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 31	98.23 11	98.01 112	95.03 26	98.07 55	95.76 298	97.78 1	97.52 48	98.80 29	88.09 108	99.86 9	99.44 1	99.37 62	99.80 1

fmvsm_s_conf0.5_n_2		96.62 58	96.82 43	96.02 132	97.98 115	90.43 175	97.50 134	98.59 19	96.59 5	99.31 2	99.08 4	84.47 166	99.75 46	99.37 2	98.45 118	97.88 192

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 17	97.08 2	99.25 5	99.10 3	87.88 114	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 37	99.24 6	98.87 22	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 35	99.30 3	98.84 27	93.34 22	99.78 40	99.32 3	99.13 85	99.50 44

fmvsm_s_conf0.1_n_2		96.33 70	96.44 66	96.00 136	97.30 154	90.37 178	97.53 131	97.92 113	96.52 6	99.14 9	99.08 4	83.21 188	99.74 47	99.22 6	98.06 134	97.88 192

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 17	96.70 3	99.38 1	99.07 7	89.92 86	99.81 30	99.16 7	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 7	99.46 41	98.08 182

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 151	92.37 96	97.91 77	98.88 4	95.83 12	98.92 16	99.05 9	91.45 57	99.80 34	99.12 9	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 37	98.84 20	99.06 8	88.80 98	99.65 65	99.06 10	98.63 108	98.18 170

test_fmvsmconf0.1_n		97.09 29	97.06 24	97.19 68	95.67 259	92.21 103	97.95 72	98.27 42	95.78 16	98.40 29	99.00 11	89.99 84	99.78 40	99.06 10	99.41 54	99.59 25

MVS_0304		96.74 52	96.31 68	98.02 19	96.87 180	94.65 30	97.58 123	94.39 360	96.47 7	97.16 60	98.39 54	87.53 123	99.87 7	98.97 12	99.41 54	99.55 35

fmvsm_s_conf0.5_n_a		96.75 51	96.93 34	96.20 122	97.64 138	90.72 165	98.00 61	98.73 9	94.55 59	98.91 17	99.08 4	88.22 107	99.63 74	98.91 13	98.37 121	98.25 165

test_fmvsmvis_n_1920		96.70 53	96.84 39	96.31 111	96.62 200	91.73 117	97.98 63	98.30 35	96.19 9	96.10 106	98.95 15	89.42 89	99.76 43	98.90 14	99.08 89	97.43 219

fmvsm_s_conf0.1_n		96.58 61	96.77 47	96.01 135	96.67 198	90.25 180	97.91 77	98.38 26	94.48 63	98.84 20	99.14 1	88.06 109	99.62 75	98.82 15	98.60 110	98.15 174

test_fmvsmconf0.01_n		96.15 74	95.85 78	97.03 75	92.66 376	91.83 116	97.97 69	97.84 127	95.57 19	97.53 47	99.00 11	84.20 172	99.76 43	98.82 15	99.08 89	99.48 48

fmvsm_s_conf0.1_n_a		96.40 66	96.47 60	96.16 124	95.48 267	90.69 166	97.91 77	98.33 32	94.07 75	98.93 13	99.14 1	87.44 127	99.61 76	98.63 17	98.32 123	98.18 170

mamv4		94.66 120	96.10 73	90.37 358	98.01 112	73.41 407	96.82 203	97.78 132	89.95 222	94.52 147	97.43 137	92.91 27	99.09 157	98.28 18	99.16 82	98.60 134

MVSMamba_PlusPlus		96.51 62	96.48 59	96.59 86	98.07 109	91.97 112	98.14 49	97.79 131	90.43 211	97.34 56	97.52 133	91.29 63	99.19 137	98.12 19	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 35	94.76 50	98.30 30	98.90 19	93.77 17	99.68 61	97.93 20	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		94.17 130	94.58 111	92.91 292	97.42 152	82.02 359	97.83 89	97.85 123	94.68 53	98.10 34	98.49 44	70.15 353	99.32 124	97.91 21	98.82 100	97.40 221

reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 95	98.21 54	95.73 17	97.99 37	99.03 10	92.63 36	99.82 28	97.80 22	99.42 51	99.67 13

balanced_conf03		96.84 45	96.89 36	96.68 80	97.63 140	92.22 102	98.17 48	97.82 129	94.44 65	98.23 32	97.36 140	90.97 71	99.22 134	97.74 23	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 56	95.80 14	97.88 41	98.98 13	92.91 27	99.81 30	97.68 24	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 56	95.80 14	97.88 41	98.98 13	92.91 27	99.81 30	97.68 24	99.43 48	99.67 13

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 111					99.86 9	97.68 24	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 111					99.86 9	97.68 24	99.67 6	99.77 2

patch_mono-2		96.83 46	97.44 17	95.01 185	99.05 39	85.39 312	96.98 190	98.77 7	94.70 52	97.99 37	98.66 33	93.61 19	99.91 1	97.67 28	99.50 35	99.72 11

test_vis1_n		92.37 202	92.26 187	92.72 300	94.75 315	82.64 349	98.02 59	96.80 246	91.18 180	97.77 45	97.93 95	58.02 403	98.29 242	97.63 29	98.21 127	97.23 230

test_fmvs1_n		92.73 192	92.88 161	92.29 311	96.08 245	81.05 367	97.98 63	97.08 216	90.72 195	96.79 73	98.18 77	63.07 394	98.45 226	97.62 30	98.42 120	97.36 222

test_fmvs1		93.21 167	93.53 139	92.25 314	96.55 209	81.20 366	97.40 150	96.96 229	90.68 197	96.80 71	98.04 86	69.25 360	98.40 229	97.58 31	98.50 113	97.16 231

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 42	95.13 30	99.19 7	98.89 20	95.54 5	99.85 18	97.52 32	99.66 10	99.56 32

test_241102_TWO								98.27 42	95.13 30	98.93 13	98.89 20	94.99 11	99.85 18	97.52 32	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	97.85 123	94.92 39	98.73 22	98.87 22	95.08 8	99.84 23	97.52 32	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 39					99.86 9	97.52 32	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 39	94.78 48	98.93 13	98.87 22	96.04 2	99.86 9	97.45 36	99.58 23	99.59 25

test_0728_THIRD									94.78 48	98.73 22	98.87 22	95.87 4	99.84 23	97.45 36	99.72 2	99.77 2

EC-MVSNet		96.42 65	96.47 60	96.26 117	97.01 174	91.52 129	98.89 5	97.75 134	94.42 66	96.64 82	97.68 116	89.32 90	98.60 214	97.45 36	99.11 88	98.67 131

IU-MVS					99.42 7	95.39 11		97.94 110	90.40 213	98.94 12				97.41 39	99.66 10	99.74 8

mmtdpeth		89.70 311	88.96 309	91.90 322	95.84 254	84.42 328	97.46 143	95.53 314	90.27 214	94.46 150	90.50 384	69.74 358	98.95 174	97.39 40	69.48 409	92.34 386

dcpmvs_2		96.37 68	97.05 27	94.31 227	98.96 49	84.11 333	97.56 126	97.51 166	93.92 80	97.43 53	98.52 41	92.75 32	99.32 124	97.32 41	99.50 35	99.51 41

CS-MVS		96.86 41	97.06 24	96.26 117	98.16 101	91.16 150	99.09 3	97.87 118	95.30 25	97.06 66	98.03 87	91.72 50	98.71 204	97.10 42	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	97.85 123	93.72 86	98.57 25	98.35 58	93.69 18	99.40 117	97.06 43	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	97.27 163	98.08 80	95.81 13	97.87 44	98.31 67	94.26 13	99.68 61	97.02 44	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 70	94.82 45	99.01 10	98.55 39	94.18 14	97.41 343	96.94 45	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 28	96.45 101	98.29 85	91.66 123	99.03 4	97.85 123	95.84 11	96.90 69	97.97 93	91.24 64	98.75 197	96.92 46	99.33 64	98.94 102

CANet		96.39 67	96.02 74	97.50 50	97.62 141	93.38 64	97.02 184	97.96 108	95.42 22	94.86 139	97.81 108	87.38 129	99.82 28	96.88 47	99.20 77	99.29 67

TSAR-MVS + GP.		96.69 55	96.49 58	97.27 62	98.31 84	93.39 63	96.79 205	96.72 249	94.17 73	97.44 51	97.66 119	92.76 31	99.33 122	96.86 48	97.76 144	99.08 88

DeepPCF-MVS	93.97 1	96.61 59	97.09 23	95.15 177	98.09 105	86.63 288	96.00 268	98.15 68	95.43 21	97.95 39	98.56 37	93.40 21	99.36 121	96.77 49	99.48 39	99.45 51

BP-MVS1		95.89 83	95.49 83	97.08 73	96.67 198	93.20 73	98.08 53	96.32 273	94.56 58	96.32 96	97.84 105	84.07 175	99.15 146	96.75 50	98.78 102	98.90 109

test_cas_vis1_n_1920		94.48 124	94.55 115	94.28 229	96.78 191	86.45 293	97.63 119	97.64 149	93.32 106	97.68 46	98.36 57	73.75 329	99.08 160	96.73 51	99.05 91	97.31 226

SMA-MVS		97.35 20	97.03 29	98.30 8	99.06 38	95.42 10	97.94 73	98.18 63	90.57 207	98.85 19	98.94 16	93.33 23	99.83 26	96.72 52	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	97.21 171	98.35 30	95.16 29	98.71 24	98.80 29	95.05 10	99.89 3	96.70 53	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 37	95.55 20	98.56 26	97.81 108	93.90 15	99.65 65	96.62 54	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 24	96.59 86	98.72 58	91.86 115	97.67 110	98.49 22	94.66 55	97.24 58	98.41 53	92.31 44	98.94 176	96.61 55	99.46 41	98.96 99

MP-MVS-pluss		96.70 53	96.27 70	97.98 22	99.23 30	94.71 29	96.96 192	98.06 88	90.67 198	95.55 126	98.78 31	91.07 68	99.86 9	96.58 56	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 42	95.34 24	98.11 33	98.56 37	94.53 12	99.71 53	96.57 57	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		97.18 25	96.84 39	98.20 14	99.30 24	95.35 15	97.12 178	98.07 85	93.54 95	96.08 107	97.69 115	93.86 16	99.71 53	96.50 58	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 42	92.37 140	98.27 31	98.65 35	93.33 23	99.72 52	96.49 59	99.52 30	99.51 41

EI-MVSNet-Vis-set		96.51 62	96.47 60	96.63 83	98.24 90	91.20 144	96.89 196	97.73 137	94.74 51	96.49 89	98.49 44	90.88 74	99.58 84	96.44 60	98.32 123	99.13 81

VDD-MVS		93.82 148	93.08 154	96.02 132	97.88 124	89.96 190	97.72 104	95.85 294	92.43 138	95.86 115	98.44 50	68.42 369	99.39 118	96.31 61	94.85 208	98.71 128

ACMMP_NAP		97.20 24	96.86 37	98.23 11	99.09 34	95.16 22	97.60 122	98.19 61	92.82 131	97.93 40	98.74 32	91.60 55	99.86 9	96.26 62	99.52 30	99.67 13

diffmvs		95.25 100	95.13 98	95.63 155	96.43 223	89.34 212	95.99 269	97.35 197	92.83 130	96.31 97	97.37 139	86.44 140	98.67 207	96.26 62	97.19 163	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 69	96.30 69	96.47 98	98.20 96	90.93 157	96.86 198	97.72 139	94.67 54	96.16 104	98.46 48	90.43 79	99.58 84	96.23 64	97.96 137	98.90 109

SR-MVS		97.01 34	96.86 37	97.47 52	99.09 34	93.27 71	97.98 63	98.07 85	93.75 85	97.45 50	98.48 47	91.43 59	99.59 81	96.22 65	99.27 68	99.54 37

xiu_mvs_v1_base_debu		95.01 106	94.76 105	95.75 147	96.58 204	91.71 119	96.25 254	97.35 197	92.99 120	96.70 77	96.63 183	82.67 204	99.44 113	96.22 65	97.46 148	96.11 263

xiu_mvs_v1_base		95.01 106	94.76 105	95.75 147	96.58 204	91.71 119	96.25 254	97.35 197	92.99 120	96.70 77	96.63 183	82.67 204	99.44 113	96.22 65	97.46 148	96.11 263

xiu_mvs_v1_base_debi		95.01 106	94.76 105	95.75 147	96.58 204	91.71 119	96.25 254	97.35 197	92.99 120	96.70 77	96.63 183	82.67 204	99.44 113	96.22 65	97.46 148	96.11 263

alignmvs		95.87 85	95.23 95	97.78 32	97.56 149	95.19 21	97.86 82	97.17 208	94.39 69	96.47 91	96.40 196	85.89 148	99.20 136	96.21 69	95.11 206	98.95 101

sasdasda		96.02 77	95.45 86	97.75 36	97.59 144	95.15 23	98.28 30	97.60 153	94.52 61	96.27 99	96.12 210	87.65 118	99.18 140	96.20 70	94.82 210	98.91 106

canonicalmvs		96.02 77	95.45 86	97.75 36	97.59 144	95.15 23	98.28 30	97.60 153	94.52 61	96.27 99	96.12 210	87.65 118	99.18 140	96.20 70	94.82 210	98.91 106

MGCFI-Net		95.94 82	95.40 90	97.56 49	97.59 144	94.62 31	98.21 42	97.57 158	94.41 67	96.17 103	96.16 208	87.54 122	99.17 142	96.19 72	94.73 215	98.91 106

RRT-MVS		94.51 122	94.35 122	94.98 188	96.40 224	86.55 291	97.56 126	97.41 189	93.19 111	94.93 137	97.04 158	79.12 269	99.30 128	96.19 72	97.32 158	99.09 87

MTAPA		97.08 30	96.78 46	97.97 23	99.37 16	94.42 36	97.24 165	98.08 80	95.07 34	96.11 105	98.59 36	90.88 74	99.90 2	96.18 74	99.50 35	99.58 28

APD-MVS_3200maxsize		96.81 47	96.71 50	97.12 70	99.01 45	92.31 99	97.98 63	98.06 88	93.11 117	97.44 51	98.55 39	90.93 72	99.55 94	96.06 75	99.25 72	99.51 41

SR-MVS-dyc-post		96.88 40	96.80 45	97.11 71	99.02 42	92.34 97	97.98 63	98.03 97	93.52 98	97.43 53	98.51 42	91.40 60	99.56 92	96.05 76	99.26 70	99.43 55

RE-MVS-def			96.72 49		99.02 42	92.34 97	97.98 63	98.03 97	93.52 98	97.43 53	98.51 42	90.71 76		96.05 76	99.26 70	99.43 55

MVS_111021_HR		96.68 57	96.58 55	96.99 76	98.46 73	92.31 99	96.20 259	98.90 3	94.30 72	95.86 115	97.74 113	92.33 42	99.38 120	96.04 78	99.42 51	99.28 69

PHI-MVS		96.77 49	96.46 63	97.71 41	98.40 78	94.07 48	98.21 42	98.45 25	89.86 224	97.11 64	98.01 90	92.52 39	99.69 59	96.03 79	99.53 29	99.36 64

casdiffmvs_mvg		95.81 86	95.57 81	96.51 94	96.87 180	91.49 130	97.50 134	97.56 162	93.99 78	95.13 135	97.92 96	87.89 113	98.78 192	95.97 80	97.33 156	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 32	98.47 5	99.08 36	96.16 4	97.55 130	97.97 107	95.59 18	96.61 83	97.89 97	92.57 38	99.84 23	95.95 81	99.51 33	99.40 58

DELS-MVS		96.61 59	96.38 67	97.30 58	97.79 128	93.19 74	95.96 270	98.18 63	95.23 26	95.87 114	97.65 120	91.45 57	99.70 58	95.87 82	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 73	96.19 72	96.39 106	98.23 94	91.35 137	96.24 257	98.79 6	93.99 78	95.80 117	97.65 120	89.92 86	99.24 132	95.87 82	99.20 77	98.58 137

h-mvs33		94.15 132	93.52 141	96.04 130	97.81 127	90.22 181	97.62 121	97.58 157	95.19 27	96.74 75	97.45 134	83.67 180	99.61 76	95.85 84	79.73 383	98.29 164

hse-mvs2		93.45 160	92.99 156	94.81 198	97.02 173	88.59 234	96.69 216	96.47 267	95.19 27	96.74 75	96.16 208	83.67 180	98.48 225	95.85 84	79.13 387	97.35 224

NCCC		97.30 22	97.03 29	98.11 17	98.77 56	95.06 25	97.34 156	98.04 95	95.96 10	97.09 65	97.88 99	93.18 25	99.71 53	95.84 86	99.17 80	99.56 32

VNet		95.89 83	95.45 86	97.21 66	98.07 109	92.94 81	97.50 134	98.15 68	93.87 82	97.52 48	97.61 126	85.29 155	99.53 98	95.81 87	95.27 201	99.16 77

PC_three_1452									90.77 192	98.89 18	98.28 72	96.24 1	98.35 237	95.76 88	99.58 23	99.59 25

9.14			96.75 48		98.93 50		97.73 101	98.23 53	91.28 176	97.88 41	98.44 50	93.00 26	99.65 65	95.76 88	99.47 40

XVS		97.18 25	96.96 33	97.81 28	99.38 14	94.03 50	98.59 12	98.20 56	94.85 41	96.59 85	98.29 70	91.70 52	99.80 34	95.66 90	99.40 56	99.62 20

X-MVStestdata		91.71 228	89.67 293	97.81 28	99.38 14	94.03 50	98.59 12	98.20 56	94.85 41	96.59 85	32.69 427	91.70 52	99.80 34	95.66 90	99.40 56	99.62 20

baseline		95.58 92	95.42 89	96.08 126	96.78 191	90.41 176	97.16 175	97.45 180	93.69 89	95.65 124	97.85 103	87.29 130	98.68 206	95.66 90	97.25 161	99.13 81

ETV-MVS		96.02 77	95.89 77	96.40 104	97.16 160	92.44 94	97.47 141	97.77 133	94.55 59	96.48 90	94.51 291	91.23 66	98.92 178	95.65 93	98.19 128	97.82 200

casdiffmvs		95.64 89	95.49 83	96.08 126	96.76 196	90.45 173	97.29 162	97.44 184	94.00 77	95.46 130	97.98 92	87.52 125	98.73 200	95.64 94	97.33 156	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 35	97.83 26	99.42 7	94.12 46	98.52 15	98.32 33	93.21 108	97.18 59	98.29 70	92.08 46	99.83 26	95.63 95	99.59 19	99.54 37

ACMMPR		97.07 31	96.84 39	97.79 30	99.44 6	93.88 53	98.52 15	98.31 34	93.21 108	97.15 61	98.33 64	91.35 61	99.86 9	95.63 95	99.59 19	99.62 20

HPM-MVS		96.69 55	96.45 64	97.40 54	99.36 18	93.11 76	98.87 6	98.06 88	91.17 181	96.40 94	97.99 91	90.99 70	99.58 84	95.61 97	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 44	97.64 45	99.33 21	93.54 60	98.80 8	98.28 39	92.99 120	96.45 93	98.30 69	91.90 49	99.85 18	95.61 97	99.68 4	99.54 37

DeepC-MVS	93.07 3	96.06 75	95.66 80	97.29 59	97.96 117	93.17 75	97.30 161	98.06 88	93.92 80	93.38 175	98.66 33	86.83 135	99.73 49	95.60 99	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 51	97.85 25	99.37 16	94.12 46	98.49 19	98.18 63	92.64 136	96.39 95	98.18 77	91.61 54	99.88 4	95.59 100	99.55 26	99.57 29

region2R		97.07 31	96.84 39	97.77 34	99.46 2	93.79 55	98.52 15	98.24 50	93.19 111	97.14 62	98.34 61	91.59 56	99.87 7	95.46 101	99.59 19	99.64 18

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 73	96.04 2	99.24 132	95.36 102	99.59 19	99.56 32

lupinMVS		94.99 110	94.56 112	96.29 115	96.34 228	91.21 142	95.83 277	96.27 277	88.93 257	96.22 101	96.88 166	86.20 145	98.85 185	95.27 103	99.05 91	98.82 121

reproduce_monomvs		91.30 256	91.10 229	91.92 320	96.82 187	82.48 353	97.01 187	97.49 169	94.64 57	88.35 306	95.27 255	70.53 348	98.10 259	95.20 104	84.60 351	95.19 314

mPP-MVS		96.86 41	96.60 53	97.64 45	99.40 11	93.44 62	98.50 18	98.09 79	93.27 107	95.95 113	98.33 64	91.04 69	99.88 4	95.20 104	99.57 25	99.60 24

DeepC-MVS_fast	93.89 2	96.93 38	96.64 52	97.78 32	98.64 67	94.30 37	97.41 146	98.04 95	94.81 46	96.59 85	98.37 56	91.24 64	99.64 73	95.16 106	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		94.84 115	94.39 121	96.18 123	95.52 265	90.93 157	96.09 263	96.52 264	89.28 243	96.01 111	97.32 141	84.70 162	98.77 195	95.15 107	98.91 99	98.85 117
jason: jason.
train_agg		96.30 71	95.83 79	97.72 39	98.70 59	94.19 42	96.41 238	98.02 100	88.58 269	96.03 108	97.56 130	92.73 34	99.59 81	95.04 108	99.37 62	99.39 60

mvsany_test1		93.93 144	93.98 127	93.78 257	94.94 305	86.80 281	94.62 327	92.55 391	88.77 266	96.85 70	98.49 44	88.98 94	98.08 264	95.03 109	95.62 195	96.46 251

test_prior2							96.35 246		92.80 132	96.03 108	97.59 127	92.01 47		95.01 110	99.38 59

nrg030		94.05 139	93.31 150	96.27 116	95.22 289	94.59 32	98.34 25	97.46 175	92.93 127	91.21 235	96.64 179	87.23 132	98.22 246	94.99 111	85.80 331	95.98 267

VDDNet		93.05 176	92.07 190	96.02 132	96.84 183	90.39 177	98.08 53	95.85 294	86.22 330	95.79 118	98.46 48	67.59 372	99.19 137	94.92 112	94.85 208	98.47 149

mvsmamba		94.57 121	94.14 125	95.87 140	97.03 172	89.93 191	97.84 86	95.85 294	91.34 172	94.79 141	96.80 168	80.67 240	98.81 189	94.85 113	98.12 132	98.85 117

APD-MVS		96.95 36	96.60 53	98.01 20	99.03 41	94.93 27	97.72 104	98.10 78	91.50 165	98.01 36	98.32 66	92.33 42	99.58 84	94.85 113	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 57	97.82 27	99.36 18	94.14 45	98.29 29	98.13 71	92.72 133	96.70 77	98.06 84	91.35 61	99.86 9	94.83 115	99.28 67	99.47 50

MP-MVS		96.77 49	96.45 64	97.72 39	99.39 13	93.80 54	98.41 23	98.06 88	93.37 103	95.54 128	98.34 61	90.59 78	99.88 4	94.83 115	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														94.81 117	99.38 59	99.45 51

PS-MVSNAJ		95.37 96	95.33 93	95.49 165	97.35 153	90.66 168	95.31 306	97.48 170	93.85 83	96.51 88	95.70 235	88.65 101	99.65 65	94.80 118	98.27 125	96.17 257

HPM-MVS_fast		96.51 62	96.27 70	97.22 65	99.32 22	92.74 85	98.74 9	98.06 88	90.57 207	96.77 74	98.35 58	90.21 81	99.53 98	94.80 118	99.63 16	99.38 62

xiu_mvs_v2_base		95.32 98	95.29 94	95.40 170	97.22 156	90.50 171	95.44 299	97.44 184	93.70 88	96.46 92	96.18 205	88.59 104	99.53 98	94.79 120	97.81 141	96.17 257

CSCG		96.05 76	95.91 76	96.46 100	99.24 28	90.47 172	98.30 28	98.57 21	89.01 252	93.97 162	97.57 128	92.62 37	99.76 43	94.66 121	99.27 68	99.15 79

test_fmvs2		89.77 310	89.93 282	89.31 372	93.68 351	76.37 399	97.64 117	95.90 291	89.84 227	91.49 222	96.26 203	58.77 402	97.10 353	94.65 122	91.13 276	94.46 350

EIA-MVS		95.53 94	95.47 85	95.71 152	97.06 168	89.63 196	97.82 91	97.87 118	93.57 91	93.92 163	95.04 264	90.61 77	98.95 174	94.62 123	98.68 106	98.54 139

SDMVSNet		94.17 130	93.61 135	95.86 142	98.09 105	91.37 136	97.35 155	98.20 56	93.18 113	91.79 215	97.28 143	79.13 268	98.93 177	94.61 124	92.84 247	97.28 227

ZD-MVS					99.05 39	94.59 32		98.08 80	89.22 245	97.03 67	98.10 80	92.52 39	99.65 65	94.58 125	99.31 66

ACMMP		96.27 72	95.93 75	97.28 61	99.24 28	92.62 88	98.25 35	98.81 5	92.99 120	94.56 146	98.39 54	88.96 95	99.85 18	94.57 126	97.63 145	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 90	95.13 98	97.09 72	96.79 190	93.26 72	97.89 80	97.83 128	93.58 90	96.80 71	97.82 107	83.06 195	99.16 144	94.40 127	97.95 138	98.87 115

PGM-MVS		96.81 47	96.53 56	97.65 43	99.35 20	93.53 61	97.65 113	98.98 2	92.22 143	97.14 62	98.44 50	91.17 67	99.85 18	94.35 128	99.46 41	99.57 29

ET-MVSNet_ETH3D		91.49 244	90.11 273	95.63 155	96.40 224	91.57 128	95.34 303	93.48 379	90.60 206	75.58 403	95.49 246	80.08 252	96.79 365	94.25 129	89.76 294	98.52 141

LFMVS		93.60 154	92.63 172	96.52 90	98.13 104	91.27 139	97.94 73	93.39 380	90.57 207	96.29 98	98.31 67	69.00 362	99.16 144	94.18 130	95.87 187	99.12 84

MVSFormer		95.37 96	95.16 97	95.99 137	96.34 228	91.21 142	98.22 40	97.57 158	91.42 169	96.22 101	97.32 141	86.20 145	97.92 295	94.07 131	99.05 91	98.85 117

test_djsdf		93.07 175	92.76 165	94.00 241	93.49 357	88.70 232	98.22 40	97.57 158	91.42 169	90.08 260	95.55 243	82.85 201	97.92 295	94.07 131	91.58 268	95.40 296

mvs_anonymous		93.82 148	93.74 131	94.06 237	96.44 222	85.41 310	95.81 278	97.05 221	89.85 226	90.09 259	96.36 198	87.44 127	97.75 313	93.97 133	96.69 174	99.02 91

VPA-MVSNet		93.24 166	92.48 181	95.51 163	95.70 257	92.39 95	97.86 82	98.66 16	92.30 141	92.09 207	95.37 250	80.49 244	98.40 229	93.95 134	85.86 330	95.75 280

agg_prior2														93.94 135	99.38 59	99.50 44

mvs_tets		92.31 205	91.76 202	93.94 248	93.41 360	88.29 243	97.63 119	97.53 164	92.04 152	88.76 298	96.45 193	74.62 321	98.09 263	93.91 136	91.48 270	95.45 292

Effi-MVS+		94.93 111	94.45 119	96.36 109	96.61 201	91.47 132	96.41 238	97.41 189	91.02 187	94.50 148	95.92 219	87.53 123	98.78 192	93.89 137	96.81 169	98.84 120

jajsoiax		92.42 199	91.89 199	94.03 240	93.33 363	88.50 239	97.73 101	97.53 164	92.00 154	88.85 295	96.50 191	75.62 313	98.11 258	93.88 138	91.56 269	95.48 288

XVG-OURS-SEG-HR		93.86 147	93.55 137	94.81 198	97.06 168	88.53 238	95.28 307	97.45 180	91.68 161	94.08 159	97.68 116	82.41 212	98.90 181	93.84 139	92.47 253	96.98 234

PS-MVSNAJss		93.74 151	93.51 142	94.44 218	93.91 343	89.28 217	97.75 98	97.56 162	92.50 137	89.94 262	96.54 189	88.65 101	98.18 251	93.83 140	90.90 282	95.86 268

EPNet		95.20 103	94.56 112	97.14 69	92.80 373	92.68 87	97.85 85	94.87 347	96.64 4	92.46 192	97.80 110	86.23 142	99.65 65	93.72 141	98.62 109	99.10 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PVSNet_Blended_VisFu		95.27 99	94.91 103	96.38 107	98.20 96	90.86 159	97.27 163	98.25 48	90.21 215	94.18 156	97.27 145	87.48 126	99.73 49	93.53 142	97.77 143	98.55 138

CPTT-MVS		95.57 93	95.19 96	96.70 79	99.27 26	91.48 131	98.33 26	98.11 76	87.79 296	95.17 134	98.03 87	87.09 133	99.61 76	93.51 143	99.42 51	99.02 91

MVSTER		93.20 168	92.81 164	94.37 221	96.56 207	89.59 199	97.06 181	97.12 211	91.24 177	91.30 229	95.96 217	82.02 219	98.05 271	93.48 144	90.55 286	95.47 290

PVSNet_BlendedMVS		94.06 138	93.92 128	94.47 216	98.27 86	89.46 207	96.73 210	98.36 27	90.17 216	94.36 151	95.24 258	88.02 110	99.58 84	93.44 145	90.72 284	94.36 354

PVSNet_Blended		94.87 114	94.56 112	95.81 144	98.27 86	89.46 207	95.47 298	98.36 27	88.84 260	94.36 151	96.09 215	88.02 110	99.58 84	93.44 145	98.18 129	98.40 157

3Dnovator	91.36 5	95.19 104	94.44 120	97.44 53	96.56 207	93.36 66	98.65 11	98.36 27	94.12 74	89.25 287	98.06 84	82.20 216	99.77 42	93.41 147	99.32 65	99.18 76

EPP-MVSNet		95.22 102	95.04 101	95.76 145	97.49 150	89.56 200	98.67 10	97.00 227	90.69 196	94.24 154	97.62 125	89.79 88	98.81 189	93.39 148	96.49 178	98.92 105

testing3-2		92.10 216	92.05 191	92.27 312	97.71 132	79.56 385	97.42 145	94.41 359	93.53 96	93.22 181	95.49 246	69.16 361	99.11 152	93.25 149	94.22 223	98.13 175

CHOSEN 280x420		93.12 172	92.72 170	94.34 224	96.71 197	87.27 269	90.29 401	97.72 139	86.61 322	91.34 226	95.29 252	84.29 171	98.41 228	93.25 149	98.94 97	97.35 224

3Dnovator+	91.43 4	95.40 95	94.48 118	98.16 16	96.90 179	95.34 16	98.48 20	97.87 118	94.65 56	88.53 303	98.02 89	83.69 179	99.71 53	93.18 151	98.96 96	99.44 53

test_yl		94.78 117	94.23 123	96.43 102	97.74 130	91.22 140	96.85 199	97.10 213	91.23 178	95.71 120	96.93 161	84.30 169	99.31 126	93.10 152	95.12 204	98.75 123

DCV-MVSNet		94.78 117	94.23 123	96.43 102	97.74 130	91.22 140	96.85 199	97.10 213	91.23 178	95.71 120	96.93 161	84.30 169	99.31 126	93.10 152	95.12 204	98.75 123

test_vis1_rt		86.16 350	85.06 351	89.46 368	93.47 359	80.46 374	96.41 238	86.61 419	85.22 344	79.15 396	88.64 398	52.41 411	97.06 354	93.08 154	90.57 285	90.87 402

test1111		93.19 169	92.82 163	94.30 228	97.58 148	84.56 327	98.21 42	89.02 410	93.53 96	94.58 145	98.21 74	72.69 332	99.05 167	93.06 155	98.48 116	99.28 69

ECVR-MVS		93.19 169	92.73 169	94.57 213	97.66 136	85.41 310	98.21 42	88.23 412	93.43 101	94.70 143	98.21 74	72.57 333	99.07 164	93.05 156	98.49 114	99.25 72

HQP_MVS		93.78 150	93.43 146	94.82 196	96.21 232	89.99 186	97.74 99	97.51 166	94.85 41	91.34 226	96.64 179	81.32 230	98.60 214	93.02 157	92.23 256	95.86 268

plane_prior5								97.51 166					98.60 214	93.02 157	92.23 256	95.86 268

MonoMVSNet		91.92 221	91.77 201	92.37 307	92.94 369	83.11 345	97.09 180	95.55 311	92.91 128	90.85 239	94.55 288	81.27 232	96.52 368	93.01 159	87.76 312	97.47 218

test2506		91.60 234	90.78 242	94.04 239	97.66 136	83.81 336	98.27 32	75.53 428	93.43 101	95.23 132	98.21 74	67.21 375	99.07 164	93.01 159	98.49 114	99.25 72

MVS_Test		94.89 113	94.62 109	95.68 153	96.83 185	89.55 201	96.70 214	97.17 208	91.17 181	95.60 125	96.11 214	87.87 115	98.76 196	93.01 159	97.17 164	98.72 126

CLD-MVS		92.98 179	92.53 178	94.32 225	96.12 242	89.20 220	95.28 307	97.47 173	92.66 134	89.90 263	95.62 239	80.58 242	98.40 229	92.73 162	92.40 254	95.38 298
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-OURS		93.72 152	93.35 149	94.80 201	97.07 165	88.61 233	94.79 324	97.46 175	91.97 155	93.99 160	97.86 102	81.74 225	98.88 182	92.64 163	92.67 252	96.92 238

旧先验2							95.94 271		81.66 383	97.34 56			98.82 187	92.26 164

CDPH-MVS		95.97 80	95.38 91	97.77 34	98.93 50	94.44 35	96.35 246	97.88 116	86.98 315	96.65 81	97.89 97	91.99 48	99.47 109	92.26 164	99.46 41	99.39 60

FIs		94.09 137	93.70 132	95.27 173	95.70 257	92.03 110	98.10 51	98.68 13	93.36 105	90.39 246	96.70 174	87.63 120	97.94 292	92.25 166	90.50 288	95.84 271

LPG-MVS_test		92.94 182	92.56 175	94.10 235	96.16 237	88.26 245	97.65 113	97.46 175	91.29 173	90.12 256	97.16 151	79.05 271	98.73 200	92.25 166	91.89 264	95.31 303

LGP-MVS_train				94.10 235	96.16 237	88.26 245		97.46 175	91.29 173	90.12 256	97.16 151	79.05 271	98.73 200	92.25 166	91.89 264	95.31 303

cascas		91.20 261	90.08 274	94.58 212	94.97 301	89.16 223	93.65 366	97.59 156	79.90 394	89.40 279	92.92 354	75.36 314	98.36 236	92.14 169	94.75 213	96.23 253

OPM-MVS		93.28 165	92.76 165	94.82 196	94.63 321	90.77 163	96.65 220	97.18 206	93.72 86	91.68 219	97.26 146	79.33 266	98.63 211	92.13 170	92.28 255	95.07 317
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BP-MVS														92.13 170

HQP-MVS		93.19 169	92.74 168	94.54 214	95.86 249	89.33 213	96.65 220	97.39 191	93.55 92	90.14 250	95.87 221	80.95 234	98.50 222	92.13 170	92.10 261	95.78 276

DP-MVS Recon		95.68 88	95.12 100	97.37 55	99.19 31	94.19 42	97.03 182	98.08 80	88.35 278	95.09 136	97.65 120	89.97 85	99.48 108	92.08 173	98.59 111	98.44 154

VPNet		92.23 211	91.31 219	94.99 186	95.56 263	90.96 155	97.22 170	97.86 122	92.96 126	90.96 237	96.62 186	75.06 316	98.20 248	91.90 174	83.65 365	95.80 274

sss		94.51 122	93.80 130	96.64 81	97.07 165	91.97 112	96.32 249	98.06 88	88.94 256	94.50 148	96.78 169	84.60 163	99.27 130	91.90 174	96.02 183	98.68 130

anonymousdsp		92.16 213	91.55 210	93.97 244	92.58 378	89.55 201	97.51 133	97.42 188	89.42 240	88.40 305	94.84 273	80.66 241	97.88 300	91.87 176	91.28 274	94.48 349

test_fmvs3		83.21 366	83.02 363	83.78 389	86.77 413	68.34 415	96.76 208	94.91 342	86.49 323	84.14 369	89.48 394	36.04 421	91.73 411	91.86 177	80.77 380	91.26 401

ACMP	89.59 10	92.62 194	92.14 189	94.05 238	96.40 224	88.20 248	97.36 154	97.25 205	91.52 164	88.30 309	96.64 179	78.46 283	98.72 203	91.86 177	91.48 270	95.23 310
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		93.66 153	92.92 159	95.87 140	98.24 90	89.88 192	94.58 329	98.49 22	85.06 348	93.78 165	95.78 230	82.86 200	98.67 207	91.77 179	95.71 192	99.07 90

UGNet		94.04 140	93.28 151	96.31 111	96.85 182	91.19 145	97.88 81	97.68 144	94.40 68	93.00 184	96.18 205	73.39 331	99.61 76	91.72 180	98.46 117	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		93.37 162	92.67 171	95.47 168	95.34 278	92.83 82	97.17 174	98.58 20	92.98 125	90.13 254	95.80 226	88.37 106	97.85 301	91.71 181	83.93 360	95.73 282

DU-MVS		92.90 184	92.04 192	95.49 165	94.95 303	92.83 82	97.16 175	98.24 50	93.02 119	90.13 254	95.71 233	83.47 183	97.85 301	91.71 181	83.93 360	95.78 276

Effi-MVS+-dtu		93.08 174	93.21 153	92.68 303	96.02 246	83.25 343	97.14 177	96.72 249	93.85 83	91.20 236	93.44 345	83.08 193	98.30 241	91.69 183	95.73 191	96.50 248

UniMVSNet (Re)		93.31 164	92.55 176	95.61 157	95.39 272	93.34 67	97.39 151	98.71 11	93.14 116	90.10 258	94.83 274	87.71 116	98.03 275	91.67 184	83.99 359	95.46 291

LCM-MVSNet-Re		92.50 195	92.52 179	92.44 305	96.82 187	81.89 360	96.92 194	93.71 377	92.41 139	84.30 365	94.60 286	85.08 158	97.03 356	91.51 185	97.36 154	98.40 157

FC-MVSNet-test		93.94 143	93.57 136	95.04 183	95.48 267	91.45 134	98.12 50	98.71 11	93.37 103	90.23 249	96.70 174	87.66 117	97.85 301	91.49 186	90.39 289	95.83 272

PMMVS		92.86 186	92.34 184	94.42 220	94.92 306	86.73 284	94.53 331	96.38 271	84.78 353	94.27 153	95.12 263	83.13 192	98.40 229	91.47 187	96.49 178	98.12 177

Vis-MVSNet		95.23 101	94.81 104	96.51 94	97.18 159	91.58 127	98.26 34	98.12 73	94.38 70	94.90 138	98.15 79	82.28 214	98.92 178	91.45 188	98.58 112	99.01 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		94.15 132	93.51 142	96.06 128	98.27 86	89.38 210	95.18 315	98.48 24	85.60 338	93.76 166	97.11 154	83.15 191	99.61 76	91.33 189	98.72 105	99.19 75

OMC-MVS		95.09 105	94.70 108	96.25 120	98.46 73	91.28 138	96.43 236	97.57 158	92.04 152	94.77 142	97.96 94	87.01 134	99.09 157	91.31 190	96.77 170	98.36 161

MG-MVS		95.61 91	95.38 91	96.31 111	98.42 76	90.53 170	96.04 265	97.48 170	93.47 100	95.67 123	98.10 80	89.17 92	99.25 131	91.27 191	98.77 103	99.13 81

ACMM	89.79 8	92.96 180	92.50 180	94.35 222	96.30 230	88.71 231	97.58 123	97.36 196	91.40 171	90.53 243	96.65 178	79.77 258	98.75 197	91.24 192	91.64 266	95.59 286
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WTY-MVS		94.71 119	94.02 126	96.79 78	97.71 132	92.05 109	96.59 229	97.35 197	90.61 204	94.64 144	96.93 161	86.41 141	99.39 118	91.20 193	94.71 216	98.94 102

testing11		91.68 231	90.75 245	94.47 216	96.53 212	86.56 290	95.76 282	94.51 356	91.10 185	91.24 234	93.59 339	68.59 366	98.86 183	91.10 194	94.29 221	98.00 186

tt0805		91.09 265	90.07 277	94.16 233	95.61 260	88.31 242	97.56 126	96.51 265	89.56 233	89.17 288	95.64 238	67.08 379	98.38 235	91.07 195	88.44 307	95.80 274

Anonymous20240529		91.98 220	90.73 247	95.73 150	98.14 102	89.40 209	97.99 62	97.72 139	79.63 395	93.54 170	97.41 138	69.94 355	99.56 92	91.04 196	91.11 277	98.22 167

AUN-MVS		91.76 227	90.75 245	94.81 198	97.00 175	88.57 235	96.65 220	96.49 266	89.63 231	92.15 203	96.12 210	78.66 280	98.50 222	90.83 197	79.18 386	97.36 222

mvsany_test3		83.59 364	82.44 368	87.03 383	83.80 416	73.82 405	93.70 362	90.92 404	86.42 324	82.51 381	90.26 387	46.76 416	95.71 380	90.82 198	76.76 393	91.57 396

CANet_DTU		94.37 125	93.65 134	96.55 88	96.46 221	92.13 107	96.21 258	96.67 256	94.38 70	93.53 171	97.03 159	79.34 265	99.71 53	90.76 199	98.45 118	97.82 200

ab-mvs		93.57 156	92.55 176	96.64 81	97.28 155	91.96 114	95.40 300	97.45 180	89.81 228	93.22 181	96.28 201	79.62 262	99.46 110	90.74 200	93.11 244	98.50 144

CostFormer		91.18 264	90.70 249	92.62 304	94.84 311	81.76 361	94.09 350	94.43 357	84.15 359	92.72 191	93.77 330	79.43 264	98.20 248	90.70 201	92.18 259	97.90 190

Anonymous202405211		92.07 217	90.83 241	95.76 145	98.19 98	88.75 230	97.58 123	95.00 336	86.00 333	93.64 167	97.45 134	66.24 384	99.53 98	90.68 202	92.71 250	99.01 94

testing99		91.62 233	90.72 248	94.32 225	96.48 218	86.11 302	95.81 278	94.76 348	91.55 163	91.75 217	93.44 345	68.55 367	98.82 187	90.43 203	93.69 237	98.04 184

tpmrst		91.44 246	91.32 218	91.79 328	95.15 294	79.20 391	93.42 371	95.37 318	88.55 272	93.49 172	93.67 336	82.49 210	98.27 243	90.41 204	89.34 298	97.90 190

thisisatest0530		93.03 177	92.21 188	95.49 165	97.07 165	89.11 224	97.49 140	92.19 393	90.16 217	94.09 158	96.41 195	76.43 306	99.05 167	90.38 205	95.68 193	98.31 163

UA-Net		95.95 81	95.53 82	97.20 67	97.67 134	92.98 80	97.65 113	98.13 71	94.81 46	96.61 83	98.35 58	88.87 96	99.51 103	90.36 206	97.35 155	99.11 85

UniMVSNet_ETH3D		91.34 254	90.22 270	94.68 206	94.86 310	87.86 259	97.23 169	97.46 175	87.99 287	89.90 263	96.92 164	66.35 382	98.23 245	90.30 207	90.99 280	97.96 187

tttt0517		92.96 180	92.33 185	94.87 195	97.11 163	87.16 275	97.97 69	92.09 394	90.63 202	93.88 164	97.01 160	76.50 303	99.06 166	90.29 208	95.45 198	98.38 159

testing91		91.90 223	91.02 231	94.53 215	96.54 210	86.55 291	95.86 275	95.64 307	91.77 158	91.89 212	93.47 344	69.94 355	98.86 183	90.23 209	93.86 236	98.18 170

FA-MVS(test-final)		93.52 158	92.92 159	95.31 172	96.77 193	88.54 237	94.82 323	96.21 282	89.61 232	94.20 155	95.25 257	83.24 187	99.14 149	90.01 210	96.16 182	98.25 165

IS-MVSNet		94.90 112	94.52 116	96.05 129	97.67 134	90.56 169	98.44 21	96.22 280	93.21 108	93.99 160	97.74 113	85.55 153	98.45 226	89.98 211	97.86 139	99.14 80

miper_enhance_ethall		91.54 241	91.01 232	93.15 284	95.35 277	87.07 277	93.97 352	96.90 237	86.79 319	89.17 288	93.43 348	86.55 138	97.64 321	89.97 212	86.93 321	94.74 343

EI-MVSNet		93.03 177	92.88 161	93.48 271	95.77 255	86.98 278	96.44 234	97.12 211	90.66 200	91.30 229	97.64 123	86.56 137	98.05 271	89.91 213	90.55 286	95.41 293

IterMVS-LS		92.29 207	91.94 197	93.34 276	96.25 231	86.97 279	96.57 232	97.05 221	90.67 198	89.50 278	94.80 276	86.59 136	97.64 321	89.91 213	86.11 329	95.40 296
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		91.21 260	90.56 255	93.14 285	96.09 244	86.80 281	94.41 337	96.58 263	87.80 295	88.58 302	93.99 323	80.85 239	97.62 324	89.87 215	86.93 321	94.99 320

CDS-MVSNet		94.14 135	93.54 138	95.93 138	96.18 235	91.46 133	96.33 248	97.04 223	88.97 255	93.56 168	96.51 190	87.55 121	97.89 299	89.80 216	95.95 185	98.44 154
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WR-MVS		92.34 203	91.53 211	94.77 203	95.13 296	90.83 160	96.40 242	97.98 106	91.88 156	89.29 284	95.54 244	82.50 209	97.80 307	89.79 217	85.27 339	95.69 283

NR-MVSNet		92.34 203	91.27 222	95.53 162	94.95 303	93.05 77	97.39 151	98.07 85	92.65 135	84.46 363	95.71 233	85.00 159	97.77 311	89.71 218	83.52 366	95.78 276

Anonymous20231211		90.63 285	89.42 300	94.27 230	98.24 90	89.19 222	98.05 57	97.89 114	79.95 393	88.25 312	94.96 266	72.56 334	98.13 254	89.70 219	85.14 341	95.49 287

testdata				95.46 169	98.18 100	88.90 228		97.66 145	82.73 375	97.03 67	98.07 83	90.06 82	98.85 185	89.67 220	98.98 95	98.64 132

Baseline_NR-MVSNet		91.20 261	90.62 251	92.95 291	93.83 346	88.03 253	97.01 187	95.12 332	88.42 276	89.70 269	95.13 262	83.47 183	97.44 340	89.66 221	83.24 368	93.37 371

DPM-MVS		95.69 87	94.92 102	98.01 20	98.08 108	95.71 9	95.27 309	97.62 152	90.43 211	95.55 126	97.07 156	91.72 50	99.50 106	89.62 222	98.94 97	98.82 121

XXY-MVS		92.16 213	91.23 224	94.95 192	94.75 315	90.94 156	97.47 141	97.43 187	89.14 247	88.90 292	96.43 194	79.71 259	98.24 244	89.56 223	87.68 313	95.67 284

miper_ehance_all_eth		91.59 235	91.13 228	92.97 290	95.55 264	86.57 289	94.47 333	96.88 240	87.77 297	88.88 294	94.01 321	86.22 143	97.54 330	89.49 224	86.93 321	94.79 339

WBMVS		90.69 284	89.99 280	92.81 297	96.48 218	85.00 320	95.21 314	96.30 275	89.46 238	89.04 291	94.05 320	72.45 335	97.82 305	89.46 225	87.41 318	95.61 285

XVG-ACMP-BASELINE		90.93 274	90.21 271	93.09 286	94.31 334	85.89 303	95.33 304	97.26 203	91.06 186	89.38 280	95.44 249	68.61 365	98.60 214	89.46 225	91.05 278	94.79 339

thisisatest0515		92.29 207	91.30 220	95.25 174	96.60 202	88.90 228	94.36 339	92.32 392	87.92 289	93.43 174	94.57 287	77.28 298	99.00 171	89.42 227	95.86 188	97.86 196

c3_l		91.38 249	90.89 235	92.88 294	95.58 262	86.30 296	94.68 326	96.84 244	88.17 282	88.83 297	94.23 311	85.65 152	97.47 337	89.36 228	84.63 349	94.89 329

AdaColmap		94.34 126	93.68 133	96.31 111	98.59 69	91.68 122	96.59 229	97.81 130	89.87 223	92.15 203	97.06 157	83.62 182	99.54 96	89.34 229	98.07 133	97.70 205

TranMVSNet+NR-MVSNet		92.50 195	91.63 207	95.14 178	94.76 314	92.07 108	97.53 131	98.11 76	92.90 129	89.56 275	96.12 210	83.16 190	97.60 326	89.30 230	83.20 369	95.75 280

D2MVS		91.30 256	90.95 234	92.35 308	94.71 318	85.52 308	96.18 260	98.21 54	88.89 258	86.60 346	93.82 328	79.92 256	97.95 291	89.29 231	90.95 281	93.56 367

1314		92.81 190	92.03 193	95.14 178	95.33 281	89.52 204	96.04 265	97.44 184	87.72 300	86.25 349	95.33 251	83.84 177	98.79 191	89.26 232	97.05 166	97.11 232

v2v482		91.59 235	90.85 239	93.80 255	93.87 345	88.17 250	96.94 193	96.88 240	89.54 234	89.53 276	94.90 270	81.70 226	98.02 276	89.25 233	85.04 345	95.20 311

114514_t		93.95 142	93.06 155	96.63 83	99.07 37	91.61 124	97.46 143	97.96 108	77.99 401	93.00 184	97.57 128	86.14 147	99.33 122	89.22 234	99.15 83	98.94 102

PAPM_NR		95.01 106	94.59 110	96.26 117	98.89 54	90.68 167	97.24 165	97.73 137	91.80 157	92.93 189	96.62 186	89.13 93	99.14 149	89.21 235	97.78 142	98.97 98

baseline1		92.82 189	91.90 198	95.55 161	97.20 158	90.77 163	97.19 172	94.58 353	92.20 145	92.36 196	96.34 199	84.16 173	98.21 247	89.20 236	83.90 363	97.68 206

IB-MVS	87.33 17	89.91 303	88.28 319	94.79 202	95.26 288	87.70 263	95.12 317	93.95 372	89.35 242	87.03 338	92.49 361	70.74 347	99.19 137	89.18 237	81.37 377	97.49 216
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	93.87 146	92.95 158	96.63 83	97.10 164	92.49 93	95.64 290	96.64 257	89.05 251	93.00 184	95.79 229	85.77 151	99.45 112	89.16 238	94.35 218	97.96 187

V42		91.58 237	90.87 236	93.73 258	94.05 340	88.50 239	97.32 159	96.97 228	88.80 265	89.71 268	94.33 303	82.54 208	98.05 271	89.01 239	85.07 343	94.64 347

sd_testset		93.10 173	92.45 182	95.05 182	98.09 105	89.21 219	96.89 196	97.64 149	93.18 113	91.79 215	97.28 143	75.35 315	98.65 209	88.99 240	92.84 247	97.28 227

OurMVSNet-221017-0		90.51 289	90.19 272	91.44 337	93.41 360	81.25 364	96.98 190	96.28 276	91.68 161	86.55 347	96.30 200	74.20 324	97.98 280	88.96 241	87.40 319	95.09 316

API-MVS		94.84 115	94.49 117	95.90 139	97.90 123	92.00 111	97.80 94	97.48 170	89.19 246	94.81 140	96.71 172	88.84 97	99.17 142	88.91 242	98.76 104	96.53 246

test-LLR		91.42 247	91.19 226	92.12 316	94.59 322	80.66 370	94.29 344	92.98 384	91.11 183	90.76 241	92.37 364	79.02 273	98.07 268	88.81 243	96.74 171	97.63 207

test-mter		90.19 299	89.54 297	92.12 316	94.59 322	80.66 370	94.29 344	92.98 384	87.68 301	90.76 241	92.37 364	67.67 371	98.07 268	88.81 243	96.74 171	97.63 207

eth_miper_zixun_eth		91.02 269	90.59 253	92.34 310	95.33 281	84.35 329	94.10 349	96.90 237	88.56 271	88.84 296	94.33 303	84.08 174	97.60 326	88.77 245	84.37 356	95.06 318

myMVS_eth3d28		91.52 242	90.97 233	93.17 283	96.91 178	83.24 344	95.61 291	94.96 340	92.24 142	91.98 209	93.28 349	69.31 359	98.40 229	88.71 246	95.68 193	97.88 192

TAMVS		94.01 141	93.46 144	95.64 154	96.16 237	90.45 173	96.71 213	96.89 239	89.27 244	93.46 173	96.92 164	87.29 130	97.94 292	88.70 247	95.74 190	98.53 140

Patchmatch-RL test		87.38 335	86.24 339	90.81 350	88.74 406	78.40 395	88.12 414	93.17 382	87.11 314	82.17 383	89.29 395	81.95 221	95.60 384	88.64 248	77.02 391	98.41 156

baseline2		91.63 232	90.86 237	93.94 248	94.33 332	86.32 295	95.92 272	91.64 398	89.37 241	86.94 342	94.69 280	81.62 227	98.69 205	88.64 248	94.57 217	96.81 241

TESTMET0.1,1		90.06 301	89.42 300	91.97 319	94.41 330	80.62 372	94.29 344	91.97 396	87.28 311	90.44 245	92.47 363	68.79 363	97.67 318	88.50 250	96.60 176	97.61 211

Vis-MVSNet (Re-imp)		94.15 132	93.88 129	94.95 192	97.61 142	87.92 256	98.10 51	95.80 297	92.22 143	93.02 183	97.45 134	84.53 165	97.91 298	88.24 251	97.97 136	99.02 91

1112_ss		93.37 162	92.42 183	96.21 121	97.05 170	90.99 153	96.31 250	96.72 249	86.87 318	89.83 266	96.69 176	86.51 139	99.14 149	88.12 252	93.67 238	98.50 144

UBG		91.55 239	90.76 243	93.94 248	96.52 214	85.06 319	95.22 312	94.54 354	90.47 210	91.98 209	92.71 356	72.02 336	98.74 199	88.10 253	95.26 202	98.01 185

CVMVSNet		91.23 259	91.75 203	89.67 366	95.77 255	74.69 402	96.44 234	94.88 344	85.81 335	92.18 202	97.64 123	79.07 270	95.58 385	88.06 254	95.86 188	98.74 125

MAR-MVS		94.22 128	93.46 144	96.51 94	98.00 114	92.19 106	97.67 110	97.47 173	88.13 286	93.00 184	95.84 223	84.86 161	99.51 103	87.99 255	98.17 130	97.83 199
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		97.89 114	87.41 307	95.22 133	97.68 116	90.25 80	99.54 96	87.95 256	99.12 87	98.49 146

CP-MVSNet		91.89 224	91.24 223	93.82 254	95.05 299	88.57 235	97.82 91	98.19 61	91.70 160	88.21 313	95.76 231	81.96 220	97.52 334	87.86 257	84.65 348	95.37 299

v148		90.99 270	90.38 259	92.81 297	93.83 346	85.80 304	96.78 207	96.68 254	89.45 239	88.75 299	93.93 325	82.96 199	97.82 305	87.83 258	83.25 367	94.80 337

v1144		91.37 251	90.60 252	93.68 263	93.89 344	88.23 247	96.84 201	97.03 225	88.37 277	89.69 270	94.39 298	82.04 218	97.98 280	87.80 259	85.37 336	94.84 331

DIV-MVS_self_test		90.97 272	90.33 260	92.88 294	95.36 276	86.19 300	94.46 335	96.63 260	87.82 293	88.18 314	94.23 311	82.99 196	97.53 332	87.72 260	85.57 333	94.93 325

gm-plane-assit					93.22 364	78.89 394			84.82 352		93.52 341		98.64 210	87.72 260

GeoE		93.89 145	93.28 151	95.72 151	96.96 177	89.75 195	98.24 38	96.92 236	89.47 237	92.12 205	97.21 149	84.42 167	98.39 234	87.71 262	96.50 177	99.01 94

cl____		90.96 273	90.32 261	92.89 293	95.37 275	86.21 299	94.46 335	96.64 257	87.82 293	88.15 315	94.18 314	82.98 197	97.54 330	87.70 263	85.59 332	94.92 327

pmmvs4		90.93 274	89.85 285	94.17 232	93.34 362	90.79 162	94.60 328	96.02 287	84.62 354	87.45 326	95.15 260	81.88 223	97.45 339	87.70 263	87.87 311	94.27 359

Test_1112_low_res		92.84 188	91.84 200	95.85 143	97.04 171	89.97 189	95.53 295	96.64 257	85.38 341	89.65 272	95.18 259	85.86 149	99.10 154	87.70 263	93.58 243	98.49 146

无先验							95.79 280	97.87 118	83.87 364				99.65 65	87.68 266		98.89 113

Fast-Effi-MVS+		93.46 159	92.75 167	95.59 158	96.77 193	90.03 183	96.81 204	97.13 210	88.19 281	91.30 229	94.27 308	86.21 144	98.63 211	87.66 267	96.46 180	98.12 177

CNLPA		94.28 127	93.53 139	96.52 90	98.38 81	92.55 91	96.59 229	96.88 240	90.13 219	91.91 211	97.24 147	85.21 156	99.09 157	87.64 268	97.83 140	97.92 189

v8		91.29 258	90.53 256	93.57 268	94.15 336	88.12 252	97.34 156	97.06 220	88.99 253	88.32 308	94.26 310	83.08 193	98.01 277	87.62 269	83.92 362	94.57 348

pmmvs5		89.86 308	88.87 312	92.82 296	92.86 371	86.23 298	96.26 253	95.39 316	84.24 358	87.12 334	94.51 291	74.27 323	97.36 346	87.61 270	87.57 314	94.86 330

Fast-Effi-MVS+-dtu		92.29 207	91.99 195	93.21 282	95.27 285	85.52 308	97.03 182	96.63 260	92.09 150	89.11 290	95.14 261	80.33 248	98.08 264	87.54 271	94.74 214	96.03 266

OpenMVS	89.19 12	92.86 186	91.68 206	96.40 104	95.34 278	92.73 86	98.27 32	98.12 73	84.86 351	85.78 352	97.75 112	78.89 278	99.74 47	87.50 272	98.65 107	96.73 243

miper_lstm_enhance		90.50 290	90.06 278	91.83 325	95.33 281	83.74 337	93.86 358	96.70 253	87.56 304	87.79 320	93.81 329	83.45 185	96.92 361	87.39 273	84.62 350	94.82 334

IterMVS-SCA-FT		90.31 292	89.81 287	91.82 326	95.52 265	84.20 332	94.30 343	96.15 284	90.61 204	87.39 329	94.27 308	75.80 310	96.44 369	87.34 274	86.88 325	94.82 334

PLC	91.00 6	94.11 136	93.43 146	96.13 125	98.58 71	91.15 151	96.69 216	97.39 191	87.29 310	91.37 225	96.71 172	88.39 105	99.52 102	87.33 275	97.13 165	97.73 203
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		90.25 295	89.74 292	91.76 331	93.92 342	79.73 384	93.98 351	93.54 378	88.28 279	91.99 208	93.25 350	77.51 297	97.44 340	87.30 276	87.94 310	98.12 177

GA-MVS		91.38 249	90.31 262	94.59 208	94.65 320	87.62 264	94.34 340	96.19 283	90.73 194	90.35 247	93.83 326	71.84 338	97.96 287	87.22 277	93.61 241	98.21 168

BH-untuned		92.94 182	92.62 173	93.92 251	97.22 156	86.16 301	96.40 242	96.25 279	90.06 220	89.79 267	96.17 207	83.19 189	98.35 237	87.19 278	97.27 160	97.24 229

v144192		91.06 267	90.28 264	93.39 274	93.66 352	87.23 272	96.83 202	97.07 218	87.43 306	89.69 270	94.28 307	81.48 228	98.00 278	87.18 279	84.92 347	94.93 325

RPSCF		90.75 279	90.86 237	90.42 357	96.84 183	76.29 400	95.61 291	96.34 272	83.89 362	91.38 224	97.87 100	76.45 304	98.78 192	87.16 280	92.23 256	96.20 255

test_f		80.57 373	79.62 375	83.41 390	83.38 419	67.80 417	93.57 369	93.72 376	80.80 390	77.91 400	87.63 406	33.40 422	92.08 410	87.14 281	79.04 388	90.34 405

PS-CasMVS		91.55 239	90.84 240	93.69 262	94.96 302	88.28 244	97.84 86	98.24 50	91.46 167	88.04 317	95.80 226	79.67 260	97.48 336	87.02 282	84.54 354	95.31 303

pm-mvs1		90.72 281	89.65 295	93.96 245	94.29 335	89.63 196	97.79 95	96.82 245	89.07 249	86.12 351	95.48 248	78.61 281	97.78 309	86.97 283	81.67 375	94.46 350

IterMVS		90.15 300	89.67 293	91.61 333	95.48 267	83.72 338	94.33 341	96.12 285	89.99 221	87.31 332	94.15 316	75.78 312	96.27 372	86.97 283	86.89 324	94.83 332
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		93.58 155	92.98 157	95.37 171	98.40 78	88.98 226	97.18 173	97.29 202	87.75 299	90.49 244	97.10 155	85.21 156	99.50 106	86.70 285	96.72 173	97.63 207

PVSNet	86.66 18	92.24 210	91.74 205	93.73 258	97.77 129	83.69 340	92.88 381	96.72 249	87.91 290	93.00 184	94.86 272	78.51 282	99.05 167	86.53 286	97.45 152	98.47 149

v1192		91.07 266	90.23 268	93.58 267	93.70 349	87.82 261	96.73 210	97.07 218	87.77 297	89.58 273	94.32 305	80.90 238	97.97 283	86.52 287	85.48 334	94.95 321

新几何1				97.32 57	98.60 68	93.59 59		97.75 134	81.58 384	95.75 119	97.85 103	90.04 83	99.67 63	86.50 288	99.13 85	98.69 129

v10		91.04 268	90.23 268	93.49 270	94.12 337	88.16 251	97.32 159	97.08 216	88.26 280	88.29 310	94.22 313	82.17 217	97.97 283	86.45 289	84.12 358	94.33 355

v1921920		90.85 276	90.03 279	93.29 278	93.55 353	86.96 280	96.74 209	97.04 223	87.36 308	89.52 277	94.34 302	80.23 250	97.97 283	86.27 290	85.21 340	94.94 323

MDTV_nov1_ep13_2view						70.35 411	93.10 378		83.88 363	93.55 169		82.47 211		86.25 291		98.38 159

test_post1							92.81 383				16.58 431	80.53 243	97.68 317	86.20 292

SCA		91.84 225	91.18 227	93.83 253	95.59 261	84.95 323	94.72 325	95.58 310	90.82 190	92.25 201	93.69 333	75.80 310	98.10 259	86.20 292	95.98 184	98.45 151

PAPR		94.18 129	93.42 148	96.48 97	97.64 138	91.42 135	95.55 293	97.71 143	88.99 253	92.34 199	95.82 225	89.19 91	99.11 152	86.14 294	97.38 153	98.90 109

GBi-Net		91.35 252	90.27 265	94.59 208	96.51 215	91.18 147	97.50 134	96.93 232	88.82 262	89.35 281	94.51 291	73.87 325	97.29 349	86.12 295	88.82 301	95.31 303

test1		91.35 252	90.27 265	94.59 208	96.51 215	91.18 147	97.50 134	96.93 232	88.82 262	89.35 281	94.51 291	73.87 325	97.29 349	86.12 295	88.82 301	95.31 303

FMVSNet3		91.78 226	90.69 250	95.03 184	96.53 212	92.27 101	97.02 184	96.93 232	89.79 229	89.35 281	94.65 284	77.01 299	97.47 337	86.12 295	88.82 301	95.35 300

EPMVS		90.70 282	89.81 287	93.37 275	94.73 317	84.21 331	93.67 365	88.02 413	89.50 236	92.38 195	93.49 342	77.82 295	97.78 309	86.03 298	92.68 251	98.11 180

MVS		91.71 228	90.44 257	95.51 163	95.20 291	91.59 126	96.04 265	97.45 180	73.44 411	87.36 330	95.60 240	85.42 154	99.10 154	85.97 299	97.46 148	95.83 272

testdata2													99.67 63	85.96 300

K. test v3		87.64 334	86.75 336	90.32 359	93.02 368	79.48 389	96.61 226	92.08 395	90.66 200	80.25 392	94.09 318	67.21 375	96.65 367	85.96 300	80.83 379	94.83 332

WR-MVS_H		92.00 219	91.35 216	93.95 246	95.09 298	89.47 205	98.04 58	98.68 13	91.46 167	88.34 307	94.68 281	85.86 149	97.56 328	85.77 302	84.24 357	94.82 334

gg-mvs-nofinetune		87.82 331	85.61 344	94.44 218	94.46 327	89.27 218	91.21 396	84.61 422	80.88 387	89.89 265	74.98 418	71.50 340	97.53 332	85.75 303	97.21 162	96.51 247

tpm2		89.96 302	89.21 304	92.23 315	94.91 308	81.25 364	93.78 360	94.42 358	80.62 391	91.56 220	93.44 345	76.44 305	97.94 292	85.60 304	92.08 263	97.49 216

v1240		90.70 282	89.85 285	93.23 280	93.51 356	86.80 281	96.61 226	97.02 226	87.16 313	89.58 273	94.31 306	79.55 263	97.98 280	85.52 305	85.44 335	94.90 328

PEN-MVS		91.20 261	90.44 257	93.48 271	94.49 326	87.91 258	97.76 97	98.18 63	91.29 173	87.78 321	95.74 232	80.35 247	97.33 347	85.46 306	82.96 370	95.19 314

QAPM		93.45 160	92.27 186	96.98 77	96.77 193	92.62 88	98.39 24	98.12 73	84.50 356	88.27 311	97.77 111	82.39 213	99.81 30	85.40 307	98.81 101	98.51 143

EU-MVSNet		88.72 323	88.90 311	88.20 376	93.15 366	74.21 404	96.63 225	94.22 367	85.18 345	87.32 331	95.97 216	76.16 307	94.98 391	85.27 308	86.17 327	95.41 293

BH-w/o		92.14 215	91.75 203	93.31 277	96.99 176	85.73 305	95.67 285	95.69 303	88.73 267	89.26 286	94.82 275	82.97 198	98.07 268	85.26 309	96.32 181	96.13 262

FMVSNet2		91.31 255	90.08 274	94.99 186	96.51 215	92.21 103	97.41 146	96.95 230	88.82 262	88.62 300	94.75 278	73.87 325	97.42 342	85.20 310	88.55 306	95.35 300

PM-MVS		83.48 365	81.86 371	88.31 375	87.83 410	77.59 397	93.43 370	91.75 397	86.91 316	80.63 388	89.91 391	44.42 417	95.84 378	85.17 311	76.73 394	91.50 398

LF4IMVS		87.94 330	87.25 327	89.98 363	92.38 383	80.05 382	94.38 338	95.25 326	87.59 303	84.34 364	94.74 279	64.31 391	97.66 320	84.83 312	87.45 315	92.23 389

PatchmatchNet		91.91 222	91.35 216	93.59 266	95.38 273	84.11 333	93.15 376	95.39 316	89.54 234	92.10 206	93.68 335	82.82 202	98.13 254	84.81 313	95.32 200	98.52 141
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		87.81 332	86.19 340	92.69 302	91.32 388	86.30 296	97.34 156	96.41 270	80.59 392	84.05 372	94.37 300	67.37 374	97.67 318	84.75 314	79.51 385	94.09 362

v7n		90.76 278	89.86 284	93.45 273	93.54 354	87.60 265	97.70 109	97.37 194	88.85 259	87.65 323	94.08 319	81.08 233	98.10 259	84.68 315	83.79 364	94.66 346

SixPastTwentyTwo		89.15 316	88.54 316	90.98 345	93.49 357	80.28 378	96.70 214	94.70 349	90.78 191	84.15 368	95.57 241	71.78 339	97.71 316	84.63 316	85.07 343	94.94 323

TDRefinement		86.53 343	84.76 355	91.85 324	82.23 421	84.25 330	96.38 244	95.35 319	84.97 350	84.09 370	94.94 267	65.76 388	98.34 240	84.60 317	74.52 399	92.97 374

ACMH	87.59 16	90.53 287	89.42 300	93.87 252	96.21 232	87.92 256	97.24 165	96.94 231	88.45 275	83.91 373	96.27 202	71.92 337	98.62 213	84.43 318	89.43 297	95.05 319
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	87.92 14	90.20 298	89.18 305	93.25 279	96.48 218	86.45 293	96.99 189	96.68 254	88.83 261	84.79 362	96.22 204	70.16 352	98.53 220	84.42 319	88.04 309	94.77 342

test_vis3_rt		72.73 379	70.55 382	79.27 393	80.02 422	68.13 416	93.92 356	74.30 430	76.90 404	58.99 421	73.58 421	20.29 430	95.37 388	84.16 320	72.80 404	74.31 418

FE-MVS		92.05 218	91.05 230	95.08 181	96.83 185	87.93 255	93.91 357	95.70 301	86.30 327	94.15 157	94.97 265	76.59 302	99.21 135	84.10 321	96.86 167	98.09 181

MS-PatchMatch		90.27 294	89.77 289	91.78 329	94.33 332	84.72 326	95.55 293	96.73 248	86.17 331	86.36 348	95.28 254	71.28 342	97.80 307	84.09 322	98.14 131	92.81 377

PatchMatch-RL		92.90 184	92.02 194	95.56 159	98.19 98	90.80 161	95.27 309	97.18 206	87.96 288	91.86 214	95.68 236	80.44 245	98.99 172	84.01 323	97.54 147	96.89 239

lessismore_v0				90.45 356	91.96 386	79.09 393		87.19 416		80.32 391	94.39 298	66.31 383	97.55 329	84.00 324	76.84 392	94.70 344

UWE-MVS		89.91 303	89.48 299	91.21 341	95.88 248	78.23 396	94.91 322	90.26 406	89.11 248	92.35 198	94.52 290	68.76 364	97.96 287	83.95 325	95.59 196	97.42 220

CMPMVS	62.92 21	85.62 357	84.92 353	87.74 379	89.14 401	73.12 409	94.17 347	96.80 246	73.98 408	73.65 407	94.93 268	66.36 381	97.61 325	83.95 325	91.28 274	92.48 385
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVP-Stereo		90.74 280	90.08 274	92.71 301	93.19 365	88.20 248	95.86 275	96.27 277	86.07 332	84.86 361	94.76 277	77.84 294	97.75 313	83.88 327	98.01 135	92.17 392
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LS3D		93.57 156	92.61 174	96.47 98	97.59 144	91.61 124	97.67 110	97.72 139	85.17 346	90.29 248	98.34 61	84.60 163	99.73 49	83.85 328	98.27 125	98.06 183

DTE-MVSNet		90.56 286	89.75 291	93.01 288	93.95 341	87.25 270	97.64 117	97.65 147	90.74 193	87.12 334	95.68 236	79.97 255	97.00 359	83.33 329	81.66 376	94.78 341

BH-RMVSNet		92.72 193	91.97 196	94.97 190	97.16 160	87.99 254	96.15 261	95.60 308	90.62 203	91.87 213	97.15 153	78.41 284	98.57 218	83.16 330	97.60 146	98.36 161

pmmvs-eth3d		86.22 349	84.45 357	91.53 334	88.34 408	87.25 270	94.47 333	95.01 335	83.47 370	79.51 395	89.61 393	69.75 357	95.71 380	83.13 331	76.73 394	91.64 394

FMVSNet1		89.88 306	88.31 318	94.59 208	95.41 271	91.18 147	97.50 134	96.93 232	86.62 321	87.41 328	94.51 291	65.94 387	97.29 349	83.04 332	87.43 316	95.31 303

testing222		90.31 292	88.96 309	94.35 222	96.54 210	87.29 267	95.50 296	93.84 375	90.97 188	91.75 217	92.96 353	62.18 399	98.00 278	82.86 333	94.08 229	97.76 202

MDTV_nov1_ep13			90.76 243		95.22 289	80.33 376	93.03 379	95.28 323	88.14 285	92.84 190	93.83 326	81.34 229	98.08 264	82.86 333	94.34 219

TR-MVS		91.48 245	90.59 253	94.16 233	96.40 224	87.33 266	95.67 285	95.34 322	87.68 301	91.46 223	95.52 245	76.77 301	98.35 237	82.85 335	93.61 241	96.79 242

dmvs_re		90.21 297	89.50 298	92.35 308	95.47 270	85.15 316	95.70 284	94.37 362	90.94 189	88.42 304	93.57 340	74.63 320	95.67 382	82.80 336	89.57 296	96.22 254

JIA-IIPM		88.26 328	87.04 332	91.91 321	93.52 355	81.42 363	89.38 408	94.38 361	80.84 388	90.93 238	80.74 415	79.22 267	97.92 295	82.76 337	91.62 267	96.38 252

PVSNet_0	82.17 19	85.46 358	83.64 361	90.92 346	95.27 285	79.49 388	90.55 400	95.60 308	83.76 366	83.00 380	89.95 390	71.09 343	97.97 283	82.75 338	60.79 420	95.31 303

ambc				86.56 385	83.60 418	70.00 412	85.69 416	94.97 338		80.60 389	88.45 399	37.42 420	96.84 364	82.69 339	75.44 398	92.86 376

USDC		88.94 318	87.83 323	92.27 312	94.66 319	84.96 322	93.86 358	95.90 291	87.34 309	83.40 375	95.56 242	67.43 373	98.19 250	82.64 340	89.67 295	93.66 366

ITE_SJBPF				92.43 306	95.34 278	85.37 313		95.92 289	91.47 166	87.75 322	96.39 197	71.00 344	97.96 287	82.36 341	89.86 293	93.97 363

UnsupCasMVSNet_eth		85.99 352	84.45 357	90.62 354	89.97 396	82.40 356	93.62 367	97.37 194	89.86 224	78.59 398	92.37 364	65.25 390	95.35 389	82.27 342	70.75 406	94.10 360

GG-mvs-BLEND				93.62 264	93.69 350	89.20 220	92.39 388	83.33 424		87.98 319	89.84 392	71.00 344	96.87 363	82.08 343	95.40 199	94.80 337

thres600view7		92.49 197	91.60 208	95.18 176	97.91 122	89.47 205	97.65 113	94.66 350	92.18 149	93.33 176	94.91 269	78.06 291	99.10 154	81.61 344	94.06 233	96.98 234

LTVRE_ROB	88.41 13	90.99 270	89.92 283	94.19 231	96.18 235	89.55 201	96.31 250	97.09 215	87.88 291	85.67 353	95.91 220	78.79 279	98.57 218	81.50 345	89.98 291	94.44 352
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		89.83 309	89.15 306	91.89 323	94.92 306	80.30 377	93.11 377	95.46 315	86.28 328	88.08 316	92.65 357	80.44 245	98.52 221	81.47 346	89.92 292	96.84 240

thres100view900		92.43 198	91.58 209	94.98 188	97.92 121	89.37 211	97.71 106	94.66 350	92.20 145	93.31 177	94.90 270	78.06 291	99.08 160	81.40 347	94.08 229	96.48 249

tfpn200view9		92.38 201	91.52 212	94.95 192	97.85 125	89.29 215	97.41 146	94.88 344	92.19 147	93.27 179	94.46 296	78.17 287	99.08 160	81.40 347	94.08 229	96.48 249

thres400		92.42 199	91.52 212	95.12 180	97.85 125	89.29 215	97.41 146	94.88 344	92.19 147	93.27 179	94.46 296	78.17 287	99.08 160	81.40 347	94.08 229	96.98 234

mvs5depth		86.53 343	85.08 350	90.87 347	88.74 406	82.52 352	91.91 390	94.23 366	86.35 326	87.11 336	93.70 332	66.52 380	97.76 312	81.37 350	75.80 396	92.31 388

ETVMVS		90.52 288	89.14 307	94.67 207	96.81 189	87.85 260	95.91 273	93.97 371	89.71 230	92.34 199	92.48 362	65.41 389	97.96 287	81.37 350	94.27 222	98.21 168

DP-MVS		92.76 191	91.51 214	96.52 90	98.77 56	90.99 153	97.38 153	96.08 286	82.38 377	89.29 284	97.87 100	83.77 178	99.69 59	81.37 350	96.69 174	98.89 113

thres200		92.23 211	91.39 215	94.75 205	97.61 142	89.03 225	96.60 228	95.09 333	92.08 151	93.28 178	94.00 322	78.39 285	99.04 170	81.26 353	94.18 225	96.19 256

CR-MVSNet		90.82 277	89.77 289	93.95 246	94.45 328	87.19 273	90.23 402	95.68 305	86.89 317	92.40 193	92.36 367	80.91 236	97.05 355	81.09 354	93.95 234	97.60 212

ttmdpeth		85.91 354	84.76 355	89.36 370	89.14 401	80.25 379	95.66 288	93.16 383	83.77 365	83.39 376	95.26 256	66.24 384	95.26 390	80.65 355	75.57 397	92.57 381

MSDG		91.42 247	90.24 267	94.96 191	97.15 162	88.91 227	93.69 364	96.32 273	85.72 337	86.93 343	96.47 192	80.24 249	98.98 173	80.57 356	95.05 207	96.98 234

dp		88.90 320	88.26 320	90.81 350	94.58 324	76.62 398	92.85 382	94.93 341	85.12 347	90.07 261	93.07 351	75.81 309	98.12 257	80.53 357	87.42 317	97.71 204

tpm cat1		88.36 326	87.21 329	91.81 327	95.13 296	80.55 373	92.58 385	95.70 301	74.97 407	87.45 326	91.96 374	78.01 293	98.17 252	80.39 358	88.74 304	96.72 244

KD-MVS_self_test		85.95 353	84.95 352	88.96 373	89.55 400	79.11 392	95.13 316	96.42 269	85.91 334	84.07 371	90.48 385	70.03 354	94.82 392	80.04 359	72.94 403	92.94 375

AllTest		90.23 296	88.98 308	93.98 242	97.94 119	86.64 285	96.51 233	95.54 312	85.38 341	85.49 355	96.77 170	70.28 350	99.15 146	80.02 360	92.87 245	96.15 260

TestCases				93.98 242	97.94 119	86.64 285		95.54 312	85.38 341	85.49 355	96.77 170	70.28 350	99.15 146	80.02 360	92.87 245	96.15 260

ADS-MVSNet2		89.45 313	88.59 315	92.03 318	95.86 249	82.26 357	90.93 397	94.32 365	83.23 372	91.28 232	91.81 376	79.01 275	95.99 374	79.52 362	91.39 272	97.84 197

ADS-MVSNet		89.89 305	88.68 314	93.53 269	95.86 249	84.89 324	90.93 397	95.07 334	83.23 372	91.28 232	91.81 376	79.01 275	97.85 301	79.52 362	91.39 272	97.84 197

our_test_3		88.78 322	87.98 322	91.20 343	92.45 381	82.53 351	93.61 368	95.69 303	85.77 336	84.88 360	93.71 331	79.99 254	96.78 366	79.47 364	86.24 326	94.28 358

EPNet_dtu		91.71 228	91.28 221	92.99 289	93.76 348	83.71 339	96.69 216	95.28 323	93.15 115	87.02 339	95.95 218	83.37 186	97.38 345	79.46 365	96.84 168	97.88 192
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		88.94 318	87.56 324	93.08 287	94.35 331	88.45 241	97.73 101	95.23 327	87.47 305	84.26 366	95.29 252	79.86 257	97.33 347	79.44 366	74.44 400	93.45 370

EG-PatchMatch MVS		87.02 340	85.44 345	91.76 331	92.67 375	85.00 320	96.08 264	96.45 268	83.41 371	79.52 394	93.49 342	57.10 405	97.72 315	79.34 367	90.87 283	92.56 382

Patchmtry		88.64 324	87.25 327	92.78 299	94.09 338	86.64 285	89.82 406	95.68 305	80.81 389	87.63 324	92.36 367	80.91 236	97.03 356	78.86 368	85.12 342	94.67 345

FMVSNet5		87.29 336	85.79 343	91.78 329	94.80 313	87.28 268	95.49 297	95.28 323	84.09 360	83.85 374	91.82 375	62.95 395	94.17 397	78.48 369	85.34 338	93.91 364

COLMAP_ROB	87.81 15	90.40 291	89.28 303	93.79 256	97.95 118	87.13 276	96.92 194	95.89 293	82.83 374	86.88 345	97.18 150	73.77 328	99.29 129	78.44 370	93.62 240	94.95 321
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		86.42 346	85.44 345	89.34 371	90.33 393	79.79 383	96.73 210	95.92 289	83.71 367	83.25 377	91.36 380	63.92 392	96.01 373	78.39 371	85.36 337	92.22 390

test0.0.03 1		89.37 315	88.70 313	91.41 338	92.47 380	85.63 306	95.22 312	92.70 389	91.11 183	86.91 344	93.65 337	79.02 273	93.19 408	78.00 372	89.18 299	95.41 293

MIMVSNet		88.50 325	86.76 335	93.72 260	94.84 311	87.77 262	91.39 392	94.05 368	86.41 325	87.99 318	92.59 360	63.27 393	95.82 379	77.44 373	92.84 247	97.57 214

MDA-MVSNet_test_wron		85.87 355	84.23 359	90.80 352	92.38 383	82.57 350	93.17 374	95.15 330	82.15 378	67.65 413	92.33 370	78.20 286	95.51 386	77.33 374	79.74 382	94.31 357

YYNet1		85.87 355	84.23 359	90.78 353	92.38 383	82.46 355	93.17 374	95.14 331	82.12 379	67.69 411	92.36 367	78.16 289	95.50 387	77.31 375	79.73 383	94.39 353

UnsupCasMVSNet_bld		82.13 371	79.46 376	90.14 361	88.00 409	82.47 354	90.89 399	96.62 262	78.94 398	75.61 402	84.40 413	56.63 406	96.31 371	77.30 376	66.77 414	91.63 395

KD-MVS_2432*1600		84.81 361	82.64 365	91.31 339	91.07 390	85.34 314	91.22 394	95.75 299	85.56 339	83.09 378	90.21 388	67.21 375	95.89 375	77.18 377	62.48 418	92.69 378

miper_refine_blended		84.81 361	82.64 365	91.31 339	91.07 390	85.34 314	91.22 394	95.75 299	85.56 339	83.09 378	90.21 388	67.21 375	95.89 375	77.18 377	62.48 418	92.69 378

PCF-MVS	89.48 11	91.56 238	89.95 281	96.36 109	96.60 202	92.52 92	92.51 386	97.26 203	79.41 396	88.90 292	96.56 188	84.04 176	99.55 94	77.01 379	97.30 159	97.01 233
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		89.88 306	89.56 296	90.82 349	94.57 325	83.06 346	95.65 289	92.85 386	87.86 292	90.83 240	94.10 317	79.66 261	96.88 362	76.34 380	94.19 224	92.54 383

testgi		87.97 329	87.21 329	90.24 360	92.86 371	80.76 368	96.67 219	94.97 338	91.74 159	85.52 354	95.83 224	62.66 397	94.47 395	76.25 381	88.36 308	95.48 288

TinyColmap		86.82 341	85.35 348	91.21 341	94.91 308	82.99 347	93.94 354	94.02 370	83.58 368	81.56 384	94.68 281	62.34 398	98.13 254	75.78 382	87.35 320	92.52 384

ppachtmachnet_test		88.35 327	87.29 326	91.53 334	92.45 381	83.57 341	93.75 361	95.97 288	84.28 357	85.32 358	94.18 314	79.00 277	96.93 360	75.71 383	84.99 346	94.10 360

PAPM		91.52 242	90.30 263	95.20 175	95.30 284	89.83 193	93.38 372	96.85 243	86.26 329	88.59 301	95.80 226	84.88 160	98.15 253	75.67 384	95.93 186	97.63 207

WAC-MVS						79.53 386								75.56 385

myMVS_eth3d		87.18 337	86.38 338	89.58 367	95.16 292	79.53 386	95.00 319	93.93 373	88.55 272	86.96 340	91.99 372	56.23 407	94.00 399	75.47 386	94.11 226	95.20 311

CL-MVSNet_self_test		86.31 348	85.15 349	89.80 365	88.83 404	81.74 362	93.93 355	96.22 280	86.67 320	85.03 359	90.80 383	78.09 290	94.50 393	74.92 387	71.86 405	93.15 373

tfpnnormal		89.70 311	88.40 317	93.60 265	95.15 294	90.10 182	97.56 126	98.16 67	87.28 311	86.16 350	94.63 285	77.57 296	98.05 271	74.48 388	84.59 352	92.65 380

DSMNet-mixed		86.34 347	86.12 342	87.00 384	89.88 397	70.43 410	94.93 321	90.08 407	77.97 402	85.42 357	92.78 355	74.44 322	93.96 401	74.43 389	95.14 203	96.62 245

Patchmatch-test		89.42 314	87.99 321	93.70 261	95.27 285	85.11 317	88.98 409	94.37 362	81.11 385	87.10 337	93.69 333	82.28 214	97.50 335	74.37 390	94.76 212	98.48 148

LCM-MVSNet		72.55 380	69.39 384	82.03 391	70.81 431	65.42 420	90.12 404	94.36 364	55.02 421	65.88 415	81.72 414	24.16 429	89.96 412	74.32 391	68.10 412	90.71 404

new-patchmatchnet		83.18 367	81.87 370	87.11 382	86.88 412	75.99 401	93.70 362	95.18 329	85.02 349	77.30 401	88.40 400	65.99 386	93.88 402	74.19 392	70.18 407	91.47 399

MVStest1		82.38 370	80.04 374	89.37 369	87.63 411	82.83 348	95.03 318	93.37 381	73.90 409	73.50 408	94.35 301	62.89 396	93.25 407	73.80 393	65.92 415	92.04 393

testing3		87.67 333	86.88 334	90.05 362	96.14 240	80.71 369	97.10 179	92.85 386	90.15 218	87.54 325	94.55 288	55.70 408	94.10 398	73.77 394	94.10 228	95.35 300

MDA-MVSNet-bldmvs		85.00 359	82.95 364	91.17 344	93.13 367	83.33 342	94.56 330	95.00 336	84.57 355	65.13 417	92.65 357	70.45 349	95.85 377	73.57 395	77.49 390	94.33 355

pmmvs3		79.97 374	77.50 379	87.39 381	82.80 420	79.38 390	92.70 384	90.75 405	70.69 412	78.66 397	87.47 408	51.34 412	93.40 404	73.39 396	69.65 408	89.38 407

test_method		66.11 388	64.89 390	69.79 405	72.62 429	35.23 437	65.19 424	92.83 388	20.35 427	65.20 416	88.08 404	43.14 418	82.70 422	73.12 397	63.46 417	91.45 400

PatchT		88.87 321	87.42 325	93.22 281	94.08 339	85.10 318	89.51 407	94.64 352	81.92 380	92.36 196	88.15 403	80.05 253	97.01 358	72.43 398	93.65 239	97.54 215

Anonymous20231206		87.09 339	86.14 341	89.93 364	91.22 389	80.35 375	96.11 262	95.35 319	83.57 369	84.16 367	93.02 352	73.54 330	95.61 383	72.16 399	86.14 328	93.84 365

MVS-HIRNet		82.47 369	81.21 372	86.26 386	95.38 273	69.21 413	88.96 410	89.49 408	66.28 415	80.79 387	74.08 420	68.48 368	97.39 344	71.93 400	95.47 197	92.18 391

new_pmnet		82.89 368	81.12 373	88.18 377	89.63 398	80.18 380	91.77 391	92.57 390	76.79 405	75.56 404	88.23 402	61.22 400	94.48 394	71.43 401	82.92 371	89.87 406

TAPA-MVS	90.10 7	92.30 206	91.22 225	95.56 159	98.33 83	89.60 198	96.79 205	97.65 147	81.83 381	91.52 221	97.23 148	87.94 112	98.91 180	71.31 402	98.37 121	98.17 173
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		86.14 351	85.40 347	88.35 374	90.12 394	80.06 381	95.90 274	95.20 328	88.59 268	81.29 385	93.62 338	71.43 341	92.65 409	71.26 403	81.17 378	92.34 386

tmp_tt		51.94 395	53.82 395	46.29 411	33.73 435	45.30 435	78.32 421	67.24 432	18.02 428	50.93 424	87.05 409	52.99 410	53.11 430	70.76 404	25.29 428	40.46 426

MIMVSNet1		84.93 360	83.05 362	90.56 355	89.56 399	84.84 325	95.40 300	95.35 319	83.91 361	80.38 390	92.21 371	57.23 404	93.34 405	70.69 405	82.75 373	93.50 368

APD_test1		79.31 375	77.70 378	84.14 388	89.11 403	69.07 414	92.36 389	91.50 399	69.07 413	73.87 406	92.63 359	39.93 419	94.32 396	70.54 406	80.25 381	89.02 408

RPMNet		88.98 317	87.05 331	94.77 203	94.45 328	87.19 273	90.23 402	98.03 97	77.87 403	92.40 193	87.55 407	80.17 251	99.51 103	68.84 407	93.95 234	97.60 212

UWE-MVS-28		86.81 342	86.41 337	88.02 378	92.87 370	74.60 403	95.38 302	86.70 418	88.17 282	87.28 333	94.67 283	70.83 346	93.30 406	67.45 408	94.31 220	96.17 257

N_pmnet		78.73 376	78.71 377	78.79 394	92.80 373	46.50 433	94.14 348	43.71 435	78.61 399	80.83 386	91.66 378	74.94 318	96.36 370	67.24 409	84.45 355	93.50 368

OpenMVS_ROB	81.14 20	84.42 363	82.28 369	90.83 348	90.06 395	84.05 335	95.73 283	94.04 369	73.89 410	80.17 393	91.53 379	59.15 401	97.64 321	66.92 410	89.05 300	90.80 403

PMMVS2		70.19 382	66.92 386	80.01 392	76.35 425	65.67 419	86.22 415	87.58 415	64.83 417	62.38 418	80.29 417	26.78 427	88.49 419	63.79 411	54.07 422	85.88 409

test_0402		86.46 345	84.79 354	91.45 336	95.02 300	85.55 307	96.29 252	94.89 343	80.90 386	82.21 382	93.97 324	68.21 370	97.29 349	62.98 412	88.68 305	91.51 397

DeepMVS_CX				74.68 403	90.84 392	64.34 421		81.61 426	65.34 416	67.47 414	88.01 405	48.60 415	80.13 425	62.33 413	73.68 402	79.58 415

Syy-MVS		87.13 338	87.02 333	87.47 380	95.16 292	73.21 408	95.00 319	93.93 373	88.55 272	86.96 340	91.99 372	75.90 308	94.00 399	61.59 414	94.11 226	95.20 311

testf1		69.31 384	66.76 387	76.94 398	78.61 423	61.93 422	88.27 412	86.11 420	55.62 419	59.69 419	85.31 411	20.19 431	89.32 413	57.62 415	69.44 410	79.58 415

APD_test2		69.31 384	66.76 387	76.94 398	78.61 423	61.93 422	88.27 412	86.11 420	55.62 419	59.69 419	85.31 411	20.19 431	89.32 413	57.62 415	69.44 410	79.58 415

EGC-MVSNET		68.77 386	63.01 392	86.07 387	92.49 379	82.24 358	93.96 353	90.96 403	0.71 432	2.62 433	90.89 382	53.66 409	93.46 403	57.25 417	84.55 353	82.51 413

dmvs_testset		81.38 372	82.60 367	77.73 395	91.74 387	51.49 430	93.03 379	84.21 423	89.07 249	78.28 399	91.25 381	76.97 300	88.53 418	56.57 418	82.24 374	93.16 372

FPMVS		71.27 381	69.85 383	75.50 401	74.64 426	59.03 426	91.30 393	91.50 399	58.80 418	57.92 422	88.28 401	29.98 425	85.53 421	53.43 419	82.84 372	81.95 414

ANet_high		63.94 390	59.58 393	77.02 397	61.24 433	66.06 418	85.66 417	87.93 414	78.53 400	42.94 425	71.04 422	25.42 428	80.71 424	52.60 420	30.83 426	84.28 412

Gipuma		67.86 387	65.41 389	75.18 402	92.66 376	73.45 406	66.50 423	94.52 355	53.33 422	57.80 423	66.07 423	30.81 423	89.20 415	48.15 421	78.88 389	62.90 423
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		69.99 383	69.33 385	71.98 404	88.78 405	61.64 424	89.86 405	59.93 434	75.67 406	74.96 405	85.45 410	50.19 413	81.66 423	43.86 422	55.27 421	72.63 419

PMVS	53.92 22	58.58 391	55.40 394	68.12 406	51.00 434	48.64 431	78.86 420	87.10 417	46.77 423	35.84 429	74.28 419	8.76 433	86.34 420	42.07 423	73.91 401	69.38 420
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	50.73 23	53.25 393	48.81 398	66.58 408	65.34 432	57.50 427	72.49 422	70.94 431	40.15 426	39.28 428	63.51 424	6.89 435	73.48 428	38.29 424	42.38 424	68.76 422
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		76.77 377	76.63 380	77.18 396	85.32 414	56.82 428	94.53 331	89.39 409	82.66 376	71.35 409	89.18 396	75.03 317	88.88 416	35.42 425	66.79 413	85.84 410

SSC-MVS		76.05 378	75.83 381	76.72 400	84.77 415	56.22 429	94.32 342	88.96 411	81.82 382	70.52 410	88.91 397	74.79 319	88.71 417	33.69 426	64.71 416	85.23 411

E-PMN		53.28 392	52.56 396	55.43 409	74.43 427	47.13 432	83.63 419	76.30 427	42.23 424	42.59 426	62.22 425	28.57 426	74.40 426	31.53 427	31.51 425	44.78 424

kuosan		65.27 389	64.66 391	67.11 407	83.80 416	61.32 425	88.53 411	60.77 433	68.22 414	67.67 412	80.52 416	49.12 414	70.76 429	29.67 428	53.64 423	69.26 421

EMVS		52.08 394	51.31 397	54.39 410	72.62 429	45.39 434	83.84 418	75.51 429	41.13 425	40.77 427	59.65 426	30.08 424	73.60 427	28.31 429	29.90 427	44.18 425

wuyk23d		25.11 396	24.57 400	26.74 412	73.98 428	39.89 436	57.88 425	9.80 436	12.27 429	10.39 430	6.97 432	7.03 434	36.44 431	25.43 430	17.39 429	3.89 429

testmvs		13.36 398	16.33 401	4.48 414	5.04 436	2.26 439	93.18 373	3.28 437	2.70 430	8.24 431	21.66 428	2.29 437	2.19 432	7.58 431	2.96 430	9.00 428

test123		13.04 399	15.66 402	5.18 413	4.51 437	3.45 438	92.50 387	1.81 438	2.50 431	7.58 432	20.15 429	3.67 436	2.18 433	7.13 432	1.07 431	9.90 427

mmdepth		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

monomultidepth		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

test_blank		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

uanet_test		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

DCPMVS		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

cdsmvs_eth3d_5k		23.24 397	30.99 399	0.00 415	0.00 438	0.00 440	0.00 426	97.63 151	0.00 433	0.00 434	96.88 166	84.38 168	0.00 434	0.00 433	0.00 432	0.00 430

pcd_1.5k_mvsjas		7.39 401	9.85 404	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	88.65 101	0.00 434	0.00 433	0.00 432	0.00 430

sosnet-low-res		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

sosnet		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

uncertanet		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

Regformer		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

ab-mvs-re		8.06 400	10.74 403	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	96.69 176	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

uanet		0.00 402	0.00 405	0.00 415	0.00 438	0.00 440	0.00 426	0.00 439	0.00 433	0.00 434	0.00 433	0.00 438	0.00 434	0.00 433	0.00 432	0.00 430

FOURS1					99.55 1	93.34 67	99.29 1	98.35 30	94.98 36	98.49 27

test_one_0601					99.32 22	95.20 20		98.25 48	95.13 30	98.48 28	98.87 22	95.16 7

eth-test2					0.00 438

eth-test					0.00 438

test_241102_ONE					99.42 7	95.30 17		98.27 42	95.09 33	99.19 7	98.81 28	95.54 5	99.65 65

save fliter					98.91 52	94.28 38	97.02 184	98.02 100	95.35 23

test0726					99.45 3	95.36 13	98.31 27	98.29 37	94.92 39	98.99 11	98.92 17	95.08 8

GSMVS																98.45 151

test_part2					99.28 25	95.74 8				98.10 34

sam_mvs1												82.76 203				98.45 151

sam_mvs												81.94 222

MTGPA								98.08 80

test_post											17.58 430	81.76 224	98.08 264

patchmatchnet-post											90.45 386	82.65 207	98.10 259

MTMP							97.86 82	82.03 425

TEST9					98.70 59	94.19 42	96.41 238	98.02 100	88.17 282	96.03 108	97.56 130	92.74 33	99.59 81

test_8					98.67 61	94.06 49	96.37 245	98.01 103	88.58 269	95.98 112	97.55 132	92.73 34	99.58 84

agg_prior					98.67 61	93.79 55		98.00 104		95.68 122			99.57 91

test_prior4						93.66 58	96.42 237

test_prior				97.23 64	98.67 61	92.99 79		98.00 104					99.41 116			99.29 67

新几何2							95.79 280

旧先验1					98.38 81	93.38 64		97.75 134			98.09 82	92.30 45			99.01 94	99.16 77

原ACMM2							95.67 285

test222					98.24 90	92.21 103	95.33 304	97.60 153	79.22 397	95.25 131	97.84 105	88.80 98			99.15 83	98.72 126

segment_acmp												92.89 30

testdata1							95.26 311		93.10 118

test12				97.65 43	98.46 73	94.26 39		97.66 145		95.52 129		90.89 73	99.46 110		99.25 72	99.22 74

plane_prior7					96.21 232	89.98 188

plane_prior6					96.10 243	90.00 184						81.32 230

plane_prior4											96.64 179

plane_prior3						90.00 184			94.46 64	91.34 226

plane_prior2							97.74 99		94.85 41

plane_prior1					96.14 240

plane_prior						89.99 186	97.24 165		94.06 76						92.16 260

n2								0.00 439

nn								0.00 439

door-mid								91.06 402

test11								97.88 116

door								91.13 401

HQP5-MVS						89.33 213

HQP-NCC					95.86 249		96.65 220		93.55 92	90.14 250

ACMP_Plane					95.86 249		96.65 220		93.55 92	90.14 250

HQP4-MVS										90.14 250			98.50 222			95.78 276

HQP3-MVS								97.39 191							92.10 261

HQP2-MVS												80.95 234

NP-MVS					95.99 247	89.81 194					95.87 221

ACMMP++_ref															90.30 290

ACMMP++															91.02 279

Test By Simon												88.73 100

High-resolution multi-view benchmark