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	99.38 260	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		98.63 202	98.40 210	99.31 181	99.86 22	97.94 283	99.67 71	99.62 47	99.43 15	99.99 2	99.91 24	87.29 416	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	99.47 220	99.63 42	99.45 11	99.98 11	99.89 39	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	98.83 209	99.65 84	99.52 123	99.10 42	99.84 51	99.76 172	95.80 204	99.99 4	99.30 86	99.84 96	99.74 108

SymmetryMVS		99.15 108	99.02 116	99.52 133	99.72 105	98.83 209	99.65 84	99.34 294	99.10 42	99.84 51	99.76 172	95.80 204	99.99 4	99.30 86	98.72 244	99.73 117

fmvsm_s_conf0.5_n_5		99.37 64	99.21 80	99.86 30	99.80 58	99.68 58	99.42 245	99.61 56	99.37 22	99.97 23	99.86 68	94.96 238	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 39	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 95	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	99.82 104	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	99.48 211	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	98.16 343	99.81 52	94.59 415	99.52 170	99.64 38	99.33 24	99.73 91	99.90 31	99.00 22	99.99 4	99.69 33	99.98 4	99.89 27

h-mvs33		97.70 316	97.28 339	98.97 229	99.70 116	97.27 311	99.36 274	99.45 230	98.94 72	99.66 115	99.64 236	94.93 241	99.99 4	99.48 62	84.36 450	99.65 157

xiu_mvs_v1_base_debu		99.29 80	99.27 70	99.34 173	99.63 156	98.97 177	99.12 351	99.51 142	98.86 78	99.84 51	99.47 303	98.18 101	99.99 4	99.50 55	99.31 185	99.08 282

xiu_mvs_v1_base		99.29 80	99.27 70	99.34 173	99.63 156	98.97 177	99.12 351	99.51 142	98.86 78	99.84 51	99.47 303	98.18 101	99.99 4	99.50 55	99.31 185	99.08 282

xiu_mvs_v1_base_debi		99.29 80	99.27 70	99.34 173	99.63 156	98.97 177	99.12 351	99.51 142	98.86 78	99.84 51	99.47 303	98.18 101	99.99 4	99.50 55	99.31 185	99.08 282

EPNet		98.86 167	98.71 174	99.30 186	97.20 442	98.18 263	99.62 102	98.91 385	99.28 27	98.63 346	99.81 119	95.96 192	99.99 4	99.24 95	99.72 142	99.73 117
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	96.60 165	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	98.87 392	99.55 1	99.74 89	99.80 136	96.47 172	99.98 18	99.97 2	99.97 8	99.94 16

test_cas_vis1_n_1920		99.16 104	99.01 121	99.61 103	99.81 52	98.86 203	99.65 84	99.64 38	99.39 20	99.97 23	99.94 6	93.20 317	99.98 18	99.55 48	99.91 44	99.99 1

test_vis1_n		97.92 274	97.44 315	99.34 173	99.53 202	98.08 270	99.74 47	99.49 174	99.15 32	100.00 1	99.94 6	79.51 451	99.98 18	99.88 24	99.76 134	99.97 4

xiu_mvs_v2_base		99.26 87	99.25 74	99.29 189	99.53 202	98.91 194	99.02 375	99.45 230	98.80 88	99.71 98	99.26 362	98.94 32	99.98 18	99.34 79	99.23 194	98.98 296

PS-MVSNAJ		99.32 75	99.32 51	99.30 186	99.57 186	98.94 189	98.97 389	99.46 219	98.92 75	99.71 98	99.24 364	99.01 18	99.98 18	99.35 74	99.66 153	98.97 297

QAPM		98.67 197	98.30 217	99.80 59	99.20 309	99.67 62	99.77 34	99.72 11	94.74 411	98.73 326	99.90 31	95.78 206	99.98 18	96.96 343	99.88 70	99.76 102

3Dnovator	97.25 9	99.24 92	99.05 105	99.81 55	99.12 331	99.66 65	99.84 12	99.74 10	99.09 49	98.92 299	99.90 31	95.94 195	99.98 18	98.95 131	99.92 37	99.79 87

OpenMVS	96.50 16	98.47 208	98.12 229	99.52 133	99.04 350	99.53 95	99.82 16	99.72 11	94.56 414	98.08 381	99.88 50	94.73 257	99.98 18	97.47 310	99.76 134	99.06 288

fmvsm_s_conf0.5_n_3		99.37 64	99.20 82	99.87 19	99.75 86	99.70 55	99.48 211	99.66 28	99.45 11	99.99 2	99.93 10	94.64 266	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 94	99.15 32	99.90 32	99.90 31	99.00 22	99.97 27	99.11 110	99.91 44	99.86 40

test_fmvsmconf0.1_n		99.55 20	99.45 27	99.86 30	99.44 242	99.65 69	99.50 189	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		98.41 214	98.14 226	99.21 202	99.82 48	97.71 296	99.74 47	99.49 174	99.32 25	99.99 2	99.95 3	85.32 429	99.97 27	99.82 27	99.84 96	99.96 7

CANet_DTU		98.97 155	98.87 152	99.25 196	99.33 273	98.42 255	99.08 360	99.30 321	99.16 31	99.43 181	99.75 177	95.27 226	99.97 27	98.56 198	99.95 21	99.36 254

MVS_0304		99.15 108	98.96 131	99.73 77	98.92 368	99.37 117	99.37 269	96.92 448	99.51 2	99.66 115	99.78 159	96.69 162	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	99.47 208	98.79 89	99.68 104	99.81 119	98.43 86	99.97 27	98.88 141	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	97.84 224	99.71 98	99.80 136	99.12 13	99.97 27	98.33 223	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	99.48 186	98.12 177	99.50 165	99.75 177	98.78 51	99.97 27	98.57 195	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	99.52 123	98.07 187	99.53 160	99.63 242	98.93 36	99.97 27	98.74 166	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	99.51 142	98.62 106	99.79 70	99.83 95	99.28 4	99.97 27	98.48 205	99.90 55	99.84 51
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 99	98.97 127	99.82 52	99.17 323	99.68 58	99.81 20	99.51 142	99.20 29	98.72 327	99.89 39	95.68 210	99.97 27	98.86 149	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	99.48 211	99.62 47	99.46 7	99.99 2	99.92 17	95.24 230	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 75	98.41 90	99.96 39	99.28 89	99.84 96	99.83 61

KinetiMVS		99.12 121	98.92 139	99.70 81	99.67 128	99.40 115	99.67 71	99.63 42	98.73 96	99.94 26	99.81 119	94.54 272	99.96 39	98.40 214	99.93 31	99.74 108

fmvsm_s_conf0.5_n_7		99.34 71	99.29 63	99.48 146	99.70 116	98.63 228	99.42 245	99.63 42	99.46 7	99.98 11	99.88 50	95.59 213	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	99.44 233	99.58 74	99.47 4	99.99 2	99.93 10	94.04 293	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	99.54 103	99.13 35	99.89 35	99.89 39	98.96 25	99.96 39	99.04 118	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	99.54 103	99.13 35	99.89 35	99.89 39	98.96 25	99.96 39	99.04 118	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	96.60 165	99.96 39	99.95 14	99.96 15	99.95 11

mvsany_test1		99.50 28	99.46 26	99.62 102	99.61 171	99.09 159	98.94 395	99.48 186	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		98.88 161	98.79 165	99.16 207	99.69 121	97.61 300	99.55 155	99.49 174	99.32 25	99.98 11	99.91 24	91.41 365	99.96 39	99.82 27	99.92 37	99.90 24

DVP-MVS++		99.59 13	99.50 17	99.88 13	99.51 211	99.88 9	99.87 8	99.51 142	98.99 63	99.88 38	99.81 119	99.27 5	99.96 39	98.85 151	99.80 119	99.81 74

MSC_two_6792asdad				99.87 19	99.51 211	99.76 44		99.33 302					99.96 39	98.87 144	99.84 96	99.89 27

No_MVS				99.87 19	99.51 211	99.76 44		99.33 302					99.96 39	98.87 144	99.84 96	99.89 27

ZD-MVS					99.71 111	99.79 36		99.61 56	96.84 329	99.56 151	99.54 276	98.58 75	99.96 39	96.93 346	99.75 136

SED-MVS		99.61 8	99.52 12	99.88 13	99.84 35	99.90 2	99.60 109	99.48 186	99.08 50	99.91 29	99.81 119	99.20 7	99.96 39	98.91 138	99.85 88	99.79 87

test_241102_TWO								99.48 186	99.08 50	99.88 38	99.81 119	98.94 32	99.96 39	98.91 138	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	98.08 186	99.55 157	99.64 236	98.91 37	99.96 39	98.72 169	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	99.37 281	99.10 42	99.81 63	99.80 136	98.94 32	99.96 39	98.93 135	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	99.80 136	99.09 14	99.96 39	98.85 151	99.90 55	99.88 33

test_0728_SECOND				99.91 4	99.84 35	99.89 5	99.57 134	99.51 142					99.96 39	98.93 135	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	98.21 161	99.73 91	99.79 152	98.68 67	99.96 39	98.44 211	99.77 131	99.79 87

DPE-MVS		99.46 39	99.32 51	99.91 4	99.78 64	99.88 9	99.36 274	99.51 142	98.73 96	99.88 38	99.84 90	98.72 64	99.96 39	98.16 238	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	99.62 162	99.55 90	99.50 189	99.70 15	98.79 89	99.77 79	99.96 1	97.45 121	99.96 39	98.92 137	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	98.15 168	99.68 104	99.69 210	99.06 16	99.96 39	98.69 174	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	98.13 175	99.66 115	99.68 217	98.96 25	99.96 39	98.62 183	99.87 73	99.84 51

HPM-MVS++		99.39 62	99.23 78	99.87 19	99.75 86	99.84 19	99.43 238	99.51 142	98.68 103	99.27 228	99.53 280	98.64 72	99.96 39	98.44 211	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 86	99.02 56	99.88 38	99.85 75	99.18 10	99.96 39	99.22 96	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	98.15 168	99.67 110	99.69 210	98.95 30	99.96 39	98.69 174	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	99.46 219	98.09 182	99.48 169	99.74 182	98.29 96	99.96 39	97.93 260	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		99.11 127	98.90 144	99.74 74	99.80 58	99.46 108	99.59 116	99.49 174	97.03 316	99.63 132	99.69 210	97.27 130	99.96 39	97.82 271	99.84 96	99.81 74

PVSNet_Blended_VisFu		99.36 68	99.28 66	99.61 103	99.86 22	99.07 164	99.47 220	99.93 2	97.66 247	99.71 98	99.86 68	97.73 116	99.96 39	99.47 64	99.82 111	99.79 87

UGNet		98.87 164	98.69 176	99.40 164	99.22 306	98.72 220	99.44 233	99.68 20	99.24 28	99.18 253	99.42 314	92.74 327	99.96 39	99.34 79	99.94 29	99.53 207
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	99.32 179	99.85 28	98.29 258	99.71 57	99.66 28	98.11 179	99.41 189	99.80 136	98.37 93	99.96 39	98.99 124	99.96 15	99.72 126

ACMMP		99.45 43	99.32 51	99.82 52	99.89 8	99.67 62	99.62 102	99.69 18	98.12 177	99.63 132	99.84 90	98.73 63	99.96 39	98.55 201	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	99.51 211	99.67 62	99.50 189	99.64 38	99.43 15	99.98 11	99.78 159	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	99.49 205	99.60 63	99.42 18	99.99 2	99.86 68	95.15 233	99.95 74	99.95 14	99.89 66	99.73 117

fmvsm_s_conf0.1_n_2		99.37 64	99.22 79	99.81 55	99.77 72	99.75 46	99.46 224	99.60 63	99.47 4	99.98 11	99.94 6	94.98 237	99.95 74	99.97 2	99.79 126	99.73 117

test_fmvsmconf0.01_n		99.22 95	99.03 110	99.79 62	98.42 422	99.48 105	99.55 155	99.51 142	99.39 20	99.78 75	99.93 10	94.80 249	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	99.52 123	98.38 131	99.76 85	99.82 104	98.53 79	99.95 74	98.61 186	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	97.97 208	99.63 132	99.68 217	98.52 80	99.95 74	98.38 216	99.86 81	99.81 74

CANet		99.25 91	99.14 89	99.59 107	99.41 250	99.16 149	99.35 279	99.57 81	98.82 83	99.51 164	99.61 251	96.46 173	99.95 74	99.59 43	99.98 4	99.65 157

MP-MVS-pluss		99.37 64	99.20 82	99.88 13	99.90 4	99.87 16	99.30 293	99.52 123	97.18 298	99.60 143	99.79 152	98.79 50	99.95 74	98.83 157	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	99.50 162	98.70 100	99.77 79	99.49 294	98.21 99	99.95 74	98.46 209	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	96.67 358

APD-MVS_3200maxsize		99.48 34	99.35 45	99.85 38	99.76 76	99.83 20	99.63 97	99.54 103	98.36 135	99.79 70	99.82 104	98.86 41	99.95 74	98.62 183	99.81 114	99.78 93

RPMNet		96.72 368	95.90 381	99.19 204	99.18 315	98.49 247	99.22 331	99.52 123	88.72 447	99.56 151	97.38 444	94.08 292	99.95 74	86.87 452	98.58 251	99.14 274

sss		99.17 102	99.05 105	99.53 127	99.62 162	98.97 177	99.36 274	99.62 47	97.83 225	99.67 110	99.65 230	97.37 125	99.95 74	99.19 99	99.19 197	99.68 145

MVSMamba_PlusPlus		99.46 39	99.41 34	99.64 95	99.68 126	99.50 102	99.75 42	99.50 162	98.27 145	99.87 44	99.92 17	98.09 105	99.94 87	99.65 39	99.95 21	99.47 231

fmvsm_s_conf0.1_n_a		99.26 87	99.06 103	99.85 38	99.52 208	99.62 77	99.54 160	99.62 47	98.69 101	99.99 2	99.96 1	94.47 276	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	94.53 274	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	99.39 265	98.91 76	99.78 75	99.85 75	99.36 2	99.94 87	98.84 154	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		98.91 159	98.75 168	99.39 168	99.46 235	98.61 232	99.76 37	99.50 162	98.06 191	99.81 63	99.88 50	93.91 300	99.94 87	99.11 110	99.27 188	99.61 174

mamv4		99.33 73	99.42 29	99.07 215	99.67 128	97.73 291	99.42 245	99.60 63	98.15 168	99.94 26	99.91 24	98.42 88	99.94 87	99.72 30	99.96 15	99.54 201

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	99.37 200	99.74 182	98.81 47	99.94 87	98.79 162	99.86 81	99.84 51

X-MVStestdata		96.55 371	95.45 390	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 200	64.01 467	98.81 47	99.94 87	98.79 162	99.86 81	99.84 51

旧先验2							98.96 390		96.70 336	99.47 170			99.94 87	98.19 234

新几何1				99.75 71	99.75 86	99.59 82		99.54 103	96.76 332	99.29 222	99.64 236	98.43 86	99.94 87	96.92 348	99.66 153	99.72 126

testdata				99.54 119	99.75 86	98.95 186		99.51 142	97.07 310	99.43 181	99.70 199	98.87 40	99.94 87	97.76 280	99.64 156	99.72 126

HPM-MVS		99.42 52	99.28 66	99.83 51	99.90 4	99.72 51	99.81 20	99.54 103	97.59 253	99.68 104	99.63 242	98.91 37	99.94 87	98.58 192	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	99.45 154	99.89 8	98.52 242	99.39 262	99.94 1	98.73 96	99.11 262	99.89 39	95.50 216	99.94 87	99.50 55	99.97 8	99.89 27

APD-MVS		99.27 84	99.08 100	99.84 50	99.75 86	99.79 36	99.50 189	99.50 162	97.16 300	99.77 79	99.82 104	98.78 51	99.94 87	97.56 301	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	99.05 367	99.66 28	99.14 34	99.57 150	99.80 136	98.46 84	99.94 87	99.57 46	99.84 96	99.60 177
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		99.06 139	98.88 151	99.61 103	99.62 162	99.16 149	99.37 269	99.56 86	98.04 200	99.53 160	99.62 247	96.84 154	99.94 87	98.85 151	98.49 259	99.72 126

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 94	98.94 72	99.63 132	99.95 3	95.82 202	99.94 87	99.37 73	99.97 8	99.73 117
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	99.18 315	99.75 46	99.56 141	99.57 81	98.45 124	99.49 168	99.85 75	97.77 115	99.94 87	98.33 223	99.84 96	99.52 208

GDP-MVS		99.08 134	98.89 148	99.64 95	99.53 202	99.34 121	99.64 91	99.48 186	98.32 140	99.77 79	99.66 228	95.14 234	99.93 105	98.97 130	99.50 170	99.64 164

SDMVSNet		99.11 127	98.90 144	99.75 71	99.81 52	99.59 82	99.81 20	99.65 35	98.78 92	99.64 129	99.88 50	94.56 269	99.93 105	99.67 35	98.26 274	99.72 126

FE-MVS		98.48 207	98.17 222	99.40 164	99.54 201	98.96 181	99.68 68	98.81 399	95.54 395	99.62 136	99.70 199	93.82 303	99.93 105	97.35 319	99.46 172	99.32 260

SF-MVS		99.38 63	99.24 75	99.79 62	99.79 62	99.68 58	99.57 134	99.54 103	97.82 229	99.71 98	99.80 136	98.95 30	99.93 105	98.19 234	99.84 96	99.74 108

dcpmvs_2		99.23 93	99.58 7	98.16 343	99.83 44	94.68 412	99.76 37	99.52 123	99.07 52	99.98 11	99.88 50	98.56 77	99.93 105	99.67 35	99.98 4	99.87 38

Anonymous20240529		98.09 244	97.68 282	99.34 173	99.66 141	98.44 252	99.40 258	99.43 250	93.67 421	99.22 240	99.89 39	90.23 382	99.93 105	99.26 94	98.33 266	99.66 152

ACMMP_NAP		99.47 37	99.34 47	99.88 13	99.87 17	99.86 17	99.47 220	99.48 186	98.05 193	99.76 85	99.86 68	98.82 46	99.93 105	98.82 161	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	99.45 230	99.01 58	99.90 32	99.83 95	98.98 24	99.93 105	99.59 43	99.95 21	99.86 40

无先验							98.99 383	99.51 142	96.89 326				99.93 105	97.53 304		99.72 126

VDDNet		97.55 331	97.02 353	99.16 207	99.49 225	98.12 269	99.38 267	99.30 321	95.35 397	99.68 104	99.90 31	82.62 442	99.93 105	99.31 83	98.13 286	99.42 243

ab-mvs		98.86 167	98.63 186	99.54 119	99.64 152	99.19 144	99.44 233	99.54 103	97.77 233	99.30 219	99.81 119	94.20 286	99.93 105	99.17 105	98.82 238	99.49 222

F-COLMAP		99.19 96	99.04 107	99.64 95	99.78 64	99.27 137	99.42 245	99.54 103	97.29 289	99.41 189	99.59 256	98.42 88	99.93 105	98.19 234	99.69 147	99.73 117

BP-MVS1		99.12 121	98.94 137	99.65 89	99.51 211	99.30 132	99.67 71	98.92 380	98.48 120	99.84 51	99.69 210	94.96 238	99.92 117	99.62 42	99.79 126	99.71 135

Anonymous202405211		98.30 225	97.98 246	99.26 195	99.57 186	98.16 264	99.41 250	98.55 424	96.03 389	99.19 249	99.74 182	91.87 352	99.92 117	99.16 106	98.29 273	99.70 138

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 95	99.78 64	99.15 153	99.61 108	99.45 230	99.01 58	99.89 35	99.82 104	99.01 18	99.92 117	99.56 47	99.95 21	99.85 44

VDD-MVS		97.73 310	97.35 327	98.88 251	99.47 233	97.12 319	99.34 282	98.85 394	98.19 163	99.67 110	99.85 75	82.98 440	99.92 117	99.49 59	98.32 270	99.60 177

VNet		99.11 127	98.90 144	99.73 77	99.52 208	99.56 88	99.41 250	99.39 265	99.01 58	99.74 89	99.78 159	95.56 214	99.92 117	99.52 53	98.18 282	99.72 126

XVG-OURS-SEG-HR		98.69 195	98.62 191	98.89 248	99.71 111	97.74 290	99.12 351	99.54 103	98.44 127	99.42 184	99.71 195	94.20 286	99.92 117	98.54 202	98.90 232	99.00 293

mvsmamba		99.06 139	98.96 131	99.36 170	99.47 233	98.64 227	99.70 58	99.05 364	97.61 252	99.65 124	99.83 95	96.54 169	99.92 117	99.19 99	99.62 159	99.51 217

HPM-MVS_fast		99.51 26	99.40 35	99.85 38	99.91 1	99.79 36	99.76 37	99.56 86	97.72 238	99.76 85	99.75 177	99.13 12	99.92 117	99.07 116	99.92 37	99.85 44

HY-MVS	97.30 7	98.85 176	98.64 185	99.47 151	99.42 245	99.08 162	99.62 102	99.36 282	97.39 281	99.28 223	99.68 217	96.44 175	99.92 117	98.37 218	98.22 277	99.40 248

DP-MVS		99.16 104	98.95 135	99.78 65	99.77 72	99.53 95	99.41 250	99.50 162	97.03 316	99.04 279	99.88 50	97.39 122	99.92 117	98.66 178	99.90 55	99.87 38

IB-MVS	95.67 18	96.22 377	95.44 391	98.57 293	99.21 307	96.70 353	98.65 424	97.74 442	96.71 335	97.27 407	98.54 419	86.03 423	99.92 117	98.47 208	86.30 448	99.10 277
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	99.63 156	99.59 82	99.36 274	99.46 219	99.07 52	99.79 70	99.82 104	98.85 42	99.92 117	98.68 176	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	99.35 267	99.31 129	99.46 224	99.13 352	98.61 107	99.86 48	99.89 39	96.41 177	99.91 129	99.67 35	99.51 168	99.63 169

balanced_conf03		99.46 39	99.39 37	99.67 84	99.55 194	99.58 87	99.74 47	99.51 142	98.42 128	99.87 44	99.84 90	98.05 108	99.91 129	99.58 45	99.94 29	99.52 208

9.14			99.10 94		99.72 105		99.40 258	99.51 142	97.53 263	99.64 129	99.78 159	98.84 44	99.91 129	97.63 292	99.82 111

SMA-MVS		99.44 47	99.30 59	99.85 38	99.73 101	99.83 20	99.56 141	99.47 208	97.45 272	99.78 75	99.82 104	99.18 10	99.91 129	98.79 162	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	99.05 367	99.41 255	96.22 374	98.95 295	99.49 294	98.77 54	99.91 129

train_agg		99.02 146	98.77 166	99.77 68	99.67 128	99.65 69	99.05 367	99.41 255	96.28 368	98.95 295	99.49 294	98.76 55	99.91 129	97.63 292	99.72 142	99.75 104

test_8					99.67 128	99.61 79	99.03 372	99.41 255	96.28 368	98.93 298	99.48 300	98.76 55	99.91 129

agg_prior					99.67 128	99.62 77		99.40 262		98.87 308			99.91 129

原ACMM1				99.65 89	99.73 101	99.33 124		99.47 208	97.46 269	99.12 260	99.66 228	98.67 69	99.91 129	97.70 289	99.69 147	99.71 135

LFMVS		97.90 277	97.35 327	99.54 119	99.52 208	99.01 171	99.39 262	98.24 431	97.10 308	99.65 124	99.79 152	84.79 432	99.91 129	99.28 89	98.38 263	99.69 141

XVG-OURS		98.73 193	98.68 177	98.88 251	99.70 116	97.73 291	98.92 397	99.55 94	98.52 116	99.45 173	99.84 90	95.27 226	99.91 129	98.08 249	98.84 236	99.00 293

PLC	97.94 4	99.02 146	98.85 157	99.53 127	99.66 141	99.01 171	99.24 324	99.52 123	96.85 328	99.27 228	99.48 300	98.25 98	99.91 129	97.76 280	99.62 159	99.65 157
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 324	97.06 352	99.47 151	99.61 171	99.09 159	98.04 450	99.25 333	91.24 438	98.51 357	99.70 199	94.55 271	99.91 129	92.76 428	99.85 88	99.42 243
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 161	98.65 183	99.58 110	99.58 181	99.34 121	99.65 84	99.52 123	98.26 148	99.83 59	99.87 61	93.37 311	99.90 142	97.81 273	99.91 44	99.49 222

StellarMVS		98.88 161	98.65 183	99.58 110	99.58 181	99.34 121	99.65 84	99.52 123	98.26 148	99.83 59	99.87 61	93.37 311	99.90 142	97.81 273	99.91 44	99.49 222

AstraMVS		99.09 132	99.03 110	99.25 196	99.66 141	98.13 267	99.57 134	98.24 431	98.82 83	99.91 29	99.88 50	95.81 203	99.90 142	99.72 30	99.67 152	99.74 108

mmtdpeth		96.95 363	96.71 362	97.67 382	99.33 273	94.90 408	99.89 2	99.28 327	98.15 168	99.72 96	98.57 418	86.56 421	99.90 142	99.82 27	89.02 443	98.20 413

UWE-MVS		97.58 330	97.29 338	98.48 306	99.09 339	96.25 373	99.01 380	96.61 454	97.86 218	99.19 249	99.01 389	88.72 397	99.90 142	97.38 317	98.69 245	99.28 263

test_vis1_rt		95.81 387	95.65 386	96.32 416	99.67 128	91.35 443	99.49 205	96.74 452	98.25 153	95.24 431	98.10 437	74.96 452	99.90 142	99.53 51	98.85 235	97.70 437

FA-MVS(test-final)		98.75 190	98.53 202	99.41 163	99.55 194	99.05 167	99.80 25	99.01 369	96.59 350	99.58 147	99.59 256	95.39 220	99.90 142	97.78 276	99.49 171	99.28 263

MCST-MVS		99.43 50	99.30 59	99.82 52	99.79 62	99.74 49	99.29 298	99.40 262	98.79 89	99.52 162	99.62 247	98.91 37	99.90 142	98.64 180	99.75 136	99.82 67

CDPH-MVS		99.13 114	98.91 142	99.80 59	99.75 86	99.71 53	99.15 345	99.41 255	96.60 348	99.60 143	99.55 271	98.83 45	99.90 142	97.48 308	99.83 107	99.78 93

NCCC		99.34 71	99.19 84	99.79 62	99.61 171	99.65 69	99.30 293	99.48 186	98.86 78	99.21 243	99.63 242	98.72 64	99.90 142	98.25 230	99.63 158	99.80 83

114514_t		98.93 157	98.67 178	99.72 80	99.85 28	99.53 95	99.62 102	99.59 69	92.65 433	99.71 98	99.78 159	98.06 107	99.90 142	98.84 154	99.91 44	99.74 108

1112_ss		98.98 153	98.77 166	99.59 107	99.68 126	99.02 169	99.25 319	99.48 186	97.23 295	99.13 258	99.58 260	96.93 148	99.90 142	98.87 144	98.78 241	99.84 51

PHI-MVS		99.30 78	99.17 87	99.70 81	99.56 190	99.52 99	99.58 126	99.80 8	97.12 304	99.62 136	99.73 188	98.58 75	99.90 142	98.61 186	99.91 44	99.68 145

AdaColmap		99.01 150	98.80 162	99.66 85	99.56 190	99.54 92	99.18 340	99.70 15	98.18 166	99.35 209	99.63 242	96.32 179	99.90 142	97.48 308	99.77 131	99.55 199

COLMAP_ROB	97.56 6	98.86 167	98.75 168	99.17 206	99.88 13	98.53 238	99.34 282	99.59 69	97.55 259	98.70 334	99.89 39	95.83 201	99.90 142	98.10 244	99.90 55	99.08 282
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 221	98.03 241	99.31 181	99.63 156	98.56 235	99.54 160	96.75 451	97.53 263	99.73 91	99.65 230	91.25 370	99.89 157	98.62 183	99.56 164	99.48 225

tttt0517		98.42 212	98.14 226	99.28 193	99.66 141	98.38 256	99.74 47	96.85 449	97.68 244	99.79 70	99.74 182	91.39 366	99.89 157	98.83 157	99.56 164	99.57 195

test12				99.75 71	99.64 152	99.61 79		99.29 325		99.21 243		98.38 92	99.89 157		99.74 139	99.74 108

Test_1112_low_res		98.89 160	98.66 181	99.57 114	99.69 121	98.95 186	99.03 372	99.47 208	96.98 318	99.15 256	99.23 365	96.77 159	99.89 157	98.83 157	98.78 241	99.86 40

CNLPA		99.14 112	98.99 123	99.59 107	99.58 181	99.41 114	99.16 342	99.44 239	98.45 124	99.19 249	99.49 294	98.08 106	99.89 157	97.73 284	99.75 136	99.48 225

diffmvs_AUTHOR		99.19 96	99.10 94	99.48 146	99.64 152	98.85 204	99.32 287	99.48 186	98.50 118	99.81 63	99.81 119	96.82 155	99.88 162	99.40 69	99.12 205	99.71 135

guyue		99.16 104	99.04 107	99.52 133	99.69 121	98.92 193	99.59 116	98.81 399	98.73 96	99.90 32	99.87 61	95.34 223	99.88 162	99.66 38	99.81 114	99.74 108

sd_testset		98.75 190	98.57 198	99.29 189	99.81 52	98.26 260	99.56 141	99.62 47	98.78 92	99.64 129	99.88 50	92.02 349	99.88 162	99.54 49	98.26 274	99.72 126

APD_test1		95.87 385	96.49 367	94.00 423	99.53 202	84.01 452	99.54 160	99.32 312	95.91 391	97.99 386	99.85 75	85.49 427	99.88 162	91.96 431	98.84 236	98.12 417

diffmvs		99.14 112	99.02 116	99.51 138	99.61 171	98.96 181	99.28 303	99.49 174	98.46 122	99.72 96	99.71 195	96.50 171	99.88 162	99.31 83	99.11 206	99.67 148
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		98.86 167	98.80 162	99.03 221	99.76 76	98.79 215	99.28 303	99.91 3	97.42 278	99.67 110	99.37 332	97.53 119	99.88 162	98.98 125	97.29 334	98.42 398

PVSNet_Blended		99.08 134	98.97 127	99.42 162	99.76 76	98.79 215	98.78 411	99.91 3	96.74 333	99.67 110	99.49 294	97.53 119	99.88 162	98.98 125	99.85 88	99.60 177

viewdifsd2359ckpt11		98.78 185	98.74 170	98.89 248	99.67 128	97.04 329	99.50 189	99.58 74	98.26 148	99.56 151	99.90 31	94.36 279	99.87 169	99.49 59	98.32 270	99.77 95

viewmsd2359difaftdt		98.78 185	98.74 170	98.90 244	99.67 128	97.04 329	99.50 189	99.58 74	98.26 148	99.56 151	99.90 31	94.36 279	99.87 169	99.49 59	98.32 270	99.77 95

MVS		97.28 352	96.55 365	99.48 146	98.78 389	98.95 186	99.27 308	99.39 265	83.53 454	98.08 381	99.54 276	96.97 146	99.87 169	94.23 409	99.16 198	99.63 169

MG-MVS		99.13 114	99.02 116	99.45 154	99.57 186	98.63 228	99.07 361	99.34 294	98.99 63	99.61 140	99.82 104	97.98 110	99.87 169	97.00 339	99.80 119	99.85 44

MSDG		98.98 153	98.80 162	99.53 127	99.76 76	99.19 144	98.75 414	99.55 94	97.25 292	99.47 170	99.77 168	97.82 113	99.87 169	96.93 346	99.90 55	99.54 201

ETV-MVS		99.26 87	99.21 80	99.40 164	99.46 235	99.30 132	99.56 141	99.52 123	98.52 116	99.44 178	99.27 360	98.41 90	99.86 174	99.10 113	99.59 162	99.04 289

thisisatest0515		98.14 239	97.79 265	99.19 204	99.50 223	98.50 246	98.61 426	96.82 450	96.95 322	99.54 158	99.43 312	91.66 361	99.86 174	98.08 249	99.51 168	99.22 271

thres600view7		97.86 283	97.51 301	98.92 238	99.72 105	97.95 281	99.59 116	98.74 409	97.94 210	99.27 228	98.62 415	91.75 355	99.86 174	93.73 415	98.19 281	98.96 299

lupinMVS		99.13 114	99.01 121	99.46 153	99.51 211	98.94 189	99.05 367	99.16 348	97.86 218	99.80 68	99.56 268	97.39 122	99.86 174	98.94 132	99.85 88	99.58 192

PVSNet	96.02 17	98.85 176	98.84 159	98.89 248	99.73 101	97.28 310	98.32 442	99.60 63	97.86 218	99.50 165	99.57 265	96.75 160	99.86 174	98.56 198	99.70 146	99.54 201

MAR-MVS		98.86 167	98.63 186	99.54 119	99.37 263	99.66 65	99.45 227	99.54 103	96.61 345	99.01 282	99.40 322	97.09 138	99.86 174	97.68 291	99.53 167	99.10 277
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		99.08 134	98.96 131	99.44 158	99.62 162	98.88 196	99.25 319	99.47 208	98.05 193	99.37 200	99.81 119	96.85 150	99.85 180	98.98 125	99.25 191	99.60 177

SSM_0404		99.16 104	99.06 103	99.44 158	99.65 149	98.96 181	99.49 205	99.50 162	98.14 173	99.62 136	99.85 75	96.85 150	99.85 180	99.19 99	99.26 190	99.52 208

testing91		97.44 344	97.02 353	98.71 280	99.18 315	96.89 347	99.19 338	99.04 365	97.78 232	98.31 368	98.29 429	85.41 428	99.85 180	98.01 255	97.95 291	99.39 249

test2506		96.81 367	96.65 363	97.29 397	99.74 94	92.21 440	99.60 109	85.06 471	99.13 35	99.77 79	99.93 10	87.82 414	99.85 180	99.38 72	99.38 177	99.80 83

AllTest		98.87 164	98.72 172	99.31 181	99.86 22	98.48 249	99.56 141	99.61 56	97.85 221	99.36 206	99.85 75	95.95 193	99.85 180	96.66 359	99.83 107	99.59 188

TestCases				99.31 181	99.86 22	98.48 249		99.61 56	97.85 221	99.36 206	99.85 75	95.95 193	99.85 180	96.66 359	99.83 107	99.59 188

jason		99.13 114	99.03 110	99.45 154	99.46 235	98.87 200	99.12 351	99.26 331	98.03 202	99.79 70	99.65 230	97.02 143	99.85 180	99.02 122	99.90 55	99.65 157
jason: jason.
CNVR-MVS		99.42 52	99.30 59	99.78 65	99.62 162	99.71 53	99.26 317	99.52 123	98.82 83	99.39 196	99.71 195	98.96 25	99.85 180	98.59 191	99.80 119	99.77 95

PAPM_NR		99.04 143	98.84 159	99.66 85	99.74 94	99.44 110	99.39 262	99.38 273	97.70 242	99.28 223	99.28 357	98.34 94	99.85 180	96.96 343	99.45 173	99.69 141

testing99		97.36 347	96.94 356	98.63 286	99.18 315	96.70 353	99.30 293	98.93 377	97.71 239	98.23 373	98.26 430	84.92 431	99.84 189	98.04 254	97.85 298	99.35 255

testing222		97.16 357	96.50 366	99.16 207	99.16 325	98.47 251	99.27 308	98.66 420	97.71 239	98.23 373	98.15 433	82.28 445	99.84 189	97.36 318	97.66 304	99.18 273

test1111		98.04 254	98.11 230	97.83 372	99.74 94	93.82 424	99.58 126	95.40 458	99.12 40	99.65 124	99.93 10	90.73 375	99.84 189	99.43 67	99.38 177	99.82 67

ECVR-MVS		98.04 254	98.05 239	98.00 356	99.74 94	94.37 419	99.59 116	94.98 459	99.13 35	99.66 115	99.93 10	90.67 376	99.84 189	99.40 69	99.38 177	99.80 83

test_yl		98.86 167	98.63 186	99.54 119	99.49 225	99.18 146	99.50 189	99.07 361	98.22 159	99.61 140	99.51 288	95.37 221	99.84 189	98.60 189	98.33 266	99.59 188

DCV-MVSNet		98.86 167	98.63 186	99.54 119	99.49 225	99.18 146	99.50 189	99.07 361	98.22 159	99.61 140	99.51 288	95.37 221	99.84 189	98.60 189	98.33 266	99.59 188

Fast-Effi-MVS+		98.70 194	98.43 207	99.51 138	99.51 211	99.28 135	99.52 170	99.47 208	96.11 384	99.01 282	99.34 342	96.20 183	99.84 189	97.88 263	98.82 238	99.39 249

TSAR-MVS + GP.		99.36 68	99.36 43	99.36 170	99.67 128	98.61 232	99.07 361	99.33 302	99.00 61	99.82 62	99.81 119	99.06 16	99.84 189	99.09 114	99.42 175	99.65 157

tpmrst		98.33 222	98.48 205	97.90 365	99.16 325	94.78 409	99.31 291	99.11 354	97.27 290	99.45 173	99.59 256	95.33 224	99.84 189	98.48 205	98.61 248	99.09 281

Vis-MVSNet		99.12 121	98.97 127	99.56 116	99.78 64	99.10 158	99.68 68	99.66 28	98.49 119	99.86 48	99.87 61	94.77 254	99.84 189	99.19 99	99.41 176	99.74 108
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 202	98.34 213	99.51 138	99.40 255	99.03 168	98.80 409	99.36 282	96.33 365	99.00 286	99.12 379	98.46 84	99.84 189	95.23 395	99.37 184	99.66 152

PatchMatch-RL		98.84 179	98.62 191	99.52 133	99.71 111	99.28 135	99.06 365	99.77 9	97.74 237	99.50 165	99.53 280	95.41 219	99.84 189	97.17 332	99.64 156	99.44 241

EPP-MVSNet		99.13 114	98.99 123	99.53 127	99.65 149	99.06 165	99.81 20	99.33 302	97.43 276	99.60 143	99.88 50	97.14 134	99.84 189	99.13 108	98.94 223	99.69 141

SSM_0407		99.13 114	99.03 110	99.43 161	99.62 162	98.88 196	99.51 179	99.50 162	98.14 173	99.37 200	99.85 75	96.85 150	99.83 202	99.19 99	99.25 191	99.60 177

testing3-2		97.84 288	97.70 280	98.24 338	99.53 202	95.37 397	99.55 155	98.67 419	98.46 122	99.27 228	99.34 342	86.58 420	99.83 202	99.32 82	98.63 247	99.52 208

testing11		97.50 337	97.10 350	98.71 280	99.20 309	96.91 345	99.29 298	98.82 397	97.89 215	98.21 376	98.40 424	85.63 426	99.83 202	98.45 210	98.04 289	99.37 253

thres100view900		97.76 302	97.45 310	98.69 282	99.72 105	97.86 287	99.59 116	98.74 409	97.93 211	99.26 233	98.62 415	91.75 355	99.83 202	93.22 420	98.18 282	98.37 404

tfpn200view9		97.72 312	97.38 323	98.72 277	99.69 121	97.96 278	99.50 189	98.73 415	97.83 225	99.17 254	98.45 422	91.67 359	99.83 202	93.22 420	98.18 282	98.37 404

test_prior				99.68 83	99.67 128	99.48 105		99.56 86					99.83 202			99.74 108

1314		98.68 196	98.54 201	99.11 213	98.89 372	98.65 225	99.27 308	99.49 174	96.89 326	97.99 386	99.56 268	97.72 117	99.83 202	97.74 283	99.27 188	98.84 305

thres400		97.77 301	97.38 323	98.92 238	99.69 121	97.96 278	99.50 189	98.73 415	97.83 225	99.17 254	98.45 422	91.67 359	99.83 202	93.22 420	98.18 282	98.96 299

casdiffmvs		99.13 114	98.98 126	99.56 116	99.65 149	99.16 149	99.56 141	99.50 162	98.33 139	99.41 189	99.86 68	95.92 196	99.83 202	99.45 66	99.16 198	99.70 138
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 91	99.69 210	98.55 78	99.82 211	99.69 33	99.85 88	99.48 225

MVS_Test		99.10 131	98.97 127	99.48 146	99.49 225	99.14 154	99.67 71	99.34 294	97.31 287	99.58 147	99.76 172	97.65 118	99.82 211	98.87 144	99.07 214	99.46 236

dp		97.75 306	97.80 264	97.59 388	99.10 336	93.71 427	99.32 287	98.88 390	96.48 357	99.08 270	99.55 271	92.67 333	99.82 211	96.52 363	98.58 251	99.24 269

RPSCF		98.22 229	98.62 191	96.99 403	99.82 48	91.58 442	99.72 53	99.44 239	96.61 345	99.66 115	99.89 39	95.92 196	99.82 211	97.46 311	99.10 211	99.57 195

PMMVS		98.80 183	98.62 191	99.34 173	99.27 291	98.70 221	98.76 413	99.31 316	97.34 284	99.21 243	99.07 381	97.20 133	99.82 211	98.56 198	98.87 233	99.52 208

UBG		97.85 284	97.48 304	98.95 232	99.25 298	97.64 298	99.24 324	98.74 409	97.90 214	98.64 344	98.20 432	88.65 401	99.81 216	98.27 228	98.40 261	99.42 243

EIA-MVS		99.18 99	99.09 99	99.45 154	99.49 225	99.18 146	99.67 71	99.53 118	97.66 247	99.40 194	99.44 310	98.10 104	99.81 216	98.94 132	99.62 159	99.35 255

Effi-MVS+		98.81 180	98.59 197	99.48 146	99.46 235	99.12 157	98.08 449	99.50 162	97.50 267	99.38 198	99.41 318	96.37 178	99.81 216	99.11 110	98.54 256	99.51 217

thres200		97.61 328	97.28 339	98.62 287	99.64 152	98.03 272	99.26 317	98.74 409	97.68 244	99.09 268	98.32 428	91.66 361	99.81 216	92.88 425	98.22 277	98.03 423

tpmvs		97.98 265	98.02 243	97.84 371	99.04 350	94.73 410	99.31 291	99.20 343	96.10 388	98.76 324	99.42 314	94.94 240	99.81 216	96.97 342	98.45 260	98.97 297

casdiffmvs_mvg		99.15 108	99.02 116	99.55 118	99.66 141	99.09 159	99.64 91	99.56 86	98.26 148	99.45 173	99.87 61	96.03 189	99.81 216	99.54 49	99.15 201	99.73 117
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	98.81 180	99.37 41	97.12 401	99.60 177	91.75 441	98.61 426	99.44 239	99.35 23	99.83 59	99.85 75	98.70 66	99.81 216	99.02 122	99.91 44	99.81 74

viewmacassd2359aftdt		99.08 134	98.94 137	99.50 143	99.66 141	98.96 181	99.51 179	99.54 103	98.27 145	99.42 184	99.89 39	95.88 200	99.80 223	99.20 98	99.11 206	99.76 102

viewmanbaseed2359cas		99.18 99	99.07 102	99.50 143	99.62 162	99.01 171	99.50 189	99.52 123	98.25 153	99.68 104	99.82 104	96.93 148	99.80 223	99.15 107	99.11 206	99.70 138

IMVS_0403		98.86 167	98.89 148	98.78 272	99.55 194	96.93 340	99.58 126	99.44 239	98.05 193	99.68 104	99.80 136	96.81 156	99.80 223	98.15 240	98.92 226	99.60 177

DPM-MVS		98.95 156	98.71 174	99.66 85	99.63 156	99.55 90	98.64 425	99.10 355	97.93 211	99.42 184	99.55 271	98.67 69	99.80 223	95.80 380	99.68 150	99.61 174

DP-MVS Recon		99.12 121	98.95 135	99.65 89	99.74 94	99.70 55	99.27 308	99.57 81	96.40 364	99.42 184	99.68 217	98.75 58	99.80 223	97.98 257	99.72 142	99.44 241

MVS_111021_LR		99.41 56	99.33 49	99.65 89	99.77 72	99.51 101	98.94 395	99.85 6	98.82 83	99.65 124	99.74 182	98.51 81	99.80 223	98.83 157	99.89 66	99.64 164

viewmambaseed2359dif		99.01 150	98.90 144	99.32 179	99.58 181	98.51 244	99.33 284	99.54 103	97.85 221	99.44 178	99.85 75	96.01 190	99.79 229	99.41 68	99.13 203	99.67 148

CS-MVS		99.50 28	99.48 20	99.54 119	99.76 76	99.42 112	99.90 1	99.55 94	98.56 112	99.78 75	99.70 199	98.65 71	99.79 229	99.65 39	99.78 128	99.41 246

Fast-Effi-MVS+-dtu		98.77 189	98.83 161	98.60 288	99.41 250	96.99 335	99.52 170	99.49 174	98.11 179	99.24 235	99.34 342	96.96 147	99.79 229	97.95 259	99.45 173	99.02 292

baseline1		98.31 223	97.95 250	99.38 169	99.50 223	98.74 218	99.59 116	98.93 377	98.41 129	99.14 257	99.60 254	94.59 267	99.79 229	98.48 205	93.29 417	99.61 174

baseline		99.15 108	99.02 116	99.53 127	99.66 141	99.14 154	99.72 53	99.48 186	98.35 136	99.42 184	99.84 90	96.07 186	99.79 229	99.51 54	99.14 202	99.67 148

PVSNet_0	94.43 19	96.09 382	95.47 389	97.94 361	99.31 281	94.34 421	97.81 451	99.70 15	97.12 304	97.46 401	98.75 412	89.71 387	99.79 229	97.69 290	81.69 454	99.68 145

API-MVS		99.04 143	99.03 110	99.06 217	99.40 255	99.31 129	99.55 155	99.56 86	98.54 114	99.33 213	99.39 326	98.76 55	99.78 235	96.98 341	99.78 128	98.07 420

OMC-MVS		99.08 134	99.04 107	99.20 203	99.67 128	98.22 262	99.28 303	99.52 123	98.07 187	99.66 115	99.81 119	97.79 114	99.78 235	97.79 275	99.81 114	99.60 177

GeoE		98.85 176	98.62 191	99.53 127	99.61 171	99.08 162	99.80 25	99.51 142	97.10 308	99.31 215	99.78 159	95.23 231	99.77 237	98.21 232	99.03 217	99.75 104

alignmvs		98.81 180	98.56 200	99.58 110	99.43 243	99.42 112	99.51 179	98.96 375	98.61 107	99.35 209	98.92 402	94.78 251	99.77 237	99.35 74	98.11 287	99.54 201

tpm cat1		97.39 346	97.36 325	97.50 391	99.17 323	93.73 426	99.43 238	99.31 316	91.27 437	98.71 328	99.08 380	94.31 284	99.77 237	96.41 368	98.50 258	99.00 293

CostFormer		97.72 312	97.73 277	97.71 380	99.15 329	94.02 423	99.54 160	99.02 368	94.67 412	99.04 279	99.35 338	92.35 345	99.77 237	98.50 204	97.94 292	99.34 258

MGCFI-Net		99.01 150	98.85 157	99.50 143	99.42 245	99.26 138	99.82 16	99.48 186	98.60 109	99.28 223	98.81 407	97.04 142	99.76 241	99.29 88	97.87 296	99.47 231

test_241102_ONE					99.84 35	99.90 2		99.48 186	99.07 52	99.91 29	99.74 182	99.20 7	99.76 241

MDTV_nov1_ep13			98.32 215		99.11 333	94.44 417	99.27 308	98.74 409	97.51 266	99.40 194	99.62 247	94.78 251	99.76 241	97.59 295	98.81 240

sasdasda		99.02 146	98.86 154	99.51 138	99.42 245	99.32 125	99.80 25	99.48 186	98.63 104	99.31 215	98.81 407	97.09 138	99.75 244	99.27 92	97.90 293	99.47 231

canonicalmvs		99.02 146	98.86 154	99.51 138	99.42 245	99.32 125	99.80 25	99.48 186	98.63 104	99.31 215	98.81 407	97.09 138	99.75 244	99.27 92	97.90 293	99.47 231

Effi-MVS+-dtu		98.78 185	98.89 148	98.47 311	99.33 273	96.91 345	99.57 134	99.30 321	98.47 121	99.41 189	98.99 392	96.78 158	99.74 246	98.73 168	99.38 177	98.74 321

patchmatchnet-post											98.70 413	94.79 250	99.74 246

SCA		98.19 233	98.16 223	98.27 337	99.30 282	95.55 388	99.07 361	98.97 373	97.57 256	99.43 181	99.57 265	92.72 328	99.74 246	97.58 296	99.20 196	99.52 208

BH-untuned		98.42 212	98.36 211	98.59 289	99.49 225	96.70 353	99.27 308	99.13 352	97.24 294	98.80 319	99.38 329	95.75 207	99.74 246	97.07 337	99.16 198	99.33 259

BH-RMVSNet		98.41 214	98.08 235	99.40 164	99.41 250	98.83 209	99.30 293	98.77 405	97.70 242	98.94 297	99.65 230	92.91 323	99.74 246	96.52 363	99.55 166	99.64 164

MVS_111021_HR		99.41 56	99.32 51	99.66 85	99.72 105	99.47 107	98.95 393	99.85 6	98.82 83	99.54 158	99.73 188	98.51 81	99.74 246	98.91 138	99.88 70	99.77 95

test_post											65.99 465	94.65 265	99.73 252

XVG-ACMP-BASELINE		97.83 291	97.71 279	98.20 340	99.11 333	96.33 369	99.41 250	99.52 123	98.06 191	99.05 278	99.50 291	89.64 389	99.73 252	97.73 284	97.38 331	98.53 386

HyFIR lowres test		99.11 127	98.92 139	99.65 89	99.90 4	99.37 117	99.02 375	99.91 3	97.67 246	99.59 146	99.75 177	95.90 198	99.73 252	99.53 51	99.02 219	99.86 40

DeepMVS_CX				93.34 426	99.29 286	82.27 455		99.22 339	85.15 452	96.33 423	99.05 384	90.97 373	99.73 252	93.57 417	97.77 301	98.01 424

Patchmatch-test		97.93 271	97.65 285	98.77 273	99.18 315	97.07 324	99.03 372	99.14 351	96.16 379	98.74 325	99.57 265	94.56 269	99.72 256	93.36 419	99.11 206	99.52 208

LPG-MVS_test		98.22 229	98.13 228	98.49 304	99.33 273	97.05 326	99.58 126	99.55 94	97.46 269	99.24 235	99.83 95	92.58 335	99.72 256	98.09 245	97.51 317	98.68 339

LGP-MVS_train				98.49 304	99.33 273	97.05 326		99.55 94	97.46 269	99.24 235	99.83 95	92.58 335	99.72 256	98.09 245	97.51 317	98.68 339

BH-w/o		98.00 263	97.89 259	98.32 329	99.35 267	96.20 375	99.01 380	98.90 387	96.42 362	98.38 364	99.00 390	95.26 228	99.72 256	96.06 373	98.61 248	99.03 290

ACMP	97.20 11	98.06 248	97.94 252	98.45 314	99.37 263	97.01 333	99.44 233	99.49 174	97.54 262	98.45 361	99.79 152	91.95 351	99.72 256	97.91 261	97.49 322	98.62 369
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 258	97.90 255	98.40 322	99.23 302	96.80 351	99.70 58	99.60 63	97.12 304	98.18 378	99.70 199	91.73 357	99.72 256	98.39 215	97.45 324	98.68 339
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							99.23 327				65.14 466	94.18 289	99.71 262	97.58 296

ADS-MVSNet		98.20 232	98.08 235	98.56 297	99.33 273	96.48 364	99.23 327	99.15 349	96.24 372	99.10 265	99.67 223	94.11 290	99.71 262	96.81 351	99.05 215	99.48 225

JIA-IIPM		97.50 337	97.02 353	98.93 236	98.73 398	97.80 289	99.30 293	98.97 373	91.73 436	98.91 300	94.86 454	95.10 235	99.71 262	97.58 296	97.98 290	99.28 263

EPMVS		97.82 294	97.65 285	98.35 326	98.88 373	95.98 379	99.49 205	94.71 461	97.57 256	99.26 233	99.48 300	92.46 342	99.71 262	97.87 265	99.08 213	99.35 255

TDRefinement		95.42 393	94.57 401	97.97 358	89.83 464	96.11 378	99.48 211	98.75 406	96.74 333	96.68 420	99.88 50	88.65 401	99.71 262	98.37 218	82.74 453	98.09 419

ACMM	97.58 5	98.37 220	98.34 213	98.48 306	99.41 250	97.10 320	99.56 141	99.45 230	98.53 115	99.04 279	99.85 75	93.00 319	99.71 262	98.74 166	97.45 324	98.64 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 268	97.77 270	98.57 293	99.59 179	96.61 360	99.45 227	99.08 358	98.21 161	98.88 305	99.80 136	88.66 400	99.70 268	98.58 192	97.72 302	99.39 249

CHOSEN 280x420		99.12 121	99.13 90	99.08 214	99.66 141	97.89 284	98.43 436	99.71 13	98.88 77	99.62 136	99.76 172	96.63 164	99.70 268	99.46 65	99.99 1	99.66 152

EC-MVSNet		99.44 47	99.39 37	99.58 110	99.56 190	99.49 103	99.88 4	99.58 74	98.38 131	99.73 91	99.69 210	98.20 100	99.70 268	99.64 41	99.82 111	99.54 201

PatchmatchNet		98.31 223	98.36 211	98.19 341	99.16 325	95.32 398	99.27 308	98.92 380	97.37 282	99.37 200	99.58 260	94.90 244	99.70 268	97.43 314	99.21 195	99.54 201
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 243	97.99 245	98.44 317	99.41 250	96.96 339	99.60 109	99.56 86	98.09 182	98.15 379	99.91 24	90.87 374	99.70 268	98.88 141	97.45 324	98.67 347
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 337	96.90 357	99.29 189	99.23 302	98.78 217	99.32 287	98.90 387	97.52 265	98.56 354	98.09 438	84.72 433	99.69 273	97.86 266	97.88 295	99.39 249

HQP_MVS		98.27 228	98.22 221	98.44 317	99.29 286	96.97 337	99.39 262	99.47 208	98.97 69	99.11 262	99.61 251	92.71 330	99.69 273	97.78 276	97.63 305	98.67 347

plane_prior5								99.47 208					99.69 273	97.78 276	97.63 305	98.67 347

D2MVS		98.41 214	98.50 204	98.15 346	99.26 294	96.62 359	99.40 258	99.61 56	97.71 239	98.98 289	99.36 335	96.04 188	99.67 276	98.70 171	97.41 329	98.15 416

IS-MVSNet		99.05 142	98.87 152	99.57 114	99.73 101	99.32 125	99.75 42	99.20 343	98.02 205	99.56 151	99.86 68	96.54 169	99.67 276	98.09 245	99.13 203	99.73 117

CLD-MVS		98.16 237	98.10 231	98.33 327	99.29 286	96.82 350	98.75 414	99.44 239	97.83 225	99.13 258	99.55 271	92.92 321	99.67 276	98.32 225	97.69 303	98.48 390
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 354	97.30 336	97.09 402	99.43 243	93.31 433	99.73 51	98.87 392	98.83 82	99.28 223	99.80 136	84.45 434	99.66 279	97.88 263	97.45 324	98.30 406

AUN-MVS		96.88 365	96.31 371	98.59 289	99.48 232	97.04 329	99.27 308	99.22 339	97.44 275	98.51 357	99.41 318	91.97 350	99.66 279	97.71 287	83.83 451	99.07 287

UniMVSNet_ETH3D		97.32 351	96.81 359	98.87 255	99.40 255	97.46 304	99.51 179	99.53 118	95.86 392	98.54 356	99.77 168	82.44 443	99.66 279	98.68 176	97.52 316	99.50 221

OPM-MVS		98.19 233	98.10 231	98.45 314	98.88 373	97.07 324	99.28 303	99.38 273	98.57 111	99.22 240	99.81 119	92.12 347	99.66 279	98.08 249	97.54 314	98.61 378
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 274	97.78 268	98.32 329	99.46 235	96.68 357	99.56 141	99.54 103	98.41 129	97.79 397	99.87 61	90.18 383	99.66 279	98.05 253	97.18 339	98.62 369

IMVS_0407		98.86 167	98.91 142	98.72 277	99.55 194	96.93 340	99.50 189	99.44 239	98.05 193	99.66 115	99.80 136	97.13 135	99.65 284	98.15 240	98.92 226	99.60 177

hse-mvs2		97.50 337	97.14 347	98.59 289	99.49 225	97.05 326	99.28 303	99.22 339	98.94 72	99.66 115	99.42 314	94.93 241	99.65 284	99.48 62	83.80 452	99.08 282

VPA-MVSNet		98.29 226	97.95 250	99.30 186	99.16 325	99.54 92	99.50 189	99.58 74	98.27 145	99.35 209	99.37 332	92.53 337	99.65 284	99.35 74	94.46 398	98.72 323

TR-MVS		97.76 302	97.41 321	98.82 264	99.06 345	97.87 285	98.87 403	98.56 423	96.63 344	98.68 336	99.22 366	92.49 338	99.65 284	95.40 391	97.79 300	98.95 301

reproduce_monomvs		97.89 278	97.87 260	97.96 360	99.51 211	95.45 393	99.60 109	99.25 333	99.17 30	98.85 313	99.49 294	89.29 392	99.64 288	99.35 74	96.31 355	98.78 309

gm-plane-assit					98.54 418	92.96 435			94.65 413		99.15 374		99.64 288	97.56 301

HQP4-MVS										98.66 337			99.64 288			98.64 360

HQP-MVS		98.02 258	97.90 255	98.37 325	99.19 312	96.83 348	98.98 386	99.39 265	98.24 155	98.66 337	99.40 322	92.47 339	99.64 288	97.19 329	97.58 310	98.64 360

PAPM		97.59 329	97.09 351	99.07 215	99.06 345	98.26 260	98.30 443	99.10 355	94.88 407	98.08 381	99.34 342	96.27 181	99.64 288	89.87 439	98.92 226	99.31 261

TAPA-MVS	97.07 15	97.74 308	97.34 330	98.94 234	99.70 116	97.53 301	99.25 319	99.51 142	91.90 435	99.30 219	99.63 242	98.78 51	99.64 288	88.09 446	99.87 73	99.65 157
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 218	98.09 234	99.24 199	99.26 294	99.32 125	99.56 141	99.55 94	97.45 272	98.71 328	99.83 95	93.23 314	99.63 294	98.88 141	96.32 354	98.76 315

ITE_SJBPF				98.08 349	99.29 286	96.37 367		98.92 380	98.34 137	98.83 314	99.75 177	91.09 371	99.62 295	95.82 378	97.40 330	98.25 410

LF4IMVS		97.52 334	97.46 309	97.70 381	98.98 361	95.55 388	99.29 298	98.82 397	98.07 187	98.66 337	99.64 236	89.97 384	99.61 296	97.01 338	96.68 344	97.94 431

tpm		97.67 323	97.55 294	98.03 351	99.02 352	95.01 405	99.43 238	98.54 425	96.44 360	99.12 260	99.34 342	91.83 354	99.60 297	97.75 282	96.46 350	99.48 225

tpm2		97.44 344	97.34 330	97.74 379	99.15 329	94.36 420	99.45 227	98.94 376	93.45 426	98.90 302	99.44 310	91.35 367	99.59 298	97.31 320	98.07 288	99.29 262

SSM_04072		99.06 139	98.96 131	99.35 172	99.62 162	98.88 196	99.25 319	99.47 208	98.05 193	99.37 200	99.81 119	96.85 150	99.58 299	98.98 125	99.25 191	99.60 177

SD_0403		97.55 331	97.53 298	97.62 384	99.61 171	93.64 430	99.72 53	99.44 239	98.03 202	98.62 349	99.39 326	96.06 187	99.57 300	87.88 448	99.01 220	99.66 152

baseline2		97.87 281	97.55 294	98.82 264	99.18 315	98.02 273	99.41 250	96.58 455	96.97 319	96.51 421	99.17 371	93.43 309	99.57 300	97.71 287	99.03 217	98.86 303

MS-PatchMatch		97.24 356	97.32 334	96.99 403	98.45 421	93.51 432	98.82 407	99.32 312	97.41 279	98.13 380	99.30 353	88.99 394	99.56 302	95.68 384	99.80 119	97.90 434

TinyColmap		97.12 359	96.89 358	97.83 372	99.07 343	95.52 391	98.57 429	98.74 409	97.58 255	97.81 396	99.79 152	88.16 408	99.56 302	95.10 396	97.21 337	98.39 402

USDC		97.34 349	97.20 344	97.75 377	99.07 343	95.20 400	98.51 433	99.04 365	97.99 206	98.31 368	99.86 68	89.02 393	99.55 304	95.67 385	97.36 332	98.49 389

MSLP-MVS++		99.46 39	99.47 22	99.44 158	99.60 177	99.16 149	99.41 250	99.71 13	98.98 66	99.45 173	99.78 159	99.19 9	99.54 305	99.28 89	99.84 96	99.63 169

UWE-MVS-28		97.36 347	97.24 343	97.75 377	98.84 382	94.44 417	99.24 324	97.58 444	97.98 207	99.00 286	99.00 390	91.35 367	99.53 306	93.75 414	98.39 262	99.27 267

TAMVS		99.12 121	99.08 100	99.24 199	99.46 235	98.55 236	99.51 179	99.46 219	98.09 182	99.45 173	99.82 104	98.34 94	99.51 307	98.70 171	98.93 224	99.67 148

EPNet_dtu		98.03 256	97.96 248	98.23 339	98.27 424	95.54 390	99.23 327	98.75 406	99.02 56	97.82 395	99.71 195	96.11 185	99.48 308	93.04 423	99.65 155	99.69 141
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 369	96.22 373	97.97 358	97.00 446	96.28 371	98.66 423	99.03 367	96.61 345	96.93 418	99.79 152	87.20 417	99.47 309	96.65 361	94.13 405	98.16 415

EG-PatchMatch MVS		95.97 384	95.69 385	96.81 410	97.78 431	92.79 436	99.16 342	98.93 377	96.16 379	94.08 439	99.22 366	82.72 441	99.47 309	95.67 385	97.50 319	98.17 414

myMVS_eth3d28		97.69 317	97.34 330	98.73 275	99.27 291	97.52 302	99.33 284	98.78 404	98.03 202	98.82 316	98.49 420	86.64 419	99.46 311	98.44 211	98.24 276	99.23 270

MVP-Stereo		97.81 296	97.75 275	97.99 357	97.53 435	96.60 361	98.96 390	98.85 394	97.22 296	97.23 408	99.36 335	95.28 225	99.46 311	95.51 387	99.78 128	97.92 433
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 204	98.67 178	98.30 331	99.35 267	95.59 387	99.50 189	99.55 94	98.60 109	99.39 196	99.83 95	94.48 275	99.45 313	98.75 165	98.56 254	99.85 44

test-LLR		98.06 248	97.90 255	98.55 299	98.79 386	97.10 320	98.67 420	97.75 440	97.34 284	98.61 350	98.85 404	94.45 277	99.45 313	97.25 323	99.38 177	99.10 277

TESTMET0.1,1		97.55 331	97.27 342	98.40 322	98.93 366	96.53 362	98.67 420	97.61 443	96.96 320	98.64 344	99.28 357	88.63 403	99.45 313	97.30 321	99.38 177	99.21 272

test-mter		97.49 342	97.13 349	98.55 299	98.79 386	97.10 320	98.67 420	97.75 440	96.65 340	98.61 350	98.85 404	88.23 407	99.45 313	97.25 323	99.38 177	99.10 277

mvs_anonymous		99.03 145	98.99 123	99.16 207	99.38 260	98.52 242	99.51 179	99.38 273	97.79 230	99.38 198	99.81 119	97.30 128	99.45 313	99.35 74	98.99 221	99.51 217

tfpnnormal		97.84 288	97.47 307	98.98 227	99.20 309	99.22 143	99.64 91	99.61 56	96.32 366	98.27 372	99.70 199	93.35 313	99.44 318	95.69 383	95.40 381	98.27 408

v7n		97.87 281	97.52 299	98.92 238	98.76 396	98.58 234	99.84 12	99.46 219	96.20 375	98.91 300	99.70 199	94.89 245	99.44 318	96.03 374	93.89 410	98.75 317

jajsoiax		98.43 211	98.28 218	98.88 251	98.60 413	98.43 253	99.82 16	99.53 118	98.19 163	98.63 346	99.80 136	93.22 316	99.44 318	99.22 96	97.50 319	98.77 313

mvs_tets		98.40 217	98.23 220	98.91 242	98.67 406	98.51 244	99.66 78	99.53 118	98.19 163	98.65 343	99.81 119	92.75 325	99.44 318	99.31 83	97.48 323	98.77 313

sc_t1		95.75 388	95.05 395	97.87 367	98.83 383	94.61 414	99.21 333	99.45 230	87.45 448	97.97 388	99.85 75	81.19 448	99.43 322	98.27 228	93.20 419	99.57 195

Vis-MVSNet (Re-imp)		98.87 164	98.72 172	99.31 181	99.71 111	98.88 196	99.80 25	99.44 239	97.91 213	99.36 206	99.78 159	95.49 217	99.43 322	97.91 261	99.11 206	99.62 172

OPU-MVS				99.64 95	99.56 190	99.72 51	99.60 109				99.70 199	99.27 5	99.42 324	98.24 231	99.80 119	99.79 87

Anonymous20231211		97.88 279	97.54 297	98.90 244	99.71 111	98.53 238	99.48 211	99.57 81	94.16 417	98.81 317	99.68 217	93.23 314	99.42 324	98.84 154	94.42 400	98.76 315

ttmdpeth		97.80 298	97.63 289	98.29 332	98.77 394	97.38 307	99.64 91	99.36 282	98.78 92	96.30 424	99.58 260	92.34 346	99.39 326	98.36 220	95.58 376	98.10 418

VPNet		97.84 288	97.44 315	99.01 223	99.21 307	98.94 189	99.48 211	99.57 81	98.38 131	99.28 223	99.73 188	88.89 395	99.39 326	99.19 99	93.27 418	98.71 325

nrg030		98.64 201	98.42 208	99.28 193	99.05 348	99.69 57	99.81 20	99.46 219	98.04 200	99.01 282	99.82 104	96.69 162	99.38 328	99.34 79	94.59 397	98.78 309

GA-MVS		97.85 284	97.47 307	99.00 225	99.38 260	97.99 275	98.57 429	99.15 349	97.04 315	98.90 302	99.30 353	89.83 386	99.38 328	96.70 356	98.33 266	99.62 172

UniMVSNet (Re)		98.29 226	98.00 244	99.13 212	99.00 355	99.36 120	99.49 205	99.51 142	97.95 209	98.97 291	99.13 376	96.30 180	99.38 328	98.36 220	93.34 416	98.66 356

FIs		98.78 185	98.63 186	99.23 201	99.18 315	99.54 92	99.83 15	99.59 69	98.28 143	98.79 321	99.81 119	96.75 160	99.37 331	99.08 115	96.38 352	98.78 309

PS-MVSNAJss		98.92 158	98.92 139	98.90 244	98.78 389	98.53 238	99.78 32	99.54 103	98.07 187	99.00 286	99.76 172	99.01 18	99.37 331	99.13 108	97.23 336	98.81 306

CDS-MVSNet		99.09 132	99.03 110	99.25 196	99.42 245	98.73 219	99.45 227	99.46 219	98.11 179	99.46 172	99.77 168	98.01 109	99.37 331	98.70 171	98.92 226	99.66 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 388	95.16 393	97.51 390	99.30 282	93.69 428	98.88 401	95.78 456	85.09 453	98.78 322	92.65 456	91.29 369	99.37 331	94.85 401	99.85 88	99.46 236

v1192		97.81 296	97.44 315	98.91 242	98.88 373	98.68 222	99.51 179	99.34 294	96.18 377	99.20 246	99.34 342	94.03 294	99.36 335	95.32 393	95.18 385	98.69 334

EI-MVSNet		98.67 197	98.67 178	98.68 283	99.35 267	97.97 276	99.50 189	99.38 273	96.93 325	99.20 246	99.83 95	97.87 111	99.36 335	98.38 216	97.56 312	98.71 325

MVSTER		98.49 206	98.32 215	99.00 225	99.35 267	99.02 169	99.54 160	99.38 273	97.41 279	99.20 246	99.73 188	93.86 302	99.36 335	98.87 144	97.56 312	98.62 369

gg-mvs-nofinetune		96.17 380	95.32 392	98.73 275	98.79 386	98.14 266	99.38 267	94.09 462	91.07 440	98.07 384	91.04 460	89.62 390	99.35 338	96.75 353	99.09 212	98.68 339

pm-mvs1		97.68 320	97.28 339	98.88 251	99.06 345	98.62 230	99.50 189	99.45 230	96.32 366	97.87 393	99.79 152	92.47 339	99.35 338	97.54 303	93.54 414	98.67 347

OurMVSNet-221017-0		97.88 279	97.77 270	98.19 341	98.71 402	96.53 362	99.88 4	99.00 370	97.79 230	98.78 322	99.94 6	91.68 358	99.35 338	97.21 325	96.99 343	98.69 334

EGC-MVSNET		82.80 425	77.86 431	97.62 384	97.91 428	96.12 377	99.33 284	99.28 327	8.40 468	25.05 469	99.27 360	84.11 435	99.33 341	89.20 441	98.22 277	97.42 442

pmmvs6		96.53 372	96.09 377	97.82 374	98.69 404	95.47 392	99.37 269	99.47 208	93.46 425	97.41 402	99.78 159	87.06 418	99.33 341	96.92 348	92.70 426	98.65 358

V42		98.06 248	97.79 265	98.86 258	98.98 361	98.84 206	99.69 62	99.34 294	96.53 352	99.30 219	99.37 332	94.67 262	99.32 343	97.57 300	94.66 395	98.42 398

lessismore_v0				97.79 376	98.69 404	95.44 395		94.75 460		95.71 430	99.87 61	88.69 399	99.32 343	95.89 377	94.93 392	98.62 369

OpenMVS_ROB	92.34 20	94.38 405	93.70 411	96.41 415	97.38 437	93.17 434	99.06 365	98.75 406	86.58 451	94.84 437	98.26 430	81.53 446	99.32 343	89.01 442	97.87 296	96.76 445

v8		97.95 270	97.63 289	98.93 236	98.95 365	98.81 214	99.80 25	99.41 255	96.03 389	99.10 265	99.42 314	94.92 243	99.30 346	96.94 345	94.08 407	98.66 356

v1921920		97.80 298	97.45 310	98.84 262	98.80 385	98.53 238	99.52 170	99.34 294	96.15 381	99.24 235	99.47 303	93.98 296	99.29 347	95.40 391	95.13 387	98.69 334

anonymousdsp		98.44 210	98.28 218	98.94 234	98.50 419	98.96 181	99.77 34	99.50 162	97.07 310	98.87 308	99.77 168	94.76 255	99.28 348	98.66 178	97.60 308	98.57 384

MVSFormer		99.17 102	99.12 92	99.29 189	99.51 211	98.94 189	99.88 4	99.46 219	97.55 259	99.80 68	99.65 230	97.39 122	99.28 348	99.03 120	99.85 88	99.65 157

test_djsdf		98.67 197	98.57 198	98.98 227	98.70 403	98.91 194	99.88 4	99.46 219	97.55 259	99.22 240	99.88 50	95.73 208	99.28 348	99.03 120	97.62 307	98.75 317

VortexMVS		98.67 197	98.66 181	98.68 283	99.62 162	97.96 278	99.59 116	99.41 255	98.13 175	99.31 215	99.70 199	95.48 218	99.27 351	99.40 69	97.32 333	98.79 307

SSC-MVS3.2		97.34 349	97.15 346	97.93 362	99.02 352	95.76 384	99.48 211	99.58 74	97.62 251	99.09 268	99.53 280	87.95 410	99.27 351	96.42 366	95.66 374	98.75 317

cascas		97.69 317	97.43 319	98.48 306	98.60 413	97.30 309	98.18 447	99.39 265	92.96 429	98.41 362	98.78 411	93.77 305	99.27 351	98.16 238	98.61 248	98.86 303

v144192		97.92 274	97.60 292	98.87 255	98.83 383	98.65 225	99.55 155	99.34 294	96.20 375	99.32 214	99.40 322	94.36 279	99.26 354	96.37 370	95.03 389	98.70 330

dmvs_re		98.08 246	98.16 223	97.85 369	99.55 194	94.67 413	99.70 58	98.92 380	98.15 168	99.06 276	99.35 338	93.67 308	99.25 355	97.77 279	97.25 335	99.64 164

v2v482		98.06 248	97.77 270	98.92 238	98.90 371	98.82 212	99.57 134	99.36 282	96.65 340	99.19 249	99.35 338	94.20 286	99.25 355	97.72 286	94.97 390	98.69 334

v1240		97.69 317	97.32 334	98.79 270	98.85 380	98.43 253	99.48 211	99.36 282	96.11 384	99.27 228	99.36 335	93.76 306	99.24 357	94.46 405	95.23 384	98.70 330

WBMVS		97.74 308	97.50 302	98.46 312	99.24 300	97.43 305	99.21 333	99.42 252	97.45 272	98.96 293	99.41 318	88.83 396	99.23 358	98.94 132	96.02 360	98.71 325

v1144		97.98 265	97.69 281	98.85 261	98.87 376	98.66 224	99.54 160	99.35 289	96.27 370	99.23 239	99.35 338	94.67 262	99.23 358	96.73 354	95.16 386	98.68 339

v10		97.85 284	97.52 299	98.86 258	98.99 358	98.67 223	99.75 42	99.41 255	95.70 393	98.98 289	99.41 318	94.75 256	99.23 358	96.01 376	94.63 396	98.67 347

WR-MVS_H		98.13 240	97.87 260	98.90 244	99.02 352	98.84 206	99.70 58	99.59 69	97.27 290	98.40 363	99.19 370	95.53 215	99.23 358	98.34 222	93.78 412	98.61 378

miper_enhance_ethall		98.16 237	98.08 235	98.41 320	98.96 364	97.72 293	98.45 435	99.32 312	96.95 322	98.97 291	99.17 371	97.06 141	99.22 362	97.86 266	95.99 363	98.29 407

GG-mvs-BLEND				98.45 314	98.55 417	98.16 264	99.43 238	93.68 463		97.23 408	98.46 421	89.30 391	99.22 362	95.43 390	98.22 277	97.98 429

FC-MVSNet-test		98.75 190	98.62 191	99.15 211	99.08 342	99.45 109	99.86 11	99.60 63	98.23 158	98.70 334	99.82 104	96.80 157	99.22 362	99.07 116	96.38 352	98.79 307

UniMVSNet_NR-MVSNet		98.22 229	97.97 247	98.96 230	98.92 368	98.98 174	99.48 211	99.53 118	97.76 234	98.71 328	99.46 307	96.43 176	99.22 362	98.57 195	92.87 424	98.69 334

DU-MVS		98.08 246	97.79 265	98.96 230	98.87 376	98.98 174	99.41 250	99.45 230	97.87 217	98.71 328	99.50 291	94.82 247	99.22 362	98.57 195	92.87 424	98.68 339

cl____		98.01 261	97.84 263	98.55 299	99.25 298	97.97 276	98.71 418	99.34 294	96.47 359	98.59 353	99.54 276	95.65 211	99.21 367	97.21 325	95.77 369	98.46 395

WR-MVS		98.06 248	97.73 277	99.06 217	98.86 379	99.25 140	99.19 338	99.35 289	97.30 288	98.66 337	99.43 312	93.94 297	99.21 367	98.58 192	94.28 402	98.71 325

test_0402		96.64 370	96.24 372	97.85 369	98.85 380	96.43 366	99.44 233	99.26 331	93.52 423	96.98 416	99.52 284	88.52 404	99.20 369	92.58 430	97.50 319	97.93 432

icg_test_0407_2		98.79 184	98.86 154	98.57 293	99.55 194	96.93 340	99.07 361	99.44 239	98.05 193	99.66 115	99.80 136	97.13 135	99.18 370	98.15 240	98.92 226	99.60 177

SixPastTwentyTwo		97.50 337	97.33 333	98.03 351	98.65 407	96.23 374	99.77 34	98.68 418	97.14 301	97.90 391	99.93 10	90.45 377	99.18 370	97.00 339	96.43 351	98.67 347

cl22		97.85 284	97.64 288	98.48 306	99.09 339	97.87 285	98.60 428	99.33 302	97.11 307	98.87 308	99.22 366	92.38 344	99.17 372	98.21 232	95.99 363	98.42 398

tt0320		95.71 390	95.07 394	97.62 384	99.05 348	95.02 404	99.25 319	99.52 123	86.81 449	97.97 388	99.72 192	83.58 438	99.15 373	96.38 369	93.35 415	98.68 339

WB-MVSnew		97.65 325	97.65 285	97.63 383	98.78 389	97.62 299	99.13 348	98.33 428	97.36 283	99.07 271	98.94 398	95.64 212	99.15 373	92.95 424	98.68 246	96.12 452

IterMVS-SCA-FT		97.82 294	97.75 275	98.06 350	99.57 186	96.36 368	99.02 375	99.49 174	97.18 298	98.71 328	99.72 192	92.72 328	99.14 375	97.44 313	95.86 368	98.67 347

pmmvs5		97.52 334	97.30 336	98.16 343	98.57 416	96.73 352	99.27 308	98.90 387	96.14 382	98.37 365	99.53 280	91.54 364	99.14 375	97.51 305	95.87 367	98.63 367

v148		97.79 300	97.55 294	98.50 303	98.74 397	97.72 293	99.54 160	99.33 302	96.26 371	98.90 302	99.51 288	94.68 261	99.14 375	97.83 270	93.15 421	98.63 367

IMVS_0404		98.53 205	98.52 203	98.55 299	99.55 194	96.93 340	99.20 336	99.44 239	98.05 193	98.96 293	99.80 136	94.66 264	99.13 378	98.15 240	98.92 226	99.60 177

miper_ehance_all_eth		98.18 235	98.10 231	98.41 320	99.23 302	97.72 293	98.72 417	99.31 316	96.60 348	98.88 305	99.29 355	97.29 129	99.13 378	97.60 294	95.99 363	98.38 403

NR-MVSNet		97.97 268	97.61 291	99.02 222	98.87 376	99.26 138	99.47 220	99.42 252	97.63 249	97.08 414	99.50 291	95.07 236	99.13 378	97.86 266	93.59 413	98.68 339

IterMVS		97.83 291	97.77 270	98.02 353	99.58 181	96.27 372	99.02 375	99.48 186	97.22 296	98.71 328	99.70 199	92.75 325	99.13 378	97.46 311	96.00 362	98.67 347
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 406	94.90 397	91.84 431	97.24 441	80.01 461	98.52 432	99.48 186	89.01 445	91.99 448	99.67 223	85.67 425	99.13 378	95.44 389	97.03 342	96.39 449
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 253	97.96 248	98.33 327	99.26 294	97.38 307	98.56 431	99.31 316	96.65 340	98.88 305	99.52 284	96.58 167	99.12 383	97.39 316	95.53 379	98.47 392

pmmvs4		98.13 240	97.90 255	98.81 267	98.61 412	98.87 200	98.99 383	99.21 342	96.44 360	99.06 276	99.58 260	95.90 198	99.11 384	97.18 331	96.11 359	98.46 395

TransMVSNet (Re)		97.15 358	96.58 364	98.86 258	99.12 331	98.85 204	99.49 205	98.91 385	95.48 396	97.16 412	99.80 136	93.38 310	99.11 384	94.16 411	91.73 431	98.62 369

ambc				93.06 429	92.68 460	82.36 454	98.47 434	98.73 415		95.09 435	97.41 443	55.55 461	99.10 386	96.42 366	91.32 432	97.71 435

Baseline_NR-MVSNet		97.76 302	97.45 310	98.68 283	99.09 339	98.29 258	99.41 250	98.85 394	95.65 394	98.63 346	99.67 223	94.82 247	99.10 386	98.07 252	92.89 423	98.64 360

test_vis3_rt		87.04 421	85.81 424	90.73 435	93.99 459	81.96 456	99.76 37	90.23 470	92.81 431	81.35 458	91.56 458	40.06 467	99.07 388	94.27 408	88.23 445	91.15 458

CP-MVSNet		98.09 244	97.78 268	99.01 223	98.97 363	99.24 141	99.67 71	99.46 219	97.25 292	98.48 360	99.64 236	93.79 304	99.06 389	98.63 182	94.10 406	98.74 321

PS-CasMVS		97.93 271	97.59 293	98.95 232	98.99 358	99.06 165	99.68 68	99.52 123	97.13 302	98.31 368	99.68 217	92.44 343	99.05 390	98.51 203	94.08 407	98.75 317

K. test v3		97.10 360	96.79 360	98.01 354	98.72 400	96.33 369	99.87 8	97.05 447	97.59 253	96.16 426	99.80 136	88.71 398	99.04 391	96.69 357	96.55 349	98.65 358

new_pmnet		96.38 376	96.03 378	97.41 393	98.13 427	95.16 403	99.05 367	99.20 343	93.94 418	97.39 405	98.79 410	91.61 363	99.04 391	90.43 437	95.77 369	98.05 422

DIV-MVS_self_test		98.01 261	97.85 262	98.48 306	99.24 300	97.95 281	98.71 418	99.35 289	96.50 353	98.60 352	99.54 276	95.72 209	99.03 393	97.21 325	95.77 369	98.46 395

IterMVS-LS		98.46 209	98.42 208	98.58 292	99.59 179	98.00 274	99.37 269	99.43 250	96.94 324	99.07 271	99.59 256	97.87 111	99.03 393	98.32 225	95.62 375	98.71 325
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 325	97.68 282	97.55 389	98.62 410	94.97 406	98.84 405	99.30 321	96.83 331	98.19 377	99.34 342	97.01 145	99.02 395	95.00 399	96.01 361	98.64 360

Patchmtry		97.75 306	97.40 322	98.81 267	99.10 336	98.87 200	99.11 357	99.33 302	94.83 409	98.81 317	99.38 329	94.33 282	99.02 395	96.10 372	95.57 377	98.53 386

N_pmnet		94.95 400	95.83 383	92.31 430	98.47 420	79.33 462	99.12 351	92.81 468	93.87 419	97.68 398	99.13 376	93.87 301	99.01 397	91.38 434	96.19 357	98.59 382

CR-MVSNet		98.17 236	97.93 253	98.87 255	99.18 315	98.49 247	99.22 331	99.33 302	96.96 320	99.56 151	99.38 329	94.33 282	99.00 398	94.83 402	98.58 251	99.14 274

c3_l		98.12 242	98.04 240	98.38 324	99.30 282	97.69 297	98.81 408	99.33 302	96.67 338	98.83 314	99.34 342	97.11 137	98.99 399	97.58 296	95.34 382	98.48 390

test0.0.03 1		97.71 315	97.42 320	98.56 297	98.41 423	97.82 288	98.78 411	98.63 421	97.34 284	98.05 385	98.98 394	94.45 277	98.98 400	95.04 398	97.15 340	98.89 302

PatchT		97.03 362	96.44 368	98.79 270	98.99 358	98.34 257	99.16 342	99.07 361	92.13 434	99.52 162	97.31 447	94.54 272	98.98 400	88.54 444	98.73 243	99.03 290

GBi-Net		97.68 320	97.48 304	98.29 332	99.51 211	97.26 313	99.43 238	99.48 186	96.49 354	99.07 271	99.32 350	90.26 379	98.98 400	97.10 333	96.65 345	98.62 369

test1		97.68 320	97.48 304	98.29 332	99.51 211	97.26 313	99.43 238	99.48 186	96.49 354	99.07 271	99.32 350	90.26 379	98.98 400	97.10 333	96.65 345	98.62 369

FMVSNet3		98.03 256	97.76 274	98.84 262	99.39 258	98.98 174	99.40 258	99.38 273	96.67 338	99.07 271	99.28 357	92.93 320	98.98 400	97.10 333	96.65 345	98.56 385

FMVSNet2		97.72 312	97.36 325	98.80 269	99.51 211	98.84 206	99.45 227	99.42 252	96.49 354	98.86 312	99.29 355	90.26 379	98.98 400	96.44 365	96.56 348	98.58 383

FMVSNet1		96.84 366	96.36 370	98.29 332	99.32 280	97.26 313	99.43 238	99.48 186	95.11 401	98.55 355	99.32 350	83.95 436	98.98 400	95.81 379	96.26 356	98.62 369

ppachtmachnet_test		97.49 342	97.45 310	97.61 387	98.62 410	95.24 399	98.80 409	99.46 219	96.11 384	98.22 375	99.62 247	96.45 174	98.97 407	93.77 413	95.97 366	98.61 378

TranMVSNet+NR-MVSNet		97.93 271	97.66 284	98.76 274	98.78 389	98.62 230	99.65 84	99.49 174	97.76 234	98.49 359	99.60 254	94.23 285	98.97 407	98.00 256	92.90 422	98.70 330

MVStest1		96.08 383	95.48 388	97.89 366	98.93 366	96.70 353	99.56 141	99.35 289	92.69 432	91.81 449	99.46 307	89.90 385	98.96 409	95.00 399	92.61 427	98.00 427

tt0320-xc		95.31 396	94.59 400	97.45 392	98.92 368	94.73 410	99.20 336	99.31 316	86.74 450	97.23 408	99.72 192	81.14 449	98.95 410	97.08 336	91.98 430	98.67 347

test_method		91.10 416	91.36 418	90.31 436	95.85 449	73.72 469	94.89 457	99.25 333	68.39 460	95.82 429	99.02 388	80.50 450	98.95 410	93.64 416	94.89 394	98.25 410

ADS-MVSNet2		98.02 258	98.07 238	97.87 367	99.33 273	95.19 401	99.23 327	99.08 358	96.24 372	99.10 265	99.67 223	94.11 290	98.93 412	96.81 351	99.05 215	99.48 225

ET-MVSNet_ETH3D		96.49 373	95.64 387	99.05 219	99.53 202	98.82 212	98.84 405	97.51 445	97.63 249	84.77 454	99.21 369	92.09 348	98.91 413	98.98 125	92.21 429	99.41 246

miper_lstm_enhance		98.00 263	97.91 254	98.28 336	99.34 272	97.43 305	98.88 401	99.36 282	96.48 357	98.80 319	99.55 271	95.98 191	98.91 413	97.27 322	95.50 380	98.51 388

MonoMVSNet		98.38 218	98.47 206	98.12 348	98.59 415	96.19 376	99.72 53	98.79 403	97.89 215	99.44 178	99.52 284	96.13 184	98.90 415	98.64 180	97.54 314	99.28 263

PEN-MVS		97.76 302	97.44 315	98.72 277	98.77 394	98.54 237	99.78 32	99.51 142	97.06 312	98.29 371	99.64 236	92.63 334	98.89 416	98.09 245	93.16 420	98.72 323

testing3		97.28 352	96.76 361	98.82 264	99.37 263	98.07 271	99.45 227	99.36 282	97.56 258	97.89 392	98.95 397	83.70 437	98.82 417	96.03 374	98.56 254	99.58 192

testgi		97.65 325	97.50 302	98.13 347	99.36 266	96.45 365	99.42 245	99.48 186	97.76 234	97.87 393	99.45 309	91.09 371	98.81 418	94.53 404	98.52 257	99.13 276

testf1		90.42 419	90.68 420	89.65 439	97.78 431	73.97 467	99.13 348	98.81 399	89.62 442	91.80 450	98.93 399	62.23 459	98.80 419	86.61 453	91.17 433	96.19 450

APD_test2		90.42 419	90.68 420	89.65 439	97.78 431	73.97 467	99.13 348	98.81 399	89.62 442	91.80 450	98.93 399	62.23 459	98.80 419	86.61 453	91.17 433	96.19 450

MIMVSNet		97.73 310	97.45 310	98.57 293	99.45 241	97.50 303	99.02 375	98.98 372	96.11 384	99.41 189	99.14 375	90.28 378	98.74 421	95.74 381	98.93 224	99.47 231

LCM-MVSNet-Re		97.83 291	98.15 225	96.87 409	99.30 282	92.25 439	99.59 116	98.26 429	97.43 276	96.20 425	99.13 376	96.27 181	98.73 422	98.17 237	98.99 221	99.64 164

Syy-MVS		97.09 361	97.14 347	96.95 406	99.00 355	92.73 437	99.29 298	99.39 265	97.06 312	97.41 402	98.15 433	93.92 299	98.68 423	91.71 432	98.34 264	99.45 239

myMVS_eth3d		96.89 364	96.37 369	98.43 319	99.00 355	97.16 317	99.29 298	99.39 265	97.06 312	97.41 402	98.15 433	83.46 439	98.68 423	95.27 394	98.34 264	99.45 239

DTE-MVSNet		97.51 336	97.19 345	98.46 312	98.63 409	98.13 267	99.84 12	99.48 186	96.68 337	97.97 388	99.67 223	92.92 321	98.56 425	96.88 350	92.60 428	98.70 330

PC_three_1452									98.18 166	99.84 51	99.70 199	99.31 3	98.52 426	98.30 227	99.80 119	99.81 74

mvsany_test3		93.77 408	93.45 412	94.74 421	95.78 450	88.01 447	99.64 91	98.25 430	98.28 143	94.31 438	97.97 440	68.89 455	98.51 427	97.50 306	90.37 438	97.71 435

UnsupCasMVSNet_bld		93.53 409	92.51 415	96.58 414	97.38 437	93.82 424	98.24 444	99.48 186	91.10 439	93.10 443	96.66 449	74.89 453	98.37 428	94.03 412	87.71 446	97.56 440

Anonymous20240521		96.20 379	95.89 382	97.13 400	97.72 434	94.96 407	99.79 31	99.29 325	93.01 428	97.20 411	99.03 386	89.69 388	98.36 429	91.16 435	96.13 358	98.07 420

test_f		91.90 415	91.26 419	93.84 424	95.52 454	85.92 449	99.69 62	98.53 426	95.31 398	93.87 440	96.37 451	55.33 462	98.27 430	95.70 382	90.98 436	97.32 443

MDA-MVSNet_test_wron		95.45 392	94.60 399	98.01 354	98.16 426	97.21 316	99.11 357	99.24 336	93.49 424	80.73 460	98.98 394	93.02 318	98.18 431	94.22 410	94.45 399	98.64 360

UnsupCasMVSNet_eth		96.44 374	96.12 375	97.40 394	98.65 407	95.65 385	99.36 274	99.51 142	97.13 302	96.04 428	98.99 392	88.40 405	98.17 432	96.71 355	90.27 439	98.40 401

KD-MVS_2432*1600		94.62 401	93.72 409	97.31 395	97.19 443	95.82 382	98.34 439	99.20 343	95.00 405	97.57 399	98.35 426	87.95 410	98.10 433	92.87 426	77.00 458	98.01 424

miper_refine_blended		94.62 401	93.72 409	97.31 395	97.19 443	95.82 382	98.34 439	99.20 343	95.00 405	97.57 399	98.35 426	87.95 410	98.10 433	92.87 426	77.00 458	98.01 424

YYNet1		95.36 394	94.51 402	97.92 363	97.89 429	97.10 320	99.10 359	99.23 337	93.26 427	80.77 459	99.04 385	92.81 324	98.02 435	94.30 406	94.18 404	98.64 360

EU-MVSNet		97.98 265	98.03 241	97.81 375	98.72 400	96.65 358	99.66 78	99.66 28	98.09 182	98.35 366	99.82 104	95.25 229	98.01 436	97.41 315	95.30 383	98.78 309

Gipuma		90.99 417	90.15 422	93.51 425	98.73 398	90.12 445	93.98 458	99.45 230	79.32 456	92.28 446	94.91 453	69.61 454	97.98 437	87.42 449	95.67 373	92.45 456
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 395	94.73 398	97.15 398	95.53 453	95.94 380	99.35 279	99.10 355	95.13 399	93.55 441	97.54 442	88.15 409	97.91 438	94.58 403	89.69 442	97.61 438

PM-MVS		92.96 412	92.23 416	95.14 420	95.61 451	89.98 446	99.37 269	98.21 433	94.80 410	95.04 436	97.69 441	65.06 456	97.90 439	94.30 406	89.98 441	97.54 441

MDA-MVSNet-bldmvs		94.96 399	93.98 406	97.92 363	98.24 425	97.27 311	99.15 345	99.33 302	93.80 420	80.09 461	99.03 386	88.31 406	97.86 440	93.49 418	94.36 401	98.62 369

Patchmatch-RL test		95.84 386	95.81 384	95.95 418	95.61 451	90.57 444	98.24 444	98.39 427	95.10 403	95.20 433	98.67 414	94.78 251	97.77 441	96.28 371	90.02 440	99.51 217

Anonymous20231206		96.22 377	96.03 378	96.79 411	97.31 440	94.14 422	99.63 97	99.08 358	96.17 378	97.04 415	99.06 383	93.94 297	97.76 442	86.96 451	95.06 388	98.47 392

SD-MVS		99.41 56	99.52 12	99.05 219	99.74 94	99.68 58	99.46 224	99.52 123	99.11 41	99.88 38	99.91 24	99.43 1	97.70 443	98.72 169	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		97.25 354	97.35 327	96.95 406	97.84 430	93.61 431	99.57 134	96.63 453	96.13 383	98.87 308	98.61 417	94.59 267	97.70 443	95.08 397	98.86 234	99.55 199

dongtai		93.26 410	92.93 414	94.25 422	99.39 258	85.68 450	97.68 453	93.27 464	92.87 430	96.85 419	99.39 326	82.33 444	97.48 445	76.78 458	97.80 299	99.58 192

pmmvs3		94.09 407	93.25 413	96.60 413	94.76 458	94.49 416	98.92 397	98.18 435	89.66 441	96.48 422	98.06 439	86.28 422	97.33 446	89.68 440	87.20 447	97.97 430

KD-MVS_self_test		95.00 398	94.34 403	96.96 405	97.07 445	95.39 396	99.56 141	99.44 239	95.11 401	97.13 413	97.32 446	91.86 353	97.27 447	90.35 438	81.23 455	98.23 412

FMVSNet5		96.43 375	96.19 374	97.15 398	99.11 333	95.89 381	99.32 287	99.52 123	94.47 416	98.34 367	99.07 381	87.54 415	97.07 448	92.61 429	95.72 372	98.47 392

new-patchmatchnet		94.48 404	94.08 405	95.67 419	95.08 456	92.41 438	99.18 340	99.28 327	94.55 415	93.49 442	97.37 445	87.86 413	97.01 449	91.57 433	88.36 444	97.61 438

LCM-MVSNet		86.80 423	85.22 427	91.53 433	87.81 465	80.96 459	98.23 446	98.99 371	71.05 458	90.13 453	96.51 450	48.45 466	96.88 450	90.51 436	85.30 449	96.76 445

CL-MVSNet_self_test		94.49 403	93.97 407	96.08 417	96.16 448	93.67 429	98.33 441	99.38 273	95.13 399	97.33 406	98.15 433	92.69 332	96.57 451	88.67 443	79.87 456	97.99 428

MIMVSNet1		95.51 391	95.04 396	96.92 408	97.38 437	95.60 386	99.52 170	99.50 162	93.65 422	96.97 417	99.17 371	85.28 430	96.56 452	88.36 445	95.55 378	98.60 381

test20.03		96.12 381	95.96 380	96.63 412	97.44 436	95.45 393	99.51 179	99.38 273	96.55 351	96.16 426	99.25 363	93.76 306	96.17 453	87.35 450	94.22 403	98.27 408

tmp_tt		82.80 425	81.52 428	86.66 441	66.61 471	68.44 470	92.79 460	97.92 437	68.96 459	80.04 462	99.85 75	85.77 424	96.15 454	97.86 266	43.89 464	95.39 454

test_fmvs3		92.10 414	91.77 417	93.08 428	96.19 447	86.25 448	99.82 16	98.62 422	96.65 340	95.19 434	96.90 448	55.05 463	95.93 455	96.63 362	90.92 437	97.06 444

kuosan		90.92 418	90.11 423	93.34 426	98.78 389	85.59 451	98.15 448	93.16 466	89.37 444	92.07 447	98.38 425	81.48 447	95.19 456	62.54 465	97.04 341	99.25 268

dmvs_testset		95.02 397	96.12 375	91.72 432	99.10 336	80.43 460	99.58 126	97.87 439	97.47 268	95.22 432	98.82 406	93.99 295	95.18 457	88.09 446	94.91 393	99.56 198

PMMVS2		86.87 422	85.37 426	91.35 434	90.21 463	83.80 453	98.89 400	97.45 446	83.13 455	91.67 452	95.03 452	48.49 465	94.70 458	85.86 455	77.62 457	95.54 453

PMVS	70.75 22	75.98 431	74.97 432	79.01 447	70.98 470	55.18 472	93.37 459	98.21 433	65.08 464	61.78 465	93.83 455	21.74 472	92.53 459	78.59 457	91.12 435	89.34 460
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 424	85.65 425	82.75 445	86.77 466	63.39 471	98.35 438	98.92 380	74.11 457	83.39 456	98.98 394	50.85 464	92.40 460	84.54 456	94.97 390	92.46 455

WB-MVS		93.10 411	94.10 404	90.12 437	95.51 455	81.88 457	99.73 51	99.27 330	95.05 404	93.09 444	98.91 403	94.70 260	91.89 461	76.62 459	94.02 409	96.58 447

SSC-MVS		92.73 413	93.73 408	89.72 438	95.02 457	81.38 458	99.76 37	99.23 337	94.87 408	92.80 445	98.93 399	94.71 259	91.37 462	74.49 461	93.80 411	96.42 448

MVE	76.82 21	76.91 430	74.31 434	84.70 442	85.38 468	76.05 466	96.88 456	93.17 465	67.39 461	71.28 463	89.01 462	21.66 473	87.69 463	71.74 462	72.29 460	90.35 459
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 427	79.88 429	82.81 444	90.75 462	76.38 465	97.69 452	95.76 457	66.44 462	83.52 455	92.25 457	62.54 458	87.16 464	68.53 463	61.40 461	84.89 462

EMVS		80.02 428	79.22 430	82.43 446	91.19 461	76.40 464	97.55 455	92.49 469	66.36 463	83.01 457	91.27 459	64.63 457	85.79 465	65.82 464	60.65 462	85.08 461

ANet_high		77.30 429	74.86 433	84.62 443	75.88 469	77.61 463	97.63 454	93.15 467	88.81 446	64.27 464	89.29 461	36.51 468	83.93 466	75.89 460	52.31 463	92.33 457

wuyk23d		40.18 432	41.29 437	36.84 448	86.18 467	49.12 473	79.73 461	22.81 473	27.64 465	25.46 468	28.45 468	21.98 471	48.89 467	55.80 466	23.56 467	12.51 465

test123		39.01 434	42.50 436	28.53 449	39.17 472	20.91 474	98.75 414	19.17 474	19.83 467	38.57 466	66.67 464	33.16 469	15.42 468	37.50 468	29.66 466	49.26 463

testmvs		39.17 433	43.78 435	25.37 450	36.04 473	16.84 475	98.36 437	26.56 472	20.06 466	38.51 467	67.32 463	29.64 470	15.30 469	37.59 467	39.90 465	43.98 464

mmdepth		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

monomultidepth		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

test_blank		0.13 438	0.17 441	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	1.57 469	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

uanet_test		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

DCPMVS		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

cdsmvs_eth3d_5k		24.64 435	32.85 438	0.00 451	0.00 474	0.00 476	0.00 462	99.51 142	0.00 469	0.00 470	99.56 268	96.58 167	0.00 470	0.00 469	0.00 468	0.00 466

pcd_1.5k_mvsjas		8.27 437	11.03 440	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	99.01 18	0.00 470	0.00 469	0.00 468	0.00 466

sosnet-low-res		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

sosnet		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

uncertanet		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

Regformer		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

ab-mvs-re		8.30 436	11.06 439	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	99.58 260	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

uanet		0.02 439	0.03 442	0.00 451	0.00 474	0.00 476	0.00 462	0.00 475	0.00 469	0.00 470	0.27 470	0.00 474	0.00 470	0.00 469	0.00 468	0.00 466

WAC-MVS						97.16 317								95.47 388

FOURS1					99.91 1	99.93 1	99.87 8	99.56 86	99.10 42	99.81 63

test_one_0601					99.81 52	99.88 9		99.49 174	98.97 69	99.65 124	99.81 119	99.09 14

eth-test2					0.00 474

eth-test					0.00 474

RE-MVS-def			99.34 47		99.76 76	99.82 26	99.63 97	99.52 123	98.38 131	99.76 85	99.82 104	98.75 58		98.61 186	99.81 114	99.77 95

IU-MVS					99.84 35	99.88 9		99.32 312	98.30 142	99.84 51				98.86 149	99.85 88	99.89 27

save fliter					99.76 76	99.59 82	99.14 347	99.40 262	99.00 61

test0726					99.85 28	99.89 5	99.62 102	99.50 162	99.10 42	99.86 48	99.82 104	98.94 32

GSMVS																99.52 208

test_part2					99.81 52	99.83 20				99.77 79

sam_mvs1												94.86 246				99.52 208

sam_mvs												94.72 258

MTGPA								99.47 208

MTMP							99.54 160	98.88 390

test9_res														97.49 307	99.72 142	99.75 104

agg_prior2														97.21 325	99.73 141	99.75 104

test_prior4						99.56 88	98.99 383

test_prior2							98.96 390		98.34 137	99.01 282	99.52 284	98.68 67		97.96 258	99.74 139

新几何2							99.01 380

旧先验1					99.74 94	99.59 82		99.54 103			99.69 210	98.47 83			99.68 150	99.73 117

原ACMM2							98.95 393

test222					99.75 86	99.49 103	98.91 399	99.49 174	96.42 362	99.34 212	99.65 230	98.28 97			99.69 147	99.72 126

segment_acmp												98.96 25

testdata1							98.85 404		98.32 140

plane_prior7					99.29 286	97.03 332

plane_prior6					99.27 291	96.98 336						92.71 330

plane_prior4											99.61 251

plane_prior3						97.00 334			98.69 101	99.11 262

plane_prior2							99.39 262		98.97 69

plane_prior1					99.26 294

plane_prior						96.97 337	99.21 333		98.45 124						97.60 308

n2								0.00 475

nn								0.00 475

door-mid								98.05 436

test11								99.35 289

door								97.92 437

HQP5-MVS						96.83 348

HQP-NCC					99.19 312		98.98 386		98.24 155	98.66 337

ACMP_Plane					99.19 312		98.98 386		98.24 155	98.66 337

BP-MVS														97.19 329

HQP3-MVS								99.39 265							97.58 310

HQP2-MVS												92.47 339

NP-MVS					99.23 302	96.92 344					99.40 322

MDTV_nov1_ep13_2view						95.18 402	99.35 279		96.84 329	99.58 147		95.19 232		97.82 271		99.46 236

ACMMP++_ref															97.19 338

ACMMP++															97.43 328

Test By Simon												98.75 58

High-resolution multi-view benchmark