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 67	99.38 250	99.37 116	99.58 126	99.62 46	99.41 18	99.87 43	99.92 17	98.81 47	100.00 1	99.97 1	99.93 30	99.94 15

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 64	99.84 34	99.44 109	99.58 126	99.69 18	99.43 14	99.98 11	99.91 24	98.62 73	100.00 1	99.97 1	99.95 20	99.90 23

test_vis1_n_1920		98.63 192	98.40 200	99.31 174	99.86 22	97.94 276	99.67 71	99.62 46	99.43 14	99.99 2	99.91 24	87.29 406	100.00 1	99.92 21	99.92 36	99.98 2

NormalMVS		99.27 83	99.19 83	99.52 132	99.89 8	98.83 203	99.65 84	99.52 118	99.10 41	99.84 50	99.76 162	95.80 196	99.99 4	99.30 81	99.84 95	99.74 104

SymmetryMVS		99.15 105	99.02 113	99.52 132	99.72 104	98.83 203	99.65 84	99.34 284	99.10 41	99.84 50	99.76 162	95.80 196	99.99 4	99.30 81	98.72 236	99.73 113

fmvsm_s_conf0.5_n_5		99.37 63	99.21 79	99.86 29	99.80 57	99.68 57	99.42 240	99.61 55	99.37 21	99.97 22	99.86 64	94.96 230	99.99 4	99.97 1	99.93 30	99.92 21

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 34	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 1	99.95 20	99.95 11

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 37	99.86 22	99.61 78	99.56 141	99.63 42	99.48 3	99.98 11	99.83 90	98.75 58	99.99 4	99.97 1	99.96 15	99.94 15

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 37	99.84 34	99.63 75	99.56 141	99.63 42	99.47 4	99.98 11	99.82 99	98.75 58	99.99 4	99.97 1	99.97 8	99.94 15

test_fmvsmconf_n		99.70 3	99.64 4	99.87 18	99.80 57	99.66 64	99.48 207	99.64 38	99.45 11	99.92 27	99.92 17	98.62 73	99.99 4	99.96 11	99.99 1	99.96 7

patch_mono-2		99.26 86	99.62 5	98.16 333	99.81 51	94.59 405	99.52 170	99.64 38	99.33 23	99.73 89	99.90 31	99.00 22	99.99 4	99.69 32	99.98 4	99.89 26

h-mvs33		97.70 306	97.28 329	98.97 222	99.70 115	97.27 304	99.36 269	99.45 221	98.94 71	99.66 112	99.64 226	94.93 233	99.99 4	99.48 59	84.36 440	99.65 150

xiu_mvs_v1_base_debu		99.29 79	99.27 69	99.34 167	99.63 151	98.97 175	99.12 342	99.51 136	98.86 77	99.84 50	99.47 293	98.18 101	99.99 4	99.50 54	99.31 184	99.08 272

xiu_mvs_v1_base		99.29 79	99.27 69	99.34 167	99.63 151	98.97 175	99.12 342	99.51 136	98.86 77	99.84 50	99.47 293	98.18 101	99.99 4	99.50 54	99.31 184	99.08 272

xiu_mvs_v1_base_debi		99.29 79	99.27 69	99.34 167	99.63 151	98.97 175	99.12 342	99.51 136	98.86 77	99.84 50	99.47 293	98.18 101	99.99 4	99.50 54	99.31 184	99.08 272

EPNet		98.86 160	98.71 164	99.30 179	97.20 432	98.18 256	99.62 102	98.91 375	99.28 26	98.63 336	99.81 113	95.96 185	99.99 4	99.24 90	99.72 141	99.73 113
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 20	99.42 28	99.89 8	99.83 43	99.74 48	99.51 179	99.62 46	99.46 7	99.99 2	99.90 31	96.60 159	99.98 17	99.95 13	99.95 20	99.96 7

MM		99.40 59	99.28 65	99.74 73	99.67 127	99.31 128	99.52 170	98.87 382	99.55 1	99.74 87	99.80 127	96.47 166	99.98 17	99.97 1	99.97 8	99.94 15

test_cas_vis1_n_1920		99.16 101	99.01 118	99.61 102	99.81 51	98.86 198	99.65 84	99.64 38	99.39 19	99.97 22	99.94 6	93.20 307	99.98 17	99.55 47	99.91 43	99.99 1

test_vis1_n		97.92 264	97.44 305	99.34 167	99.53 192	98.08 263	99.74 47	99.49 168	99.15 31	100.00 1	99.94 6	79.51 441	99.98 17	99.88 23	99.76 133	99.97 4

xiu_mvs_v2_base		99.26 86	99.25 73	99.29 182	99.53 192	98.91 191	99.02 365	99.45 221	98.80 87	99.71 96	99.26 352	98.94 32	99.98 17	99.34 74	99.23 191	98.98 286

PS-MVSNAJ		99.32 74	99.32 50	99.30 179	99.57 177	98.94 186	98.97 379	99.46 210	98.92 74	99.71 96	99.24 354	99.01 18	99.98 17	99.35 69	99.66 152	98.97 287

QAPM		98.67 187	98.30 207	99.80 58	99.20 299	99.67 61	99.77 34	99.72 11	94.74 401	98.73 316	99.90 31	95.78 198	99.98 17	96.96 333	99.88 69	99.76 99

3Dnovator	97.25 9	99.24 91	99.05 102	99.81 54	99.12 321	99.66 64	99.84 12	99.74 10	99.09 48	98.92 289	99.90 31	95.94 188	99.98 17	98.95 122	99.92 36	99.79 86

OpenMVS	96.50 16	98.47 198	98.12 219	99.52 132	99.04 340	99.53 94	99.82 16	99.72 11	94.56 404	98.08 371	99.88 46	94.73 249	99.98 17	97.47 300	99.76 133	99.06 278

fmvsm_s_conf0.5_n_3		99.37 63	99.20 81	99.87 18	99.75 85	99.70 54	99.48 207	99.66 28	99.45 11	99.99 2	99.93 10	94.64 258	99.97 26	99.94 18	99.97 8	99.95 11

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 63	99.88 9	99.56 141	99.55 91	99.15 31	99.90 31	99.90 31	99.00 22	99.97 26	99.11 103	99.91 43	99.86 39

test_fmvsmconf0.1_n		99.55 19	99.45 26	99.86 29	99.44 232	99.65 68	99.50 188	99.61 55	99.45 11	99.87 43	99.92 17	97.31 127	99.97 26	99.95 13	99.99 1	99.97 4

test_fmvs1_n		98.41 204	98.14 216	99.21 195	99.82 47	97.71 289	99.74 47	99.49 168	99.32 24	99.99 2	99.95 3	85.32 419	99.97 26	99.82 26	99.84 95	99.96 7

CANet_DTU		98.97 148	98.87 145	99.25 189	99.33 263	98.42 248	99.08 351	99.30 311	99.16 30	99.43 174	99.75 167	95.27 218	99.97 26	98.56 189	99.95 20	99.36 244

MVS_0304		99.15 105	98.96 128	99.73 76	98.92 358	99.37 116	99.37 264	96.92 438	99.51 2	99.66 112	99.78 149	96.69 156	99.97 26	99.84 25	99.97 8	99.84 50

MTAPA		99.52 24	99.39 36	99.89 8	99.90 4	99.86 17	99.66 78	99.47 201	98.79 88	99.68 102	99.81 113	98.43 86	99.97 26	98.88 132	99.90 54	99.83 60

PGM-MVS		99.45 42	99.31 56	99.86 29	99.87 17	99.78 41	99.58 126	99.65 35	97.84 214	99.71 96	99.80 127	99.12 13	99.97 26	98.33 214	99.87 72	99.83 60

mPP-MVS		99.44 46	99.30 58	99.86 29	99.88 13	99.79 35	99.69 62	99.48 180	98.12 171	99.50 159	99.75 167	98.78 51	99.97 26	98.57 186	99.89 65	99.83 60

CP-MVS		99.45 42	99.32 50	99.85 37	99.83 43	99.75 45	99.69 62	99.52 118	98.07 181	99.53 154	99.63 232	98.93 36	99.97 26	98.74 157	99.91 43	99.83 60

SteuartSystems-ACMMP		99.54 20	99.42 28	99.87 18	99.82 47	99.81 30	99.59 116	99.51 136	98.62 105	99.79 68	99.83 90	99.28 4	99.97 26	98.48 196	99.90 54	99.84 50
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 97	98.97 124	99.82 51	99.17 313	99.68 57	99.81 20	99.51 136	99.20 28	98.72 317	99.89 37	95.68 202	99.97 26	98.86 140	99.86 80	99.81 73

fmvsm_s_conf0.5_n_9		99.41 55	99.28 65	99.81 54	99.84 34	99.52 98	99.48 207	99.62 46	99.46 7	99.99 2	99.92 17	95.24 222	99.96 38	99.97 1	99.97 8	99.96 7

lecture		99.60 12	99.50 17	99.89 8	99.89 8	99.90 2	99.75 42	99.59 68	99.06 54	99.88 37	99.85 71	98.41 90	99.96 38	99.28 84	99.84 95	99.83 60

KinetiMVS		99.12 118	98.92 133	99.70 80	99.67 127	99.40 114	99.67 71	99.63 42	98.73 95	99.94 25	99.81 113	94.54 264	99.96 38	98.40 205	99.93 30	99.74 104

fmvsm_s_conf0.5_n_7		99.34 70	99.29 62	99.48 143	99.70 115	98.63 222	99.42 240	99.63 42	99.46 7	99.98 11	99.88 46	95.59 205	99.96 38	99.97 1	99.98 4	99.85 43

fmvsm_s_conf0.5_n_2		99.32 74	99.13 89	99.89 8	99.80 57	99.77 42	99.44 228	99.58 73	99.47 4	99.99 2	99.93 10	94.04 283	99.96 38	99.96 11	99.93 30	99.93 20

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 75	99.88 9	99.52 170	99.54 100	99.13 34	99.89 34	99.89 37	98.96 25	99.96 38	99.04 111	99.90 54	99.85 43

our_new_method		99.61 8	99.52 12	99.90 5	99.76 75	99.88 9	99.52 170	99.54 100	99.13 34	99.89 34	99.89 37	98.96 25	99.96 38	99.04 111	99.90 54	99.85 43

fmvsm_s_conf0.5_n_a		99.56 18	99.47 22	99.85 37	99.83 43	99.64 74	99.52 170	99.65 35	99.10 41	99.98 11	99.92 17	97.35 126	99.96 38	99.94 18	99.92 36	99.95 11

fmvsm_s_conf0.5_n		99.51 25	99.40 34	99.85 37	99.84 34	99.65 68	99.51 179	99.67 23	99.13 34	99.98 11	99.92 17	96.60 159	99.96 38	99.95 13	99.96 15	99.95 11

mvsany_test1		99.50 27	99.46 25	99.62 101	99.61 163	99.09 158	98.94 385	99.48 180	99.10 41	99.96 24	99.91 24	98.85 42	99.96 38	99.72 29	99.58 162	99.82 66

test_fmvs1		98.88 154	98.79 157	99.16 200	99.69 120	97.61 293	99.55 155	99.49 168	99.32 24	99.98 11	99.91 24	91.41 355	99.96 38	99.82 26	99.92 36	99.90 23

DVP-MVS++		99.59 13	99.50 17	99.88 12	99.51 201	99.88 9	99.87 8	99.51 136	98.99 62	99.88 37	99.81 113	99.27 5	99.96 38	98.85 142	99.80 118	99.81 73

MSC_two_6792asdad				99.87 18	99.51 201	99.76 43		99.33 292					99.96 38	98.87 135	99.84 95	99.89 26

No_MVS				99.87 18	99.51 201	99.76 43		99.33 292					99.96 38	98.87 135	99.84 95	99.89 26

ZD-MVS					99.71 110	99.79 35		99.61 55	96.84 319	99.56 147	99.54 266	98.58 75	99.96 38	96.93 336	99.75 135

SED-MVS		99.61 8	99.52 12	99.88 12	99.84 34	99.90 2	99.60 109	99.48 180	99.08 49	99.91 28	99.81 113	99.20 7	99.96 38	98.91 129	99.85 87	99.79 86

test_241102_TWO								99.48 180	99.08 49	99.88 37	99.81 113	98.94 32	99.96 38	98.91 129	99.84 95	99.88 32

ZNCC-MVS		99.47 36	99.33 48	99.87 18	99.87 17	99.81 30	99.64 91	99.67 23	98.08 180	99.55 151	99.64 226	98.91 37	99.96 38	98.72 160	99.90 54	99.82 66

DVP-MVS		99.57 17	99.47 22	99.88 12	99.85 28	99.89 5	99.57 134	99.37 271	99.10 41	99.81 62	99.80 127	98.94 32	99.96 38	98.93 126	99.86 80	99.81 73
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 62	99.81 62	99.80 127	99.09 14	99.96 38	98.85 142	99.90 54	99.88 32

test_0728_SECOND				99.91 3	99.84 34	99.89 5	99.57 134	99.51 136					99.96 38	98.93 126	99.86 80	99.88 32

SR-MVS		99.43 49	99.29 62	99.86 29	99.75 85	99.83 20	99.59 116	99.62 46	98.21 155	99.73 89	99.79 142	98.68 67	99.96 38	98.44 202	99.77 130	99.79 86

DPE-MVS		99.46 38	99.32 50	99.91 3	99.78 63	99.88 9	99.36 269	99.51 136	98.73 95	99.88 37	99.84 85	98.72 64	99.96 38	98.16 229	99.87 72	99.88 32
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 51	99.29 62	99.80 58	99.62 157	99.55 89	99.50 188	99.70 15	98.79 88	99.77 77	99.96 1	97.45 121	99.96 38	98.92 128	99.90 54	99.89 26

HFP-MVS		99.49 29	99.37 40	99.86 29	99.87 17	99.80 32	99.66 78	99.67 23	98.15 162	99.68 102	99.69 200	99.06 16	99.96 38	98.69 165	99.87 72	99.84 50

region2R		99.48 33	99.35 44	99.87 18	99.88 13	99.80 32	99.65 84	99.66 28	98.13 169	99.66 112	99.68 207	98.96 25	99.96 38	98.62 174	99.87 72	99.84 50

HPM-MVS++		99.39 61	99.23 77	99.87 18	99.75 85	99.84 19	99.43 233	99.51 136	98.68 102	99.27 218	99.53 270	98.64 72	99.96 38	98.44 202	99.80 118	99.79 86

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 71	99.89 5	99.75 42	99.56 83	99.02 55	99.88 37	99.85 71	99.18 10	99.96 38	99.22 91	99.92 36	99.90 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 29	99.36 42	99.86 29	99.87 17	99.79 35	99.66 78	99.67 23	98.15 162	99.67 107	99.69 200	98.95 30	99.96 38	98.69 165	99.87 72	99.84 50

MP-MVS		99.33 72	99.15 87	99.87 18	99.88 13	99.82 26	99.66 78	99.46 210	98.09 176	99.48 163	99.74 172	98.29 96	99.96 38	97.93 250	99.87 72	99.82 66
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 124	98.90 138	99.74 73	99.80 57	99.46 107	99.59 116	99.49 168	97.03 306	99.63 128	99.69 200	97.27 130	99.96 38	97.82 261	99.84 95	99.81 73

PVSNet_Blended_VisFu		99.36 67	99.28 65	99.61 102	99.86 22	99.07 163	99.47 216	99.93 2	97.66 237	99.71 96	99.86 64	97.73 116	99.96 38	99.47 61	99.82 110	99.79 86

UGNet		98.87 157	98.69 166	99.40 159	99.22 296	98.72 214	99.44 228	99.68 20	99.24 27	99.18 243	99.42 304	92.74 317	99.96 38	99.34 74	99.94 28	99.53 197
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 74	99.32 50	99.32 173	99.85 28	98.29 251	99.71 57	99.66 28	98.11 173	99.41 181	99.80 127	98.37 93	99.96 38	98.99 117	99.96 15	99.72 122

ACMMP		99.45 42	99.32 50	99.82 51	99.89 8	99.67 61	99.62 102	99.69 18	98.12 171	99.63 128	99.84 85	98.73 63	99.96 38	98.55 192	99.83 106	99.81 73
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 20	99.44 27	99.85 37	99.51 201	99.67 61	99.50 188	99.64 38	99.43 14	99.98 11	99.78 149	97.26 132	99.95 73	99.95 13	99.93 30	99.92 21

fmvsm_s_conf0.5_n_4		99.36 67	99.24 74	99.73 76	99.78 63	99.53 94	99.49 201	99.60 62	99.42 17	99.99 2	99.86 64	95.15 225	99.95 73	99.95 13	99.89 65	99.73 113

fmvsm_s_conf0.1_n_2		99.37 63	99.22 78	99.81 54	99.77 71	99.75 45	99.46 219	99.60 62	99.47 4	99.98 11	99.94 6	94.98 229	99.95 73	99.97 1	99.79 125	99.73 113

test_fmvsmconf0.01_n		99.22 94	99.03 107	99.79 61	98.42 412	99.48 104	99.55 155	99.51 136	99.39 19	99.78 73	99.93 10	94.80 241	99.95 73	99.93 20	99.95 20	99.94 15

SR-MVS-dyc-post		99.45 42	99.31 56	99.85 37	99.76 75	99.82 26	99.63 97	99.52 118	98.38 129	99.76 83	99.82 99	98.53 79	99.95 73	98.61 177	99.81 113	99.77 94

GST-MVS		99.40 59	99.24 74	99.85 37	99.86 22	99.79 35	99.60 109	99.67 23	97.97 199	99.63 128	99.68 207	98.52 80	99.95 73	98.38 207	99.86 80	99.81 73

CANet		99.25 90	99.14 88	99.59 106	99.41 240	99.16 148	99.35 274	99.57 78	98.82 82	99.51 158	99.61 241	96.46 167	99.95 73	99.59 42	99.98 4	99.65 150

MP-MVS-pluss		99.37 63	99.20 81	99.88 12	99.90 4	99.87 16	99.30 286	99.52 118	97.18 288	99.60 139	99.79 142	98.79 50	99.95 73	98.83 148	99.91 43	99.83 60
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 51	99.27 69	99.88 12	99.89 8	99.80 32	99.67 71	99.50 156	98.70 99	99.77 77	99.49 284	98.21 99	99.95 73	98.46 200	99.77 130	99.88 32
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 73	96.67 348

APD-MVS_3200maxsize		99.48 33	99.35 44	99.85 37	99.76 75	99.83 20	99.63 97	99.54 100	98.36 133	99.79 68	99.82 99	98.86 41	99.95 73	98.62 174	99.81 113	99.78 92

RPMNet		96.72 358	95.90 371	99.19 197	99.18 305	98.49 240	99.22 322	99.52 118	88.72 437	99.56 147	97.38 434	94.08 282	99.95 73	86.87 442	98.58 243	99.14 264

sss		99.17 99	99.05 102	99.53 126	99.62 157	98.97 175	99.36 269	99.62 46	97.83 215	99.67 107	99.65 220	97.37 125	99.95 73	99.19 93	99.19 194	99.68 139

MVSMamba_PlusPlus		99.46 38	99.41 33	99.64 94	99.68 125	99.50 101	99.75 42	99.50 156	98.27 143	99.87 43	99.92 17	98.09 105	99.94 86	99.65 38	99.95 20	99.47 221

fmvsm_s_conf0.1_n_a		99.26 86	99.06 100	99.85 37	99.52 198	99.62 76	99.54 160	99.62 46	98.69 100	99.99 2	99.96 1	94.47 268	99.94 86	99.88 23	99.92 36	99.98 2

fmvsm_s_conf0.1_n		99.29 79	99.10 93	99.86 29	99.70 115	99.65 68	99.53 169	99.62 46	98.74 94	99.99 2	99.95 3	94.53 266	99.94 86	99.89 22	99.96 15	99.97 4

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 54	99.91 1	99.66 64	99.63 97	99.39 255	98.91 75	99.78 73	99.85 71	99.36 2	99.94 86	98.84 145	99.88 69	99.82 66
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 152	98.75 160	99.39 163	99.46 225	98.61 226	99.76 37	99.50 156	98.06 185	99.81 62	99.88 46	93.91 290	99.94 86	99.11 103	99.27 187	99.61 167

mamv4		99.33 72	99.42 28	99.07 208	99.67 127	97.73 284	99.42 240	99.60 62	98.15 162	99.94 25	99.91 24	98.42 88	99.94 86	99.72 29	99.96 15	99.54 191

XVS		99.53 23	99.42 28	99.87 18	99.85 28	99.83 20	99.69 62	99.68 20	98.98 65	99.37 192	99.74 172	98.81 47	99.94 86	98.79 153	99.86 80	99.84 50

X-MVStestdata		96.55 361	95.45 380	99.87 18	99.85 28	99.83 20	99.69 62	99.68 20	98.98 65	99.37 192	64.01 457	98.81 47	99.94 86	98.79 153	99.86 80	99.84 50

旧先验2							98.96 380		96.70 326	99.47 164			99.94 86	98.19 225

新几何1				99.75 70	99.75 85	99.59 81		99.54 100	96.76 322	99.29 212	99.64 226	98.43 86	99.94 86	96.92 338	99.66 152	99.72 122

testdata				99.54 118	99.75 85	98.95 183		99.51 136	97.07 300	99.43 174	99.70 189	98.87 40	99.94 86	97.76 270	99.64 155	99.72 122

HPM-MVS		99.42 51	99.28 65	99.83 50	99.90 4	99.72 50	99.81 20	99.54 100	97.59 243	99.68 102	99.63 232	98.91 37	99.94 86	98.58 183	99.91 43	99.84 50
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 95	99.10 93	99.45 150	99.89 8	98.52 236	99.39 257	99.94 1	98.73 95	99.11 252	99.89 37	95.50 208	99.94 86	99.50 54	99.97 8	99.89 26

APD-MVS		99.27 83	99.08 98	99.84 49	99.75 85	99.79 35	99.50 188	99.50 156	97.16 290	99.77 77	99.82 99	98.78 51	99.94 86	97.56 291	99.86 80	99.80 82
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 33	99.42 28	99.65 88	99.72 104	99.40 114	99.05 357	99.66 28	99.14 33	99.57 146	99.80 127	98.46 84	99.94 86	99.57 45	99.84 95	99.60 170
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		99.06 134	98.88 144	99.61 102	99.62 157	99.16 148	99.37 264	99.56 83	98.04 191	99.53 154	99.62 237	96.84 149	99.94 86	98.85 142	98.49 251	99.72 122

DeepC-MVS	98.35 2	99.30 77	99.19 83	99.64 94	99.82 47	99.23 141	99.62 102	99.55 91	98.94 71	99.63 128	99.95 3	95.82 194	99.94 86	99.37 68	99.97 8	99.73 113
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 83	99.12 91	99.74 73	99.18 305	99.75 45	99.56 141	99.57 78	98.45 122	99.49 162	99.85 71	97.77 115	99.94 86	98.33 214	99.84 95	99.52 198

GDP-MVS		99.08 131	98.89 141	99.64 94	99.53 192	99.34 120	99.64 91	99.48 180	98.32 138	99.77 77	99.66 218	95.14 226	99.93 104	98.97 121	99.50 169	99.64 157

SDMVSNet		99.11 124	98.90 138	99.75 70	99.81 51	99.59 81	99.81 20	99.65 35	98.78 91	99.64 125	99.88 46	94.56 261	99.93 104	99.67 34	98.26 264	99.72 122

FE-MVS		98.48 197	98.17 212	99.40 159	99.54 191	98.96 179	99.68 68	98.81 389	95.54 385	99.62 132	99.70 189	93.82 293	99.93 104	97.35 309	99.46 171	99.32 250

SF-MVS		99.38 62	99.24 74	99.79 61	99.79 61	99.68 57	99.57 134	99.54 100	97.82 219	99.71 96	99.80 127	98.95 30	99.93 104	98.19 225	99.84 95	99.74 104

dcpmvs_2		99.23 92	99.58 7	98.16 333	99.83 43	94.68 402	99.76 37	99.52 118	99.07 51	99.98 11	99.88 46	98.56 77	99.93 104	99.67 34	99.98 4	99.87 37

Anonymous20240529		98.09 234	97.68 272	99.34 167	99.66 138	98.44 245	99.40 253	99.43 240	93.67 411	99.22 230	99.89 37	90.23 372	99.93 104	99.26 89	98.33 258	99.66 145

ACMMP_NAP		99.47 36	99.34 46	99.88 12	99.87 17	99.86 17	99.47 216	99.48 180	98.05 187	99.76 83	99.86 64	98.82 46	99.93 104	98.82 152	99.91 43	99.84 50

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 94	99.78 63	99.14 153	99.60 109	99.45 221	99.01 57	99.90 31	99.83 90	98.98 24	99.93 104	99.59 42	99.95 20	99.86 39

无先验							98.99 373	99.51 136	96.89 316				99.93 104	97.53 294		99.72 122

VDDNet		97.55 321	97.02 343	99.16 200	99.49 215	98.12 262	99.38 262	99.30 311	95.35 387	99.68 102	99.90 31	82.62 432	99.93 104	99.31 78	98.13 276	99.42 233

ab-mvs		98.86 160	98.63 176	99.54 118	99.64 148	99.19 143	99.44 228	99.54 100	97.77 223	99.30 209	99.81 113	94.20 276	99.93 104	99.17 99	98.82 230	99.49 212

F-COLMAP		99.19 95	99.04 104	99.64 94	99.78 63	99.27 136	99.42 240	99.54 100	97.29 279	99.41 181	99.59 246	98.42 88	99.93 104	98.19 225	99.69 146	99.73 113

BP-MVS1		99.12 118	98.94 132	99.65 88	99.51 201	99.30 131	99.67 71	98.92 370	98.48 118	99.84 50	99.69 200	94.96 230	99.92 116	99.62 41	99.79 125	99.71 131

Anonymous202405211		98.30 215	97.98 236	99.26 188	99.57 177	98.16 257	99.41 245	98.55 414	96.03 379	99.19 239	99.74 172	91.87 342	99.92 116	99.16 100	98.29 263	99.70 133

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 94	99.78 63	99.15 152	99.61 108	99.45 221	99.01 57	99.89 34	99.82 99	99.01 18	99.92 116	99.56 46	99.95 20	99.85 43

VDD-MVS		97.73 300	97.35 317	98.88 242	99.47 223	97.12 312	99.34 277	98.85 384	98.19 157	99.67 107	99.85 71	82.98 430	99.92 116	99.49 58	98.32 262	99.60 170

VNet		99.11 124	98.90 138	99.73 76	99.52 198	99.56 87	99.41 245	99.39 255	99.01 57	99.74 87	99.78 149	95.56 206	99.92 116	99.52 52	98.18 272	99.72 122

XVG-OURS-SEG-HR		98.69 185	98.62 181	98.89 240	99.71 110	97.74 283	99.12 342	99.54 100	98.44 125	99.42 177	99.71 185	94.20 276	99.92 116	98.54 193	98.90 224	99.00 283

mvsmamba		99.06 134	98.96 128	99.36 165	99.47 223	98.64 221	99.70 58	99.05 354	97.61 242	99.65 120	99.83 90	96.54 163	99.92 116	99.19 93	99.62 158	99.51 207

HPM-MVS_fast		99.51 25	99.40 34	99.85 37	99.91 1	99.79 35	99.76 37	99.56 83	97.72 228	99.76 83	99.75 167	99.13 12	99.92 116	99.07 109	99.92 36	99.85 43

HY-MVS	97.30 7	98.85 169	98.64 175	99.47 147	99.42 235	99.08 161	99.62 102	99.36 272	97.39 271	99.28 213	99.68 207	96.44 169	99.92 116	98.37 209	98.22 267	99.40 238

DP-MVS		99.16 101	98.95 130	99.78 64	99.77 71	99.53 94	99.41 245	99.50 156	97.03 306	99.04 269	99.88 46	97.39 122	99.92 116	98.66 169	99.90 54	99.87 37

IB-MVS	95.67 18	96.22 367	95.44 381	98.57 284	99.21 297	96.70 343	98.65 414	97.74 432	96.71 325	97.27 397	98.54 409	86.03 413	99.92 116	98.47 199	86.30 438	99.10 267
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 29	99.39 36	99.77 67	99.63 151	99.59 81	99.36 269	99.46 210	99.07 51	99.79 68	99.82 99	98.85 42	99.92 116	98.68 167	99.87 72	99.82 66
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 92	99.10 93	99.61 102	99.35 257	99.31 128	99.46 219	99.13 342	98.61 106	99.86 47	99.89 37	96.41 171	99.91 128	99.67 34	99.51 167	99.63 162

balanced_conf03		99.46 38	99.39 36	99.67 83	99.55 185	99.58 86	99.74 47	99.51 136	98.42 126	99.87 43	99.84 85	98.05 108	99.91 128	99.58 44	99.94 28	99.52 198

9.14			99.10 93		99.72 104		99.40 253	99.51 136	97.53 253	99.64 125	99.78 149	98.84 44	99.91 128	97.63 282	99.82 110

SMA-MVS		99.44 46	99.30 58	99.85 37	99.73 100	99.83 20	99.56 141	99.47 201	97.45 262	99.78 73	99.82 99	99.18 10	99.91 128	98.79 153	99.89 65	99.81 73
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					99.67 127	99.65 68	99.05 357	99.41 245	96.22 364	98.95 285	99.49 284	98.77 54	99.91 128

train_agg		99.02 140	98.77 158	99.77 67	99.67 127	99.65 68	99.05 357	99.41 245	96.28 358	98.95 285	99.49 284	98.76 55	99.91 128	97.63 282	99.72 141	99.75 100

test_8					99.67 127	99.61 78	99.03 362	99.41 245	96.28 358	98.93 288	99.48 290	98.76 55	99.91 128

agg_prior					99.67 127	99.62 76		99.40 252		98.87 298			99.91 128

原ACMM1				99.65 88	99.73 100	99.33 123		99.47 201	97.46 259	99.12 250	99.66 218	98.67 69	99.91 128	97.70 279	99.69 146	99.71 131

LFMVS		97.90 267	97.35 317	99.54 118	99.52 198	99.01 170	99.39 257	98.24 421	97.10 298	99.65 120	99.79 142	84.79 422	99.91 128	99.28 84	98.38 255	99.69 135

XVG-OURS		98.73 183	98.68 167	98.88 242	99.70 115	97.73 284	98.92 387	99.55 91	98.52 115	99.45 167	99.84 85	95.27 218	99.91 128	98.08 239	98.84 228	99.00 283

PLC	97.94 4	99.02 140	98.85 149	99.53 126	99.66 138	99.01 170	99.24 315	99.52 118	96.85 318	99.27 218	99.48 290	98.25 98	99.91 128	97.76 270	99.62 158	99.65 150
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 314	97.06 342	99.47 147	99.61 163	99.09 158	98.04 440	99.25 323	91.24 428	98.51 347	99.70 189	94.55 263	99.91 128	92.76 418	99.85 87	99.42 233
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 154	98.65 173	99.58 109	99.58 173	99.34 120	99.65 84	99.52 118	98.26 145	99.83 58	99.87 57	93.37 301	99.90 141	97.81 263	99.91 43	99.49 212

StellarMVS		98.88 154	98.65 173	99.58 109	99.58 173	99.34 120	99.65 84	99.52 118	98.26 145	99.83 58	99.87 57	93.37 301	99.90 141	97.81 263	99.91 43	99.49 212

AstraMVS		99.09 129	99.03 107	99.25 189	99.66 138	98.13 260	99.57 134	98.24 421	98.82 82	99.91 28	99.88 46	95.81 195	99.90 141	99.72 29	99.67 151	99.74 104

mmtdpeth		96.95 353	96.71 352	97.67 372	99.33 263	94.90 398	99.89 2	99.28 317	98.15 162	99.72 94	98.57 408	86.56 411	99.90 141	99.82 26	89.02 433	98.20 403

UWE-MVS		97.58 320	97.29 328	98.48 296	99.09 329	96.25 363	99.01 370	96.61 444	97.86 209	99.19 239	99.01 379	88.72 387	99.90 141	97.38 307	98.69 237	99.28 253

test_vis1_rt		95.81 377	95.65 376	96.32 406	99.67 127	91.35 433	99.49 201	96.74 442	98.25 148	95.24 421	98.10 427	74.96 442	99.90 141	99.53 50	98.85 227	97.70 427

FA-MVS(test-final)		98.75 180	98.53 192	99.41 158	99.55 185	99.05 166	99.80 25	99.01 359	96.59 340	99.58 143	99.59 246	95.39 212	99.90 141	97.78 266	99.49 170	99.28 253

MCST-MVS		99.43 49	99.30 58	99.82 51	99.79 61	99.74 48	99.29 291	99.40 252	98.79 88	99.52 156	99.62 237	98.91 37	99.90 141	98.64 171	99.75 135	99.82 66

CDPH-MVS		99.13 111	98.91 136	99.80 58	99.75 85	99.71 52	99.15 336	99.41 245	96.60 338	99.60 139	99.55 261	98.83 45	99.90 141	97.48 298	99.83 106	99.78 92

NCCC		99.34 70	99.19 83	99.79 61	99.61 163	99.65 68	99.30 286	99.48 180	98.86 77	99.21 233	99.63 232	98.72 64	99.90 141	98.25 221	99.63 157	99.80 82

114514_t		98.93 150	98.67 168	99.72 79	99.85 28	99.53 94	99.62 102	99.59 68	92.65 423	99.71 96	99.78 149	98.06 107	99.90 141	98.84 145	99.91 43	99.74 104

1112_ss		98.98 146	98.77 158	99.59 106	99.68 125	99.02 168	99.25 312	99.48 180	97.23 285	99.13 248	99.58 250	96.93 146	99.90 141	98.87 135	98.78 233	99.84 50

PHI-MVS		99.30 77	99.17 86	99.70 80	99.56 181	99.52 98	99.58 126	99.80 8	97.12 294	99.62 132	99.73 178	98.58 75	99.90 141	98.61 177	99.91 43	99.68 139

AdaColmap		99.01 144	98.80 154	99.66 84	99.56 181	99.54 91	99.18 331	99.70 15	98.18 160	99.35 199	99.63 232	96.32 173	99.90 141	97.48 298	99.77 130	99.55 189

COLMAP_ROB	97.56 6	98.86 160	98.75 160	99.17 199	99.88 13	98.53 232	99.34 277	99.59 68	97.55 249	98.70 324	99.89 37	95.83 193	99.90 141	98.10 234	99.90 54	99.08 272
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 211	98.03 231	99.31 174	99.63 151	98.56 229	99.54 160	96.75 441	97.53 253	99.73 89	99.65 220	91.25 360	99.89 156	98.62 174	99.56 163	99.48 215

tttt0517		98.42 202	98.14 216	99.28 186	99.66 138	98.38 249	99.74 47	96.85 439	97.68 234	99.79 68	99.74 172	91.39 356	99.89 156	98.83 148	99.56 163	99.57 185

test12				99.75 70	99.64 148	99.61 78		99.29 315		99.21 233		98.38 92	99.89 156		99.74 138	99.74 104

Test_1112_low_res		98.89 153	98.66 171	99.57 113	99.69 120	98.95 183	99.03 362	99.47 201	96.98 308	99.15 246	99.23 355	96.77 153	99.89 156	98.83 148	98.78 233	99.86 39

CNLPA		99.14 109	98.99 120	99.59 106	99.58 173	99.41 113	99.16 333	99.44 230	98.45 122	99.19 239	99.49 284	98.08 106	99.89 156	97.73 274	99.75 135	99.48 215

guyue		99.16 101	99.04 104	99.52 132	99.69 120	98.92 190	99.59 116	98.81 389	98.73 95	99.90 31	99.87 57	95.34 215	99.88 161	99.66 37	99.81 113	99.74 104

sd_testset		98.75 180	98.57 188	99.29 182	99.81 51	98.26 253	99.56 141	99.62 46	98.78 91	99.64 125	99.88 46	92.02 339	99.88 161	99.54 48	98.26 264	99.72 122

APD_test1		95.87 375	96.49 357	94.00 413	99.53 192	84.01 442	99.54 160	99.32 302	95.91 381	97.99 376	99.85 71	85.49 417	99.88 161	91.96 421	98.84 228	98.12 407

diffmvs		99.14 109	99.02 113	99.51 137	99.61 163	98.96 179	99.28 296	99.49 168	98.46 120	99.72 94	99.71 185	96.50 165	99.88 161	99.31 78	99.11 201	99.67 142
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 160	98.80 154	99.03 214	99.76 75	98.79 209	99.28 296	99.91 3	97.42 268	99.67 107	99.37 322	97.53 119	99.88 161	98.98 118	97.29 324	98.42 388

PVSNet_Blended		99.08 131	98.97 124	99.42 157	99.76 75	98.79 209	98.78 401	99.91 3	96.74 323	99.67 107	99.49 284	97.53 119	99.88 161	98.98 118	99.85 87	99.60 170

MVS		97.28 342	96.55 355	99.48 143	98.78 379	98.95 183	99.27 301	99.39 255	83.53 444	98.08 371	99.54 266	96.97 144	99.87 167	94.23 399	99.16 195	99.63 162

MG-MVS		99.13 111	99.02 113	99.45 150	99.57 177	98.63 222	99.07 352	99.34 284	98.99 62	99.61 136	99.82 99	97.98 110	99.87 167	97.00 329	99.80 118	99.85 43

MSDG		98.98 146	98.80 154	99.53 126	99.76 75	99.19 143	98.75 404	99.55 91	97.25 282	99.47 164	99.77 158	97.82 113	99.87 167	96.93 336	99.90 54	99.54 191

ETV-MVS		99.26 86	99.21 79	99.40 159	99.46 225	99.30 131	99.56 141	99.52 118	98.52 115	99.44 172	99.27 350	98.41 90	99.86 170	99.10 106	99.59 161	99.04 279

thisisatest0515		98.14 229	97.79 255	99.19 197	99.50 213	98.50 239	98.61 416	96.82 440	96.95 312	99.54 152	99.43 302	91.66 351	99.86 170	98.08 239	99.51 167	99.22 261

thres600view7		97.86 273	97.51 291	98.92 231	99.72 104	97.95 274	99.59 116	98.74 399	97.94 201	99.27 218	98.62 405	91.75 345	99.86 170	93.73 405	98.19 271	98.96 289

lupinMVS		99.13 111	99.01 118	99.46 149	99.51 201	98.94 186	99.05 357	99.16 338	97.86 209	99.80 66	99.56 258	97.39 122	99.86 170	98.94 123	99.85 87	99.58 182

PVSNet	96.02 17	98.85 169	98.84 151	98.89 240	99.73 100	97.28 303	98.32 432	99.60 62	97.86 209	99.50 159	99.57 255	96.75 154	99.86 170	98.56 189	99.70 145	99.54 191

MAR-MVS		98.86 160	98.63 176	99.54 118	99.37 253	99.66 64	99.45 222	99.54 100	96.61 335	99.01 272	99.40 312	97.09 137	99.86 170	97.68 281	99.53 166	99.10 267
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_0404		99.16 101	99.06 100	99.44 154	99.65 145	98.96 179	99.49 201	99.50 156	98.14 167	99.62 132	99.85 71	96.85 147	99.85 176	99.19 93	99.26 189	99.52 198

testing91		97.44 334	97.02 343	98.71 271	99.18 305	96.89 337	99.19 329	99.04 355	97.78 222	98.31 358	98.29 419	85.41 418	99.85 176	98.01 245	97.95 281	99.39 239

test2506		96.81 357	96.65 353	97.29 387	99.74 93	92.21 430	99.60 109	85.06 461	99.13 34	99.77 77	99.93 10	87.82 404	99.85 176	99.38 67	99.38 176	99.80 82

AllTest		98.87 157	98.72 162	99.31 174	99.86 22	98.48 242	99.56 141	99.61 55	97.85 212	99.36 196	99.85 71	95.95 186	99.85 176	96.66 349	99.83 106	99.59 178

TestCases				99.31 174	99.86 22	98.48 242		99.61 55	97.85 212	99.36 196	99.85 71	95.95 186	99.85 176	96.66 349	99.83 106	99.59 178

jason		99.13 111	99.03 107	99.45 150	99.46 225	98.87 195	99.12 342	99.26 321	98.03 193	99.79 68	99.65 220	97.02 142	99.85 176	99.02 115	99.90 54	99.65 150
jason: jason.
CNVR-MVS		99.42 51	99.30 58	99.78 64	99.62 157	99.71 52	99.26 310	99.52 118	98.82 82	99.39 188	99.71 185	98.96 25	99.85 176	98.59 182	99.80 118	99.77 94

PAPM_NR		99.04 137	98.84 151	99.66 84	99.74 93	99.44 109	99.39 257	99.38 263	97.70 232	99.28 213	99.28 347	98.34 94	99.85 176	96.96 333	99.45 172	99.69 135

testing99		97.36 337	96.94 346	98.63 277	99.18 305	96.70 343	99.30 286	98.93 367	97.71 229	98.23 363	98.26 420	84.92 421	99.84 184	98.04 244	97.85 288	99.35 245

testing222		97.16 347	96.50 356	99.16 200	99.16 315	98.47 244	99.27 301	98.66 410	97.71 229	98.23 363	98.15 423	82.28 435	99.84 184	97.36 308	97.66 294	99.18 263

test1111		98.04 244	98.11 220	97.83 362	99.74 93	93.82 414	99.58 126	95.40 448	99.12 39	99.65 120	99.93 10	90.73 365	99.84 184	99.43 64	99.38 176	99.82 66

ECVR-MVS		98.04 244	98.05 229	98.00 346	99.74 93	94.37 409	99.59 116	94.98 449	99.13 34	99.66 112	99.93 10	90.67 366	99.84 184	99.40 65	99.38 176	99.80 82

test_yl		98.86 160	98.63 176	99.54 118	99.49 215	99.18 145	99.50 188	99.07 351	98.22 153	99.61 136	99.51 278	95.37 213	99.84 184	98.60 180	98.33 258	99.59 178

DCV-MVSNet		98.86 160	98.63 176	99.54 118	99.49 215	99.18 145	99.50 188	99.07 351	98.22 153	99.61 136	99.51 278	95.37 213	99.84 184	98.60 180	98.33 258	99.59 178

Fast-Effi-MVS+		98.70 184	98.43 197	99.51 137	99.51 201	99.28 134	99.52 170	99.47 201	96.11 374	99.01 272	99.34 332	96.20 177	99.84 184	97.88 253	98.82 230	99.39 239

TSAR-MVS + GP.		99.36 67	99.36 42	99.36 165	99.67 127	98.61 226	99.07 352	99.33 292	99.00 60	99.82 61	99.81 113	99.06 16	99.84 184	99.09 107	99.42 174	99.65 150

tpmrst		98.33 212	98.48 195	97.90 355	99.16 315	94.78 399	99.31 284	99.11 344	97.27 280	99.45 167	99.59 246	95.33 216	99.84 184	98.48 196	98.61 240	99.09 271

Vis-MVSNet		99.12 118	98.97 124	99.56 115	99.78 63	99.10 157	99.68 68	99.66 28	98.49 117	99.86 47	99.87 57	94.77 246	99.84 184	99.19 93	99.41 175	99.74 104
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 192	98.34 203	99.51 137	99.40 245	99.03 167	98.80 399	99.36 272	96.33 355	99.00 276	99.12 369	98.46 84	99.84 184	95.23 385	99.37 183	99.66 145

PatchMatch-RL		98.84 172	98.62 181	99.52 132	99.71 110	99.28 134	99.06 355	99.77 9	97.74 227	99.50 159	99.53 270	95.41 211	99.84 184	97.17 322	99.64 155	99.44 231

EPP-MVSNet		99.13 111	98.99 120	99.53 126	99.65 145	99.06 164	99.81 20	99.33 292	97.43 266	99.60 139	99.88 46	97.14 134	99.84 184	99.13 101	98.94 216	99.69 135

mamba_test_0407		99.13 111	99.03 107	99.43 156	99.62 157	98.88 193	99.51 179	99.50 156	98.14 167	99.37 192	99.85 71	96.85 147	99.83 197	99.19 93	99.25 190	99.60 170

testing3-2		97.84 278	97.70 270	98.24 328	99.53 192	95.37 387	99.55 155	98.67 409	98.46 120	99.27 218	99.34 332	86.58 410	99.83 197	99.32 77	98.63 239	99.52 198

testing11		97.50 327	97.10 340	98.71 271	99.20 299	96.91 335	99.29 291	98.82 387	97.89 206	98.21 366	98.40 414	85.63 416	99.83 197	98.45 201	98.04 279	99.37 243

thres100view900		97.76 292	97.45 300	98.69 273	99.72 104	97.86 280	99.59 116	98.74 399	97.93 202	99.26 223	98.62 405	91.75 345	99.83 197	93.22 410	98.18 272	98.37 394

tfpn200view9		97.72 302	97.38 313	98.72 268	99.69 120	97.96 271	99.50 188	98.73 405	97.83 215	99.17 244	98.45 412	91.67 349	99.83 197	93.22 410	98.18 272	98.37 394

test_prior				99.68 82	99.67 127	99.48 104		99.56 83					99.83 197			99.74 104

1314		98.68 186	98.54 191	99.11 206	98.89 362	98.65 219	99.27 301	99.49 168	96.89 316	97.99 376	99.56 258	97.72 117	99.83 197	97.74 273	99.27 187	98.84 295

thres400		97.77 291	97.38 313	98.92 231	99.69 120	97.96 271	99.50 188	98.73 405	97.83 215	99.17 244	98.45 412	91.67 349	99.83 197	93.22 410	98.18 272	98.96 289

casdiffmvs		99.13 111	98.98 123	99.56 115	99.65 145	99.16 148	99.56 141	99.50 156	98.33 137	99.41 181	99.86 64	95.92 189	99.83 197	99.45 63	99.16 195	99.70 133
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 29	99.48 20	99.54 118	99.78 63	99.30 131	99.89 2	99.58 73	98.56 111	99.73 89	99.69 200	98.55 78	99.82 206	99.69 32	99.85 87	99.48 215

MVS_Test		99.10 128	98.97 124	99.48 143	99.49 215	99.14 153	99.67 71	99.34 284	97.31 277	99.58 143	99.76 162	97.65 118	99.82 206	98.87 135	99.07 207	99.46 226

dp		97.75 296	97.80 254	97.59 378	99.10 326	93.71 417	99.32 281	98.88 380	96.48 347	99.08 260	99.55 261	92.67 323	99.82 206	96.52 353	98.58 243	99.24 259

RPSCF		98.22 219	98.62 181	96.99 393	99.82 47	91.58 432	99.72 53	99.44 230	96.61 335	99.66 112	99.89 37	95.92 189	99.82 206	97.46 301	99.10 204	99.57 185

PMMVS		98.80 176	98.62 181	99.34 167	99.27 281	98.70 215	98.76 403	99.31 306	97.34 274	99.21 233	99.07 371	97.20 133	99.82 206	98.56 189	98.87 225	99.52 198

UBG		97.85 274	97.48 294	98.95 225	99.25 288	97.64 291	99.24 315	98.74 399	97.90 205	98.64 334	98.20 422	88.65 391	99.81 211	98.27 219	98.40 253	99.42 233

EIA-MVS		99.18 97	99.09 97	99.45 150	99.49 215	99.18 145	99.67 71	99.53 113	97.66 237	99.40 186	99.44 300	98.10 104	99.81 211	98.94 123	99.62 158	99.35 245

Effi-MVS+		98.81 173	98.59 187	99.48 143	99.46 225	99.12 156	98.08 439	99.50 156	97.50 257	99.38 190	99.41 308	96.37 172	99.81 211	99.11 103	98.54 248	99.51 207

thres200		97.61 318	97.28 329	98.62 278	99.64 148	98.03 265	99.26 310	98.74 399	97.68 234	99.09 258	98.32 418	91.66 351	99.81 211	92.88 415	98.22 267	98.03 413

tpmvs		97.98 255	98.02 233	97.84 361	99.04 340	94.73 400	99.31 284	99.20 333	96.10 378	98.76 314	99.42 304	94.94 232	99.81 211	96.97 332	98.45 252	98.97 287

casdiffmvs_mvg		99.15 105	99.02 113	99.55 117	99.66 138	99.09 158	99.64 91	99.56 83	98.26 145	99.45 167	99.87 57	96.03 183	99.81 211	99.54 48	99.15 198	99.73 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepPCF-MVS	98.18 3	98.81 173	99.37 40	97.12 391	99.60 169	91.75 431	98.61 416	99.44 230	99.35 22	99.83 58	99.85 71	98.70 66	99.81 211	99.02 115	99.91 43	99.81 73

icg_test_0403		98.86 160	98.89 141	98.78 263	99.55 185	96.93 331	99.58 126	99.44 230	98.05 187	99.68 102	99.80 127	96.81 150	99.80 218	98.15 231	98.92 219	99.60 170

DPM-MVS		98.95 149	98.71 164	99.66 84	99.63 151	99.55 89	98.64 415	99.10 345	97.93 202	99.42 177	99.55 261	98.67 69	99.80 218	95.80 370	99.68 149	99.61 167

DP-MVS Recon		99.12 118	98.95 130	99.65 88	99.74 93	99.70 54	99.27 301	99.57 78	96.40 354	99.42 177	99.68 207	98.75 58	99.80 218	97.98 247	99.72 141	99.44 231

MVS_111021_LR		99.41 55	99.33 48	99.65 88	99.77 71	99.51 100	98.94 385	99.85 6	98.82 82	99.65 120	99.74 172	98.51 81	99.80 218	98.83 148	99.89 65	99.64 157

CS-MVS		99.50 27	99.48 20	99.54 118	99.76 75	99.42 111	99.90 1	99.55 91	98.56 111	99.78 73	99.70 189	98.65 71	99.79 222	99.65 38	99.78 127	99.41 236

Fast-Effi-MVS+-dtu		98.77 179	98.83 153	98.60 279	99.41 240	96.99 326	99.52 170	99.49 168	98.11 173	99.24 225	99.34 332	96.96 145	99.79 222	97.95 249	99.45 172	99.02 282

baseline1		98.31 213	97.95 240	99.38 164	99.50 213	98.74 212	99.59 116	98.93 367	98.41 127	99.14 247	99.60 244	94.59 259	99.79 222	98.48 196	93.29 407	99.61 167

baseline		99.15 105	99.02 113	99.53 126	99.66 138	99.14 153	99.72 53	99.48 180	98.35 134	99.42 177	99.84 85	96.07 180	99.79 222	99.51 53	99.14 199	99.67 142

PVSNet_0	94.43 19	96.09 372	95.47 379	97.94 351	99.31 271	94.34 411	97.81 441	99.70 15	97.12 294	97.46 391	98.75 402	89.71 377	99.79 222	97.69 280	81.69 444	99.68 139

API-MVS		99.04 137	99.03 107	99.06 210	99.40 245	99.31 128	99.55 155	99.56 83	98.54 113	99.33 203	99.39 316	98.76 55	99.78 227	96.98 331	99.78 127	98.07 410

OMC-MVS		99.08 131	99.04 104	99.20 196	99.67 127	98.22 255	99.28 296	99.52 118	98.07 181	99.66 112	99.81 113	97.79 114	99.78 227	97.79 265	99.81 113	99.60 170

GeoE		98.85 169	98.62 181	99.53 126	99.61 163	99.08 161	99.80 25	99.51 136	97.10 298	99.31 205	99.78 149	95.23 223	99.77 229	98.21 223	99.03 210	99.75 100

alignmvs		98.81 173	98.56 190	99.58 109	99.43 233	99.42 111	99.51 179	98.96 365	98.61 106	99.35 199	98.92 392	94.78 243	99.77 229	99.35 69	98.11 277	99.54 191

tpm cat1		97.39 336	97.36 315	97.50 381	99.17 313	93.73 416	99.43 233	99.31 306	91.27 427	98.71 318	99.08 370	94.31 274	99.77 229	96.41 358	98.50 250	99.00 283

CostFormer		97.72 302	97.73 267	97.71 370	99.15 319	94.02 413	99.54 160	99.02 358	94.67 402	99.04 269	99.35 328	92.35 335	99.77 229	98.50 195	97.94 282	99.34 248

MGCFI-Net		99.01 144	98.85 149	99.50 142	99.42 235	99.26 137	99.82 16	99.48 180	98.60 108	99.28 213	98.81 397	97.04 141	99.76 233	99.29 83	97.87 286	99.47 221

test_241102_ONE					99.84 34	99.90 2		99.48 180	99.07 51	99.91 28	99.74 172	99.20 7	99.76 233

MDTV_nov1_ep13			98.32 205		99.11 323	94.44 407	99.27 301	98.74 399	97.51 256	99.40 186	99.62 237	94.78 243	99.76 233	97.59 285	98.81 232

sasdasda		99.02 140	98.86 147	99.51 137	99.42 235	99.32 124	99.80 25	99.48 180	98.63 103	99.31 205	98.81 397	97.09 137	99.75 236	99.27 87	97.90 283	99.47 221

canonicalmvs		99.02 140	98.86 147	99.51 137	99.42 235	99.32 124	99.80 25	99.48 180	98.63 103	99.31 205	98.81 397	97.09 137	99.75 236	99.27 87	97.90 283	99.47 221

Effi-MVS+-dtu		98.78 177	98.89 141	98.47 301	99.33 263	96.91 335	99.57 134	99.30 311	98.47 119	99.41 181	98.99 382	96.78 152	99.74 238	98.73 159	99.38 176	98.74 311

patchmatchnet-post											98.70 403	94.79 242	99.74 238

SCA		98.19 223	98.16 213	98.27 327	99.30 272	95.55 378	99.07 352	98.97 363	97.57 246	99.43 174	99.57 255	92.72 318	99.74 238	97.58 286	99.20 193	99.52 198

BH-untuned		98.42 202	98.36 201	98.59 280	99.49 215	96.70 343	99.27 301	99.13 342	97.24 284	98.80 309	99.38 319	95.75 199	99.74 238	97.07 327	99.16 195	99.33 249

BH-RMVSNet		98.41 204	98.08 225	99.40 159	99.41 240	98.83 203	99.30 286	98.77 395	97.70 232	98.94 287	99.65 220	92.91 313	99.74 238	96.52 353	99.55 165	99.64 157

MVS_111021_HR		99.41 55	99.32 50	99.66 84	99.72 104	99.47 106	98.95 383	99.85 6	98.82 82	99.54 152	99.73 178	98.51 81	99.74 238	98.91 129	99.88 69	99.77 94

test_post											65.99 455	94.65 257	99.73 244

XVG-ACMP-BASELINE		97.83 281	97.71 269	98.20 330	99.11 323	96.33 359	99.41 245	99.52 118	98.06 185	99.05 268	99.50 281	89.64 379	99.73 244	97.73 274	97.38 321	98.53 376

HyFIR lowres test		99.11 124	98.92 133	99.65 88	99.90 4	99.37 116	99.02 365	99.91 3	97.67 236	99.59 142	99.75 167	95.90 191	99.73 244	99.53 50	99.02 212	99.86 39

DeepMVS_CX				93.34 416	99.29 276	82.27 445		99.22 329	85.15 442	96.33 413	99.05 374	90.97 363	99.73 244	93.57 407	97.77 291	98.01 414

Patchmatch-test		97.93 261	97.65 275	98.77 264	99.18 305	97.07 317	99.03 362	99.14 341	96.16 369	98.74 315	99.57 255	94.56 261	99.72 248	93.36 409	99.11 201	99.52 198

LPG-MVS_test		98.22 219	98.13 218	98.49 294	99.33 263	97.05 319	99.58 126	99.55 91	97.46 259	99.24 225	99.83 90	92.58 325	99.72 248	98.09 235	97.51 307	98.68 329

LGP-MVS_train				98.49 294	99.33 263	97.05 319		99.55 91	97.46 259	99.24 225	99.83 90	92.58 325	99.72 248	98.09 235	97.51 307	98.68 329

BH-w/o		98.00 253	97.89 249	98.32 319	99.35 257	96.20 365	99.01 370	98.90 377	96.42 352	98.38 354	99.00 380	95.26 220	99.72 248	96.06 363	98.61 240	99.03 280

ACMP	97.20 11	98.06 238	97.94 242	98.45 304	99.37 253	97.01 324	99.44 228	99.49 168	97.54 252	98.45 351	99.79 142	91.95 341	99.72 248	97.91 251	97.49 312	98.62 359
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 248	97.90 245	98.40 312	99.23 292	96.80 341	99.70 58	99.60 62	97.12 294	98.18 368	99.70 189	91.73 347	99.72 248	98.39 206	97.45 314	98.68 329
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							99.23 318				65.14 456	94.18 279	99.71 254	97.58 286

ADS-MVSNet		98.20 222	98.08 225	98.56 287	99.33 263	96.48 354	99.23 318	99.15 339	96.24 362	99.10 255	99.67 213	94.11 280	99.71 254	96.81 341	99.05 208	99.48 215

JIA-IIPM		97.50 327	97.02 343	98.93 229	98.73 388	97.80 282	99.30 286	98.97 363	91.73 426	98.91 290	94.86 444	95.10 227	99.71 254	97.58 286	97.98 280	99.28 253

EPMVS		97.82 284	97.65 275	98.35 316	98.88 363	95.98 369	99.49 201	94.71 451	97.57 246	99.26 223	99.48 290	92.46 332	99.71 254	97.87 255	99.08 206	99.35 245

TDRefinement		95.42 383	94.57 391	97.97 348	89.83 454	96.11 368	99.48 207	98.75 396	96.74 323	96.68 410	99.88 46	88.65 391	99.71 254	98.37 209	82.74 443	98.09 409

ACMM	97.58 5	98.37 210	98.34 203	98.48 296	99.41 240	97.10 313	99.56 141	99.45 221	98.53 114	99.04 269	99.85 71	93.00 309	99.71 254	98.74 157	97.45 314	98.64 350
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 258	97.77 260	98.57 284	99.59 171	96.61 350	99.45 222	99.08 348	98.21 155	98.88 295	99.80 127	88.66 390	99.70 260	98.58 183	97.72 292	99.39 239

CHOSEN 280x420		99.12 118	99.13 89	99.08 207	99.66 138	97.89 277	98.43 426	99.71 13	98.88 76	99.62 132	99.76 162	96.63 158	99.70 260	99.46 62	99.99 1	99.66 145

EC-MVSNet		99.44 46	99.39 36	99.58 109	99.56 181	99.49 102	99.88 4	99.58 73	98.38 129	99.73 89	99.69 200	98.20 100	99.70 260	99.64 40	99.82 110	99.54 191

PatchmatchNet		98.31 213	98.36 201	98.19 331	99.16 315	95.32 388	99.27 301	98.92 370	97.37 272	99.37 192	99.58 250	94.90 236	99.70 260	97.43 304	99.21 192	99.54 191
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 233	97.99 235	98.44 307	99.41 240	96.96 330	99.60 109	99.56 83	98.09 176	98.15 369	99.91 24	90.87 364	99.70 260	98.88 132	97.45 314	98.67 337
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 327	96.90 347	99.29 182	99.23 292	98.78 211	99.32 281	98.90 377	97.52 255	98.56 344	98.09 428	84.72 423	99.69 265	97.86 256	97.88 285	99.39 239

HQP_MVS		98.27 218	98.22 211	98.44 307	99.29 276	96.97 328	99.39 257	99.47 201	98.97 68	99.11 252	99.61 241	92.71 320	99.69 265	97.78 266	97.63 295	98.67 337

plane_prior5								99.47 201					99.69 265	97.78 266	97.63 295	98.67 337

D2MVS		98.41 204	98.50 194	98.15 336	99.26 284	96.62 349	99.40 253	99.61 55	97.71 229	98.98 279	99.36 325	96.04 182	99.67 268	98.70 162	97.41 319	98.15 406

IS-MVSNet		99.05 136	98.87 145	99.57 113	99.73 100	99.32 124	99.75 42	99.20 333	98.02 196	99.56 147	99.86 64	96.54 163	99.67 268	98.09 235	99.13 200	99.73 113

CLD-MVS		98.16 227	98.10 221	98.33 317	99.29 276	96.82 340	98.75 404	99.44 230	97.83 215	99.13 248	99.55 261	92.92 311	99.67 268	98.32 216	97.69 293	98.48 380
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 344	97.30 326	97.09 392	99.43 233	93.31 423	99.73 51	98.87 382	98.83 81	99.28 213	99.80 127	84.45 424	99.66 271	97.88 253	97.45 314	98.30 396

AUN-MVS		96.88 355	96.31 361	98.59 280	99.48 222	97.04 322	99.27 301	99.22 329	97.44 265	98.51 347	99.41 308	91.97 340	99.66 271	97.71 277	83.83 441	99.07 277

UniMVSNet_ETH3D		97.32 341	96.81 349	98.87 246	99.40 245	97.46 297	99.51 179	99.53 113	95.86 382	98.54 346	99.77 158	82.44 433	99.66 271	98.68 167	97.52 306	99.50 211

OPM-MVS		98.19 223	98.10 221	98.45 304	98.88 363	97.07 317	99.28 296	99.38 263	98.57 110	99.22 230	99.81 113	92.12 337	99.66 271	98.08 239	97.54 304	98.61 368
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 264	97.78 258	98.32 319	99.46 225	96.68 347	99.56 141	99.54 100	98.41 127	97.79 387	99.87 57	90.18 373	99.66 271	98.05 243	97.18 329	98.62 359

icg_test_0407		98.86 160	98.91 136	98.72 268	99.55 185	96.93 331	99.50 188	99.44 230	98.05 187	99.66 112	99.80 127	97.13 135	99.65 276	98.15 231	98.92 219	99.60 170

hse-mvs2		97.50 327	97.14 337	98.59 280	99.49 215	97.05 319	99.28 296	99.22 329	98.94 71	99.66 112	99.42 304	94.93 233	99.65 276	99.48 59	83.80 442	99.08 272

VPA-MVSNet		98.29 216	97.95 240	99.30 179	99.16 315	99.54 91	99.50 188	99.58 73	98.27 143	99.35 199	99.37 322	92.53 327	99.65 276	99.35 69	94.46 388	98.72 313

TR-MVS		97.76 292	97.41 311	98.82 255	99.06 335	97.87 278	98.87 393	98.56 413	96.63 334	98.68 326	99.22 356	92.49 328	99.65 276	95.40 381	97.79 290	98.95 291

reproduce_monomvs		97.89 268	97.87 250	97.96 350	99.51 201	95.45 383	99.60 109	99.25 323	99.17 29	98.85 303	99.49 284	89.29 382	99.64 280	99.35 69	96.31 345	98.78 299

gm-plane-assit					98.54 408	92.96 425			94.65 403		99.15 364		99.64 280	97.56 291

HQP4-MVS										98.66 327			99.64 280			98.64 350

HQP-MVS		98.02 248	97.90 245	98.37 315	99.19 302	96.83 338	98.98 376	99.39 255	98.24 149	98.66 327	99.40 312	92.47 329	99.64 280	97.19 319	97.58 300	98.64 350

PAPM		97.59 319	97.09 341	99.07 208	99.06 335	98.26 253	98.30 433	99.10 345	94.88 397	98.08 371	99.34 332	96.27 175	99.64 280	89.87 429	98.92 219	99.31 251

TAPA-MVS	97.07 15	97.74 298	97.34 320	98.94 227	99.70 115	97.53 294	99.25 312	99.51 136	91.90 425	99.30 209	99.63 232	98.78 51	99.64 280	88.09 436	99.87 72	99.65 150
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 208	98.09 224	99.24 192	99.26 284	99.32 124	99.56 141	99.55 91	97.45 262	98.71 318	99.83 90	93.23 304	99.63 286	98.88 132	96.32 344	98.76 305

ITE_SJBPF				98.08 339	99.29 276	96.37 357		98.92 370	98.34 135	98.83 304	99.75 167	91.09 361	99.62 287	95.82 368	97.40 320	98.25 400

LF4IMVS		97.52 324	97.46 299	97.70 371	98.98 351	95.55 378	99.29 291	98.82 387	98.07 181	98.66 327	99.64 226	89.97 374	99.61 288	97.01 328	96.68 334	97.94 421

tpm		97.67 313	97.55 284	98.03 341	99.02 342	95.01 395	99.43 233	98.54 415	96.44 350	99.12 250	99.34 332	91.83 344	99.60 289	97.75 272	96.46 340	99.48 215

tpm2		97.44 334	97.34 320	97.74 369	99.15 319	94.36 410	99.45 222	98.94 366	93.45 416	98.90 292	99.44 300	91.35 357	99.59 290	97.31 310	98.07 278	99.29 252

SD_0403		97.55 321	97.53 288	97.62 374	99.61 163	93.64 420	99.72 53	99.44 230	98.03 193	98.62 339	99.39 316	96.06 181	99.57 291	87.88 438	99.01 213	99.66 145

baseline2		97.87 271	97.55 284	98.82 255	99.18 305	98.02 266	99.41 245	96.58 445	96.97 309	96.51 411	99.17 361	93.43 299	99.57 291	97.71 277	99.03 210	98.86 293

MS-PatchMatch		97.24 346	97.32 324	96.99 393	98.45 411	93.51 422	98.82 397	99.32 302	97.41 269	98.13 370	99.30 343	88.99 384	99.56 293	95.68 374	99.80 118	97.90 424

TinyColmap		97.12 349	96.89 348	97.83 362	99.07 333	95.52 381	98.57 419	98.74 399	97.58 245	97.81 386	99.79 142	88.16 398	99.56 293	95.10 386	97.21 327	98.39 392

USDC		97.34 339	97.20 334	97.75 367	99.07 333	95.20 390	98.51 423	99.04 355	97.99 197	98.31 358	99.86 64	89.02 383	99.55 295	95.67 375	97.36 322	98.49 379

MSLP-MVS++		99.46 38	99.47 22	99.44 154	99.60 169	99.16 148	99.41 245	99.71 13	98.98 65	99.45 167	99.78 149	99.19 9	99.54 296	99.28 84	99.84 95	99.63 162

UWE-MVS-28		97.36 337	97.24 333	97.75 367	98.84 372	94.44 407	99.24 315	97.58 434	97.98 198	99.00 276	99.00 380	91.35 357	99.53 297	93.75 404	98.39 254	99.27 257

TAMVS		99.12 118	99.08 98	99.24 192	99.46 225	98.55 230	99.51 179	99.46 210	98.09 176	99.45 167	99.82 99	98.34 94	99.51 298	98.70 162	98.93 217	99.67 142

EPNet_dtu		98.03 246	97.96 238	98.23 329	98.27 414	95.54 380	99.23 318	98.75 396	99.02 55	97.82 385	99.71 185	96.11 179	99.48 299	93.04 413	99.65 154	99.69 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 359	96.22 363	97.97 348	97.00 436	96.28 361	98.66 413	99.03 357	96.61 335	96.93 408	99.79 142	87.20 407	99.47 300	96.65 351	94.13 395	98.16 405

EG-PatchMatch MVS		95.97 374	95.69 375	96.81 400	97.78 421	92.79 426	99.16 333	98.93 367	96.16 369	94.08 429	99.22 356	82.72 431	99.47 300	95.67 375	97.50 309	98.17 404

myMVS_eth3d28		97.69 307	97.34 320	98.73 266	99.27 281	97.52 295	99.33 279	98.78 394	98.03 193	98.82 306	98.49 410	86.64 409	99.46 302	98.44 202	98.24 266	99.23 260

MVP-Stereo		97.81 286	97.75 265	97.99 347	97.53 425	96.60 351	98.96 380	98.85 384	97.22 286	97.23 398	99.36 325	95.28 217	99.46 302	95.51 377	99.78 127	97.92 423
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 194	98.67 168	98.30 321	99.35 257	95.59 377	99.50 188	99.55 91	98.60 108	99.39 188	99.83 90	94.48 267	99.45 304	98.75 156	98.56 246	99.85 43

test-LLR		98.06 238	97.90 245	98.55 289	98.79 376	97.10 313	98.67 410	97.75 430	97.34 274	98.61 340	98.85 394	94.45 269	99.45 304	97.25 313	99.38 176	99.10 267

TESTMET0.1,1		97.55 321	97.27 332	98.40 312	98.93 356	96.53 352	98.67 410	97.61 433	96.96 310	98.64 334	99.28 347	88.63 393	99.45 304	97.30 311	99.38 176	99.21 262

test-mter		97.49 332	97.13 339	98.55 289	98.79 376	97.10 313	98.67 410	97.75 430	96.65 330	98.61 340	98.85 394	88.23 397	99.45 304	97.25 313	99.38 176	99.10 267

mvs_anonymous		99.03 139	98.99 120	99.16 200	99.38 250	98.52 236	99.51 179	99.38 263	97.79 220	99.38 190	99.81 113	97.30 128	99.45 304	99.35 69	98.99 214	99.51 207

tfpnnormal		97.84 278	97.47 297	98.98 220	99.20 299	99.22 142	99.64 91	99.61 55	96.32 356	98.27 362	99.70 189	93.35 303	99.44 309	95.69 373	95.40 371	98.27 398

v7n		97.87 271	97.52 289	98.92 231	98.76 386	98.58 228	99.84 12	99.46 210	96.20 365	98.91 290	99.70 189	94.89 237	99.44 309	96.03 364	93.89 400	98.75 307

jajsoiax		98.43 201	98.28 208	98.88 242	98.60 403	98.43 246	99.82 16	99.53 113	98.19 157	98.63 336	99.80 127	93.22 306	99.44 309	99.22 91	97.50 309	98.77 303

mvs_tets		98.40 207	98.23 210	98.91 235	98.67 396	98.51 238	99.66 78	99.53 113	98.19 157	98.65 333	99.81 113	92.75 315	99.44 309	99.31 78	97.48 313	98.77 303

sc_t1		95.75 378	95.05 385	97.87 357	98.83 373	94.61 404	99.21 324	99.45 221	87.45 438	97.97 378	99.85 71	81.19 438	99.43 313	98.27 219	93.20 409	99.57 185

Vis-MVSNet (Re-imp)		98.87 157	98.72 162	99.31 174	99.71 110	98.88 193	99.80 25	99.44 230	97.91 204	99.36 196	99.78 149	95.49 209	99.43 313	97.91 251	99.11 201	99.62 165

OPU-MVS				99.64 94	99.56 181	99.72 50	99.60 109				99.70 189	99.27 5	99.42 315	98.24 222	99.80 118	99.79 86

Anonymous20231211		97.88 269	97.54 287	98.90 237	99.71 110	98.53 232	99.48 207	99.57 78	94.16 407	98.81 307	99.68 207	93.23 304	99.42 315	98.84 145	94.42 390	98.76 305

ttmdpeth		97.80 288	97.63 279	98.29 322	98.77 384	97.38 300	99.64 91	99.36 272	98.78 91	96.30 414	99.58 250	92.34 336	99.39 317	98.36 211	95.58 366	98.10 408

VPNet		97.84 278	97.44 305	99.01 216	99.21 297	98.94 186	99.48 207	99.57 78	98.38 129	99.28 213	99.73 178	88.89 385	99.39 317	99.19 93	93.27 408	98.71 315

nrg030		98.64 191	98.42 198	99.28 186	99.05 338	99.69 56	99.81 20	99.46 210	98.04 191	99.01 272	99.82 99	96.69 156	99.38 319	99.34 74	94.59 387	98.78 299

GA-MVS		97.85 274	97.47 297	99.00 218	99.38 250	97.99 268	98.57 419	99.15 339	97.04 305	98.90 292	99.30 343	89.83 376	99.38 319	96.70 346	98.33 258	99.62 165

UniMVSNet (Re)		98.29 216	98.00 234	99.13 205	99.00 345	99.36 119	99.49 201	99.51 136	97.95 200	98.97 281	99.13 366	96.30 174	99.38 319	98.36 211	93.34 406	98.66 346

FIs		98.78 177	98.63 176	99.23 194	99.18 305	99.54 91	99.83 15	99.59 68	98.28 141	98.79 311	99.81 113	96.75 154	99.37 322	99.08 108	96.38 342	98.78 299

PS-MVSNAJss		98.92 151	98.92 133	98.90 237	98.78 379	98.53 232	99.78 32	99.54 100	98.07 181	99.00 276	99.76 162	99.01 18	99.37 322	99.13 101	97.23 326	98.81 296

CDS-MVSNet		99.09 129	99.03 107	99.25 189	99.42 235	98.73 213	99.45 222	99.46 210	98.11 173	99.46 166	99.77 158	98.01 109	99.37 322	98.70 162	98.92 219	99.66 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 378	95.16 383	97.51 380	99.30 272	93.69 418	98.88 391	95.78 446	85.09 443	98.78 312	92.65 446	91.29 359	99.37 322	94.85 391	99.85 87	99.46 226

v1192		97.81 286	97.44 305	98.91 235	98.88 363	98.68 216	99.51 179	99.34 284	96.18 367	99.20 236	99.34 332	94.03 284	99.36 326	95.32 383	95.18 375	98.69 324

EI-MVSNet		98.67 187	98.67 168	98.68 274	99.35 257	97.97 269	99.50 188	99.38 263	96.93 315	99.20 236	99.83 90	97.87 111	99.36 326	98.38 207	97.56 302	98.71 315

MVSTER		98.49 196	98.32 205	99.00 218	99.35 257	99.02 168	99.54 160	99.38 263	97.41 269	99.20 236	99.73 178	93.86 292	99.36 326	98.87 135	97.56 302	98.62 359

gg-mvs-nofinetune		96.17 370	95.32 382	98.73 266	98.79 376	98.14 259	99.38 262	94.09 452	91.07 430	98.07 374	91.04 450	89.62 380	99.35 329	96.75 343	99.09 205	98.68 329

pm-mvs1		97.68 310	97.28 329	98.88 242	99.06 335	98.62 224	99.50 188	99.45 221	96.32 356	97.87 383	99.79 142	92.47 329	99.35 329	97.54 293	93.54 404	98.67 337

OurMVSNet-221017-0		97.88 269	97.77 260	98.19 331	98.71 392	96.53 352	99.88 4	99.00 360	97.79 220	98.78 312	99.94 6	91.68 348	99.35 329	97.21 315	96.99 333	98.69 324

EGC-MVSNET		82.80 415	77.86 421	97.62 374	97.91 418	96.12 367	99.33 279	99.28 317	8.40 458	25.05 459	99.27 350	84.11 425	99.33 332	89.20 431	98.22 267	97.42 432

pmmvs6		96.53 362	96.09 367	97.82 364	98.69 394	95.47 382	99.37 264	99.47 201	93.46 415	97.41 392	99.78 149	87.06 408	99.33 332	96.92 338	92.70 416	98.65 348

V42		98.06 238	97.79 255	98.86 249	98.98 351	98.84 200	99.69 62	99.34 284	96.53 342	99.30 209	99.37 322	94.67 254	99.32 334	97.57 290	94.66 385	98.42 388

lessismore_v0				97.79 366	98.69 394	95.44 385		94.75 450		95.71 420	99.87 57	88.69 389	99.32 334	95.89 367	94.93 382	98.62 359

OpenMVS_ROB	92.34 20	94.38 395	93.70 401	96.41 405	97.38 427	93.17 424	99.06 355	98.75 396	86.58 441	94.84 427	98.26 420	81.53 436	99.32 334	89.01 432	97.87 286	96.76 435

v8		97.95 260	97.63 279	98.93 229	98.95 355	98.81 208	99.80 25	99.41 245	96.03 379	99.10 255	99.42 304	94.92 235	99.30 337	96.94 335	94.08 397	98.66 346

v1921920		97.80 288	97.45 300	98.84 253	98.80 375	98.53 232	99.52 170	99.34 284	96.15 371	99.24 225	99.47 293	93.98 286	99.29 338	95.40 381	95.13 377	98.69 324

anonymousdsp		98.44 200	98.28 208	98.94 227	98.50 409	98.96 179	99.77 34	99.50 156	97.07 300	98.87 298	99.77 158	94.76 247	99.28 339	98.66 169	97.60 298	98.57 374

MVSFormer		99.17 99	99.12 91	99.29 182	99.51 201	98.94 186	99.88 4	99.46 210	97.55 249	99.80 66	99.65 220	97.39 122	99.28 339	99.03 113	99.85 87	99.65 150

test_djsdf		98.67 187	98.57 188	98.98 220	98.70 393	98.91 191	99.88 4	99.46 210	97.55 249	99.22 230	99.88 46	95.73 200	99.28 339	99.03 113	97.62 297	98.75 307

VortexMVS		98.67 187	98.66 171	98.68 274	99.62 157	97.96 271	99.59 116	99.41 245	98.13 169	99.31 205	99.70 189	95.48 210	99.27 342	99.40 65	97.32 323	98.79 297

SSC-MVS3.2		97.34 339	97.15 336	97.93 352	99.02 342	95.76 374	99.48 207	99.58 73	97.62 241	99.09 258	99.53 270	87.95 400	99.27 342	96.42 356	95.66 364	98.75 307

cascas		97.69 307	97.43 309	98.48 296	98.60 403	97.30 302	98.18 437	99.39 255	92.96 419	98.41 352	98.78 401	93.77 295	99.27 342	98.16 229	98.61 240	98.86 293

v144192		97.92 264	97.60 282	98.87 246	98.83 373	98.65 219	99.55 155	99.34 284	96.20 365	99.32 204	99.40 312	94.36 271	99.26 345	96.37 360	95.03 379	98.70 320

dmvs_re		98.08 236	98.16 213	97.85 359	99.55 185	94.67 403	99.70 58	98.92 370	98.15 162	99.06 266	99.35 328	93.67 298	99.25 346	97.77 269	97.25 325	99.64 157

v2v482		98.06 238	97.77 260	98.92 231	98.90 361	98.82 206	99.57 134	99.36 272	96.65 330	99.19 239	99.35 328	94.20 276	99.25 346	97.72 276	94.97 380	98.69 324

v1240		97.69 307	97.32 324	98.79 261	98.85 370	98.43 246	99.48 207	99.36 272	96.11 374	99.27 218	99.36 325	93.76 296	99.24 348	94.46 395	95.23 374	98.70 320

WBMVS		97.74 298	97.50 292	98.46 302	99.24 290	97.43 298	99.21 324	99.42 242	97.45 262	98.96 283	99.41 308	88.83 386	99.23 349	98.94 123	96.02 350	98.71 315

v1144		97.98 255	97.69 271	98.85 252	98.87 366	98.66 218	99.54 160	99.35 279	96.27 360	99.23 229	99.35 328	94.67 254	99.23 349	96.73 344	95.16 376	98.68 329

v10		97.85 274	97.52 289	98.86 249	98.99 348	98.67 217	99.75 42	99.41 245	95.70 383	98.98 279	99.41 308	94.75 248	99.23 349	96.01 366	94.63 386	98.67 337

WR-MVS_H		98.13 230	97.87 250	98.90 237	99.02 342	98.84 200	99.70 58	99.59 68	97.27 280	98.40 353	99.19 360	95.53 207	99.23 349	98.34 213	93.78 402	98.61 368

miper_enhance_ethall		98.16 227	98.08 225	98.41 310	98.96 354	97.72 286	98.45 425	99.32 302	96.95 312	98.97 281	99.17 361	97.06 140	99.22 353	97.86 256	95.99 353	98.29 397

GG-mvs-BLEND				98.45 304	98.55 407	98.16 257	99.43 233	93.68 453		97.23 398	98.46 411	89.30 381	99.22 353	95.43 380	98.22 267	97.98 419

FC-MVSNet-test		98.75 180	98.62 181	99.15 204	99.08 332	99.45 108	99.86 11	99.60 62	98.23 152	98.70 324	99.82 99	96.80 151	99.22 353	99.07 109	96.38 342	98.79 297

UniMVSNet_NR-MVSNet		98.22 219	97.97 237	98.96 223	98.92 358	98.98 172	99.48 207	99.53 113	97.76 224	98.71 318	99.46 297	96.43 170	99.22 353	98.57 186	92.87 414	98.69 324

DU-MVS		98.08 236	97.79 255	98.96 223	98.87 366	98.98 172	99.41 245	99.45 221	97.87 208	98.71 318	99.50 281	94.82 239	99.22 353	98.57 186	92.87 414	98.68 329

cl____		98.01 251	97.84 253	98.55 289	99.25 288	97.97 269	98.71 408	99.34 284	96.47 349	98.59 343	99.54 266	95.65 203	99.21 358	97.21 315	95.77 359	98.46 385

WR-MVS		98.06 238	97.73 267	99.06 210	98.86 369	99.25 139	99.19 329	99.35 279	97.30 278	98.66 327	99.43 302	93.94 287	99.21 358	98.58 183	94.28 392	98.71 315

test_0402		96.64 360	96.24 362	97.85 359	98.85 370	96.43 356	99.44 228	99.26 321	93.52 413	96.98 406	99.52 274	88.52 394	99.20 360	92.58 420	97.50 309	97.93 422

SixPastTwentyTwo		97.50 327	97.33 323	98.03 341	98.65 397	96.23 364	99.77 34	98.68 408	97.14 291	97.90 381	99.93 10	90.45 367	99.18 361	97.00 329	96.43 341	98.67 337

cl22		97.85 274	97.64 278	98.48 296	99.09 329	97.87 278	98.60 418	99.33 292	97.11 297	98.87 298	99.22 356	92.38 334	99.17 362	98.21 223	95.99 353	98.42 388

tt0320		95.71 380	95.07 384	97.62 374	99.05 338	95.02 394	99.25 312	99.52 118	86.81 439	97.97 378	99.72 182	83.58 428	99.15 363	96.38 359	93.35 405	98.68 329

WB-MVSnew		97.65 315	97.65 275	97.63 373	98.78 379	97.62 292	99.13 339	98.33 418	97.36 273	99.07 261	98.94 388	95.64 204	99.15 363	92.95 414	98.68 238	96.12 442

IterMVS-SCA-FT		97.82 284	97.75 265	98.06 340	99.57 177	96.36 358	99.02 365	99.49 168	97.18 288	98.71 318	99.72 182	92.72 318	99.14 365	97.44 303	95.86 358	98.67 337

pmmvs5		97.52 324	97.30 326	98.16 333	98.57 406	96.73 342	99.27 301	98.90 377	96.14 372	98.37 355	99.53 270	91.54 354	99.14 365	97.51 295	95.87 357	98.63 357

v148		97.79 290	97.55 284	98.50 293	98.74 387	97.72 286	99.54 160	99.33 292	96.26 361	98.90 292	99.51 278	94.68 253	99.14 365	97.83 260	93.15 411	98.63 357

ICG_test_0404		98.53 195	98.52 193	98.55 289	99.55 185	96.93 331	99.20 327	99.44 230	98.05 187	98.96 283	99.80 127	94.66 256	99.13 368	98.15 231	98.92 219	99.60 170

miper_ehance_all_eth		98.18 225	98.10 221	98.41 310	99.23 292	97.72 286	98.72 407	99.31 306	96.60 338	98.88 295	99.29 345	97.29 129	99.13 368	97.60 284	95.99 353	98.38 393

NR-MVSNet		97.97 258	97.61 281	99.02 215	98.87 366	99.26 137	99.47 216	99.42 242	97.63 239	97.08 404	99.50 281	95.07 228	99.13 368	97.86 256	93.59 403	98.68 329

IterMVS		97.83 281	97.77 260	98.02 343	99.58 173	96.27 362	99.02 365	99.48 180	97.22 286	98.71 318	99.70 189	92.75 315	99.13 368	97.46 301	96.00 352	98.67 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 396	94.90 387	91.84 421	97.24 431	80.01 451	98.52 422	99.48 180	89.01 435	91.99 438	99.67 213	85.67 415	99.13 368	95.44 379	97.03 332	96.39 439
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 243	97.96 238	98.33 317	99.26 284	97.38 300	98.56 421	99.31 306	96.65 330	98.88 295	99.52 274	96.58 161	99.12 373	97.39 306	95.53 369	98.47 382

pmmvs4		98.13 230	97.90 245	98.81 258	98.61 402	98.87 195	98.99 373	99.21 332	96.44 350	99.06 266	99.58 250	95.90 191	99.11 374	97.18 321	96.11 349	98.46 385

TransMVSNet (Re)		97.15 348	96.58 354	98.86 249	99.12 321	98.85 199	99.49 201	98.91 375	95.48 386	97.16 402	99.80 127	93.38 300	99.11 374	94.16 401	91.73 421	98.62 359

ambc				93.06 419	92.68 450	82.36 444	98.47 424	98.73 405		95.09 425	97.41 433	55.55 451	99.10 376	96.42 356	91.32 422	97.71 425

Baseline_NR-MVSNet		97.76 292	97.45 300	98.68 274	99.09 329	98.29 251	99.41 245	98.85 384	95.65 384	98.63 336	99.67 213	94.82 239	99.10 376	98.07 242	92.89 413	98.64 350

test_vis3_rt		87.04 411	85.81 414	90.73 425	93.99 449	81.96 446	99.76 37	90.23 460	92.81 421	81.35 448	91.56 448	40.06 457	99.07 378	94.27 398	88.23 435	91.15 448

CP-MVSNet		98.09 234	97.78 258	99.01 216	98.97 353	99.24 140	99.67 71	99.46 210	97.25 282	98.48 350	99.64 226	93.79 294	99.06 379	98.63 173	94.10 396	98.74 311

PS-CasMVS		97.93 261	97.59 283	98.95 225	98.99 348	99.06 164	99.68 68	99.52 118	97.13 292	98.31 358	99.68 207	92.44 333	99.05 380	98.51 194	94.08 397	98.75 307

K. test v3		97.10 350	96.79 350	98.01 344	98.72 390	96.33 359	99.87 8	97.05 437	97.59 243	96.16 416	99.80 127	88.71 388	99.04 381	96.69 347	96.55 339	98.65 348

new_pmnet		96.38 366	96.03 368	97.41 383	98.13 417	95.16 393	99.05 357	99.20 333	93.94 408	97.39 395	98.79 400	91.61 353	99.04 381	90.43 427	95.77 359	98.05 412

DIV-MVS_self_test		98.01 251	97.85 252	98.48 296	99.24 290	97.95 274	98.71 408	99.35 279	96.50 343	98.60 342	99.54 266	95.72 201	99.03 383	97.21 315	95.77 359	98.46 385

IterMVS-LS		98.46 199	98.42 198	98.58 283	99.59 171	98.00 267	99.37 264	99.43 240	96.94 314	99.07 261	99.59 246	97.87 111	99.03 383	98.32 216	95.62 365	98.71 315
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 315	97.68 272	97.55 379	98.62 400	94.97 396	98.84 395	99.30 311	96.83 321	98.19 367	99.34 332	97.01 143	99.02 385	95.00 389	96.01 351	98.64 350

Patchmtry		97.75 296	97.40 312	98.81 258	99.10 326	98.87 195	99.11 348	99.33 292	94.83 399	98.81 307	99.38 319	94.33 272	99.02 385	96.10 362	95.57 367	98.53 376

N_pmnet		94.95 390	95.83 373	92.31 420	98.47 410	79.33 452	99.12 342	92.81 458	93.87 409	97.68 388	99.13 366	93.87 291	99.01 387	91.38 424	96.19 347	98.59 372

CR-MVSNet		98.17 226	97.93 243	98.87 246	99.18 305	98.49 240	99.22 322	99.33 292	96.96 310	99.56 147	99.38 319	94.33 272	99.00 388	94.83 392	98.58 243	99.14 264

c3_l		98.12 232	98.04 230	98.38 314	99.30 272	97.69 290	98.81 398	99.33 292	96.67 328	98.83 304	99.34 332	97.11 136	98.99 389	97.58 286	95.34 372	98.48 380

test0.0.03 1		97.71 305	97.42 310	98.56 287	98.41 413	97.82 281	98.78 401	98.63 411	97.34 274	98.05 375	98.98 384	94.45 269	98.98 390	95.04 388	97.15 330	98.89 292

PatchT		97.03 352	96.44 358	98.79 261	98.99 348	98.34 250	99.16 333	99.07 351	92.13 424	99.52 156	97.31 437	94.54 264	98.98 390	88.54 434	98.73 235	99.03 280

GBi-Net		97.68 310	97.48 294	98.29 322	99.51 201	97.26 306	99.43 233	99.48 180	96.49 344	99.07 261	99.32 340	90.26 369	98.98 390	97.10 323	96.65 335	98.62 359

test1		97.68 310	97.48 294	98.29 322	99.51 201	97.26 306	99.43 233	99.48 180	96.49 344	99.07 261	99.32 340	90.26 369	98.98 390	97.10 323	96.65 335	98.62 359

FMVSNet3		98.03 246	97.76 264	98.84 253	99.39 248	98.98 172	99.40 253	99.38 263	96.67 328	99.07 261	99.28 347	92.93 310	98.98 390	97.10 323	96.65 335	98.56 375

FMVSNet2		97.72 302	97.36 315	98.80 260	99.51 201	98.84 200	99.45 222	99.42 242	96.49 344	98.86 302	99.29 345	90.26 369	98.98 390	96.44 355	96.56 338	98.58 373

FMVSNet1		96.84 356	96.36 360	98.29 322	99.32 270	97.26 306	99.43 233	99.48 180	95.11 391	98.55 345	99.32 340	83.95 426	98.98 390	95.81 369	96.26 346	98.62 359

ppachtmachnet_test		97.49 332	97.45 300	97.61 377	98.62 400	95.24 389	98.80 399	99.46 210	96.11 374	98.22 365	99.62 237	96.45 168	98.97 397	93.77 403	95.97 356	98.61 368

TranMVSNet+NR-MVSNet		97.93 261	97.66 274	98.76 265	98.78 379	98.62 224	99.65 84	99.49 168	97.76 224	98.49 349	99.60 244	94.23 275	98.97 397	98.00 246	92.90 412	98.70 320

MVStest1		96.08 373	95.48 378	97.89 356	98.93 356	96.70 343	99.56 141	99.35 279	92.69 422	91.81 439	99.46 297	89.90 375	98.96 399	95.00 389	92.61 417	98.00 417

tt0320-xc		95.31 386	94.59 390	97.45 382	98.92 358	94.73 400	99.20 327	99.31 306	86.74 440	97.23 398	99.72 182	81.14 439	98.95 400	97.08 326	91.98 420	98.67 337

test_method		91.10 406	91.36 408	90.31 426	95.85 439	73.72 459	94.89 447	99.25 323	68.39 450	95.82 419	99.02 378	80.50 440	98.95 400	93.64 406	94.89 384	98.25 400

ADS-MVSNet2		98.02 248	98.07 228	97.87 357	99.33 263	95.19 391	99.23 318	99.08 348	96.24 362	99.10 255	99.67 213	94.11 280	98.93 402	96.81 341	99.05 208	99.48 215

ET-MVSNet_ETH3D		96.49 363	95.64 377	99.05 212	99.53 192	98.82 206	98.84 395	97.51 435	97.63 239	84.77 444	99.21 359	92.09 338	98.91 403	98.98 118	92.21 419	99.41 236

miper_lstm_enhance		98.00 253	97.91 244	98.28 326	99.34 262	97.43 298	98.88 391	99.36 272	96.48 347	98.80 309	99.55 261	95.98 184	98.91 403	97.27 312	95.50 370	98.51 378

MonoMVSNet		98.38 208	98.47 196	98.12 338	98.59 405	96.19 366	99.72 53	98.79 393	97.89 206	99.44 172	99.52 274	96.13 178	98.90 405	98.64 171	97.54 304	99.28 253

PEN-MVS		97.76 292	97.44 305	98.72 268	98.77 384	98.54 231	99.78 32	99.51 136	97.06 302	98.29 361	99.64 226	92.63 324	98.89 406	98.09 235	93.16 410	98.72 313

testing3		97.28 342	96.76 351	98.82 255	99.37 253	98.07 264	99.45 222	99.36 272	97.56 248	97.89 382	98.95 387	83.70 427	98.82 407	96.03 364	98.56 246	99.58 182

testgi		97.65 315	97.50 292	98.13 337	99.36 256	96.45 355	99.42 240	99.48 180	97.76 224	97.87 383	99.45 299	91.09 361	98.81 408	94.53 394	98.52 249	99.13 266

testf1		90.42 409	90.68 410	89.65 429	97.78 421	73.97 457	99.13 339	98.81 389	89.62 432	91.80 440	98.93 389	62.23 449	98.80 409	86.61 443	91.17 423	96.19 440

APD_test2		90.42 409	90.68 410	89.65 429	97.78 421	73.97 457	99.13 339	98.81 389	89.62 432	91.80 440	98.93 389	62.23 449	98.80 409	86.61 443	91.17 423	96.19 440

MIMVSNet		97.73 300	97.45 300	98.57 284	99.45 231	97.50 296	99.02 365	98.98 362	96.11 374	99.41 181	99.14 365	90.28 368	98.74 411	95.74 371	98.93 217	99.47 221

LCM-MVSNet-Re		97.83 281	98.15 215	96.87 399	99.30 272	92.25 429	99.59 116	98.26 419	97.43 266	96.20 415	99.13 366	96.27 175	98.73 412	98.17 228	98.99 214	99.64 157

Syy-MVS		97.09 351	97.14 337	96.95 396	99.00 345	92.73 427	99.29 291	99.39 255	97.06 302	97.41 392	98.15 423	93.92 289	98.68 413	91.71 422	98.34 256	99.45 229

myMVS_eth3d		96.89 354	96.37 359	98.43 309	99.00 345	97.16 310	99.29 291	99.39 255	97.06 302	97.41 392	98.15 423	83.46 429	98.68 413	95.27 384	98.34 256	99.45 229

DTE-MVSNet		97.51 326	97.19 335	98.46 302	98.63 399	98.13 260	99.84 12	99.48 180	96.68 327	97.97 378	99.67 213	92.92 311	98.56 415	96.88 340	92.60 418	98.70 320

PC_three_1452									98.18 160	99.84 50	99.70 189	99.31 3	98.52 416	98.30 218	99.80 118	99.81 73

mvsany_test3		93.77 398	93.45 402	94.74 411	95.78 440	88.01 437	99.64 91	98.25 420	98.28 141	94.31 428	97.97 430	68.89 445	98.51 417	97.50 296	90.37 428	97.71 425

UnsupCasMVSNet_bld		93.53 399	92.51 405	96.58 404	97.38 427	93.82 414	98.24 434	99.48 180	91.10 429	93.10 433	96.66 439	74.89 443	98.37 418	94.03 402	87.71 436	97.56 430

Anonymous20240521		96.20 369	95.89 372	97.13 390	97.72 424	94.96 397	99.79 31	99.29 315	93.01 418	97.20 401	99.03 376	89.69 378	98.36 419	91.16 425	96.13 348	98.07 410

test_f		91.90 405	91.26 409	93.84 414	95.52 444	85.92 439	99.69 62	98.53 416	95.31 388	93.87 430	96.37 441	55.33 452	98.27 420	95.70 372	90.98 426	97.32 433

MDA-MVSNet_test_wron		95.45 382	94.60 389	98.01 344	98.16 416	97.21 309	99.11 348	99.24 326	93.49 414	80.73 450	98.98 384	93.02 308	98.18 421	94.22 400	94.45 389	98.64 350

UnsupCasMVSNet_eth		96.44 364	96.12 365	97.40 384	98.65 397	95.65 375	99.36 269	99.51 136	97.13 292	96.04 418	98.99 382	88.40 395	98.17 422	96.71 345	90.27 429	98.40 391

KD-MVS_2432*1600		94.62 391	93.72 399	97.31 385	97.19 433	95.82 372	98.34 429	99.20 333	95.00 395	97.57 389	98.35 416	87.95 400	98.10 423	92.87 416	77.00 448	98.01 414

miper_refine_blended		94.62 391	93.72 399	97.31 385	97.19 433	95.82 372	98.34 429	99.20 333	95.00 395	97.57 389	98.35 416	87.95 400	98.10 423	92.87 416	77.00 448	98.01 414

YYNet1		95.36 384	94.51 392	97.92 353	97.89 419	97.10 313	99.10 350	99.23 327	93.26 417	80.77 449	99.04 375	92.81 314	98.02 425	94.30 396	94.18 394	98.64 350

EU-MVSNet		97.98 255	98.03 231	97.81 365	98.72 390	96.65 348	99.66 78	99.66 28	98.09 176	98.35 356	99.82 99	95.25 221	98.01 426	97.41 305	95.30 373	98.78 299

Gipuma		90.99 407	90.15 412	93.51 415	98.73 388	90.12 435	93.98 448	99.45 221	79.32 446	92.28 436	94.91 443	69.61 444	97.98 427	87.42 439	95.67 363	92.45 446
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 385	94.73 388	97.15 388	95.53 443	95.94 370	99.35 274	99.10 345	95.13 389	93.55 431	97.54 432	88.15 399	97.91 428	94.58 393	89.69 432	97.61 428

PM-MVS		92.96 402	92.23 406	95.14 410	95.61 441	89.98 436	99.37 264	98.21 423	94.80 400	95.04 426	97.69 431	65.06 446	97.90 429	94.30 396	89.98 431	97.54 431

MDA-MVSNet-bldmvs		94.96 389	93.98 396	97.92 353	98.24 415	97.27 304	99.15 336	99.33 292	93.80 410	80.09 451	99.03 376	88.31 396	97.86 430	93.49 408	94.36 391	98.62 359

Patchmatch-RL test		95.84 376	95.81 374	95.95 408	95.61 441	90.57 434	98.24 434	98.39 417	95.10 393	95.20 423	98.67 404	94.78 243	97.77 431	96.28 361	90.02 430	99.51 207

Anonymous20231206		96.22 367	96.03 368	96.79 401	97.31 430	94.14 412	99.63 97	99.08 348	96.17 368	97.04 405	99.06 373	93.94 287	97.76 432	86.96 441	95.06 378	98.47 382

SD-MVS		99.41 55	99.52 12	99.05 212	99.74 93	99.68 57	99.46 219	99.52 118	99.11 40	99.88 37	99.91 24	99.43 1	97.70 433	98.72 160	99.93 30	99.77 94
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		97.25 344	97.35 317	96.95 396	97.84 420	93.61 421	99.57 134	96.63 443	96.13 373	98.87 298	98.61 407	94.59 259	97.70 433	95.08 387	98.86 226	99.55 189

dongtai		93.26 400	92.93 404	94.25 412	99.39 248	85.68 440	97.68 443	93.27 454	92.87 420	96.85 409	99.39 316	82.33 434	97.48 435	76.78 448	97.80 289	99.58 182

pmmvs3		94.09 397	93.25 403	96.60 403	94.76 448	94.49 406	98.92 387	98.18 425	89.66 431	96.48 412	98.06 429	86.28 412	97.33 436	89.68 430	87.20 437	97.97 420

KD-MVS_self_test		95.00 388	94.34 393	96.96 395	97.07 435	95.39 386	99.56 141	99.44 230	95.11 391	97.13 403	97.32 436	91.86 343	97.27 437	90.35 428	81.23 445	98.23 402

FMVSNet5		96.43 365	96.19 364	97.15 388	99.11 323	95.89 371	99.32 281	99.52 118	94.47 406	98.34 357	99.07 371	87.54 405	97.07 438	92.61 419	95.72 362	98.47 382

new-patchmatchnet		94.48 394	94.08 395	95.67 409	95.08 446	92.41 428	99.18 331	99.28 317	94.55 405	93.49 432	97.37 435	87.86 403	97.01 439	91.57 423	88.36 434	97.61 428

LCM-MVSNet		86.80 413	85.22 417	91.53 423	87.81 455	80.96 449	98.23 436	98.99 361	71.05 448	90.13 443	96.51 440	48.45 456	96.88 440	90.51 426	85.30 439	96.76 435

CL-MVSNet_self_test		94.49 393	93.97 397	96.08 407	96.16 438	93.67 419	98.33 431	99.38 263	95.13 389	97.33 396	98.15 423	92.69 322	96.57 441	88.67 433	79.87 446	97.99 418

MIMVSNet1		95.51 381	95.04 386	96.92 398	97.38 427	95.60 376	99.52 170	99.50 156	93.65 412	96.97 407	99.17 361	85.28 420	96.56 442	88.36 435	95.55 368	98.60 371

test20.03		96.12 371	95.96 370	96.63 402	97.44 426	95.45 383	99.51 179	99.38 263	96.55 341	96.16 416	99.25 353	93.76 296	96.17 443	87.35 440	94.22 393	98.27 398

tmp_tt		82.80 415	81.52 418	86.66 431	66.61 461	68.44 460	92.79 450	97.92 427	68.96 449	80.04 452	99.85 71	85.77 414	96.15 444	97.86 256	43.89 454	95.39 444

test_fmvs3		92.10 404	91.77 407	93.08 418	96.19 437	86.25 438	99.82 16	98.62 412	96.65 330	95.19 424	96.90 438	55.05 453	95.93 445	96.63 352	90.92 427	97.06 434

kuosan		90.92 408	90.11 413	93.34 416	98.78 379	85.59 441	98.15 438	93.16 456	89.37 434	92.07 437	98.38 415	81.48 437	95.19 446	62.54 455	97.04 331	99.25 258

dmvs_testset		95.02 387	96.12 365	91.72 422	99.10 326	80.43 450	99.58 126	97.87 429	97.47 258	95.22 422	98.82 396	93.99 285	95.18 447	88.09 436	94.91 383	99.56 188

PMMVS2		86.87 412	85.37 416	91.35 424	90.21 453	83.80 443	98.89 390	97.45 436	83.13 445	91.67 442	95.03 442	48.49 455	94.70 448	85.86 445	77.62 447	95.54 443

PMVS	70.75 22	75.98 421	74.97 422	79.01 437	70.98 460	55.18 462	93.37 449	98.21 423	65.08 454	61.78 455	93.83 445	21.74 462	92.53 449	78.59 447	91.12 425	89.34 450
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 414	85.65 415	82.75 435	86.77 456	63.39 461	98.35 428	98.92 370	74.11 447	83.39 446	98.98 384	50.85 454	92.40 450	84.54 446	94.97 380	92.46 445

WB-MVS		93.10 401	94.10 394	90.12 427	95.51 445	81.88 447	99.73 51	99.27 320	95.05 394	93.09 434	98.91 393	94.70 252	91.89 451	76.62 449	94.02 399	96.58 437

SSC-MVS		92.73 403	93.73 398	89.72 428	95.02 447	81.38 448	99.76 37	99.23 327	94.87 398	92.80 435	98.93 389	94.71 251	91.37 452	74.49 451	93.80 401	96.42 438

MVE	76.82 21	76.91 420	74.31 424	84.70 432	85.38 458	76.05 456	96.88 446	93.17 455	67.39 451	71.28 453	89.01 452	21.66 463	87.69 453	71.74 452	72.29 450	90.35 449
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 417	79.88 419	82.81 434	90.75 452	76.38 455	97.69 442	95.76 447	66.44 452	83.52 445	92.25 447	62.54 448	87.16 454	68.53 453	61.40 451	84.89 452

EMVS		80.02 418	79.22 420	82.43 436	91.19 451	76.40 454	97.55 445	92.49 459	66.36 453	83.01 447	91.27 449	64.63 447	85.79 455	65.82 454	60.65 452	85.08 451

ANet_high		77.30 419	74.86 423	84.62 433	75.88 459	77.61 453	97.63 444	93.15 457	88.81 436	64.27 454	89.29 451	36.51 458	83.93 456	75.89 450	52.31 453	92.33 447

wuyk23d		40.18 422	41.29 427	36.84 438	86.18 457	49.12 463	79.73 451	22.81 463	27.64 455	25.46 458	28.45 458	21.98 461	48.89 457	55.80 456	23.56 457	12.51 455

test123		39.01 424	42.50 426	28.53 439	39.17 462	20.91 464	98.75 404	19.17 464	19.83 457	38.57 456	66.67 454	33.16 459	15.42 458	37.50 458	29.66 456	49.26 453

testmvs		39.17 423	43.78 425	25.37 440	36.04 463	16.84 465	98.36 427	26.56 462	20.06 456	38.51 457	67.32 453	29.64 460	15.30 459	37.59 457	39.90 455	43.98 454

mmdepth		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

monomultidepth		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

test_blank		0.13 428	0.17 431	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	1.57 459	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uanet_test		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

DCPMVS		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

cdsmvs_eth3d_5k		24.64 425	32.85 428	0.00 441	0.00 464	0.00 466	0.00 452	99.51 136	0.00 459	0.00 460	99.56 258	96.58 161	0.00 460	0.00 459	0.00 458	0.00 456

pcd_1.5k_mvsjas		8.27 427	11.03 430	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	99.01 18	0.00 460	0.00 459	0.00 458	0.00 456

sosnet-low-res		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

sosnet		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uncertanet		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

Regformer		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

ab-mvs-re		8.30 426	11.06 429	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	99.58 250	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

uanet		0.02 429	0.03 432	0.00 441	0.00 464	0.00 466	0.00 452	0.00 465	0.00 459	0.00 460	0.27 460	0.00 464	0.00 460	0.00 459	0.00 458	0.00 456

WAC-MVS						97.16 310								95.47 378

FOURS1					99.91 1	99.93 1	99.87 8	99.56 83	99.10 41	99.81 62

test_one_0601					99.81 51	99.88 9		99.49 168	98.97 68	99.65 120	99.81 113	99.09 14

eth-test2					0.00 464

eth-test					0.00 464

RE-MVS-def			99.34 46		99.76 75	99.82 26	99.63 97	99.52 118	98.38 129	99.76 83	99.82 99	98.75 58		98.61 177	99.81 113	99.77 94

IU-MVS					99.84 34	99.88 9		99.32 302	98.30 140	99.84 50				98.86 140	99.85 87	99.89 26

save fliter					99.76 75	99.59 81	99.14 338	99.40 252	99.00 60

test0726					99.85 28	99.89 5	99.62 102	99.50 156	99.10 41	99.86 47	99.82 99	98.94 32

GSMVS																99.52 198

test_part2					99.81 51	99.83 20				99.77 77

sam_mvs1												94.86 238				99.52 198

sam_mvs												94.72 250

MTGPA								99.47 201

MTMP							99.54 160	98.88 380

test9_res														97.49 297	99.72 141	99.75 100

agg_prior2														97.21 315	99.73 140	99.75 100

test_prior4						99.56 87	98.99 373

test_prior2							98.96 380		98.34 135	99.01 272	99.52 274	98.68 67		97.96 248	99.74 138

新几何2							99.01 370

旧先验1					99.74 93	99.59 81		99.54 100			99.69 200	98.47 83			99.68 149	99.73 113

原ACMM2							98.95 383

test222					99.75 85	99.49 102	98.91 389	99.49 168	96.42 352	99.34 202	99.65 220	98.28 97			99.69 146	99.72 122

segment_acmp												98.96 25

testdata1							98.85 394		98.32 138

plane_prior7					99.29 276	97.03 323

plane_prior6					99.27 281	96.98 327						92.71 320

plane_prior4											99.61 241

plane_prior3						97.00 325			98.69 100	99.11 252

plane_prior2							99.39 257		98.97 68

plane_prior1					99.26 284

plane_prior						96.97 328	99.21 324		98.45 122						97.60 298

n2								0.00 465

nn								0.00 465

door-mid								98.05 426

test11								99.35 279

door								97.92 427

HQP5-MVS						96.83 338

HQP-NCC					99.19 302		98.98 376		98.24 149	98.66 327

ACMP_Plane					99.19 302		98.98 376		98.24 149	98.66 327

BP-MVS														97.19 319

HQP3-MVS								99.39 255							97.58 300

HQP2-MVS												92.47 329

NP-MVS					99.23 292	96.92 334					99.40 312

MDTV_nov1_ep13_2view						95.18 392	99.35 274		96.84 319	99.58 143		95.19 224		97.82 261		99.46 226

ACMMP++_ref															97.19 328

ACMMP++															97.43 318

Test By Simon												98.75 58

High-resolution multi-view benchmark