99.96 39	99.28 86	99.84 96	99.83 61

KinetiMVS		99.12 120	98.92 137	99.70 81	99.67 128	99.40 115	99.67 71	99.63 42	98.73 96	99.94 26	99.81 116	94.54 270	99.96 39	98.40 210	99.93 31	99.74 105

fmvsm_s_conf0.5_n_7		99.34 71	99.29 63	99.48 145	99.70 116	98.63 226	99.42 242	99.63 42	99.46 7	99.98 11	99.88 47	95.59 211	99.96 39	99.97 2	99.98 4	99.85 44

fmvsm_s_conf0.5_n_2		99.32 75	99.13 90	99.89 9	99.80 58	99.77 43	99.44 230	99.58 74	99.47 4	99.99 2	99.93 10	94.04 289	99.96 39	99.96 12	99.93 31	99.93 21

reproduce-ours		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 170	99.54 101	99.13 35	99.89 35	99.89 37	98.96 25	99.96 39	99.04 114	99.90 55	99.85 44

our_new_method		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 170	99.54 101	99.13 35	99.89 35	99.89 37	98.96 25	99.96 39	99.04 114	99.90 55	99.85 44

fmvsm_s_conf0.5_n_a		99.56 19	99.47 22	99.85 38	99.83 44	99.64 75	99.52 170	99.65 35	99.10 42	99.98 11	99.92 17	97.35 126	99.96 39	99.94 19	99.92 37	99.95 11

fmvsm_s_conf0.5_n		99.51 26	99.40 35	99.85 38	99.84 35	99.65 69	99.51 179	99.67 23	99.13 35	99.98 11	99.92 17	96.60 164	99.96 39	99.95 14	99.96 15	99.95 11

mvsany_test1		99.50 28	99.46 26	99.62 102	99.61 167	99.09 159	98.94 391	99.48 183	99.10 42	99.96 25	99.91 24	98.85 42	99.96 39	99.72 30	99.58 163	99.82 67

test_fmvs1		98.88 159	98.79 163	99.16 205	99.69 121	97.61 298	99.55 155	99.49 171	99.32 25	99.98 11	99.91 24	91.41 361	99.96 39	99.82 27	99.92 37	99.90 24

DVP-MVS++		99.59 13	99.50 17	99.88 13	99.51 207	99.88 9	99.87 8	99.51 139	98.99 63	99.88 38	99.81 116	99.27 5	99.96 39	98.85 147	99.80 119	99.81 74

MSC_two_6792asdad				99.87 19	99.51 207	99.76 44		99.33 298					99.96 39	98.87 140	99.84 96	99.89 27

No_MVS				99.87 19	99.51 207	99.76 44		99.33 298					99.96 39	98.87 140	99.84 96	99.89 27

ZD-MVS					99.71 111	99.79 36		99.61 56	96.84 325	99.56 150	99.54 272	98.58 75	99.96 39	96.93 342	99.75 136

SED-MVS		99.61 8	99.52 12	99.88 13	99.84 35	99.90 2	99.60 109	99.48 183	99.08 50	99.91 29	99.81 116	99.20 7	99.96 39	98.91 134	99.85 88	99.79 87

test_241102_TWO								99.48 183	99.08 50	99.88 38	99.81 116	98.94 32	99.96 39	98.91 134	99.84 96	99.88 33

ZNCC-MVS		99.47 37	99.33 49	99.87 19	99.87 17	99.81 31	99.64 91	99.67 23	98.08 182	99.55 154	99.64 232	98.91 37	99.96 39	98.72 165	99.90 55	99.82 67

DVP-MVS		99.57 18	99.47 22	99.88 13	99.85 28	99.89 5	99.57 134	99.37 277	99.10 42	99.81 63	99.80 132	98.94 32	99.96 39	98.93 131	99.86 81	99.81 74
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 63	99.81 63	99.80 132	99.09 14	99.96 39	98.85 147	99.90 55	99.88 33

test_0728_SECOND				99.91 4	99.84 35	99.89 5	99.57 134	99.51 139					99.96 39	98.93 131	99.86 81	99.88 33

SR-MVS		99.43 50	99.29 63	99.86 30	99.75 86	99.83 20	99.59 116	99.62 47	98.21 157	99.73 90	99.79 148	98.68 67	99.96 39	98.44 207	99.77 131	99.79 87

DPE-MVS		99.46 39	99.32 51	99.91 4	99.78 64	99.88 9	99.36 271	99.51 139	98.73 96	99.88 38	99.84 87	98.72 64	99.96 39	98.16 234	99.87 73	99.88 33
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 52	99.29 63	99.80 59	99.62 158	99.55 90	99.50 188	99.70 15	98.79 89	99.77 78	99.96 1	97.45 121	99.96 39	98.92 133	99.90 55	99.89 27

HFP-MVS		99.49 30	99.37 41	99.86 30	99.87 17	99.80 33	99.66 78	99.67 23	98.15 164	99.68 103	99.69 206	99.06 16	99.96 39	98.69 170	99.87 73	99.84 51

region2R		99.48 34	99.35 45	99.87 19	99.88 13	99.80 33	99.65 84	99.66 28	98.13 171	99.66 114	99.68 213	98.96 25	99.96 39	98.62 179	99.87 73	99.84 51

HPM-MVS++		99.39 62	99.23 78	99.87 19	99.75 86	99.84 19	99.43 235	99.51 139	98.68 103	99.27 224	99.53 276	98.64 72	99.96 39	98.44 207	99.80 119	99.79 87

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 72	99.89 5	99.75 42	99.56 84	99.02 56	99.88 38	99.85 72	99.18 10	99.96 39	99.22 93	99.92 37	99.90 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 30	99.36 43	99.86 30	99.87 17	99.79 36	99.66 78	99.67 23	98.15 164	99.67 109	99.69 206	98.95 30	99.96 39	98.69 170	99.87 73	99.84 51

MP-MVS		99.33 73	99.15 88	99.87 19	99.88 13	99.82 26	99.66 78	99.46 215	98.09 178	99.48 166	99.74 178	98.29 96	99.96 39	97.93 256	99.87 73	99.82 67
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 126	98.90 142	99.74 74	99.80 58	99.46 108	99.59 116	99.49 171	97.03 312	99.63 131	99.69 206	97.27 130	99.96 39	97.82 267	99.84 96	99.81 74

PVSNet_Blended_VisFu		99.36 68	99.28 66	99.61 103	99.86 22	99.07 164	99.47 217	99.93 2	97.66 243	99.71 97	99.86 65	97.73 116	99.96 39	99.47 62	99.82 111	99.79 87

UGNet		98.87 162	98.69 172	99.40 162	99.22 302	98.72 218	99.44 230	99.68 20	99.24 28	99.18 249	99.42 310	92.74 323	99.96 39	99.34 76	99.94 29	99.53 203
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 75	99.32 51	99.32 177	99.85 28	98.29 256	99.71 57	99.66 28	98.11 175	99.41 185	99.80 132	98.37 93	99.96 39	98.99 120	99.96 15	99.72 123

ACMMP		99.45 43	99.32 51	99.82 52	99.89 8	99.67 62	99.62 102	99.69 18	98.12 173	99.63 131	99.84 87	98.73 63	99.96 39	98.55 197	99.83 107	99.81 74
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
fmvsm_s_conf0.5_n_6		99.54 21	99.44 28	99.85 38	99.51 207	99.67 62	99.50 188	99.64 38	99.43 15	99.98 11	99.78 155	97.26 132	99.95 74	99.95 14	99.93 31	99.92 22

fmvsm_s_conf0.5_n_4		99.36 68	99.24 75	99.73 77	99.78 64	99.53 95	99.49 202	99.60 63	99.42 18	99.99 2	99.86 65	95.15 231	99.95 74	99.95 14	99.89 66	99.73 114

fmvsm_s_conf0.1_n_2		99.37 64	99.22 79	99.81 55	99.77 72	99.75 46	99.46 221	99.60 63	99.47 4	99.98 11	99.94 6	94.98 235	99.95 74	99.97 2	99.79 126	99.73 114

test_fmvsmconf0.01_n		99.22 95	99.03 109	99.79 62	98.42 418	99.48 105	99.55 155	99.51 139	99.39 20	99.78 74	99.93 10	94.80 247	99.95 74	99.93 21	99.95 21	99.94 16

SR-MVS-dyc-post		99.45 43	99.31 57	99.85 38	99.76 76	99.82 26	99.63 97	99.52 120	98.38 130	99.76 84	99.82 101	98.53 79	99.95 74	98.61 182	99.81 114	99.77 95

GST-MVS		99.40 60	99.24 75	99.85 38	99.86 22	99.79 36	99.60 109	99.67 23	97.97 204	99.63 131	99.68 213	98.52 80	99.95 74	98.38 212	99.86 81	99.81 74

CANet		99.25 91	99.14 89	99.59 107	99.41 246	99.16 149	99.35 276	99.57 79	98.82 83	99.51 161	99.61 247	96.46 172	99.95 74	99.59 43	99.98 4	99.65 153

MP-MVS-pluss		99.37 64	99.20 82	99.88 13	99.90 4	99.87 16	99.30 289	99.52 120	97.18 294	99.60 142	99.79 148	98.79 50	99.95 74	98.83 153	99.91 44	99.83 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 52	99.27 70	99.88 13	99.89 8	99.80 33	99.67 71	99.50 159	98.70 100	99.77 78	99.49 290	98.21 99	99.95 74	98.46 205	99.77 131	99.88 33
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 74	96.67 354

APD-MVS_3200maxsize		99.48 34	99.35 45	99.85 38	99.76 76	99.83 20	99.63 97	99.54 101	98.36 134	99.79 69	99.82 101	98.86 41	99.95 74	98.62 179	99.81 114	99.78 93

RPMNet		96.72 364	95.90 377	99.19 202	99.18 311	98.49 245	99.22 327	99.52 120	88.72 443	99.56 150	97.38 440	94.08 288	99.95 74	86.87 448	98.58 249	99.14 270

sss		99.17 101	99.05 104	99.53 127	99.62 158	98.97 177	99.36 271	99.62 47	97.83 221	99.67 109	99.65 226	97.37 125	99.95 74	99.19 95	99.19 197	99.68 141

MVSMamba_PlusPlus		99.46 39	99.41 34	99.64 95	99.68 126	99.50 102	99.75 42	99.50 159	98.27 144	99.87 44	99.92 17	98.09 105	99.94 87	99.65 39	99.95 21	99.47 227

fmvsm_s_conf0.1_n_a		99.26 87	99.06 102	99.85 38	99.52 204	99.62 77	99.54 160	99.62 47	98.69 101	99.99 2	99.96 1	94.47 274	99.94 87	99.88 24	99.92 37	99.98 2

fmvsm_s_conf0.1_n		99.29 80	99.10 94	99.86 30	99.70 116	99.65 69	99.53 169	99.62 47	98.74 95	99.99 2	99.95 3	94.53 272	99.94 87	99.89 23	99.96 15	99.97 4

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 55	99.91 1	99.66 65	99.63 97	99.39 261	98.91 76	99.78 74	99.85 72	99.36 2	99.94 87	98.84 150	99.88 70	99.82 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 157	98.75 166	99.39 166	99.46 231	98.61 230	99.76 37	99.50 159	98.06 187	99.81 63	99.88 47	93.91 296	99.94 87	99.11 106	99.27 188	99.61 170

mamv4		99.33 73	99.42 29	99.07 213	99.67 128	97.73 289	99.42 242	99.60 63	98.15 164	99.94 26	99.91 24	98.42 88	99.94 87	99.72 30	99.96 15	99.54 197

XVS		99.53 24	99.42 29	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 196	99.74 178	98.81 47	99.94 87	98.79 158	99.86 81	99.84 51

X-MVStestdata		96.55 367	95.45 386	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 196	64.01 463	98.81 47	99.94 87	98.79 158	99.86 81	99.84 51

旧先验2							98.96 386		96.70 332	99.47 167			99.94 87	98.19 230

新几何1				99.75 71	99.75 86	99.59 82		99.54 101	96.76 328	99.29 218	99.64 232	98.43 86	99.94 87	96.92 344	99.66 153	99.72 123

testdata				99.54 119	99.75 86	98.95 185		99.51 139	97.07 306	99.43 178	99.70 195	98.87 40	99.94 87	97.76 276	99.64 156	99.72 123

HPM-MVS		99.42 52	99.28 66	99.83 51	99.90 4	99.72 51	99.81 20	99.54 101	97.59 249	99.68 103	99.63 238	98.91 37	99.94 87	98.58 188	99.91 44	99.84 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 96	99.10 94	99.45 152	99.89 8	98.52 240	99.39 259	99.94 1	98.73 96	99.11 258	99.89 37	95.50 214	99.94 87	99.50 55	99.97 8	99.89 27

APD-MVS		99.27 84	99.08 99	99.84 50	99.75 86	99.79 36	99.50 188	99.50 159	97.16 296	99.77 78	99.82 101	98.78 51	99.94 87	97.56 297	99.86 81	99.80 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 34	99.42 29	99.65 89	99.72 105	99.40 115	99.05 363	99.66 28	99.14 34	99.57 149	99.80 132	98.46 84	99.94 87	99.57 46	99.84 96	99.60 173
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		99.06 137	98.88 149	99.61 103	99.62 158	99.16 149	99.37 266	99.56 84	98.04 196	99.53 157	99.62 243	96.84 154	99.94 87	98.85 147	98.49 257	99.72 123

DeepC-MVS	98.35 2	99.30 78	99.19 84	99.64 95	99.82 48	99.23 142	99.62 102	99.55 92	98.94 72	99.63 131	99.95 3	95.82 200	99.94 87	99.37 70	99.97 8	99.73 114
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 84	99.12 92	99.74 74	99.18 311	99.75 46	99.56 141	99.57 79	98.45 123	99.49 165	99.85 72	97.77 115	99.94 87	98.33 219	99.84 96	99.52 204

GDP-MVS		99.08 133	98.89 146	99.64 95	99.53 198	99.34 121	99.64 91	99.48 183	98.32 139	99.77 78	99.66 224	95.14 232	99.93 105	98.97 126	99.50 170	99.64 160

SDMVSNet		99.11 126	98.90 142	99.75 71	99.81 52	99.59 82	99.81 20	99.65 35	98.78 92	99.64 128	99.88 47	94.56 267	99.93 105	99.67 35	98.26 270	99.72 123

FE-MVS		98.48 203	98.17 218	99.40 162	99.54 197	98.96 181	99.68 68	98.81 395	95.54 391	99.62 135	99.70 195	93.82 299	99.93 105	97.35 315	99.46 172	99.32 256

SF-MVS		99.38 63	99.24 75	99.79 62	99.79 62	99.68 58	99.57 134	99.54 101	97.82 225	99.71 97	99.80 132	98.95 30	99.93 105	98.19 230	99.84 96	99.74 105

dcpmvs_2		99.23 93	99.58 7	98.16 339	99.83 44	94.68 408	99.76 37	99.52 120	99.07 52	99.98 11	99.88 47	98.56 77	99.93 105	99.67 35	99.98 4	99.87 38

Anonymous20240529		98.09 240	97.68 278	99.34 171	99.66 139	98.44 250	99.40 255	99.43 246	93.67 417	99.22 236	99.89 37	90.23 378	99.93 105	99.26 91	98.33 264	99.66 148

ACMMP_NAP		99.47 37	99.34 47	99.88 13	99.87 17	99.86 17	99.47 217	99.48 183	98.05 189	99.76 84	99.86 65	98.82 46	99.93 105	98.82 157	99.91 44	99.84 51

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 95	99.78 64	99.14 154	99.60 109	99.45 226	99.01 58	99.90 32	99.83 92	98.98 24	99.93 105	99.59 43	99.95 21	99.86 40

无先验							98.99 379	99.51 139	96.89 322				99.93 105	97.53 300		99.72 123

VDDNet		97.55 327	97.02 349	99.16 205	99.49 221	98.12 267	99.38 264	99.30 317	95.35 393	99.68 103	99.90 31	82.62 438	99.93 105	99.31 80	98.13 282	99.42 239

ab-mvs		98.86 165	98.63 182	99.54 119	99.64 149	99.19 144	99.44 230	99.54 101	97.77 229	99.30 215	99.81 116	94.20 282	99.93 105	99.17 101	98.82 236	99.49 218

F-COLMAP		99.19 96	99.04 106	99.64 95	99.78 64	99.27 137	99.42 242	99.54 101	97.29 285	99.41 185	99.59 252	98.42 88	99.93 105	98.19 230	99.69 147	99.73 114

BP-MVS1		99.12 120	98.94 136	99.65 89	99.51 207	99.30 132	99.67 71	98.92 376	98.48 119	99.84 51	99.69 206	94.96 236	99.92 117	99.62 42	99.79 126	99.71 132

Anonymous202405211		98.30 221	97.98 242	99.26 193	99.57 182	98.16 262	99.41 247	98.55 420	96.03 385	99.19 245	99.74 178	91.87 348	99.92 117	99.16 102	98.29 269	99.70 134

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 95	99.78 64	99.15 153	99.61 108	99.45 226	99.01 58	99.89 35	99.82 101	99.01 18	99.92 117	99.56 47	99.95 21	99.85 44

VDD-MVS		97.73 306	97.35 323	98.88 247	99.47 229	97.12 317	99.34 279	98.85 390	98.19 159	99.67 109	99.85 72	82.98 436	99.92 117	99.49 59	98.32 268	99.60 173

VNet		99.11 126	98.90 142	99.73 77	99.52 204	99.56 88	99.41 247	99.39 261	99.01 58	99.74 88	99.78 155	95.56 212	99.92 117	99.52 53	98.18 278	99.72 123

XVG-OURS-SEG-HR		98.69 191	98.62 187	98.89 245	99.71 111	97.74 288	99.12 347	99.54 101	98.44 126	99.42 181	99.71 191	94.20 282	99.92 117	98.54 198	98.90 230	99.00 289

mvsmamba		99.06 137	98.96 130	99.36 168	99.47 229	98.64 225	99.70 58	99.05 360	97.61 248	99.65 123	99.83 92	96.54 168	99.92 117	99.19 95	99.62 159	99.51 213

HPM-MVS_fast		99.51 26	99.40 35	99.85 38	99.91 1	99.79 36	99.76 37	99.56 84	97.72 234	99.76 84	99.75 173	99.13 12	99.92 117	99.07 112	99.92 37	99.85 44

HY-MVS	97.30 7	98.85 174	98.64 181	99.47 149	99.42 241	99.08 162	99.62 102	99.36 278	97.39 277	99.28 219	99.68 213	96.44 174	99.92 117	98.37 214	98.22 273	99.40 244

DP-MVS		99.16 103	98.95 134	99.78 65	99.77 72	99.53 95	99.41 247	99.50 159	97.03 312	99.04 275	99.88 47	97.39 122	99.92 117	98.66 174	99.90 55	99.87 38

IB-MVS	95.67 18	96.22 373	95.44 387	98.57 289	99.21 303	96.70 349	98.65 420	97.74 438	96.71 331	97.27 403	98.54 415	86.03 419	99.92 117	98.47 204	86.30 444	99.10 273
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 30	99.39 37	99.77 68	99.63 152	99.59 82	99.36 271	99.46 215	99.07 52	99.79 69	99.82 101	98.85 42	99.92 117	98.68 172	99.87 73	99.82 67
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 93	99.10 94	99.61 103	99.35 263	99.31 129	99.46 221	99.13 348	98.61 107	99.86 48	99.89 37	96.41 176	99.91 129	99.67 35	99.51 168	99.63 165

balanced_conf03		99.46 39	99.39 37	99.67 84	99.55 190	99.58 87	99.74 47	99.51 139	98.42 127	99.87 44	99.84 87	98.05 108	99.91 129	99.58 45	99.94 29	99.52 204

9.14			99.10 94		99.72 105		99.40 255	99.51 139	97.53 259	99.64 128	99.78 155	98.84 44	99.91 129	97.63 288	99.82 111

SMA-MVS		99.44 47	99.30 59	99.85 38	99.73 101	99.83 20	99.56 141	99.47 204	97.45 268	99.78 74	99.82 101	99.18 10	99.91 129	98.79 158	99.89 66	99.81 74
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					99.67 128	99.65 69	99.05 363	99.41 251	96.22 370	98.95 291	99.49 290	98.77 54	99.91 129

train_agg		99.02 144	98.77 164	99.77 68	99.67 128	99.65 69	99.05 363	99.41 251	96.28 364	98.95 291	99.49 290	98.76 55	99.91 129	97.63 288	99.72 142	99.75 101

test_8					99.67 128	99.61 79	99.03 368	99.41 251	96.28 364	98.93 294	99.48 296	98.76 55	99.91 129

agg_prior					99.67 128	99.62 77		99.40 258		98.87 304			99.91 129

原ACMM1				99.65 89	99.73 101	99.33 124		99.47 204	97.46 265	99.12 256	99.66 224	98.67 69	99.91 129	97.70 285	99.69 147	99.71 132

LFMVS		97.90 273	97.35 323	99.54 119	99.52 204	99.01 171	99.39 259	98.24 427	97.10 304	99.65 123	99.79 148	84.79 428	99.91 129	99.28 86	98.38 261	99.69 137

XVG-OURS		98.73 189	98.68 173	98.88 247	99.70 116	97.73 289	98.92 393	99.55 92	98.52 116	99.45 170	99.84 87	95.27 224	99.91 129	98.08 245	98.84 234	99.00 289

PLC	97.94 4	99.02 144	98.85 155	99.53 127	99.66 139	99.01 171	99.24 320	99.52 120	96.85 324	99.27 224	99.48 296	98.25 98	99.91 129	97.76 276	99.62 159	99.65 153
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 320	97.06 348	99.47 149	99.61 167	99.09 159	98.04 446	99.25 329	91.24 434	98.51 353	99.70 195	94.55 269	99.91 129	92.76 424	99.85 88	99.42 239
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 159	98.65 179	99.58 110	99.58 177	99.34 121	99.65 84	99.52 120	98.26 146	99.83 59	99.87 58	93.37 307	99.90 142	97.81 269	99.91 44	99.49 218

StellarMVS		98.88 159	98.65 179	99.58 110	99.58 177	99.34 121	99.65 84	99.52 120	98.26 146	99.83 59	99.87 58	93.37 307	99.90 142	97.81 269	99.91 44	99.49 218

AstraMVS		99.09 131	99.03 109	99.25 194	99.66 139	98.13 265	99.57 134	98.24 427	98.82 83	99.91 29	99.88 47	95.81 201	99.90 142	99.72 30	99.67 152	99.74 105

mmtdpeth		96.95 359	96.71 358	97.67 378	99.33 269	94.90 404	99.89 2	99.28 323	98.15 164	99.72 95	98.57 414	86.56 417	99.90 142	99.82 27	89.02 439	98.20 409

UWE-MVS		97.58 326	97.29 334	98.48 302	99.09 335	96.25 369	99.01 376	96.61 450	97.86 214	99.19 245	99.01 385	88.72 393	99.90 142	97.38 313	98.69 243	99.28 259

test_vis1_rt		95.81 383	95.65 382	96.32 412	99.67 128	91.35 439	99.49 202	96.74 448	98.25 149	95.24 427	98.10 433	74.96 448	99.90 142	99.53 51	98.85 233	97.70 433

FA-MVS(test-final)		98.75 186	98.53 198	99.41 161	99.55 190	99.05 167	99.80 25	99.01 365	96.59 346	99.58 146	99.59 252	95.39 218	99.90 142	97.78 272	99.49 171	99.28 259

MCST-MVS		99.43 50	99.30 59	99.82 52	99.79 62	99.74 49	99.29 294	99.40 258	98.79 89	99.52 159	99.62 243	98.91 37	99.90 142	98.64 176	99.75 136	99.82 67

CDPH-MVS		99.13 113	98.91 140	99.80 59	99.75 86	99.71 53	99.15 341	99.41 251	96.60 344	99.60 142	99.55 267	98.83 45	99.90 142	97.48 304	99.83 107	99.78 93

NCCC		99.34 71	99.19 84	99.79 62	99.61 167	99.65 69	99.30 289	99.48 183	98.86 78	99.21 239	99.63 238	98.72 64	99.90 142	98.25 226	99.63 158	99.80 83

114514_t		98.93 155	98.67 174	99.72 80	99.85 28	99.53 95	99.62 102	99.59 69	92.65 429	99.71 97	99.78 155	98.06 107	99.90 142	98.84 150	99.91 44	99.74 105

1112_ss		98.98 151	98.77 164	99.59 107	99.68 126	99.02 169	99.25 315	99.48 183	97.23 291	99.13 254	99.58 256	96.93 148	99.90 142	98.87 140	98.78 239	99.84 51

PHI-MVS		99.30 78	99.17 87	99.70 81	99.56 186	99.52 99	99.58 126	99.80 8	97.12 300	99.62 135	99.73 184	98.58 75	99.90 142	98.61 182	99.91 44	99.68 141

AdaColmap		99.01 148	98.80 160	99.66 85	99.56 186	99.54 92	99.18 336	99.70 15	98.18 162	99.35 205	99.63 238	96.32 178	99.90 142	97.48 304	99.77 131	99.55 195

COLMAP_ROB	97.56 6	98.86 165	98.75 166	99.17 204	99.88 13	98.53 236	99.34 279	99.59 69	97.55 255	98.70 330	99.89 37	95.83 199	99.90 142	98.10 240	99.90 55	99.08 278
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 217	98.03 237	99.31 179	99.63 152	98.56 233	99.54 160	96.75 447	97.53 259	99.73 90	99.65 226	91.25 366	99.89 157	98.62 179	99.56 164	99.48 221

tttt0517		98.42 208	98.14 222	99.28 191	99.66 139	98.38 254	99.74 47	96.85 445	97.68 240	99.79 69	99.74 178	91.39 362	99.89 157	98.83 153	99.56 164	99.57 191

test12				99.75 71	99.64 149	99.61 79		99.29 321		99.21 239		98.38 92	99.89 157		99.74 139	99.74 105

Test_1112_low_res		98.89 158	98.66 177	99.57 114	99.69 121	98.95 185	99.03 368	99.47 204	96.98 314	99.15 252	99.23 361	96.77 158	99.89 157	98.83 153	98.78 239	99.86 40

CNLPA		99.14 111	98.99 122	99.59 107	99.58 177	99.41 114	99.16 338	99.44 235	98.45 123	99.19 245	99.49 290	98.08 106	99.89 157	97.73 280	99.75 136	99.48 221

guyue		99.16 103	99.04 106	99.52 133	99.69 121	98.92 192	99.59 116	98.81 395	98.73 96	99.90 32	99.87 58	95.34 221	99.88 162	99.66 38	99.81 114	99.74 105

sd_testset		98.75 186	98.57 194	99.29 187	99.81 52	98.26 258	99.56 141	99.62 47	98.78 92	99.64 128	99.88 47	92.02 345	99.88 162	99.54 49	98.26 270	99.72 123

APD_test1		95.87 381	96.49 363	94.00 419	99.53 198	84.01 448	99.54 160	99.32 308	95.91 387	97.99 382	99.85 72	85.49 423	99.88 162	91.96 427	98.84 234	98.12 413

diffmvs		99.14 111	99.02 115	99.51 138	99.61 167	98.96 181	99.28 299	99.49 171	98.46 121	99.72 95	99.71 191	96.50 170	99.88 162	99.31 80	99.11 205	99.67 144
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		98.86 165	98.80 160	99.03 219	99.76 76	98.79 213	99.28 299	99.91 3	97.42 274	99.67 109	99.37 328	97.53 119	99.88 162	98.98 121	97.29 330	98.42 394

PVSNet_Blended		99.08 133	98.97 126	99.42 160	99.76 76	98.79 213	98.78 407	99.91 3	96.74 329	99.67 109	99.49 290	97.53 119	99.88 162	98.98 121	99.85 88	99.60 173

MVS		97.28 348	96.55 361	99.48 145	98.78 385	98.95 185	99.27 304	99.39 261	83.53 450	98.08 377	99.54 272	96.97 146	99.87 168	94.23 405	99.16 198	99.63 165

MG-MVS		99.13 113	99.02 115	99.45 152	99.57 182	98.63 226	99.07 357	99.34 290	98.99 63	99.61 139	99.82 101	97.98 110	99.87 168	97.00 335	99.80 119	99.85 44

MSDG		98.98 151	98.80 160	99.53 127	99.76 76	99.19 144	98.75 410	99.55 92	97.25 288	99.47 167	99.77 164	97.82 113	99.87 168	96.93 342	99.90 55	99.54 197

ETV-MVS		99.26 87	99.21 80	99.40 162	99.46 231	99.30 132	99.56 141	99.52 120	98.52 116	99.44 175	99.27 356	98.41 90	99.86 171	99.10 109	99.59 162	99.04 285

thisisatest0515		98.14 235	97.79 261	99.19 202	99.50 219	98.50 244	98.61 422	96.82 446	96.95 318	99.54 155	99.43 308	91.66 357	99.86 171	98.08 245	99.51 168	99.22 267

thres600view7		97.86 279	97.51 297	98.92 236	99.72 105	97.95 279	99.59 116	98.74 405	97.94 206	99.27 224	98.62 411	91.75 351	99.86 171	93.73 411	98.19 277	98.96 295

lupinMVS		99.13 113	99.01 120	99.46 151	99.51 207	98.94 188	99.05 363	99.16 344	97.86 214	99.80 67	99.56 264	97.39 122	99.86 171	98.94 128	99.85 88	99.58 188

PVSNet	96.02 17	98.85 174	98.84 157	98.89 245	99.73 101	97.28 308	98.32 438	99.60 63	97.86 214	99.50 162	99.57 261	96.75 159	99.86 171	98.56 194	99.70 146	99.54 197

MAR-MVS		98.86 165	98.63 182	99.54 119	99.37 259	99.66 65	99.45 224	99.54 101	96.61 341	99.01 278	99.40 318	97.09 138	99.86 171	97.68 287	99.53 167	99.10 273
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		99.08 133	98.96 130	99.44 156	99.62 158	98.88 195	99.25 315	99.47 204	98.05 189	99.37 196	99.81 116	96.85 150	99.85 177	98.98 121	99.25 191	99.60 173

mamba_0404		99.16 103	99.06 102	99.44 156	99.65 146	98.96 181	99.49 202	99.50 159	98.14 169	99.62 135	99.85 72	96.85 150	99.85 177	99.19 95	99.26 190	99.52 204

testing91		97.44 340	97.02 349	98.71 276	99.18 311	96.89 343	99.19 334	99.04 361	97.78 228	98.31 364	98.29 425	85.41 424	99.85 177	98.01 251	97.95 287	99.39 245

test2506		96.81 363	96.65 359	97.29 393	99.74 94	92.21 436	99.60 109	85.06 467	99.13 35	99.77 78	99.93 10	87.82 410	99.85 177	99.38 69	99.38 177	99.80 83

AllTest		98.87 162	98.72 168	99.31 179	99.86 22	98.48 247	99.56 141	99.61 56	97.85 217	99.36 202	99.85 72	95.95 192	99.85 177	96.66 355	99.83 107	99.59 184

TestCases				99.31 179	99.86 22	98.48 247		99.61 56	97.85 217	99.36 202	99.85 72	95.95 192	99.85 177	96.66 355	99.83 107	99.59 184

jason		99.13 113	99.03 109	99.45 152	99.46 231	98.87 199	99.12 347	99.26 327	98.03 198	99.79 69	99.65 226	97.02 143	99.85 177	99.02 118	99.90 55	99.65 153
jason: jason.
CNVR-MVS		99.42 52	99.30 59	99.78 65	99.62 158	99.71 53	99.26 313	99.52 120	98.82 83	99.39 192	99.71 191	98.96 25	99.85 177	98.59 187	99.80 119	99.77 95

PAPM_NR		99.04 141	98.84 157	99.66 85	99.74 94	99.44 110	99.39 259	99.38 269	97.70 238	99.28 219	99.28 353	98.34 94	99.85 177	96.96 339	99.45 173	99.69 137

testing99		97.36 343	96.94 352	98.63 282	99.18 311	96.70 349	99.30 289	98.93 373	97.71 235	98.23 369	98.26 426	84.92 427	99.84 186	98.04 250	97.85 294	99.35 251

testing222		97.16 353	96.50 362	99.16 205	99.16 321	98.47 249	99.27 304	98.66 416	97.71 235	98.23 369	98.15 429	82.28 441	99.84 186	97.36 314	97.66 300	99.18 269

test1111		98.04 250	98.11 226	97.83 368	99.74 94	93.82 420	99.58 126	95.40 454	99.12 40	99.65 123	99.93 10	90.73 371	99.84 186	99.43 65	99.38 177	99.82 67

ECVR-MVS		98.04 250	98.05 235	98.00 352	99.74 94	94.37 415	99.59 116	94.98 455	99.13 35	99.66 114	99.93 10	90.67 372	99.84 186	99.40 67	99.38 177	99.80 83

test_yl		98.86 165	98.63 182	99.54 119	99.49 221	99.18 146	99.50 188	99.07 357	98.22 155	99.61 139	99.51 284	95.37 219	99.84 186	98.60 185	98.33 264	99.59 184

DCV-MVSNet		98.86 165	98.63 182	99.54 119	99.49 221	99.18 146	99.50 188	99.07 357	98.22 155	99.61 139	99.51 284	95.37 219	99.84 186	98.60 185	98.33 264	99.59 184

Fast-Effi-MVS+		98.70 190	98.43 203	99.51 138	99.51 207	99.28 135	99.52 170	99.47 204	96.11 380	99.01 278	99.34 338	96.20 182	99.84 186	97.88 259	98.82 236	99.39 245

TSAR-MVS + GP.		99.36 68	99.36 43	99.36 168	99.67 128	98.61 230	99.07 357	99.33 298	99.00 61	99.82 62	99.81 116	99.06 16	99.84 186	99.09 110	99.42 175	99.65 153

tpmrst		98.33 218	98.48 201	97.90 361	99.16 321	94.78 405	99.31 287	99.11 350	97.27 286	99.45 170	99.59 252	95.33 222	99.84 186	98.48 201	98.61 246	99.09 277

Vis-MVSNet		99.12 120	98.97 126	99.56 116	99.78 64	99.10 158	99.68 68	99.66 28	98.49 118	99.86 48	99.87 58	94.77 252	99.84 186	99.19 95	99.41 176	99.74 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 198	98.34 209	99.51 138	99.40 251	99.03 168	98.80 405	99.36 278	96.33 361	99.00 282	99.12 375	98.46 84	99.84 186	95.23 391	99.37 184	99.66 148

PatchMatch-RL		98.84 177	98.62 187	99.52 133	99.71 111	99.28 135	99.06 361	99.77 9	97.74 233	99.50 162	99.53 276	95.41 217	99.84 186	97.17 328	99.64 156	99.44 237

EPP-MVSNet		99.13 113	98.99 122	99.53 127	99.65 146	99.06 165	99.81 20	99.33 298	97.43 272	99.60 142	99.88 47	97.14 134	99.84 186	99.13 104	98.94 221	99.69 137

mamba_test_0407		99.13 113	99.03 109	99.43 159	99.62 158	98.88 195	99.51 179	99.50 159	98.14 169	99.37 196	99.85 72	96.85 150	99.83 199	99.19 95	99.25 191	99.60 173

testing3-2		97.84 284	97.70 276	98.24 334	99.53 198	95.37 393	99.55 155	98.67 415	98.46 121	99.27 224	99.34 338	86.58 416	99.83 199	99.32 79	98.63 245	99.52 204

testing11		97.50 333	97.10 346	98.71 276	99.20 305	96.91 341	99.29 294	98.82 393	97.89 211	98.21 372	98.40 420	85.63 422	99.83 199	98.45 206	98.04 285	99.37 249

thres100view900		97.76 298	97.45 306	98.69 278	99.72 105	97.86 285	99.59 116	98.74 405	97.93 207	99.26 229	98.62 411	91.75 351	99.83 199	93.22 416	98.18 278	98.37 400

tfpn200view9		97.72 308	97.38 319	98.72 273	99.69 121	97.96 276	99.50 188	98.73 411	97.83 221	99.17 250	98.45 418	91.67 355	99.83 199	93.22 416	98.18 278	98.37 400

test_prior				99.68 83	99.67 128	99.48 105		99.56 84					99.83 199			99.74 105

1314		98.68 192	98.54 197	99.11 211	98.89 368	98.65 223	99.27 304	99.49 171	96.89 322	97.99 382	99.56 264	97.72 117	99.83 199	97.74 279	99.27 188	98.84 301

thres400		97.77 297	97.38 319	98.92 236	99.69 121	97.96 276	99.50 188	98.73 411	97.83 221	99.17 250	98.45 418	91.67 355	99.83 199	93.22 416	98.18 278	98.96 295

casdiffmvs		99.13 113	98.98 125	99.56 116	99.65 146	99.16 149	99.56 141	99.50 159	98.33 138	99.41 185	99.86 65	95.92 195	99.83 199	99.45 64	99.16 198	99.70 134
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 30	99.48 20	99.54 119	99.78 64	99.30 132	99.89 2	99.58 74	98.56 112	99.73 90	99.69 206	98.55 78	99.82 208	99.69 33	99.85 88	99.48 221

MVS_Test		99.10 130	98.97 126	99.48 145	99.49 221	99.14 154	99.67 71	99.34 290	97.31 283	99.58 146	99.76 168	97.65 118	99.82 208	98.87 140	99.07 212	99.46 232

dp		97.75 302	97.80 260	97.59 384	99.10 332	93.71 423	99.32 284	98.88 386	96.48 353	99.08 266	99.55 267	92.67 329	99.82 208	96.52 359	98.58 249	99.24 265

RPSCF		98.22 225	98.62 187	96.99 399	99.82 48	91.58 438	99.72 53	99.44 235	96.61 341	99.66 114	99.89 37	95.92 195	99.82 208	97.46 307	99.10 209	99.57 191

PMMVS		98.80 181	98.62 187	99.34 171	99.27 287	98.70 219	98.76 409	99.31 312	97.34 280	99.21 239	99.07 377	97.20 133	99.82 208	98.56 194	98.87 231	99.52 204

UBG		97.85 280	97.48 300	98.95 230	99.25 294	97.64 296	99.24 320	98.74 405	97.90 210	98.64 340	98.20 428	88.65 397	99.81 213	98.27 224	98.40 259	99.42 239

EIA-MVS		99.18 98	99.09 98	99.45 152	99.49 221	99.18 146	99.67 71	99.53 115	97.66 243	99.40 190	99.44 306	98.10 104	99.81 213	98.94 128	99.62 159	99.35 251

Effi-MVS+		98.81 178	98.59 193	99.48 145	99.46 231	99.12 157	98.08 445	99.50 159	97.50 263	99.38 194	99.41 314	96.37 177	99.81 213	99.11 106	98.54 254	99.51 213

thres200		97.61 324	97.28 335	98.62 283	99.64 149	98.03 270	99.26 313	98.74 405	97.68 240	99.09 264	98.32 424	91.66 357	99.81 213	92.88 421	98.22 273	98.03 419

tpmvs		97.98 261	98.02 239	97.84 367	99.04 346	94.73 406	99.31 287	99.20 339	96.10 384	98.76 320	99.42 310	94.94 238	99.81 213	96.97 338	98.45 258	98.97 293

casdiffmvs_mvg		99.15 107	99.02 115	99.55 118	99.66 139	99.09 159	99.64 91	99.56 84	98.26 146	99.45 170	99.87 58	96.03 188	99.81 213	99.54 49	99.15 201	99.73 114
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	98.81 178	99.37 41	97.12 397	99.60 173	91.75 437	98.61 422	99.44 235	99.35 23	99.83 59	99.85 72	98.70 66	99.81 213	99.02 118	99.91 44	99.81 74

viewmanbaseed2359cas		99.18 98	99.07 101	99.50 143	99.62 158	99.01 171	99.50 188	99.52 120	98.25 149	99.68 103	99.82 101	96.93 148	99.80 220	99.15 103	99.11 205	99.70 134

icg_test_0403		98.86 165	98.89 146	98.78 268	99.55 190	96.93 336	99.58 126	99.44 235	98.05 189	99.68 103	99.80 132	96.81 155	99.80 220	98.15 236	98.92 224	99.60 173

DPM-MVS		98.95 154	98.71 170	99.66 85	99.63 152	99.55 90	98.64 421	99.10 351	97.93 207	99.42 181	99.55 267	98.67 69	99.80 220	95.80 376	99.68 150	99.61 170

DP-MVS Recon		99.12 120	98.95 134	99.65 89	99.74 94	99.70 55	99.27 304	99.57 79	96.40 360	99.42 181	99.68 213	98.75 58	99.80 220	97.98 253	99.72 142	99.44 237

MVS_111021_LR		99.41 56	99.33 49	99.65 89	99.77 72	99.51 101	98.94 391	99.85 6	98.82 83	99.65 123	99.74 178	98.51 81	99.80 220	98.83 153	99.89 66	99.64 160

viewmambaseed2359dif		99.01 148	98.90 142	99.32 177	99.58 177	98.51 242	99.33 281	99.54 101	97.85 217	99.44 175	99.85 72	96.01 189	99.79 225	99.41 66	99.13 203	99.67 144

CS-MVS		99.50 28	99.48 20	99.54 119	99.76 76	99.42 112	99.90 1	99.55 92	98.56 112	99.78 74	99.70 195	98.65 71	99.79 225	99.65 39	99.78 128	99.41 242

Fast-Effi-MVS+-dtu		98.77 185	98.83 159	98.60 284	99.41 246	96.99 331	99.52 170	99.49 171	98.11 175	99.24 231	99.34 338	96.96 147	99.79 225	97.95 255	99.45 173	99.02 288

baseline1		98.31 219	97.95 246	99.38 167	99.50 219	98.74 216	99.59 116	98.93 373	98.41 128	99.14 253	99.60 250	94.59 265	99.79 225	98.48 201	93.29 413	99.61 170

baseline		99.15 107	99.02 115	99.53 127	99.66 139	99.14 154	99.72 53	99.48 183	98.35 135	99.42 181	99.84 87	96.07 185	99.79 225	99.51 54	99.14 202	99.67 144

PVSNet_0	94.43 19	96.09 378	95.47 385	97.94 357	99.31 277	94.34 417	97.81 447	99.70 15	97.12 300	97.46 397	98.75 408	89.71 383	99.79 225	97.69 286	81.69 450	99.68 141

API-MVS		99.04 141	99.03 109	99.06 215	99.40 251	99.31 129	99.55 155	99.56 84	98.54 114	99.33 209	99.39 322	98.76 55	99.78 231	96.98 337	99.78 128	98.07 416

OMC-MVS		99.08 133	99.04 106	99.20 201	99.67 128	98.22 260	99.28 299	99.52 120	98.07 183	99.66 114	99.81 116	97.79 114	99.78 231	97.79 271	99.81 114	99.60 173

GeoE		98.85 174	98.62 187	99.53 127	99.61 167	99.08 162	99.80 25	99.51 139	97.10 304	99.31 211	99.78 155	95.23 229	99.77 233	98.21 228	99.03 215	99.75 101

alignmvs		98.81 178	98.56 196	99.58 110	99.43 239	99.42 112	99.51 179	98.96 371	98.61 107	99.35 205	98.92 398	94.78 249	99.77 233	99.35 71	98.11 283	99.54 197

tpm cat1		97.39 342	97.36 321	97.50 387	99.17 319	93.73 422	99.43 235	99.31 312	91.27 433	98.71 324	99.08 376	94.31 280	99.77 233	96.41 364	98.50 256	99.00 289

CostFormer		97.72 308	97.73 273	97.71 376	99.15 325	94.02 419	99.54 160	99.02 364	94.67 408	99.04 275	99.35 334	92.35 341	99.77 233	98.50 200	97.94 288	99.34 254

MGCFI-Net		99.01 148	98.85 155	99.50 143	99.42 241	99.26 138	99.82 16	99.48 183	98.60 109	99.28 219	98.81 403	97.04 142	99.76 237	99.29 85	97.87 292	99.47 227

test_241102_ONE					99.84 35	99.90 2		99.48 183	99.07 52	99.91 29	99.74 178	99.20 7	99.76 237

MDTV_nov1_ep13			98.32 211		99.11 329	94.44 413	99.27 304	98.74 405	97.51 262	99.40 190	99.62 243	94.78 249	99.76 237	97.59 291	98.81 238

sasdasda		99.02 144	98.86 152	99.51 138	99.42 241	99.32 125	99.80 25	99.48 183	98.63 104	99.31 211	98.81 403	97.09 138	99.75 240	99.27 89	97.90 289	99.47 227

canonicalmvs		99.02 144	98.86 152	99.51 138	99.42 241	99.32 125	99.80 25	99.48 183	98.63 104	99.31 211	98.81 403	97.09 138	99.75 240	99.27 89	97.90 289	99.47 227

Effi-MVS+-dtu		98.78 183	98.89 146	98.47 307	99.33 269	96.91 341	99.57 134	99.30 317	98.47 120	99.41 185	98.99 388	96.78 157	99.74 242	98.73 164	99.38 177	98.74 317

patchmatchnet-post											98.70 409	94.79 248	99.74 242

SCA		98.19 229	98.16 219	98.27 333	99.30 278	95.55 384	99.07 357	98.97 369	97.57 252	99.43 178	99.57 261	92.72 324	99.74 242	97.58 292	99.20 196	99.52 204

BH-untuned		98.42 208	98.36 207	98.59 285	99.49 221	96.70 349	99.27 304	99.13 348	97.24 290	98.80 315	99.38 325	95.75 205	99.74 242	97.07 333	99.16 198	99.33 255

BH-RMVSNet		98.41 210	98.08 231	99.40 162	99.41 246	98.83 207	99.30 289	98.77 401	97.70 238	98.94 293	99.65 226	92.91 319	99.74 242	96.52 359	99.55 166	99.64 160

MVS_111021_HR		99.41 56	99.32 51	99.66 85	99.72 105	99.47 107	98.95 389	99.85 6	98.82 83	99.54 155	99.73 184	98.51 81	99.74 242	98.91 134	99.88 70	99.77 95

test_post											65.99 461	94.65 263	99.73 248

XVG-ACMP-BASELINE		97.83 287	97.71 275	98.20 336	99.11 329	96.33 365	99.41 247	99.52 120	98.06 187	99.05 274	99.50 287	89.64 385	99.73 248	97.73 280	97.38 327	98.53 382

HyFIR lowres test		99.11 126	98.92 137	99.65 89	99.90 4	99.37 117	99.02 371	99.91 3	97.67 242	99.59 145	99.75 173	95.90 197	99.73 248	99.53 51	99.02 217	99.86 40

DeepMVS_CX				93.34 422	99.29 282	82.27 451		99.22 335	85.15 448	96.33 419	99.05 380	90.97 369	99.73 248	93.57 413	97.77 297	98.01 420

Patchmatch-test		97.93 267	97.65 281	98.77 269	99.18 311	97.07 322	99.03 368	99.14 347	96.16 375	98.74 321	99.57 261	94.56 267	99.72 252	93.36 415	99.11 205	99.52 204

LPG-MVS_test		98.22 225	98.13 224	98.49 300	99.33 269	97.05 324	99.58 126	99.55 92	97.46 265	99.24 231	99.83 92	92.58 331	99.72 252	98.09 241	97.51 313	98.68 335

LGP-MVS_train				98.49 300	99.33 269	97.05 324		99.55 92	97.46 265	99.24 231	99.83 92	92.58 331	99.72 252	98.09 241	97.51 313	98.68 335

BH-w/o		98.00 259	97.89 255	98.32 325	99.35 263	96.20 371	99.01 376	98.90 383	96.42 358	98.38 360	99.00 386	95.26 226	99.72 252	96.06 369	98.61 246	99.03 286

ACMP	97.20 11	98.06 244	97.94 248	98.45 310	99.37 259	97.01 329	99.44 230	99.49 171	97.54 258	98.45 357	99.79 148	91.95 347	99.72 252	97.91 257	97.49 318	98.62 365
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 254	97.90 251	98.40 318	99.23 298	96.80 347	99.70 58	99.60 63	97.12 300	98.18 374	99.70 195	91.73 353	99.72 252	98.39 211	97.45 320	98.68 335
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
test_post1							99.23 323				65.14 462	94.18 285	99.71 258	97.58 292

ADS-MVSNet		98.20 228	98.08 231	98.56 293	99.33 269	96.48 360	99.23 323	99.15 345	96.24 368	99.10 261	99.67 219	94.11 286	99.71 258	96.81 347	99.05 213	99.48 221

JIA-IIPM		97.50 333	97.02 349	98.93 234	98.73 394	97.80 287	99.30 289	98.97 369	91.73 432	98.91 296	94.86 450	95.10 233	99.71 258	97.58 292	97.98 286	99.28 259

EPMVS		97.82 290	97.65 281	98.35 322	98.88 369	95.98 375	99.49 202	94.71 457	97.57 252	99.26 229	99.48 296	92.46 338	99.71 258	97.87 261	99.08 211	99.35 251

TDRefinement		95.42 389	94.57 397	97.97 354	89.83 460	96.11 374	99.48 208	98.75 402	96.74 329	96.68 416	99.88 47	88.65 397	99.71 258	98.37 214	82.74 449	98.09 415

ACMM	97.58 5	98.37 216	98.34 209	98.48 302	99.41 246	97.10 318	99.56 141	99.45 226	98.53 115	99.04 275	99.85 72	93.00 315	99.71 258	98.74 162	97.45 320	98.64 356
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 264	97.77 266	98.57 289	99.59 175	96.61 356	99.45 224	99.08 354	98.21 157	98.88 301	99.80 132	88.66 396	99.70 264	98.58 188	97.72 298	99.39 245

CHOSEN 280x420		99.12 120	99.13 90	99.08 212	99.66 139	97.89 282	98.43 432	99.71 13	98.88 77	99.62 135	99.76 168	96.63 163	99.70 264	99.46 63	99.99 1	99.66 148

EC-MVSNet		99.44 47	99.39 37	99.58 110	99.56 186	99.49 103	99.88 4	99.58 74	98.38 130	99.73 90	99.69 206	98.20 100	99.70 264	99.64 41	99.82 111	99.54 197

PatchmatchNet		98.31 219	98.36 207	98.19 337	99.16 321	95.32 394	99.27 304	98.92 376	97.37 278	99.37 196	99.58 256	94.90 242	99.70 264	97.43 310	99.21 195	99.54 197
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 239	97.99 241	98.44 313	99.41 246	96.96 335	99.60 109	99.56 84	98.09 178	98.15 375	99.91 24	90.87 370	99.70 264	98.88 137	97.45 320	98.67 343
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 333	96.90 353	99.29 187	99.23 298	98.78 215	99.32 284	98.90 383	97.52 261	98.56 350	98.09 434	84.72 429	99.69 269	97.86 262	97.88 291	99.39 245

HQP_MVS		98.27 224	98.22 217	98.44 313	99.29 282	96.97 333	99.39 259	99.47 204	98.97 69	99.11 258	99.61 247	92.71 326	99.69 269	97.78 272	97.63 301	98.67 343

plane_prior5								99.47 204					99.69 269	97.78 272	97.63 301	98.67 343

D2MVS		98.41 210	98.50 200	98.15 342	99.26 290	96.62 355	99.40 255	99.61 56	97.71 235	98.98 285	99.36 331	96.04 187	99.67 272	98.70 167	97.41 325	98.15 412

IS-MVSNet		99.05 140	98.87 150	99.57 114	99.73 101	99.32 125	99.75 42	99.20 339	98.02 201	99.56 150	99.86 65	96.54 168	99.67 272	98.09 241	99.13 203	99.73 114

CLD-MVS		98.16 233	98.10 227	98.33 323	99.29 282	96.82 346	98.75 410	99.44 235	97.83 221	99.13 254	99.55 267	92.92 317	99.67 272	98.32 221	97.69 299	98.48 386
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 350	97.30 332	97.09 398	99.43 239	93.31 429	99.73 51	98.87 388	98.83 82	99.28 219	99.80 132	84.45 430	99.66 275	97.88 259	97.45 320	98.30 402

AUN-MVS		96.88 361	96.31 367	98.59 285	99.48 228	97.04 327	99.27 304	99.22 335	97.44 271	98.51 353	99.41 314	91.97 346	99.66 275	97.71 283	83.83 447	99.07 283

UniMVSNet_ETH3D		97.32 347	96.81 355	98.87 251	99.40 251	97.46 302	99.51 179	99.53 115	95.86 388	98.54 352	99.77 164	82.44 439	99.66 275	98.68 172	97.52 312	99.50 217

OPM-MVS		98.19 229	98.10 227	98.45 310	98.88 369	97.07 322	99.28 299	99.38 269	98.57 111	99.22 236	99.81 116	92.12 343	99.66 275	98.08 245	97.54 310	98.61 374
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 270	97.78 264	98.32 325	99.46 231	96.68 353	99.56 141	99.54 101	98.41 128	97.79 393	99.87 58	90.18 379	99.66 275	98.05 249	97.18 335	98.62 365

icg_test_0407		98.86 165	98.91 140	98.72 273	99.55 190	96.93 336	99.50 188	99.44 235	98.05 189	99.66 114	99.80 132	97.13 135	99.65 280	98.15 236	98.92 224	99.60 173

hse-mvs2		97.50 333	97.14 343	98.59 285	99.49 221	97.05 324	99.28 299	99.22 335	98.94 72	99.66 114	99.42 310	94.93 239	99.65 280	99.48 60	83.80 448	99.08 278

VPA-MVSNet		98.29 222	97.95 246	99.30 184	99.16 321	99.54 92	99.50 188	99.58 74	98.27 144	99.35 205	99.37 328	92.53 333	99.65 280	99.35 71	94.46 394	98.72 319

TR-MVS		97.76 298	97.41 317	98.82 260	99.06 341	97.87 283	98.87 399	98.56 419	96.63 340	98.68 332	99.22 362	92.49 334	99.65 280	95.40 387	97.79 296	98.95 297

reproduce_monomvs		97.89 274	97.87 256	97.96 356	99.51 207	95.45 389	99.60 109	99.25 329	99.17 30	98.85 309	99.49 290	89.29 388	99.64 284	99.35 71	96.31 351	98.78 305

gm-plane-assit					98.54 414	92.96 431			94.65 409		99.15 370		99.64 284	97.56 297

HQP4-MVS										98.66 333			99.64 284			98.64 356

HQP-MVS		98.02 254	97.90 251	98.37 321	99.19 308	96.83 344	98.98 382	99.39 261	98.24 151	98.66 333	99.40 318	92.47 335	99.64 284	97.19 325	97.58 306	98.64 356

PAPM		97.59 325	97.09 347	99.07 213	99.06 341	98.26 258	98.30 439	99.10 351	94.88 403	98.08 377	99.34 338	96.27 180	99.64 284	89.87 435	98.92 224	99.31 257

TAPA-MVS	97.07 15	97.74 304	97.34 326	98.94 232	99.70 116	97.53 299	99.25 315	99.51 139	91.90 431	99.30 215	99.63 238	98.78 51	99.64 284	88.09 442	99.87 73	99.65 153
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 214	98.09 230	99.24 197	99.26 290	99.32 125	99.56 141	99.55 92	97.45 268	98.71 324	99.83 92	93.23 310	99.63 290	98.88 137	96.32 350	98.76 311

ITE_SJBPF				98.08 345	99.29 282	96.37 363		98.92 376	98.34 136	98.83 310	99.75 173	91.09 367	99.62 291	95.82 374	97.40 326	98.25 406

LF4IMVS		97.52 330	97.46 305	97.70 377	98.98 357	95.55 384	99.29 294	98.82 393	98.07 183	98.66 333	99.64 232	89.97 380	99.61 292	97.01 334	96.68 340	97.94 427

tpm		97.67 319	97.55 290	98.03 347	99.02 348	95.01 401	99.43 235	98.54 421	96.44 356	99.12 256	99.34 338	91.83 350	99.60 293	97.75 278	96.46 346	99.48 221

tpm2		97.44 340	97.34 326	97.74 375	99.15 325	94.36 416	99.45 224	98.94 372	93.45 422	98.90 298	99.44 306	91.35 363	99.59 294	97.31 316	98.07 284	99.29 258

mamba_test_0407_2		99.06 137	98.96 130	99.35 170	99.62 158	98.88 195	99.25 315	99.47 204	98.05 189	99.37 196	99.81 116	96.85 150	99.58 295	98.98 121	99.25 191	99.60 173

SD_0403		97.55 327	97.53 294	97.62 380	99.61 167	93.64 426	99.72 53	99.44 235	98.03 198	98.62 345	99.39 322	96.06 186	99.57 296	87.88 444	99.01 218	99.66 148

baseline2		97.87 277	97.55 290	98.82 260	99.18 311	98.02 271	99.41 247	96.58 451	96.97 315	96.51 417	99.17 367	93.43 305	99.57 296	97.71 283	99.03 215	98.86 299

MS-PatchMatch		97.24 352	97.32 330	96.99 399	98.45 417	93.51 428	98.82 403	99.32 308	97.41 275	98.13 376	99.30 349	88.99 390	99.56 298	95.68 380	99.80 119	97.90 430

TinyColmap		97.12 355	96.89 354	97.83 368	99.07 339	95.52 387	98.57 425	98.74 405	97.58 251	97.81 392	99.79 148	88.16 404	99.56 298	95.10 392	97.21 333	98.39 398

USDC		97.34 345	97.20 340	97.75 373	99.07 339	95.20 396	98.51 429	99.04 361	97.99 202	98.31 364	99.86 65	89.02 389	99.55 300	95.67 381	97.36 328	98.49 385

MSLP-MVS++		99.46 39	99.47 22	99.44 156	99.60 173	99.16 149	99.41 247	99.71 13	98.98 66	99.45 170	99.78 155	99.19 9	99.54 301	99.28 86	99.84 96	99.63 165

UWE-MVS-28		97.36 343	97.24 339	97.75 373	98.84 378	94.44 413	99.24 320	97.58 440	97.98 203	99.00 282	99.00 386	91.35 363	99.53 302	93.75 410	98.39 260	99.27 263

TAMVS		99.12 120	99.08 99	99.24 197	99.46 231	98.55 234	99.51 179	99.46 215	98.09 178	99.45 170	99.82 101	98.34 94	99.51 303	98.70 167	98.93 222	99.67 144

EPNet_dtu		98.03 252	97.96 244	98.23 335	98.27 420	95.54 386	99.23 323	98.75 402	99.02 56	97.82 391	99.71 191	96.11 184	99.48 304	93.04 419	99.65 155	99.69 137
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 365	96.22 369	97.97 354	97.00 442	96.28 367	98.66 419	99.03 363	96.61 341	96.93 414	99.79 148	87.20 413	99.47 305	96.65 357	94.13 401	98.16 411

EG-PatchMatch MVS		95.97 380	95.69 381	96.81 406	97.78 427	92.79 432	99.16 338	98.93 373	96.16 375	94.08 435	99.22 362	82.72 437	99.47 305	95.67 381	97.50 315	98.17 410

myMVS_eth3d28		97.69 313	97.34 326	98.73 271	99.27 287	97.52 300	99.33 281	98.78 400	98.03 198	98.82 312	98.49 416	86.64 415	99.46 307	98.44 207	98.24 272	99.23 266

MVP-Stereo		97.81 292	97.75 271	97.99 353	97.53 431	96.60 357	98.96 386	98.85 390	97.22 292	97.23 404	99.36 331	95.28 223	99.46 307	95.51 383	99.78 128	97.92 429
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 200	98.67 174	98.30 327	99.35 263	95.59 383	99.50 188	99.55 92	98.60 109	99.39 192	99.83 92	94.48 273	99.45 309	98.75 161	98.56 252	99.85 44

test-LLR		98.06 244	97.90 251	98.55 295	98.79 382	97.10 318	98.67 416	97.75 436	97.34 280	98.61 346	98.85 400	94.45 275	99.45 309	97.25 319	99.38 177	99.10 273

TESTMET0.1,1		97.55 327	97.27 338	98.40 318	98.93 362	96.53 358	98.67 416	97.61 439	96.96 316	98.64 340	99.28 353	88.63 399	99.45 309	97.30 317	99.38 177	99.21 268

test-mter		97.49 338	97.13 345	98.55 295	98.79 382	97.10 318	98.67 416	97.75 436	96.65 336	98.61 346	98.85 400	88.23 403	99.45 309	97.25 319	99.38 177	99.10 273

mvs_anonymous		99.03 143	98.99 122	99.16 205	99.38 256	98.52 240	99.51 179	99.38 269	97.79 226	99.38 194	99.81 116	97.30 128	99.45 309	99.35 71	98.99 219	99.51 213

tfpnnormal		97.84 284	97.47 303	98.98 225	99.20 305	99.22 143	99.64 91	99.61 56	96.32 362	98.27 368	99.70 195	93.35 309	99.44 314	95.69 379	95.40 377	98.27 404

v7n		97.87 277	97.52 295	98.92 236	98.76 392	98.58 232	99.84 12	99.46 215	96.20 371	98.91 296	99.70 195	94.89 243	99.44 314	96.03 370	93.89 406	98.75 313

jajsoiax		98.43 207	98.28 214	98.88 247	98.60 409	98.43 251	99.82 16	99.53 115	98.19 159	98.63 342	99.80 132	93.22 312	99.44 314	99.22 93	97.50 315	98.77 309

mvs_tets		98.40 213	98.23 216	98.91 240	98.67 402	98.51 242	99.66 78	99.53 115	98.19 159	98.65 339	99.81 116	92.75 321	99.44 314	99.31 80	97.48 319	98.77 309

sc_t1		95.75 384	95.05 391	97.87 363	98.83 379	94.61 410	99.21 329	99.45 226	87.45 444	97.97 384	99.85 72	81.19 444	99.43 318	98.27 224	93.20 415	99.57 191

Vis-MVSNet (Re-imp)		98.87 162	98.72 168	99.31 179	99.71 111	98.88 195	99.80 25	99.44 235	97.91 209	99.36 202	99.78 155	95.49 215	99.43 318	97.91 257	99.11 205	99.62 168

OPU-MVS				99.64 95	99.56 186	99.72 51	99.60 109				99.70 195	99.27 5	99.42 320	98.24 227	99.80 119	99.79 87

Anonymous20231211		97.88 275	97.54 293	98.90 242	99.71 111	98.53 236	99.48 208	99.57 79	94.16 413	98.81 313	99.68 213	93.23 310	99.42 320	98.84 150	94.42 396	98.76 311

ttmdpeth		97.80 294	97.63 285	98.29 328	98.77 390	97.38 305	99.64 91	99.36 278	98.78 92	96.30 420	99.58 256	92.34 342	99.39 322	98.36 216	95.58 372	98.10 414

VPNet		97.84 284	97.44 311	99.01 221	99.21 303	98.94 188	99.48 208	99.57 79	98.38 130	99.28 219	99.73 184	88.89 391	99.39 322	99.19 95	93.27 414	98.71 321

nrg030		98.64 197	98.42 204	99.28 191	99.05 344	99.69 57	99.81 20	99.46 215	98.04 196	99.01 278	99.82 101	96.69 161	99.38 324	99.34 76	94.59 393	98.78 305

GA-MVS		97.85 280	97.47 303	99.00 223	99.38 256	97.99 273	98.57 425	99.15 345	97.04 311	98.90 298	99.30 349	89.83 382	99.38 324	96.70 352	98.33 264	99.62 168

UniMVSNet (Re)		98.29 222	98.00 240	99.13 210	99.00 351	99.36 120	99.49 202	99.51 139	97.95 205	98.97 287	99.13 372	96.30 179	99.38 324	98.36 216	93.34 412	98.66 352

FIs		98.78 183	98.63 182	99.23 199	99.18 311	99.54 92	99.83 15	99.59 69	98.28 142	98.79 317	99.81 116	96.75 159	99.37 327	99.08 111	96.38 348	98.78 305

PS-MVSNAJss		98.92 156	98.92 137	98.90 242	98.78 385	98.53 236	99.78 32	99.54 101	98.07 183	99.00 282	99.76 168	99.01 18	99.37 327	99.13 104	97.23 332	98.81 302

CDS-MVSNet		99.09 131	99.03 109	99.25 194	99.42 241	98.73 217	99.45 224	99.46 215	98.11 175	99.46 169	99.77 164	98.01 109	99.37 327	98.70 167	98.92 224	99.66 148
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 384	95.16 389	97.51 386	99.30 278	93.69 424	98.88 397	95.78 452	85.09 449	98.78 318	92.65 452	91.29 365	99.37 327	94.85 397	99.85 88	99.46 232

v1192		97.81 292	97.44 311	98.91 240	98.88 369	98.68 220	99.51 179	99.34 290	96.18 373	99.20 242	99.34 338	94.03 290	99.36 331	95.32 389	95.18 381	98.69 330

EI-MVSNet		98.67 193	98.67 174	98.68 279	99.35 263	97.97 274	99.50 188	99.38 269	96.93 321	99.20 242	99.83 92	97.87 111	99.36 331	98.38 212	97.56 308	98.71 321

MVSTER		98.49 202	98.32 211	99.00 223	99.35 263	99.02 169	99.54 160	99.38 269	97.41 275	99.20 242	99.73 184	93.86 298	99.36 331	98.87 140	97.56 308	98.62 365

gg-mvs-nofinetune		96.17 376	95.32 388	98.73 271	98.79 382	98.14 264	99.38 264	94.09 458	91.07 436	98.07 380	91.04 456	89.62 386	99.35 334	96.75 349	99.09 210	98.68 335

pm-mvs1		97.68 316	97.28 335	98.88 247	99.06 341	98.62 228	99.50 188	99.45 226	96.32 362	97.87 389	99.79 148	92.47 335	99.35 334	97.54 299	93.54 410	98.67 343

OurMVSNet-221017-0		97.88 275	97.77 266	98.19 337	98.71 398	96.53 358	99.88 4	99.00 366	97.79 226	98.78 318	99.94 6	91.68 354	99.35 334	97.21 321	96.99 339	98.69 330

EGC-MVSNET		82.80 421	77.86 427	97.62 380	97.91 424	96.12 373	99.33 281	99.28 323	8.40 464	25.05 465	99.27 356	84.11 431	99.33 337	89.20 437	98.22 273	97.42 438

pmmvs6		96.53 368	96.09 373	97.82 370	98.69 400	95.47 388	99.37 266	99.47 204	93.46 421	97.41 398	99.78 155	87.06 414	99.33 337	96.92 344	92.70 422	98.65 354

V42		98.06 244	97.79 261	98.86 254	98.98 357	98.84 204	99.69 62	99.34 290	96.53 348	99.30 215	99.37 328	94.67 260	99.32 339	97.57 296	94.66 391	98.42 394

lessismore_v0				97.79 372	98.69 400	95.44 391		94.75 456		95.71 426	99.87 58	88.69 395	99.32 339	95.89 373	94.93 388	98.62 365

OpenMVS_ROB	92.34 20	94.38 401	93.70 407	96.41 411	97.38 433	93.17 430	99.06 361	98.75 402	86.58 447	94.84 433	98.26 426	81.53 442	99.32 339	89.01 438	97.87 292	96.76 441

v8		97.95 266	97.63 285	98.93 234	98.95 361	98.81 212	99.80 25	99.41 251	96.03 385	99.10 261	99.42 310	94.92 241	99.30 342	96.94 341	94.08 403	98.66 352

v1921920		97.80 294	97.45 306	98.84 258	98.80 381	98.53 236	99.52 170	99.34 290	96.15 377	99.24 231	99.47 299	93.98 292	99.29 343	95.40 387	95.13 383	98.69 330

anonymousdsp		98.44 206	98.28 214	98.94 232	98.50 415	98.96 181	99.77 34	99.50 159	97.07 306	98.87 304	99.77 164	94.76 253	99.28 344	98.66 174	97.60 304	98.57 380

MVSFormer		99.17 101	99.12 92	99.29 187	99.51 207	98.94 188	99.88 4	99.46 215	97.55 255	99.80 67	99.65 226	97.39 122	99.28 344	99.03 116	99.85 88	99.65 153

test_djsdf		98.67 193	98.57 194	98.98 225	98.70 399	98.91 193	99.88 4	99.46 215	97.55 255	99.22 236	99.88 47	95.73 206	99.28 344	99.03 116	97.62 303	98.75 313

VortexMVS		98.67 193	98.66 177	98.68 279	99.62 158	97.96 276	99.59 116	99.41 251	98.13 171	99.31 211	99.70 195	95.48 216	99.27 347	99.40 67	97.32 329	98.79 303

SSC-MVS3.2		97.34 345	97.15 342	97.93 358	99.02 348	95.76 380	99.48 208	99.58 74	97.62 247	99.09 264	99.53 276	87.95 406	99.27 347	96.42 362	95.66 370	98.75 313

cascas		97.69 313	97.43 315	98.48 302	98.60 409	97.30 307	98.18 443	99.39 261	92.96 425	98.41 358	98.78 407	93.77 301	99.27 347	98.16 234	98.61 246	98.86 299

v144192		97.92 270	97.60 288	98.87 251	98.83 379	98.65 223	99.55 155	99.34 290	96.20 371	99.32 210	99.40 318	94.36 277	99.26 350	96.37 366	95.03 385	98.70 326

dmvs_re		98.08 242	98.16 219	97.85 365	99.55 190	94.67 409	99.70 58	98.92 376	98.15 164	99.06 272	99.35 334	93.67 304	99.25 351	97.77 275	97.25 331	99.64 160

v2v482		98.06 244	97.77 266	98.92 236	98.90 367	98.82 210	99.57 134	99.36 278	96.65 336	99.19 245	99.35 334	94.20 282	99.25 351	97.72 282	94.97 386	98.69 330

v1240		97.69 313	97.32 330	98.79 266	98.85 376	98.43 251	99.48 208	99.36 278	96.11 380	99.27 224	99.36 331	93.76 302	99.24 353	94.46 401	95.23 380	98.70 326

WBMVS		97.74 304	97.50 298	98.46 308	99.24 296	97.43 303	99.21 329	99.42 248	97.45 268	98.96 289	99.41 314	88.83 392	99.23 354	98.94 128	96.02 356	98.71 321

v1144		97.98 261	97.69 277	98.85 257	98.87 372	98.66 222	99.54 160	99.35 285	96.27 366	99.23 235	99.35 334	94.67 260	99.23 354	96.73 350	95.16 382	98.68 335

v10		97.85 280	97.52 295	98.86 254	98.99 354	98.67 221	99.75 42	99.41 251	95.70 389	98.98 285	99.41 314	94.75 254	99.23 354	96.01 372	94.63 392	98.67 343

WR-MVS_H		98.13 236	97.87 256	98.90 242	99.02 348	98.84 204	99.70 58	99.59 69	97.27 286	98.40 359	99.19 366	95.53 213	99.23 354	98.34 218	93.78 408	98.61 374

miper_enhance_ethall		98.16 233	98.08 231	98.41 316	98.96 360	97.72 291	98.45 431	99.32 308	96.95 318	98.97 287	99.17 367	97.06 141	99.22 358	97.86 262	95.99 359	98.29 403

GG-mvs-BLEND				98.45 310	98.55 413	98.16 262	99.43 235	93.68 459		97.23 404	98.46 417	89.30 387	99.22 358	95.43 386	98.22 273	97.98 425

FC-MVSNet-test		98.75 186	98.62 187	99.15 209	99.08 338	99.45 109	99.86 11	99.60 63	98.23 154	98.70 330	99.82 101	96.80 156	99.22 358	99.07 112	96.38 348	98.79 303

UniMVSNet_NR-MVSNet		98.22 225	97.97 243	98.96 228	98.92 364	98.98 174	99.48 208	99.53 115	97.76 230	98.71 324	99.46 303	96.43 175	99.22 358	98.57 191	92.87 420	98.69 330

DU-MVS		98.08 242	97.79 261	98.96 228	98.87 372	98.98 174	99.41 247	99.45 226	97.87 213	98.71 324	99.50 287	94.82 245	99.22 358	98.57 191	92.87 420	98.68 335

cl____		98.01 257	97.84 259	98.55 295	99.25 294	97.97 274	98.71 414	99.34 290	96.47 355	98.59 349	99.54 272	95.65 209	99.21 363	97.21 321	95.77 365	98.46 391

WR-MVS		98.06 244	97.73 273	99.06 215	98.86 375	99.25 140	99.19 334	99.35 285	97.30 284	98.66 333	99.43 308	93.94 293	99.21 363	98.58 188	94.28 398	98.71 321

test_0402		96.64 366	96.24 368	97.85 365	98.85 376	96.43 362	99.44 230	99.26 327	93.52 419	96.98 412	99.52 280	88.52 400	99.20 365	92.58 426	97.50 315	97.93 428

icg_test_0407_2		98.79 182	98.86 152	98.57 289	99.55 190	96.93 336	99.07 357	99.44 235	98.05 189	99.66 114	99.80 132	97.13 135	99.18 366	98.15 236	98.92 224	99.60 173

SixPastTwentyTwo		97.50 333	97.33 329	98.03 347	98.65 403	96.23 370	99.77 34	98.68 414	97.14 297	97.90 387	99.93 10	90.45 373	99.18 366	97.00 335	96.43 347	98.67 343

cl22		97.85 280	97.64 284	98.48 302	99.09 335	97.87 283	98.60 424	99.33 298	97.11 303	98.87 304	99.22 362	92.38 340	99.17 368	98.21 228	95.99 359	98.42 394

tt0320		95.71 386	95.07 390	97.62 380	99.05 344	95.02 400	99.25 315	99.52 120	86.81 445	97.97 384	99.72 188	83.58 434	99.15 369	96.38 365	93.35 411	98.68 335

WB-MVSnew		97.65 321	97.65 281	97.63 379	98.78 385	97.62 297	99.13 344	98.33 424	97.36 279	99.07 267	98.94 394	95.64 210	99.15 369	92.95 420	98.68 244	96.12 448

IterMVS-SCA-FT		97.82 290	97.75 271	98.06 346	99.57 182	96.36 364	99.02 371	99.49 171	97.18 294	98.71 324	99.72 188	92.72 324	99.14 371	97.44 309	95.86 364	98.67 343

pmmvs5		97.52 330	97.30 332	98.16 339	98.57 412	96.73 348	99.27 304	98.90 383	96.14 378	98.37 361	99.53 276	91.54 360	99.14 371	97.51 301	95.87 363	98.63 363

v148		97.79 296	97.55 290	98.50 299	98.74 393	97.72 291	99.54 160	99.33 298	96.26 367	98.90 298	99.51 284	94.68 259	99.14 371	97.83 266	93.15 417	98.63 363

ICG_test_0404		98.53 201	98.52 199	98.55 295	99.55 190	96.93 336	99.20 332	99.44 235	98.05 189	98.96 289	99.80 132	94.66 262	99.13 374	98.15 236	98.92 224	99.60 173

miper_ehance_all_eth		98.18 231	98.10 227	98.41 316	99.23 298	97.72 291	98.72 413	99.31 312	96.60 344	98.88 301	99.29 351	97.29 129	99.13 374	97.60 290	95.99 359	98.38 399

NR-MVSNet		97.97 264	97.61 287	99.02 220	98.87 372	99.26 138	99.47 217	99.42 248	97.63 245	97.08 410	99.50 287	95.07 234	99.13 374	97.86 262	93.59 409	98.68 335

IterMVS		97.83 287	97.77 266	98.02 349	99.58 177	96.27 368	99.02 371	99.48 183	97.22 292	98.71 324	99.70 195	92.75 321	99.13 374	97.46 307	96.00 358	98.67 343
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 402	94.90 393	91.84 427	97.24 437	80.01 457	98.52 428	99.48 183	89.01 441	91.99 444	99.67 219	85.67 421	99.13 374	95.44 385	97.03 338	96.39 445
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 249	97.96 244	98.33 323	99.26 290	97.38 305	98.56 427	99.31 312	96.65 336	98.88 301	99.52 280	96.58 166	99.12 379	97.39 312	95.53 375	98.47 388

pmmvs4		98.13 236	97.90 251	98.81 263	98.61 408	98.87 199	98.99 379	99.21 338	96.44 356	99.06 272	99.58 256	95.90 197	99.11 380	97.18 327	96.11 355	98.46 391

TransMVSNet (Re)		97.15 354	96.58 360	98.86 254	99.12 327	98.85 203	99.49 202	98.91 381	95.48 392	97.16 408	99.80 132	93.38 306	99.11 380	94.16 407	91.73 427	98.62 365

ambc				93.06 425	92.68 456	82.36 450	98.47 430	98.73 411		95.09 431	97.41 439	55.55 457	99.10 382	96.42 362	91.32 428	97.71 431

Baseline_NR-MVSNet		97.76 298	97.45 306	98.68 279	99.09 335	98.29 256	99.41 247	98.85 390	95.65 390	98.63 342	99.67 219	94.82 245	99.10 382	98.07 248	92.89 419	98.64 356

test_vis3_rt		87.04 417	85.81 420	90.73 431	93.99 455	81.96 452	99.76 37	90.23 466	92.81 427	81.35 454	91.56 454	40.06 463	99.07 384	94.27 404	88.23 441	91.15 454

CP-MVSNet		98.09 240	97.78 264	99.01 221	98.97 359	99.24 141	99.67 71	99.46 215	97.25 288	98.48 356	99.64 232	93.79 300	99.06 385	98.63 178	94.10 402	98.74 317

PS-CasMVS		97.93 267	97.59 289	98.95 230	98.99 354	99.06 165	99.68 68	99.52 120	97.13 298	98.31 364	99.68 213	92.44 339	99.05 386	98.51 199	94.08 403	98.75 313

K. test v3		97.10 356	96.79 356	98.01 350	98.72 396	96.33 365	99.87 8	97.05 443	97.59 249	96.16 422	99.80 132	88.71 394	99.04 387	96.69 353	96.55 345	98.65 354

new_pmnet		96.38 372	96.03 374	97.41 389	98.13 423	95.16 399	99.05 363	99.20 339	93.94 414	97.39 401	98.79 406	91.61 359	99.04 387	90.43 433	95.77 365	98.05 418

DIV-MVS_self_test		98.01 257	97.85 258	98.48 302	99.24 296	97.95 279	98.71 414	99.35 285	96.50 349	98.60 348	99.54 272	95.72 207	99.03 389	97.21 321	95.77 365	98.46 391

IterMVS-LS		98.46 205	98.42 204	98.58 288	99.59 175	98.00 272	99.37 266	99.43 246	96.94 320	99.07 267	99.59 252	97.87 111	99.03 389	98.32 221	95.62 371	98.71 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 321	97.68 278	97.55 385	98.62 406	94.97 402	98.84 401	99.30 317	96.83 327	98.19 373	99.34 338	97.01 145	99.02 391	95.00 395	96.01 357	98.64 356

Patchmtry		97.75 302	97.40 318	98.81 263	99.10 332	98.87 199	99.11 353	99.33 298	94.83 405	98.81 313	99.38 325	94.33 278	99.02 391	96.10 368	95.57 373	98.53 382

N_pmnet		94.95 396	95.83 379	92.31 426	98.47 416	79.33 458	99.12 347	92.81 464	93.87 415	97.68 394	99.13 372	93.87 297	99.01 393	91.38 430	96.19 353	98.59 378

CR-MVSNet		98.17 232	97.93 249	98.87 251	99.18 311	98.49 245	99.22 327	99.33 298	96.96 316	99.56 150	99.38 325	94.33 278	99.00 394	94.83 398	98.58 249	99.14 270

c3_l		98.12 238	98.04 236	98.38 320	99.30 278	97.69 295	98.81 404	99.33 298	96.67 334	98.83 310	99.34 338	97.11 137	98.99 395	97.58 292	95.34 378	98.48 386

test0.0.03 1		97.71 311	97.42 316	98.56 293	98.41 419	97.82 286	98.78 407	98.63 417	97.34 280	98.05 381	98.98 390	94.45 275	98.98 396	95.04 394	97.15 336	98.89 298

PatchT		97.03 358	96.44 364	98.79 266	98.99 354	98.34 255	99.16 338	99.07 357	92.13 430	99.52 159	97.31 443	94.54 270	98.98 396	88.54 440	98.73 241	99.03 286

GBi-Net		97.68 316	97.48 300	98.29 328	99.51 207	97.26 311	99.43 235	99.48 183	96.49 350	99.07 267	99.32 346	90.26 375	98.98 396	97.10 329	96.65 341	98.62 365

test1		97.68 316	97.48 300	98.29 328	99.51 207	97.26 311	99.43 235	99.48 183	96.49 350	99.07 267	99.32 346	90.26 375	98.98 396	97.10 329	96.65 341	98.62 365

FMVSNet3		98.03 252	97.76 270	98.84 258	99.39 254	98.98 174	99.40 255	99.38 269	96.67 334	99.07 267	99.28 353	92.93 316	98.98 396	97.10 329	96.65 341	98.56 381

FMVSNet2		97.72 308	97.36 321	98.80 265	99.51 207	98.84 204	99.45 224	99.42 248	96.49 350	98.86 308	99.29 351	90.26 375	98.98 396	96.44 361	96.56 344	98.58 379

FMVSNet1		96.84 362	96.36 366	98.29 328	99.32 276	97.26 311	99.43 235	99.48 183	95.11 397	98.55 351	99.32 346	83.95 432	98.98 396	95.81 375	96.26 352	98.62 365

ppachtmachnet_test		97.49 338	97.45 306	97.61 383	98.62 406	95.24 395	98.80 405	99.46 215	96.11 380	98.22 371	99.62 243	96.45 173	98.97 403	93.77 409	95.97 362	98.61 374

TranMVSNet+NR-MVSNet		97.93 267	97.66 280	98.76 270	98.78 385	98.62 228	99.65 84	99.49 171	97.76 230	98.49 355	99.60 250	94.23 281	98.97 403	98.00 252	92.90 418	98.70 326

MVStest1		96.08 379	95.48 384	97.89 362	98.93 362	96.70 349	99.56 141	99.35 285	92.69 428	91.81 445	99.46 303	89.90 381	98.96 405	95.00 395	92.61 423	98.00 423

tt0320-xc		95.31 392	94.59 396	97.45 388	98.92 364	94.73 406	99.20 332	99.31 312	86.74 446	97.23 404	99.72 188	81.14 445	98.95 406	97.08 332	91.98 426	98.67 343

test_method		91.10 412	91.36 414	90.31 432	95.85 445	73.72 465	94.89 453	99.25 329	68.39 456	95.82 425	99.02 384	80.50 446	98.95 406	93.64 412	94.89 390	98.25 406

ADS-MVSNet2		98.02 254	98.07 234	97.87 363	99.33 269	95.19 397	99.23 323	99.08 354	96.24 368	99.10 261	99.67 219	94.11 286	98.93 408	96.81 347	99.05 213	99.48 221

ET-MVSNet_ETH3D		96.49 369	95.64 383	99.05 217	99.53 198	98.82 210	98.84 401	97.51 441	97.63 245	84.77 450	99.21 365	92.09 344	98.91 409	98.98 121	92.21 425	99.41 242

miper_lstm_enhance		98.00 259	97.91 250	98.28 332	99.34 268	97.43 303	98.88 397	99.36 278	96.48 353	98.80 315	99.55 267	95.98 190	98.91 409	97.27 318	95.50 376	98.51 384

MonoMVSNet		98.38 214	98.47 202	98.12 344	98.59 411	96.19 372	99.72 53	98.79 399	97.89 211	99.44 175	99.52 280	96.13 183	98.90 411	98.64 176	97.54 310	99.28 259

PEN-MVS		97.76 298	97.44 311	98.72 273	98.77 390	98.54 235	99.78 32	99.51 139	97.06 308	98.29 367	99.64 232	92.63 330	98.89 412	98.09 241	93.16 416	98.72 319

testing3		97.28 348	96.76 357	98.82 260	99.37 259	98.07 269	99.45 224	99.36 278	97.56 254	97.89 388	98.95 393	83.70 433	98.82 413	96.03 370	98.56 252	99.58 188

testgi		97.65 321	97.50 298	98.13 343	99.36 262	96.45 361	99.42 242	99.48 183	97.76 230	97.87 389	99.45 305	91.09 367	98.81 414	94.53 400	98.52 255	99.13 272

testf1		90.42 415	90.68 416	89.65 435	97.78 427	73.97 463	99.13 344	98.81 395	89.62 438	91.80 446	98.93 395	62.23 455	98.80 415	86.61 449	91.17 429	96.19 446

APD_test2		90.42 415	90.68 416	89.65 435	97.78 427	73.97 463	99.13 344	98.81 395	89.62 438	91.80 446	98.93 395	62.23 455	98.80 415	86.61 449	91.17 429	96.19 446

MIMVSNet		97.73 306	97.45 306	98.57 289	99.45 237	97.50 301	99.02 371	98.98 368	96.11 380	99.41 185	99.14 371	90.28 374	98.74 417	95.74 377	98.93 222	99.47 227

LCM-MVSNet-Re		97.83 287	98.15 221	96.87 405	99.30 278	92.25 435	99.59 116	98.26 425	97.43 272	96.20 421	99.13 372	96.27 180	98.73 418	98.17 233	98.99 219	99.64 160

Syy-MVS		97.09 357	97.14 343	96.95 402	99.00 351	92.73 433	99.29 294	99.39 261	97.06 308	97.41 398	98.15 429	93.92 295	98.68 419	91.71 428	98.34 262	99.45 235

myMVS_eth3d		96.89 360	96.37 365	98.43 315	99.00 351	97.16 315	99.29 294	99.39 261	97.06 308	97.41 398	98.15 429	83.46 435	98.68 419	95.27 390	98.34 262	99.45 235

DTE-MVSNet		97.51 332	97.19 341	98.46 308	98.63 405	98.13 265	99.84 12	99.48 183	96.68 333	97.97 384	99.67 219	92.92 317	98.56 421	96.88 346	92.60 424	98.70 326

PC_three_1452									98.18 162	99.84 51	99.70 195	99.31 3	98.52 422	98.30 223	99.80 119	99.81 74

mvsany_test3		93.77 404	93.45 408	94.74 417	95.78 446	88.01 443	99.64 91	98.25 426	98.28 142	94.31 434	97.97 436	68.89 451	98.51 423	97.50 302	90.37 434	97.71 431

UnsupCasMVSNet_bld		93.53 405	92.51 411	96.58 410	97.38 433	93.82 420	98.24 440	99.48 183	91.10 435	93.10 439	96.66 445	74.89 449	98.37 424	94.03 408	87.71 442	97.56 436

Anonymous20240521		96.20 375	95.89 378	97.13 396	97.72 430	94.96 403	99.79 31	99.29 321	93.01 424	97.20 407	99.03 382	89.69 384	98.36 425	91.16 431	96.13 354	98.07 416

test_f		91.90 411	91.26 415	93.84 420	95.52 450	85.92 445	99.69 62	98.53 422	95.31 394	93.87 436	96.37 447	55.33 458	98.27 426	95.70 378	90.98 432	97.32 439

MDA-MVSNet_test_wron		95.45 388	94.60 395	98.01 350	98.16 422	97.21 314	99.11 353	99.24 332	93.49 420	80.73 456	98.98 390	93.02 314	98.18 427	94.22 406	94.45 395	98.64 356

UnsupCasMVSNet_eth		96.44 370	96.12 371	97.40 390	98.65 403	95.65 381	99.36 271	99.51 139	97.13 298	96.04 424	98.99 388	88.40 401	98.17 428	96.71 351	90.27 435	98.40 397

KD-MVS_2432*1600		94.62 397	93.72 405	97.31 391	97.19 439	95.82 378	98.34 435	99.20 339	95.00 401	97.57 395	98.35 422	87.95 406	98.10 429	92.87 422	77.00 454	98.01 420

miper_refine_blended		94.62 397	93.72 405	97.31 391	97.19 439	95.82 378	98.34 435	99.20 339	95.00 401	97.57 395	98.35 422	87.95 406	98.10 429	92.87 422	77.00 454	98.01 420

YYNet1		95.36 390	94.51 398	97.92 359	97.89 425	97.10 318	99.10 355	99.23 333	93.26 423	80.77 455	99.04 381	92.81 320	98.02 431	94.30 402	94.18 400	98.64 356

EU-MVSNet		97.98 261	98.03 237	97.81 371	98.72 396	96.65 354	99.66 78	99.66 28	98.09 178	98.35 362	99.82 101	95.25 227	98.01 432	97.41 311	95.30 379	98.78 305

Gipuma		90.99 413	90.15 418	93.51 421	98.73 394	90.12 441	93.98 454	99.45 226	79.32 452	92.28 442	94.91 449	69.61 450	97.98 433	87.42 445	95.67 369	92.45 452
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 391	94.73 394	97.15 394	95.53 449	95.94 376	99.35 276	99.10 351	95.13 395	93.55 437	97.54 438	88.15 405	97.91 434	94.58 399	89.69 438	97.61 434

PM-MVS		92.96 408	92.23 412	95.14 416	95.61 447	89.98 442	99.37 266	98.21 429	94.80 406	95.04 432	97.69 437	65.06 452	97.90 435	94.30 402	89.98 437	97.54 437

MDA-MVSNet-bldmvs		94.96 395	93.98 402	97.92 359	98.24 421	97.27 309	99.15 341	99.33 298	93.80 416	80.09 457	99.03 382	88.31 402	97.86 436	93.49 414	94.36 397	98.62 365

Patchmatch-RL test		95.84 382	95.81 380	95.95 414	95.61 447	90.57 440	98.24 440	98.39 423	95.10 399	95.20 429	98.67 410	94.78 249	97.77 437	96.28 367	90.02 436	99.51 213

Anonymous20231206		96.22 373	96.03 374	96.79 407	97.31 436	94.14 418	99.63 97	99.08 354	96.17 374	97.04 411	99.06 379	93.94 293	97.76 438	86.96 447	95.06 384	98.47 388

SD-MVS		99.41 56	99.52 12	99.05 217	99.74 94	99.68 58	99.46 221	99.52 120	99.11 41	99.88 38	99.91 24	99.43 1	97.70 439	98.72 165	99.93 31	99.77 95
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		97.25 350	97.35 323	96.95 402	97.84 426	93.61 427	99.57 134	96.63 449	96.13 379	98.87 304	98.61 413	94.59 265	97.70 439	95.08 393	98.86 232	99.55 195

dongtai		93.26 406	92.93 410	94.25 418	99.39 254	85.68 446	97.68 449	93.27 460	92.87 426	96.85 415	99.39 322	82.33 440	97.48 441	76.78 454	97.80 295	99.58 188

pmmvs3		94.09 403	93.25 409	96.60 409	94.76 454	94.49 412	98.92 393	98.18 431	89.66 437	96.48 418	98.06 435	86.28 418	97.33 442	89.68 436	87.20 443	97.97 426

KD-MVS_self_test		95.00 394	94.34 399	96.96 401	97.07 441	95.39 392	99.56 141	99.44 235	95.11 397	97.13 409	97.32 442	91.86 349	97.27 443	90.35 434	81.23 451	98.23 408

FMVSNet5		96.43 371	96.19 370	97.15 394	99.11 329	95.89 377	99.32 284	99.52 120	94.47 412	98.34 363	99.07 377	87.54 411	97.07 444	92.61 425	95.72 368	98.47 388

new-patchmatchnet		94.48 400	94.08 401	95.67 415	95.08 452	92.41 434	99.18 336	99.28 323	94.55 411	93.49 438	97.37 441	87.86 409	97.01 445	91.57 429	88.36 440	97.61 434

LCM-MVSNet		86.80 419	85.22 423	91.53 429	87.81 461	80.96 455	98.23 442	98.99 367	71.05 454	90.13 449	96.51 446	48.45 462	96.88 446	90.51 432	85.30 445	96.76 441

CL-MVSNet_self_test		94.49 399	93.97 403	96.08 413	96.16 444	93.67 425	98.33 437	99.38 269	95.13 395	97.33 402	98.15 429	92.69 328	96.57 447	88.67 439	79.87 452	97.99 424

MIMVSNet1		95.51 387	95.04 392	96.92 404	97.38 433	95.60 382	99.52 170	99.50 159	93.65 418	96.97 413	99.17 367	85.28 426	96.56 448	88.36 441	95.55 374	98.60 377

test20.03		96.12 377	95.96 376	96.63 408	97.44 432	95.45 389	99.51 179	99.38 269	96.55 347	96.16 422	99.25 359	93.76 302	96.17 449	87.35 446	94.22 399	98.27 404

tmp_tt		82.80 421	81.52 424	86.66 437	66.61 467	68.44 466	92.79 456	97.92 433	68.96 455	80.04 458	99.85 72	85.77 420	96.15 450	97.86 262	43.89 460	95.39 450

test_fmvs3		92.10 410	91.77 413	93.08 424	96.19 443	86.25 444	99.82 16	98.62 418	96.65 336	95.19 430	96.90 444	55.05 459	95.93 451	96.63 358	90.92 433	97.06 440

kuosan		90.92 414	90.11 419	93.34 422	98.78 385	85.59 447	98.15 444	93.16 462	89.37 440	92.07 443	98.38 421	81.48 443	95.19 452	62.54 461	97.04 337	99.25 264

dmvs_testset		95.02 393	96.12 371	91.72 428	99.10 332	80.43 456	99.58 126	97.87 435	97.47 264	95.22 428	98.82 402	93.99 291	95.18 453	88.09 442	94.91 389	99.56 194

PMMVS2		86.87 418	85.37 422	91.35 430	90.21 459	83.80 449	98.89 396	97.45 442	83.13 451	91.67 448	95.03 448	48.49 461	94.70 454	85.86 451	77.62 453	95.54 449

PMVS	70.75 22	75.98 427	74.97 428	79.01 443	70.98 466	55.18 468	93.37 455	98.21 429	65.08 460	61.78 461	93.83 451	21.74 468	92.53 455	78.59 453	91.12 431	89.34 456
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 420	85.65 421	82.75 441	86.77 462	63.39 467	98.35 434	98.92 376	74.11 453	83.39 452	98.98 390	50.85 460	92.40 456	84.54 452	94.97 386	92.46 451

WB-MVS		93.10 407	94.10 400	90.12 433	95.51 451	81.88 453	99.73 51	99.27 326	95.05 400	93.09 440	98.91 399	94.70 258	91.89 457	76.62 455	94.02 405	96.58 443

SSC-MVS		92.73 409	93.73 404	89.72 434	95.02 453	81.38 454	99.76 37	99.23 333	94.87 404	92.80 441	98.93 395	94.71 257	91.37 458	74.49 457	93.80 407	96.42 444

MVE	76.82 21	76.91 426	74.31 430	84.70 438	85.38 464	76.05 462	96.88 452	93.17 461	67.39 457	71.28 459	89.01 458	21.66 469	87.69 459	71.74 458	72.29 456	90.35 455
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 423	79.88 425	82.81 440	90.75 458	76.38 461	97.69 448	95.76 453	66.44 458	83.52 451	92.25 453	62.54 454	87.16 460	68.53 459	61.40 457	84.89 458

EMVS		80.02 424	79.22 426	82.43 442	91.19 457	76.40 460	97.55 451	92.49 465	66.36 459	83.01 453	91.27 455	64.63 453	85.79 461	65.82 460	60.65 458	85.08 457

ANet_high		77.30 425	74.86 429	84.62 439	75.88 465	77.61 459	97.63 450	93.15 463	88.81 442	64.27 460	89.29 457	36.51 464	83.93 462	75.89 456	52.31 459	92.33 453

wuyk23d		40.18 428	41.29 433	36.84 444	86.18 463	49.12 469	79.73 457	22.81 469	27.64 461	25.46 464	28.45 464	21.98 467	48.89 463	55.80 462	23.56 463	12.51 461

test123		39.01 430	42.50 432	28.53 445	39.17 468	20.91 470	98.75 410	19.17 470	19.83 463	38.57 462	66.67 460	33.16 465	15.42 464	37.50 464	29.66 462	49.26 459

testmvs		39.17 429	43.78 431	25.37 446	36.04 469	16.84 471	98.36 433	26.56 468	20.06 462	38.51 463	67.32 459	29.64 466	15.30 465	37.59 463	39.90 461	43.98 460

mmdepth		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

monomultidepth		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

test_blank		0.13 434	0.17 437	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	1.57 465	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uanet_test		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

DCPMVS		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

cdsmvs_eth3d_5k		24.64 431	32.85 434	0.00 447	0.00 470	0.00 472	0.00 458	99.51 139	0.00 465	0.00 466	99.56 264	96.58 166	0.00 466	0.00 465	0.00 464	0.00 462

pcd_1.5k_mvsjas		8.27 433	11.03 436	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	99.01 18	0.00 466	0.00 465	0.00 464	0.00 462

sosnet-low-res		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

sosnet		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uncertanet		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

Regformer		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

ab-mvs-re		8.30 432	11.06 435	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	99.58 256	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

uanet		0.02 435	0.03 438	0.00 447	0.00 470	0.00 472	0.00 458	0.00 471	0.00 465	0.00 466	0.27 466	0.00 470	0.00 466	0.00 465	0.00 464	0.00 462

WAC-MVS						97.16 315								95.47 384

FOURS1					99.91 1	99.93 1	99.87 8	99.56 84	99.10 42	99.81 63

test_one_0601					99.81 52	99.88 9		99.49 171	98.97 69	99.65 123	99.81 116	99.09 14

eth-test2					0.00 470

eth-test					0.00 470

RE-MVS-def			99.34 47		99.76 76	99.82 26	99.63 97	99.52 120	98.38 130	99.76 84	99.82 101	98.75 58		98.61 182	99.81 114	99.77 95

IU-MVS					99.84 35	99.88 9		99.32 308	98.30 141	99.84 51				98.86 145	99.85 88	99.89 27

save fliter					99.76 76	99.59 82	99.14 343	99.40 258	99.00 61

test0726					99.85 28	99.89 5	99.62 102	99.50 159	99.10 42	99.86 48	99.82 101	98.94 32

GSMVS																99.52 204

test_part2					99.81 52	99.83 20				99.77 78

sam_mvs1												94.86 244				99.52 204

sam_mvs												94.72 256

MTGPA								99.47 204

MTMP							99.54 160	98.88 386

test9_res														97.49 303	99.72 142	99.75 101

agg_prior2														97.21 321	99.73 141	99.75 101

test_prior4						99.56 88	98.99 379

test_prior2							98.96 386		98.34 136	99.01 278	99.52 280	98.68 67		97.96 254	99.74 139

新几何2							99.01 376

旧先验1					99.74 94	99.59 82		99.54 101			99.69 206	98.47 83			99.68 150	99.73 114

原ACMM2							98.95 389

test222					99.75 86	99.49 103	98.91 395	99.49 171	96.42 358	99.34 208	99.65 226	98.28 97			99.69 147	99.72 123

segment_acmp												98.96 25

testdata1							98.85 400		98.32 139

plane_prior7					99.29 282	97.03 328

plane_prior6					99.27 287	96.98 332						92.71 326

plane_prior4											99.61 247

plane_prior3						97.00 330			98.69 101	99.11 258

plane_prior2							99.39 259		98.97 69

plane_prior1					99.26 290

plane_prior						96.97 333	99.21 329		98.45 123						97.60 304

n2								0.00 471

nn								0.00 471

door-mid								98.05 432

test11								99.35 285

door								97.92 433

HQP5-MVS						96.83 344

HQP-NCC					99.19 308		98.98 382		98.24 151	98.66 333

ACMP_Plane					99.19 308		98.98 382		98.24 151	98.66 333

BP-MVS														97.19 325

HQP3-MVS								99.39 261							97.58 306

HQP2-MVS												92.47 335

NP-MVS					99.23 298	96.92 340					99.40 318

MDTV_nov1_ep13_2view						95.18 398	99.35 276		96.84 325	99.58 146		95.19 230		97.82 267		99.46 232

ACMMP++_ref															97.19 334

ACMMP++															97.43 324

Test By Simon												98.75 58

High-resolution multi-view benchmark