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.

CNVR-MVS		99.40 1	99.26 1	99.84 6	99.98 2	99.51 6	99.98 15	98.69 68	98.20 8	99.93 1	99.98 2	96.82 21	100.00 1	99.75 28	100.00 1	99.99 23

fmvsm_l_conf0.5_n_a		99.00 15	98.91 14	99.28 45	99.21 103	97.91 79	99.98 15	98.85 56	98.25 5	99.92 2	99.75 69	94.72 64	99.97 54	99.87 19	99.64 91	99.95 71

fmvsm_l_conf0.5_n		98.94 16	98.84 17	99.25 46	99.17 106	97.81 82	99.98 15	98.86 53	98.25 5	99.90 3	99.76 63	94.21 85	99.97 54	99.87 19	99.52 104	99.98 48

patch_mono-2		98.24 57	99.12 5	95.59 228	99.67 78	86.91 346	99.95 53	98.89 49	97.60 22	99.90 3	99.76 63	96.54 27	99.98 44	99.94 11	99.82 79	99.88 85

NCCC		99.37 2	99.25 2	99.71 15	99.96 8	99.15 22	99.97 28	98.62 81	98.02 13	99.90 3	99.95 3	97.33 15	100.00 1	99.54 39	100.00 1	100.00 1

TSAR-MVS + MP.		98.93 17	98.77 19	99.41 38	99.74 70	98.67 49	99.77 145	98.38 161	96.73 53	99.88 6	99.74 76	94.89 59	99.59 149	99.80 25	99.98 32	99.97 58
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
test0726					99.93 24	99.29 15	99.96 35	98.42 145	97.28 32	99.86 7	99.94 4	97.22 17

xiu_mvs_v2_base		98.23 58	97.97 60	99.02 73	98.69 143	98.66 51	99.52 203	98.08 205	97.05 41	99.86 7	99.86 26	90.65 171	99.71 138	99.39 50	98.63 144	98.69 224

test_vis1_n_1920		95.44 175	95.31 167	95.82 224	98.50 162	88.74 325	99.98 15	97.30 284	97.84 16	99.85 9	99.19 142	66.82 363	99.97 54	98.82 82	99.46 111	98.76 219

PS-MVSNAJ		98.44 41	98.20 46	99.16 57	98.80 138	98.92 29	99.54 201	98.17 193	97.34 29	99.85 9	99.85 30	91.20 157	99.89 96	99.41 48	99.67 89	98.69 224

旧先验2							99.46 216		94.21 133	99.85 9			99.95 70	96.96 160

IU-MVS					99.93 24	99.31 10		98.41 150	97.71 19	99.84 12				100.00 1	100.00 1	100.00 1

DVP-MVS		99.30 4	99.16 3	99.73 12	99.93 24	99.29 15	99.95 53	98.32 174	97.28 32	99.83 13	99.91 14	97.22 17	100.00 1	99.99 5	100.00 1	99.89 84
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									96.48 59	99.83 13	99.91 14	97.87 4	100.00 1	99.92 13	100.00 1	100.00 1

SF-MVS		98.67 27	98.40 32	99.50 30	99.77 65	98.67 49	99.90 90	98.21 188	93.53 159	99.81 15	99.89 19	94.70 66	99.86 107	99.84 22	99.93 61	99.96 64

SD-MVS		98.92 18	98.70 20	99.56 25	99.70 77	98.73 46	99.94 69	98.34 171	96.38 65	99.81 15	99.76 63	94.59 67	99.98 44	99.84 22	99.96 46	99.97 58
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
test_fmvsm_n_1920		98.44 41	98.61 24	97.92 145	99.27 102	95.18 187	100.00 1	98.90 47	98.05 12	99.80 17	99.73 78	92.64 129	99.99 36	99.58 38	99.51 107	98.59 227

DVP-MVS++		99.26 6	99.09 9	99.77 8	99.91 39	99.31 10	99.95 53	98.43 133	96.48 59	99.80 17	99.93 11	97.44 12	100.00 1	99.92 13	99.98 32	100.00 1

PC_three_1452									96.96 44	99.80 17	99.79 55	97.49 8	100.00 1	99.99 5	99.98 32	100.00 1

SED-MVS		99.28 5	99.11 7	99.77 8	99.93 24	99.30 12	99.96 35	98.43 133	97.27 34	99.80 17	99.94 4	96.71 22	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_TWO								98.43 133	97.27 34	99.80 17	99.94 4	97.18 19	100.00 1	100.00 1	100.00 1	100.00 1

test_241102_ONE					99.93 24	99.30 12		98.43 133	97.26 36	99.80 17	99.88 21	96.71 22	100.00 1

MSLP-MVS++		99.13 8	99.01 11	99.49 32	99.94 13	98.46 61	99.98 15	98.86 53	97.10 40	99.80 17	99.94 4	95.92 35	100.00 1	99.51 40	100.00 1	100.00 1

SteuartSystems-ACMMP		99.02 13	98.97 13	99.18 52	98.72 142	97.71 84	99.98 15	98.44 125	96.85 46	99.80 17	99.91 14	97.57 6	99.85 108	99.44 46	99.99 21	99.99 23
Skip Steuart: Steuart Systems R&D Blog.
testdata				98.42 119	99.47 93	95.33 179		98.56 92	93.78 153	99.79 25	99.85 30	93.64 102	99.94 78	94.97 187	99.94 55	100.00 1

9.14			98.38 34		99.87 51		99.91 84	98.33 172	93.22 169	99.78 26	99.89 19	94.57 68	99.85 108	99.84 22	99.97 42

SMA-MVS		98.76 24	98.48 29	99.62 20	99.87 51	98.87 33	99.86 115	98.38 161	93.19 170	99.77 27	99.94 4	95.54 41	100.00 1	99.74 30	99.99 21	100.00 1
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
CDPH-MVS		98.65 28	98.36 38	99.49 32	99.94 13	98.73 46	99.87 104	98.33 172	93.97 145	99.76 28	99.87 24	94.99 57	99.75 132	98.55 99	100.00 1	99.98 48

fmvsm_s_conf0.5_n_a		97.73 84	97.72 72	97.77 155	98.63 150	94.26 210	99.96 35	98.92 46	97.18 39	99.75 29	99.69 87	87.00 219	99.97 54	99.46 44	98.89 136	99.08 203

test_one_0601					99.94 13	99.30 12		98.41 150	96.63 56	99.75 29	99.93 11	97.49 8

balanced_conf03		98.27 52	97.99 58	99.11 66	98.64 149	98.43 62	99.47 212	97.79 232	94.56 113	99.74 31	98.35 217	94.33 78	99.25 167	99.12 58	99.96 46	99.64 121

APD-MVS		98.62 29	98.35 39	99.41 38	99.90 42	98.51 59	99.87 104	98.36 165	94.08 137	99.74 31	99.73 78	94.08 88	99.74 134	99.42 47	99.99 21	99.99 23
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
test_fmvs1		95.35 177	95.68 159	94.36 276	98.99 117	84.98 356	99.96 35	96.65 344	97.60 22	99.73 33	98.96 163	71.58 343	99.93 85	98.31 110	99.37 118	98.17 234

test_prior2							99.95 53		95.78 79	99.73 33	99.76 63	96.00 32		99.78 27	100.00 1

TEST9					99.92 31	98.92 29	99.96 35	98.43 133	93.90 150	99.71 35	99.86 26	95.88 36	99.85 108

train_agg		98.88 20	98.65 21	99.59 23	99.92 31	98.92 29	99.96 35	98.43 133	94.35 124	99.71 35	99.86 26	95.94 33	99.85 108	99.69 35	99.98 32	99.99 23

test_8					99.92 31	98.88 32	99.96 35	98.43 133	94.35 124	99.69 37	99.85 30	95.94 33	99.85 108

CS-MVS		97.79 79	97.91 66	97.43 176	99.10 109	94.42 203	99.99 4	97.10 305	95.07 96	99.68 38	99.75 69	92.95 121	98.34 234	98.38 105	99.14 128	99.54 148

test_fmvsmconf_n		98.43 43	98.32 40	98.78 87	98.12 189	96.41 132	99.99 4	98.83 59	98.22 7	99.67 39	99.64 99	91.11 161	99.94 78	99.67 36	99.62 94	99.98 48

test_fmvs1_n		94.25 210	94.36 190	93.92 291	97.68 218	83.70 362	99.90 90	96.57 347	97.40 28	99.67 39	98.88 174	61.82 379	99.92 88	98.23 112	99.13 129	98.14 237

fmvsm_s_conf0.1_n_a		97.09 112	96.90 106	97.63 165	95.65 301	94.21 212	99.83 130	98.50 114	96.27 70	99.65 41	99.64 99	84.72 241	99.93 85	99.04 64	98.84 139	98.74 221

test12				99.43 35	99.74 70	98.56 57		98.40 154		99.65 41		94.76 62	99.75 132		99.98 32	99.99 23

DPE-MVS		99.26 6	99.10 8	99.74 11	99.89 45	99.24 19	99.87 104	98.44 125	97.48 27	99.64 43	99.94 4	96.68 24	99.99 36	99.99 5	100.00 1	99.99 23
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.5_n		97.80 77	97.85 69	97.67 161	99.06 111	94.41 204	99.98 15	98.97 40	97.34 29	99.63 44	99.69 87	87.27 214	99.97 54	99.62 37	99.06 132	98.62 226

agg_prior					99.93 24	98.77 42		98.43 133		99.63 44			99.85 108

EC-MVSNet		97.38 99	97.24 92	97.80 150	97.41 232	95.64 167	99.99 4	97.06 310	94.59 112	99.63 44	99.32 130	89.20 196	98.14 250	98.76 87	99.23 125	99.62 127

xiu_mvs_v1_base_debu		97.43 92	97.06 98	98.55 106	97.74 210	98.14 67	99.31 234	97.86 227	96.43 62	99.62 47	99.69 87	85.56 232	99.68 142	99.05 61	98.31 151	97.83 241

CS-MVS-test		97.88 68	97.94 64	97.70 160	99.28 101	95.20 186	99.98 15	97.15 300	95.53 87	99.62 47	99.79 55	92.08 146	98.38 230	98.75 88	99.28 122	99.52 153

xiu_mvs_v1_base		97.43 92	97.06 98	98.55 106	97.74 210	98.14 67	99.31 234	97.86 227	96.43 62	99.62 47	99.69 87	85.56 232	99.68 142	99.05 61	98.31 151	97.83 241

xiu_mvs_v1_base_debi		97.43 92	97.06 98	98.55 106	97.74 210	98.14 67	99.31 234	97.86 227	96.43 62	99.62 47	99.69 87	85.56 232	99.68 142	99.05 61	98.31 151	97.83 241

原ACMM1				98.96 79	99.73 73	96.99 114		98.51 108	94.06 140	99.62 47	99.85 30	94.97 58	99.96 62	95.11 184	99.95 50	99.92 81

PHI-MVS		98.41 45	98.21 45	99.03 71	99.86 53	97.10 111	99.98 15	98.80 62	90.78 258	99.62 47	99.78 59	95.30 47	100.00 1	99.80 25	99.93 61	99.99 23

mvsany_test1		97.82 74	97.90 67	97.55 168	98.77 140	93.04 242	99.80 139	97.93 218	96.95 45	99.61 53	99.68 93	90.92 165	99.83 118	99.18 56	98.29 154	99.80 96

test_cas_vis1_n_1920		96.59 139	96.23 133	97.65 162	98.22 179	94.23 211	99.99 4	97.25 291	97.77 17	99.58 54	99.08 148	77.10 303	99.97 54	97.64 142	99.45 112	98.74 221

DPM-MVS		98.83 21	98.46 30	99.97 1	99.33 99	99.92 1	99.96 35	98.44 125	97.96 14	99.55 55	99.94 4	97.18 19	100.00 1	93.81 217	99.94 55	99.98 48

新几何1				99.42 37	99.75 69	98.27 64		98.63 80	92.69 190	99.55 55	99.82 46	94.40 71	100.00 1	91.21 253	99.94 55	99.99 23

test_vis1_n		93.61 225	93.03 226	95.35 235	95.86 287	86.94 344	99.87 104	96.36 353	96.85 46	99.54 57	98.79 184	52.41 392	99.83 118	98.64 95	98.97 135	99.29 186

ACMMP_NAP		98.49 37	98.14 50	99.54 27	99.66 79	98.62 55	99.85 118	98.37 164	94.68 110	99.53 58	99.83 43	92.87 123	100.00 1	98.66 94	99.84 74	99.99 23

PMMVS		96.76 130	96.76 114	96.76 199	98.28 175	92.10 263	99.91 84	97.98 213	94.12 135	99.53 58	99.39 125	86.93 220	98.73 200	96.95 161	97.73 166	99.45 164

FOURS1					99.92 31	97.66 88	99.95 53	98.36 165	95.58 85	99.52 60

MSP-MVS		99.09 9	99.12 5	98.98 77	99.93 24	97.24 103	99.95 53	98.42 145	97.50 26	99.52 60	99.88 21	97.43 14	99.71 138	99.50 41	99.98 32	100.00 1
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
fmvsm_s_conf0.1_n		97.30 101	97.21 94	97.60 167	97.38 234	94.40 206	99.90 90	98.64 76	96.47 61	99.51 62	99.65 98	84.99 240	99.93 85	99.22 55	99.09 131	98.46 228

test_part2					99.89 45	99.25 18				99.49 63

APDe-MVS		99.06 11	98.91 14	99.51 29	99.94 13	98.76 45	99.91 84	98.39 157	97.20 38	99.46 64	99.85 30	95.53 43	99.79 123	99.86 21	100.00 1	99.99 23
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
region2R		98.54 33	98.37 36	99.05 69	99.96 8	97.18 106	99.96 35	98.55 98	94.87 103	99.45 65	99.85 30	94.07 89	100.00 1	98.67 92	100.00 1	99.98 48

MVS_0304		99.06 11	98.84 17	99.72 13	99.76 66	99.21 21	99.99 4	99.34 25	98.70 2	99.44 66	99.75 69	93.24 113	99.99 36	99.94 11	99.41 116	99.95 71

HPM-MVS++		99.07 10	98.88 16	99.63 17	99.90 42	99.02 25	99.95 53	98.56 92	97.56 25	99.44 66	99.85 30	95.38 46	100.00 1	99.31 51	99.99 21	99.87 87

MVSFormer		96.94 120	96.60 122	97.95 142	97.28 243	97.70 86	99.55 199	97.27 289	91.17 244	99.43 68	99.54 110	90.92 165	96.89 313	94.67 199	99.62 94	99.25 190

lupinMVS		97.85 70	97.60 77	98.62 99	97.28 243	97.70 86	99.99 4	97.55 255	95.50 89	99.43 68	99.67 94	90.92 165	98.71 203	98.40 104	99.62 94	99.45 164

XVS		98.70 26	98.55 25	99.15 59	99.94 13	97.50 95	99.94 69	98.42 145	96.22 71	99.41 70	99.78 59	94.34 76	99.96 62	98.92 75	99.95 50	99.99 23

X-MVStestdata		93.83 215	92.06 248	99.15 59	99.94 13	97.50 95	99.94 69	98.42 145	96.22 71	99.41 70	41.37 412	94.34 76	99.96 62	98.92 75	99.95 50	99.99 23

SR-MVS-dyc-post		98.31 49	98.17 48	98.71 92	99.79 62	96.37 136	99.76 150	98.31 176	94.43 119	99.40 72	99.75 69	93.28 111	99.78 125	98.90 78	99.92 64	99.97 58

RE-MVS-def			98.13 51		99.79 62	96.37 136	99.76 150	98.31 176	94.43 119	99.40 72	99.75 69	92.95 121		98.90 78	99.92 64	99.97 58

MM		98.83 21	98.53 27	99.76 10	99.59 82	99.33 8	99.99 4	99.76 6	98.39 4	99.39 74	99.80 51	90.49 176	99.96 62	99.89 17	99.43 114	99.98 48

APD-MVS_3200maxsize		98.25 56	98.08 55	98.78 87	99.81 60	96.60 127	99.82 133	98.30 179	93.95 147	99.37 75	99.77 61	92.84 124	99.76 131	98.95 72	99.92 64	99.97 58

PGM-MVS		98.34 48	98.13 51	98.99 75	99.92 31	97.00 113	99.75 153	99.50 17	93.90 150	99.37 75	99.76 63	93.24 113	100.00 1	97.75 141	99.96 46	99.98 48

SR-MVS		98.46 39	98.30 43	98.93 82	99.88 49	97.04 112	99.84 123	98.35 167	94.92 101	99.32 77	99.80 51	93.35 106	99.78 125	99.30 52	99.95 50	99.96 64

ZD-MVS					99.92 31	98.57 56		98.52 105	92.34 209	99.31 78	99.83 43	95.06 52	99.80 121	99.70 34	99.97 42

HFP-MVS		98.56 32	98.37 36	99.14 61	99.96 8	97.43 99	99.95 53	98.61 82	94.77 105	99.31 78	99.85 30	94.22 83	100.00 1	98.70 90	99.98 32	99.98 48

ACMMPR		98.50 36	98.32 40	99.05 69	99.96 8	97.18 106	99.95 53	98.60 84	94.77 105	99.31 78	99.84 41	93.73 99	100.00 1	98.70 90	99.98 32	99.98 48

ETV-MVS		97.92 67	97.80 71	98.25 127	98.14 187	96.48 129	99.98 15	97.63 244	95.61 84	99.29 81	99.46 116	92.55 133	98.82 192	99.02 69	98.54 145	99.46 162

test222					99.55 87	97.41 101	99.34 230	98.55 98	91.86 222	99.27 82	99.83 43	93.84 97			99.95 50	99.99 23

MVSMamba_PlusPlus		97.83 71	97.45 82	98.99 75	98.60 151	98.15 65	99.58 191	97.74 235	90.34 266	99.26 83	98.32 220	94.29 80	99.23 168	99.03 67	99.89 67	99.58 139

bld_raw_conf03		97.82 74	97.45 82	98.94 81	98.51 160	98.15 65	99.58 191	97.74 235	94.01 143	99.26 83	98.38 216	90.66 170	99.09 182	98.99 71	99.89 67	99.58 139

CANet_DTU		96.76 130	96.15 136	98.60 101	98.78 139	97.53 92	99.84 123	97.63 244	97.25 37	99.20 85	99.64 99	81.36 266	99.98 44	92.77 237	98.89 136	98.28 233

EPNet		98.49 37	98.40 32	98.77 89	99.62 81	96.80 122	99.90 90	99.51 16	97.60 22	99.20 85	99.36 128	93.71 100	99.91 89	97.99 125	98.71 143	99.61 130
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
DeepPCF-MVS	95.94 2	97.71 85	98.98 12	93.92 291	99.63 80	81.76 374	99.96 35	98.56 92	99.47 1	99.19 87	99.99 1	94.16 87	100.00 1	99.92 13	99.93 61	100.00 1

VNet		97.21 106	96.57 124	99.13 65	98.97 119	97.82 81	99.03 267	99.21 29	94.31 127	99.18 88	98.88 174	86.26 228	99.89 96	98.93 74	94.32 233	99.69 112

MCST-MVS		99.32 3	99.14 4	99.86 5	99.97 3	99.59 5	99.97 28	98.64 76	98.47 3	99.13 89	99.92 13	96.38 29	100.00 1	99.74 30	100.00 1	100.00 1

DeepC-MVS_fast	96.59 1	98.81 23	98.54 26	99.62 20	99.90 42	98.85 35	99.24 243	98.47 117	98.14 10	99.08 90	99.91 14	93.09 117	100.00 1	99.04 64	99.99 21	100.00 1
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
114514_t		97.41 97	96.83 111	99.14 61	99.51 91	97.83 80	99.89 98	98.27 183	88.48 302	99.06 91	99.66 96	90.30 179	99.64 148	96.32 168	99.97 42	99.96 64

PVSNet	91.05 13	97.13 109	96.69 119	98.45 116	99.52 89	95.81 156	99.95 53	99.65 12	94.73 107	99.04 92	99.21 141	84.48 244	99.95 70	94.92 189	98.74 142	99.58 139

CHOSEN 280x420		99.01 14	99.03 10	98.95 80	99.38 97	98.87 33	98.46 312	99.42 21	97.03 42	99.02 93	99.09 147	99.35 1	98.21 247	99.73 32	99.78 83	99.77 101

MG-MVS		98.91 19	98.65 21	99.68 16	99.94 13	99.07 24	99.64 182	99.44 19	97.33 31	99.00 94	99.72 81	94.03 90	99.98 44	98.73 89	100.00 1	100.00 1

diffmvs		97.00 117	96.64 120	98.09 136	97.64 221	96.17 147	99.81 135	97.19 294	94.67 111	98.95 95	99.28 131	86.43 225	98.76 197	98.37 107	97.42 174	99.33 180
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
HPM-MVS_fast		97.80 77	97.50 80	98.68 94	99.79 62	96.42 131	99.88 101	98.16 197	91.75 227	98.94 96	99.54 110	91.82 152	99.65 147	97.62 144	99.99 21	99.99 23

dcpmvs_2		97.42 96	98.09 54	95.42 233	99.58 86	87.24 342	99.23 244	96.95 321	94.28 130	98.93 97	99.73 78	94.39 74	99.16 178	99.89 17	99.82 79	99.86 89

CP-MVS		98.45 40	98.32 40	98.87 84	99.96 8	96.62 126	99.97 28	98.39 157	94.43 119	98.90 98	99.87 24	94.30 79	100.00 1	99.04 64	99.99 21	99.99 23

test_fmvsmconf0.1_n		97.74 82	97.44 84	98.64 98	95.76 292	96.20 144	99.94 69	98.05 208	98.17 9	98.89 99	99.42 118	87.65 209	99.90 91	99.50 41	99.60 100	99.82 92

testing222		97.08 115	96.75 115	98.06 138	98.56 153	96.82 120	99.85 118	98.61 82	92.53 201	98.84 100	98.84 183	93.36 105	98.30 238	95.84 176	94.30 234	99.05 205

MVS_Test		96.46 143	95.74 155	98.61 100	98.18 183	97.23 104	99.31 234	97.15 300	91.07 249	98.84 100	97.05 260	88.17 205	98.97 185	94.39 203	97.50 171	99.61 130

API-MVS		97.86 69	97.66 74	98.47 114	99.52 89	95.41 176	99.47 212	98.87 52	91.68 228	98.84 100	99.85 30	92.34 140	99.99 36	98.44 103	99.96 46	100.00 1

GST-MVS		98.27 52	97.97 60	99.17 55	99.92 31	97.57 91	99.93 76	98.39 157	94.04 142	98.80 103	99.74 76	92.98 120	100.00 1	98.16 115	99.76 84	99.93 76

MVS_111021_LR		98.42 44	98.38 34	98.53 111	99.39 96	95.79 157	99.87 104	99.86 2	96.70 54	98.78 104	99.79 55	92.03 147	99.90 91	99.17 57	99.86 73	99.88 85

h-mvs33		94.92 186	94.36 190	96.59 205	98.85 135	91.29 284	98.93 276	98.94 41	95.90 76	98.77 105	98.42 215	90.89 168	99.77 128	97.80 134	70.76 379	98.72 223

hse-mvs2		94.38 204	94.08 198	95.31 238	98.27 176	90.02 310	99.29 239	98.56 92	95.90 76	98.77 105	98.00 231	90.89 168	98.26 245	97.80 134	69.20 385	97.64 246

TSAR-MVS + GP.		98.60 30	98.51 28	98.86 85	99.73 73	96.63 125	99.97 28	97.92 221	98.07 11	98.76 107	99.55 108	95.00 56	99.94 78	99.91 16	97.68 168	99.99 23

sss		97.57 88	97.03 102	99.18 52	98.37 167	98.04 72	99.73 161	99.38 22	93.46 161	98.76 107	99.06 150	91.21 156	99.89 96	96.33 167	97.01 185	99.62 127

CostFormer		96.10 156	95.88 152	96.78 198	97.03 249	92.55 255	97.08 354	97.83 230	90.04 273	98.72 109	94.89 338	95.01 55	98.29 239	96.54 166	95.77 210	99.50 158

tpmrst		96.27 155	95.98 142	97.13 188	97.96 196	93.15 238	96.34 366	98.17 193	92.07 215	98.71 110	95.12 329	93.91 93	98.73 200	94.91 191	96.62 190	99.50 158

MVS_111021_HR		98.72 25	98.62 23	99.01 74	99.36 98	97.18 106	99.93 76	99.90 1	96.81 51	98.67 111	99.77 61	93.92 92	99.89 96	99.27 53	99.94 55	99.96 64

MAR-MVS		97.43 92	97.19 95	98.15 133	99.47 93	94.79 197	99.05 264	98.76 63	92.65 193	98.66 112	99.82 46	88.52 203	99.98 44	98.12 117	99.63 93	99.67 115
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
Effi-MVS+		96.30 152	95.69 157	98.16 130	97.85 203	96.26 139	97.41 346	97.21 293	90.37 264	98.65 113	98.58 202	86.61 224	98.70 204	97.11 153	97.37 176	99.52 153

HPM-MVS		97.96 64	97.72 72	98.68 94	99.84 56	96.39 135	99.90 90	98.17 193	92.61 195	98.62 114	99.57 107	91.87 150	99.67 145	98.87 80	99.99 21	99.99 23
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mPP-MVS		98.39 47	98.20 46	98.97 78	99.97 3	96.92 117	99.95 53	98.38 161	95.04 97	98.61 115	99.80 51	93.39 104	100.00 1	98.64 95	100.00 1	99.98 48

jason		97.24 104	96.86 110	98.38 122	95.73 295	97.32 102	99.97 28	97.40 274	95.34 92	98.60 116	99.54 110	87.70 208	98.56 211	97.94 128	99.47 109	99.25 190
jason: jason.
CANet		98.27 52	97.82 70	99.63 17	99.72 75	99.10 23	99.98 15	98.51 108	97.00 43	98.52 117	99.71 83	87.80 207	99.95 70	99.75 28	99.38 117	99.83 91

EI-MVSNet-Vis-set		98.27 52	98.11 53	98.75 90	99.83 57	96.59 128	99.40 220	98.51 108	95.29 93	98.51 118	99.76 63	93.60 103	99.71 138	98.53 100	99.52 104	99.95 71

ZNCC-MVS		98.31 49	98.03 56	99.17 55	99.88 49	97.59 89	99.94 69	98.44 125	94.31 127	98.50 119	99.82 46	93.06 118	99.99 36	98.30 111	99.99 21	99.93 76

LFMVS		94.75 192	93.56 212	98.30 125	99.03 113	95.70 163	98.74 295	97.98 213	87.81 312	98.47 120	99.39 125	67.43 361	99.53 150	98.01 123	95.20 224	99.67 115

tpm2		95.47 174	95.18 172	96.35 213	96.91 256	91.70 277	96.96 357	97.93 218	88.04 309	98.44 121	95.40 315	93.32 108	97.97 259	94.00 210	95.61 214	99.38 171

mvsmamba		96.94 120	96.73 116	97.55 168	97.99 194	94.37 207	99.62 185	97.70 238	93.13 172	98.42 122	97.92 235	88.02 206	98.75 199	98.78 85	99.01 134	99.52 153

alignmvs		97.81 76	97.33 89	99.25 46	98.77 140	98.66 51	99.99 4	98.44 125	94.40 123	98.41 123	99.47 114	93.65 101	99.42 164	98.57 98	94.26 235	99.67 115

UA-Net		96.54 140	95.96 146	98.27 126	98.23 178	95.71 162	98.00 337	98.45 120	93.72 156	98.41 123	99.27 134	88.71 202	99.66 146	91.19 254	97.69 167	99.44 166

DP-MVS Recon		98.41 45	98.02 57	99.56 25	99.97 3	98.70 48	99.92 79	98.44 125	92.06 217	98.40 125	99.84 41	95.68 39	100.00 1	98.19 113	99.71 87	99.97 58

CPTT-MVS		97.64 87	97.32 90	98.58 104	99.97 3	95.77 158	99.96 35	98.35 167	89.90 275	98.36 126	99.79 55	91.18 160	99.99 36	98.37 107	99.99 21	99.99 23

PAPM		98.60 30	98.42 31	99.14 61	96.05 281	98.96 26	99.90 90	99.35 24	96.68 55	98.35 127	99.66 96	96.45 28	98.51 214	99.45 45	99.89 67	99.96 64

HY-MVS	92.50 7	97.79 79	97.17 97	99.63 17	98.98 118	99.32 9	97.49 344	99.52 14	95.69 82	98.32 128	97.41 247	93.32 108	99.77 128	98.08 121	95.75 212	99.81 94

EI-MVSNet-UG-set		98.14 60	97.99 58	98.60 101	99.80 61	96.27 138	99.36 229	98.50 114	95.21 95	98.30 129	99.75 69	93.29 110	99.73 137	98.37 107	99.30 121	99.81 94

PVSNet_BlendedMVS		96.05 157	95.82 154	96.72 201	99.59 82	96.99 114	99.95 53	99.10 31	94.06 140	98.27 130	95.80 296	89.00 198	99.95 70	99.12 58	87.53 290	93.24 347

PVSNet_Blended		97.94 65	97.64 75	98.83 86	99.59 82	96.99 114	100.00 1	99.10 31	95.38 90	98.27 130	99.08 148	89.00 198	99.95 70	99.12 58	99.25 123	99.57 142

MP-MVS		98.23 58	97.97 60	99.03 71	99.94 13	97.17 109	99.95 53	98.39 157	94.70 109	98.26 132	99.81 50	91.84 151	100.00 1	98.85 81	99.97 42	99.93 76
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
WTY-MVS		98.10 62	97.60 77	99.60 22	98.92 126	99.28 17	99.89 98	99.52 14	95.58 85	98.24 133	99.39 125	93.33 107	99.74 134	97.98 127	95.58 215	99.78 100

DELS-MVS		98.54 33	98.22 44	99.50 30	99.15 108	98.65 53	100.00 1	98.58 87	97.70 20	98.21 134	99.24 139	92.58 132	99.94 78	98.63 97	99.94 55	99.92 81
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
ETVMVS		97.03 116	96.64 120	98.20 129	98.67 145	97.12 110	99.89 98	98.57 89	91.10 248	98.17 135	98.59 199	93.86 96	98.19 248	95.64 179	95.24 223	99.28 187

testing11		97.48 91	97.27 91	98.10 135	98.36 168	96.02 151	99.92 79	98.45 120	93.45 163	98.15 136	98.70 189	95.48 44	99.22 170	97.85 133	95.05 225	99.07 204

MDTV_nov1_ep13_2view						96.26 139	96.11 371		91.89 221	98.06 137		94.40 71		94.30 206		99.67 115

PAPR		98.52 35	98.16 49	99.58 24	99.97 3	98.77 42	99.95 53	98.43 133	95.35 91	98.03 138	99.75 69	94.03 90	99.98 44	98.11 118	99.83 75	99.99 23

MDTV_nov1_ep13			95.69 157		97.90 199	94.15 213	95.98 374	98.44 125	93.12 173	97.98 139	95.74 298	95.10 50	98.58 210	90.02 278	96.92 187

test2506		97.53 89	97.19 95	98.58 104	98.66 146	96.90 118	98.81 290	99.77 5	94.93 99	97.95 140	98.96 163	92.51 134	99.20 174	94.93 188	98.15 156	99.64 121

GG-mvs-BLEND				98.54 109	98.21 180	98.01 73	93.87 384	98.52 105		97.92 141	97.92 235	99.02 2	97.94 264	98.17 114	99.58 101	99.67 115

EIA-MVS		97.53 89	97.46 81	97.76 157	98.04 192	94.84 194	99.98 15	97.61 249	94.41 122	97.90 142	99.59 104	92.40 138	98.87 189	98.04 122	99.13 129	99.59 133

test_fmvsmconf0.01_n		96.39 147	95.74 155	98.32 124	91.47 369	95.56 170	99.84 123	97.30 284	97.74 18	97.89 143	99.35 129	79.62 285	99.85 108	99.25 54	99.24 124	99.55 144

sasdasda		97.09 112	96.32 130	99.39 40	98.93 123	98.95 27	99.72 164	97.35 277	94.45 116	97.88 144	99.42 118	86.71 221	99.52 151	98.48 101	93.97 239	99.72 107

test_yl		97.83 71	97.37 87	99.21 49	99.18 104	97.98 75	99.64 182	99.27 27	91.43 237	97.88 144	98.99 157	95.84 37	99.84 116	98.82 82	95.32 221	99.79 97

DCV-MVSNet		97.83 71	97.37 87	99.21 49	99.18 104	97.98 75	99.64 182	99.27 27	91.43 237	97.88 144	98.99 157	95.84 37	99.84 116	98.82 82	95.32 221	99.79 97

canonicalmvs		97.09 112	96.32 130	99.39 40	98.93 123	98.95 27	99.72 164	97.35 277	94.45 116	97.88 144	99.42 118	86.71 221	99.52 151	98.48 101	93.97 239	99.72 107

MGCFI-Net		97.00 117	96.22 134	99.34 43	98.86 134	98.80 39	99.67 176	97.30 284	94.31 127	97.77 148	99.41 122	86.36 227	99.50 155	98.38 105	93.90 241	99.72 107

VDDNet		93.12 236	91.91 251	96.76 199	96.67 271	92.65 253	98.69 301	98.21 188	82.81 364	97.75 149	99.28 131	61.57 380	99.48 161	98.09 120	94.09 237	98.15 235

EPMVS		96.53 141	96.01 139	98.09 136	98.43 165	96.12 150	96.36 365	99.43 20	93.53 159	97.64 150	95.04 331	94.41 70	98.38 230	91.13 255	98.11 159	99.75 103

JIA-IIPM		91.76 269	90.70 270	94.94 248	96.11 279	87.51 340	93.16 387	98.13 202	75.79 386	97.58 151	77.68 400	92.84 124	97.97 259	88.47 294	96.54 191	99.33 180

EPNet_dtu		95.71 167	95.39 164	96.66 203	98.92 126	93.41 234	99.57 195	98.90 47	96.19 73	97.52 152	98.56 204	92.65 128	97.36 281	77.89 367	98.33 150	99.20 193
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
PAPM_NR		98.12 61	97.93 65	98.70 93	99.94 13	96.13 148	99.82 133	98.43 133	94.56 113	97.52 152	99.70 85	94.40 71	99.98 44	97.00 156	99.98 32	99.99 23

FE-MVS		95.70 169	95.01 178	97.79 152	98.21 180	94.57 199	95.03 379	98.69 68	88.90 293	97.50 154	96.19 287	92.60 131	99.49 160	89.99 279	97.94 165	99.31 182

thisisatest0515		97.41 97	97.02 103	98.59 103	97.71 217	97.52 93	99.97 28	98.54 101	91.83 223	97.45 155	99.04 151	97.50 7	99.10 181	94.75 196	96.37 197	99.16 195

OMC-MVS		97.28 102	97.23 93	97.41 177	99.76 66	93.36 237	99.65 178	97.95 216	96.03 75	97.41 156	99.70 85	89.61 187	99.51 153	96.73 165	98.25 155	99.38 171

testing99		97.17 107	96.91 105	97.95 142	98.35 170	95.70 163	99.91 84	98.43 133	92.94 177	97.36 157	98.72 187	94.83 60	99.21 171	97.00 156	94.64 227	98.95 209

testing91		97.16 108	96.90 106	97.97 141	98.35 170	95.67 166	99.91 84	98.42 145	92.91 179	97.33 158	98.72 187	94.81 61	99.21 171	96.98 158	94.63 228	99.03 206

gg-mvs-nofinetune		93.51 227	91.86 253	98.47 114	97.72 215	97.96 77	92.62 388	98.51 108	74.70 390	97.33 158	69.59 403	98.91 3	97.79 268	97.77 139	99.56 102	99.67 115

PatchT		90.38 295	88.75 311	95.25 240	95.99 283	90.16 307	91.22 395	97.54 257	76.80 382	97.26 160	86.01 394	91.88 149	96.07 348	66.16 393	95.91 207	99.51 156

PLC	95.54 3	97.93 66	97.89 68	98.05 139	99.82 58	94.77 198	99.92 79	98.46 119	93.93 148	97.20 161	99.27 134	95.44 45	99.97 54	97.41 146	99.51 107	99.41 169
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
MTAPA		98.29 51	97.96 63	99.30 44	99.85 54	97.93 78	99.39 224	98.28 181	95.76 80	97.18 162	99.88 21	92.74 127	100.00 1	98.67 92	99.88 71	99.99 23

UWE-MVS		96.79 127	96.72 117	97.00 191	98.51 160	93.70 225	99.71 167	98.60 84	92.96 176	97.09 163	98.34 219	96.67 26	98.85 191	92.11 243	96.50 193	98.44 229

PatchmatchNet		95.94 160	95.45 162	97.39 179	97.83 204	94.41 204	96.05 372	98.40 154	92.86 180	97.09 163	95.28 326	94.21 85	98.07 255	89.26 285	98.11 159	99.70 110
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
thisisatest0530		97.10 110	96.72 117	98.22 128	97.60 223	96.70 123	99.92 79	98.54 101	91.11 247	97.07 165	98.97 161	97.47 10	99.03 183	93.73 222	96.09 200	98.92 210

test_fmvsmvis_n_1920		97.67 86	97.59 79	97.91 147	97.02 250	95.34 178	99.95 53	98.45 120	97.87 15	97.02 166	99.59 104	89.64 186	99.98 44	99.41 48	99.34 120	98.42 230

CR-MVSNet		93.45 230	92.62 234	95.94 220	96.29 274	92.66 251	92.01 391	96.23 355	92.62 194	96.94 167	93.31 362	91.04 162	96.03 349	79.23 360	95.96 203	99.13 199

RPMNet		89.76 310	87.28 325	97.19 187	96.29 274	92.66 251	92.01 391	98.31 176	70.19 396	96.94 167	85.87 395	87.25 215	99.78 125	62.69 397	95.96 203	99.13 199

baseline		96.43 144	95.98 142	97.76 157	97.34 237	95.17 188	99.51 205	97.17 297	93.92 149	96.90 169	99.28 131	85.37 236	98.64 208	97.50 145	96.86 189	99.46 162

ECVR-MVS		95.66 170	95.05 176	97.51 172	98.66 146	93.71 224	98.85 287	98.45 120	94.93 99	96.86 170	98.96 163	75.22 326	99.20 174	95.34 181	98.15 156	99.64 121

Vis-MVSNet		95.72 165	95.15 173	97.45 174	97.62 222	94.28 209	99.28 240	98.24 185	94.27 132	96.84 171	98.94 170	79.39 287	98.76 197	93.25 227	98.49 146	99.30 184
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
VDD-MVS		93.77 219	92.94 227	96.27 214	98.55 156	90.22 306	98.77 294	97.79 232	90.85 254	96.82 172	99.42 118	61.18 382	99.77 128	98.95 72	94.13 236	98.82 216

UGNet		95.33 178	94.57 187	97.62 166	98.55 156	94.85 193	98.67 303	99.32 26	95.75 81	96.80 173	96.27 285	72.18 340	99.96 62	94.58 201	99.05 133	98.04 238
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
AdaColmap		97.23 105	96.80 113	98.51 112	99.99 1	95.60 169	99.09 253	98.84 58	93.32 166	96.74 174	99.72 81	86.04 229	100.00 1	98.01 123	99.43 114	99.94 75

tpm		93.70 223	93.41 218	94.58 263	95.36 307	87.41 341	97.01 355	96.90 328	90.85 254	96.72 175	94.14 354	90.40 177	96.84 316	90.75 266	88.54 277	99.51 156

test1111		95.57 172	94.98 179	97.37 180	98.56 153	93.37 236	98.86 285	98.45 120	94.95 98	96.63 176	98.95 168	75.21 327	99.11 179	95.02 186	98.14 158	99.64 121

tttt0517		96.85 124	96.49 126	97.92 145	97.48 230	95.89 155	99.85 118	98.54 101	90.72 259	96.63 176	98.93 172	97.47 10	99.02 184	93.03 234	95.76 211	98.85 214

casdiffmvs		96.42 146	95.97 145	97.77 155	97.30 241	94.98 190	99.84 123	97.09 307	93.75 155	96.58 178	99.26 137	85.07 238	98.78 195	97.77 139	97.04 183	99.54 148
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CNLPA		97.76 81	97.38 86	98.92 83	99.53 88	96.84 119	99.87 104	98.14 201	93.78 153	96.55 179	99.69 87	92.28 141	99.98 44	97.13 152	99.44 113	99.93 76

PatchMatch-RL		96.04 158	95.40 163	97.95 142	99.59 82	95.22 185	99.52 203	99.07 34	93.96 146	96.49 180	98.35 217	82.28 257	99.82 120	90.15 277	99.22 126	98.81 217

MP-MVS-pluss		98.07 63	97.64 75	99.38 42	99.74 70	98.41 63	99.74 156	98.18 192	93.35 164	96.45 181	99.85 30	92.64 129	99.97 54	98.91 77	99.89 67	99.77 101
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
ADS-MVSNet2		93.80 218	93.88 204	93.55 304	97.87 201	85.94 350	94.24 380	96.84 332	90.07 271	96.43 182	94.48 349	90.29 180	95.37 358	87.44 304	97.23 177	99.36 174

ADS-MVSNet		94.79 189	94.02 199	97.11 190	97.87 201	93.79 221	94.24 380	98.16 197	90.07 271	96.43 182	94.48 349	90.29 180	98.19 248	87.44 304	97.23 177	99.36 174

ACMMP		97.74 82	97.44 84	98.66 96	99.92 31	96.13 148	99.18 248	99.45 18	94.84 104	96.41 184	99.71 83	91.40 154	99.99 36	97.99 125	98.03 163	99.87 87
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
PVSNet_Blended_VisFu		97.27 103	96.81 112	98.66 96	98.81 137	96.67 124	99.92 79	98.64 76	94.51 115	96.38 185	98.49 208	89.05 197	99.88 102	97.10 154	98.34 149	99.43 167

AUN-MVS		93.28 231	92.60 235	95.34 236	98.29 173	90.09 309	99.31 234	98.56 92	91.80 226	96.35 186	98.00 231	89.38 190	98.28 241	92.46 238	69.22 384	97.64 246

FA-MVS(test-final)		95.86 161	95.09 175	98.15 133	97.74 210	95.62 168	96.31 367	98.17 193	91.42 239	96.26 187	96.13 290	90.56 174	99.47 162	92.18 242	97.07 181	99.35 177

thres200		96.96 119	96.21 135	99.22 48	98.97 119	98.84 36	99.85 118	99.71 7	93.17 171	96.26 187	98.88 174	89.87 184	99.51 153	94.26 207	94.91 226	99.31 182

HyFIR lowres test		96.66 137	96.43 128	97.36 182	99.05 112	93.91 220	99.70 171	99.80 3	90.54 261	96.26 187	98.08 228	92.15 144	98.23 246	96.84 164	95.46 216	99.93 76

SCA		94.69 193	93.81 206	97.33 184	97.10 246	94.44 201	98.86 285	98.32 174	93.30 167	96.17 190	95.59 305	76.48 313	97.95 262	91.06 257	97.43 172	99.59 133

casdiffmvs_mvg		96.43 144	95.94 148	97.89 149	97.44 231	95.47 172	99.86 115	97.29 287	93.35 164	96.03 191	99.19 142	85.39 235	98.72 202	97.89 132	97.04 183	99.49 160
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
tfpn200view9		96.79 127	95.99 140	99.19 51	98.94 121	98.82 37	99.78 142	99.71 7	92.86 180	96.02 192	98.87 177	89.33 191	99.50 155	93.84 214	94.57 229	99.27 188

thres400		96.78 129	95.99 140	99.16 57	98.94 121	98.82 37	99.78 142	99.71 7	92.86 180	96.02 192	98.87 177	89.33 191	99.50 155	93.84 214	94.57 229	99.16 195

iter_conf05		97.35 100	96.89 109	98.73 91	98.60 151	97.59 89	98.26 324	97.46 266	90.34 266	95.94 194	98.32 220	94.29 80	99.23 168	99.03 67	99.82 79	99.36 174

mamv4		95.24 179	96.90 106	90.25 344	98.65 148	72.11 391	98.28 323	97.64 243	89.99 274	95.93 195	98.25 223	94.74 63	99.11 179	99.01 70	99.64 91	99.53 152

dp		95.05 183	94.43 189	96.91 194	97.99 194	92.73 249	96.29 368	97.98 213	89.70 278	95.93 195	94.67 344	93.83 98	98.45 219	86.91 317	96.53 192	99.54 148

thres100view900		96.74 132	95.92 150	99.18 52	98.90 131	98.77 42	99.74 156	99.71 7	92.59 197	95.84 197	98.86 179	89.25 193	99.50 155	93.84 214	94.57 229	99.27 188

thres600view7		96.69 135	95.87 153	99.14 61	98.90 131	98.78 41	99.74 156	99.71 7	92.59 197	95.84 197	98.86 179	89.25 193	99.50 155	93.44 226	94.50 232	99.16 195

EPP-MVSNet		96.69 135	96.60 122	96.96 193	97.74 210	93.05 241	99.37 227	98.56 92	88.75 296	95.83 199	99.01 154	96.01 31	98.56 211	96.92 162	97.20 179	99.25 190

TESTMET0.1,1		96.74 132	96.26 132	98.16 130	97.36 236	96.48 129	99.96 35	98.29 180	91.93 220	95.77 200	98.07 229	95.54 41	98.29 239	90.55 269	98.89 136	99.70 110

F-COLMAP		96.93 122	96.95 104	96.87 196	99.71 76	91.74 273	99.85 118	97.95 216	93.11 174	95.72 201	99.16 145	92.35 139	99.94 78	95.32 182	99.35 119	98.92 210

test-LLR		96.47 142	96.04 138	97.78 153	97.02 250	95.44 173	99.96 35	98.21 188	94.07 138	95.55 202	96.38 281	93.90 94	98.27 243	90.42 272	98.83 140	99.64 121

test-mter		96.39 147	95.93 149	97.78 153	97.02 250	95.44 173	99.96 35	98.21 188	91.81 225	95.55 202	96.38 281	95.17 48	98.27 243	90.42 272	98.83 140	99.64 121

IS-MVSNet		96.29 153	95.90 151	97.45 174	98.13 188	94.80 196	99.08 255	97.61 249	92.02 219	95.54 204	98.96 163	90.64 172	98.08 253	93.73 222	97.41 175	99.47 161

CHOSEN 1792x2688		96.81 126	96.53 125	97.64 163	98.91 130	93.07 239	99.65 178	99.80 3	95.64 83	95.39 205	98.86 179	84.35 246	99.90 91	96.98 158	99.16 127	99.95 71

CDS-MVSNet		96.34 149	96.07 137	97.13 188	97.37 235	94.96 191	99.53 202	97.91 222	91.55 231	95.37 206	98.32 220	95.05 53	97.13 296	93.80 218	95.75 212	99.30 184
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
Effi-MVS+-dtu		94.53 200	95.30 168	92.22 327	97.77 208	82.54 367	99.59 189	97.06 310	94.92 101	95.29 207	95.37 319	85.81 230	97.89 265	94.80 194	97.07 181	96.23 262

CSCG		97.10 110	97.04 101	97.27 186	99.89 45	91.92 268	99.90 90	99.07 34	88.67 298	95.26 208	99.82 46	93.17 116	99.98 44	98.15 116	99.47 109	99.90 83

Vis-MVSNet (Re-imp)		96.32 150	95.98 142	97.35 183	97.93 198	94.82 195	99.47 212	98.15 200	91.83 223	95.09 209	99.11 146	91.37 155	97.47 279	93.47 225	97.43 172	99.74 104

TAMVS		95.85 162	95.58 160	96.65 204	97.07 247	93.50 231	99.17 249	97.82 231	91.39 241	95.02 210	98.01 230	92.20 142	97.30 286	93.75 221	95.83 209	99.14 198

XVG-OURS-SEG-HR		94.79 189	94.70 186	95.08 243	98.05 191	89.19 320	99.08 255	97.54 257	93.66 157	94.87 211	99.58 106	78.78 294	99.79 123	97.31 148	93.40 246	96.25 260

XVG-OURS		94.82 187	94.74 185	95.06 244	98.00 193	89.19 320	99.08 255	97.55 255	94.10 136	94.71 212	99.62 102	80.51 278	99.74 134	96.04 172	93.06 251	96.25 260

ab-mvs		94.69 193	93.42 216	98.51 112	98.07 190	96.26 139	96.49 363	98.68 70	90.31 268	94.54 213	97.00 262	76.30 315	99.71 138	95.98 173	93.38 247	99.56 143

TAPA-MVS	92.12 8	94.42 203	93.60 209	96.90 195	99.33 99	91.78 272	99.78 142	98.00 210	89.89 276	94.52 214	99.47 114	91.97 148	99.18 176	69.90 385	99.52 104	99.73 105
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
TR-MVS		94.54 198	93.56 212	97.49 173	97.96 196	94.34 208	98.71 298	97.51 262	90.30 269	94.51 215	98.69 190	75.56 321	98.77 196	92.82 236	95.99 202	99.35 177

Fast-Effi-MVS+		95.02 184	94.19 195	97.52 171	97.88 200	94.55 200	99.97 28	97.08 308	88.85 295	94.47 216	97.96 234	84.59 243	98.41 222	89.84 281	97.10 180	99.59 133

DeepC-MVS	94.51 4	96.92 123	96.40 129	98.45 116	99.16 107	95.90 154	99.66 177	98.06 206	96.37 68	94.37 217	99.49 113	83.29 253	99.90 91	97.63 143	99.61 98	99.55 144
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
RPSCF		91.80 266	92.79 231	88.83 355	98.15 186	69.87 393	98.11 333	96.60 346	83.93 355	94.33 218	99.27 134	79.60 286	99.46 163	91.99 244	93.16 249	97.18 253

WB-MVSnew		92.90 241	92.77 232	93.26 311	96.95 254	93.63 227	99.71 167	98.16 197	91.49 232	94.28 219	98.14 226	81.33 267	96.48 330	79.47 359	95.46 216	89.68 383

BH-RMVSNet		95.18 180	94.31 193	97.80 150	98.17 184	95.23 184	99.76 150	97.53 259	92.52 202	94.27 220	99.25 138	76.84 308	98.80 193	90.89 263	99.54 103	99.35 177

CVMVSNet		94.68 195	94.94 180	93.89 294	96.80 264	86.92 345	99.06 260	98.98 38	94.45 116	94.23 221	99.02 152	85.60 231	95.31 360	90.91 262	95.39 219	99.43 167

baseline1		95.78 164	94.86 181	98.54 109	98.47 164	98.07 70	99.06 260	97.99 211	92.68 191	94.13 222	98.62 198	93.28 111	98.69 205	93.79 219	85.76 298	98.84 215

Anonymous202405211		93.10 237	91.99 249	96.40 210	99.10 109	89.65 316	98.88 281	97.93 218	83.71 357	94.00 223	98.75 186	68.79 353	99.88 102	95.08 185	91.71 253	99.68 113

cascas		94.64 196	93.61 207	97.74 159	97.82 205	96.26 139	99.96 35	97.78 234	85.76 337	94.00 223	97.54 244	76.95 307	99.21 171	97.23 150	95.43 218	97.76 245

Anonymous20240529		92.10 259	90.65 271	96.47 206	98.82 136	90.61 297	98.72 297	98.67 73	75.54 387	93.90 225	98.58 202	66.23 365	99.90 91	94.70 198	90.67 256	98.90 213

LS3D		95.84 163	95.11 174	98.02 140	99.85 54	95.10 189	98.74 295	98.50 114	87.22 319	93.66 226	99.86 26	87.45 212	99.95 70	90.94 261	99.81 82	99.02 207

GeoE		94.36 207	93.48 214	96.99 192	97.29 242	93.54 230	99.96 35	96.72 341	88.35 305	93.43 227	98.94 170	82.05 258	98.05 256	88.12 299	96.48 195	99.37 173

HQP-NCC					95.78 288		99.87 104		96.82 48	93.37 228

ACMP_Plane					95.78 288		99.87 104		96.82 48	93.37 228

HQP4-MVS										93.37 228			98.39 226			94.53 268

HQP-MVS		94.61 197	94.50 188	94.92 249	95.78 288	91.85 269	99.87 104	97.89 223	96.82 48	93.37 228	98.65 194	80.65 276	98.39 226	97.92 129	89.60 258	94.53 268

HQP_MVS		94.49 201	94.36 190	94.87 250	95.71 298	91.74 273	99.84 123	97.87 225	96.38 65	93.01 232	98.59 199	80.47 280	98.37 232	97.79 137	89.55 261	94.52 270

plane_prior3						91.64 279			96.63 56	93.01 232

GA-MVS		93.83 215	92.84 228	96.80 197	95.73 295	93.57 228	99.88 101	97.24 292	92.57 199	92.92 234	96.66 273	78.73 295	97.67 273	87.75 302	94.06 238	99.17 194

tpm cat1		93.51 227	92.52 241	96.47 206	97.77 208	91.47 283	96.13 370	98.06 206	80.98 372	92.91 235	93.78 357	89.66 185	98.87 189	87.03 313	96.39 196	99.09 201

1112_ss		96.01 159	95.20 171	98.42 119	97.80 206	96.41 132	99.65 178	96.66 343	92.71 188	92.88 236	99.40 123	92.16 143	99.30 165	91.92 246	93.66 242	99.55 144

Test_1112_low_res		95.72 165	94.83 182	98.42 119	97.79 207	96.41 132	99.65 178	96.65 344	92.70 189	92.86 237	96.13 290	92.15 144	99.30 165	91.88 247	93.64 243	99.55 144

IB-MVS	92.85 6	94.99 185	93.94 202	98.16 130	97.72 215	95.69 165	99.99 4	98.81 60	94.28 130	92.70 238	96.90 264	95.08 51	99.17 177	96.07 171	73.88 374	99.60 132
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
Fast-Effi-MVS+-dtu		93.72 222	93.86 205	93.29 309	97.06 248	86.16 348	99.80 139	96.83 333	92.66 192	92.58 239	97.83 240	81.39 265	97.67 273	89.75 282	96.87 188	96.05 265

SDMVSNet		94.80 188	93.96 201	97.33 184	98.92 126	95.42 175	99.59 189	98.99 37	92.41 206	92.55 240	97.85 238	75.81 320	98.93 188	97.90 131	91.62 254	97.64 246

sd_testset		93.55 226	92.83 229	95.74 226	98.92 126	90.89 292	98.24 326	98.85 56	92.41 206	92.55 240	97.85 238	71.07 348	98.68 206	93.93 211	91.62 254	97.64 246

dmvs_re		93.20 233	93.15 224	93.34 307	96.54 272	83.81 361	98.71 298	98.51 108	91.39 241	92.37 242	98.56 204	78.66 296	97.83 267	93.89 212	89.74 257	98.38 231

tpmvs		94.28 209	93.57 211	96.40 210	98.55 156	91.50 282	95.70 378	98.55 98	87.47 314	92.15 243	94.26 353	91.42 153	98.95 187	88.15 297	95.85 208	98.76 219

Syy-MVS		90.00 306	90.63 272	88.11 362	97.68 218	74.66 389	99.71 167	98.35 167	90.79 256	92.10 244	98.67 191	79.10 292	93.09 382	63.35 396	95.95 205	96.59 258

myMVS_eth3d		94.46 202	94.76 184	93.55 304	97.68 218	90.97 287	99.71 167	98.35 167	90.79 256	92.10 244	98.67 191	92.46 137	93.09 382	87.13 310	95.95 205	96.59 258

BH-w/o		95.71 167	95.38 165	96.68 202	98.49 163	92.28 259	99.84 123	97.50 263	92.12 214	92.06 246	98.79 184	84.69 242	98.67 207	95.29 183	99.66 90	99.09 201

VPA-MVSNet		92.70 246	91.55 258	96.16 216	95.09 309	96.20 144	98.88 281	99.00 36	91.02 251	91.82 247	95.29 325	76.05 319	97.96 261	95.62 180	81.19 332	94.30 286

baseline2		96.71 134	96.49 126	97.37 180	95.63 303	95.96 153	99.74 156	98.88 51	92.94 177	91.61 248	98.97 161	97.72 5	98.62 209	94.83 193	98.08 162	97.53 251

OPM-MVS		93.21 232	92.80 230	94.44 272	93.12 343	90.85 293	99.77 145	97.61 249	96.19 73	91.56 249	98.65 194	75.16 328	98.47 215	93.78 220	89.39 264	93.99 316
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
EI-MVSNet		93.73 221	93.40 219	94.74 255	96.80 264	92.69 250	99.06 260	97.67 241	88.96 290	91.39 250	99.02 152	88.75 201	97.30 286	91.07 256	87.85 285	94.22 291

MVSTER		95.53 173	95.22 170	96.45 208	98.56 153	97.72 83	99.91 84	97.67 241	92.38 208	91.39 250	97.14 254	97.24 16	97.30 286	94.80 194	87.85 285	94.34 285

testing3		93.92 213	94.23 194	92.99 318	97.54 225	90.23 305	99.99 4	99.16 30	90.57 260	91.33 252	98.63 197	92.99 119	92.52 386	82.46 344	95.39 219	96.22 263

test_fmvs2		89.47 314	89.70 291	88.77 358	94.54 319	75.74 386	99.83 130	94.70 383	94.71 108	91.08 253	96.82 272	54.46 389	97.78 270	92.87 235	88.27 280	92.80 355

BH-untuned		95.18 180	94.83 182	96.22 215	98.36 168	91.22 285	99.80 139	97.32 282	90.91 252	91.08 253	98.67 191	83.51 250	98.54 213	94.23 208	99.61 98	98.92 210

CLD-MVS		94.06 212	93.90 203	94.55 265	96.02 282	90.69 294	99.98 15	97.72 237	96.62 58	91.05 255	98.85 182	77.21 302	98.47 215	98.11 118	89.51 263	94.48 272
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
MVS		96.60 138	95.56 161	99.72 13	96.85 261	99.22 20	98.31 321	98.94 41	91.57 230	90.90 256	99.61 103	86.66 223	99.96 62	97.36 147	99.88 71	99.99 23

MSDG		94.37 205	93.36 220	97.40 178	98.88 133	93.95 219	99.37 227	97.38 275	85.75 339	90.80 257	99.17 144	84.11 248	99.88 102	86.35 318	98.43 148	98.36 232

VPNet		91.81 263	90.46 274	95.85 223	94.74 315	95.54 171	98.98 270	98.59 86	92.14 213	90.77 258	97.44 246	68.73 355	97.54 277	94.89 192	77.89 357	94.46 273

MIMVSNet		90.30 298	88.67 312	95.17 242	96.45 273	91.64 279	92.39 389	97.15 300	85.99 334	90.50 259	93.19 364	66.95 362	94.86 367	82.01 348	93.43 245	99.01 208

mvs_anonymous		95.65 171	95.03 177	97.53 170	98.19 182	95.74 160	99.33 231	97.49 264	90.87 253	90.47 260	97.10 256	88.23 204	97.16 293	95.92 174	97.66 169	99.68 113

Patchmatch-test		92.65 249	91.50 259	96.10 218	96.85 261	90.49 300	91.50 393	97.19 294	82.76 365	90.23 261	95.59 305	95.02 54	98.00 258	77.41 369	96.98 186	99.82 92

LPG-MVS_test		92.96 239	92.71 233	93.71 298	95.43 305	88.67 327	99.75 153	97.62 246	92.81 183	90.05 262	98.49 208	75.24 324	98.40 224	95.84 176	89.12 265	94.07 308

LGP-MVS_train				93.71 298	95.43 305	88.67 327		97.62 246	92.81 183	90.05 262	98.49 208	75.24 324	98.40 224	95.84 176	89.12 265	94.07 308

DP-MVS		94.54 198	93.42 216	97.91 147	99.46 95	94.04 215	98.93 276	97.48 265	81.15 371	90.04 264	99.55 108	87.02 218	99.95 70	88.97 287	98.11 159	99.73 105

test_djsdf		92.83 243	92.29 244	94.47 270	91.90 363	92.46 256	99.55 199	97.27 289	91.17 244	89.96 265	96.07 293	81.10 269	96.89 313	94.67 199	88.91 267	94.05 310

ACMM	91.95 10	92.88 242	92.52 241	93.98 290	95.75 294	89.08 323	99.77 145	97.52 261	93.00 175	89.95 266	97.99 233	76.17 317	98.46 218	93.63 224	88.87 269	94.39 280
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
1314		96.84 125	95.96 146	99.48 34	96.74 268	98.52 58	98.31 321	98.86 53	95.82 78	89.91 267	98.98 159	87.49 211	99.96 62	97.80 134	99.73 86	99.96 64

XVG-ACMP-BASELINE		91.22 278	90.75 269	92.63 324	93.73 332	85.61 351	98.52 311	97.44 268	92.77 186	89.90 268	96.85 268	66.64 364	98.39 226	92.29 240	88.61 274	93.89 324

miper_enhance_ethall		94.36 207	93.98 200	95.49 229	98.68 144	95.24 183	99.73 161	97.29 287	93.28 168	89.86 269	95.97 294	94.37 75	97.05 302	92.20 241	84.45 310	94.19 294

nrg030		93.51 227	92.53 240	96.45 208	94.36 321	97.20 105	99.81 135	97.16 299	91.60 229	89.86 269	97.46 245	86.37 226	97.68 272	95.88 175	80.31 344	94.46 273

V42		91.28 275	90.12 286	94.74 255	93.42 338	93.46 232	99.68 174	97.02 313	87.36 316	89.85 271	95.05 330	81.31 268	97.34 283	87.34 307	80.07 346	93.40 342

v144192		90.79 286	89.52 296	94.59 262	93.11 344	92.77 245	99.56 197	96.99 316	86.38 330	89.82 272	94.95 337	80.50 279	97.10 299	83.98 334	80.41 342	93.90 323

GBi-Net		90.88 283	89.82 289	94.08 283	97.53 226	91.97 264	98.43 315	96.95 321	87.05 320	89.68 273	94.72 340	71.34 344	96.11 344	87.01 314	85.65 299	94.17 295

test1		90.88 283	89.82 289	94.08 283	97.53 226	91.97 264	98.43 315	96.95 321	87.05 320	89.68 273	94.72 340	71.34 344	96.11 344	87.01 314	85.65 299	94.17 295

FMVSNet3		92.69 247	91.58 256	95.99 219	98.29 173	97.42 100	99.26 242	97.62 246	89.80 277	89.68 273	95.32 321	81.62 264	96.27 339	87.01 314	85.65 299	94.29 287

IterMVS-LS		92.69 247	92.11 246	94.43 274	96.80 264	92.74 247	99.45 217	96.89 329	88.98 288	89.65 276	95.38 318	88.77 200	96.34 336	90.98 260	82.04 326	94.22 291
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1144		91.09 279	89.83 288	94.87 250	93.25 340	93.69 226	99.62 185	96.98 318	86.83 326	89.64 277	94.99 335	80.94 271	97.05 302	85.08 328	81.16 333	93.87 326

v1921920		90.46 293	89.12 303	94.50 268	92.96 348	92.46 256	99.49 209	96.98 318	86.10 333	89.61 278	95.30 322	78.55 298	97.03 307	82.17 347	80.89 340	94.01 313

v1192		90.62 291	89.25 301	94.72 257	93.13 341	93.07 239	99.50 207	97.02 313	86.33 331	89.56 279	95.01 332	79.22 289	97.09 301	82.34 346	81.16 333	94.01 313

PCF-MVS	94.20 5	95.18 180	94.10 197	98.43 118	98.55 156	95.99 152	97.91 339	97.31 283	90.35 265	89.48 280	99.22 140	85.19 237	99.89 96	90.40 274	98.47 147	99.41 169
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
3Dnovator	91.47 12	96.28 154	95.34 166	99.08 68	96.82 263	97.47 98	99.45 217	98.81 60	95.52 88	89.39 281	99.00 156	81.97 259	99.95 70	97.27 149	99.83 75	99.84 90

v1240		90.20 301	88.79 310	94.44 272	93.05 346	92.27 260	99.38 225	96.92 327	85.89 335	89.36 282	94.87 339	77.89 301	97.03 307	80.66 354	81.08 336	94.01 313

FIs		94.10 211	93.43 215	96.11 217	94.70 316	96.82 120	99.58 191	98.93 45	92.54 200	89.34 283	97.31 250	87.62 210	97.10 299	94.22 209	86.58 294	94.40 279

ITE_SJBPF				92.38 325	95.69 300	85.14 354		95.71 365	92.81 183	89.33 284	98.11 227	70.23 350	98.42 221	85.91 323	88.16 282	93.59 339

v2v482		91.30 273	90.07 287	95.01 245	93.13 341	93.79 221	99.77 145	97.02 313	88.05 308	89.25 285	95.37 319	80.73 274	97.15 294	87.28 308	80.04 347	94.09 307

UniMVSNet (Re)		93.07 238	92.13 245	95.88 221	94.84 313	96.24 143	99.88 101	98.98 38	92.49 204	89.25 285	95.40 315	87.09 217	97.14 295	93.13 232	78.16 355	94.26 288

tt0805		91.28 275	90.18 283	94.60 261	96.26 276	87.55 339	98.39 319	98.72 65	89.00 287	89.22 287	98.47 212	62.98 376	98.96 186	90.57 268	88.00 284	97.28 252

UniMVSNet_NR-MVSNet		92.95 240	92.11 246	95.49 229	94.61 318	95.28 181	99.83 130	99.08 33	91.49 232	89.21 288	96.86 267	87.14 216	96.73 321	93.20 228	77.52 360	94.46 273

DU-MVS		92.46 252	91.45 261	95.49 229	94.05 326	95.28 181	99.81 135	98.74 64	92.25 212	89.21 288	96.64 275	81.66 262	96.73 321	93.20 228	77.52 360	94.46 273

eth_miper_zixun_eth		92.41 253	91.93 250	93.84 295	97.28 243	90.68 295	98.83 288	96.97 320	88.57 301	89.19 290	95.73 300	89.24 195	96.69 323	89.97 280	81.55 329	94.15 301

cl22		93.77 219	93.25 223	95.33 237	99.49 92	94.43 202	99.61 187	98.09 203	90.38 263	89.16 291	95.61 303	90.56 174	97.34 283	91.93 245	84.45 310	94.21 293

Baseline_NR-MVSNet		90.33 297	89.51 297	92.81 322	92.84 349	89.95 312	99.77 145	93.94 390	84.69 351	89.04 292	95.66 302	81.66 262	96.52 328	90.99 259	76.98 366	91.97 366

FC-MVSNet-test		93.81 217	93.15 224	95.80 225	94.30 323	96.20 144	99.42 219	98.89 49	92.33 210	89.03 293	97.27 252	87.39 213	96.83 317	93.20 228	86.48 295	94.36 281

QAPM		95.40 176	94.17 196	99.10 67	96.92 255	97.71 84	99.40 220	98.68 70	89.31 281	88.94 294	98.89 173	82.48 256	99.96 62	93.12 233	99.83 75	99.62 127

miper_ehance_all_eth		93.16 235	92.60 235	94.82 254	97.57 224	93.56 229	99.50 207	97.07 309	88.75 296	88.85 295	95.52 309	90.97 164	96.74 320	90.77 265	84.45 310	94.17 295

AllTest		92.48 251	91.64 254	95.00 246	99.01 114	88.43 331	98.94 275	96.82 335	86.50 328	88.71 296	98.47 212	74.73 330	99.88 102	85.39 325	96.18 198	96.71 256

TestCases				95.00 246	99.01 114	88.43 331		96.82 335	86.50 328	88.71 296	98.47 212	74.73 330	99.88 102	85.39 325	96.18 198	96.71 256

c3_l		92.53 250	91.87 252	94.52 266	97.40 233	92.99 243	99.40 220	96.93 326	87.86 310	88.69 298	95.44 313	89.95 183	96.44 332	90.45 271	80.69 341	94.14 304

pmmvs4		92.10 259	91.07 267	95.18 241	92.82 351	94.96 191	99.48 211	96.83 333	87.45 315	88.66 299	96.56 279	83.78 249	96.83 317	89.29 284	84.77 308	93.75 332

kuosan		93.17 234	92.60 235	94.86 253	98.40 166	89.54 318	98.44 314	98.53 104	84.46 352	88.49 300	97.92 235	90.57 173	97.05 302	83.10 340	93.49 244	97.99 239

PS-MVSNAJss		93.64 224	93.31 221	94.61 260	92.11 360	92.19 261	99.12 251	97.38 275	92.51 203	88.45 301	96.99 263	91.20 157	97.29 289	94.36 204	87.71 287	94.36 281

UniMVSNet_ETH3D		90.06 305	88.58 313	94.49 269	94.67 317	88.09 336	97.81 342	97.57 254	83.91 356	88.44 302	97.41 247	57.44 386	97.62 275	91.41 251	88.59 276	97.77 244

TranMVSNet+NR-MVSNet		91.68 270	90.61 273	94.87 250	93.69 333	93.98 218	99.69 172	98.65 74	91.03 250	88.44 302	96.83 271	80.05 283	96.18 342	90.26 276	76.89 368	94.45 278

FMVSNet2		91.02 280	89.56 294	95.41 234	97.53 226	95.74 160	98.98 270	97.41 273	87.05 320	88.43 304	95.00 334	71.34 344	96.24 341	85.12 327	85.21 304	94.25 290

COLMAP_ROB	90.47 14	92.18 258	91.49 260	94.25 279	99.00 116	88.04 337	98.42 318	96.70 342	82.30 367	88.43 304	99.01 154	76.97 306	99.85 108	86.11 321	96.50 193	94.86 267
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
3Dnovator+	91.53 11	96.31 151	95.24 169	99.52 28	96.88 260	98.64 54	99.72 164	98.24 185	95.27 94	88.42 306	98.98 159	82.76 255	99.94 78	97.10 154	99.83 75	99.96 64

v148		90.70 287	89.63 292	93.92 291	92.97 347	90.97 287	99.75 153	96.89 329	87.51 313	88.27 307	95.01 332	81.67 261	97.04 305	87.40 306	77.17 365	93.75 332

DSMNet-mixed		88.28 323	88.24 318	88.42 360	89.64 382	75.38 388	98.06 335	89.86 403	85.59 341	88.20 308	92.14 372	76.15 318	91.95 389	78.46 365	96.05 201	97.92 240

WR-MVS		92.31 255	91.25 263	95.48 232	94.45 320	95.29 180	99.60 188	98.68 70	90.10 270	88.07 309	96.89 265	80.68 275	96.80 319	93.14 231	79.67 348	94.36 281

test0.0.03 1		93.86 214	93.61 207	94.64 259	95.02 312	92.18 262	99.93 76	98.58 87	94.07 138	87.96 310	98.50 207	93.90 94	94.96 364	81.33 351	93.17 248	96.78 255

XXY-MVS		91.82 262	90.46 274	95.88 221	93.91 329	95.40 177	98.87 284	97.69 240	88.63 300	87.87 311	97.08 257	74.38 333	97.89 265	91.66 249	84.07 314	94.35 284

Patchmtry		89.70 311	88.49 314	93.33 308	96.24 277	89.94 314	91.37 394	96.23 355	78.22 380	87.69 312	93.31 362	91.04 162	96.03 349	80.18 358	82.10 325	94.02 311

DIV-MVS_self_test		92.32 254	91.60 255	94.47 270	97.31 240	92.74 247	99.58 191	96.75 339	86.99 323	87.64 313	95.54 307	89.55 188	96.50 329	88.58 291	82.44 323	94.17 295

D2MVS		92.76 244	92.59 239	93.27 310	95.13 308	89.54 318	99.69 172	99.38 22	92.26 211	87.59 314	94.61 346	85.05 239	97.79 268	91.59 250	88.01 283	92.47 360

cl____		92.31 255	91.58 256	94.52 266	97.33 239	92.77 245	99.57 195	96.78 338	86.97 324	87.56 315	95.51 310	89.43 189	96.62 325	88.60 290	82.44 323	94.16 300

v8		90.54 292	89.17 302	94.66 258	93.43 337	93.40 235	99.20 246	96.94 325	85.76 337	87.56 315	94.51 347	81.96 260	97.19 292	84.94 329	78.25 354	93.38 344

miper_lstm_enhance		91.81 263	91.39 262	93.06 317	97.34 237	89.18 322	99.38 225	96.79 337	86.70 327	87.47 317	95.22 327	90.00 182	95.86 353	88.26 295	81.37 331	94.15 301

anonymousdsp		91.79 268	90.92 268	94.41 275	90.76 375	92.93 244	98.93 276	97.17 297	89.08 283	87.46 318	95.30 322	78.43 300	96.92 312	92.38 239	88.73 272	93.39 343

jajsoiax		91.92 261	91.18 264	94.15 280	91.35 370	90.95 290	99.00 269	97.42 271	92.61 195	87.38 319	97.08 257	72.46 339	97.36 281	94.53 202	88.77 271	94.13 305

mvs_tets		91.81 263	91.08 266	94.00 288	91.63 367	90.58 298	98.67 303	97.43 269	92.43 205	87.37 320	97.05 260	71.76 341	97.32 285	94.75 196	88.68 273	94.11 306

v10		90.25 300	88.82 309	94.57 264	93.53 335	93.43 233	99.08 255	96.87 331	85.00 346	87.34 321	94.51 347	80.93 272	97.02 309	82.85 342	79.23 349	93.26 346

pmmvs5		90.17 303	89.09 304	93.40 306	92.10 361	89.77 315	99.74 156	95.58 369	85.88 336	87.24 322	95.74 298	73.41 337	96.48 330	88.54 292	83.56 317	93.95 319

ACMP	92.05 9	92.74 245	92.42 243	93.73 296	95.91 286	88.72 326	99.81 135	97.53 259	94.13 134	87.00 323	98.23 224	74.07 334	98.47 215	96.22 170	88.86 270	93.99 316
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
MVS-HIRNet		86.22 332	83.19 345	95.31 238	96.71 270	90.29 304	92.12 390	97.33 281	62.85 397	86.82 324	70.37 402	69.37 352	97.49 278	75.12 377	97.99 164	98.15 235

Anonymous20231211		89.86 308	88.44 315	94.13 282	98.93 123	90.68 295	98.54 309	98.26 184	76.28 383	86.73 325	95.54 307	70.60 349	97.56 276	90.82 264	80.27 345	94.15 301

v7n		89.65 312	88.29 317	93.72 297	92.22 358	90.56 299	99.07 259	97.10 305	85.42 344	86.73 325	94.72 340	80.06 282	97.13 296	81.14 352	78.12 356	93.49 340

IterMVS-SCA-FT		90.85 285	90.16 285	92.93 319	96.72 269	89.96 311	98.89 279	96.99 316	88.95 291	86.63 327	95.67 301	76.48 313	95.00 363	87.04 312	84.04 316	93.84 328

EU-MVSNet		90.14 304	90.34 278	89.54 350	92.55 354	81.06 378	98.69 301	98.04 209	91.41 240	86.59 328	96.84 270	80.83 273	93.31 381	86.20 319	81.91 327	94.26 288

OpenMVS	90.15 15	94.77 191	93.59 210	98.33 123	96.07 280	97.48 97	99.56 197	98.57 89	90.46 262	86.51 329	98.95 168	78.57 297	99.94 78	93.86 213	99.74 85	97.57 250

IterMVS		90.91 282	90.17 284	93.12 314	96.78 267	90.42 303	98.89 279	97.05 312	89.03 285	86.49 330	95.42 314	76.59 311	95.02 362	87.22 309	84.09 313	93.93 321
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
WR-MVS_H		91.30 273	90.35 277	94.15 280	94.17 325	92.62 254	99.17 249	98.94 41	88.87 294	86.48 331	94.46 351	84.36 245	96.61 326	88.19 296	78.51 353	93.21 348

MS-PatchMatch		90.65 288	90.30 279	91.71 333	94.22 324	85.50 353	98.24 326	97.70 238	88.67 298	86.42 332	96.37 283	67.82 359	98.03 257	83.62 337	99.62 94	91.60 368

CP-MVSNet		91.23 277	90.22 281	94.26 278	93.96 328	92.39 258	99.09 253	98.57 89	88.95 291	86.42 332	96.57 278	79.19 290	96.37 334	90.29 275	78.95 350	94.02 311

LF4IMVS		89.25 318	88.85 308	90.45 343	92.81 352	81.19 377	98.12 332	94.79 380	91.44 236	86.29 334	97.11 255	65.30 370	98.11 252	88.53 293	85.25 303	92.07 363

PVSNet_0	88.03 19	91.80 266	90.27 280	96.38 212	98.27 176	90.46 301	99.94 69	99.61 13	93.99 144	86.26 335	97.39 249	71.13 347	99.89 96	98.77 86	67.05 390	98.79 218

PS-CasMVS		90.63 290	89.51 297	93.99 289	93.83 330	91.70 277	98.98 270	98.52 105	88.48 302	86.15 336	96.53 280	75.46 322	96.31 338	88.83 288	78.86 352	93.95 319

FMVSNet1		88.50 321	86.64 327	94.08 283	95.62 304	91.97 264	98.43 315	96.95 321	83.00 362	86.08 337	94.72 340	59.09 384	96.11 344	81.82 350	84.07 314	94.17 295

PEN-MVS		90.19 302	89.06 305	93.57 303	93.06 345	90.90 291	99.06 260	98.47 117	88.11 307	85.91 338	96.30 284	76.67 309	95.94 352	87.07 311	76.91 367	93.89 324

ppachtmachnet_test		89.58 313	88.35 316	93.25 312	92.40 356	90.44 302	99.33 231	96.73 340	85.49 342	85.90 339	95.77 297	81.09 270	96.00 351	76.00 376	82.49 322	93.30 345

OurMVSNet-221017-0		89.81 309	89.48 299	90.83 339	91.64 366	81.21 376	98.17 331	95.38 373	91.48 234	85.65 340	97.31 250	72.66 338	97.29 289	88.15 297	84.83 307	93.97 318

our_test_3		90.39 294	89.48 299	93.12 314	92.40 356	89.57 317	99.33 231	96.35 354	87.84 311	85.30 341	94.99 335	84.14 247	96.09 347	80.38 355	84.56 309	93.71 337

testgi		89.01 319	88.04 320	91.90 331	93.49 336	84.89 357	99.73 161	95.66 367	93.89 152	85.14 342	98.17 225	59.68 383	94.66 369	77.73 368	88.88 268	96.16 264

DTE-MVSNet		89.40 315	88.24 318	92.88 320	92.66 353	89.95 312	99.10 252	98.22 187	87.29 317	85.12 343	96.22 286	76.27 316	95.30 361	83.56 338	75.74 371	93.41 341

dongtai		91.55 272	91.13 265	92.82 321	98.16 185	86.35 347	99.47 212	98.51 108	83.24 360	85.07 344	97.56 243	90.33 178	94.94 365	76.09 375	91.73 252	97.18 253

FMVSNet5		88.32 322	87.47 324	90.88 337	96.90 259	88.39 333	97.28 348	95.68 366	82.60 366	84.67 345	92.40 370	79.83 284	91.16 391	76.39 374	81.51 330	93.09 349

tfpnnormal		89.29 317	87.61 323	94.34 277	94.35 322	94.13 214	98.95 274	98.94 41	83.94 354	84.47 346	95.51 310	74.84 329	97.39 280	77.05 372	80.41 342	91.48 370

MVP-Stereo		90.93 281	90.45 276	92.37 326	91.25 372	88.76 324	98.05 336	96.17 357	87.27 318	84.04 347	95.30 322	78.46 299	97.27 291	83.78 336	99.70 88	91.09 371
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
LTVRE_ROB	88.28 18	90.29 299	89.05 306	94.02 286	95.08 310	90.15 308	97.19 350	97.43 269	84.91 349	83.99 348	97.06 259	74.00 335	98.28 241	84.08 332	87.71 287	93.62 338
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
pm-mvs1		89.36 316	87.81 322	94.01 287	93.40 339	91.93 267	98.62 306	96.48 351	86.25 332	83.86 349	96.14 289	73.68 336	97.04 305	86.16 320	75.73 372	93.04 351

USDC		90.00 306	88.96 307	93.10 316	94.81 314	88.16 335	98.71 298	95.54 370	93.66 157	83.75 350	97.20 253	65.58 367	98.31 237	83.96 335	87.49 291	92.85 354

CL-MVSNet_self_test		84.50 343	83.15 346	88.53 359	86.00 390	81.79 373	98.82 289	97.35 277	85.12 345	83.62 351	90.91 377	76.66 310	91.40 390	69.53 386	60.36 399	92.40 361

ACMH+	89.98 16	90.35 296	89.54 295	92.78 323	95.99 283	86.12 349	98.81 290	97.18 296	89.38 280	83.14 352	97.76 241	68.42 357	98.43 220	89.11 286	86.05 297	93.78 331

Anonymous20231206		86.32 331	85.42 334	89.02 354	89.11 384	80.53 382	99.05 264	95.28 374	85.43 343	82.82 353	93.92 355	74.40 332	93.44 380	66.99 390	81.83 328	93.08 350

KD-MVS_self_test		83.59 349	82.06 349	88.20 361	86.93 388	80.70 380	97.21 349	96.38 352	82.87 363	82.49 354	88.97 383	67.63 360	92.32 387	73.75 379	62.30 398	91.58 369

SixPastTwentyTwo		88.73 320	88.01 321	90.88 337	91.85 364	82.24 369	98.22 329	95.18 378	88.97 289	82.26 355	96.89 265	71.75 342	96.67 324	84.00 333	82.98 318	93.72 336

KD-MVS_2432*1600		88.00 325	86.10 329	93.70 300	96.91 256	94.04 215	97.17 351	97.12 303	84.93 347	81.96 356	92.41 368	92.48 135	94.51 370	79.23 360	52.68 402	92.56 357

miper_refine_blended		88.00 325	86.10 329	93.70 300	96.91 256	94.04 215	97.17 351	97.12 303	84.93 347	81.96 356	92.41 368	92.48 135	94.51 370	79.23 360	52.68 402	92.56 357

TinyColmap		87.87 327	86.51 328	91.94 330	95.05 311	85.57 352	97.65 343	94.08 387	84.40 353	81.82 358	96.85 268	62.14 378	98.33 235	80.25 357	86.37 296	91.91 367

ACMH	89.72 17	90.64 289	89.63 292	93.66 302	95.64 302	88.64 329	98.55 307	97.45 267	89.03 285	81.62 359	97.61 242	69.75 351	98.41 222	89.37 283	87.62 289	93.92 322
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
Anonymous20240521		85.15 339	83.81 341	89.16 353	88.32 385	82.69 365	98.80 292	95.74 364	79.72 376	81.53 360	90.99 375	65.38 369	94.16 372	72.69 380	81.11 335	90.63 376

pmmvs6		85.69 333	83.84 340	91.26 336	90.00 381	84.41 359	97.82 341	96.15 358	75.86 385	81.29 361	95.39 317	61.21 381	96.87 315	83.52 339	73.29 375	92.50 359

TransMVSNet (Re)		87.25 328	85.28 335	93.16 313	93.56 334	91.03 286	98.54 309	94.05 389	83.69 358	81.09 362	96.16 288	75.32 323	96.40 333	76.69 373	68.41 386	92.06 364

test_method		80.79 354	79.70 358	84.08 369	92.83 350	67.06 395	99.51 205	95.42 371	54.34 401	81.07 363	93.53 359	44.48 397	92.22 388	78.90 364	77.23 364	92.94 352

NR-MVSNet		91.56 271	90.22 281	95.60 227	94.05 326	95.76 159	98.25 325	98.70 67	91.16 246	80.78 364	96.64 275	83.23 254	96.57 327	91.41 251	77.73 359	94.46 273

LCM-MVSNet-Re		92.31 255	92.60 235	91.43 334	97.53 226	79.27 384	99.02 268	91.83 399	92.07 215	80.31 365	94.38 352	83.50 251	95.48 356	97.22 151	97.58 170	99.54 148

TDRefinement		84.76 340	82.56 348	91.38 335	74.58 406	84.80 358	97.36 347	94.56 384	84.73 350	80.21 366	96.12 292	63.56 374	98.39 226	87.92 300	63.97 395	90.95 374

N_pmnet		80.06 357	80.78 355	77.89 376	91.94 362	45.28 414	98.80 292	56.82 416	78.10 381	80.08 367	93.33 360	77.03 304	95.76 354	68.14 389	82.81 319	92.64 356

test_fmvs3		79.99 358	80.17 357	79.45 375	84.02 394	62.83 396	99.05 264	93.49 394	88.29 306	80.06 368	86.65 392	28.09 404	88.00 396	88.63 289	73.27 376	87.54 392

test_0402		85.58 334	83.94 339	90.50 341	93.81 331	85.04 355	98.55 307	95.20 377	76.01 384	79.72 369	95.13 328	64.15 373	96.26 340	66.04 394	86.88 293	90.21 379

test20.03		84.72 342	83.99 337	86.91 364	88.19 387	80.62 381	98.88 281	95.94 361	88.36 304	78.87 370	94.62 345	68.75 354	89.11 395	66.52 392	75.82 370	91.00 372

pmmvs3		80.27 356	77.77 361	87.76 363	80.32 401	82.43 368	98.23 328	91.97 398	72.74 394	78.75 371	87.97 388	57.30 387	90.99 392	70.31 384	62.37 397	89.87 381

dmvs_testset		83.79 347	86.07 331	76.94 377	92.14 359	48.60 412	96.75 360	90.27 402	89.48 279	78.65 372	98.55 206	79.25 288	86.65 400	66.85 391	82.69 320	95.57 266

MIMVSNet1		82.58 350	80.51 356	88.78 356	86.68 389	84.20 360	96.65 361	95.41 372	78.75 379	78.59 373	92.44 367	51.88 393	89.76 394	65.26 395	78.95 350	92.38 362

DeepMVS_CX				82.92 372	95.98 285	58.66 403		96.01 360	92.72 187	78.34 374	95.51 310	58.29 385	98.08 253	82.57 343	85.29 302	92.03 365

test_vis1_rt		86.87 330	86.05 332	89.34 351	96.12 278	78.07 385	99.87 104	83.54 410	92.03 218	78.21 375	89.51 381	45.80 396	99.91 89	96.25 169	93.11 250	90.03 380

mvsany_test3		82.12 351	81.14 353	85.06 368	81.87 397	70.41 392	97.09 353	92.14 397	91.27 243	77.84 376	88.73 384	39.31 399	95.49 355	90.75 266	71.24 378	89.29 388

Patchmatch-RL test		86.90 329	85.98 333	89.67 349	84.45 392	75.59 387	89.71 398	92.43 396	86.89 325	77.83 377	90.94 376	94.22 83	93.63 378	87.75 302	69.61 381	99.79 97

APD_test1		81.15 353	80.92 354	81.86 373	92.45 355	59.76 402	96.04 373	93.61 393	73.29 393	77.06 378	96.64 275	44.28 398	96.16 343	72.35 381	82.52 321	89.67 384

lessismore_v0				90.53 340	90.58 376	80.90 379		95.80 363		77.01 379	95.84 295	66.15 366	96.95 310	83.03 341	75.05 373	93.74 335

K. test v3		88.05 324	87.24 326	90.47 342	91.82 365	82.23 370	98.96 273	97.42 271	89.05 284	76.93 380	95.60 304	68.49 356	95.42 357	85.87 324	81.01 338	93.75 332

ambc				83.23 371	77.17 404	62.61 397	87.38 400	94.55 385		76.72 381	86.65 392	30.16 401	96.36 335	84.85 330	69.86 380	90.73 375

PM-MVS		80.47 355	78.88 360	85.26 367	83.79 395	72.22 390	95.89 376	91.08 400	85.71 340	76.56 382	88.30 385	36.64 400	93.90 375	82.39 345	69.57 382	89.66 385

OpenMVS_ROB	79.82 20	83.77 348	81.68 351	90.03 347	88.30 386	82.82 364	98.46 312	95.22 376	73.92 392	76.00 383	91.29 374	55.00 388	96.94 311	68.40 388	88.51 278	90.34 377

UnsupCasMVSNet_eth		85.52 335	83.99 337	90.10 346	89.36 383	83.51 363	96.65 361	97.99 211	89.14 282	75.89 384	93.83 356	63.25 375	93.92 374	81.92 349	67.90 389	92.88 353

new_pmnet		84.49 344	82.92 347	89.21 352	90.03 380	82.60 366	96.89 359	95.62 368	80.59 373	75.77 385	89.17 382	65.04 371	94.79 368	72.12 382	81.02 337	90.23 378

EG-PatchMatch MVS		85.35 338	83.81 341	89.99 348	90.39 377	81.89 372	98.21 330	96.09 359	81.78 369	74.73 386	93.72 358	51.56 394	97.12 298	79.16 363	88.61 274	90.96 373

test_f		78.40 360	77.59 362	80.81 374	80.82 399	62.48 399	96.96 357	93.08 395	83.44 359	74.57 387	84.57 396	27.95 405	92.63 385	84.15 331	72.79 377	87.32 393

pmmvs-eth3d		84.03 346	81.97 350	90.20 345	84.15 393	87.09 343	98.10 334	94.73 382	83.05 361	74.10 388	87.77 389	65.56 368	94.01 373	81.08 353	69.24 383	89.49 386

new-patchmatchnet		81.19 352	79.34 359	86.76 365	82.86 396	80.36 383	97.92 338	95.27 375	82.09 368	72.02 389	86.87 391	62.81 377	90.74 393	71.10 383	63.08 396	89.19 389

ET-MVSNet_ETH3D		94.37 205	93.28 222	97.64 163	98.30 172	97.99 74	99.99 4	97.61 249	94.35 124	71.57 390	99.45 117	96.23 30	95.34 359	96.91 163	85.14 305	99.59 133

UnsupCasMVSNet_bld		79.97 359	77.03 364	88.78 356	85.62 391	81.98 371	93.66 385	97.35 277	75.51 388	70.79 391	83.05 397	48.70 395	94.91 366	78.31 366	60.29 400	89.46 387

CMPMVS	61.59 21	84.75 341	85.14 336	83.57 370	90.32 378	62.54 398	96.98 356	97.59 253	74.33 391	69.95 392	96.66 273	64.17 372	98.32 236	87.88 301	88.41 279	89.84 382
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
WB-MVS		76.28 361	77.28 363	73.29 381	81.18 398	54.68 406	97.87 340	94.19 386	81.30 370	69.43 393	90.70 378	77.02 305	82.06 404	35.71 409	68.11 388	83.13 395

SSC-MVS		75.42 362	76.40 365	72.49 385	80.68 400	53.62 407	97.42 345	94.06 388	80.42 374	68.75 394	90.14 380	76.54 312	81.66 405	33.25 410	66.34 392	82.19 396

testmvs		40.60 377	44.45 380	29.05 394	19.49 418	14.11 420	99.68 174	18.47 417	20.74 410	64.59 395	98.48 211	10.95 415	17.09 414	56.66 403	11.01 410	55.94 407

LCM-MVSNet		67.77 368	64.73 371	76.87 378	62.95 412	56.25 405	89.37 399	93.74 392	44.53 404	61.99 396	80.74 398	20.42 411	86.53 401	69.37 387	59.50 401	87.84 390

PMMVS2		67.15 369	64.15 372	76.14 379	70.56 409	62.07 400	93.89 383	87.52 407	58.09 398	60.02 397	78.32 399	22.38 408	84.54 402	59.56 399	47.03 404	81.80 397

testf1		68.38 366	66.92 367	72.78 383	78.80 402	50.36 409	90.95 396	87.35 408	55.47 399	58.95 398	88.14 386	20.64 409	87.60 397	57.28 401	64.69 393	80.39 398

APD_test2		68.38 366	66.92 367	72.78 383	78.80 402	50.36 409	90.95 396	87.35 408	55.47 399	58.95 398	88.14 386	20.64 409	87.60 397	57.28 401	64.69 393	80.39 398

Gipuma		66.95 370	65.00 370	72.79 382	91.52 368	67.96 394	66.16 405	95.15 379	47.89 403	58.54 400	67.99 405	29.74 402	87.54 399	50.20 404	77.83 358	62.87 405
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
YYNet1		85.50 337	83.33 343	92.00 329	90.89 374	88.38 334	99.22 245	96.55 348	79.60 378	57.26 401	92.72 365	79.09 293	93.78 377	77.25 370	77.37 363	93.84 328

MDA-MVSNet_test_wron		85.51 336	83.32 344	92.10 328	90.96 373	88.58 330	99.20 246	96.52 349	79.70 377	57.12 402	92.69 366	79.11 291	93.86 376	77.10 371	77.46 362	93.86 327

MDA-MVSNet-bldmvs		84.09 345	81.52 352	91.81 332	91.32 371	88.00 338	98.67 303	95.92 362	80.22 375	55.60 403	93.32 361	68.29 358	93.60 379	73.76 378	76.61 369	93.82 330

FPMVS		68.72 365	68.72 366	68.71 387	65.95 410	44.27 416	95.97 375	94.74 381	51.13 402	53.26 404	90.50 379	25.11 407	83.00 403	60.80 398	80.97 339	78.87 400

test123		37.68 378	39.14 381	33.31 393	19.94 417	24.83 419	98.36 320	9.75 418	15.53 411	51.31 405	87.14 390	19.62 412	17.74 413	47.10 405	3.47 412	57.36 406

test_vis3_rt		68.82 364	66.69 369	75.21 380	76.24 405	60.41 401	96.44 364	68.71 415	75.13 389	50.54 406	69.52 404	16.42 414	96.32 337	80.27 356	66.92 391	68.89 402

tmp_tt		65.23 371	62.94 374	72.13 386	44.90 415	50.03 411	81.05 402	89.42 406	38.45 405	48.51 407	99.90 18	54.09 390	78.70 407	91.84 248	18.26 409	87.64 391

E-PMN		52.30 374	52.18 376	52.67 391	71.51 407	45.40 413	93.62 386	76.60 413	36.01 407	43.50 408	64.13 407	27.11 406	67.31 410	31.06 411	26.06 406	45.30 409

EMVS		51.44 376	51.22 378	52.11 392	70.71 408	44.97 415	94.04 382	75.66 414	35.34 409	42.40 409	61.56 410	28.93 403	65.87 411	27.64 412	24.73 407	45.49 408

MVE	53.74 22	51.54 375	47.86 379	62.60 389	59.56 413	50.93 408	79.41 403	77.69 412	35.69 408	36.27 410	61.76 409	5.79 418	69.63 408	37.97 408	36.61 405	67.24 403
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
ANet_high		56.10 372	52.24 375	67.66 388	49.27 414	56.82 404	83.94 401	82.02 411	70.47 395	33.28 411	64.54 406	17.23 413	69.16 409	45.59 406	23.85 408	77.02 401

PMVS	49.05 23	53.75 373	51.34 377	60.97 390	40.80 416	34.68 417	74.82 404	89.62 405	37.55 406	28.67 412	72.12 401	7.09 416	81.63 406	43.17 407	68.21 387	66.59 404
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
wuyk23d		20.37 380	20.84 383	18.99 395	65.34 411	27.73 418	50.43 406	7.67 419	9.50 412	8.01 413	6.34 413	6.13 417	26.24 412	23.40 413	10.69 411	2.99 410

EGC-MVSNET		69.38 363	63.76 373	86.26 366	90.32 378	81.66 375	96.24 369	93.85 391	0.99 413	3.22 414	92.33 371	52.44 391	92.92 384	59.53 400	84.90 306	84.21 394

test_blank		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.02 414	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet_test		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

DCPMVS		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

cdsmvs_eth3d_5k		23.43 379	31.24 382	0.00 396	0.00 419	0.00 421	0.00 407	98.09 203	0.00 414	0.00 415	99.67 94	83.37 252	0.00 415	0.00 414	0.00 413	0.00 411

pcd_1.5k_mvsjas		7.60 382	10.13 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	91.20 157	0.00 415	0.00 414	0.00 413	0.00 411

sosnet-low-res		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

sosnet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uncertanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

Regformer		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

ab-mvs-re		8.28 381	11.04 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	99.40 123	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

uanet		0.00 383	0.00 386	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 415	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

WAC-MVS						90.97 287								86.10 322

MSC_two_6792asdad				99.93 2	99.91 39	99.80 2		98.41 150					100.00 1	99.96 9	100.00 1	100.00 1

No_MVS				99.93 2	99.91 39	99.80 2		98.41 150					100.00 1	99.96 9	100.00 1	100.00 1

eth-test2					0.00 419

eth-test					0.00 419

OPU-MVS				99.93 2	99.89 45	99.80 2	99.96 35				99.80 51	97.44 12	100.00 1	100.00 1	99.98 32	100.00 1

save fliter					99.82 58	98.79 40	99.96 35	98.40 154	97.66 21

test_0728_SECOND				99.82 7	99.94 13	99.47 7	99.95 53	98.43 133					100.00 1	99.99 5	100.00 1	100.00 1

GSMVS																99.59 133

sam_mvs1												94.72 64				99.59 133

sam_mvs												94.25 82

MTGPA								98.28 181

test_post1							95.78 377				59.23 411	93.20 115	97.74 271	91.06 257

test_post											63.35 408	94.43 69	98.13 251

patchmatchnet-post											91.70 373	95.12 49	97.95 262

MTMP							99.87 104	96.49 350

gm-plane-assit					96.97 253	93.76 223			91.47 235		98.96 163		98.79 194	94.92 189

test9_res														99.71 33	99.99 21	100.00 1

agg_prior2														99.48 43	100.00 1	100.00 1

test_prior4						98.05 71	99.94 69

test_prior				99.43 35	99.94 13	98.49 60		98.65 74					99.80 121			99.99 23

新几何2							99.40 220

旧先验1					99.76 66	97.52 93		98.64 76			99.85 30	95.63 40			99.94 55	99.99 23

无先验							99.49 209	98.71 66	93.46 161				100.00 1	94.36 204		99.99 23

原ACMM2							99.90 90

testdata2													99.99 36	90.54 270

segment_acmp												96.68 24

testdata1							99.28 240		96.35 69

plane_prior7					95.71 298	91.59 281

plane_prior6					95.76 292	91.72 276						80.47 280

plane_prior5								97.87 225					98.37 232	97.79 137	89.55 261	94.52 270

plane_prior4											98.59 199

plane_prior2							99.84 123		96.38 65

plane_prior1					95.73 295

plane_prior						91.74 273	99.86 115		96.76 52						89.59 260

n2								0.00 420

nn								0.00 420

door-mid								89.69 404

test11								98.44 125

door								90.31 401

HQP5-MVS						91.85 269

BP-MVS														97.92 129

HQP3-MVS								97.89 223							89.60 258

HQP2-MVS												80.65 276

NP-MVS					95.77 291	91.79 271					98.65 194

ACMMP++_ref															87.04 292

ACMMP++															88.23 281

Test By Simon												92.82 126

High-resolution multi-view benchmark