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.

MM		97.29 23	96.98 32	98.23 11	98.01 112	95.03 26	98.07 55	95.76 300	97.78 1	97.52 49	98.80 30	88.09 109	99.86 9	99.44 1	99.37 62	99.80 1

fmvsm_s_conf0.5_n_2		96.62 59	96.82 44	96.02 132	97.98 115	90.43 175	97.50 135	98.59 20	96.59 5	99.31 2	99.08 4	84.47 167	99.75 46	99.37 2	98.45 119	97.88 193

fmvsm_s_conf0.5_n_3		97.15 27	97.36 19	96.52 90	97.98 115	91.19 145	97.84 86	98.65 18	97.08 2	99.25 5	99.10 3	87.88 115	99.79 37	99.32 3	99.18 79	98.59 136

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 63	98.25 89	92.59 90	97.81 93	98.68 13	94.93 38	99.24 6	98.87 23	93.52 20	99.79 37	99.32 3	99.21 75	99.40 58

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 56	98.21 95	92.75 84	97.83 89	98.73 9	95.04 36	99.30 3	98.84 28	93.34 22	99.78 40	99.32 3	99.13 85	99.50 44

fmvsm_s_conf0.1_n_2		96.33 71	96.44 67	96.00 136	97.30 155	90.37 178	97.53 132	97.92 114	96.52 6	99.14 9	99.08 4	83.21 189	99.74 47	99.22 6	98.06 135	97.88 193

fmvsm_s_conf0.5_n_4		96.75 51	97.07 24	95.79 145	97.76 130	89.57 200	97.66 113	98.66 16	95.36 23	99.03 10	98.90 19	88.39 105	99.73 49	99.17 7	98.66 107	98.08 182

fmvsm_l_conf0.5_n_3		97.64 8	97.60 9	97.79 30	98.14 102	93.94 52	97.93 75	98.65 18	96.70 3	99.38 1	99.07 7	89.92 86	99.81 30	99.16 8	99.43 48	99.61 23

test_fmvsm_n_1920		97.55 12	97.89 3	96.53 89	98.41 77	91.73 117	98.01 60	99.02 1	96.37 8	99.30 3	98.92 17	92.39 41	99.79 37	99.16 8	99.46 41	98.08 182

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 152	92.37 96	97.91 77	98.88 4	95.83 12	98.92 17	99.05 9	91.45 57	99.80 34	99.12 10	99.46 41	99.69 12

fmvsm_s_conf0.5_n		96.85 43	97.13 21	96.04 130	98.07 109	90.28 179	97.97 69	98.76 8	94.93 38	98.84 21	99.06 8	88.80 98	99.65 66	99.06 11	98.63 109	98.18 170

test_fmvsmconf0.1_n		97.09 29	97.06 25	97.19 68	95.67 260	92.21 103	97.95 72	98.27 43	95.78 16	98.40 30	99.00 11	89.99 84	99.78 40	99.06 11	99.41 54	99.59 25

MVS_0304		96.74 53	96.31 69	98.02 19	96.87 181	94.65 30	97.58 124	94.39 362	96.47 7	97.16 61	98.39 55	87.53 124	99.87 7	98.97 13	99.41 54	99.55 35

fmvsm_s_conf0.5_n_a		96.75 51	96.93 35	96.20 122	97.64 139	90.72 165	98.00 61	98.73 9	94.55 60	98.91 18	99.08 4	88.22 108	99.63 75	98.91 14	98.37 122	98.25 165

test_fmvsmvis_n_1920		96.70 54	96.84 40	96.31 111	96.62 201	91.73 117	97.98 63	98.30 36	96.19 9	96.10 107	98.95 15	89.42 89	99.76 43	98.90 15	99.08 89	97.43 220

fmvsm_s_conf0.1_n		96.58 62	96.77 48	96.01 135	96.67 199	90.25 180	97.91 77	98.38 27	94.48 64	98.84 21	99.14 1	88.06 110	99.62 76	98.82 16	98.60 111	98.15 174

test_fmvsmconf0.01_n		96.15 75	95.85 79	97.03 75	92.66 378	91.83 116	97.97 69	97.84 128	95.57 19	97.53 48	99.00 11	84.20 173	99.76 43	98.82 16	99.08 89	99.48 48

fmvsm_s_conf0.1_n_a		96.40 67	96.47 61	96.16 124	95.48 268	90.69 166	97.91 77	98.33 33	94.07 76	98.93 14	99.14 1	87.44 128	99.61 77	98.63 18	98.32 124	98.18 170

mamv4		94.66 121	96.10 74	90.37 360	98.01 112	73.41 409	96.82 204	97.78 133	89.95 224	94.52 148	97.43 138	92.91 27	99.09 158	98.28 19	99.16 82	98.60 134

MVSMamba_PlusPlus		96.51 63	96.48 60	96.59 86	98.07 109	91.97 112	98.14 49	97.79 132	90.43 213	97.34 57	97.52 134	91.29 63	99.19 138	98.12 20	99.64 14	98.60 134

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 36	94.76 51	98.30 31	98.90 19	93.77 17	99.68 62	97.93 21	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_vis1_n_1920		94.17 131	94.58 112	92.91 293	97.42 153	82.02 360	97.83 89	97.85 124	94.68 54	98.10 35	98.49 45	70.15 354	99.32 125	97.91 22	98.82 100	97.40 222

reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 95	98.21 55	95.73 17	97.99 38	99.03 10	92.63 36	99.82 28	97.80 23	99.42 51	99.67 13

balanced_conf03		96.84 45	96.89 37	96.68 80	97.63 141	92.22 102	98.17 48	97.82 130	94.44 66	98.23 33	97.36 141	90.97 71	99.22 135	97.74 24	99.66 10	98.61 133

reproduce-ours		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 106	98.20 57	95.80 14	97.88 42	98.98 13	92.91 27	99.81 30	97.68 25	99.43 48	99.67 13

our_new_method		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 106	98.20 57	95.80 14	97.88 42	98.98 13	92.91 27	99.81 30	97.68 25	99.43 48	99.67 13

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 112					99.86 9	97.68 25	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 112					99.86 9	97.68 25	99.67 6	99.77 2

patch_mono-2		96.83 46	97.44 17	95.01 186	99.05 39	85.39 313	96.98 191	98.77 7	94.70 53	97.99 38	98.66 34	93.61 19	99.91 1	97.67 29	99.50 35	99.72 11

test_vis1_n		92.37 203	92.26 188	92.72 301	94.75 317	82.64 350	98.02 59	96.80 248	91.18 182	97.77 46	97.93 96	58.02 405	98.29 243	97.63 30	98.21 128	97.23 231

test_fmvs1_n		92.73 193	92.88 162	92.29 312	96.08 246	81.05 368	97.98 63	97.08 217	90.72 197	96.79 74	98.18 78	63.07 396	98.45 227	97.62 31	98.42 121	97.36 223

test_fmvs1		93.21 168	93.53 140	92.25 315	96.55 210	81.20 367	97.40 151	96.96 231	90.68 199	96.80 72	98.04 87	69.25 362	98.40 230	97.58 32	98.50 114	97.16 232

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 43	95.13 31	99.19 7	98.89 21	95.54 5	99.85 18	97.52 33	99.66 10	99.56 32

test_241102_TWO								98.27 43	95.13 31	98.93 14	98.89 21	94.99 11	99.85 18	97.52 33	99.65 13	99.74 8

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 124	94.92 40	98.73 23	98.87 23	95.08 8	99.84 23	97.52 33	99.67 6	99.48 48
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_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 40					99.86 9	97.52 33	99.67 6	99.75 6

DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 61	95.39 11	99.29 1	98.28 40	94.78 49	98.93 14	98.87 23	96.04 2	99.86 9	97.45 37	99.58 23	99.59 25

test_0728_THIRD									94.78 49	98.73 23	98.87 23	95.87 4	99.84 23	97.45 37	99.72 2	99.77 2

EC-MVSNet		96.42 66	96.47 61	96.26 117	97.01 175	91.52 129	98.89 5	97.75 135	94.42 67	96.64 83	97.68 117	89.32 90	98.60 215	97.45 37	99.11 88	98.67 131

IU-MVS					99.42 7	95.39 11		97.94 111	90.40 215	98.94 13				97.41 40	99.66 10	99.74 8

mmtdpeth		89.70 313	88.96 311	91.90 323	95.84 255	84.42 329	97.46 144	95.53 316	90.27 216	94.46 151	90.50 386	69.74 360	98.95 175	97.39 41	69.48 411	92.34 388

dcpmvs_2		96.37 69	97.05 28	94.31 228	98.96 49	84.11 334	97.56 127	97.51 167	93.92 81	97.43 54	98.52 42	92.75 32	99.32 125	97.32 42	99.50 35	99.51 41

CS-MVS		96.86 41	97.06 25	96.26 117	98.16 101	91.16 150	99.09 3	97.87 119	95.30 26	97.06 67	98.03 88	91.72 50	98.71 205	97.10 43	99.17 80	98.90 109

TSAR-MVS + MP.		97.42 17	97.33 20	97.69 42	99.25 27	94.24 41	98.07 55	97.85 124	93.72 87	98.57 26	98.35 59	93.69 18	99.40 118	97.06 44	99.46 41	99.44 53
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		97.68 6	97.44 17	98.37 7	98.90 53	95.86 6	97.27 164	98.08 81	95.81 13	97.87 45	98.31 68	94.26 13	99.68 62	97.02 45	99.49 38	99.57 29

SD-MVS		97.41 18	97.53 12	97.06 74	98.57 72	94.46 34	97.92 76	98.14 71	94.82 46	99.01 11	98.55 40	94.18 14	97.41 345	96.94 46	99.64 14	99.32 66
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
SPE-MVS-test		96.89 39	97.04 29	96.45 101	98.29 85	91.66 123	99.03 4	97.85 124	95.84 11	96.90 70	97.97 94	91.24 64	98.75 198	96.92 47	99.33 64	98.94 102

CANet		96.39 68	96.02 75	97.50 50	97.62 142	93.38 64	97.02 185	97.96 109	95.42 22	94.86 140	97.81 109	87.38 130	99.82 28	96.88 48	99.20 77	99.29 67

TSAR-MVS + GP.		96.69 56	96.49 59	97.27 62	98.31 84	93.39 63	96.79 206	96.72 251	94.17 74	97.44 52	97.66 120	92.76 31	99.33 123	96.86 49	97.76 145	99.08 88

DeepPCF-MVS	93.97 1	96.61 60	97.09 23	95.15 178	98.09 105	86.63 289	96.00 269	98.15 69	95.43 21	97.95 40	98.56 38	93.40 21	99.36 122	96.77 50	99.48 39	99.45 51

BP-MVS1		95.89 84	95.49 84	97.08 73	96.67 199	93.20 73	98.08 53	96.32 275	94.56 59	96.32 97	97.84 106	84.07 176	99.15 147	96.75 51	98.78 102	98.90 109

test_cas_vis1_n_1920		94.48 125	94.55 116	94.28 230	96.78 192	86.45 294	97.63 120	97.64 150	93.32 107	97.68 47	98.36 58	73.75 330	99.08 161	96.73 52	99.05 91	97.31 227

SMA-MVS		97.35 20	97.03 30	98.30 8	99.06 38	95.42 10	97.94 73	98.18 64	90.57 209	98.85 20	98.94 16	93.33 23	99.83 26	96.72 53	99.68 4	99.63 19
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
DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 172	98.35 31	95.16 30	98.71 25	98.80 30	95.05 10	99.89 3	96.70 54	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.59 11	97.54 11	97.73 38	99.40 11	93.77 57	98.53 14	98.29 38	95.55 20	98.56 27	97.81 109	93.90 15	99.65 66	96.62 55	99.21 75	99.77 2
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
MSLP-MVS++		96.94 37	97.06 25	96.59 86	98.72 58	91.86 115	97.67 110	98.49 23	94.66 56	97.24 59	98.41 54	92.31 44	98.94 177	96.61 56	99.46 41	98.96 99

MP-MVS-pluss		96.70 54	96.27 71	97.98 22	99.23 30	94.71 29	96.96 193	98.06 89	90.67 200	95.55 127	98.78 32	91.07 68	99.86 9	96.58 57	99.55 26	99.38 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		97.62 10	97.53 12	97.87 24	98.39 80	94.25 40	98.43 22	98.27 43	95.34 25	98.11 34	98.56 38	94.53 12	99.71 54	96.57 58	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		97.18 25	96.84 40	98.20 14	99.30 24	95.35 15	97.12 179	98.07 86	93.54 96	96.08 108	97.69 116	93.86 16	99.71 54	96.50 59	99.39 58	99.55 35

SF-MVS		97.39 19	97.13 21	98.17 15	99.02 42	95.28 19	98.23 39	98.27 43	92.37 141	98.27 32	98.65 36	93.33 23	99.72 53	96.49 60	99.52 30	99.51 41

EI-MVSNet-Vis-set		96.51 63	96.47 61	96.63 83	98.24 90	91.20 144	96.89 197	97.73 138	94.74 52	96.49 90	98.49 45	90.88 74	99.58 85	96.44 61	98.32 124	99.13 81

VDD-MVS		93.82 149	93.08 155	96.02 132	97.88 124	89.96 190	97.72 104	95.85 296	92.43 139	95.86 116	98.44 51	68.42 371	99.39 119	96.31 62	94.85 209	98.71 128

ACMMP_NAP		97.20 24	96.86 38	98.23 11	99.09 34	95.16 22	97.60 123	98.19 62	92.82 132	97.93 41	98.74 33	91.60 55	99.86 9	96.26 63	99.52 30	99.67 13

diffmvs		95.25 101	95.13 99	95.63 156	96.43 224	89.34 213	95.99 270	97.35 198	92.83 131	96.31 98	97.37 140	86.44 141	98.67 208	96.26 63	97.19 164	98.87 115
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet-UG-set		96.34 70	96.30 70	96.47 98	98.20 96	90.93 157	96.86 199	97.72 140	94.67 55	96.16 105	98.46 49	90.43 79	99.58 85	96.23 65	97.96 138	98.90 109

SR-MVS		97.01 34	96.86 38	97.47 52	99.09 34	93.27 71	97.98 63	98.07 86	93.75 86	97.45 51	98.48 48	91.43 59	99.59 82	96.22 66	99.27 68	99.54 37

xiu_mvs_v1_base_debu		95.01 107	94.76 106	95.75 148	96.58 205	91.71 119	96.25 255	97.35 198	92.99 121	96.70 78	96.63 184	82.67 205	99.44 114	96.22 66	97.46 149	96.11 264

xiu_mvs_v1_base		95.01 107	94.76 106	95.75 148	96.58 205	91.71 119	96.25 255	97.35 198	92.99 121	96.70 78	96.63 184	82.67 205	99.44 114	96.22 66	97.46 149	96.11 264

xiu_mvs_v1_base_debi		95.01 107	94.76 106	95.75 148	96.58 205	91.71 119	96.25 255	97.35 198	92.99 121	96.70 78	96.63 184	82.67 205	99.44 114	96.22 66	97.46 149	96.11 264

alignmvs		95.87 86	95.23 96	97.78 32	97.56 150	95.19 21	97.86 82	97.17 209	94.39 70	96.47 92	96.40 197	85.89 149	99.20 137	96.21 70	95.11 207	98.95 101

sasdasda		96.02 78	95.45 87	97.75 36	97.59 145	95.15 23	98.28 30	97.60 154	94.52 62	96.27 100	96.12 211	87.65 119	99.18 141	96.20 71	94.82 211	98.91 106

canonicalmvs		96.02 78	95.45 87	97.75 36	97.59 145	95.15 23	98.28 30	97.60 154	94.52 62	96.27 100	96.12 211	87.65 119	99.18 141	96.20 71	94.82 211	98.91 106

MGCFI-Net		95.94 83	95.40 91	97.56 49	97.59 145	94.62 31	98.21 42	97.57 159	94.41 68	96.17 104	96.16 209	87.54 123	99.17 143	96.19 73	94.73 216	98.91 106

RRT-MVS		94.51 123	94.35 123	94.98 189	96.40 225	86.55 292	97.56 127	97.41 190	93.19 112	94.93 138	97.04 159	79.12 270	99.30 129	96.19 73	97.32 159	99.09 87

MTAPA		97.08 30	96.78 47	97.97 23	99.37 16	94.42 36	97.24 166	98.08 81	95.07 35	96.11 106	98.59 37	90.88 74	99.90 2	96.18 75	99.50 35	99.58 28

APD-MVS_3200maxsize		96.81 47	96.71 51	97.12 70	99.01 45	92.31 99	97.98 63	98.06 89	93.11 118	97.44 52	98.55 40	90.93 72	99.55 95	96.06 76	99.25 72	99.51 41

SR-MVS-dyc-post		96.88 40	96.80 46	97.11 71	99.02 42	92.34 97	97.98 63	98.03 98	93.52 99	97.43 54	98.51 43	91.40 60	99.56 93	96.05 77	99.26 70	99.43 55

RE-MVS-def			96.72 50		99.02 42	92.34 97	97.98 63	98.03 98	93.52 99	97.43 54	98.51 43	90.71 76		96.05 77	99.26 70	99.43 55

MVS_111021_HR		96.68 58	96.58 56	96.99 76	98.46 73	92.31 99	96.20 260	98.90 3	94.30 73	95.86 116	97.74 114	92.33 42	99.38 121	96.04 79	99.42 51	99.28 69

PHI-MVS		96.77 49	96.46 64	97.71 41	98.40 78	94.07 48	98.21 42	98.45 26	89.86 226	97.11 65	98.01 91	92.52 39	99.69 60	96.03 80	99.53 29	99.36 64

casdiffmvs_mvg		95.81 87	95.57 82	96.51 94	96.87 181	91.49 130	97.50 135	97.56 163	93.99 79	95.13 136	97.92 97	87.89 114	98.78 193	95.97 81	97.33 157	99.26 71
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS++		97.34 21	96.97 33	98.47 5	99.08 36	96.16 4	97.55 131	97.97 108	95.59 18	96.61 84	97.89 98	92.57 38	99.84 23	95.95 82	99.51 33	99.40 58

DELS-MVS		96.61 60	96.38 68	97.30 58	97.79 128	93.19 74	95.96 271	98.18 64	95.23 27	95.87 115	97.65 121	91.45 57	99.70 59	95.87 83	99.44 47	99.00 97
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
MVS_111021_LR		96.24 74	96.19 73	96.39 106	98.23 94	91.35 137	96.24 258	98.79 6	93.99 79	95.80 118	97.65 121	89.92 86	99.24 133	95.87 83	99.20 77	98.58 137

h-mvs33		94.15 133	93.52 142	96.04 130	97.81 127	90.22 181	97.62 122	97.58 158	95.19 28	96.74 76	97.45 135	83.67 181	99.61 77	95.85 85	79.73 385	98.29 164

hse-mvs2		93.45 161	92.99 157	94.81 199	97.02 174	88.59 235	96.69 217	96.47 269	95.19 28	96.74 76	96.16 209	83.67 181	98.48 226	95.85 85	79.13 389	97.35 225

NCCC		97.30 22	97.03 30	98.11 17	98.77 56	95.06 25	97.34 157	98.04 96	95.96 10	97.09 66	97.88 100	93.18 25	99.71 54	95.84 87	99.17 80	99.56 32

VNet		95.89 84	95.45 87	97.21 66	98.07 109	92.94 81	97.50 135	98.15 69	93.87 83	97.52 49	97.61 127	85.29 156	99.53 99	95.81 88	95.27 202	99.16 77

PC_three_1452									90.77 194	98.89 19	98.28 73	96.24 1	98.35 238	95.76 89	99.58 23	99.59 25

9.14			96.75 49		98.93 50		97.73 101	98.23 54	91.28 178	97.88 42	98.44 51	93.00 26	99.65 66	95.76 89	99.47 40

XVS		97.18 25	96.96 34	97.81 28	99.38 14	94.03 50	98.59 12	98.20 57	94.85 42	96.59 86	98.29 71	91.70 52	99.80 34	95.66 91	99.40 56	99.62 20

X-MVStestdata		91.71 229	89.67 294	97.81 28	99.38 14	94.03 50	98.59 12	98.20 57	94.85 42	96.59 86	32.69 429	91.70 52	99.80 34	95.66 91	99.40 56	99.62 20

baseline		95.58 93	95.42 90	96.08 126	96.78 192	90.41 176	97.16 176	97.45 181	93.69 90	95.65 125	97.85 104	87.29 131	98.68 207	95.66 91	97.25 162	99.13 81

ETV-MVS		96.02 78	95.89 78	96.40 104	97.16 161	92.44 94	97.47 142	97.77 134	94.55 60	96.48 91	94.51 292	91.23 66	98.92 179	95.65 94	98.19 129	97.82 201

casdiffmvs		95.64 90	95.49 84	96.08 126	96.76 197	90.45 173	97.29 163	97.44 185	94.00 78	95.46 131	97.98 93	87.52 126	98.73 201	95.64 95	97.33 157	99.08 88
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HFP-MVS		97.14 28	96.92 36	97.83 26	99.42 7	94.12 46	98.52 15	98.32 34	93.21 109	97.18 60	98.29 71	92.08 46	99.83 26	95.63 96	99.59 19	99.54 37

ACMMPR		97.07 31	96.84 40	97.79 30	99.44 6	93.88 53	98.52 15	98.31 35	93.21 109	97.15 62	98.33 65	91.35 61	99.86 9	95.63 96	99.59 19	99.62 20

HPM-MVS		96.69 56	96.45 65	97.40 54	99.36 18	93.11 76	98.87 6	98.06 89	91.17 183	96.40 95	97.99 92	90.99 70	99.58 85	95.61 98	99.61 18	99.49 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		97.02 33	96.81 45	97.64 45	99.33 21	93.54 60	98.80 8	98.28 40	92.99 121	96.45 94	98.30 70	91.90 49	99.85 18	95.61 98	99.68 4	99.54 37

DeepC-MVS	93.07 3	96.06 76	95.66 81	97.29 59	97.96 117	93.17 75	97.30 162	98.06 89	93.92 81	93.38 176	98.66 34	86.83 136	99.73 49	95.60 100	99.22 74	98.96 99
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		96.96 35	96.67 52	97.85 25	99.37 16	94.12 46	98.49 19	98.18 64	92.64 137	96.39 96	98.18 78	91.61 54	99.88 4	95.59 101	99.55 26	99.57 29

region2R		97.07 31	96.84 40	97.77 34	99.46 2	93.79 55	98.52 15	98.24 51	93.19 112	97.14 63	98.34 62	91.59 56	99.87 7	95.46 102	99.59 19	99.64 18

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 74	96.04 2	99.24 133	95.36 103	99.59 19	99.56 32

lupinMVS		94.99 111	94.56 113	96.29 115	96.34 229	91.21 142	95.83 278	96.27 279	88.93 259	96.22 102	96.88 167	86.20 146	98.85 186	95.27 104	99.05 91	98.82 121

reproduce_monomvs		91.30 257	91.10 230	91.92 321	96.82 188	82.48 354	97.01 188	97.49 170	94.64 58	88.35 308	95.27 256	70.53 349	98.10 260	95.20 105	84.60 353	95.19 316

mPP-MVS		96.86 41	96.60 54	97.64 45	99.40 11	93.44 62	98.50 18	98.09 80	93.27 108	95.95 114	98.33 65	91.04 69	99.88 4	95.20 105	99.57 25	99.60 24

DeepC-MVS_fast	93.89 2	96.93 38	96.64 53	97.78 32	98.64 67	94.30 37	97.41 147	98.04 96	94.81 47	96.59 86	98.37 57	91.24 64	99.64 74	95.16 107	99.52 30	99.42 57
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
jason		94.84 116	94.39 122	96.18 123	95.52 266	90.93 157	96.09 264	96.52 266	89.28 245	96.01 112	97.32 142	84.70 163	98.77 196	95.15 108	98.91 99	98.85 117
jason: jason.
train_agg		96.30 72	95.83 80	97.72 39	98.70 59	94.19 42	96.41 239	98.02 101	88.58 271	96.03 109	97.56 131	92.73 34	99.59 82	95.04 109	99.37 62	99.39 60

mvsany_test1		93.93 145	93.98 128	93.78 258	94.94 307	86.80 282	94.62 328	92.55 393	88.77 268	96.85 71	98.49 45	88.98 94	98.08 265	95.03 110	95.62 196	96.46 252

test_prior2							96.35 247		92.80 133	96.03 109	97.59 128	92.01 47		95.01 111	99.38 59

nrg030		94.05 140	93.31 151	96.27 116	95.22 290	94.59 32	98.34 25	97.46 176	92.93 128	91.21 236	96.64 180	87.23 133	98.22 247	94.99 112	85.80 333	95.98 268

VDDNet		93.05 177	92.07 191	96.02 132	96.84 184	90.39 177	98.08 53	95.85 296	86.22 332	95.79 119	98.46 49	67.59 374	99.19 138	94.92 113	94.85 209	98.47 149

mvsmamba		94.57 122	94.14 126	95.87 140	97.03 173	89.93 191	97.84 86	95.85 296	91.34 174	94.79 142	96.80 169	80.67 241	98.81 190	94.85 114	98.12 133	98.85 117

APD-MVS		96.95 36	96.60 54	98.01 20	99.03 41	94.93 27	97.72 104	98.10 79	91.50 167	98.01 37	98.32 67	92.33 42	99.58 85	94.85 114	99.51 33	99.53 40
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
GST-MVS		96.85 43	96.52 58	97.82 27	99.36 18	94.14 45	98.29 29	98.13 72	92.72 134	96.70 78	98.06 85	91.35 61	99.86 9	94.83 116	99.28 67	99.47 50

MP-MVS		96.77 49	96.45 65	97.72 39	99.39 13	93.80 54	98.41 23	98.06 89	93.37 104	95.54 129	98.34 62	90.59 78	99.88 4	94.83 116	99.54 28	99.49 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
test9_res														94.81 118	99.38 59	99.45 51

PS-MVSNAJ		95.37 97	95.33 94	95.49 166	97.35 154	90.66 168	95.31 307	97.48 171	93.85 84	96.51 89	95.70 236	88.65 101	99.65 66	94.80 119	98.27 126	96.17 258

HPM-MVS_fast		96.51 63	96.27 71	97.22 65	99.32 22	92.74 85	98.74 9	98.06 89	90.57 209	96.77 75	98.35 59	90.21 81	99.53 99	94.80 119	99.63 16	99.38 62

xiu_mvs_v2_base		95.32 99	95.29 95	95.40 171	97.22 157	90.50 171	95.44 300	97.44 185	93.70 89	96.46 93	96.18 206	88.59 104	99.53 99	94.79 121	97.81 142	96.17 258

CSCG		96.05 77	95.91 77	96.46 100	99.24 28	90.47 172	98.30 28	98.57 22	89.01 254	93.97 163	97.57 129	92.62 37	99.76 43	94.66 122	99.27 68	99.15 79

test_fmvs2		89.77 311	89.93 283	89.31 374	93.68 353	76.37 401	97.64 118	95.90 293	89.84 229	91.49 223	96.26 204	58.77 404	97.10 355	94.65 123	91.13 277	94.46 352

EIA-MVS		95.53 95	95.47 86	95.71 153	97.06 169	89.63 196	97.82 91	97.87 119	93.57 92	93.92 164	95.04 265	90.61 77	98.95 175	94.62 124	98.68 106	98.54 139

SDMVSNet		94.17 131	93.61 136	95.86 142	98.09 105	91.37 136	97.35 156	98.20 57	93.18 114	91.79 216	97.28 144	79.13 269	98.93 178	94.61 125	92.84 248	97.28 228

ZD-MVS					99.05 39	94.59 32		98.08 81	89.22 247	97.03 68	98.10 81	92.52 39	99.65 66	94.58 126	99.31 66

ACMMP		96.27 73	95.93 76	97.28 61	99.24 28	92.62 88	98.25 35	98.81 5	92.99 121	94.56 147	98.39 55	88.96 95	99.85 18	94.57 127	97.63 146	99.36 64
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
GDP-MVS		95.62 91	95.13 99	97.09 72	96.79 191	93.26 72	97.89 80	97.83 129	93.58 91	96.80 72	97.82 108	83.06 196	99.16 145	94.40 128	97.95 139	98.87 115

PGM-MVS		96.81 47	96.53 57	97.65 43	99.35 20	93.53 61	97.65 114	98.98 2	92.22 144	97.14 63	98.44 51	91.17 67	99.85 18	94.35 129	99.46 41	99.57 29

ET-MVSNet_ETH3D		91.49 245	90.11 274	95.63 156	96.40 225	91.57 128	95.34 304	93.48 381	90.60 208	75.58 405	95.49 247	80.08 253	96.79 367	94.25 130	89.76 295	98.52 141

LFMVS		93.60 155	92.63 173	96.52 90	98.13 104	91.27 139	97.94 73	93.39 382	90.57 209	96.29 99	98.31 68	69.00 364	99.16 145	94.18 131	95.87 188	99.12 84

MVSFormer		95.37 97	95.16 98	95.99 137	96.34 229	91.21 142	98.22 40	97.57 159	91.42 171	96.22 102	97.32 142	86.20 146	97.92 296	94.07 132	99.05 91	98.85 117

test_djsdf		93.07 176	92.76 166	94.00 242	93.49 359	88.70 233	98.22 40	97.57 159	91.42 171	90.08 261	95.55 244	82.85 202	97.92 296	94.07 132	91.58 269	95.40 298

mvs_anonymous		93.82 149	93.74 132	94.06 238	96.44 223	85.41 311	95.81 279	97.05 222	89.85 228	90.09 260	96.36 199	87.44 128	97.75 315	93.97 134	96.69 175	99.02 91

VPA-MVSNet		93.24 167	92.48 182	95.51 164	95.70 258	92.39 95	97.86 82	98.66 16	92.30 142	92.09 208	95.37 251	80.49 245	98.40 230	93.95 135	85.86 332	95.75 281

agg_prior2														93.94 136	99.38 59	99.50 44

mvs_tets		92.31 206	91.76 203	93.94 249	93.41 362	88.29 244	97.63 120	97.53 165	92.04 153	88.76 300	96.45 194	74.62 322	98.09 264	93.91 137	91.48 271	95.45 293

Effi-MVS+		94.93 112	94.45 120	96.36 109	96.61 202	91.47 132	96.41 239	97.41 190	91.02 189	94.50 149	95.92 220	87.53 124	98.78 193	93.89 138	96.81 170	98.84 120

jajsoiax		92.42 200	91.89 200	94.03 241	93.33 365	88.50 240	97.73 101	97.53 165	92.00 155	88.85 297	96.50 192	75.62 314	98.11 259	93.88 139	91.56 270	95.48 289

XVG-OURS-SEG-HR		93.86 148	93.55 138	94.81 199	97.06 169	88.53 239	95.28 308	97.45 181	91.68 163	94.08 160	97.68 117	82.41 213	98.90 182	93.84 140	92.47 254	96.98 235

PS-MVSNAJss		93.74 152	93.51 143	94.44 219	93.91 345	89.28 218	97.75 98	97.56 163	92.50 138	89.94 263	96.54 190	88.65 101	98.18 252	93.83 141	90.90 283	95.86 269

EPNet		95.20 104	94.56 113	97.14 69	92.80 375	92.68 87	97.85 85	94.87 349	96.64 4	92.46 193	97.80 111	86.23 143	99.65 66	93.72 142	98.62 110	99.10 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		95.27 100	94.91 104	96.38 107	98.20 96	90.86 159	97.27 164	98.25 49	90.21 217	94.18 157	97.27 146	87.48 127	99.73 49	93.53 143	97.77 144	98.55 138

CPTT-MVS		95.57 94	95.19 97	96.70 79	99.27 26	91.48 131	98.33 26	98.11 77	87.79 298	95.17 135	98.03 88	87.09 134	99.61 77	93.51 144	99.42 51	99.02 91

MVSTER		93.20 169	92.81 165	94.37 222	96.56 208	89.59 199	97.06 182	97.12 212	91.24 179	91.30 230	95.96 218	82.02 220	98.05 272	93.48 145	90.55 287	95.47 291

PVSNet_BlendedMVS		94.06 139	93.92 129	94.47 217	98.27 86	89.46 208	96.73 211	98.36 28	90.17 218	94.36 152	95.24 259	88.02 111	99.58 85	93.44 146	90.72 285	94.36 356

PVSNet_Blended		94.87 115	94.56 113	95.81 144	98.27 86	89.46 208	95.47 299	98.36 28	88.84 262	94.36 152	96.09 216	88.02 111	99.58 85	93.44 146	98.18 130	98.40 157

3Dnovator	91.36 5	95.19 105	94.44 121	97.44 53	96.56 208	93.36 66	98.65 11	98.36 28	94.12 75	89.25 288	98.06 85	82.20 217	99.77 42	93.41 148	99.32 65	99.18 76

EPP-MVSNet		95.22 103	95.04 102	95.76 146	97.49 151	89.56 201	98.67 10	97.00 229	90.69 198	94.24 155	97.62 126	89.79 88	98.81 190	93.39 149	96.49 179	98.92 105

testing3-2		92.10 217	92.05 192	92.27 313	97.71 133	79.56 387	97.42 146	94.41 361	93.53 97	93.22 182	95.49 247	69.16 363	99.11 153	93.25 150	94.22 224	98.13 175

CHOSEN 280x420		93.12 173	92.72 171	94.34 225	96.71 198	87.27 270	90.29 403	97.72 140	86.61 324	91.34 227	95.29 253	84.29 172	98.41 229	93.25 150	98.94 97	97.35 225

3Dnovator+	91.43 4	95.40 96	94.48 119	98.16 16	96.90 180	95.34 16	98.48 20	97.87 119	94.65 57	88.53 305	98.02 90	83.69 180	99.71 54	93.18 152	98.96 96	99.44 53

test_yl		94.78 118	94.23 124	96.43 102	97.74 131	91.22 140	96.85 200	97.10 214	91.23 180	95.71 121	96.93 162	84.30 170	99.31 127	93.10 153	95.12 205	98.75 123

DCV-MVSNet		94.78 118	94.23 124	96.43 102	97.74 131	91.22 140	96.85 200	97.10 214	91.23 180	95.71 121	96.93 162	84.30 170	99.31 127	93.10 153	95.12 205	98.75 123

test_vis1_rt		86.16 352	85.06 353	89.46 370	93.47 361	80.46 375	96.41 239	86.61 421	85.22 346	79.15 398	88.64 400	52.41 413	97.06 356	93.08 155	90.57 286	90.87 404

test1111		93.19 170	92.82 164	94.30 229	97.58 149	84.56 328	98.21 42	89.02 412	93.53 97	94.58 146	98.21 75	72.69 333	99.05 168	93.06 156	98.48 117	99.28 69

ECVR-MVS		93.19 170	92.73 170	94.57 214	97.66 137	85.41 311	98.21 42	88.23 414	93.43 102	94.70 144	98.21 75	72.57 334	99.07 165	93.05 157	98.49 115	99.25 72

HQP_MVS		93.78 151	93.43 147	94.82 197	96.21 233	89.99 186	97.74 99	97.51 167	94.85 42	91.34 227	96.64 180	81.32 231	98.60 215	93.02 158	92.23 257	95.86 269

plane_prior5								97.51 167					98.60 215	93.02 158	92.23 257	95.86 269

MonoMVSNet		91.92 222	91.77 202	92.37 308	92.94 371	83.11 346	97.09 181	95.55 313	92.91 129	90.85 240	94.55 289	81.27 233	96.52 370	93.01 160	87.76 313	97.47 219

test2506		91.60 235	90.78 243	94.04 240	97.66 137	83.81 337	98.27 32	75.53 430	93.43 102	95.23 133	98.21 75	67.21 377	99.07 165	93.01 160	98.49 115	99.25 72

MVS_Test		94.89 114	94.62 110	95.68 154	96.83 186	89.55 202	96.70 215	97.17 209	91.17 183	95.60 126	96.11 215	87.87 116	98.76 197	93.01 160	97.17 165	98.72 126

CLD-MVS		92.98 180	92.53 179	94.32 226	96.12 243	89.20 221	95.28 308	97.47 174	92.66 135	89.90 264	95.62 240	80.58 243	98.40 230	92.73 163	92.40 255	95.38 300
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-OURS		93.72 153	93.35 150	94.80 202	97.07 166	88.61 234	94.79 325	97.46 176	91.97 156	93.99 161	97.86 103	81.74 226	98.88 183	92.64 164	92.67 253	96.92 239

旧先验2							95.94 272		81.66 385	97.34 57			98.82 188	92.26 165

CDPH-MVS		95.97 81	95.38 92	97.77 34	98.93 50	94.44 35	96.35 247	97.88 117	86.98 317	96.65 82	97.89 98	91.99 48	99.47 110	92.26 165	99.46 41	99.39 60

FIs		94.09 138	93.70 133	95.27 174	95.70 258	92.03 110	98.10 51	98.68 13	93.36 106	90.39 247	96.70 175	87.63 121	97.94 293	92.25 167	90.50 289	95.84 272

LPG-MVS_test		92.94 183	92.56 176	94.10 236	96.16 238	88.26 246	97.65 114	97.46 176	91.29 175	90.12 257	97.16 152	79.05 272	98.73 201	92.25 167	91.89 265	95.31 305

LGP-MVS_train				94.10 236	96.16 238	88.26 246		97.46 176	91.29 175	90.12 257	97.16 152	79.05 272	98.73 201	92.25 167	91.89 265	95.31 305

cascas		91.20 262	90.08 275	94.58 213	94.97 303	89.16 224	93.65 368	97.59 157	79.90 396	89.40 280	92.92 356	75.36 315	98.36 237	92.14 170	94.75 214	96.23 254

OPM-MVS		93.28 166	92.76 166	94.82 197	94.63 323	90.77 163	96.65 221	97.18 207	93.72 87	91.68 220	97.26 147	79.33 267	98.63 212	92.13 171	92.28 256	95.07 319
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BP-MVS														92.13 171

HQP-MVS		93.19 170	92.74 169	94.54 215	95.86 250	89.33 214	96.65 221	97.39 192	93.55 93	90.14 251	95.87 222	80.95 235	98.50 223	92.13 171	92.10 262	95.78 277

DP-MVS Recon		95.68 89	95.12 101	97.37 55	99.19 31	94.19 42	97.03 183	98.08 81	88.35 280	95.09 137	97.65 121	89.97 85	99.48 109	92.08 174	98.59 112	98.44 154

VPNet		92.23 212	91.31 220	94.99 187	95.56 264	90.96 155	97.22 171	97.86 123	92.96 127	90.96 238	96.62 187	75.06 317	98.20 249	91.90 175	83.65 367	95.80 275

sss		94.51 123	93.80 131	96.64 81	97.07 166	91.97 112	96.32 250	98.06 89	88.94 258	94.50 149	96.78 170	84.60 164	99.27 131	91.90 175	96.02 184	98.68 130

anonymousdsp		92.16 214	91.55 211	93.97 245	92.58 380	89.55 202	97.51 134	97.42 189	89.42 242	88.40 307	94.84 274	80.66 242	97.88 301	91.87 177	91.28 275	94.48 351

test_fmvs3		83.21 368	83.02 365	83.78 391	86.77 415	68.34 417	96.76 209	94.91 344	86.49 325	84.14 371	89.48 396	36.04 423	91.73 413	91.86 178	80.77 382	91.26 403

ACMP	89.59 10	92.62 195	92.14 190	94.05 239	96.40 225	88.20 249	97.36 155	97.25 206	91.52 166	88.30 311	96.64 180	78.46 284	98.72 204	91.86 178	91.48 271	95.23 312
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		93.66 154	92.92 160	95.87 140	98.24 90	89.88 192	94.58 330	98.49 23	85.06 350	93.78 166	95.78 231	82.86 201	98.67 208	91.77 180	95.71 193	99.07 90

UGNet		94.04 141	93.28 152	96.31 111	96.85 183	91.19 145	97.88 81	97.68 145	94.40 69	93.00 185	96.18 206	73.39 332	99.61 77	91.72 181	98.46 118	98.13 175
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
UniMVSNet_NR-MVSNet		93.37 163	92.67 172	95.47 169	95.34 279	92.83 82	97.17 175	98.58 21	92.98 126	90.13 255	95.80 227	88.37 107	97.85 302	91.71 182	83.93 362	95.73 283

DU-MVS		92.90 185	92.04 193	95.49 166	94.95 305	92.83 82	97.16 176	98.24 51	93.02 120	90.13 255	95.71 234	83.47 184	97.85 302	91.71 182	83.93 362	95.78 277

Effi-MVS+-dtu		93.08 175	93.21 154	92.68 304	96.02 247	83.25 344	97.14 178	96.72 251	93.85 84	91.20 237	93.44 347	83.08 194	98.30 242	91.69 184	95.73 192	96.50 249

UniMVSNet (Re)		93.31 165	92.55 177	95.61 158	95.39 273	93.34 67	97.39 152	98.71 11	93.14 117	90.10 259	94.83 275	87.71 117	98.03 276	91.67 185	83.99 361	95.46 292

LCM-MVSNet-Re		92.50 196	92.52 180	92.44 306	96.82 188	81.89 361	96.92 195	93.71 379	92.41 140	84.30 367	94.60 287	85.08 159	97.03 358	91.51 186	97.36 155	98.40 157

FC-MVSNet-test		93.94 144	93.57 137	95.04 184	95.48 268	91.45 134	98.12 50	98.71 11	93.37 104	90.23 250	96.70 175	87.66 118	97.85 302	91.49 187	90.39 290	95.83 273

PMMVS		92.86 187	92.34 185	94.42 221	94.92 308	86.73 285	94.53 332	96.38 273	84.78 355	94.27 154	95.12 264	83.13 193	98.40 230	91.47 188	96.49 179	98.12 177

Vis-MVSNet		95.23 102	94.81 105	96.51 94	97.18 160	91.58 127	98.26 34	98.12 74	94.38 71	94.90 139	98.15 80	82.28 215	98.92 179	91.45 189	98.58 113	99.01 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		94.15 133	93.51 143	96.06 128	98.27 86	89.38 211	95.18 316	98.48 25	85.60 340	93.76 167	97.11 155	83.15 192	99.61 77	91.33 190	98.72 105	99.19 75

OMC-MVS		95.09 106	94.70 109	96.25 120	98.46 73	91.28 138	96.43 237	97.57 159	92.04 153	94.77 143	97.96 95	87.01 135	99.09 158	91.31 191	96.77 171	98.36 161

MG-MVS		95.61 92	95.38 92	96.31 111	98.42 76	90.53 170	96.04 266	97.48 171	93.47 101	95.67 124	98.10 81	89.17 92	99.25 132	91.27 192	98.77 103	99.13 81

ACMM	89.79 8	92.96 181	92.50 181	94.35 223	96.30 231	88.71 232	97.58 124	97.36 197	91.40 173	90.53 244	96.65 179	79.77 259	98.75 198	91.24 193	91.64 267	95.59 287
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WTY-MVS		94.71 120	94.02 127	96.79 78	97.71 133	92.05 109	96.59 230	97.35 198	90.61 206	94.64 145	96.93 162	86.41 142	99.39 119	91.20 194	94.71 217	98.94 102

testing11		91.68 232	90.75 246	94.47 217	96.53 213	86.56 291	95.76 283	94.51 358	91.10 187	91.24 235	93.59 341	68.59 368	98.86 184	91.10 195	94.29 222	98.00 187

tt0805		91.09 266	90.07 278	94.16 234	95.61 261	88.31 243	97.56 127	96.51 267	89.56 235	89.17 289	95.64 239	67.08 381	98.38 236	91.07 196	88.44 308	95.80 275

Anonymous20240529		91.98 221	90.73 248	95.73 151	98.14 102	89.40 210	97.99 62	97.72 140	79.63 397	93.54 171	97.41 139	69.94 356	99.56 93	91.04 197	91.11 278	98.22 167

AUN-MVS		91.76 228	90.75 246	94.81 199	97.00 176	88.57 236	96.65 221	96.49 268	89.63 233	92.15 204	96.12 211	78.66 281	98.50 223	90.83 198	79.18 388	97.36 223

mvsany_test3		83.59 366	82.44 370	87.03 385	83.80 418	73.82 407	93.70 364	90.92 406	86.42 326	82.51 383	90.26 389	46.76 418	95.71 382	90.82 199	76.76 395	91.57 398

CANet_DTU		94.37 126	93.65 135	96.55 88	96.46 222	92.13 107	96.21 259	96.67 258	94.38 71	93.53 172	97.03 160	79.34 266	99.71 54	90.76 200	98.45 119	97.82 201

ab-mvs		93.57 157	92.55 177	96.64 81	97.28 156	91.96 114	95.40 301	97.45 181	89.81 230	93.22 182	96.28 202	79.62 263	99.46 111	90.74 201	93.11 245	98.50 144

CostFormer		91.18 265	90.70 250	92.62 305	94.84 313	81.76 362	94.09 352	94.43 359	84.15 361	92.72 192	93.77 332	79.43 265	98.20 249	90.70 202	92.18 260	97.90 191

Anonymous202405211		92.07 218	90.83 242	95.76 146	98.19 98	88.75 231	97.58 124	95.00 338	86.00 335	93.64 168	97.45 135	66.24 386	99.53 99	90.68 203	92.71 251	99.01 94

testing99		91.62 234	90.72 249	94.32 226	96.48 219	86.11 303	95.81 279	94.76 350	91.55 165	91.75 218	93.44 347	68.55 369	98.82 188	90.43 204	93.69 238	98.04 185

tpmrst		91.44 247	91.32 219	91.79 329	95.15 296	79.20 393	93.42 373	95.37 320	88.55 274	93.49 173	93.67 338	82.49 211	98.27 244	90.41 205	89.34 299	97.90 191

thisisatest0530		93.03 178	92.21 189	95.49 166	97.07 166	89.11 225	97.49 141	92.19 395	90.16 219	94.09 159	96.41 196	76.43 307	99.05 168	90.38 206	95.68 194	98.31 163

UA-Net		95.95 82	95.53 83	97.20 67	97.67 135	92.98 80	97.65 114	98.13 72	94.81 47	96.61 84	98.35 59	88.87 96	99.51 104	90.36 207	97.35 156	99.11 85

UniMVSNet_ETH3D		91.34 255	90.22 271	94.68 207	94.86 312	87.86 260	97.23 170	97.46 176	87.99 289	89.90 264	96.92 165	66.35 384	98.23 246	90.30 208	90.99 281	97.96 188

tttt0517		92.96 181	92.33 186	94.87 196	97.11 164	87.16 276	97.97 69	92.09 396	90.63 204	93.88 165	97.01 161	76.50 304	99.06 167	90.29 209	95.45 199	98.38 159

testing91		91.90 224	91.02 232	94.53 216	96.54 211	86.55 292	95.86 276	95.64 309	91.77 160	91.89 213	93.47 346	69.94 356	98.86 184	90.23 210	93.86 237	98.18 170

FA-MVS(test-final)		93.52 159	92.92 160	95.31 173	96.77 194	88.54 238	94.82 324	96.21 284	89.61 234	94.20 156	95.25 258	83.24 188	99.14 150	90.01 211	96.16 183	98.25 165

IS-MVSNet		94.90 113	94.52 117	96.05 129	97.67 135	90.56 169	98.44 21	96.22 282	93.21 109	93.99 161	97.74 114	85.55 154	98.45 227	89.98 212	97.86 140	99.14 80

miper_enhance_ethall		91.54 242	91.01 233	93.15 285	95.35 278	87.07 278	93.97 354	96.90 239	86.79 321	89.17 289	93.43 350	86.55 139	97.64 323	89.97 213	86.93 322	94.74 345

EI-MVSNet		93.03 178	92.88 162	93.48 272	95.77 256	86.98 279	96.44 235	97.12 212	90.66 202	91.30 230	97.64 124	86.56 138	98.05 272	89.91 214	90.55 287	95.41 295

IterMVS-LS		92.29 208	91.94 198	93.34 277	96.25 232	86.97 280	96.57 233	97.05 222	90.67 200	89.50 279	94.80 277	86.59 137	97.64 323	89.91 214	86.11 331	95.40 298
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		91.21 261	90.56 256	93.14 286	96.09 245	86.80 282	94.41 339	96.58 265	87.80 297	88.58 304	93.99 325	80.85 240	97.62 326	89.87 216	86.93 322	94.99 322

CDS-MVSNet		94.14 136	93.54 139	95.93 138	96.18 236	91.46 133	96.33 249	97.04 224	88.97 257	93.56 169	96.51 191	87.55 122	97.89 300	89.80 217	95.95 186	98.44 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WR-MVS		92.34 204	91.53 212	94.77 204	95.13 298	90.83 160	96.40 243	97.98 107	91.88 157	89.29 285	95.54 245	82.50 210	97.80 309	89.79 218	85.27 341	95.69 284

NR-MVSNet		92.34 204	91.27 223	95.53 163	94.95 305	93.05 77	97.39 152	98.07 86	92.65 136	84.46 365	95.71 234	85.00 160	97.77 313	89.71 219	83.52 368	95.78 277

Anonymous20231211		90.63 286	89.42 301	94.27 231	98.24 90	89.19 223	98.05 57	97.89 115	79.95 395	88.25 314	94.96 267	72.56 335	98.13 255	89.70 220	85.14 343	95.49 288

testdata				95.46 170	98.18 100	88.90 229		97.66 146	82.73 377	97.03 68	98.07 84	90.06 82	98.85 186	89.67 221	98.98 95	98.64 132

Baseline_NR-MVSNet		91.20 262	90.62 252	92.95 292	93.83 348	88.03 254	97.01 188	95.12 334	88.42 278	89.70 270	95.13 263	83.47 184	97.44 342	89.66 222	83.24 370	93.37 373

DPM-MVS		95.69 88	94.92 103	98.01 20	98.08 108	95.71 9	95.27 310	97.62 153	90.43 213	95.55 127	97.07 157	91.72 50	99.50 107	89.62 223	98.94 97	98.82 121

XXY-MVS		92.16 214	91.23 225	94.95 193	94.75 317	90.94 156	97.47 142	97.43 188	89.14 249	88.90 293	96.43 195	79.71 260	98.24 245	89.56 224	87.68 314	95.67 285

miper_ehance_all_eth		91.59 236	91.13 229	92.97 291	95.55 265	86.57 290	94.47 335	96.88 242	87.77 299	88.88 295	94.01 323	86.22 144	97.54 332	89.49 225	86.93 322	94.79 341

WBMVS		90.69 285	89.99 281	92.81 298	96.48 219	85.00 321	95.21 315	96.30 277	89.46 240	89.04 292	94.05 322	72.45 336	97.82 306	89.46 226	87.41 319	95.61 286

XVG-ACMP-BASELINE		90.93 275	90.21 272	93.09 287	94.31 336	85.89 304	95.33 305	97.26 204	91.06 188	89.38 281	95.44 250	68.61 367	98.60 215	89.46 226	91.05 279	94.79 341

thisisatest0515		92.29 208	91.30 221	95.25 175	96.60 203	88.90 229	94.36 341	92.32 394	87.92 291	93.43 175	94.57 288	77.28 299	99.00 172	89.42 228	95.86 189	97.86 197

c3_l		91.38 250	90.89 236	92.88 295	95.58 263	86.30 297	94.68 327	96.84 246	88.17 284	88.83 299	94.23 312	85.65 153	97.47 339	89.36 229	84.63 351	94.89 331

AdaColmap		94.34 127	93.68 134	96.31 111	98.59 69	91.68 122	96.59 230	97.81 131	89.87 225	92.15 204	97.06 158	83.62 183	99.54 97	89.34 230	98.07 134	97.70 206

TranMVSNet+NR-MVSNet		92.50 196	91.63 208	95.14 179	94.76 316	92.07 108	97.53 132	98.11 77	92.90 130	89.56 276	96.12 211	83.16 191	97.60 328	89.30 231	83.20 371	95.75 281

D2MVS		91.30 257	90.95 235	92.35 309	94.71 320	85.52 309	96.18 261	98.21 55	88.89 260	86.60 348	93.82 330	79.92 257	97.95 292	89.29 232	90.95 282	93.56 369

1314		92.81 191	92.03 194	95.14 179	95.33 282	89.52 205	96.04 266	97.44 185	87.72 302	86.25 351	95.33 252	83.84 178	98.79 192	89.26 233	97.05 167	97.11 233

v2v482		91.59 236	90.85 240	93.80 256	93.87 347	88.17 251	96.94 194	96.88 242	89.54 236	89.53 277	94.90 271	81.70 227	98.02 277	89.25 234	85.04 347	95.20 313

114514_t		93.95 143	93.06 156	96.63 83	99.07 37	91.61 124	97.46 144	97.96 109	77.99 403	93.00 185	97.57 129	86.14 148	99.33 123	89.22 235	99.15 83	98.94 102

PAPM_NR		95.01 107	94.59 111	96.26 117	98.89 54	90.68 167	97.24 166	97.73 138	91.80 158	92.93 190	96.62 187	89.13 93	99.14 150	89.21 236	97.78 143	98.97 98

baseline1		92.82 190	91.90 199	95.55 162	97.20 159	90.77 163	97.19 173	94.58 355	92.20 146	92.36 197	96.34 200	84.16 174	98.21 248	89.20 237	83.90 365	97.68 207

IB-MVS	87.33 17	89.91 304	88.28 321	94.79 203	95.26 289	87.70 264	95.12 318	93.95 374	89.35 244	87.03 340	92.49 363	70.74 348	99.19 138	89.18 238	81.37 379	97.49 217
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
HY-MVS	89.66 9	93.87 147	92.95 159	96.63 83	97.10 165	92.49 93	95.64 291	96.64 259	89.05 253	93.00 185	95.79 230	85.77 152	99.45 113	89.16 239	94.35 219	97.96 188

V42		91.58 238	90.87 237	93.73 259	94.05 342	88.50 240	97.32 160	96.97 230	88.80 267	89.71 269	94.33 304	82.54 209	98.05 272	89.01 240	85.07 345	94.64 349

sd_testset		93.10 174	92.45 183	95.05 183	98.09 105	89.21 220	96.89 197	97.64 150	93.18 114	91.79 216	97.28 144	75.35 316	98.65 210	88.99 241	92.84 248	97.28 228

OurMVSNet-221017-0		90.51 290	90.19 273	91.44 338	93.41 362	81.25 365	96.98 191	96.28 278	91.68 163	86.55 349	96.30 201	74.20 325	97.98 281	88.96 242	87.40 320	95.09 318

API-MVS		94.84 116	94.49 118	95.90 139	97.90 123	92.00 111	97.80 94	97.48 171	89.19 248	94.81 141	96.71 173	88.84 97	99.17 143	88.91 243	98.76 104	96.53 247

test-LLR		91.42 248	91.19 227	92.12 317	94.59 324	80.66 371	94.29 346	92.98 386	91.11 185	90.76 242	92.37 366	79.02 274	98.07 269	88.81 244	96.74 172	97.63 208

test-mter		90.19 300	89.54 298	92.12 317	94.59 324	80.66 371	94.29 346	92.98 386	87.68 303	90.76 242	92.37 366	67.67 373	98.07 269	88.81 244	96.74 172	97.63 208

eth_miper_zixun_eth		91.02 270	90.59 254	92.34 311	95.33 282	84.35 330	94.10 351	96.90 239	88.56 273	88.84 298	94.33 304	84.08 175	97.60 328	88.77 246	84.37 358	95.06 320

myMVS_eth3d28		91.52 243	90.97 234	93.17 284	96.91 179	83.24 345	95.61 292	94.96 342	92.24 143	91.98 210	93.28 351	69.31 361	98.40 230	88.71 247	95.68 194	97.88 193

TAMVS		94.01 142	93.46 145	95.64 155	96.16 238	90.45 173	96.71 214	96.89 241	89.27 246	93.46 174	96.92 165	87.29 131	97.94 293	88.70 248	95.74 191	98.53 140

Patchmatch-RL test		87.38 337	86.24 341	90.81 352	88.74 408	78.40 397	88.12 416	93.17 384	87.11 316	82.17 385	89.29 397	81.95 222	95.60 386	88.64 249	77.02 393	98.41 156

baseline2		91.63 233	90.86 238	93.94 249	94.33 334	86.32 296	95.92 273	91.64 400	89.37 243	86.94 344	94.69 281	81.62 228	98.69 206	88.64 249	94.57 218	96.81 242

TESTMET0.1,1		90.06 302	89.42 301	91.97 320	94.41 332	80.62 373	94.29 346	91.97 398	87.28 313	90.44 246	92.47 365	68.79 365	97.67 320	88.50 251	96.60 177	97.61 212

Vis-MVSNet (Re-imp)		94.15 133	93.88 130	94.95 193	97.61 143	87.92 257	98.10 51	95.80 299	92.22 144	93.02 184	97.45 135	84.53 166	97.91 299	88.24 252	97.97 137	99.02 91

1112_ss		93.37 163	92.42 184	96.21 121	97.05 171	90.99 153	96.31 251	96.72 251	86.87 320	89.83 267	96.69 177	86.51 140	99.14 150	88.12 253	93.67 239	98.50 144

UBG		91.55 240	90.76 244	93.94 249	96.52 215	85.06 320	95.22 313	94.54 356	90.47 212	91.98 210	92.71 358	72.02 337	98.74 200	88.10 254	95.26 203	98.01 186

CVMVSNet		91.23 260	91.75 204	89.67 368	95.77 256	74.69 404	96.44 235	94.88 346	85.81 337	92.18 203	97.64 124	79.07 271	95.58 387	88.06 255	95.86 189	98.74 125

MAR-MVS		94.22 129	93.46 145	96.51 94	98.00 114	92.19 106	97.67 110	97.47 174	88.13 288	93.00 185	95.84 224	84.86 162	99.51 104	87.99 256	98.17 131	97.83 200
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
原ACMM1				96.38 107	98.59 69	91.09 152		97.89 115	87.41 309	95.22 134	97.68 117	90.25 80	99.54 97	87.95 257	99.12 87	98.49 146

CP-MVSNet		91.89 225	91.24 224	93.82 255	95.05 301	88.57 236	97.82 91	98.19 62	91.70 162	88.21 315	95.76 232	81.96 221	97.52 336	87.86 258	84.65 350	95.37 301

v148		90.99 271	90.38 260	92.81 298	93.83 348	85.80 305	96.78 208	96.68 256	89.45 241	88.75 301	93.93 327	82.96 200	97.82 306	87.83 259	83.25 369	94.80 339

v1144		91.37 252	90.60 253	93.68 264	93.89 346	88.23 248	96.84 202	97.03 226	88.37 279	89.69 271	94.39 299	82.04 219	97.98 281	87.80 260	85.37 338	94.84 333

DIV-MVS_self_test		90.97 273	90.33 261	92.88 295	95.36 277	86.19 301	94.46 337	96.63 262	87.82 295	88.18 316	94.23 312	82.99 197	97.53 334	87.72 261	85.57 335	94.93 327

gm-plane-assit					93.22 366	78.89 396			84.82 354		93.52 343		98.64 211	87.72 261

GeoE		93.89 146	93.28 152	95.72 152	96.96 178	89.75 195	98.24 38	96.92 238	89.47 239	92.12 206	97.21 150	84.42 168	98.39 235	87.71 263	96.50 178	99.01 94

cl____		90.96 274	90.32 262	92.89 294	95.37 276	86.21 300	94.46 337	96.64 259	87.82 295	88.15 317	94.18 315	82.98 198	97.54 332	87.70 264	85.59 334	94.92 329

pmmvs4		90.93 275	89.85 286	94.17 233	93.34 364	90.79 162	94.60 329	96.02 289	84.62 356	87.45 328	95.15 261	81.88 224	97.45 341	87.70 264	87.87 312	94.27 361

Test_1112_low_res		92.84 189	91.84 201	95.85 143	97.04 172	89.97 189	95.53 296	96.64 259	85.38 343	89.65 273	95.18 260	85.86 150	99.10 155	87.70 264	93.58 244	98.49 146

无先验							95.79 281	97.87 119	83.87 366				99.65 66	87.68 267		98.89 113

Fast-Effi-MVS+		93.46 160	92.75 168	95.59 159	96.77 194	90.03 183	96.81 205	97.13 211	88.19 283	91.30 230	94.27 309	86.21 145	98.63 212	87.66 268	96.46 181	98.12 177

CNLPA		94.28 128	93.53 140	96.52 90	98.38 81	92.55 91	96.59 230	96.88 242	90.13 221	91.91 212	97.24 148	85.21 157	99.09 158	87.64 269	97.83 141	97.92 190

v8		91.29 259	90.53 257	93.57 269	94.15 338	88.12 253	97.34 157	97.06 221	88.99 255	88.32 310	94.26 311	83.08 194	98.01 278	87.62 270	83.92 364	94.57 350

pmmvs5		89.86 309	88.87 314	92.82 297	92.86 373	86.23 299	96.26 254	95.39 318	84.24 360	87.12 336	94.51 292	74.27 324	97.36 348	87.61 271	87.57 315	94.86 332

Fast-Effi-MVS+-dtu		92.29 208	91.99 196	93.21 283	95.27 286	85.52 309	97.03 183	96.63 262	92.09 151	89.11 291	95.14 262	80.33 249	98.08 265	87.54 272	94.74 215	96.03 267

OpenMVS	89.19 12	92.86 187	91.68 207	96.40 104	95.34 279	92.73 86	98.27 32	98.12 74	84.86 353	85.78 354	97.75 113	78.89 279	99.74 47	87.50 273	98.65 108	96.73 244

miper_lstm_enhance		90.50 291	90.06 279	91.83 326	95.33 282	83.74 338	93.86 360	96.70 255	87.56 306	87.79 322	93.81 331	83.45 186	96.92 363	87.39 274	84.62 352	94.82 336

IterMVS-SCA-FT		90.31 293	89.81 288	91.82 327	95.52 266	84.20 333	94.30 345	96.15 286	90.61 206	87.39 331	94.27 309	75.80 311	96.44 371	87.34 275	86.88 326	94.82 336

PLC	91.00 6	94.11 137	93.43 147	96.13 125	98.58 71	91.15 151	96.69 217	97.39 192	87.29 312	91.37 226	96.71 173	88.39 105	99.52 103	87.33 276	97.13 166	97.73 204
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		90.25 296	89.74 293	91.76 332	93.92 344	79.73 386	93.98 353	93.54 380	88.28 281	91.99 209	93.25 352	77.51 298	97.44 342	87.30 277	87.94 311	98.12 177

GA-MVS		91.38 250	90.31 263	94.59 209	94.65 322	87.62 265	94.34 342	96.19 285	90.73 196	90.35 248	93.83 328	71.84 339	97.96 288	87.22 278	93.61 242	98.21 168

BH-untuned		92.94 183	92.62 174	93.92 252	97.22 157	86.16 302	96.40 243	96.25 281	90.06 222	89.79 268	96.17 208	83.19 190	98.35 238	87.19 279	97.27 161	97.24 230

v144192		91.06 268	90.28 265	93.39 275	93.66 354	87.23 273	96.83 203	97.07 219	87.43 308	89.69 271	94.28 308	81.48 229	98.00 279	87.18 280	84.92 349	94.93 327

RPSCF		90.75 280	90.86 238	90.42 359	96.84 184	76.29 402	95.61 292	96.34 274	83.89 364	91.38 225	97.87 101	76.45 305	98.78 193	87.16 281	92.23 257	96.20 256

test_f		80.57 375	79.62 377	83.41 392	83.38 421	67.80 419	93.57 371	93.72 378	80.80 392	77.91 402	87.63 408	33.40 424	92.08 412	87.14 282	79.04 390	90.34 407

PS-CasMVS		91.55 240	90.84 241	93.69 263	94.96 304	88.28 245	97.84 86	98.24 51	91.46 169	88.04 319	95.80 227	79.67 261	97.48 338	87.02 283	84.54 356	95.31 305

pm-mvs1		90.72 282	89.65 296	93.96 246	94.29 337	89.63 196	97.79 95	96.82 247	89.07 251	86.12 353	95.48 249	78.61 282	97.78 311	86.97 284	81.67 377	94.46 352

IterMVS		90.15 301	89.67 294	91.61 334	95.48 268	83.72 339	94.33 343	96.12 287	89.99 223	87.31 334	94.15 317	75.78 313	96.27 374	86.97 284	86.89 325	94.83 334
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		93.58 156	92.98 158	95.37 172	98.40 78	88.98 227	97.18 174	97.29 203	87.75 301	90.49 245	97.10 156	85.21 157	99.50 107	86.70 286	96.72 174	97.63 208

PVSNet	86.66 18	92.24 211	91.74 206	93.73 259	97.77 129	83.69 341	92.88 383	96.72 251	87.91 292	93.00 185	94.86 273	78.51 283	99.05 168	86.53 287	97.45 153	98.47 149

v1192		91.07 267	90.23 269	93.58 268	93.70 351	87.82 262	96.73 211	97.07 219	87.77 299	89.58 274	94.32 306	80.90 239	97.97 284	86.52 288	85.48 336	94.95 323

新几何1				97.32 57	98.60 68	93.59 59		97.75 135	81.58 386	95.75 120	97.85 104	90.04 83	99.67 64	86.50 289	99.13 85	98.69 129

v10		91.04 269	90.23 269	93.49 271	94.12 339	88.16 252	97.32 160	97.08 217	88.26 282	88.29 312	94.22 314	82.17 218	97.97 284	86.45 290	84.12 360	94.33 357

v1921920		90.85 277	90.03 280	93.29 279	93.55 355	86.96 281	96.74 210	97.04 224	87.36 310	89.52 278	94.34 303	80.23 251	97.97 284	86.27 291	85.21 342	94.94 325

MDTV_nov1_ep13_2view						70.35 413	93.10 380		83.88 365	93.55 170		82.47 212		86.25 292		98.38 159

test_post1							92.81 385				16.58 433	80.53 244	97.68 319	86.20 293

SCA		91.84 226	91.18 228	93.83 254	95.59 262	84.95 324	94.72 326	95.58 312	90.82 192	92.25 202	93.69 335	75.80 311	98.10 260	86.20 293	95.98 185	98.45 151

PAPR		94.18 130	93.42 149	96.48 97	97.64 139	91.42 135	95.55 294	97.71 144	88.99 255	92.34 200	95.82 226	89.19 91	99.11 153	86.14 295	97.38 154	98.90 109

GBi-Net		91.35 253	90.27 266	94.59 209	96.51 216	91.18 147	97.50 135	96.93 234	88.82 264	89.35 282	94.51 292	73.87 326	97.29 351	86.12 296	88.82 302	95.31 305

test1		91.35 253	90.27 266	94.59 209	96.51 216	91.18 147	97.50 135	96.93 234	88.82 264	89.35 282	94.51 292	73.87 326	97.29 351	86.12 296	88.82 302	95.31 305

FMVSNet3		91.78 227	90.69 251	95.03 185	96.53 213	92.27 101	97.02 185	96.93 234	89.79 231	89.35 282	94.65 285	77.01 300	97.47 339	86.12 296	88.82 302	95.35 302

EPMVS		90.70 283	89.81 288	93.37 276	94.73 319	84.21 332	93.67 367	88.02 415	89.50 238	92.38 196	93.49 344	77.82 296	97.78 311	86.03 299	92.68 252	98.11 180

MVS		91.71 229	90.44 258	95.51 164	95.20 292	91.59 126	96.04 266	97.45 181	73.44 413	87.36 332	95.60 241	85.42 155	99.10 155	85.97 300	97.46 149	95.83 273

testdata2													99.67 64	85.96 301

K. test v3		87.64 336	86.75 338	90.32 361	93.02 370	79.48 391	96.61 227	92.08 397	90.66 202	80.25 394	94.09 320	67.21 377	96.65 369	85.96 301	80.83 381	94.83 334

WR-MVS_H		92.00 220	91.35 217	93.95 247	95.09 300	89.47 206	98.04 58	98.68 13	91.46 169	88.34 309	94.68 282	85.86 150	97.56 330	85.77 303	84.24 359	94.82 336

gg-mvs-nofinetune		87.82 333	85.61 346	94.44 219	94.46 329	89.27 219	91.21 398	84.61 424	80.88 389	89.89 266	74.98 420	71.50 341	97.53 334	85.75 304	97.21 163	96.51 248

tpm2		89.96 303	89.21 306	92.23 316	94.91 310	81.25 365	93.78 362	94.42 360	80.62 393	91.56 221	93.44 347	76.44 306	97.94 293	85.60 305	92.08 264	97.49 217

v1240		90.70 283	89.85 286	93.23 281	93.51 358	86.80 282	96.61 227	97.02 228	87.16 315	89.58 274	94.31 307	79.55 264	97.98 281	85.52 306	85.44 337	94.90 330

PEN-MVS		91.20 262	90.44 258	93.48 272	94.49 328	87.91 259	97.76 97	98.18 64	91.29 175	87.78 323	95.74 233	80.35 248	97.33 349	85.46 307	82.96 372	95.19 316

QAPM		93.45 161	92.27 187	96.98 77	96.77 194	92.62 88	98.39 24	98.12 74	84.50 358	88.27 313	97.77 112	82.39 214	99.81 30	85.40 308	98.81 101	98.51 143

SSC-MVS3.2		89.74 312	89.26 305	91.19 345	95.16 293	80.29 379	94.53 332	97.03 226	91.79 159	88.86 296	94.10 318	69.94 356	97.82 306	85.29 309	86.66 327	95.45 293

EU-MVSNet		88.72 325	88.90 313	88.20 378	93.15 368	74.21 406	96.63 226	94.22 369	85.18 347	87.32 333	95.97 217	76.16 308	94.98 393	85.27 310	86.17 329	95.41 295

BH-w/o		92.14 216	91.75 204	93.31 278	96.99 177	85.73 306	95.67 286	95.69 305	88.73 269	89.26 287	94.82 276	82.97 199	98.07 269	85.26 311	96.32 182	96.13 263

FMVSNet2		91.31 256	90.08 275	94.99 187	96.51 216	92.21 103	97.41 147	96.95 232	88.82 264	88.62 302	94.75 279	73.87 326	97.42 344	85.20 312	88.55 307	95.35 302

PM-MVS		83.48 367	81.86 373	88.31 377	87.83 412	77.59 399	93.43 372	91.75 399	86.91 318	80.63 390	89.91 393	44.42 419	95.84 380	85.17 313	76.73 396	91.50 400

LF4IMVS		87.94 332	87.25 329	89.98 365	92.38 385	80.05 384	94.38 340	95.25 328	87.59 305	84.34 366	94.74 280	64.31 393	97.66 322	84.83 314	87.45 316	92.23 391

PatchmatchNet		91.91 223	91.35 217	93.59 267	95.38 274	84.11 334	93.15 378	95.39 318	89.54 236	92.10 207	93.68 337	82.82 203	98.13 255	84.81 315	95.32 201	98.52 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		87.81 334	86.19 342	92.69 303	91.32 390	86.30 297	97.34 157	96.41 272	80.59 394	84.05 374	94.37 301	67.37 376	97.67 320	84.75 316	79.51 387	94.09 364

v7n		90.76 279	89.86 285	93.45 274	93.54 356	87.60 266	97.70 109	97.37 195	88.85 261	87.65 325	94.08 321	81.08 234	98.10 260	84.68 317	83.79 366	94.66 348

SixPastTwentyTwo		89.15 318	88.54 318	90.98 347	93.49 359	80.28 380	96.70 215	94.70 351	90.78 193	84.15 370	95.57 242	71.78 340	97.71 318	84.63 318	85.07 345	94.94 325

TDRefinement		86.53 345	84.76 357	91.85 325	82.23 423	84.25 331	96.38 245	95.35 321	84.97 352	84.09 372	94.94 268	65.76 390	98.34 241	84.60 319	74.52 401	92.97 376

ACMH	87.59 16	90.53 288	89.42 301	93.87 253	96.21 233	87.92 257	97.24 166	96.94 233	88.45 277	83.91 375	96.27 203	71.92 338	98.62 214	84.43 320	89.43 298	95.05 321
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	87.92 14	90.20 299	89.18 307	93.25 280	96.48 219	86.45 294	96.99 190	96.68 256	88.83 263	84.79 364	96.22 205	70.16 353	98.53 221	84.42 321	88.04 310	94.77 344

test_vis3_rt		72.73 381	70.55 384	79.27 395	80.02 424	68.13 418	93.92 358	74.30 432	76.90 406	58.99 423	73.58 423	20.29 432	95.37 390	84.16 322	72.80 406	74.31 420

FE-MVS		92.05 219	91.05 231	95.08 182	96.83 186	87.93 256	93.91 359	95.70 303	86.30 329	94.15 158	94.97 266	76.59 303	99.21 136	84.10 323	96.86 168	98.09 181

MS-PatchMatch		90.27 295	89.77 290	91.78 330	94.33 334	84.72 327	95.55 294	96.73 250	86.17 333	86.36 350	95.28 255	71.28 343	97.80 309	84.09 324	98.14 132	92.81 379

PatchMatch-RL		92.90 185	92.02 195	95.56 160	98.19 98	90.80 161	95.27 310	97.18 207	87.96 290	91.86 215	95.68 237	80.44 246	98.99 173	84.01 325	97.54 148	96.89 240

lessismore_v0				90.45 358	91.96 388	79.09 395		87.19 418		80.32 393	94.39 299	66.31 385	97.55 331	84.00 326	76.84 394	94.70 346

UWE-MVS		89.91 304	89.48 300	91.21 342	95.88 249	78.23 398	94.91 323	90.26 408	89.11 250	92.35 199	94.52 291	68.76 366	97.96 288	83.95 327	95.59 197	97.42 221

CMPMVS	62.92 21	85.62 359	84.92 355	87.74 381	89.14 403	73.12 411	94.17 349	96.80 248	73.98 410	73.65 409	94.93 269	66.36 383	97.61 327	83.95 327	91.28 275	92.48 387
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVP-Stereo		90.74 281	90.08 275	92.71 302	93.19 367	88.20 249	95.86 276	96.27 279	86.07 334	84.86 363	94.76 278	77.84 295	97.75 315	83.88 329	98.01 136	92.17 394
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LS3D		93.57 157	92.61 175	96.47 98	97.59 145	91.61 124	97.67 110	97.72 140	85.17 348	90.29 249	98.34 62	84.60 164	99.73 49	83.85 330	98.27 126	98.06 184

DTE-MVSNet		90.56 287	89.75 292	93.01 289	93.95 343	87.25 271	97.64 118	97.65 148	90.74 195	87.12 336	95.68 237	79.97 256	97.00 361	83.33 331	81.66 378	94.78 343

BH-RMVSNet		92.72 194	91.97 197	94.97 191	97.16 161	87.99 255	96.15 262	95.60 310	90.62 205	91.87 214	97.15 154	78.41 285	98.57 219	83.16 332	97.60 147	98.36 161

pmmvs-eth3d		86.22 351	84.45 359	91.53 335	88.34 410	87.25 271	94.47 335	95.01 337	83.47 372	79.51 397	89.61 395	69.75 359	95.71 382	83.13 333	76.73 396	91.64 396

FMVSNet1		89.88 307	88.31 320	94.59 209	95.41 272	91.18 147	97.50 135	96.93 234	86.62 323	87.41 330	94.51 292	65.94 389	97.29 351	83.04 334	87.43 317	95.31 305

testing222		90.31 293	88.96 311	94.35 223	96.54 211	87.29 268	95.50 297	93.84 377	90.97 190	91.75 218	92.96 355	62.18 401	98.00 279	82.86 335	94.08 230	97.76 203

MDTV_nov1_ep13			90.76 244		95.22 290	80.33 377	93.03 381	95.28 325	88.14 287	92.84 191	93.83 328	81.34 230	98.08 265	82.86 335	94.34 220

TR-MVS		91.48 246	90.59 254	94.16 234	96.40 225	87.33 267	95.67 286	95.34 324	87.68 303	91.46 224	95.52 246	76.77 302	98.35 238	82.85 337	93.61 242	96.79 243

dmvs_re		90.21 298	89.50 299	92.35 309	95.47 271	85.15 317	95.70 285	94.37 364	90.94 191	88.42 306	93.57 342	74.63 321	95.67 384	82.80 338	89.57 297	96.22 255

JIA-IIPM		88.26 330	87.04 334	91.91 322	93.52 357	81.42 364	89.38 410	94.38 363	80.84 390	90.93 239	80.74 417	79.22 268	97.92 296	82.76 339	91.62 268	96.38 253

PVSNet_0	82.17 19	85.46 360	83.64 363	90.92 348	95.27 286	79.49 390	90.55 402	95.60 310	83.76 368	83.00 382	89.95 392	71.09 344	97.97 284	82.75 340	60.79 422	95.31 305

ambc				86.56 387	83.60 420	70.00 414	85.69 418	94.97 340		80.60 391	88.45 401	37.42 422	96.84 366	82.69 341	75.44 400	92.86 378

USDC		88.94 320	87.83 325	92.27 313	94.66 321	84.96 323	93.86 360	95.90 293	87.34 311	83.40 377	95.56 243	67.43 375	98.19 251	82.64 342	89.67 296	93.66 368

ITE_SJBPF				92.43 307	95.34 279	85.37 314		95.92 291	91.47 168	87.75 324	96.39 198	71.00 345	97.96 288	82.36 343	89.86 294	93.97 365

UnsupCasMVSNet_eth		85.99 354	84.45 359	90.62 356	89.97 398	82.40 357	93.62 369	97.37 195	89.86 226	78.59 400	92.37 366	65.25 392	95.35 391	82.27 344	70.75 408	94.10 362

GG-mvs-BLEND				93.62 265	93.69 352	89.20 221	92.39 390	83.33 426		87.98 321	89.84 394	71.00 345	96.87 365	82.08 345	95.40 200	94.80 339

thres600view7		92.49 198	91.60 209	95.18 177	97.91 122	89.47 206	97.65 114	94.66 352	92.18 150	93.33 177	94.91 270	78.06 292	99.10 155	81.61 346	94.06 234	96.98 235

LTVRE_ROB	88.41 13	90.99 271	89.92 284	94.19 232	96.18 236	89.55 202	96.31 251	97.09 216	87.88 293	85.67 355	95.91 221	78.79 280	98.57 219	81.50 347	89.98 292	94.44 354
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
tpmvs		89.83 310	89.15 308	91.89 324	94.92 308	80.30 378	93.11 379	95.46 317	86.28 330	88.08 318	92.65 359	80.44 246	98.52 222	81.47 348	89.92 293	96.84 241

thres100view900		92.43 199	91.58 210	94.98 189	97.92 121	89.37 212	97.71 106	94.66 352	92.20 146	93.31 178	94.90 271	78.06 292	99.08 161	81.40 349	94.08 230	96.48 250

tfpn200view9		92.38 202	91.52 213	94.95 193	97.85 125	89.29 216	97.41 147	94.88 346	92.19 148	93.27 180	94.46 297	78.17 288	99.08 161	81.40 349	94.08 230	96.48 250

thres400		92.42 200	91.52 213	95.12 181	97.85 125	89.29 216	97.41 147	94.88 346	92.19 148	93.27 180	94.46 297	78.17 288	99.08 161	81.40 349	94.08 230	96.98 235

mvs5depth		86.53 345	85.08 352	90.87 349	88.74 408	82.52 353	91.91 392	94.23 368	86.35 328	87.11 338	93.70 334	66.52 382	97.76 314	81.37 352	75.80 398	92.31 390

ETVMVS		90.52 289	89.14 309	94.67 208	96.81 190	87.85 261	95.91 274	93.97 373	89.71 232	92.34 200	92.48 364	65.41 391	97.96 288	81.37 352	94.27 223	98.21 168

DP-MVS		92.76 192	91.51 215	96.52 90	98.77 56	90.99 153	97.38 154	96.08 288	82.38 379	89.29 285	97.87 101	83.77 179	99.69 60	81.37 352	96.69 175	98.89 113

thres200		92.23 212	91.39 216	94.75 206	97.61 143	89.03 226	96.60 229	95.09 335	92.08 152	93.28 179	94.00 324	78.39 286	99.04 171	81.26 355	94.18 226	96.19 257

CR-MVSNet		90.82 278	89.77 290	93.95 247	94.45 330	87.19 274	90.23 404	95.68 307	86.89 319	92.40 194	92.36 369	80.91 237	97.05 357	81.09 356	93.95 235	97.60 213

ttmdpeth		85.91 356	84.76 357	89.36 372	89.14 403	80.25 381	95.66 289	93.16 385	83.77 367	83.39 378	95.26 257	66.24 386	95.26 392	80.65 357	75.57 399	92.57 383

MSDG		91.42 248	90.24 268	94.96 192	97.15 163	88.91 228	93.69 366	96.32 275	85.72 339	86.93 345	96.47 193	80.24 250	98.98 174	80.57 358	95.05 208	96.98 235

dp		88.90 322	88.26 322	90.81 352	94.58 326	76.62 400	92.85 384	94.93 343	85.12 349	90.07 262	93.07 353	75.81 310	98.12 258	80.53 359	87.42 318	97.71 205

tpm cat1		88.36 328	87.21 331	91.81 328	95.13 298	80.55 374	92.58 387	95.70 303	74.97 409	87.45 328	91.96 376	78.01 294	98.17 253	80.39 360	88.74 305	96.72 245

KD-MVS_self_test		85.95 355	84.95 354	88.96 375	89.55 402	79.11 394	95.13 317	96.42 271	85.91 336	84.07 373	90.48 387	70.03 355	94.82 394	80.04 361	72.94 405	92.94 377

AllTest		90.23 297	88.98 310	93.98 243	97.94 119	86.64 286	96.51 234	95.54 314	85.38 343	85.49 357	96.77 171	70.28 351	99.15 147	80.02 362	92.87 246	96.15 261

TestCases				93.98 243	97.94 119	86.64 286		95.54 314	85.38 343	85.49 357	96.77 171	70.28 351	99.15 147	80.02 362	92.87 246	96.15 261

ADS-MVSNet2		89.45 315	88.59 317	92.03 319	95.86 250	82.26 358	90.93 399	94.32 367	83.23 374	91.28 233	91.81 378	79.01 276	95.99 376	79.52 364	91.39 273	97.84 198

ADS-MVSNet		89.89 306	88.68 316	93.53 270	95.86 250	84.89 325	90.93 399	95.07 336	83.23 374	91.28 233	91.81 378	79.01 276	97.85 302	79.52 364	91.39 273	97.84 198

our_test_3		88.78 324	87.98 324	91.20 344	92.45 383	82.53 352	93.61 370	95.69 305	85.77 338	84.88 362	93.71 333	79.99 255	96.78 368	79.47 366	86.24 328	94.28 360

EPNet_dtu		91.71 229	91.28 222	92.99 290	93.76 350	83.71 340	96.69 217	95.28 325	93.15 116	87.02 341	95.95 219	83.37 187	97.38 347	79.46 367	96.84 169	97.88 193
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		88.94 320	87.56 326	93.08 288	94.35 333	88.45 242	97.73 101	95.23 329	87.47 307	84.26 368	95.29 253	79.86 258	97.33 349	79.44 368	74.44 402	93.45 372

EG-PatchMatch MVS		87.02 342	85.44 347	91.76 332	92.67 377	85.00 321	96.08 265	96.45 270	83.41 373	79.52 396	93.49 344	57.10 407	97.72 317	79.34 369	90.87 284	92.56 384

Patchmtry		88.64 326	87.25 329	92.78 300	94.09 340	86.64 286	89.82 408	95.68 307	80.81 391	87.63 326	92.36 369	80.91 237	97.03 358	78.86 370	85.12 344	94.67 347

FMVSNet5		87.29 338	85.79 345	91.78 330	94.80 315	87.28 269	95.49 298	95.28 325	84.09 362	83.85 376	91.82 377	62.95 397	94.17 399	78.48 371	85.34 340	93.91 366

COLMAP_ROB	87.81 15	90.40 292	89.28 304	93.79 257	97.95 118	87.13 277	96.92 195	95.89 295	82.83 376	86.88 347	97.18 151	73.77 329	99.29 130	78.44 372	93.62 241	94.95 323
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		86.42 348	85.44 347	89.34 373	90.33 395	79.79 385	96.73 211	95.92 291	83.71 369	83.25 379	91.36 382	63.92 394	96.01 375	78.39 373	85.36 339	92.22 392

test0.0.03 1		89.37 317	88.70 315	91.41 339	92.47 382	85.63 307	95.22 313	92.70 391	91.11 185	86.91 346	93.65 339	79.02 274	93.19 410	78.00 374	89.18 300	95.41 295

MIMVSNet		88.50 327	86.76 337	93.72 261	94.84 313	87.77 263	91.39 394	94.05 370	86.41 327	87.99 320	92.59 362	63.27 395	95.82 381	77.44 375	92.84 248	97.57 215

MDA-MVSNet_test_wron		85.87 357	84.23 361	90.80 354	92.38 385	82.57 351	93.17 376	95.15 332	82.15 380	67.65 415	92.33 372	78.20 287	95.51 388	77.33 376	79.74 384	94.31 359

YYNet1		85.87 357	84.23 361	90.78 355	92.38 385	82.46 356	93.17 376	95.14 333	82.12 381	67.69 413	92.36 369	78.16 290	95.50 389	77.31 377	79.73 385	94.39 355

UnsupCasMVSNet_bld		82.13 373	79.46 378	90.14 363	88.00 411	82.47 355	90.89 401	96.62 264	78.94 400	75.61 404	84.40 415	56.63 408	96.31 373	77.30 378	66.77 416	91.63 397

KD-MVS_2432*1600		84.81 363	82.64 367	91.31 340	91.07 392	85.34 315	91.22 396	95.75 301	85.56 341	83.09 380	90.21 390	67.21 377	95.89 377	77.18 379	62.48 420	92.69 380

miper_refine_blended		84.81 363	82.64 367	91.31 340	91.07 392	85.34 315	91.22 396	95.75 301	85.56 341	83.09 380	90.21 390	67.21 377	95.89 377	77.18 379	62.48 420	92.69 380

PCF-MVS	89.48 11	91.56 239	89.95 282	96.36 109	96.60 203	92.52 92	92.51 388	97.26 204	79.41 398	88.90 293	96.56 189	84.04 177	99.55 95	77.01 381	97.30 160	97.01 234
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		89.88 307	89.56 297	90.82 351	94.57 327	83.06 347	95.65 290	92.85 388	87.86 294	90.83 241	94.10 318	79.66 262	96.88 364	76.34 382	94.19 225	92.54 385

testgi		87.97 331	87.21 331	90.24 362	92.86 373	80.76 369	96.67 220	94.97 340	91.74 161	85.52 356	95.83 225	62.66 399	94.47 397	76.25 383	88.36 309	95.48 289

TinyColmap		86.82 343	85.35 350	91.21 342	94.91 310	82.99 348	93.94 356	94.02 372	83.58 370	81.56 386	94.68 282	62.34 400	98.13 255	75.78 384	87.35 321	92.52 386

ppachtmachnet_test		88.35 329	87.29 328	91.53 335	92.45 383	83.57 342	93.75 363	95.97 290	84.28 359	85.32 360	94.18 315	79.00 278	96.93 362	75.71 385	84.99 348	94.10 362

PAPM		91.52 243	90.30 264	95.20 176	95.30 285	89.83 193	93.38 374	96.85 245	86.26 331	88.59 303	95.80 227	84.88 161	98.15 254	75.67 386	95.93 187	97.63 208

WAC-MVS						79.53 388								75.56 387

myMVS_eth3d		87.18 339	86.38 340	89.58 369	95.16 293	79.53 388	95.00 320	93.93 375	88.55 274	86.96 342	91.99 374	56.23 409	94.00 401	75.47 388	94.11 227	95.20 313

CL-MVSNet_self_test		86.31 350	85.15 351	89.80 367	88.83 406	81.74 363	93.93 357	96.22 282	86.67 322	85.03 361	90.80 385	78.09 291	94.50 395	74.92 389	71.86 407	93.15 375

tfpnnormal		89.70 313	88.40 319	93.60 266	95.15 296	90.10 182	97.56 127	98.16 68	87.28 313	86.16 352	94.63 286	77.57 297	98.05 272	74.48 390	84.59 354	92.65 382

DSMNet-mixed		86.34 349	86.12 344	87.00 386	89.88 399	70.43 412	94.93 322	90.08 409	77.97 404	85.42 359	92.78 357	74.44 323	93.96 403	74.43 391	95.14 204	96.62 246

Patchmatch-test		89.42 316	87.99 323	93.70 262	95.27 286	85.11 318	88.98 411	94.37 364	81.11 387	87.10 339	93.69 335	82.28 215	97.50 337	74.37 392	94.76 213	98.48 148

LCM-MVSNet		72.55 382	69.39 386	82.03 393	70.81 433	65.42 422	90.12 406	94.36 366	55.02 423	65.88 417	81.72 416	24.16 431	89.96 414	74.32 393	68.10 414	90.71 406

new-patchmatchnet		83.18 369	81.87 372	87.11 384	86.88 414	75.99 403	93.70 364	95.18 331	85.02 351	77.30 403	88.40 402	65.99 388	93.88 404	74.19 394	70.18 409	91.47 401

MVStest1		82.38 372	80.04 376	89.37 371	87.63 413	82.83 349	95.03 319	93.37 383	73.90 411	73.50 410	94.35 302	62.89 398	93.25 409	73.80 395	65.92 417	92.04 395

testing3		87.67 335	86.88 336	90.05 364	96.14 241	80.71 370	97.10 180	92.85 388	90.15 220	87.54 327	94.55 289	55.70 410	94.10 400	73.77 396	94.10 229	95.35 302

MDA-MVSNet-bldmvs		85.00 361	82.95 366	91.17 346	93.13 369	83.33 343	94.56 331	95.00 338	84.57 357	65.13 419	92.65 359	70.45 350	95.85 379	73.57 397	77.49 392	94.33 357

pmmvs3		79.97 376	77.50 381	87.39 383	82.80 422	79.38 392	92.70 386	90.75 407	70.69 414	78.66 399	87.47 410	51.34 414	93.40 406	73.39 398	69.65 410	89.38 409

test_method		66.11 390	64.89 392	69.79 407	72.62 431	35.23 439	65.19 426	92.83 390	20.35 429	65.20 418	88.08 406	43.14 420	82.70 424	73.12 399	63.46 419	91.45 402

PatchT		88.87 323	87.42 327	93.22 282	94.08 341	85.10 319	89.51 409	94.64 354	81.92 382	92.36 197	88.15 405	80.05 254	97.01 360	72.43 400	93.65 240	97.54 216

Anonymous20231206		87.09 341	86.14 343	89.93 366	91.22 391	80.35 376	96.11 263	95.35 321	83.57 371	84.16 369	93.02 354	73.54 331	95.61 385	72.16 401	86.14 330	93.84 367

MVS-HIRNet		82.47 371	81.21 374	86.26 388	95.38 274	69.21 415	88.96 412	89.49 410	66.28 417	80.79 389	74.08 422	68.48 370	97.39 346	71.93 402	95.47 198	92.18 393

new_pmnet		82.89 370	81.12 375	88.18 379	89.63 400	80.18 382	91.77 393	92.57 392	76.79 407	75.56 406	88.23 404	61.22 402	94.48 396	71.43 403	82.92 373	89.87 408

TAPA-MVS	90.10 7	92.30 207	91.22 226	95.56 160	98.33 83	89.60 198	96.79 206	97.65 148	81.83 383	91.52 222	97.23 149	87.94 113	98.91 181	71.31 404	98.37 122	98.17 173
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		86.14 353	85.40 349	88.35 376	90.12 396	80.06 383	95.90 275	95.20 330	88.59 270	81.29 387	93.62 340	71.43 342	92.65 411	71.26 405	81.17 380	92.34 388

tmp_tt		51.94 397	53.82 397	46.29 413	33.73 437	45.30 437	78.32 423	67.24 434	18.02 430	50.93 426	87.05 411	52.99 412	53.11 432	70.76 406	25.29 430	40.46 428

MIMVSNet1		84.93 362	83.05 364	90.56 357	89.56 401	84.84 326	95.40 301	95.35 321	83.91 363	80.38 392	92.21 373	57.23 406	93.34 407	70.69 407	82.75 375	93.50 370

APD_test1		79.31 377	77.70 380	84.14 390	89.11 405	69.07 416	92.36 391	91.50 401	69.07 415	73.87 408	92.63 361	39.93 421	94.32 398	70.54 408	80.25 383	89.02 410

RPMNet		88.98 319	87.05 333	94.77 204	94.45 330	87.19 274	90.23 404	98.03 98	77.87 405	92.40 194	87.55 409	80.17 252	99.51 104	68.84 409	93.95 235	97.60 213

UWE-MVS-28		86.81 344	86.41 339	88.02 380	92.87 372	74.60 405	95.38 303	86.70 420	88.17 284	87.28 335	94.67 284	70.83 347	93.30 408	67.45 410	94.31 221	96.17 258

N_pmnet		78.73 378	78.71 379	78.79 396	92.80 375	46.50 435	94.14 350	43.71 437	78.61 401	80.83 388	91.66 380	74.94 319	96.36 372	67.24 411	84.45 357	93.50 370

OpenMVS_ROB	81.14 20	84.42 365	82.28 371	90.83 350	90.06 397	84.05 336	95.73 284	94.04 371	73.89 412	80.17 395	91.53 381	59.15 403	97.64 323	66.92 412	89.05 301	90.80 405

PMMVS2		70.19 384	66.92 388	80.01 394	76.35 427	65.67 421	86.22 417	87.58 417	64.83 419	62.38 420	80.29 419	26.78 429	88.49 421	63.79 413	54.07 424	85.88 411

test_0402		86.46 347	84.79 356	91.45 337	95.02 302	85.55 308	96.29 253	94.89 345	80.90 388	82.21 384	93.97 326	68.21 372	97.29 351	62.98 414	88.68 306	91.51 399

DeepMVS_CX				74.68 405	90.84 394	64.34 423		81.61 428	65.34 418	67.47 416	88.01 407	48.60 417	80.13 427	62.33 415	73.68 404	79.58 417

Syy-MVS		87.13 340	87.02 335	87.47 382	95.16 293	73.21 410	95.00 320	93.93 375	88.55 274	86.96 342	91.99 374	75.90 309	94.00 401	61.59 416	94.11 227	95.20 313

testf1		69.31 386	66.76 389	76.94 400	78.61 425	61.93 424	88.27 414	86.11 422	55.62 421	59.69 421	85.31 413	20.19 433	89.32 415	57.62 417	69.44 412	79.58 417

APD_test2		69.31 386	66.76 389	76.94 400	78.61 425	61.93 424	88.27 414	86.11 422	55.62 421	59.69 421	85.31 413	20.19 433	89.32 415	57.62 417	69.44 412	79.58 417

EGC-MVSNET		68.77 388	63.01 394	86.07 389	92.49 381	82.24 359	93.96 355	90.96 405	0.71 434	2.62 435	90.89 384	53.66 411	93.46 405	57.25 419	84.55 355	82.51 415

dmvs_testset		81.38 374	82.60 369	77.73 397	91.74 389	51.49 432	93.03 381	84.21 425	89.07 251	78.28 401	91.25 383	76.97 301	88.53 420	56.57 420	82.24 376	93.16 374

FPMVS		71.27 383	69.85 385	75.50 403	74.64 428	59.03 428	91.30 395	91.50 401	58.80 420	57.92 424	88.28 403	29.98 427	85.53 423	53.43 421	82.84 374	81.95 416

ANet_high		63.94 392	59.58 395	77.02 399	61.24 435	66.06 420	85.66 419	87.93 416	78.53 402	42.94 427	71.04 424	25.42 430	80.71 426	52.60 422	30.83 428	84.28 414

Gipuma		67.86 389	65.41 391	75.18 404	92.66 378	73.45 408	66.50 425	94.52 357	53.33 424	57.80 425	66.07 425	30.81 425	89.20 417	48.15 423	78.88 391	62.90 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		69.99 385	69.33 387	71.98 406	88.78 407	61.64 426	89.86 407	59.93 436	75.67 408	74.96 407	85.45 412	50.19 415	81.66 425	43.86 424	55.27 423	72.63 421

PMVS	53.92 22	58.58 393	55.40 396	68.12 408	51.00 436	48.64 433	78.86 422	87.10 419	46.77 425	35.84 431	74.28 421	8.76 435	86.34 422	42.07 425	73.91 403	69.38 422
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	50.73 23	53.25 395	48.81 400	66.58 410	65.34 434	57.50 429	72.49 424	70.94 433	40.15 428	39.28 430	63.51 426	6.89 437	73.48 430	38.29 426	42.38 426	68.76 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		76.77 379	76.63 382	77.18 398	85.32 416	56.82 430	94.53 332	89.39 411	82.66 378	71.35 411	89.18 398	75.03 318	88.88 418	35.42 427	66.79 415	85.84 412

SSC-MVS		76.05 380	75.83 383	76.72 402	84.77 417	56.22 431	94.32 344	88.96 413	81.82 384	70.52 412	88.91 399	74.79 320	88.71 419	33.69 428	64.71 418	85.23 413

E-PMN		53.28 394	52.56 398	55.43 411	74.43 429	47.13 434	83.63 421	76.30 429	42.23 426	42.59 428	62.22 427	28.57 428	74.40 428	31.53 429	31.51 427	44.78 426

kuosan		65.27 391	64.66 393	67.11 409	83.80 418	61.32 427	88.53 413	60.77 435	68.22 416	67.67 414	80.52 418	49.12 416	70.76 431	29.67 430	53.64 425	69.26 423

EMVS		52.08 396	51.31 399	54.39 412	72.62 431	45.39 436	83.84 420	75.51 431	41.13 427	40.77 429	59.65 428	30.08 426	73.60 429	28.31 431	29.90 429	44.18 427

wuyk23d		25.11 398	24.57 402	26.74 414	73.98 430	39.89 438	57.88 427	9.80 438	12.27 431	10.39 432	6.97 434	7.03 436	36.44 433	25.43 432	17.39 431	3.89 431

testmvs		13.36 400	16.33 403	4.48 416	5.04 438	2.26 441	93.18 375	3.28 439	2.70 432	8.24 433	21.66 430	2.29 439	2.19 434	7.58 433	2.96 432	9.00 430

test123		13.04 401	15.66 404	5.18 415	4.51 439	3.45 440	92.50 389	1.81 440	2.50 433	7.58 434	20.15 431	3.67 438	2.18 435	7.13 434	1.07 433	9.90 429

mmdepth		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

monomultidepth		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

test_blank		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uanet_test		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

DCPMVS		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

cdsmvs_eth3d_5k		23.24 399	30.99 401	0.00 417	0.00 440	0.00 442	0.00 428	97.63 152	0.00 435	0.00 436	96.88 167	84.38 169	0.00 436	0.00 435	0.00 434	0.00 432

pcd_1.5k_mvsjas		7.39 403	9.85 406	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	88.65 101	0.00 436	0.00 435	0.00 434	0.00 432

sosnet-low-res		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

sosnet		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uncertanet		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

Regformer		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

ab-mvs-re		8.06 402	10.74 405	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	96.69 177	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

uanet		0.00 404	0.00 407	0.00 417	0.00 440	0.00 442	0.00 428	0.00 441	0.00 435	0.00 436	0.00 435	0.00 440	0.00 436	0.00 435	0.00 434	0.00 432

FOURS1					99.55 1	93.34 67	99.29 1	98.35 31	94.98 37	98.49 28

test_one_0601					99.32 22	95.20 20		98.25 49	95.13 31	98.48 29	98.87 23	95.16 7

eth-test2					0.00 440

eth-test					0.00 440

test_241102_ONE					99.42 7	95.30 17		98.27 43	95.09 34	99.19 7	98.81 29	95.54 5	99.65 66

save fliter					98.91 52	94.28 38	97.02 185	98.02 101	95.35 24

test0726					99.45 3	95.36 13	98.31 27	98.29 38	94.92 40	98.99 12	98.92 17	95.08 8

GSMVS																98.45 151

test_part2					99.28 25	95.74 8				98.10 35

sam_mvs1												82.76 204				98.45 151

sam_mvs												81.94 223

MTGPA								98.08 81

test_post											17.58 432	81.76 225	98.08 265

patchmatchnet-post											90.45 388	82.65 208	98.10 260

MTMP							97.86 82	82.03 427

TEST9					98.70 59	94.19 42	96.41 239	98.02 101	88.17 284	96.03 109	97.56 131	92.74 33	99.59 82

test_8					98.67 61	94.06 49	96.37 246	98.01 104	88.58 271	95.98 113	97.55 133	92.73 34	99.58 85

agg_prior					98.67 61	93.79 55		98.00 105		95.68 123			99.57 92

test_prior4						93.66 58	96.42 238

test_prior				97.23 64	98.67 61	92.99 79		98.00 105					99.41 117			99.29 67

新几何2							95.79 281

旧先验1					98.38 81	93.38 64		97.75 135			98.09 83	92.30 45			99.01 94	99.16 77

原ACMM2							95.67 286

test222					98.24 90	92.21 103	95.33 305	97.60 154	79.22 399	95.25 132	97.84 106	88.80 98			99.15 83	98.72 126

segment_acmp												92.89 30

testdata1							95.26 312		93.10 119

test12				97.65 43	98.46 73	94.26 39		97.66 146		95.52 130		90.89 73	99.46 111		99.25 72	99.22 74

plane_prior7					96.21 233	89.98 188

plane_prior6					96.10 244	90.00 184						81.32 231

plane_prior4											96.64 180

plane_prior3						90.00 184			94.46 65	91.34 227

plane_prior2							97.74 99		94.85 42

plane_prior1					96.14 241

plane_prior						89.99 186	97.24 166		94.06 77						92.16 261

n2								0.00 441

nn								0.00 441

door-mid								91.06 404

test11								97.88 117

door								91.13 403

HQP5-MVS						89.33 214

HQP-NCC					95.86 250		96.65 221		93.55 93	90.14 251

ACMP_Plane					95.86 250		96.65 221		93.55 93	90.14 251

HQP4-MVS										90.14 251			98.50 223			95.78 277

HQP3-MVS								97.39 192							92.10 262

HQP2-MVS												80.95 235

NP-MVS					95.99 248	89.81 194					95.87 222

ACMMP++_ref															90.30 291

ACMMP++															91.02 280

Test By Simon												88.73 100

High-resolution multi-view benchmark