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.

OPU-MVS				99.49 4	99.64 23	98.51 4	99.77 29				99.19 45	95.12 9	99.97 26	99.90 1	99.92 3	99.99 2

PC_three_1452									94.60 51	99.41 11	99.12 63	95.50 7	99.96 34	99.84 2	99.92 3	99.97 8

MM		97.76 12	97.39 22	98.86 6	98.30 105	96.83 8	99.81 20	99.13 9	97.66 2	98.29 60	98.96 88	85.84 144	99.90 62	99.72 3	98.80 105	99.85 35

MGCNet		97.81 10	97.51 16	98.74 10	98.97 81	96.57 12	99.91 3	98.17 39	97.45 5	98.76 39	98.97 83	86.69 123	99.96 34	99.72 3	98.92 96	99.69 65

SED-MVS		98.18 2	98.10 4	98.41 19	99.63 24	95.24 29	99.77 29	97.72 98	94.17 59	99.30 17	99.54 4	93.32 22	99.98 14	99.70 5	99.81 23	99.99 2

test_241102_TWO								97.72 98	94.17 59	99.23 20	99.54 4	93.14 27	99.98 14	99.70 5	99.82 19	99.99 2

IU-MVS					99.63 24	95.38 26		97.73 97	95.54 37	99.54 9				99.69 7	99.81 23	99.99 2

fmvsm_s_conf0.5_n_8		97.06 33	96.94 30	97.44 53	97.78 124	92.77 106	99.83 15	97.83 78	97.58 3	99.25 19	99.20 41	82.71 206	99.92 50	99.64 8	98.61 117	99.64 76

DVP-MVS		98.07 7	98.00 7	98.29 20	99.66 18	95.20 34	99.72 38	97.47 164	93.95 66	99.07 26	99.46 15	93.18 25	99.97 26	99.64 8	99.82 19	99.69 65
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				98.77 9	99.66 18	96.37 15	99.72 38	97.68 109					99.98 14	99.64 8	99.82 19	99.96 11

patch_mono-2		97.10 31	97.97 9	94.49 242	99.21 69	83.73 377	99.62 60	98.25 34	95.28 41	99.38 14	98.91 96	92.28 33	99.94 41	99.61 11	99.22 78	99.78 46

DPE-MVS		98.11 6	98.00 7	98.44 17	99.50 48	95.39 25	99.29 105	97.72 98	94.50 52	98.64 44	99.54 4	93.32 22	99.97 26	99.58 12	99.90 7	99.95 16
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.5_n_11		96.80 41	96.97 29	96.28 130	98.09 114	92.26 119	99.87 6	96.49 261	97.55 4	99.75 3	99.32 28	83.20 191	99.91 57	99.57 13	98.88 99	96.67 297

fmvsm_l_conf0.5_n_a		97.70 14	97.80 12	97.42 56	97.59 136	92.91 102	99.86 9	98.04 56	96.70 19	99.58 8	99.26 30	90.90 44	99.94 41	99.57 13	98.66 115	99.40 104

fmvsm_s_conf0.5_n_9		96.76 45	96.92 31	96.29 129	97.95 119	89.21 217	99.81 20	97.55 145	97.04 14	99.68 5	99.22 37	82.84 200	99.94 41	99.56 15	98.61 117	99.71 60

test-260524					99.74 11	96.14 17		97.62 130		97.79 77		91.57 36	100.00 1	99.55 16	99.75 29

fmvsm_l_conf0.5_n		97.65 15	97.72 13	97.41 57	97.51 142	92.78 105	99.85 12	98.05 54	96.78 17	99.60 7	99.23 35	90.42 57	99.92 50	99.55 16	98.50 124	99.55 87

MSC_two_6792asdad				99.51 2	99.61 30	98.60 2		97.69 107					99.98 14	99.55 16	99.83 15	99.96 11

No_MVS				99.51 2	99.61 30	98.60 2		97.69 107					99.98 14	99.55 16	99.83 15	99.96 11

MED-MVS test				97.84 37	99.75 8	93.67 73	99.65 52	98.11 47	92.89 100	98.58 49	99.53 8		100.00 1	99.53 20	99.64 44	99.87 32

MED-MVS		98.04 8	98.10 4	97.86 36	99.75 8	93.67 73	99.65 52	98.11 47	94.03 64	98.58 49	99.49 12	93.98 18	100.00 1	99.53 20	99.75 29	99.90 23

ME-MVS		97.59 16	97.51 16	97.84 37	99.73 12	93.67 73	99.52 72	98.07 50	92.38 114	98.32 59	99.53 8	90.83 48	99.97 26	99.53 20	99.64 44	99.87 32

fmvsm_l_conf0.5_n_9		97.33 22	97.32 24	97.37 60	97.64 131	92.45 115	99.93 1	97.85 72	97.39 6	99.84 2	99.09 69	85.42 153	99.92 50	99.52 23	99.20 82	99.73 58

fmvsm_s_conf0.5_n_10		96.95 35	96.82 40	97.33 62	97.76 125	93.00 97	99.87 6	97.95 62	97.32 9	99.71 4	99.20 41	81.48 230	99.90 62	99.32 24	98.78 109	99.09 135

fmvsm_s_conf0.5_n_2		95.85 84	95.83 78	95.91 157	97.19 161	91.79 128	99.78 28	97.65 122	97.23 10	99.22 22	99.06 73	75.93 304	99.90 62	99.30 25	97.09 163	96.02 317

DeepPCF-MVS	93.56 1	96.55 57	97.84 11	92.68 308	98.71 97	78.11 442	99.70 41	97.71 102	98.18 1	97.36 85	99.76 1	90.37 59	99.94 41	99.27 26	99.54 58	99.99 2

fmvsm_s_conf0.5_n_3		96.58 54	96.55 50	96.66 104	97.23 157	92.59 112	99.81 20	97.82 79	97.35 7	99.42 10	99.16 51	80.27 243	99.93 47	99.26 27	98.60 119	97.45 269

APDe-MVS		97.53 17	97.47 18	97.70 45	99.58 36	93.63 76	99.56 65	97.52 154	93.59 83	98.01 71	99.12 63	90.80 49	99.55 129	99.26 27	99.79 27	99.93 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
DVP-MVS++		98.18 2	98.09 6	98.44 17	99.61 30	95.38 26	99.55 66	97.68 109	93.01 93	99.23 20	99.45 19	95.12 9	99.98 14	99.25 29	99.92 3	99.97 8

test_0728_THIRD									93.01 93	99.07 26	99.46 15	94.66 14	99.97 26	99.25 29	99.82 19	99.95 16

fmvsm_s_conf0.5_n_5		96.46 59	96.23 62	97.15 73	96.42 197	92.80 104	99.83 15	97.39 178	94.50 52	98.71 40	99.13 60	82.52 209	99.90 62	99.24 31	98.38 128	98.74 181

fmvsm_l_conf0.5_n_3		97.12 29	96.89 34	97.79 44	97.39 147	93.84 71	99.87 6	97.70 103	97.34 8	99.39 13	99.20 41	82.86 198	99.94 41	99.21 32	99.07 85	99.58 86

dcpmvs_2		95.67 96	96.18 65	94.12 262	98.82 93	84.22 370	97.37 339	95.45 383	90.70 156	95.77 133	98.63 123	90.47 55	98.68 197	99.20 33	99.22 78	99.45 100

fmvsm_s_conf0.5_n_7		95.87 82	96.25 61	94.72 230	96.19 212	87.74 272	99.66 50	97.94 64	95.78 31	98.44 53	99.23 35	81.26 236	99.90 62	99.17 34	98.57 121	96.52 305

fmvsm_s_conf0.5_n		96.19 67	96.49 52	95.30 196	97.37 149	89.16 220	99.86 9	98.47 26	95.68 34	98.87 34	99.15 55	82.44 216	99.92 50	99.14 35	97.43 154	96.83 291

test_fmvsmconf_n		96.78 43	96.84 37	96.61 106	95.99 223	90.25 175	99.90 4	98.13 45	96.68 20	98.42 54	98.92 95	85.34 155	99.88 72	99.12 36	99.08 83	99.70 62

test_fmvsm_n_1920		97.08 32	97.55 15	95.67 168	97.94 120	89.61 206	99.93 1	98.48 25	97.08 12	99.08 25	99.13 60	88.17 88	99.93 47	99.11 37	99.06 86	97.47 268

fmvsm_s_conf0.5_n_4		96.17 68	96.49 52	95.21 202	97.06 172	89.26 215	99.76 32	98.07 50	95.99 28	99.35 15	99.22 37	82.19 220	99.89 70	99.06 38	97.68 145	96.49 306

fmvsm_s_conf0.5_n_6		96.78 43	96.64 48	97.20 70	96.03 222	93.20 90	99.82 19	97.68 109	95.20 42	99.61 6	99.11 67	84.52 169	99.90 62	99.04 39	98.77 110	98.50 211

TSAR-MVS + GP.		96.95 35	96.91 33	97.07 74	98.88 91	91.62 135	99.58 63	96.54 255	95.09 44	96.84 100	98.63 123	91.16 37	99.77 108	99.04 39	96.42 175	99.81 40

fmvsm_s_conf0.1_n_2		95.24 109	95.04 109	95.83 160	95.60 237	91.71 134	99.65 52	96.18 286	96.99 15	98.79 38	98.91 96	73.91 328	99.87 76	99.00 41	96.30 179	95.91 319

MCST-MVS		98.18 2	97.95 10	98.86 6	99.85 4	96.60 11	99.70 41	97.98 61	97.18 11	95.96 124	99.33 27	92.62 29	100.00 1	98.99 42	99.93 1	99.98 7

CNVR-MVS		98.46 1	98.38 1	98.72 11	99.80 5	96.19 16	99.80 26	97.99 60	97.05 13	99.41 11	99.59 3	92.89 28	100.00 1	98.99 42	99.90 7	99.96 11

test_fmvsmconf0.1_n		95.94 79	95.79 84	96.40 120	92.42 378	89.92 192	99.79 27	96.85 230	96.53 24	97.22 88	98.67 119	82.71 206	99.84 88	98.92 44	98.98 91	99.43 103

fmvsm_s_conf0.5_n_a		95.97 76	96.19 63	95.31 193	96.51 193	89.01 229	99.81 20	98.39 29	95.46 39	99.19 24	99.16 51	81.44 233	99.91 57	98.83 45	96.97 164	97.01 287

CANet		97.00 34	96.49 52	98.55 13	98.86 92	96.10 18	99.83 15	97.52 154	95.90 29	97.21 89	98.90 98	82.66 208	99.93 47	98.71 46	98.80 105	99.63 79

9.14			96.87 35		99.34 56		99.50 74	97.49 161	89.41 216	98.59 47	99.43 21	89.78 66	99.69 114	98.69 47	99.62 50

SD-MVS		97.51 18	97.40 21	97.81 41	99.01 80	93.79 72	99.33 103	97.38 179	93.73 78	98.83 37	99.02 79	90.87 47	99.88 72	98.69 47	99.74 31	99.77 51
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
balanced_ft_v1		94.96 117	94.35 121	96.78 92	97.54 139	92.05 122	98.03 298	96.20 281	90.90 149	96.83 102	95.51 297	76.75 294	98.77 187	98.68 49	98.70 112	99.52 90

fmvsm_s_conf0.1_n		95.56 98	95.68 87	95.20 204	94.35 318	89.10 222	99.50 74	97.67 114	94.76 49	98.68 43	99.03 77	81.13 237	99.86 82	98.63 50	97.36 156	96.63 298

test9_res														98.60 51	99.87 9	99.90 23

PS-MVSNAJ		96.87 38	96.40 56	98.29 20	97.35 150	97.29 6	99.03 147	97.11 211	95.83 30	98.97 31	99.14 58	82.48 212	99.60 126	98.60 51	99.08 83	98.00 249

xiu_mvs_v2_base		96.66 48	96.17 68	98.11 30	97.11 170	96.96 7	99.01 150	97.04 218	95.51 38	98.86 35	99.11 67	82.19 220	99.36 153	98.59 53	98.14 135	98.00 249

train_agg		97.20 27	97.08 27	97.57 51	99.57 39	93.17 91	99.38 95	97.66 115	90.18 181	98.39 55	99.18 48	90.94 42	99.66 117	98.58 54	99.85 13	99.88 29

reproduce_model		96.57 55	96.75 44	96.02 148	98.93 88	88.46 253	98.56 220	97.34 186	93.18 91	96.96 96	99.35 26	88.69 81	99.80 100	98.53 55	99.21 81	99.79 43

reproduce-ours		96.66 48	96.80 41	96.22 132	98.95 85	89.03 227	98.62 204	97.38 179	93.42 85	96.80 106	99.36 24	88.92 76	99.80 100	98.51 56	99.26 75	99.82 37

our_new_method		96.66 48	96.80 41	96.22 132	98.95 85	89.03 227	98.62 204	97.38 179	93.42 85	96.80 106	99.36 24	88.92 76	99.80 100	98.51 56	99.26 75	99.82 37

TSAR-MVS + MP.		97.44 20	97.46 19	97.39 59	99.12 73	93.49 84	98.52 224	97.50 159	94.46 54	98.99 29	98.64 121	91.58 35	99.08 173	98.49 58	99.83 15	99.60 82
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SF-MVS		97.22 26	96.92 31	98.12 29	99.11 74	94.88 40	99.44 85	97.45 167	89.60 206	98.70 41	99.42 22	90.42 57	99.72 112	98.47 59	99.65 42	99.77 51

BridgeMVS		96.83 39	96.51 51	97.81 41	97.60 135	95.15 36	98.40 248	96.77 236	93.00 95	98.69 42	96.19 278	89.75 67	98.76 190	98.45 60	99.72 34	99.51 93

PHI-MVS		96.65 51	96.46 55	97.21 69	99.34 56	91.77 130	99.70 41	98.05 54	86.48 321	98.05 68	99.20 41	89.33 71	99.96 34	98.38 61	99.62 50	99.90 23

test_fmvsmvis_n_1920		95.47 100	95.40 95	95.70 166	94.33 322	90.22 178	99.70 41	96.98 225	96.80 16	92.75 204	98.89 100	82.46 215	99.92 50	98.36 62	98.33 130	96.97 288

ZD-MVS					99.67 16	93.28 87		97.61 132	87.78 283	97.41 83	99.16 51	90.15 63	99.56 128	98.35 63	99.70 39

test_prior2							99.57 64		91.43 136	98.12 65	98.97 83	90.43 56		98.33 64	99.81 23

SMA-MVS		97.24 24	96.99 28	98.00 33	99.30 60	94.20 64	99.16 122	97.65 122	89.55 210	99.22 22	99.52 11	90.34 60	99.99 9	98.32 65	99.83 15	99.82 37
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
CHOSEN 280x420		96.80 41	96.85 36	96.66 104	97.85 123	94.42 59	94.76 420	98.36 31	92.50 107	95.62 139	97.52 188	97.92 1	97.38 315	98.31 66	98.80 105	98.20 237

test_fmvsmconf0.01_n		94.14 147	93.51 157	96.04 146	86.79 458	89.19 218	99.28 108	95.94 316	95.70 32	95.50 140	98.49 134	73.27 334	99.79 104	98.28 67	98.32 132	99.15 127

NCCC		98.12 5	98.11 3	98.13 27	99.76 7	94.46 56	99.81 20	97.88 68	96.54 22	98.84 36	99.46 15	92.55 30	99.98 14	98.25 68	99.93 1	99.94 19

fmvsm_s_conf0.1_n_a		95.16 111	95.15 103	95.18 205	92.06 385	88.94 235	99.29 105	97.53 150	94.46 54	98.98 30	98.99 81	79.99 246	99.85 86	98.24 69	96.86 168	96.73 295

MSP-MVS		97.77 11	98.18 2	96.53 113	99.54 42	90.14 181	99.41 92	97.70 103	95.46 39	98.60 46	99.19 45	95.71 5	99.49 135	98.15 70	99.85 13	99.95 16
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
ETV-MVS		96.00 73	96.00 73	96.00 151	96.56 189	91.05 153	99.63 59	96.61 245	93.26 90	97.39 84	98.30 145	86.62 125	98.13 232	98.07 71	97.57 147	98.82 168

MSLP-MVS++		97.50 19	97.45 20	97.63 47	99.65 22	93.21 89	99.70 41	98.13 45	94.61 50	97.78 78	99.46 15	89.85 65	99.81 98	97.97 72	99.91 6	99.88 29

APD-MVS		96.95 35	96.72 45	97.63 47	99.51 47	93.58 79	99.16 122	97.44 171	90.08 187	98.59 47	99.07 70	89.06 73	99.42 146	97.92 73	99.66 41	99.88 29
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
SteuartSystems-ACMMP		97.25 23	97.34 23	97.01 77	97.38 148	91.46 140	99.75 35	97.66 115	94.14 63	98.13 63	99.26 30	92.16 34	99.66 117	97.91 74	99.64 44	99.90 23
Skip Steuart: Steuart Systems R&D Blog.
MVSMamba_PlusPlus		95.73 94	95.15 103	97.44 53	97.28 156	94.35 62	98.26 268	96.75 237	83.09 384	97.84 75	95.97 286	89.59 69	98.48 208	97.86 75	99.73 33	99.49 96

test_vis1_n_1920		93.08 199	93.42 160	92.04 321	96.31 204	79.36 428	99.83 15	96.06 301	96.72 18	98.53 51	98.10 153	58.57 437	99.91 57	97.86 75	98.79 108	96.85 290

agg_prior2														97.84 77	99.87 9	99.91 22

lecture		96.67 47	96.77 43	96.39 121	99.27 63	89.71 202	99.65 52	98.62 22	92.28 116	98.62 45	99.07 70	86.74 120	99.79 104	97.83 78	98.82 102	99.66 71

mvsany_test1		94.57 135	95.09 107	92.98 295	95.84 228	82.07 401	98.76 178	95.24 398	92.87 102	96.45 114	98.71 116	84.81 165	99.15 166	97.68 79	95.49 199	97.73 256

HPM-MVS++		97.72 13	97.59 14	98.14 26	99.53 46	94.76 48	99.19 116	97.75 93	95.66 35	98.21 61	99.29 29	91.10 39	99.99 9	97.68 79	99.87 9	99.68 67

test_vis1_n		90.40 275	90.27 257	90.79 356	91.55 397	76.48 452	99.12 137	94.44 424	94.31 57	97.34 86	96.95 238	43.60 483	99.42 146	97.57 81	97.60 146	96.47 307

SR-MVS		96.13 69	96.16 70	96.07 145	99.42 53	89.04 225	98.59 214	97.33 189	90.44 170	96.84 100	99.12 63	86.75 119	99.41 149	97.47 82	99.44 64	99.76 53

PVSNet_BlendedMVS		93.36 186	93.20 169	93.84 275	98.77 95	91.61 137	99.47 78	98.04 56	91.44 135	94.21 166	92.63 357	83.50 182	99.87 76	97.41 83	83.37 350	90.05 431

PVSNet_Blended		95.94 79	95.66 88	96.75 95	98.77 95	91.61 137	99.88 5	98.04 56	93.64 82	94.21 166	97.76 166	83.50 182	99.87 76	97.41 83	97.75 144	98.79 172

mvsmamba		94.27 143	93.91 142	95.35 188	96.42 197	88.61 247	97.77 314	96.38 268	91.17 145	94.05 171	95.27 304	78.41 277	97.96 265	97.36 85	98.40 127	99.48 97

test_fmvs1		92.35 220	92.94 180	90.57 361	97.19 161	75.43 458	99.55 66	94.97 408	95.20 42	96.82 104	97.57 185	59.59 435	99.84 88	97.30 86	98.29 133	96.46 308

EC-MVSNet		95.09 113	95.17 102	94.84 223	95.42 248	88.17 260	99.48 76	95.92 321	91.47 134	97.34 86	98.36 142	82.77 202	97.41 314	97.24 87	98.58 120	98.94 154

MVS_111021_HR		96.69 46	96.69 46	96.72 99	98.58 100	91.00 155	99.14 130	99.45 1	93.86 73	95.15 147	98.73 111	88.48 83	99.76 109	97.23 88	99.56 56	99.40 104

test_fmvs1_n		91.07 255	91.41 228	90.06 375	94.10 331	74.31 462	99.18 118	94.84 412	94.81 47	96.37 117	97.46 192	50.86 470	99.82 95	97.14 89	97.90 138	96.04 315

xiu_mvs_v1_base_debu		94.73 127	93.98 134	96.99 79	95.19 262	95.24 29	98.62 204	96.50 257	92.99 96	97.52 80	98.83 104	72.37 343	99.15 166	97.03 90	96.74 169	96.58 301

xiu_mvs_v1_base		94.73 127	93.98 134	96.99 79	95.19 262	95.24 29	98.62 204	96.50 257	92.99 96	97.52 80	98.83 104	72.37 343	99.15 166	97.03 90	96.74 169	96.58 301

xiu_mvs_v1_base_debi		94.73 127	93.98 134	96.99 79	95.19 262	95.24 29	98.62 204	96.50 257	92.99 96	97.52 80	98.83 104	72.37 343	99.15 166	97.03 90	96.74 169	96.58 301

lupinMVS		96.32 63	95.94 74	97.44 53	95.05 281	94.87 41	99.86 9	96.50 257	93.82 76	98.04 69	98.77 107	85.52 146	98.09 241	96.98 93	98.97 92	99.37 107

SPE-MVS-test		95.98 75	96.34 59	94.90 219	98.06 116	87.66 277	99.69 48	96.10 293	93.66 80	98.35 58	99.05 75	86.28 135	97.66 296	96.96 94	98.90 98	99.37 107

MVS_111021_LR		95.78 88	95.94 74	95.28 197	98.19 111	87.69 273	98.80 171	99.26 7	93.39 87	95.04 149	98.69 118	84.09 176	99.76 109	96.96 94	99.06 86	98.38 220

RRT-MVS		93.39 183	92.64 189	95.64 170	96.11 220	88.75 244	97.40 335	95.77 344	89.46 214	92.70 207	95.42 301	72.98 337	98.81 185	96.91 96	96.97 164	99.37 107

VNet		95.08 114	94.26 123	97.55 52	98.07 115	93.88 69	98.68 191	98.73 17	90.33 174	97.16 92	97.43 194	79.19 259	99.53 132	96.91 96	91.85 278	99.24 120

myMVS_eth3d28		95.74 93	95.34 96	96.92 86	97.41 145	93.58 79	99.28 108	97.70 103	90.97 148	93.91 175	97.25 210	90.59 53	98.75 191	96.85 98	94.14 227	98.44 214

test_cas_vis1_n_1920		93.86 163	93.74 150	94.22 258	95.39 251	86.08 332	99.73 37	96.07 300	96.38 26	97.19 91	97.78 164	65.46 408	99.86 82	96.71 99	98.92 96	96.73 295

CS-MVS		95.75 91	96.19 63	94.40 246	97.88 122	86.22 322	99.66 50	96.12 291	92.69 104	98.07 67	98.89 100	87.09 111	97.59 302	96.71 99	98.62 116	99.39 106

APD-MVS_3200maxsize		95.64 97	95.65 90	95.62 174	99.24 66	87.80 271	98.42 241	97.22 197	88.93 235	96.64 113	98.98 82	85.49 149	99.36 153	96.68 101	99.27 74	99.70 62

SR-MVS-dyc-post		95.75 91	95.86 77	95.41 184	99.22 67	87.26 299	98.40 248	97.21 198	89.63 203	96.67 111	98.97 83	86.73 122	99.36 153	96.62 102	99.31 71	99.60 82

RE-MVS-def			95.70 86		99.22 67	87.26 299	98.40 248	97.21 198	89.63 203	96.67 111	98.97 83	85.24 159		96.62 102	99.31 71	99.60 82

DeepC-MVS_fast	93.52 2	97.16 28	96.84 37	98.13 27	99.61 30	94.45 57	98.85 164	97.64 124	96.51 25	95.88 127	99.39 23	87.35 107	99.99 9	96.61 104	99.69 40	99.96 11
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
VDD-MVS		91.24 252	90.18 258	94.45 245	97.08 171	85.84 343	98.40 248	96.10 293	86.99 303	93.36 189	98.16 151	54.27 457	99.20 163	96.59 105	90.63 303	98.31 229

MP-MVS-pluss		95.80 87	95.30 97	97.29 64	98.95 85	92.66 107	98.59 214	97.14 207	88.95 233	93.12 192	99.25 32	85.62 145	99.94 41	96.56 106	99.48 60	99.28 117
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
diffmvs		94.59 134	94.19 126	95.81 161	95.54 242	90.69 163	98.70 187	95.68 357	91.61 128	95.96 124	97.81 161	80.11 244	98.06 251	96.52 107	95.76 191	98.67 194
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
ACMMP_NAP		96.59 52	96.18 65	97.81 41	98.82 93	93.55 81	98.88 163	97.59 138	90.66 158	97.98 72	99.14 58	86.59 126	100.00 1	96.47 108	99.46 61	99.89 28

onestephybrid01		94.12 148	93.87 145	94.86 222	95.26 256	87.86 269	98.60 211	95.82 340	90.70 156	95.67 137	97.72 173	79.72 248	98.13 232	96.37 109	94.99 210	98.60 204

PAPM		96.35 61	95.94 74	97.58 49	94.10 331	95.25 28	98.93 157	98.17 39	94.26 58	93.94 174	98.72 113	89.68 68	97.88 271	96.36 110	99.29 73	99.62 81

mmtdpeth		83.69 395	82.59 394	86.99 425	92.82 371	76.98 450	96.16 393	91.63 469	82.89 393	92.41 215	82.90 475	54.95 454	98.19 224	96.27 111	53.27 495	85.81 475

MTAPA		96.09 70	95.80 83	96.96 84	99.29 61	91.19 145	97.23 346	97.45 167	92.58 105	94.39 163	99.24 34	86.43 133	99.99 9	96.22 112	99.40 68	99.71 60

diffmvs_AUTHOR		94.30 142	93.92 140	95.45 179	94.77 302	89.92 192	98.55 223	95.68 357	91.33 139	95.83 132	97.64 180	79.58 251	98.05 255	96.19 113	95.66 194	98.37 223

alignmvs		95.77 89	95.00 110	98.06 31	97.35 150	95.68 22	99.71 40	97.50 159	91.50 133	96.16 122	98.61 125	86.28 135	99.00 176	96.19 113	91.74 280	99.51 93

UBG		95.73 94	95.41 94	96.69 101	96.97 176	93.23 88	99.13 135	97.79 87	91.28 141	94.38 164	96.78 256	92.37 32	98.56 202	96.17 115	93.84 233	98.26 230

AstraMVS		93.38 185	93.01 177	94.50 241	93.94 339	86.55 308	98.91 160	95.86 335	93.88 72	92.88 200	97.49 190	75.61 312	98.21 222	96.15 116	92.39 264	98.73 186

sasdasda		95.02 115	93.96 137	98.20 23	97.53 140	95.92 19	98.71 184	96.19 284	91.78 125	95.86 129	98.49 134	79.53 254	99.03 174	96.12 117	91.42 292	99.66 71

canonicalmvs		95.02 115	93.96 137	98.20 23	97.53 140	95.92 19	98.71 184	96.19 284	91.78 125	95.86 129	98.49 134	79.53 254	99.03 174	96.12 117	91.42 292	99.66 71

DELS-MVS		97.12 29	96.60 49	98.68 12	98.03 117	96.57 12	99.84 14	97.84 74	96.36 27	95.20 146	98.24 147	88.17 88	99.83 92	96.11 119	99.60 54	99.64 76
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
jason		95.40 104	94.86 112	97.03 76	92.91 369	94.23 63	99.70 41	96.30 273	93.56 84	96.73 109	98.52 129	81.46 232	97.91 267	96.08 120	98.47 126	98.96 149
jason: jason.
guyue		94.21 145	93.72 151	95.66 169	95.22 259	90.17 180	98.74 180	96.85 230	93.67 79	93.01 197	96.72 260	78.83 268	98.06 251	96.04 121	94.44 221	98.77 177

CP-MVS		96.22 66	96.15 71	96.42 118	99.67 16	89.62 205	99.70 41	97.61 132	90.07 188	96.00 123	99.16 51	87.43 101	99.92 50	96.03 122	99.72 34	99.70 62

MP-MVS		96.00 73	95.82 80	96.54 112	99.47 52	90.13 183	99.36 99	97.41 175	90.64 161	95.49 141	98.95 91	85.51 148	99.98 14	96.00 123	99.59 55	99.52 90
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
testing3-2		95.17 110	94.78 113	96.33 127	97.35 150	92.35 116	99.85 12	98.43 28	90.60 162	92.84 203	97.00 235	90.89 45	98.89 181	95.95 124	90.12 306	97.76 254

MGCFI-Net		94.89 118	93.84 146	98.06 31	97.49 143	95.55 23	98.64 198	96.10 293	91.60 131	95.75 134	98.46 140	79.31 258	98.98 178	95.95 124	91.24 297	99.65 75

TestfortrainingZip a		97.38 21	97.10 26	98.24 22	99.75 8	94.82 46	99.65 52	97.86 70	94.03 64	99.04 28	99.49 12	90.76 51	99.99 9	95.87 126	97.45 153	99.90 23

h-mvs33		92.47 219	91.95 215	94.05 267	97.13 167	85.01 359	98.36 257	98.08 49	93.85 74	96.27 120	96.73 259	83.19 192	99.43 145	95.81 127	68.09 449	97.70 260

hse-mvs2		91.67 240	91.51 226	92.15 318	96.22 208	82.61 397	97.74 318	97.53 150	93.85 74	96.27 120	96.15 279	83.19 192	97.44 312	95.81 127	66.86 457	96.40 310

HFP-MVS		96.42 60	96.26 60	96.90 87	99.69 14	90.96 156	99.47 78	97.81 83	90.54 167	96.88 97	99.05 75	87.57 98	99.96 34	95.65 129	99.72 34	99.78 46

XVS		96.47 58	96.37 57	96.77 93	99.62 28	90.66 165	99.43 89	97.58 140	92.41 111	96.86 98	98.96 88	87.37 103	99.87 76	95.65 129	99.43 65	99.78 46

X-MVStestdata		90.69 266	88.66 297	96.77 93	99.62 28	90.66 165	99.43 89	97.58 140	92.41 111	96.86 98	29.59 536	87.37 103	99.87 76	95.65 129	99.43 65	99.78 46

ACMMPR		96.28 65	96.14 72	96.73 97	99.68 15	90.47 170	99.47 78	97.80 85	90.54 167	96.83 102	99.03 77	86.51 131	99.95 38	95.65 129	99.72 34	99.75 54

HPM-MVS		95.41 103	95.22 101	95.99 152	99.29 61	89.14 221	99.17 121	97.09 215	87.28 298	95.40 142	98.48 137	84.93 162	99.38 151	95.64 133	99.65 42	99.47 99
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
BP-MVS1		96.59 52	96.36 58	97.29 64	95.05 281	94.72 50	99.44 85	97.45 167	92.71 103	96.41 116	98.50 131	94.11 17	98.50 203	95.61 134	97.97 137	98.66 199

test_yl		95.27 107	94.60 116	97.28 66	98.53 101	92.98 98	99.05 145	98.70 18	86.76 313	94.65 158	97.74 170	87.78 95	99.44 142	95.57 135	92.61 255	99.44 101

DCV-MVSNet		95.27 107	94.60 116	97.28 66	98.53 101	92.98 98	99.05 145	98.70 18	86.76 313	94.65 158	97.74 170	87.78 95	99.44 142	95.57 135	92.61 255	99.44 101

hybridnocas07		93.98 153	93.52 155	95.36 185	95.01 284	89.37 212	98.63 200	95.64 363	90.79 155	94.69 156	97.31 204	79.01 261	98.11 236	95.54 137	95.07 208	98.61 202

hybrid		93.89 160	93.41 161	95.33 191	94.98 287	89.30 214	98.58 217	95.70 353	89.70 200	94.76 153	97.54 187	78.98 262	98.07 248	95.52 138	94.92 211	98.61 202

region2R		96.30 64	96.17 68	96.70 100	99.70 13	90.31 174	99.46 82	97.66 115	90.55 166	97.07 93	99.07 70	86.85 117	99.97 26	95.43 139	99.74 31	99.81 40

EI-MVSNet-Vis-set		95.76 90	95.63 92	96.17 139	99.14 72	90.33 173	98.49 230	97.82 79	91.92 123	94.75 154	98.88 102	87.06 113	99.48 139	95.40 140	97.17 161	98.70 190

MonoMVSNet		90.69 266	89.78 263	93.45 286	91.78 393	84.97 361	96.51 376	94.44 424	90.56 165	85.96 312	90.97 393	78.61 275	96.27 373	95.35 141	83.79 346	99.11 133

EPNet		96.82 40	96.68 47	97.25 68	98.65 98	93.10 93	99.48 76	98.76 14	96.54 22	97.84 75	98.22 148	87.49 100	99.66 117	95.35 141	97.78 143	99.00 144
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MG-MVS		97.24 24	96.83 39	98.47 16	99.79 6	95.71 21	99.07 141	99.06 10	94.45 56	96.42 115	98.70 117	88.81 79	99.74 111	95.35 141	99.86 12	99.97 8

HY-MVS	88.56 7	95.29 106	94.23 124	98.48 15	97.72 127	96.41 14	94.03 433	98.74 15	92.42 110	95.65 138	94.76 312	86.52 130	99.49 135	95.29 144	92.97 250	99.53 89

testing11		95.33 105	94.98 111	96.37 123	97.20 159	92.31 117	99.29 105	97.68 109	90.59 163	94.43 160	97.20 214	90.79 50	98.60 200	95.25 145	92.38 265	98.18 239

mPP-MVS		95.90 81	95.75 85	96.38 122	99.58 36	89.41 211	99.26 111	97.41 175	90.66 158	94.82 151	98.95 91	86.15 139	99.98 14	95.24 146	99.64 44	99.74 55

viewmamba		93.88 161	93.59 154	94.78 225	94.82 300	87.68 274	98.41 244	95.60 366	91.61 128	94.17 168	97.93 157	79.65 250	98.01 261	95.20 147	94.87 213	98.66 199

ZNCC-MVS		96.09 70	95.81 82	96.95 85	99.42 53	91.19 145	99.55 66	97.53 150	89.72 199	95.86 129	98.94 94	86.59 126	99.97 26	95.13 148	99.56 56	99.68 67

GG-mvs-BLEND				96.98 82	96.53 191	94.81 47	87.20 479	97.74 94		93.91 175	96.40 271	96.56 2	96.94 332	95.08 149	98.95 95	99.20 124

EIA-MVS		95.11 112	95.27 99	94.64 234	96.34 203	86.51 310	99.59 62	96.62 244	92.51 106	94.08 170	98.64 121	86.05 140	98.24 219	95.07 150	98.50 124	99.18 125

DeepC-MVS	91.02 4	94.56 136	93.92 140	96.46 115	97.16 165	90.76 161	98.39 253	97.11 211	93.92 68	88.66 288	98.33 143	78.14 280	99.85 86	95.02 151	98.57 121	98.78 175
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
casdiffmvs_mvg		94.00 151	93.33 165	96.03 147	95.22 259	90.90 159	99.09 139	95.99 304	90.58 164	91.55 235	97.37 198	79.91 247	98.06 251	95.01 152	95.22 204	99.13 130
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
E3new		94.19 146	93.78 149	95.43 182	95.81 229	89.44 210	98.80 171	96.11 292	90.24 178	93.85 177	97.75 167	80.94 240	98.14 229	95.00 153	95.48 200	98.72 187

WTY-MVS		95.97 76	95.11 106	98.54 14	97.62 132	96.65 10	99.44 85	98.74 15	92.25 117	95.21 145	98.46 140	86.56 128	99.46 141	95.00 153	92.69 254	99.50 95

CSCG		94.87 122	94.71 114	95.36 185	99.54 42	86.49 311	99.34 102	98.15 43	82.71 394	90.15 265	99.25 32	89.48 70	99.86 82	94.97 155	98.82 102	99.72 59

EI-MVSNet-UG-set		95.43 101	95.29 98	95.86 159	99.07 78	89.87 194	98.43 238	97.80 85	91.78 125	94.11 169	98.77 107	86.25 137	99.48 139	94.95 156	96.45 174	98.22 235

LuminaMVS		93.16 195	92.30 199	95.76 163	92.26 380	92.64 110	97.60 331	96.21 280	90.30 176	93.06 194	95.59 295	76.00 303	97.89 269	94.93 157	94.70 215	96.76 292

CPTT-MVS		94.60 133	94.43 120	95.09 209	99.66 18	86.85 304	99.44 85	97.47 164	83.22 381	94.34 165	98.96 88	82.50 210	99.55 129	94.81 158	99.50 59	98.88 160

PVSNet_0	83.28 16	87.31 339	85.16 355	93.74 280	94.78 301	84.59 365	98.91 160	98.69 20	89.81 196	78.59 416	93.23 343	61.95 426	99.34 157	94.75 159	55.72 492	97.30 275

CLD-MVS		91.06 257	90.71 249	92.10 319	94.05 335	86.10 331	99.55 66	96.29 276	94.16 61	84.70 322	97.17 218	69.62 366	97.82 275	94.74 160	86.08 327	92.39 344
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
casdiffmvs		93.98 153	93.43 159	95.61 175	95.07 280	89.86 195	98.80 171	95.84 337	90.98 147	92.74 205	97.66 177	79.71 249	98.10 239	94.72 161	95.37 201	98.87 163
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
VDDNet		90.08 287	88.54 303	94.69 231	94.41 316	87.68 274	98.21 274	96.40 264	76.21 447	93.33 190	97.75 167	54.93 455	98.77 187	94.71 162	90.96 298	97.61 266

viewcassd2359sk11		93.95 155	93.48 158	95.36 185	95.48 245	89.25 216	98.74 180	96.10 293	90.10 185	93.48 186	97.55 186	80.05 245	98.14 229	94.66 163	95.16 205	98.69 191

CDPH-MVS		96.56 56	96.18 65	97.70 45	99.59 34	93.92 68	99.13 135	97.44 171	89.02 230	97.90 74	99.22 37	88.90 78	99.49 135	94.63 164	99.79 27	99.68 67

GST-MVS		95.97 76	95.66 88	96.90 87	99.49 51	91.22 143	99.45 84	97.48 162	89.69 201	95.89 126	98.72 113	86.37 134	99.95 38	94.62 165	99.22 78	99.52 90

Effi-MVS+		93.87 162	93.15 171	96.02 148	95.79 230	90.76 161	96.70 370	95.78 342	86.98 306	95.71 135	97.17 218	79.58 251	98.01 261	94.57 166	96.09 186	99.31 114

LFMVS		92.23 226	90.84 245	96.42 118	98.24 108	91.08 152	98.24 271	96.22 279	83.39 379	94.74 155	98.31 144	61.12 430	98.85 183	94.45 167	92.82 251	99.32 113

viewmanbaseed2359cas		93.90 158	93.34 164	95.56 177	95.39 251	89.72 201	98.58 217	96.00 303	90.32 175	93.58 184	97.78 164	78.71 272	98.07 248	94.43 168	95.29 202	98.88 160

NormalMVS		95.87 82	95.83 78	95.99 152	99.27 63	90.37 171	99.14 130	96.39 265	94.92 45	96.30 118	97.98 155	85.33 156	99.23 161	94.35 169	98.82 102	98.37 223

SymmetryMVS		95.49 99	95.27 99	96.17 139	97.13 167	90.37 171	99.14 130	98.59 23	94.92 45	96.30 118	97.98 155	85.33 156	99.23 161	94.35 169	93.67 240	98.92 157

ET-MVSNet_ETH3D		92.56 217	91.45 227	95.88 158	96.39 201	94.13 66	99.46 82	96.97 226	92.18 119	66.94 479	98.29 146	94.65 15	94.28 441	94.34 171	83.82 345	99.24 120

baseline		93.91 157	93.30 166	95.72 165	95.10 278	90.07 185	97.48 333	95.91 328	91.03 146	93.54 185	97.68 175	79.58 251	98.02 260	94.27 172	95.14 206	99.08 139

SDMVSNet		91.09 254	89.91 261	94.65 232	96.80 182	90.54 168	97.78 312	97.81 83	88.34 260	85.73 313	95.26 305	66.44 400	98.26 217	94.25 173	86.75 319	95.14 323

E2		93.62 173	93.07 172	95.26 199	95.00 285	88.99 231	98.63 200	96.09 298	89.84 193	93.02 195	97.36 199	78.88 264	98.11 236	94.23 174	94.60 217	98.67 194

E3		93.62 173	93.07 172	95.26 199	94.98 287	89.00 230	98.63 200	96.09 298	89.83 194	93.01 197	97.35 201	78.90 263	98.11 236	94.23 174	94.60 217	98.67 194

reproduce_monomvs		92.11 230	91.82 219	92.98 295	98.25 106	90.55 167	98.38 255	97.93 65	94.81 47	80.46 387	92.37 359	96.46 3	97.17 321	94.06 176	73.61 416	91.23 399

PAPR		96.35 61	95.82 80	97.94 35	99.63 24	94.19 65	99.42 91	97.55 145	92.43 108	93.82 180	99.12 63	87.30 108	99.91 57	94.02 177	99.06 86	99.74 55

PGM-MVS		95.85 84	95.65 90	96.45 116	99.50 48	89.77 200	98.22 272	98.90 13	89.19 221	96.74 108	98.95 91	85.91 143	99.92 50	93.94 178	99.46 61	99.66 71

Casviewmamba		93.63 172	93.20 169	94.94 217	95.12 269	87.64 278	98.76 178	95.92 321	90.44 170	92.12 221	97.90 158	79.15 260	98.16 228	93.89 179	95.52 197	99.00 144

gg-mvs-nofinetune		90.00 288	87.71 315	96.89 91	96.15 214	94.69 52	85.15 486	97.74 94	68.32 482	92.97 199	60.16 513	96.10 4	96.84 335	93.89 179	98.87 100	99.14 128

MVS		93.92 156	92.28 200	98.83 8	95.69 234	96.82 9	96.22 390	98.17 39	84.89 351	84.34 327	98.61 125	79.32 257	99.83 92	93.88 181	99.43 65	99.86 34

旧先验2							98.67 194		85.75 336	98.96 32			98.97 179	93.84 182

ACMMP		94.67 131	94.30 122	95.79 162	99.25 65	88.13 262	98.41 244	98.67 21	90.38 173	91.43 237	98.72 113	82.22 219	99.95 38	93.83 183	95.76 191	99.29 116
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
BP-MVS														93.82 184

HQP-MVS		91.50 242	91.23 232	92.29 313	93.95 336	86.39 315	99.16 122	96.37 269	93.92 68	87.57 296	96.67 263	73.34 331	97.77 281	93.82 184	86.29 322	92.72 339

DP-MVS Recon		95.85 84	95.15 103	97.95 34	99.87 2	94.38 60	99.60 61	97.48 162	86.58 316	94.42 161	99.13 60	87.36 106	99.98 14	93.64 186	98.33 130	99.48 97

CHOSEN 1792x2688		94.35 140	93.82 147	95.95 155	97.40 146	88.74 245	98.41 244	98.27 33	92.18 119	91.43 237	96.40 271	78.88 264	99.81 98	93.59 187	97.81 140	99.30 115

E4		93.15 197	92.50 194	95.09 209	94.41 316	88.61 247	98.48 232	95.99 304	89.40 217	92.22 218	97.13 220	77.43 286	98.10 239	93.58 188	93.90 232	98.56 207

testing91		94.88 120	94.44 119	96.21 134	97.19 161	91.90 127	99.23 113	97.66 115	89.91 191	93.66 182	97.05 233	90.21 62	98.50 203	93.52 189	91.53 289	98.25 231

testing99		94.88 120	94.45 118	96.17 139	97.20 159	91.91 126	99.20 115	97.66 115	89.95 190	93.68 181	97.06 231	90.28 61	98.50 203	93.52 189	91.54 286	98.12 246

cascas		90.93 261	89.33 277	95.76 163	95.69 234	93.03 96	98.99 152	96.59 249	80.49 423	86.79 308	94.45 315	65.23 410	98.60 200	93.52 189	92.18 272	95.66 322

viewmambaseed2359dif		93.05 201	92.64 189	94.25 255	94.94 292	86.53 309	98.38 255	95.69 356	87.03 302	93.38 188	97.74 170	78.79 270	98.08 243	93.49 192	94.35 224	98.15 241

HQP_MVS		91.26 249	90.95 241	92.16 317	93.84 344	86.07 334	99.02 148	96.30 273	93.38 88	86.99 303	96.52 266	72.92 338	97.75 288	93.46 193	86.17 325	92.67 341

plane_prior5								96.30 273					97.75 288	93.46 193	86.17 325	92.67 341

PVSNet_Blended_VisFu		94.67 131	94.11 129	96.34 125	97.14 166	91.10 150	99.32 104	97.43 173	92.10 122	91.53 236	96.38 274	83.29 188	99.68 115	93.42 195	96.37 176	98.25 231

viewdifsd2359ckpt09		93.54 176	92.91 181	95.44 181	95.57 239	89.48 208	98.68 191	95.66 362	89.52 211	92.50 211	97.75 167	78.46 276	98.03 258	93.32 196	94.69 216	98.81 169

AdaColmap		93.82 164	93.06 174	96.10 144	99.88 1	89.07 224	98.33 259	97.55 145	86.81 311	90.39 260	98.65 120	75.09 314	99.98 14	93.32 196	97.53 150	99.26 119

viewdifsd2359ckpt13		93.45 178	92.86 183	95.21 202	95.45 246	88.91 239	98.59 214	95.92 321	89.39 218	92.67 208	97.33 203	78.02 282	98.03 258	93.27 198	95.12 207	98.69 191

E5new		92.80 204	92.19 203	94.62 236	94.34 319	87.64 278	98.08 291	95.97 307	89.15 223	92.01 222	97.08 228	76.37 298	98.08 243	93.25 199	93.46 242	98.15 241

E6new		92.80 204	92.19 203	94.62 236	94.31 327	87.64 278	98.08 291	95.97 307	89.15 223	92.01 222	97.10 223	76.38 296	98.08 243	93.25 199	93.45 244	98.15 241

E6		92.80 204	92.19 203	94.62 236	94.31 327	87.64 278	98.08 291	95.97 307	89.15 223	92.01 222	97.10 223	76.38 296	98.08 243	93.25 199	93.45 244	98.15 241

E5		92.80 204	92.19 203	94.62 236	94.34 319	87.64 278	98.08 291	95.97 307	89.15 223	92.01 222	97.08 228	76.37 298	98.08 243	93.25 199	93.46 242	98.15 241

HyFIR lowres test		93.68 169	93.29 167	94.87 220	97.57 138	88.04 264	98.18 276	98.47 26	87.57 291	91.24 242	95.05 308	85.49 149	97.46 310	93.22 203	92.82 251	99.10 134

viewdifsd2359ckpt07		92.71 210	92.19 203	94.28 252	94.96 290	86.26 319	98.29 266	95.80 341	88.71 245	90.81 247	97.34 202	76.57 295	98.19 224	93.16 204	94.05 229	98.39 219

HPM-MVS_fast		94.89 118	94.62 115	95.70 166	99.11 74	88.44 254	99.14 130	97.11 211	85.82 333	95.69 136	98.47 138	83.46 184	99.32 158	93.16 204	99.63 49	99.35 110

PMMVS		93.62 173	93.90 143	92.79 301	96.79 184	81.40 409	98.85 164	96.81 232	91.25 142	96.82 104	98.15 152	77.02 292	98.13 232	93.15 206	96.30 179	98.83 167

dtuplus		92.78 208	92.35 197	94.07 264	94.70 304	85.91 338	98.47 235	95.59 368	87.50 294	92.88 200	97.66 177	77.24 289	98.12 235	93.01 207	94.15 226	98.20 237

LCM-MVSNet-Re		88.59 320	88.61 298	88.51 409	95.53 243	72.68 472	96.85 362	88.43 492	88.45 253	73.14 450	90.63 405	75.82 307	94.38 440	92.95 208	95.71 193	98.48 213

viewmacassd2359aftdt		93.16 195	92.44 196	95.31 193	94.34 319	89.19 218	98.40 248	95.84 337	89.62 205	92.87 202	97.31 204	76.07 302	98.00 263	92.93 209	94.58 219	98.75 180

EPP-MVSNet		93.75 166	93.67 152	94.01 269	95.86 227	85.70 345	98.67 194	97.66 115	84.46 361	91.36 240	97.18 217	91.16 37	97.79 279	92.93 209	93.75 238	98.53 209

CostFormer		92.89 203	92.48 195	94.12 262	94.99 286	85.89 340	92.89 446	97.00 224	86.98 306	95.00 150	90.78 397	90.05 64	97.51 308	92.92 211	91.73 281	98.96 149

XVG-OURS-SEG-HR		90.95 260	90.66 252	91.83 324	95.18 265	81.14 416	95.92 398	95.92 321	88.40 257	90.33 261	97.85 159	70.66 360	99.38 151	92.83 212	88.83 311	94.98 326

sss		94.85 123	93.94 139	97.58 49	96.43 196	94.09 67	98.93 157	99.16 8	89.50 212	95.27 144	97.85 159	81.50 229	99.65 121	92.79 213	94.02 230	98.99 146

hybridcas		93.44 179	92.82 185	95.31 193	94.91 295	89.08 223	98.82 167	95.84 337	90.28 177	91.22 243	97.65 179	78.39 278	98.06 251	92.71 214	95.55 196	98.79 172

test_vis1_rt		81.31 415	80.05 417	85.11 442	91.29 402	70.66 478	98.98 154	77.39 511	85.76 335	68.80 470	82.40 478	36.56 493	99.44 142	92.67 215	86.55 321	85.24 482

MAR-MVS		94.43 139	94.09 130	95.45 179	99.10 76	87.47 289	98.39 253	97.79 87	88.37 258	94.02 172	99.17 50	78.64 274	99.91 57	92.48 216	98.85 101	98.96 149
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
viewdifsd2359ckpt11		90.42 274	89.65 265	92.73 306	93.71 351	82.67 393	98.09 288	95.27 393	89.80 197	90.10 267	97.40 196	69.43 368	98.18 226	92.46 217	80.61 367	97.34 272

viewmsd2359difaftdt		90.43 273	89.65 265	92.74 304	93.72 350	82.67 393	98.09 288	95.27 393	89.80 197	90.12 266	97.40 196	69.43 368	98.20 223	92.45 218	80.62 366	97.34 272

API-MVS		94.78 125	94.18 128	96.59 108	99.21 69	90.06 188	98.80 171	97.78 90	83.59 376	93.85 177	99.21 40	83.79 179	99.97 26	92.37 219	99.00 90	99.74 55

nrg030		90.23 280	88.87 291	94.32 251	91.53 398	93.54 82	98.79 176	95.89 331	88.12 268	84.55 324	94.61 314	78.80 269	96.88 334	92.35 220	75.21 398	92.53 343

OMC-MVS		93.90 158	93.62 153	94.73 229	98.63 99	87.00 302	98.04 297	96.56 253	92.19 118	92.46 213	98.73 111	79.49 256	99.14 170	92.16 221	94.34 225	98.03 248

0.3-1-1-0.015		91.27 248	89.64 267	96.15 143	92.69 373	91.62 135	99.74 36	97.35 185	84.68 357	92.71 206	93.18 344	85.31 158	97.75 288	92.11 222	68.98 445	99.09 135

0.4-1-1-0.2		91.19 253	89.53 270	96.20 135	92.78 372	91.76 132	99.76 32	97.34 186	84.77 353	92.54 210	93.05 348	84.51 170	97.74 291	92.01 223	68.98 445	99.09 135

VortexMVS		90.18 283	89.28 278	92.89 299	95.58 238	90.94 158	97.82 309	95.94 316	90.90 149	82.11 364	91.48 381	78.75 271	96.08 382	91.99 224	78.97 375	91.65 369

testing222		94.48 138	94.00 133	95.95 155	97.30 153	92.27 118	98.82 167	97.92 66	89.20 220	94.82 151	97.26 208	87.13 110	97.32 318	91.95 225	91.56 284	98.25 231

1314		93.44 179	91.98 213	97.84 37	95.24 257	94.38 60	96.22 390	97.92 66	90.18 181	82.28 357	97.71 174	77.63 285	99.80 100	91.94 226	98.67 114	99.34 112

0.4-1-1-0.1		91.07 255	89.43 274	96.01 150	92.48 376	91.23 142	99.69 48	97.34 186	84.50 360	92.49 212	92.98 352	84.53 168	97.72 293	91.87 227	68.97 447	99.08 139

DPM-MVS		97.86 9	97.25 25	99.68 1	98.25 106	99.10 1	99.76 32	97.78 90	96.61 21	98.15 62	99.53 8	93.62 19	100.00 1	91.79 228	99.80 26	99.94 19

GDP-MVS		96.05 72	95.63 92	97.31 63	95.37 253	94.65 53	99.36 99	96.42 263	92.14 121	97.07 93	98.53 127	93.33 21	98.50 203	91.76 229	96.66 172	98.78 175

mvs_anonymous		92.50 218	91.65 223	95.06 212	96.60 188	89.64 204	97.06 354	96.44 262	86.64 315	84.14 328	93.93 325	82.49 211	96.17 378	91.47 230	96.08 187	99.35 110

baseline2		94.04 150	93.80 148	94.74 228	93.07 368	90.25 175	98.12 282	98.16 42	89.86 192	86.53 309	96.95 238	95.56 6	98.05 255	91.44 231	94.53 220	95.93 318

IB-MVS	89.43 6	92.12 228	90.83 247	95.98 154	95.40 250	90.78 160	99.81 20	98.06 52	91.23 144	85.63 316	93.66 333	90.63 52	98.78 186	91.22 232	71.85 434	98.36 226
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
ab-mvs		91.05 258	89.17 280	96.69 101	95.96 224	91.72 133	92.62 450	97.23 196	85.61 337	89.74 275	93.89 327	68.55 374	99.42 146	91.09 233	87.84 314	98.92 157

XVG-OURS		90.83 262	90.49 254	91.86 323	95.23 258	81.25 413	95.79 406	95.92 321	88.96 232	90.02 269	98.03 154	71.60 353	99.35 156	91.06 234	87.78 315	94.98 326

3Dnovator	87.35 11	93.17 194	91.77 221	97.37 60	95.41 249	93.07 94	98.82 167	97.85 72	91.53 132	82.56 350	97.58 184	71.97 348	99.82 95	91.01 235	99.23 77	99.22 123

VPA-MVSNet		89.10 303	87.66 316	93.45 286	92.56 374	91.02 154	97.97 302	98.32 32	86.92 308	86.03 311	92.01 365	68.84 373	97.10 326	90.92 236	75.34 397	92.23 351

PAPM_NR		95.43 101	95.05 108	96.57 111	99.42 53	90.14 181	98.58 217	97.51 156	90.65 160	92.44 214	98.90 98	87.77 97	99.90 62	90.88 237	99.32 70	99.68 67

3Dnovator+	87.72 8	93.43 181	91.84 218	98.17 25	95.73 233	95.08 37	98.92 159	97.04 218	91.42 137	81.48 377	97.60 182	74.60 317	99.79 104	90.84 238	98.97 92	99.64 76

test_fmvs2		85.10 376	85.45 352	84.02 450	89.85 419	65.63 489	98.49 230	92.59 454	90.45 169	85.43 319	93.32 339	43.94 481	96.59 345	90.81 239	84.19 340	89.85 435

gm-plane-assit					94.69 305	88.14 261			88.22 265		97.20 214		98.29 215	90.79 240

MVSTER		92.71 210	92.32 198	93.86 274	97.29 154	92.95 101	99.01 150	96.59 249	90.09 186	85.51 317	94.00 322	94.61 16	96.56 347	90.77 241	83.03 352	92.08 359

ETVMVS		94.50 137	93.90 143	96.31 128	97.48 144	92.98 98	99.07 141	97.86 70	88.09 269	94.40 162	96.90 245	88.35 85	97.28 319	90.72 242	92.25 271	98.66 199

ACMP	87.39 10	88.71 316	88.24 307	90.12 374	93.91 342	81.06 417	98.50 228	95.67 359	89.43 215	80.37 388	95.55 296	65.67 403	97.83 274	90.55 243	84.51 336	91.47 381
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
ECVR-MVS		92.29 223	91.33 229	95.15 206	96.41 199	87.84 270	98.10 285	94.84 412	90.82 153	91.42 239	97.28 206	65.61 405	98.49 207	90.33 244	97.19 159	99.12 131

testdata				95.26 199	98.20 109	87.28 296		97.60 134	85.21 342	98.48 52	99.15 55	88.15 90	98.72 195	90.29 245	99.45 63	99.78 46

LPG-MVS_test		88.86 308	88.47 304	90.06 375	93.35 361	80.95 418	98.22 272	95.94 316	87.73 287	83.17 339	96.11 281	66.28 401	97.77 281	90.19 246	85.19 332	91.46 382

LGP-MVS_train				90.06 375	93.35 361	80.95 418		95.94 316	87.73 287	83.17 339	96.11 281	66.28 401	97.77 281	90.19 246	85.19 332	91.46 382

MVSFormer		94.71 130	94.08 131	96.61 106	95.05 281	94.87 41	97.77 314	96.17 288	86.84 309	98.04 69	98.52 129	85.52 146	95.99 386	89.83 248	98.97 92	98.96 149

test_djsdf		88.26 325	87.73 314	89.84 382	88.05 445	82.21 399	97.77 314	96.17 288	86.84 309	82.41 355	91.95 369	72.07 347	95.99 386	89.83 248	84.50 337	91.32 394

test2506		94.80 124	94.21 125	96.58 109	96.41 199	92.18 121	98.01 299	98.96 11	90.82 153	93.46 187	97.28 206	85.92 141	98.45 209	89.82 250	97.19 159	99.12 131

tpmrst		92.78 208	92.16 208	94.65 232	96.27 206	87.45 290	91.83 457	97.10 214	89.10 229	94.68 157	90.69 401	88.22 87	97.73 292	89.78 251	91.80 279	98.77 177

PLC	91.07 3	94.23 144	94.01 132	94.87 220	99.17 71	87.49 288	99.25 112	96.55 254	88.43 256	91.26 241	98.21 150	85.92 141	99.86 82	89.77 252	97.57 147	97.24 278
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
test1111		92.12 228	91.19 233	94.94 217	96.15 214	87.36 293	98.12 282	94.84 412	90.85 152	90.97 245	97.26 208	65.60 406	98.37 211	89.74 253	97.14 162	99.07 142

CDS-MVSNet		93.47 177	93.04 176	94.76 226	94.75 303	89.45 209	98.82 167	97.03 220	87.91 276	90.97 245	96.48 269	89.06 73	96.36 360	89.50 254	92.81 253	98.49 212
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		89.97 289	90.68 251	87.81 415	95.15 266	71.98 474	97.87 307	95.40 387	91.92 123	87.57 296	91.44 382	74.27 323	96.84 335	89.45 255	93.10 249	94.60 329

jajsoiax		87.35 338	86.51 336	89.87 380	87.75 452	81.74 404	97.03 355	95.98 306	88.47 250	80.15 391	93.80 329	61.47 427	96.36 360	89.44 256	84.47 338	91.50 379

mvs_tets		87.09 341	86.22 339	89.71 386	87.87 448	81.39 410	96.73 369	95.90 329	88.19 266	79.99 393	93.61 334	59.96 434	96.31 368	89.40 257	84.34 339	91.43 384

PS-MVSNAJss		89.54 297	89.05 286	91.00 349	88.77 435	84.36 368	97.39 336	95.97 307	88.47 250	81.88 369	93.80 329	82.48 212	96.50 351	89.34 258	83.34 351	92.15 356

VPNet		88.30 323	86.57 334	93.49 284	91.95 388	91.35 141	98.18 276	97.20 202	88.61 247	84.52 325	94.89 309	62.21 425	96.76 340	89.34 258	72.26 431	92.36 345

114514_t		94.06 149	93.05 175	97.06 75	99.08 77	92.26 119	98.97 155	97.01 223	82.58 396	92.57 209	98.22 148	80.68 241	99.30 159	89.34 258	99.02 89	99.63 79

OPM-MVS		89.76 293	89.15 284	91.57 339	90.53 410	85.58 347	98.11 284	95.93 320	92.88 101	86.05 310	96.47 270	67.06 390	97.87 272	89.29 261	86.08 327	91.26 397
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
SSM_0407		92.04 233	91.03 238	95.07 211	95.12 269	89.81 197	97.18 350	95.49 378	86.17 325	89.50 278	97.13 220	75.65 309	97.68 294	89.26 262	93.79 235	97.73 256

SSM_0404		92.33 221	91.33 229	95.33 191	95.35 254	90.54 168	97.45 334	95.49 378	86.17 325	90.26 262	97.13 220	75.65 309	97.82 275	89.26 262	95.26 203	97.63 264

MVS_Test		93.67 170	92.67 188	96.69 101	96.72 186	92.66 107	97.22 347	96.03 302	87.69 289	95.12 148	94.03 320	81.55 227	98.28 216	89.17 264	96.46 173	99.14 128

BH-w/o		92.32 222	91.79 220	93.91 273	96.85 179	86.18 328	99.11 138	95.74 347	88.13 267	84.81 321	97.00 235	77.26 288	97.91 267	89.16 265	98.03 136	97.64 261

TAMVS		92.62 214	92.09 211	94.20 259	94.10 331	87.68 274	98.41 244	96.97 226	87.53 293	89.74 275	96.04 284	84.77 167	96.49 353	88.97 266	92.31 268	98.42 215

WBMVS		91.35 247	90.49 254	93.94 271	96.97 176	93.40 86	99.27 110	96.71 238	87.40 296	83.10 342	91.76 373	92.38 31	96.23 374	88.95 267	77.89 381	92.17 355

CNLPA		93.64 171	92.74 186	96.36 124	98.96 84	90.01 191	99.19 116	95.89 331	86.22 324	89.40 281	98.85 103	80.66 242	99.84 88	88.57 268	96.92 166	99.24 120

baseline1		92.61 215	91.28 231	96.58 109	97.05 174	94.63 54	97.72 319	96.20 281	89.82 195	88.56 289	96.85 250	86.85 117	97.82 275	88.42 269	80.10 371	97.30 275

CANet_DTU		94.31 141	93.35 163	97.20 70	97.03 175	94.71 51	98.62 204	95.54 371	95.61 36	97.21 89	98.47 138	71.88 349	99.84 88	88.38 270	97.46 152	97.04 285

thisisatest0515		94.75 126	94.19 126	96.43 117	96.13 219	92.64 110	99.47 78	97.60 134	87.55 292	93.17 191	97.59 183	94.71 13	98.42 210	88.28 271	93.20 247	98.24 234

原ACMM1				96.18 137	99.03 79	90.08 184		97.63 128	88.98 231	97.00 95	98.97 83	88.14 91	99.71 113	88.23 272	99.62 50	98.76 179

UGNet		91.91 235	90.85 244	95.10 208	97.06 172	88.69 246	98.01 299	98.24 36	92.41 111	92.39 216	93.61 334	60.52 432	99.68 115	88.14 273	97.25 157	96.92 289
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
AUN-MVS		90.17 284	89.50 271	92.19 316	96.21 209	82.67 393	97.76 317	97.53 150	88.05 270	91.67 230	96.15 279	83.10 194	97.47 309	88.11 274	66.91 456	96.43 309

Vis-MVSNet (Re-imp)		93.26 191	93.00 179	94.06 266	96.14 216	86.71 307	98.68 191	96.70 239	88.30 262	89.71 277	97.64 180	85.43 152	96.39 358	88.06 275	96.32 177	99.08 139

PVSNet	87.13 12	93.69 167	92.83 184	96.28 130	97.99 118	90.22 178	99.38 95	98.93 12	91.42 137	93.66 182	97.68 175	71.29 356	99.64 123	87.94 276	97.20 158	98.98 147

FIs		90.70 265	89.87 262	93.18 291	92.29 379	91.12 148	98.17 278	98.25 34	89.11 228	83.44 333	94.82 311	82.26 218	96.17 378	87.76 277	82.76 354	92.25 349

tpm2		91.77 238	91.09 235	93.82 276	94.83 299	85.56 348	92.51 451	97.16 206	84.00 367	93.83 179	90.66 403	87.54 99	97.17 321	87.73 278	91.55 285	98.72 187

无先验							98.52 224	97.82 79	87.20 300				99.90 62	87.64 279		99.85 35

Anonymous202405211		88.84 309	87.03 329	94.27 253	98.14 113	84.18 371	98.44 237	95.58 369	76.79 445	89.34 282	96.88 248	53.42 461	99.54 131	87.53 280	87.12 318	99.09 135

mamba_0408		90.65 268	89.16 281	95.12 207	95.12 269	89.81 197	83.02 496	95.17 405	85.95 330	89.50 278	96.85 250	75.85 305	97.82 275	87.19 281	93.79 235	97.73 256

SSM_04072		90.31 278	89.16 281	93.74 280	95.12 269	89.81 197	83.02 496	95.17 405	85.95 330	89.50 278	96.85 250	75.85 305	93.69 447	87.19 281	93.79 235	97.73 256

IS-MVSNet		93.00 202	92.51 193	94.49 242	96.14 216	87.36 293	98.31 262	95.70 353	88.58 249	90.17 264	97.50 189	83.02 196	97.22 320	87.06 283	96.07 188	98.90 159

MDTV_nov1_ep13_2view						91.17 147	91.38 465		87.45 295	93.08 193		86.67 124		87.02 284		98.95 153

Anonymous20240529		87.66 335	85.58 349	93.92 272	97.59 136	85.01 359	98.13 280	97.13 209	66.69 487	88.47 290	96.01 285	55.09 453	99.51 133	87.00 285	84.12 341	97.23 279

UniMVSNet_NR-MVSNet		89.60 295	88.55 302	92.75 303	92.17 383	90.07 185	98.74 180	98.15 43	88.37 258	83.21 337	93.98 323	82.86 198	95.93 390	86.95 286	72.47 428	92.25 349

DU-MVS		88.83 311	87.51 319	92.79 301	91.46 399	90.07 185	98.71 184	97.62 130	88.87 237	83.21 337	93.68 331	74.63 315	95.93 390	86.95 286	72.47 428	92.36 345

FA-MVS(test-final)		92.22 227	91.08 236	95.64 170	96.05 221	88.98 232	91.60 461	97.25 192	86.99 303	91.84 226	92.12 361	83.03 195	99.00 176	86.91 288	93.91 231	98.93 155

ACMM	86.95 13	88.77 314	88.22 308	90.43 366	93.61 352	81.34 411	98.50 228	95.92 321	87.88 277	83.85 331	95.20 307	67.20 388	97.89 269	86.90 289	84.90 334	92.06 360
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
UniMVSNet (Re)		89.50 298	88.32 306	93.03 293	92.21 382	90.96 156	98.90 162	98.39 29	89.13 227	83.22 336	92.03 363	81.69 226	96.34 366	86.79 290	72.53 427	91.81 366

BH-untuned		91.46 244	90.84 245	93.33 289	96.51 193	84.83 363	98.84 166	95.50 377	86.44 323	83.50 332	96.70 261	75.49 313	97.77 281	86.78 291	97.81 140	97.40 270

KinetiMVS		93.07 200	91.98 213	96.34 125	94.84 298	91.78 129	98.73 183	97.18 203	91.25 142	94.01 173	97.09 227	71.02 357	98.86 182	86.77 292	96.89 167	98.37 223

icg_test_0407_2		91.56 241	90.90 243	93.54 283	94.61 309	86.22 322	95.72 408	95.72 348	88.78 239	89.76 273	96.93 241	77.24 289	95.65 410	86.73 293	92.59 257	98.74 181

IMVS_0407		91.79 237	90.98 239	94.24 257	94.61 309	86.22 322	96.45 378	95.72 348	88.78 239	89.76 273	96.93 241	77.24 289	97.77 281	86.73 293	92.59 257	98.74 181

IMVS_0404		89.79 292	88.57 301	93.47 285	94.61 309	86.22 322	94.45 422	95.72 348	88.78 239	81.88 369	96.93 241	65.39 409	95.47 416	86.73 293	92.59 257	98.74 181

IMVS_0403		91.93 234	91.13 234	94.34 249	94.61 309	86.22 322	96.70 370	95.72 348	88.78 239	90.00 270	96.93 241	78.07 281	98.07 248	86.73 293	92.59 257	98.74 181

mvsany_test3		75.85 446	74.52 445	79.83 467	73.53 504	60.64 495	91.73 459	87.87 495	83.91 370	70.55 462	82.52 477	31.12 495	93.66 448	86.66 297	62.83 466	85.19 483

miper_enhance_ethall		90.33 277	89.70 264	92.22 314	97.12 169	88.93 237	98.35 258	95.96 313	88.60 248	83.14 341	92.33 360	87.38 102	96.18 376	86.49 298	77.89 381	91.55 378

casdiffseed414692147		91.84 236	90.69 250	95.28 197	94.50 314	89.32 213	98.31 262	95.67 359	87.82 281	90.22 263	96.63 265	74.27 323	97.94 266	86.37 299	92.43 263	98.59 206

thisisatest0530		94.00 151	93.52 155	95.43 182	95.76 232	90.02 190	98.99 152	97.60 134	86.58 316	91.74 228	97.36 199	94.78 12	98.34 212	86.37 299	92.48 262	97.94 252

UWE-MVS		93.18 192	93.40 162	92.50 311	96.56 189	83.55 379	98.09 288	97.84 74	89.50 212	91.72 229	96.23 277	91.08 40	96.70 341	86.28 301	93.33 246	97.26 277

TESTMET0.1,1		93.82 164	93.26 168	95.49 178	95.21 261	90.25 175	99.15 127	97.54 149	89.18 222	91.79 227	94.87 310	89.13 72	97.63 299	86.21 302	96.29 181	98.60 204

anonymousdsp		86.69 348	85.75 347	89.53 391	86.46 461	82.94 386	96.39 380	95.71 352	83.97 368	79.63 398	90.70 400	68.85 372	95.94 389	86.01 303	84.02 342	89.72 437

F-COLMAP		92.07 231	91.75 222	93.02 294	98.16 112	82.89 389	98.79 176	95.97 307	86.54 318	87.92 293	97.80 162	78.69 273	99.65 121	85.97 304	95.93 190	96.53 304

cl22		89.57 296	88.79 294	91.91 322	97.94 120	87.62 283	97.98 301	96.51 256	85.03 347	82.37 356	91.79 370	83.65 180	96.50 351	85.96 305	77.89 381	91.61 375

test-LLR		93.11 198	92.68 187	94.40 246	94.94 292	87.27 297	99.15 127	97.25 192	90.21 179	91.57 232	94.04 318	84.89 163	97.58 304	85.94 306	96.13 184	98.36 226

test-mter		93.27 190	92.89 182	94.40 246	94.94 292	87.27 297	99.15 127	97.25 192	88.95 233	91.57 232	94.04 318	88.03 93	97.58 304	85.94 306	96.13 184	98.36 226

FC-MVSNet-test		90.22 281	89.40 275	92.67 309	91.78 393	89.86 195	97.89 304	98.22 37	88.81 238	82.96 343	94.66 313	81.90 225	95.96 388	85.89 308	82.52 357	92.20 354

Vis-MVSNet		92.64 213	91.85 217	95.03 215	95.12 269	88.23 259	98.48 232	96.81 232	91.61 128	92.16 220	97.22 213	71.58 354	98.00 263	85.85 309	97.81 140	98.88 160
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
sd_testset		89.23 299	88.05 312	92.74 304	96.80 182	85.33 352	95.85 404	97.03 220	88.34 260	85.73 313	95.26 305	61.12 430	97.76 287	85.61 310	86.75 319	95.14 323

test_fmvs3		75.09 449	75.19 440	74.81 475	77.45 498	54.08 502	95.93 397	90.64 478	82.51 399	73.29 448	81.19 486	22.29 503	86.29 499	85.50 311	67.89 451	84.06 486

WR-MVS		88.54 321	87.22 326	92.52 310	91.93 390	89.50 207	98.56 220	97.84 74	86.99 303	81.87 371	93.81 328	74.25 325	95.92 392	85.29 312	74.43 407	92.12 357

XXY-MVS		87.75 331	86.02 342	92.95 298	90.46 412	89.70 203	97.71 321	95.90 329	84.02 366	80.95 380	94.05 317	67.51 386	97.10 326	85.16 313	78.41 378	92.04 361

thres200		93.69 167	92.59 192	96.97 83	97.76 125	94.74 49	99.35 101	99.36 2	89.23 219	91.21 244	96.97 237	83.42 185	98.77 187	85.08 314	90.96 298	97.39 271

tttt0517		93.30 188	93.01 177	94.17 260	95.57 239	86.47 312	98.51 227	97.60 134	85.99 329	90.55 255	97.19 216	94.80 11	98.31 213	85.06 315	91.86 277	97.74 255

XVG-ACMP-BASELINE		85.86 364	84.95 359	88.57 408	89.90 417	77.12 449	94.30 427	95.60 366	87.40 296	82.12 360	92.99 351	53.42 461	97.66 296	85.02 316	83.83 343	90.92 407

dmvs_re		88.69 317	88.06 311	90.59 360	93.83 346	78.68 435	95.75 407	96.18 286	87.99 273	84.48 326	96.32 275	67.52 385	96.94 332	84.98 317	85.49 331	96.14 313

新几何1				97.40 58	98.92 89	92.51 114		97.77 92	85.52 338	96.69 110	99.06 73	88.08 92	99.89 70	84.88 318	99.62 50	99.79 43

1112_ss		92.71 210	91.55 225	96.20 135	95.56 241	91.12 148	98.48 232	94.69 419	88.29 263	86.89 306	98.50 131	87.02 114	98.66 198	84.75 319	89.77 309	98.81 169

miper_ehance_all_eth		88.94 306	88.12 310	91.40 340	95.32 255	86.93 303	97.85 308	95.55 370	84.19 364	81.97 367	91.50 380	84.16 175	95.91 395	84.69 320	77.89 381	91.36 391

Test_1112_low_res		92.27 225	90.97 240	96.18 137	95.53 243	91.10 150	98.47 235	94.66 420	88.28 264	86.83 307	93.50 338	87.00 115	98.65 199	84.69 320	89.74 310	98.80 171

UWE-MVS-28		90.99 259	91.93 216	88.15 411	95.12 269	77.87 445	97.18 350	97.79 87	88.72 244	88.69 287	96.52 266	86.54 129	90.75 477	84.64 322	92.16 275	95.83 320

TR-MVS		90.77 263	89.44 273	94.76 226	96.31 204	88.02 265	97.92 303	95.96 313	85.52 338	88.22 292	97.23 212	66.80 394	98.09 241	84.58 323	92.38 265	98.17 240

tt0805		86.50 354	84.79 363	91.63 338	91.97 386	81.49 406	96.49 377	97.38 179	82.24 403	82.44 352	95.82 292	51.22 467	98.25 218	84.55 324	80.96 365	95.13 325

OpenMVS	85.28 14	90.75 264	88.84 292	96.48 114	93.58 353	93.51 83	98.80 171	97.41 175	82.59 395	78.62 411	97.49 190	68.00 381	99.82 95	84.52 325	98.55 123	96.11 314

UniMVSNet_ETH3D		85.65 371	83.79 380	91.21 344	90.41 413	80.75 421	95.36 412	95.78 342	78.76 433	81.83 374	94.33 316	49.86 473	96.66 342	84.30 326	83.52 349	96.22 312

NR-MVSNet		87.74 334	86.00 343	92.96 297	91.46 399	90.68 164	96.65 372	97.42 174	88.02 272	73.42 447	93.68 331	77.31 287	95.83 398	84.26 327	71.82 435	92.36 345

D2MVS		87.96 327	87.39 321	89.70 387	91.84 392	83.40 381	98.31 262	98.49 24	88.04 271	78.23 421	90.26 417	73.57 329	96.79 339	84.21 328	83.53 348	88.90 450

testdata2													99.88 72	84.16 329

Baseline_NR-MVSNet		85.83 365	84.82 362	88.87 407	88.73 436	83.34 382	98.63 200	91.66 468	80.41 426	82.44 352	91.35 384	74.63 315	95.42 419	84.13 330	71.39 437	87.84 456

thres100view900		93.34 187	92.15 209	96.90 87	97.62 132	94.84 43	99.06 144	99.36 2	87.96 274	90.47 258	96.78 256	83.29 188	98.75 191	84.11 331	90.69 300	97.12 280

tfpn200view9		93.43 181	92.27 201	96.90 87	97.68 129	94.84 43	99.18 118	99.36 2	88.45 253	90.79 248	96.90 245	83.31 186	98.75 191	84.11 331	90.69 300	97.12 280

thres400		93.39 183	92.27 201	96.73 97	97.68 129	94.84 43	99.18 118	99.36 2	88.45 253	90.79 248	96.90 245	83.31 186	98.75 191	84.11 331	90.69 300	96.61 299

c3_l		88.19 326	87.23 325	91.06 347	94.97 289	86.17 329	97.72 319	95.38 388	83.43 378	81.68 375	91.37 383	82.81 201	95.72 405	84.04 334	73.70 415	91.29 396

usedtu_blend_shiyan5		82.04 409	78.78 422	91.80 327	82.91 478	88.24 255	94.33 425	92.37 457	66.55 488	78.60 413	86.54 460	66.93 392	95.77 400	83.97 335	56.84 485	91.38 387

blend_shiyan4		86.02 360	84.08 375	91.83 324	83.24 476	88.24 255	98.42 241	95.51 373	75.55 457	79.43 401	86.84 457	84.51 170	95.77 400	83.97 335	69.26 442	91.48 380

UA-Net		93.30 188	92.62 191	95.34 189	96.27 206	88.53 252	95.88 401	96.97 226	90.90 149	95.37 143	97.07 230	82.38 217	99.10 172	83.91 337	94.86 214	98.38 220

IterMVS-LS		88.34 322	87.44 320	91.04 348	94.10 331	85.85 342	98.10 285	95.48 381	85.12 343	82.03 365	91.21 388	81.35 234	95.63 412	83.86 338	75.73 395	91.63 371
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
EI-MVSNet		89.87 290	89.38 276	91.36 343	94.32 323	85.87 341	97.61 329	96.59 249	85.10 344	85.51 317	97.10 223	81.30 235	96.56 347	83.85 339	83.03 352	91.64 370

Elysia		90.62 270	88.95 288	95.64 170	93.08 366	91.94 124	97.65 326	96.39 265	84.72 355	90.59 253	95.95 287	62.22 423	98.23 220	83.69 340	96.23 182	96.74 293

StellarMVS		90.62 270	88.95 288	95.64 170	93.08 366	91.94 124	97.65 326	96.39 265	84.72 355	90.59 253	95.95 287	62.22 423	98.23 220	83.69 340	96.23 182	96.74 293

tpm		89.67 294	88.95 288	91.82 326	92.54 375	81.43 408	92.95 445	95.92 321	87.81 282	90.50 257	89.44 432	84.99 161	95.65 410	83.67 342	82.71 355	98.38 220

dtuonly		89.80 291	89.16 281	91.70 336	90.49 411	81.48 407	96.58 373	93.12 448	87.21 299	88.72 286	96.87 249	72.09 346	97.59 302	83.52 343	93.84 233	96.03 316

eth_miper_zixun_eth		87.76 330	87.00 330	90.06 375	94.67 306	82.65 396	97.02 357	95.37 389	84.19 364	81.86 373	91.58 377	81.47 231	95.90 396	83.24 344	73.61 416	91.61 375

Fast-Effi-MVS+		91.72 239	90.79 248	94.49 242	95.89 225	87.40 292	99.54 71	95.70 353	85.01 349	89.28 283	95.68 294	77.75 284	97.57 307	83.22 345	95.06 209	98.51 210

test_post1							90.74 473				41.37 529	85.38 154	96.36 360	83.16 346

SCA		90.64 269	89.25 279	94.83 224	94.95 291	88.83 240	96.26 387	97.21 198	90.06 189	90.03 268	90.62 406	66.61 397	96.81 337	83.16 346	94.36 223	98.84 164

TranMVSNet+NR-MVSNet		87.75 331	86.31 338	92.07 320	90.81 407	88.56 249	98.33 259	97.18 203	87.76 284	81.87 371	93.90 326	72.45 342	95.43 418	83.13 348	71.30 438	92.23 351

CMPMVS	58.40 21	80.48 418	80.11 416	81.59 464	85.10 468	59.56 496	94.14 431	95.95 315	68.54 481	60.71 491	93.31 340	55.35 452	97.87 272	83.06 349	84.85 335	87.33 463
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
thres600view7		93.18 192	92.00 212	96.75 95	97.62 132	94.92 38	99.07 141	99.36 2	87.96 274	90.47 258	96.78 256	83.29 188	98.71 196	82.93 350	90.47 304	96.61 299

usedtu_dtu_shiyan1		89.12 301	87.56 317	93.78 277	89.74 421	93.60 77	98.70 187	96.60 246	87.85 278	83.43 334	91.56 378	76.34 300	95.92 392	82.75 351	81.08 362	91.82 364

FE-MVSNET3		89.12 301	87.56 317	93.78 277	89.74 421	93.60 77	98.70 187	96.60 246	87.85 278	83.43 334	91.56 378	76.34 300	95.92 392	82.75 351	81.08 362	91.82 364

pmmvs4		87.58 337	86.17 341	91.80 327	89.58 425	88.92 238	97.25 344	95.28 392	82.54 397	80.49 385	93.17 346	75.62 311	96.05 384	82.75 351	78.90 376	90.42 422

CVMVSNet		90.30 279	90.91 242	88.46 410	94.32 323	73.58 466	97.61 329	97.59 138	90.16 184	88.43 291	97.10 223	76.83 293	92.86 456	82.64 354	93.54 241	98.93 155

Anonymous20231211		84.72 380	82.65 392	90.91 351	97.71 128	84.55 366	97.28 342	96.67 240	66.88 486	79.18 406	90.87 396	58.47 438	96.60 344	82.61 355	74.20 411	91.59 377

GA-MVS		90.10 286	88.69 296	94.33 250	92.44 377	87.97 267	99.08 140	96.26 277	89.65 202	86.92 305	93.11 347	68.09 379	96.96 330	82.54 356	90.15 305	98.05 247

blended_shiyan8		83.22 401	80.40 413	91.71 335	82.77 484	88.01 266	98.25 270	95.49 378	75.64 454	78.68 409	86.55 458	66.76 395	95.75 402	82.50 357	56.93 484	91.36 391

wanda-best-256-512		83.28 399	80.44 410	91.78 332	82.91 478	88.24 255	98.43 238	95.51 373	75.76 451	78.60 413	86.54 460	66.95 391	95.71 406	82.44 358	56.84 485	91.38 387

FE-blended-shiyan7		83.27 400	80.44 410	91.78 332	82.91 478	88.24 255	98.43 238	95.51 373	75.76 451	78.60 413	86.54 460	66.93 392	95.71 406	82.44 358	56.84 485	91.38 387

blended_shiyan6		83.17 402	80.34 414	91.67 337	82.80 483	87.93 268	98.29 266	95.51 373	75.63 455	78.46 417	86.48 463	66.74 396	95.70 408	82.33 360	56.84 485	91.37 390

QAPM		91.41 245	89.49 272	97.17 72	95.66 236	93.42 85	98.60 211	97.51 156	80.92 421	81.39 378	97.41 195	72.89 340	99.87 76	82.33 360	98.68 113	98.21 236

Patchmatch-RL test		81.90 412	80.13 415	87.23 422	80.71 488	70.12 481	84.07 492	88.19 493	83.16 383	70.57 461	82.18 480	87.18 109	92.59 461	82.28 362	62.78 467	98.98 147

v2v482		87.27 340	85.76 346	91.78 332	89.59 424	87.58 285	98.56 220	95.54 371	84.53 359	82.51 351	91.78 371	73.11 335	96.47 354	82.07 363	74.14 413	91.30 395

Fast-Effi-MVS+-dtu		88.84 309	88.59 300	89.58 390	93.44 359	78.18 439	98.65 196	94.62 421	88.46 252	84.12 329	95.37 303	68.91 371	96.52 350	82.06 364	91.70 282	94.06 330

pmmvs5		85.87 363	84.40 373	90.30 371	88.53 439	84.23 369	98.60 211	93.71 441	81.53 411	80.29 389	92.02 364	64.51 412	95.52 414	82.04 365	78.34 379	91.15 401

V42		87.00 342	85.68 348	90.98 350	89.91 416	86.08 332	98.32 261	95.61 365	83.67 375	82.72 345	90.67 402	74.00 327	96.53 349	81.94 366	74.28 410	90.32 424

gbinet_0.2-2-1-0.02		83.16 403	80.42 412	91.39 342	83.70 474	87.60 284	98.62 204	95.77 344	75.83 450	79.33 403	87.92 441	64.07 414	95.34 421	81.87 367	56.67 489	91.25 398

EPMVS		92.59 216	91.59 224	95.59 176	97.22 158	90.03 189	91.78 458	98.04 56	90.42 172	91.66 231	90.65 404	86.49 132	97.46 310	81.78 368	96.31 178	99.28 117

DIV-MVS_self_test		87.82 328	86.81 332	90.87 354	94.87 297	85.39 351	97.81 310	95.22 403	82.92 391	80.76 382	91.31 386	81.99 222	95.81 399	81.36 369	75.04 400	91.42 385

cl____		87.82 328	86.79 333	90.89 353	94.88 296	85.43 349	97.81 310	95.24 398	82.91 392	80.71 383	91.22 387	81.97 224	95.84 397	81.34 370	75.06 399	91.40 386

RPSCF		85.33 373	85.55 350	84.67 447	94.63 308	62.28 493	93.73 435	93.76 439	74.38 463	85.23 320	97.06 231	64.09 413	98.31 213	80.98 371	86.08 327	93.41 335

OurMVSNet-221017-0		84.13 392	83.59 381	85.77 439	87.81 449	70.24 479	94.89 418	93.65 443	86.08 327	76.53 426	93.28 342	61.41 428	96.14 380	80.95 372	77.69 387	90.93 406

v148		86.38 356	85.06 356	90.37 370	89.47 429	84.10 372	98.52 224	95.48 381	83.80 371	80.93 381	90.22 421	74.60 317	96.31 368	80.92 373	71.55 436	90.69 417

PatchMatch-RL		91.47 243	90.54 253	94.26 254	98.20 109	86.36 317	96.94 358	97.14 207	87.75 285	88.98 284	95.75 293	71.80 351	99.40 150	80.92 373	97.39 155	97.02 286

FE-MVS		91.38 246	90.16 259	95.05 214	96.46 195	87.53 287	89.69 476	97.84 74	82.97 387	92.18 219	92.00 367	84.07 177	98.93 180	80.71 375	95.52 197	98.68 193

miper_lstm_enhance		86.90 343	86.20 340	89.00 404	94.53 313	81.19 414	96.74 368	95.24 398	82.33 402	80.15 391	90.51 413	81.99 222	94.68 437	80.71 375	73.58 418	91.12 402

PCF-MVS	89.78 5	91.26 249	89.63 268	96.16 142	95.44 247	91.58 139	95.29 414	96.10 293	85.07 346	82.75 344	97.45 193	78.28 279	99.78 107	80.60 377	95.65 195	97.12 280
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
BH-RMVSNet		91.25 251	89.99 260	95.03 215	96.75 185	88.55 250	98.65 196	94.95 409	87.74 286	87.74 295	97.80 162	68.27 377	98.14 229	80.53 378	97.49 151	98.41 216

GeoE		90.60 272	89.56 269	93.72 282	95.10 278	85.43 349	99.41 92	94.94 410	83.96 369	87.21 302	96.83 255	74.37 321	97.05 328	80.50 379	93.73 239	98.67 194

CP-MVSNet		86.54 352	85.45 352	89.79 384	91.02 406	82.78 392	97.38 338	97.56 144	85.37 340	79.53 400	93.03 349	71.86 350	95.25 424	79.92 380	73.43 422	91.34 393

PatchmatchNet		92.05 232	91.04 237	95.06 212	96.17 213	89.04 225	91.26 467	97.26 191	89.56 209	90.64 252	90.56 410	88.35 85	97.11 324	79.53 381	96.07 188	99.03 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
v1144		86.83 345	85.31 354	91.40 340	89.75 420	87.21 301	98.31 262	95.45 383	83.22 381	82.70 346	90.78 397	73.36 330	96.36 360	79.49 382	74.69 404	90.63 419

IterMVS		85.81 366	84.67 366	89.22 398	93.51 355	83.67 378	96.32 384	94.80 415	85.09 345	78.69 408	90.17 424	66.57 399	93.17 455	79.48 383	77.42 388	90.81 409
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
IterMVS-SCA-FT		85.73 369	84.64 367	89.00 404	93.46 358	82.90 388	96.27 385	94.70 418	85.02 348	78.62 411	90.35 415	66.61 397	93.33 451	79.38 384	77.36 389	90.76 413

GBi-Net		86.67 349	84.96 357	91.80 327	95.11 275	88.81 241	96.77 364	95.25 395	82.94 388	82.12 360	90.25 418	62.89 420	94.97 428	79.04 385	80.24 368	91.62 372

test1		86.67 349	84.96 357	91.80 327	95.11 275	88.81 241	96.77 364	95.25 395	82.94 388	82.12 360	90.25 418	62.89 420	94.97 428	79.04 385	80.24 368	91.62 372

FMVSNet3		88.81 313	87.08 327	93.99 270	96.52 192	94.59 55	98.08 291	96.20 281	85.85 332	82.12 360	91.60 376	74.05 326	95.40 420	79.04 385	80.24 368	91.99 362

LF4IMVS		81.94 411	81.17 404	84.25 449	87.23 456	68.87 485	93.35 441	91.93 465	83.35 380	75.40 436	93.00 350	49.25 477	96.65 343	78.88 388	78.11 380	87.22 465

v8		86.11 359	84.45 370	91.10 346	89.99 415	86.85 304	97.24 345	95.36 390	81.99 406	79.89 395	89.86 427	74.53 319	96.39 358	78.83 389	72.32 430	90.05 431

pm-mvs1		84.68 381	82.78 389	90.40 367	89.58 425	85.18 355	97.31 340	94.73 417	81.93 408	76.05 430	92.01 365	65.48 407	96.11 381	78.75 390	69.14 443	89.91 434

test_f		71.94 455	70.82 456	75.30 474	72.77 506	53.28 503	91.62 460	89.66 487	75.44 458	64.47 486	78.31 496	20.48 504	89.56 485	78.63 391	66.02 459	83.05 492

v144192		86.40 355	84.89 360	90.91 351	89.48 428	85.59 346	98.21 274	95.43 386	82.45 400	82.62 349	90.58 409	72.79 341	96.36 360	78.45 392	74.04 414	90.79 411

PS-CasMVS		85.81 366	84.58 368	89.49 394	90.77 408	82.11 400	97.20 348	97.36 183	84.83 352	79.12 407	92.84 353	67.42 387	95.16 426	78.39 393	73.25 423	91.21 400

tmp_tt		53.66 476	52.86 476	56.05 499	32.75 552	41.97 521	73.42 512	76.12 512	21.91 523	39.68 512	96.39 273	42.59 484	65.10 522	78.00 394	14.92 537	61.08 514

JIA-IIPM		85.97 362	84.85 361	89.33 397	93.23 363	73.68 465	85.05 487	97.13 209	69.62 478	91.56 234	68.03 509	88.03 93	96.96 330	77.89 395	93.12 248	97.34 272

MDTV_nov1_ep13			90.47 256		96.14 216	88.55 250	91.34 466	97.51 156	89.58 207	92.24 217	90.50 414	86.99 116	97.61 301	77.64 396	92.34 267

v1192		86.32 357	84.71 365	91.17 345	89.53 427	86.40 314	98.13 280	95.44 385	82.52 398	82.42 354	90.62 406	71.58 354	96.33 367	77.23 397	74.88 401	90.79 411

FMVSNet2		86.90 343	84.79 363	93.24 290	95.11 275	92.54 113	97.67 324	95.86 335	82.94 388	80.55 384	91.17 389	62.89 420	95.29 423	77.23 397	79.71 374	91.90 363

MVP-Stereo		86.61 351	85.83 345	88.93 406	88.70 437	83.85 376	96.07 395	94.41 429	82.15 405	75.64 435	91.96 368	67.65 384	96.45 356	77.20 399	98.72 111	86.51 470
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
tpm cat1		88.89 307	87.27 324	93.76 279	95.79 230	85.32 353	90.76 472	97.09 215	76.14 448	85.72 315	88.59 438	82.92 197	98.04 257	76.96 400	91.43 291	97.90 253

v10		85.73 369	84.01 377	90.87 354	90.03 414	86.73 306	97.20 348	95.22 403	81.25 414	79.85 396	89.75 428	73.30 333	96.28 372	76.87 401	72.64 426	89.61 439

v1921920		86.02 360	84.44 371	90.77 357	89.32 430	85.20 354	98.10 285	95.35 391	82.19 404	82.25 358	90.71 399	70.73 358	96.30 371	76.85 402	74.49 406	90.80 410

MS-PatchMatch		86.75 347	85.92 344	89.22 398	91.97 386	82.47 398	96.91 359	96.14 290	83.74 372	77.73 423	93.53 337	58.19 439	97.37 317	76.75 403	98.35 129	87.84 456

K. test v3		81.04 416	79.77 418	84.83 445	87.41 453	70.23 480	95.60 410	93.93 437	83.70 374	67.51 477	89.35 434	55.76 447	93.58 450	76.67 404	68.03 450	90.67 418

PM-MVS		74.88 451	72.85 452	80.98 465	78.98 493	64.75 490	90.81 471	85.77 498	80.95 420	68.23 474	82.81 476	29.08 499	92.84 457	76.54 405	62.46 469	85.36 480

SSC-MVS3.2		85.22 374	83.90 379	89.17 400	91.87 391	79.84 425	97.66 325	96.63 243	86.81 311	81.99 366	91.35 384	55.80 446	96.00 385	76.52 406	76.53 392	91.67 368

WR-MVS_H		86.53 353	85.49 351	89.66 389	91.04 405	83.31 383	97.53 332	98.20 38	84.95 350	79.64 397	90.90 395	78.01 283	95.33 422	76.29 407	72.81 424	90.35 423

ACMH+	83.78 15	84.21 389	82.56 395	89.15 401	93.73 349	79.16 430	96.43 379	94.28 431	81.09 417	74.00 443	94.03 320	54.58 456	97.67 295	76.10 408	78.81 377	90.63 419

PEN-MVS		85.21 375	83.93 378	89.07 403	89.89 418	81.31 412	97.09 353	97.24 195	84.45 362	78.66 410	92.68 356	68.44 376	94.87 431	75.98 409	70.92 439	91.04 404

USDC		84.74 379	82.93 385	90.16 373	91.73 395	83.54 380	95.00 417	93.30 447	88.77 243	73.19 449	93.30 341	53.62 460	97.65 298	75.88 410	81.54 361	89.30 442

EU-MVSNet		84.19 390	84.42 372	83.52 455	88.64 438	67.37 487	96.04 396	95.76 346	85.29 341	78.44 418	93.18 344	70.67 359	91.48 474	75.79 411	75.98 393	91.70 367

v1240		85.77 368	84.11 374	90.73 358	89.26 431	85.15 357	97.88 306	95.23 402	81.89 409	82.16 359	90.55 411	69.60 367	96.31 368	75.59 412	74.87 402	90.72 416

ITE_SJBPF				87.93 413	92.26 380	76.44 453		93.47 446	87.67 290	79.95 394	95.49 300	56.50 445	97.38 315	75.24 413	82.33 358	89.98 433

dp		90.16 285	88.83 293	94.14 261	96.38 202	86.42 313	91.57 462	97.06 217	84.76 354	88.81 285	90.19 423	84.29 174	97.43 313	75.05 414	91.35 295	98.56 207

LS3D		90.19 282	88.72 295	94.59 240	98.97 81	86.33 318	96.90 360	96.60 246	74.96 460	84.06 330	98.74 110	75.78 308	99.83 92	74.93 415	97.57 147	97.62 265

TDRefinement		78.01 436	75.31 439	86.10 434	70.06 510	73.84 464	93.59 438	91.58 471	74.51 462	73.08 452	91.04 390	49.63 475	97.12 323	74.88 416	59.47 477	87.33 463

tpmvs		89.16 300	87.76 313	93.35 288	97.19 161	84.75 364	90.58 474	97.36 183	81.99 406	84.56 323	89.31 435	83.98 178	98.17 227	74.85 417	90.00 308	97.12 280

pmmvs6		79.90 421	77.31 429	87.67 416	84.17 471	78.13 441	95.86 403	93.68 442	67.94 483	72.67 455	89.62 430	50.98 469	95.75 402	74.80 418	66.04 458	89.14 445

SixPastTwentyTwo		82.63 406	81.58 399	85.79 438	88.12 444	71.01 477	95.17 415	92.54 455	84.33 363	72.93 454	92.08 362	60.41 433	95.61 413	74.47 419	74.15 412	90.75 414

ACMH	83.09 17	84.60 382	82.61 393	90.57 361	93.18 364	82.94 386	96.27 385	94.92 411	81.01 419	72.61 456	93.61 334	56.54 444	97.79 279	74.31 420	81.07 364	90.99 405
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
test_vis3_rt		61.29 464	58.75 467	68.92 484	67.41 514	52.84 505	91.18 469	59.23 522	66.96 485	41.96 510	58.44 516	11.37 518	94.72 436	74.25 421	57.97 481	59.20 515

ADS-MVSNet2		87.62 336	86.88 331	89.86 381	96.21 209	79.14 431	87.15 480	92.99 449	83.01 385	89.91 271	87.27 450	78.87 266	92.80 459	74.20 422	92.27 269	97.64 261

ADS-MVSNet		88.99 304	87.30 323	94.07 264	96.21 209	87.56 286	87.15 480	96.78 235	83.01 385	89.91 271	87.27 450	78.87 266	97.01 329	74.20 422	92.27 269	97.64 261

sc_t1		78.53 432	74.87 443	89.48 395	87.92 447	77.36 448	94.80 419	90.61 481	57.65 494	76.28 427	89.59 431	38.25 490	96.18 376	74.04 424	64.72 463	94.91 328

lessismore_v0				85.08 443	85.59 467	69.28 482		90.56 482		67.68 476	90.21 422	54.21 458	95.46 417	73.88 425	62.64 468	90.50 421

MIMVSNet		84.48 385	81.83 397	92.42 312	91.73 395	87.36 293	85.52 483	94.42 428	81.40 412	81.91 368	87.58 444	51.92 464	92.81 458	73.84 426	88.15 313	97.08 284

v7n		84.42 387	82.75 390	89.43 396	88.15 443	81.86 403	96.75 367	95.67 359	80.53 422	78.38 419	89.43 433	69.89 362	96.35 365	73.83 427	72.13 432	90.07 429

ambc				79.60 469	72.76 507	56.61 498	76.20 508	92.01 464		68.25 473	80.23 490	23.34 502	94.73 435	73.78 428	60.81 474	87.48 460

pmmvs-eth3d		78.71 430	76.16 435	86.38 430	80.25 491	81.19 414	94.17 430	92.13 462	77.97 437	66.90 480	82.31 479	55.76 447	92.56 462	73.63 429	62.31 470	85.38 479

ArgMatch-Sym		75.37 447	74.07 446	79.27 470	86.10 465	64.15 491	92.14 454	85.97 497	78.66 434	71.15 458	91.00 391	29.88 498	86.45 498	73.44 430	58.34 480	87.22 465

FMVSNet1		83.94 394	81.32 403	91.80 327	91.94 389	88.81 241	96.77 364	95.25 395	77.98 436	78.25 420	90.25 418	50.37 472	94.97 428	73.27 431	77.81 386	91.62 372

MSDG		88.29 324	86.37 337	94.04 268	96.90 178	86.15 330	96.52 375	94.36 430	77.89 440	79.22 405	96.95 238	69.72 364	99.59 127	73.20 432	92.58 261	96.37 311

test0.0.03 1		88.96 305	88.61 298	90.03 379	91.09 404	84.43 367	98.97 155	97.02 222	90.21 179	80.29 389	96.31 276	84.89 163	91.93 471	72.98 433	85.70 330	93.73 331

ArgMatch-SfM		75.24 448	73.75 447	79.70 468	85.92 466	63.67 492	91.51 463	85.16 500	79.74 427	70.70 460	90.27 416	30.46 497	87.73 494	72.95 434	57.08 483	87.70 459

UnsupCasMVSNet_eth		78.90 428	76.67 433	85.58 440	82.81 482	74.94 460	91.98 456	96.31 272	84.64 358	65.84 485	87.71 443	51.33 466	92.23 466	72.89 435	56.50 491	89.56 440

WB-MVSnew		88.69 317	88.34 305	89.77 385	94.30 329	85.99 337	98.14 279	97.31 190	87.15 301	87.85 294	96.07 283	69.91 361	95.52 414	72.83 436	91.47 290	87.80 458

DTE-MVSNet		84.14 391	82.80 387	88.14 412	88.95 434	79.87 424	96.81 363	96.24 278	83.50 377	77.60 424	92.52 358	67.89 383	94.24 442	72.64 437	69.05 444	90.32 424

SD_0403		86.82 346	87.08 327	86.04 435	93.55 354	69.09 483	94.11 432	95.02 407	87.84 280	80.48 386	95.86 291	73.05 336	91.04 476	72.53 438	91.26 296	97.99 251

ttmdpeth		79.80 423	77.91 426	85.47 441	83.34 475	75.75 455	95.32 413	91.45 473	76.84 444	74.81 439	91.71 374	53.98 459	94.13 443	72.42 439	61.29 471	86.51 470

EPNet_dtu		92.28 224	92.15 209	92.70 307	97.29 154	84.84 362	98.64 198	97.82 79	92.91 99	93.02 195	97.02 234	85.48 151	95.70 408	72.25 440	94.89 212	97.55 267
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FE-MVSNET2		78.42 434	75.71 437	86.55 429	78.55 495	81.99 402	95.40 411	93.86 438	81.11 415	66.27 482	81.89 481	49.29 476	91.80 472	72.03 441	63.02 465	85.86 474

dtuonlycased		79.10 426	78.53 423	80.81 466	86.63 459	72.95 469	96.33 383	90.81 477	81.09 417	68.85 469	87.27 450	56.94 443	87.84 493	71.57 442	67.30 455	81.65 493

AllTest		84.97 378	83.12 384	90.52 364	96.82 180	78.84 433	95.89 399	92.17 460	77.96 438	75.94 431	95.50 298	55.48 449	99.18 164	71.15 443	87.14 316	93.55 333

TestCases				90.52 364	96.82 180	78.84 433		92.17 460	77.96 438	75.94 431	95.50 298	55.48 449	99.18 164	71.15 443	87.14 316	93.55 333

DP-MVS		88.75 315	86.56 335	95.34 189	98.92 89	87.45 290	97.64 328	93.52 445	70.55 473	81.49 376	97.25 210	74.43 320	99.88 72	71.14 445	94.09 228	98.67 194

CR-MVSNet		88.83 311	87.38 322	93.16 292	93.47 356	86.24 320	84.97 488	94.20 433	88.92 236	90.76 250	86.88 455	84.43 172	94.82 433	70.64 446	92.17 273	98.41 216

KD-MVS_2432*1600		82.98 404	80.52 408	90.38 368	94.32 323	88.98 232	92.87 447	95.87 333	80.46 424	73.79 444	87.49 447	82.76 204	93.29 453	70.56 447	46.53 505	88.87 451

miper_refine_blended		82.98 404	80.52 408	90.38 368	94.32 323	88.98 232	92.87 447	95.87 333	80.46 424	73.79 444	87.49 447	82.76 204	93.29 453	70.56 447	46.53 505	88.87 451

test_method		70.10 457	68.66 460	74.41 477	86.30 463	55.84 500	94.47 421	89.82 485	35.18 516	66.15 483	84.75 472	30.54 496	77.96 511	70.40 449	60.33 475	89.44 441

tt0320-xc		75.92 444	72.23 455	87.01 424	88.40 440	78.15 440	93.57 439	89.15 490	55.46 495	69.66 466	85.79 468	38.20 491	93.85 445	69.72 450	60.08 476	89.03 446

LTVRE_ROB	81.71 19	84.59 383	82.72 391	90.18 372	92.89 370	83.18 384	93.15 442	94.74 416	78.99 430	75.14 438	92.69 355	65.64 404	97.63 299	69.46 451	81.82 360	89.74 436
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
myMVS_eth3d		88.68 319	89.07 285	87.50 419	95.14 267	79.74 426	97.68 322	96.66 241	86.52 319	82.63 347	96.84 253	85.22 160	89.89 482	69.43 452	91.54 286	92.87 337

mvs5depth		78.17 435	75.56 438	85.97 436	80.43 490	76.44 453	85.46 484	89.24 489	76.39 446	78.17 422	88.26 439	51.73 465	95.73 404	69.31 453	61.09 472	85.73 476

FMVSNet5		82.29 407	80.54 407	87.52 418	93.79 348	84.01 373	93.73 435	92.47 456	76.92 443	74.27 441	86.15 465	63.69 418	89.24 488	69.07 454	74.79 403	89.29 443

tt0320		76.58 441	73.16 451	86.86 427	88.03 446	77.60 446	93.55 440	90.63 479	55.37 496	70.93 459	84.98 469	41.57 485	94.01 444	69.02 455	64.32 464	88.97 447

our_test_3		84.47 386	82.80 387	89.50 392	89.01 432	83.90 375	97.03 355	94.56 422	81.33 413	75.36 437	90.52 412	71.69 352	94.54 439	68.81 456	76.84 390	90.07 429

UnsupCasMVSNet_bld		73.85 453	70.14 457	84.99 444	79.44 492	75.73 456	88.53 477	95.24 398	70.12 476	61.94 489	74.81 502	41.41 487	93.62 449	68.65 457	51.13 500	85.62 477

Patchmtry		83.61 398	81.64 398	89.50 392	93.36 360	82.84 391	84.10 491	94.20 433	69.47 479	79.57 399	86.88 455	84.43 172	94.78 434	68.48 458	74.30 409	90.88 408

KD-MVS_self_test		77.47 439	75.88 436	82.24 458	81.59 485	68.93 484	92.83 449	94.02 436	77.03 442	73.14 450	83.39 474	55.44 451	90.42 479	67.95 459	57.53 482	87.38 461

WAC-MVS						79.74 426								67.75 460

TransMVSNet (Re)		81.97 410	79.61 419	89.08 402	89.70 423	84.01 373	97.26 343	91.85 466	78.84 431	73.07 453	91.62 375	67.17 389	95.21 425	67.50 461	59.46 478	88.02 455

COLMAP_ROB	82.69 18	84.54 384	82.82 386	89.70 387	96.72 186	78.85 432	95.89 399	92.83 452	71.55 470	77.54 425	95.89 290	59.40 436	99.14 170	67.26 462	88.26 312	91.11 403
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
EG-PatchMatch MVS		79.92 420	77.59 427	86.90 426	87.06 457	77.90 444	96.20 392	94.06 435	74.61 461	66.53 481	88.76 437	40.40 489	96.20 375	67.02 463	83.66 347	86.61 468

DSMNet-mixed		81.60 413	81.43 401	82.10 461	84.36 470	60.79 494	93.63 437	86.74 496	79.00 429	79.32 404	87.15 453	63.87 416	89.78 484	66.89 464	91.92 276	95.73 321

testgi		82.29 407	81.00 405	86.17 433	87.24 455	74.84 461	97.39 336	91.62 470	88.63 246	75.85 434	95.42 301	46.07 480	91.55 473	66.87 465	79.94 372	92.12 357

MDA-MVSNet_test_wron		79.65 424	77.05 430	87.45 420	87.79 451	80.13 422	96.25 388	94.44 424	73.87 464	51.80 499	87.47 449	68.04 380	92.12 469	66.02 466	67.79 452	90.09 427

YYNet1		79.64 425	77.04 431	87.43 421	87.80 450	79.98 423	96.23 389	94.44 424	73.83 465	51.83 498	87.53 445	67.96 382	92.07 470	66.00 467	67.75 453	90.23 426

DeepMVS_CX				76.08 472	90.74 409	51.65 507		90.84 476	86.47 322	57.89 495	87.98 440	35.88 494	92.60 460	65.77 468	65.06 461	83.97 487

MASt3R-SfM		60.79 466	59.91 466	63.44 494	62.41 521	35.46 524	75.76 511	71.46 516	54.67 497	58.30 494	86.10 466	14.86 512	74.25 515	65.44 469	50.18 502	80.59 495

Anonymous20240521		78.63 431	76.90 432	83.82 451	82.82 481	72.86 470	95.72 408	93.57 444	73.55 467	72.17 457	84.79 471	49.69 474	92.51 463	65.29 470	74.50 405	86.09 473

TinyColmap		80.42 419	77.94 425	87.85 414	92.09 384	78.58 436	93.74 434	89.94 484	74.99 459	69.77 465	91.78 371	46.09 479	97.58 304	65.17 471	77.89 381	87.38 461

kuosan		84.40 388	83.34 382	87.60 417	95.87 226	79.21 429	92.39 452	96.87 229	76.12 449	73.79 444	93.98 323	81.51 228	90.63 478	64.13 472	75.42 396	92.95 336

MVS-HIRNet		79.01 427	75.13 441	90.66 359	93.82 347	81.69 405	85.16 485	93.75 440	54.54 498	74.17 442	59.15 515	57.46 441	96.58 346	63.74 473	94.38 222	93.72 332

ppachtmachnet_test		83.63 397	81.57 400	89.80 383	89.01 432	85.09 358	97.13 352	94.50 423	78.84 431	76.14 429	91.00 391	69.78 363	94.61 438	63.40 474	74.36 408	89.71 438

CL-MVSNet_self_test		79.89 422	78.34 424	84.54 448	81.56 486	75.01 459	96.88 361	95.62 364	81.10 416	75.86 433	85.81 467	68.49 375	90.26 480	63.21 475	56.51 490	88.35 453

Patchmatch-test		86.25 358	84.06 376	92.82 300	94.42 315	82.88 390	82.88 498	94.23 432	71.58 469	79.39 402	90.62 406	89.00 75	96.42 357	63.03 476	91.37 294	99.16 126

pmmvs3		72.86 454	69.76 459	82.17 459	73.86 503	74.19 463	94.20 429	89.01 491	64.23 491	67.72 475	80.91 489	41.48 486	88.65 491	62.40 477	54.02 494	83.68 489

new_pmnet		76.02 443	73.71 448	82.95 456	83.88 472	72.85 471	91.26 467	92.26 459	70.44 474	62.60 488	81.37 485	47.64 478	92.32 465	61.85 478	72.10 433	83.68 489

tfpnnormal		83.65 396	81.35 402	90.56 363	91.37 401	88.06 263	97.29 341	97.87 69	78.51 435	76.20 428	90.91 394	64.78 411	96.47 354	61.71 479	73.50 419	87.13 467

testing3		87.75 331	88.22 308	86.36 431	94.66 307	77.41 447	99.52 72	97.95 62	86.05 328	81.12 379	96.69 262	86.18 138	89.31 487	61.65 480	90.12 306	92.35 348

MDA-MVSNet-bldmvs		77.82 438	74.75 444	87.03 423	88.33 441	78.52 437	96.34 382	92.85 451	75.57 456	48.87 501	87.89 442	57.32 442	92.49 464	60.79 481	64.80 462	90.08 428

Anonymous20231206		80.76 417	79.42 420	84.79 446	84.78 469	72.98 468	96.53 374	92.97 450	79.56 428	74.33 440	88.83 436	61.27 429	92.15 467	60.59 482	75.92 394	89.24 444

new-patchmatchnet		74.80 452	72.40 453	81.99 462	78.36 496	72.20 473	94.44 423	92.36 458	77.06 441	63.47 487	79.98 491	51.04 468	88.85 489	60.53 483	54.35 493	84.92 484

LCM-MVSNet		60.07 468	56.37 470	71.18 481	54.81 530	48.67 510	82.17 501	89.48 488	37.95 513	49.13 500	69.12 507	13.75 514	81.76 501	59.28 484	51.63 499	83.10 491

MVStest1		76.56 442	73.43 449	85.96 437	86.30 463	80.88 420	94.26 428	91.74 467	61.98 492	58.53 493	89.96 425	69.30 370	91.47 475	59.26 485	49.56 503	85.52 478

TAPA-MVS	87.50 9	90.35 276	89.05 286	94.25 255	98.48 103	85.17 356	98.42 241	96.58 252	82.44 401	87.24 301	98.53 127	82.77 202	98.84 184	59.09 486	97.88 139	98.72 187
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		78.51 433	77.48 428	81.62 463	83.07 477	71.03 476	96.11 394	92.83 452	81.66 410	69.31 468	89.68 429	57.53 440	87.29 496	58.65 487	68.47 448	86.53 469

PatchT		85.44 372	83.19 383	92.22 314	93.13 365	83.00 385	83.80 494	96.37 269	70.62 472	90.55 255	79.63 492	84.81 165	94.87 431	58.18 488	91.59 283	98.79 172

usedtu_dtu_shiyan2		69.89 458	65.80 463	82.15 460	69.90 511	68.09 486	93.09 443	90.63 479	58.33 493	61.56 490	79.31 494	28.96 500	89.43 486	57.76 489	52.68 498	88.92 449

APD_test1		68.93 459	66.98 461	74.77 476	80.62 489	53.15 504	87.97 478	85.01 501	53.76 499	59.26 492	87.52 446	25.19 501	89.95 481	56.20 490	67.33 454	81.19 494

MIMVSNet1		75.92 444	73.30 450	83.81 452	81.29 487	75.57 457	92.26 453	92.05 463	73.09 468	67.48 478	86.18 464	40.87 488	87.64 495	55.78 491	70.68 440	88.21 454

FE-MVSNET		75.08 450	72.25 454	83.56 454	77.93 497	76.96 451	94.36 424	87.96 494	75.72 453	66.01 484	81.60 484	50.48 471	88.85 489	55.38 492	60.82 473	84.86 485

OpenMVS_ROB	73.86 20	77.99 437	75.06 442	86.77 428	83.81 473	77.94 443	96.38 381	91.53 472	67.54 484	68.38 472	87.13 454	43.94 481	96.08 382	55.03 493	81.83 359	86.29 472

RPMNet		85.07 377	81.88 396	94.64 234	93.47 356	86.24 320	84.97 488	97.21 198	64.85 490	90.76 250	78.80 495	80.95 239	99.27 160	53.76 494	92.17 273	98.41 216

N_pmnet		70.19 456	69.87 458	71.12 482	88.24 442	30.63 533	95.85 404	28.70 531	70.18 475	68.73 471	86.55 458	64.04 415	93.81 446	53.12 495	73.46 420	88.94 448

dmvs_testset		77.17 440	78.99 421	71.71 480	87.25 454	38.55 523	91.44 464	81.76 506	85.77 334	69.49 467	95.94 289	69.71 365	84.37 500	52.71 496	76.82 391	92.21 353

PDCNetPlus		48.73 480	46.34 482	55.88 500	64.17 519	41.40 522	76.11 510	34.96 528	50.17 503	35.24 515	71.04 504	15.41 510	67.33 520	52.41 497	17.59 532	58.93 516

dongtai		81.36 414	80.61 406	83.62 453	94.25 330	73.32 467	95.15 416	96.81 232	73.56 466	69.79 464	92.81 354	81.00 238	86.80 497	52.08 498	70.06 441	90.75 414

DenseAffine		61.07 465	57.33 468	72.29 478	78.74 494	56.29 499	83.24 495	69.15 517	53.26 500	47.82 503	79.48 493	13.61 515	80.66 506	51.15 499	39.51 509	79.92 496

PMMVS2		58.97 469	55.07 472	70.69 483	62.72 520	55.37 501	85.97 482	80.52 507	49.48 504	45.94 504	68.31 508	15.73 509	80.78 505	49.79 500	37.12 511	75.91 500

DKM		55.59 474	51.49 479	67.89 486	72.36 508	48.29 511	80.45 505	52.05 524	47.86 505	42.54 508	77.08 498	9.06 527	77.32 513	48.87 501	33.13 512	78.05 497

RoMa-SfM		58.43 470	54.99 473	68.74 485	74.29 501	50.87 508	82.37 499	58.12 523	50.53 502	48.40 502	81.78 482	12.70 516	78.25 510	47.71 502	39.01 510	77.09 499

test_0402		78.81 429	76.33 434	86.26 432	91.18 403	78.44 438	95.88 401	91.34 474	68.55 480	70.51 463	89.91 426	52.65 463	94.99 427	47.14 503	79.78 373	85.34 481

Syy-MVS		84.10 393	84.53 369	82.83 457	95.14 267	65.71 488	97.68 322	96.66 241	86.52 319	82.63 347	96.84 253	68.15 378	89.89 482	45.62 504	91.54 286	92.87 337

LoFTR		61.59 462	56.89 469	75.68 473	76.61 499	50.06 509	82.20 500	79.57 508	52.13 501	39.02 514	75.71 499	14.90 511	93.30 452	45.35 505	46.48 507	83.69 488

DKM-HiRes		50.92 478	46.71 481	63.56 493	66.42 515	42.72 518	76.47 506	41.46 527	42.47 508	39.40 513	73.35 503	7.13 533	72.77 517	44.18 506	29.50 514	75.19 503

RoMa-HiRes		51.04 477	47.47 480	61.73 496	65.35 516	42.38 520	76.31 507	41.57 526	42.69 507	42.32 509	77.75 497	9.33 524	73.10 516	42.68 507	29.24 515	69.72 510

FPMVS		61.57 463	60.32 465	65.34 489	60.14 526	42.44 519	91.02 470	89.72 486	44.15 506	42.63 507	80.93 487	19.02 505	80.59 507	42.50 508	72.76 425	73.00 506

PMatch-SfM		44.26 483	39.30 488	59.12 498	52.80 531	33.36 526	66.34 513	29.85 529	36.60 514	30.58 517	70.53 505	2.50 551	68.49 518	42.14 509	22.39 525	75.51 501

testf1		56.38 472	53.73 474	64.31 491	64.84 517	45.11 513	80.50 503	75.94 514	38.87 511	42.74 505	75.07 500	11.26 519	81.19 503	41.11 510	53.27 495	66.63 511

APD_test2		56.38 472	53.73 474	64.31 491	64.84 517	45.11 513	80.50 503	75.94 514	38.87 511	42.74 505	75.07 500	11.26 519	81.19 503	41.11 510	53.27 495	66.63 511

EGC-MVSNET		60.70 467	55.37 471	76.72 471	86.35 462	71.08 475	89.96 475	84.44 503	0.38 551	1.50 553	84.09 473	37.30 492	88.10 492	40.85 512	73.44 421	70.97 509

ELoFTR		47.00 481	42.41 485	60.77 497	51.54 532	32.77 527	63.82 516	61.24 521	39.04 510	29.94 518	67.31 510	4.83 535	75.52 514	39.39 513	24.54 523	74.03 505

PMatch-Up-SfM		39.29 487	34.48 490	53.73 503	46.70 535	28.02 534	58.71 517	21.05 541	31.53 517	27.94 519	66.24 511	1.99 554	61.38 524	38.41 514	17.72 530	71.80 508

ANet_high		50.71 479	46.17 483	64.33 490	44.27 537	52.30 506	76.13 509	78.73 509	64.95 489	27.37 521	55.23 518	14.61 513	67.74 519	36.01 515	18.23 529	72.95 507

MatchFormer		56.78 471	51.80 478	71.74 479	73.47 505	45.39 512	81.84 502	76.12 512	40.41 509	35.13 516	69.22 506	12.67 517	92.15 467	35.57 516	41.74 508	77.67 498

Gipuma		54.77 475	52.22 477	62.40 495	86.50 460	59.37 497	50.20 526	90.35 483	36.52 515	41.20 511	49.49 520	18.33 507	81.29 502	32.10 517	65.34 460	46.54 524
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
PMVS	41.42 23	45.67 482	42.50 484	55.17 501	34.28 550	32.37 528	66.24 514	78.71 510	30.72 518	22.04 527	59.59 514	4.59 536	77.85 512	27.49 518	58.84 479	55.29 517
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
GLUNet-SfM		37.11 488	32.05 492	52.28 504	44.07 539	25.94 535	52.38 525	46.25 525	24.11 522	21.50 528	55.60 517	6.32 534	66.20 521	27.48 519	10.71 542	64.70 513

MVE	44.00 22	41.70 484	37.64 489	53.90 502	49.46 533	43.37 517	65.09 515	66.66 518	26.19 521	25.77 524	48.53 521	3.58 539	63.35 523	26.15 520	27.28 520	54.97 518
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
WB-MVS		66.44 460	66.29 462	66.89 487	74.84 500	44.93 515	93.00 444	84.09 504	71.15 471	55.82 496	81.63 483	63.79 417	80.31 508	21.85 521	50.47 501	75.43 502

SP-DiffGlue		29.92 494	29.42 498	31.40 512	32.10 553	20.02 537	47.81 527	27.27 534	14.91 527	26.24 522	54.34 519	10.53 522	24.46 536	21.49 522	30.15 513	49.71 523

SSC-MVS		65.42 461	65.20 464	66.06 488	73.96 502	43.83 516	92.08 455	83.54 505	69.77 477	54.73 497	80.92 488	63.30 419	79.92 509	20.48 523	48.02 504	74.44 504

E-PMN		41.02 485	40.93 486	41.29 505	61.97 522	33.83 525	84.00 493	65.17 519	27.17 519	27.56 520	46.72 524	17.63 508	60.41 525	19.32 524	18.82 526	29.61 528

EMVS		39.96 486	39.88 487	40.18 506	59.57 528	32.12 530	84.79 490	64.57 520	26.27 520	26.14 523	44.18 528	18.73 506	59.29 526	17.03 525	17.67 531	29.12 529

wuyk23d		16.71 504	16.73 508	16.65 518	60.15 525	25.22 536	41.24 528	5.17 556	6.56 545	5.48 549	3.61 551	3.64 538	22.72 537	15.20 526	9.52 544	1.99 548

testmvs		18.81 500	23.05 501	6.10 533	4.48 556	2.29 559	97.78 312	3.00 557	3.27 549	18.60 534	62.71 512	1.53 556	2.49 553	14.26 527	1.80 550	13.50 533

XFeat-MNN		22.62 497	22.31 502	23.56 515	28.01 554	15.00 551	39.69 529	25.09 538	11.81 532	17.88 536	39.92 534	7.77 531	29.38 530	13.26 528	17.33 535	26.31 530

XFeat-NN		22.06 499	22.11 503	21.91 516	27.57 555	14.27 552	38.62 530	22.62 540	11.16 533	18.84 533	41.23 530	7.46 532	26.91 531	13.19 529	18.30 528	24.56 531

SP-SuperGlue		30.18 493	29.74 497	31.50 511	60.57 524	18.71 540	57.45 518	26.07 535	13.70 528	20.25 530	39.95 532	9.22 526	25.03 535	11.85 530	28.64 518	50.78 520

SP-LightGlue		30.23 492	29.76 496	31.66 510	60.90 523	18.79 539	57.25 519	25.88 536	13.65 529	20.11 531	39.95 532	9.29 525	25.08 534	11.83 531	28.96 516	51.11 519

SP-NN		29.64 495	29.14 499	31.16 514	59.77 527	18.23 541	56.90 521	24.71 539	12.64 530	18.99 532	40.64 531	8.48 528	25.23 533	11.37 532	28.74 517	50.01 522

test123		16.58 505	19.47 504	7.91 532	3.59 557	5.37 558	94.32 426	1.39 558	2.49 550	13.98 537	44.60 527	2.91 547	2.65 552	11.35 533	0.57 551	15.70 532

SP-MNN		29.29 496	28.62 500	31.29 513	59.13 529	18.03 544	56.77 522	25.19 537	11.83 531	18.01 535	39.35 535	8.35 529	25.39 532	10.99 534	27.91 519	50.47 521

ALIKED-NN		33.05 490	31.67 493	37.18 509	69.89 512	31.76 531	55.83 524	28.14 532	16.92 525	23.23 525	47.45 522	9.65 523	45.41 529	8.80 535	25.13 522	34.38 527

ALIKED-LG		33.96 489	32.42 491	38.57 507	70.35 509	32.25 529	57.19 520	29.49 530	19.94 524	22.96 526	46.96 523	10.85 521	47.42 527	8.53 536	25.49 521	36.04 525

ALIKED-MNN		32.26 491	30.45 494	37.68 508	69.07 513	31.55 532	56.28 523	27.56 533	16.30 526	21.15 529	44.78 526	8.12 530	46.74 528	8.19 537	22.59 524	34.76 526

SIFT-NN		18.10 501	18.53 505	16.83 517	48.67 534	18.97 538	33.34 531	14.35 542	7.78 534	10.98 538	25.86 537	3.78 537	19.51 538	3.23 538	18.78 527	12.02 534

SIFT-MNN		17.20 502	17.47 506	16.41 519	45.38 536	18.16 542	31.28 533	14.20 543	7.60 535	9.54 539	25.18 538	3.39 540	19.18 539	3.18 539	17.44 533	11.88 535

SIFT-NN-NCMNet		16.94 503	17.19 507	16.19 520	43.53 540	18.04 543	31.30 532	14.18 544	7.55 537	9.51 540	24.88 539	3.32 541	18.84 540	3.08 540	17.35 534	11.70 537

SIFT-NN-UMatch		15.49 508	15.62 511	15.11 524	38.08 546	15.93 548	29.97 534	13.04 545	7.57 536	7.22 544	24.84 541	3.26 542	18.03 543	3.02 541	13.56 538	11.37 538

SIFT-NN-CMatch		15.72 507	15.77 510	15.60 522	39.99 544	16.99 547	28.08 536	12.85 547	7.52 538	9.34 541	24.86 540	3.24 543	18.08 542	2.99 542	13.01 539	11.71 536

SIFT-UMatch		14.73 510	14.79 513	14.57 525	40.58 543	15.36 550	27.70 537	11.21 550	7.28 541	6.62 546	24.07 543	2.81 549	17.91 545	2.87 543	9.94 543	10.45 541

SIFT-NN-PointCN		14.43 511	14.70 514	13.64 527	36.13 547	12.94 554	27.63 538	11.82 549	7.03 544	8.24 542	23.49 546	3.21 544	16.75 547	2.85 544	11.89 540	11.22 539

SIFT-ConvMatch		15.12 509	15.10 512	15.19 523	42.19 541	17.16 546	26.33 539	12.02 548	7.39 539	7.26 543	24.08 542	2.92 546	17.97 544	2.85 544	10.90 541	10.43 542

SIFT-NCM-Cal		16.07 506	16.20 509	15.69 521	44.16 538	17.32 545	29.83 535	12.88 546	7.33 540	6.22 547	23.59 545	3.00 545	18.75 541	2.74 546	16.09 536	10.99 540

SIFT-UM-Cal		13.73 513	13.86 516	13.34 528	39.95 545	13.63 553	25.68 540	9.21 553	7.19 543	5.57 548	23.60 544	2.66 550	16.67 548	2.70 547	8.18 547	9.73 544

SIFT-CM-Cal		14.12 512	14.09 515	14.22 526	40.92 542	15.56 549	23.80 541	10.18 551	7.20 542	6.72 545	23.20 547	2.86 548	16.98 546	2.67 548	9.24 546	10.13 543

SIFT-PCN-Cal		12.09 515	12.36 518	11.26 530	35.43 548	9.79 556	22.24 543	8.83 554	6.37 547	5.43 550	20.44 548	2.34 552	14.88 549	2.35 549	7.87 548	9.13 546

SIFT-PointCN		12.37 514	12.72 517	11.33 529	35.33 549	10.01 555	23.72 542	9.79 552	6.45 546	5.30 551	20.10 549	2.22 553	14.67 550	2.33 550	9.26 545	9.30 545

SIFT-NCMNet		10.41 516	10.63 520	9.76 531	33.41 551	9.03 557	18.23 544	5.49 555	6.29 548	4.60 552	17.58 550	1.84 555	12.74 551	2.03 551	6.21 549	7.52 547

mmdepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

monomultidepth		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

test_blank		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet_test		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

DCPMVS		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

cdsmvs_eth3d_5k		22.52 498	30.03 495	0.00 534	0.00 558	0.00 560	0.00 545	97.17 205	0.00 552	0.00 554	98.77 107	74.35 322	0.00 554	0.00 552	0.00 552	0.00 549

pcd_1.5k_mvsjas		6.87 518	9.16 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	82.48 212	0.00 554	0.00 552	0.00 552	0.00 549

sosnet-low-res		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

sosnet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uncertanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

Regformer		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

ab-mvs-re		8.21 517	10.94 519	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	98.50 131	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

uanet		0.00 519	0.00 522	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	0.00 557	0.00 554	0.00 552	0.00 552	0.00 549

TestfortrainingZip				99.33 5	99.87 2	97.98 5	99.65 52	98.06 52	92.29 115	99.91 1	99.64 2	95.49 8	100.00 1		98.29 133	100.00 1

FOURS1					99.50 48	88.94 235	99.55 66	97.47 164	91.32 140	98.12 65

test_one_0601					99.59 34	94.89 39		97.64 124	93.14 92	98.93 33	99.45 19	93.45 20

eth-test2					0.00 558

eth-test					0.00 558

test_241102_ONE					99.63 24	95.24 29		97.72 98	94.16 61	99.30 17	99.49 12	93.32 22	99.98 14

save fliter					99.34 56	93.85 70	99.65 52	97.63 128	95.69 33

test0726					99.66 18	95.20 34	99.77 29	97.70 103	93.95 66	99.35 15	99.54 4	93.18 25

GSMVS																98.84 164

test_part2					99.54 42	95.42 24				98.13 63

sam_mvs1												88.39 84				98.84 164

sam_mvs												87.08 112

MTGPA								97.45 167

test_post											46.00 525	87.37 103	97.11 324

patchmatchnet-post											84.86 470	88.73 80	96.81 337

MTMP							99.21 114	91.09 475

TEST9					99.57 39	93.17 91	99.38 95	97.66 115	89.57 208	98.39 55	99.18 48	90.88 46	99.66 117

test_8					99.55 41	93.07 94	99.37 98	97.64 124	90.18 181	98.36 57	99.19 45	90.94 42	99.64 123

agg_prior					99.54 42	92.66 107		97.64 124		97.98 72			99.61 125

test_prior4						92.00 123	99.41 92

test_prior				97.01 77	99.58 36	91.77 130		97.57 143					99.49 135			99.79 43

新几何2							98.26 268

旧先验1					98.97 81	92.90 103		97.74 94			99.15 55	91.05 41			99.33 69	99.60 82

原ACMM2							98.69 190

test222					98.32 104	91.21 144	98.08 291	97.58 140	83.74 372	95.87 128	99.02 79	86.74 120			99.64 44	99.81 40

segment_acmp												90.56 54

testdata1							97.89 304		92.43 108

test12				97.83 40	99.33 59	94.45 57		97.55 145		97.56 79		88.60 82	99.50 134		99.71 38	99.55 87

plane_prior7					93.84 344	85.73 344

plane_prior6					93.92 341	86.02 336						72.92 338

plane_prior4											96.52 266

plane_prior3						85.91 338			93.65 81	86.99 303

plane_prior2							99.02 148		93.38 88

plane_prior1					93.90 343

plane_prior						86.07 334	99.14 130		93.81 77						86.26 324

n2								0.00 559

nn								0.00 559

door-mid								84.90 502

test11								97.68 109

door								85.30 499

HQP5-MVS						86.39 315

HQP-NCC					93.95 336		99.16 122		93.92 68	87.57 296

ACMP_Plane					93.95 336		99.16 122		93.92 68	87.57 296

HQP4-MVS										87.57 296			97.77 281			92.72 339

HQP3-MVS								96.37 269							86.29 322

HQP2-MVS												73.34 331

NP-MVS					93.94 339	86.22 322					96.67 263

ACMMP++_ref															82.64 356

ACMMP++															83.83 343

Test By Simon												83.62 181

High-resolution multi-view benchmark