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 65	99.38 240	99.37 114	99.58 122	99.62 46	99.41 17	99.87 41	99.92 17	98.81 47	100.00 1	99.97 1	99.93 29	99.94 14

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 62	99.84 32	99.44 107	99.58 122	99.69 18	99.43 13	99.98 10	99.91 23	98.62 73	100.00 1	99.97 1	99.95 19	99.90 22

test_vis1_n_1920		98.63 184	98.40 191	99.31 168	99.86 20	97.94 270	99.67 69	99.62 46	99.43 13	99.99 2	99.91 23	87.29 396	100.00 1	99.92 20	99.92 35	99.98 2

fmvsm_s_conf0.5_n_5		99.37 61	99.21 77	99.86 28	99.80 54	99.68 56	99.42 231	99.61 54	99.37 20	99.97 21	99.86 63	94.96 221	99.99 4	99.97 1	99.93 29	99.92 20

fmvsm_l_conf0.5_n_3		99.61 8	99.51 16	99.92 1	99.84 32	99.82 25	99.54 155	99.66 28	99.46 7	99.98 10	99.89 36	97.27 129	99.99 4	99.97 1	99.95 19	99.95 10

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 36	99.86 20	99.61 77	99.56 136	99.63 42	99.48 3	99.98 10	99.83 86	98.75 58	99.99 4	99.97 1	99.96 14	99.94 14

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 36	99.84 32	99.63 74	99.56 136	99.63 42	99.47 4	99.98 10	99.82 95	98.75 58	99.99 4	99.97 1	99.97 8	99.94 14

test_fmvsmconf_n		99.70 3	99.64 4	99.87 17	99.80 54	99.66 63	99.48 199	99.64 38	99.45 10	99.92 26	99.92 17	98.62 73	99.99 4	99.96 10	99.99 1	99.96 7

patch_mono-2		99.26 83	99.62 5	98.16 324	99.81 48	94.59 396	99.52 165	99.64 38	99.33 22	99.73 85	99.90 30	99.00 22	99.99 4	99.69 31	99.98 4	99.89 25

h-mvs33		97.70 297	97.28 319	98.97 216	99.70 111	97.27 298	99.36 260	99.45 216	98.94 67	99.66 107	99.64 217	94.93 224	99.99 4	99.48 58	84.36 430	99.65 145

xiu_mvs_v1_base_debu		99.29 77	99.27 67	99.34 161	99.63 146	98.97 173	99.12 332	99.51 133	98.86 73	99.84 48	99.47 284	98.18 100	99.99 4	99.50 53	99.31 181	99.08 262

xiu_mvs_v1_base		99.29 77	99.27 67	99.34 161	99.63 146	98.97 173	99.12 332	99.51 133	98.86 73	99.84 48	99.47 284	98.18 100	99.99 4	99.50 53	99.31 181	99.08 262

xiu_mvs_v1_base_debi		99.29 77	99.27 67	99.34 161	99.63 146	98.97 173	99.12 332	99.51 133	98.86 73	99.84 48	99.47 284	98.18 100	99.99 4	99.50 53	99.31 181	99.08 262

EPNet		98.86 154	98.71 156	99.30 173	97.20 422	98.18 250	99.62 98	98.91 365	99.28 25	98.63 327	99.81 109	95.96 179	99.99 4	99.24 86	99.72 138	99.73 110
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_8		99.54 19	99.42 27	99.89 8	99.83 40	99.74 47	99.51 174	99.62 46	99.46 7	99.99 2	99.90 30	96.60 154	99.98 15	99.95 12	99.95 19	99.96 7

MM		99.40 57	99.28 64	99.74 71	99.67 123	99.31 126	99.52 165	98.87 372	99.55 1	99.74 83	99.80 123	96.47 161	99.98 15	99.97 1	99.97 8	99.94 14

test_cas_vis1_n_1920		99.16 98	99.01 112	99.61 100	99.81 48	98.86 194	99.65 82	99.64 38	99.39 18	99.97 21	99.94 6	93.20 297	99.98 15	99.55 46	99.91 42	99.99 1

test_vis1_n		97.92 255	97.44 295	99.34 161	99.53 182	98.08 257	99.74 46	99.49 163	99.15 30	100.00 1	99.94 6	79.51 431	99.98 15	99.88 22	99.76 130	99.97 4

xiu_mvs_v2_base		99.26 83	99.25 71	99.29 176	99.53 182	98.91 188	99.02 355	99.45 216	98.80 83	99.71 92	99.26 342	98.94 32	99.98 15	99.34 73	99.23 186	98.98 276

PS-MVSNAJ		99.32 72	99.32 49	99.30 173	99.57 170	98.94 183	98.97 369	99.46 205	98.92 70	99.71 92	99.24 344	99.01 18	99.98 15	99.35 68	99.66 149	98.97 277

QAPM		98.67 179	98.30 198	99.80 56	99.20 289	99.67 60	99.77 34	99.72 11	94.74 391	98.73 307	99.90 30	95.78 190	99.98 15	96.96 324	99.88 68	99.76 97

3Dnovator	97.25 9	99.24 88	99.05 98	99.81 53	99.12 311	99.66 63	99.84 12	99.74 10	99.09 45	98.92 280	99.90 30	95.94 182	99.98 15	98.95 116	99.92 35	99.79 84

OpenMVS	96.50 16	98.47 189	98.12 210	99.52 130	99.04 330	99.53 93	99.82 16	99.72 11	94.56 394	98.08 361	99.88 45	94.73 240	99.98 15	97.47 291	99.76 130	99.06 268

fmvsm_s_conf0.5_n_3		99.37 61	99.20 79	99.87 17	99.75 82	99.70 53	99.48 199	99.66 28	99.45 10	99.99 2	99.93 10	94.64 248	99.97 24	99.94 17	99.97 8	99.95 10

reproduce_model		99.63 7	99.54 11	99.90 5	99.78 60	99.88 8	99.56 136	99.55 89	99.15 30	99.90 30	99.90 30	99.00 22	99.97 24	99.11 97	99.91 42	99.86 38

test_fmvsmconf0.1_n		99.55 18	99.45 25	99.86 28	99.44 222	99.65 67	99.50 182	99.61 54	99.45 10	99.87 41	99.92 17	97.31 126	99.97 24	99.95 12	99.99 1	99.97 4

test_fmvs1_n		98.41 195	98.14 207	99.21 189	99.82 44	97.71 283	99.74 46	99.49 163	99.32 23	99.99 2	99.95 3	85.32 409	99.97 24	99.82 25	99.84 94	99.96 7

CANet_DTU		98.97 142	98.87 137	99.25 183	99.33 253	98.42 242	99.08 341	99.30 301	99.16 29	99.43 167	99.75 158	95.27 210	99.97 24	98.56 183	99.95 19	99.36 234

MVS_0304		99.15 101	98.96 122	99.73 74	98.92 348	99.37 114	99.37 255	96.92 428	99.51 2	99.66 107	99.78 142	96.69 151	99.97 24	99.84 24	99.97 8	99.84 49

MTAPA		99.52 23	99.39 35	99.89 8	99.90 4	99.86 16	99.66 76	99.47 196	98.79 84	99.68 98	99.81 109	98.43 86	99.97 24	98.88 126	99.90 53	99.83 59

PGM-MVS		99.45 41	99.31 55	99.86 28	99.87 15	99.78 40	99.58 122	99.65 35	97.84 204	99.71 92	99.80 123	99.12 13	99.97 24	98.33 208	99.87 71	99.83 59

mPP-MVS		99.44 45	99.30 57	99.86 28	99.88 11	99.79 34	99.69 60	99.48 175	98.12 165	99.50 152	99.75 158	98.78 51	99.97 24	98.57 180	99.89 64	99.83 59

CP-MVS		99.45 41	99.32 49	99.85 36	99.83 40	99.75 44	99.69 60	99.52 116	98.07 175	99.53 147	99.63 223	98.93 36	99.97 24	98.74 151	99.91 42	99.83 59

SteuartSystems-ACMMP		99.54 19	99.42 27	99.87 17	99.82 44	99.81 29	99.59 112	99.51 133	98.62 101	99.79 64	99.83 86	99.28 4	99.97 24	98.48 190	99.90 53	99.84 49
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 94	98.97 118	99.82 50	99.17 303	99.68 56	99.81 20	99.51 133	99.20 27	98.72 308	99.89 36	95.68 194	99.97 24	98.86 134	99.86 79	99.81 71

KinetiMVS		99.12 112	98.92 127	99.70 78	99.67 123	99.40 112	99.67 69	99.63 42	98.73 91	99.94 24	99.81 109	94.54 254	99.96 36	98.40 199	99.93 29	99.74 102

fmvsm_s_conf0.5_n_7		99.34 68	99.29 61	99.48 139	99.70 111	98.63 216	99.42 231	99.63 42	99.46 7	99.98 10	99.88 45	95.59 197	99.96 36	99.97 1	99.98 4	99.85 42

fmvsm_s_conf0.5_n_2		99.32 72	99.13 86	99.89 8	99.80 54	99.77 41	99.44 219	99.58 71	99.47 4	99.99 2	99.93 10	94.04 273	99.96 36	99.96 10	99.93 29	99.93 19

reproduce-ours		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 165	99.54 98	99.13 33	99.89 33	99.89 36	98.96 25	99.96 36	99.04 105	99.90 53	99.85 42

our_new_method		99.61 8	99.52 12	99.90 5	99.76 72	99.88 8	99.52 165	99.54 98	99.13 33	99.89 33	99.89 36	98.96 25	99.96 36	99.04 105	99.90 53	99.85 42

fmvsm_s_conf0.5_n_a		99.56 17	99.47 21	99.85 36	99.83 40	99.64 73	99.52 165	99.65 35	99.10 40	99.98 10	99.92 17	97.35 125	99.96 36	99.94 17	99.92 35	99.95 10

fmvsm_s_conf0.5_n		99.51 24	99.40 33	99.85 36	99.84 32	99.65 67	99.51 174	99.67 23	99.13 33	99.98 10	99.92 17	96.60 154	99.96 36	99.95 12	99.96 14	99.95 10

mvsany_test1		99.50 26	99.46 24	99.62 99	99.61 157	99.09 156	98.94 375	99.48 175	99.10 40	99.96 23	99.91 23	98.85 42	99.96 36	99.72 28	99.58 159	99.82 64

test_fmvs1		98.88 148	98.79 149	99.16 194	99.69 116	97.61 287	99.55 150	99.49 163	99.32 23	99.98 10	99.91 23	91.41 345	99.96 36	99.82 25	99.92 35	99.90 22

DVP-MVS++		99.59 12	99.50 17	99.88 11	99.51 191	99.88 8	99.87 8	99.51 133	98.99 58	99.88 36	99.81 109	99.27 5	99.96 36	98.85 136	99.80 115	99.81 71

MSC_two_6792asdad				99.87 17	99.51 191	99.76 42		99.33 282					99.96 36	98.87 129	99.84 94	99.89 25

No_MVS				99.87 17	99.51 191	99.76 42		99.33 282					99.96 36	98.87 129	99.84 94	99.89 25

ZD-MVS					99.71 106	99.79 34		99.61 54	96.84 309	99.56 140	99.54 257	98.58 75	99.96 36	96.93 327	99.75 132

SED-MVS		99.61 8	99.52 12	99.88 11	99.84 32	99.90 2	99.60 105	99.48 175	99.08 46	99.91 27	99.81 109	99.20 7	99.96 36	98.91 123	99.85 86	99.79 84

test_241102_TWO								99.48 175	99.08 46	99.88 36	99.81 109	98.94 32	99.96 36	98.91 123	99.84 94	99.88 31

ZNCC-MVS		99.47 35	99.33 47	99.87 17	99.87 15	99.81 29	99.64 87	99.67 23	98.08 174	99.55 144	99.64 217	98.91 37	99.96 36	98.72 154	99.90 53	99.82 64

DVP-MVS		99.57 16	99.47 21	99.88 11	99.85 26	99.89 4	99.57 129	99.37 262	99.10 40	99.81 58	99.80 123	98.94 32	99.96 36	98.93 120	99.86 79	99.81 71
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 58	99.81 58	99.80 123	99.09 14	99.96 36	98.85 136	99.90 53	99.88 31

test_0728_SECOND				99.91 3	99.84 32	99.89 4	99.57 129	99.51 133					99.96 36	98.93 120	99.86 79	99.88 31

SR-MVS		99.43 48	99.29 61	99.86 28	99.75 82	99.83 19	99.59 112	99.62 46	98.21 151	99.73 85	99.79 135	98.68 67	99.96 36	98.44 196	99.77 127	99.79 84

DPE-MVS		99.46 37	99.32 49	99.91 3	99.78 60	99.88 8	99.36 260	99.51 133	98.73 91	99.88 36	99.84 81	98.72 64	99.96 36	98.16 223	99.87 71	99.88 31
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 50	99.29 61	99.80 56	99.62 152	99.55 88	99.50 182	99.70 15	98.79 84	99.77 73	99.96 1	97.45 120	99.96 36	98.92 122	99.90 53	99.89 25

HFP-MVS		99.49 28	99.37 39	99.86 28	99.87 15	99.80 31	99.66 76	99.67 23	98.15 158	99.68 98	99.69 191	99.06 16	99.96 36	98.69 159	99.87 71	99.84 49

region2R		99.48 32	99.35 43	99.87 17	99.88 11	99.80 31	99.65 82	99.66 28	98.13 163	99.66 107	99.68 198	98.96 25	99.96 36	98.62 168	99.87 71	99.84 49

HPM-MVS++		99.39 59	99.23 75	99.87 17	99.75 82	99.84 18	99.43 224	99.51 133	98.68 98	99.27 210	99.53 261	98.64 72	99.96 36	98.44 196	99.80 115	99.79 84

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 68	99.89 4	99.75 42	99.56 81	99.02 51	99.88 36	99.85 70	99.18 10	99.96 36	99.22 87	99.92 35	99.90 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 28	99.36 41	99.86 28	99.87 15	99.79 34	99.66 76	99.67 23	98.15 158	99.67 102	99.69 191	98.95 30	99.96 36	98.69 159	99.87 71	99.84 49

MP-MVS		99.33 70	99.15 84	99.87 17	99.88 11	99.82 25	99.66 76	99.46 205	98.09 170	99.48 156	99.74 163	98.29 95	99.96 36	97.93 241	99.87 71	99.82 64
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 118	98.90 131	99.74 71	99.80 54	99.46 105	99.59 112	99.49 163	97.03 296	99.63 122	99.69 191	97.27 129	99.96 36	97.82 252	99.84 94	99.81 71

PVSNet_Blended_VisFu		99.36 65	99.28 64	99.61 100	99.86 20	99.07 161	99.47 207	99.93 2	97.66 227	99.71 92	99.86 63	97.73 115	99.96 36	99.47 60	99.82 107	99.79 84

UGNet		98.87 151	98.69 158	99.40 153	99.22 286	98.72 208	99.44 219	99.68 20	99.24 26	99.18 235	99.42 295	92.74 307	99.96 36	99.34 73	99.94 27	99.53 188
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 72	99.32 49	99.32 167	99.85 26	98.29 245	99.71 55	99.66 28	98.11 167	99.41 174	99.80 123	98.37 92	99.96 36	98.99 111	99.96 14	99.72 118

ACMMP		99.45 41	99.32 49	99.82 50	99.89 8	99.67 60	99.62 98	99.69 18	98.12 165	99.63 122	99.84 81	98.73 63	99.96 36	98.55 186	99.83 103	99.81 71
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 19	99.44 26	99.85 36	99.51 191	99.67 60	99.50 182	99.64 38	99.43 13	99.98 10	99.78 142	97.26 131	99.95 69	99.95 12	99.93 29	99.92 20

fmvsm_s_conf0.5_n_4		99.36 65	99.24 72	99.73 74	99.78 60	99.53 93	99.49 194	99.60 61	99.42 16	99.99 2	99.86 63	95.15 216	99.95 69	99.95 12	99.89 64	99.73 110

fmvsm_s_conf0.1_n_2		99.37 61	99.22 76	99.81 53	99.77 68	99.75 44	99.46 210	99.60 61	99.47 4	99.98 10	99.94 6	94.98 220	99.95 69	99.97 1	99.79 122	99.73 110

test_fmvsmconf0.01_n		99.22 91	99.03 103	99.79 59	98.42 402	99.48 102	99.55 150	99.51 133	99.39 18	99.78 69	99.93 10	94.80 232	99.95 69	99.93 19	99.95 19	99.94 14

SR-MVS-dyc-post		99.45 41	99.31 55	99.85 36	99.76 72	99.82 25	99.63 93	99.52 116	98.38 125	99.76 79	99.82 95	98.53 79	99.95 69	98.61 171	99.81 110	99.77 92

GST-MVS		99.40 57	99.24 72	99.85 36	99.86 20	99.79 34	99.60 105	99.67 23	97.97 189	99.63 122	99.68 198	98.52 80	99.95 69	98.38 201	99.86 79	99.81 71

CANet		99.25 87	99.14 85	99.59 104	99.41 230	99.16 146	99.35 265	99.57 76	98.82 78	99.51 151	99.61 232	96.46 162	99.95 69	99.59 41	99.98 4	99.65 145

MP-MVS-pluss		99.37 61	99.20 79	99.88 11	99.90 4	99.87 15	99.30 277	99.52 116	97.18 278	99.60 132	99.79 135	98.79 50	99.95 69	98.83 142	99.91 42	99.83 59
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 50	99.27 67	99.88 11	99.89 8	99.80 31	99.67 69	99.50 153	98.70 95	99.77 73	99.49 275	98.21 98	99.95 69	98.46 194	99.77 127	99.88 31
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 69	96.67 339

APD-MVS_3200maxsize		99.48 32	99.35 43	99.85 36	99.76 72	99.83 19	99.63 93	99.54 98	98.36 129	99.79 64	99.82 95	98.86 41	99.95 69	98.62 168	99.81 110	99.78 90

RPMNet		96.72 348	95.90 361	99.19 191	99.18 295	98.49 234	99.22 313	99.52 116	88.72 427	99.56 140	97.38 424	94.08 272	99.95 69	86.87 432	98.58 233	99.14 254

sss		99.17 96	99.05 98	99.53 124	99.62 152	98.97 173	99.36 260	99.62 46	97.83 205	99.67 102	99.65 211	97.37 124	99.95 69	99.19 89	99.19 189	99.68 135

MVSMamba_PlusPlus		99.46 37	99.41 32	99.64 92	99.68 121	99.50 99	99.75 42	99.50 153	98.27 139	99.87 41	99.92 17	98.09 104	99.94 82	99.65 37	99.95 19	99.47 211

fmvsm_s_conf0.1_n_a		99.26 83	99.06 97	99.85 36	99.52 188	99.62 75	99.54 155	99.62 46	98.69 96	99.99 2	99.96 1	94.47 258	99.94 82	99.88 22	99.92 35	99.98 2

fmvsm_s_conf0.1_n		99.29 77	99.10 90	99.86 28	99.70 111	99.65 67	99.53 164	99.62 46	98.74 90	99.99 2	99.95 3	94.53 256	99.94 82	99.89 21	99.96 14	99.97 4

TSAR-MVS + MP.		99.58 13	99.50 17	99.81 53	99.91 1	99.66 63	99.63 93	99.39 246	98.91 71	99.78 69	99.85 70	99.36 2	99.94 82	98.84 139	99.88 68	99.82 64
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
RRT-MVS		98.91 146	98.75 152	99.39 157	99.46 215	98.61 220	99.76 37	99.50 153	98.06 179	99.81 58	99.88 45	93.91 280	99.94 82	99.11 97	99.27 184	99.61 162

mamv4		99.33 70	99.42 27	99.07 202	99.67 123	97.73 278	99.42 231	99.60 61	98.15 158	99.94 24	99.91 23	98.42 88	99.94 82	99.72 28	99.96 14	99.54 182

XVS		99.53 22	99.42 27	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 185	99.74 163	98.81 47	99.94 82	98.79 147	99.86 79	99.84 49

X-MVStestdata		96.55 351	95.45 370	99.87 17	99.85 26	99.83 19	99.69 60	99.68 20	98.98 61	99.37 185	64.01 447	98.81 47	99.94 82	98.79 147	99.86 79	99.84 49

旧先验2							98.96 370		96.70 316	99.47 157			99.94 82	98.19 219

新几何1				99.75 68	99.75 82	99.59 80		99.54 98	96.76 312	99.29 204	99.64 217	98.43 86	99.94 82	96.92 329	99.66 149	99.72 118

testdata				99.54 116	99.75 82	98.95 180		99.51 133	97.07 290	99.43 167	99.70 180	98.87 40	99.94 82	97.76 261	99.64 152	99.72 118

HPM-MVS		99.42 50	99.28 64	99.83 49	99.90 4	99.72 49	99.81 20	99.54 98	97.59 233	99.68 98	99.63 223	98.91 37	99.94 82	98.58 177	99.91 42	99.84 49
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 92	99.10 90	99.45 146	99.89 8	98.52 230	99.39 248	99.94 1	98.73 91	99.11 244	99.89 36	95.50 200	99.94 82	99.50 53	99.97 8	99.89 25

APD-MVS		99.27 81	99.08 95	99.84 48	99.75 82	99.79 34	99.50 182	99.50 153	97.16 280	99.77 73	99.82 95	98.78 51	99.94 82	97.56 282	99.86 79	99.80 80
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 32	99.42 27	99.65 86	99.72 101	99.40 112	99.05 347	99.66 28	99.14 32	99.57 139	99.80 123	98.46 84	99.94 82	99.57 44	99.84 94	99.60 165
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		99.06 128	98.88 136	99.61 100	99.62 152	99.16 146	99.37 255	99.56 81	98.04 182	99.53 147	99.62 228	96.84 145	99.94 82	98.85 136	98.49 241	99.72 118

DeepC-MVS	98.35 2	99.30 75	99.19 81	99.64 92	99.82 44	99.23 139	99.62 98	99.55 89	98.94 67	99.63 122	99.95 3	95.82 188	99.94 82	99.37 67	99.97 8	99.73 110
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 81	99.12 88	99.74 71	99.18 295	99.75 44	99.56 136	99.57 76	98.45 118	99.49 155	99.85 70	97.77 114	99.94 82	98.33 208	99.84 94	99.52 189

GDP-MVS		99.08 125	98.89 134	99.64 92	99.53 182	99.34 118	99.64 87	99.48 175	98.32 134	99.77 73	99.66 209	95.14 217	99.93 100	98.97 115	99.50 166	99.64 152

SDMVSNet		99.11 118	98.90 131	99.75 68	99.81 48	99.59 80	99.81 20	99.65 35	98.78 87	99.64 119	99.88 45	94.56 251	99.93 100	99.67 33	98.26 254	99.72 118

FE-MVS		98.48 188	98.17 203	99.40 153	99.54 181	98.96 177	99.68 66	98.81 379	95.54 375	99.62 126	99.70 180	93.82 283	99.93 100	97.35 300	99.46 168	99.32 240

SF-MVS		99.38 60	99.24 72	99.79 59	99.79 58	99.68 56	99.57 129	99.54 98	97.82 209	99.71 92	99.80 123	98.95 30	99.93 100	98.19 219	99.84 94	99.74 102

dcpmvs_2		99.23 89	99.58 7	98.16 324	99.83 40	94.68 393	99.76 37	99.52 116	99.07 48	99.98 10	99.88 45	98.56 77	99.93 100	99.67 33	99.98 4	99.87 36

Anonymous20240529		98.09 225	97.68 263	99.34 161	99.66 134	98.44 239	99.40 244	99.43 231	93.67 401	99.22 222	99.89 36	90.23 362	99.93 100	99.26 85	98.33 248	99.66 141

ACMMP_NAP		99.47 35	99.34 45	99.88 11	99.87 15	99.86 16	99.47 207	99.48 175	98.05 181	99.76 79	99.86 63	98.82 46	99.93 100	98.82 146	99.91 42	99.84 49

EI-MVSNet-UG-set		99.58 13	99.57 8	99.64 92	99.78 60	99.14 151	99.60 105	99.45 216	99.01 53	99.90 30	99.83 86	98.98 24	99.93 100	99.59 41	99.95 19	99.86 38

无先验							98.99 363	99.51 133	96.89 306				99.93 100	97.53 285		99.72 118

VDDNet		97.55 312	97.02 333	99.16 194	99.49 205	98.12 256	99.38 253	99.30 301	95.35 377	99.68 98	99.90 30	82.62 422	99.93 100	99.31 77	98.13 266	99.42 223

ab-mvs		98.86 154	98.63 168	99.54 116	99.64 143	99.19 141	99.44 219	99.54 98	97.77 213	99.30 201	99.81 109	94.20 266	99.93 100	99.17 93	98.82 221	99.49 202

F-COLMAP		99.19 92	99.04 100	99.64 92	99.78 60	99.27 134	99.42 231	99.54 98	97.29 269	99.41 174	99.59 237	98.42 88	99.93 100	98.19 219	99.69 143	99.73 110

BP-MVS1		99.12 112	98.94 126	99.65 86	99.51 191	99.30 129	99.67 69	98.92 360	98.48 114	99.84 48	99.69 191	94.96 221	99.92 112	99.62 40	99.79 122	99.71 127

Anonymous202405211		98.30 206	97.98 227	99.26 182	99.57 170	98.16 251	99.41 236	98.55 404	96.03 369	99.19 231	99.74 163	91.87 332	99.92 112	99.16 94	98.29 253	99.70 129

EI-MVSNet-Vis-set		99.58 13	99.56 10	99.64 92	99.78 60	99.15 150	99.61 104	99.45 216	99.01 53	99.89 33	99.82 95	99.01 18	99.92 112	99.56 45	99.95 19	99.85 42

VDD-MVS		97.73 291	97.35 307	98.88 236	99.47 213	97.12 306	99.34 268	98.85 374	98.19 153	99.67 102	99.85 70	82.98 420	99.92 112	99.49 57	98.32 252	99.60 165

VNet		99.11 118	98.90 131	99.73 74	99.52 188	99.56 86	99.41 236	99.39 246	99.01 53	99.74 83	99.78 142	95.56 198	99.92 112	99.52 51	98.18 262	99.72 118

XVG-OURS-SEG-HR		98.69 177	98.62 173	98.89 234	99.71 106	97.74 277	99.12 332	99.54 98	98.44 121	99.42 170	99.71 176	94.20 266	99.92 112	98.54 187	98.90 215	99.00 273

mvsmamba		99.06 128	98.96 122	99.36 159	99.47 213	98.64 215	99.70 56	99.05 344	97.61 232	99.65 114	99.83 86	96.54 158	99.92 112	99.19 89	99.62 155	99.51 197

HPM-MVS_fast		99.51 24	99.40 33	99.85 36	99.91 1	99.79 34	99.76 37	99.56 81	97.72 218	99.76 79	99.75 158	99.13 12	99.92 112	99.07 103	99.92 35	99.85 42

HY-MVS	97.30 7	98.85 161	98.64 167	99.47 143	99.42 225	99.08 159	99.62 98	99.36 263	97.39 261	99.28 205	99.68 198	96.44 164	99.92 112	98.37 203	98.22 257	99.40 228

DP-MVS		99.16 98	98.95 124	99.78 62	99.77 68	99.53 93	99.41 236	99.50 153	97.03 296	99.04 261	99.88 45	97.39 121	99.92 112	98.66 163	99.90 53	99.87 36

IB-MVS	95.67 18	96.22 357	95.44 371	98.57 276	99.21 287	96.70 334	98.65 404	97.74 422	96.71 315	97.27 387	98.54 399	86.03 403	99.92 112	98.47 193	86.30 428	99.10 257
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 28	99.39 35	99.77 65	99.63 146	99.59 80	99.36 260	99.46 205	99.07 48	99.79 64	99.82 95	98.85 42	99.92 112	98.68 161	99.87 71	99.82 64
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 89	99.10 90	99.61 100	99.35 247	99.31 126	99.46 210	99.13 332	98.61 102	99.86 45	99.89 36	96.41 166	99.91 124	99.67 33	99.51 164	99.63 157

balanced_conf03		99.46 37	99.39 35	99.67 81	99.55 178	99.58 85	99.74 46	99.51 133	98.42 122	99.87 41	99.84 81	98.05 107	99.91 124	99.58 43	99.94 27	99.52 189

9.14			99.10 90		99.72 101		99.40 244	99.51 133	97.53 243	99.64 119	99.78 142	98.84 44	99.91 124	97.63 273	99.82 107

SMA-MVS		99.44 45	99.30 57	99.85 36	99.73 97	99.83 19	99.56 136	99.47 196	97.45 252	99.78 69	99.82 95	99.18 10	99.91 124	98.79 147	99.89 64	99.81 71
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					99.67 123	99.65 67	99.05 347	99.41 236	96.22 354	98.95 276	99.49 275	98.77 54	99.91 124

train_agg		99.02 134	98.77 150	99.77 65	99.67 123	99.65 67	99.05 347	99.41 236	96.28 348	98.95 276	99.49 275	98.76 55	99.91 124	97.63 273	99.72 138	99.75 98

test_8					99.67 123	99.61 77	99.03 352	99.41 236	96.28 348	98.93 279	99.48 281	98.76 55	99.91 124

agg_prior					99.67 123	99.62 75		99.40 243		98.87 289			99.91 124

原ACMM1				99.65 86	99.73 97	99.33 121		99.47 196	97.46 249	99.12 242	99.66 209	98.67 69	99.91 124	97.70 270	99.69 143	99.71 127

LFMVS		97.90 258	97.35 307	99.54 116	99.52 188	99.01 168	99.39 248	98.24 411	97.10 288	99.65 114	99.79 135	84.79 412	99.91 124	99.28 81	98.38 245	99.69 131

XVG-OURS		98.73 175	98.68 159	98.88 236	99.70 111	97.73 278	98.92 377	99.55 89	98.52 111	99.45 160	99.84 81	95.27 210	99.91 124	98.08 230	98.84 219	99.00 273

PLC	97.94 4	99.02 134	98.85 141	99.53 124	99.66 134	99.01 168	99.24 306	99.52 116	96.85 308	99.27 210	99.48 281	98.25 97	99.91 124	97.76 261	99.62 155	99.65 145
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 305	97.06 332	99.47 143	99.61 157	99.09 156	98.04 430	99.25 313	91.24 418	98.51 337	99.70 180	94.55 253	99.91 124	92.76 409	99.85 86	99.42 223
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ElysianMVS		98.88 148	98.65 165	99.58 107	99.58 166	99.34 118	99.65 82	99.52 116	98.26 141	99.83 54	99.87 56	93.37 291	99.90 137	97.81 254	99.91 42	99.49 202

StellarMVS		98.88 148	98.65 165	99.58 107	99.58 166	99.34 118	99.65 82	99.52 116	98.26 141	99.83 54	99.87 56	93.37 291	99.90 137	97.81 254	99.91 42	99.49 202

AstraMVS		99.09 123	99.03 103	99.25 183	99.66 134	98.13 254	99.57 129	98.24 411	98.82 78	99.91 27	99.88 45	95.81 189	99.90 137	99.72 28	99.67 148	99.74 102

mmtdpeth		96.95 343	96.71 342	97.67 363	99.33 253	94.90 389	99.89 2	99.28 307	98.15 158	99.72 90	98.57 398	86.56 401	99.90 137	99.82 25	89.02 423	98.20 393

UWE-MVS		97.58 311	97.29 318	98.48 287	99.09 319	96.25 354	99.01 360	96.61 434	97.86 199	99.19 231	99.01 369	88.72 377	99.90 137	97.38 298	98.69 227	99.28 243

test_vis1_rt		95.81 367	95.65 366	96.32 396	99.67 123	91.35 423	99.49 194	96.74 432	98.25 144	95.24 411	98.10 417	74.96 432	99.90 137	99.53 49	98.85 218	97.70 417

FA-MVS(test-final)		98.75 172	98.53 184	99.41 152	99.55 178	99.05 164	99.80 25	99.01 349	96.59 330	99.58 136	99.59 237	95.39 204	99.90 137	97.78 257	99.49 167	99.28 243

MCST-MVS		99.43 48	99.30 57	99.82 50	99.79 58	99.74 47	99.29 282	99.40 243	98.79 84	99.52 149	99.62 228	98.91 37	99.90 137	98.64 165	99.75 132	99.82 64

CDPH-MVS		99.13 106	98.91 130	99.80 56	99.75 82	99.71 51	99.15 326	99.41 236	96.60 328	99.60 132	99.55 252	98.83 45	99.90 137	97.48 289	99.83 103	99.78 90

NCCC		99.34 68	99.19 81	99.79 59	99.61 157	99.65 67	99.30 277	99.48 175	98.86 73	99.21 225	99.63 223	98.72 64	99.90 137	98.25 215	99.63 154	99.80 80

114514_t		98.93 144	98.67 160	99.72 77	99.85 26	99.53 93	99.62 98	99.59 67	92.65 413	99.71 92	99.78 142	98.06 106	99.90 137	98.84 139	99.91 42	99.74 102

1112_ss		98.98 140	98.77 150	99.59 104	99.68 121	99.02 166	99.25 303	99.48 175	97.23 275	99.13 240	99.58 241	96.93 144	99.90 137	98.87 129	98.78 224	99.84 49

PHI-MVS		99.30 75	99.17 83	99.70 78	99.56 174	99.52 97	99.58 122	99.80 8	97.12 284	99.62 126	99.73 169	98.58 75	99.90 137	98.61 171	99.91 42	99.68 135

AdaColmap		99.01 138	98.80 146	99.66 82	99.56 174	99.54 90	99.18 321	99.70 15	98.18 156	99.35 191	99.63 223	96.32 168	99.90 137	97.48 289	99.77 127	99.55 180

COLMAP_ROB	97.56 6	98.86 154	98.75 152	99.17 193	99.88 11	98.53 226	99.34 268	99.59 67	97.55 239	98.70 315	99.89 36	95.83 187	99.90 137	98.10 225	99.90 53	99.08 262
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 202	98.03 222	99.31 168	99.63 146	98.56 223	99.54 155	96.75 431	97.53 243	99.73 85	99.65 211	91.25 350	99.89 152	98.62 168	99.56 160	99.48 205

tttt0517		98.42 193	98.14 207	99.28 180	99.66 134	98.38 243	99.74 46	96.85 429	97.68 224	99.79 64	99.74 163	91.39 346	99.89 152	98.83 142	99.56 160	99.57 176

test12				99.75 68	99.64 143	99.61 77		99.29 305		99.21 225		98.38 91	99.89 152		99.74 135	99.74 102

Test_1112_low_res		98.89 147	98.66 163	99.57 111	99.69 116	98.95 180	99.03 352	99.47 196	96.98 298	99.15 238	99.23 345	96.77 148	99.89 152	98.83 142	98.78 224	99.86 38

CNLPA		99.14 104	98.99 114	99.59 104	99.58 166	99.41 111	99.16 323	99.44 225	98.45 118	99.19 231	99.49 275	98.08 105	99.89 152	97.73 265	99.75 132	99.48 205

guyue		99.16 98	99.04 100	99.52 130	99.69 116	98.92 187	99.59 112	98.81 379	98.73 91	99.90 30	99.87 56	95.34 207	99.88 157	99.66 36	99.81 110	99.74 102

sd_testset		98.75 172	98.57 180	99.29 176	99.81 48	98.26 247	99.56 136	99.62 46	98.78 87	99.64 119	99.88 45	92.02 329	99.88 157	99.54 47	98.26 254	99.72 118

APD_test1		95.87 365	96.49 347	94.00 403	99.53 182	84.01 432	99.54 155	99.32 292	95.91 371	97.99 366	99.85 70	85.49 407	99.88 157	91.96 412	98.84 219	98.12 397

diffmvs		99.14 104	99.02 108	99.51 133	99.61 157	98.96 177	99.28 287	99.49 163	98.46 116	99.72 90	99.71 176	96.50 160	99.88 157	99.31 77	99.11 196	99.67 138
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_BlendedMVS		98.86 154	98.80 146	99.03 208	99.76 72	98.79 203	99.28 287	99.91 3	97.42 258	99.67 102	99.37 312	97.53 118	99.88 157	98.98 112	97.29 314	98.42 378

PVSNet_Blended		99.08 125	98.97 118	99.42 151	99.76 72	98.79 203	98.78 391	99.91 3	96.74 313	99.67 102	99.49 275	97.53 118	99.88 157	98.98 112	99.85 86	99.60 165

MVS		97.28 332	96.55 345	99.48 139	98.78 369	98.95 180	99.27 292	99.39 246	83.53 434	98.08 361	99.54 257	96.97 142	99.87 163	94.23 390	99.16 190	99.63 157

MG-MVS		99.13 106	99.02 108	99.45 146	99.57 170	98.63 216	99.07 342	99.34 275	98.99 58	99.61 129	99.82 95	97.98 109	99.87 163	97.00 320	99.80 115	99.85 42

MSDG		98.98 140	98.80 146	99.53 124	99.76 72	99.19 141	98.75 394	99.55 89	97.25 272	99.47 157	99.77 151	97.82 112	99.87 163	96.93 327	99.90 53	99.54 182

ETV-MVS		99.26 83	99.21 77	99.40 153	99.46 215	99.30 129	99.56 136	99.52 116	98.52 111	99.44 165	99.27 340	98.41 90	99.86 166	99.10 100	99.59 158	99.04 269

thisisatest0515		98.14 220	97.79 246	99.19 191	99.50 203	98.50 233	98.61 406	96.82 430	96.95 302	99.54 145	99.43 293	91.66 341	99.86 166	98.08 230	99.51 164	99.22 251

thres600view7		97.86 264	97.51 281	98.92 225	99.72 101	97.95 268	99.59 112	98.74 389	97.94 191	99.27 210	98.62 395	91.75 335	99.86 166	93.73 396	98.19 261	98.96 279

lupinMVS		99.13 106	99.01 112	99.46 145	99.51 191	98.94 183	99.05 347	99.16 328	97.86 199	99.80 62	99.56 249	97.39 121	99.86 166	98.94 117	99.85 86	99.58 173

PVSNet	96.02 17	98.85 161	98.84 143	98.89 234	99.73 97	97.28 297	98.32 422	99.60 61	97.86 199	99.50 152	99.57 246	96.75 149	99.86 166	98.56 183	99.70 142	99.54 182

MAR-MVS		98.86 154	98.63 168	99.54 116	99.37 243	99.66 63	99.45 213	99.54 98	96.61 325	99.01 264	99.40 303	97.09 135	99.86 166	97.68 272	99.53 163	99.10 257
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		97.44 324	97.02 333	98.71 263	99.18 295	96.89 328	99.19 319	99.04 345	97.78 212	98.31 348	98.29 409	85.41 408	99.85 172	98.01 236	97.95 271	99.39 229

test2506		96.81 347	96.65 343	97.29 377	99.74 90	92.21 420	99.60 105	85.06 451	99.13 33	99.77 73	99.93 10	87.82 394	99.85 172	99.38 66	99.38 173	99.80 80

AllTest		98.87 151	98.72 154	99.31 168	99.86 20	98.48 236	99.56 136	99.61 54	97.85 202	99.36 188	99.85 70	95.95 180	99.85 172	96.66 340	99.83 103	99.59 169

TestCases				99.31 168	99.86 20	98.48 236		99.61 54	97.85 202	99.36 188	99.85 70	95.95 180	99.85 172	96.66 340	99.83 103	99.59 169

jason		99.13 106	99.03 103	99.45 146	99.46 215	98.87 191	99.12 332	99.26 311	98.03 184	99.79 64	99.65 211	97.02 140	99.85 172	99.02 109	99.90 53	99.65 145
jason: jason.
CNVR-MVS		99.42 50	99.30 57	99.78 62	99.62 152	99.71 51	99.26 301	99.52 116	98.82 78	99.39 181	99.71 176	98.96 25	99.85 172	98.59 176	99.80 115	99.77 92

PAPM_NR		99.04 131	98.84 143	99.66 82	99.74 90	99.44 107	99.39 248	99.38 254	97.70 222	99.28 205	99.28 337	98.34 93	99.85 172	96.96 324	99.45 169	99.69 131

testing99		97.36 327	96.94 336	98.63 269	99.18 295	96.70 334	99.30 277	98.93 357	97.71 219	98.23 353	98.26 410	84.92 411	99.84 179	98.04 235	97.85 278	99.35 235

testing222		97.16 337	96.50 346	99.16 194	99.16 305	98.47 238	99.27 292	98.66 400	97.71 219	98.23 353	98.15 413	82.28 425	99.84 179	97.36 299	97.66 284	99.18 253

test1111		98.04 235	98.11 211	97.83 353	99.74 90	93.82 405	99.58 122	95.40 438	99.12 38	99.65 114	99.93 10	90.73 355	99.84 179	99.43 63	99.38 173	99.82 64

ECVR-MVS		98.04 235	98.05 220	98.00 337	99.74 90	94.37 400	99.59 112	94.98 439	99.13 33	99.66 107	99.93 10	90.67 356	99.84 179	99.40 64	99.38 173	99.80 80

test_yl		98.86 154	98.63 168	99.54 116	99.49 205	99.18 143	99.50 182	99.07 341	98.22 149	99.61 129	99.51 269	95.37 205	99.84 179	98.60 174	98.33 248	99.59 169

DCV-MVSNet		98.86 154	98.63 168	99.54 116	99.49 205	99.18 143	99.50 182	99.07 341	98.22 149	99.61 129	99.51 269	95.37 205	99.84 179	98.60 174	98.33 248	99.59 169

Fast-Effi-MVS+		98.70 176	98.43 188	99.51 133	99.51 191	99.28 132	99.52 165	99.47 196	96.11 364	99.01 264	99.34 322	96.20 172	99.84 179	97.88 244	98.82 221	99.39 229

TSAR-MVS + GP.		99.36 65	99.36 41	99.36 159	99.67 123	98.61 220	99.07 342	99.33 282	99.00 56	99.82 57	99.81 109	99.06 16	99.84 179	99.09 101	99.42 171	99.65 145

tpmrst		98.33 203	98.48 186	97.90 346	99.16 305	94.78 390	99.31 275	99.11 334	97.27 270	99.45 160	99.59 237	95.33 208	99.84 179	98.48 190	98.61 230	99.09 261

Vis-MVSNet		99.12 112	98.97 118	99.56 113	99.78 60	99.10 155	99.68 66	99.66 28	98.49 113	99.86 45	99.87 56	94.77 237	99.84 179	99.19 89	99.41 172	99.74 102
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 184	98.34 194	99.51 133	99.40 235	99.03 165	98.80 389	99.36 263	96.33 345	99.00 268	99.12 359	98.46 84	99.84 179	95.23 376	99.37 180	99.66 141

PatchMatch-RL		98.84 164	98.62 173	99.52 130	99.71 106	99.28 132	99.06 345	99.77 9	97.74 217	99.50 152	99.53 261	95.41 203	99.84 179	97.17 313	99.64 152	99.44 221

EPP-MVSNet		99.13 106	98.99 114	99.53 124	99.65 141	99.06 162	99.81 20	99.33 282	97.43 256	99.60 132	99.88 45	97.14 133	99.84 179	99.13 95	98.94 210	99.69 131

testing3-2		97.84 269	97.70 261	98.24 319	99.53 182	95.37 378	99.55 150	98.67 399	98.46 116	99.27 210	99.34 322	86.58 400	99.83 192	99.32 76	98.63 229	99.52 189

testing11		97.50 317	97.10 330	98.71 263	99.20 289	96.91 326	99.29 282	98.82 377	97.89 196	98.21 356	98.40 404	85.63 406	99.83 192	98.45 195	98.04 269	99.37 233

thres100view900		97.76 283	97.45 290	98.69 265	99.72 101	97.86 274	99.59 112	98.74 389	97.93 192	99.26 215	98.62 395	91.75 335	99.83 192	93.22 401	98.18 262	98.37 384

tfpn200view9		97.72 293	97.38 303	98.72 261	99.69 116	97.96 265	99.50 182	98.73 395	97.83 205	99.17 236	98.45 402	91.67 339	99.83 192	93.22 401	98.18 262	98.37 384

test_prior				99.68 80	99.67 123	99.48 102		99.56 81					99.83 192			99.74 102

1314		98.68 178	98.54 183	99.11 200	98.89 352	98.65 213	99.27 292	99.49 163	96.89 306	97.99 366	99.56 249	97.72 116	99.83 192	97.74 264	99.27 184	98.84 285

thres400		97.77 282	97.38 303	98.92 225	99.69 116	97.96 265	99.50 182	98.73 395	97.83 205	99.17 236	98.45 402	91.67 339	99.83 192	93.22 401	98.18 262	98.96 279

casdiffmvs		99.13 106	98.98 117	99.56 113	99.65 141	99.16 146	99.56 136	99.50 153	98.33 133	99.41 174	99.86 63	95.92 183	99.83 192	99.45 62	99.16 190	99.70 129
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 28	99.48 19	99.54 116	99.78 60	99.30 129	99.89 2	99.58 71	98.56 107	99.73 85	99.69 191	98.55 78	99.82 200	99.69 31	99.85 86	99.48 205

MVS_Test		99.10 122	98.97 118	99.48 139	99.49 205	99.14 151	99.67 69	99.34 275	97.31 267	99.58 136	99.76 155	97.65 117	99.82 200	98.87 129	99.07 202	99.46 216

dp		97.75 287	97.80 245	97.59 368	99.10 316	93.71 408	99.32 272	98.88 370	96.48 337	99.08 252	99.55 252	92.67 313	99.82 200	96.52 344	98.58 233	99.24 249

RPSCF		98.22 210	98.62 173	96.99 383	99.82 44	91.58 422	99.72 52	99.44 225	96.61 325	99.66 107	99.89 36	95.92 183	99.82 200	97.46 292	99.10 199	99.57 176

PMMVS		98.80 168	98.62 173	99.34 161	99.27 271	98.70 209	98.76 393	99.31 296	97.34 264	99.21 225	99.07 361	97.20 132	99.82 200	98.56 183	98.87 216	99.52 189

UBG		97.85 265	97.48 284	98.95 219	99.25 278	97.64 285	99.24 306	98.74 389	97.90 195	98.64 325	98.20 412	88.65 381	99.81 205	98.27 213	98.40 243	99.42 223

EIA-MVS		99.18 94	99.09 94	99.45 146	99.49 205	99.18 143	99.67 69	99.53 111	97.66 227	99.40 179	99.44 291	98.10 103	99.81 205	98.94 117	99.62 155	99.35 235

Effi-MVS+		98.81 165	98.59 179	99.48 139	99.46 215	99.12 154	98.08 429	99.50 153	97.50 247	99.38 183	99.41 299	96.37 167	99.81 205	99.11 97	98.54 238	99.51 197

thres200		97.61 309	97.28 319	98.62 270	99.64 143	98.03 259	99.26 301	98.74 389	97.68 224	99.09 250	98.32 408	91.66 341	99.81 205	92.88 406	98.22 257	98.03 403

tpmvs		97.98 246	98.02 224	97.84 352	99.04 330	94.73 391	99.31 275	99.20 323	96.10 368	98.76 305	99.42 295	94.94 223	99.81 205	96.97 323	98.45 242	98.97 277

casdiffmvs_mvg		99.15 101	99.02 108	99.55 115	99.66 134	99.09 156	99.64 87	99.56 81	98.26 141	99.45 160	99.87 56	96.03 177	99.81 205	99.54 47	99.15 193	99.73 110
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	98.81 165	99.37 39	97.12 381	99.60 162	91.75 421	98.61 406	99.44 225	99.35 21	99.83 54	99.85 70	98.70 66	99.81 205	99.02 109	99.91 42	99.81 71

DPM-MVS		98.95 143	98.71 156	99.66 82	99.63 146	99.55 88	98.64 405	99.10 335	97.93 192	99.42 170	99.55 252	98.67 69	99.80 212	95.80 361	99.68 146	99.61 162

DP-MVS Recon		99.12 112	98.95 124	99.65 86	99.74 90	99.70 53	99.27 292	99.57 76	96.40 344	99.42 170	99.68 198	98.75 58	99.80 212	97.98 238	99.72 138	99.44 221

MVS_111021_LR		99.41 54	99.33 47	99.65 86	99.77 68	99.51 98	98.94 375	99.85 6	98.82 78	99.65 114	99.74 163	98.51 81	99.80 212	98.83 142	99.89 64	99.64 152

CS-MVS		99.50 26	99.48 19	99.54 116	99.76 72	99.42 109	99.90 1	99.55 89	98.56 107	99.78 69	99.70 180	98.65 71	99.79 215	99.65 37	99.78 124	99.41 226

Fast-Effi-MVS+-dtu		98.77 171	98.83 145	98.60 271	99.41 230	96.99 320	99.52 165	99.49 163	98.11 167	99.24 217	99.34 322	96.96 143	99.79 215	97.95 240	99.45 169	99.02 272

baseline1		98.31 204	97.95 231	99.38 158	99.50 203	98.74 206	99.59 112	98.93 357	98.41 123	99.14 239	99.60 235	94.59 249	99.79 215	98.48 190	93.29 397	99.61 162

baseline		99.15 101	99.02 108	99.53 124	99.66 134	99.14 151	99.72 52	99.48 175	98.35 130	99.42 170	99.84 81	96.07 175	99.79 215	99.51 52	99.14 194	99.67 138

PVSNet_0	94.43 19	96.09 362	95.47 369	97.94 342	99.31 261	94.34 402	97.81 431	99.70 15	97.12 284	97.46 381	98.75 392	89.71 367	99.79 215	97.69 271	81.69 434	99.68 135

API-MVS		99.04 131	99.03 103	99.06 204	99.40 235	99.31 126	99.55 150	99.56 81	98.54 109	99.33 195	99.39 307	98.76 55	99.78 220	96.98 322	99.78 124	98.07 400

OMC-MVS		99.08 125	99.04 100	99.20 190	99.67 123	98.22 249	99.28 287	99.52 116	98.07 175	99.66 107	99.81 109	97.79 113	99.78 220	97.79 256	99.81 110	99.60 165

GeoE		98.85 161	98.62 173	99.53 124	99.61 157	99.08 159	99.80 25	99.51 133	97.10 288	99.31 197	99.78 142	95.23 214	99.77 222	98.21 217	99.03 205	99.75 98

alignmvs		98.81 165	98.56 182	99.58 107	99.43 223	99.42 109	99.51 174	98.96 355	98.61 102	99.35 191	98.92 382	94.78 234	99.77 222	99.35 68	98.11 267	99.54 182

tpm cat1		97.39 326	97.36 305	97.50 371	99.17 303	93.73 407	99.43 224	99.31 296	91.27 417	98.71 309	99.08 360	94.31 264	99.77 222	96.41 349	98.50 240	99.00 273

CostFormer		97.72 293	97.73 258	97.71 361	99.15 309	94.02 404	99.54 155	99.02 348	94.67 392	99.04 261	99.35 318	92.35 325	99.77 222	98.50 189	97.94 272	99.34 238

MGCFI-Net		99.01 138	98.85 141	99.50 138	99.42 225	99.26 135	99.82 16	99.48 175	98.60 104	99.28 205	98.81 387	97.04 139	99.76 226	99.29 80	97.87 276	99.47 211

test_241102_ONE					99.84 32	99.90 2		99.48 175	99.07 48	99.91 27	99.74 163	99.20 7	99.76 226

MDTV_nov1_ep13			98.32 196		99.11 313	94.44 398	99.27 292	98.74 389	97.51 246	99.40 179	99.62 228	94.78 234	99.76 226	97.59 276	98.81 223

sasdasda		99.02 134	98.86 139	99.51 133	99.42 225	99.32 122	99.80 25	99.48 175	98.63 99	99.31 197	98.81 387	97.09 135	99.75 229	99.27 83	97.90 273	99.47 211

canonicalmvs		99.02 134	98.86 139	99.51 133	99.42 225	99.32 122	99.80 25	99.48 175	98.63 99	99.31 197	98.81 387	97.09 135	99.75 229	99.27 83	97.90 273	99.47 211

Effi-MVS+-dtu		98.78 169	98.89 134	98.47 292	99.33 253	96.91 326	99.57 129	99.30 301	98.47 115	99.41 174	98.99 372	96.78 147	99.74 231	98.73 153	99.38 173	98.74 301

patchmatchnet-post											98.70 393	94.79 233	99.74 231

SCA		98.19 214	98.16 204	98.27 318	99.30 262	95.55 369	99.07 342	98.97 353	97.57 236	99.43 167	99.57 246	92.72 308	99.74 231	97.58 277	99.20 188	99.52 189

BH-untuned		98.42 193	98.36 192	98.59 272	99.49 205	96.70 334	99.27 292	99.13 332	97.24 274	98.80 300	99.38 309	95.75 191	99.74 231	97.07 318	99.16 190	99.33 239

BH-RMVSNet		98.41 195	98.08 216	99.40 153	99.41 230	98.83 199	99.30 277	98.77 385	97.70 222	98.94 278	99.65 211	92.91 303	99.74 231	96.52 344	99.55 162	99.64 152

MVS_111021_HR		99.41 54	99.32 49	99.66 82	99.72 101	99.47 104	98.95 373	99.85 6	98.82 78	99.54 145	99.73 169	98.51 81	99.74 231	98.91 123	99.88 68	99.77 92

test_post											65.99 445	94.65 247	99.73 237

XVG-ACMP-BASELINE		97.83 272	97.71 260	98.20 321	99.11 313	96.33 350	99.41 236	99.52 116	98.06 179	99.05 260	99.50 272	89.64 369	99.73 237	97.73 265	97.38 311	98.53 366

HyFIR lowres test		99.11 118	98.92 127	99.65 86	99.90 4	99.37 114	99.02 355	99.91 3	97.67 226	99.59 135	99.75 158	95.90 185	99.73 237	99.53 49	99.02 207	99.86 38

DeepMVS_CX				93.34 406	99.29 266	82.27 435		99.22 319	85.15 432	96.33 403	99.05 364	90.97 353	99.73 237	93.57 398	97.77 281	98.01 404

Patchmatch-test		97.93 252	97.65 266	98.77 257	99.18 295	97.07 311	99.03 352	99.14 331	96.16 359	98.74 306	99.57 246	94.56 251	99.72 241	93.36 400	99.11 196	99.52 189

LPG-MVS_test		98.22 210	98.13 209	98.49 285	99.33 253	97.05 313	99.58 122	99.55 89	97.46 249	99.24 217	99.83 86	92.58 315	99.72 241	98.09 226	97.51 297	98.68 319

LGP-MVS_train				98.49 285	99.33 253	97.05 313		99.55 89	97.46 249	99.24 217	99.83 86	92.58 315	99.72 241	98.09 226	97.51 297	98.68 319

BH-w/o		98.00 244	97.89 240	98.32 310	99.35 247	96.20 356	99.01 360	98.90 367	96.42 342	98.38 344	99.00 370	95.26 212	99.72 241	96.06 354	98.61 230	99.03 270

ACMP	97.20 11	98.06 229	97.94 233	98.45 295	99.37 243	97.01 318	99.44 219	99.49 163	97.54 242	98.45 341	99.79 135	91.95 331	99.72 241	97.91 242	97.49 302	98.62 349
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 239	97.90 236	98.40 303	99.23 282	96.80 332	99.70 56	99.60 61	97.12 284	98.18 358	99.70 180	91.73 337	99.72 241	98.39 200	97.45 304	98.68 319
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							99.23 309				65.14 446	94.18 269	99.71 247	97.58 277

ADS-MVSNet		98.20 213	98.08 216	98.56 279	99.33 253	96.48 345	99.23 309	99.15 329	96.24 352	99.10 247	99.67 204	94.11 270	99.71 247	96.81 332	99.05 203	99.48 205

JIA-IIPM		97.50 317	97.02 333	98.93 223	98.73 378	97.80 276	99.30 277	98.97 353	91.73 416	98.91 281	94.86 434	95.10 218	99.71 247	97.58 277	97.98 270	99.28 243

EPMVS		97.82 275	97.65 266	98.35 307	98.88 353	95.98 360	99.49 194	94.71 441	97.57 236	99.26 215	99.48 281	92.46 322	99.71 247	97.87 246	99.08 201	99.35 235

TDRefinement		95.42 373	94.57 381	97.97 339	89.83 444	96.11 359	99.48 199	98.75 386	96.74 313	96.68 400	99.88 45	88.65 381	99.71 247	98.37 203	82.74 433	98.09 399

ACMM	97.58 5	98.37 201	98.34 194	98.48 287	99.41 230	97.10 307	99.56 136	99.45 216	98.53 110	99.04 261	99.85 70	93.00 299	99.71 247	98.74 151	97.45 304	98.64 340
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 249	97.77 251	98.57 276	99.59 164	96.61 341	99.45 213	99.08 338	98.21 151	98.88 286	99.80 123	88.66 380	99.70 253	98.58 177	97.72 282	99.39 229

CHOSEN 280x420		99.12 112	99.13 86	99.08 201	99.66 134	97.89 271	98.43 416	99.71 13	98.88 72	99.62 126	99.76 155	96.63 153	99.70 253	99.46 61	99.99 1	99.66 141

EC-MVSNet		99.44 45	99.39 35	99.58 107	99.56 174	99.49 100	99.88 4	99.58 71	98.38 125	99.73 85	99.69 191	98.20 99	99.70 253	99.64 39	99.82 107	99.54 182

PatchmatchNet		98.31 204	98.36 192	98.19 322	99.16 305	95.32 379	99.27 292	98.92 360	97.37 262	99.37 185	99.58 241	94.90 227	99.70 253	97.43 295	99.21 187	99.54 182
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 224	97.99 226	98.44 298	99.41 230	96.96 324	99.60 105	99.56 81	98.09 170	98.15 359	99.91 23	90.87 354	99.70 253	98.88 126	97.45 304	98.67 327
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 317	96.90 337	99.29 176	99.23 282	98.78 205	99.32 272	98.90 367	97.52 245	98.56 334	98.09 418	84.72 413	99.69 258	97.86 247	97.88 275	99.39 229

HQP_MVS		98.27 209	98.22 202	98.44 298	99.29 266	96.97 322	99.39 248	99.47 196	98.97 64	99.11 244	99.61 232	92.71 310	99.69 258	97.78 257	97.63 285	98.67 327

plane_prior5								99.47 196					99.69 258	97.78 257	97.63 285	98.67 327

D2MVS		98.41 195	98.50 185	98.15 327	99.26 274	96.62 340	99.40 244	99.61 54	97.71 219	98.98 271	99.36 315	96.04 176	99.67 261	98.70 156	97.41 309	98.15 396

IS-MVSNet		99.05 130	98.87 137	99.57 111	99.73 97	99.32 122	99.75 42	99.20 323	98.02 186	99.56 140	99.86 63	96.54 158	99.67 261	98.09 226	99.13 195	99.73 110

CLD-MVS		98.16 218	98.10 212	98.33 308	99.29 266	96.82 331	98.75 394	99.44 225	97.83 205	99.13 240	99.55 252	92.92 301	99.67 261	98.32 210	97.69 283	98.48 370
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 334	97.30 316	97.09 382	99.43 223	93.31 413	99.73 50	98.87 372	98.83 77	99.28 205	99.80 123	84.45 414	99.66 264	97.88 244	97.45 304	98.30 386

AUN-MVS		96.88 345	96.31 351	98.59 272	99.48 212	97.04 316	99.27 292	99.22 319	97.44 255	98.51 337	99.41 299	91.97 330	99.66 264	97.71 268	83.83 431	99.07 267

UniMVSNet_ETH3D		97.32 331	96.81 339	98.87 240	99.40 235	97.46 291	99.51 174	99.53 111	95.86 372	98.54 336	99.77 151	82.44 423	99.66 264	98.68 161	97.52 296	99.50 201

OPM-MVS		98.19 214	98.10 212	98.45 295	98.88 353	97.07 311	99.28 287	99.38 254	98.57 106	99.22 222	99.81 109	92.12 327	99.66 264	98.08 230	97.54 294	98.61 358
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 255	97.78 249	98.32 310	99.46 215	96.68 338	99.56 136	99.54 98	98.41 123	97.79 377	99.87 56	90.18 363	99.66 264	98.05 234	97.18 319	98.62 349

hse-mvs2		97.50 317	97.14 327	98.59 272	99.49 205	97.05 313	99.28 287	99.22 319	98.94 67	99.66 107	99.42 295	94.93 224	99.65 269	99.48 58	83.80 432	99.08 262

VPA-MVSNet		98.29 207	97.95 231	99.30 173	99.16 305	99.54 90	99.50 182	99.58 71	98.27 139	99.35 191	99.37 312	92.53 317	99.65 269	99.35 68	94.46 378	98.72 303

TR-MVS		97.76 283	97.41 301	98.82 249	99.06 325	97.87 272	98.87 383	98.56 403	96.63 324	98.68 317	99.22 346	92.49 318	99.65 269	95.40 372	97.79 280	98.95 281

reproduce_monomvs		97.89 259	97.87 241	97.96 341	99.51 191	95.45 374	99.60 105	99.25 313	99.17 28	98.85 294	99.49 275	89.29 372	99.64 272	99.35 68	96.31 335	98.78 289

gm-plane-assit					98.54 398	92.96 415			94.65 393		99.15 354		99.64 272	97.56 282

HQP4-MVS										98.66 318			99.64 272			98.64 340

HQP-MVS		98.02 239	97.90 236	98.37 306	99.19 292	96.83 329	98.98 366	99.39 246	98.24 145	98.66 318	99.40 303	92.47 319	99.64 272	97.19 310	97.58 290	98.64 340

PAPM		97.59 310	97.09 331	99.07 202	99.06 325	98.26 247	98.30 423	99.10 335	94.88 387	98.08 361	99.34 322	96.27 170	99.64 272	89.87 420	98.92 213	99.31 241

TAPA-MVS	97.07 15	97.74 289	97.34 310	98.94 221	99.70 111	97.53 288	99.25 303	99.51 133	91.90 415	99.30 201	99.63 223	98.78 51	99.64 272	88.09 427	99.87 71	99.65 145
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 199	98.09 215	99.24 186	99.26 274	99.32 122	99.56 136	99.55 89	97.45 252	98.71 309	99.83 86	93.23 294	99.63 278	98.88 126	96.32 334	98.76 295

ITE_SJBPF				98.08 330	99.29 266	96.37 348		98.92 360	98.34 131	98.83 295	99.75 158	91.09 351	99.62 279	95.82 359	97.40 310	98.25 390

LF4IMVS		97.52 314	97.46 289	97.70 362	98.98 341	95.55 369	99.29 282	98.82 377	98.07 175	98.66 318	99.64 217	89.97 364	99.61 280	97.01 319	96.68 324	97.94 411

tpm		97.67 304	97.55 275	98.03 332	99.02 332	95.01 386	99.43 224	98.54 405	96.44 340	99.12 242	99.34 322	91.83 334	99.60 281	97.75 263	96.46 330	99.48 205

tpm2		97.44 324	97.34 310	97.74 360	99.15 309	94.36 401	99.45 213	98.94 356	93.45 406	98.90 283	99.44 291	91.35 347	99.59 282	97.31 301	98.07 268	99.29 242

baseline2		97.87 262	97.55 275	98.82 249	99.18 295	98.02 260	99.41 236	96.58 435	96.97 299	96.51 401	99.17 351	93.43 289	99.57 283	97.71 268	99.03 205	98.86 283

MS-PatchMatch		97.24 336	97.32 314	96.99 383	98.45 401	93.51 412	98.82 387	99.32 292	97.41 259	98.13 360	99.30 333	88.99 374	99.56 284	95.68 365	99.80 115	97.90 414

TinyColmap		97.12 339	96.89 338	97.83 353	99.07 323	95.52 372	98.57 409	98.74 389	97.58 235	97.81 376	99.79 135	88.16 388	99.56 284	95.10 377	97.21 317	98.39 382

USDC		97.34 329	97.20 324	97.75 358	99.07 323	95.20 381	98.51 413	99.04 345	97.99 187	98.31 348	99.86 63	89.02 373	99.55 286	95.67 366	97.36 312	98.49 369

MSLP-MVS++		99.46 37	99.47 21	99.44 150	99.60 162	99.16 146	99.41 236	99.71 13	98.98 61	99.45 160	99.78 142	99.19 9	99.54 287	99.28 81	99.84 94	99.63 157

UWE-MVS-28		97.36 327	97.24 323	97.75 358	98.84 362	94.44 398	99.24 306	97.58 424	97.98 188	99.00 268	99.00 370	91.35 347	99.53 288	93.75 395	98.39 244	99.27 247

TAMVS		99.12 112	99.08 95	99.24 186	99.46 215	98.55 224	99.51 174	99.46 205	98.09 170	99.45 160	99.82 95	98.34 93	99.51 289	98.70 156	98.93 211	99.67 138

EPNet_dtu		98.03 237	97.96 229	98.23 320	98.27 404	95.54 371	99.23 309	98.75 386	99.02 51	97.82 375	99.71 176	96.11 174	99.48 290	93.04 404	99.65 151	99.69 131
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
mvs5depth		96.66 349	96.22 353	97.97 339	97.00 426	96.28 352	98.66 403	99.03 347	96.61 325	96.93 398	99.79 135	87.20 397	99.47 291	96.65 342	94.13 385	98.16 395

EG-PatchMatch MVS		95.97 364	95.69 365	96.81 390	97.78 411	92.79 416	99.16 323	98.93 357	96.16 359	94.08 419	99.22 346	82.72 421	99.47 291	95.67 366	97.50 299	98.17 394

myMVS_eth3d28		97.69 298	97.34 310	98.73 259	99.27 271	97.52 289	99.33 270	98.78 384	98.03 184	98.82 297	98.49 400	86.64 399	99.46 293	98.44 196	98.24 256	99.23 250

MVP-Stereo		97.81 277	97.75 256	97.99 338	97.53 415	96.60 342	98.96 370	98.85 374	97.22 276	97.23 388	99.36 315	95.28 209	99.46 293	95.51 368	99.78 124	97.92 413
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 186	98.67 160	98.30 312	99.35 247	95.59 368	99.50 182	99.55 89	98.60 104	99.39 181	99.83 86	94.48 257	99.45 295	98.75 150	98.56 236	99.85 42

test-LLR		98.06 229	97.90 236	98.55 281	98.79 366	97.10 307	98.67 400	97.75 420	97.34 264	98.61 330	98.85 384	94.45 259	99.45 295	97.25 304	99.38 173	99.10 257

TESTMET0.1,1		97.55 312	97.27 322	98.40 303	98.93 346	96.53 343	98.67 400	97.61 423	96.96 300	98.64 325	99.28 337	88.63 383	99.45 295	97.30 302	99.38 173	99.21 252

test-mter		97.49 322	97.13 329	98.55 281	98.79 366	97.10 307	98.67 400	97.75 420	96.65 320	98.61 330	98.85 384	88.23 387	99.45 295	97.25 304	99.38 173	99.10 257

mvs_anonymous		99.03 133	98.99 114	99.16 194	99.38 240	98.52 230	99.51 174	99.38 254	97.79 210	99.38 183	99.81 109	97.30 127	99.45 295	99.35 68	98.99 208	99.51 197

tfpnnormal		97.84 269	97.47 287	98.98 214	99.20 289	99.22 140	99.64 87	99.61 54	96.32 346	98.27 352	99.70 180	93.35 293	99.44 300	95.69 364	95.40 361	98.27 388

v7n		97.87 262	97.52 279	98.92 225	98.76 376	98.58 222	99.84 12	99.46 205	96.20 355	98.91 281	99.70 180	94.89 228	99.44 300	96.03 355	93.89 390	98.75 297

jajsoiax		98.43 192	98.28 199	98.88 236	98.60 393	98.43 240	99.82 16	99.53 111	98.19 153	98.63 327	99.80 123	93.22 296	99.44 300	99.22 87	97.50 299	98.77 293

mvs_tets		98.40 198	98.23 201	98.91 229	98.67 386	98.51 232	99.66 76	99.53 111	98.19 153	98.65 324	99.81 109	92.75 305	99.44 300	99.31 77	97.48 303	98.77 293

sc_t1		95.75 368	95.05 375	97.87 348	98.83 363	94.61 395	99.21 315	99.45 216	87.45 428	97.97 368	99.85 70	81.19 428	99.43 304	98.27 213	93.20 399	99.57 176

Vis-MVSNet (Re-imp)		98.87 151	98.72 154	99.31 168	99.71 106	98.88 190	99.80 25	99.44 225	97.91 194	99.36 188	99.78 142	95.49 201	99.43 304	97.91 242	99.11 196	99.62 160

OPU-MVS				99.64 92	99.56 174	99.72 49	99.60 105				99.70 180	99.27 5	99.42 306	98.24 216	99.80 115	99.79 84

Anonymous20231211		97.88 260	97.54 278	98.90 231	99.71 106	98.53 226	99.48 199	99.57 76	94.16 397	98.81 298	99.68 198	93.23 294	99.42 306	98.84 139	94.42 380	98.76 295

ttmdpeth		97.80 279	97.63 270	98.29 313	98.77 374	97.38 294	99.64 87	99.36 263	98.78 87	96.30 404	99.58 241	92.34 326	99.39 308	98.36 205	95.58 356	98.10 398

VPNet		97.84 269	97.44 295	99.01 210	99.21 287	98.94 183	99.48 199	99.57 76	98.38 125	99.28 205	99.73 169	88.89 375	99.39 308	99.19 89	93.27 398	98.71 305

nrg030		98.64 183	98.42 189	99.28 180	99.05 328	99.69 55	99.81 20	99.46 205	98.04 182	99.01 264	99.82 95	96.69 151	99.38 310	99.34 73	94.59 377	98.78 289

GA-MVS		97.85 265	97.47 287	99.00 212	99.38 240	97.99 262	98.57 409	99.15 329	97.04 295	98.90 283	99.30 333	89.83 366	99.38 310	96.70 337	98.33 248	99.62 160

UniMVSNet (Re)		98.29 207	98.00 225	99.13 199	99.00 335	99.36 117	99.49 194	99.51 133	97.95 190	98.97 273	99.13 356	96.30 169	99.38 310	98.36 205	93.34 396	98.66 336

FIs		98.78 169	98.63 168	99.23 188	99.18 295	99.54 90	99.83 15	99.59 67	98.28 137	98.79 302	99.81 109	96.75 149	99.37 313	99.08 102	96.38 332	98.78 289

PS-MVSNAJss		98.92 145	98.92 127	98.90 231	98.78 369	98.53 226	99.78 32	99.54 98	98.07 175	99.00 268	99.76 155	99.01 18	99.37 313	99.13 95	97.23 316	98.81 286

CDS-MVSNet		99.09 123	99.03 103	99.25 183	99.42 225	98.73 207	99.45 213	99.46 205	98.11 167	99.46 159	99.77 151	98.01 108	99.37 313	98.70 156	98.92 213	99.66 141
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 368	95.16 373	97.51 370	99.30 262	93.69 409	98.88 381	95.78 436	85.09 433	98.78 303	92.65 436	91.29 349	99.37 313	94.85 382	99.85 86	99.46 216

v1192		97.81 277	97.44 295	98.91 229	98.88 353	98.68 210	99.51 174	99.34 275	96.18 357	99.20 228	99.34 322	94.03 274	99.36 317	95.32 374	95.18 365	98.69 314

EI-MVSNet		98.67 179	98.67 160	98.68 266	99.35 247	97.97 263	99.50 182	99.38 254	96.93 305	99.20 228	99.83 86	97.87 110	99.36 317	98.38 201	97.56 292	98.71 305

MVSTER		98.49 187	98.32 196	99.00 212	99.35 247	99.02 166	99.54 155	99.38 254	97.41 259	99.20 228	99.73 169	93.86 282	99.36 317	98.87 129	97.56 292	98.62 349

gg-mvs-nofinetune		96.17 360	95.32 372	98.73 259	98.79 366	98.14 253	99.38 253	94.09 442	91.07 420	98.07 364	91.04 440	89.62 370	99.35 320	96.75 334	99.09 200	98.68 319

pm-mvs1		97.68 301	97.28 319	98.88 236	99.06 325	98.62 218	99.50 182	99.45 216	96.32 346	97.87 373	99.79 135	92.47 319	99.35 320	97.54 284	93.54 394	98.67 327

OurMVSNet-221017-0		97.88 260	97.77 251	98.19 322	98.71 382	96.53 343	99.88 4	99.00 350	97.79 210	98.78 303	99.94 6	91.68 338	99.35 320	97.21 306	96.99 323	98.69 314

EGC-MVSNET		82.80 405	77.86 411	97.62 365	97.91 408	96.12 358	99.33 270	99.28 307	8.40 448	25.05 449	99.27 340	84.11 415	99.33 323	89.20 422	98.22 257	97.42 422

pmmvs6		96.53 352	96.09 357	97.82 355	98.69 384	95.47 373	99.37 255	99.47 196	93.46 405	97.41 382	99.78 142	87.06 398	99.33 323	96.92 329	92.70 406	98.65 338

V42		98.06 229	97.79 246	98.86 243	98.98 341	98.84 196	99.69 60	99.34 275	96.53 332	99.30 201	99.37 312	94.67 245	99.32 325	97.57 281	94.66 375	98.42 378

lessismore_v0				97.79 357	98.69 384	95.44 376		94.75 440		95.71 410	99.87 56	88.69 379	99.32 325	95.89 358	94.93 372	98.62 349

OpenMVS_ROB	92.34 20	94.38 385	93.70 391	96.41 395	97.38 417	93.17 414	99.06 345	98.75 386	86.58 431	94.84 417	98.26 410	81.53 426	99.32 325	89.01 423	97.87 276	96.76 425

v8		97.95 251	97.63 270	98.93 223	98.95 345	98.81 202	99.80 25	99.41 236	96.03 369	99.10 247	99.42 295	94.92 226	99.30 328	96.94 326	94.08 387	98.66 336

v1921920		97.80 279	97.45 290	98.84 247	98.80 365	98.53 226	99.52 165	99.34 275	96.15 361	99.24 217	99.47 284	93.98 276	99.29 329	95.40 372	95.13 367	98.69 314

anonymousdsp		98.44 191	98.28 199	98.94 221	98.50 399	98.96 177	99.77 34	99.50 153	97.07 290	98.87 289	99.77 151	94.76 238	99.28 330	98.66 163	97.60 288	98.57 364

MVSFormer		99.17 96	99.12 88	99.29 176	99.51 191	98.94 183	99.88 4	99.46 205	97.55 239	99.80 62	99.65 211	97.39 121	99.28 330	99.03 107	99.85 86	99.65 145

test_djsdf		98.67 179	98.57 180	98.98 214	98.70 383	98.91 188	99.88 4	99.46 205	97.55 239	99.22 222	99.88 45	95.73 192	99.28 330	99.03 107	97.62 287	98.75 297

VortexMVS		98.67 179	98.66 163	98.68 266	99.62 152	97.96 265	99.59 112	99.41 236	98.13 163	99.31 197	99.70 180	95.48 202	99.27 333	99.40 64	97.32 313	98.79 287

SSC-MVS3.2		97.34 329	97.15 326	97.93 343	99.02 332	95.76 365	99.48 199	99.58 71	97.62 231	99.09 250	99.53 261	87.95 390	99.27 333	96.42 347	95.66 354	98.75 297

cascas		97.69 298	97.43 299	98.48 287	98.60 393	97.30 296	98.18 427	99.39 246	92.96 409	98.41 342	98.78 391	93.77 285	99.27 333	98.16 223	98.61 230	98.86 283

v144192		97.92 255	97.60 273	98.87 240	98.83 363	98.65 213	99.55 150	99.34 275	96.20 355	99.32 196	99.40 303	94.36 261	99.26 336	96.37 351	95.03 369	98.70 310

dmvs_re		98.08 227	98.16 204	97.85 350	99.55 178	94.67 394	99.70 56	98.92 360	98.15 158	99.06 258	99.35 318	93.67 288	99.25 337	97.77 260	97.25 315	99.64 152

v2v482		98.06 229	97.77 251	98.92 225	98.90 351	98.82 200	99.57 129	99.36 263	96.65 320	99.19 231	99.35 318	94.20 266	99.25 337	97.72 267	94.97 370	98.69 314

v1240		97.69 298	97.32 314	98.79 255	98.85 360	98.43 240	99.48 199	99.36 263	96.11 364	99.27 210	99.36 315	93.76 286	99.24 339	94.46 386	95.23 364	98.70 310

WBMVS		97.74 289	97.50 282	98.46 293	99.24 280	97.43 292	99.21 315	99.42 233	97.45 252	98.96 275	99.41 299	88.83 376	99.23 340	98.94 117	96.02 340	98.71 305

v1144		97.98 246	97.69 262	98.85 246	98.87 356	98.66 212	99.54 155	99.35 270	96.27 350	99.23 221	99.35 318	94.67 245	99.23 340	96.73 335	95.16 366	98.68 319

v10		97.85 265	97.52 279	98.86 243	98.99 338	98.67 211	99.75 42	99.41 236	95.70 373	98.98 271	99.41 299	94.75 239	99.23 340	96.01 357	94.63 376	98.67 327

WR-MVS_H		98.13 221	97.87 241	98.90 231	99.02 332	98.84 196	99.70 56	99.59 67	97.27 270	98.40 343	99.19 350	95.53 199	99.23 340	98.34 207	93.78 392	98.61 358

miper_enhance_ethall		98.16 218	98.08 216	98.41 301	98.96 344	97.72 280	98.45 415	99.32 292	96.95 302	98.97 273	99.17 351	97.06 138	99.22 344	97.86 247	95.99 343	98.29 387

GG-mvs-BLEND				98.45 295	98.55 397	98.16 251	99.43 224	93.68 443		97.23 388	98.46 401	89.30 371	99.22 344	95.43 371	98.22 257	97.98 409

FC-MVSNet-test		98.75 172	98.62 173	99.15 198	99.08 322	99.45 106	99.86 11	99.60 61	98.23 148	98.70 315	99.82 95	96.80 146	99.22 344	99.07 103	96.38 332	98.79 287

UniMVSNet_NR-MVSNet		98.22 210	97.97 228	98.96 217	98.92 348	98.98 170	99.48 199	99.53 111	97.76 214	98.71 309	99.46 288	96.43 165	99.22 344	98.57 180	92.87 404	98.69 314

DU-MVS		98.08 227	97.79 246	98.96 217	98.87 356	98.98 170	99.41 236	99.45 216	97.87 198	98.71 309	99.50 272	94.82 230	99.22 344	98.57 180	92.87 404	98.68 319

cl____		98.01 242	97.84 244	98.55 281	99.25 278	97.97 263	98.71 398	99.34 275	96.47 339	98.59 333	99.54 257	95.65 195	99.21 349	97.21 306	95.77 349	98.46 375

WR-MVS		98.06 229	97.73 258	99.06 204	98.86 359	99.25 137	99.19 319	99.35 270	97.30 268	98.66 318	99.43 293	93.94 277	99.21 349	98.58 177	94.28 382	98.71 305

test_0402		96.64 350	96.24 352	97.85 350	98.85 360	96.43 347	99.44 219	99.26 311	93.52 403	96.98 396	99.52 265	88.52 384	99.20 351	92.58 411	97.50 299	97.93 412

SixPastTwentyTwo		97.50 317	97.33 313	98.03 332	98.65 387	96.23 355	99.77 34	98.68 398	97.14 281	97.90 371	99.93 10	90.45 357	99.18 352	97.00 320	96.43 331	98.67 327

cl22		97.85 265	97.64 269	98.48 287	99.09 319	97.87 272	98.60 408	99.33 282	97.11 287	98.87 289	99.22 346	92.38 324	99.17 353	98.21 217	95.99 343	98.42 378

tt0320		95.71 370	95.07 374	97.62 365	99.05 328	95.02 385	99.25 303	99.52 116	86.81 429	97.97 368	99.72 173	83.58 418	99.15 354	96.38 350	93.35 395	98.68 319

WB-MVSnew		97.65 306	97.65 266	97.63 364	98.78 369	97.62 286	99.13 329	98.33 408	97.36 263	99.07 253	98.94 378	95.64 196	99.15 354	92.95 405	98.68 228	96.12 432

IterMVS-SCA-FT		97.82 275	97.75 256	98.06 331	99.57 170	96.36 349	99.02 355	99.49 163	97.18 278	98.71 309	99.72 173	92.72 308	99.14 356	97.44 294	95.86 348	98.67 327

pmmvs5		97.52 314	97.30 316	98.16 324	98.57 396	96.73 333	99.27 292	98.90 367	96.14 362	98.37 345	99.53 261	91.54 344	99.14 356	97.51 286	95.87 347	98.63 347

v148		97.79 281	97.55 275	98.50 284	98.74 377	97.72 280	99.54 155	99.33 282	96.26 351	98.90 283	99.51 269	94.68 244	99.14 356	97.83 251	93.15 401	98.63 347

miper_ehance_all_eth		98.18 216	98.10 212	98.41 301	99.23 282	97.72 280	98.72 397	99.31 296	96.60 328	98.88 286	99.29 335	97.29 128	99.13 359	97.60 275	95.99 343	98.38 383

NR-MVSNet		97.97 249	97.61 272	99.02 209	98.87 356	99.26 135	99.47 207	99.42 233	97.63 229	97.08 394	99.50 272	95.07 219	99.13 359	97.86 247	93.59 393	98.68 319

IterMVS		97.83 272	97.77 251	98.02 334	99.58 166	96.27 353	99.02 355	99.48 175	97.22 276	98.71 309	99.70 180	92.75 305	99.13 359	97.46 292	96.00 342	98.67 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 386	94.90 377	91.84 411	97.24 421	80.01 441	98.52 412	99.48 175	89.01 425	91.99 428	99.67 204	85.67 405	99.13 359	95.44 370	97.03 322	96.39 429
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 234	97.96 229	98.33 308	99.26 274	97.38 294	98.56 411	99.31 296	96.65 320	98.88 286	99.52 265	96.58 156	99.12 363	97.39 297	95.53 359	98.47 372

pmmvs4		98.13 221	97.90 236	98.81 252	98.61 392	98.87 191	98.99 363	99.21 322	96.44 340	99.06 258	99.58 241	95.90 185	99.11 364	97.18 312	96.11 339	98.46 375

TransMVSNet (Re)		97.15 338	96.58 344	98.86 243	99.12 311	98.85 195	99.49 194	98.91 365	95.48 376	97.16 392	99.80 123	93.38 290	99.11 364	94.16 392	91.73 411	98.62 349

ambc				93.06 409	92.68 440	82.36 434	98.47 414	98.73 395		95.09 415	97.41 423	55.55 441	99.10 366	96.42 347	91.32 412	97.71 415

Baseline_NR-MVSNet		97.76 283	97.45 290	98.68 266	99.09 319	98.29 245	99.41 236	98.85 374	95.65 374	98.63 327	99.67 204	94.82 230	99.10 366	98.07 233	92.89 403	98.64 340

test_vis3_rt		87.04 401	85.81 404	90.73 415	93.99 439	81.96 436	99.76 37	90.23 450	92.81 411	81.35 438	91.56 438	40.06 447	99.07 368	94.27 389	88.23 425	91.15 438

CP-MVSNet		98.09 225	97.78 249	99.01 210	98.97 343	99.24 138	99.67 69	99.46 205	97.25 272	98.48 340	99.64 217	93.79 284	99.06 369	98.63 167	94.10 386	98.74 301

PS-CasMVS		97.93 252	97.59 274	98.95 219	98.99 338	99.06 162	99.68 66	99.52 116	97.13 282	98.31 348	99.68 198	92.44 323	99.05 370	98.51 188	94.08 387	98.75 297

K. test v3		97.10 340	96.79 340	98.01 335	98.72 380	96.33 350	99.87 8	97.05 427	97.59 233	96.16 406	99.80 123	88.71 378	99.04 371	96.69 338	96.55 329	98.65 338

new_pmnet		96.38 356	96.03 358	97.41 373	98.13 407	95.16 384	99.05 347	99.20 323	93.94 398	97.39 385	98.79 390	91.61 343	99.04 371	90.43 418	95.77 349	98.05 402

DIV-MVS_self_test		98.01 242	97.85 243	98.48 287	99.24 280	97.95 268	98.71 398	99.35 270	96.50 333	98.60 332	99.54 257	95.72 193	99.03 373	97.21 306	95.77 349	98.46 375

IterMVS-LS		98.46 190	98.42 189	98.58 275	99.59 164	98.00 261	99.37 255	99.43 231	96.94 304	99.07 253	99.59 237	97.87 110	99.03 373	98.32 210	95.62 355	98.71 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 306	97.68 263	97.55 369	98.62 390	94.97 387	98.84 385	99.30 301	96.83 311	98.19 357	99.34 322	97.01 141	99.02 375	95.00 380	96.01 341	98.64 340

Patchmtry		97.75 287	97.40 302	98.81 252	99.10 316	98.87 191	99.11 338	99.33 282	94.83 389	98.81 298	99.38 309	94.33 262	99.02 375	96.10 353	95.57 357	98.53 366

N_pmnet		94.95 380	95.83 363	92.31 410	98.47 400	79.33 442	99.12 332	92.81 448	93.87 399	97.68 378	99.13 356	93.87 281	99.01 377	91.38 415	96.19 337	98.59 362

CR-MVSNet		98.17 217	97.93 234	98.87 240	99.18 295	98.49 234	99.22 313	99.33 282	96.96 300	99.56 140	99.38 309	94.33 262	99.00 378	94.83 383	98.58 233	99.14 254

c3_l		98.12 223	98.04 221	98.38 305	99.30 262	97.69 284	98.81 388	99.33 282	96.67 318	98.83 295	99.34 322	97.11 134	98.99 379	97.58 277	95.34 362	98.48 370

test0.0.03 1		97.71 296	97.42 300	98.56 279	98.41 403	97.82 275	98.78 391	98.63 401	97.34 264	98.05 365	98.98 374	94.45 259	98.98 380	95.04 379	97.15 320	98.89 282

PatchT		97.03 342	96.44 348	98.79 255	98.99 338	98.34 244	99.16 323	99.07 341	92.13 414	99.52 149	97.31 427	94.54 254	98.98 380	88.54 425	98.73 226	99.03 270

GBi-Net		97.68 301	97.48 284	98.29 313	99.51 191	97.26 300	99.43 224	99.48 175	96.49 334	99.07 253	99.32 330	90.26 359	98.98 380	97.10 314	96.65 325	98.62 349

test1		97.68 301	97.48 284	98.29 313	99.51 191	97.26 300	99.43 224	99.48 175	96.49 334	99.07 253	99.32 330	90.26 359	98.98 380	97.10 314	96.65 325	98.62 349

FMVSNet3		98.03 237	97.76 255	98.84 247	99.39 238	98.98 170	99.40 244	99.38 254	96.67 318	99.07 253	99.28 337	92.93 300	98.98 380	97.10 314	96.65 325	98.56 365

FMVSNet2		97.72 293	97.36 305	98.80 254	99.51 191	98.84 196	99.45 213	99.42 233	96.49 334	98.86 293	99.29 335	90.26 359	98.98 380	96.44 346	96.56 328	98.58 363

FMVSNet1		96.84 346	96.36 350	98.29 313	99.32 260	97.26 300	99.43 224	99.48 175	95.11 381	98.55 335	99.32 330	83.95 416	98.98 380	95.81 360	96.26 336	98.62 349

ppachtmachnet_test		97.49 322	97.45 290	97.61 367	98.62 390	95.24 380	98.80 389	99.46 205	96.11 364	98.22 355	99.62 228	96.45 163	98.97 387	93.77 394	95.97 346	98.61 358

TranMVSNet+NR-MVSNet		97.93 252	97.66 265	98.76 258	98.78 369	98.62 218	99.65 82	99.49 163	97.76 214	98.49 339	99.60 235	94.23 265	98.97 387	98.00 237	92.90 402	98.70 310

MVStest1		96.08 363	95.48 368	97.89 347	98.93 346	96.70 334	99.56 136	99.35 270	92.69 412	91.81 429	99.46 288	89.90 365	98.96 389	95.00 380	92.61 407	98.00 407

tt0320-xc		95.31 376	94.59 380	97.45 372	98.92 348	94.73 391	99.20 318	99.31 296	86.74 430	97.23 388	99.72 173	81.14 429	98.95 390	97.08 317	91.98 410	98.67 327

test_method		91.10 396	91.36 398	90.31 416	95.85 429	73.72 449	94.89 437	99.25 313	68.39 440	95.82 409	99.02 368	80.50 430	98.95 390	93.64 397	94.89 374	98.25 390

ADS-MVSNet2		98.02 239	98.07 219	97.87 348	99.33 253	95.19 382	99.23 309	99.08 338	96.24 352	99.10 247	99.67 204	94.11 270	98.93 392	96.81 332	99.05 203	99.48 205

ET-MVSNet_ETH3D		96.49 353	95.64 367	99.05 206	99.53 182	98.82 200	98.84 385	97.51 425	97.63 229	84.77 434	99.21 349	92.09 328	98.91 393	98.98 112	92.21 409	99.41 226

miper_lstm_enhance		98.00 244	97.91 235	98.28 317	99.34 252	97.43 292	98.88 381	99.36 263	96.48 337	98.80 300	99.55 252	95.98 178	98.91 393	97.27 303	95.50 360	98.51 368

MonoMVSNet		98.38 199	98.47 187	98.12 329	98.59 395	96.19 357	99.72 52	98.79 383	97.89 196	99.44 165	99.52 265	96.13 173	98.90 395	98.64 165	97.54 294	99.28 243

PEN-MVS		97.76 283	97.44 295	98.72 261	98.77 374	98.54 225	99.78 32	99.51 133	97.06 292	98.29 351	99.64 217	92.63 314	98.89 396	98.09 226	93.16 400	98.72 303

testing3		97.28 332	96.76 341	98.82 249	99.37 243	98.07 258	99.45 213	99.36 263	97.56 238	97.89 372	98.95 377	83.70 417	98.82 397	96.03 355	98.56 236	99.58 173

testgi		97.65 306	97.50 282	98.13 328	99.36 246	96.45 346	99.42 231	99.48 175	97.76 214	97.87 373	99.45 290	91.09 351	98.81 398	94.53 385	98.52 239	99.13 256

testf1		90.42 399	90.68 400	89.65 419	97.78 411	73.97 447	99.13 329	98.81 379	89.62 422	91.80 430	98.93 379	62.23 439	98.80 399	86.61 433	91.17 413	96.19 430

APD_test2		90.42 399	90.68 400	89.65 419	97.78 411	73.97 447	99.13 329	98.81 379	89.62 422	91.80 430	98.93 379	62.23 439	98.80 399	86.61 433	91.17 413	96.19 430

MIMVSNet		97.73 291	97.45 290	98.57 276	99.45 221	97.50 290	99.02 355	98.98 352	96.11 364	99.41 174	99.14 355	90.28 358	98.74 401	95.74 362	98.93 211	99.47 211

LCM-MVSNet-Re		97.83 272	98.15 206	96.87 389	99.30 262	92.25 419	99.59 112	98.26 409	97.43 256	96.20 405	99.13 356	96.27 170	98.73 402	98.17 222	98.99 208	99.64 152

Syy-MVS		97.09 341	97.14 327	96.95 386	99.00 335	92.73 417	99.29 282	99.39 246	97.06 292	97.41 382	98.15 413	93.92 279	98.68 403	91.71 413	98.34 246	99.45 219

myMVS_eth3d		96.89 344	96.37 349	98.43 300	99.00 335	97.16 304	99.29 282	99.39 246	97.06 292	97.41 382	98.15 413	83.46 419	98.68 403	95.27 375	98.34 246	99.45 219

DTE-MVSNet		97.51 316	97.19 325	98.46 293	98.63 389	98.13 254	99.84 12	99.48 175	96.68 317	97.97 368	99.67 204	92.92 301	98.56 405	96.88 331	92.60 408	98.70 310

PC_three_1452									98.18 156	99.84 48	99.70 180	99.31 3	98.52 406	98.30 212	99.80 115	99.81 71

mvsany_test3		93.77 388	93.45 392	94.74 401	95.78 430	88.01 427	99.64 87	98.25 410	98.28 137	94.31 418	97.97 420	68.89 435	98.51 407	97.50 287	90.37 418	97.71 415

UnsupCasMVSNet_bld		93.53 389	92.51 395	96.58 394	97.38 417	93.82 405	98.24 424	99.48 175	91.10 419	93.10 423	96.66 429	74.89 433	98.37 408	94.03 393	87.71 426	97.56 420

Anonymous20240521		96.20 359	95.89 362	97.13 380	97.72 414	94.96 388	99.79 31	99.29 305	93.01 408	97.20 391	99.03 366	89.69 368	98.36 409	91.16 416	96.13 338	98.07 400

test_f		91.90 395	91.26 399	93.84 404	95.52 434	85.92 429	99.69 60	98.53 406	95.31 378	93.87 420	96.37 431	55.33 442	98.27 410	95.70 363	90.98 416	97.32 423

MDA-MVSNet_test_wron		95.45 372	94.60 379	98.01 335	98.16 406	97.21 303	99.11 338	99.24 316	93.49 404	80.73 440	98.98 374	93.02 298	98.18 411	94.22 391	94.45 379	98.64 340

UnsupCasMVSNet_eth		96.44 354	96.12 355	97.40 374	98.65 387	95.65 366	99.36 260	99.51 133	97.13 282	96.04 408	98.99 372	88.40 385	98.17 412	96.71 336	90.27 419	98.40 381

KD-MVS_2432*1600		94.62 381	93.72 389	97.31 375	97.19 423	95.82 363	98.34 419	99.20 323	95.00 385	97.57 379	98.35 406	87.95 390	98.10 413	92.87 407	77.00 438	98.01 404

miper_refine_blended		94.62 381	93.72 389	97.31 375	97.19 423	95.82 363	98.34 419	99.20 323	95.00 385	97.57 379	98.35 406	87.95 390	98.10 413	92.87 407	77.00 438	98.01 404

YYNet1		95.36 374	94.51 382	97.92 344	97.89 409	97.10 307	99.10 340	99.23 317	93.26 407	80.77 439	99.04 365	92.81 304	98.02 415	94.30 387	94.18 384	98.64 340

EU-MVSNet		97.98 246	98.03 222	97.81 356	98.72 380	96.65 339	99.66 76	99.66 28	98.09 170	98.35 346	99.82 95	95.25 213	98.01 416	97.41 296	95.30 363	98.78 289

Gipuma		90.99 397	90.15 402	93.51 405	98.73 378	90.12 425	93.98 438	99.45 216	79.32 436	92.28 426	94.91 433	69.61 434	97.98 417	87.42 429	95.67 353	92.45 436
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 375	94.73 378	97.15 378	95.53 433	95.94 361	99.35 265	99.10 335	95.13 379	93.55 421	97.54 422	88.15 389	97.91 418	94.58 384	89.69 422	97.61 418

PM-MVS		92.96 392	92.23 396	95.14 400	95.61 431	89.98 426	99.37 255	98.21 413	94.80 390	95.04 416	97.69 421	65.06 436	97.90 419	94.30 387	89.98 421	97.54 421

MDA-MVSNet-bldmvs		94.96 379	93.98 386	97.92 344	98.24 405	97.27 298	99.15 326	99.33 282	93.80 400	80.09 441	99.03 366	88.31 386	97.86 420	93.49 399	94.36 381	98.62 349

Patchmatch-RL test		95.84 366	95.81 364	95.95 398	95.61 431	90.57 424	98.24 424	98.39 407	95.10 383	95.20 413	98.67 394	94.78 234	97.77 421	96.28 352	90.02 420	99.51 197

Anonymous20231206		96.22 357	96.03 358	96.79 391	97.31 420	94.14 403	99.63 93	99.08 338	96.17 358	97.04 395	99.06 363	93.94 277	97.76 422	86.96 431	95.06 368	98.47 372

SD-MVS		99.41 54	99.52 12	99.05 206	99.74 90	99.68 56	99.46 210	99.52 116	99.11 39	99.88 36	99.91 23	99.43 1	97.70 423	98.72 154	99.93 29	99.77 92
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		97.25 334	97.35 307	96.95 386	97.84 410	93.61 411	99.57 129	96.63 433	96.13 363	98.87 289	98.61 397	94.59 249	97.70 423	95.08 378	98.86 217	99.55 180

dongtai		93.26 390	92.93 394	94.25 402	99.39 238	85.68 430	97.68 433	93.27 444	92.87 410	96.85 399	99.39 307	82.33 424	97.48 425	76.78 438	97.80 279	99.58 173

pmmvs3		94.09 387	93.25 393	96.60 393	94.76 438	94.49 397	98.92 377	98.18 415	89.66 421	96.48 402	98.06 419	86.28 402	97.33 426	89.68 421	87.20 427	97.97 410

KD-MVS_self_test		95.00 378	94.34 383	96.96 385	97.07 425	95.39 377	99.56 136	99.44 225	95.11 381	97.13 393	97.32 426	91.86 333	97.27 427	90.35 419	81.23 435	98.23 392

FMVSNet5		96.43 355	96.19 354	97.15 378	99.11 313	95.89 362	99.32 272	99.52 116	94.47 396	98.34 347	99.07 361	87.54 395	97.07 428	92.61 410	95.72 352	98.47 372

new-patchmatchnet		94.48 384	94.08 385	95.67 399	95.08 436	92.41 418	99.18 321	99.28 307	94.55 395	93.49 422	97.37 425	87.86 393	97.01 429	91.57 414	88.36 424	97.61 418

LCM-MVSNet		86.80 403	85.22 407	91.53 413	87.81 445	80.96 439	98.23 426	98.99 351	71.05 438	90.13 433	96.51 430	48.45 446	96.88 430	90.51 417	85.30 429	96.76 425

CL-MVSNet_self_test		94.49 383	93.97 387	96.08 397	96.16 428	93.67 410	98.33 421	99.38 254	95.13 379	97.33 386	98.15 413	92.69 312	96.57 431	88.67 424	79.87 436	97.99 408

MIMVSNet1		95.51 371	95.04 376	96.92 388	97.38 417	95.60 367	99.52 165	99.50 153	93.65 402	96.97 397	99.17 351	85.28 410	96.56 432	88.36 426	95.55 358	98.60 361

test20.03		96.12 361	95.96 360	96.63 392	97.44 416	95.45 374	99.51 174	99.38 254	96.55 331	96.16 406	99.25 343	93.76 286	96.17 433	87.35 430	94.22 383	98.27 388

tmp_tt		82.80 405	81.52 408	86.66 421	66.61 451	68.44 450	92.79 440	97.92 417	68.96 439	80.04 442	99.85 70	85.77 404	96.15 434	97.86 247	43.89 444	95.39 434

test_fmvs3		92.10 394	91.77 397	93.08 408	96.19 427	86.25 428	99.82 16	98.62 402	96.65 320	95.19 414	96.90 428	55.05 443	95.93 435	96.63 343	90.92 417	97.06 424

kuosan		90.92 398	90.11 403	93.34 406	98.78 369	85.59 431	98.15 428	93.16 446	89.37 424	92.07 427	98.38 405	81.48 427	95.19 436	62.54 445	97.04 321	99.25 248

dmvs_testset		95.02 377	96.12 355	91.72 412	99.10 316	80.43 440	99.58 122	97.87 419	97.47 248	95.22 412	98.82 386	93.99 275	95.18 437	88.09 427	94.91 373	99.56 179

PMMVS2		86.87 402	85.37 406	91.35 414	90.21 443	83.80 433	98.89 380	97.45 426	83.13 435	91.67 432	95.03 432	48.49 445	94.70 438	85.86 435	77.62 437	95.54 433

PMVS	70.75 22	75.98 411	74.97 412	79.01 427	70.98 450	55.18 452	93.37 439	98.21 413	65.08 444	61.78 445	93.83 435	21.74 452	92.53 439	78.59 437	91.12 415	89.34 440
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 404	85.65 405	82.75 425	86.77 446	63.39 451	98.35 418	98.92 360	74.11 437	83.39 436	98.98 374	50.85 444	92.40 440	84.54 436	94.97 370	92.46 435

WB-MVS		93.10 391	94.10 384	90.12 417	95.51 435	81.88 437	99.73 50	99.27 310	95.05 384	93.09 424	98.91 383	94.70 243	91.89 441	76.62 439	94.02 389	96.58 427

SSC-MVS		92.73 393	93.73 388	89.72 418	95.02 437	81.38 438	99.76 37	99.23 317	94.87 388	92.80 425	98.93 379	94.71 242	91.37 442	74.49 441	93.80 391	96.42 428

MVE	76.82 21	76.91 410	74.31 414	84.70 422	85.38 448	76.05 446	96.88 436	93.17 445	67.39 441	71.28 443	89.01 442	21.66 453	87.69 443	71.74 442	72.29 440	90.35 439
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 407	79.88 409	82.81 424	90.75 442	76.38 445	97.69 432	95.76 437	66.44 442	83.52 435	92.25 437	62.54 438	87.16 444	68.53 443	61.40 441	84.89 442

EMVS		80.02 408	79.22 410	82.43 426	91.19 441	76.40 444	97.55 435	92.49 449	66.36 443	83.01 437	91.27 439	64.63 437	85.79 445	65.82 444	60.65 442	85.08 441

ANet_high		77.30 409	74.86 413	84.62 423	75.88 449	77.61 443	97.63 434	93.15 447	88.81 426	64.27 444	89.29 441	36.51 448	83.93 446	75.89 440	52.31 443	92.33 437

wuyk23d		40.18 412	41.29 417	36.84 428	86.18 447	49.12 453	79.73 441	22.81 453	27.64 445	25.46 448	28.45 448	21.98 451	48.89 447	55.80 446	23.56 447	12.51 445

test123		39.01 414	42.50 416	28.53 429	39.17 452	20.91 454	98.75 394	19.17 454	19.83 447	38.57 446	66.67 444	33.16 449	15.42 448	37.50 448	29.66 446	49.26 443

testmvs		39.17 413	43.78 415	25.37 430	36.04 453	16.84 455	98.36 417	26.56 452	20.06 446	38.51 447	67.32 443	29.64 450	15.30 449	37.59 447	39.90 445	43.98 444

mmdepth		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

monomultidepth		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

test_blank		0.13 418	0.17 421	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	1.57 449	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

uanet_test		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

DCPMVS		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

cdsmvs_eth3d_5k		24.64 415	32.85 418	0.00 431	0.00 454	0.00 456	0.00 442	99.51 133	0.00 449	0.00 450	99.56 249	96.58 156	0.00 450	0.00 449	0.00 448	0.00 446

pcd_1.5k_mvsjas		8.27 417	11.03 420	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	99.01 18	0.00 450	0.00 449	0.00 448	0.00 446

sosnet-low-res		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

sosnet		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

uncertanet		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

Regformer		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

ab-mvs-re		8.30 416	11.06 419	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	99.58 241	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

uanet		0.02 419	0.03 422	0.00 431	0.00 454	0.00 456	0.00 442	0.00 455	0.00 449	0.00 450	0.27 450	0.00 454	0.00 450	0.00 449	0.00 448	0.00 446

WAC-MVS						97.16 304								95.47 369

FOURS1					99.91 1	99.93 1	99.87 8	99.56 81	99.10 40	99.81 58

test_one_0601					99.81 48	99.88 8		99.49 163	98.97 64	99.65 114	99.81 109	99.09 14

eth-test2					0.00 454

eth-test					0.00 454

RE-MVS-def			99.34 45		99.76 72	99.82 25	99.63 93	99.52 116	98.38 125	99.76 79	99.82 95	98.75 58		98.61 171	99.81 110	99.77 92

IU-MVS					99.84 32	99.88 8		99.32 292	98.30 136	99.84 48				98.86 134	99.85 86	99.89 25

save fliter					99.76 72	99.59 80	99.14 328	99.40 243	99.00 56

test0726					99.85 26	99.89 4	99.62 98	99.50 153	99.10 40	99.86 45	99.82 95	98.94 32

GSMVS																99.52 189

test_part2					99.81 48	99.83 19				99.77 73

sam_mvs1												94.86 229				99.52 189

sam_mvs												94.72 241

MTGPA								99.47 196

MTMP							99.54 155	98.88 370

test9_res														97.49 288	99.72 138	99.75 98

agg_prior2														97.21 306	99.73 137	99.75 98

test_prior4						99.56 86	98.99 363

test_prior2							98.96 370		98.34 131	99.01 264	99.52 265	98.68 67		97.96 239	99.74 135

新几何2							99.01 360

旧先验1					99.74 90	99.59 80		99.54 98			99.69 191	98.47 83			99.68 146	99.73 110

原ACMM2							98.95 373

test222					99.75 82	99.49 100	98.91 379	99.49 163	96.42 342	99.34 194	99.65 211	98.28 96			99.69 143	99.72 118

segment_acmp												98.96 25

testdata1							98.85 384		98.32 134

plane_prior7					99.29 266	97.03 317

plane_prior6					99.27 271	96.98 321						92.71 310

plane_prior4											99.61 232

plane_prior3						97.00 319			98.69 96	99.11 244

plane_prior2							99.39 248		98.97 64

plane_prior1					99.26 274

plane_prior						96.97 322	99.21 315		98.45 118						97.60 288

n2								0.00 455

nn								0.00 455

door-mid								98.05 416

test11								99.35 270

door								97.92 417

HQP5-MVS						96.83 329

HQP-NCC					99.19 292		98.98 366		98.24 145	98.66 318

ACMP_Plane					99.19 292		98.98 366		98.24 145	98.66 318

BP-MVS														97.19 310

HQP3-MVS								99.39 246							97.58 290

HQP2-MVS												92.47 319

NP-MVS					99.23 282	96.92 325					99.40 303

MDTV_nov1_ep13_2view						95.18 383	99.35 265		96.84 309	99.58 136		95.19 215		97.82 252		99.46 216

ACMMP++_ref															97.19 318

ACMMP++															97.43 308

Test By Simon												98.75 58

High-resolution multi-view benchmark