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_cas_vis1_n_1920		99.16 104	99.01 121	99.61 103	99.81 52	98.86 202	99.65 84	99.64 38	99.39 20	99.97 23	99.94 6	93.20 314	99.98 18	99.55 48	99.91 44	99.99 1

fmvsm_s_conf0.1_n_a		99.26 87	99.06 103	99.85 38	99.52 205	99.62 77	99.54 160	99.62 47	98.69 101	99.99 2	99.96 1	94.47 275	99.94 87	99.88 24	99.92 37	99.98 2

test_vis1_n_1920		98.63 199	98.40 207	99.31 180	99.86 22	97.94 282	99.67 71	99.62 47	99.43 15	99.99 2	99.91 24	87.29 413	100.00 1	99.92 22	99.92 37	99.98 2

fmvsm_s_conf0.1_n		99.29 80	99.10 94	99.86 30	99.70 116	99.65 69	99.53 169	99.62 47	98.74 95	99.99 2	99.95 3	94.53 273	99.94 87	99.89 23	99.96 15	99.97 4

test_fmvsmconf0.1_n		99.55 20	99.45 27	99.86 30	99.44 239	99.65 69	99.50 188	99.61 56	99.45 11	99.87 44	99.92 17	97.31 127	99.97 27	99.95 14	99.99 1	99.97 4

test_vis1_n		97.92 271	97.44 312	99.34 172	99.53 199	98.08 269	99.74 47	99.49 171	99.15 32	100.00 1	99.94 6	79.51 448	99.98 18	99.88 24	99.76 134	99.97 4

fmvsm_s_conf0.5_n_9		99.41 56	99.28 66	99.81 55	99.84 35	99.52 99	99.48 208	99.62 47	99.46 7	99.99 2	99.92 17	95.24 229	99.96 39	99.97 2	99.97 8	99.96 7

fmvsm_s_conf0.5_n_8		99.54 21	99.42 29	99.89 9	99.83 44	99.74 49	99.51 179	99.62 47	99.46 7	99.99 2	99.90 31	96.60 165	99.98 18	99.95 14	99.95 21	99.96 7

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

test_fmvs1_n		98.41 211	98.14 223	99.21 201	99.82 48	97.71 295	99.74 47	99.49 171	99.32 25	99.99 2	99.95 3	85.32 426	99.97 27	99.82 27	99.84 96	99.96 7

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

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

fmvsm_s_conf0.5_n_3		99.37 64	99.20 82	99.87 19	99.75 86	99.70 55	99.48 208	99.66 28	99.45 11	99.99 2	99.93 10	94.64 265	99.97 27	99.94 19	99.97 8	99.95 11

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

fmvsm_s_conf0.5_n		99.51 26	99.40 35	99.85 38	99.84 35	99.65 69	99.51 179	99.67 23	99.13 35	99.98 11	99.92 17	96.60 165	99.96 39	99.95 14	99.96 15	99.95 11

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

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

MM		99.40 60	99.28 66	99.74 74	99.67 128	99.31 129	99.52 170	98.87 389	99.55 1	99.74 89	99.80 133	96.47 172	99.98 18	99.97 2	99.97 8	99.94 16

test_fmvsmconf0.01_n		99.22 95	99.03 110	99.79 62	98.42 419	99.48 105	99.55 155	99.51 139	99.39 20	99.78 75	99.93 10	94.80 248	99.95 74	99.93 21	99.95 21	99.94 16

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 68	99.38 257	99.37 117	99.58 126	99.62 47	99.41 19	99.87 44	99.92 17	98.81 47	100.00 1	99.97 2	99.93 31	99.94 16

fmvsm_s_conf0.5_n_2		99.32 75	99.13 90	99.89 9	99.80 58	99.77 43	99.44 230	99.58 74	99.47 4	99.99 2	99.93 10	94.04 290	99.96 39	99.96 12	99.93 31	99.93 21

fmvsm_s_conf0.5_n_6		99.54 21	99.44 28	99.85 38	99.51 208	99.67 62	99.50 188	99.64 38	99.43 15	99.98 11	99.78 156	97.26 132	99.95 74	99.95 14	99.93 31	99.92 22

fmvsm_s_conf0.5_n_5		99.37 64	99.21 80	99.86 30	99.80 58	99.68 58	99.42 242	99.61 56	99.37 22	99.97 23	99.86 65	94.96 237	99.99 4	99.97 2	99.93 31	99.92 22

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

test_fmvs1		98.88 160	98.79 164	99.16 206	99.69 121	97.61 299	99.55 155	99.49 171	99.32 25	99.98 11	99.91 24	91.41 362	99.96 39	99.82 27	99.92 37	99.90 24

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 72	99.89 5	99.75 42	99.56 84	99.02 56	99.88 38	99.85 72	99.18 10	99.96 39	99.22 94	99.92 37	99.90 24
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
patch_mono-2		99.26 87	99.62 5	98.16 340	99.81 52	94.59 412	99.52 170	99.64 38	99.33 24	99.73 91	99.90 31	99.00 22	99.99 4	99.69 33	99.98 4	99.89 27

MSC_two_6792asdad				99.87 19	99.51 208	99.76 44		99.33 299					99.96 39	98.87 141	99.84 96	99.89 27

No_MVS				99.87 19	99.51 208	99.76 44		99.33 299					99.96 39	98.87 141	99.84 96	99.89 27

IU-MVS					99.84 35	99.88 9		99.32 309	98.30 142	99.84 51				98.86 146	99.85 88	99.89 27

UA-Net		99.42 52	99.29 63	99.80 59	99.62 159	99.55 90	99.50 188	99.70 15	98.79 89	99.77 79	99.96 1	97.45 121	99.96 39	98.92 134	99.90 55	99.89 27

CHOSEN 1792x2688		99.19 96	99.10 94	99.45 153	99.89 8	98.52 241	99.39 259	99.94 1	98.73 96	99.11 259	99.89 37	95.50 215	99.94 87	99.50 55	99.97 8	99.89 27

test_241102_TWO								99.48 183	99.08 50	99.88 38	99.81 116	98.94 32	99.96 39	98.91 135	99.84 96	99.88 33

test_0728_THIRD									98.99 63	99.81 63	99.80 133	99.09 14	99.96 39	98.85 148	99.90 55	99.88 33

test_0728_SECOND				99.91 4	99.84 35	99.89 5	99.57 134	99.51 139					99.96 39	98.93 132	99.86 81	99.88 33

DPE-MVS		99.46 39	99.32 51	99.91 4	99.78 64	99.88 9	99.36 271	99.51 139	98.73 96	99.88 38	99.84 87	98.72 64	99.96 39	98.16 235	99.87 73	99.88 33
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		99.42 52	99.27 70	99.88 13	99.89 8	99.80 33	99.67 71	99.50 159	98.70 100	99.77 79	99.49 291	98.21 99	99.95 74	98.46 206	99.77 131	99.88 33
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
dcpmvs_2		99.23 93	99.58 7	98.16 340	99.83 44	94.68 409	99.76 37	99.52 120	99.07 52	99.98 11	99.88 47	98.56 77	99.93 105	99.67 35	99.98 4	99.87 38

DP-MVS		99.16 104	98.95 135	99.78 65	99.77 72	99.53 95	99.41 247	99.50 159	97.03 313	99.04 276	99.88 47	97.39 122	99.92 117	98.66 175	99.90 55	99.87 38

reproduce_model		99.63 7	99.54 11	99.90 6	99.78 64	99.88 9	99.56 141	99.55 92	99.15 32	99.90 32	99.90 31	99.00 22	99.97 27	99.11 107	99.91 44	99.86 40

EI-MVSNet-UG-set		99.58 14	99.57 8	99.64 95	99.78 64	99.14 154	99.60 109	99.45 227	99.01 58	99.90 32	99.83 92	98.98 24	99.93 105	99.59 43	99.95 21	99.86 40

Test_1112_low_res		98.89 159	98.66 178	99.57 114	99.69 121	98.95 185	99.03 369	99.47 205	96.98 315	99.15 253	99.23 362	96.77 159	99.89 157	98.83 154	98.78 240	99.86 40

HyFIR lowres test		99.11 127	98.92 138	99.65 89	99.90 4	99.37 117	99.02 372	99.91 3	97.67 243	99.59 146	99.75 174	95.90 198	99.73 249	99.53 51	99.02 218	99.86 40

fmvsm_s_conf0.5_n_7		99.34 71	99.29 63	99.48 145	99.70 116	98.63 227	99.42 242	99.63 42	99.46 7	99.98 11	99.88 47	95.59 212	99.96 39	99.97 2	99.98 4	99.85 44

reproduce-ours		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 170	99.54 101	99.13 35	99.89 35	99.89 37	98.96 25	99.96 39	99.04 115	99.90 55	99.85 44

our_new_method		99.61 8	99.52 12	99.90 6	99.76 76	99.88 9	99.52 170	99.54 101	99.13 35	99.89 35	99.89 37	98.96 25	99.96 39	99.04 115	99.90 55	99.85 44

EI-MVSNet-Vis-set		99.58 14	99.56 10	99.64 95	99.78 64	99.15 153	99.61 108	99.45 227	99.01 58	99.89 35	99.82 101	99.01 18	99.92 117	99.56 47	99.95 21	99.85 44

CVMVSNet		98.57 201	98.67 175	98.30 328	99.35 264	95.59 384	99.50 188	99.55 92	98.60 109	99.39 193	99.83 92	94.48 274	99.45 310	98.75 162	98.56 253	99.85 44

HPM-MVS_fast		99.51 26	99.40 35	99.85 38	99.91 1	99.79 36	99.76 37	99.56 84	97.72 235	99.76 85	99.75 174	99.13 12	99.92 117	99.07 113	99.92 37	99.85 44

MG-MVS		99.13 114	99.02 116	99.45 153	99.57 183	98.63 227	99.07 358	99.34 291	98.99 63	99.61 140	99.82 101	97.98 110	99.87 169	97.00 336	99.80 119	99.85 44

MVS_0304		99.15 108	98.96 131	99.73 77	98.92 365	99.37 117	99.37 266	96.92 445	99.51 2	99.66 115	99.78 156	96.69 162	99.97 27	99.84 26	99.97 8	99.84 51

ACMMP_NAP		99.47 37	99.34 47	99.88 13	99.87 17	99.86 17	99.47 217	99.48 183	98.05 190	99.76 85	99.86 65	98.82 46	99.93 105	98.82 158	99.91 44	99.84 51

HFP-MVS		99.49 30	99.37 41	99.86 30	99.87 17	99.80 33	99.66 78	99.67 23	98.15 165	99.68 104	99.69 207	99.06 16	99.96 39	98.69 171	99.87 73	99.84 51

region2R		99.48 34	99.35 45	99.87 19	99.88 13	99.80 33	99.65 84	99.66 28	98.13 172	99.66 115	99.68 214	98.96 25	99.96 39	98.62 180	99.87 73	99.84 51

XVS		99.53 24	99.42 29	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 197	99.74 179	98.81 47	99.94 87	98.79 159	99.86 81	99.84 51

X-MVStestdata		96.55 368	95.45 387	99.87 19	99.85 28	99.83 20	99.69 62	99.68 20	98.98 66	99.37 197	64.01 464	98.81 47	99.94 87	98.79 159	99.86 81	99.84 51

ACMMPR		99.49 30	99.36 43	99.86 30	99.87 17	99.79 36	99.66 78	99.67 23	98.15 165	99.67 110	99.69 207	98.95 30	99.96 39	98.69 171	99.87 73	99.84 51

HPM-MVS		99.42 52	99.28 66	99.83 51	99.90 4	99.72 51	99.81 20	99.54 101	97.59 250	99.68 104	99.63 239	98.91 37	99.94 87	98.58 189	99.91 44	99.84 51
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
SteuartSystems-ACMMP		99.54 21	99.42 29	99.87 19	99.82 48	99.81 31	99.59 116	99.51 139	98.62 106	99.79 70	99.83 92	99.28 4	99.97 27	98.48 202	99.90 55	99.84 51
Skip Steuart: Steuart Systems R&D Blog.
1112_ss		98.98 152	98.77 165	99.59 107	99.68 126	99.02 169	99.25 316	99.48 183	97.23 292	99.13 255	99.58 257	96.93 148	99.90 142	98.87 141	98.78 240	99.84 51

lecture		99.60 12	99.50 17	99.89 9	99.89 8	99.90 2	99.75 42	99.59 69	99.06 55	99.88 38	99.85 72	98.41 90	99.96 39	99.28 87	99.84 96	99.83 61

MP-MVS-pluss		99.37 64	99.20 82	99.88 13	99.90 4	99.87 16	99.30 290	99.52 120	97.18 295	99.60 143	99.79 149	98.79 50	99.95 74	98.83 154	99.91 44	99.83 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MTAPA		99.52 25	99.39 37	99.89 9	99.90 4	99.86 17	99.66 78	99.47 205	98.79 89	99.68 104	99.81 116	98.43 86	99.97 27	98.88 138	99.90 55	99.83 61

PGM-MVS		99.45 43	99.31 57	99.86 30	99.87 17	99.78 42	99.58 126	99.65 35	97.84 221	99.71 98	99.80 133	99.12 13	99.97 27	98.33 220	99.87 73	99.83 61

mPP-MVS		99.44 47	99.30 59	99.86 30	99.88 13	99.79 36	99.69 62	99.48 183	98.12 174	99.50 163	99.75 174	98.78 51	99.97 27	98.57 192	99.89 66	99.83 61

CP-MVS		99.45 43	99.32 51	99.85 38	99.83 44	99.75 46	99.69 62	99.52 120	98.07 184	99.53 158	99.63 239	98.93 36	99.97 27	98.74 163	99.91 44	99.83 61

mvsany_test1		99.50 28	99.46 26	99.62 102	99.61 168	99.09 159	98.94 392	99.48 183	99.10 42	99.96 25	99.91 24	98.85 42	99.96 39	99.72 30	99.58 163	99.82 67

test1111		98.04 251	98.11 227	97.83 369	99.74 94	93.82 421	99.58 126	95.40 455	99.12 40	99.65 124	99.93 10	90.73 372	99.84 187	99.43 65	99.38 177	99.82 67

ZNCC-MVS		99.47 37	99.33 49	99.87 19	99.87 17	99.81 31	99.64 91	99.67 23	98.08 183	99.55 155	99.64 233	98.91 37	99.96 39	98.72 166	99.90 55	99.82 67

TSAR-MVS + MP.		99.58 14	99.50 17	99.81 55	99.91 1	99.66 65	99.63 97	99.39 262	98.91 76	99.78 75	99.85 72	99.36 2	99.94 87	98.84 151	99.88 70	99.82 67
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
MP-MVS		99.33 73	99.15 88	99.87 19	99.88 13	99.82 26	99.66 78	99.46 216	98.09 179	99.48 167	99.74 179	98.29 96	99.96 39	97.93 257	99.87 73	99.82 67
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
MCST-MVS		99.43 50	99.30 59	99.82 52	99.79 62	99.74 49	99.29 295	99.40 259	98.79 89	99.52 160	99.62 244	98.91 37	99.90 142	98.64 177	99.75 136	99.82 67

DeepC-MVS_fast	98.69 1	99.49 30	99.39 37	99.77 68	99.63 153	99.59 82	99.36 271	99.46 216	99.07 52	99.79 70	99.82 101	98.85 42	99.92 117	98.68 173	99.87 73	99.82 67
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
DVP-MVS++		99.59 13	99.50 17	99.88 13	99.51 208	99.88 9	99.87 8	99.51 139	98.99 63	99.88 38	99.81 116	99.27 5	99.96 39	98.85 148	99.80 119	99.81 74

PC_three_1452									98.18 163	99.84 51	99.70 196	99.31 3	98.52 423	98.30 224	99.80 119	99.81 74

DVP-MVS		99.57 18	99.47 22	99.88 13	99.85 28	99.89 5	99.57 134	99.37 278	99.10 42	99.81 63	99.80 133	98.94 32	99.96 39	98.93 132	99.86 81	99.81 74
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
GST-MVS		99.40 60	99.24 75	99.85 38	99.86 22	99.79 36	99.60 109	99.67 23	97.97 205	99.63 132	99.68 214	98.52 80	99.95 74	98.38 213	99.86 81	99.81 74

SMA-MVS		99.44 47	99.30 59	99.85 38	99.73 101	99.83 20	99.56 141	99.47 205	97.45 269	99.78 75	99.82 101	99.18 10	99.91 129	98.79 159	99.89 66	99.81 74
Yufeng Yin; Xiaoyan Liu; Zichao Zhang: SMA-MVS: Segmentation-Guided Multi-Scale Anchor Deformation Patch Multi-View Stereo. IEEE Transactions on Circuits and Systems for Video Technology
CPTT-MVS		99.11 127	98.90 143	99.74 74	99.80 58	99.46 108	99.59 116	99.49 171	97.03 313	99.63 132	99.69 207	97.27 130	99.96 39	97.82 268	99.84 96	99.81 74

ACMMP		99.45 43	99.32 51	99.82 52	99.89 8	99.67 62	99.62 102	99.69 18	98.12 174	99.63 132	99.84 87	98.73 63	99.96 39	98.55 198	99.83 107	99.81 74
Qingshan Xu, Weihang Kong, Wenbing Tao, Marc Pollefeys: Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo. IEEE Transactions on Pattern Analysis and Machine Intelligence
DeepPCF-MVS	98.18 3	98.81 179	99.37 41	97.12 398	99.60 174	91.75 438	98.61 423	99.44 236	99.35 23	99.83 59	99.85 72	98.70 66	99.81 214	99.02 119	99.91 44	99.81 74

3Dnovator+	97.12 13	99.18 99	98.97 127	99.82 52	99.17 320	99.68 58	99.81 20	99.51 139	99.20 29	98.72 324	99.89 37	95.68 209	99.97 27	98.86 146	99.86 81	99.81 74

test2506		96.81 364	96.65 360	97.29 394	99.74 94	92.21 437	99.60 109	85.06 468	99.13 35	99.77 79	99.93 10	87.82 411	99.85 178	99.38 70	99.38 177	99.80 83

ECVR-MVS		98.04 251	98.05 236	98.00 353	99.74 94	94.37 416	99.59 116	94.98 456	99.13 35	99.66 115	99.93 10	90.67 373	99.84 187	99.40 67	99.38 177	99.80 83

APD-MVS		99.27 84	99.08 100	99.84 50	99.75 86	99.79 36	99.50 188	99.50 159	97.16 297	99.77 79	99.82 101	98.78 51	99.94 87	97.56 298	99.86 81	99.80 83
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
NCCC		99.34 71	99.19 84	99.79 62	99.61 168	99.65 69	99.30 290	99.48 183	98.86 78	99.21 240	99.63 239	98.72 64	99.90 142	98.25 227	99.63 158	99.80 83

SED-MVS		99.61 8	99.52 12	99.88 13	99.84 35	99.90 2	99.60 109	99.48 183	99.08 50	99.91 29	99.81 116	99.20 7	99.96 39	98.91 135	99.85 88	99.79 87

OPU-MVS				99.64 95	99.56 187	99.72 51	99.60 109				99.70 196	99.27 5	99.42 321	98.24 228	99.80 119	99.79 87

SR-MVS		99.43 50	99.29 63	99.86 30	99.75 86	99.83 20	99.59 116	99.62 47	98.21 158	99.73 91	99.79 149	98.68 67	99.96 39	98.44 208	99.77 131	99.79 87

HPM-MVS++		99.39 62	99.23 78	99.87 19	99.75 86	99.84 19	99.43 235	99.51 139	98.68 103	99.27 225	99.53 277	98.64 72	99.96 39	98.44 208	99.80 119	99.79 87

PVSNet_Blended_VisFu		99.36 68	99.28 66	99.61 103	99.86 22	99.07 164	99.47 217	99.93 2	97.66 244	99.71 98	99.86 65	97.73 116	99.96 39	99.47 62	99.82 111	99.79 87

3Dnovator	97.25 9	99.24 92	99.05 105	99.81 55	99.12 328	99.66 65	99.84 12	99.74 10	99.09 49	98.92 296	99.90 31	95.94 195	99.98 18	98.95 128	99.92 37	99.79 87

APD-MVS_3200maxsize		99.48 34	99.35 45	99.85 38	99.76 76	99.83 20	99.63 97	99.54 101	98.36 135	99.79 70	99.82 101	98.86 41	99.95 74	98.62 180	99.81 114	99.78 93

CDPH-MVS		99.13 114	98.91 141	99.80 59	99.75 86	99.71 53	99.15 342	99.41 252	96.60 345	99.60 143	99.55 268	98.83 45	99.90 142	97.48 305	99.83 107	99.78 93

SR-MVS-dyc-post		99.45 43	99.31 57	99.85 38	99.76 76	99.82 26	99.63 97	99.52 120	98.38 131	99.76 85	99.82 101	98.53 79	99.95 74	98.61 183	99.81 114	99.77 95

RE-MVS-def			99.34 47		99.76 76	99.82 26	99.63 97	99.52 120	98.38 131	99.76 85	99.82 101	98.75 58		98.61 183	99.81 114	99.77 95

SD-MVS		99.41 56	99.52 12	99.05 218	99.74 94	99.68 58	99.46 221	99.52 120	99.11 41	99.88 38	99.91 24	99.43 1	97.70 440	98.72 166	99.93 31	99.77 95
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
CNVR-MVS		99.42 52	99.30 59	99.78 65	99.62 159	99.71 53	99.26 314	99.52 120	98.82 83	99.39 193	99.71 192	98.96 25	99.85 178	98.59 188	99.80 119	99.77 95

MVS_111021_HR		99.41 56	99.32 51	99.66 85	99.72 105	99.47 107	98.95 390	99.85 6	98.82 83	99.54 156	99.73 185	98.51 81	99.74 243	98.91 135	99.88 70	99.77 95

QAPM		98.67 194	98.30 214	99.80 59	99.20 306	99.67 62	99.77 34	99.72 11	94.74 408	98.73 323	99.90 31	95.78 205	99.98 18	96.96 340	99.88 70	99.76 100

GeoE		98.85 175	98.62 188	99.53 127	99.61 168	99.08 162	99.80 25	99.51 139	97.10 305	99.31 212	99.78 156	95.23 230	99.77 234	98.21 229	99.03 216	99.75 101

test9_res														97.49 304	99.72 142	99.75 101

train_agg		99.02 145	98.77 165	99.77 68	99.67 128	99.65 69	99.05 364	99.41 252	96.28 365	98.95 292	99.49 291	98.76 55	99.91 129	97.63 289	99.72 142	99.75 101

agg_prior2														97.21 322	99.73 141	99.75 101

NormalMVS		99.27 84	99.19 84	99.52 133	99.89 8	98.83 208	99.65 84	99.52 120	99.10 42	99.84 51	99.76 169	95.80 203	99.99 4	99.30 84	99.84 96	99.74 105

KinetiMVS		99.12 121	98.92 138	99.70 81	99.67 128	99.40 115	99.67 71	99.63 42	98.73 96	99.94 26	99.81 116	94.54 271	99.96 39	98.40 211	99.93 31	99.74 105

AstraMVS		99.09 132	99.03 110	99.25 195	99.66 139	98.13 266	99.57 134	98.24 428	98.82 83	99.91 29	99.88 47	95.81 202	99.90 142	99.72 30	99.67 152	99.74 105

guyue		99.16 104	99.04 107	99.52 133	99.69 121	98.92 192	99.59 116	98.81 396	98.73 96	99.90 32	99.87 58	95.34 222	99.88 162	99.66 38	99.81 114	99.74 105

SF-MVS		99.38 63	99.24 75	99.79 62	99.79 62	99.68 58	99.57 134	99.54 101	97.82 226	99.71 98	99.80 133	98.95 30	99.93 105	98.19 231	99.84 96	99.74 105

test_prior				99.68 83	99.67 128	99.48 105		99.56 84					99.83 200			99.74 105

test12				99.75 71	99.64 149	99.61 79		99.29 322		99.21 240		98.38 92	99.89 157		99.74 139	99.74 105

114514_t		98.93 156	98.67 175	99.72 80	99.85 28	99.53 95	99.62 102	99.59 69	92.65 430	99.71 98	99.78 156	98.06 107	99.90 142	98.84 151	99.91 44	99.74 105

Vis-MVSNet		99.12 121	98.97 127	99.56 116	99.78 64	99.10 158	99.68 68	99.66 28	98.49 119	99.86 48	99.87 58	94.77 253	99.84 187	99.19 96	99.41 176	99.74 105
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
SymmetryMVS		99.15 108	99.02 116	99.52 133	99.72 105	98.83 208	99.65 84	99.34 291	99.10 42	99.84 51	99.76 169	95.80 203	99.99 4	99.30 84	98.72 243	99.73 114

fmvsm_s_conf0.5_n_4		99.36 68	99.24 75	99.73 77	99.78 64	99.53 95	99.49 202	99.60 63	99.42 18	99.99 2	99.86 65	95.15 232	99.95 74	99.95 14	99.89 66	99.73 114

fmvsm_s_conf0.1_n_2		99.37 64	99.22 79	99.81 55	99.77 72	99.75 46	99.46 221	99.60 63	99.47 4	99.98 11	99.94 6	94.98 236	99.95 74	99.97 2	99.79 126	99.73 114

旧先验1					99.74 94	99.59 82		99.54 101			99.69 207	98.47 83			99.68 150	99.73 114

casdiffmvs_mvg		99.15 108	99.02 116	99.55 118	99.66 139	99.09 159	99.64 91	99.56 84	98.26 147	99.45 171	99.87 58	96.03 189	99.81 214	99.54 49	99.15 201	99.73 114
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPNet		98.86 166	98.71 171	99.30 185	97.20 439	98.18 262	99.62 102	98.91 382	99.28 27	98.63 343	99.81 116	95.96 192	99.99 4	99.24 93	99.72 142	99.73 114
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
IS-MVSNet		99.05 141	98.87 151	99.57 114	99.73 101	99.32 125	99.75 42	99.20 340	98.02 202	99.56 151	99.86 65	96.54 169	99.67 273	98.09 242	99.13 203	99.73 114

F-COLMAP		99.19 96	99.04 107	99.64 95	99.78 64	99.27 137	99.42 242	99.54 101	97.29 286	99.41 186	99.59 253	98.42 88	99.93 105	98.19 231	99.69 147	99.73 114

DeepC-MVS	98.35 2	99.30 78	99.19 84	99.64 95	99.82 48	99.23 142	99.62 102	99.55 92	98.94 72	99.63 132	99.95 3	95.82 201	99.94 87	99.37 71	99.97 8	99.73 114
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SDMVSNet		99.11 127	98.90 143	99.75 71	99.81 52	99.59 82	99.81 20	99.65 35	98.78 92	99.64 129	99.88 47	94.56 268	99.93 105	99.67 35	98.26 271	99.72 123

sd_testset		98.75 187	98.57 195	99.29 188	99.81 52	98.26 259	99.56 141	99.62 47	98.78 92	99.64 129	99.88 47	92.02 346	99.88 162	99.54 49	98.26 271	99.72 123

新几何1				99.75 71	99.75 86	99.59 82		99.54 101	96.76 329	99.29 219	99.64 233	98.43 86	99.94 87	96.92 345	99.66 153	99.72 123

无先验							98.99 380	99.51 139	96.89 323				99.93 105	97.53 301		99.72 123

test222					99.75 86	99.49 103	98.91 396	99.49 171	96.42 359	99.34 209	99.65 227	98.28 97			99.69 147	99.72 123

testdata				99.54 119	99.75 86	98.95 185		99.51 139	97.07 307	99.43 179	99.70 196	98.87 40	99.94 87	97.76 277	99.64 156	99.72 123

VNet		99.11 127	98.90 143	99.73 77	99.52 205	99.56 88	99.41 247	99.39 262	99.01 58	99.74 89	99.78 156	95.56 213	99.92 117	99.52 53	98.18 279	99.72 123

WTY-MVS		99.06 138	98.88 150	99.61 103	99.62 159	99.16 149	99.37 266	99.56 84	98.04 197	99.53 158	99.62 244	96.84 154	99.94 87	98.85 148	98.49 258	99.72 123

CSCG		99.32 75	99.32 51	99.32 178	99.85 28	98.29 257	99.71 57	99.66 28	98.11 176	99.41 186	99.80 133	98.37 93	99.96 39	98.99 121	99.96 15	99.72 123

diffmvs_AUTHOR		99.19 96	99.10 94	99.48 145	99.64 149	98.85 203	99.32 284	99.48 183	98.50 118	99.81 63	99.81 116	96.82 155	99.88 162	99.40 67	99.12 205	99.71 132

BP-MVS1		99.12 121	98.94 137	99.65 89	99.51 208	99.30 132	99.67 71	98.92 377	98.48 120	99.84 51	99.69 207	94.96 237	99.92 117	99.62 42	99.79 126	99.71 132

原ACMM1				99.65 89	99.73 101	99.33 124		99.47 205	97.46 266	99.12 257	99.66 225	98.67 69	99.91 129	97.70 286	99.69 147	99.71 132

viewmanbaseed2359cas		99.18 99	99.07 102	99.50 143	99.62 159	99.01 171	99.50 188	99.52 120	98.25 150	99.68 104	99.82 101	96.93 148	99.80 221	99.15 104	99.11 206	99.70 135

Anonymous202405211		98.30 222	97.98 243	99.26 194	99.57 183	98.16 263	99.41 247	98.55 421	96.03 386	99.19 246	99.74 179	91.87 349	99.92 117	99.16 103	98.29 270	99.70 135

casdiffmvs		99.13 114	98.98 126	99.56 116	99.65 146	99.16 149	99.56 141	99.50 159	98.33 139	99.41 186	99.86 65	95.92 196	99.83 200	99.45 64	99.16 198	99.70 135
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
LFMVS		97.90 274	97.35 324	99.54 119	99.52 205	99.01 171	99.39 259	98.24 428	97.10 305	99.65 124	99.79 149	84.79 429	99.91 129	99.28 87	98.38 262	99.69 138

EPNet_dtu		98.03 253	97.96 245	98.23 336	98.27 421	95.54 387	99.23 324	98.75 403	99.02 56	97.82 392	99.71 192	96.11 185	99.48 305	93.04 420	99.65 155	99.69 138
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		99.04 142	98.84 158	99.66 85	99.74 94	99.44 110	99.39 259	99.38 270	97.70 239	99.28 220	99.28 354	98.34 94	99.85 178	96.96 340	99.45 173	99.69 138

EPP-MVSNet		99.13 114	98.99 123	99.53 127	99.65 146	99.06 165	99.81 20	99.33 299	97.43 273	99.60 143	99.88 47	97.14 134	99.84 187	99.13 105	98.94 222	99.69 138

sss		99.17 102	99.05 105	99.53 127	99.62 159	98.97 177	99.36 271	99.62 47	97.83 222	99.67 110	99.65 227	97.37 125	99.95 74	99.19 96	99.19 197	99.68 142

PHI-MVS		99.30 78	99.17 87	99.70 81	99.56 187	99.52 99	99.58 126	99.80 8	97.12 301	99.62 136	99.73 185	98.58 75	99.90 142	98.61 183	99.91 44	99.68 142

PVSNet_0	94.43 19	96.09 379	95.47 386	97.94 358	99.31 278	94.34 418	97.81 448	99.70 15	97.12 301	97.46 398	98.75 409	89.71 384	99.79 226	97.69 287	81.69 451	99.68 142

viewmambaseed2359dif		99.01 149	98.90 143	99.32 178	99.58 178	98.51 243	99.33 281	99.54 101	97.85 218	99.44 176	99.85 72	96.01 190	99.79 226	99.41 66	99.13 203	99.67 145

diffmvs		99.14 112	99.02 116	99.51 138	99.61 168	98.96 181	99.28 300	99.49 171	98.46 122	99.72 96	99.71 192	96.50 171	99.88 162	99.31 81	99.11 206	99.67 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		99.15 108	99.02 116	99.53 127	99.66 139	99.14 154	99.72 53	99.48 183	98.35 136	99.42 182	99.84 87	96.07 186	99.79 226	99.51 54	99.14 202	99.67 145

TAMVS		99.12 121	99.08 100	99.24 198	99.46 232	98.55 235	99.51 179	99.46 216	98.09 179	99.45 171	99.82 101	98.34 94	99.51 304	98.70 168	98.93 223	99.67 145

SD_0403		97.55 328	97.53 295	97.62 381	99.61 168	93.64 427	99.72 53	99.44 236	98.03 199	98.62 346	99.39 323	96.06 187	99.57 297	87.88 445	99.01 219	99.66 149

Anonymous20240529		98.09 241	97.68 279	99.34 172	99.66 139	98.44 251	99.40 255	99.43 247	93.67 418	99.22 237	99.89 37	90.23 379	99.93 105	99.26 92	98.33 265	99.66 149

CHOSEN 280x420		99.12 121	99.13 90	99.08 213	99.66 139	97.89 283	98.43 433	99.71 13	98.88 77	99.62 136	99.76 169	96.63 164	99.70 265	99.46 63	99.99 1	99.66 149

CDS-MVSNet		99.09 132	99.03 110	99.25 195	99.42 242	98.73 218	99.45 224	99.46 216	98.11 176	99.46 170	99.77 165	98.01 109	99.37 328	98.70 168	98.92 225	99.66 149
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
PAPR		98.63 199	98.34 210	99.51 138	99.40 252	99.03 168	98.80 406	99.36 279	96.33 362	99.00 283	99.12 376	98.46 84	99.84 187	95.23 392	99.37 184	99.66 149

h-mvs33		97.70 313	97.28 336	98.97 228	99.70 116	97.27 310	99.36 271	99.45 227	98.94 72	99.66 115	99.64 233	94.93 240	99.99 4	99.48 60	84.36 447	99.65 154

CANet		99.25 91	99.14 89	99.59 107	99.41 247	99.16 149	99.35 276	99.57 79	98.82 83	99.51 162	99.61 248	96.46 173	99.95 74	99.59 43	99.98 4	99.65 154

TSAR-MVS + GP.		99.36 68	99.36 43	99.36 169	99.67 128	98.61 231	99.07 358	99.33 299	99.00 61	99.82 62	99.81 116	99.06 16	99.84 187	99.09 111	99.42 175	99.65 154

MVSFormer		99.17 102	99.12 92	99.29 188	99.51 208	98.94 188	99.88 4	99.46 216	97.55 256	99.80 68	99.65 227	97.39 122	99.28 345	99.03 117	99.85 88	99.65 154

jason		99.13 114	99.03 110	99.45 153	99.46 232	98.87 199	99.12 348	99.26 328	98.03 199	99.79 70	99.65 227	97.02 143	99.85 178	99.02 119	99.90 55	99.65 154
jason: jason.
PLC	97.94 4	99.02 145	98.85 156	99.53 127	99.66 139	99.01 171	99.24 321	99.52 120	96.85 325	99.27 225	99.48 297	98.25 98	99.91 129	97.76 277	99.62 159	99.65 154
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
TAPA-MVS	97.07 15	97.74 305	97.34 327	98.94 233	99.70 116	97.53 300	99.25 316	99.51 139	91.90 432	99.30 216	99.63 239	98.78 51	99.64 285	88.09 443	99.87 73	99.65 154
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GDP-MVS		99.08 134	98.89 147	99.64 95	99.53 199	99.34 121	99.64 91	99.48 183	98.32 140	99.77 79	99.66 225	95.14 233	99.93 105	98.97 127	99.50 170	99.64 161

dmvs_re		98.08 243	98.16 220	97.85 366	99.55 191	94.67 410	99.70 58	98.92 377	98.15 165	99.06 273	99.35 335	93.67 305	99.25 352	97.77 276	97.25 332	99.64 161

LCM-MVSNet-Re		97.83 288	98.15 222	96.87 406	99.30 279	92.25 436	99.59 116	98.26 426	97.43 273	96.20 422	99.13 373	96.27 181	98.73 419	98.17 234	98.99 220	99.64 161

BH-RMVSNet		98.41 211	98.08 232	99.40 163	99.41 247	98.83 208	99.30 290	98.77 402	97.70 239	98.94 294	99.65 227	92.91 320	99.74 243	96.52 360	99.55 166	99.64 161

MVS_111021_LR		99.41 56	99.33 49	99.65 89	99.77 72	99.51 101	98.94 392	99.85 6	98.82 83	99.65 124	99.74 179	98.51 81	99.80 221	98.83 154	99.89 66	99.64 161

LuminaMVS		99.23 93	99.10 94	99.61 103	99.35 264	99.31 129	99.46 221	99.13 349	98.61 107	99.86 48	99.89 37	96.41 177	99.91 129	99.67 35	99.51 168	99.63 166

MVS		97.28 349	96.55 362	99.48 145	98.78 386	98.95 185	99.27 305	99.39 262	83.53 451	98.08 378	99.54 273	96.97 146	99.87 169	94.23 406	99.16 198	99.63 166

MSLP-MVS++		99.46 39	99.47 22	99.44 157	99.60 174	99.16 149	99.41 247	99.71 13	98.98 66	99.45 171	99.78 156	99.19 9	99.54 302	99.28 87	99.84 96	99.63 166

GA-MVS		97.85 281	97.47 304	99.00 224	99.38 257	97.99 274	98.57 426	99.15 346	97.04 312	98.90 299	99.30 350	89.83 383	99.38 325	96.70 353	98.33 265	99.62 169

Vis-MVSNet (Re-imp)		98.87 163	98.72 169	99.31 180	99.71 111	98.88 195	99.80 25	99.44 236	97.91 210	99.36 203	99.78 156	95.49 216	99.43 319	97.91 258	99.11 206	99.62 169

DPM-MVS		98.95 155	98.71 171	99.66 85	99.63 153	99.55 90	98.64 422	99.10 352	97.93 208	99.42 182	99.55 268	98.67 69	99.80 221	95.80 377	99.68 150	99.61 171

RRT-MVS		98.91 158	98.75 167	99.39 167	99.46 232	98.61 231	99.76 37	99.50 159	98.06 188	99.81 63	99.88 47	93.91 297	99.94 87	99.11 107	99.27 188	99.61 171

baseline1		98.31 220	97.95 247	99.38 168	99.50 220	98.74 217	99.59 116	98.93 374	98.41 129	99.14 254	99.60 251	94.59 266	99.79 226	98.48 202	93.29 414	99.61 171

mamba_0408		99.08 134	98.96 131	99.44 157	99.62 159	98.88 195	99.25 316	99.47 205	98.05 190	99.37 197	99.81 116	96.85 150	99.85 178	98.98 122	99.25 191	99.60 174

icg_test_0407_2		98.79 183	98.86 153	98.57 290	99.55 191	96.93 337	99.07 358	99.44 236	98.05 190	99.66 115	99.80 133	97.13 135	99.18 367	98.15 237	98.92 225	99.60 174

SSM_04072		99.06 138	98.96 131	99.35 171	99.62 159	98.88 195	99.25 316	99.47 205	98.05 190	99.37 197	99.81 116	96.85 150	99.58 296	98.98 122	99.25 191	99.60 174

SSM_0407		99.13 114	99.03 110	99.43 160	99.62 159	98.88 195	99.51 179	99.50 159	98.14 170	99.37 197	99.85 72	96.85 150	99.83 200	99.19 96	99.25 191	99.60 174

IMVS_0407		98.86 166	98.91 141	98.72 274	99.55 191	96.93 337	99.50 188	99.44 236	98.05 190	99.66 115	99.80 133	97.13 135	99.65 281	98.15 237	98.92 225	99.60 174

IMVS_0404		98.53 202	98.52 200	98.55 296	99.55 191	96.93 337	99.20 333	99.44 236	98.05 190	98.96 290	99.80 133	94.66 263	99.13 375	98.15 237	98.92 225	99.60 174

IMVS_0403		98.86 166	98.89 147	98.78 269	99.55 191	96.93 337	99.58 126	99.44 236	98.05 190	99.68 104	99.80 133	96.81 156	99.80 221	98.15 237	98.92 225	99.60 174

VDD-MVS		97.73 307	97.35 324	98.88 248	99.47 230	97.12 318	99.34 279	98.85 391	98.19 160	99.67 110	99.85 72	82.98 437	99.92 117	99.49 59	98.32 269	99.60 174

DELS-MVS		99.48 34	99.42 29	99.65 89	99.72 105	99.40 115	99.05 364	99.66 28	99.14 34	99.57 150	99.80 133	98.46 84	99.94 87	99.57 46	99.84 96	99.60 174
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
PVSNet_Blended		99.08 134	98.97 127	99.42 161	99.76 76	98.79 214	98.78 408	99.91 3	96.74 330	99.67 110	99.49 291	97.53 119	99.88 162	98.98 122	99.85 88	99.60 174

OMC-MVS		99.08 134	99.04 107	99.20 202	99.67 128	98.22 261	99.28 300	99.52 120	98.07 184	99.66 115	99.81 116	97.79 114	99.78 232	97.79 272	99.81 114	99.60 174

test_yl		98.86 166	98.63 183	99.54 119	99.49 222	99.18 146	99.50 188	99.07 358	98.22 156	99.61 140	99.51 285	95.37 220	99.84 187	98.60 186	98.33 265	99.59 185

DCV-MVSNet		98.86 166	98.63 183	99.54 119	99.49 222	99.18 146	99.50 188	99.07 358	98.22 156	99.61 140	99.51 285	95.37 220	99.84 187	98.60 186	98.33 265	99.59 185

AllTest		98.87 163	98.72 169	99.31 180	99.86 22	98.48 248	99.56 141	99.61 56	97.85 218	99.36 203	99.85 72	95.95 193	99.85 178	96.66 356	99.83 107	99.59 185

TestCases				99.31 180	99.86 22	98.48 248		99.61 56	97.85 218	99.36 203	99.85 72	95.95 193	99.85 178	96.66 356	99.83 107	99.59 185

dongtai		93.26 407	92.93 411	94.25 419	99.39 255	85.68 447	97.68 450	93.27 461	92.87 427	96.85 416	99.39 323	82.33 441	97.48 442	76.78 455	97.80 296	99.58 189

testing3		97.28 349	96.76 358	98.82 261	99.37 260	98.07 270	99.45 224	99.36 279	97.56 255	97.89 389	98.95 394	83.70 434	98.82 414	96.03 371	98.56 253	99.58 189

lupinMVS		99.13 114	99.01 121	99.46 152	99.51 208	98.94 188	99.05 364	99.16 345	97.86 215	99.80 68	99.56 265	97.39 122	99.86 172	98.94 129	99.85 88	99.58 189

sc_t1		95.75 385	95.05 392	97.87 364	98.83 380	94.61 411	99.21 330	99.45 227	87.45 445	97.97 385	99.85 72	81.19 445	99.43 319	98.27 225	93.20 416	99.57 192

tttt0517		98.42 209	98.14 223	99.28 192	99.66 139	98.38 255	99.74 47	96.85 446	97.68 241	99.79 70	99.74 179	91.39 363	99.89 157	98.83 154	99.56 164	99.57 192

RPSCF		98.22 226	98.62 188	96.99 400	99.82 48	91.58 439	99.72 53	99.44 236	96.61 342	99.66 115	99.89 37	95.92 196	99.82 209	97.46 308	99.10 210	99.57 192

dmvs_testset		95.02 394	96.12 372	91.72 429	99.10 333	80.43 457	99.58 126	97.87 436	97.47 265	95.22 429	98.82 403	93.99 292	95.18 454	88.09 443	94.91 390	99.56 195

DSMNet-mixed		97.25 351	97.35 324	96.95 403	97.84 427	93.61 428	99.57 134	96.63 450	96.13 380	98.87 305	98.61 414	94.59 266	97.70 440	95.08 394	98.86 233	99.55 196

AdaColmap		99.01 149	98.80 161	99.66 85	99.56 187	99.54 92	99.18 337	99.70 15	98.18 163	99.35 206	99.63 239	96.32 179	99.90 142	97.48 305	99.77 131	99.55 196

alignmvs		98.81 179	98.56 197	99.58 110	99.43 240	99.42 112	99.51 179	98.96 372	98.61 107	99.35 206	98.92 399	94.78 250	99.77 234	99.35 72	98.11 284	99.54 198

mamv4		99.33 73	99.42 29	99.07 214	99.67 128	97.73 290	99.42 242	99.60 63	98.15 165	99.94 26	99.91 24	98.42 88	99.94 87	99.72 30	99.96 15	99.54 198

EC-MVSNet		99.44 47	99.39 37	99.58 110	99.56 187	99.49 103	99.88 4	99.58 74	98.38 131	99.73 91	99.69 207	98.20 100	99.70 265	99.64 41	99.82 111	99.54 198

PatchmatchNet		98.31 220	98.36 208	98.19 338	99.16 322	95.32 395	99.27 305	98.92 377	97.37 279	99.37 197	99.58 257	94.90 243	99.70 265	97.43 311	99.21 195	99.54 198
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
PVSNet	96.02 17	98.85 175	98.84 158	98.89 246	99.73 101	97.28 309	98.32 439	99.60 63	97.86 215	99.50 163	99.57 262	96.75 160	99.86 172	98.56 195	99.70 146	99.54 198

MSDG		98.98 152	98.80 161	99.53 127	99.76 76	99.19 144	98.75 411	99.55 92	97.25 289	99.47 168	99.77 165	97.82 113	99.87 169	96.93 343	99.90 55	99.54 198

UGNet		98.87 163	98.69 173	99.40 163	99.22 303	98.72 219	99.44 230	99.68 20	99.24 28	99.18 250	99.42 311	92.74 324	99.96 39	99.34 77	99.94 29	99.53 204
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
SSM_0404		99.16 104	99.06 103	99.44 157	99.65 146	98.96 181	99.49 202	99.50 159	98.14 170	99.62 136	99.85 72	96.85 150	99.85 178	99.19 96	99.26 190	99.52 205

testing3-2		97.84 285	97.70 277	98.24 335	99.53 199	95.37 394	99.55 155	98.67 416	98.46 122	99.27 225	99.34 339	86.58 417	99.83 200	99.32 80	98.63 246	99.52 205

balanced_conf03		99.46 39	99.39 37	99.67 84	99.55 191	99.58 87	99.74 47	99.51 139	98.42 128	99.87 44	99.84 87	98.05 108	99.91 129	99.58 45	99.94 29	99.52 205

GSMVS																99.52 205

sam_mvs1												94.86 245				99.52 205

SCA		98.19 230	98.16 220	98.27 334	99.30 279	95.55 385	99.07 358	98.97 370	97.57 253	99.43 179	99.57 262	92.72 325	99.74 243	97.58 293	99.20 196	99.52 205

Patchmatch-test		97.93 268	97.65 282	98.77 270	99.18 312	97.07 323	99.03 369	99.14 348	96.16 376	98.74 322	99.57 262	94.56 268	99.72 253	93.36 416	99.11 206	99.52 205

PMMVS		98.80 182	98.62 188	99.34 172	99.27 288	98.70 220	98.76 410	99.31 313	97.34 281	99.21 240	99.07 378	97.20 133	99.82 209	98.56 195	98.87 232	99.52 205

LS3D		99.27 84	99.12 92	99.74 74	99.18 312	99.75 46	99.56 141	99.57 79	98.45 124	99.49 166	99.85 72	97.77 115	99.94 87	98.33 220	99.84 96	99.52 205

Effi-MVS+		98.81 179	98.59 194	99.48 145	99.46 232	99.12 157	98.08 446	99.50 159	97.50 264	99.38 195	99.41 315	96.37 178	99.81 214	99.11 107	98.54 255	99.51 214

Patchmatch-RL test		95.84 383	95.81 381	95.95 415	95.61 448	90.57 441	98.24 441	98.39 424	95.10 400	95.20 430	98.67 411	94.78 250	97.77 438	96.28 368	90.02 437	99.51 214

mvs_anonymous		99.03 144	98.99 123	99.16 206	99.38 257	98.52 241	99.51 179	99.38 270	97.79 227	99.38 195	99.81 116	97.30 128	99.45 310	99.35 72	98.99 220	99.51 214

mvsmamba		99.06 138	98.96 131	99.36 169	99.47 230	98.64 226	99.70 58	99.05 361	97.61 249	99.65 124	99.83 92	96.54 169	99.92 117	99.19 96	99.62 159	99.51 214

UniMVSNet_ETH3D		97.32 348	96.81 356	98.87 252	99.40 252	97.46 303	99.51 179	99.53 115	95.86 389	98.54 353	99.77 165	82.44 440	99.66 276	98.68 173	97.52 313	99.50 218

Elysia		98.88 160	98.65 180	99.58 110	99.58 178	99.34 121	99.65 84	99.52 120	98.26 147	99.83 59	99.87 58	93.37 308	99.90 142	97.81 270	99.91 44	99.49 219

StellarMVS		98.88 160	98.65 180	99.58 110	99.58 178	99.34 121	99.65 84	99.52 120	98.26 147	99.83 59	99.87 58	93.37 308	99.90 142	97.81 270	99.91 44	99.49 219

ab-mvs		98.86 166	98.63 183	99.54 119	99.64 149	99.19 144	99.44 230	99.54 101	97.77 230	99.30 216	99.81 116	94.20 283	99.93 105	99.17 102	98.82 237	99.49 219

thisisatest0530		98.35 218	98.03 238	99.31 180	99.63 153	98.56 234	99.54 160	96.75 448	97.53 260	99.73 91	99.65 227	91.25 367	99.89 157	98.62 180	99.56 164	99.48 222

SPE-MVS-test		99.49 30	99.48 20	99.54 119	99.78 64	99.30 132	99.89 2	99.58 74	98.56 112	99.73 91	99.69 207	98.55 78	99.82 209	99.69 33	99.85 88	99.48 222

ADS-MVSNet2		98.02 255	98.07 235	97.87 364	99.33 270	95.19 398	99.23 324	99.08 355	96.24 369	99.10 262	99.67 220	94.11 287	98.93 409	96.81 348	99.05 214	99.48 222

ADS-MVSNet		98.20 229	98.08 232	98.56 294	99.33 270	96.48 361	99.23 324	99.15 346	96.24 369	99.10 262	99.67 220	94.11 287	99.71 259	96.81 348	99.05 214	99.48 222

tpm		97.67 320	97.55 291	98.03 348	99.02 349	95.01 402	99.43 235	98.54 422	96.44 357	99.12 257	99.34 339	91.83 351	99.60 294	97.75 279	96.46 347	99.48 222

CNLPA		99.14 112	98.99 123	99.59 107	99.58 178	99.41 114	99.16 339	99.44 236	98.45 124	99.19 246	99.49 291	98.08 106	99.89 157	97.73 281	99.75 136	99.48 222

MVSMamba_PlusPlus		99.46 39	99.41 34	99.64 95	99.68 126	99.50 102	99.75 42	99.50 159	98.27 145	99.87 44	99.92 17	98.09 105	99.94 87	99.65 39	99.95 21	99.47 228

MGCFI-Net		99.01 149	98.85 156	99.50 143	99.42 242	99.26 138	99.82 16	99.48 183	98.60 109	99.28 220	98.81 404	97.04 142	99.76 238	99.29 86	97.87 293	99.47 228

sasdasda		99.02 145	98.86 153	99.51 138	99.42 242	99.32 125	99.80 25	99.48 183	98.63 104	99.31 212	98.81 404	97.09 138	99.75 241	99.27 90	97.90 290	99.47 228

canonicalmvs		99.02 145	98.86 153	99.51 138	99.42 242	99.32 125	99.80 25	99.48 183	98.63 104	99.31 212	98.81 404	97.09 138	99.75 241	99.27 90	97.90 290	99.47 228

MIMVSNet		97.73 307	97.45 307	98.57 290	99.45 238	97.50 302	99.02 372	98.98 369	96.11 381	99.41 186	99.14 372	90.28 375	98.74 418	95.74 378	98.93 223	99.47 228

MVS_Test		99.10 131	98.97 127	99.48 145	99.49 222	99.14 154	99.67 71	99.34 291	97.31 284	99.58 147	99.76 169	97.65 118	99.82 209	98.87 141	99.07 213	99.46 233

MDTV_nov1_ep13_2view						95.18 399	99.35 276		96.84 326	99.58 147		95.19 231		97.82 268		99.46 233

MVS-HIRNet		95.75 385	95.16 390	97.51 387	99.30 279	93.69 425	98.88 398	95.78 453	85.09 450	98.78 319	92.65 453	91.29 366	99.37 328	94.85 398	99.85 88	99.46 233

Syy-MVS		97.09 358	97.14 344	96.95 403	99.00 352	92.73 434	99.29 295	99.39 262	97.06 309	97.41 399	98.15 430	93.92 296	98.68 420	91.71 429	98.34 263	99.45 236

myMVS_eth3d		96.89 361	96.37 366	98.43 316	99.00 352	97.16 316	99.29 295	99.39 262	97.06 309	97.41 399	98.15 430	83.46 436	98.68 420	95.27 391	98.34 263	99.45 236

DP-MVS Recon		99.12 121	98.95 135	99.65 89	99.74 94	99.70 55	99.27 305	99.57 79	96.40 361	99.42 182	99.68 214	98.75 58	99.80 221	97.98 254	99.72 142	99.44 238

PatchMatch-RL		98.84 178	98.62 188	99.52 133	99.71 111	99.28 135	99.06 362	99.77 9	97.74 234	99.50 163	99.53 277	95.41 218	99.84 187	97.17 329	99.64 156	99.44 238

UBG		97.85 281	97.48 301	98.95 231	99.25 295	97.64 297	99.24 321	98.74 406	97.90 211	98.64 341	98.20 429	88.65 398	99.81 214	98.27 225	98.40 260	99.42 240

VDDNet		97.55 328	97.02 350	99.16 206	99.49 222	98.12 268	99.38 264	99.30 318	95.35 394	99.68 104	99.90 31	82.62 439	99.93 105	99.31 81	98.13 283	99.42 240

PCF-MVS	97.08 14	97.66 321	97.06 349	99.47 150	99.61 168	99.09 159	98.04 447	99.25 330	91.24 435	98.51 354	99.70 196	94.55 270	99.91 129	92.76 425	99.85 88	99.42 240
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ET-MVSNet_ETH3D		96.49 370	95.64 384	99.05 218	99.53 199	98.82 211	98.84 402	97.51 442	97.63 246	84.77 451	99.21 366	92.09 345	98.91 410	98.98 122	92.21 426	99.41 243

CS-MVS		99.50 28	99.48 20	99.54 119	99.76 76	99.42 112	99.90 1	99.55 92	98.56 112	99.78 75	99.70 196	98.65 71	99.79 226	99.65 39	99.78 128	99.41 243

HY-MVS	97.30 7	98.85 175	98.64 182	99.47 150	99.42 242	99.08 162	99.62 102	99.36 279	97.39 278	99.28 220	99.68 214	96.44 175	99.92 117	98.37 215	98.22 274	99.40 245

testing91		97.44 341	97.02 350	98.71 277	99.18 312	96.89 344	99.19 335	99.04 362	97.78 229	98.31 365	98.29 426	85.41 425	99.85 178	98.01 252	97.95 288	99.39 246

ETVMVS		97.50 334	96.90 354	99.29 188	99.23 299	98.78 216	99.32 284	98.90 384	97.52 262	98.56 351	98.09 435	84.72 430	99.69 270	97.86 263	97.88 292	99.39 246

tt0805		97.97 265	97.77 267	98.57 290	99.59 176	96.61 357	99.45 224	99.08 355	98.21 158	98.88 302	99.80 133	88.66 397	99.70 265	98.58 189	97.72 299	99.39 246

Fast-Effi-MVS+		98.70 191	98.43 204	99.51 138	99.51 208	99.28 135	99.52 170	99.47 205	96.11 381	99.01 279	99.34 339	96.20 183	99.84 187	97.88 260	98.82 237	99.39 246

testing11		97.50 334	97.10 347	98.71 277	99.20 306	96.91 342	99.29 295	98.82 394	97.89 212	98.21 373	98.40 421	85.63 423	99.83 200	98.45 207	98.04 286	99.37 250

CANet_DTU		98.97 154	98.87 151	99.25 195	99.33 270	98.42 254	99.08 357	99.30 318	99.16 31	99.43 179	99.75 174	95.27 225	99.97 27	98.56 195	99.95 21	99.36 251

testing99		97.36 344	96.94 353	98.63 283	99.18 312	96.70 350	99.30 290	98.93 374	97.71 236	98.23 370	98.26 427	84.92 428	99.84 187	98.04 251	97.85 295	99.35 252

EIA-MVS		99.18 99	99.09 99	99.45 153	99.49 222	99.18 146	99.67 71	99.53 115	97.66 244	99.40 191	99.44 307	98.10 104	99.81 214	98.94 129	99.62 159	99.35 252

EPMVS		97.82 291	97.65 282	98.35 323	98.88 370	95.98 376	99.49 202	94.71 458	97.57 253	99.26 230	99.48 297	92.46 339	99.71 259	97.87 262	99.08 212	99.35 252

CostFormer		97.72 309	97.73 274	97.71 377	99.15 326	94.02 420	99.54 160	99.02 365	94.67 409	99.04 276	99.35 335	92.35 342	99.77 234	98.50 201	97.94 289	99.34 255

BH-untuned		98.42 209	98.36 208	98.59 286	99.49 222	96.70 350	99.27 305	99.13 349	97.24 291	98.80 316	99.38 326	95.75 206	99.74 243	97.07 334	99.16 198	99.33 256

FE-MVS		98.48 204	98.17 219	99.40 163	99.54 198	98.96 181	99.68 68	98.81 396	95.54 392	99.62 136	99.70 196	93.82 300	99.93 105	97.35 316	99.46 172	99.32 257

PAPM		97.59 326	97.09 348	99.07 214	99.06 342	98.26 259	98.30 440	99.10 352	94.88 404	98.08 378	99.34 339	96.27 181	99.64 285	89.87 436	98.92 225	99.31 258

tpm2		97.44 341	97.34 327	97.74 376	99.15 326	94.36 417	99.45 224	98.94 373	93.45 423	98.90 299	99.44 307	91.35 364	99.59 295	97.31 317	98.07 285	99.29 259

UWE-MVS		97.58 327	97.29 335	98.48 303	99.09 336	96.25 370	99.01 377	96.61 451	97.86 215	99.19 246	99.01 386	88.72 394	99.90 142	97.38 314	98.69 244	99.28 260

FA-MVS(test-final)		98.75 187	98.53 199	99.41 162	99.55 191	99.05 167	99.80 25	99.01 366	96.59 347	99.58 147	99.59 253	95.39 219	99.90 142	97.78 273	99.49 171	99.28 260

MonoMVSNet		98.38 215	98.47 203	98.12 345	98.59 412	96.19 373	99.72 53	98.79 400	97.89 212	99.44 176	99.52 281	96.13 184	98.90 412	98.64 177	97.54 311	99.28 260

JIA-IIPM		97.50 334	97.02 350	98.93 235	98.73 395	97.80 288	99.30 290	98.97 370	91.73 433	98.91 297	94.86 451	95.10 234	99.71 259	97.58 293	97.98 287	99.28 260

UWE-MVS-28		97.36 344	97.24 340	97.75 374	98.84 379	94.44 414	99.24 321	97.58 441	97.98 204	99.00 283	99.00 387	91.35 364	99.53 303	93.75 411	98.39 261	99.27 264

kuosan		90.92 415	90.11 420	93.34 423	98.78 386	85.59 448	98.15 445	93.16 463	89.37 441	92.07 444	98.38 422	81.48 444	95.19 453	62.54 462	97.04 338	99.25 265

dp		97.75 303	97.80 261	97.59 385	99.10 333	93.71 424	99.32 284	98.88 387	96.48 354	99.08 267	99.55 268	92.67 330	99.82 209	96.52 360	98.58 250	99.24 266

myMVS_eth3d28		97.69 314	97.34 327	98.73 272	99.27 288	97.52 301	99.33 281	98.78 401	98.03 199	98.82 313	98.49 417	86.64 416	99.46 308	98.44 208	98.24 273	99.23 267

thisisatest0515		98.14 236	97.79 262	99.19 203	99.50 220	98.50 245	98.61 423	96.82 447	96.95 319	99.54 156	99.43 309	91.66 358	99.86 172	98.08 246	99.51 168	99.22 268

TESTMET0.1,1		97.55 328	97.27 339	98.40 319	98.93 363	96.53 359	98.67 417	97.61 440	96.96 317	98.64 341	99.28 354	88.63 400	99.45 310	97.30 318	99.38 177	99.21 269

testing222		97.16 354	96.50 363	99.16 206	99.16 322	98.47 250	99.27 305	98.66 417	97.71 236	98.23 370	98.15 430	82.28 442	99.84 187	97.36 315	97.66 301	99.18 270

CR-MVSNet		98.17 233	97.93 250	98.87 252	99.18 312	98.49 246	99.22 328	99.33 299	96.96 317	99.56 151	99.38 326	94.33 279	99.00 395	94.83 399	98.58 250	99.14 271

RPMNet		96.72 365	95.90 378	99.19 203	99.18 312	98.49 246	99.22 328	99.52 120	88.72 444	99.56 151	97.38 441	94.08 289	99.95 74	86.87 449	98.58 250	99.14 271

testgi		97.65 322	97.50 299	98.13 344	99.36 263	96.45 362	99.42 242	99.48 183	97.76 231	97.87 390	99.45 306	91.09 368	98.81 415	94.53 401	98.52 256	99.13 273

test-LLR		98.06 245	97.90 252	98.55 296	98.79 383	97.10 319	98.67 417	97.75 437	97.34 281	98.61 347	98.85 401	94.45 276	99.45 310	97.25 320	99.38 177	99.10 274

test-mter		97.49 339	97.13 346	98.55 296	98.79 383	97.10 319	98.67 417	97.75 437	96.65 337	98.61 347	98.85 401	88.23 404	99.45 310	97.25 320	99.38 177	99.10 274

IB-MVS	95.67 18	96.22 374	95.44 388	98.57 290	99.21 304	96.70 350	98.65 421	97.74 439	96.71 332	97.27 404	98.54 416	86.03 420	99.92 117	98.47 205	86.30 445	99.10 274
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
MAR-MVS		98.86 166	98.63 183	99.54 119	99.37 260	99.66 65	99.45 224	99.54 101	96.61 342	99.01 279	99.40 319	97.09 138	99.86 172	97.68 288	99.53 167	99.10 274
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
tpmrst		98.33 219	98.48 202	97.90 362	99.16 322	94.78 406	99.31 288	99.11 351	97.27 287	99.45 171	99.59 253	95.33 223	99.84 187	98.48 202	98.61 247	99.09 278

hse-mvs2		97.50 334	97.14 344	98.59 286	99.49 222	97.05 325	99.28 300	99.22 336	98.94 72	99.66 115	99.42 311	94.93 240	99.65 281	99.48 60	83.80 449	99.08 279

xiu_mvs_v1_base_debu		99.29 80	99.27 70	99.34 172	99.63 153	98.97 177	99.12 348	99.51 139	98.86 78	99.84 51	99.47 300	98.18 101	99.99 4	99.50 55	99.31 185	99.08 279

xiu_mvs_v1_base		99.29 80	99.27 70	99.34 172	99.63 153	98.97 177	99.12 348	99.51 139	98.86 78	99.84 51	99.47 300	98.18 101	99.99 4	99.50 55	99.31 185	99.08 279

xiu_mvs_v1_base_debi		99.29 80	99.27 70	99.34 172	99.63 153	98.97 177	99.12 348	99.51 139	98.86 78	99.84 51	99.47 300	98.18 101	99.99 4	99.50 55	99.31 185	99.08 279

COLMAP_ROB	97.56 6	98.86 166	98.75 167	99.17 205	99.88 13	98.53 237	99.34 279	99.59 69	97.55 256	98.70 331	99.89 37	95.83 200	99.90 142	98.10 241	99.90 55	99.08 279
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
AUN-MVS		96.88 362	96.31 368	98.59 286	99.48 229	97.04 328	99.27 305	99.22 336	97.44 272	98.51 354	99.41 315	91.97 347	99.66 276	97.71 284	83.83 448	99.07 284

OpenMVS	96.50 16	98.47 205	98.12 226	99.52 133	99.04 347	99.53 95	99.82 16	99.72 11	94.56 411	98.08 378	99.88 47	94.73 256	99.98 18	97.47 307	99.76 134	99.06 285

ETV-MVS		99.26 87	99.21 80	99.40 163	99.46 232	99.30 132	99.56 141	99.52 120	98.52 116	99.44 176	99.27 357	98.41 90	99.86 172	99.10 110	99.59 162	99.04 286

PatchT		97.03 359	96.44 365	98.79 267	98.99 355	98.34 256	99.16 339	99.07 358	92.13 431	99.52 160	97.31 444	94.54 271	98.98 397	88.54 441	98.73 242	99.03 287

BH-w/o		98.00 260	97.89 256	98.32 326	99.35 264	96.20 372	99.01 377	98.90 384	96.42 359	98.38 361	99.00 387	95.26 227	99.72 253	96.06 370	98.61 247	99.03 287

Fast-Effi-MVS+-dtu		98.77 186	98.83 160	98.60 285	99.41 247	96.99 332	99.52 170	99.49 171	98.11 176	99.24 232	99.34 339	96.96 147	99.79 226	97.95 256	99.45 173	99.02 289

XVG-OURS-SEG-HR		98.69 192	98.62 188	98.89 246	99.71 111	97.74 289	99.12 348	99.54 101	98.44 127	99.42 182	99.71 192	94.20 283	99.92 117	98.54 199	98.90 231	99.00 290

XVG-OURS		98.73 190	98.68 174	98.88 248	99.70 116	97.73 290	98.92 394	99.55 92	98.52 116	99.45 171	99.84 87	95.27 225	99.91 129	98.08 246	98.84 235	99.00 290

tpm cat1		97.39 343	97.36 322	97.50 388	99.17 320	93.73 423	99.43 235	99.31 313	91.27 434	98.71 325	99.08 377	94.31 281	99.77 234	96.41 365	98.50 257	99.00 290

xiu_mvs_v2_base		99.26 87	99.25 74	99.29 188	99.53 199	98.91 193	99.02 372	99.45 227	98.80 88	99.71 98	99.26 359	98.94 32	99.98 18	99.34 77	99.23 194	98.98 293

PS-MVSNAJ		99.32 75	99.32 51	99.30 185	99.57 183	98.94 188	98.97 386	99.46 216	98.92 75	99.71 98	99.24 361	99.01 18	99.98 18	99.35 72	99.66 153	98.97 294

tpmvs		97.98 262	98.02 240	97.84 368	99.04 347	94.73 407	99.31 288	99.20 340	96.10 385	98.76 321	99.42 311	94.94 239	99.81 214	96.97 339	98.45 259	98.97 294

thres600view7		97.86 280	97.51 298	98.92 237	99.72 105	97.95 280	99.59 116	98.74 406	97.94 207	99.27 225	98.62 412	91.75 352	99.86 172	93.73 412	98.19 278	98.96 296

thres400		97.77 298	97.38 320	98.92 237	99.69 121	97.96 277	99.50 188	98.73 412	97.83 222	99.17 251	98.45 419	91.67 356	99.83 200	93.22 417	98.18 279	98.96 296

TR-MVS		97.76 299	97.41 318	98.82 261	99.06 342	97.87 284	98.87 400	98.56 420	96.63 341	98.68 333	99.22 363	92.49 335	99.65 281	95.40 388	97.79 297	98.95 298

test0.0.03 1		97.71 312	97.42 317	98.56 294	98.41 420	97.82 287	98.78 408	98.63 418	97.34 281	98.05 382	98.98 391	94.45 276	98.98 397	95.04 395	97.15 337	98.89 299

baseline2		97.87 278	97.55 291	98.82 261	99.18 312	98.02 272	99.41 247	96.58 452	96.97 316	96.51 418	99.17 368	93.43 306	99.57 297	97.71 284	99.03 216	98.86 300

cascas		97.69 314	97.43 316	98.48 303	98.60 410	97.30 308	98.18 444	99.39 262	92.96 426	98.41 359	98.78 408	93.77 302	99.27 348	98.16 235	98.61 247	98.86 300

1314		98.68 193	98.54 198	99.11 212	98.89 369	98.65 224	99.27 305	99.49 171	96.89 323	97.99 383	99.56 265	97.72 117	99.83 200	97.74 280	99.27 188	98.84 302

PS-MVSNAJss		98.92 157	98.92 138	98.90 243	98.78 386	98.53 237	99.78 32	99.54 101	98.07 184	99.00 283	99.76 169	99.01 18	99.37 328	99.13 105	97.23 333	98.81 303

VortexMVS		98.67 194	98.66 178	98.68 280	99.62 159	97.96 277	99.59 116	99.41 252	98.13 172	99.31 212	99.70 196	95.48 217	99.27 348	99.40 67	97.32 330	98.79 304

FC-MVSNet-test		98.75 187	98.62 188	99.15 210	99.08 339	99.45 109	99.86 11	99.60 63	98.23 155	98.70 331	99.82 101	96.80 157	99.22 359	99.07 113	96.38 349	98.79 304

reproduce_monomvs		97.89 275	97.87 257	97.96 357	99.51 208	95.45 390	99.60 109	99.25 330	99.17 30	98.85 310	99.49 291	89.29 389	99.64 285	99.35 72	96.31 352	98.78 306

nrg030		98.64 198	98.42 205	99.28 192	99.05 345	99.69 57	99.81 20	99.46 216	98.04 197	99.01 279	99.82 101	96.69 162	99.38 325	99.34 77	94.59 394	98.78 306

FIs		98.78 184	98.63 183	99.23 200	99.18 312	99.54 92	99.83 15	99.59 69	98.28 143	98.79 318	99.81 116	96.75 160	99.37 328	99.08 112	96.38 349	98.78 306

EU-MVSNet		97.98 262	98.03 238	97.81 372	98.72 397	96.65 355	99.66 78	99.66 28	98.09 179	98.35 363	99.82 101	95.25 228	98.01 433	97.41 312	95.30 380	98.78 306

jajsoiax		98.43 208	98.28 215	98.88 248	98.60 410	98.43 252	99.82 16	99.53 115	98.19 160	98.63 343	99.80 133	93.22 313	99.44 315	99.22 94	97.50 316	98.77 310

mvs_tets		98.40 214	98.23 217	98.91 241	98.67 403	98.51 243	99.66 78	99.53 115	98.19 160	98.65 340	99.81 116	92.75 322	99.44 315	99.31 81	97.48 320	98.77 310

Anonymous20231211		97.88 276	97.54 294	98.90 243	99.71 111	98.53 237	99.48 208	99.57 79	94.16 414	98.81 314	99.68 214	93.23 311	99.42 321	98.84 151	94.42 397	98.76 312

XXY-MVS		98.38 215	98.09 231	99.24 198	99.26 291	99.32 125	99.56 141	99.55 92	97.45 269	98.71 325	99.83 92	93.23 311	99.63 291	98.88 138	96.32 351	98.76 312

SSC-MVS3.2		97.34 346	97.15 343	97.93 359	99.02 349	95.76 381	99.48 208	99.58 74	97.62 248	99.09 265	99.53 277	87.95 407	99.27 348	96.42 363	95.66 371	98.75 314

v7n		97.87 278	97.52 296	98.92 237	98.76 393	98.58 233	99.84 12	99.46 216	96.20 372	98.91 297	99.70 196	94.89 244	99.44 315	96.03 371	93.89 407	98.75 314

PS-CasMVS		97.93 268	97.59 290	98.95 231	98.99 355	99.06 165	99.68 68	99.52 120	97.13 299	98.31 365	99.68 214	92.44 340	99.05 387	98.51 200	94.08 404	98.75 314

test_djsdf		98.67 194	98.57 195	98.98 226	98.70 400	98.91 193	99.88 4	99.46 216	97.55 256	99.22 237	99.88 47	95.73 207	99.28 345	99.03 117	97.62 304	98.75 314

Effi-MVS+-dtu		98.78 184	98.89 147	98.47 308	99.33 270	96.91 342	99.57 134	99.30 318	98.47 121	99.41 186	98.99 389	96.78 158	99.74 243	98.73 165	99.38 177	98.74 318

CP-MVSNet		98.09 241	97.78 265	99.01 222	98.97 360	99.24 141	99.67 71	99.46 216	97.25 289	98.48 357	99.64 233	93.79 301	99.06 386	98.63 179	94.10 403	98.74 318

VPA-MVSNet		98.29 223	97.95 247	99.30 185	99.16 322	99.54 92	99.50 188	99.58 74	98.27 145	99.35 206	99.37 329	92.53 334	99.65 281	99.35 72	94.46 395	98.72 320

PEN-MVS		97.76 299	97.44 312	98.72 274	98.77 391	98.54 236	99.78 32	99.51 139	97.06 309	98.29 368	99.64 233	92.63 331	98.89 413	98.09 242	93.16 417	98.72 320

WBMVS		97.74 305	97.50 299	98.46 309	99.24 297	97.43 304	99.21 330	99.42 249	97.45 269	98.96 290	99.41 315	88.83 393	99.23 355	98.94 129	96.02 357	98.71 322

VPNet		97.84 285	97.44 312	99.01 222	99.21 304	98.94 188	99.48 208	99.57 79	98.38 131	99.28 220	99.73 185	88.89 392	99.39 323	99.19 96	93.27 415	98.71 322

EI-MVSNet		98.67 194	98.67 175	98.68 280	99.35 264	97.97 275	99.50 188	99.38 270	96.93 322	99.20 243	99.83 92	97.87 111	99.36 332	98.38 213	97.56 309	98.71 322

WR-MVS		98.06 245	97.73 274	99.06 216	98.86 376	99.25 140	99.19 335	99.35 286	97.30 285	98.66 334	99.43 309	93.94 294	99.21 364	98.58 189	94.28 399	98.71 322

IterMVS-LS		98.46 206	98.42 205	98.58 289	99.59 176	98.00 273	99.37 266	99.43 247	96.94 321	99.07 268	99.59 253	97.87 111	99.03 390	98.32 222	95.62 372	98.71 322
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v144192		97.92 271	97.60 289	98.87 252	98.83 380	98.65 224	99.55 155	99.34 291	96.20 372	99.32 211	99.40 319	94.36 278	99.26 351	96.37 367	95.03 386	98.70 327

v1240		97.69 314	97.32 331	98.79 267	98.85 377	98.43 252	99.48 208	99.36 279	96.11 381	99.27 225	99.36 332	93.76 303	99.24 354	94.46 402	95.23 381	98.70 327

DTE-MVSNet		97.51 333	97.19 342	98.46 309	98.63 406	98.13 266	99.84 12	99.48 183	96.68 334	97.97 385	99.67 220	92.92 318	98.56 422	96.88 347	92.60 425	98.70 327

TranMVSNet+NR-MVSNet		97.93 268	97.66 281	98.76 271	98.78 386	98.62 229	99.65 84	99.49 171	97.76 231	98.49 356	99.60 251	94.23 282	98.97 404	98.00 253	92.90 419	98.70 327

v1921920		97.80 295	97.45 307	98.84 259	98.80 382	98.53 237	99.52 170	99.34 291	96.15 378	99.24 232	99.47 300	93.98 293	99.29 344	95.40 388	95.13 384	98.69 331

v1192		97.81 293	97.44 312	98.91 241	98.88 370	98.68 221	99.51 179	99.34 291	96.18 374	99.20 243	99.34 339	94.03 291	99.36 332	95.32 390	95.18 382	98.69 331

v2v482		98.06 245	97.77 267	98.92 237	98.90 368	98.82 211	99.57 134	99.36 279	96.65 337	99.19 246	99.35 335	94.20 283	99.25 352	97.72 283	94.97 387	98.69 331

UniMVSNet_NR-MVSNet		98.22 226	97.97 244	98.96 229	98.92 365	98.98 174	99.48 208	99.53 115	97.76 231	98.71 325	99.46 304	96.43 176	99.22 359	98.57 192	92.87 421	98.69 331

OurMVSNet-221017-0		97.88 276	97.77 267	98.19 338	98.71 399	96.53 359	99.88 4	99.00 367	97.79 227	98.78 319	99.94 6	91.68 355	99.35 335	97.21 322	96.99 340	98.69 331

tt0320		95.71 387	95.07 391	97.62 381	99.05 345	95.02 401	99.25 316	99.52 120	86.81 446	97.97 385	99.72 189	83.58 435	99.15 370	96.38 366	93.35 412	98.68 336

gg-mvs-nofinetune		96.17 377	95.32 389	98.73 272	98.79 383	98.14 265	99.38 264	94.09 459	91.07 437	98.07 381	91.04 457	89.62 387	99.35 335	96.75 350	99.09 211	98.68 336

v1144		97.98 262	97.69 278	98.85 258	98.87 373	98.66 223	99.54 160	99.35 286	96.27 367	99.23 236	99.35 335	94.67 261	99.23 355	96.73 351	95.16 383	98.68 336

DU-MVS		98.08 243	97.79 262	98.96 229	98.87 373	98.98 174	99.41 247	99.45 227	97.87 214	98.71 325	99.50 288	94.82 246	99.22 359	98.57 192	92.87 421	98.68 336

NR-MVSNet		97.97 265	97.61 288	99.02 221	98.87 373	99.26 138	99.47 217	99.42 249	97.63 246	97.08 411	99.50 288	95.07 235	99.13 375	97.86 263	93.59 410	98.68 336

LPG-MVS_test		98.22 226	98.13 225	98.49 301	99.33 270	97.05 325	99.58 126	99.55 92	97.46 266	99.24 232	99.83 92	92.58 332	99.72 253	98.09 242	97.51 314	98.68 336

LGP-MVS_train				98.49 301	99.33 270	97.05 325		99.55 92	97.46 266	99.24 232	99.83 92	92.58 332	99.72 253	98.09 242	97.51 314	98.68 336

LTVRE_ROB	97.16 12	98.02 255	97.90 252	98.40 319	99.23 299	96.80 348	99.70 58	99.60 63	97.12 301	98.18 375	99.70 196	91.73 354	99.72 253	98.39 212	97.45 321	98.68 336
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
tt0320-xc		95.31 393	94.59 397	97.45 389	98.92 365	94.73 407	99.20 333	99.31 313	86.74 447	97.23 405	99.72 189	81.14 446	98.95 407	97.08 333	91.98 427	98.67 344

IterMVS-SCA-FT		97.82 291	97.75 272	98.06 347	99.57 183	96.36 365	99.02 372	99.49 171	97.18 295	98.71 325	99.72 189	92.72 325	99.14 372	97.44 310	95.86 365	98.67 344

pm-mvs1		97.68 317	97.28 336	98.88 248	99.06 342	98.62 229	99.50 188	99.45 227	96.32 363	97.87 390	99.79 149	92.47 336	99.35 335	97.54 300	93.54 411	98.67 344

v10		97.85 281	97.52 296	98.86 255	98.99 355	98.67 222	99.75 42	99.41 252	95.70 390	98.98 286	99.41 315	94.75 255	99.23 355	96.01 373	94.63 393	98.67 344

HQP_MVS		98.27 225	98.22 218	98.44 314	99.29 283	96.97 334	99.39 259	99.47 205	98.97 69	99.11 259	99.61 248	92.71 327	99.69 270	97.78 273	97.63 302	98.67 344

plane_prior5								99.47 205					99.69 270	97.78 273	97.63 302	98.67 344

SixPastTwentyTwo		97.50 334	97.33 330	98.03 348	98.65 404	96.23 371	99.77 34	98.68 415	97.14 298	97.90 388	99.93 10	90.45 374	99.18 367	97.00 336	96.43 348	98.67 344

IterMVS		97.83 288	97.77 267	98.02 350	99.58 178	96.27 369	99.02 372	99.48 183	97.22 293	98.71 325	99.70 196	92.75 322	99.13 375	97.46 308	96.00 359	98.67 344
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMH	97.28 8	98.10 240	97.99 242	98.44 314	99.41 247	96.96 336	99.60 109	99.56 84	98.09 179	98.15 376	99.91 24	90.87 371	99.70 265	98.88 138	97.45 321	98.67 344
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v8		97.95 267	97.63 286	98.93 235	98.95 362	98.81 213	99.80 25	99.41 252	96.03 386	99.10 262	99.42 311	94.92 242	99.30 343	96.94 342	94.08 404	98.66 353

UniMVSNet (Re)		98.29 223	98.00 241	99.13 211	99.00 352	99.36 120	99.49 202	99.51 139	97.95 206	98.97 288	99.13 373	96.30 180	99.38 325	98.36 217	93.34 413	98.66 353

pmmvs6		96.53 369	96.09 374	97.82 371	98.69 401	95.47 389	99.37 266	99.47 205	93.46 422	97.41 399	99.78 156	87.06 415	99.33 338	96.92 345	92.70 423	98.65 355

K. test v3		97.10 357	96.79 357	98.01 351	98.72 397	96.33 366	99.87 8	97.05 444	97.59 250	96.16 423	99.80 133	88.71 395	99.04 388	96.69 354	96.55 346	98.65 355

our_test_3		97.65 322	97.68 279	97.55 386	98.62 407	94.97 403	98.84 402	99.30 318	96.83 328	98.19 374	99.34 339	97.01 145	99.02 392	95.00 396	96.01 358	98.64 357

YYNet1		95.36 391	94.51 399	97.92 360	97.89 426	97.10 319	99.10 356	99.23 334	93.26 424	80.77 456	99.04 382	92.81 321	98.02 432	94.30 403	94.18 401	98.64 357

MDA-MVSNet_test_wron		95.45 389	94.60 396	98.01 351	98.16 423	97.21 315	99.11 354	99.24 333	93.49 421	80.73 457	98.98 391	93.02 315	98.18 428	94.22 407	94.45 396	98.64 357

Baseline_NR-MVSNet		97.76 299	97.45 307	98.68 280	99.09 336	98.29 257	99.41 247	98.85 391	95.65 391	98.63 343	99.67 220	94.82 246	99.10 383	98.07 249	92.89 420	98.64 357

HQP4-MVS										98.66 334			99.64 285			98.64 357

HQP-MVS		98.02 255	97.90 252	98.37 322	99.19 309	96.83 345	98.98 383	99.39 262	98.24 152	98.66 334	99.40 319	92.47 336	99.64 285	97.19 326	97.58 307	98.64 357

ACMM	97.58 5	98.37 217	98.34 210	98.48 303	99.41 247	97.10 319	99.56 141	99.45 227	98.53 115	99.04 276	99.85 72	93.00 316	99.71 259	98.74 163	97.45 321	98.64 357
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
pmmvs5		97.52 331	97.30 333	98.16 340	98.57 413	96.73 349	99.27 305	98.90 384	96.14 379	98.37 362	99.53 277	91.54 361	99.14 372	97.51 302	95.87 364	98.63 364

v148		97.79 297	97.55 291	98.50 300	98.74 394	97.72 292	99.54 160	99.33 299	96.26 368	98.90 299	99.51 285	94.68 260	99.14 372	97.83 267	93.15 418	98.63 364

MDA-MVSNet-bldmvs		94.96 396	93.98 403	97.92 360	98.24 422	97.27 310	99.15 342	99.33 299	93.80 417	80.09 458	99.03 383	88.31 403	97.86 437	93.49 415	94.36 398	98.62 366

TransMVSNet (Re)		97.15 355	96.58 361	98.86 255	99.12 328	98.85 203	99.49 202	98.91 382	95.48 393	97.16 409	99.80 133	93.38 307	99.11 381	94.16 408	91.73 428	98.62 366

lessismore_v0				97.79 373	98.69 401	95.44 392		94.75 457		95.71 427	99.87 58	88.69 396	99.32 340	95.89 374	94.93 389	98.62 366

MVSTER		98.49 203	98.32 212	99.00 224	99.35 264	99.02 169	99.54 160	99.38 270	97.41 276	99.20 243	99.73 185	93.86 299	99.36 332	98.87 141	97.56 309	98.62 366

GBi-Net		97.68 317	97.48 301	98.29 329	99.51 208	97.26 312	99.43 235	99.48 183	96.49 351	99.07 268	99.32 347	90.26 376	98.98 397	97.10 330	96.65 342	98.62 366

test1		97.68 317	97.48 301	98.29 329	99.51 208	97.26 312	99.43 235	99.48 183	96.49 351	99.07 268	99.32 347	90.26 376	98.98 397	97.10 330	96.65 342	98.62 366

FMVSNet1		96.84 363	96.36 367	98.29 329	99.32 277	97.26 312	99.43 235	99.48 183	95.11 398	98.55 352	99.32 347	83.95 433	98.98 397	95.81 376	96.26 353	98.62 366

ACMP	97.20 11	98.06 245	97.94 249	98.45 311	99.37 260	97.01 330	99.44 230	99.49 171	97.54 259	98.45 358	99.79 149	91.95 348	99.72 253	97.91 258	97.49 319	98.62 366
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ACMH+	97.24 10	97.92 271	97.78 265	98.32 326	99.46 232	96.68 354	99.56 141	99.54 101	98.41 129	97.79 394	99.87 58	90.18 380	99.66 276	98.05 250	97.18 336	98.62 366

ppachtmachnet_test		97.49 339	97.45 307	97.61 384	98.62 407	95.24 396	98.80 406	99.46 216	96.11 381	98.22 372	99.62 244	96.45 174	98.97 404	93.77 410	95.97 363	98.61 375

OPM-MVS		98.19 230	98.10 228	98.45 311	98.88 370	97.07 323	99.28 300	99.38 270	98.57 111	99.22 237	99.81 116	92.12 344	99.66 276	98.08 246	97.54 311	98.61 375
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
WR-MVS_H		98.13 237	97.87 257	98.90 243	99.02 349	98.84 205	99.70 58	99.59 69	97.27 287	98.40 360	99.19 367	95.53 214	99.23 355	98.34 219	93.78 409	98.61 375

MIMVSNet1		95.51 388	95.04 393	96.92 405	97.38 434	95.60 383	99.52 170	99.50 159	93.65 419	96.97 414	99.17 368	85.28 427	96.56 449	88.36 442	95.55 375	98.60 378

N_pmnet		94.95 397	95.83 380	92.31 427	98.47 417	79.33 459	99.12 348	92.81 465	93.87 416	97.68 395	99.13 373	93.87 298	99.01 394	91.38 431	96.19 354	98.59 379

FMVSNet2		97.72 309	97.36 322	98.80 266	99.51 208	98.84 205	99.45 224	99.42 249	96.49 351	98.86 309	99.29 352	90.26 376	98.98 397	96.44 362	96.56 345	98.58 380

anonymousdsp		98.44 207	98.28 215	98.94 233	98.50 416	98.96 181	99.77 34	99.50 159	97.07 307	98.87 305	99.77 165	94.76 254	99.28 345	98.66 175	97.60 305	98.57 381

FMVSNet3		98.03 253	97.76 271	98.84 259	99.39 255	98.98 174	99.40 255	99.38 270	96.67 335	99.07 268	99.28 354	92.93 317	98.98 397	97.10 330	96.65 342	98.56 382

XVG-ACMP-BASELINE		97.83 288	97.71 276	98.20 337	99.11 330	96.33 366	99.41 247	99.52 120	98.06 188	99.05 275	99.50 288	89.64 386	99.73 249	97.73 281	97.38 328	98.53 383

Patchmtry		97.75 303	97.40 319	98.81 264	99.10 333	98.87 199	99.11 354	99.33 299	94.83 406	98.81 314	99.38 326	94.33 279	99.02 392	96.10 369	95.57 374	98.53 383

miper_lstm_enhance		98.00 260	97.91 251	98.28 333	99.34 269	97.43 304	98.88 398	99.36 279	96.48 354	98.80 316	99.55 268	95.98 191	98.91 410	97.27 319	95.50 377	98.51 385

USDC		97.34 346	97.20 341	97.75 374	99.07 340	95.20 397	98.51 430	99.04 362	97.99 203	98.31 365	99.86 65	89.02 390	99.55 301	95.67 382	97.36 329	98.49 386

c3_l		98.12 239	98.04 237	98.38 321	99.30 279	97.69 296	98.81 405	99.33 299	96.67 335	98.83 311	99.34 339	97.11 137	98.99 396	97.58 293	95.34 379	98.48 387

CLD-MVS		98.16 234	98.10 228	98.33 324	99.29 283	96.82 347	98.75 411	99.44 236	97.83 222	99.13 255	99.55 268	92.92 318	99.67 273	98.32 222	97.69 300	98.48 387
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
eth_miper_zixun_eth		98.05 250	97.96 245	98.33 324	99.26 291	97.38 306	98.56 428	99.31 313	96.65 337	98.88 302	99.52 281	96.58 167	99.12 380	97.39 313	95.53 376	98.47 389

Anonymous20231206		96.22 374	96.03 375	96.79 408	97.31 437	94.14 419	99.63 97	99.08 355	96.17 375	97.04 412	99.06 380	93.94 294	97.76 439	86.96 448	95.06 385	98.47 389

FMVSNet5		96.43 372	96.19 371	97.15 395	99.11 330	95.89 378	99.32 284	99.52 120	94.47 413	98.34 364	99.07 378	87.54 412	97.07 445	92.61 426	95.72 369	98.47 389

cl____		98.01 258	97.84 260	98.55 296	99.25 295	97.97 275	98.71 415	99.34 291	96.47 356	98.59 350	99.54 273	95.65 210	99.21 364	97.21 322	95.77 366	98.46 392

DIV-MVS_self_test		98.01 258	97.85 259	98.48 303	99.24 297	97.95 280	98.71 415	99.35 286	96.50 350	98.60 349	99.54 273	95.72 208	99.03 390	97.21 322	95.77 366	98.46 392

pmmvs4		98.13 237	97.90 252	98.81 264	98.61 409	98.87 199	98.99 380	99.21 339	96.44 357	99.06 273	99.58 257	95.90 198	99.11 381	97.18 328	96.11 356	98.46 392

cl22		97.85 281	97.64 285	98.48 303	99.09 336	97.87 284	98.60 425	99.33 299	97.11 304	98.87 305	99.22 363	92.38 341	99.17 369	98.21 229	95.99 360	98.42 395

V42		98.06 245	97.79 262	98.86 255	98.98 358	98.84 205	99.69 62	99.34 291	96.53 349	99.30 216	99.37 329	94.67 261	99.32 340	97.57 297	94.66 392	98.42 395

PVSNet_BlendedMVS		98.86 166	98.80 161	99.03 220	99.76 76	98.79 214	99.28 300	99.91 3	97.42 275	99.67 110	99.37 329	97.53 119	99.88 162	98.98 122	97.29 331	98.42 395

UnsupCasMVSNet_eth		96.44 371	96.12 372	97.40 391	98.65 404	95.65 382	99.36 271	99.51 139	97.13 299	96.04 425	98.99 389	88.40 402	98.17 429	96.71 352	90.27 436	98.40 398

TinyColmap		97.12 356	96.89 355	97.83 369	99.07 340	95.52 388	98.57 426	98.74 406	97.58 252	97.81 393	99.79 149	88.16 405	99.56 299	95.10 393	97.21 334	98.39 399

miper_ehance_all_eth		98.18 232	98.10 228	98.41 317	99.23 299	97.72 292	98.72 414	99.31 313	96.60 345	98.88 302	99.29 352	97.29 129	99.13 375	97.60 291	95.99 360	98.38 400

thres100view900		97.76 299	97.45 307	98.69 279	99.72 105	97.86 286	99.59 116	98.74 406	97.93 208	99.26 230	98.62 412	91.75 352	99.83 200	93.22 417	98.18 279	98.37 401

tfpn200view9		97.72 309	97.38 320	98.72 274	99.69 121	97.96 277	99.50 188	98.73 412	97.83 222	99.17 251	98.45 419	91.67 356	99.83 200	93.22 417	98.18 279	98.37 401

test_fmvs2		97.25 351	97.30 333	97.09 399	99.43 240	93.31 430	99.73 51	98.87 389	98.83 82	99.28 220	99.80 133	84.45 431	99.66 276	97.88 260	97.45 321	98.30 403

miper_enhance_ethall		98.16 234	98.08 232	98.41 317	98.96 361	97.72 292	98.45 432	99.32 309	96.95 319	98.97 288	99.17 368	97.06 141	99.22 359	97.86 263	95.99 360	98.29 404

tfpnnormal		97.84 285	97.47 304	98.98 226	99.20 306	99.22 143	99.64 91	99.61 56	96.32 363	98.27 369	99.70 196	93.35 310	99.44 315	95.69 380	95.40 378	98.27 405

test20.03		96.12 378	95.96 377	96.63 409	97.44 433	95.45 390	99.51 179	99.38 270	96.55 348	96.16 423	99.25 360	93.76 303	96.17 450	87.35 447	94.22 400	98.27 405

test_method		91.10 413	91.36 415	90.31 433	95.85 446	73.72 466	94.89 454	99.25 330	68.39 457	95.82 426	99.02 385	80.50 447	98.95 407	93.64 413	94.89 391	98.25 407

ITE_SJBPF				98.08 346	99.29 283	96.37 364		98.92 377	98.34 137	98.83 311	99.75 174	91.09 368	99.62 292	95.82 375	97.40 327	98.25 407

KD-MVS_self_test		95.00 395	94.34 400	96.96 402	97.07 442	95.39 393	99.56 141	99.44 236	95.11 398	97.13 410	97.32 443	91.86 350	97.27 444	90.35 435	81.23 452	98.23 409

mmtdpeth		96.95 360	96.71 359	97.67 379	99.33 270	94.90 405	99.89 2	99.28 324	98.15 165	99.72 96	98.57 415	86.56 418	99.90 142	99.82 27	89.02 440	98.20 410

EG-PatchMatch MVS		95.97 381	95.69 382	96.81 407	97.78 428	92.79 433	99.16 339	98.93 374	96.16 376	94.08 436	99.22 363	82.72 438	99.47 306	95.67 382	97.50 316	98.17 411

mvs5depth		96.66 366	96.22 370	97.97 355	97.00 443	96.28 368	98.66 420	99.03 364	96.61 342	96.93 415	99.79 149	87.20 414	99.47 306	96.65 358	94.13 402	98.16 412

D2MVS		98.41 211	98.50 201	98.15 343	99.26 291	96.62 356	99.40 255	99.61 56	97.71 236	98.98 286	99.36 332	96.04 188	99.67 273	98.70 168	97.41 326	98.15 413

APD_test1		95.87 382	96.49 364	94.00 420	99.53 199	84.01 449	99.54 160	99.32 309	95.91 388	97.99 383	99.85 72	85.49 424	99.88 162	91.96 428	98.84 235	98.12 414

ttmdpeth		97.80 295	97.63 286	98.29 329	98.77 391	97.38 306	99.64 91	99.36 279	98.78 92	96.30 421	99.58 257	92.34 343	99.39 323	98.36 217	95.58 373	98.10 415

TDRefinement		95.42 390	94.57 398	97.97 355	89.83 461	96.11 375	99.48 208	98.75 403	96.74 330	96.68 417	99.88 47	88.65 398	99.71 259	98.37 215	82.74 450	98.09 416

Anonymous20240521		96.20 376	95.89 379	97.13 397	97.72 431	94.96 404	99.79 31	99.29 322	93.01 425	97.20 408	99.03 383	89.69 385	98.36 426	91.16 432	96.13 355	98.07 417

API-MVS		99.04 142	99.03 110	99.06 216	99.40 252	99.31 129	99.55 155	99.56 84	98.54 114	99.33 210	99.39 323	98.76 55	99.78 232	96.98 338	99.78 128	98.07 417

new_pmnet		96.38 373	96.03 375	97.41 390	98.13 424	95.16 400	99.05 364	99.20 340	93.94 415	97.39 402	98.79 407	91.61 360	99.04 388	90.43 434	95.77 366	98.05 419

thres200		97.61 325	97.28 336	98.62 284	99.64 149	98.03 271	99.26 314	98.74 406	97.68 241	99.09 265	98.32 425	91.66 358	99.81 214	92.88 422	98.22 274	98.03 420

KD-MVS_2432*1600		94.62 398	93.72 406	97.31 392	97.19 440	95.82 379	98.34 436	99.20 340	95.00 402	97.57 396	98.35 423	87.95 407	98.10 430	92.87 423	77.00 455	98.01 421

miper_refine_blended		94.62 398	93.72 406	97.31 392	97.19 440	95.82 379	98.34 436	99.20 340	95.00 402	97.57 396	98.35 423	87.95 407	98.10 430	92.87 423	77.00 455	98.01 421

DeepMVS_CX				93.34 423	99.29 283	82.27 452		99.22 336	85.15 449	96.33 420	99.05 381	90.97 370	99.73 249	93.57 414	97.77 298	98.01 421

MVStest1		96.08 380	95.48 385	97.89 363	98.93 363	96.70 350	99.56 141	99.35 286	92.69 429	91.81 446	99.46 304	89.90 382	98.96 406	95.00 396	92.61 424	98.00 424

CL-MVSNet_self_test		94.49 400	93.97 404	96.08 414	96.16 445	93.67 426	98.33 438	99.38 270	95.13 396	97.33 403	98.15 430	92.69 329	96.57 448	88.67 440	79.87 453	97.99 425

GG-mvs-BLEND				98.45 311	98.55 414	98.16 263	99.43 235	93.68 460		97.23 405	98.46 418	89.30 388	99.22 359	95.43 387	98.22 274	97.98 426

pmmvs3		94.09 404	93.25 410	96.60 410	94.76 455	94.49 413	98.92 394	98.18 432	89.66 438	96.48 419	98.06 436	86.28 419	97.33 443	89.68 437	87.20 444	97.97 427

LF4IMVS		97.52 331	97.46 306	97.70 378	98.98 358	95.55 385	99.29 295	98.82 394	98.07 184	98.66 334	99.64 233	89.97 381	99.61 293	97.01 335	96.68 341	97.94 428

test_0402		96.64 367	96.24 369	97.85 366	98.85 377	96.43 363	99.44 230	99.26 328	93.52 420	96.98 413	99.52 281	88.52 401	99.20 366	92.58 427	97.50 316	97.93 429

MVP-Stereo		97.81 293	97.75 272	97.99 354	97.53 432	96.60 358	98.96 387	98.85 391	97.22 293	97.23 405	99.36 332	95.28 224	99.46 308	95.51 384	99.78 128	97.92 430
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MS-PatchMatch		97.24 353	97.32 331	96.99 400	98.45 418	93.51 429	98.82 404	99.32 309	97.41 276	98.13 377	99.30 350	88.99 391	99.56 299	95.68 381	99.80 119	97.90 431

mvsany_test3		93.77 405	93.45 409	94.74 418	95.78 447	88.01 444	99.64 91	98.25 427	98.28 143	94.31 435	97.97 437	68.89 452	98.51 424	97.50 303	90.37 435	97.71 432

ambc				93.06 426	92.68 457	82.36 451	98.47 431	98.73 412		95.09 432	97.41 440	55.55 458	99.10 383	96.42 363	91.32 429	97.71 432

test_vis1_rt		95.81 384	95.65 383	96.32 413	99.67 128	91.35 440	99.49 202	96.74 449	98.25 150	95.24 428	98.10 434	74.96 449	99.90 142	99.53 51	98.85 234	97.70 434

new-patchmatchnet		94.48 401	94.08 402	95.67 416	95.08 453	92.41 435	99.18 337	99.28 324	94.55 412	93.49 439	97.37 442	87.86 410	97.01 446	91.57 430	88.36 441	97.61 435

pmmvs-eth3d		95.34 392	94.73 395	97.15 395	95.53 450	95.94 377	99.35 276	99.10 352	95.13 396	93.55 438	97.54 439	88.15 406	97.91 435	94.58 400	89.69 439	97.61 435

UnsupCasMVSNet_bld		93.53 406	92.51 412	96.58 411	97.38 434	93.82 421	98.24 441	99.48 183	91.10 436	93.10 440	96.66 446	74.89 450	98.37 425	94.03 409	87.71 443	97.56 437

PM-MVS		92.96 409	92.23 413	95.14 417	95.61 448	89.98 443	99.37 266	98.21 430	94.80 407	95.04 433	97.69 438	65.06 453	97.90 436	94.30 403	89.98 438	97.54 438

EGC-MVSNET		82.80 422	77.86 428	97.62 381	97.91 425	96.12 374	99.33 281	99.28 324	8.40 465	25.05 466	99.27 357	84.11 432	99.33 338	89.20 438	98.22 274	97.42 439

test_f		91.90 412	91.26 416	93.84 421	95.52 451	85.92 446	99.69 62	98.53 423	95.31 395	93.87 437	96.37 448	55.33 459	98.27 427	95.70 379	90.98 433	97.32 440

test_fmvs3		92.10 411	91.77 414	93.08 425	96.19 444	86.25 445	99.82 16	98.62 419	96.65 337	95.19 431	96.90 445	55.05 460	95.93 452	96.63 359	90.92 434	97.06 441

LCM-MVSNet		86.80 420	85.22 424	91.53 430	87.81 462	80.96 456	98.23 443	98.99 368	71.05 455	90.13 450	96.51 447	48.45 463	96.88 447	90.51 433	85.30 446	96.76 442

OpenMVS_ROB	92.34 20	94.38 402	93.70 408	96.41 412	97.38 434	93.17 431	99.06 362	98.75 403	86.58 448	94.84 434	98.26 427	81.53 443	99.32 340	89.01 439	97.87 293	96.76 442

WB-MVS		93.10 408	94.10 401	90.12 434	95.51 452	81.88 454	99.73 51	99.27 327	95.05 401	93.09 441	98.91 400	94.70 259	91.89 458	76.62 456	94.02 406	96.58 444

SSC-MVS		92.73 410	93.73 405	89.72 435	95.02 454	81.38 455	99.76 37	99.23 334	94.87 405	92.80 442	98.93 396	94.71 258	91.37 459	74.49 458	93.80 408	96.42 445

CMPMVS	69.68 23	94.13 403	94.90 394	91.84 428	97.24 438	80.01 458	98.52 429	99.48 183	89.01 442	91.99 445	99.67 220	85.67 422	99.13 375	95.44 386	97.03 339	96.39 446
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
testf1		90.42 416	90.68 417	89.65 436	97.78 428	73.97 464	99.13 345	98.81 396	89.62 439	91.80 447	98.93 396	62.23 456	98.80 416	86.61 450	91.17 430	96.19 447

APD_test2		90.42 416	90.68 417	89.65 436	97.78 428	73.97 464	99.13 345	98.81 396	89.62 439	91.80 447	98.93 396	62.23 456	98.80 416	86.61 450	91.17 430	96.19 447

WB-MVSnew		97.65 322	97.65 282	97.63 380	98.78 386	97.62 298	99.13 345	98.33 425	97.36 280	99.07 268	98.94 395	95.64 211	99.15 370	92.95 421	98.68 245	96.12 449

PMMVS2		86.87 419	85.37 423	91.35 431	90.21 460	83.80 450	98.89 397	97.45 443	83.13 452	91.67 449	95.03 449	48.49 462	94.70 455	85.86 452	77.62 454	95.54 450

tmp_tt		82.80 422	81.52 425	86.66 438	66.61 468	68.44 467	92.79 457	97.92 434	68.96 456	80.04 459	99.85 72	85.77 421	96.15 451	97.86 263	43.89 461	95.39 451

FPMVS		84.93 421	85.65 422	82.75 442	86.77 463	63.39 468	98.35 435	98.92 377	74.11 454	83.39 453	98.98 391	50.85 461	92.40 457	84.54 453	94.97 387	92.46 452

Gipuma		90.99 414	90.15 419	93.51 422	98.73 395	90.12 442	93.98 455	99.45 227	79.32 453	92.28 443	94.91 450	69.61 451	97.98 434	87.42 446	95.67 370	92.45 453
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		77.30 426	74.86 430	84.62 440	75.88 466	77.61 460	97.63 451	93.15 464	88.81 443	64.27 461	89.29 458	36.51 465	83.93 463	75.89 457	52.31 460	92.33 454

test_vis3_rt		87.04 418	85.81 421	90.73 432	93.99 456	81.96 453	99.76 37	90.23 467	92.81 428	81.35 455	91.56 455	40.06 464	99.07 385	94.27 405	88.23 442	91.15 455

MVE	76.82 21	76.91 427	74.31 431	84.70 439	85.38 465	76.05 463	96.88 453	93.17 462	67.39 458	71.28 460	89.01 459	21.66 470	87.69 460	71.74 459	72.29 457	90.35 456
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	70.75 22	75.98 428	74.97 429	79.01 444	70.98 467	55.18 469	93.37 456	98.21 430	65.08 461	61.78 462	93.83 452	21.74 469	92.53 456	78.59 454	91.12 432	89.34 457
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
EMVS		80.02 425	79.22 427	82.43 443	91.19 458	76.40 461	97.55 452	92.49 466	66.36 460	83.01 454	91.27 456	64.63 454	85.79 462	65.82 461	60.65 459	85.08 458

E-PMN		80.61 424	79.88 426	82.81 441	90.75 459	76.38 462	97.69 449	95.76 454	66.44 459	83.52 452	92.25 454	62.54 455	87.16 461	68.53 460	61.40 458	84.89 459

test123		39.01 431	42.50 433	28.53 446	39.17 469	20.91 471	98.75 411	19.17 471	19.83 464	38.57 463	66.67 461	33.16 466	15.42 465	37.50 465	29.66 463	49.26 460

testmvs		39.17 430	43.78 432	25.37 447	36.04 470	16.84 472	98.36 434	26.56 469	20.06 463	38.51 464	67.32 460	29.64 467	15.30 466	37.59 464	39.90 462	43.98 461

wuyk23d		40.18 429	41.29 434	36.84 445	86.18 464	49.12 470	79.73 458	22.81 470	27.64 462	25.46 465	28.45 465	21.98 468	48.89 464	55.80 463	23.56 464	12.51 462

mmdepth		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

monomultidepth		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

test_blank		0.13 435	0.17 438	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	1.57 466	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet_test		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

DCPMVS		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

cdsmvs_eth3d_5k		24.64 432	32.85 435	0.00 448	0.00 471	0.00 473	0.00 459	99.51 139	0.00 466	0.00 467	99.56 265	96.58 167	0.00 467	0.00 466	0.00 465	0.00 463

pcd_1.5k_mvsjas		8.27 434	11.03 437	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	99.01 18	0.00 467	0.00 466	0.00 465	0.00 463

sosnet-low-res		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

sosnet		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uncertanet		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

Regformer		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

ab-mvs-re		8.30 433	11.06 436	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	99.58 257	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

uanet		0.02 436	0.03 439	0.00 448	0.00 471	0.00 473	0.00 459	0.00 472	0.00 466	0.00 467	0.27 467	0.00 471	0.00 467	0.00 466	0.00 465	0.00 463

WAC-MVS						97.16 316								95.47 385

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

test_one_0601					99.81 52	99.88 9		99.49 171	98.97 69	99.65 124	99.81 116	99.09 14

eth-test2					0.00 471

eth-test					0.00 471

ZD-MVS					99.71 111	99.79 36		99.61 56	96.84 326	99.56 151	99.54 273	98.58 75	99.96 39	96.93 343	99.75 136

test_241102_ONE					99.84 35	99.90 2		99.48 183	99.07 52	99.91 29	99.74 179	99.20 7	99.76 238

9.14			99.10 94		99.72 105		99.40 255	99.51 139	97.53 260	99.64 129	99.78 156	98.84 44	99.91 129	97.63 289	99.82 111

save fliter					99.76 76	99.59 82	99.14 344	99.40 259	99.00 61

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

test_part2					99.81 52	99.83 20				99.77 79

sam_mvs												94.72 257

MTGPA								99.47 205

test_post1							99.23 324				65.14 463	94.18 286	99.71 259	97.58 293

test_post											65.99 462	94.65 264	99.73 249

patchmatchnet-post											98.70 410	94.79 249	99.74 243

MTMP							99.54 160	98.88 387

gm-plane-assit					98.54 415	92.96 432			94.65 410		99.15 371		99.64 285	97.56 298

TEST9					99.67 128	99.65 69	99.05 364	99.41 252	96.22 371	98.95 292	99.49 291	98.77 54	99.91 129

test_8					99.67 128	99.61 79	99.03 369	99.41 252	96.28 365	98.93 295	99.48 297	98.76 55	99.91 129

agg_prior					99.67 128	99.62 77		99.40 259		98.87 305			99.91 129

test_prior4						99.56 88	98.99 380

test_prior2							98.96 387		98.34 137	99.01 279	99.52 281	98.68 67		97.96 255	99.74 139

旧先验2							98.96 387		96.70 333	99.47 168			99.94 87	98.19 231

新几何2							99.01 377

原ACMM2							98.95 390

testdata2													99.95 74	96.67 355

segment_acmp												98.96 25

testdata1							98.85 401		98.32 140

plane_prior7					99.29 283	97.03 329

plane_prior6					99.27 288	96.98 333						92.71 327

plane_prior4											99.61 248

plane_prior3						97.00 331			98.69 101	99.11 259

plane_prior2							99.39 259		98.97 69

plane_prior1					99.26 291

plane_prior						96.97 334	99.21 330		98.45 124						97.60 305

n2								0.00 472

nn								0.00 472

door-mid								98.05 433

test11								99.35 286

door								97.92 434

HQP5-MVS						96.83 345

HQP-NCC					99.19 309		98.98 383		98.24 152	98.66 334

ACMP_Plane					99.19 309		98.98 383		98.24 152	98.66 334

BP-MVS														97.19 326

HQP3-MVS								99.39 262							97.58 307

HQP2-MVS												92.47 336

NP-MVS					99.23 299	96.92 341					99.40 319

MDTV_nov1_ep13			98.32 212		99.11 330	94.44 414	99.27 305	98.74 406	97.51 263	99.40 191	99.62 244	94.78 250	99.76 238	97.59 292	98.81 239

ACMMP++_ref															97.19 335

ACMMP++															97.43 325

Test By Simon												98.75 58

High-resolution multi-view benchmark