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_l_conf0.5_n		97.65 14	97.72 12	97.41 51	97.51 128	92.78 94	99.85 9	98.05 47	96.78 12	99.60 1	99.23 29	90.42 52	99.92 43	99.55 13	98.50 110	99.55 78

fmvsm_l_conf0.5_n_a		97.70 13	97.80 11	97.42 50	97.59 123	92.91 92	99.86 6	98.04 49	96.70 14	99.58 2	99.26 24	90.90 41	99.94 35	99.57 12	98.66 104	99.40 94

IU-MVS					99.63 18	95.38 24		97.73 85	95.54 30	99.54 3				99.69 7	99.81 23	99.99 1

fmvsm_s_conf0.5_n_3		96.58 44	96.55 40	96.66 93	97.23 143	92.59 99	99.81 14	97.82 67	97.35 4	99.42 4	99.16 40	80.27 222	99.93 40	99.26 18	98.60 106	97.45 216

PC_three_1452									94.60 41	99.41 5	99.12 51	95.50 7	99.96 28	99.84 2	99.92 3	99.97 7

CNVR-MVS		98.46 1	98.38 1	98.72 10	99.80 4	96.19 15	99.80 19	97.99 53	97.05 9	99.41 5	99.59 2	92.89 26	100.00 1	98.99 29	99.90 7	99.96 10

fmvsm_l_conf0.5_n_3		97.12 25	96.89 27	97.79 39	97.39 133	93.84 68	99.87 5	97.70 91	97.34 5	99.39 7	99.20 32	82.86 184	99.94 35	99.21 22	99.07 80	99.58 77

patch_mono-2		97.10 27	97.97 8	94.49 191	99.21 61	83.73 307	99.62 43	98.25 32	95.28 34	99.38 8	98.91 81	92.28 31	99.94 35	99.61 10	99.22 74	99.78 41

test0726					99.66 12	95.20 32	99.77 22	97.70 91	93.95 53	99.35 9	99.54 3	93.18 23

SED-MVS		98.18 2	98.10 4	98.41 18	99.63 18	95.24 27	99.77 22	97.72 86	94.17 48	99.30 10	99.54 3	93.32 20	99.98 9	99.70 5	99.81 23	99.99 1

test_241102_ONE					99.63 18	95.24 27		97.72 86	94.16 50	99.30 10	99.49 9	93.32 20	99.98 9

DVP-MVS++		98.18 2	98.09 5	98.44 16	99.61 24	95.38 24	99.55 49	97.68 97	93.01 78	99.23 12	99.45 14	95.12 8	99.98 9	99.25 20	99.92 3	99.97 7

test_241102_TWO								97.72 86	94.17 48	99.23 12	99.54 3	93.14 25	99.98 9	99.70 5	99.82 19	99.99 1

fmvsm_s_conf0.5_n_2		95.85 70	95.83 65	95.91 137	97.19 147	91.79 110	99.78 21	97.65 109	97.23 6	99.22 14	99.06 58	75.93 252	99.90 52	99.30 16	97.09 146	96.02 255

SMA-MVS		97.24 20	96.99 24	98.00 31	99.30 54	94.20 61	99.16 104	97.65 109	89.55 172	99.22 14	99.52 8	90.34 55	99.99 5	98.32 51	99.83 15	99.82 32
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_s_conf0.5_n_a		95.97 64	96.19 50	95.31 161	96.51 178	89.01 186	99.81 14	98.39 27	95.46 32	99.19 16	99.16 40	81.44 214	99.91 48	98.83 32	96.97 147	97.01 232

test_fmvsm_n_1920		97.08 28	97.55 14	95.67 147	97.94 110	89.61 173	99.93 1	98.48 23	97.08 8	99.08 17	99.13 49	88.17 84	99.93 40	99.11 26	99.06 81	97.47 215

DVP-MVS		98.07 7	98.00 6	98.29 19	99.66 12	95.20 32	99.72 28	97.47 149	93.95 53	99.07 18	99.46 10	93.18 23	99.97 21	99.64 8	99.82 19	99.69 58
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									93.01 78	99.07 18	99.46 10	94.66 13	99.97 21	99.25 20	99.82 19	99.95 15

TSAR-MVS + MP.		97.44 18	97.46 17	97.39 53	99.12 65	93.49 76	98.52 185	97.50 144	94.46 43	98.99 20	98.64 106	91.58 33	99.08 155	98.49 44	99.83 15	99.60 73
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.1_n_a		95.16 96	95.15 88	95.18 166	92.06 322	88.94 190	99.29 87	97.53 135	94.46 43	98.98 21	98.99 66	79.99 224	99.85 71	98.24 55	96.86 150	96.73 237

PS-MVSNAJ		96.87 32	96.40 45	98.29 19	97.35 136	97.29 5	99.03 127	97.11 191	95.83 24	98.97 22	99.14 47	82.48 195	99.60 110	98.60 37	99.08 78	98.00 201

旧先验2							98.67 164		85.75 275	98.96 23			98.97 161	93.84 151

test_one_0601					99.59 28	94.89 37		97.64 111	93.14 77	98.93 24	99.45 14	93.45 18

fmvsm_s_conf0.5_n		96.19 56	96.49 42	95.30 162	97.37 135	89.16 178	99.86 6	98.47 24	95.68 27	98.87 25	99.15 44	82.44 199	99.92 43	99.14 24	97.43 137	96.83 236

xiu_mvs_v2_base		96.66 38	96.17 55	98.11 28	97.11 155	96.96 6	99.01 130	97.04 198	95.51 31	98.86 26	99.11 55	82.19 203	99.36 137	98.59 39	98.14 120	98.00 201

NCCC		98.12 5	98.11 3	98.13 25	99.76 6	94.46 53	99.81 14	97.88 59	96.54 17	98.84 27	99.46 10	92.55 28	99.98 9	98.25 54	99.93 1	99.94 18

SD-MVS		97.51 16	97.40 19	97.81 36	99.01 72	93.79 69	99.33 85	97.38 163	93.73 64	98.83 28	99.02 64	90.87 44	99.88 57	98.69 34	99.74 29	99.77 46
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
fmvsm_s_conf0.1_n_2		95.24 94	95.04 94	95.83 140	95.60 218	91.71 114	99.65 40	96.18 257	96.99 10	98.79 29	98.91 81	73.91 270	99.87 61	99.00 28	96.30 161	95.91 257

MVS_0304		97.81 9	97.51 15	98.74 9	98.97 73	96.57 11	99.91 2	98.17 37	97.45 3	98.76 30	98.97 68	86.69 118	99.96 28	99.72 3	98.92 91	99.69 58

SF-MVS		97.22 22	96.92 25	98.12 27	99.11 66	94.88 38	99.44 67	97.45 152	89.60 168	98.70 31	99.42 17	90.42 52	99.72 96	98.47 45	99.65 40	99.77 46

balanced_conf03		96.83 33	96.51 41	97.81 36	97.60 122	95.15 34	98.40 203	96.77 215	93.00 80	98.69 32	96.19 223	89.75 63	98.76 170	98.45 46	99.72 32	99.51 83

fmvsm_s_conf0.1_n		95.56 84	95.68 73	95.20 165	94.35 270	89.10 180	99.50 56	97.67 101	94.76 39	98.68 33	99.03 62	81.13 217	99.86 67	98.63 36	97.36 139	96.63 239

DPE-MVS		98.11 6	98.00 6	98.44 16	99.50 42	95.39 23	99.29 87	97.72 86	94.50 42	98.64 34	99.54 3	93.32 20	99.97 21	99.58 11	99.90 7	99.95 15
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
MSP-MVS		97.77 10	98.18 2	96.53 102	99.54 36	90.14 154	99.41 74	97.70 91	95.46 32	98.60 35	99.19 34	95.71 5	99.49 119	98.15 56	99.85 13	99.95 15
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
9.14			96.87 28		99.34 50		99.50 56	97.49 146	89.41 177	98.59 36	99.43 16	89.78 62	99.69 98	98.69 34	99.62 46

APD-MVS		96.95 30	96.72 36	97.63 42	99.51 41	93.58 71	99.16 104	97.44 156	90.08 155	98.59 36	99.07 56	89.06 69	99.42 130	97.92 59	99.66 39	99.88 26
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_vis1_n_1920		93.08 164	93.42 138	92.04 257	96.31 188	79.36 354	99.83 12	96.06 268	96.72 13	98.53 38	98.10 138	58.57 365	99.91 48	97.86 61	98.79 100	96.85 235

testdata				95.26 164	98.20 101	87.28 234		97.60 120	85.21 281	98.48 39	99.15 44	88.15 86	98.72 175	90.29 196	99.45 59	99.78 41

test_fmvsmconf_n		96.78 36	96.84 30	96.61 95	95.99 205	90.25 149	99.90 3	98.13 43	96.68 15	98.42 40	98.92 80	85.34 149	99.88 57	99.12 25	99.08 78	99.70 55

TEST9					99.57 33	93.17 82	99.38 77	97.66 102	89.57 170	98.39 41	99.18 37	90.88 43	99.66 101

train_agg		97.20 23	97.08 23	97.57 46	99.57 33	93.17 82	99.38 77	97.66 102	90.18 150	98.39 41	99.18 37	90.94 39	99.66 101	98.58 40	99.85 13	99.88 26

test_8					99.55 35	93.07 85	99.37 80	97.64 111	90.18 150	98.36 43	99.19 34	90.94 39	99.64 107

SPE-MVS-test		95.98 63	96.34 48	94.90 176	98.06 107	87.66 221	99.69 38	96.10 263	93.66 65	98.35 44	99.05 60	86.28 130	97.66 238	96.96 80	98.90 93	99.37 97

MM		97.76 11	97.39 20	98.86 5	98.30 97	96.83 7	99.81 14	99.13 9	97.66 2	98.29 45	98.96 73	85.84 139	99.90 52	99.72 3	98.80 97	99.85 30

HPM-MVS++		97.72 12	97.59 13	98.14 24	99.53 40	94.76 45	99.19 98	97.75 81	95.66 28	98.21 46	99.29 23	91.10 36	99.99 5	97.68 64	99.87 9	99.68 60

DPM-MVS		97.86 8	97.25 22	99.68 1	98.25 98	99.10 1	99.76 25	97.78 78	96.61 16	98.15 47	99.53 7	93.62 17	100.00 1	91.79 179	99.80 26	99.94 18

test_part2					99.54 36	95.42 22				98.13 48

SteuartSystems-ACMMP		97.25 19	97.34 21	97.01 67	97.38 134	91.46 119	99.75 26	97.66 102	94.14 52	98.13 48	99.26 24	92.16 32	99.66 101	97.91 60	99.64 42	99.90 22
Skip Steuart: Steuart Systems R&D Blog.
FOURS1					99.50 42	88.94 190	99.55 49	97.47 149	91.32 119	98.12 50

test_prior2							99.57 47		91.43 116	98.12 50	98.97 68	90.43 51		98.33 50	99.81 23

CS-MVS		95.75 77	96.19 50	94.40 195	97.88 112	86.22 257	99.66 39	96.12 262	92.69 88	98.07 52	98.89 85	87.09 107	97.59 244	96.71 85	98.62 105	99.39 96

PHI-MVS		96.65 41	96.46 44	97.21 61	99.34 50	91.77 111	99.70 31	98.05 47	86.48 264	98.05 53	99.20 32	89.33 67	99.96 28	98.38 47	99.62 46	99.90 22

MVSFormer		94.71 114	94.08 115	96.61 95	95.05 250	94.87 39	97.77 255	96.17 259	86.84 252	98.04 54	98.52 114	85.52 141	95.99 325	89.83 199	98.97 87	98.96 134

lupinMVS		96.32 52	95.94 61	97.44 48	95.05 250	94.87 39	99.86 6	96.50 234	93.82 62	98.04 54	98.77 92	85.52 141	98.09 207	96.98 79	98.97 87	99.37 97

APDe-MVS		97.53 15	97.47 16	97.70 40	99.58 30	93.63 70	99.56 48	97.52 139	93.59 68	98.01 56	99.12 51	90.80 45	99.55 113	99.26 18	99.79 27	99.93 20
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMP_NAP		96.59 42	96.18 52	97.81 36	98.82 85	93.55 73	98.88 142	97.59 124	90.66 132	97.98 57	99.14 47	86.59 121	100.00 1	96.47 94	99.46 57	99.89 25

agg_prior					99.54 36	92.66 95		97.64 111		97.98 57			99.61 109

CDPH-MVS		96.56 46	96.18 52	97.70 40	99.59 28	93.92 65	99.13 115	97.44 156	89.02 185	97.90 59	99.22 30	88.90 74	99.49 119	94.63 139	99.79 27	99.68 60

MVSMamba_PlusPlus		95.73 80	95.15 88	97.44 48	97.28 142	94.35 59	98.26 218	96.75 216	83.09 318	97.84 60	95.97 231	89.59 65	98.48 188	97.86 61	99.73 31	99.49 86

EPNet		96.82 34	96.68 38	97.25 60	98.65 90	93.10 84	99.48 58	98.76 14	96.54 17	97.84 60	98.22 133	87.49 96	99.66 101	95.35 120	97.78 128	99.00 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MSLP-MVS++		97.50 17	97.45 18	97.63 42	99.65 16	93.21 81	99.70 31	98.13 43	94.61 40	97.78 62	99.46 10	89.85 61	99.81 83	97.97 58	99.91 6	99.88 26

test12				97.83 35	99.33 53	94.45 54		97.55 131		97.56 63		88.60 78	99.50 118		99.71 36	99.55 78

xiu_mvs_v1_base_debu		94.73 111	93.98 118	96.99 69	95.19 235	95.24 27	98.62 171	96.50 234	92.99 81	97.52 64	98.83 89	72.37 284	99.15 148	97.03 76	96.74 151	96.58 242

xiu_mvs_v1_base		94.73 111	93.98 118	96.99 69	95.19 235	95.24 27	98.62 171	96.50 234	92.99 81	97.52 64	98.83 89	72.37 284	99.15 148	97.03 76	96.74 151	96.58 242

xiu_mvs_v1_base_debi		94.73 111	93.98 118	96.99 69	95.19 235	95.24 27	98.62 171	96.50 234	92.99 81	97.52 64	98.83 89	72.37 284	99.15 148	97.03 76	96.74 151	96.58 242

ZD-MVS					99.67 10	93.28 79		97.61 118	87.78 229	97.41 67	99.16 40	90.15 58	99.56 112	98.35 49	99.70 37

ETV-MVS		96.00 61	96.00 60	96.00 132	96.56 174	91.05 131	99.63 42	96.61 224	93.26 75	97.39 68	98.30 130	86.62 120	98.13 204	98.07 57	97.57 131	98.82 151

DeepPCF-MVS	93.56 1	96.55 47	97.84 10	92.68 244	98.71 89	78.11 367	99.70 31	97.71 90	98.18 1	97.36 69	99.76 1	90.37 54	99.94 35	99.27 17	99.54 54	99.99 1

test_vis1_n		90.40 219	90.27 209	90.79 284	91.55 334	76.48 374	99.12 117	94.44 353	94.31 46	97.34 70	96.95 192	43.60 408	99.42 130	97.57 66	97.60 130	96.47 246

EC-MVSNet		95.09 98	95.17 87	94.84 179	95.42 225	88.17 209	99.48 58	95.92 282	91.47 114	97.34 70	98.36 127	82.77 187	97.41 255	97.24 73	98.58 107	98.94 139

test_fmvsmconf0.1_n		95.94 67	95.79 70	96.40 109	92.42 316	89.92 165	99.79 20	96.85 210	96.53 19	97.22 72	98.67 104	82.71 191	99.84 73	98.92 31	98.98 86	99.43 93

CANet		97.00 29	96.49 42	98.55 12	98.86 84	96.10 16	99.83 12	97.52 139	95.90 23	97.21 73	98.90 83	82.66 192	99.93 40	98.71 33	98.80 97	99.63 70

CANet_DTU		94.31 125	93.35 140	97.20 62	97.03 160	94.71 48	98.62 171	95.54 312	95.61 29	97.21 73	98.47 123	71.88 289	99.84 73	88.38 219	97.46 136	97.04 230

test_cas_vis1_n_1920		93.86 138	93.74 131	94.22 203	95.39 228	86.08 263	99.73 27	96.07 267	96.38 21	97.19 75	97.78 145	65.46 340	99.86 67	96.71 85	98.92 91	96.73 237

VNet		95.08 99	94.26 107	97.55 47	98.07 106	93.88 66	98.68 162	98.73 17	90.33 147	97.16 76	97.43 164	79.19 234	99.53 116	96.91 82	91.85 221	99.24 110

GDP-MVS		96.05 60	95.63 78	97.31 55	95.37 229	94.65 50	99.36 81	96.42 239	92.14 102	97.07 77	98.53 112	93.33 19	98.50 183	91.76 180	96.66 154	98.78 156

region2R		96.30 53	96.17 55	96.70 89	99.70 7	90.31 148	99.46 64	97.66 102	90.55 140	97.07 77	99.07 56	86.85 113	99.97 21	95.43 118	99.74 29	99.81 35

原ACMM1				96.18 121	99.03 71	90.08 157		97.63 115	88.98 186	97.00 79	98.97 68	88.14 87	99.71 97	88.23 221	99.62 46	98.76 159

reproduce_model		96.57 45	96.75 35	96.02 130	98.93 80	88.46 206	98.56 182	97.34 169	93.18 76	96.96 80	99.35 21	88.69 77	99.80 85	98.53 41	99.21 77	99.79 38

HFP-MVS		96.42 49	96.26 49	96.90 77	99.69 8	90.96 134	99.47 60	97.81 71	90.54 141	96.88 81	99.05 60	87.57 94	99.96 28	95.65 110	99.72 32	99.78 41

XVS		96.47 48	96.37 46	96.77 82	99.62 22	90.66 142	99.43 71	97.58 126	92.41 95	96.86 82	98.96 73	87.37 99	99.87 61	95.65 110	99.43 61	99.78 41

X-MVStestdata		90.69 215	88.66 238	96.77 82	99.62 22	90.66 142	99.43 71	97.58 126	92.41 95	96.86 82	29.59 432	87.37 99	99.87 61	95.65 110	99.43 61	99.78 41

SR-MVS		96.13 57	96.16 57	96.07 127	99.42 47	89.04 182	98.59 179	97.33 170	90.44 144	96.84 84	99.12 51	86.75 115	99.41 133	97.47 67	99.44 60	99.76 48

TSAR-MVS + GP.		96.95 30	96.91 26	97.07 64	98.88 83	91.62 115	99.58 46	96.54 232	95.09 36	96.84 84	98.63 108	91.16 34	99.77 92	99.04 27	96.42 157	99.81 35

ACMMPR		96.28 54	96.14 59	96.73 86	99.68 9	90.47 146	99.47 60	97.80 73	90.54 141	96.83 86	99.03 62	86.51 126	99.95 32	95.65 110	99.72 32	99.75 49

test_fmvs1		92.35 177	92.94 152	90.57 289	97.19 147	75.43 380	99.55 49	94.97 337	95.20 35	96.82 87	97.57 158	59.59 363	99.84 73	97.30 71	98.29 119	96.46 247

PMMVS		93.62 147	93.90 126	92.79 239	96.79 169	81.40 335	98.85 143	96.81 211	91.25 121	96.82 87	98.15 137	77.02 250	98.13 204	93.15 166	96.30 161	98.83 150

reproduce-ours		96.66 38	96.80 33	96.22 117	98.95 77	89.03 184	98.62 171	97.38 163	93.42 70	96.80 89	99.36 19	88.92 72	99.80 85	98.51 42	99.26 71	99.82 32

our_new_method		96.66 38	96.80 33	96.22 117	98.95 77	89.03 184	98.62 171	97.38 163	93.42 70	96.80 89	99.36 19	88.92 72	99.80 85	98.51 42	99.26 71	99.82 32

PGM-MVS		95.85 70	95.65 76	96.45 105	99.50 42	89.77 169	98.22 221	98.90 13	89.19 180	96.74 91	98.95 76	85.91 138	99.92 43	93.94 148	99.46 57	99.66 64

jason		95.40 89	94.86 97	97.03 66	92.91 310	94.23 60	99.70 31	96.30 246	93.56 69	96.73 92	98.52 114	81.46 213	97.91 217	96.08 103	98.47 113	98.96 134
jason: jason.
新几何1				97.40 52	98.92 81	92.51 101		97.77 80	85.52 277	96.69 93	99.06 58	88.08 88	99.89 56	84.88 259	99.62 46	99.79 38

SR-MVS-dyc-post		95.75 77	95.86 64	95.41 156	99.22 59	87.26 237	98.40 203	97.21 179	89.63 166	96.67 94	98.97 68	86.73 117	99.36 137	96.62 88	99.31 67	99.60 73

RE-MVS-def			95.70 72		99.22 59	87.26 237	98.40 203	97.21 179	89.63 166	96.67 94	98.97 68	85.24 150		96.62 88	99.31 67	99.60 73

APD-MVS_3200maxsize		95.64 83	95.65 76	95.62 150	99.24 58	87.80 217	98.42 198	97.22 178	88.93 190	96.64 96	98.98 67	85.49 144	99.36 137	96.68 87	99.27 70	99.70 55

mvsany_test1		94.57 119	95.09 92	92.98 234	95.84 210	82.07 329	98.76 155	95.24 330	92.87 86	96.45 97	98.71 101	84.81 156	99.15 148	97.68 64	95.49 176	97.73 207

MG-MVS		97.24 20	96.83 32	98.47 15	99.79 5	95.71 19	99.07 121	99.06 10	94.45 45	96.42 98	98.70 102	88.81 75	99.74 95	95.35 120	99.86 12	99.97 7

BP-MVS1		96.59 42	96.36 47	97.29 56	95.05 250	94.72 47	99.44 67	97.45 152	92.71 87	96.41 99	98.50 116	94.11 16	98.50 183	95.61 115	97.97 122	98.66 167

test_fmvs1_n		91.07 205	91.41 186	90.06 303	94.10 278	74.31 384	99.18 100	94.84 341	94.81 37	96.37 100	97.46 162	50.86 397	99.82 80	97.14 75	97.90 123	96.04 254

h-mvs33		92.47 176	91.95 173	94.05 211	97.13 153	85.01 289	98.36 210	98.08 45	93.85 60	96.27 101	96.73 206	83.19 178	99.43 129	95.81 108	68.09 382	97.70 208

hse-mvs2		91.67 192	91.51 184	92.15 254	96.22 192	82.61 325	97.74 259	97.53 135	93.85 60	96.27 101	96.15 224	83.19 178	97.44 253	95.81 108	66.86 389	96.40 249

alignmvs		95.77 75	95.00 95	98.06 29	97.35 136	95.68 20	99.71 30	97.50 144	91.50 113	96.16 103	98.61 110	86.28 130	99.00 158	96.19 98	91.74 223	99.51 83

CP-MVS		96.22 55	96.15 58	96.42 107	99.67 10	89.62 172	99.70 31	97.61 118	90.07 156	96.00 104	99.16 40	87.43 97	99.92 43	96.03 104	99.72 32	99.70 55

MCST-MVS		98.18 2	97.95 9	98.86 5	99.85 3	96.60 10	99.70 31	97.98 54	97.18 7	95.96 105	99.33 22	92.62 27	100.00 1	98.99 29	99.93 1	99.98 6

diffmvs		94.59 118	94.19 110	95.81 141	95.54 221	90.69 140	98.70 160	95.68 304	91.61 109	95.96 105	97.81 142	80.11 223	98.06 209	96.52 93	95.76 171	98.67 164
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
GST-MVS		95.97 64	95.66 74	96.90 77	99.49 45	91.22 121	99.45 66	97.48 147	89.69 164	95.89 107	98.72 98	86.37 129	99.95 32	94.62 140	99.22 74	99.52 81

DeepC-MVS_fast	93.52 2	97.16 24	96.84 30	98.13 25	99.61 24	94.45 54	98.85 143	97.64 111	96.51 20	95.88 108	99.39 18	87.35 103	99.99 5	96.61 90	99.69 38	99.96 10
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test222					98.32 96	91.21 122	98.08 238	97.58 126	83.74 306	95.87 109	99.02 64	86.74 116			99.64 42	99.81 35

sasdasda		95.02 100	93.96 121	98.20 21	97.53 126	95.92 17	98.71 157	96.19 255	91.78 106	95.86 110	98.49 119	79.53 229	99.03 156	96.12 100	91.42 235	99.66 64

ZNCC-MVS		96.09 58	95.81 68	96.95 75	99.42 47	91.19 123	99.55 49	97.53 135	89.72 163	95.86 110	98.94 79	86.59 121	99.97 21	95.13 126	99.56 52	99.68 60

canonicalmvs		95.02 100	93.96 121	98.20 21	97.53 126	95.92 17	98.71 157	96.19 255	91.78 106	95.86 110	98.49 119	79.53 229	99.03 156	96.12 100	91.42 235	99.66 64

dcpmvs_2		95.67 82	96.18 52	94.12 207	98.82 85	84.22 300	97.37 276	95.45 317	90.70 131	95.77 113	98.63 108	90.47 50	98.68 177	99.20 23	99.22 74	99.45 90

MGCFI-Net		94.89 102	93.84 128	98.06 29	97.49 129	95.55 21	98.64 168	96.10 263	91.60 111	95.75 114	98.46 125	79.31 233	98.98 160	95.95 106	91.24 239	99.65 67

Effi-MVS+		93.87 137	93.15 146	96.02 130	95.79 211	90.76 138	96.70 306	95.78 296	86.98 249	95.71 115	97.17 180	79.58 227	98.01 214	94.57 141	96.09 166	99.31 104

HPM-MVS_fast		94.89 102	94.62 100	95.70 145	99.11 66	88.44 207	99.14 112	97.11 191	85.82 272	95.69 116	98.47 123	83.46 171	99.32 142	93.16 165	99.63 45	99.35 100

HY-MVS	88.56 7	95.29 91	94.23 108	98.48 14	97.72 115	96.41 13	94.03 359	98.74 15	92.42 94	95.65 117	94.76 253	86.52 125	99.49 119	95.29 123	92.97 199	99.53 80

CHOSEN 280x420		96.80 35	96.85 29	96.66 93	97.85 113	94.42 56	94.76 350	98.36 29	92.50 91	95.62 118	97.52 159	97.92 1	97.38 256	98.31 52	98.80 97	98.20 195

test_fmvsmconf0.01_n		94.14 128	93.51 136	96.04 128	86.79 389	89.19 177	99.28 90	95.94 277	95.70 25	95.50 119	98.49 119	73.27 276	99.79 89	98.28 53	98.32 118	99.15 117

MP-MVS		96.00 61	95.82 66	96.54 101	99.47 46	90.13 156	99.36 81	97.41 160	90.64 135	95.49 120	98.95 76	85.51 143	99.98 9	96.00 105	99.59 51	99.52 81
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS		95.41 88	95.22 86	95.99 133	99.29 55	89.14 179	99.17 103	97.09 195	87.28 243	95.40 121	98.48 122	84.93 153	99.38 135	95.64 114	99.65 40	99.47 89
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
UA-Net		93.30 156	92.62 159	95.34 159	96.27 190	88.53 205	95.88 333	96.97 206	90.90 127	95.37 122	97.07 184	82.38 200	99.10 154	83.91 276	94.86 182	98.38 180

sss		94.85 107	93.94 123	97.58 44	96.43 181	94.09 64	98.93 137	99.16 8	89.50 173	95.27 123	97.85 140	81.50 211	99.65 105	92.79 171	94.02 189	98.99 131

WTY-MVS		95.97 64	95.11 91	98.54 13	97.62 119	96.65 9	99.44 67	98.74 15	92.25 98	95.21 124	98.46 125	86.56 123	99.46 125	95.00 131	92.69 203	99.50 85

DELS-MVS		97.12 25	96.60 39	98.68 11	98.03 108	96.57 11	99.84 11	97.84 63	96.36 22	95.20 125	98.24 132	88.17 84	99.83 77	96.11 102	99.60 50	99.64 68
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_HR		96.69 37	96.69 37	96.72 88	98.58 92	91.00 133	99.14 112	99.45 1	93.86 59	95.15 126	98.73 96	88.48 79	99.76 93	97.23 74	99.56 52	99.40 94

MVS_Test		93.67 145	92.67 157	96.69 90	96.72 171	92.66 95	97.22 284	96.03 269	87.69 235	95.12 127	94.03 261	81.55 209	98.28 196	89.17 213	96.46 155	99.14 118

MVS_111021_LR		95.78 74	95.94 61	95.28 163	98.19 103	87.69 218	98.80 149	99.26 7	93.39 72	95.04 128	98.69 103	84.09 163	99.76 93	96.96 80	99.06 81	98.38 180

CostFormer		92.89 166	92.48 162	94.12 207	94.99 253	85.89 270	92.89 369	97.00 204	86.98 249	95.00 129	90.78 331	90.05 60	97.51 249	92.92 169	91.73 224	98.96 134

testing222		94.48 122	94.00 117	95.95 135	97.30 139	92.27 104	98.82 146	97.92 57	89.20 179	94.82 130	97.26 170	87.13 106	97.32 259	91.95 177	91.56 227	98.25 189

mPP-MVS		95.90 69	95.75 71	96.38 110	99.58 30	89.41 176	99.26 93	97.41 160	90.66 132	94.82 130	98.95 76	86.15 134	99.98 9	95.24 125	99.64 42	99.74 50

EI-MVSNet-Vis-set		95.76 76	95.63 78	96.17 123	99.14 64	90.33 147	98.49 191	97.82 67	91.92 104	94.75 132	98.88 87	87.06 109	99.48 123	95.40 119	97.17 144	98.70 162

LFMVS		92.23 182	90.84 198	96.42 107	98.24 100	91.08 130	98.24 220	96.22 252	83.39 313	94.74 133	98.31 129	61.12 358	98.85 164	94.45 142	92.82 200	99.32 103

tpmrst		92.78 167	92.16 167	94.65 186	96.27 190	87.45 228	91.83 379	97.10 194	89.10 184	94.68 134	90.69 335	88.22 83	97.73 236	89.78 202	91.80 222	98.77 158

test_yl		95.27 92	94.60 101	97.28 58	98.53 93	92.98 88	99.05 125	98.70 18	86.76 256	94.65 135	97.74 148	87.78 91	99.44 126	95.57 116	92.61 204	99.44 91

DCV-MVSNet		95.27 92	94.60 101	97.28 58	98.53 93	92.98 88	99.05 125	98.70 18	86.76 256	94.65 135	97.74 148	87.78 91	99.44 126	95.57 116	92.61 204	99.44 91

testing11		95.33 90	94.98 96	96.37 111	97.20 145	92.31 103	99.29 87	97.68 97	90.59 137	94.43 137	97.20 176	90.79 46	98.60 180	95.25 124	92.38 208	98.18 196

DP-MVS Recon		95.85 70	95.15 88	97.95 32	99.87 2	94.38 57	99.60 44	97.48 147	86.58 259	94.42 138	99.13 49	87.36 102	99.98 9	93.64 155	98.33 116	99.48 87

ETVMVS		94.50 121	93.90 126	96.31 115	97.48 130	92.98 88	99.07 121	97.86 61	88.09 219	94.40 139	96.90 195	88.35 81	97.28 260	90.72 193	92.25 214	98.66 167

MTAPA		96.09 58	95.80 69	96.96 74	99.29 55	91.19 123	97.23 283	97.45 152	92.58 89	94.39 140	99.24 28	86.43 128	99.99 5	96.22 97	99.40 64	99.71 54

UBG		95.73 80	95.41 80	96.69 90	96.97 161	93.23 80	99.13 115	97.79 75	91.28 120	94.38 141	96.78 203	92.37 30	98.56 182	96.17 99	93.84 191	98.26 188

CPTT-MVS		94.60 117	94.43 105	95.09 169	99.66 12	86.85 242	99.44 67	97.47 149	83.22 315	94.34 142	98.96 73	82.50 193	99.55 113	94.81 134	99.50 55	98.88 144

PVSNet_BlendedMVS		93.36 154	93.20 145	93.84 219	98.77 87	91.61 116	99.47 60	98.04 49	91.44 115	94.21 143	92.63 295	83.50 169	99.87 61	97.41 68	83.37 292	90.05 358

PVSNet_Blended		95.94 67	95.66 74	96.75 84	98.77 87	91.61 116	99.88 4	98.04 49	93.64 67	94.21 143	97.76 146	83.50 169	99.87 61	97.41 68	97.75 129	98.79 154

EI-MVSNet-UG-set		95.43 86	95.29 84	95.86 139	99.07 70	89.87 166	98.43 197	97.80 73	91.78 106	94.11 145	98.77 92	86.25 132	99.48 123	94.95 133	96.45 156	98.22 193

EIA-MVS		95.11 97	95.27 85	94.64 188	96.34 187	86.51 246	99.59 45	96.62 223	92.51 90	94.08 146	98.64 106	86.05 135	98.24 199	95.07 128	98.50 110	99.18 115

mvsmamba		94.27 126	93.91 125	95.35 158	96.42 182	88.61 201	97.77 255	96.38 241	91.17 123	94.05 147	95.27 245	78.41 242	97.96 216	97.36 70	98.40 114	99.48 87

MAR-MVS		94.43 123	94.09 114	95.45 154	99.10 68	87.47 227	98.39 207	97.79 75	88.37 208	94.02 148	99.17 39	78.64 240	99.91 48	92.48 173	98.85 95	98.96 134
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
PAPM		96.35 50	95.94 61	97.58 44	94.10 278	95.25 26	98.93 137	98.17 37	94.26 47	93.94 149	98.72 98	89.68 64	97.88 220	96.36 95	99.29 69	99.62 72

myMVS_eth3d28		95.74 79	95.34 82	96.92 76	97.41 131	93.58 71	99.28 90	97.70 91	90.97 126	93.91 150	97.25 172	90.59 48	98.75 171	96.85 84	94.14 187	98.44 175

GG-mvs-BLEND				96.98 72	96.53 176	94.81 44	87.20 400	97.74 82		93.91 150	96.40 216	96.56 2	96.94 273	95.08 127	98.95 90	99.20 114

API-MVS		94.78 109	94.18 112	96.59 97	99.21 61	90.06 161	98.80 149	97.78 78	83.59 310	93.85 152	99.21 31	83.79 166	99.97 21	92.37 174	99.00 85	99.74 50

tpm2		91.77 190	91.09 191	93.82 220	94.83 260	85.56 278	92.51 374	97.16 186	84.00 301	93.83 153	90.66 337	87.54 95	97.17 262	87.73 227	91.55 228	98.72 160

PAPR		96.35 50	95.82 66	97.94 33	99.63 18	94.19 62	99.42 73	97.55 131	92.43 92	93.82 154	99.12 51	87.30 104	99.91 48	94.02 147	99.06 81	99.74 50

testing99		94.88 104	94.45 103	96.17 123	97.20 145	91.91 108	99.20 97	97.66 102	89.95 158	93.68 155	97.06 185	90.28 56	98.50 183	93.52 157	91.54 229	98.12 198

testing91		94.88 104	94.44 104	96.21 119	97.19 147	91.90 109	99.23 95	97.66 102	89.91 159	93.66 156	97.05 187	90.21 57	98.50 183	93.52 157	91.53 232	98.25 189

PVSNet	87.13 12	93.69 142	92.83 154	96.28 116	97.99 109	90.22 152	99.38 77	98.93 12	91.42 117	93.66 156	97.68 151	71.29 296	99.64 107	87.94 225	97.20 141	98.98 132

baseline		93.91 135	93.30 142	95.72 144	95.10 247	90.07 158	97.48 271	95.91 287	91.03 124	93.54 158	97.68 151	79.58 227	98.02 213	94.27 144	95.14 179	99.08 126

test2506		94.80 108	94.21 109	96.58 98	96.41 183	92.18 106	98.01 241	98.96 11	90.82 129	93.46 159	97.28 168	85.92 136	98.45 189	89.82 201	97.19 142	99.12 121

VDD-MVS		91.24 203	90.18 210	94.45 194	97.08 157	85.84 273	98.40 203	96.10 263	86.99 246	93.36 160	98.16 136	54.27 384	99.20 145	96.59 91	90.63 245	98.31 187

VDDNet		90.08 229	88.54 243	94.69 185	94.41 269	87.68 219	98.21 223	96.40 240	76.21 378	93.33 161	97.75 147	54.93 382	98.77 168	94.71 138	90.96 240	97.61 213

thisisatest0515		94.75 110	94.19 110	96.43 106	96.13 202	92.64 98	99.47 60	97.60 120	87.55 238	93.17 162	97.59 156	94.71 12	98.42 190	88.28 220	93.20 196	98.24 192

MP-MVS-pluss		95.80 73	95.30 83	97.29 56	98.95 77	92.66 95	98.59 179	97.14 187	88.95 188	93.12 163	99.25 26	85.62 140	99.94 35	96.56 92	99.48 56	99.28 107
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MDTV_nov1_ep13_2view						91.17 125	91.38 386		87.45 240	93.08 164		86.67 119		87.02 231		98.95 138

EPNet_dtu		92.28 180	92.15 168	92.70 243	97.29 140	84.84 292	98.64 168	97.82 67	92.91 84	93.02 165	97.02 188	85.48 146	95.70 340	72.25 365	94.89 181	97.55 214
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
gg-mvs-nofinetune		90.00 230	87.71 255	96.89 81	96.15 197	94.69 49	85.15 407	97.74 82	68.32 406	92.97 166	60.16 420	96.10 4	96.84 276	93.89 149	98.87 94	99.14 118

testing3-2		95.17 95	94.78 98	96.33 114	97.35 136	92.35 102	99.85 9	98.43 26	90.60 136	92.84 167	97.00 189	90.89 42	98.89 163	95.95 106	90.12 248	97.76 205

test_fmvsmvis_n_1920		95.47 85	95.40 81	95.70 145	94.33 271	90.22 152	99.70 31	96.98 205	96.80 11	92.75 168	98.89 85	82.46 198	99.92 43	98.36 48	98.33 116	96.97 233

casdiffmvs		93.98 133	93.43 137	95.61 151	95.07 249	89.86 167	98.80 149	95.84 295	90.98 125	92.74 169	97.66 153	79.71 226	98.10 206	94.72 137	95.37 177	98.87 146
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
RRT-MVS		93.39 152	92.64 158	95.64 148	96.11 203	88.75 198	97.40 272	95.77 298	89.46 175	92.70 170	95.42 242	72.98 278	98.81 166	96.91 82	96.97 147	99.37 97

114514_t		94.06 129	93.05 148	97.06 65	99.08 69	92.26 105	98.97 135	97.01 203	82.58 330	92.57 171	98.22 133	80.68 220	99.30 143	89.34 209	99.02 84	99.63 70

OMC-MVS		93.90 136	93.62 133	94.73 184	98.63 91	87.00 240	98.04 240	96.56 230	92.19 99	92.46 172	98.73 96	79.49 231	99.14 152	92.16 176	94.34 186	98.03 200

PAPM_NR		95.43 86	95.05 93	96.57 100	99.42 47	90.14 154	98.58 181	97.51 141	90.65 134	92.44 173	98.90 83	87.77 93	99.90 52	90.88 188	99.32 66	99.68 60

mmtdpeth		83.69 331	82.59 330	86.99 351	92.82 312	76.98 373	96.16 325	91.63 395	82.89 327	92.41 174	82.90 396	54.95 381	98.19 201	96.27 96	53.27 414	85.81 396

UGNet		91.91 189	90.85 197	95.10 168	97.06 158	88.69 200	98.01 241	98.24 34	92.41 95	92.39 175	93.61 275	60.52 360	99.68 99	88.14 222	97.25 140	96.92 234
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
MDTV_nov1_ep13			90.47 208		96.14 199	88.55 203	91.34 387	97.51 141	89.58 169	92.24 176	90.50 348	86.99 112	97.61 243	77.64 325	92.34 210

FE-MVS		91.38 198	90.16 211	95.05 172	96.46 180	87.53 225	89.69 397	97.84 63	82.97 321	92.18 177	92.00 305	84.07 164	98.93 162	80.71 304	95.52 175	98.68 163

Vis-MVSNet		92.64 170	91.85 175	95.03 173	95.12 242	88.23 208	98.48 193	96.81 211	91.61 109	92.16 178	97.22 175	71.58 294	98.00 215	85.85 250	97.81 125	98.88 144
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
FA-MVS(test-final)		92.22 183	91.08 192	95.64 148	96.05 204	88.98 187	91.60 383	97.25 173	86.99 246	91.84 179	92.12 299	83.03 181	99.00 158	86.91 235	93.91 190	98.93 140

TESTMET0.1,1		93.82 139	93.26 144	95.49 153	95.21 234	90.25 149	99.15 109	97.54 134	89.18 181	91.79 180	94.87 251	89.13 68	97.63 241	86.21 243	96.29 163	98.60 169

thisisatest0530		94.00 131	93.52 135	95.43 155	95.76 213	90.02 163	98.99 132	97.60 120	86.58 259	91.74 181	97.36 167	94.78 11	98.34 192	86.37 241	92.48 207	97.94 203

UWE-MVS		93.18 160	93.40 139	92.50 247	96.56 174	83.55 309	98.09 237	97.84 63	89.50 173	91.72 182	96.23 222	91.08 37	96.70 282	86.28 242	93.33 195	97.26 222

AUN-MVS		90.17 226	89.50 219	92.19 252	96.21 193	82.67 323	97.76 258	97.53 135	88.05 220	91.67 183	96.15 224	83.10 180	97.47 250	88.11 223	66.91 388	96.43 248

EPMVS		92.59 173	91.59 182	95.59 152	97.22 144	90.03 162	91.78 380	98.04 49	90.42 145	91.66 184	90.65 338	86.49 127	97.46 251	81.78 297	96.31 160	99.28 107

test-LLR		93.11 163	92.68 156	94.40 195	94.94 256	87.27 235	99.15 109	97.25 173	90.21 148	91.57 185	94.04 259	84.89 154	97.58 245	85.94 247	96.13 164	98.36 184

test-mter		93.27 158	92.89 153	94.40 195	94.94 256	87.27 235	99.15 109	97.25 173	88.95 188	91.57 185	94.04 259	88.03 89	97.58 245	85.94 247	96.13 164	98.36 184

JIA-IIPM		85.97 298	84.85 298	89.33 324	93.23 306	73.68 387	85.05 408	97.13 189	69.62 402	91.56 187	68.03 418	88.03 89	96.96 271	77.89 324	93.12 197	97.34 219

casdiffmvs_mvg		94.00 131	93.33 141	96.03 129	95.22 233	90.90 136	99.09 119	95.99 270	90.58 138	91.55 188	97.37 166	79.91 225	98.06 209	95.01 130	95.22 178	99.13 120
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet_Blended_VisFu		94.67 115	94.11 113	96.34 113	97.14 152	91.10 128	99.32 86	97.43 158	92.10 103	91.53 189	96.38 219	83.29 175	99.68 99	93.42 162	96.37 158	98.25 189

CHOSEN 1792x2688		94.35 124	93.82 129	95.95 135	97.40 132	88.74 199	98.41 200	98.27 31	92.18 100	91.43 190	96.40 216	78.88 235	99.81 83	93.59 156	97.81 125	99.30 105

ACMMP		94.67 115	94.30 106	95.79 142	99.25 57	88.13 211	98.41 200	98.67 21	90.38 146	91.43 190	98.72 98	82.22 202	99.95 32	93.83 152	95.76 171	99.29 106
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
ECVR-MVS		92.29 179	91.33 187	95.15 167	96.41 183	87.84 216	98.10 234	94.84 341	90.82 129	91.42 192	97.28 168	65.61 337	98.49 187	90.33 195	97.19 142	99.12 121

EPP-MVSNet		93.75 141	93.67 132	94.01 213	95.86 209	85.70 275	98.67 164	97.66 102	84.46 295	91.36 193	97.18 179	91.16 34	97.79 226	92.93 168	93.75 192	98.53 171

PLC	91.07 3	94.23 127	94.01 116	94.87 177	99.17 63	87.49 226	99.25 94	96.55 231	88.43 206	91.26 194	98.21 135	85.92 136	99.86 67	89.77 203	97.57 131	97.24 223
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
HyFIR lowres test		93.68 144	93.29 143	94.87 177	97.57 125	88.04 213	98.18 225	98.47 24	87.57 237	91.24 195	95.05 249	85.49 144	97.46 251	93.22 164	92.82 200	99.10 124

thres200		93.69 142	92.59 160	96.97 73	97.76 114	94.74 46	99.35 83	99.36 2	89.23 178	91.21 196	96.97 191	83.42 172	98.77 168	85.08 255	90.96 240	97.39 218

test1111		92.12 184	91.19 190	94.94 175	96.15 197	87.36 231	98.12 231	94.84 341	90.85 128	90.97 197	97.26 170	65.60 338	98.37 191	89.74 204	97.14 145	99.07 128

CDS-MVSNet		93.47 148	93.04 149	94.76 181	94.75 262	89.45 175	98.82 146	97.03 200	87.91 226	90.97 197	96.48 214	89.06 69	96.36 301	89.50 205	92.81 202	98.49 173
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
tfpn200view9		93.43 150	92.27 165	96.90 77	97.68 117	94.84 41	99.18 100	99.36 2	88.45 203	90.79 199	96.90 195	83.31 173	98.75 171	84.11 272	90.69 242	97.12 225

thres400		93.39 152	92.27 165	96.73 86	97.68 117	94.84 41	99.18 100	99.36 2	88.45 203	90.79 199	96.90 195	83.31 173	98.75 171	84.11 272	90.69 242	96.61 240

CR-MVSNet		88.83 249	87.38 260	93.16 231	93.47 299	86.24 255	84.97 409	94.20 362	88.92 191	90.76 201	86.88 385	84.43 159	94.82 361	70.64 369	92.17 216	98.41 177

RPMNet		85.07 313	81.88 332	94.64 188	93.47 299	86.24 255	84.97 409	97.21 179	64.85 413	90.76 201	78.80 411	80.95 219	99.27 144	53.76 412	92.17 216	98.41 177

PatchmatchNet		92.05 188	91.04 193	95.06 170	96.17 196	89.04 182	91.26 388	97.26 172	89.56 171	90.64 203	90.56 344	88.35 81	97.11 265	79.53 310	96.07 168	99.03 129
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tttt0517		93.30 156	93.01 150	94.17 205	95.57 219	86.47 248	98.51 188	97.60 120	85.99 270	90.55 204	97.19 178	94.80 10	98.31 193	85.06 256	91.86 220	97.74 206

PatchT		85.44 308	83.19 319	92.22 250	93.13 308	83.00 315	83.80 415	96.37 242	70.62 396	90.55 204	79.63 410	84.81 156	94.87 359	58.18 408	91.59 226	98.79 154

tpm		89.67 234	88.95 231	91.82 261	92.54 314	81.43 334	92.95 368	95.92 282	87.81 228	90.50 206	89.44 364	84.99 152	95.65 341	83.67 279	82.71 297	98.38 180

thres100view900		93.34 155	92.15 168	96.90 77	97.62 119	94.84 41	99.06 124	99.36 2	87.96 224	90.47 207	96.78 203	83.29 175	98.75 171	84.11 272	90.69 242	97.12 225

thres600view7		93.18 160	92.00 171	96.75 84	97.62 119	94.92 36	99.07 121	99.36 2	87.96 224	90.47 207	96.78 203	83.29 175	98.71 176	82.93 286	90.47 246	96.61 240

AdaColmap		93.82 139	93.06 147	96.10 126	99.88 1	89.07 181	98.33 212	97.55 131	86.81 254	90.39 209	98.65 105	75.09 257	99.98 9	93.32 163	97.53 134	99.26 109

XVG-OURS-SEG-HR		90.95 209	90.66 204	91.83 260	95.18 238	81.14 342	95.92 330	95.92 282	88.40 207	90.33 210	97.85 140	70.66 299	99.38 135	92.83 170	88.83 253	94.98 264

IS-MVSNet		93.00 165	92.51 161	94.49 191	96.14 199	87.36 231	98.31 215	95.70 302	88.58 199	90.17 211	97.50 160	83.02 182	97.22 261	87.06 230	96.07 168	98.90 143

CSCG		94.87 106	94.71 99	95.36 157	99.54 36	86.49 247	99.34 84	98.15 41	82.71 328	90.15 212	99.25 26	89.48 66	99.86 67	94.97 132	98.82 96	99.72 53

SCA		90.64 217	89.25 225	94.83 180	94.95 255	88.83 194	96.26 319	97.21 179	90.06 157	90.03 213	90.62 340	66.61 329	96.81 278	83.16 282	94.36 185	98.84 147

XVG-OURS		90.83 211	90.49 206	91.86 259	95.23 232	81.25 339	95.79 338	95.92 282	88.96 187	90.02 214	98.03 139	71.60 293	99.35 140	91.06 185	87.78 257	94.98 264

ADS-MVSNet2		87.62 274	86.88 268	89.86 309	96.21 193	79.14 357	87.15 401	92.99 376	83.01 319	89.91 215	87.27 381	78.87 236	92.80 383	74.20 351	92.27 212	97.64 209

ADS-MVSNet		88.99 242	87.30 261	94.07 209	96.21 193	87.56 224	87.15 401	96.78 214	83.01 319	89.91 215	87.27 381	78.87 236	97.01 270	74.20 351	92.27 212	97.64 209

mamv4		91.41 196	93.57 134	84.91 368	97.11 155	58.11 415	95.68 341	95.93 280	82.09 340	89.78 217	95.71 236	90.09 59	98.24 199	97.26 72	98.50 110	98.38 180

ab-mvs		91.05 207	89.17 226	96.69 90	95.96 206	91.72 113	92.62 373	97.23 177	85.61 276	89.74 218	93.89 268	68.55 311	99.42 130	91.09 184	87.84 256	98.92 142

TAMVS		92.62 171	92.09 170	94.20 204	94.10 278	87.68 219	98.41 200	96.97 206	87.53 239	89.74 218	96.04 229	84.77 158	96.49 294	88.97 215	92.31 211	98.42 176

Vis-MVSNet (Re-imp)		93.26 159	93.00 151	94.06 210	96.14 199	86.71 245	98.68 162	96.70 218	88.30 212	89.71 220	97.64 154	85.43 147	96.39 299	88.06 224	96.32 159	99.08 126

CNLPA		93.64 146	92.74 155	96.36 112	98.96 76	90.01 164	99.19 98	95.89 290	86.22 267	89.40 221	98.85 88	80.66 221	99.84 73	88.57 217	96.92 149	99.24 110

Anonymous202405211		88.84 247	87.03 266	94.27 200	98.14 105	84.18 301	98.44 196	95.58 310	76.79 376	89.34 222	96.88 198	53.42 388	99.54 115	87.53 229	87.12 260	99.09 125

Fast-Effi-MVS+		91.72 191	90.79 201	94.49 191	95.89 207	87.40 230	99.54 54	95.70 302	85.01 288	89.28 223	95.68 237	77.75 246	97.57 248	83.22 281	95.06 180	98.51 172

PatchMatch-RL		91.47 194	90.54 205	94.26 201	98.20 101	86.36 253	96.94 294	97.14 187	87.75 231	88.98 224	95.75 235	71.80 291	99.40 134	80.92 302	97.39 138	97.02 231

dp		90.16 227	88.83 234	94.14 206	96.38 186	86.42 249	91.57 384	97.06 197	84.76 292	88.81 225	90.19 356	84.29 161	97.43 254	75.05 343	91.35 238	98.56 170

UWE-MVS-28		90.99 208	91.93 174	88.15 338	95.12 242	77.87 370	97.18 287	97.79 75	88.72 195	88.69 226	96.52 211	86.54 124	90.75 398	84.64 263	92.16 218	95.83 258

DeepC-MVS	91.02 4	94.56 120	93.92 124	96.46 104	97.16 151	90.76 138	98.39 207	97.11 191	93.92 55	88.66 227	98.33 128	78.14 244	99.85 71	95.02 129	98.57 108	98.78 156
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
baseline1		92.61 172	91.28 188	96.58 98	97.05 159	94.63 51	97.72 260	96.20 253	89.82 161	88.56 228	96.85 199	86.85 113	97.82 224	88.42 218	80.10 309	97.30 220

Anonymous20240529		87.66 273	85.58 286	93.92 216	97.59 123	85.01 289	98.13 229	97.13 189	66.69 411	88.47 229	96.01 230	55.09 380	99.51 117	87.00 232	84.12 283	97.23 224

CVMVSNet		90.30 222	90.91 196	88.46 337	94.32 272	73.58 388	97.61 268	97.59 124	90.16 153	88.43 230	97.10 182	76.83 251	92.86 380	82.64 288	93.54 194	98.93 140

TR-MVS		90.77 212	89.44 221	94.76 181	96.31 188	88.02 214	97.92 245	95.96 274	85.52 277	88.22 231	97.23 174	66.80 328	98.09 207	84.58 264	92.38 208	98.17 197

F-COLMAP		92.07 187	91.75 180	93.02 233	98.16 104	82.89 319	98.79 153	95.97 272	86.54 261	87.92 232	97.80 143	78.69 239	99.65 105	85.97 245	95.93 170	96.53 245

WB-MVSnew		88.69 255	88.34 245	89.77 313	94.30 276	85.99 268	98.14 228	97.31 171	87.15 245	87.85 233	96.07 228	69.91 300	95.52 344	72.83 362	91.47 233	87.80 382

BH-RMVSNet		91.25 202	89.99 212	95.03 173	96.75 170	88.55 203	98.65 166	94.95 338	87.74 232	87.74 234	97.80 143	68.27 314	98.14 203	80.53 307	97.49 135	98.41 177

Effi-MVS+-dtu		89.97 231	90.68 203	87.81 342	95.15 239	71.98 395	97.87 249	95.40 321	91.92 104	87.57 235	91.44 317	74.27 266	96.84 276	89.45 206	93.10 198	94.60 266

HQP-NCC					93.95 283		99.16 104		93.92 55	87.57 235

ACMP_Plane					93.95 283		99.16 104		93.92 55	87.57 235

HQP4-MVS										87.57 235			97.77 228			92.72 276

HQP-MVS		91.50 193	91.23 189	92.29 249	93.95 283	86.39 251	99.16 104	96.37 242	93.92 55	87.57 235	96.67 209	73.34 273	97.77 228	93.82 153	86.29 264	92.72 276

TAPA-MVS	87.50 9	90.35 220	89.05 229	94.25 202	98.48 95	85.17 286	98.42 198	96.58 229	82.44 335	87.24 240	98.53 112	82.77 187	98.84 165	59.09 406	97.88 124	98.72 160
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
GeoE		90.60 218	89.56 218	93.72 223	95.10 247	85.43 279	99.41 74	94.94 339	83.96 303	87.21 241	96.83 202	74.37 264	97.05 269	80.50 308	93.73 193	98.67 164

HQP_MVS		91.26 200	90.95 195	92.16 253	93.84 290	86.07 265	99.02 128	96.30 246	93.38 73	86.99 242	96.52 211	72.92 279	97.75 234	93.46 160	86.17 267	92.67 278

plane_prior3						85.91 269			93.65 66	86.99 242

GA-MVS		90.10 228	88.69 237	94.33 198	92.44 315	87.97 215	99.08 120	96.26 250	89.65 165	86.92 244	93.11 287	68.09 316	96.96 271	82.54 290	90.15 247	98.05 199

1112_ss		92.71 168	91.55 183	96.20 120	95.56 220	91.12 126	98.48 193	94.69 348	88.29 213	86.89 245	98.50 116	87.02 110	98.66 178	84.75 260	89.77 251	98.81 152

Test_1112_low_res		92.27 181	90.97 194	96.18 121	95.53 222	91.10 128	98.47 195	94.66 349	88.28 214	86.83 246	93.50 279	87.00 111	98.65 179	84.69 261	89.74 252	98.80 153

cascas		90.93 210	89.33 224	95.76 143	95.69 215	93.03 87	98.99 132	96.59 226	80.49 356	86.79 247	94.45 256	65.23 341	98.60 180	93.52 157	92.18 215	95.66 260

baseline2		94.04 130	93.80 130	94.74 183	93.07 309	90.25 149	98.12 231	98.16 40	89.86 160	86.53 248	96.95 192	95.56 6	98.05 211	91.44 182	94.53 183	95.93 256

OPM-MVS		89.76 233	89.15 227	91.57 268	90.53 347	85.58 277	98.11 233	95.93 280	92.88 85	86.05 249	96.47 215	67.06 327	97.87 221	89.29 212	86.08 269	91.26 325
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
VPA-MVSNet		89.10 241	87.66 256	93.45 225	92.56 313	91.02 132	97.97 244	98.32 30	86.92 251	86.03 250	92.01 303	68.84 310	97.10 267	90.92 187	75.34 334	92.23 288

MonoMVSNet		90.69 215	89.78 215	93.45 225	91.78 330	84.97 291	96.51 310	94.44 353	90.56 139	85.96 251	90.97 327	78.61 241	96.27 314	95.35 120	83.79 288	99.11 123

SDMVSNet		91.09 204	89.91 213	94.65 186	96.80 167	90.54 145	97.78 253	97.81 71	88.34 210	85.73 252	95.26 246	66.44 332	98.26 197	94.25 145	86.75 261	95.14 261

sd_testset		89.23 239	88.05 252	92.74 242	96.80 167	85.33 282	95.85 336	97.03 200	88.34 210	85.73 252	95.26 246	61.12 358	97.76 233	85.61 251	86.75 261	95.14 261

tpm cat1		88.89 245	87.27 262	93.76 221	95.79 211	85.32 283	90.76 393	97.09 195	76.14 379	85.72 254	88.59 370	82.92 183	98.04 212	76.96 329	91.43 234	97.90 204

IB-MVS	89.43 6	92.12 184	90.83 200	95.98 134	95.40 227	90.78 137	99.81 14	98.06 46	91.23 122	85.63 255	93.66 274	90.63 47	98.78 167	91.22 183	71.85 371	98.36 184
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
EI-MVSNet		89.87 232	89.38 223	91.36 271	94.32 272	85.87 271	97.61 268	96.59 226	85.10 283	85.51 256	97.10 182	81.30 216	96.56 288	83.85 278	83.03 294	91.64 304

MVSTER		92.71 168	92.32 163	93.86 218	97.29 140	92.95 91	99.01 130	96.59 226	90.09 154	85.51 256	94.00 263	94.61 15	96.56 288	90.77 192	83.03 294	92.08 296

test_fmvs2		85.10 312	85.45 289	84.02 374	89.85 355	65.63 408	98.49 191	92.59 381	90.45 143	85.43 258	93.32 280	43.94 406	96.59 286	90.81 190	84.19 282	89.85 362

RPSCF		85.33 309	85.55 287	84.67 371	94.63 266	62.28 410	93.73 361	93.76 367	74.38 387	85.23 259	97.06 185	64.09 344	98.31 193	80.98 300	86.08 269	93.41 272

BH-w/o		92.32 178	91.79 178	93.91 217	96.85 164	86.18 259	99.11 118	95.74 300	88.13 217	84.81 260	97.00 189	77.26 249	97.91 217	89.16 214	98.03 121	97.64 209

CLD-MVS		91.06 206	90.71 202	92.10 255	94.05 282	86.10 262	99.55 49	96.29 249	94.16 50	84.70 261	97.17 180	69.62 305	97.82 224	94.74 136	86.08 269	92.39 281
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
tpmvs		89.16 240	87.76 253	93.35 227	97.19 147	84.75 294	90.58 395	97.36 167	81.99 341	84.56 262	89.31 367	83.98 165	98.17 202	74.85 346	90.00 250	97.12 225

nrg030		90.23 223	88.87 232	94.32 199	91.53 335	93.54 74	98.79 153	95.89 290	88.12 218	84.55 263	94.61 255	78.80 238	96.88 275	92.35 175	75.21 335	92.53 280

VPNet		88.30 261	86.57 271	93.49 224	91.95 325	91.35 120	98.18 225	97.20 183	88.61 197	84.52 264	94.89 250	62.21 353	96.76 281	89.34 209	72.26 368	92.36 282

dmvs_re		88.69 255	88.06 251	90.59 288	93.83 292	78.68 361	95.75 339	96.18 257	87.99 223	84.48 265	96.32 220	67.52 322	96.94 273	84.98 258	85.49 273	96.14 252

MVS		93.92 134	92.28 164	98.83 7	95.69 215	96.82 8	96.22 322	98.17 37	84.89 290	84.34 266	98.61 110	79.32 232	99.83 77	93.88 150	99.43 61	99.86 29

mvs_anonymous		92.50 175	91.65 181	95.06 170	96.60 173	89.64 171	97.06 290	96.44 238	86.64 258	84.14 267	93.93 266	82.49 194	96.17 318	91.47 181	96.08 167	99.35 100

Fast-Effi-MVS+-dtu		88.84 247	88.59 241	89.58 318	93.44 302	78.18 365	98.65 166	94.62 350	88.46 202	84.12 268	95.37 244	68.91 308	96.52 291	82.06 294	91.70 225	94.06 267

LS3D		90.19 225	88.72 236	94.59 190	98.97 73	86.33 254	96.90 296	96.60 225	74.96 384	84.06 269	98.74 95	75.78 254	99.83 77	74.93 344	97.57 131	97.62 212

ACMM	86.95 13	88.77 252	88.22 248	90.43 294	93.61 296	81.34 337	98.50 189	95.92 282	87.88 227	83.85 270	95.20 248	67.20 325	97.89 219	86.90 236	84.90 276	92.06 297
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
BH-untuned		91.46 195	90.84 198	93.33 228	96.51 178	84.83 293	98.84 145	95.50 314	86.44 266	83.50 271	96.70 207	75.49 256	97.77 228	86.78 238	97.81 125	97.40 217

FIs		90.70 214	89.87 214	93.18 230	92.29 317	91.12 126	98.17 227	98.25 32	89.11 183	83.44 272	94.82 252	82.26 201	96.17 318	87.76 226	82.76 296	92.25 286

UniMVSNet (Re)		89.50 238	88.32 246	93.03 232	92.21 319	90.96 134	98.90 141	98.39 27	89.13 182	83.22 273	92.03 301	81.69 208	96.34 307	86.79 237	72.53 364	91.81 301

UniMVSNet_NR-MVSNet		89.60 235	88.55 242	92.75 241	92.17 320	90.07 158	98.74 156	98.15 41	88.37 208	83.21 274	93.98 264	82.86 184	95.93 329	86.95 233	72.47 365	92.25 286

DU-MVS		88.83 249	87.51 257	92.79 239	91.46 336	90.07 158	98.71 157	97.62 117	88.87 192	83.21 274	93.68 272	74.63 258	95.93 329	86.95 233	72.47 365	92.36 282

LPG-MVS_test		88.86 246	88.47 244	90.06 303	93.35 304	80.95 344	98.22 221	95.94 277	87.73 233	83.17 276	96.11 226	66.28 333	97.77 228	90.19 197	85.19 274	91.46 315

LGP-MVS_train				90.06 303	93.35 304	80.95 344		95.94 277	87.73 233	83.17 276	96.11 226	66.28 333	97.77 228	90.19 197	85.19 274	91.46 315

miper_enhance_ethall		90.33 221	89.70 216	92.22 250	97.12 154	88.93 192	98.35 211	95.96 274	88.60 198	83.14 278	92.33 298	87.38 98	96.18 317	86.49 240	77.89 318	91.55 312

WBMVS		91.35 199	90.49 206	93.94 215	96.97 161	93.40 78	99.27 92	96.71 217	87.40 241	83.10 279	91.76 311	92.38 29	96.23 315	88.95 216	77.89 318	92.17 292

FC-MVSNet-test		90.22 224	89.40 222	92.67 245	91.78 330	89.86 167	97.89 246	98.22 35	88.81 193	82.96 280	94.66 254	81.90 207	95.96 327	85.89 249	82.52 299	92.20 291

PCF-MVS	89.78 5	91.26 200	89.63 217	96.16 125	95.44 224	91.58 118	95.29 345	96.10 263	85.07 285	82.75 281	97.45 163	78.28 243	99.78 91	80.60 306	95.65 174	97.12 225
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
V42		87.00 280	85.68 285	90.98 278	89.91 352	86.08 263	98.32 214	95.61 308	83.67 309	82.72 282	90.67 336	74.00 269	96.53 290	81.94 296	74.28 347	90.32 351

v1144		86.83 283	85.31 291	91.40 269	89.75 356	87.21 239	98.31 215	95.45 317	83.22 315	82.70 283	90.78 331	73.36 272	96.36 301	79.49 311	74.69 341	90.63 346

Syy-MVS		84.10 329	84.53 306	82.83 380	95.14 240	65.71 407	97.68 263	96.66 220	86.52 262	82.63 284	96.84 200	68.15 315	89.89 403	45.62 418	91.54 229	92.87 274

myMVS_eth3d		88.68 257	89.07 228	87.50 346	95.14 240	79.74 352	97.68 263	96.66 220	86.52 262	82.63 284	96.84 200	85.22 151	89.89 403	69.43 374	91.54 229	92.87 274

v144192		86.40 292	84.89 297	90.91 279	89.48 362	85.59 276	98.21 223	95.43 320	82.45 334	82.62 286	90.58 343	72.79 282	96.36 301	78.45 321	74.04 351	90.79 338

3Dnovator	87.35 11	93.17 162	91.77 179	97.37 54	95.41 226	93.07 85	98.82 146	97.85 62	91.53 112	82.56 287	97.58 157	71.97 288	99.82 80	91.01 186	99.23 73	99.22 113

v2v482		87.27 278	85.76 283	91.78 266	89.59 358	87.58 223	98.56 182	95.54 312	84.53 294	82.51 288	91.78 309	73.11 277	96.47 295	82.07 293	74.14 350	91.30 323

tt0805		86.50 291	84.79 300	91.63 267	91.97 323	81.49 333	96.49 311	97.38 163	82.24 337	82.44 289	95.82 234	51.22 394	98.25 198	84.55 265	80.96 305	95.13 263

Baseline_NR-MVSNet		85.83 301	84.82 299	88.87 334	88.73 370	83.34 312	98.63 170	91.66 394	80.41 359	82.44 289	91.35 319	74.63 258	95.42 348	84.13 271	71.39 374	87.84 380

v1192		86.32 294	84.71 302	91.17 273	89.53 361	86.40 250	98.13 229	95.44 319	82.52 332	82.42 291	90.62 340	71.58 294	96.33 308	77.23 326	74.88 338	90.79 338

test_djsdf		88.26 263	87.73 254	89.84 310	88.05 378	82.21 327	97.77 255	96.17 259	86.84 252	82.41 292	91.95 307	72.07 287	95.99 325	89.83 199	84.50 279	91.32 322

cl22		89.57 236	88.79 235	91.91 258	97.94 110	87.62 222	97.98 243	96.51 233	85.03 286	82.37 293	91.79 308	83.65 167	96.50 292	85.96 246	77.89 318	91.61 309

1314		93.44 149	91.98 172	97.84 34	95.24 231	94.38 57	96.22 322	97.92 57	90.18 150	82.28 294	97.71 150	77.63 247	99.80 85	91.94 178	98.67 103	99.34 102

v1921920		86.02 297	84.44 308	90.77 285	89.32 364	85.20 284	98.10 234	95.35 325	82.19 338	82.25 295	90.71 333	70.73 297	96.30 312	76.85 331	74.49 343	90.80 337

v1240		85.77 304	84.11 311	90.73 286	89.26 365	85.15 287	97.88 248	95.23 334	81.89 344	82.16 296	90.55 345	69.60 306	96.31 309	75.59 341	74.87 339	90.72 343

XVG-ACMP-BASELINE		85.86 300	84.95 296	88.57 335	89.90 353	77.12 372	94.30 354	95.60 309	87.40 241	82.12 297	92.99 290	53.42 388	97.66 238	85.02 257	83.83 285	90.92 334

GBi-Net		86.67 286	84.96 294	91.80 262	95.11 244	88.81 195	96.77 300	95.25 327	82.94 322	82.12 297	90.25 351	62.89 350	94.97 356	79.04 314	80.24 306	91.62 306

test1		86.67 286	84.96 294	91.80 262	95.11 244	88.81 195	96.77 300	95.25 327	82.94 322	82.12 297	90.25 351	62.89 350	94.97 356	79.04 314	80.24 306	91.62 306

FMVSNet3		88.81 251	87.08 265	93.99 214	96.52 177	94.59 52	98.08 238	96.20 253	85.85 271	82.12 297	91.60 314	74.05 268	95.40 349	79.04 314	80.24 306	91.99 299

IterMVS-LS		88.34 260	87.44 258	91.04 276	94.10 278	85.85 272	98.10 234	95.48 315	85.12 282	82.03 301	91.21 323	81.35 215	95.63 342	83.86 277	75.73 332	91.63 305
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
SSC-MVS3.2		85.22 310	83.90 315	89.17 327	91.87 328	79.84 351	97.66 266	96.63 222	86.81 254	81.99 302	91.35 319	55.80 373	96.00 324	76.52 335	76.53 329	91.67 303

miper_ehance_all_eth		88.94 244	88.12 250	91.40 269	95.32 230	86.93 241	97.85 250	95.55 311	84.19 298	81.97 303	91.50 316	84.16 162	95.91 332	84.69 261	77.89 318	91.36 320

MIMVSNet		84.48 321	81.83 333	92.42 248	91.73 332	87.36 231	85.52 404	94.42 357	81.40 347	81.91 304	87.58 375	51.92 391	92.81 382	73.84 354	88.15 255	97.08 229

PS-MVSNAJss		89.54 237	89.05 229	91.00 277	88.77 369	84.36 298	97.39 273	95.97 272	88.47 200	81.88 305	93.80 270	82.48 195	96.50 292	89.34 209	83.34 293	92.15 293

WR-MVS		88.54 259	87.22 264	92.52 246	91.93 327	89.50 174	98.56 182	97.84 63	86.99 246	81.87 306	93.81 269	74.25 267	95.92 331	85.29 253	74.43 344	92.12 294

TranMVSNet+NR-MVSNet		87.75 269	86.31 275	92.07 256	90.81 344	88.56 202	98.33 212	97.18 184	87.76 230	81.87 306	93.90 267	72.45 283	95.43 347	83.13 284	71.30 375	92.23 288

eth_miper_zixun_eth		87.76 268	87.00 267	90.06 303	94.67 264	82.65 324	97.02 293	95.37 323	84.19 298	81.86 308	91.58 315	81.47 212	95.90 333	83.24 280	73.61 353	91.61 309

UniMVSNet_ETH3D		85.65 307	83.79 316	91.21 272	90.41 349	80.75 347	95.36 343	95.78 296	78.76 365	81.83 309	94.33 257	49.86 399	96.66 283	84.30 267	83.52 291	96.22 251

c3_l		88.19 264	87.23 263	91.06 275	94.97 254	86.17 260	97.72 260	95.38 322	83.43 312	81.68 310	91.37 318	82.81 186	95.72 339	84.04 275	73.70 352	91.29 324

DP-MVS		88.75 253	86.56 272	95.34 159	98.92 81	87.45 228	97.64 267	93.52 373	70.55 397	81.49 311	97.25 172	74.43 263	99.88 57	71.14 368	94.09 188	98.67 164

3Dnovator+	87.72 8	93.43 150	91.84 176	98.17 23	95.73 214	95.08 35	98.92 139	97.04 198	91.42 117	81.48 312	97.60 155	74.60 260	99.79 89	90.84 189	98.97 87	99.64 68

QAPM		91.41 196	89.49 220	97.17 63	95.66 217	93.42 77	98.60 177	97.51 141	80.92 354	81.39 313	97.41 165	72.89 281	99.87 61	82.33 291	98.68 102	98.21 194

testing3		87.75 269	88.22 248	86.36 355	94.66 265	77.41 371	99.52 55	97.95 55	86.05 269	81.12 314	96.69 208	86.18 133	89.31 407	61.65 400	90.12 248	92.35 285

XXY-MVS		87.75 269	86.02 279	92.95 237	90.46 348	89.70 170	97.71 262	95.90 288	84.02 300	80.95 315	94.05 258	67.51 323	97.10 267	85.16 254	78.41 315	92.04 298

v148		86.38 293	85.06 293	90.37 298	89.47 363	84.10 302	98.52 185	95.48 315	83.80 305	80.93 316	90.22 354	74.60 260	96.31 309	80.92 302	71.55 373	90.69 344

DIV-MVS_self_test		87.82 266	86.81 269	90.87 282	94.87 259	85.39 281	97.81 251	95.22 335	82.92 325	80.76 317	91.31 321	81.99 204	95.81 336	81.36 298	75.04 337	91.42 318

cl____		87.82 266	86.79 270	90.89 281	94.88 258	85.43 279	97.81 251	95.24 330	82.91 326	80.71 318	91.22 322	81.97 206	95.84 334	81.34 299	75.06 336	91.40 319

FMVSNet2		86.90 281	84.79 300	93.24 229	95.11 244	92.54 100	97.67 265	95.86 294	82.94 322	80.55 319	91.17 324	62.89 350	95.29 351	77.23 326	79.71 312	91.90 300

pmmvs4		87.58 275	86.17 278	91.80 262	89.58 359	88.92 193	97.25 281	95.28 326	82.54 331	80.49 320	93.17 286	75.62 255	96.05 323	82.75 287	78.90 313	90.42 349

reproduce_monomvs		92.11 186	91.82 177	92.98 234	98.25 98	90.55 144	98.38 209	97.93 56	94.81 37	80.46 321	92.37 297	96.46 3	97.17 262	94.06 146	73.61 353	91.23 326

ACMP	87.39 10	88.71 254	88.24 247	90.12 302	93.91 288	81.06 343	98.50 189	95.67 305	89.43 176	80.37 322	95.55 238	65.67 335	97.83 223	90.55 194	84.51 278	91.47 314
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
pmmvs5		85.87 299	84.40 310	90.30 299	88.53 373	84.23 299	98.60 177	93.71 369	81.53 346	80.29 323	92.02 302	64.51 343	95.52 344	82.04 295	78.34 316	91.15 328

test0.0.03 1		88.96 243	88.61 239	90.03 307	91.09 341	84.43 297	98.97 135	97.02 202	90.21 148	80.29 323	96.31 221	84.89 154	91.93 394	72.98 360	85.70 272	93.73 268

miper_lstm_enhance		86.90 281	86.20 277	89.00 331	94.53 267	81.19 340	96.74 304	95.24 330	82.33 336	80.15 325	90.51 347	81.99 204	94.68 365	80.71 304	73.58 355	91.12 329

jajsoiax		87.35 276	86.51 273	89.87 308	87.75 383	81.74 331	97.03 291	95.98 271	88.47 200	80.15 325	93.80 270	61.47 355	96.36 301	89.44 207	84.47 280	91.50 313

mvs_tets		87.09 279	86.22 276	89.71 314	87.87 379	81.39 336	96.73 305	95.90 288	88.19 216	79.99 327	93.61 275	59.96 362	96.31 309	89.40 208	84.34 281	91.43 317

ITE_SJBPF				87.93 340	92.26 318	76.44 375		93.47 374	87.67 236	79.95 328	95.49 241	56.50 372	97.38 256	75.24 342	82.33 300	89.98 360

v8		86.11 296	84.45 307	91.10 274	89.99 351	86.85 242	97.24 282	95.36 324	81.99 341	79.89 329	89.86 360	74.53 262	96.39 299	78.83 318	72.32 367	90.05 358

v10		85.73 305	84.01 313	90.87 282	90.03 350	86.73 244	97.20 285	95.22 335	81.25 349	79.85 330	89.75 361	73.30 275	96.28 313	76.87 330	72.64 363	89.61 366

WR-MVS_H		86.53 290	85.49 288	89.66 317	91.04 342	83.31 313	97.53 270	98.20 36	84.95 289	79.64 331	90.90 329	78.01 245	95.33 350	76.29 336	72.81 361	90.35 350

anonymousdsp		86.69 285	85.75 284	89.53 319	86.46 391	82.94 316	96.39 313	95.71 301	83.97 302	79.63 332	90.70 334	68.85 309	95.94 328	86.01 244	84.02 284	89.72 364

Patchmtry		83.61 334	81.64 334	89.50 320	93.36 303	82.84 321	84.10 412	94.20 362	69.47 403	79.57 333	86.88 385	84.43 159	94.78 362	68.48 379	74.30 346	90.88 335

CP-MVSNet		86.54 289	85.45 289	89.79 312	91.02 343	82.78 322	97.38 275	97.56 130	85.37 279	79.53 334	93.03 288	71.86 290	95.25 352	79.92 309	73.43 359	91.34 321

Patchmatch-test		86.25 295	84.06 312	92.82 238	94.42 268	82.88 320	82.88 416	94.23 361	71.58 393	79.39 335	90.62 340	89.00 71	96.42 298	63.03 396	91.37 237	99.16 116

DSMNet-mixed		81.60 343	81.43 337	82.10 383	84.36 398	60.79 411	93.63 363	86.74 416	79.00 361	79.32 336	87.15 383	63.87 346	89.78 405	66.89 385	91.92 219	95.73 259

MSDG		88.29 262	86.37 274	94.04 212	96.90 163	86.15 261	96.52 309	94.36 359	77.89 371	79.22 337	96.95 192	69.72 303	99.59 111	73.20 359	92.58 206	96.37 250

Anonymous20231211		84.72 316	82.65 328	90.91 279	97.71 116	84.55 296	97.28 279	96.67 219	66.88 410	79.18 338	90.87 330	58.47 366	96.60 285	82.61 289	74.20 348	91.59 311

PS-CasMVS		85.81 302	84.58 305	89.49 322	90.77 345	82.11 328	97.20 285	97.36 167	84.83 291	79.12 339	92.84 291	67.42 324	95.16 354	78.39 322	73.25 360	91.21 327

IterMVS		85.81 302	84.67 303	89.22 325	93.51 298	83.67 308	96.32 316	94.80 344	85.09 284	78.69 340	90.17 357	66.57 331	93.17 379	79.48 312	77.42 325	90.81 336
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PEN-MVS		85.21 311	83.93 314	89.07 330	89.89 354	81.31 338	97.09 289	97.24 176	84.45 296	78.66 341	92.68 294	68.44 313	94.87 359	75.98 338	70.92 376	91.04 331

IterMVS-SCA-FT		85.73 305	84.64 304	89.00 331	93.46 301	82.90 318	96.27 317	94.70 347	85.02 287	78.62 342	90.35 349	66.61 329	93.33 376	79.38 313	77.36 326	90.76 340

OpenMVS	85.28 14	90.75 213	88.84 233	96.48 103	93.58 297	93.51 75	98.80 149	97.41 160	82.59 329	78.62 342	97.49 161	68.00 318	99.82 80	84.52 266	98.55 109	96.11 253

PVSNet_0	83.28 16	87.31 277	85.16 292	93.74 222	94.78 261	84.59 295	98.91 140	98.69 20	89.81 162	78.59 344	93.23 284	61.95 354	99.34 141	94.75 135	55.72 411	97.30 220

EU-MVSNet		84.19 326	84.42 309	83.52 378	88.64 372	67.37 406	96.04 328	95.76 299	85.29 280	78.44 345	93.18 285	70.67 298	91.48 396	75.79 340	75.98 330	91.70 302

v7n		84.42 323	82.75 326	89.43 323	88.15 376	81.86 330	96.75 303	95.67 305	80.53 355	78.38 346	89.43 365	69.89 301	96.35 306	73.83 355	72.13 369	90.07 356

FMVSNet1		83.94 330	81.32 339	91.80 262	91.94 326	88.81 195	96.77 300	95.25 327	77.98 367	78.25 347	90.25 351	50.37 398	94.97 356	73.27 358	77.81 323	91.62 306

D2MVS		87.96 265	87.39 259	89.70 315	91.84 329	83.40 311	98.31 215	98.49 22	88.04 221	78.23 348	90.26 350	73.57 271	96.79 280	84.21 269	83.53 290	88.90 374

mvs5depth		78.17 362	75.56 366	85.97 359	80.43 411	76.44 375	85.46 405	89.24 411	76.39 377	78.17 349	88.26 371	51.73 392	95.73 338	69.31 375	61.09 401	85.73 397

MS-PatchMatch		86.75 284	85.92 281	89.22 325	91.97 323	82.47 326	96.91 295	96.14 261	83.74 306	77.73 350	93.53 278	58.19 367	97.37 258	76.75 332	98.35 115	87.84 380

DTE-MVSNet		84.14 327	82.80 323	88.14 339	88.95 368	79.87 350	96.81 299	96.24 251	83.50 311	77.60 351	92.52 296	67.89 320	94.24 370	72.64 363	69.05 380	90.32 351

COLMAP_ROB	82.69 18	84.54 320	82.82 322	89.70 315	96.72 171	78.85 358	95.89 331	92.83 379	71.55 394	77.54 352	95.89 233	59.40 364	99.14 152	67.26 383	88.26 254	91.11 330
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
OurMVSNet-221017-0		84.13 328	83.59 317	85.77 362	87.81 380	70.24 400	94.89 349	93.65 371	86.08 268	76.53 353	93.28 283	61.41 356	96.14 320	80.95 301	77.69 324	90.93 333

tfpnnormal		83.65 332	81.35 338	90.56 291	91.37 338	88.06 212	97.29 278	97.87 60	78.51 366	76.20 354	90.91 328	64.78 342	96.47 295	61.71 399	73.50 356	87.13 389

ppachtmachnet_test		83.63 333	81.57 336	89.80 311	89.01 366	85.09 288	97.13 288	94.50 352	78.84 363	76.14 355	91.00 326	69.78 302	94.61 366	63.40 394	74.36 345	89.71 365

pm-mvs1		84.68 317	82.78 325	90.40 295	89.58 359	85.18 285	97.31 277	94.73 346	81.93 343	76.05 356	92.01 303	65.48 339	96.11 321	78.75 319	69.14 379	89.91 361

AllTest		84.97 314	83.12 320	90.52 292	96.82 165	78.84 359	95.89 331	92.17 386	77.96 369	75.94 357	95.50 239	55.48 376	99.18 146	71.15 366	87.14 258	93.55 270

TestCases				90.52 292	96.82 165	78.84 359		92.17 386	77.96 369	75.94 357	95.50 239	55.48 376	99.18 146	71.15 366	87.14 258	93.55 270

CL-MVSNet_self_test		79.89 352	78.34 353	84.54 372	81.56 407	75.01 381	96.88 297	95.62 307	81.10 350	75.86 359	85.81 390	68.49 312	90.26 401	63.21 395	56.51 409	88.35 377

testgi		82.29 338	81.00 341	86.17 357	87.24 386	74.84 383	97.39 273	91.62 396	88.63 196	75.85 360	95.42 242	46.07 405	91.55 395	66.87 386	79.94 310	92.12 294

MVP-Stereo		86.61 288	85.83 282	88.93 333	88.70 371	83.85 306	96.07 327	94.41 358	82.15 339	75.64 361	91.96 306	67.65 321	96.45 297	77.20 328	98.72 101	86.51 392
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LF4IMVS		81.94 341	81.17 340	84.25 373	87.23 387	68.87 405	93.35 365	91.93 391	83.35 314	75.40 362	93.00 289	49.25 402	96.65 284	78.88 317	78.11 317	87.22 388

our_test_3		84.47 322	82.80 323	89.50 320	89.01 366	83.90 305	97.03 291	94.56 351	81.33 348	75.36 363	90.52 346	71.69 292	94.54 367	68.81 377	76.84 327	90.07 356

LTVRE_ROB	81.71 19	84.59 319	82.72 327	90.18 300	92.89 311	83.18 314	93.15 366	94.74 345	78.99 362	75.14 364	92.69 293	65.64 336	97.63 241	69.46 373	81.82 302	89.74 363
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
ttmdpeth		79.80 353	77.91 355	85.47 364	83.34 402	75.75 377	95.32 344	91.45 399	76.84 375	74.81 365	91.71 312	53.98 386	94.13 371	72.42 364	61.29 400	86.51 392

Anonymous20231206		80.76 347	79.42 351	84.79 370	84.78 397	72.98 390	96.53 308	92.97 377	79.56 360	74.33 366	88.83 368	61.27 357	92.15 391	60.59 402	75.92 331	89.24 371

FMVSNet5		82.29 338	80.54 343	87.52 345	93.79 294	84.01 303	93.73 361	92.47 383	76.92 374	74.27 367	86.15 389	63.69 348	89.24 408	69.07 376	74.79 340	89.29 370

MVS-HIRNet		79.01 356	75.13 369	90.66 287	93.82 293	81.69 332	85.16 406	93.75 368	54.54 416	74.17 368	59.15 422	57.46 369	96.58 287	63.74 393	94.38 184	93.72 269

ACMH+	83.78 15	84.21 325	82.56 331	89.15 328	93.73 295	79.16 356	96.43 312	94.28 360	81.09 351	74.00 369	94.03 261	54.58 383	97.67 237	76.10 337	78.81 314	90.63 346

kuosan		84.40 324	83.34 318	87.60 344	95.87 208	79.21 355	92.39 375	96.87 209	76.12 380	73.79 370	93.98 264	81.51 210	90.63 399	64.13 392	75.42 333	92.95 273

KD-MVS_2432*1600		82.98 335	80.52 344	90.38 296	94.32 272	88.98 187	92.87 370	95.87 292	80.46 357	73.79 370	87.49 378	82.76 189	93.29 377	70.56 370	46.53 422	88.87 375

miper_refine_blended		82.98 335	80.52 344	90.38 296	94.32 272	88.98 187	92.87 370	95.87 292	80.46 357	73.79 370	87.49 378	82.76 189	93.29 377	70.56 370	46.53 422	88.87 375

NR-MVSNet		87.74 272	86.00 280	92.96 236	91.46 336	90.68 141	96.65 307	97.42 159	88.02 222	73.42 373	93.68 272	77.31 248	95.83 335	84.26 268	71.82 372	92.36 282

test_fmvs3		75.09 372	75.19 368	74.81 393	77.45 416	54.08 419	95.93 329	90.64 403	82.51 333	73.29 374	81.19 404	22.29 422	86.29 415	85.50 252	67.89 384	84.06 406

USDC		84.74 315	82.93 321	90.16 301	91.73 332	83.54 310	95.00 348	93.30 375	88.77 194	73.19 375	93.30 282	53.62 387	97.65 240	75.88 339	81.54 303	89.30 369

KD-MVS_self_test		77.47 366	75.88 365	82.24 381	81.59 406	68.93 404	92.83 372	94.02 365	77.03 373	73.14 376	83.39 395	55.44 378	90.42 400	67.95 380	57.53 408	87.38 384

LCM-MVSNet-Re		88.59 258	88.61 239	88.51 336	95.53 222	72.68 393	96.85 298	88.43 413	88.45 203	73.14 376	90.63 339	75.82 253	94.38 368	92.95 167	95.71 173	98.48 174

TDRefinement		78.01 363	75.31 367	86.10 358	70.06 423	73.84 386	93.59 364	91.58 397	74.51 386	73.08 378	91.04 325	49.63 401	97.12 264	74.88 345	59.47 404	87.33 386

TransMVSNet (Re)		81.97 340	79.61 350	89.08 329	89.70 357	84.01 303	97.26 280	91.85 392	78.84 363	73.07 379	91.62 313	67.17 326	95.21 353	67.50 382	59.46 405	88.02 379

SixPastTwentyTwo		82.63 337	81.58 335	85.79 361	88.12 377	71.01 398	95.17 346	92.54 382	84.33 297	72.93 380	92.08 300	60.41 361	95.61 343	74.47 348	74.15 349	90.75 341

pmmvs6		79.90 351	77.31 358	87.67 343	84.17 399	78.13 366	95.86 335	93.68 370	67.94 407	72.67 381	89.62 363	50.98 396	95.75 337	74.80 347	66.04 390	89.14 372

ACMH	83.09 17	84.60 318	82.61 329	90.57 289	93.18 307	82.94 316	96.27 317	94.92 340	81.01 352	72.61 382	93.61 275	56.54 371	97.79 226	74.31 349	81.07 304	90.99 332
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		78.63 360	76.90 361	83.82 375	82.82 404	72.86 391	95.72 340	93.57 372	73.55 391	72.17 383	84.79 392	49.69 400	92.51 387	65.29 390	74.50 342	86.09 395

Patchmatch-RL test		81.90 342	80.13 346	87.23 349	80.71 409	70.12 402	84.07 413	88.19 414	83.16 317	70.57 384	82.18 401	87.18 105	92.59 385	82.28 292	62.78 396	98.98 132

mvsany_test3		75.85 371	74.52 372	79.83 388	73.53 420	60.64 412	91.73 381	87.87 415	83.91 304	70.55 385	82.52 398	31.12 417	93.66 373	86.66 239	62.83 395	85.19 404

test_0402		78.81 358	76.33 363	86.26 356	91.18 340	78.44 364	95.88 333	91.34 400	68.55 404	70.51 386	89.91 359	52.65 390	94.99 355	47.14 417	79.78 311	85.34 402

dongtai		81.36 344	80.61 342	83.62 377	94.25 277	73.32 389	95.15 347	96.81 211	73.56 390	69.79 387	92.81 292	81.00 218	86.80 414	52.08 415	70.06 378	90.75 341

TinyColmap		80.42 349	77.94 354	87.85 341	92.09 321	78.58 362	93.74 360	89.94 406	74.99 383	69.77 388	91.78 309	46.09 404	97.58 245	65.17 391	77.89 318	87.38 384

dmvs_testset		77.17 367	78.99 352	71.71 396	87.25 385	38.55 433	91.44 385	81.76 424	85.77 273	69.49 389	95.94 232	69.71 304	84.37 416	52.71 414	76.82 328	92.21 290

test20.03		78.51 361	77.48 357	81.62 385	83.07 403	71.03 397	96.11 326	92.83 379	81.66 345	69.31 390	89.68 362	57.53 368	87.29 413	58.65 407	68.47 381	86.53 391

test_vis1_rt		81.31 345	80.05 348	85.11 365	91.29 339	70.66 399	98.98 134	77.39 428	85.76 274	68.80 391	82.40 399	36.56 415	99.44 126	92.67 172	86.55 263	85.24 403

N_pmnet		70.19 378	69.87 380	71.12 398	88.24 375	30.63 437	95.85 336	28.70 436	70.18 399	68.73 392	86.55 387	64.04 345	93.81 372	53.12 413	73.46 357	88.94 373

OpenMVS_ROB	73.86 20	77.99 364	75.06 370	86.77 353	83.81 401	77.94 368	96.38 314	91.53 398	67.54 408	68.38 393	87.13 384	43.94 406	96.08 322	55.03 411	81.83 301	86.29 394

ambc				79.60 389	72.76 422	56.61 416	76.20 420	92.01 390		68.25 394	80.23 408	23.34 421	94.73 363	73.78 356	60.81 402	87.48 383

PM-MVS		74.88 373	72.85 376	80.98 387	78.98 414	64.75 409	90.81 392	85.77 417	80.95 353	68.23 395	82.81 397	29.08 419	92.84 381	76.54 334	62.46 398	85.36 401

pmmvs3		72.86 376	69.76 381	82.17 382	73.86 419	74.19 385	94.20 356	89.01 412	64.23 414	67.72 396	80.91 407	41.48 410	88.65 410	62.40 397	54.02 413	83.68 408

lessismore_v0				85.08 366	85.59 395	69.28 403		90.56 404		67.68 397	90.21 355	54.21 385	95.46 346	73.88 353	62.64 397	90.50 348

K. test v3		81.04 346	79.77 349	84.83 369	87.41 384	70.23 401	95.60 342	93.93 366	83.70 308	67.51 398	89.35 366	55.76 374	93.58 375	76.67 333	68.03 383	90.67 345

MIMVSNet1		75.92 370	73.30 375	83.81 376	81.29 408	75.57 379	92.26 376	92.05 389	73.09 392	67.48 399	86.18 388	40.87 412	87.64 412	55.78 410	70.68 377	88.21 378

ET-MVSNet_ETH3D		92.56 174	91.45 185	95.88 138	96.39 185	94.13 63	99.46 64	96.97 206	92.18 100	66.94 400	98.29 131	94.65 14	94.28 369	94.34 143	83.82 287	99.24 110

pmmvs-eth3d		78.71 359	76.16 364	86.38 354	80.25 412	81.19 340	94.17 357	92.13 388	77.97 368	66.90 401	82.31 400	55.76 374	92.56 386	73.63 357	62.31 399	85.38 400

EG-PatchMatch MVS		79.92 350	77.59 356	86.90 352	87.06 388	77.90 369	96.20 324	94.06 364	74.61 385	66.53 402	88.76 369	40.40 413	96.20 316	67.02 384	83.66 289	86.61 390

test_method		70.10 379	68.66 382	74.41 395	86.30 393	55.84 417	94.47 351	89.82 407	35.18 424	66.15 403	84.75 393	30.54 418	77.96 425	70.40 372	60.33 403	89.44 368

UnsupCasMVSNet_eth		78.90 357	76.67 362	85.58 363	82.81 405	74.94 382	91.98 378	96.31 245	84.64 293	65.84 404	87.71 374	51.33 393	92.23 390	72.89 361	56.50 410	89.56 367

test_f		71.94 377	70.82 378	75.30 392	72.77 421	53.28 420	91.62 382	89.66 409	75.44 382	64.47 405	78.31 412	20.48 423	89.56 406	78.63 320	66.02 391	83.05 411

new-patchmatchnet		74.80 374	72.40 377	81.99 384	78.36 415	72.20 394	94.44 352	92.36 384	77.06 372	63.47 406	79.98 409	51.04 395	88.85 409	60.53 403	54.35 412	84.92 405

new_pmnet		76.02 369	73.71 373	82.95 379	83.88 400	72.85 392	91.26 388	92.26 385	70.44 398	62.60 407	81.37 403	47.64 403	92.32 389	61.85 398	72.10 370	83.68 408

UnsupCasMVSNet_bld		73.85 375	70.14 379	84.99 367	79.44 413	75.73 378	88.53 398	95.24 330	70.12 400	61.94 408	74.81 415	41.41 411	93.62 374	68.65 378	51.13 418	85.62 398

CMPMVS	58.40 21	80.48 348	80.11 347	81.59 386	85.10 396	59.56 413	94.14 358	95.95 276	68.54 405	60.71 409	93.31 281	55.35 379	97.87 221	83.06 285	84.85 277	87.33 386
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
APD_test1		68.93 380	66.98 383	74.77 394	80.62 410	53.15 421	87.97 399	85.01 419	53.76 417	59.26 410	87.52 377	25.19 420	89.95 402	56.20 409	67.33 387	81.19 412

MVStest1		76.56 368	73.43 374	85.96 360	86.30 393	80.88 346	94.26 355	91.74 393	61.98 415	58.53 411	89.96 358	69.30 307	91.47 397	59.26 405	49.56 420	85.52 399

DeepMVS_CX				76.08 391	90.74 346	51.65 424		90.84 402	86.47 265	57.89 412	87.98 372	35.88 416	92.60 384	65.77 389	65.06 393	83.97 407

WB-MVS		66.44 381	66.29 384	66.89 401	74.84 417	44.93 428	93.00 367	84.09 422	71.15 395	55.82 413	81.63 402	63.79 347	80.31 423	21.85 427	50.47 419	75.43 414

SSC-MVS		65.42 382	65.20 385	66.06 402	73.96 418	43.83 429	92.08 377	83.54 423	69.77 401	54.73 414	80.92 406	63.30 349	79.92 424	20.48 428	48.02 421	74.44 415

YYNet1		79.64 355	77.04 360	87.43 348	87.80 381	79.98 349	96.23 321	94.44 353	73.83 389	51.83 415	87.53 376	67.96 319	92.07 393	66.00 388	67.75 386	90.23 353

MDA-MVSNet_test_wron		79.65 354	77.05 359	87.45 347	87.79 382	80.13 348	96.25 320	94.44 353	73.87 388	51.80 416	87.47 380	68.04 317	92.12 392	66.02 387	67.79 385	90.09 354

LCM-MVSNet		60.07 386	56.37 388	71.18 397	54.81 432	48.67 425	82.17 417	89.48 410	37.95 422	49.13 417	69.12 416	13.75 430	81.76 417	59.28 404	51.63 417	83.10 410

MDA-MVSNet-bldmvs		77.82 365	74.75 371	87.03 350	88.33 374	78.52 363	96.34 315	92.85 378	75.57 381	48.87 418	87.89 373	57.32 370	92.49 388	60.79 401	64.80 394	90.08 355

PMMVS2		58.97 387	55.07 390	70.69 399	62.72 427	55.37 418	85.97 403	80.52 425	49.48 418	45.94 419	68.31 417	15.73 428	80.78 421	49.79 416	37.12 424	75.91 413

testf1		56.38 388	53.73 391	64.31 405	64.84 425	45.11 426	80.50 418	75.94 430	38.87 420	42.74 420	75.07 413	11.26 432	81.19 419	41.11 420	53.27 414	66.63 419

APD_test2		56.38 388	53.73 391	64.31 405	64.84 425	45.11 426	80.50 418	75.94 430	38.87 420	42.74 420	75.07 413	11.26 432	81.19 419	41.11 420	53.27 414	66.63 419

FPMVS		61.57 383	60.32 386	65.34 403	60.14 430	42.44 431	91.02 391	89.72 408	44.15 419	42.63 422	80.93 405	19.02 424	80.59 422	42.50 419	72.76 362	73.00 416

test_vis3_rt		61.29 384	58.75 387	68.92 400	67.41 424	52.84 422	91.18 390	59.23 435	66.96 409	41.96 423	58.44 423	11.37 431	94.72 364	74.25 350	57.97 407	59.20 422

Gipuma		54.77 390	52.22 394	62.40 407	86.50 390	59.37 414	50.20 425	90.35 405	36.52 423	41.20 424	49.49 425	18.33 426	81.29 418	32.10 424	65.34 392	46.54 425
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
tmp_tt		53.66 391	52.86 393	56.05 408	32.75 436	41.97 432	73.42 422	76.12 429	21.91 429	39.68 425	96.39 218	42.59 409	65.10 428	78.00 323	14.92 429	61.08 421

E-PMN		41.02 395	40.93 397	41.29 411	61.97 428	33.83 434	84.00 414	65.17 433	27.17 426	27.56 426	46.72 427	17.63 427	60.41 430	19.32 429	18.82 426	29.61 426

ANet_high		50.71 392	46.17 395	64.33 404	44.27 434	52.30 423	76.13 421	78.73 426	64.95 412	27.37 427	55.23 424	14.61 429	67.74 427	36.01 423	18.23 427	72.95 417

EMVS		39.96 396	39.88 398	40.18 412	59.57 431	32.12 436	84.79 411	64.57 434	26.27 427	26.14 428	44.18 430	18.73 425	59.29 431	17.03 430	17.67 428	29.12 427

MVE	44.00 22	41.70 394	37.64 399	53.90 410	49.46 433	43.37 430	65.09 424	66.66 432	26.19 428	25.77 429	48.53 426	3.58 436	63.35 429	26.15 426	27.28 425	54.97 424
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
PMVS	41.42 23	45.67 393	42.50 396	55.17 409	34.28 435	32.37 435	66.24 423	78.71 427	30.72 425	22.04 430	59.59 421	4.59 434	77.85 426	27.49 425	58.84 406	55.29 423
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
testmvs		18.81 398	23.05 401	6.10 415	4.48 437	2.29 440	97.78 253	3.00 438	3.27 431	18.60 431	62.71 419	1.53 438	2.49 434	14.26 432	1.80 431	13.50 429

test123		16.58 400	19.47 402	7.91 414	3.59 438	5.37 439	94.32 353	1.39 439	2.49 432	13.98 432	44.60 429	2.91 437	2.65 433	11.35 433	0.57 432	15.70 428

wuyk23d		16.71 399	16.73 403	16.65 413	60.15 429	25.22 438	41.24 426	5.17 437	6.56 430	5.48 433	3.61 433	3.64 435	22.72 432	15.20 431	9.52 430	1.99 430

EGC-MVSNET		60.70 385	55.37 389	76.72 390	86.35 392	71.08 396	89.96 396	84.44 421	0.38 433	1.50 434	84.09 394	37.30 414	88.10 411	40.85 422	73.44 358	70.97 418

mmdepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

monomultidepth		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

test_blank		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet_test		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

DCPMVS		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

cdsmvs_eth3d_5k		22.52 397	30.03 400	0.00 416	0.00 439	0.00 441	0.00 427	97.17 185	0.00 434	0.00 435	98.77 92	74.35 265	0.00 435	0.00 434	0.00 433	0.00 431

pcd_1.5k_mvsjas		6.87 402	9.16 405	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	82.48 195	0.00 435	0.00 434	0.00 433	0.00 431

sosnet-low-res		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

sosnet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uncertanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

Regformer		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

ab-mvs-re		8.21 401	10.94 404	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	98.50 116	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

uanet		0.00 403	0.00 406	0.00 416	0.00 439	0.00 441	0.00 427	0.00 440	0.00 434	0.00 435	0.00 434	0.00 439	0.00 435	0.00 434	0.00 433	0.00 431

WAC-MVS						79.74 352								67.75 381

MSC_two_6792asdad				99.51 2	99.61 24	98.60 2		97.69 95					99.98 9	99.55 13	99.83 15	99.96 10

No_MVS				99.51 2	99.61 24	98.60 2		97.69 95					99.98 9	99.55 13	99.83 15	99.96 10

eth-test2					0.00 439

eth-test					0.00 439

OPU-MVS				99.49 4	99.64 17	98.51 4	99.77 22				99.19 34	95.12 8	99.97 21	99.90 1	99.92 3	99.99 1

save fliter					99.34 50	93.85 67	99.65 40	97.63 115	95.69 26

test_0728_SECOND				98.77 8	99.66 12	96.37 14	99.72 28	97.68 97					99.98 9	99.64 8	99.82 19	99.96 10

GSMVS																98.84 147

sam_mvs1												88.39 80				98.84 147

sam_mvs												87.08 108

MTGPA								97.45 152

test_post1							90.74 394				41.37 431	85.38 148	96.36 301	83.16 282

test_post											46.00 428	87.37 99	97.11 265

patchmatchnet-post											84.86 391	88.73 76	96.81 278

MTMP							99.21 96	91.09 401

gm-plane-assit					94.69 263	88.14 210			88.22 215		97.20 176		98.29 195	90.79 191

test9_res														98.60 37	99.87 9	99.90 22

agg_prior2														97.84 63	99.87 9	99.91 21

test_prior4						92.00 107	99.41 74

test_prior				97.01 67	99.58 30	91.77 111		97.57 129					99.49 119			99.79 38

新几何2							98.26 218

旧先验1					98.97 73	92.90 93		97.74 82			99.15 44	91.05 38			99.33 65	99.60 73

无先验							98.52 185	97.82 67	87.20 244				99.90 52	87.64 228		99.85 30

原ACMM2							98.69 161

testdata2													99.88 57	84.16 270

segment_acmp												90.56 49

testdata1							97.89 246		92.43 92

plane_prior7					93.84 290	85.73 274

plane_prior6					93.92 287	86.02 267						72.92 279

plane_prior5								96.30 246					97.75 234	93.46 160	86.17 267	92.67 278

plane_prior4											96.52 211

plane_prior2							99.02 128		93.38 73

plane_prior1					93.90 289

plane_prior						86.07 265	99.14 112		93.81 63						86.26 266

n2								0.00 440

nn								0.00 440

door-mid								84.90 420

test11								97.68 97

door								85.30 418

HQP5-MVS						86.39 251

BP-MVS														93.82 153

HQP3-MVS								96.37 242							86.29 264

HQP2-MVS												73.34 273

NP-MVS					93.94 286	86.22 257					96.67 209

ACMMP++_ref															82.64 298

ACMMP++															83.83 285

Test By Simon												83.62 168

High-resolution multi-view benchmark