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.

fmvsm_s_conf0.5_n_9		97.33 27	97.57 15	96.62 102	98.43 84	90.32 207	97.80 105	98.53 29	97.24 4	99.62 2	99.14 2	88.65 110	99.80 41	99.54 1	99.15 94	99.74 10

MM		97.29 31	96.98 42	98.23 13	98.01 125	95.03 29	98.07 61	95.76 366	97.78 1	97.52 64	98.80 40	88.09 120	99.86 11	99.44 2	99.37 67	99.80 3

fmvsm_s_conf0.5_n_8		97.32 28	97.48 23	96.85 89	98.28 96	91.07 171	97.76 109	98.62 25	97.53 2	99.20 12	99.12 5	88.24 118	99.81 36	99.41 3	99.17 91	99.67 16

fmvsm_s_conf0.5_n_10		97.29 31	97.40 26	96.97 87	98.24 102	91.96 128	97.89 89	98.72 12	96.77 7	99.46 3	99.06 12	87.78 128	99.84 27	99.40 4	99.27 75	99.12 94

fmvsm_s_conf0.5_n_2		96.62 70	96.82 55	96.02 155	97.98 127	90.43 199	97.50 156	98.59 26	96.59 10	99.31 6	99.08 8	84.47 212	99.75 59	99.37 5	98.45 133	97.88 250

fmvsm_l_conf0.5_n_9		97.59 13	97.79 6	96.97 87	98.28 96	91.49 146	97.61 141	98.71 13	97.10 5	99.70 1	98.93 24	90.95 77	99.77 53	99.35 6	99.53 33	99.65 21

fmvsm_s_conf0.5_n_3		97.15 36	97.36 28	96.52 108	97.98 127	91.19 163	97.84 96	98.65 23	97.08 6	99.25 9	99.10 6	87.88 126	99.79 47	99.32 7	99.18 90	98.59 179

fmvsm_l_conf0.5_n_a		97.63 11	97.76 7	97.26 69	98.25 101	92.59 102	97.81 104	98.68 18	94.93 50	99.24 10	98.87 33	93.52 23	99.79 47	99.32 7	99.21 83	99.40 66

fmvsm_l_conf0.5_n		97.65 9	97.75 8	97.34 62	98.21 108	92.75 94	97.83 99	98.73 10	95.04 47	99.30 7	98.84 38	93.34 26	99.78 50	99.32 7	99.13 97	99.50 52

fmvsm_s_conf0.5_n_11		97.30 29	97.59 14	96.43 120	98.42 85	91.37 153	98.04 64	98.00 118	97.30 3	99.45 4	99.21 1	89.28 98	99.80 41	99.27 10	99.35 69	98.12 229

fmvsm_s_conf0.1_n_2		96.33 84	96.44 79	96.00 159	97.30 169	90.37 205	97.53 153	97.92 128	96.52 11	99.14 15	99.08 8	83.21 236	99.74 60	99.22 11	98.06 151	97.88 250

fmvsm_s_conf0.5_n_5		97.00 45	96.97 43	97.09 80	97.58 162	92.56 103	97.68 126	98.47 34	94.02 96	98.90 26	98.89 30	88.94 104	99.78 50	99.18 12	99.03 106	98.93 129

fmvsm_s_conf0.5_n_4		96.75 62	97.07 34	95.79 178	97.76 143	89.57 239	97.66 130	98.66 21	95.36 32	99.03 16	98.90 27	88.39 115	99.73 62	99.17 13	98.66 121	98.08 237

fmvsm_l_conf0.5_n_3		97.64 10	97.60 13	97.79 35	98.14 115	93.94 58	97.93 84	98.65 23	96.70 8	99.38 5	99.07 11	89.92 92	99.81 36	99.16 14	99.43 53	99.61 30

test_fmvsm_n_1920		97.55 16	97.89 4	96.53 106	98.41 87	91.73 132	98.01 67	99.02 1	96.37 13	99.30 7	98.92 25	92.39 45	99.79 47	99.16 14	99.46 46	98.08 237

test_fmvsmconf_n		97.49 21	97.56 16	97.29 65	97.44 166	92.37 109	97.91 86	98.88 4	95.83 19	98.92 24	99.05 14	91.45 62	99.80 41	99.12 16	99.46 46	99.69 15

fmvsm_s_conf0.5_n_6		97.08 39	97.17 30	96.81 90	97.28 171	91.73 132	97.75 111	98.50 30	94.86 54	99.22 11	98.78 42	89.75 95	99.76 55	99.10 17	99.29 73	98.94 125

fmvsm_s_conf0.5_n		96.85 54	97.13 31	96.04 152	98.07 122	90.28 208	97.97 78	98.76 9	94.93 50	98.84 29	99.06 12	88.80 107	99.65 80	99.06 18	98.63 123	98.18 222

test_fmvsmconf0.1_n		97.09 38	97.06 35	97.19 74	95.67 317	92.21 116	97.95 81	98.27 55	95.78 23	98.40 42	99.00 16	89.99 90	99.78 50	99.06 18	99.41 59	99.59 32

MGCNet		96.74 64	96.31 81	98.02 22	96.87 206	94.65 33	97.58 143	94.39 435	96.47 12	97.16 76	98.39 68	87.53 137	99.87 8	98.97 20	99.41 59	99.55 43

fmvsm_s_conf0.5_n_a		96.75 62	96.93 46	96.20 141	97.64 152	90.72 189	98.00 68	98.73 10	94.55 75	98.91 25	99.08 8	88.22 119	99.63 89	98.91 21	98.37 137	98.25 217

test_fmvsmvis_n_1920		96.70 65	96.84 51	96.31 130	96.62 234	91.73 132	97.98 72	98.30 48	96.19 14	96.10 127	98.95 20	89.42 96	99.76 55	98.90 22	99.08 101	97.43 277

fmvsm_s_conf0.1_n		96.58 73	96.77 60	96.01 158	96.67 232	90.25 209	97.91 86	98.38 37	94.48 79	98.84 29	99.14 2	88.06 121	99.62 91	98.82 23	98.60 125	98.15 226

test_fmvsmconf0.01_n		96.15 88	95.85 91	97.03 84	92.66 443	91.83 131	97.97 78	97.84 143	95.57 28	97.53 63	99.00 16	84.20 219	99.76 55	98.82 23	99.08 101	99.48 56

fmvsm_s_conf0.5_n_7		96.45 77	96.80 57	95.37 214	97.29 170	88.38 295	97.23 198	98.47 34	95.14 41	98.43 41	99.09 7	87.58 134	99.72 66	98.80 25	99.21 83	98.02 241

fmvsm_s_conf0.1_n_a		96.40 79	96.47 73	96.16 143	95.48 326	90.69 190	97.91 86	98.33 45	94.07 94	98.93 21	99.14 2	87.44 142	99.61 92	98.63 26	98.32 139	98.18 222

MVSMamba_PlusPlus		96.51 74	96.48 72	96.59 103	98.07 122	91.97 126	98.14 55	97.79 147	90.43 270	97.34 72	97.52 177	91.29 68	99.19 157	98.12 27	99.64 14	98.60 178

test-260524					99.31 29	95.74 9		98.19 74		97.99 52		93.53 22	99.87 8	98.08 28	99.63 16

APDe-MVS		97.82 6	97.73 9	98.08 20	99.15 40	94.82 31	98.81 8	98.30 48	94.76 66	98.30 43	98.90 27	93.77 19	99.68 76	97.93 29	99.69 3	99.75 8
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test_vis1_n_1920		94.17 174	94.58 148	92.91 364	97.42 167	82.02 436	97.83 99	97.85 138	94.68 69	98.10 49	98.49 58	70.15 422	99.32 143	97.91 30	98.82 113	97.40 279

reproduce_model		97.51 20	97.51 20	97.50 55	98.99 53	93.01 84	97.79 107	98.21 67	95.73 24	97.99 52	99.03 15	92.63 40	99.82 34	97.80 31	99.42 56	99.67 16

BridgeMVS		96.84 56	96.89 48	96.68 94	97.63 154	92.22 115	98.17 54	97.82 145	94.44 81	98.23 45	97.36 187	90.97 76	99.22 154	97.74 32	99.66 10	98.61 177

reproduce-ours		97.53 18	97.51 20	97.60 52	98.97 54	93.31 75	97.71 122	98.20 69	95.80 21	97.88 57	98.98 18	92.91 32	99.81 36	97.68 33	99.43 53	99.67 16

our_new_method		97.53 18	97.51 20	97.60 52	98.97 54	93.31 75	97.71 122	98.20 69	95.80 21	97.88 57	98.98 18	92.91 32	99.81 36	97.68 33	99.43 53	99.67 16

MSC_two_6792asdad				98.86 1	98.67 68	96.94 1		97.93 126					99.86 11	97.68 33	99.67 6	99.77 4

No_MVS				98.86 1	98.67 68	96.94 1		97.93 126					99.86 11	97.68 33	99.67 6	99.77 4

patch_mono-2		96.83 57	97.44 24	95.01 234	99.05 46	85.39 388	96.98 221	98.77 8	94.70 68	97.99 52	98.66 45	93.61 21	99.91 1	97.67 37	99.50 40	99.72 14

lecture		97.58 15	97.63 11	97.43 59	99.37 19	92.93 88	98.86 7	98.85 5	95.27 36	98.65 36	98.90 27	91.97 53	99.80 41	97.63 38	99.21 83	99.57 36

test_vis1_n		92.37 258	92.26 242	92.72 372	94.75 376	82.64 426	98.02 66	96.80 305	91.18 233	97.77 61	97.93 114	58.02 480	98.29 299	97.63 38	98.21 144	97.23 288

test_fmvs1_n		92.73 247	92.88 215	92.29 384	96.08 301	81.05 444	97.98 72	97.08 268	90.72 252	96.79 89	98.18 91	63.07 469	98.45 281	97.62 40	98.42 135	97.36 280

test_fmvs1		93.21 221	93.53 186	92.25 387	96.55 250	81.20 443	97.40 175	96.96 287	90.68 254	96.80 87	98.04 101	69.25 430	98.40 284	97.58 41	98.50 128	97.16 291

SED-MVS		98.05 3	97.99 2	98.24 12	99.42 10	95.30 19	98.25 40	98.27 55	95.13 42	99.19 13	98.89 30	95.54 5	99.85 22	97.52 42	99.66 10	99.56 40

test_241102_TWO								98.27 55	95.13 42	98.93 21	98.89 30	94.99 12	99.85 22	97.52 42	99.65 13	99.74 10

DVP-MVS		97.91 4	97.81 5	98.22 15	99.45 6	95.36 15	98.21 48	97.85 138	94.92 52	98.73 31	98.87 33	95.08 9	99.84 27	97.52 42	99.67 6	99.48 56
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
test_0728_SECOND				98.51 4	99.45 6	95.93 6	98.21 48	98.28 52					99.86 11	97.52 42	99.67 6	99.75 8

DVP-MVS++		98.06 2	97.99 2	98.28 10	98.67 68	95.39 13	99.29 1	98.28 52	94.78 63	98.93 21	98.87 33	96.04 2	99.86 11	97.45 46	99.58 25	99.59 32

test_0728_THIRD									94.78 63	98.73 31	98.87 33	95.87 4	99.84 27	97.45 46	99.72 2	99.77 4

EC-MVSNet		96.42 78	96.47 73	96.26 136	97.01 194	91.52 145	98.89 5	97.75 150	94.42 82	96.64 98	97.68 156	89.32 97	98.60 267	97.45 46	99.11 100	98.67 174

IU-MVS					99.42 10	95.39 13		97.94 125	90.40 272	98.94 20				97.41 49	99.66 10	99.74 10

MED-MVS test				98.00 25	99.56 1	94.50 37	98.69 11	98.70 16	93.45 123	98.73 31	98.53 53		99.86 11	97.40 50	99.58 25	99.65 21

MED-MVS		98.08 1	98.08 1	98.06 21	99.56 1	94.50 37	98.69 11	98.70 16	95.63 25	98.73 31	98.95 20	95.46 7	99.86 11	97.40 50	99.63 16	99.82 1

ME-MVS		97.54 17	97.39 27	98.00 25	99.21 37	94.50 37	97.75 111	98.34 44	94.23 89	98.15 47	98.53 53	93.32 29	99.84 27	97.40 50	99.58 25	99.65 21

balanced_ft_v1		95.56 110	95.40 105	96.07 149	97.16 177	90.36 206	98.23 44	97.31 238	92.89 156	96.36 116	97.11 205	83.28 234	99.26 150	97.40 50	98.80 115	98.58 180

mmtdpeth		89.70 372	88.96 370	91.90 396	95.84 312	84.42 404	97.46 167	95.53 385	90.27 273	94.46 196	90.50 454	69.74 428	98.95 195	97.39 54	69.48 491	92.34 465

dcpmvs_2		96.37 81	97.05 38	94.31 285	98.96 56	84.11 409	97.56 147	97.51 195	93.92 100	97.43 69	98.52 55	92.75 36	99.32 143	97.32 55	99.50 40	99.51 49

CS-MVS		96.86 52	97.06 35	96.26 136	98.16 114	91.16 168	99.09 3	97.87 133	95.30 35	97.06 82	98.03 103	91.72 55	98.71 245	97.10 56	99.17 91	98.90 134

TSAR-MVS + MP.		97.42 22	97.33 29	97.69 47	99.25 33	94.24 47	98.07 61	97.85 138	93.72 107	98.57 37	98.35 72	93.69 20	99.40 135	97.06 57	99.46 46	99.44 61
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CNVR-MVS		97.68 8	97.44 24	98.37 7	98.90 60	95.86 7	97.27 192	98.08 94	95.81 20	97.87 60	98.31 81	94.26 14	99.68 76	97.02 58	99.49 43	99.57 36

SD-MVS		97.41 23	97.53 18	97.06 83	98.57 79	94.46 40	97.92 85	98.14 84	94.82 59	99.01 17	98.55 51	94.18 15	97.41 413	96.94 59	99.64 14	99.32 74
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
SPE-MVS-test		96.89 50	97.04 39	96.45 119	98.29 95	91.66 139	99.03 4	97.85 138	95.84 18	96.90 85	97.97 111	91.24 69	98.75 234	96.92 60	99.33 70	98.94 125

CANet		96.39 80	96.02 87	97.50 55	97.62 155	93.38 70	97.02 214	97.96 123	95.42 31	94.86 181	97.81 140	87.38 144	99.82 34	96.88 61	99.20 88	99.29 75

AstraMVS		94.82 154	94.64 144	95.34 217	96.36 272	88.09 312	97.58 143	94.56 427	94.98 48	95.70 146	97.92 117	81.93 274	98.93 198	96.87 62	95.88 239	98.99 114

TSAR-MVS + GP.		96.69 67	96.49 71	97.27 68	98.31 94	93.39 69	96.79 245	96.72 308	94.17 90	97.44 67	97.66 159	92.76 35	99.33 141	96.86 63	97.76 163	99.08 100

DeepPCF-MVS	93.97 1	96.61 71	97.09 33	95.15 225	98.09 118	86.63 354	96.00 325	98.15 82	95.43 30	97.95 55	98.56 49	93.40 25	99.36 139	96.77 64	99.48 44	99.45 59

BP-MVS1		95.89 98	95.49 98	97.08 82	96.67 232	93.20 79	98.08 59	96.32 334	94.56 74	96.32 117	97.84 134	84.07 222	99.15 166	96.75 65	98.78 116	98.90 134

test_cas_vis1_n_1920		94.48 167	94.55 152	94.28 287	96.78 223	86.45 360	97.63 137	97.64 165	93.32 129	97.68 62	98.36 71	73.75 391	99.08 179	96.73 66	99.05 103	97.31 284

SMA-MVS		97.35 25	97.03 40	98.30 9	99.06 45	95.42 12	97.94 82	98.18 77	90.57 265	98.85 28	98.94 23	93.33 27	99.83 32	96.72 67	99.68 4	99.63 26
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
guyue		95.17 131	94.96 127	95.82 173	96.97 198	89.65 234	97.56 147	95.58 378	94.82 59	95.72 143	97.42 183	82.90 248	98.84 209	96.71 68	96.93 196	98.96 118

DPE-MVS		97.86 5	97.65 10	98.47 5	99.17 39	95.78 8	97.21 201	98.35 41	95.16 40	98.71 35	98.80 40	95.05 11	99.89 3	96.70 69	99.73 1	99.73 13
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
TestfortrainingZip a		97.79 7	97.62 12	98.28 10	99.56 1	95.15 25	98.69 11	98.35 41	95.63 25	98.95 19	98.95 20	93.45 24	99.88 4	96.63 70	98.41 136	99.82 1

MSP-MVS		97.59 13	97.54 17	97.73 43	99.40 14	93.77 63	98.53 19	98.29 50	95.55 29	98.56 38	97.81 140	93.90 17	99.65 80	96.62 71	99.21 83	99.77 4
Zhenlong Yuan, Cong Liu, Fei Shen, Zhaoxin Li, Jingguo luo, Tianlu Mao and Zhaoqi Wang: MSP-MVS: Multi-granularity Segmentation Prior Guided Multi-View Stereo. AAAI2025
MSLP-MVS++		96.94 48	97.06 35	96.59 103	98.72 65	91.86 130	97.67 127	98.49 31	94.66 71	97.24 74	98.41 67	92.31 48	98.94 197	96.61 72	99.46 46	98.96 118

MP-MVS-pluss		96.70 65	96.27 83	97.98 27	99.23 36	94.71 32	96.96 223	98.06 102	90.67 255	95.55 153	98.78 42	91.07 73	99.86 11	96.58 73	99.55 30	99.38 70
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
SteuartSystems-ACMMP		97.62 12	97.53 18	97.87 29	98.39 90	94.25 46	98.43 27	98.27 55	95.34 34	98.11 48	98.56 49	94.53 13	99.71 68	96.57 74	99.62 19	99.65 21
Skip Steuart: Steuart Systems R&D Blog.
MCST-MVS		97.18 34	96.84 51	98.20 16	99.30 30	95.35 17	97.12 208	98.07 99	93.54 117	96.08 128	97.69 155	93.86 18	99.71 68	96.50 75	99.39 63	99.55 43

SF-MVS		97.39 24	97.13 31	98.17 17	99.02 49	95.28 21	98.23 44	98.27 55	92.37 177	98.27 44	98.65 47	93.33 27	99.72 66	96.49 76	99.52 35	99.51 49

EI-MVSNet-Vis-set		96.51 74	96.47 73	96.63 99	98.24 102	91.20 162	96.89 231	97.73 153	94.74 67	96.49 108	98.49 58	90.88 80	99.58 100	96.44 77	98.32 139	99.13 91

LuminaMVS		94.89 148	94.35 161	96.53 106	95.48 326	92.80 93	96.88 233	96.18 351	92.85 157	95.92 136	96.87 224	81.44 281	98.83 210	96.43 78	97.10 191	97.94 246

diffmvs_AUTHOR		95.33 116	95.27 112	95.50 206	96.37 271	89.08 266	96.08 318	97.38 228	93.09 142	96.53 106	97.74 149	86.45 162	98.68 249	96.32 79	97.48 169	98.75 165

VDD-MVS		93.82 197	93.08 206	96.02 155	97.88 136	89.96 223	97.72 119	95.85 362	92.43 175	95.86 138	98.44 64	68.42 439	99.39 136	96.31 80	94.85 265	98.71 171

ACMMP_NAP		97.20 33	96.86 49	98.23 13	99.09 41	95.16 24	97.60 142	98.19 74	92.82 159	97.93 56	98.74 44	91.60 60	99.86 11	96.26 81	99.52 35	99.67 16

diffmvs		95.25 122	95.13 117	95.63 192	96.43 265	89.34 253	95.99 326	97.35 233	92.83 158	96.31 118	97.37 186	86.44 163	98.67 252	96.26 81	97.19 188	98.87 145
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EI-MVSNet-UG-set		96.34 83	96.30 82	96.47 116	98.20 109	90.93 178	96.86 234	97.72 155	94.67 70	96.16 125	98.46 62	90.43 85	99.58 100	96.23 83	97.96 156	98.90 134

SR-MVS		97.01 44	96.86 49	97.47 57	99.09 41	93.27 77	97.98 72	98.07 99	93.75 106	97.45 66	98.48 61	91.43 64	99.59 97	96.22 84	99.27 75	99.54 45

xiu_mvs_v1_base_debu		95.01 140	94.76 138	95.75 184	96.58 243	91.71 135	96.25 304	97.35 233	92.99 144	96.70 93	96.63 240	82.67 254	99.44 131	96.22 84	97.46 170	96.11 326

xiu_mvs_v1_base		95.01 140	94.76 138	95.75 184	96.58 243	91.71 135	96.25 304	97.35 233	92.99 144	96.70 93	96.63 240	82.67 254	99.44 131	96.22 84	97.46 170	96.11 326

xiu_mvs_v1_base_debi		95.01 140	94.76 138	95.75 184	96.58 243	91.71 135	96.25 304	97.35 233	92.99 144	96.70 93	96.63 240	82.67 254	99.44 131	96.22 84	97.46 170	96.11 326

alignmvs		95.87 100	95.23 113	97.78 37	97.56 164	95.19 23	97.86 92	97.17 257	94.39 85	96.47 110	96.40 254	85.89 174	99.20 156	96.21 88	95.11 263	98.95 122

sasdasda		96.02 91	95.45 101	97.75 41	97.59 158	95.15 25	98.28 35	97.60 172	94.52 77	96.27 120	96.12 269	87.65 131	99.18 160	96.20 89	94.82 267	98.91 131

canonicalmvs		96.02 91	95.45 101	97.75 41	97.59 158	95.15 25	98.28 35	97.60 172	94.52 77	96.27 120	96.12 269	87.65 131	99.18 160	96.20 89	94.82 267	98.91 131

MGCFI-Net		95.94 96	95.40 105	97.56 54	97.59 158	94.62 34	98.21 48	97.57 179	94.41 83	96.17 124	96.16 267	87.54 136	99.17 162	96.19 91	94.73 272	98.91 131

RRT-MVS		94.51 165	94.35 161	94.98 238	96.40 266	86.55 357	97.56 147	97.41 222	93.19 134	94.93 179	97.04 210	79.12 328	99.30 147	96.19 91	97.32 181	99.09 98

MTAPA		97.08 39	96.78 59	97.97 28	99.37 19	94.42 42	97.24 194	98.08 94	95.07 46	96.11 126	98.59 48	90.88 80	99.90 2	96.18 93	99.50 40	99.58 35

APD-MVS_3200maxsize		96.81 58	96.71 63	97.12 77	99.01 52	92.31 112	97.98 72	98.06 102	93.11 140	97.44 67	98.55 51	90.93 78	99.55 110	96.06 94	99.25 80	99.51 49

SR-MVS-dyc-post		96.88 51	96.80 57	97.11 79	99.02 49	92.34 110	97.98 72	98.03 111	93.52 120	97.43 69	98.51 56	91.40 65	99.56 108	96.05 95	99.26 78	99.43 63

RE-MVS-def			96.72 62		99.02 49	92.34 110	97.98 72	98.03 111	93.52 120	97.43 69	98.51 56	90.71 82		96.05 95	99.26 78	99.43 63

MVS_111021_HR		96.68 69	96.58 68	96.99 85	98.46 81	92.31 112	96.20 310	98.90 3	94.30 88	95.86 138	97.74 149	92.33 46	99.38 138	96.04 97	99.42 56	99.28 77

PHI-MVS		96.77 60	96.46 76	97.71 46	98.40 88	94.07 54	98.21 48	98.45 36	89.86 282	97.11 80	98.01 106	92.52 43	99.69 74	96.03 98	99.53 33	99.36 72

casdiffmvs_mvg		95.81 101	95.57 94	96.51 112	96.87 206	91.49 146	97.50 156	97.56 187	93.99 98	95.13 170	97.92 117	87.89 125	98.78 218	95.97 99	97.33 179	99.26 79
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS++		97.34 26	96.97 43	98.47 5	99.08 43	96.16 5	97.55 152	97.97 122	95.59 27	96.61 99	97.89 122	92.57 42	99.84 27	95.95 100	99.51 38	99.40 66

DELS-MVS		96.61 71	96.38 80	97.30 64	97.79 141	93.19 80	95.96 327	98.18 77	95.23 37	95.87 137	97.65 160	91.45 62	99.70 73	95.87 101	99.44 52	99.00 112
Christian Sormann, Emanuele Santellani, Mattia Rossi, Andreas Kuhn, Friedrich Fraundorfer: DELS-MVS: Deep Epipolar Line Search for Multi-View Stereo. Winter Conference on Applications of Computer Vision (WACV), 2023
MVS_111021_LR		96.24 87	96.19 85	96.39 125	98.23 107	91.35 155	96.24 307	98.79 7	93.99 98	95.80 140	97.65 160	89.92 92	99.24 152	95.87 101	99.20 88	98.58 180

h-mvs33		94.15 177	93.52 188	96.04 152	97.81 140	90.22 210	97.62 140	97.58 176	95.19 38	96.74 91	97.45 180	83.67 227	99.61 92	95.85 103	79.73 448	98.29 215

hse-mvs2		93.45 214	92.99 208	94.81 248	97.02 193	88.59 285	96.69 259	96.47 326	95.19 38	96.74 91	96.16 267	83.67 227	98.48 280	95.85 103	79.13 452	97.35 282

NCCC		97.30 29	97.03 40	98.11 19	98.77 63	95.06 28	97.34 181	98.04 109	95.96 15	97.09 81	97.88 127	93.18 30	99.71 68	95.84 105	99.17 91	99.56 40

VNet		95.89 98	95.45 101	97.21 72	98.07 122	92.94 87	97.50 156	98.15 82	93.87 102	97.52 64	97.61 167	85.29 195	99.53 114	95.81 106	95.27 258	99.16 86

PC_three_1452									90.77 249	98.89 27	98.28 86	96.24 1	98.35 292	95.76 107	99.58 25	99.59 32

9.14			96.75 61		98.93 57		97.73 116	98.23 66	91.28 226	97.88 57	98.44 64	93.00 31	99.65 80	95.76 107	99.47 45

viewmamba		95.18 130	95.15 116	95.26 221	96.31 275	88.25 302	96.29 300	97.27 244	93.61 111	95.65 149	97.91 119	86.79 154	98.64 259	95.69 109	96.82 203	98.88 142

XVS		97.18 34	96.96 45	97.81 33	99.38 17	94.03 56	98.59 17	98.20 69	94.85 55	96.59 101	98.29 84	91.70 57	99.80 41	95.66 110	99.40 61	99.62 27

X-MVStestdata		91.71 284	89.67 353	97.81 33	99.38 17	94.03 56	98.59 17	98.20 69	94.85 55	96.59 101	32.69 545	91.70 57	99.80 41	95.66 110	99.40 61	99.62 27

baseline		95.58 108	95.42 104	96.08 147	96.78 223	90.41 200	97.16 205	97.45 212	93.69 110	95.65 149	97.85 132	87.29 146	98.68 249	95.66 110	97.25 185	99.13 91

ETV-MVS		96.02 91	95.89 90	96.40 123	97.16 177	92.44 107	97.47 165	97.77 149	94.55 75	96.48 109	94.51 351	91.23 71	98.92 200	95.65 113	98.19 145	97.82 258

casdiffmvs		95.64 105	95.49 98	96.08 147	96.76 229	90.45 197	97.29 187	97.44 216	94.00 97	95.46 158	97.98 110	87.52 139	98.73 238	95.64 114	97.33 179	99.08 100
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HFP-MVS		97.14 37	96.92 47	97.83 31	99.42 10	94.12 52	98.52 20	98.32 46	93.21 131	97.18 75	98.29 84	92.08 50	99.83 32	95.63 115	99.59 21	99.54 45

ACMMPR		97.07 41	96.84 51	97.79 35	99.44 9	93.88 59	98.52 20	98.31 47	93.21 131	97.15 77	98.33 78	91.35 66	99.86 11	95.63 115	99.59 21	99.62 27

HPM-MVS		96.69 67	96.45 77	97.40 60	99.36 23	93.11 82	98.87 6	98.06 102	91.17 234	96.40 114	97.99 109	90.99 75	99.58 100	95.61 117	99.61 20	99.49 54
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CP-MVS		97.02 43	96.81 56	97.64 50	99.33 26	93.54 66	98.80 9	98.28 52	92.99 144	96.45 113	98.30 83	91.90 54	99.85 22	95.61 117	99.68 4	99.54 45

DeepC-MVS	93.07 3	96.06 89	95.66 93	97.29 65	97.96 129	93.17 81	97.30 186	98.06 102	93.92 100	93.38 232	98.66 45	86.83 153	99.73 62	95.60 119	99.22 82	98.96 118
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ZNCC-MVS		96.96 46	96.67 64	97.85 30	99.37 19	94.12 52	98.49 24	98.18 77	92.64 167	96.39 115	98.18 91	91.61 59	99.88 4	95.59 120	99.55 30	99.57 36

onestephybrid01		95.12 132	95.01 124	95.46 211	96.39 270	88.92 273	96.28 302	97.27 244	92.67 163	96.00 133	97.73 152	86.28 165	98.66 255	95.58 121	96.85 201	98.79 156

hybridnocas07		94.93 145	94.78 137	95.37 214	96.27 277	88.62 283	96.10 316	97.26 246	92.35 178	95.58 152	97.48 178	85.60 188	98.65 257	95.47 122	96.90 199	98.85 147

region2R		97.07 41	96.84 51	97.77 39	99.46 5	93.79 61	98.52 20	98.24 63	93.19 134	97.14 78	98.34 75	91.59 61	99.87 8	95.46 123	99.59 21	99.64 25

Casviewmamba		95.67 104	95.55 95	96.03 154	96.95 200	90.12 212	97.72 119	97.55 191	94.10 93	95.23 166	98.18 91	87.32 145	98.80 216	95.40 124	97.52 168	99.19 83

OPU-MVS				98.55 3	98.82 62	96.86 3	98.25 40				98.26 87	96.04 2	99.24 152	95.36 125	99.59 21	99.56 40

lupinMVS		94.99 144	94.56 149	96.29 134	96.34 273	91.21 160	95.83 335	96.27 341	88.93 319	96.22 122	96.88 222	86.20 169	98.85 207	95.27 126	99.05 103	98.82 153

hybrid		94.76 158	94.60 146	95.27 219	96.24 279	88.36 296	96.05 320	97.25 249	91.40 220	95.40 159	97.59 170	85.48 191	98.63 262	95.23 127	96.71 211	98.83 152

reproduce_monomvs		91.30 314	91.10 286	91.92 394	96.82 215	82.48 430	97.01 217	97.49 198	94.64 73	88.35 368	95.27 314	70.53 417	98.10 318	95.20 128	84.60 415	95.19 379

mPP-MVS		96.86 52	96.60 66	97.64 50	99.40 14	93.44 68	98.50 23	98.09 93	93.27 130	95.95 135	98.33 78	91.04 74	99.88 4	95.20 128	99.57 29	99.60 31

DeepC-MVS_fast	93.89 2	96.93 49	96.64 65	97.78 37	98.64 74	94.30 43	97.41 171	98.04 109	94.81 61	96.59 101	98.37 70	91.24 69	99.64 88	95.16 130	99.52 35	99.42 65
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
jason		94.84 152	94.39 159	96.18 142	95.52 324	90.93 178	96.09 317	96.52 323	89.28 304	96.01 132	97.32 188	84.70 208	98.77 222	95.15 131	98.91 112	98.85 147
jason: jason.
train_agg		96.30 85	95.83 92	97.72 44	98.70 66	94.19 48	96.41 283	98.02 114	88.58 331	96.03 129	97.56 174	92.73 38	99.59 97	95.04 132	99.37 67	99.39 68

mvsany_test1		93.93 193	93.98 171	93.78 320	94.94 366	86.80 347	94.62 395	92.55 469	88.77 328	96.85 86	98.49 58	88.98 102	98.08 323	95.03 133	95.62 248	96.46 314

test_prior2							96.35 292		92.80 160	96.03 129	97.59 170	92.01 51		95.01 134	99.38 64

NormalMVS		96.36 82	96.11 86	97.12 77	99.37 19	92.90 89	97.99 69	97.63 167	95.92 16	96.57 104	97.93 114	85.34 193	99.50 122	94.99 135	99.21 83	98.97 115

SymmetryMVS		95.94 96	95.54 96	97.15 75	97.85 137	92.90 89	97.99 69	96.91 295	95.92 16	96.57 104	97.93 114	85.34 193	99.50 122	94.99 135	96.39 230	99.05 105

nrg030		94.05 184	93.31 198	96.27 135	95.22 349	94.59 35	98.34 30	97.46 207	92.93 151	91.21 293	96.64 236	87.23 148	98.22 304	94.99 135	85.80 395	95.98 330

E5new		95.04 136	94.88 130	95.52 200	96.62 234	89.02 268	97.29 187	97.57 179	92.54 168	95.04 172	97.89 122	85.65 183	98.77 222	94.92 138	96.44 225	98.78 157

E6new		95.04 136	94.88 130	95.52 200	96.60 239	89.02 268	97.29 187	97.57 179	92.54 168	95.04 172	97.90 120	85.66 181	98.77 222	94.92 138	96.44 225	98.78 157

E6		95.04 136	94.88 130	95.52 200	96.60 239	89.02 268	97.29 187	97.57 179	92.54 168	95.04 172	97.90 120	85.66 181	98.77 222	94.92 138	96.44 225	98.78 157

E5		95.04 136	94.88 130	95.52 200	96.62 234	89.02 268	97.29 187	97.57 179	92.54 168	95.04 172	97.89 122	85.65 183	98.77 222	94.92 138	96.44 225	98.78 157

VDDNet		93.05 230	92.07 245	96.02 155	96.84 210	90.39 201	98.08 59	95.85 362	86.22 395	95.79 141	98.46 62	67.59 442	99.19 157	94.92 138	94.85 265	98.47 194

E3new		95.28 118	95.11 120	95.80 175	97.03 191	89.76 229	96.78 249	97.54 192	92.06 195	95.40 159	97.75 146	87.49 140	98.76 228	94.85 143	97.10 191	98.88 142

mvsmamba		94.57 162	94.14 166	95.87 167	97.03 191	89.93 224	97.84 96	95.85 362	91.34 222	94.79 185	96.80 225	80.67 297	98.81 213	94.85 143	98.12 149	98.85 147

APD-MVS		96.95 47	96.60 66	98.01 23	99.03 48	94.93 30	97.72 119	98.10 92	91.50 214	98.01 51	98.32 80	92.33 46	99.58 100	94.85 143	99.51 38	99.53 48
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
GST-MVS		96.85 54	96.52 70	97.82 32	99.36 23	94.14 51	98.29 34	98.13 85	92.72 162	96.70 93	98.06 99	91.35 66	99.86 11	94.83 146	99.28 74	99.47 58

MP-MVS		96.77 60	96.45 77	97.72 44	99.39 16	93.80 60	98.41 28	98.06 102	93.37 126	95.54 155	98.34 75	90.59 84	99.88 4	94.83 146	99.54 32	99.49 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
viewcassd2359sk11		95.26 120	95.09 121	95.80 175	96.95 200	89.72 231	96.80 244	97.56 187	92.21 186	95.37 161	97.80 142	87.17 149	98.77 222	94.82 148	97.10 191	98.90 134

test9_res														94.81 149	99.38 64	99.45 59

viewmanbaseed2359cas		95.24 123	95.02 123	95.91 164	96.87 206	89.98 220	96.82 240	97.49 198	92.26 182	95.47 157	97.82 138	86.47 161	98.69 247	94.80 150	97.20 187	99.06 104

PS-MVSNAJ		95.37 114	95.33 109	95.49 207	97.35 168	90.66 192	95.31 367	97.48 201	93.85 103	96.51 107	95.70 294	88.65 110	99.65 80	94.80 150	98.27 142	96.17 320

HPM-MVS_fast		96.51 74	96.27 83	97.22 71	99.32 27	92.74 95	98.74 10	98.06 102	90.57 265	96.77 90	98.35 72	90.21 87	99.53 114	94.80 150	99.63 16	99.38 70

E2		95.20 126	95.00 125	95.79 178	96.79 218	89.66 232	96.82 240	97.58 176	92.35 178	95.28 163	97.83 136	86.68 156	98.76 228	94.79 153	96.92 197	98.95 122

E3		95.20 126	95.00 125	95.79 178	96.77 225	89.66 232	96.82 240	97.58 176	92.35 178	95.28 163	97.83 136	86.69 155	98.76 228	94.79 153	96.92 197	98.95 122

xiu_mvs_v2_base		95.32 117	95.29 110	95.40 213	97.22 173	90.50 195	95.44 360	97.44 216	93.70 109	96.46 111	96.18 264	88.59 114	99.53 114	94.79 153	97.81 160	96.17 320

hybridcas		95.46 112	95.29 110	95.96 162	96.83 212	90.08 214	97.63 137	97.49 198	93.76 105	94.79 185	98.04 101	86.87 152	98.72 243	94.71 156	97.53 167	99.08 100

E4		95.09 133	94.86 134	95.77 181	96.58 243	89.56 240	96.85 235	97.56 187	92.50 172	95.03 176	97.86 130	86.03 172	98.78 218	94.71 156	96.65 215	98.96 118

CSCG		96.05 90	95.91 89	96.46 118	99.24 34	90.47 196	98.30 33	98.57 28	89.01 313	93.97 212	97.57 172	92.62 41	99.76 55	94.66 158	99.27 75	99.15 88

test_fmvs2		89.77 370	89.93 342	89.31 450	93.68 412	76.37 481	97.64 135	95.90 359	89.84 285	91.49 279	96.26 262	58.77 478	97.10 424	94.65 159	91.13 334	94.46 424

EIA-MVS		95.53 111	95.47 100	95.71 189	97.06 186	89.63 235	97.82 101	97.87 133	93.57 113	93.92 214	95.04 323	90.61 83	98.95 195	94.62 160	98.68 120	98.54 184

SDMVSNet		94.17 174	93.61 182	95.86 170	98.09 118	91.37 153	97.35 180	98.20 69	93.18 136	91.79 272	97.28 192	79.13 327	98.93 198	94.61 161	92.84 305	97.28 285

VortexMVS		92.88 240	92.64 226	93.58 336	96.58 243	87.53 328	96.93 226	97.28 243	92.78 161	89.75 326	94.99 324	82.73 253	97.76 373	94.60 162	88.16 371	95.46 354

ZD-MVS					99.05 46	94.59 35		98.08 94	89.22 306	97.03 83	98.10 95	92.52 43	99.65 80	94.58 163	99.31 72

ACMMP		96.27 86	95.93 88	97.28 67	99.24 34	92.62 100	98.25 40	98.81 6	92.99 144	94.56 192	98.39 68	88.96 103	99.85 22	94.57 164	97.63 164	99.36 72
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
viewdifsd2359ckpt11		93.46 211	93.22 202	94.17 291	96.11 298	85.42 384	96.43 279	97.07 271	92.91 152	94.20 203	98.00 107	80.82 295	98.73 238	94.42 165	89.04 362	98.34 212

viewmsd2359difaftdt		93.46 211	93.23 201	94.17 291	96.12 296	85.42 384	96.43 279	97.08 268	92.91 152	94.21 202	98.00 107	80.82 295	98.74 236	94.41 166	89.05 360	98.34 212

viewmacassd2359aftdt		95.07 135	94.80 136	95.87 167	96.53 253	89.84 226	96.90 230	97.48 201	92.44 174	95.36 162	97.89 122	85.23 196	98.68 249	94.40 167	97.00 195	99.09 98

GDP-MVS		95.62 106	95.13 117	97.09 80	96.79 218	93.26 78	97.89 89	97.83 144	93.58 112	96.80 87	97.82 138	83.06 243	99.16 164	94.40 167	97.95 157	98.87 145

viewdifsd2359ckpt07		94.76 158	94.68 143	95.01 234	96.76 229	87.41 329	96.38 289	97.43 219	92.65 165	94.52 193	97.75 146	85.55 189	98.81 213	94.36 169	96.69 212	98.82 153

PGM-MVS		96.81 58	96.53 69	97.65 48	99.35 25	93.53 67	97.65 131	98.98 2	92.22 184	97.14 78	98.44 64	91.17 72	99.85 22	94.35 170	99.46 46	99.57 36

ET-MVSNet_ETH3D		91.49 302	90.11 332	95.63 192	96.40 266	91.57 144	95.34 364	93.48 456	90.60 263	75.58 486	95.49 305	80.08 310	96.79 439	94.25 171	89.76 352	98.52 186

LFMVS		93.60 204	92.63 227	96.52 108	98.13 117	91.27 157	97.94 82	93.39 457	90.57 265	96.29 119	98.31 81	69.00 432	99.16 164	94.18 172	95.87 240	99.12 94

MVSFormer		95.37 114	95.16 115	95.99 160	96.34 273	91.21 160	98.22 46	97.57 179	91.42 218	96.22 122	97.32 188	86.20 169	97.92 355	94.07 173	99.05 103	98.85 147

test_djsdf		93.07 229	92.76 219	94.00 302	93.49 421	88.70 280	98.22 46	97.57 179	91.42 218	90.08 318	95.55 302	82.85 250	97.92 355	94.07 173	91.58 326	95.40 361

mvs_anonymous		93.82 197	93.74 178	94.06 298	96.44 264	85.41 386	95.81 337	97.05 278	89.85 284	90.09 317	96.36 256	87.44 142	97.75 375	93.97 175	96.69 212	99.02 106

VPA-MVSNet		93.24 220	92.48 236	95.51 204	95.70 315	92.39 108	97.86 92	98.66 21	92.30 181	92.09 264	95.37 309	80.49 302	98.40 284	93.95 176	85.86 394	95.75 343

agg_prior2														93.94 177	99.38 64	99.50 52

mvs_tets		92.31 261	91.76 258	93.94 310	93.41 426	88.29 298	97.63 137	97.53 193	92.04 196	88.76 360	96.45 251	74.62 383	98.09 322	93.91 178	91.48 328	95.45 356

Effi-MVS+		94.93 145	94.45 157	96.36 128	96.61 237	91.47 149	96.41 283	97.41 222	91.02 242	94.50 194	95.92 278	87.53 137	98.78 218	93.89 179	96.81 204	98.84 151

jajsoiax		92.42 255	91.89 255	94.03 301	93.33 429	88.50 291	97.73 116	97.53 193	92.00 198	88.85 357	96.50 249	75.62 373	98.11 317	93.88 180	91.56 327	95.48 351

XVG-OURS-SEG-HR		93.86 196	93.55 184	94.81 248	97.06 186	88.53 290	95.28 368	97.45 212	91.68 206	94.08 209	97.68 156	82.41 262	98.90 203	93.84 181	92.47 311	96.98 294

PS-MVSNAJss		93.74 200	93.51 189	94.44 275	93.91 404	89.28 258	97.75 111	97.56 187	92.50 172	89.94 320	96.54 247	88.65 110	98.18 309	93.83 182	90.90 340	95.86 331

EPNet		95.20 126	94.56 149	97.14 76	92.80 440	92.68 99	97.85 95	94.87 418	96.64 9	92.46 249	97.80 142	86.23 166	99.65 80	93.72 183	98.62 124	99.10 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
viewmambaseed2359dif		94.28 170	94.14 166	94.71 256	96.21 280	86.97 343	95.93 329	97.11 264	89.00 314	95.00 178	97.70 153	86.02 173	98.59 271	93.71 184	96.59 217	98.57 182

viewdifsd2359ckpt13		94.87 150	94.52 153	95.90 165	96.88 205	90.19 211	96.92 227	97.36 231	91.26 227	94.65 189	97.46 179	85.79 178	98.64 259	93.64 185	96.76 206	98.88 142

viewdifsd2359ckpt09		94.81 155	94.37 160	96.12 146	96.91 202	90.75 188	96.94 224	97.31 238	90.51 268	94.31 199	97.38 185	85.70 180	98.71 245	93.54 186	96.75 207	98.90 134

PVSNet_Blended_VisFu		95.27 119	94.91 129	96.38 126	98.20 109	90.86 181	97.27 192	98.25 61	90.21 274	94.18 205	97.27 194	87.48 141	99.73 62	93.53 187	97.77 162	98.55 183

CPTT-MVS		95.57 109	95.19 114	96.70 93	99.27 32	91.48 148	98.33 31	98.11 90	87.79 359	95.17 169	98.03 103	87.09 150	99.61 92	93.51 188	99.42 56	99.02 106

MVSTER		93.20 222	92.81 218	94.37 278	96.56 248	89.59 238	97.06 211	97.12 260	91.24 228	91.30 287	95.96 276	82.02 270	98.05 330	93.48 189	90.55 344	95.47 353

PVSNet_BlendedMVS		94.06 183	93.92 173	94.47 273	98.27 98	89.46 248	96.73 253	98.36 38	90.17 275	94.36 197	95.24 317	88.02 122	99.58 100	93.44 190	90.72 342	94.36 428

PVSNet_Blended		94.87 150	94.56 149	95.81 174	98.27 98	89.46 248	95.47 358	98.36 38	88.84 322	94.36 197	96.09 274	88.02 122	99.58 100	93.44 190	98.18 146	98.40 202

3Dnovator	91.36 5	95.19 129	94.44 158	97.44 58	96.56 248	93.36 72	98.65 16	98.36 38	94.12 92	89.25 346	98.06 99	82.20 266	99.77 53	93.41 192	99.32 71	99.18 85

EPP-MVSNet		95.22 125	95.04 122	95.76 182	97.49 165	89.56 240	98.67 15	97.00 285	90.69 253	94.24 201	97.62 166	89.79 94	98.81 213	93.39 193	96.49 222	98.92 130

testing3-2		92.10 272	92.05 246	92.27 385	97.71 146	79.56 464	97.42 169	94.41 434	93.53 118	93.22 238	95.49 305	69.16 431	99.11 172	93.25 194	94.22 280	98.13 227

CHOSEN 280x420		93.12 226	92.72 224	94.34 281	96.71 231	87.27 333	90.29 481	97.72 155	86.61 387	91.34 284	95.29 311	84.29 218	98.41 283	93.25 194	98.94 110	97.35 282

3Dnovator+	91.43 4	95.40 113	94.48 156	98.16 18	96.90 204	95.34 18	98.48 25	97.87 133	94.65 72	88.53 365	98.02 105	83.69 226	99.71 68	93.18 196	98.96 109	99.44 61

test_yl		94.78 156	94.23 164	96.43 120	97.74 144	91.22 158	96.85 235	97.10 265	91.23 231	95.71 144	96.93 217	84.30 216	99.31 145	93.10 197	95.12 261	98.75 165

DCV-MVSNet		94.78 156	94.23 164	96.43 120	97.74 144	91.22 158	96.85 235	97.10 265	91.23 231	95.71 144	96.93 217	84.30 216	99.31 145	93.10 197	95.12 261	98.75 165

test_vis1_rt		86.16 422	85.06 418	89.46 446	93.47 423	80.46 451	96.41 283	86.61 503	85.22 409	79.15 477	88.64 471	52.41 490	97.06 426	93.08 199	90.57 343	90.87 483

test1111		93.19 223	92.82 217	94.30 286	97.58 162	84.56 403	98.21 48	89.02 493	93.53 118	94.58 191	98.21 88	72.69 399	99.05 188	93.06 200	98.48 131	99.28 77

ECVR-MVS		93.19 223	92.73 223	94.57 267	97.66 150	85.41 386	98.21 48	88.23 495	93.43 124	94.70 188	98.21 88	72.57 400	99.07 183	93.05 201	98.49 129	99.25 80

HQP_MVS		93.78 199	93.43 194	94.82 246	96.21 280	89.99 218	97.74 114	97.51 195	94.85 55	91.34 284	96.64 236	81.32 283	98.60 267	93.02 202	92.23 314	95.86 331

plane_prior5								97.51 195					98.60 267	93.02 202	92.23 314	95.86 331

MonoMVSNet		91.92 277	91.77 257	92.37 379	92.94 436	83.11 422	97.09 210	95.55 380	92.91 152	90.85 297	94.55 348	81.27 285	96.52 443	93.01 204	87.76 375	97.47 276

test2506		91.60 292	90.78 299	94.04 300	97.66 150	83.81 412	98.27 37	75.53 515	93.43 124	95.23 166	98.21 88	67.21 445	99.07 183	93.01 204	98.49 129	99.25 80

MVS_Test		94.89 148	94.62 145	95.68 190	96.83 212	89.55 242	96.70 257	97.17 257	91.17 234	95.60 151	96.11 273	87.87 127	98.76 228	93.01 204	97.17 189	98.72 169

CLD-MVS		92.98 233	92.53 233	94.32 283	96.12 296	89.20 261	95.28 368	97.47 205	92.66 164	89.90 321	95.62 298	80.58 300	98.40 284	92.73 207	92.40 312	95.38 363
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
XVG-OURS		93.72 201	93.35 197	94.80 251	97.07 183	88.61 284	94.79 392	97.46 207	91.97 199	93.99 210	97.86 130	81.74 277	98.88 204	92.64 208	92.67 310	96.92 299

dtuplus		94.16 176	93.98 171	94.70 257	96.18 288	86.85 346	96.04 321	97.07 271	89.75 288	95.02 177	97.79 144	84.94 205	98.62 265	92.62 209	96.43 229	98.62 176

KinetiMVS		95.26 120	94.75 141	96.79 91	96.99 196	92.05 122	97.82 101	97.78 148	94.77 65	96.46 111	97.70 153	80.62 299	99.34 140	92.37 210	98.28 141	98.97 115

旧先验2							95.94 328		81.66 460	97.34 72			98.82 211	92.26 211

CDPH-MVS		95.97 94	95.38 107	97.77 39	98.93 57	94.44 41	96.35 292	97.88 131	86.98 379	96.65 97	97.89 122	91.99 52	99.47 127	92.26 211	99.46 46	99.39 68

FIs		94.09 182	93.70 179	95.27 219	95.70 315	92.03 124	98.10 57	98.68 18	93.36 128	90.39 304	96.70 231	87.63 133	97.94 352	92.25 213	90.50 346	95.84 334

LPG-MVS_test		92.94 236	92.56 230	94.10 296	96.16 291	88.26 300	97.65 131	97.46 207	91.29 223	90.12 314	97.16 200	79.05 330	98.73 238	92.25 213	91.89 322	95.31 368

LGP-MVS_train				94.10 296	96.16 291	88.26 300		97.46 207	91.29 223	90.12 314	97.16 200	79.05 330	98.73 238	92.25 213	91.89 322	95.31 368

SSM_0407		94.54 164	94.12 168	95.80 175	96.79 218	90.38 202	96.79 245	97.29 240	91.24 228	93.68 218	97.60 168	85.03 200	98.67 252	92.14 216	96.51 218	98.35 208

SSM_0404		94.73 160	94.31 163	95.98 161	97.05 188	90.90 180	97.01 217	97.29 240	91.24 228	94.17 206	97.60 168	85.03 200	98.76 228	92.14 216	97.30 182	98.29 215

cascas		91.20 319	90.08 333	94.58 266	94.97 362	89.16 264	93.65 440	97.59 175	79.90 471	89.40 338	92.92 420	75.36 374	98.36 291	92.14 216	94.75 270	96.23 316

OPM-MVS		93.28 219	92.76 219	94.82 246	94.63 382	90.77 186	96.65 263	97.18 255	93.72 107	91.68 276	97.26 195	79.33 325	98.63 262	92.13 219	92.28 313	95.07 384
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
BP-MVS														92.13 219

HQP-MVS		93.19 223	92.74 222	94.54 269	95.86 307	89.33 254	96.65 263	97.39 224	93.55 114	90.14 308	95.87 280	80.95 289	98.50 277	92.13 219	92.10 319	95.78 339

DP-MVS Recon		95.68 103	95.12 119	97.37 61	99.19 38	94.19 48	97.03 212	98.08 94	88.35 340	95.09 171	97.65 160	89.97 91	99.48 126	92.08 222	98.59 126	98.44 199

VPNet		92.23 267	91.31 275	94.99 236	95.56 322	90.96 174	97.22 200	97.86 137	92.96 150	90.96 295	96.62 243	75.06 376	98.20 306	91.90 223	83.65 429	95.80 337

sss		94.51 165	93.80 175	96.64 95	97.07 183	91.97 126	96.32 297	98.06 102	88.94 318	94.50 194	96.78 226	84.60 209	99.27 149	91.90 223	96.02 234	98.68 173

anonymousdsp		92.16 269	91.55 266	93.97 306	92.58 445	89.55 242	97.51 155	97.42 221	89.42 301	88.40 367	94.84 333	80.66 298	97.88 360	91.87 225	91.28 332	94.48 423

test_fmvs3		83.21 443	83.02 438	83.78 471	86.77 496	68.34 499	96.76 251	94.91 413	86.49 388	84.14 444	89.48 465	36.04 503	91.73 496	91.86 226	80.77 444	91.26 482

ACMP	89.59 10	92.62 249	92.14 244	94.05 299	96.40 266	88.20 307	97.36 179	97.25 249	91.52 213	88.30 371	96.64 236	78.46 342	98.72 243	91.86 226	91.48 328	95.23 375
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
HyFIR lowres test		93.66 203	92.92 213	95.87 167	98.24 102	89.88 225	94.58 397	98.49 31	85.06 413	93.78 216	95.78 289	82.86 249	98.67 252	91.77 228	95.71 245	99.07 103

UGNet		94.04 185	93.28 199	96.31 130	96.85 209	91.19 163	97.88 91	97.68 160	94.40 84	93.00 241	96.18 264	73.39 395	99.61 92	91.72 229	98.46 132	98.13 227
Wanjuan Su, Qingshan Xu, Wenbing Tao: Uncertainty-guided Multi-view Stereo Network for Depth Estimation. IEEE Transactions on Circuits and Systems for Video Technology, 2022
UniMVSNet_NR-MVSNet		93.37 216	92.67 225	95.47 210	95.34 338	92.83 91	97.17 204	98.58 27	92.98 149	90.13 312	95.80 285	88.37 117	97.85 361	91.71 230	83.93 424	95.73 345

DU-MVS		92.90 238	92.04 247	95.49 207	94.95 364	92.83 91	97.16 205	98.24 63	93.02 143	90.13 312	95.71 292	83.47 230	97.85 361	91.71 230	83.93 424	95.78 339

Effi-MVS+-dtu		93.08 228	93.21 203	92.68 375	96.02 304	83.25 419	97.14 207	96.72 308	93.85 103	91.20 294	93.44 410	83.08 241	98.30 298	91.69 232	95.73 244	96.50 311

UniMVSNet (Re)		93.31 218	92.55 231	95.61 194	95.39 332	93.34 73	97.39 176	98.71 13	93.14 139	90.10 316	94.83 334	87.71 129	98.03 334	91.67 233	83.99 423	95.46 354

LCM-MVSNet-Re		92.50 250	92.52 234	92.44 377	96.82 215	81.89 437	96.92 227	93.71 454	92.41 176	84.30 440	94.60 346	85.08 199	97.03 428	91.51 234	97.36 177	98.40 202

FC-MVSNet-test		93.94 191	93.57 183	95.04 232	95.48 326	91.45 151	98.12 56	98.71 13	93.37 126	90.23 307	96.70 231	87.66 130	97.85 361	91.49 235	90.39 347	95.83 335

PMMVS		92.86 241	92.34 239	94.42 277	94.92 367	86.73 350	94.53 399	96.38 332	84.78 418	94.27 200	95.12 322	83.13 240	98.40 284	91.47 236	96.49 222	98.12 229

Vis-MVSNet		95.23 124	94.81 135	96.51 112	97.18 176	91.58 143	98.26 39	98.12 87	94.38 86	94.90 180	98.15 94	82.28 264	98.92 200	91.45 237	98.58 127	99.01 109
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
CHOSEN 1792x2688		94.15 177	93.51 189	96.06 150	98.27 98	89.38 251	95.18 379	98.48 33	85.60 403	93.76 217	97.11 205	83.15 239	99.61 92	91.33 238	98.72 119	99.19 83

OMC-MVS		95.09 133	94.70 142	96.25 139	98.46 81	91.28 156	96.43 279	97.57 179	92.04 196	94.77 187	97.96 112	87.01 151	99.09 177	91.31 239	96.77 205	98.36 206

MG-MVS		95.61 107	95.38 107	96.31 130	98.42 85	90.53 194	96.04 321	97.48 201	93.47 122	95.67 148	98.10 95	89.17 100	99.25 151	91.27 240	98.77 117	99.13 91

ACMM	89.79 8	92.96 234	92.50 235	94.35 279	96.30 276	88.71 279	97.58 143	97.36 231	91.40 220	90.53 301	96.65 235	79.77 316	98.75 234	91.24 241	91.64 324	95.59 349
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
WTY-MVS		94.71 161	94.02 169	96.79 91	97.71 146	92.05 122	96.59 272	97.35 233	90.61 261	94.64 190	96.93 217	86.41 164	99.39 136	91.20 242	94.71 273	98.94 125

testing11		91.68 287	90.75 302	94.47 273	96.53 253	86.56 356	95.76 341	94.51 430	91.10 240	91.24 292	93.59 403	68.59 436	98.86 205	91.10 243	94.29 278	98.00 243

tt0805		91.09 323	90.07 336	94.16 294	95.61 319	88.31 297	97.56 147	96.51 324	89.56 294	89.17 349	95.64 297	67.08 449	98.38 290	91.07 244	88.44 369	95.80 337

Anonymous20240529		91.98 276	90.73 304	95.73 187	98.14 115	89.40 250	97.99 69	97.72 155	79.63 472	93.54 225	97.41 184	69.94 424	99.56 108	91.04 245	91.11 335	98.22 219

mamba_0408		93.70 202	92.99 208	95.83 172	96.79 218	90.38 202	88.69 491	97.07 271	90.96 244	93.68 218	97.31 190	84.97 203	98.76 228	90.95 246	96.51 218	98.35 208

SSM_04072		93.51 210	92.99 208	95.05 230	96.79 218	90.38 202	88.69 491	97.07 271	90.96 244	93.68 218	97.31 190	84.97 203	96.42 445	90.95 246	96.51 218	98.35 208

AUN-MVS		91.76 283	90.75 302	94.81 248	97.00 195	88.57 286	96.65 263	96.49 325	89.63 292	92.15 260	96.12 269	78.66 339	98.50 277	90.83 248	79.18 451	97.36 280

mvsany_test3		83.59 441	82.44 443	87.03 464	83.80 501	73.82 489	93.70 435	90.92 487	86.42 389	82.51 457	90.26 457	46.76 495	95.71 456	90.82 249	76.76 461	91.57 476

Elysia		94.00 187	93.12 204	96.64 95	96.08 301	92.72 97	97.50 156	97.63 167	91.15 236	94.82 182	97.12 203	74.98 378	99.06 185	90.78 250	98.02 152	98.12 229

StellarMVS		94.00 187	93.12 204	96.64 95	96.08 301	92.72 97	97.50 156	97.63 167	91.15 236	94.82 182	97.12 203	74.98 378	99.06 185	90.78 250	98.02 152	98.12 229

CANet_DTU		94.37 168	93.65 181	96.55 105	96.46 263	92.13 120	96.21 308	96.67 315	94.38 86	93.53 226	97.03 215	79.34 324	99.71 68	90.76 252	98.45 133	97.82 258

ab-mvs		93.57 207	92.55 231	96.64 95	97.28 171	91.96 128	95.40 361	97.45 212	89.81 286	93.22 238	96.28 260	79.62 321	99.46 128	90.74 253	93.11 302	98.50 189

CostFormer		91.18 322	90.70 306	92.62 376	94.84 372	81.76 438	94.09 421	94.43 432	84.15 425	92.72 248	93.77 392	79.43 323	98.20 306	90.70 254	92.18 317	97.90 248

casdiffseed414692147		94.55 163	94.02 169	96.15 144	96.61 237	90.79 184	97.42 169	97.39 224	92.18 191	93.95 213	97.64 163	84.37 215	98.66 255	90.68 255	95.91 238	99.00 112

icg_test_0407_2		93.58 205	93.46 191	93.94 310	96.19 284	86.16 369	93.73 434	97.24 251	91.54 209	93.50 227	97.04 210	85.64 186	96.91 434	90.68 255	95.59 249	98.76 161

IMVS_0407		93.94 191	93.75 177	94.49 272	96.19 284	86.16 369	96.35 292	97.24 251	91.54 209	93.50 227	97.04 210	85.64 186	98.54 274	90.68 255	95.59 249	98.76 161

IMVS_0404		92.44 253	91.92 253	94.00 302	96.19 284	86.16 369	93.84 431	97.24 251	91.54 209	88.17 377	97.04 210	76.96 360	97.09 425	90.68 255	95.59 249	98.76 161

IMVS_0403		93.98 189	93.79 176	94.55 268	96.19 284	86.16 369	96.35 292	97.24 251	91.54 209	93.59 222	97.04 210	85.86 175	98.73 238	90.68 255	95.59 249	98.76 161

Anonymous202405211		92.07 273	90.83 298	95.76 182	98.19 111	88.75 278	97.58 143	95.00 407	86.00 398	93.64 221	97.45 180	66.24 454	99.53 114	90.68 255	92.71 308	99.01 109

testing99		91.62 291	90.72 305	94.32 283	96.48 260	86.11 374	95.81 337	94.76 420	91.55 208	91.75 274	93.44 410	68.55 437	98.82 211	90.43 261	93.69 295	98.04 240

tpmrst		91.44 304	91.32 274	91.79 402	95.15 355	79.20 470	93.42 445	95.37 389	88.55 334	93.49 229	93.67 398	82.49 260	98.27 301	90.41 262	89.34 356	97.90 248

thisisatest0530		93.03 231	92.21 243	95.49 207	97.07 183	89.11 265	97.49 164	92.19 474	90.16 276	94.09 208	96.41 253	76.43 366	99.05 188	90.38 263	95.68 246	98.31 214

UA-Net		95.95 95	95.53 97	97.20 73	97.67 148	92.98 86	97.65 131	98.13 85	94.81 61	96.61 99	98.35 72	88.87 105	99.51 119	90.36 264	97.35 178	99.11 96

UniMVSNet_ETH3D		91.34 312	90.22 329	94.68 258	94.86 371	87.86 320	97.23 198	97.46 207	87.99 349	89.90 321	96.92 220	66.35 452	98.23 303	90.30 265	90.99 338	97.96 244

tttt0517		92.96 234	92.33 240	94.87 245	97.11 181	87.16 339	97.97 78	92.09 475	90.63 259	93.88 215	97.01 216	76.50 363	99.06 185	90.29 266	95.45 255	98.38 204

testing91		91.90 279	91.02 288	94.53 270	96.54 251	86.55 357	95.86 333	95.64 375	91.77 203	91.89 269	93.47 408	69.94 424	98.86 205	90.23 267	93.86 293	98.18 222

FA-MVS(test-final)		93.52 209	92.92 213	95.31 218	96.77 225	88.54 288	94.82 391	96.21 348	89.61 293	94.20 203	95.25 316	83.24 235	99.14 169	90.01 268	96.16 233	98.25 217

IS-MVSNet		94.90 147	94.52 153	96.05 151	97.67 148	90.56 193	98.44 26	96.22 346	93.21 131	93.99 210	97.74 149	85.55 189	98.45 281	89.98 269	97.86 158	99.14 90

miper_enhance_ethall		91.54 299	91.01 289	93.15 356	95.35 337	87.07 341	93.97 423	96.90 296	86.79 383	89.17 349	93.43 413	86.55 159	97.64 385	89.97 270	86.93 384	94.74 417

EI-MVSNet		93.03 231	92.88 215	93.48 343	95.77 313	86.98 342	96.44 277	97.12 260	90.66 257	91.30 287	97.64 163	86.56 158	98.05 330	89.91 271	90.55 344	95.41 358

IterMVS-LS		92.29 263	91.94 252	93.34 348	96.25 278	86.97 343	96.57 275	97.05 278	90.67 255	89.50 337	94.80 336	86.59 157	97.64 385	89.91 271	86.11 393	95.40 361
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
cl22		91.21 318	90.56 314	93.14 357	96.09 300	86.80 347	94.41 408	96.58 322	87.80 358	88.58 364	93.99 385	80.85 294	97.62 388	89.87 273	86.93 384	94.99 387

CDS-MVSNet		94.14 180	93.54 185	95.93 163	96.18 288	91.46 150	96.33 296	97.04 280	88.97 317	93.56 223	96.51 248	87.55 135	97.89 359	89.80 274	95.95 236	98.44 199
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
WR-MVS		92.34 259	91.53 267	94.77 253	95.13 357	90.83 182	96.40 287	97.98 121	91.88 200	89.29 343	95.54 303	82.50 259	97.80 368	89.79 275	85.27 403	95.69 346

NR-MVSNet		92.34 259	91.27 278	95.53 199	94.95 364	93.05 83	97.39 176	98.07 99	92.65 165	84.46 437	95.71 292	85.00 202	97.77 372	89.71 276	83.52 430	95.78 339

Anonymous20231211		90.63 344	89.42 360	94.27 288	98.24 102	89.19 263	98.05 63	97.89 129	79.95 470	88.25 374	94.96 326	72.56 401	98.13 313	89.70 277	85.14 405	95.49 350

testdata				95.46 211	98.18 113	88.90 275		97.66 161	82.73 450	97.03 83	98.07 98	90.06 88	98.85 207	89.67 278	98.98 108	98.64 175

Baseline_NR-MVSNet		91.20 319	90.62 310	92.95 363	93.83 407	88.03 313	97.01 217	95.12 403	88.42 338	89.70 328	95.13 321	83.47 230	97.44 410	89.66 279	83.24 432	93.37 448

DPM-MVS		95.69 102	94.92 128	98.01 23	98.08 121	95.71 11	95.27 370	97.62 171	90.43 270	95.55 153	97.07 208	91.72 55	99.50 122	89.62 280	98.94 110	98.82 153

XXY-MVS		92.16 269	91.23 280	94.95 242	94.75 376	90.94 177	97.47 165	97.43 219	89.14 308	88.90 353	96.43 252	79.71 317	98.24 302	89.56 281	87.68 376	95.67 347

miper_ehance_all_eth		91.59 293	91.13 284	92.97 362	95.55 323	86.57 355	94.47 404	96.88 299	87.77 360	88.88 355	94.01 383	86.22 167	97.54 400	89.49 282	86.93 384	94.79 412

WBMVS		90.69 343	89.99 340	92.81 369	96.48 260	85.00 396	95.21 376	96.30 336	89.46 299	89.04 352	94.05 382	72.45 402	97.82 365	89.46 283	87.41 381	95.61 348

XVG-ACMP-BASELINE		90.93 332	90.21 330	93.09 358	94.31 395	85.89 375	95.33 365	97.26 246	91.06 241	89.38 339	95.44 308	68.61 435	98.60 267	89.46 283	91.05 336	94.79 412

thisisatest0515		92.29 263	91.30 276	95.25 222	96.60 239	88.90 275	94.36 410	92.32 472	87.92 351	93.43 231	94.57 347	77.28 357	99.00 192	89.42 285	95.86 241	97.86 254

c3_l		91.38 307	90.89 292	92.88 366	95.58 321	86.30 363	94.68 394	96.84 303	88.17 344	88.83 359	94.23 372	85.65 183	97.47 407	89.36 286	84.63 413	94.89 396

AdaColmap		94.34 169	93.68 180	96.31 130	98.59 76	91.68 138	96.59 272	97.81 146	89.87 281	92.15 260	97.06 209	83.62 229	99.54 112	89.34 287	98.07 150	97.70 263

TranMVSNet+NR-MVSNet		92.50 250	91.63 263	95.14 226	94.76 375	92.07 121	97.53 153	98.11 90	92.90 155	89.56 334	96.12 269	83.16 238	97.60 390	89.30 288	83.20 433	95.75 343

D2MVS		91.30 314	90.95 291	92.35 380	94.71 379	85.52 382	96.18 312	98.21 67	88.89 320	86.60 409	93.82 390	79.92 314	97.95 350	89.29 289	90.95 339	93.56 444

1314		92.81 245	92.03 248	95.14 226	95.33 341	89.52 245	96.04 321	97.44 216	87.72 363	86.25 414	95.33 310	83.84 224	98.79 217	89.26 290	97.05 194	97.11 292

v2v482		91.59 293	90.85 296	93.80 318	93.87 406	88.17 309	96.94 224	96.88 299	89.54 295	89.53 335	94.90 330	81.70 278	98.02 335	89.25 291	85.04 409	95.20 376

114514_t		93.95 190	93.06 207	96.63 99	99.07 44	91.61 140	97.46 167	97.96 123	77.99 479	93.00 241	97.57 172	86.14 171	99.33 141	89.22 292	99.15 94	98.94 125

PAPM_NR		95.01 140	94.59 147	96.26 136	98.89 61	90.68 191	97.24 194	97.73 153	91.80 201	92.93 246	96.62 243	89.13 101	99.14 169	89.21 293	97.78 161	98.97 115

baseline1		92.82 244	91.90 254	95.55 198	97.20 175	90.77 186	97.19 202	94.58 426	92.20 187	92.36 253	96.34 257	84.16 220	98.21 305	89.20 294	83.90 427	97.68 264

IB-MVS	87.33 17	89.91 363	88.28 380	94.79 252	95.26 348	87.70 324	95.12 383	93.95 449	89.35 303	87.03 401	92.49 427	70.74 416	99.19 157	89.18 295	81.37 441	97.49 274
Christian Sormann, Mattia Rossi, Andreas Kuhn and Friedrich Fraundorfer: IB-MVS: An Iterative Algorithm for Deep Multi-View Stereo based on Binary Decisions. BMVC 2021
HY-MVS	89.66 9	93.87 195	92.95 212	96.63 99	97.10 182	92.49 106	95.64 350	96.64 316	89.05 312	93.00 241	95.79 288	85.77 179	99.45 130	89.16 296	94.35 275	97.96 244

0.4-1-1-0.1		86.83 409	84.27 429	94.50 271	91.39 458	88.23 303	92.62 462	92.27 473	84.04 427	86.01 421	83.30 500	65.29 462	98.31 296	89.08 297	74.45 470	96.96 298

V42		91.58 295	90.87 293	93.73 321	94.05 401	88.50 291	97.32 184	96.97 286	88.80 327	89.71 327	94.33 364	82.54 258	98.05 330	89.01 298	85.07 407	94.64 421

sd_testset		93.10 227	92.45 237	95.05 230	98.09 118	89.21 260	96.89 231	97.64 165	93.18 136	91.79 272	97.28 192	75.35 375	98.65 257	88.99 299	92.84 305	97.28 285

0.3-1-1-0.015		86.11 424	83.37 435	94.34 281	90.58 464	88.02 314	91.64 470	92.45 471	83.56 438	84.46 437	81.84 503	62.73 472	98.31 296	88.98 300	74.09 473	96.70 306

OurMVSNet-221017-0		90.51 348	90.19 331	91.44 411	93.41 426	81.25 441	96.98 221	96.28 340	91.68 206	86.55 411	96.30 258	74.20 386	97.98 339	88.96 301	87.40 382	95.09 383

API-MVS		94.84 152	94.49 155	95.90 165	97.90 135	92.00 125	97.80 105	97.48 201	89.19 307	94.81 184	96.71 229	88.84 106	99.17 162	88.91 302	98.76 118	96.53 309

0.4-1-1-0.2		86.27 420	83.62 434	94.20 289	90.38 465	87.69 325	91.04 476	92.52 470	83.43 441	85.22 432	81.49 505	65.31 461	98.29 299	88.90 303	74.30 472	96.64 307

test-LLR		91.42 305	91.19 282	92.12 390	94.59 383	80.66 447	94.29 415	92.98 462	91.11 238	90.76 299	92.37 430	79.02 332	98.07 327	88.81 304	96.74 208	97.63 265

test-mter		90.19 358	89.54 357	92.12 390	94.59 383	80.66 447	94.29 415	92.98 462	87.68 365	90.76 299	92.37 430	67.67 441	98.07 327	88.81 304	96.74 208	97.63 265

eth_miper_zixun_eth		91.02 327	90.59 312	92.34 382	95.33 341	84.35 405	94.10 420	96.90 296	88.56 333	88.84 358	94.33 364	84.08 221	97.60 390	88.77 306	84.37 420	95.06 385

myMVS_eth3d28		91.52 300	90.97 290	93.17 355	96.91 202	83.24 420	95.61 351	94.96 411	92.24 183	91.98 266	93.28 415	69.31 429	98.40 284	88.71 307	95.68 246	97.88 250

TAMVS		94.01 186	93.46 191	95.64 191	96.16 291	90.45 197	96.71 256	96.89 298	89.27 305	93.46 230	96.92 220	87.29 146	97.94 352	88.70 308	95.74 243	98.53 185

Patchmatch-RL test		87.38 398	86.24 400	90.81 426	88.74 482	78.40 474	88.12 498	93.17 459	87.11 378	82.17 460	89.29 466	81.95 272	95.60 460	88.64 309	77.02 459	98.41 201

baseline2		91.63 290	90.86 294	93.94 310	94.33 393	86.32 362	95.92 330	91.64 479	89.37 302	86.94 405	94.69 340	81.62 279	98.69 247	88.64 309	94.57 274	96.81 302

TESTMET0.1,1		90.06 360	89.42 360	91.97 393	94.41 391	80.62 449	94.29 415	91.97 477	87.28 375	90.44 303	92.47 429	68.79 433	97.67 380	88.50 311	96.60 216	97.61 269

Vis-MVSNet (Re-imp)		94.15 177	93.88 174	94.95 242	97.61 156	87.92 317	98.10 57	95.80 365	92.22 184	93.02 240	97.45 180	84.53 211	97.91 358	88.24 312	97.97 155	99.02 106

1112_ss		93.37 216	92.42 238	96.21 140	97.05 188	90.99 172	96.31 298	96.72 308	86.87 382	89.83 324	96.69 233	86.51 160	99.14 169	88.12 313	93.67 296	98.50 189

UBG		91.55 297	90.76 300	93.94 310	96.52 256	85.06 395	95.22 374	94.54 428	90.47 269	91.98 266	92.71 422	72.02 403	98.74 236	88.10 314	95.26 259	98.01 242

CVMVSNet		91.23 317	91.75 259	89.67 443	95.77 313	74.69 486	96.44 277	94.88 415	85.81 400	92.18 259	97.64 163	79.07 329	95.58 461	88.06 315	95.86 241	98.74 168

MAR-MVS		94.22 172	93.46 191	96.51 112	98.00 126	92.19 119	97.67 127	97.47 205	88.13 348	93.00 241	95.84 282	84.86 207	99.51 119	87.99 316	98.17 147	97.83 257
Zhenyu Xu, Yiguang Liu, Xuelei Shi, Ying Wang, Yunan Zheng: MARMVS: Matching Ambiguity Reduced Multiple View Stereo for Efficient Large Scale Scene Reconstruction. CVPR 2020
原ACMM1				96.38 126	98.59 76	91.09 170		97.89 129	87.41 371	95.22 168	97.68 156	90.25 86	99.54 112	87.95 317	99.12 99	98.49 191

CP-MVSNet		91.89 280	91.24 279	93.82 317	95.05 360	88.57 286	97.82 101	98.19 74	91.70 205	88.21 375	95.76 290	81.96 271	97.52 404	87.86 318	84.65 412	95.37 364

v148		90.99 328	90.38 318	92.81 369	93.83 407	85.80 376	96.78 249	96.68 313	89.45 300	88.75 361	93.93 387	82.96 247	97.82 365	87.83 319	83.25 431	94.80 410

blended_shiyan8		87.58 396	85.55 407	93.66 330	88.76 481	88.54 288	95.21 376	96.29 339	82.81 447	86.25 414	87.73 480	73.70 392	97.58 392	87.81 320	71.42 483	94.85 400

v1144		91.37 309	90.60 311	93.68 328	93.89 405	88.23 303	96.84 238	97.03 282	88.37 339	89.69 329	94.39 358	82.04 269	97.98 339	87.80 321	85.37 400	94.84 401

usedtu_blend_shiyan5		87.06 406	84.84 421	93.69 325	88.54 485	88.70 280	95.83 335	95.54 381	78.74 476	85.92 422	86.89 489	73.03 397	97.55 395	87.73 322	71.36 484	94.83 402

blend_shiyan4		86.87 408	84.61 426	93.67 329	88.87 477	88.70 280	95.17 380	96.30 336	82.80 448	86.16 416	87.11 486	65.12 465	97.55 395	87.73 322	72.21 480	94.75 416

DIV-MVS_self_test		90.97 330	90.33 319	92.88 366	95.36 336	86.19 368	94.46 406	96.63 319	87.82 356	88.18 376	94.23 372	82.99 244	97.53 402	87.72 324	85.57 397	94.93 392

gm-plane-assit					93.22 430	78.89 473			84.82 417		93.52 405		98.64 259	87.72 324

GeoE		93.89 194	93.28 199	95.72 188	96.96 199	89.75 230	98.24 43	96.92 294	89.47 298	92.12 262	97.21 198	84.42 213	98.39 289	87.71 326	96.50 221	99.01 109

blended_shiyan6		87.55 397	85.52 408	93.64 331	88.78 479	88.50 291	95.23 373	96.30 336	82.80 448	86.09 420	87.70 481	73.69 393	97.56 393	87.70 327	71.36 484	94.86 397

cl____		90.96 331	90.32 320	92.89 365	95.37 335	86.21 366	94.46 406	96.64 316	87.82 356	88.15 378	94.18 375	82.98 245	97.54 400	87.70 327	85.59 396	94.92 394

pmmvs4		90.93 332	89.85 345	94.17 291	93.34 428	90.79 184	94.60 396	96.02 355	84.62 419	87.45 389	95.15 319	81.88 275	97.45 409	87.70 327	87.87 374	94.27 433

Test_1112_low_res		92.84 243	91.84 256	95.85 171	97.04 190	89.97 222	95.53 355	96.64 316	85.38 406	89.65 331	95.18 318	85.86 175	99.10 174	87.70 327	93.58 301	98.49 191

wanda-best-256-512		87.29 400	85.21 413	93.53 339	88.54 485	88.21 305	94.51 402	96.27 341	82.69 451	85.92 422	86.89 489	73.04 396	97.55 395	87.68 331	71.36 484	94.83 402

FE-blended-shiyan7		87.29 400	85.21 413	93.53 339	88.54 485	88.21 305	94.51 402	96.27 341	82.69 451	85.92 422	86.89 489	73.03 397	97.55 395	87.68 331	71.36 484	94.83 402

无先验							95.79 339	97.87 133	83.87 431				99.65 80	87.68 331		98.89 140

Fast-Effi-MVS+		93.46 211	92.75 221	95.59 195	96.77 225	90.03 215	96.81 243	97.13 259	88.19 343	91.30 287	94.27 369	86.21 168	98.63 262	87.66 334	96.46 224	98.12 229

CNLPA		94.28 170	93.53 186	96.52 108	98.38 91	92.55 104	96.59 272	96.88 299	90.13 278	91.91 268	97.24 196	85.21 197	99.09 177	87.64 335	97.83 159	97.92 247

v8		91.29 316	90.53 315	93.57 338	94.15 397	88.12 311	97.34 181	97.06 277	88.99 315	88.32 370	94.26 371	83.08 241	98.01 336	87.62 336	83.92 426	94.57 422

pmmvs5		89.86 368	88.87 373	92.82 368	92.86 438	86.23 365	96.26 303	95.39 387	84.24 424	87.12 397	94.51 351	74.27 385	97.36 417	87.61 337	87.57 377	94.86 397

usedtu_dtu_shiyan1		91.65 288	90.67 308	94.60 260	93.65 415	90.95 175	94.86 389	97.12 260	89.69 290	89.21 347	93.62 400	81.17 286	97.67 380	87.54 338	89.14 358	95.17 381

FE-MVSNET3		91.65 288	90.67 308	94.60 260	93.65 415	90.95 175	94.86 389	97.12 260	89.69 290	89.21 347	93.62 400	81.17 286	97.67 380	87.54 338	89.14 358	95.17 381

Fast-Effi-MVS+-dtu		92.29 263	91.99 250	93.21 354	95.27 345	85.52 382	97.03 212	96.63 319	92.09 193	89.11 351	95.14 320	80.33 306	98.08 323	87.54 338	94.74 271	96.03 329

OpenMVS	89.19 12	92.86 241	91.68 262	96.40 123	95.34 338	92.73 96	98.27 37	98.12 87	84.86 416	85.78 425	97.75 146	78.89 337	99.74 60	87.50 341	98.65 122	96.73 304

gbinet_0.2-2-1-0.02		87.30 399	85.16 415	93.69 325	88.70 484	88.81 277	95.14 381	96.20 349	83.03 445	86.14 418	87.06 487	71.26 411	97.40 414	87.46 342	71.49 482	94.86 397

dtuonly		90.88 334	91.13 284	90.13 437	92.98 435	75.01 485	92.74 460	95.54 381	87.69 364	91.37 282	96.61 245	79.65 320	98.15 311	87.44 343	96.21 232	97.23 288

miper_lstm_enhance		90.50 349	90.06 337	91.83 399	95.33 341	83.74 413	93.86 429	96.70 312	87.56 368	87.79 383	93.81 391	83.45 232	96.92 433	87.39 344	84.62 414	94.82 407

IterMVS-SCA-FT		90.31 351	89.81 347	91.82 400	95.52 324	84.20 408	94.30 414	96.15 352	90.61 261	87.39 392	94.27 369	75.80 370	96.44 444	87.34 345	86.88 388	94.82 407

PLC	91.00 6	94.11 181	93.43 194	96.13 145	98.58 78	91.15 169	96.69 259	97.39 224	87.29 374	91.37 282	96.71 229	88.39 115	99.52 118	87.33 346	97.13 190	97.73 261
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
tpm		90.25 354	89.74 352	91.76 405	93.92 403	79.73 462	93.98 422	93.54 455	88.28 341	91.99 265	93.25 416	77.51 356	97.44 410	87.30 347	87.94 373	98.12 229

GA-MVS		91.38 307	90.31 321	94.59 262	94.65 381	87.62 326	94.34 411	96.19 350	90.73 251	90.35 305	93.83 388	71.84 405	97.96 346	87.22 348	93.61 299	98.21 220

BH-untuned		92.94 236	92.62 228	93.92 314	97.22 173	86.16 369	96.40 287	96.25 345	90.06 279	89.79 325	96.17 266	83.19 237	98.35 292	87.19 349	97.27 184	97.24 287

v144192		91.06 325	90.28 323	93.39 346	93.66 413	87.23 336	96.83 239	97.07 271	87.43 370	89.69 329	94.28 368	81.48 280	98.00 337	87.18 350	84.92 411	94.93 392

RPSCF		90.75 338	90.86 294	90.42 433	96.84 210	76.29 482	95.61 351	96.34 333	83.89 429	91.38 281	97.87 128	76.45 364	98.78 218	87.16 351	92.23 314	96.20 318

test_f		80.57 452	79.62 454	83.41 473	83.38 505	67.80 501	93.57 443	93.72 453	80.80 467	77.91 482	87.63 482	33.40 504	92.08 495	87.14 352	79.04 453	90.34 486

PS-CasMVS		91.55 297	90.84 297	93.69 325	94.96 363	88.28 299	97.84 96	98.24 63	91.46 216	88.04 380	95.80 285	79.67 318	97.48 406	87.02 353	84.54 418	95.31 368

pm-mvs1		90.72 340	89.65 355	93.96 307	94.29 396	89.63 235	97.79 107	96.82 304	89.07 310	86.12 419	95.48 307	78.61 340	97.78 370	86.97 354	81.67 439	94.46 424

IterMVS		90.15 359	89.67 353	91.61 407	95.48 326	83.72 414	94.33 412	96.12 353	89.99 280	87.31 395	94.15 377	75.78 372	96.27 448	86.97 354	86.89 387	94.83 402
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
F-COLMAP		93.58 205	92.98 211	95.37 214	98.40 88	88.98 272	97.18 203	97.29 240	87.75 362	90.49 302	97.10 207	85.21 197	99.50 122	86.70 356	96.72 210	97.63 265

PVSNet	86.66 18	92.24 266	91.74 261	93.73 321	97.77 142	83.69 416	92.88 455	96.72 308	87.91 352	93.00 241	94.86 332	78.51 341	99.05 188	86.53 357	97.45 174	98.47 194

v1192		91.07 324	90.23 327	93.58 336	93.70 410	87.82 322	96.73 253	97.07 271	87.77 360	89.58 332	94.32 366	80.90 293	97.97 342	86.52 358	85.48 398	94.95 388

新几何1				97.32 63	98.60 75	93.59 65		97.75 150	81.58 461	95.75 142	97.85 132	90.04 89	99.67 78	86.50 359	99.13 97	98.69 172

v10		91.04 326	90.23 327	93.49 342	94.12 398	88.16 310	97.32 184	97.08 268	88.26 342	88.29 372	94.22 374	82.17 267	97.97 342	86.45 360	84.12 422	94.33 429

v1921920		90.85 335	90.03 338	93.29 350	93.55 417	86.96 345	96.74 252	97.04 280	87.36 372	89.52 336	94.34 363	80.23 308	97.97 342	86.27 361	85.21 404	94.94 390

MDTV_nov1_ep13_2view						70.35 495	93.10 452		83.88 430	93.55 224		82.47 261		86.25 362		98.38 204

test_post1							92.81 458				16.58 550	80.53 301	97.68 379	86.20 363

SCA		91.84 281	91.18 283	93.83 316	95.59 320	84.95 399	94.72 393	95.58 378	90.82 247	92.25 258	93.69 395	75.80 370	98.10 318	86.20 363	95.98 235	98.45 196

PAPR		94.18 173	93.42 196	96.48 115	97.64 152	91.42 152	95.55 353	97.71 159	88.99 315	92.34 256	95.82 284	89.19 99	99.11 172	86.14 365	97.38 176	98.90 134

GBi-Net		91.35 310	90.27 324	94.59 262	96.51 257	91.18 165	97.50 156	96.93 290	88.82 324	89.35 340	94.51 351	73.87 387	97.29 420	86.12 366	88.82 363	95.31 368

test1		91.35 310	90.27 324	94.59 262	96.51 257	91.18 165	97.50 156	96.93 290	88.82 324	89.35 340	94.51 351	73.87 387	97.29 420	86.12 366	88.82 363	95.31 368

FMVSNet3		91.78 282	90.69 307	95.03 233	96.53 253	92.27 114	97.02 214	96.93 290	89.79 287	89.35 340	94.65 344	77.01 358	97.47 407	86.12 366	88.82 363	95.35 365

EPMVS		90.70 341	89.81 347	93.37 347	94.73 378	84.21 407	93.67 438	88.02 496	89.50 297	92.38 252	93.49 406	77.82 354	97.78 370	86.03 369	92.68 309	98.11 235

MVS		91.71 284	90.44 316	95.51 204	95.20 351	91.59 142	96.04 321	97.45 212	73.44 489	87.36 393	95.60 299	85.42 192	99.10 174	85.97 370	97.46 170	95.83 335

testdata2													99.67 78	85.96 371

K. test v3		87.64 395	86.75 397	90.32 434	93.02 434	79.48 468	96.61 269	92.08 476	90.66 257	80.25 472	94.09 380	67.21 445	96.65 442	85.96 371	80.83 443	94.83 402

WR-MVS_H		92.00 275	91.35 272	93.95 308	95.09 359	89.47 246	98.04 64	98.68 18	91.46 216	88.34 369	94.68 341	85.86 175	97.56 393	85.77 373	84.24 421	94.82 407

gg-mvs-nofinetune		87.82 392	85.61 406	94.44 275	94.46 388	89.27 259	91.21 475	84.61 506	80.88 464	89.89 323	74.98 512	71.50 408	97.53 402	85.75 374	97.21 186	96.51 310

tpm2		89.96 362	89.21 365	92.23 388	94.91 369	81.25 441	93.78 432	94.42 433	80.62 468	91.56 277	93.44 410	76.44 365	97.94 352	85.60 375	92.08 321	97.49 274

v1240		90.70 341	89.85 345	93.23 352	93.51 420	86.80 347	96.61 269	97.02 284	87.16 377	89.58 332	94.31 367	79.55 322	97.98 339	85.52 376	85.44 399	94.90 395

PEN-MVS		91.20 319	90.44 316	93.48 343	94.49 387	87.91 319	97.76 109	98.18 77	91.29 223	87.78 384	95.74 291	80.35 305	97.33 418	85.46 377	82.96 434	95.19 379

QAPM		93.45 214	92.27 241	96.98 86	96.77 225	92.62 100	98.39 29	98.12 87	84.50 421	88.27 373	97.77 145	82.39 263	99.81 36	85.40 378	98.81 114	98.51 188

SSC-MVS3.2		89.74 371	89.26 364	91.19 419	95.16 352	80.29 455	94.53 399	97.03 282	91.79 202	88.86 356	94.10 378	69.94 424	97.82 365	85.29 379	86.66 389	95.45 356

EU-MVSNet		88.72 384	88.90 372	88.20 455	93.15 432	74.21 488	96.63 268	94.22 442	85.18 410	87.32 394	95.97 275	76.16 367	94.98 469	85.27 380	86.17 391	95.41 358

BH-w/o		92.14 271	91.75 259	93.31 349	96.99 196	85.73 379	95.67 345	95.69 371	88.73 329	89.26 345	94.82 335	82.97 246	98.07 327	85.26 381	96.32 231	96.13 325

FMVSNet2		91.31 313	90.08 333	94.99 236	96.51 257	92.21 116	97.41 171	96.95 288	88.82 324	88.62 362	94.75 338	73.87 387	97.42 412	85.20 382	88.55 368	95.35 365

PM-MVS		83.48 442	81.86 448	88.31 454	87.83 490	77.59 476	93.43 444	91.75 478	86.91 380	80.63 468	89.91 461	44.42 499	95.84 454	85.17 383	76.73 462	91.50 479

LF4IMVS		87.94 391	87.25 388	89.98 439	92.38 451	80.05 460	94.38 409	95.25 397	87.59 367	84.34 439	94.74 339	64.31 466	97.66 384	84.83 384	87.45 378	92.23 468

PatchmatchNet		91.91 278	91.35 272	93.59 335	95.38 333	84.11 409	93.15 450	95.39 387	89.54 295	92.10 263	93.68 397	82.82 251	98.13 313	84.81 385	95.32 257	98.52 186
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
pmmvs6		87.81 393	86.19 401	92.69 374	91.32 459	86.30 363	97.34 181	96.41 330	80.59 469	84.05 447	94.37 360	67.37 444	97.67 380	84.75 386	79.51 450	94.09 436

v7n		90.76 337	89.86 344	93.45 345	93.54 418	87.60 327	97.70 125	97.37 229	88.85 321	87.65 386	94.08 381	81.08 288	98.10 318	84.68 387	83.79 428	94.66 420

SixPastTwentyTwo		89.15 377	88.54 377	90.98 421	93.49 421	80.28 456	96.70 257	94.70 422	90.78 248	84.15 443	95.57 300	71.78 406	97.71 378	84.63 388	85.07 407	94.94 390

TDRefinement		86.53 412	84.76 423	91.85 398	82.23 508	84.25 406	96.38 289	95.35 390	84.97 415	84.09 445	94.94 327	65.76 458	98.34 295	84.60 389	74.52 469	92.97 451

ACMH	87.59 16	90.53 346	89.42 360	93.87 315	96.21 280	87.92 317	97.24 194	96.94 289	88.45 337	83.91 448	96.27 261	71.92 404	98.62 265	84.43 390	89.43 355	95.05 386
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ACMH+	87.92 14	90.20 357	89.18 366	93.25 351	96.48 260	86.45 360	96.99 220	96.68 313	88.83 323	84.79 436	96.22 263	70.16 421	98.53 275	84.42 391	88.04 372	94.77 415

sc_t1		86.48 414	84.10 432	93.63 332	93.45 424	85.76 378	96.79 245	94.71 421	73.06 490	86.45 412	94.35 361	55.13 486	97.95 350	84.38 392	78.55 455	97.18 290

test_vis3_rt		72.73 459	70.55 462	79.27 479	80.02 513	68.13 500	93.92 427	74.30 518	76.90 482	58.99 509	73.58 515	20.29 518	95.37 466	84.16 393	72.80 478	74.31 511

FE-MVS		92.05 274	91.05 287	95.08 229	96.83 212	87.93 316	93.91 428	95.70 369	86.30 392	94.15 207	94.97 325	76.59 362	99.21 155	84.10 394	96.86 200	98.09 236

MS-PatchMatch		90.27 353	89.77 349	91.78 403	94.33 393	84.72 402	95.55 353	96.73 307	86.17 396	86.36 413	95.28 313	71.28 410	97.80 368	84.09 395	98.14 148	92.81 454

PatchMatch-RL		92.90 238	92.02 249	95.56 196	98.19 111	90.80 183	95.27 370	97.18 255	87.96 350	91.86 271	95.68 295	80.44 303	98.99 193	84.01 396	97.54 166	96.89 300

lessismore_v0				90.45 432	91.96 454	79.09 472		87.19 500		80.32 471	94.39 358	66.31 453	97.55 395	84.00 397	76.84 460	94.70 418

UWE-MVS		89.91 363	89.48 359	91.21 416	95.88 306	78.23 475	94.91 388	90.26 489	89.11 309	92.35 255	94.52 350	68.76 434	97.96 346	83.95 398	95.59 249	97.42 278

CMPMVS	62.92 21	85.62 431	84.92 420	87.74 458	89.14 474	73.12 492	94.17 418	96.80 305	73.98 486	73.65 490	94.93 328	66.36 451	97.61 389	83.95 398	91.28 332	92.48 463
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MVP-Stereo		90.74 339	90.08 333	92.71 373	93.19 431	88.20 307	95.86 333	96.27 341	86.07 397	84.86 435	94.76 337	77.84 353	97.75 375	83.88 400	98.01 154	92.17 471
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LS3D		93.57 207	92.61 229	96.47 116	97.59 158	91.61 140	97.67 127	97.72 155	85.17 411	90.29 306	98.34 75	84.60 209	99.73 62	83.85 401	98.27 142	98.06 239

DTE-MVSNet		90.56 345	89.75 351	93.01 360	93.95 402	87.25 334	97.64 135	97.65 163	90.74 250	87.12 397	95.68 295	79.97 313	97.00 431	83.33 402	81.66 440	94.78 414

BH-RMVSNet		92.72 248	91.97 251	94.97 240	97.16 177	87.99 315	96.15 314	95.60 376	90.62 260	91.87 270	97.15 202	78.41 343	98.57 272	83.16 403	97.60 165	98.36 206

pmmvs-eth3d		86.22 421	84.45 427	91.53 408	88.34 488	87.25 334	94.47 404	95.01 406	83.47 439	79.51 475	89.61 464	69.75 427	95.71 456	83.13 404	76.73 462	91.64 474

FMVSNet1		89.88 366	88.31 379	94.59 262	95.41 331	91.18 165	97.50 156	96.93 290	86.62 386	87.41 391	94.51 351	65.94 457	97.29 420	83.04 405	87.43 379	95.31 368

testing222		90.31 351	88.96 370	94.35 279	96.54 251	87.29 331	95.50 356	93.84 452	90.97 243	91.75 274	92.96 419	62.18 475	98.00 337	82.86 406	94.08 286	97.76 260

MDTV_nov1_ep13			90.76 300		95.22 349	80.33 453	93.03 453	95.28 394	88.14 347	92.84 247	93.83 388	81.34 282	98.08 323	82.86 406	94.34 276

TR-MVS		91.48 303	90.59 312	94.16 294	96.40 266	87.33 330	95.67 345	95.34 393	87.68 365	91.46 280	95.52 304	76.77 361	98.35 292	82.85 408	93.61 299	96.79 303

dmvs_re		90.21 356	89.50 358	92.35 380	95.47 330	85.15 392	95.70 344	94.37 437	90.94 246	88.42 366	93.57 404	74.63 382	95.67 458	82.80 409	89.57 354	96.22 317

JIA-IIPM		88.26 389	87.04 393	91.91 395	93.52 419	81.42 440	89.38 488	94.38 436	80.84 465	90.93 296	80.74 507	79.22 326	97.92 355	82.76 410	91.62 325	96.38 315

PVSNet_0	82.17 19	85.46 432	83.64 433	90.92 422	95.27 345	79.49 467	90.55 480	95.60 376	83.76 433	83.00 455	89.95 460	71.09 412	97.97 342	82.75 411	60.79 505	95.31 368

ambc				86.56 467	83.60 503	70.00 496	85.69 503	94.97 409		80.60 469	88.45 472	37.42 502	96.84 437	82.69 412	75.44 467	92.86 453

USDC		88.94 379	87.83 384	92.27 385	94.66 380	84.96 398	93.86 429	95.90 359	87.34 373	83.40 450	95.56 301	67.43 443	98.19 308	82.64 413	89.67 353	93.66 443

FE-MVSNET2		86.36 417	84.68 425	91.39 413	87.67 491	86.47 359	96.21 308	96.41 330	87.87 354	79.31 476	89.64 463	65.29 462	95.58 461	82.42 414	77.28 458	92.14 472

ITE_SJBPF				92.43 378	95.34 338	85.37 389		95.92 357	91.47 215	87.75 385	96.39 255	71.00 413	97.96 346	82.36 415	89.86 351	93.97 439

UnsupCasMVSNet_eth		85.99 425	84.45 427	90.62 430	89.97 469	82.40 433	93.62 441	97.37 229	89.86 282	78.59 480	92.37 430	65.25 464	95.35 467	82.27 416	70.75 488	94.10 434

GG-mvs-BLEND				93.62 333	93.69 411	89.20 261	92.39 466	83.33 509		87.98 382	89.84 462	71.00 413	96.87 436	82.08 417	95.40 256	94.80 410

ArgMatch-SfM		83.09 445	81.67 450	87.34 461	91.48 457	76.29 482	92.76 459	91.31 483	84.26 423	81.99 462	93.35 414	45.52 496	92.98 492	81.83 418	72.49 479	92.76 455

ArgMatch-Sym		83.08 446	81.73 449	87.11 462	91.53 456	76.72 479	92.86 456	91.54 480	83.66 435	82.34 458	93.45 409	44.99 497	92.15 494	81.78 419	73.46 476	92.47 464

thres600view7		92.49 252	91.60 264	95.18 224	97.91 134	89.47 246	97.65 131	94.66 423	92.18 191	93.33 233	94.91 329	78.06 350	99.10 174	81.61 420	94.06 290	96.98 294

LTVRE_ROB	88.41 13	90.99 328	89.92 343	94.19 290	96.18 288	89.55 242	96.31 298	97.09 267	87.88 353	85.67 426	95.91 279	78.79 338	98.57 272	81.50 421	89.98 349	94.44 426
Andreas Kuhn, Heiko HirschmÃ¼ller, Daniel Scharstein, Helmut Mayer: A TV Prior for High-Quality Scalable Multi-View Stereo Reconstruction. International Journal of Computer Vision 2016
tt0320-xc		84.83 436	82.33 444	92.31 383	93.66 413	86.20 367	96.17 313	94.06 444	71.26 492	82.04 461	92.22 437	55.07 487	96.72 441	81.49 422	75.04 468	94.02 437

tpmvs		89.83 369	89.15 367	91.89 397	94.92 367	80.30 454	93.11 451	95.46 386	86.28 393	88.08 379	92.65 423	80.44 303	98.52 276	81.47 423	89.92 350	96.84 301

thres100view900		92.43 254	91.58 265	94.98 238	97.92 133	89.37 252	97.71 122	94.66 423	92.20 187	93.31 234	94.90 330	78.06 350	99.08 179	81.40 424	94.08 286	96.48 312

tfpn200view9		92.38 257	91.52 268	94.95 242	97.85 137	89.29 256	97.41 171	94.88 415	92.19 189	93.27 236	94.46 356	78.17 346	99.08 179	81.40 424	94.08 286	96.48 312

thres400		92.42 255	91.52 268	95.12 228	97.85 137	89.29 256	97.41 171	94.88 415	92.19 189	93.27 236	94.46 356	78.17 346	99.08 179	81.40 424	94.08 286	96.98 294

mvs5depth		86.53 412	85.08 417	90.87 423	88.74 482	82.52 429	91.91 468	94.23 441	86.35 391	87.11 399	93.70 394	66.52 450	97.76 373	81.37 427	75.80 464	92.31 467

ETVMVS		90.52 347	89.14 368	94.67 259	96.81 217	87.85 321	95.91 331	93.97 448	89.71 289	92.34 256	92.48 428	65.41 460	97.96 346	81.37 427	94.27 279	98.21 220

DP-MVS		92.76 246	91.51 270	96.52 108	98.77 63	90.99 172	97.38 178	96.08 354	82.38 454	89.29 343	97.87 128	83.77 225	99.69 74	81.37 427	96.69 212	98.89 140

thres200		92.23 267	91.39 271	94.75 255	97.61 156	89.03 267	96.60 271	95.09 404	92.08 194	93.28 235	94.00 384	78.39 344	99.04 191	81.26 430	94.18 282	96.19 319

CR-MVSNet		90.82 336	89.77 349	93.95 308	94.45 389	87.19 337	90.23 482	95.68 373	86.89 381	92.40 250	92.36 433	80.91 291	97.05 427	81.09 431	93.95 291	97.60 270

tt0320		85.39 433	83.12 436	92.19 389	93.44 425	85.79 377	96.19 311	94.87 418	71.19 493	82.92 456	91.76 446	58.43 479	96.81 438	81.03 432	78.26 456	93.98 438

ttmdpeth		85.91 427	84.76 423	89.36 448	89.14 474	80.25 457	95.66 348	93.16 461	83.77 432	83.39 451	95.26 315	66.24 454	95.26 468	80.65 433	75.57 465	92.57 459

MSDG		91.42 305	90.24 326	94.96 241	97.15 180	88.91 274	93.69 437	96.32 334	85.72 402	86.93 406	96.47 250	80.24 307	98.98 194	80.57 434	95.05 264	96.98 294

dp		88.90 381	88.26 381	90.81 426	94.58 385	76.62 480	92.85 457	94.93 412	85.12 412	90.07 319	93.07 417	75.81 369	98.12 316	80.53 435	87.42 380	97.71 262

tpm cat1		88.36 387	87.21 390	91.81 401	95.13 357	80.55 450	92.58 463	95.70 369	74.97 485	87.45 389	91.96 442	78.01 352	98.17 310	80.39 436	88.74 366	96.72 305

KD-MVS_self_test		85.95 426	84.95 419	88.96 452	89.55 473	79.11 471	95.13 382	96.42 329	85.91 399	84.07 446	90.48 455	70.03 423	94.82 470	80.04 437	72.94 477	92.94 452

AllTest		90.23 355	88.98 369	93.98 304	97.94 131	86.64 351	96.51 276	95.54 381	85.38 406	85.49 428	96.77 227	70.28 419	99.15 166	80.02 438	92.87 303	96.15 323

TestCases				93.98 304	97.94 131	86.64 351		95.54 381	85.38 406	85.49 428	96.77 227	70.28 419	99.15 166	80.02 438	92.87 303	96.15 323

dtuonlycased		85.91 427	85.69 405	86.60 466	92.42 450	76.96 477	93.66 439	94.49 431	86.68 384	80.87 465	92.00 439	71.52 407	93.23 490	79.58 440	79.97 446	89.60 489

ADS-MVSNet2		89.45 374	88.59 376	92.03 392	95.86 307	82.26 434	90.93 477	94.32 440	83.23 443	91.28 290	91.81 444	79.01 334	95.99 450	79.52 441	91.39 330	97.84 255

ADS-MVSNet		89.89 365	88.68 375	93.53 339	95.86 307	84.89 400	90.93 477	95.07 405	83.23 443	91.28 290	91.81 444	79.01 334	97.85 361	79.52 441	91.39 330	97.84 255

our_test_3		88.78 383	87.98 383	91.20 418	92.45 448	82.53 428	93.61 442	95.69 371	85.77 401	84.88 434	93.71 393	79.99 312	96.78 440	79.47 443	86.24 390	94.28 432

EPNet_dtu		91.71 284	91.28 277	92.99 361	93.76 409	83.71 415	96.69 259	95.28 394	93.15 138	87.02 402	95.95 277	83.37 233	97.38 416	79.46 444	96.84 202	97.88 250
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
TransMVSNet (Re)		88.94 379	87.56 385	93.08 359	94.35 392	88.45 294	97.73 116	95.23 398	87.47 369	84.26 441	95.29 311	79.86 315	97.33 418	79.44 445	74.44 471	93.45 447

EG-PatchMatch MVS		87.02 407	85.44 409	91.76 405	92.67 442	85.00 396	96.08 318	96.45 328	83.41 442	79.52 474	93.49 406	57.10 482	97.72 377	79.34 446	90.87 341	92.56 460

Patchmtry		88.64 385	87.25 388	92.78 371	94.09 399	86.64 351	89.82 486	95.68 373	80.81 466	87.63 387	92.36 433	80.91 291	97.03 428	78.86 447	85.12 406	94.67 419

FMVSNet5		87.29 400	85.79 404	91.78 403	94.80 374	87.28 332	95.49 357	95.28 394	84.09 426	83.85 449	91.82 443	62.95 470	94.17 477	78.48 448	85.34 402	93.91 440

COLMAP_ROB	87.81 15	90.40 350	89.28 363	93.79 319	97.95 130	87.13 340	96.92 227	95.89 361	82.83 446	86.88 408	97.18 199	73.77 390	99.29 148	78.44 449	93.62 298	94.95 388
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
Anonymous20240521		86.42 416	85.44 409	89.34 449	90.33 466	79.79 461	96.73 253	95.92 357	83.71 434	83.25 452	91.36 450	63.92 467	96.01 449	78.39 450	85.36 401	92.22 469

test0.0.03 1		89.37 376	88.70 374	91.41 412	92.47 447	85.63 380	95.22 374	92.70 467	91.11 238	86.91 407	93.65 399	79.02 332	93.19 491	78.00 451	89.18 357	95.41 358

MIMVSNet		88.50 386	86.76 396	93.72 323	94.84 372	87.77 323	91.39 471	94.05 445	86.41 390	87.99 381	92.59 426	63.27 468	95.82 455	77.44 452	92.84 305	97.57 272

MDA-MVSNet_test_wron		85.87 429	84.23 430	90.80 428	92.38 451	82.57 427	93.17 448	95.15 401	82.15 455	67.65 497	92.33 436	78.20 345	95.51 464	77.33 453	79.74 447	94.31 431

YYNet1		85.87 429	84.23 430	90.78 429	92.38 451	82.46 432	93.17 448	95.14 402	82.12 456	67.69 495	92.36 433	78.16 348	95.50 465	77.31 454	79.73 448	94.39 427

UnsupCasMVSNet_bld		82.13 450	79.46 455	90.14 436	88.00 489	82.47 431	90.89 479	96.62 321	78.94 475	75.61 485	84.40 498	56.63 483	96.31 447	77.30 455	66.77 497	91.63 475

KD-MVS_2432*1600		84.81 437	82.64 440	91.31 414	91.07 461	85.34 390	91.22 473	95.75 367	85.56 404	83.09 453	90.21 458	67.21 445	95.89 451	77.18 456	62.48 503	92.69 456

miper_refine_blended		84.81 437	82.64 440	91.31 414	91.07 461	85.34 390	91.22 473	95.75 367	85.56 404	83.09 453	90.21 458	67.21 445	95.89 451	77.18 456	62.48 503	92.69 456

PCF-MVS	89.48 11	91.56 296	89.95 341	96.36 128	96.60 239	92.52 105	92.51 464	97.26 246	79.41 473	88.90 353	96.56 246	84.04 223	99.55 110	77.01 458	97.30 182	97.01 293
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
WB-MVSnew		89.88 366	89.56 356	90.82 425	94.57 386	83.06 423	95.65 349	92.85 464	87.86 355	90.83 298	94.10 378	79.66 319	96.88 435	76.34 459	94.19 281	92.54 461

testgi		87.97 390	87.21 390	90.24 435	92.86 438	80.76 445	96.67 262	94.97 409	91.74 204	85.52 427	95.83 283	62.66 473	94.47 474	76.25 460	88.36 370	95.48 351

MASt3R-SfM		71.17 464	70.37 463	73.55 493	74.50 521	51.20 522	82.17 509	80.88 513	64.49 503	72.54 492	91.37 449	25.17 512	81.85 514	75.86 461	66.37 498	87.59 493

TinyColmap		86.82 410	85.35 412	91.21 416	94.91 369	82.99 424	93.94 425	94.02 447	83.58 436	81.56 463	94.68 341	62.34 474	98.13 313	75.78 462	87.35 383	92.52 462

ppachtmachnet_test		88.35 388	87.29 387	91.53 408	92.45 448	83.57 417	93.75 433	95.97 356	84.28 422	85.32 431	94.18 375	79.00 336	96.93 432	75.71 463	84.99 410	94.10 434

PAPM		91.52 300	90.30 322	95.20 223	95.30 344	89.83 227	93.38 446	96.85 302	86.26 394	88.59 363	95.80 285	84.88 206	98.15 311	75.67 464	95.93 237	97.63 265

WAC-MVS						79.53 465								75.56 465

myMVS_eth3d		87.18 403	86.38 399	89.58 444	95.16 352	79.53 465	95.00 385	93.93 450	88.55 334	86.96 403	91.99 440	56.23 484	94.00 480	75.47 466	94.11 283	95.20 376

CL-MVSNet_self_test		86.31 419	85.15 416	89.80 442	88.83 478	81.74 439	93.93 426	96.22 346	86.67 385	85.03 433	90.80 453	78.09 349	94.50 472	74.92 467	71.86 481	93.15 450

tfpnnormal		89.70 372	88.40 378	93.60 334	95.15 355	90.10 213	97.56 147	98.16 81	87.28 375	86.16 416	94.63 345	77.57 355	98.05 330	74.48 468	84.59 416	92.65 458

DSMNet-mixed		86.34 418	86.12 403	87.00 465	89.88 470	70.43 494	94.93 387	90.08 490	77.97 480	85.42 430	92.78 421	74.44 384	93.96 482	74.43 469	95.14 260	96.62 308

Patchmatch-test		89.42 375	87.99 382	93.70 324	95.27 345	85.11 393	88.98 489	94.37 437	81.11 462	87.10 400	93.69 395	82.28 264	97.50 405	74.37 470	94.76 269	98.48 193

LCM-MVSNet		72.55 460	69.39 465	82.03 475	70.81 530	65.42 506	90.12 484	94.36 439	55.02 511	65.88 499	81.72 504	24.16 513	89.96 497	74.32 471	68.10 495	90.71 485

new-patchmatchnet		83.18 444	81.87 447	87.11 462	86.88 495	75.99 484	93.70 435	95.18 400	85.02 414	77.30 483	88.40 473	65.99 456	93.88 483	74.19 472	70.18 489	91.47 480

MVStest1		82.38 449	80.04 453	89.37 447	87.63 492	82.83 425	95.03 384	93.37 458	73.90 487	73.50 491	94.35 361	62.89 471	93.25 489	73.80 473	65.92 499	92.04 473

testing3		87.67 394	86.88 395	90.05 438	96.14 294	80.71 446	97.10 209	92.85 464	90.15 277	87.54 388	94.55 348	55.70 485	94.10 478	73.77 474	94.10 285	95.35 365

MDA-MVSNet-bldmvs		85.00 434	82.95 439	91.17 420	93.13 433	83.33 418	94.56 398	95.00 407	84.57 420	65.13 501	92.65 423	70.45 418	95.85 453	73.57 475	77.49 457	94.33 429

pmmvs3		79.97 454	77.50 458	87.39 460	82.80 507	79.38 469	92.70 461	90.75 488	70.69 494	78.66 479	87.47 484	51.34 491	93.40 486	73.39 476	69.65 490	89.38 490

test_method		66.11 474	64.89 474	69.79 497	72.62 528	35.23 536	65.19 525	92.83 466	20.35 531	65.20 500	88.08 477	43.14 500	82.70 513	73.12 477	63.46 501	91.45 481

SD_0403		90.01 361	90.02 339	89.96 440	95.65 318	76.76 478	95.76 341	96.46 327	90.58 264	86.59 410	96.29 259	82.12 268	94.78 471	73.00 478	93.76 294	98.35 208

PatchT		88.87 382	87.42 386	93.22 353	94.08 400	85.10 394	89.51 487	94.64 425	81.92 457	92.36 253	88.15 476	80.05 311	97.01 430	72.43 479	93.65 297	97.54 273

Anonymous20231206		87.09 405	86.14 402	89.93 441	91.22 460	80.35 452	96.11 315	95.35 390	83.57 437	84.16 442	93.02 418	73.54 394	95.61 459	72.16 480	86.14 392	93.84 441

MVS-HIRNet		82.47 448	81.21 451	86.26 468	95.38 333	69.21 497	88.96 490	89.49 491	66.28 498	80.79 467	74.08 514	68.48 438	97.39 415	71.93 481	95.47 254	92.18 470

new_pmnet		82.89 447	81.12 452	88.18 456	89.63 471	80.18 458	91.77 469	92.57 468	76.79 483	75.56 487	88.23 475	61.22 476	94.48 473	71.43 482	82.92 435	89.87 487

TAPA-MVS	90.10 7	92.30 262	91.22 281	95.56 196	98.33 93	89.60 237	96.79 245	97.65 163	81.83 458	91.52 278	97.23 197	87.94 124	98.91 202	71.31 483	98.37 137	98.17 225
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
test20.03		86.14 423	85.40 411	88.35 453	90.12 467	80.06 459	95.90 332	95.20 399	88.59 330	81.29 464	93.62 400	71.43 409	92.65 493	71.26 484	81.17 442	92.34 465

tmp_tt		51.94 487	53.82 485	46.29 509	33.73 555	45.30 532	78.32 512	67.24 522	18.02 533	50.93 516	87.05 488	52.99 489	53.11 529	70.76 485	25.29 537	40.46 530

MIMVSNet1		84.93 435	83.05 437	90.56 431	89.56 472	84.84 401	95.40 361	95.35 390	83.91 428	80.38 470	92.21 438	57.23 481	93.34 487	70.69 486	82.75 437	93.50 445

usedtu_dtu_shiyan2		80.00 453	76.91 459	89.27 451	82.13 509	79.69 463	95.45 359	94.20 443	72.95 491	75.80 484	87.75 479	44.44 498	94.30 476	70.64 487	68.81 494	93.84 441

APD_test1		79.31 455	77.70 457	84.14 470	89.11 476	69.07 498	92.36 467	91.50 481	69.07 495	73.87 489	92.63 425	39.93 501	94.32 475	70.54 488	80.25 445	89.02 491

FE-MVSNET		83.85 440	81.97 446	89.51 445	87.19 494	83.19 421	95.21 376	93.17 459	83.45 440	78.90 478	89.05 468	65.46 459	93.84 484	69.71 489	75.56 466	91.51 477

RPMNet		88.98 378	87.05 392	94.77 253	94.45 389	87.19 337	90.23 482	98.03 111	77.87 481	92.40 250	87.55 483	80.17 309	99.51 119	68.84 490	93.95 291	97.60 270

UWE-MVS-28		86.81 411	86.41 398	88.02 457	92.87 437	74.60 487	95.38 363	86.70 502	88.17 344	87.28 396	94.67 343	70.83 415	93.30 488	67.45 491	94.31 277	96.17 320

N_pmnet		78.73 456	78.71 456	78.79 481	92.80 440	46.50 530	94.14 419	43.71 531	78.61 477	80.83 466	91.66 447	74.94 380	96.36 446	67.24 492	84.45 419	93.50 445

OpenMVS_ROB	81.14 20	84.42 439	82.28 445	90.83 424	90.06 468	84.05 411	95.73 343	94.04 446	73.89 488	80.17 473	91.53 448	59.15 477	97.64 385	66.92 493	89.05 360	90.80 484

DenseAffine		72.53 461	69.17 467	82.59 474	87.49 493	70.91 493	88.38 495	81.13 512	67.58 497	64.27 503	87.44 485	23.61 515	88.47 505	66.10 494	56.56 507	88.38 492

PDCNetPlus		61.05 479	58.26 482	69.44 498	75.52 519	55.68 520	81.49 510	51.76 528	62.45 505	51.54 515	82.02 502	23.69 514	78.90 519	65.91 495	29.91 531	73.74 512

DKM		67.96 471	64.19 476	79.27 479	83.41 504	64.35 507	86.88 501	68.11 521	63.15 504	59.36 507	86.08 493	16.45 527	86.15 508	64.54 496	49.73 512	87.32 494

PMMVS2		70.19 466	66.92 470	80.01 477	76.35 518	65.67 504	86.22 502	87.58 498	64.83 502	62.38 504	80.29 509	26.78 509	88.49 504	63.79 497	54.07 510	85.88 496

RoMa-SfM		70.64 465	67.48 469	80.09 476	84.70 500	66.61 502	88.62 493	73.09 519	65.10 501	64.98 502	88.91 469	22.38 516	87.00 506	63.51 498	56.06 508	86.67 495

test_0402		86.46 415	84.79 422	91.45 410	95.02 361	85.55 381	96.29 300	94.89 414	80.90 463	82.21 459	93.97 386	68.21 440	97.29 420	62.98 499	88.68 367	91.51 477

DeepMVS_CX				74.68 492	90.84 463	64.34 508		81.61 511	65.34 500	67.47 498	88.01 478	48.60 494	80.13 518	62.33 500	73.68 475	79.58 508

Syy-MVS		87.13 404	87.02 394	87.47 459	95.16 352	73.21 491	95.00 385	93.93 450	88.55 334	86.96 403	91.99 440	75.90 368	94.00 480	61.59 501	94.11 283	95.20 376

LoFTR		72.43 462	68.71 468	83.60 472	85.67 497	65.61 505	88.04 499	87.40 499	66.11 499	55.94 513	85.54 494	25.43 510	95.55 463	60.87 502	63.38 502	89.63 488

DKM-HiRes		64.02 477	59.97 480	76.17 488	79.46 514	59.20 514	84.48 506	58.37 526	58.52 508	56.03 512	83.71 499	13.19 533	83.72 512	60.49 503	45.50 514	85.59 498

RoMa-HiRes		64.40 476	60.91 479	74.89 491	78.66 515	58.85 516	85.22 505	58.46 525	58.65 507	59.29 508	86.60 492	16.97 524	83.91 511	59.14 504	45.20 515	81.91 507

PMatch-SfM		57.38 482	52.53 487	71.95 496	68.62 531	49.38 523	77.61 513	45.82 529	52.41 515	46.59 517	82.04 501	4.86 550	81.03 516	58.34 505	36.49 525	85.43 499

testf1		69.31 468	66.76 471	76.94 485	78.61 516	61.93 509	88.27 496	86.11 504	55.62 509	59.69 505	85.31 496	20.19 519	89.32 498	57.62 506	69.44 492	79.58 508

APD_test2		69.31 468	66.76 471	76.94 485	78.61 516	61.93 509	88.27 496	86.11 504	55.62 509	59.69 505	85.31 496	20.19 519	89.32 498	57.62 506	69.44 492	79.58 508

EGC-MVSNET		68.77 470	63.01 478	86.07 469	92.49 446	82.24 435	93.96 424	90.96 486	0.71 551	2.62 553	90.89 452	53.66 488	93.46 485	57.25 508	84.55 417	82.51 505

dmvs_testset		81.38 451	82.60 442	77.73 482	91.74 455	51.49 521	93.03 453	84.21 508	89.07 310	78.28 481	91.25 451	76.97 359	88.53 503	56.57 509	82.24 438	93.16 449

ELoFTR		60.03 480	55.86 483	72.52 494	67.65 532	48.49 525	76.21 514	75.14 517	53.94 513	45.93 518	79.98 510	9.14 535	85.06 510	55.39 510	39.36 523	84.02 503

PMatch-Up-SfM		52.53 485	47.58 490	67.36 500	63.24 535	43.29 533	72.10 516	34.71 541	47.03 516	43.51 519	79.07 511	3.90 553	75.83 520	54.68 511	30.02 530	82.95 504

FPMVS		71.27 463	69.85 464	75.50 489	74.64 520	59.03 515	91.30 472	91.50 481	58.80 506	57.92 510	88.28 474	29.98 507	85.53 509	53.43 512	82.84 436	81.95 506

ANet_high		63.94 478	59.58 481	77.02 484	61.24 537	66.06 503	85.66 504	87.93 497	78.53 478	42.94 520	71.04 516	25.42 511	80.71 517	52.60 513	30.83 528	84.28 502

MatchFormer		67.84 473	63.81 477	79.93 478	83.26 506	60.99 513	87.61 500	84.49 507	54.89 512	51.76 514	81.06 506	22.08 517	94.10 478	50.36 514	58.82 506	84.72 501

Gipuma		67.86 472	65.41 473	75.18 490	92.66 443	73.45 490	66.50 524	94.52 429	53.33 514	57.80 511	66.07 519	30.81 505	89.20 500	48.15 515	78.88 454	62.90 523
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
dongtai		69.99 467	69.33 466	71.98 495	88.78 479	61.64 511	89.86 485	59.93 524	75.67 484	74.96 488	85.45 495	50.19 492	81.66 515	43.86 516	55.27 509	72.63 514

PMVS	53.92 22	58.58 481	55.40 484	68.12 499	51.00 550	48.64 524	78.86 511	87.10 501	46.77 517	35.84 527	74.28 513	8.76 536	86.34 507	42.07 517	73.91 474	69.38 515
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
MVE	50.73 23	53.25 484	48.81 489	66.58 502	65.34 533	57.50 517	72.49 515	70.94 520	40.15 520	39.28 524	63.51 520	6.89 539	73.48 524	38.29 518	42.38 520	68.76 517
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
GLUNet-SfM		46.44 489	41.21 498	62.14 503	51.92 547	38.44 535	58.72 527	57.51 527	34.08 521	34.61 528	67.84 518	11.40 534	74.90 521	35.48 519	19.30 542	73.08 513

WB-MVS		76.77 457	76.63 460	77.18 483	85.32 498	56.82 518	94.53 399	89.39 492	82.66 453	71.35 493	89.18 467	75.03 377	88.88 501	35.42 520	66.79 496	85.84 497

SP-DiffGlue		43.94 492	43.32 493	45.79 512	47.79 552	33.03 537	63.37 526	42.65 534	25.71 525	41.26 522	69.27 517	18.83 522	38.88 536	34.96 521	46.05 513	65.47 522

SSC-MVS		76.05 458	75.83 461	76.72 487	84.77 499	56.22 519	94.32 413	88.96 494	81.82 459	70.52 494	88.91 469	74.79 381	88.71 502	33.69 522	64.71 500	85.23 500

E-PMN		53.28 483	52.56 486	55.43 504	74.43 522	47.13 529	83.63 508	76.30 514	42.23 518	42.59 521	62.22 523	28.57 508	74.40 522	31.53 523	31.51 526	44.78 527

kuosan		65.27 475	64.66 475	67.11 501	83.80 501	61.32 512	88.53 494	60.77 523	68.22 496	67.67 496	80.52 508	49.12 493	70.76 525	29.67 524	53.64 511	69.26 516

EMVS		52.08 486	51.31 488	54.39 506	72.62 528	45.39 531	83.84 507	75.51 516	41.13 519	40.77 523	59.65 525	30.08 506	73.60 523	28.31 525	29.90 532	44.18 528

wuyk23d		25.11 505	24.57 509	26.74 521	73.98 524	39.89 534	57.88 528	9.80 556	12.27 545	10.39 547	6.97 551	7.03 538	36.44 537	25.43 526	17.39 544	3.89 548

XFeat-MNN		35.01 497	34.34 500	37.02 515	42.54 553	25.71 551	54.01 529	39.41 538	20.70 530	30.13 535	55.85 530	14.08 531	44.62 530	22.90 527	29.45 535	40.75 529

XFeat-NN		33.93 498	33.70 501	34.60 516	41.69 554	24.48 552	51.85 530	36.02 540	19.55 532	31.20 533	56.38 528	13.46 532	40.91 531	22.51 528	30.65 529	38.42 531

SP-SuperGlue		43.33 494	42.50 495	45.81 511	73.95 525	31.24 540	71.34 518	41.17 535	23.96 526	33.42 530	56.47 527	16.72 526	39.64 534	21.11 529	44.32 517	66.57 519

SP-LightGlue		43.37 493	42.49 496	46.03 510	74.26 523	31.37 539	71.24 519	40.98 536	23.86 527	33.18 531	56.34 529	16.78 525	39.73 533	21.09 530	44.68 516	66.97 518

SP-NN		42.37 495	41.40 497	45.29 514	72.86 527	30.45 542	70.32 522	39.16 539	22.21 528	31.32 532	56.73 526	15.45 528	39.53 535	20.27 531	44.25 518	65.88 521

SP-MNN		42.11 496	40.98 499	45.49 513	72.87 526	30.19 544	70.72 521	39.96 537	20.98 529	30.21 534	55.72 531	15.26 529	40.07 532	19.70 532	43.42 519	66.21 520

ALIKED-NN		46.19 490	43.87 492	53.16 508	80.39 512	47.77 527	69.82 523	43.65 532	27.89 523	36.60 526	63.35 521	17.30 523	61.29 528	15.84 533	39.98 522	50.41 526

ALIKED-LG		47.63 488	45.22 491	54.88 505	81.48 510	48.47 526	71.83 517	45.44 530	32.66 522	37.07 525	63.26 522	19.21 521	63.71 526	15.49 534	40.53 521	52.46 524

ALIKED-MNN		45.42 491	42.62 494	53.80 507	80.52 511	47.58 528	70.83 520	43.05 533	27.21 524	34.32 529	61.10 524	14.85 530	62.94 527	14.90 535	36.82 524	50.89 525

testmvs		13.36 515	16.33 518	4.48 533	5.04 556	2.26 559	93.18 447	3.28 557	2.70 549	8.24 551	21.66 547	2.29 556	2.19 552	7.58 536	2.96 550	9.00 547

test123		13.04 516	15.66 519	5.18 532	4.51 557	3.45 558	92.50 465	1.81 558	2.50 550	7.58 552	20.15 548	3.67 554	2.18 553	7.13 537	1.07 551	9.90 546

SIFT-NN		28.47 499	28.54 503	28.27 517	64.38 534	31.62 538	48.50 531	24.78 542	14.32 534	19.55 536	40.46 532	7.22 537	31.96 538	6.20 538	31.47 527	21.24 532

SIFT-MNN		27.50 500	27.40 504	27.80 518	61.71 536	30.57 541	46.59 532	24.66 543	14.04 535	17.35 537	39.90 533	6.52 540	31.80 539	6.13 539	29.65 533	21.04 533

SIFT-NN-NCMNet		27.16 501	27.05 505	27.51 519	59.97 539	30.42 543	46.49 533	24.52 544	13.94 537	17.23 538	39.47 534	6.39 541	31.40 540	5.94 540	29.49 534	20.72 535

SIFT-NN-UMatch		25.24 504	25.01 508	25.92 524	54.55 545	27.33 548	44.97 534	22.85 545	13.97 536	13.40 542	39.41 535	6.28 542	30.23 543	5.83 541	23.82 538	20.21 536

SIFT-NN-CMatch		25.59 503	25.23 507	26.67 522	56.47 543	28.89 547	42.75 536	22.52 547	13.89 538	16.98 539	39.39 536	6.26 543	30.38 542	5.77 542	22.99 539	20.75 534

SIFT-UMatch		24.03 507	23.67 512	25.10 525	57.10 542	26.49 550	42.43 537	20.05 550	13.49 541	12.40 544	38.51 538	5.45 548	30.07 545	5.56 543	18.08 543	18.74 539

SIFT-NN-PointCN		23.81 508	23.84 511	23.73 527	52.41 546	22.80 554	42.30 538	20.98 549	13.02 544	15.14 540	37.74 541	6.20 544	28.40 547	5.52 544	21.24 540	19.98 537

SIFT-ConvMatch		24.62 506	24.14 510	26.03 523	58.66 540	29.15 546	40.80 539	21.31 548	13.69 539	13.51 541	38.52 537	5.65 546	30.22 544	5.51 545	19.65 541	18.73 540

SIFT-NCM-Cal		25.87 502	25.57 506	26.75 520	60.60 538	29.37 545	44.96 535	22.64 546	13.57 540	11.67 545	37.90 539	5.81 545	31.26 541	5.32 546	27.70 536	19.63 538

SIFT-UM-Cal		22.52 511	22.27 514	23.27 528	56.41 544	23.87 553	39.94 540	16.81 553	13.33 543	10.54 546	37.90 539	5.16 549	28.36 548	5.23 547	15.12 547	17.57 542

SIFT-CM-Cal		23.18 510	22.70 513	24.60 526	57.42 541	26.79 549	37.63 541	18.36 551	13.35 542	12.57 543	37.37 542	5.54 547	28.79 546	5.17 548	16.92 546	18.23 541

SIFT-PCN-Cal		20.26 513	20.34 516	20.01 530	51.70 548	17.74 556	35.64 543	16.15 554	11.90 547	10.28 548	33.69 543	4.55 551	25.68 549	4.57 549	14.59 548	16.60 544

SIFT-PointCN		20.70 512	20.89 515	20.14 529	51.62 549	18.11 555	37.52 542	17.71 552	12.03 546	10.05 549	33.23 544	4.33 552	25.40 550	4.55 550	16.94 545	16.90 543

SIFT-NCMNet		17.70 514	17.74 517	17.60 531	49.47 551	16.50 557	30.22 544	10.39 555	11.77 548	8.79 550	29.74 546	3.61 555	22.42 551	3.97 551	11.69 549	13.89 545

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		23.24 509	30.99 502	0.00 534	0.00 558	0.00 560	0.00 545	97.63 167	0.00 552	0.00 554	96.88 222	84.38 214	0.00 554	0.00 552	0.00 552	0.00 549

pcd_1.5k_mvsjas		7.39 518	9.85 521	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	0.00 552	88.65 110	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		8.06 517	10.74 520	0.00 534	0.00 558	0.00 560	0.00 545	0.00 559	0.00 552	0.00 554	96.69 233	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				98.34 8	98.54 80	96.25 4	98.69 11	97.85 138	94.15 91	98.17 46	97.94 113	94.00 16	99.63 89		97.45 174	99.15 88

FOURS1					99.55 4	93.34 73	99.29 1	98.35 41	94.98 48	98.49 39

test_one_0601					99.32 27	95.20 22		98.25 61	95.13 42	98.48 40	98.87 33	95.16 8

eth-test2					0.00 558

eth-test					0.00 558

test_241102_ONE					99.42 10	95.30 19		98.27 55	95.09 45	99.19 13	98.81 39	95.54 5	99.65 80

save fliter					98.91 59	94.28 44	97.02 214	98.02 114	95.35 33

test0726					99.45 6	95.36 15	98.31 32	98.29 50	94.92 52	98.99 18	98.92 25	95.08 9

GSMVS																98.45 196

test_part2					99.28 31	95.74 9				98.10 49

sam_mvs1												82.76 252				98.45 196

sam_mvs												81.94 273

MTGPA								98.08 94

test_post											17.58 549	81.76 276	98.08 323

patchmatchnet-post											90.45 456	82.65 257	98.10 318

MTMP							97.86 92	82.03 510

TEST9					98.70 66	94.19 48	96.41 283	98.02 114	88.17 344	96.03 129	97.56 174	92.74 37	99.59 97

test_8					98.67 68	94.06 55	96.37 291	98.01 117	88.58 331	95.98 134	97.55 176	92.73 38	99.58 100

agg_prior					98.67 68	93.79 61		98.00 118		95.68 147			99.57 107

test_prior4						93.66 64	96.42 282

test_prior				97.23 70	98.67 68	92.99 85		98.00 118					99.41 134			99.29 75

新几何2							95.79 339

旧先验1					98.38 91	93.38 70		97.75 150			98.09 97	92.30 49			99.01 107	99.16 86

原ACMM2							95.67 345

test222					98.24 102	92.21 116	95.33 365	97.60 172	79.22 474	95.25 165	97.84 134	88.80 107			99.15 94	98.72 169

segment_acmp												92.89 34

testdata1							95.26 372		93.10 141

test12				97.65 48	98.46 81	94.26 45		97.66 161		95.52 156		90.89 79	99.46 128		99.25 80	99.22 82

plane_prior7					96.21 280	89.98 220

plane_prior6					96.10 299	90.00 216						81.32 283

plane_prior4											96.64 236

plane_prior3						90.00 216			94.46 80	91.34 284

plane_prior2							97.74 114		94.85 55

plane_prior1					96.14 294

plane_prior						89.99 218	97.24 194		94.06 95						92.16 318

n2								0.00 559

nn								0.00 559

door-mid								91.06 485

test11								97.88 131

door								91.13 484

HQP5-MVS						89.33 254

HQP-NCC					95.86 307		96.65 263		93.55 114	90.14 308

ACMP_Plane					95.86 307		96.65 263		93.55 114	90.14 308

HQP4-MVS										90.14 308			98.50 277			95.78 339

HQP3-MVS								97.39 224							92.10 319

HQP2-MVS												80.95 289

NP-MVS					95.99 305	89.81 228					95.87 280

ACMMP++_ref															90.30 348

ACMMP++															91.02 337

Test By Simon												88.73 109

High-resolution multi-view benchmark