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.

IU-MVS					99.03 15	85.34 61		96.86 54	92.05 32	98.74 1				98.15 16	98.97 17	99.42 13

PC_three_1452									91.12 41	98.33 2	98.42 33	92.51 2	99.81 22	98.96 4	99.37 1	99.70 3

fmvsm_l_conf0.5_n		94.89 16	95.24 17	93.86 53	94.42 173	84.61 82	99.13 12	96.15 141	92.06 30	97.92 3	98.52 24	84.52 41	99.74 43	98.76 6	95.67 120	97.22 154

SMA-MVS		94.70 21	94.68 22	94.76 29	98.02 59	85.94 44	97.47 105	96.77 65	85.32 152	97.92 3	98.70 15	83.09 59	99.84 13	95.79 49	99.08 10	98.49 57
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
fmvsm_l_conf0.5_n_a		94.91 15	95.30 16	93.72 62	94.50 170	84.30 87	99.14 11	96.00 152	91.94 33	97.91 5	98.60 18	84.78 38	99.77 33	98.84 5	96.03 113	97.08 163

SED-MVS		95.88 5	96.22 4	94.87 25	99.03 15	85.03 74	99.12 13	96.78 59	88.72 73	97.79 6	98.91 2	88.48 17	99.82 19	98.15 16	98.97 17	99.74 1

test_241102_ONE					99.03 15	85.03 74		96.78 59	88.72 73	97.79 6	98.90 5	88.48 17	99.82 19

DVP-MVS++		96.05 4	96.41 3	94.96 24	99.05 9	85.34 61	98.13 56	96.77 65	88.38 81	97.70 8	98.77 10	92.06 3	99.84 13	97.47 30	99.37 1	99.70 3

test_241102_TWO								96.78 59	88.72 73	97.70 8	98.91 2	87.86 22	99.82 19	98.15 16	99.00 15	99.47 9

patch_mono-2		95.14 13	96.08 7	92.33 127	98.44 43	77.84 257	98.43 43	97.21 23	92.58 24	97.68 10	97.65 85	86.88 27	99.83 17	98.25 12	97.60 69	99.33 18

test0726					99.05 9	85.18 66	99.11 16	96.78 59	88.75 71	97.65 11	98.91 2	87.69 23

fmvsm_s_conf0.5_n_3		93.95 36	94.53 24	92.20 136	94.41 174	80.04 190	98.90 28	95.96 156	94.53 8	97.63 12	98.58 19	75.95 154	99.79 29	98.25 12	96.60 101	96.77 176

fmvsm_l_conf0.5_n_3		94.61 22	94.92 20	93.68 66	94.52 165	82.80 115	99.33 1	96.37 122	95.08 4	97.59 13	98.48 27	77.40 124	99.79 29	98.28 11	97.21 82	98.44 61

TSAR-MVS + MP.		94.79 20	95.17 18	93.64 68	97.66 69	84.10 90	95.85 227	96.42 113	91.26 39	97.49 14	96.80 129	86.50 29	98.49 141	95.54 54	99.03 13	98.33 66
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.5_n_4		93.59 41	94.32 31	91.41 172	93.89 192	79.24 211	98.89 29	96.53 100	92.82 22	97.37 15	98.47 28	77.21 131	99.78 31	98.11 19	95.59 122	95.21 223

test_fmvsm_n_1920		94.81 19	95.60 11	92.45 119	95.29 140	80.96 160	99.29 3	97.21 23	94.50 9	97.29 16	98.44 30	82.15 64	99.78 31	98.56 7	97.68 67	96.61 183

MSP-MVS		95.62 8	96.54 1	92.86 102	98.31 48	80.10 189	97.42 112	96.78 59	92.20 27	97.11 17	98.29 41	93.46 1	99.10 110	96.01 45	99.30 5	99.38 14
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
MVS_0304		95.58 9	95.44 15	96.01 10	97.63 70	89.26 12	99.27 4	96.59 92	94.71 5	97.08 18	97.99 61	78.69 103	99.86 10	99.15 2	97.85 62	98.91 35

fmvsm_s_conf0.5_n_2		92.97 53	93.38 50	91.73 159	94.10 186	80.64 170	98.96 25	95.89 165	94.09 12	97.05 19	98.40 34	68.92 242	99.80 25	98.53 8	94.50 134	94.74 233

fmvsm_s_conf0.5_n_a		93.34 47	93.71 40	92.22 134	93.38 209	81.71 143	98.86 30	96.98 41	91.64 34	96.85 20	98.55 20	75.58 162	99.77 33	97.88 25	93.68 148	95.18 224

CNVR-MVS		96.30 1	96.54 1	95.55 15	99.31 5	87.69 24	99.06 18	97.12 30	94.66 6	96.79 21	98.78 9	86.42 30	99.95 3	97.59 29	99.18 7	99.00 31

DVP-MVS		95.58 9	95.91 9	94.57 34	99.05 9	85.18 66	99.06 18	96.46 108	88.75 71	96.69 22	98.76 12	87.69 23	99.76 35	97.90 23	98.85 21	98.77 40
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_THIRD									88.38 81	96.69 22	98.76 12	89.64 12	99.76 35	97.47 30	98.84 23	99.38 14

SD-MVS		94.84 18	95.02 19	94.29 40	97.87 64	84.61 82	97.76 82	96.19 139	89.59 63	96.66 24	98.17 49	84.33 43	99.60 65	96.09 44	98.50 38	98.66 49
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
MM		95.85 6	95.74 10	96.15 8	96.34 102	89.50 9	99.18 7	98.10 8	95.68 1	96.64 25	97.92 67	80.72 72	99.80 25	99.16 1	97.96 58	99.15 27

fmvsm_s_conf0.1_n_a		92.38 79	92.49 69	92.06 143	88.08 334	81.62 146	97.97 68	96.01 151	90.62 49	96.58 26	98.33 40	74.09 192	99.71 50	97.23 34	93.46 153	94.86 229

test_one_0601					98.91 18	84.56 84		96.70 75	88.06 91	96.57 27	98.77 10	88.04 21

DPE-MVS		95.32 11	95.55 12	94.64 33	98.79 23	84.87 79	97.77 80	96.74 70	86.11 134	96.54 28	98.89 6	88.39 19	99.74 43	97.67 28	99.05 12	99.31 20
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
DPM-MVS		96.21 2	95.53 13	98.26 1	96.26 105	95.09 1	99.15 9	96.98 41	93.39 18	96.45 29	98.79 8	90.17 9	99.99 1	89.33 146	99.25 6	99.70 3

fmvsm_s_conf0.5_n		93.69 39	94.13 36	92.34 125	94.56 162	82.01 128	99.07 17	97.13 28	92.09 28	96.25 30	98.53 23	76.47 143	99.80 25	98.39 9	94.71 130	95.22 222

PS-MVSNAJ		94.17 31	93.52 45	96.10 9	95.65 128	92.35 2	98.21 51	95.79 172	92.42 26	96.24 31	98.18 46	71.04 229	99.17 104	96.77 40	97.39 77	96.79 174

fmvsm_s_conf0.1_n_2		92.26 83	92.48 70	91.60 166	92.29 245	80.55 173	98.73 33	94.33 263	93.80 15	96.18 32	98.11 52	66.93 255	99.75 40	98.19 15	93.74 147	94.50 240

旧先验2							96.97 152		74.06 347	96.10 33			97.76 180	88.38 157

test_part2					98.90 19	85.14 72				96.07 34

fmvsm_s_conf0.1_n		92.93 55	93.16 54	92.24 132	90.52 294	81.92 132	98.42 44	96.24 133	91.17 40	96.02 35	98.35 39	75.34 173	99.74 43	97.84 26	94.58 132	95.05 225

xiu_mvs_v2_base		93.92 37	93.26 51	95.91 11	95.07 148	92.02 6	98.19 52	95.68 178	92.06 30	96.01 36	98.14 50	70.83 233	98.96 118	96.74 42	96.57 102	96.76 178

balanced_conf03		94.60 24	94.30 32	95.48 16	96.45 100	88.82 14	96.33 198	95.58 182	91.12 41	95.84 37	93.87 210	83.47 55	98.37 150	97.26 33	98.81 24	99.24 23

HPM-MVS++		95.32 11	95.48 14	94.85 26	98.62 34	86.04 40	97.81 77	96.93 47	92.45 25	95.69 38	98.50 25	85.38 34	99.85 11	94.75 65	99.18 7	98.65 50

fmvsm_s_conf0.5_n_5		93.57 43	93.75 38	93.01 95	92.87 227	82.73 116	98.93 27	95.90 164	90.96 46	95.61 39	98.39 35	76.57 141	99.63 62	98.32 10	96.24 106	96.68 182

NCCC		95.63 7	95.94 8	94.69 32	99.21 6	85.15 71	99.16 8	96.96 44	94.11 11	95.59 40	98.64 17	85.07 36	99.91 4	95.61 52	99.10 9	99.00 31

EPNet		94.06 34	94.15 35	93.76 57	97.27 91	84.35 85	98.29 48	97.64 14	94.57 7	95.36 41	96.88 124	79.96 86	99.12 109	91.30 112	96.11 110	97.82 109
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
CANet		94.89 16	94.64 23	95.63 13	97.55 76	88.12 18	99.06 18	96.39 118	94.07 13	95.34 42	97.80 76	76.83 137	99.87 8	97.08 37	97.64 68	98.89 36

test_fmvsmconf_n		93.99 35	94.36 30	92.86 102	92.82 228	81.12 153	99.26 5	96.37 122	93.47 17	95.16 43	98.21 44	79.00 96	99.64 60	98.21 14	96.73 99	97.83 107

TEST9					98.64 31	83.71 97	97.82 75	96.65 82	84.29 185	95.16 43	98.09 54	84.39 42	99.36 87

train_agg		94.28 28	94.45 27	93.74 59	98.64 31	83.71 97	97.82 75	96.65 82	84.50 176	95.16 43	98.09 54	84.33 43	99.36 87	95.91 48	98.96 19	98.16 80

test_8					98.63 33	83.64 100	97.81 77	96.63 87	84.50 176	95.10 46	98.11 52	84.33 43	99.23 94

DeepPCF-MVS	89.82 1	94.61 22	96.17 5	89.91 219	97.09 94	70.21 353	98.99 24	96.69 77	95.57 2	95.08 47	99.23 1	86.40 31	99.87 8	97.84 26	98.66 32	99.65 6

SF-MVS		94.17 31	94.05 37	94.55 35	97.56 75	85.95 42	97.73 84	96.43 112	84.02 192	95.07 48	98.74 14	82.93 60	99.38 84	95.42 56	98.51 36	98.32 67

APDe-MVS		94.56 25	94.75 21	93.96 51	98.84 22	83.40 105	98.04 64	96.41 114	85.79 143	95.00 49	98.28 42	84.32 46	99.18 103	97.35 32	98.77 28	99.28 21
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
MVSFormer		91.36 106	90.57 112	93.73 61	93.00 220	88.08 19	94.80 271	94.48 249	80.74 259	94.90 50	97.13 112	78.84 99	95.10 322	83.77 195	97.46 72	98.02 89

lupinMVS		93.87 38	93.58 44	94.75 30	93.00 220	88.08 19	99.15 9	95.50 189	91.03 44	94.90 50	97.66 81	78.84 99	97.56 191	94.64 68	97.46 72	98.62 52

SPE-MVS-test		92.98 52	93.67 41	90.90 188	96.52 99	76.87 280	98.68 35	94.73 232	90.36 56	94.84 52	97.89 71	77.94 113	97.15 222	94.28 73	97.80 64	98.70 48

9.14			94.26 34		98.10 57		98.14 53	96.52 101	84.74 168	94.83 53	98.80 7	82.80 62	99.37 86	95.95 47	98.42 42

testdata				90.13 210	95.92 119	74.17 315		96.49 107	73.49 352	94.82 54	97.99 61	78.80 101	97.93 169	83.53 203	97.52 71	98.29 71

APD-MVS		93.61 40	93.59 43	93.69 65	98.76 24	83.26 108	97.21 124	96.09 145	82.41 235	94.65 55	98.21 44	81.96 67	98.81 128	94.65 67	98.36 47	99.01 30
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_prior2							98.37 46		86.08 136	94.57 56	98.02 60	83.14 57		95.05 61	98.79 27

CS-MVS		92.73 61	93.48 47	90.48 201	96.27 104	75.93 300	98.55 41	94.93 219	89.32 66	94.54 57	97.67 80	78.91 98	97.02 226	93.80 76	97.32 79	98.49 57

FOURS1					98.51 39	78.01 249	98.13 56	96.21 136	83.04 219	94.39 58

ACMMP_NAP		93.46 45	93.23 52	94.17 46	97.16 92	84.28 88	96.82 165	96.65 82	86.24 132	94.27 59	97.99 61	77.94 113	99.83 17	93.39 81	98.57 34	98.39 64

agg_prior					98.59 35	83.13 110		96.56 97		94.19 60			99.16 105

SteuartSystems-ACMMP		94.13 33	94.44 28	93.20 87	95.41 135	81.35 150	99.02 22	96.59 92	89.50 65	94.18 61	98.36 38	83.68 54	99.45 81	94.77 64	98.45 41	98.81 39
Skip Steuart: Steuart Systems R&D Blog.
PHI-MVS		93.59 41	93.63 42	93.48 79	98.05 58	81.76 140	98.64 38	97.13 28	82.60 231	94.09 62	98.49 26	80.35 76	99.85 11	94.74 66	98.62 33	98.83 38

test_fmvsmconf0.1_n		93.08 51	93.22 53	92.65 112	88.45 329	80.81 165	99.00 23	95.11 211	93.21 19	94.00 63	97.91 69	76.84 135	99.59 66	97.91 22	96.55 103	97.54 129

MVSMamba_PlusPlus		92.37 80	91.55 92	94.83 27	95.37 137	87.69 24	95.60 239	95.42 198	74.65 342	93.95 64	92.81 228	83.11 58	97.70 183	94.49 69	98.53 35	99.11 28

TSAR-MVS + GP.		94.35 27	94.50 25	93.89 52	97.38 88	83.04 112	98.10 58	95.29 205	91.57 35	93.81 65	97.45 94	86.64 28	99.43 82	96.28 43	94.01 140	99.20 25

CANet_DTU		90.98 117	90.04 128	93.83 54	94.76 158	86.23 38	96.32 199	93.12 328	93.11 20	93.71 66	96.82 128	63.08 280	99.48 79	84.29 188	95.12 126	95.77 206

VNet		92.11 86	91.22 98	94.79 28	96.91 95	86.98 31	97.91 70	97.96 10	86.38 131	93.65 67	95.74 149	70.16 238	98.95 120	93.39 81	88.87 196	98.43 62

test_vis1_n_1920		89.95 137	90.59 111	88.03 259	92.36 240	68.98 362	99.12 13	94.34 262	93.86 14	93.64 68	97.01 120	51.54 353	99.59 66	96.76 41	96.71 100	95.53 213

ZD-MVS					99.09 8	83.22 109		96.60 91	82.88 224	93.61 69	98.06 59	82.93 60	99.14 106	95.51 55	98.49 39

xiu_mvs_v1_base_debu		90.54 126	89.54 137	93.55 74	92.31 241	87.58 26	96.99 147	94.87 223	87.23 115	93.27 70	97.56 90	57.43 322	98.32 152	92.72 95	93.46 153	94.74 233

xiu_mvs_v1_base		90.54 126	89.54 137	93.55 74	92.31 241	87.58 26	96.99 147	94.87 223	87.23 115	93.27 70	97.56 90	57.43 322	98.32 152	92.72 95	93.46 153	94.74 233

xiu_mvs_v1_base_debi		90.54 126	89.54 137	93.55 74	92.31 241	87.58 26	96.99 147	94.87 223	87.23 115	93.27 70	97.56 90	57.43 322	98.32 152	92.72 95	93.46 153	94.74 233

CDPH-MVS		93.12 49	92.91 58	93.74 59	98.65 30	83.88 92	97.67 88	96.26 131	83.00 221	93.22 73	98.24 43	81.31 69	99.21 96	89.12 147	98.74 30	98.14 82

GDP-MVS		92.85 58	92.55 68	93.75 58	92.82 228	85.76 47	97.63 89	95.05 215	88.34 83	93.15 74	97.10 115	86.92 26	98.01 166	87.95 161	94.00 141	97.47 138

ETV-MVS		92.72 63	92.87 59	92.28 131	94.54 164	81.89 134	97.98 66	95.21 209	89.77 62	93.11 75	96.83 126	77.23 130	97.50 199	95.74 50	95.38 124	97.44 140

MSLP-MVS++		94.28 28	94.39 29	93.97 50	98.30 49	84.06 91	98.64 38	96.93 47	90.71 48	93.08 76	98.70 15	79.98 85	99.21 96	94.12 74	99.07 11	98.63 51

alignmvs		92.97 53	92.26 76	95.12 21	95.54 132	87.77 22	98.67 36	96.38 119	88.04 92	93.01 77	97.45 94	79.20 94	98.60 134	93.25 87	88.76 197	98.99 33

sasdasda		92.27 81	91.22 98	95.41 17	95.80 123	88.31 15	97.09 142	94.64 240	88.49 78	92.99 78	97.31 101	72.68 207	98.57 136	93.38 83	88.58 200	99.36 16

canonicalmvs		92.27 81	91.22 98	95.41 17	95.80 123	88.31 15	97.09 142	94.64 240	88.49 78	92.99 78	97.31 101	72.68 207	98.57 136	93.38 83	88.58 200	99.36 16

EC-MVSNet		91.73 94	92.11 81	90.58 197	93.54 201	77.77 261	98.07 61	94.40 259	87.44 108	92.99 78	97.11 114	74.59 186	96.87 237	93.75 77	97.08 86	97.11 161

MGCFI-Net		91.95 88	91.03 104	94.72 31	95.68 127	86.38 36	96.93 157	94.48 249	88.25 86	92.78 81	97.24 107	72.34 212	98.46 144	93.13 91	88.43 204	99.32 19

jason		92.73 61	92.23 77	94.21 44	90.50 295	87.30 30	98.65 37	95.09 212	90.61 50	92.76 82	97.13 112	75.28 174	97.30 211	93.32 85	96.75 98	98.02 89
jason: jason.
reproduce_model		92.53 75	92.87 59	91.50 169	97.41 83	77.14 278	96.02 215	95.91 163	83.65 208	92.45 83	98.39 35	79.75 88	99.21 96	95.27 60	96.98 89	98.14 82

reproduce-ours		92.70 66	93.02 55	91.75 157	97.45 79	77.77 261	96.16 208	95.94 160	84.12 188	92.45 83	98.43 31	80.06 83	99.24 92	95.35 57	97.18 83	98.24 75

our_new_method		92.70 66	93.02 55	91.75 157	97.45 79	77.77 261	96.16 208	95.94 160	84.12 188	92.45 83	98.43 31	80.06 83	99.24 92	95.35 57	97.18 83	98.24 75

test_cas_vis1_n_1920		89.90 138	90.02 129	89.54 227	90.14 303	74.63 310	98.71 34	94.43 257	93.04 21	92.40 86	96.35 138	53.41 349	99.08 112	95.59 53	96.16 108	94.90 227

test12				94.25 41	98.34 46	85.55 57		96.35 124		92.36 87		80.84 71	99.22 95		98.31 49	97.98 96

MG-MVS		94.25 30	93.72 39	95.85 12	99.38 3	89.35 11	97.98 66	98.09 9	89.99 59	92.34 88	96.97 121	81.30 70	98.99 116	88.54 153	98.88 20	99.20 25

test_fmvs1		87.79 188	88.52 154	85.62 309	92.98 224	64.31 382	97.88 72	92.42 338	87.95 94	92.24 89	95.82 148	47.94 369	98.44 148	95.31 59	94.09 137	94.09 246

h-mvs33		89.30 149	88.95 146	90.36 204	95.07 148	76.04 294	96.96 154	97.11 31	90.39 54	92.22 90	95.10 178	74.70 182	98.86 125	93.14 89	65.89 371	96.16 196

hse-mvs2		88.22 179	88.21 158	88.25 253	93.54 201	73.41 318	95.41 247	95.89 165	90.39 54	92.22 90	94.22 200	74.70 182	96.66 248	93.14 89	64.37 376	94.69 238

MCST-MVS		96.17 3	96.12 6	96.32 7	99.42 2	89.36 10	98.94 26	97.10 32	95.17 3	92.11 92	98.46 29	87.33 25	99.97 2	97.21 35	99.31 4	99.63 7

BP-MVS1		93.55 44	93.50 46	93.71 63	92.64 235	85.39 60	97.78 79	96.84 55	89.52 64	92.00 93	97.06 118	88.21 20	98.03 164	91.45 111	96.00 115	97.70 118

test_fmvsmconf0.01_n		91.08 114	90.68 110	92.29 130	82.43 388	80.12 188	97.94 69	93.93 282	92.07 29	91.97 94	97.60 88	67.56 248	99.53 74	97.09 36	95.56 123	97.21 156

SR-MVS		92.16 84	92.27 75	91.83 155	98.37 45	78.41 235	96.67 176	95.76 173	82.19 239	91.97 94	98.07 58	76.44 144	98.64 132	93.71 78	97.27 80	98.45 60

region2R		92.72 63	92.70 63	92.79 105	98.68 26	80.53 177	97.53 100	96.51 102	85.22 155	91.94 96	97.98 64	77.26 126	99.67 58	90.83 120	98.37 46	98.18 78

Effi-MVS+		90.70 123	89.90 134	93.09 92	93.61 198	83.48 103	95.20 255	92.79 334	83.22 214	91.82 97	95.70 151	71.82 220	97.48 201	91.25 113	93.67 149	98.32 67

HFP-MVS		92.89 56	92.86 61	92.98 97	98.71 25	81.12 153	97.58 95	96.70 75	85.20 157	91.75 98	97.97 66	78.47 105	99.71 50	90.95 115	98.41 43	98.12 85

DeepC-MVS_fast	89.06 2	94.48 26	94.30 32	95.02 22	98.86 21	85.68 51	98.06 62	96.64 85	93.64 16	91.74 99	98.54 21	80.17 81	99.90 5	92.28 100	98.75 29	99.49 8
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
ACMMPR		92.69 68	92.67 64	92.75 106	98.66 28	80.57 172	97.58 95	96.69 77	85.20 157	91.57 100	97.92 67	77.01 132	99.67 58	90.95 115	98.41 43	98.00 94

DELS-MVS		94.98 14	94.49 26	96.44 6	96.42 101	90.59 7	99.21 6	97.02 38	94.40 10	91.46 101	97.08 116	83.32 56	99.69 54	92.83 94	98.70 31	99.04 29
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
XVS		92.69 68	92.71 62	92.63 114	98.52 37	80.29 180	97.37 116	96.44 110	87.04 120	91.38 102	97.83 75	77.24 128	99.59 66	90.46 128	98.07 54	98.02 89

X-MVStestdata		86.26 212	84.14 233	92.63 114	98.52 37	80.29 180	97.37 116	96.44 110	87.04 120	91.38 102	20.73 432	77.24 128	99.59 66	90.46 128	98.07 54	98.02 89

PMMVS		89.46 146	89.92 133	88.06 257	94.64 159	69.57 359	96.22 204	94.95 218	87.27 114	91.37 104	96.54 136	65.88 262	97.39 206	88.54 153	93.89 144	97.23 153

test_fmvs1_n		86.34 210	86.72 195	85.17 316	87.54 341	63.64 387	96.91 159	92.37 340	87.49 107	91.33 105	95.58 157	40.81 396	98.46 144	95.00 62	93.49 151	93.41 260

dcpmvs_2		93.10 50	93.46 48	92.02 146	97.77 65	79.73 200	94.82 269	93.86 289	86.91 122	91.33 105	96.76 130	85.20 35	98.06 162	96.90 39	97.60 69	98.27 73

原ACMM1				91.22 180	97.77 65	78.10 247		96.61 88	81.05 253	91.28 107	97.42 98	77.92 115	98.98 117	79.85 233	98.51 36	96.59 184

新几何1				93.12 90	97.44 81	81.60 147		96.71 74	74.54 343	91.22 108	97.57 89	79.13 95	99.51 77	77.40 259	98.46 40	98.26 74

UA-Net		88.92 156	88.48 155	90.24 207	94.06 188	77.18 276	93.04 316	94.66 237	87.39 110	91.09 109	93.89 209	74.92 179	98.18 159	75.83 275	91.43 175	95.35 218

ZNCC-MVS		92.75 59	92.60 66	93.23 86	98.24 51	81.82 138	97.63 89	96.50 104	85.00 163	91.05 110	97.74 78	78.38 106	99.80 25	90.48 126	98.34 48	98.07 87

APD-MVS_3200maxsize		91.23 110	91.35 95	90.89 189	97.89 62	76.35 290	96.30 200	95.52 187	79.82 282	91.03 111	97.88 72	74.70 182	98.54 138	92.11 104	96.89 92	97.77 112

test_vis1_n		85.60 224	85.70 204	85.33 313	84.79 372	64.98 380	96.83 163	91.61 351	87.36 111	91.00 112	94.84 187	36.14 403	97.18 218	95.66 51	93.03 158	93.82 251

GST-MVS		92.43 78	92.22 79	93.04 94	98.17 54	81.64 145	97.40 114	96.38 119	84.71 170	90.90 113	97.40 99	77.55 122	99.76 35	89.75 139	97.74 65	97.72 115

PGM-MVS		91.93 89	91.80 87	92.32 129	98.27 50	79.74 199	95.28 249	97.27 21	83.83 201	90.89 114	97.78 77	76.12 151	99.56 72	88.82 150	97.93 61	97.66 121

SR-MVS-dyc-post		91.29 108	91.45 94	90.80 191	97.76 67	76.03 295	96.20 206	95.44 194	80.56 264	90.72 115	97.84 73	75.76 158	98.61 133	91.99 106	96.79 96	97.75 113

RE-MVS-def			91.18 102		97.76 67	76.03 295	96.20 206	95.44 194	80.56 264	90.72 115	97.84 73	73.36 202		91.99 106	96.79 96	97.75 113

MP-MVS		92.61 72	92.67 64	92.42 123	98.13 56	79.73 200	97.33 119	96.20 137	85.63 145	90.53 117	97.66 81	78.14 111	99.70 53	92.12 103	98.30 50	97.85 105
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HY-MVS	84.06 6	91.63 98	90.37 119	95.39 19	96.12 110	88.25 17	90.22 348	97.58 15	88.33 84	90.50 118	91.96 244	79.26 92	99.06 113	90.29 133	89.07 192	98.88 37

CP-MVS		92.54 74	92.60 66	92.34 125	98.50 40	79.90 193	98.40 45	96.40 116	84.75 167	90.48 119	98.09 54	77.40 124	99.21 96	91.15 114	98.23 52	97.92 100

diffmvs		91.17 111	90.74 109	92.44 121	93.11 219	82.50 122	96.25 203	93.62 304	87.79 99	90.40 120	95.93 145	73.44 201	97.42 203	93.62 80	92.55 163	97.41 142
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
MVS_Test		90.29 133	89.18 141	93.62 70	95.23 141	84.93 77	94.41 276	94.66 237	84.31 181	90.37 121	91.02 257	75.13 176	97.82 178	83.11 208	94.42 135	98.12 85

MTAPA		92.45 77	92.31 74	92.86 102	97.90 61	80.85 164	92.88 320	96.33 125	87.92 95	90.20 122	98.18 46	76.71 140	99.76 35	92.57 98	98.09 53	97.96 99

test_yl		91.46 102	90.53 113	94.24 42	97.41 83	85.18 66	98.08 59	97.72 11	80.94 254	89.85 123	96.14 141	75.61 159	98.81 128	90.42 131	88.56 202	98.74 42

DCV-MVSNet		91.46 102	90.53 113	94.24 42	97.41 83	85.18 66	98.08 59	97.72 11	80.94 254	89.85 123	96.14 141	75.61 159	98.81 128	90.42 131	88.56 202	98.74 42

WTY-MVS		92.65 71	91.68 89	95.56 14	96.00 113	88.90 13	98.23 50	97.65 13	88.57 76	89.82 125	97.22 109	79.29 91	99.06 113	89.57 142	88.73 198	98.73 46

MVS_111021_HR		93.41 46	93.39 49	93.47 81	97.34 89	82.83 114	97.56 97	98.27 6	89.16 69	89.71 126	97.14 111	79.77 87	99.56 72	93.65 79	97.94 59	98.02 89

sss		90.87 121	89.96 131	93.60 71	94.15 182	83.84 95	97.14 135	98.13 7	85.93 141	89.68 127	96.09 143	71.67 221	99.30 89	87.69 164	89.16 191	97.66 121

test222					96.15 109	78.41 235	95.87 225	96.46 108	71.97 363	89.66 128	97.45 94	76.33 148			98.24 51	98.30 70

LFMVS		89.27 150	87.64 169	94.16 48	97.16 92	85.52 58	97.18 128	94.66 237	79.17 296	89.63 129	96.57 135	55.35 339	98.22 156	89.52 144	89.54 187	98.74 42

CostFormer		89.08 152	88.39 156	91.15 181	93.13 217	79.15 216	88.61 360	96.11 144	83.14 216	89.58 130	86.93 318	83.83 53	96.87 237	88.22 159	85.92 231	97.42 141

PVSNet_BlendedMVS		90.05 135	89.96 131	90.33 205	97.47 77	83.86 93	98.02 65	96.73 71	87.98 93	89.53 131	89.61 278	76.42 145	99.57 70	94.29 71	79.59 277	87.57 346

PVSNet_Blended		93.13 48	92.98 57	93.57 73	97.47 77	83.86 93	99.32 2	96.73 71	91.02 45	89.53 131	96.21 140	76.42 145	99.57 70	94.29 71	95.81 119	97.29 152

HPM-MVS		91.62 99	91.53 93	91.89 150	97.88 63	79.22 213	96.99 147	95.73 176	82.07 241	89.50 133	97.19 110	75.59 161	98.93 123	90.91 117	97.94 59	97.54 129
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
testing11		92.48 76	92.04 84	93.78 56	95.94 117	86.00 41	97.56 97	97.08 33	87.52 106	89.32 134	95.40 162	84.60 39	98.02 165	91.93 108	89.04 193	97.32 148

UBG		92.68 70	92.35 72	93.70 64	95.61 129	85.65 54	97.25 122	97.06 35	87.92 95	89.28 135	95.03 180	86.06 33	98.07 161	92.24 101	90.69 182	97.37 146

EI-MVSNet-Vis-set		91.84 93	91.77 88	92.04 145	97.60 72	81.17 152	96.61 177	96.87 52	88.20 88	89.19 136	97.55 93	78.69 103	99.14 106	90.29 133	90.94 179	95.80 204

testing222		91.09 113	90.49 115	92.87 101	95.82 121	85.04 73	96.51 184	97.28 20	86.05 137	89.13 137	95.34 164	80.16 82	96.62 249	85.82 176	88.31 206	96.96 166

MP-MVS-pluss		92.58 73	92.35 72	93.29 83	97.30 90	82.53 120	96.44 189	96.04 150	84.68 171	89.12 138	98.37 37	77.48 123	99.74 43	93.31 86	98.38 45	97.59 127
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
VDD-MVS		88.28 177	87.02 189	92.06 143	95.09 146	80.18 187	97.55 99	94.45 254	83.09 217	89.10 139	95.92 147	47.97 368	98.49 141	93.08 93	86.91 220	97.52 134

baseline		90.76 122	90.10 126	92.74 107	92.90 226	82.56 119	94.60 273	94.56 246	87.69 102	89.06 140	95.67 153	73.76 196	97.51 198	90.43 130	92.23 169	98.16 80

testing99		91.91 90	91.35 95	93.60 71	95.98 115	85.70 49	97.31 120	96.92 49	86.82 125	88.91 141	95.25 165	84.26 47	97.89 176	88.80 151	87.94 210	97.21 156

EIA-MVS		91.73 94	92.05 83	90.78 193	94.52 165	76.40 289	98.06 62	95.34 203	89.19 68	88.90 142	97.28 106	77.56 121	97.73 182	90.77 121	96.86 95	98.20 77

testing91		91.90 91	91.31 97	93.66 67	95.99 114	85.68 51	97.39 115	96.89 50	86.75 129	88.85 143	95.23 168	83.93 51	97.90 175	88.91 148	87.89 211	97.41 142

mvsany_test1		87.58 193	88.22 157	85.67 307	89.78 307	67.18 369	95.25 252	87.93 387	83.96 195	88.79 144	97.06 118	72.52 209	94.53 339	92.21 102	86.45 224	95.30 220

HPM-MVS_fast		90.38 132	90.17 125	91.03 184	97.61 71	77.35 272	97.15 134	95.48 190	79.51 288	88.79 144	96.90 122	71.64 223	98.81 128	87.01 172	97.44 74	96.94 167

ETVMVS		90.99 116	90.26 120	93.19 88	95.81 122	85.64 55	96.97 152	97.18 26	85.43 149	88.77 146	94.86 186	82.00 66	96.37 256	82.70 211	88.60 199	97.57 128

PAPM		92.87 57	92.40 71	94.30 39	92.25 249	87.85 21	96.40 193	96.38 119	91.07 43	88.72 147	96.90 122	82.11 65	97.37 208	90.05 136	97.70 66	97.67 120

MVS_111021_LR		91.60 100	91.64 91	91.47 171	95.74 125	78.79 226	96.15 210	96.77 65	88.49 78	88.64 148	97.07 117	72.33 213	99.19 102	93.13 91	96.48 104	96.43 188

casdiffmvs		90.95 119	90.39 117	92.63 114	92.82 228	82.53 120	96.83 163	94.47 252	87.69 102	88.47 149	95.56 158	74.04 193	97.54 195	90.90 118	92.74 161	97.83 107
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
mPP-MVS		91.88 92	91.82 86	92.07 142	98.38 44	78.63 229	97.29 121	96.09 145	85.12 159	88.45 150	97.66 81	75.53 163	99.68 56	89.83 137	98.02 57	97.88 101

PAPR		92.74 60	92.17 80	94.45 36	98.89 20	84.87 79	97.20 126	96.20 137	87.73 101	88.40 151	98.12 51	78.71 102	99.76 35	87.99 160	96.28 105	98.74 42

tpmrst		88.36 174	87.38 180	91.31 174	94.36 176	79.92 192	87.32 372	95.26 207	85.32 152	88.34 152	86.13 335	80.60 75	96.70 245	83.78 194	85.34 239	97.30 151

GG-mvs-BLEND				93.49 78	94.94 152	86.26 37	81.62 400	97.00 39		88.32 153	94.30 198	91.23 5	96.21 264	88.49 155	97.43 75	98.00 94

EI-MVSNet-UG-set		91.35 107	91.22 98	91.73 159	97.39 86	80.68 168	96.47 186	96.83 56	87.92 95	88.30 154	97.36 100	77.84 116	99.13 108	89.43 145	89.45 188	95.37 217

myMVS_eth3d28		92.72 63	92.23 77	94.21 44	96.16 108	87.46 29	97.37 116	96.99 40	88.13 90	88.18 155	95.47 160	84.12 48	98.04 163	92.46 99	91.17 177	97.14 160

MAR-MVS		90.63 124	90.22 122	91.86 152	98.47 42	78.20 245	97.18 128	96.61 88	83.87 199	88.18 155	98.18 46	68.71 243	99.75 40	83.66 200	97.15 85	97.63 124
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
DP-MVS Recon		91.72 96	90.85 106	94.34 38	99.50 1	85.00 76	98.51 42	95.96 156	80.57 263	88.08 157	97.63 87	76.84 135	99.89 7	85.67 178	94.88 127	98.13 84

VDDNet		86.44 208	84.51 223	92.22 134	91.56 270	81.83 137	97.10 141	94.64 240	69.50 376	87.84 158	95.19 172	48.01 367	97.92 174	89.82 138	86.92 219	96.89 171

UGNet		87.73 189	86.55 197	91.27 177	95.16 145	79.11 217	96.35 196	96.23 134	88.14 89	87.83 159	90.48 265	50.65 356	99.09 111	80.13 230	94.03 138	95.60 210
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
test2506		90.96 118	90.39 117	92.65 112	93.54 201	82.46 123	96.37 194	97.35 18	86.78 127	87.55 160	95.25 165	77.83 117	97.50 199	84.07 190	94.80 128	97.98 96

tpm2		87.35 196	86.26 199	90.62 196	92.93 225	78.67 228	88.06 367	95.99 153	79.33 291	87.40 161	86.43 329	80.28 78	96.40 254	80.23 228	85.73 235	96.79 174

CPTT-MVS		89.72 141	89.87 135	89.29 230	98.33 47	73.30 321	97.70 86	95.35 202	75.68 333	87.40 161	97.44 97	70.43 235	98.25 155	89.56 143	96.90 91	96.33 193

gg-mvs-nofinetune		85.48 228	82.90 251	93.24 85	94.51 169	85.82 46	79.22 405	96.97 43	61.19 402	87.33 163	53.01 421	90.58 6	96.07 267	86.07 175	97.23 81	97.81 110

CHOSEN 280x420		91.71 97	91.85 85	91.29 176	94.94 152	82.69 117	87.89 368	96.17 140	85.94 140	87.27 164	94.31 197	90.27 8	95.65 294	94.04 75	95.86 117	95.53 213

test_fmvsmvis_n_1920		92.12 85	92.10 82	92.17 138	90.87 287	81.04 156	98.34 47	93.90 286	92.71 23	87.24 165	97.90 70	74.83 180	99.72 48	96.96 38	96.20 107	95.76 207

casdiffmvs_mvg		91.13 112	90.45 116	93.17 89	92.99 223	83.58 101	97.46 107	94.56 246	87.69 102	87.19 166	94.98 184	74.50 187	97.60 188	91.88 109	92.79 160	98.34 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
EPNet_dtu		87.65 192	87.89 163	86.93 286	94.57 161	71.37 347	96.72 171	96.50 104	88.56 77	87.12 167	95.02 181	75.91 156	94.01 349	66.62 337	90.00 184	95.42 216
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
Vis-MVSNet		88.67 164	87.82 165	91.24 178	92.68 231	78.82 223	96.95 155	93.85 290	87.55 105	87.07 168	95.13 176	63.43 277	97.21 216	77.58 255	96.15 109	97.70 118
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
mvsmamba		90.53 129	90.08 127	91.88 151	94.81 156	80.93 161	93.94 293	94.45 254	88.24 87	87.02 169	92.35 235	68.04 245	95.80 282	94.86 63	97.03 88	98.92 34

thisisatest0515		90.95 119	90.26 120	93.01 95	94.03 191	84.27 89	97.91 70	96.67 79	83.18 215	86.87 170	95.51 159	88.66 15	97.85 177	80.46 224	89.01 194	96.92 170

TESTMET0.1,1		89.83 139	89.34 140	91.31 174	92.54 238	80.19 186	97.11 138	96.57 95	86.15 133	86.85 171	91.83 248	79.32 90	96.95 231	81.30 219	92.35 167	96.77 176

testing3-2		91.37 105	91.01 105	92.44 121	95.93 118	83.77 96	98.83 31	97.45 16	86.88 123	86.63 172	94.69 191	84.57 40	97.75 181	89.65 140	84.44 242	95.80 204

PVSNet_Blended_VisFu		91.24 109	90.77 108	92.66 111	95.09 146	82.40 124	97.77 80	95.87 169	88.26 85	86.39 173	93.94 208	76.77 138	99.27 90	88.80 151	94.00 141	96.31 194

API-MVS		90.18 134	88.97 144	93.80 55	98.66 28	82.95 113	97.50 104	95.63 181	75.16 337	86.31 174	97.69 79	72.49 210	99.90 5	81.26 220	96.07 111	98.56 54

test-LLR		88.48 170	87.98 162	89.98 215	92.26 247	77.23 274	97.11 138	95.96 156	83.76 204	86.30 175	91.38 251	72.30 214	96.78 243	80.82 221	91.92 171	95.94 201

test-mter		88.95 154	88.60 152	89.98 215	92.26 247	77.23 274	97.11 138	95.96 156	85.32 152	86.30 175	91.38 251	76.37 147	96.78 243	80.82 221	91.92 171	95.94 201

PAPM_NR		91.46 102	90.82 107	93.37 82	98.50 40	81.81 139	95.03 265	96.13 142	84.65 172	86.10 177	97.65 85	79.24 93	99.75 40	83.20 206	96.88 93	98.56 54

FA-MVS(test-final)		87.71 191	86.23 200	92.17 138	94.19 180	80.55 173	87.16 374	96.07 148	82.12 240	85.98 178	88.35 295	72.04 218	98.49 141	80.26 227	89.87 185	97.48 137

RRT-MVS		89.67 142	88.67 150	92.67 110	94.44 172	81.08 155	94.34 280	94.45 254	86.05 137	85.79 179	92.39 234	63.39 278	98.16 160	93.22 88	93.95 143	98.76 41

MDTV_nov1_ep13_2view						81.74 141	86.80 376		80.65 261	85.65 180		74.26 189		76.52 267		96.98 165

ECVR-MVS		88.35 175	87.25 182	91.65 162	93.54 201	79.40 207	96.56 181	90.78 366	86.78 127	85.57 181	95.25 165	57.25 326	97.56 191	84.73 186	94.80 128	97.98 96

mmtdpeth		78.04 323	76.76 322	81.86 355	89.60 315	66.12 377	92.34 328	87.18 390	76.83 326	85.55 182	76.49 398	46.77 374	97.02 226	90.85 119	45.24 414	82.43 395

AUN-MVS		86.25 213	85.57 206	88.26 252	93.57 200	73.38 319	95.45 245	95.88 167	83.94 196	85.47 183	94.21 201	73.70 199	96.67 247	83.54 202	64.41 375	94.73 237

PVSNet	82.34 9	89.02 153	87.79 166	92.71 109	95.49 133	81.50 148	97.70 86	97.29 19	87.76 100	85.47 183	95.12 177	56.90 328	98.90 124	80.33 225	94.02 139	97.71 117

EPP-MVSNet		89.76 140	89.72 136	89.87 220	93.78 194	76.02 297	97.22 123	96.51 102	79.35 290	85.11 185	95.01 182	84.82 37	97.10 224	87.46 167	88.21 208	96.50 186

test1111		88.11 180	87.04 188	91.35 173	93.15 215	78.79 226	96.57 179	90.78 366	86.88 123	85.04 186	95.20 171	57.23 327	97.39 206	83.88 192	94.59 131	97.87 103

FE-MVS		86.06 215	84.15 232	91.78 156	94.33 177	79.81 194	84.58 392	96.61 88	76.69 327	85.00 187	87.38 309	70.71 234	98.37 150	70.39 319	91.70 174	97.17 159

OMC-MVS		88.80 161	88.16 160	90.72 194	95.30 139	77.92 254	94.81 270	94.51 248	86.80 126	84.97 188	96.85 125	67.53 249	98.60 134	85.08 182	87.62 214	95.63 209

CHOSEN 1792x2688		91.07 115	90.21 123	93.64 68	95.18 144	83.53 102	96.26 202	96.13 142	88.92 70	84.90 189	93.10 226	72.86 205	99.62 64	88.86 149	95.67 120	97.79 111

thres200		88.92 156	87.65 168	92.73 108	96.30 103	85.62 56	97.85 73	98.86 1	84.38 180	84.82 190	93.99 207	75.12 177	98.01 166	70.86 316	86.67 221	94.56 239

UWE-MVS		88.56 169	88.91 148	87.50 273	94.17 181	72.19 333	95.82 229	97.05 36	84.96 164	84.78 191	93.51 220	81.33 68	94.75 332	79.43 236	89.17 190	95.57 211

MDTV_nov1_ep13			83.69 236		94.09 187	81.01 157	86.78 377	96.09 145	83.81 202	84.75 192	84.32 359	74.44 188	96.54 250	63.88 351	85.07 240

CDS-MVSNet		89.50 145	88.96 145	91.14 182	91.94 266	80.93 161	97.09 142	95.81 171	84.26 186	84.72 193	94.20 202	80.31 77	95.64 295	83.37 205	88.96 195	96.85 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
ACMMP		90.39 130	89.97 130	91.64 163	97.58 74	78.21 244	96.78 168	96.72 73	84.73 169	84.72 193	97.23 108	71.22 226	99.63 62	88.37 158	92.41 166	97.08 163
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
CSCG		92.02 87	91.65 90	93.12 90	98.53 36	80.59 171	97.47 105	97.18 26	77.06 324	84.64 195	97.98 64	83.98 50	99.52 75	90.72 122	97.33 78	99.23 24

ab-mvs		87.08 197	84.94 219	93.48 79	93.34 210	83.67 99	88.82 357	95.70 177	81.18 251	84.55 196	90.14 273	62.72 281	98.94 122	85.49 180	82.54 261	97.85 105

EPMVS		87.47 195	85.90 203	92.18 137	95.41 135	82.26 127	87.00 375	96.28 129	85.88 142	84.23 197	85.57 342	75.07 178	96.26 260	71.14 314	92.50 164	98.03 88

Anonymous202405211		84.41 245	81.93 266	91.85 154	96.78 97	78.41 235	97.44 108	91.34 356	70.29 371	84.06 198	94.26 199	41.09 393	98.96 118	79.46 235	82.65 260	98.17 79

HyFIR lowres test		89.36 147	88.60 152	91.63 165	94.91 154	80.76 167	95.60 239	95.53 185	82.56 232	84.03 199	91.24 254	78.03 112	96.81 241	87.07 171	88.41 205	97.32 148

tfpn200view9		88.48 170	87.15 184	92.47 118	96.21 106	85.30 64	97.44 108	98.85 2	83.37 212	83.99 200	93.82 212	75.36 170	97.93 169	69.04 324	86.24 228	94.17 242

thres400		88.42 173	87.15 184	92.23 133	96.21 106	85.30 64	97.44 108	98.85 2	83.37 212	83.99 200	93.82 212	75.36 170	97.93 169	69.04 324	86.24 228	93.45 258

tpm		85.55 225	84.47 226	88.80 240	90.19 300	75.39 305	88.79 358	94.69 233	84.83 166	83.96 202	85.21 348	78.22 109	94.68 336	76.32 271	78.02 294	96.34 191

Fast-Effi-MVS+		87.93 185	86.94 191	90.92 187	94.04 189	79.16 215	98.26 49	93.72 300	81.29 250	83.94 203	92.90 227	69.83 239	96.68 246	76.70 265	91.74 173	96.93 168

XVG-OURS-SEG-HR		85.74 221	85.16 215	87.49 275	90.22 299	71.45 345	91.29 340	94.09 277	81.37 249	83.90 204	95.22 169	60.30 297	97.53 197	85.58 179	84.42 244	93.50 256

thisisatest0530		89.65 143	89.02 143	91.53 168	93.46 207	80.78 166	96.52 182	96.67 79	81.69 247	83.79 205	94.90 185	88.85 14	97.68 184	77.80 248	87.49 217	96.14 197

DeepC-MVS	86.58 3	91.53 101	91.06 103	92.94 99	94.52 165	81.89 134	95.95 219	95.98 154	90.76 47	83.76 206	96.76 130	73.24 203	99.71 50	91.67 110	96.96 90	97.22 154
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
IS-MVSNet		88.67 164	88.16 160	90.20 209	93.61 198	76.86 281	96.77 170	93.07 329	84.02 192	83.62 207	95.60 156	74.69 185	96.24 263	78.43 247	93.66 150	97.49 136

thres100view900		88.30 176	86.95 190	92.33 127	96.10 111	84.90 78	97.14 135	98.85 2	82.69 229	83.41 208	93.66 216	75.43 167	97.93 169	69.04 324	86.24 228	94.17 242

thres600view7		88.06 181	86.70 196	92.15 140	96.10 111	85.17 70	97.14 135	98.85 2	82.70 228	83.41 208	93.66 216	75.43 167	97.82 178	67.13 333	85.88 232	93.45 258

XVG-OURS		85.18 232	84.38 227	87.59 269	90.42 297	71.73 342	91.06 343	94.07 278	82.00 243	83.29 210	95.08 179	56.42 333	97.55 193	83.70 199	83.42 249	93.49 257

Vis-MVSNet (Re-imp)		88.88 158	88.87 149	88.91 237	93.89 192	74.43 313	96.93 157	94.19 271	84.39 179	83.22 211	95.67 153	78.24 108	94.70 334	78.88 243	94.40 136	97.61 126

TAMVS		88.48 170	87.79 166	90.56 198	91.09 282	79.18 214	96.45 188	95.88 167	83.64 209	83.12 212	93.33 221	75.94 155	95.74 290	82.40 213	88.27 207	96.75 179

baseline1		88.85 159	87.49 176	92.93 100	95.21 143	86.85 32	95.47 244	94.61 243	87.29 112	83.11 213	94.99 183	80.70 73	96.89 235	82.28 214	73.72 310	95.05 225

AdaColmap		88.81 160	87.61 172	92.39 124	99.33 4	79.95 191	96.70 175	95.58 182	77.51 316	83.05 214	96.69 134	61.90 290	99.72 48	84.29 188	93.47 152	97.50 135

PatchmatchNet		86.83 203	85.12 216	91.95 148	94.12 185	82.27 126	86.55 379	95.64 180	84.59 174	82.98 215	84.99 354	77.26 126	95.96 274	68.61 327	91.34 176	97.64 123
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
SCA		85.63 223	83.64 239	91.60 166	92.30 244	81.86 136	92.88 320	95.56 184	84.85 165	82.52 216	85.12 352	58.04 315	95.39 305	73.89 293	87.58 216	97.54 129

114514_t		88.79 162	87.57 174	92.45 119	98.21 53	81.74 141	96.99 147	95.45 193	75.16 337	82.48 217	95.69 152	68.59 244	98.50 140	80.33 225	95.18 125	97.10 162

PatchT		79.75 309	76.85 321	88.42 245	89.55 316	75.49 304	77.37 411	94.61 243	63.07 392	82.46 218	73.32 407	75.52 164	93.41 361	51.36 395	84.43 243	96.36 189

TR-MVS		86.30 211	84.93 220	90.42 202	94.63 160	77.58 267	96.57 179	93.82 291	80.30 272	82.42 219	95.16 174	58.74 308	97.55 193	74.88 283	87.82 212	96.13 198

HQP-NCC					92.08 258		97.63 89		90.52 51	82.30 220

ACMP_Plane					92.08 258		97.63 89		90.52 51	82.30 220

HQP4-MVS										82.30 220			97.32 209			91.13 270

HQP-MVS		87.91 186	87.55 175	88.98 236	92.08 258	78.48 231	97.63 89	94.80 228	90.52 51	82.30 220	94.56 193	65.40 266	97.32 209	87.67 165	83.01 253	91.13 270

CR-MVSNet		83.53 258	81.36 275	90.06 211	90.16 301	79.75 197	79.02 407	91.12 358	84.24 187	82.27 224	80.35 384	75.45 165	93.67 356	63.37 355	86.25 226	96.75 179

RPMNet		79.85 308	75.92 328	91.64 163	90.16 301	79.75 197	79.02 407	95.44 194	58.43 412	82.27 224	72.55 410	73.03 204	98.41 149	46.10 408	86.25 226	96.75 179

CVMVSNet		84.83 237	85.57 206	82.63 348	91.55 271	60.38 399	95.13 259	95.03 216	80.60 262	82.10 226	94.71 189	66.40 260	90.19 390	74.30 290	90.32 183	97.31 150

PLC	83.97 7	88.00 183	87.38 180	89.83 222	98.02 59	76.46 287	97.16 132	94.43 257	79.26 295	81.98 227	96.28 139	69.36 240	99.27 90	77.71 252	92.25 168	93.77 252
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
JIA-IIPM		79.00 318	77.20 317	84.40 330	89.74 311	64.06 385	75.30 415	95.44 194	62.15 396	81.90 228	59.08 419	78.92 97	95.59 299	66.51 340	85.78 234	93.54 255

Anonymous20240529		83.15 265	80.60 285	90.80 191	95.74 125	78.27 239	96.81 166	94.92 220	60.10 407	81.89 229	92.54 232	45.82 377	98.82 127	79.25 239	78.32 292	95.31 219

tttt0517		88.57 168	88.19 159	89.71 226	93.00 220	75.99 298	95.67 234	96.67 79	80.78 258	81.82 230	94.40 196	88.97 13	97.58 190	76.05 273	86.31 225	95.57 211

WB-MVSnew		84.08 250	83.51 243	85.80 302	91.34 276	76.69 285	95.62 238	96.27 130	81.77 245	81.81 231	92.81 228	58.23 312	94.70 334	66.66 336	87.06 218	85.99 370

BH-RMVSNet		86.84 202	85.28 211	91.49 170	95.35 138	80.26 183	96.95 155	92.21 341	82.86 225	81.77 232	95.46 161	59.34 304	97.64 186	69.79 322	93.81 146	96.57 185

HQP_MVS		87.50 194	87.09 187	88.74 241	91.86 267	77.96 251	97.18 128	94.69 233	89.89 60	81.33 233	94.15 203	64.77 271	97.30 211	87.08 169	82.82 257	90.96 272

plane_prior3						77.75 264			90.17 58	81.33 233

VPA-MVSNet		85.32 230	83.83 235	89.77 225	90.25 298	82.63 118	96.36 195	97.07 34	83.03 220	81.21 235	89.02 283	61.58 291	96.31 259	85.02 184	70.95 327	90.36 278

GeoE		86.36 209	85.20 212	89.83 222	93.17 214	76.13 292	97.53 100	92.11 342	79.58 287	80.99 236	94.01 206	66.60 259	96.17 266	73.48 297	89.30 189	97.20 158

GA-MVS		85.79 220	84.04 234	91.02 185	89.47 318	80.27 182	96.90 160	94.84 226	85.57 146	80.88 237	89.08 281	56.56 332	96.47 253	77.72 251	85.35 238	96.34 191

1112_ss		88.60 167	87.47 178	92.00 147	93.21 212	80.97 159	96.47 186	92.46 337	83.64 209	80.86 238	97.30 104	80.24 79	97.62 187	77.60 254	85.49 236	97.40 144

dp		84.30 247	82.31 260	90.28 206	94.24 179	77.97 250	86.57 378	95.53 185	79.94 281	80.75 239	85.16 350	71.49 225	96.39 255	63.73 352	83.36 250	96.48 187

Test_1112_low_res		88.03 182	86.73 194	91.94 149	93.15 215	80.88 163	96.44 189	92.41 339	83.59 211	80.74 240	91.16 255	80.18 80	97.59 189	77.48 257	85.40 237	97.36 147

cascas		86.50 207	84.48 225	92.55 117	92.64 235	85.95 42	97.04 146	95.07 214	75.32 335	80.50 241	91.02 257	54.33 346	97.98 168	86.79 173	87.62 214	93.71 253

TAPA-MVS	81.61 12	85.02 234	83.67 237	89.06 233	96.79 96	73.27 324	95.92 221	94.79 230	74.81 340	80.47 242	96.83 126	71.07 228	98.19 158	49.82 401	92.57 162	95.71 208
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
OPM-MVS		85.84 218	85.10 217	88.06 257	88.34 331	77.83 258	95.72 232	94.20 270	87.89 98	80.45 243	94.05 205	58.57 309	97.26 215	83.88 192	82.76 259	89.09 308
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
nrg030		86.79 204	85.43 208	90.87 190	88.76 323	85.34 61	97.06 145	94.33 263	84.31 181	80.45 243	91.98 243	72.36 211	96.36 257	88.48 156	71.13 325	90.93 274

EI-MVSNet		85.80 219	85.20 212	87.59 269	91.55 271	77.41 270	95.13 259	95.36 200	80.43 269	80.33 245	94.71 189	73.72 197	95.97 271	76.96 263	78.64 286	89.39 295

MVSTER		89.25 151	88.92 147	90.24 207	95.98 115	84.66 81	96.79 167	95.36 200	87.19 118	80.33 245	90.61 264	90.02 11	95.97 271	85.38 181	78.64 286	90.09 287

ADS-MVSNet2		79.57 312	77.53 315	85.71 306	93.78 194	72.13 334	79.48 403	86.11 398	73.09 355	80.14 247	79.99 387	62.15 285	90.14 391	59.49 368	83.52 247	94.85 230

ADS-MVSNet		81.26 294	78.36 308	89.96 217	93.78 194	79.78 195	79.48 403	93.60 305	73.09 355	80.14 247	79.99 387	62.15 285	95.24 314	59.49 368	83.52 247	94.85 230

test_fmvs2		79.59 311	79.90 297	78.67 373	82.86 387	55.82 410	95.20 255	89.55 374	81.09 252	80.12 249	89.80 275	34.31 408	93.51 359	87.82 162	78.36 291	86.69 359

baseline2		90.39 130	90.21 123	90.93 186	90.86 288	80.99 158	95.20 255	97.41 17	86.03 139	80.07 250	94.61 192	90.58 6	97.47 202	87.29 168	89.86 186	94.35 241

Effi-MVS+-dtu		84.61 241	84.90 221	83.72 338	91.96 264	63.14 390	94.95 266	93.34 318	85.57 146	79.79 251	87.12 315	61.99 288	95.61 298	83.55 201	85.83 233	92.41 265

VPNet		84.69 239	82.92 250	90.01 213	89.01 322	83.45 104	96.71 173	95.46 192	85.71 144	79.65 252	92.18 239	56.66 331	96.01 270	83.05 209	67.84 358	90.56 276

SDMVSNet		87.02 198	85.61 205	91.24 178	94.14 183	83.30 107	93.88 295	95.98 154	84.30 183	79.63 253	92.01 240	58.23 312	97.68 184	90.28 135	82.02 265	92.75 261

sd_testset		84.62 240	83.11 248	89.17 231	94.14 183	77.78 260	91.54 339	94.38 260	84.30 183	79.63 253	92.01 240	52.28 351	96.98 229	77.67 253	82.02 265	92.75 261

CLD-MVS		87.97 184	87.48 177	89.44 228	92.16 254	80.54 176	98.14 53	94.92 220	91.41 37	79.43 255	95.40 162	62.34 283	97.27 214	90.60 125	82.90 256	90.50 277
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
IB-MVS	85.34 4	88.67 164	87.14 186	93.26 84	93.12 218	84.32 86	98.76 32	97.27 21	87.19 118	79.36 256	90.45 266	83.92 52	98.53 139	84.41 187	69.79 338	96.93 168
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
PatchMatch-RL		85.00 235	83.66 238	89.02 235	95.86 120	74.55 312	92.49 324	93.60 305	79.30 293	79.29 257	91.47 249	58.53 310	98.45 146	70.22 320	92.17 170	94.07 247

mamv4		85.50 226	86.76 193	81.72 356	93.23 211	54.93 413	89.95 350	92.94 331	69.96 373	79.00 258	92.20 238	80.69 74	94.22 345	92.06 105	90.77 180	96.01 199

CNLPA		86.96 199	85.37 210	91.72 161	97.59 73	79.34 210	97.21 124	91.05 361	74.22 344	78.90 259	96.75 132	67.21 253	98.95 120	74.68 285	90.77 180	96.88 172

MVS		90.60 125	88.64 151	96.50 5	94.25 178	90.53 8	93.33 308	97.21 23	77.59 315	78.88 260	97.31 101	71.52 224	99.69 54	89.60 141	98.03 56	99.27 22

mvs_anonymous		88.68 163	87.62 171	91.86 152	94.80 157	81.69 144	93.53 304	94.92 220	82.03 242	78.87 261	90.43 267	75.77 157	95.34 308	85.04 183	93.16 157	98.55 56

UWE-MVS-28		85.41 229	86.36 198	82.59 349	91.12 281	66.81 374	93.88 295	97.03 37	83.86 200	78.55 262	93.84 211	77.76 119	88.55 395	73.47 298	87.69 213	92.41 265

tpm cat1		83.63 257	81.38 274	90.39 203	93.53 206	78.19 246	85.56 386	95.09 212	70.78 369	78.51 263	83.28 369	74.80 181	97.03 225	66.77 335	84.05 245	95.95 200

UniMVSNet (Re)		85.31 231	84.23 229	88.55 244	89.75 309	80.55 173	96.72 171	96.89 50	85.42 150	78.40 264	88.93 284	75.38 169	95.52 302	78.58 245	68.02 355	89.57 294

FIs		86.73 206	86.10 201	88.61 243	90.05 304	80.21 185	96.14 211	96.95 45	85.56 148	78.37 265	92.30 236	76.73 139	95.28 312	79.51 234	79.27 280	90.35 279

WBMVS		87.73 189	86.79 192	90.56 198	95.61 129	85.68 51	97.63 89	95.52 187	83.77 203	78.30 266	88.44 293	86.14 32	95.78 284	82.54 212	73.15 316	90.21 282

BH-w/o		88.24 178	87.47 178	90.54 200	95.03 151	78.54 230	97.41 113	93.82 291	84.08 190	78.23 267	94.51 195	69.34 241	97.21 216	80.21 229	94.58 132	95.87 203

MonoMVSNet		85.68 222	84.22 230	90.03 212	88.43 330	77.83 258	92.95 319	91.46 352	87.28 113	78.11 268	85.96 337	66.31 261	94.81 331	90.71 123	76.81 297	97.46 139

UniMVSNet_NR-MVSNet		85.49 227	84.59 222	88.21 255	89.44 319	79.36 208	96.71 173	96.41 114	85.22 155	78.11 268	90.98 259	76.97 134	95.14 319	79.14 240	68.30 352	90.12 285

DU-MVS		84.57 242	83.33 246	88.28 251	88.76 323	79.36 208	96.43 191	95.41 199	85.42 150	78.11 268	90.82 260	67.61 246	95.14 319	79.14 240	68.30 352	90.33 280

dmvs_re		84.10 249	82.90 251	87.70 264	91.41 275	73.28 322	90.59 346	93.19 322	85.02 161	77.96 271	93.68 215	57.92 320	96.18 265	75.50 278	80.87 269	93.63 254

miper_enhance_ethall		85.95 217	85.20 212	88.19 256	94.85 155	79.76 196	96.00 216	94.06 279	82.98 222	77.74 272	88.76 286	79.42 89	95.46 304	80.58 223	72.42 318	89.36 301

v1144		82.90 271	81.27 276	87.78 263	86.29 352	79.07 220	96.14 211	93.93 282	80.05 278	77.38 273	86.80 320	65.50 264	95.93 276	75.21 281	70.13 333	88.33 332

FC-MVSNet-test		85.96 216	85.39 209	87.66 266	89.38 320	78.02 248	95.65 236	96.87 52	85.12 159	77.34 274	91.94 246	76.28 149	94.74 333	77.09 260	78.82 284	90.21 282

v2v482		83.46 259	81.86 267	88.25 253	86.19 354	79.65 202	96.34 197	94.02 280	81.56 248	77.32 275	88.23 297	65.62 263	96.03 268	77.77 249	69.72 340	89.09 308

Baseline_NR-MVSNet		81.22 295	80.07 293	84.68 322	85.32 368	75.12 307	96.48 185	88.80 382	76.24 331	77.28 276	86.40 330	67.61 246	94.39 342	75.73 277	66.73 369	84.54 380

V42		83.04 268	81.53 272	87.57 271	86.27 353	79.09 219	95.87 225	94.11 276	80.35 271	77.22 277	86.79 321	65.32 268	96.02 269	77.74 250	70.14 332	87.61 345

v144192		82.43 277	80.73 282	87.54 272	85.81 361	78.22 241	95.98 217	93.78 296	79.09 298	77.11 278	86.49 325	64.66 273	95.91 277	74.20 291	69.42 341	88.49 326

ACMM	80.70 13	83.72 256	82.85 253	86.31 296	91.19 278	72.12 335	95.88 224	94.29 265	80.44 267	77.02 279	91.96 244	55.24 340	97.14 223	79.30 238	80.38 272	89.67 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
v1192		82.31 281	80.55 286	87.60 268	85.94 358	78.47 234	95.85 227	93.80 294	79.33 291	76.97 280	86.51 324	63.33 279	95.87 278	73.11 299	70.13 333	88.46 328

PCF-MVS	84.09 5	86.77 205	85.00 218	92.08 141	92.06 261	83.07 111	92.14 329	94.47 252	79.63 286	76.90 281	94.78 188	71.15 227	99.20 101	72.87 300	91.05 178	93.98 248
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
cl22		85.11 233	84.17 231	87.92 260	95.06 150	78.82 223	95.51 242	94.22 269	79.74 284	76.77 282	87.92 302	75.96 153	95.68 291	79.93 232	72.42 318	89.27 303

v1921920		82.02 284	80.23 290	87.41 276	85.62 362	77.92 254	95.79 231	93.69 301	78.86 302	76.67 283	86.44 327	62.50 282	95.83 280	72.69 301	69.77 339	88.47 327

WR-MVS		84.32 246	82.96 249	88.41 246	89.38 320	80.32 179	96.59 178	96.25 132	83.97 194	76.63 284	90.36 268	67.53 249	94.86 329	75.82 276	70.09 336	90.06 289

BH-untuned		86.95 200	85.94 202	89.99 214	94.52 165	77.46 269	96.78 168	93.37 317	81.80 244	76.62 285	93.81 214	66.64 258	97.02 226	76.06 272	93.88 145	95.48 215

SSC-MVS3.2		81.06 297	79.49 301	85.75 305	89.78 307	73.00 327	94.40 279	95.23 208	83.76 204	76.61 286	87.82 304	49.48 363	94.88 327	66.80 334	71.56 323	89.38 297

v1240		81.70 288	79.83 298	87.30 280	85.50 363	77.70 266	95.48 243	93.44 310	78.46 307	76.53 287	86.44 327	60.85 295	95.84 279	71.59 308	70.17 331	88.35 331

PS-MVSNAJss		84.91 236	84.30 228	86.74 287	85.89 360	74.40 314	94.95 266	94.16 273	83.93 197	76.45 288	90.11 274	71.04 229	95.77 285	83.16 207	79.02 283	90.06 289

miper_ehance_all_eth		84.57 242	83.60 241	87.50 273	92.64 235	78.25 240	95.40 248	93.47 309	79.28 294	76.41 289	87.64 306	76.53 142	95.24 314	78.58 245	72.42 318	89.01 313

LPG-MVS_test		84.20 248	83.49 244	86.33 293	90.88 285	73.06 325	95.28 249	94.13 274	82.20 237	76.31 290	93.20 222	54.83 344	96.95 231	83.72 197	80.83 270	88.98 314

LGP-MVS_train				86.33 293	90.88 285	73.06 325		94.13 274	82.20 237	76.31 290	93.20 222	54.83 344	96.95 231	83.72 197	80.83 270	88.98 314

F-COLMAP		84.50 244	83.44 245	87.67 265	95.22 142	72.22 331	95.95 219	93.78 296	75.74 332	76.30 292	95.18 173	59.50 302	98.45 146	72.67 302	86.59 223	92.35 267

tpmvs		83.04 268	80.77 281	89.84 221	95.43 134	77.96 251	85.59 385	95.32 204	75.31 336	76.27 293	83.70 365	73.89 194	97.41 204	59.53 367	81.93 267	94.14 244

tt0805		81.20 296	79.06 305	87.61 267	86.50 348	72.97 328	93.66 299	95.48 190	74.11 345	76.23 294	91.99 242	41.36 392	97.40 205	77.44 258	74.78 306	92.45 264

3Dnovator	82.32 10	89.33 148	87.64 169	94.42 37	93.73 197	85.70 49	97.73 84	96.75 69	86.73 130	76.21 295	95.93 145	62.17 284	99.68 56	81.67 218	97.81 63	97.88 101

TranMVSNet+NR-MVSNet		83.24 264	81.71 269	87.83 261	87.71 338	78.81 225	96.13 213	94.82 227	84.52 175	76.18 296	90.78 262	64.07 274	94.60 337	74.60 288	66.59 370	90.09 287

c3_l		83.80 254	82.65 256	87.25 281	92.10 257	77.74 265	95.25 252	93.04 330	78.58 305	76.01 297	87.21 314	75.25 175	95.11 321	77.54 256	68.89 346	88.91 319

1314		88.94 155	87.20 183	94.17 46	93.21 212	85.73 48	93.33 308	96.64 85	82.89 223	75.98 298	96.36 137	66.83 257	99.39 83	83.52 204	96.02 114	97.39 145

Fast-Effi-MVS+-dtu		83.33 261	82.60 257	85.50 311	89.55 316	69.38 360	96.09 214	91.38 353	82.30 236	75.96 299	91.41 250	56.71 329	95.58 300	75.13 282	84.90 241	91.54 268

XXY-MVS		83.84 253	82.00 265	89.35 229	87.13 343	81.38 149	95.72 232	94.26 266	80.15 276	75.92 300	90.63 263	61.96 289	96.52 251	78.98 242	73.28 315	90.14 284

GBi-Net		82.42 278	80.43 288	88.39 248	92.66 232	81.95 129	94.30 283	93.38 314	79.06 299	75.82 301	85.66 338	56.38 334	93.84 352	71.23 311	75.38 303	89.38 297

test1		82.42 278	80.43 288	88.39 248	92.66 232	81.95 129	94.30 283	93.38 314	79.06 299	75.82 301	85.66 338	56.38 334	93.84 352	71.23 311	75.38 303	89.38 297

FMVSNet3		84.71 238	82.71 255	90.70 195	94.55 163	87.71 23	95.92 221	94.67 236	81.73 246	75.82 301	88.08 300	66.99 254	94.47 340	71.23 311	75.38 303	89.91 291

eth_miper_zixun_eth		83.12 266	82.01 264	86.47 292	91.85 269	74.80 308	94.33 281	93.18 324	79.11 297	75.74 304	87.25 313	72.71 206	95.32 310	76.78 264	67.13 365	89.27 303

IterMVS-LS		83.93 252	82.80 254	87.31 279	91.46 274	77.39 271	95.66 235	93.43 312	80.44 267	75.51 305	87.26 312	73.72 197	95.16 318	76.99 261	70.72 329	89.39 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
3Dnovator+	82.88 8	89.63 144	87.85 164	94.99 23	94.49 171	86.76 34	97.84 74	95.74 175	86.10 135	75.47 306	96.02 144	65.00 270	99.51 77	82.91 210	97.07 87	98.72 47

test_djsdf		83.00 270	82.45 259	84.64 324	84.07 380	69.78 356	94.80 271	94.48 249	80.74 259	75.41 307	87.70 305	61.32 294	95.10 322	83.77 195	79.76 273	89.04 311

v148		82.41 280	80.89 279	86.99 285	86.18 355	76.81 282	96.27 201	93.82 291	80.49 266	75.28 308	86.11 336	67.32 252	95.75 287	75.48 279	67.03 367	88.42 330

QAPM		86.88 201	84.51 223	93.98 49	94.04 189	85.89 45	97.19 127	96.05 149	73.62 349	75.12 309	95.62 155	62.02 287	99.74 43	70.88 315	96.06 112	96.30 195

UniMVSNet_ETH3D		80.86 301	78.75 307	87.22 282	86.31 351	72.02 336	91.95 330	93.76 299	73.51 350	75.06 310	90.16 272	43.04 386	95.66 292	76.37 270	78.55 289	93.98 248

cl____		83.27 262	82.12 262	86.74 287	92.20 250	75.95 299	95.11 261	93.27 320	78.44 308	74.82 311	87.02 317	74.19 190	95.19 316	74.67 286	69.32 342	89.09 308

DIV-MVS_self_test		83.27 262	82.12 262	86.74 287	92.19 251	75.92 301	95.11 261	93.26 321	78.44 308	74.81 312	87.08 316	74.19 190	95.19 316	74.66 287	69.30 343	89.11 307

FMVSNet2		82.79 272	80.44 287	89.83 222	92.66 232	85.43 59	95.42 246	94.35 261	79.06 299	74.46 313	87.28 310	56.38 334	94.31 343	69.72 323	74.68 307	89.76 292

MIMVSNet		79.18 317	75.99 327	88.72 242	87.37 342	80.66 169	79.96 401	91.82 346	77.38 318	74.33 314	81.87 375	41.78 389	90.74 386	66.36 342	83.10 252	94.76 232

RPSCF		77.73 328	76.63 323	81.06 360	88.66 327	55.76 411	87.77 369	87.88 388	64.82 390	74.14 315	92.79 230	49.22 364	96.81 241	67.47 331	76.88 296	90.62 275

ACMP	81.66 11	84.00 251	83.22 247	86.33 293	91.53 273	72.95 329	95.91 223	93.79 295	83.70 207	73.79 316	92.22 237	54.31 347	96.89 235	83.98 191	79.74 275	89.16 306
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
reproduce_monomvs		87.80 187	87.60 173	88.40 247	96.56 98	80.26 183	95.80 230	96.32 127	91.56 36	73.60 317	88.36 294	88.53 16	96.25 262	90.47 127	67.23 364	88.67 321

pmmvs5		81.34 293	79.54 299	86.73 290	85.02 370	76.91 279	96.22 204	91.65 349	77.65 314	73.55 318	88.61 288	55.70 337	94.43 341	74.12 292	73.35 314	88.86 320

jajsoiax		82.12 283	81.15 278	85.03 318	84.19 378	70.70 349	94.22 287	93.95 281	83.07 218	73.48 319	89.75 276	49.66 362	95.37 307	82.24 215	79.76 273	89.02 312

Syy-MVS		77.97 326	78.05 311	77.74 377	92.13 255	56.85 406	93.97 291	94.23 267	82.43 233	73.39 320	93.57 218	57.95 318	87.86 399	32.40 420	82.34 262	88.51 324

myMVS_eth3d		81.93 285	82.18 261	81.18 359	92.13 255	67.18 369	93.97 291	94.23 267	82.43 233	73.39 320	93.57 218	76.98 133	87.86 399	50.53 399	82.34 262	88.51 324

mvs_tets		81.74 287	80.71 283	84.84 319	84.22 377	70.29 352	93.91 294	93.78 296	82.77 227	73.37 322	89.46 279	47.36 373	95.31 311	81.99 216	79.55 279	88.92 318

pmmvs4		82.54 276	80.79 280	87.79 262	86.11 356	80.49 178	93.55 303	93.18 324	77.29 319	73.35 323	89.40 280	65.26 269	95.05 325	75.32 280	73.61 311	87.83 340

LS3D		82.22 282	79.94 296	89.06 233	97.43 82	74.06 317	93.20 314	92.05 343	61.90 397	73.33 324	95.21 170	59.35 303	99.21 96	54.54 388	92.48 165	93.90 250

v10		81.43 292	79.53 300	87.11 283	86.38 349	78.87 222	94.31 282	93.43 312	77.88 311	73.24 325	85.26 346	65.44 265	95.75 287	72.14 305	67.71 359	86.72 358

v8		81.88 286	80.06 294	87.32 278	86.63 347	79.04 221	94.41 276	93.65 303	78.77 303	73.19 326	85.57 342	66.87 256	95.81 281	73.84 295	67.61 360	87.11 354

test0.0.03 1		82.79 272	82.48 258	83.74 337	86.81 346	72.22 331	96.52 182	95.03 216	83.76 204	73.00 327	93.20 222	72.30 214	88.88 393	64.15 350	77.52 295	90.12 285

anonymousdsp		80.98 300	79.97 295	84.01 332	81.73 390	70.44 351	92.49 324	93.58 307	77.10 323	72.98 328	86.31 331	57.58 321	94.90 326	79.32 237	78.63 288	86.69 359

XVG-ACMP-BASELINE		79.38 315	77.90 313	83.81 334	84.98 371	67.14 373	89.03 356	93.18 324	80.26 275	72.87 329	88.15 299	38.55 398	96.26 260	76.05 273	78.05 293	88.02 337

WR-MVS_H		81.02 298	80.09 291	83.79 335	88.08 334	71.26 348	94.46 274	96.54 98	80.08 277	72.81 330	86.82 319	70.36 236	92.65 365	64.18 349	67.50 361	87.46 351

OpenMVS	79.58 14	86.09 214	83.62 240	93.50 77	90.95 284	86.71 35	97.44 108	95.83 170	75.35 334	72.64 331	95.72 150	57.42 325	99.64 60	71.41 309	95.85 118	94.13 245

Anonymous20231211		79.72 310	77.19 318	87.33 277	95.59 131	77.16 277	95.18 258	94.18 272	59.31 410	72.57 332	86.20 334	47.89 370	95.66 292	74.53 289	69.24 344	89.18 305

CP-MVSNet		81.01 299	80.08 292	83.79 335	87.91 336	70.51 350	94.29 286	95.65 179	80.83 256	72.54 333	88.84 285	63.71 275	92.32 368	68.58 328	68.36 351	88.55 323

miper_lstm_enhance		81.66 290	80.66 284	84.67 323	91.19 278	71.97 338	91.94 331	93.19 322	77.86 312	72.27 334	85.26 346	73.46 200	93.42 360	73.71 296	67.05 366	88.61 322

PS-CasMVS		80.27 306	79.18 302	83.52 341	87.56 340	69.88 355	94.08 289	95.29 205	80.27 274	72.08 335	88.51 292	59.22 306	92.23 370	67.49 330	68.15 354	88.45 329

FMVSNet1		79.50 313	76.54 324	88.39 248	88.47 328	81.95 129	94.30 283	93.38 314	73.14 354	72.04 336	85.66 338	43.86 380	93.84 352	65.48 344	72.53 317	89.38 297

mvs5depth		71.40 364	68.36 369	80.54 364	75.31 413	65.56 379	79.94 402	85.14 401	69.11 378	71.75 337	81.59 376	41.02 394	93.94 350	60.90 365	50.46 404	82.10 397

PEN-MVS		79.47 314	78.26 310	83.08 344	86.36 350	68.58 363	93.85 297	94.77 231	79.76 283	71.37 338	88.55 289	59.79 298	92.46 366	64.50 348	65.40 372	88.19 334

testing3		80.74 302	81.17 277	79.44 369	91.15 280	63.48 388	97.16 132	95.76 173	80.83 256	71.36 339	93.15 225	78.22 109	87.30 404	43.19 412	79.67 276	87.55 349

Patchmtry		77.36 332	74.59 337	85.67 307	89.75 309	75.75 303	77.85 410	91.12 358	60.28 405	71.23 340	80.35 384	75.45 165	93.56 358	57.94 373	67.34 363	87.68 343

IterMVS		80.67 303	79.16 303	85.20 315	89.79 306	76.08 293	92.97 318	91.86 345	80.28 273	71.20 341	85.14 351	57.93 319	91.34 380	72.52 303	70.74 328	88.18 335
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		81.47 291	78.28 309	91.04 183	98.14 55	78.48 231	95.09 264	86.97 391	61.14 403	71.12 342	92.78 231	59.59 300	99.38 84	53.11 392	86.61 222	95.27 221

IterMVS-SCA-FT		80.51 305	79.10 304	84.73 321	89.63 314	74.66 309	92.98 317	91.81 347	80.05 278	71.06 343	85.18 349	58.04 315	91.40 379	72.48 304	70.70 330	88.12 336

v7n		79.32 316	77.34 316	85.28 314	84.05 381	72.89 330	93.38 306	93.87 288	75.02 339	70.68 344	84.37 358	59.58 301	95.62 297	67.60 329	67.50 361	87.32 353

MS-PatchMatch		83.05 267	81.82 268	86.72 291	89.64 313	79.10 218	94.88 268	94.59 245	79.70 285	70.67 345	89.65 277	50.43 358	96.82 240	70.82 318	95.99 116	84.25 383

DTE-MVSNet		78.37 320	77.06 319	82.32 352	85.22 369	67.17 372	93.40 305	93.66 302	78.71 304	70.53 346	88.29 296	59.06 307	92.23 370	61.38 362	63.28 381	87.56 347

pm-mvs1		80.05 307	78.02 312	86.15 298	85.42 364	75.81 302	95.11 261	92.69 336	77.13 321	70.36 347	87.43 308	58.44 311	95.27 313	71.36 310	64.25 377	87.36 352

D2MVS		82.67 274	81.55 271	86.04 300	87.77 337	76.47 286	95.21 254	96.58 94	82.66 230	70.26 348	85.46 345	60.39 296	95.80 282	76.40 269	79.18 281	85.83 373

PVSNet_0	77.72 15	81.70 288	78.95 306	89.94 218	90.77 291	76.72 284	95.96 218	96.95 45	85.01 162	70.24 349	88.53 291	52.32 350	98.20 157	86.68 174	44.08 417	94.89 228

CL-MVSNet_self_test		75.81 341	74.14 343	80.83 362	78.33 401	67.79 366	94.22 287	93.52 308	77.28 320	69.82 350	81.54 378	61.47 293	89.22 392	57.59 376	53.51 398	85.48 375

tfpnnormal		78.14 322	75.42 330	86.31 296	88.33 332	79.24 211	94.41 276	96.22 135	73.51 350	69.81 351	85.52 344	55.43 338	95.75 287	47.65 406	67.86 357	83.95 386

EU-MVSNet		76.92 336	76.95 320	76.83 382	84.10 379	54.73 414	91.77 334	92.71 335	72.74 358	69.57 352	88.69 287	58.03 317	87.43 403	64.91 347	70.00 337	88.33 332

ITE_SJBPF				82.38 350	87.00 344	65.59 378		89.55 374	79.99 280	69.37 353	91.30 253	41.60 391	95.33 309	62.86 357	74.63 308	86.24 365

DSMNet-mixed		73.13 355	72.45 350	75.19 388	77.51 404	46.82 419	85.09 390	82.01 412	67.61 385	69.27 354	81.33 379	50.89 355	86.28 406	54.54 388	83.80 246	92.46 263

MVP-Stereo		82.65 275	81.67 270	85.59 310	86.10 357	78.29 238	93.33 308	92.82 333	77.75 313	69.17 355	87.98 301	59.28 305	95.76 286	71.77 306	96.88 93	82.73 391
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
MSDG		80.62 304	77.77 314	89.14 232	93.43 208	77.24 273	91.89 332	90.18 370	69.86 375	68.02 356	91.94 246	52.21 352	98.84 126	59.32 370	83.12 251	91.35 269

NR-MVSNet		83.35 260	81.52 273	88.84 238	88.76 323	81.31 151	94.45 275	95.16 210	84.65 172	67.81 357	90.82 260	70.36 236	94.87 328	74.75 284	66.89 368	90.33 280

TransMVSNet (Re)		76.94 335	74.38 339	84.62 325	85.92 359	75.25 306	95.28 249	89.18 379	73.88 348	67.22 358	86.46 326	59.64 299	94.10 347	59.24 371	52.57 402	84.50 381

Anonymous20231206		75.29 344	73.64 345	80.22 365	80.75 391	63.38 389	93.36 307	90.71 368	73.09 355	67.12 359	83.70 365	50.33 359	90.85 385	53.63 391	70.10 335	86.44 362

ppachtmachnet_test		77.19 333	74.22 341	86.13 299	85.39 365	78.22 241	93.98 290	91.36 355	71.74 365	67.11 360	84.87 355	56.67 330	93.37 362	52.21 393	64.59 374	86.80 357

KD-MVS_2432*1600		77.63 329	74.92 334	85.77 303	90.86 288	79.44 205	88.08 365	93.92 284	76.26 329	67.05 361	82.78 371	72.15 216	91.92 373	61.53 359	41.62 420	85.94 371

miper_refine_blended		77.63 329	74.92 334	85.77 303	90.86 288	79.44 205	88.08 365	93.92 284	76.26 329	67.05 361	82.78 371	72.15 216	91.92 373	61.53 359	41.62 420	85.94 371

Patchmatch-test		78.25 321	74.72 336	88.83 239	91.20 277	74.10 316	73.91 418	88.70 385	59.89 408	66.82 363	85.12 352	78.38 106	94.54 338	48.84 404	79.58 278	97.86 104

test_fmvs3		69.56 368	69.19 366	70.67 392	69.01 418	47.05 418	90.87 344	86.81 393	71.31 368	66.79 364	77.15 395	16.40 423	83.17 414	81.84 217	62.51 383	81.79 401

LTVRE_ROB	73.68 18	77.99 324	75.74 329	84.74 320	90.45 296	72.02 336	86.41 380	91.12 358	72.57 360	66.63 365	87.27 311	54.95 343	96.98 229	56.29 382	75.98 298	85.21 377
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
OurMVSNet-221017-0		77.18 334	76.06 326	80.55 363	83.78 384	60.00 401	90.35 347	91.05 361	77.01 325	66.62 366	87.92 302	47.73 371	94.03 348	71.63 307	68.44 350	87.62 344

testgi		74.88 346	73.40 346	79.32 370	80.13 395	61.75 394	93.21 313	86.64 396	79.49 289	66.56 367	91.06 256	35.51 406	88.67 394	56.79 381	71.25 324	87.56 347

LCM-MVSNet-Re		83.75 255	83.54 242	84.39 331	93.54 201	64.14 384	92.51 323	84.03 407	83.90 198	66.14 368	86.59 323	67.36 251	92.68 364	84.89 185	92.87 159	96.35 190

pmmvs6		74.65 347	71.67 354	83.60 340	79.13 398	69.94 354	93.31 311	90.88 365	61.05 404	65.83 369	84.15 361	43.43 382	94.83 330	66.62 337	60.63 386	86.02 369

our_test_3		77.90 327	75.37 331	85.48 312	85.39 365	76.74 283	93.63 300	91.67 348	73.39 353	65.72 370	84.65 357	58.20 314	93.13 363	57.82 374	67.87 356	86.57 361

ttmdpeth		69.58 367	66.92 373	77.54 379	75.95 412	62.40 392	88.09 364	84.32 406	62.87 394	65.70 371	86.25 333	36.53 401	88.53 396	55.65 386	46.96 413	81.70 402

COLMAP_ROB	73.24 19	75.74 342	73.00 349	83.94 333	92.38 239	69.08 361	91.85 333	86.93 392	61.48 400	65.32 372	90.27 269	42.27 388	96.93 234	50.91 397	75.63 302	85.80 374
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
FMVSNet5		76.46 338	74.16 342	83.35 343	90.05 304	76.17 291	89.58 352	89.85 372	71.39 367	65.29 373	80.42 383	50.61 357	87.70 402	61.05 364	69.24 344	86.18 366

ACMH+	76.62 16	77.47 331	74.94 333	85.05 317	91.07 283	71.58 344	93.26 312	90.01 371	71.80 364	64.76 374	88.55 289	41.62 390	96.48 252	62.35 358	71.00 326	87.09 355

Patchmatch-RL test		76.65 337	74.01 344	84.55 326	77.37 405	64.23 383	78.49 409	82.84 411	78.48 306	64.63 375	73.40 406	76.05 152	91.70 378	76.99 261	57.84 390	97.72 115

SixPastTwentyTwo		76.04 339	74.32 340	81.22 358	84.54 374	61.43 397	91.16 341	89.30 378	77.89 310	64.04 376	86.31 331	48.23 365	94.29 344	63.54 354	63.84 379	87.93 339

AllTest		75.92 340	73.06 348	84.47 327	92.18 252	67.29 367	91.07 342	84.43 404	67.63 381	63.48 377	90.18 270	38.20 399	97.16 219	57.04 378	73.37 312	88.97 316

TestCases				84.47 327	92.18 252	67.29 367		84.43 404	67.63 381	63.48 377	90.18 270	38.20 399	97.16 219	57.04 378	73.37 312	88.97 316

ACMH	75.40 17	77.99 324	74.96 332	87.10 284	90.67 292	76.41 288	93.19 315	91.64 350	72.47 361	63.44 379	87.61 307	43.34 383	97.16 219	58.34 372	73.94 309	87.72 341
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ET-MVSNet_ETH3D		90.01 136	89.03 142	92.95 98	94.38 175	86.77 33	98.14 53	96.31 128	89.30 67	63.33 380	96.72 133	90.09 10	93.63 357	90.70 124	82.29 264	98.46 59

USDC		78.65 319	76.25 325	85.85 301	87.58 339	74.60 311	89.58 352	90.58 369	84.05 191	63.13 381	88.23 297	40.69 397	96.86 239	66.57 339	75.81 301	86.09 368

LF4IMVS		72.36 359	70.82 357	76.95 381	79.18 397	56.33 407	86.12 382	86.11 398	69.30 377	63.06 382	86.66 322	33.03 410	92.25 369	65.33 345	68.64 348	82.28 396

dmvs_testset		72.00 362	73.36 347	67.91 394	83.83 383	31.90 434	85.30 388	77.12 419	82.80 226	63.05 383	92.46 233	61.54 292	82.55 416	42.22 415	71.89 322	89.29 302

KD-MVS_self_test		70.97 366	69.31 365	75.95 387	76.24 411	55.39 412	87.45 370	90.94 364	70.20 372	62.96 384	77.48 394	44.01 379	88.09 397	61.25 363	53.26 399	84.37 382

Anonymous20240521		72.06 361	69.91 362	78.50 375	77.11 406	61.67 396	91.62 338	90.97 363	65.52 388	62.37 385	79.05 390	36.32 402	90.96 384	57.75 375	68.52 349	82.87 388

test_0402		72.68 357	69.54 364	82.09 353	88.67 326	71.81 341	92.72 322	86.77 395	61.52 399	62.21 386	83.91 363	43.22 384	93.76 355	34.60 418	72.23 321	80.72 405

OpenMVS_ROB	68.52 20	73.02 356	69.57 363	83.37 342	80.54 394	71.82 340	93.60 302	88.22 386	62.37 395	61.98 387	83.15 370	35.31 407	95.47 303	45.08 410	75.88 300	82.82 389

MVS-HIRNet		71.36 365	67.00 371	84.46 329	90.58 293	69.74 357	79.15 406	87.74 389	46.09 418	61.96 388	50.50 422	45.14 378	95.64 295	53.74 390	88.11 209	88.00 338

test20.03		72.36 359	71.15 356	75.98 386	77.79 402	59.16 403	92.40 326	89.35 377	74.09 346	61.50 389	84.32 359	48.09 366	85.54 409	50.63 398	62.15 384	83.24 387

mvsany_test3		67.19 375	65.34 377	72.72 390	63.08 424	48.57 417	83.12 397	78.09 418	72.07 362	61.21 390	77.11 396	22.94 418	87.78 401	78.59 244	51.88 403	81.80 400

PM-MVS		69.32 371	66.93 372	76.49 383	73.60 415	55.84 409	85.91 383	79.32 417	74.72 341	61.09 391	78.18 392	21.76 419	91.10 383	70.86 316	56.90 392	82.51 392

TDRefinement		69.20 372	65.78 376	79.48 368	66.04 423	62.21 393	88.21 362	86.12 397	62.92 393	61.03 392	85.61 341	33.23 409	94.16 346	55.82 385	53.02 400	82.08 398

ambc				76.02 385	68.11 420	51.43 415	64.97 423	89.59 373		60.49 393	74.49 403	17.17 422	92.46 366	61.50 361	52.85 401	84.17 384

pmmvs-eth3d		73.59 350	70.66 358	82.38 350	76.40 409	73.38 319	89.39 355	89.43 376	72.69 359	60.34 394	77.79 393	46.43 376	91.26 382	66.42 341	57.06 391	82.51 392

test_vis1_rt		73.96 348	72.40 351	78.64 374	83.91 382	61.16 398	95.63 237	68.18 427	76.32 328	60.09 395	74.77 401	29.01 416	97.54 195	87.74 163	75.94 299	77.22 410

kuosan		73.55 351	72.39 352	77.01 380	89.68 312	66.72 375	85.24 389	93.44 310	67.76 380	60.04 396	83.40 368	71.90 219	84.25 411	45.34 409	54.75 393	80.06 406

K. test v3		73.62 349	71.59 355	79.69 367	82.98 386	59.85 402	90.85 345	88.83 381	77.13 321	58.90 397	82.11 373	43.62 381	91.72 377	65.83 343	54.10 397	87.50 350

EG-PatchMatch MVS		74.92 345	72.02 353	83.62 339	83.76 385	73.28 322	93.62 301	92.04 344	68.57 379	58.88 398	83.80 364	31.87 412	95.57 301	56.97 380	78.67 285	82.00 399

lessismore_v0				79.98 366	80.59 393	58.34 405		80.87 413		58.49 399	83.46 367	43.10 385	93.89 351	63.11 356	48.68 407	87.72 341

N_pmnet		61.30 380	60.20 383	64.60 399	84.32 376	17.00 440	91.67 337	10.98 438	61.77 398	58.45 400	78.55 391	49.89 361	91.83 376	42.27 414	63.94 378	84.97 378

TinyColmap		72.41 358	68.99 367	82.68 347	88.11 333	69.59 358	88.41 361	85.20 400	65.55 387	57.91 401	84.82 356	30.80 414	95.94 275	51.38 394	68.70 347	82.49 394

UnsupCasMVSNet_eth		73.25 354	70.57 359	81.30 357	77.53 403	66.33 376	87.24 373	93.89 287	80.38 270	57.90 402	81.59 376	42.91 387	90.56 387	65.18 346	48.51 408	87.01 356

MIMVSNet1		69.44 370	66.65 374	77.84 376	76.48 408	62.84 391	87.42 371	88.97 380	66.96 386	57.75 403	79.72 389	32.77 411	85.83 408	46.32 407	63.42 380	84.85 379

pmmvs3		65.75 378	62.18 381	76.45 384	67.12 422	64.54 381	88.68 359	85.05 402	54.77 416	57.54 404	73.79 404	29.40 415	86.21 407	55.49 387	47.77 411	78.62 408

dongtai		69.47 369	68.98 368	70.93 391	86.87 345	58.45 404	88.19 363	93.18 324	63.98 391	56.04 405	80.17 386	70.97 232	79.24 418	33.46 419	47.94 410	75.09 412

test_f		64.01 379	62.13 382	69.65 393	63.00 425	45.30 424	83.66 396	80.68 414	61.30 401	55.70 406	72.62 409	14.23 425	84.64 410	69.84 321	58.11 389	79.00 407

new-patchmatchnet		68.85 373	65.93 375	77.61 378	73.57 416	63.94 386	90.11 349	88.73 384	71.62 366	55.08 407	73.60 405	40.84 395	87.22 405	51.35 396	48.49 409	81.67 403

UnsupCasMVSNet_bld		68.60 374	64.50 378	80.92 361	74.63 414	67.80 365	83.97 394	92.94 331	65.12 389	54.63 408	68.23 415	35.97 404	92.17 372	60.13 366	44.83 415	82.78 390

CMPMVS	54.94 21	75.71 343	74.56 338	79.17 371	79.69 396	55.98 408	89.59 351	93.30 319	60.28 405	53.85 409	89.07 282	47.68 372	96.33 258	76.55 266	81.02 268	85.22 376
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
new_pmnet		66.18 377	63.18 379	75.18 389	76.27 410	61.74 395	83.79 395	84.66 403	56.64 414	51.57 410	71.85 413	31.29 413	87.93 398	49.98 400	62.55 382	75.86 411

test_method		56.77 382	54.53 386	63.49 401	76.49 407	40.70 427	75.68 414	74.24 421	19.47 429	48.73 411	71.89 412	19.31 420	65.80 429	57.46 377	47.51 412	83.97 385

MVStest1		66.93 376	63.01 380	78.69 372	78.56 399	71.43 346	85.51 387	86.81 393	49.79 417	48.57 412	84.15 361	53.46 348	83.31 412	43.14 413	37.15 423	81.34 404

YYNet1		73.53 353	70.43 360	82.85 346	84.52 375	71.73 342	91.69 336	91.37 354	67.63 381	46.79 413	81.21 380	55.04 342	90.43 388	55.93 383	59.70 388	86.38 363

MDA-MVSNet_test_wron		73.54 352	70.43 360	82.86 345	84.55 373	71.85 339	91.74 335	91.32 357	67.63 381	46.73 414	81.09 381	55.11 341	90.42 389	55.91 384	59.76 387	86.31 364

WB-MVS		57.26 381	56.22 384	60.39 405	69.29 417	35.91 432	86.39 381	70.06 425	59.84 409	46.46 415	72.71 408	51.18 354	78.11 419	15.19 429	34.89 424	67.14 418

SSC-MVS		56.01 384	54.96 385	59.17 406	68.42 419	34.13 433	84.98 391	69.23 426	58.08 413	45.36 416	71.67 414	50.30 360	77.46 420	14.28 430	32.33 425	65.91 419

MDA-MVSNet-bldmvs		71.45 363	67.94 370	81.98 354	85.33 367	68.50 364	92.35 327	88.76 383	70.40 370	42.99 417	81.96 374	46.57 375	91.31 381	48.75 405	54.39 396	86.11 367

APD_test1		56.56 383	53.58 387	65.50 396	67.93 421	46.51 421	77.24 413	72.95 422	38.09 420	42.75 418	75.17 400	13.38 426	82.78 415	40.19 416	54.53 395	67.23 417

DeepMVS_CX				64.06 400	78.53 400	43.26 425		68.11 429	69.94 374	38.55 419	76.14 399	18.53 421	79.34 417	43.72 411	41.62 420	69.57 415

LCM-MVSNet		52.52 387	48.24 390	65.35 397	47.63 434	41.45 426	72.55 419	83.62 409	31.75 422	37.66 420	57.92 420	9.19 432	76.76 422	49.26 402	44.60 416	77.84 409

test_vis3_rt		54.10 386	51.04 389	63.27 402	58.16 426	46.08 423	84.17 393	49.32 437	56.48 415	36.56 421	49.48 424	8.03 433	91.91 375	67.29 332	49.87 405	51.82 423

FPMVS		55.09 385	52.93 388	61.57 403	55.98 427	40.51 428	83.11 398	83.41 410	37.61 421	34.95 422	71.95 411	14.40 424	76.95 421	29.81 421	65.16 373	67.25 416

PMMVS2		50.90 389	46.31 392	64.67 398	55.53 428	46.67 420	77.30 412	71.02 424	40.89 419	34.16 423	59.32 418	9.83 431	76.14 424	40.09 417	28.63 426	71.21 413

testf1		45.70 391	42.41 393	55.58 407	53.29 431	40.02 429	68.96 421	62.67 431	27.45 424	29.85 424	61.58 416	5.98 434	73.83 426	28.49 424	43.46 418	52.90 421

APD_test2		45.70 391	42.41 393	55.58 407	53.29 431	40.02 429	68.96 421	62.67 431	27.45 424	29.85 424	61.58 416	5.98 434	73.83 426	28.49 424	43.46 418	52.90 421

tmp_tt		41.54 394	41.93 396	40.38 412	20.10 438	26.84 436	61.93 424	59.09 433	14.81 431	28.51 426	80.58 382	35.53 405	48.33 433	63.70 353	13.11 430	45.96 426

Gipuma		45.11 393	42.05 395	54.30 409	80.69 392	51.30 416	35.80 427	83.81 408	28.13 423	27.94 427	34.53 427	11.41 430	76.70 423	21.45 426	54.65 394	34.90 427
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
ANet_high		46.22 390	41.28 397	61.04 404	39.91 436	46.25 422	70.59 420	76.18 420	58.87 411	23.09 428	48.00 425	12.58 428	66.54 428	28.65 423	13.62 429	70.35 414

MVE	35.65 22	33.85 396	29.49 401	46.92 411	41.86 435	36.28 431	50.45 426	56.52 434	18.75 430	18.28 429	37.84 426	2.41 437	58.41 430	18.71 427	20.62 427	46.06 425
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	34.80 23	39.19 395	35.53 398	50.18 410	29.72 437	30.30 435	59.60 425	66.20 430	26.06 426	17.91 430	49.53 423	3.12 436	74.09 425	18.19 428	49.40 406	46.14 424
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		32.70 397	32.39 399	33.65 413	53.35 430	25.70 437	74.07 417	53.33 435	21.08 427	17.17 431	33.63 429	11.85 429	54.84 431	12.98 431	14.04 428	20.42 428

EMVS		31.70 398	31.45 400	32.48 414	50.72 433	23.95 438	74.78 416	52.30 436	20.36 428	16.08 432	31.48 430	12.80 427	53.60 432	11.39 432	13.10 431	19.88 429

wuyk23d		14.10 400	13.89 403	14.72 415	55.23 429	22.91 439	33.83 428	3.56 439	4.94 432	4.11 433	2.28 435	2.06 438	19.66 434	10.23 433	8.74 432	1.59 432

testmvs		9.92 401	12.94 404	0.84 417	0.65 439	0.29 442	93.78 298	0.39 440	0.42 433	2.85 434	15.84 433	0.17 440	0.30 436	2.18 434	0.21 433	1.91 431

test123		9.07 402	11.73 405	1.11 416	0.50 440	0.77 441	89.44 354	0.20 441	0.34 434	2.15 435	10.72 434	0.34 439	0.32 435	1.79 435	0.08 434	2.23 430

EGC-MVSNET		52.46 388	47.56 391	67.15 395	81.98 389	60.11 400	82.54 399	72.44 423	0.11 435	0.70 436	74.59 402	25.11 417	83.26 413	29.04 422	61.51 385	58.09 420

mmdepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

monomultidepth		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

test_blank		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet_test		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

DCPMVS		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

cdsmvs_eth3d_5k		21.43 399	28.57 402	0.00 418	0.00 441	0.00 443	0.00 429	95.93 162	0.00 436	0.00 437	97.66 81	63.57 276	0.00 437	0.00 436	0.00 435	0.00 433

pcd_1.5k_mvsjas		5.92 404	7.89 407	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	71.04 229	0.00 437	0.00 436	0.00 435	0.00 433

sosnet-low-res		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

sosnet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uncertanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

Regformer		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

ab-mvs-re		8.11 403	10.81 406	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	97.30 104	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

uanet		0.00 405	0.00 408	0.00 418	0.00 441	0.00 443	0.00 429	0.00 442	0.00 436	0.00 437	0.00 436	0.00 441	0.00 437	0.00 436	0.00 435	0.00 433

WAC-MVS						67.18 369								49.00 403

MSC_two_6792asdad				97.14 3	99.05 9	92.19 4		96.83 56					99.81 22	98.08 20	98.81 24	99.43 11

No_MVS				97.14 3	99.05 9	92.19 4		96.83 56					99.81 22	98.08 20	98.81 24	99.43 11

eth-test2					0.00 441

eth-test					0.00 441

OPU-MVS				97.30 2	99.19 7	92.31 3	99.12 13				98.54 21	92.06 3	99.84 13	99.11 3	99.37 1	99.74 1

save fliter					98.24 51	83.34 106	98.61 40	96.57 95	91.32 38

test_0728_SECOND				95.14 20	99.04 14	86.14 39	99.06 18	96.77 65					99.84 13	97.90 23	98.85 21	99.45 10

GSMVS																97.54 129

sam_mvs1												77.59 120				97.54 129

sam_mvs												75.35 172

MTGPA								96.33 125

test_post1							85.88 384				30.24 431	73.77 195	95.07 324	73.89 293

test_post											33.80 428	76.17 150	95.97 271

patchmatchnet-post											77.09 397	77.78 118	95.39 305

MTMP							97.53 100	68.16 428

gm-plane-assit					92.27 246	79.64 203			84.47 178		95.15 175		97.93 169	85.81 177

test9_res														96.00 46	99.03 13	98.31 69

agg_prior2														94.30 70	99.00 15	98.57 53

test_prior4						82.34 125	97.75 83

test_prior				93.09 92	98.68 26	81.91 133		96.40 116					99.06 113			98.29 71

新几何2							96.42 192

旧先验1					97.39 86	79.58 204		96.54 98			98.08 57	84.00 49			97.42 76	97.62 125

无先验							96.87 161	96.78 59	77.39 317				99.52 75	79.95 231		98.43 62

原ACMM2							96.84 162

testdata2													99.48 79	76.45 268

segment_acmp												82.69 63

testdata1							95.57 241		87.44 108

plane_prior7					91.86 267	77.55 268

plane_prior6					91.98 263	77.92 254						64.77 271

plane_prior5								94.69 233					97.30 211	87.08 169	82.82 257	90.96 272

plane_prior4											94.15 203

plane_prior2							97.18 128		89.89 60

plane_prior1					91.95 265

plane_prior						77.96 251	97.52 103		90.36 56						82.96 255

n2								0.00 442

nn								0.00 442

door-mid								79.75 416

test11								96.50 104

door								80.13 415

HQP5-MVS						78.48 231

BP-MVS														87.67 165

HQP3-MVS								94.80 228							83.01 253

HQP2-MVS												65.40 266

NP-MVS					92.04 262	78.22 241					94.56 193

ACMMP++_ref															78.45 290

ACMMP++															79.05 282

Test By Simon												71.65 222

High-resolution multi-view benchmark