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	99.38 245	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		98.63 188	98.40 195	99.31 172	99.86 22	97.94 274	99.67 71	99.62 46	99.43 14	99.99 2	99.91 24	87.29 401	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	98.83 201	99.65 84	99.52 118	99.10 41	99.84 50	99.76 157	95.80 192	99.99 4	99.30 81	99.84 95	99.74 104

SymmetryMVS		99.15 104	99.02 111	99.52 132	99.72 104	98.83 201	99.65 84	99.34 279	99.10 41	99.84 50	99.76 157	95.80 192	99.99 4	99.30 81	98.72 231	99.73 113

fmvsm_s_conf0.5_n_5		99.37 63	99.21 79	99.86 29	99.80 57	99.68 57	99.42 236	99.61 55	99.37 21	99.97 22	99.86 64	94.96 226	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	99.54 159	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	99.56 140	99.63 42	99.48 3	99.98 11	99.83 88	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	99.56 140	99.63 42	99.47 4	99.98 11	99.82 97	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	99.48 203	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	98.16 328	99.81 51	94.59 400	99.52 169	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		97.70 301	97.28 324	98.97 220	99.70 115	97.27 302	99.36 265	99.45 219	98.94 71	99.66 111	99.64 221	94.93 229	99.99 4	99.48 59	84.36 435	99.65 150

xiu_mvs_v1_base_debu		99.29 79	99.27 69	99.34 165	99.63 150	98.97 175	99.12 337	99.51 136	98.86 77	99.84 50	99.47 288	98.18 101	99.99 4	99.50 54	99.31 184	99.08 267

xiu_mvs_v1_base		99.29 79	99.27 69	99.34 165	99.63 150	98.97 175	99.12 337	99.51 136	98.86 77	99.84 50	99.47 288	98.18 101	99.99 4	99.50 54	99.31 184	99.08 267

xiu_mvs_v1_base_debi		99.29 79	99.27 69	99.34 165	99.63 150	98.97 175	99.12 337	99.51 136	98.86 77	99.84 50	99.47 288	98.18 101	99.99 4	99.50 54	99.31 184	99.08 267

EPNet		98.86 158	98.71 160	99.30 177	97.20 427	98.18 254	99.62 102	98.91 370	99.28 26	98.63 331	99.81 111	95.96 181	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	99.51 178	99.62 46	99.46 7	99.99 2	99.90 31	96.60 155	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	99.52 169	98.87 377	99.55 1	99.74 87	99.80 125	96.47 162	99.98 17	99.97 1	99.97 8	99.94 15

test_cas_vis1_n_1920		99.16 101	99.01 116	99.61 102	99.81 51	98.86 196	99.65 84	99.64 38	99.39 19	99.97 22	99.94 6	93.20 302	99.98 17	99.55 47	99.91 43	99.99 1

test_vis1_n		97.92 259	97.44 300	99.34 165	99.53 187	98.08 261	99.74 47	99.49 166	99.15 31	100.00 1	99.94 6	79.51 436	99.98 17	99.88 23	99.76 133	99.97 4

xiu_mvs_v2_base		99.26 86	99.25 73	99.29 180	99.53 187	98.91 190	99.02 360	99.45 219	98.80 87	99.71 96	99.26 347	98.94 32	99.98 17	99.34 74	99.23 189	98.98 281

PS-MVSNAJ		99.32 74	99.32 50	99.30 177	99.57 175	98.94 185	98.97 374	99.46 208	98.92 74	99.71 96	99.24 349	99.01 18	99.98 17	99.35 69	99.66 152	98.97 282

QAPM		98.67 183	98.30 202	99.80 58	99.20 294	99.67 61	99.77 34	99.72 11	94.74 396	98.73 311	99.90 31	95.78 194	99.98 17	96.96 328	99.88 69	99.76 99

3Dnovator	97.25 9	99.24 91	99.05 101	99.81 54	99.12 316	99.66 64	99.84 12	99.74 10	99.09 48	98.92 284	99.90 31	95.94 184	99.98 17	98.95 120	99.92 36	99.79 86

OpenMVS	96.50 16	98.47 193	98.12 214	99.52 132	99.04 335	99.53 94	99.82 16	99.72 11	94.56 399	98.08 366	99.88 46	94.73 245	99.98 17	97.47 295	99.76 133	99.06 273

fmvsm_s_conf0.5_n_3		99.37 63	99.20 81	99.87 18	99.75 85	99.70 54	99.48 203	99.66 28	99.45 11	99.99 2	99.93 10	94.64 253	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	99.56 140	99.55 91	99.15 31	99.90 31	99.90 31	99.00 22	99.97 26	99.11 101	99.91 43	99.86 39

test_fmvsmconf0.1_n		99.55 19	99.45 26	99.86 29	99.44 227	99.65 68	99.50 186	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		98.41 199	98.14 211	99.21 193	99.82 47	97.71 287	99.74 47	99.49 166	99.32 24	99.99 2	99.95 3	85.32 414	99.97 26	99.82 26	99.84 95	99.96 7

CANet_DTU		98.97 146	98.87 141	99.25 187	99.33 258	98.42 246	99.08 346	99.30 306	99.16 30	99.43 171	99.75 162	95.27 214	99.97 26	98.56 187	99.95 20	99.36 239

MVS_0304		99.15 104	98.96 126	99.73 76	98.92 353	99.37 116	99.37 260	96.92 433	99.51 2	99.66 111	99.78 144	96.69 152	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	99.47 199	98.79 88	99.68 102	99.81 111	98.43 86	99.97 26	98.88 130	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	97.84 209	99.71 96	99.80 125	99.12 13	99.97 26	98.33 212	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	99.48 178	98.12 169	99.50 156	99.75 162	98.78 51	99.97 26	98.57 184	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	98.07 179	99.53 151	99.63 227	98.93 36	99.97 26	98.74 155	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 88	99.28 4	99.97 26	98.48 194	99.90 54	99.84 50
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 97	98.97 122	99.82 51	99.17 308	99.68 57	99.81 20	99.51 136	99.20 28	98.72 312	99.89 37	95.68 198	99.97 26	98.86 138	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	99.48 203	99.62 46	99.46 7	99.99 2	99.92 17	95.24 218	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		99.12 116	98.92 131	99.70 80	99.67 127	99.40 114	99.67 71	99.63 42	98.73 95	99.94 25	99.81 111	94.54 259	99.96 38	98.40 203	99.93 30	99.74 104

fmvsm_s_conf0.5_n_7		99.34 70	99.29 62	99.48 143	99.70 115	98.63 220	99.42 236	99.63 42	99.46 7	99.98 11	99.88 46	95.59 201	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	99.44 224	99.58 73	99.47 4	99.99 2	99.93 10	94.04 278	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	99.52 169	99.54 100	99.13 34	99.89 34	99.89 37	98.96 25	99.96 38	99.04 109	99.90 54	99.85 43

our_new_method		99.61 8	99.52 12	99.90 5	99.76 75	99.88 9	99.52 169	99.54 100	99.13 34	99.89 34	99.89 37	98.96 25	99.96 38	99.04 109	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	99.52 169	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	99.51 178	99.67 23	99.13 34	99.98 11	99.92 17	96.60 155	99.96 38	99.95 13	99.96 15	99.95 11

mvsany_test1		99.50 27	99.46 25	99.62 101	99.61 161	99.09 158	98.94 380	99.48 178	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		98.88 152	98.79 153	99.16 198	99.69 120	97.61 291	99.55 154	99.49 166	99.32 24	99.98 11	99.91 24	91.41 350	99.96 38	99.82 26	99.92 36	99.90 23

DVP-MVS++		99.59 13	99.50 17	99.88 12	99.51 196	99.88 9	99.87 8	99.51 136	98.99 62	99.88 37	99.81 111	99.27 5	99.96 38	98.85 140	99.80 118	99.81 73

MSC_two_6792asdad				99.87 18	99.51 196	99.76 43		99.33 287					99.96 38	98.87 133	99.84 95	99.89 26

No_MVS				99.87 18	99.51 196	99.76 43		99.33 287					99.96 38	98.87 133	99.84 95	99.89 26

ZD-MVS					99.71 110	99.79 35		99.61 55	96.84 314	99.56 144	99.54 261	98.58 75	99.96 38	96.93 331	99.75 135

SED-MVS		99.61 8	99.52 12	99.88 12	99.84 34	99.90 2	99.60 109	99.48 178	99.08 49	99.91 28	99.81 111	99.20 7	99.96 38	98.91 127	99.85 87	99.79 86

test_241102_TWO								99.48 178	99.08 49	99.88 37	99.81 111	98.94 32	99.96 38	98.91 127	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	98.08 178	99.55 148	99.64 221	98.91 37	99.96 38	98.72 158	99.90 54	99.82 66

DVP-MVS		99.57 17	99.47 22	99.88 12	99.85 28	99.89 5	99.57 133	99.37 266	99.10 41	99.81 62	99.80 125	98.94 32	99.96 38	98.93 124	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	99.80 125	99.09 14	99.96 38	98.85 140	99.90 54	99.88 32

test_0728_SECOND				99.91 3	99.84 34	99.89 5	99.57 133	99.51 136					99.96 38	98.93 124	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	99.79 137	98.68 67	99.96 38	98.44 200	99.77 130	99.79 86

DPE-MVS		99.46 38	99.32 50	99.91 3	99.78 63	99.88 9	99.36 265	99.51 136	98.73 95	99.88 37	99.84 83	98.72 64	99.96 38	98.16 227	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	99.62 156	99.55 89	99.50 186	99.70 15	98.79 88	99.77 77	99.96 1	97.45 121	99.96 38	98.92 126	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	99.69 195	99.06 16	99.96 38	98.69 163	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	98.13 167	99.66 111	99.68 202	98.96 25	99.96 38	98.62 172	99.87 72	99.84 50

HPM-MVS++		99.39 61	99.23 77	99.87 18	99.75 85	99.84 19	99.43 229	99.51 136	98.68 102	99.27 214	99.53 265	98.64 72	99.96 38	98.44 200	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	99.67 106	99.69 195	98.95 30	99.96 38	98.69 163	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	99.46 208	98.09 174	99.48 160	99.74 167	98.29 96	99.96 38	97.93 245	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		99.11 122	98.90 135	99.74 73	99.80 57	99.46 107	99.59 116	99.49 166	97.03 301	99.63 126	99.69 195	97.27 130	99.96 38	97.82 256	99.84 95	99.81 73

PVSNet_Blended_VisFu		99.36 67	99.28 65	99.61 102	99.86 22	99.07 163	99.47 212	99.93 2	97.66 232	99.71 96	99.86 64	97.73 116	99.96 38	99.47 61	99.82 110	99.79 86

UGNet		98.87 155	98.69 162	99.40 157	99.22 291	98.72 212	99.44 224	99.68 20	99.24 27	99.18 239	99.42 299	92.74 312	99.96 38	99.34 74	99.94 28	99.53 193
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	99.32 171	99.85 28	98.29 249	99.71 57	99.66 28	98.11 171	99.41 178	99.80 125	98.37 93	99.96 38	98.99 115	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	98.12 169	99.63 126	99.84 83	98.73 63	99.96 38	98.55 190	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	99.51 196	99.67 61	99.50 186	99.64 38	99.43 14	99.98 11	99.78 144	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	99.49 198	99.60 62	99.42 17	99.99 2	99.86 64	95.15 221	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	99.46 215	99.60 62	99.47 4	99.98 11	99.94 6	94.98 225	99.95 73	99.97 1	99.79 125	99.73 113

test_fmvsmconf0.01_n		99.22 94	99.03 106	99.79 61	98.42 407	99.48 104	99.55 154	99.51 136	99.39 19	99.78 73	99.93 10	94.80 237	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 97	98.53 79	99.95 73	98.61 175	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	97.97 194	99.63 126	99.68 202	98.52 80	99.95 73	98.38 205	99.86 80	99.81 73

CANet		99.25 90	99.14 88	99.59 106	99.41 235	99.16 148	99.35 270	99.57 78	98.82 82	99.51 155	99.61 236	96.46 163	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	99.30 282	99.52 118	97.18 283	99.60 136	99.79 137	98.79 50	99.95 73	98.83 146	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	99.49 279	98.21 99	99.95 73	98.46 198	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	96.67 343

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 97	98.86 41	99.95 73	98.62 172	99.81 113	99.78 92

RPMNet		96.72 353	95.90 366	99.19 195	99.18 300	98.49 238	99.22 318	99.52 118	88.72 432	99.56 144	97.38 429	94.08 277	99.95 73	86.87 437	98.58 238	99.14 259

sss		99.17 99	99.05 101	99.53 126	99.62 156	98.97 175	99.36 265	99.62 46	97.83 210	99.67 106	99.65 215	97.37 125	99.95 73	99.19 93	99.19 192	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	99.47 216

fmvsm_s_conf0.1_n_a		99.26 86	99.06 100	99.85 37	99.52 193	99.62 76	99.54 159	99.62 46	98.69 100	99.99 2	99.96 1	94.47 263	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	99.53 168	99.62 46	98.74 94	99.99 2	99.95 3	94.53 261	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	99.39 250	98.91 75	99.78 73	99.85 71	99.36 2	99.94 86	98.84 143	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		98.91 150	98.75 156	99.39 161	99.46 220	98.61 224	99.76 37	99.50 156	98.06 183	99.81 62	99.88 46	93.91 285	99.94 86	99.11 101	99.27 187	99.61 167

mamv4		99.33 72	99.42 28	99.07 206	99.67 127	97.73 282	99.42 236	99.60 62	98.15 162	99.94 25	99.91 24	98.42 88	99.94 86	99.72 29	99.96 15	99.54 187

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	99.37 189	99.74 167	98.81 47	99.94 86	98.79 151	99.86 80	99.84 50

X-MVStestdata		96.55 356	95.45 375	99.87 18	99.85 28	99.83 20	99.69 62	99.68 20	98.98 65	99.37 189	64.01 452	98.81 47	99.94 86	98.79 151	99.86 80	99.84 50

旧先验2							98.96 375		96.70 321	99.47 161			99.94 86	98.19 223

新几何1				99.75 70	99.75 85	99.59 81		99.54 100	96.76 317	99.29 208	99.64 221	98.43 86	99.94 86	96.92 333	99.66 152	99.72 122

testdata				99.54 118	99.75 85	98.95 182		99.51 136	97.07 295	99.43 171	99.70 184	98.87 40	99.94 86	97.76 265	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	97.59 238	99.68 102	99.63 227	98.91 37	99.94 86	98.58 181	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	98.52 234	99.39 253	99.94 1	98.73 95	99.11 248	99.89 37	95.50 204	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	99.50 186	99.50 156	97.16 285	99.77 77	99.82 97	98.78 51	99.94 86	97.56 286	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	99.05 352	99.66 28	99.14 33	99.57 143	99.80 125	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		99.06 132	98.88 140	99.61 102	99.62 156	99.16 148	99.37 260	99.56 83	98.04 186	99.53 151	99.62 232	96.84 146	99.94 86	98.85 140	98.49 246	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	99.63 126	99.95 3	95.82 190	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	99.18 300	99.75 45	99.56 140	99.57 78	98.45 122	99.49 159	99.85 71	97.77 115	99.94 86	98.33 212	99.84 95	99.52 194

GDP-MVS		99.08 129	98.89 138	99.64 94	99.53 187	99.34 120	99.64 91	99.48 178	98.32 138	99.77 77	99.66 213	95.14 222	99.93 104	98.97 119	99.50 169	99.64 157

SDMVSNet		99.11 122	98.90 135	99.75 70	99.81 51	99.59 81	99.81 20	99.65 35	98.78 91	99.64 123	99.88 46	94.56 256	99.93 104	99.67 34	98.26 259	99.72 122

FE-MVS		98.48 192	98.17 207	99.40 157	99.54 186	98.96 179	99.68 68	98.81 384	95.54 380	99.62 130	99.70 184	93.82 288	99.93 104	97.35 304	99.46 171	99.32 245

SF-MVS		99.38 62	99.24 74	99.79 61	99.79 61	99.68 57	99.57 133	99.54 100	97.82 214	99.71 96	99.80 125	98.95 30	99.93 104	98.19 223	99.84 95	99.74 104

dcpmvs_2		99.23 92	99.58 7	98.16 328	99.83 43	94.68 397	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		98.09 229	97.68 267	99.34 165	99.66 138	98.44 243	99.40 249	99.43 235	93.67 406	99.22 226	99.89 37	90.23 367	99.93 104	99.26 89	98.33 253	99.66 145

ACMMP_NAP		99.47 36	99.34 46	99.88 12	99.87 17	99.86 17	99.47 212	99.48 178	98.05 185	99.76 83	99.86 64	98.82 46	99.93 104	98.82 150	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	99.45 219	99.01 57	99.90 31	99.83 88	98.98 24	99.93 104	99.59 42	99.95 20	99.86 39

无先验							98.99 368	99.51 136	96.89 311				99.93 104	97.53 289		99.72 122

VDDNet		97.55 316	97.02 338	99.16 198	99.49 210	98.12 260	99.38 258	99.30 306	95.35 382	99.68 102	99.90 31	82.62 427	99.93 104	99.31 78	98.13 271	99.42 228

ab-mvs		98.86 158	98.63 172	99.54 118	99.64 147	99.19 143	99.44 224	99.54 100	97.77 218	99.30 205	99.81 111	94.20 271	99.93 104	99.17 97	98.82 225	99.49 207

F-COLMAP		99.19 95	99.04 103	99.64 94	99.78 63	99.27 136	99.42 236	99.54 100	97.29 274	99.41 178	99.59 241	98.42 88	99.93 104	98.19 223	99.69 146	99.73 113

BP-MVS1		99.12 116	98.94 130	99.65 88	99.51 196	99.30 131	99.67 71	98.92 365	98.48 118	99.84 50	99.69 195	94.96 226	99.92 116	99.62 41	99.79 125	99.71 131

Anonymous202405211		98.30 210	97.98 231	99.26 186	99.57 175	98.16 255	99.41 241	98.55 409	96.03 374	99.19 235	99.74 167	91.87 337	99.92 116	99.16 98	98.29 258	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	99.45 219	99.01 57	99.89 34	99.82 97	99.01 18	99.92 116	99.56 46	99.95 20	99.85 43

VDD-MVS		97.73 295	97.35 312	98.88 240	99.47 218	97.12 310	99.34 273	98.85 379	98.19 157	99.67 106	99.85 71	82.98 425	99.92 116	99.49 58	98.32 257	99.60 170

VNet		99.11 122	98.90 135	99.73 76	99.52 193	99.56 87	99.41 241	99.39 250	99.01 57	99.74 87	99.78 144	95.56 202	99.92 116	99.52 52	98.18 267	99.72 122

XVG-OURS-SEG-HR		98.69 181	98.62 177	98.89 238	99.71 110	97.74 281	99.12 337	99.54 100	98.44 125	99.42 174	99.71 180	94.20 271	99.92 116	98.54 191	98.90 219	99.00 278

mvsmamba		99.06 132	98.96 126	99.36 163	99.47 218	98.64 219	99.70 58	99.05 349	97.61 237	99.65 118	99.83 88	96.54 159	99.92 116	99.19 93	99.62 158	99.51 202

HPM-MVS_fast		99.51 25	99.40 34	99.85 37	99.91 1	99.79 35	99.76 37	99.56 83	97.72 223	99.76 83	99.75 162	99.13 12	99.92 116	99.07 107	99.92 36	99.85 43

HY-MVS	97.30 7	98.85 165	98.64 171	99.47 147	99.42 230	99.08 161	99.62 102	99.36 267	97.39 266	99.28 209	99.68 202	96.44 165	99.92 116	98.37 207	98.22 262	99.40 233

DP-MVS		99.16 101	98.95 128	99.78 64	99.77 71	99.53 94	99.41 241	99.50 156	97.03 301	99.04 265	99.88 46	97.39 122	99.92 116	98.66 167	99.90 54	99.87 37

IB-MVS	95.67 18	96.22 362	95.44 376	98.57 280	99.21 292	96.70 338	98.65 409	97.74 427	96.71 320	97.27 392	98.54 404	86.03 408	99.92 116	98.47 197	86.30 433	99.10 262
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	99.63 150	99.59 81	99.36 265	99.46 208	99.07 51	99.79 68	99.82 97	98.85 42	99.92 116	98.68 165	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	99.35 252	99.31 128	99.46 215	99.13 337	98.61 106	99.86 47	99.89 37	96.41 167	99.91 128	99.67 34	99.51 167	99.63 162

balanced_conf03		99.46 38	99.39 36	99.67 83	99.55 183	99.58 86	99.74 47	99.51 136	98.42 126	99.87 43	99.84 83	98.05 108	99.91 128	99.58 44	99.94 28	99.52 194

9.14			99.10 93		99.72 104		99.40 249	99.51 136	97.53 248	99.64 123	99.78 144	98.84 44	99.91 128	97.63 277	99.82 110

SMA-MVS		99.44 46	99.30 58	99.85 37	99.73 100	99.83 20	99.56 140	99.47 199	97.45 257	99.78 73	99.82 97	99.18 10	99.91 128	98.79 151	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	99.05 352	99.41 240	96.22 359	98.95 280	99.49 279	98.77 54	99.91 128

train_agg		99.02 138	98.77 154	99.77 67	99.67 127	99.65 68	99.05 352	99.41 240	96.28 353	98.95 280	99.49 279	98.76 55	99.91 128	97.63 277	99.72 141	99.75 100

test_8					99.67 127	99.61 78	99.03 357	99.41 240	96.28 353	98.93 283	99.48 285	98.76 55	99.91 128

agg_prior					99.67 127	99.62 76		99.40 247		98.87 293			99.91 128

原ACMM1				99.65 88	99.73 100	99.33 123		99.47 199	97.46 254	99.12 246	99.66 213	98.67 69	99.91 128	97.70 274	99.69 146	99.71 131

LFMVS		97.90 262	97.35 312	99.54 118	99.52 193	99.01 170	99.39 253	98.24 416	97.10 293	99.65 118	99.79 137	84.79 417	99.91 128	99.28 84	98.38 250	99.69 135

XVG-OURS		98.73 179	98.68 163	98.88 240	99.70 115	97.73 282	98.92 382	99.55 91	98.52 115	99.45 164	99.84 83	95.27 214	99.91 128	98.08 234	98.84 223	99.00 278

PLC	97.94 4	99.02 138	98.85 145	99.53 126	99.66 138	99.01 170	99.24 311	99.52 118	96.85 313	99.27 214	99.48 285	98.25 98	99.91 128	97.76 265	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	97.66 309	97.06 337	99.47 147	99.61 161	99.09 158	98.04 435	99.25 318	91.24 423	98.51 342	99.70 184	94.55 258	99.91 128	92.76 413	99.85 87	99.42 228
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
Elysia		98.88 152	98.65 169	99.58 109	99.58 171	99.34 120	99.65 84	99.52 118	98.26 145	99.83 58	99.87 57	93.37 296	99.90 141	97.81 258	99.91 43	99.49 207

StellarMVS		98.88 152	98.65 169	99.58 109	99.58 171	99.34 120	99.65 84	99.52 118	98.26 145	99.83 58	99.87 57	93.37 296	99.90 141	97.81 258	99.91 43	99.49 207

AstraMVS		99.09 127	99.03 106	99.25 187	99.66 138	98.13 258	99.57 133	98.24 416	98.82 82	99.91 28	99.88 46	95.81 191	99.90 141	99.72 29	99.67 151	99.74 104

mmtdpeth		96.95 348	96.71 347	97.67 367	99.33 258	94.90 393	99.89 2	99.28 312	98.15 162	99.72 94	98.57 403	86.56 406	99.90 141	99.82 26	89.02 428	98.20 398

UWE-MVS		97.58 315	97.29 323	98.48 291	99.09 324	96.25 358	99.01 365	96.61 439	97.86 204	99.19 235	99.01 374	88.72 382	99.90 141	97.38 302	98.69 232	99.28 248

test_vis1_rt		95.81 372	95.65 371	96.32 401	99.67 127	91.35 428	99.49 198	96.74 437	98.25 148	95.24 416	98.10 422	74.96 437	99.90 141	99.53 50	98.85 222	97.70 422

FA-MVS(test-final)		98.75 176	98.53 188	99.41 156	99.55 183	99.05 166	99.80 25	99.01 354	96.59 335	99.58 140	99.59 241	95.39 208	99.90 141	97.78 261	99.49 170	99.28 248

MCST-MVS		99.43 49	99.30 58	99.82 51	99.79 61	99.74 48	99.29 287	99.40 247	98.79 88	99.52 153	99.62 232	98.91 37	99.90 141	98.64 169	99.75 135	99.82 66

CDPH-MVS		99.13 110	98.91 134	99.80 58	99.75 85	99.71 52	99.15 331	99.41 240	96.60 333	99.60 136	99.55 256	98.83 45	99.90 141	97.48 293	99.83 106	99.78 92

NCCC		99.34 70	99.19 83	99.79 61	99.61 161	99.65 68	99.30 282	99.48 178	98.86 77	99.21 229	99.63 227	98.72 64	99.90 141	98.25 219	99.63 157	99.80 82

114514_t		98.93 148	98.67 164	99.72 79	99.85 28	99.53 94	99.62 102	99.59 68	92.65 418	99.71 96	99.78 144	98.06 107	99.90 141	98.84 143	99.91 43	99.74 104

1112_ss		98.98 144	98.77 154	99.59 106	99.68 125	99.02 168	99.25 308	99.48 178	97.23 280	99.13 244	99.58 245	96.93 145	99.90 141	98.87 133	98.78 228	99.84 50

PHI-MVS		99.30 77	99.17 86	99.70 80	99.56 179	99.52 98	99.58 126	99.80 8	97.12 289	99.62 130	99.73 173	98.58 75	99.90 141	98.61 175	99.91 43	99.68 139

AdaColmap		99.01 142	98.80 150	99.66 84	99.56 179	99.54 91	99.18 326	99.70 15	98.18 160	99.35 195	99.63 227	96.32 169	99.90 141	97.48 293	99.77 130	99.55 185

COLMAP_ROB	97.56 6	98.86 158	98.75 156	99.17 197	99.88 13	98.53 230	99.34 273	99.59 68	97.55 244	98.70 319	99.89 37	95.83 189	99.90 141	98.10 229	99.90 54	99.08 267
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 206	98.03 226	99.31 172	99.63 150	98.56 227	99.54 159	96.75 436	97.53 248	99.73 89	99.65 215	91.25 355	99.89 156	98.62 172	99.56 163	99.48 210

tttt0517		98.42 197	98.14 211	99.28 184	99.66 138	98.38 247	99.74 47	96.85 434	97.68 229	99.79 68	99.74 167	91.39 351	99.89 156	98.83 146	99.56 163	99.57 181

test12				99.75 70	99.64 147	99.61 78		99.29 310		99.21 229		98.38 92	99.89 156		99.74 138	99.74 104

Test_1112_low_res		98.89 151	98.66 167	99.57 113	99.69 120	98.95 182	99.03 357	99.47 199	96.98 303	99.15 242	99.23 350	96.77 149	99.89 156	98.83 146	98.78 228	99.86 39

CNLPA		99.14 108	98.99 118	99.59 106	99.58 171	99.41 113	99.16 328	99.44 228	98.45 122	99.19 235	99.49 279	98.08 106	99.89 156	97.73 269	99.75 135	99.48 210

guyue		99.16 101	99.04 103	99.52 132	99.69 120	98.92 189	99.59 116	98.81 384	98.73 95	99.90 31	99.87 57	95.34 211	99.88 161	99.66 37	99.81 113	99.74 104

sd_testset		98.75 176	98.57 184	99.29 180	99.81 51	98.26 251	99.56 140	99.62 46	98.78 91	99.64 123	99.88 46	92.02 334	99.88 161	99.54 48	98.26 259	99.72 122

APD_test1		95.87 370	96.49 352	94.00 408	99.53 187	84.01 437	99.54 159	99.32 297	95.91 376	97.99 371	99.85 71	85.49 412	99.88 161	91.96 416	98.84 223	98.12 402

diffmvs		99.14 108	99.02 111	99.51 137	99.61 161	98.96 179	99.28 292	99.49 166	98.46 120	99.72 94	99.71 180	96.50 161	99.88 161	99.31 78	99.11 199	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		98.86 158	98.80 150	99.03 212	99.76 75	98.79 207	99.28 292	99.91 3	97.42 263	99.67 106	99.37 317	97.53 119	99.88 161	98.98 116	97.29 319	98.42 383

PVSNet_Blended		99.08 129	98.97 122	99.42 155	99.76 75	98.79 207	98.78 396	99.91 3	96.74 318	99.67 106	99.49 279	97.53 119	99.88 161	98.98 116	99.85 87	99.60 170

MVS		97.28 337	96.55 350	99.48 143	98.78 374	98.95 182	99.27 297	99.39 250	83.53 439	98.08 366	99.54 261	96.97 143	99.87 167	94.23 394	99.16 193	99.63 162

MG-MVS		99.13 110	99.02 111	99.45 150	99.57 175	98.63 220	99.07 347	99.34 279	98.99 62	99.61 133	99.82 97	97.98 110	99.87 167	97.00 324	99.80 118	99.85 43

MSDG		98.98 144	98.80 150	99.53 126	99.76 75	99.19 143	98.75 399	99.55 91	97.25 277	99.47 161	99.77 153	97.82 113	99.87 167	96.93 331	99.90 54	99.54 187

ETV-MVS		99.26 86	99.21 79	99.40 157	99.46 220	99.30 131	99.56 140	99.52 118	98.52 115	99.44 169	99.27 345	98.41 90	99.86 170	99.10 104	99.59 161	99.04 274

thisisatest0515		98.14 224	97.79 250	99.19 195	99.50 208	98.50 237	98.61 411	96.82 435	96.95 307	99.54 149	99.43 297	91.66 346	99.86 170	98.08 234	99.51 167	99.22 256

thres600view7		97.86 268	97.51 286	98.92 229	99.72 104	97.95 272	99.59 116	98.74 394	97.94 196	99.27 214	98.62 400	91.75 340	99.86 170	93.73 400	98.19 266	98.96 284

lupinMVS		99.13 110	99.01 116	99.46 149	99.51 196	98.94 185	99.05 352	99.16 333	97.86 204	99.80 66	99.56 253	97.39 122	99.86 170	98.94 121	99.85 87	99.58 178

PVSNet	96.02 17	98.85 165	98.84 147	98.89 238	99.73 100	97.28 301	98.32 427	99.60 62	97.86 204	99.50 156	99.57 250	96.75 150	99.86 170	98.56 187	99.70 145	99.54 187

MAR-MVS		98.86 158	98.63 172	99.54 118	99.37 248	99.66 64	99.45 218	99.54 100	96.61 330	99.01 268	99.40 307	97.09 136	99.86 170	97.68 276	99.53 166	99.10 262
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
testing91		97.44 329	97.02 338	98.71 267	99.18 300	96.89 332	99.19 324	99.04 350	97.78 217	98.31 353	98.29 414	85.41 413	99.85 176	98.01 240	97.95 276	99.39 234

test2506		96.81 352	96.65 348	97.29 382	99.74 93	92.21 425	99.60 109	85.06 456	99.13 34	99.77 77	99.93 10	87.82 399	99.85 176	99.38 67	99.38 176	99.80 82

AllTest		98.87 155	98.72 158	99.31 172	99.86 22	98.48 240	99.56 140	99.61 55	97.85 207	99.36 192	99.85 71	95.95 182	99.85 176	96.66 344	99.83 106	99.59 174

TestCases				99.31 172	99.86 22	98.48 240		99.61 55	97.85 207	99.36 192	99.85 71	95.95 182	99.85 176	96.66 344	99.83 106	99.59 174

jason		99.13 110	99.03 106	99.45 150	99.46 220	98.87 193	99.12 337	99.26 316	98.03 188	99.79 68	99.65 215	97.02 141	99.85 176	99.02 113	99.90 54	99.65 150
jason: jason.
CNVR-MVS		99.42 51	99.30 58	99.78 64	99.62 156	99.71 52	99.26 306	99.52 118	98.82 82	99.39 185	99.71 180	98.96 25	99.85 176	98.59 180	99.80 118	99.77 94

PAPM_NR		99.04 135	98.84 147	99.66 84	99.74 93	99.44 109	99.39 253	99.38 258	97.70 227	99.28 209	99.28 342	98.34 94	99.85 176	96.96 328	99.45 172	99.69 135

testing99		97.36 332	96.94 341	98.63 273	99.18 300	96.70 338	99.30 282	98.93 362	97.71 224	98.23 358	98.26 415	84.92 416	99.84 183	98.04 239	97.85 283	99.35 240

testing222		97.16 342	96.50 351	99.16 198	99.16 310	98.47 242	99.27 297	98.66 405	97.71 224	98.23 358	98.15 418	82.28 430	99.84 183	97.36 303	97.66 289	99.18 258

test1111		98.04 239	98.11 215	97.83 357	99.74 93	93.82 409	99.58 126	95.40 443	99.12 39	99.65 118	99.93 10	90.73 360	99.84 183	99.43 64	99.38 176	99.82 66

ECVR-MVS		98.04 239	98.05 224	98.00 341	99.74 93	94.37 404	99.59 116	94.98 444	99.13 34	99.66 111	99.93 10	90.67 361	99.84 183	99.40 65	99.38 176	99.80 82

test_yl		98.86 158	98.63 172	99.54 118	99.49 210	99.18 145	99.50 186	99.07 346	98.22 153	99.61 133	99.51 273	95.37 209	99.84 183	98.60 178	98.33 253	99.59 174

DCV-MVSNet		98.86 158	98.63 172	99.54 118	99.49 210	99.18 145	99.50 186	99.07 346	98.22 153	99.61 133	99.51 273	95.37 209	99.84 183	98.60 178	98.33 253	99.59 174

Fast-Effi-MVS+		98.70 180	98.43 192	99.51 137	99.51 196	99.28 134	99.52 169	99.47 199	96.11 369	99.01 268	99.34 327	96.20 173	99.84 183	97.88 248	98.82 225	99.39 234

TSAR-MVS + GP.		99.36 67	99.36 42	99.36 163	99.67 127	98.61 224	99.07 347	99.33 287	99.00 60	99.82 61	99.81 111	99.06 16	99.84 183	99.09 105	99.42 174	99.65 150

tpmrst		98.33 207	98.48 190	97.90 350	99.16 310	94.78 394	99.31 280	99.11 339	97.27 275	99.45 164	99.59 241	95.33 212	99.84 183	98.48 194	98.61 235	99.09 266

Vis-MVSNet		99.12 116	98.97 122	99.56 115	99.78 63	99.10 157	99.68 68	99.66 28	98.49 117	99.86 47	99.87 57	94.77 242	99.84 183	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		98.63 188	98.34 198	99.51 137	99.40 240	99.03 167	98.80 394	99.36 267	96.33 350	99.00 272	99.12 364	98.46 84	99.84 183	95.23 380	99.37 183	99.66 145

PatchMatch-RL		98.84 168	98.62 177	99.52 132	99.71 110	99.28 134	99.06 350	99.77 9	97.74 222	99.50 156	99.53 265	95.41 207	99.84 183	97.17 317	99.64 155	99.44 226

EPP-MVSNet		99.13 110	98.99 118	99.53 126	99.65 145	99.06 164	99.81 20	99.33 287	97.43 261	99.60 136	99.88 46	97.14 134	99.84 183	99.13 99	98.94 214	99.69 135

testing3-2		97.84 273	97.70 265	98.24 323	99.53 187	95.37 382	99.55 154	98.67 404	98.46 120	99.27 214	99.34 327	86.58 405	99.83 196	99.32 77	98.63 234	99.52 194

testing11		97.50 322	97.10 335	98.71 267	99.20 294	96.91 330	99.29 287	98.82 382	97.89 201	98.21 361	98.40 409	85.63 411	99.83 196	98.45 199	98.04 274	99.37 238

thres100view900		97.76 287	97.45 295	98.69 269	99.72 104	97.86 278	99.59 116	98.74 394	97.93 197	99.26 219	98.62 400	91.75 340	99.83 196	93.22 405	98.18 267	98.37 389

tfpn200view9		97.72 297	97.38 308	98.72 265	99.69 120	97.96 269	99.50 186	98.73 400	97.83 210	99.17 240	98.45 407	91.67 344	99.83 196	93.22 405	98.18 267	98.37 389

test_prior				99.68 82	99.67 127	99.48 104		99.56 83					99.83 196			99.74 104

1314		98.68 182	98.54 187	99.11 204	98.89 357	98.65 217	99.27 297	99.49 166	96.89 311	97.99 371	99.56 253	97.72 117	99.83 196	97.74 268	99.27 187	98.84 290

thres400		97.77 286	97.38 308	98.92 229	99.69 120	97.96 269	99.50 186	98.73 400	97.83 210	99.17 240	98.45 407	91.67 344	99.83 196	93.22 405	98.18 267	98.96 284

casdiffmvs		99.13 110	98.98 121	99.56 115	99.65 145	99.16 148	99.56 140	99.50 156	98.33 137	99.41 178	99.86 64	95.92 185	99.83 196	99.45 63	99.16 193	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	99.69 195	98.55 78	99.82 204	99.69 32	99.85 87	99.48 210

MVS_Test		99.10 126	98.97 122	99.48 143	99.49 210	99.14 153	99.67 71	99.34 279	97.31 272	99.58 140	99.76 157	97.65 118	99.82 204	98.87 133	99.07 205	99.46 221

dp		97.75 291	97.80 249	97.59 373	99.10 321	93.71 412	99.32 277	98.88 375	96.48 342	99.08 256	99.55 256	92.67 318	99.82 204	96.52 348	98.58 238	99.24 254

RPSCF		98.22 214	98.62 177	96.99 388	99.82 47	91.58 427	99.72 53	99.44 228	96.61 330	99.66 111	99.89 37	95.92 185	99.82 204	97.46 296	99.10 202	99.57 181

PMMVS		98.80 172	98.62 177	99.34 165	99.27 276	98.70 213	98.76 398	99.31 301	97.34 269	99.21 229	99.07 366	97.20 133	99.82 204	98.56 187	98.87 220	99.52 194

UBG		97.85 269	97.48 289	98.95 223	99.25 283	97.64 289	99.24 311	98.74 394	97.90 200	98.64 329	98.20 417	88.65 386	99.81 209	98.27 217	98.40 248	99.42 228

EIA-MVS		99.18 97	99.09 97	99.45 150	99.49 210	99.18 145	99.67 71	99.53 113	97.66 232	99.40 183	99.44 295	98.10 104	99.81 209	98.94 121	99.62 158	99.35 240

Effi-MVS+		98.81 169	98.59 183	99.48 143	99.46 220	99.12 156	98.08 434	99.50 156	97.50 252	99.38 187	99.41 303	96.37 168	99.81 209	99.11 101	98.54 243	99.51 202

thres200		97.61 313	97.28 324	98.62 274	99.64 147	98.03 263	99.26 306	98.74 394	97.68 229	99.09 254	98.32 413	91.66 346	99.81 209	92.88 410	98.22 262	98.03 408

tpmvs		97.98 250	98.02 228	97.84 356	99.04 335	94.73 395	99.31 280	99.20 328	96.10 373	98.76 309	99.42 299	94.94 228	99.81 209	96.97 327	98.45 247	98.97 282

casdiffmvs_mvg		99.15 104	99.02 111	99.55 117	99.66 138	99.09 158	99.64 91	99.56 83	98.26 145	99.45 164	99.87 57	96.03 179	99.81 209	99.54 48	99.15 196	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	98.81 169	99.37 40	97.12 386	99.60 167	91.75 426	98.61 411	99.44 228	99.35 22	99.83 58	99.85 71	98.70 66	99.81 209	99.02 113	99.91 43	99.81 73

DPM-MVS		98.95 147	98.71 160	99.66 84	99.63 150	99.55 89	98.64 410	99.10 340	97.93 197	99.42 174	99.55 256	98.67 69	99.80 216	95.80 365	99.68 149	99.61 167

DP-MVS Recon		99.12 116	98.95 128	99.65 88	99.74 93	99.70 54	99.27 297	99.57 78	96.40 349	99.42 174	99.68 202	98.75 58	99.80 216	97.98 242	99.72 141	99.44 226

MVS_111021_LR		99.41 55	99.33 48	99.65 88	99.77 71	99.51 100	98.94 380	99.85 6	98.82 82	99.65 118	99.74 167	98.51 81	99.80 216	98.83 146	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	99.70 184	98.65 71	99.79 219	99.65 38	99.78 127	99.41 231

Fast-Effi-MVS+-dtu		98.77 175	98.83 149	98.60 275	99.41 235	96.99 324	99.52 169	99.49 166	98.11 171	99.24 221	99.34 327	96.96 144	99.79 219	97.95 244	99.45 172	99.02 277

baseline1		98.31 208	97.95 235	99.38 162	99.50 208	98.74 210	99.59 116	98.93 362	98.41 127	99.14 243	99.60 239	94.59 254	99.79 219	98.48 194	93.29 402	99.61 167

baseline		99.15 104	99.02 111	99.53 126	99.66 138	99.14 153	99.72 53	99.48 178	98.35 134	99.42 174	99.84 83	96.07 176	99.79 219	99.51 53	99.14 197	99.67 142

PVSNet_0	94.43 19	96.09 367	95.47 374	97.94 346	99.31 266	94.34 406	97.81 436	99.70 15	97.12 289	97.46 386	98.75 397	89.71 372	99.79 219	97.69 275	81.69 439	99.68 139

API-MVS		99.04 135	99.03 106	99.06 208	99.40 240	99.31 128	99.55 154	99.56 83	98.54 113	99.33 199	99.39 311	98.76 55	99.78 224	96.98 326	99.78 127	98.07 405

OMC-MVS		99.08 129	99.04 103	99.20 194	99.67 127	98.22 253	99.28 292	99.52 118	98.07 179	99.66 111	99.81 111	97.79 114	99.78 224	97.79 260	99.81 113	99.60 170

GeoE		98.85 165	98.62 177	99.53 126	99.61 161	99.08 161	99.80 25	99.51 136	97.10 293	99.31 201	99.78 144	95.23 219	99.77 226	98.21 221	99.03 208	99.75 100

alignmvs		98.81 169	98.56 186	99.58 109	99.43 228	99.42 111	99.51 178	98.96 360	98.61 106	99.35 195	98.92 387	94.78 239	99.77 226	99.35 69	98.11 272	99.54 187

tpm cat1		97.39 331	97.36 310	97.50 376	99.17 308	93.73 411	99.43 229	99.31 301	91.27 422	98.71 313	99.08 365	94.31 269	99.77 226	96.41 353	98.50 245	99.00 278

CostFormer		97.72 297	97.73 262	97.71 365	99.15 314	94.02 408	99.54 159	99.02 353	94.67 397	99.04 265	99.35 323	92.35 330	99.77 226	98.50 193	97.94 277	99.34 243

MGCFI-Net		99.01 142	98.85 145	99.50 142	99.42 230	99.26 137	99.82 16	99.48 178	98.60 108	99.28 209	98.81 392	97.04 140	99.76 230	99.29 83	97.87 281	99.47 216

test_241102_ONE					99.84 34	99.90 2		99.48 178	99.07 51	99.91 28	99.74 167	99.20 7	99.76 230

MDTV_nov1_ep13			98.32 200		99.11 318	94.44 402	99.27 297	98.74 394	97.51 251	99.40 183	99.62 232	94.78 239	99.76 230	97.59 280	98.81 227

sasdasda		99.02 138	98.86 143	99.51 137	99.42 230	99.32 124	99.80 25	99.48 178	98.63 103	99.31 201	98.81 392	97.09 136	99.75 233	99.27 87	97.90 278	99.47 216

canonicalmvs		99.02 138	98.86 143	99.51 137	99.42 230	99.32 124	99.80 25	99.48 178	98.63 103	99.31 201	98.81 392	97.09 136	99.75 233	99.27 87	97.90 278	99.47 216

Effi-MVS+-dtu		98.78 173	98.89 138	98.47 296	99.33 258	96.91 330	99.57 133	99.30 306	98.47 119	99.41 178	98.99 377	96.78 148	99.74 235	98.73 157	99.38 176	98.74 306

patchmatchnet-post											98.70 398	94.79 238	99.74 235

SCA		98.19 218	98.16 208	98.27 322	99.30 267	95.55 373	99.07 347	98.97 358	97.57 241	99.43 171	99.57 250	92.72 313	99.74 235	97.58 281	99.20 191	99.52 194

BH-untuned		98.42 197	98.36 196	98.59 276	99.49 210	96.70 338	99.27 297	99.13 337	97.24 279	98.80 304	99.38 314	95.75 195	99.74 235	97.07 322	99.16 193	99.33 244

BH-RMVSNet		98.41 199	98.08 220	99.40 157	99.41 235	98.83 201	99.30 282	98.77 390	97.70 227	98.94 282	99.65 215	92.91 308	99.74 235	96.52 348	99.55 165	99.64 157

MVS_111021_HR		99.41 55	99.32 50	99.66 84	99.72 104	99.47 106	98.95 378	99.85 6	98.82 82	99.54 149	99.73 173	98.51 81	99.74 235	98.91 127	99.88 69	99.77 94

test_post											65.99 450	94.65 252	99.73 241

XVG-ACMP-BASELINE		97.83 276	97.71 264	98.20 325	99.11 318	96.33 354	99.41 241	99.52 118	98.06 183	99.05 264	99.50 276	89.64 374	99.73 241	97.73 269	97.38 316	98.53 371

HyFIR lowres test		99.11 122	98.92 131	99.65 88	99.90 4	99.37 116	99.02 360	99.91 3	97.67 231	99.59 139	99.75 162	95.90 187	99.73 241	99.53 50	99.02 210	99.86 39

DeepMVS_CX				93.34 411	99.29 271	82.27 440		99.22 324	85.15 437	96.33 408	99.05 369	90.97 358	99.73 241	93.57 402	97.77 286	98.01 409

Patchmatch-test		97.93 256	97.65 270	98.77 261	99.18 300	97.07 315	99.03 357	99.14 336	96.16 364	98.74 310	99.57 250	94.56 256	99.72 245	93.36 404	99.11 199	99.52 194

LPG-MVS_test		98.22 214	98.13 213	98.49 289	99.33 258	97.05 317	99.58 126	99.55 91	97.46 254	99.24 221	99.83 88	92.58 320	99.72 245	98.09 230	97.51 302	98.68 324

LGP-MVS_train				98.49 289	99.33 258	97.05 317		99.55 91	97.46 254	99.24 221	99.83 88	92.58 320	99.72 245	98.09 230	97.51 302	98.68 324

BH-w/o		98.00 248	97.89 244	98.32 314	99.35 252	96.20 360	99.01 365	98.90 372	96.42 347	98.38 349	99.00 375	95.26 216	99.72 245	96.06 358	98.61 235	99.03 275

ACMP	97.20 11	98.06 233	97.94 237	98.45 299	99.37 248	97.01 322	99.44 224	99.49 166	97.54 247	98.45 346	99.79 137	91.95 336	99.72 245	97.91 246	97.49 307	98.62 354
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 243	97.90 240	98.40 307	99.23 287	96.80 336	99.70 58	99.60 62	97.12 289	98.18 363	99.70 184	91.73 342	99.72 245	98.39 204	97.45 309	98.68 324
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							99.23 314				65.14 451	94.18 274	99.71 251	97.58 281

ADS-MVSNet		98.20 217	98.08 220	98.56 283	99.33 258	96.48 349	99.23 314	99.15 334	96.24 357	99.10 251	99.67 208	94.11 275	99.71 251	96.81 336	99.05 206	99.48 210

JIA-IIPM		97.50 322	97.02 338	98.93 227	98.73 383	97.80 280	99.30 282	98.97 358	91.73 421	98.91 285	94.86 439	95.10 223	99.71 251	97.58 281	97.98 275	99.28 248

EPMVS		97.82 279	97.65 270	98.35 311	98.88 358	95.98 364	99.49 198	94.71 446	97.57 241	99.26 219	99.48 285	92.46 327	99.71 251	97.87 250	99.08 204	99.35 240

TDRefinement		95.42 378	94.57 386	97.97 343	89.83 449	96.11 363	99.48 203	98.75 391	96.74 318	96.68 405	99.88 46	88.65 386	99.71 251	98.37 207	82.74 438	98.09 404

ACMM	97.58 5	98.37 205	98.34 198	98.48 291	99.41 235	97.10 311	99.56 140	99.45 219	98.53 114	99.04 265	99.85 71	93.00 304	99.71 251	98.74 155	97.45 309	98.64 345
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 253	97.77 255	98.57 280	99.59 169	96.61 345	99.45 218	99.08 343	98.21 155	98.88 290	99.80 125	88.66 385	99.70 257	98.58 181	97.72 287	99.39 234

CHOSEN 280x420		99.12 116	99.13 89	99.08 205	99.66 138	97.89 275	98.43 421	99.71 13	98.88 76	99.62 130	99.76 157	96.63 154	99.70 257	99.46 62	99.99 1	99.66 145

EC-MVSNet		99.44 46	99.39 36	99.58 109	99.56 179	99.49 102	99.88 4	99.58 73	98.38 129	99.73 89	99.69 195	98.20 100	99.70 257	99.64 40	99.82 110	99.54 187

PatchmatchNet		98.31 208	98.36 196	98.19 326	99.16 310	95.32 383	99.27 297	98.92 365	97.37 267	99.37 189	99.58 245	94.90 232	99.70 257	97.43 299	99.21 190	99.54 187
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 228	97.99 230	98.44 302	99.41 235	96.96 328	99.60 109	99.56 83	98.09 174	98.15 364	99.91 24	90.87 359	99.70 257	98.88 130	97.45 309	98.67 332
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 322	96.90 342	99.29 180	99.23 287	98.78 209	99.32 277	98.90 372	97.52 250	98.56 339	98.09 423	84.72 418	99.69 262	97.86 251	97.88 280	99.39 234

HQP_MVS		98.27 213	98.22 206	98.44 302	99.29 271	96.97 326	99.39 253	99.47 199	98.97 68	99.11 248	99.61 236	92.71 315	99.69 262	97.78 261	97.63 290	98.67 332

plane_prior5								99.47 199					99.69 262	97.78 261	97.63 290	98.67 332

D2MVS		98.41 199	98.50 189	98.15 331	99.26 279	96.62 344	99.40 249	99.61 55	97.71 224	98.98 275	99.36 320	96.04 178	99.67 265	98.70 160	97.41 314	98.15 401

IS-MVSNet		99.05 134	98.87 141	99.57 113	99.73 100	99.32 124	99.75 42	99.20 328	98.02 191	99.56 144	99.86 64	96.54 159	99.67 265	98.09 230	99.13 198	99.73 113

CLD-MVS		98.16 222	98.10 216	98.33 312	99.29 271	96.82 335	98.75 399	99.44 228	97.83 210	99.13 244	99.55 256	92.92 306	99.67 265	98.32 214	97.69 288	98.48 375
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 339	97.30 321	97.09 387	99.43 228	93.31 418	99.73 51	98.87 377	98.83 81	99.28 209	99.80 125	84.45 419	99.66 268	97.88 248	97.45 309	98.30 391

AUN-MVS		96.88 350	96.31 356	98.59 276	99.48 217	97.04 320	99.27 297	99.22 324	97.44 260	98.51 342	99.41 303	91.97 335	99.66 268	97.71 272	83.83 436	99.07 272

UniMVSNet_ETH3D		97.32 336	96.81 344	98.87 244	99.40 240	97.46 295	99.51 178	99.53 113	95.86 377	98.54 341	99.77 153	82.44 428	99.66 268	98.68 165	97.52 301	99.50 206

OPM-MVS		98.19 218	98.10 216	98.45 299	98.88 358	97.07 315	99.28 292	99.38 258	98.57 110	99.22 226	99.81 111	92.12 332	99.66 268	98.08 234	97.54 299	98.61 363
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 259	97.78 253	98.32 314	99.46 220	96.68 342	99.56 140	99.54 100	98.41 127	97.79 382	99.87 57	90.18 368	99.66 268	98.05 238	97.18 324	98.62 354

hse-mvs2		97.50 322	97.14 332	98.59 276	99.49 210	97.05 317	99.28 292	99.22 324	98.94 71	99.66 111	99.42 299	94.93 229	99.65 273	99.48 59	83.80 437	99.08 267

VPA-MVSNet		98.29 211	97.95 235	99.30 177	99.16 310	99.54 91	99.50 186	99.58 73	98.27 143	99.35 195	99.37 317	92.53 322	99.65 273	99.35 69	94.46 383	98.72 308

TR-MVS		97.76 287	97.41 306	98.82 253	99.06 330	97.87 276	98.87 388	98.56 408	96.63 329	98.68 321	99.22 351	92.49 323	99.65 273	95.40 376	97.79 285	98.95 286

reproduce_monomvs		97.89 263	97.87 245	97.96 345	99.51 196	95.45 378	99.60 109	99.25 318	99.17 29	98.85 298	99.49 279	89.29 377	99.64 276	99.35 69	96.31 340	98.78 294

gm-plane-assit					98.54 403	92.96 420			94.65 398		99.15 359		99.64 276	97.56 286

HQP4-MVS										98.66 322			99.64 276			98.64 345

HQP-MVS		98.02 243	97.90 240	98.37 310	99.19 297	96.83 333	98.98 371	99.39 250	98.24 149	98.66 322	99.40 307	92.47 324	99.64 276	97.19 314	97.58 295	98.64 345

PAPM		97.59 314	97.09 336	99.07 206	99.06 330	98.26 251	98.30 428	99.10 340	94.88 392	98.08 366	99.34 327	96.27 171	99.64 276	89.87 424	98.92 217	99.31 246

TAPA-MVS	97.07 15	97.74 293	97.34 315	98.94 225	99.70 115	97.53 292	99.25 308	99.51 136	91.90 420	99.30 205	99.63 227	98.78 51	99.64 276	88.09 431	99.87 72	99.65 150
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 203	98.09 219	99.24 190	99.26 279	99.32 124	99.56 140	99.55 91	97.45 257	98.71 313	99.83 88	93.23 299	99.63 282	98.88 130	96.32 339	98.76 300

ITE_SJBPF				98.08 334	99.29 271	96.37 352		98.92 365	98.34 135	98.83 299	99.75 162	91.09 356	99.62 283	95.82 363	97.40 315	98.25 395

LF4IMVS		97.52 319	97.46 294	97.70 366	98.98 346	95.55 373	99.29 287	98.82 382	98.07 179	98.66 322	99.64 221	89.97 369	99.61 284	97.01 323	96.68 329	97.94 416

tpm		97.67 308	97.55 279	98.03 336	99.02 337	95.01 390	99.43 229	98.54 410	96.44 345	99.12 246	99.34 327	91.83 339	99.60 285	97.75 267	96.46 335	99.48 210

tpm2		97.44 329	97.34 315	97.74 364	99.15 314	94.36 405	99.45 218	98.94 361	93.45 411	98.90 287	99.44 295	91.35 352	99.59 286	97.31 305	98.07 273	99.29 247

SD_0403		97.55 316	97.53 283	97.62 369	99.61 161	93.64 415	99.72 53	99.44 228	98.03 188	98.62 334	99.39 311	96.06 177	99.57 287	87.88 433	99.01 211	99.66 145

baseline2		97.87 266	97.55 279	98.82 253	99.18 300	98.02 264	99.41 241	96.58 440	96.97 304	96.51 406	99.17 356	93.43 294	99.57 287	97.71 272	99.03 208	98.86 288

MS-PatchMatch		97.24 341	97.32 319	96.99 388	98.45 406	93.51 417	98.82 392	99.32 297	97.41 264	98.13 365	99.30 338	88.99 379	99.56 289	95.68 369	99.80 118	97.90 419

TinyColmap		97.12 344	96.89 343	97.83 357	99.07 328	95.52 376	98.57 414	98.74 394	97.58 240	97.81 381	99.79 137	88.16 393	99.56 289	95.10 381	97.21 322	98.39 387

USDC		97.34 334	97.20 329	97.75 362	99.07 328	95.20 385	98.51 418	99.04 350	97.99 192	98.31 353	99.86 64	89.02 378	99.55 291	95.67 370	97.36 317	98.49 374

MSLP-MVS++		99.46 38	99.47 22	99.44 154	99.60 167	99.16 148	99.41 241	99.71 13	98.98 65	99.45 164	99.78 144	99.19 9	99.54 292	99.28 84	99.84 95	99.63 162

UWE-MVS-28		97.36 332	97.24 328	97.75 362	98.84 367	94.44 402	99.24 311	97.58 429	97.98 193	99.00 272	99.00 375	91.35 352	99.53 293	93.75 399	98.39 249	99.27 252

TAMVS		99.12 116	99.08 98	99.24 190	99.46 220	98.55 228	99.51 178	99.46 208	98.09 174	99.45 164	99.82 97	98.34 94	99.51 294	98.70 160	98.93 215	99.67 142

EPNet_dtu		98.03 241	97.96 233	98.23 324	98.27 409	95.54 375	99.23 314	98.75 391	99.02 55	97.82 380	99.71 180	96.11 175	99.48 295	93.04 408	99.65 154	99.69 135
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 354	96.22 358	97.97 343	97.00 431	96.28 356	98.66 408	99.03 352	96.61 330	96.93 403	99.79 137	87.20 402	99.47 296	96.65 346	94.13 390	98.16 400

EG-PatchMatch MVS		95.97 369	95.69 370	96.81 395	97.78 416	92.79 421	99.16 328	98.93 362	96.16 364	94.08 424	99.22 351	82.72 426	99.47 296	95.67 370	97.50 304	98.17 399

myMVS_eth3d28		97.69 302	97.34 315	98.73 263	99.27 276	97.52 293	99.33 275	98.78 389	98.03 188	98.82 301	98.49 405	86.64 404	99.46 298	98.44 200	98.24 261	99.23 255

MVP-Stereo		97.81 281	97.75 260	97.99 342	97.53 420	96.60 346	98.96 375	98.85 379	97.22 281	97.23 393	99.36 320	95.28 213	99.46 298	95.51 372	99.78 127	97.92 418
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 190	98.67 164	98.30 316	99.35 252	95.59 372	99.50 186	99.55 91	98.60 108	99.39 185	99.83 88	94.48 262	99.45 300	98.75 154	98.56 241	99.85 43

test-LLR		98.06 233	97.90 240	98.55 285	98.79 371	97.10 311	98.67 405	97.75 425	97.34 269	98.61 335	98.85 389	94.45 264	99.45 300	97.25 308	99.38 176	99.10 262

TESTMET0.1,1		97.55 316	97.27 327	98.40 307	98.93 351	96.53 347	98.67 405	97.61 428	96.96 305	98.64 329	99.28 342	88.63 388	99.45 300	97.30 306	99.38 176	99.21 257

test-mter		97.49 327	97.13 334	98.55 285	98.79 371	97.10 311	98.67 405	97.75 425	96.65 325	98.61 335	98.85 389	88.23 392	99.45 300	97.25 308	99.38 176	99.10 262

mvs_anonymous		99.03 137	98.99 118	99.16 198	99.38 245	98.52 234	99.51 178	99.38 258	97.79 215	99.38 187	99.81 111	97.30 128	99.45 300	99.35 69	98.99 212	99.51 202

tfpnnormal		97.84 273	97.47 292	98.98 218	99.20 294	99.22 142	99.64 91	99.61 55	96.32 351	98.27 357	99.70 184	93.35 298	99.44 305	95.69 368	95.40 366	98.27 393

v7n		97.87 266	97.52 284	98.92 229	98.76 381	98.58 226	99.84 12	99.46 208	96.20 360	98.91 285	99.70 184	94.89 233	99.44 305	96.03 359	93.89 395	98.75 302

jajsoiax		98.43 196	98.28 203	98.88 240	98.60 398	98.43 244	99.82 16	99.53 113	98.19 157	98.63 331	99.80 125	93.22 301	99.44 305	99.22 91	97.50 304	98.77 298

mvs_tets		98.40 202	98.23 205	98.91 233	98.67 391	98.51 236	99.66 78	99.53 113	98.19 157	98.65 328	99.81 111	92.75 310	99.44 305	99.31 78	97.48 308	98.77 298

sc_t1		95.75 373	95.05 380	97.87 352	98.83 368	94.61 399	99.21 320	99.45 219	87.45 433	97.97 373	99.85 71	81.19 433	99.43 309	98.27 217	93.20 404	99.57 181

Vis-MVSNet (Re-imp)		98.87 155	98.72 158	99.31 172	99.71 110	98.88 192	99.80 25	99.44 228	97.91 199	99.36 192	99.78 144	95.49 205	99.43 309	97.91 246	99.11 199	99.62 165

OPU-MVS				99.64 94	99.56 179	99.72 50	99.60 109				99.70 184	99.27 5	99.42 311	98.24 220	99.80 118	99.79 86

Anonymous20231211		97.88 264	97.54 282	98.90 235	99.71 110	98.53 230	99.48 203	99.57 78	94.16 402	98.81 302	99.68 202	93.23 299	99.42 311	98.84 143	94.42 385	98.76 300

ttmdpeth		97.80 283	97.63 274	98.29 317	98.77 379	97.38 298	99.64 91	99.36 267	98.78 91	96.30 409	99.58 245	92.34 331	99.39 313	98.36 209	95.58 361	98.10 403

VPNet		97.84 273	97.44 300	99.01 214	99.21 292	98.94 185	99.48 203	99.57 78	98.38 129	99.28 209	99.73 173	88.89 380	99.39 313	99.19 93	93.27 403	98.71 310

nrg030		98.64 187	98.42 193	99.28 184	99.05 333	99.69 56	99.81 20	99.46 208	98.04 186	99.01 268	99.82 97	96.69 152	99.38 315	99.34 74	94.59 382	98.78 294

GA-MVS		97.85 269	97.47 292	99.00 216	99.38 245	97.99 266	98.57 414	99.15 334	97.04 300	98.90 287	99.30 338	89.83 371	99.38 315	96.70 341	98.33 253	99.62 165

UniMVSNet (Re)		98.29 211	98.00 229	99.13 203	99.00 340	99.36 119	99.49 198	99.51 136	97.95 195	98.97 277	99.13 361	96.30 170	99.38 315	98.36 209	93.34 401	98.66 341

FIs		98.78 173	98.63 172	99.23 192	99.18 300	99.54 91	99.83 15	99.59 68	98.28 141	98.79 306	99.81 111	96.75 150	99.37 318	99.08 106	96.38 337	98.78 294

PS-MVSNAJss		98.92 149	98.92 131	98.90 235	98.78 374	98.53 230	99.78 32	99.54 100	98.07 179	99.00 272	99.76 157	99.01 18	99.37 318	99.13 99	97.23 321	98.81 291

CDS-MVSNet		99.09 127	99.03 106	99.25 187	99.42 230	98.73 211	99.45 218	99.46 208	98.11 171	99.46 163	99.77 153	98.01 109	99.37 318	98.70 160	98.92 217	99.66 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 373	95.16 378	97.51 375	99.30 267	93.69 413	98.88 386	95.78 441	85.09 438	98.78 307	92.65 441	91.29 354	99.37 318	94.85 386	99.85 87	99.46 221

v1192		97.81 281	97.44 300	98.91 233	98.88 358	98.68 214	99.51 178	99.34 279	96.18 362	99.20 232	99.34 327	94.03 279	99.36 322	95.32 378	95.18 370	98.69 319

EI-MVSNet		98.67 183	98.67 164	98.68 270	99.35 252	97.97 267	99.50 186	99.38 258	96.93 310	99.20 232	99.83 88	97.87 111	99.36 322	98.38 205	97.56 297	98.71 310

MVSTER		98.49 191	98.32 200	99.00 216	99.35 252	99.02 168	99.54 159	99.38 258	97.41 264	99.20 232	99.73 173	93.86 287	99.36 322	98.87 133	97.56 297	98.62 354

gg-mvs-nofinetune		96.17 365	95.32 377	98.73 263	98.79 371	98.14 257	99.38 258	94.09 447	91.07 425	98.07 369	91.04 445	89.62 375	99.35 325	96.75 338	99.09 203	98.68 324

pm-mvs1		97.68 305	97.28 324	98.88 240	99.06 330	98.62 222	99.50 186	99.45 219	96.32 351	97.87 378	99.79 137	92.47 324	99.35 325	97.54 288	93.54 399	98.67 332

OurMVSNet-221017-0		97.88 264	97.77 255	98.19 326	98.71 387	96.53 347	99.88 4	99.00 355	97.79 215	98.78 307	99.94 6	91.68 343	99.35 325	97.21 310	96.99 328	98.69 319

EGC-MVSNET		82.80 410	77.86 416	97.62 369	97.91 413	96.12 362	99.33 275	99.28 312	8.40 453	25.05 454	99.27 345	84.11 420	99.33 328	89.20 426	98.22 262	97.42 427

pmmvs6		96.53 357	96.09 362	97.82 359	98.69 389	95.47 377	99.37 260	99.47 199	93.46 410	97.41 387	99.78 144	87.06 403	99.33 328	96.92 333	92.70 411	98.65 343

V42		98.06 233	97.79 250	98.86 247	98.98 346	98.84 198	99.69 62	99.34 279	96.53 337	99.30 205	99.37 317	94.67 250	99.32 330	97.57 285	94.66 380	98.42 383

lessismore_v0				97.79 361	98.69 389	95.44 380		94.75 445		95.71 415	99.87 57	88.69 384	99.32 330	95.89 362	94.93 377	98.62 354

OpenMVS_ROB	92.34 20	94.38 390	93.70 396	96.41 400	97.38 422	93.17 419	99.06 350	98.75 391	86.58 436	94.84 422	98.26 415	81.53 431	99.32 330	89.01 427	97.87 281	96.76 430

v8		97.95 255	97.63 274	98.93 227	98.95 350	98.81 206	99.80 25	99.41 240	96.03 374	99.10 251	99.42 299	94.92 231	99.30 333	96.94 330	94.08 392	98.66 341

v1921920		97.80 283	97.45 295	98.84 251	98.80 370	98.53 230	99.52 169	99.34 279	96.15 366	99.24 221	99.47 288	93.98 281	99.29 334	95.40 376	95.13 372	98.69 319

anonymousdsp		98.44 195	98.28 203	98.94 225	98.50 404	98.96 179	99.77 34	99.50 156	97.07 295	98.87 293	99.77 153	94.76 243	99.28 335	98.66 167	97.60 293	98.57 369

MVSFormer		99.17 99	99.12 91	99.29 180	99.51 196	98.94 185	99.88 4	99.46 208	97.55 244	99.80 66	99.65 215	97.39 122	99.28 335	99.03 111	99.85 87	99.65 150

test_djsdf		98.67 183	98.57 184	98.98 218	98.70 388	98.91 190	99.88 4	99.46 208	97.55 244	99.22 226	99.88 46	95.73 196	99.28 335	99.03 111	97.62 292	98.75 302

VortexMVS		98.67 183	98.66 167	98.68 270	99.62 156	97.96 269	99.59 116	99.41 240	98.13 167	99.31 201	99.70 184	95.48 206	99.27 338	99.40 65	97.32 318	98.79 292

SSC-MVS3.2		97.34 334	97.15 331	97.93 347	99.02 337	95.76 369	99.48 203	99.58 73	97.62 236	99.09 254	99.53 265	87.95 395	99.27 338	96.42 351	95.66 359	98.75 302

cascas		97.69 302	97.43 304	98.48 291	98.60 398	97.30 300	98.18 432	99.39 250	92.96 414	98.41 347	98.78 396	93.77 290	99.27 338	98.16 227	98.61 235	98.86 288

v144192		97.92 259	97.60 277	98.87 244	98.83 368	98.65 217	99.55 154	99.34 279	96.20 360	99.32 200	99.40 307	94.36 266	99.26 341	96.37 355	95.03 374	98.70 315

dmvs_re		98.08 231	98.16 208	97.85 354	99.55 183	94.67 398	99.70 58	98.92 365	98.15 162	99.06 262	99.35 323	93.67 293	99.25 342	97.77 264	97.25 320	99.64 157

v2v482		98.06 233	97.77 255	98.92 229	98.90 356	98.82 204	99.57 133	99.36 267	96.65 325	99.19 235	99.35 323	94.20 271	99.25 342	97.72 271	94.97 375	98.69 319

v1240		97.69 302	97.32 319	98.79 259	98.85 365	98.43 244	99.48 203	99.36 267	96.11 369	99.27 214	99.36 320	93.76 291	99.24 344	94.46 390	95.23 369	98.70 315

WBMVS		97.74 293	97.50 287	98.46 297	99.24 285	97.43 296	99.21 320	99.42 237	97.45 257	98.96 279	99.41 303	88.83 381	99.23 345	98.94 121	96.02 345	98.71 310

v1144		97.98 250	97.69 266	98.85 250	98.87 361	98.66 216	99.54 159	99.35 274	96.27 355	99.23 225	99.35 323	94.67 250	99.23 345	96.73 339	95.16 371	98.68 324

v10		97.85 269	97.52 284	98.86 247	98.99 343	98.67 215	99.75 42	99.41 240	95.70 378	98.98 275	99.41 303	94.75 244	99.23 345	96.01 361	94.63 381	98.67 332

WR-MVS_H		98.13 225	97.87 245	98.90 235	99.02 337	98.84 198	99.70 58	99.59 68	97.27 275	98.40 348	99.19 355	95.53 203	99.23 345	98.34 211	93.78 397	98.61 363

miper_enhance_ethall		98.16 222	98.08 220	98.41 305	98.96 349	97.72 284	98.45 420	99.32 297	96.95 307	98.97 277	99.17 356	97.06 139	99.22 349	97.86 251	95.99 348	98.29 392

GG-mvs-BLEND				98.45 299	98.55 402	98.16 255	99.43 229	93.68 448		97.23 393	98.46 406	89.30 376	99.22 349	95.43 375	98.22 262	97.98 414

FC-MVSNet-test		98.75 176	98.62 177	99.15 202	99.08 327	99.45 108	99.86 11	99.60 62	98.23 152	98.70 319	99.82 97	96.80 147	99.22 349	99.07 107	96.38 337	98.79 292

UniMVSNet_NR-MVSNet		98.22 214	97.97 232	98.96 221	98.92 353	98.98 172	99.48 203	99.53 113	97.76 219	98.71 313	99.46 292	96.43 166	99.22 349	98.57 184	92.87 409	98.69 319

DU-MVS		98.08 231	97.79 250	98.96 221	98.87 361	98.98 172	99.41 241	99.45 219	97.87 203	98.71 313	99.50 276	94.82 235	99.22 349	98.57 184	92.87 409	98.68 324

cl____		98.01 246	97.84 248	98.55 285	99.25 283	97.97 267	98.71 403	99.34 279	96.47 344	98.59 338	99.54 261	95.65 199	99.21 354	97.21 310	95.77 354	98.46 380

WR-MVS		98.06 233	97.73 262	99.06 208	98.86 364	99.25 139	99.19 324	99.35 274	97.30 273	98.66 322	99.43 297	93.94 282	99.21 354	98.58 181	94.28 387	98.71 310

test_0402		96.64 355	96.24 357	97.85 354	98.85 365	96.43 351	99.44 224	99.26 316	93.52 408	96.98 401	99.52 269	88.52 389	99.20 356	92.58 415	97.50 304	97.93 417

SixPastTwentyTwo		97.50 322	97.33 318	98.03 336	98.65 392	96.23 359	99.77 34	98.68 403	97.14 286	97.90 376	99.93 10	90.45 362	99.18 357	97.00 324	96.43 336	98.67 332

cl22		97.85 269	97.64 273	98.48 291	99.09 324	97.87 276	98.60 413	99.33 287	97.11 292	98.87 293	99.22 351	92.38 329	99.17 358	98.21 221	95.99 348	98.42 383

tt0320		95.71 375	95.07 379	97.62 369	99.05 333	95.02 389	99.25 308	99.52 118	86.81 434	97.97 373	99.72 177	83.58 423	99.15 359	96.38 354	93.35 400	98.68 324

WB-MVSnew		97.65 310	97.65 270	97.63 368	98.78 374	97.62 290	99.13 334	98.33 413	97.36 268	99.07 257	98.94 383	95.64 200	99.15 359	92.95 409	98.68 233	96.12 437

IterMVS-SCA-FT		97.82 279	97.75 260	98.06 335	99.57 175	96.36 353	99.02 360	99.49 166	97.18 283	98.71 313	99.72 177	92.72 313	99.14 361	97.44 298	95.86 353	98.67 332

pmmvs5		97.52 319	97.30 321	98.16 328	98.57 401	96.73 337	99.27 297	98.90 372	96.14 367	98.37 350	99.53 265	91.54 349	99.14 361	97.51 290	95.87 352	98.63 352

v148		97.79 285	97.55 279	98.50 288	98.74 382	97.72 284	99.54 159	99.33 287	96.26 356	98.90 287	99.51 273	94.68 249	99.14 361	97.83 255	93.15 406	98.63 352

miper_ehance_all_eth		98.18 220	98.10 216	98.41 305	99.23 287	97.72 284	98.72 402	99.31 301	96.60 333	98.88 290	99.29 340	97.29 129	99.13 364	97.60 279	95.99 348	98.38 388

NR-MVSNet		97.97 253	97.61 276	99.02 213	98.87 361	99.26 137	99.47 212	99.42 237	97.63 234	97.08 399	99.50 276	95.07 224	99.13 364	97.86 251	93.59 398	98.68 324

IterMVS		97.83 276	97.77 255	98.02 338	99.58 171	96.27 357	99.02 360	99.48 178	97.22 281	98.71 313	99.70 184	92.75 310	99.13 364	97.46 296	96.00 347	98.67 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 391	94.90 382	91.84 416	97.24 426	80.01 446	98.52 417	99.48 178	89.01 430	91.99 433	99.67 208	85.67 410	99.13 364	95.44 374	97.03 327	96.39 434
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 238	97.96 233	98.33 312	99.26 279	97.38 298	98.56 416	99.31 301	96.65 325	98.88 290	99.52 269	96.58 157	99.12 368	97.39 301	95.53 364	98.47 377

pmmvs4		98.13 225	97.90 240	98.81 256	98.61 397	98.87 193	98.99 368	99.21 327	96.44 345	99.06 262	99.58 245	95.90 187	99.11 369	97.18 316	96.11 344	98.46 380

TransMVSNet (Re)		97.15 343	96.58 349	98.86 247	99.12 316	98.85 197	99.49 198	98.91 370	95.48 381	97.16 397	99.80 125	93.38 295	99.11 369	94.16 396	91.73 416	98.62 354

ambc				93.06 414	92.68 445	82.36 439	98.47 419	98.73 400		95.09 420	97.41 428	55.55 446	99.10 371	96.42 351	91.32 417	97.71 420

Baseline_NR-MVSNet		97.76 287	97.45 295	98.68 270	99.09 324	98.29 249	99.41 241	98.85 379	95.65 379	98.63 331	99.67 208	94.82 235	99.10 371	98.07 237	92.89 408	98.64 345

test_vis3_rt		87.04 406	85.81 409	90.73 420	93.99 444	81.96 441	99.76 37	90.23 455	92.81 416	81.35 443	91.56 443	40.06 452	99.07 373	94.27 393	88.23 430	91.15 443

CP-MVSNet		98.09 229	97.78 253	99.01 214	98.97 348	99.24 140	99.67 71	99.46 208	97.25 277	98.48 345	99.64 221	93.79 289	99.06 374	98.63 171	94.10 391	98.74 306

PS-CasMVS		97.93 256	97.59 278	98.95 223	98.99 343	99.06 164	99.68 68	99.52 118	97.13 287	98.31 353	99.68 202	92.44 328	99.05 375	98.51 192	94.08 392	98.75 302

K. test v3		97.10 345	96.79 345	98.01 339	98.72 385	96.33 354	99.87 8	97.05 432	97.59 238	96.16 411	99.80 125	88.71 383	99.04 376	96.69 342	96.55 334	98.65 343

new_pmnet		96.38 361	96.03 363	97.41 378	98.13 412	95.16 388	99.05 352	99.20 328	93.94 403	97.39 390	98.79 395	91.61 348	99.04 376	90.43 422	95.77 354	98.05 407

DIV-MVS_self_test		98.01 246	97.85 247	98.48 291	99.24 285	97.95 272	98.71 403	99.35 274	96.50 338	98.60 337	99.54 261	95.72 197	99.03 378	97.21 310	95.77 354	98.46 380

IterMVS-LS		98.46 194	98.42 193	98.58 279	99.59 169	98.00 265	99.37 260	99.43 235	96.94 309	99.07 257	99.59 241	97.87 111	99.03 378	98.32 214	95.62 360	98.71 310
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 310	97.68 267	97.55 374	98.62 395	94.97 391	98.84 390	99.30 306	96.83 316	98.19 362	99.34 327	97.01 142	99.02 380	95.00 384	96.01 346	98.64 345

Patchmtry		97.75 291	97.40 307	98.81 256	99.10 321	98.87 193	99.11 343	99.33 287	94.83 394	98.81 302	99.38 314	94.33 267	99.02 380	96.10 357	95.57 362	98.53 371

N_pmnet		94.95 385	95.83 368	92.31 415	98.47 405	79.33 447	99.12 337	92.81 453	93.87 404	97.68 383	99.13 361	93.87 286	99.01 382	91.38 419	96.19 342	98.59 367

CR-MVSNet		98.17 221	97.93 238	98.87 244	99.18 300	98.49 238	99.22 318	99.33 287	96.96 305	99.56 144	99.38 314	94.33 267	99.00 383	94.83 387	98.58 238	99.14 259

c3_l		98.12 227	98.04 225	98.38 309	99.30 267	97.69 288	98.81 393	99.33 287	96.67 323	98.83 299	99.34 327	97.11 135	98.99 384	97.58 281	95.34 367	98.48 375

test0.0.03 1		97.71 300	97.42 305	98.56 283	98.41 408	97.82 279	98.78 396	98.63 406	97.34 269	98.05 370	98.98 379	94.45 264	98.98 385	95.04 383	97.15 325	98.89 287

PatchT		97.03 347	96.44 353	98.79 259	98.99 343	98.34 248	99.16 328	99.07 346	92.13 419	99.52 153	97.31 432	94.54 259	98.98 385	88.54 429	98.73 230	99.03 275

GBi-Net		97.68 305	97.48 289	98.29 317	99.51 196	97.26 304	99.43 229	99.48 178	96.49 339	99.07 257	99.32 335	90.26 364	98.98 385	97.10 318	96.65 330	98.62 354

test1		97.68 305	97.48 289	98.29 317	99.51 196	97.26 304	99.43 229	99.48 178	96.49 339	99.07 257	99.32 335	90.26 364	98.98 385	97.10 318	96.65 330	98.62 354

FMVSNet3		98.03 241	97.76 259	98.84 251	99.39 243	98.98 172	99.40 249	99.38 258	96.67 323	99.07 257	99.28 342	92.93 305	98.98 385	97.10 318	96.65 330	98.56 370

FMVSNet2		97.72 297	97.36 310	98.80 258	99.51 196	98.84 198	99.45 218	99.42 237	96.49 339	98.86 297	99.29 340	90.26 364	98.98 385	96.44 350	96.56 333	98.58 368

FMVSNet1		96.84 351	96.36 355	98.29 317	99.32 265	97.26 304	99.43 229	99.48 178	95.11 386	98.55 340	99.32 335	83.95 421	98.98 385	95.81 364	96.26 341	98.62 354

ppachtmachnet_test		97.49 327	97.45 295	97.61 372	98.62 395	95.24 384	98.80 394	99.46 208	96.11 369	98.22 360	99.62 232	96.45 164	98.97 392	93.77 398	95.97 351	98.61 363

TranMVSNet+NR-MVSNet		97.93 256	97.66 269	98.76 262	98.78 374	98.62 222	99.65 84	99.49 166	97.76 219	98.49 344	99.60 239	94.23 270	98.97 392	98.00 241	92.90 407	98.70 315

MVStest1		96.08 368	95.48 373	97.89 351	98.93 351	96.70 338	99.56 140	99.35 274	92.69 417	91.81 434	99.46 292	89.90 370	98.96 394	95.00 384	92.61 412	98.00 412

tt0320-xc		95.31 381	94.59 385	97.45 377	98.92 353	94.73 395	99.20 323	99.31 301	86.74 435	97.23 393	99.72 177	81.14 434	98.95 395	97.08 321	91.98 415	98.67 332

test_method		91.10 401	91.36 403	90.31 421	95.85 434	73.72 454	94.89 442	99.25 318	68.39 445	95.82 414	99.02 373	80.50 435	98.95 395	93.64 401	94.89 379	98.25 395

ADS-MVSNet2		98.02 243	98.07 223	97.87 352	99.33 258	95.19 386	99.23 314	99.08 343	96.24 357	99.10 251	99.67 208	94.11 275	98.93 397	96.81 336	99.05 206	99.48 210

ET-MVSNet_ETH3D		96.49 358	95.64 372	99.05 210	99.53 187	98.82 204	98.84 390	97.51 430	97.63 234	84.77 439	99.21 354	92.09 333	98.91 398	98.98 116	92.21 414	99.41 231

miper_lstm_enhance		98.00 248	97.91 239	98.28 321	99.34 257	97.43 296	98.88 386	99.36 267	96.48 342	98.80 304	99.55 256	95.98 180	98.91 398	97.27 307	95.50 365	98.51 373

MonoMVSNet		98.38 203	98.47 191	98.12 333	98.59 400	96.19 361	99.72 53	98.79 388	97.89 201	99.44 169	99.52 269	96.13 174	98.90 400	98.64 169	97.54 299	99.28 248

PEN-MVS		97.76 287	97.44 300	98.72 265	98.77 379	98.54 229	99.78 32	99.51 136	97.06 297	98.29 356	99.64 221	92.63 319	98.89 401	98.09 230	93.16 405	98.72 308

testing3		97.28 337	96.76 346	98.82 253	99.37 248	98.07 262	99.45 218	99.36 267	97.56 243	97.89 377	98.95 382	83.70 422	98.82 402	96.03 359	98.56 241	99.58 178

testgi		97.65 310	97.50 287	98.13 332	99.36 251	96.45 350	99.42 236	99.48 178	97.76 219	97.87 378	99.45 294	91.09 356	98.81 403	94.53 389	98.52 244	99.13 261

testf1		90.42 404	90.68 405	89.65 424	97.78 416	73.97 452	99.13 334	98.81 384	89.62 427	91.80 435	98.93 384	62.23 444	98.80 404	86.61 438	91.17 418	96.19 435

APD_test2		90.42 404	90.68 405	89.65 424	97.78 416	73.97 452	99.13 334	98.81 384	89.62 427	91.80 435	98.93 384	62.23 444	98.80 404	86.61 438	91.17 418	96.19 435

MIMVSNet		97.73 295	97.45 295	98.57 280	99.45 226	97.50 294	99.02 360	98.98 357	96.11 369	99.41 178	99.14 360	90.28 363	98.74 406	95.74 366	98.93 215	99.47 216

LCM-MVSNet-Re		97.83 276	98.15 210	96.87 394	99.30 267	92.25 424	99.59 116	98.26 414	97.43 261	96.20 410	99.13 361	96.27 171	98.73 407	98.17 226	98.99 212	99.64 157

Syy-MVS		97.09 346	97.14 332	96.95 391	99.00 340	92.73 422	99.29 287	99.39 250	97.06 297	97.41 387	98.15 418	93.92 284	98.68 408	91.71 417	98.34 251	99.45 224

myMVS_eth3d		96.89 349	96.37 354	98.43 304	99.00 340	97.16 308	99.29 287	99.39 250	97.06 297	97.41 387	98.15 418	83.46 424	98.68 408	95.27 379	98.34 251	99.45 224

DTE-MVSNet		97.51 321	97.19 330	98.46 297	98.63 394	98.13 258	99.84 12	99.48 178	96.68 322	97.97 373	99.67 208	92.92 306	98.56 410	96.88 335	92.60 413	98.70 315

PC_three_1452									98.18 160	99.84 50	99.70 184	99.31 3	98.52 411	98.30 216	99.80 118	99.81 73

mvsany_test3		93.77 393	93.45 397	94.74 406	95.78 435	88.01 432	99.64 91	98.25 415	98.28 141	94.31 423	97.97 425	68.89 440	98.51 412	97.50 291	90.37 423	97.71 420

UnsupCasMVSNet_bld		93.53 394	92.51 400	96.58 399	97.38 422	93.82 409	98.24 429	99.48 178	91.10 424	93.10 428	96.66 434	74.89 438	98.37 413	94.03 397	87.71 431	97.56 425

Anonymous20240521		96.20 364	95.89 367	97.13 385	97.72 419	94.96 392	99.79 31	99.29 310	93.01 413	97.20 396	99.03 371	89.69 373	98.36 414	91.16 420	96.13 343	98.07 405

test_f		91.90 400	91.26 404	93.84 409	95.52 439	85.92 434	99.69 62	98.53 411	95.31 383	93.87 425	96.37 436	55.33 447	98.27 415	95.70 367	90.98 421	97.32 428

MDA-MVSNet_test_wron		95.45 377	94.60 384	98.01 339	98.16 411	97.21 307	99.11 343	99.24 321	93.49 409	80.73 445	98.98 379	93.02 303	98.18 416	94.22 395	94.45 384	98.64 345

UnsupCasMVSNet_eth		96.44 359	96.12 360	97.40 379	98.65 392	95.65 370	99.36 265	99.51 136	97.13 287	96.04 413	98.99 377	88.40 390	98.17 417	96.71 340	90.27 424	98.40 386

KD-MVS_2432*1600		94.62 386	93.72 394	97.31 380	97.19 428	95.82 367	98.34 424	99.20 328	95.00 390	97.57 384	98.35 411	87.95 395	98.10 418	92.87 411	77.00 443	98.01 409

miper_refine_blended		94.62 386	93.72 394	97.31 380	97.19 428	95.82 367	98.34 424	99.20 328	95.00 390	97.57 384	98.35 411	87.95 395	98.10 418	92.87 411	77.00 443	98.01 409

YYNet1		95.36 379	94.51 387	97.92 348	97.89 414	97.10 311	99.10 345	99.23 322	93.26 412	80.77 444	99.04 370	92.81 309	98.02 420	94.30 391	94.18 389	98.64 345

EU-MVSNet		97.98 250	98.03 226	97.81 360	98.72 385	96.65 343	99.66 78	99.66 28	98.09 174	98.35 351	99.82 97	95.25 217	98.01 421	97.41 300	95.30 368	98.78 294

Gipuma		90.99 402	90.15 407	93.51 410	98.73 383	90.12 430	93.98 443	99.45 219	79.32 441	92.28 431	94.91 438	69.61 439	97.98 422	87.42 434	95.67 358	92.45 441
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 380	94.73 383	97.15 383	95.53 438	95.94 365	99.35 270	99.10 340	95.13 384	93.55 426	97.54 427	88.15 394	97.91 423	94.58 388	89.69 427	97.61 423

PM-MVS		92.96 397	92.23 401	95.14 405	95.61 436	89.98 431	99.37 260	98.21 418	94.80 395	95.04 421	97.69 426	65.06 441	97.90 424	94.30 391	89.98 426	97.54 426

MDA-MVSNet-bldmvs		94.96 384	93.98 391	97.92 348	98.24 410	97.27 302	99.15 331	99.33 287	93.80 405	80.09 446	99.03 371	88.31 391	97.86 425	93.49 403	94.36 386	98.62 354

Patchmatch-RL test		95.84 371	95.81 369	95.95 403	95.61 436	90.57 429	98.24 429	98.39 412	95.10 388	95.20 418	98.67 399	94.78 239	97.77 426	96.28 356	90.02 425	99.51 202

Anonymous20231206		96.22 362	96.03 363	96.79 396	97.31 425	94.14 407	99.63 97	99.08 343	96.17 363	97.04 400	99.06 368	93.94 282	97.76 427	86.96 436	95.06 373	98.47 377

SD-MVS		99.41 55	99.52 12	99.05 210	99.74 93	99.68 57	99.46 215	99.52 118	99.11 40	99.88 37	99.91 24	99.43 1	97.70 428	98.72 158	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		97.25 339	97.35 312	96.95 391	97.84 415	93.61 416	99.57 133	96.63 438	96.13 368	98.87 293	98.61 402	94.59 254	97.70 428	95.08 382	98.86 221	99.55 185

dongtai		93.26 395	92.93 399	94.25 407	99.39 243	85.68 435	97.68 438	93.27 449	92.87 415	96.85 404	99.39 311	82.33 429	97.48 430	76.78 443	97.80 284	99.58 178

pmmvs3		94.09 392	93.25 398	96.60 398	94.76 443	94.49 401	98.92 382	98.18 420	89.66 426	96.48 407	98.06 424	86.28 407	97.33 431	89.68 425	87.20 432	97.97 415

KD-MVS_self_test		95.00 383	94.34 388	96.96 390	97.07 430	95.39 381	99.56 140	99.44 228	95.11 386	97.13 398	97.32 431	91.86 338	97.27 432	90.35 423	81.23 440	98.23 397

FMVSNet5		96.43 360	96.19 359	97.15 383	99.11 318	95.89 366	99.32 277	99.52 118	94.47 401	98.34 352	99.07 366	87.54 400	97.07 433	92.61 414	95.72 357	98.47 377

new-patchmatchnet		94.48 389	94.08 390	95.67 404	95.08 441	92.41 423	99.18 326	99.28 312	94.55 400	93.49 427	97.37 430	87.86 398	97.01 434	91.57 418	88.36 429	97.61 423

LCM-MVSNet		86.80 408	85.22 412	91.53 418	87.81 450	80.96 444	98.23 431	98.99 356	71.05 443	90.13 438	96.51 435	48.45 451	96.88 435	90.51 421	85.30 434	96.76 430

CL-MVSNet_self_test		94.49 388	93.97 392	96.08 402	96.16 433	93.67 414	98.33 426	99.38 258	95.13 384	97.33 391	98.15 418	92.69 317	96.57 436	88.67 428	79.87 441	97.99 413

MIMVSNet1		95.51 376	95.04 381	96.92 393	97.38 422	95.60 371	99.52 169	99.50 156	93.65 407	96.97 402	99.17 356	85.28 415	96.56 437	88.36 430	95.55 363	98.60 366

test20.03		96.12 366	95.96 365	96.63 397	97.44 421	95.45 378	99.51 178	99.38 258	96.55 336	96.16 411	99.25 348	93.76 291	96.17 438	87.35 435	94.22 388	98.27 393

tmp_tt		82.80 410	81.52 413	86.66 426	66.61 456	68.44 455	92.79 445	97.92 422	68.96 444	80.04 447	99.85 71	85.77 409	96.15 439	97.86 251	43.89 449	95.39 439

test_fmvs3		92.10 399	91.77 402	93.08 413	96.19 432	86.25 433	99.82 16	98.62 407	96.65 325	95.19 419	96.90 433	55.05 448	95.93 440	96.63 347	90.92 422	97.06 429

kuosan		90.92 403	90.11 408	93.34 411	98.78 374	85.59 436	98.15 433	93.16 451	89.37 429	92.07 432	98.38 410	81.48 432	95.19 441	62.54 450	97.04 326	99.25 253

dmvs_testset		95.02 382	96.12 360	91.72 417	99.10 321	80.43 445	99.58 126	97.87 424	97.47 253	95.22 417	98.82 391	93.99 280	95.18 442	88.09 431	94.91 378	99.56 184

PMMVS2		86.87 407	85.37 411	91.35 419	90.21 448	83.80 438	98.89 385	97.45 431	83.13 440	91.67 437	95.03 437	48.49 450	94.70 443	85.86 440	77.62 442	95.54 438

PMVS	70.75 22	75.98 416	74.97 417	79.01 432	70.98 455	55.18 457	93.37 444	98.21 418	65.08 449	61.78 450	93.83 440	21.74 457	92.53 444	78.59 442	91.12 420	89.34 445
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 409	85.65 410	82.75 430	86.77 451	63.39 456	98.35 423	98.92 365	74.11 442	83.39 441	98.98 379	50.85 449	92.40 445	84.54 441	94.97 375	92.46 440

WB-MVS		93.10 396	94.10 389	90.12 422	95.51 440	81.88 442	99.73 51	99.27 315	95.05 389	93.09 429	98.91 388	94.70 248	91.89 446	76.62 444	94.02 394	96.58 432

SSC-MVS		92.73 398	93.73 393	89.72 423	95.02 442	81.38 443	99.76 37	99.23 322	94.87 393	92.80 430	98.93 384	94.71 247	91.37 447	74.49 446	93.80 396	96.42 433

MVE	76.82 21	76.91 415	74.31 419	84.70 427	85.38 453	76.05 451	96.88 441	93.17 450	67.39 446	71.28 448	89.01 447	21.66 458	87.69 448	71.74 447	72.29 445	90.35 444
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 412	79.88 414	82.81 429	90.75 447	76.38 450	97.69 437	95.76 442	66.44 447	83.52 440	92.25 442	62.54 443	87.16 449	68.53 448	61.40 446	84.89 447

EMVS		80.02 413	79.22 415	82.43 431	91.19 446	76.40 449	97.55 440	92.49 454	66.36 448	83.01 442	91.27 444	64.63 442	85.79 450	65.82 449	60.65 447	85.08 446

ANet_high		77.30 414	74.86 418	84.62 428	75.88 454	77.61 448	97.63 439	93.15 452	88.81 431	64.27 449	89.29 446	36.51 453	83.93 451	75.89 445	52.31 448	92.33 442

wuyk23d		40.18 417	41.29 422	36.84 433	86.18 452	49.12 458	79.73 446	22.81 458	27.64 450	25.46 453	28.45 453	21.98 456	48.89 452	55.80 451	23.56 452	12.51 450

test123		39.01 419	42.50 421	28.53 434	39.17 457	20.91 459	98.75 399	19.17 459	19.83 452	38.57 451	66.67 449	33.16 454	15.42 453	37.50 453	29.66 451	49.26 448

testmvs		39.17 418	43.78 420	25.37 435	36.04 458	16.84 460	98.36 422	26.56 457	20.06 451	38.51 452	67.32 448	29.64 455	15.30 454	37.59 452	39.90 450	43.98 449

mmdepth		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

monomultidepth		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

test_blank		0.13 423	0.17 426	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	1.57 454	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

uanet_test		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

DCPMVS		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

cdsmvs_eth3d_5k		24.64 420	32.85 423	0.00 436	0.00 459	0.00 461	0.00 447	99.51 136	0.00 454	0.00 455	99.56 253	96.58 157	0.00 455	0.00 454	0.00 453	0.00 451

pcd_1.5k_mvsjas		8.27 422	11.03 425	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	99.01 18	0.00 455	0.00 454	0.00 453	0.00 451

sosnet-low-res		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

sosnet		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

uncertanet		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

Regformer		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

ab-mvs-re		8.30 421	11.06 424	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	99.58 245	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

uanet		0.02 424	0.03 427	0.00 436	0.00 459	0.00 461	0.00 447	0.00 460	0.00 454	0.00 455	0.27 455	0.00 459	0.00 455	0.00 454	0.00 453	0.00 451

WAC-MVS						97.16 308								95.47 373

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		99.49 166	98.97 68	99.65 118	99.81 111	99.09 14

eth-test2					0.00 459

eth-test					0.00 459

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 97	98.75 58		98.61 175	99.81 113	99.77 94

IU-MVS					99.84 34	99.88 9		99.32 297	98.30 140	99.84 50				98.86 138	99.85 87	99.89 26

save fliter					99.76 75	99.59 81	99.14 333	99.40 247	99.00 60

test0726					99.85 28	99.89 5	99.62 102	99.50 156	99.10 41	99.86 47	99.82 97	98.94 32

GSMVS																99.52 194

test_part2					99.81 51	99.83 20				99.77 77

sam_mvs1												94.86 234				99.52 194

sam_mvs												94.72 246

MTGPA								99.47 199

MTMP							99.54 159	98.88 375

test9_res														97.49 292	99.72 141	99.75 100

agg_prior2														97.21 310	99.73 140	99.75 100

test_prior4						99.56 87	98.99 368

test_prior2							98.96 375		98.34 135	99.01 268	99.52 269	98.68 67		97.96 243	99.74 138

新几何2							99.01 365

旧先验1					99.74 93	99.59 81		99.54 100			99.69 195	98.47 83			99.68 149	99.73 113

原ACMM2							98.95 378

test222					99.75 85	99.49 102	98.91 384	99.49 166	96.42 347	99.34 198	99.65 215	98.28 97			99.69 146	99.72 122

segment_acmp												98.96 25

testdata1							98.85 389		98.32 138

plane_prior7					99.29 271	97.03 321

plane_prior6					99.27 276	96.98 325						92.71 315

plane_prior4											99.61 236

plane_prior3						97.00 323			98.69 100	99.11 248

plane_prior2							99.39 253		98.97 68

plane_prior1					99.26 279

plane_prior						96.97 326	99.21 320		98.45 122						97.60 293

n2								0.00 460

nn								0.00 460

door-mid								98.05 421

test11								99.35 274

door								97.92 422

HQP5-MVS						96.83 333

HQP-NCC					99.19 297		98.98 371		98.24 149	98.66 322

ACMP_Plane					99.19 297		98.98 371		98.24 149	98.66 322

BP-MVS														97.19 314

HQP3-MVS								99.39 250							97.58 295

HQP2-MVS												92.47 324

NP-MVS					99.23 287	96.92 329					99.40 307

MDTV_nov1_ep13_2view						95.18 387	99.35 270		96.84 314	99.58 140		95.19 220		97.82 256		99.46 221

ACMMP++_ref															97.19 323

ACMMP++															97.43 313

Test By Simon												98.75 58

High-resolution multi-view benchmark