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.

test_fmvsmvis_n_1920		99.65 6	99.61 6	99.77 55	99.38 219	99.37 104	99.58 112	99.62 41	99.41 9	99.87 27	99.92 14	98.81 44	100.00 1	99.97 1	99.93 27	99.94 11

test_fmvsm_n_1920		99.69 4	99.66 3	99.78 52	99.84 32	99.44 98	99.58 112	99.69 18	99.43 7	99.98 6	99.91 21	98.62 70	100.00 1	99.97 1	99.95 18	99.90 16

test_vis1_n_1920		98.63 164	98.40 170	99.31 150	99.86 20	97.94 250	99.67 67	99.62 41	99.43 7	99.99 2	99.91 21	87.29 372	100.00 1	99.92 11	99.92 29	99.98 2

fmvsm_l_conf0.5_n_a		99.71 1	99.67 1	99.85 28	99.86 20	99.61 67	99.56 125	99.63 39	99.48 3	99.98 6	99.83 70	98.75 55	99.99 4	99.97 1	99.96 12	99.94 11

fmvsm_l_conf0.5_n		99.71 1	99.67 1	99.85 28	99.84 32	99.63 64	99.56 125	99.63 39	99.47 4	99.98 6	99.82 79	98.75 55	99.99 4	99.97 1	99.97 7	99.94 11

test_fmvsmconf_n		99.70 3	99.64 4	99.87 11	99.80 52	99.66 53	99.48 181	99.64 36	99.45 5	99.92 17	99.92 14	98.62 70	99.99 4	99.96 6	99.99 1	99.96 7

patch_mono-2		99.26 73	99.62 5	98.16 302	99.81 46	94.59 366	99.52 151	99.64 36	99.33 13	99.73 66	99.90 28	99.00 22	99.99 4	99.69 20	99.98 4	99.89 19

h-mvs33		97.70 274	97.28 295	98.97 197	99.70 101	97.27 277	99.36 235	99.45 199	98.94 54	99.66 87	99.64 193	94.93 209	99.99 4	99.48 45	84.36 399	99.65 129

xiu_mvs_v1_base_debu		99.29 67	99.27 62	99.34 143	99.63 133	98.97 158	99.12 302	99.51 117	98.86 60	99.84 34	99.47 257	98.18 97	99.99 4	99.50 40	99.31 163	99.08 238

xiu_mvs_v1_base		99.29 67	99.27 62	99.34 143	99.63 133	98.97 158	99.12 302	99.51 117	98.86 60	99.84 34	99.47 257	98.18 97	99.99 4	99.50 40	99.31 163	99.08 238

xiu_mvs_v1_base_debi		99.29 67	99.27 62	99.34 143	99.63 133	98.97 158	99.12 302	99.51 117	98.86 60	99.84 34	99.47 257	98.18 97	99.99 4	99.50 40	99.31 163	99.08 238

EPNet		98.86 135	98.71 139	99.30 155	97.20 392	98.18 232	99.62 91	98.91 340	99.28 16	98.63 300	99.81 93	95.96 173	99.99 4	99.24 71	99.72 123	99.73 97
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
MM		99.40 52	99.28 59	99.74 61	99.67 112	99.31 113	99.52 151	98.87 347	99.55 1	99.74 64	99.80 106	96.47 157	99.98 13	99.97 1	99.97 7	99.94 11

test_cas_vis1_n_1920		99.16 87	99.01 99	99.61 88	99.81 46	98.86 178	99.65 78	99.64 36	99.39 10	99.97 13	99.94 6	93.20 276	99.98 13	99.55 33	99.91 36	99.99 1

test_vis1_n		97.92 234	97.44 272	99.34 143	99.53 166	98.08 238	99.74 45	99.49 147	99.15 20	100.00 1	99.94 6	79.51 400	99.98 13	99.88 13	99.76 115	99.97 4

xiu_mvs_v2_base		99.26 73	99.25 66	99.29 158	99.53 166	98.91 172	99.02 325	99.45 199	98.80 69	99.71 72	99.26 314	98.94 29	99.98 13	99.34 59	99.23 167	98.98 252

PS-MVSNAJ		99.32 63	99.32 44	99.30 155	99.57 154	98.94 168	98.97 339	99.46 188	98.92 57	99.71 72	99.24 316	99.01 18	99.98 13	99.35 55	99.66 133	98.97 253

QAPM		98.67 160	98.30 177	99.80 46	99.20 265	99.67 51	99.77 33	99.72 11	94.74 363	98.73 280	99.90 28	95.78 183	99.98 13	96.96 297	99.88 56	99.76 87

3Dnovator	97.25 9	99.24 78	99.05 87	99.81 44	99.12 287	99.66 53	99.84 11	99.74 10	99.09 32	98.92 255	99.90 28	95.94 176	99.98 13	98.95 96	99.92 29	99.79 74

OpenMVS	96.50 16	98.47 169	98.12 189	99.52 115	99.04 305	99.53 84	99.82 15	99.72 11	94.56 366	98.08 334	99.88 37	94.73 225	99.98 13	97.47 265	99.76 115	99.06 244

test_fmvsmconf0.1_n		99.55 14	99.45 21	99.86 21	99.44 201	99.65 57	99.50 165	99.61 48	99.45 5	99.87 27	99.92 14	97.31 125	99.97 21	99.95 7	99.99 1	99.97 4

test_fmvs1_n		98.41 175	98.14 186	99.21 170	99.82 42	97.71 263	99.74 45	99.49 147	99.32 14	99.99 2	99.95 3	85.32 381	99.97 21	99.82 16	99.84 82	99.96 7

CANet_DTU		98.97 126	98.87 121	99.25 165	99.33 231	98.42 224	99.08 311	99.30 281	99.16 19	99.43 146	99.75 139	95.27 200	99.97 21	98.56 162	99.95 18	99.36 213

MVS_0304		99.15 89	98.96 109	99.73 64	98.92 322	99.37 104	99.37 230	96.92 397	99.51 2	99.66 87	99.78 124	96.69 148	99.97 21	99.84 15	99.97 7	99.84 39

MTAPA		99.52 17	99.39 30	99.89 4	99.90 4	99.86 13	99.66 72	99.47 179	98.79 70	99.68 78	99.81 93	98.43 83	99.97 21	98.88 106	99.90 44	99.83 49

PGM-MVS		99.45 36	99.31 51	99.86 21	99.87 15	99.78 36	99.58 112	99.65 33	97.84 178	99.71 72	99.80 106	99.12 13	99.97 21	98.33 185	99.87 59	99.83 49

mPP-MVS		99.44 40	99.30 53	99.86 21	99.88 11	99.79 30	99.69 58	99.48 159	98.12 143	99.50 132	99.75 139	98.78 48	99.97 21	98.57 159	99.89 53	99.83 49

CP-MVS		99.45 36	99.32 44	99.85 28	99.83 39	99.75 39	99.69 58	99.52 103	98.07 153	99.53 127	99.63 199	98.93 33	99.97 21	98.74 131	99.91 36	99.83 49

SteuartSystems-ACMMP		99.54 15	99.42 22	99.87 11	99.82 42	99.81 25	99.59 104	99.51 117	98.62 85	99.79 46	99.83 70	99.28 4	99.97 21	98.48 169	99.90 44	99.84 39
Skip Steuart: Steuart Systems R&D Blog.
3Dnovator+	97.12 13	99.18 83	98.97 105	99.82 41	99.17 279	99.68 48	99.81 19	99.51 117	99.20 18	98.72 281	99.89 32	95.68 187	99.97 21	98.86 114	99.86 67	99.81 61

fmvsm_s_conf0.5_n_a		99.56 13	99.47 17	99.85 28	99.83 39	99.64 63	99.52 151	99.65 33	99.10 27	99.98 6	99.92 14	97.35 124	99.96 31	99.94 9	99.92 29	99.95 9

fmvsm_s_conf0.5_n		99.51 18	99.40 27	99.85 28	99.84 32	99.65 57	99.51 158	99.67 23	99.13 22	99.98 6	99.92 14	96.60 151	99.96 31	99.95 7	99.96 12	99.95 9

mvsany_test1		99.50 20	99.46 20	99.62 86	99.61 143	99.09 141	98.94 345	99.48 159	99.10 27	99.96 14	99.91 21	98.85 39	99.96 31	99.72 18	99.58 143	99.82 54

test_fmvs1		98.88 131	98.79 133	99.16 175	99.69 105	97.61 267	99.55 138	99.49 147	99.32 14	99.98 6	99.91 21	91.41 324	99.96 31	99.82 16	99.92 29	99.90 16

DVP-MVS++		99.59 8	99.50 13	99.88 5	99.51 174	99.88 8	99.87 7	99.51 117	98.99 45	99.88 22	99.81 93	99.27 5	99.96 31	98.85 116	99.80 102	99.81 61

MSC_two_6792asdad				99.87 11	99.51 174	99.76 37		99.33 263					99.96 31	98.87 109	99.84 82	99.89 19

No_MVS				99.87 11	99.51 174	99.76 37		99.33 263					99.96 31	98.87 109	99.84 82	99.89 19

ZD-MVS					99.71 96	99.79 30		99.61 48	96.84 282	99.56 120	99.54 233	98.58 72	99.96 31	96.93 300	99.75 117

SED-MVS		99.61 7	99.52 11	99.88 5	99.84 32	99.90 2	99.60 98	99.48 159	99.08 33	99.91 18	99.81 93	99.20 7	99.96 31	98.91 103	99.85 74	99.79 74

test_241102_TWO								99.48 159	99.08 33	99.88 22	99.81 93	98.94 29	99.96 31	98.91 103	99.84 82	99.88 25

ZNCC-MVS		99.47 30	99.33 42	99.87 11	99.87 15	99.81 25	99.64 81	99.67 23	98.08 152	99.55 124	99.64 193	98.91 34	99.96 31	98.72 134	99.90 44	99.82 54

DVP-MVS		99.57 12	99.47 17	99.88 5	99.85 26	99.89 4	99.57 119	99.37 243	99.10 27	99.81 41	99.80 106	98.94 29	99.96 31	98.93 100	99.86 67	99.81 61
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									98.99 45	99.81 41	99.80 106	99.09 14	99.96 31	98.85 116	99.90 44	99.88 25

test_0728_SECOND				99.91 2	99.84 32	99.89 4	99.57 119	99.51 117					99.96 31	98.93 100	99.86 67	99.88 25

SR-MVS		99.43 43	99.29 57	99.86 21	99.75 73	99.83 16	99.59 104	99.62 41	98.21 130	99.73 66	99.79 118	98.68 64	99.96 31	98.44 175	99.77 112	99.79 74

DPE-MVS		99.46 32	99.32 44	99.91 2	99.78 56	99.88 8	99.36 235	99.51 117	98.73 77	99.88 22	99.84 65	98.72 61	99.96 31	98.16 199	99.87 59	99.88 25
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
UA-Net		99.42 45	99.29 57	99.80 46	99.62 139	99.55 79	99.50 165	99.70 15	98.79 70	99.77 55	99.96 1	97.45 119	99.96 31	98.92 102	99.90 44	99.89 19

HFP-MVS		99.49 22	99.37 34	99.86 21	99.87 15	99.80 27	99.66 72	99.67 23	98.15 137	99.68 78	99.69 169	99.06 16	99.96 31	98.69 139	99.87 59	99.84 39

region2R		99.48 26	99.35 38	99.87 11	99.88 11	99.80 27	99.65 78	99.66 28	98.13 141	99.66 87	99.68 175	98.96 24	99.96 31	98.62 147	99.87 59	99.84 39

HPM-MVS++		99.39 54	99.23 69	99.87 11	99.75 73	99.84 15	99.43 201	99.51 117	98.68 82	99.27 188	99.53 237	98.64 69	99.96 31	98.44 175	99.80 102	99.79 74

APDe-MVS		99.66 5	99.57 8	99.92 1	99.77 62	99.89 4	99.75 40	99.56 71	99.02 38	99.88 22	99.85 54	99.18 10	99.96 31	99.22 72	99.92 29	99.90 16
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
ACMMPR		99.49 22	99.36 36	99.86 21	99.87 15	99.79 30	99.66 72	99.67 23	98.15 137	99.67 82	99.69 169	98.95 27	99.96 31	98.69 139	99.87 59	99.84 39

MP-MVS		99.33 61	99.15 75	99.87 11	99.88 11	99.82 22	99.66 72	99.46 188	98.09 148	99.48 136	99.74 144	98.29 92	99.96 31	97.93 217	99.87 59	99.82 54
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
CPTT-MVS		99.11 104	98.90 116	99.74 61	99.80 52	99.46 96	99.59 104	99.49 147	97.03 269	99.63 102	99.69 169	97.27 128	99.96 31	97.82 228	99.84 82	99.81 61

PVSNet_Blended_VisFu		99.36 58	99.28 59	99.61 88	99.86 20	99.07 146	99.47 187	99.93 2	97.66 201	99.71 72	99.86 49	97.73 114	99.96 31	99.47 47	99.82 95	99.79 74

UGNet		98.87 132	98.69 141	99.40 136	99.22 262	98.72 192	99.44 197	99.68 20	99.24 17	99.18 212	99.42 268	92.74 286	99.96 31	99.34 59	99.94 25	99.53 169
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
CSCG		99.32 63	99.32 44	99.32 149	99.85 26	98.29 227	99.71 53	99.66 28	98.11 145	99.41 153	99.80 106	98.37 89	99.96 31	98.99 92	99.96 12	99.72 103

ACMMP		99.45 36	99.32 44	99.82 41	99.89 8	99.67 51	99.62 91	99.69 18	98.12 143	99.63 102	99.84 65	98.73 60	99.96 31	98.55 165	99.83 91	99.81 61
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
test_fmvsmconf0.01_n		99.22 80	99.03 91	99.79 49	98.42 372	99.48 93	99.55 138	99.51 117	99.39 10	99.78 51	99.93 9	94.80 217	99.95 59	99.93 10	99.95 18	99.94 11

SR-MVS-dyc-post		99.45 36	99.31 51	99.85 28	99.76 65	99.82 22	99.63 86	99.52 103	98.38 106	99.76 60	99.82 79	98.53 76	99.95 59	98.61 150	99.81 98	99.77 82

GST-MVS		99.40 52	99.24 67	99.85 28	99.86 20	99.79 30	99.60 98	99.67 23	97.97 164	99.63 102	99.68 175	98.52 77	99.95 59	98.38 178	99.86 67	99.81 61

CANet		99.25 77	99.14 76	99.59 91	99.41 209	99.16 131	99.35 240	99.57 66	98.82 65	99.51 131	99.61 208	96.46 158	99.95 59	99.59 28	99.98 4	99.65 129

MP-MVS-pluss		99.37 57	99.20 71	99.88 5	99.90 4	99.87 12	99.30 251	99.52 103	97.18 251	99.60 112	99.79 118	98.79 47	99.95 59	98.83 122	99.91 36	99.83 49
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
MSP-MVS		99.42 45	99.27 62	99.88 5	99.89 8	99.80 27	99.67 67	99.50 137	98.70 79	99.77 55	99.49 249	98.21 95	99.95 59	98.46 173	99.77 112	99.88 25
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
testdata2													99.95 59	96.67 312

APD-MVS_3200maxsize		99.48 26	99.35 38	99.85 28	99.76 65	99.83 16	99.63 86	99.54 87	98.36 110	99.79 46	99.82 79	98.86 38	99.95 59	98.62 147	99.81 98	99.78 80

RPMNet		96.72 321	95.90 333	99.19 172	99.18 271	98.49 216	99.22 285	99.52 103	88.72 399	99.56 120	97.38 393	94.08 255	99.95 59	86.87 401	98.58 213	99.14 230

sss		99.17 85	99.05 87	99.53 109	99.62 139	98.97 158	99.36 235	99.62 41	97.83 179	99.67 82	99.65 187	97.37 123	99.95 59	99.19 74	99.19 170	99.68 119

MVSMamba_PlusPlus		99.46 32	99.41 26	99.64 80	99.68 109	99.50 89	99.75 40	99.50 137	98.27 119	99.87 27	99.92 14	98.09 101	99.94 69	99.65 24	99.95 18	99.47 189

fmvsm_s_conf0.1_n_a		99.26 73	99.06 86	99.85 28	99.52 171	99.62 65	99.54 142	99.62 41	98.69 80	99.99 2	99.96 1	94.47 241	99.94 69	99.88 13	99.92 29	99.98 2

fmvsm_s_conf0.1_n		99.29 67	99.10 80	99.86 21	99.70 101	99.65 57	99.53 150	99.62 41	98.74 76	99.99 2	99.95 3	94.53 239	99.94 69	99.89 12	99.96 12	99.97 4

TSAR-MVS + MP.		99.58 9	99.50 13	99.81 44	99.91 1	99.66 53	99.63 86	99.39 227	98.91 58	99.78 51	99.85 54	99.36 2	99.94 69	98.84 119	99.88 56	99.82 54
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
iter_conf05		99.48 26	99.40 27	99.71 67	99.68 109	99.61 67	99.49 176	99.58 62	98.27 119	99.95 15	99.92 14	98.09 101	99.94 69	99.65 24	99.96 12	99.58 154

mamv4		99.33 61	99.42 22	99.07 183	99.67 112	97.73 258	99.42 208	99.60 54	98.15 137	99.94 16	99.91 21	98.42 85	99.94 69	99.72 18	99.96 12	99.54 163

XVS		99.53 16	99.42 22	99.87 11	99.85 26	99.83 16	99.69 58	99.68 20	98.98 48	99.37 164	99.74 144	98.81 44	99.94 69	98.79 127	99.86 67	99.84 39

X-MVStestdata		96.55 323	95.45 342	99.87 11	99.85 26	99.83 16	99.69 58	99.68 20	98.98 48	99.37 164	64.01 416	98.81 44	99.94 69	98.79 127	99.86 67	99.84 39

旧先验2							98.96 340		96.70 289	99.47 137			99.94 69	98.19 195

新几何1				99.75 58	99.75 73	99.59 71		99.54 87	96.76 285	99.29 182	99.64 193	98.43 83	99.94 69	96.92 302	99.66 133	99.72 103

testdata				99.54 101	99.75 73	98.95 165		99.51 117	97.07 263	99.43 146	99.70 159	98.87 37	99.94 69	97.76 235	99.64 136	99.72 103

HPM-MVS		99.42 45	99.28 59	99.83 40	99.90 4	99.72 42	99.81 19	99.54 87	97.59 206	99.68 78	99.63 199	98.91 34	99.94 69	98.58 156	99.91 36	99.84 39
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
CHOSEN 1792x2688		99.19 81	99.10 80	99.45 129	99.89 8	98.52 212	99.39 223	99.94 1	98.73 77	99.11 221	99.89 32	95.50 192	99.94 69	99.50 40	99.97 7	99.89 19

APD-MVS		99.27 71	99.08 84	99.84 39	99.75 73	99.79 30	99.50 165	99.50 137	97.16 253	99.77 55	99.82 79	98.78 48	99.94 69	97.56 256	99.86 67	99.80 70
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
DELS-MVS		99.48 26	99.42 22	99.65 75	99.72 91	99.40 103	99.05 317	99.66 28	99.14 21	99.57 119	99.80 106	98.46 81	99.94 69	99.57 31	99.84 82	99.60 146
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
WTY-MVS		99.06 112	98.88 120	99.61 88	99.62 139	99.16 131	99.37 230	99.56 71	98.04 159	99.53 127	99.62 204	96.84 142	99.94 69	98.85 116	98.49 221	99.72 103

DeepC-MVS	98.35 2	99.30 65	99.19 72	99.64 80	99.82 42	99.23 124	99.62 91	99.55 79	98.94 54	99.63 102	99.95 3	95.82 182	99.94 69	99.37 54	99.97 7	99.73 97
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
LS3D		99.27 71	99.12 78	99.74 61	99.18 271	99.75 39	99.56 125	99.57 66	98.45 99	99.49 135	99.85 54	97.77 113	99.94 69	98.33 185	99.84 82	99.52 170

SDMVSNet		99.11 104	98.90 116	99.75 58	99.81 46	99.59 71	99.81 19	99.65 33	98.78 73	99.64 99	99.88 37	94.56 235	99.93 87	99.67 22	98.26 233	99.72 103

FE-MVS		98.48 168	98.17 182	99.40 136	99.54 165	98.96 162	99.68 64	98.81 354	95.54 347	99.62 106	99.70 159	93.82 264	99.93 87	97.35 274	99.46 150	99.32 219

SF-MVS		99.38 56	99.24 67	99.79 49	99.79 54	99.68 48	99.57 119	99.54 87	97.82 183	99.71 72	99.80 106	98.95 27	99.93 87	98.19 195	99.84 82	99.74 92

dcpmvs_2		99.23 79	99.58 7	98.16 302	99.83 39	94.68 364	99.76 36	99.52 103	99.07 35	99.98 6	99.88 37	98.56 74	99.93 87	99.67 22	99.98 4	99.87 30

Anonymous20240529		98.09 204	97.68 240	99.34 143	99.66 122	98.44 221	99.40 219	99.43 213	93.67 373	99.22 199	99.89 32	90.23 340	99.93 87	99.26 70	98.33 227	99.66 125

ACMMP_NAP		99.47 30	99.34 40	99.88 5	99.87 15	99.86 13	99.47 187	99.48 159	98.05 158	99.76 60	99.86 49	98.82 43	99.93 87	98.82 126	99.91 36	99.84 39

EI-MVSNet-UG-set		99.58 9	99.57 8	99.64 80	99.78 56	99.14 136	99.60 98	99.45 199	99.01 40	99.90 20	99.83 70	98.98 23	99.93 87	99.59 28	99.95 18	99.86 32

无先验							98.99 333	99.51 117	96.89 279				99.93 87	97.53 259		99.72 103

VDDNet		97.55 288	97.02 307	99.16 175	99.49 185	98.12 237	99.38 228	99.30 281	95.35 349	99.68 78	99.90 28	82.62 393	99.93 87	99.31 62	98.13 244	99.42 202

ab-mvs		98.86 135	98.63 148	99.54 101	99.64 130	99.19 126	99.44 197	99.54 87	97.77 187	99.30 179	99.81 93	94.20 249	99.93 87	99.17 78	98.82 202	99.49 182

F-COLMAP		99.19 81	99.04 89	99.64 80	99.78 56	99.27 119	99.42 208	99.54 87	97.29 242	99.41 153	99.59 213	98.42 85	99.93 87	98.19 195	99.69 128	99.73 97

Anonymous202405211		98.30 185	97.98 206	99.26 164	99.57 154	98.16 233	99.41 211	98.55 375	96.03 341	99.19 208	99.74 144	91.87 311	99.92 98	99.16 79	98.29 232	99.70 113

EI-MVSNet-Vis-set		99.58 9	99.56 10	99.64 80	99.78 56	99.15 135	99.61 97	99.45 199	99.01 40	99.89 21	99.82 79	99.01 18	99.92 98	99.56 32	99.95 18	99.85 35

VDD-MVS		97.73 268	97.35 284	98.88 217	99.47 193	97.12 285	99.34 243	98.85 349	98.19 132	99.67 82	99.85 54	82.98 391	99.92 98	99.49 44	98.32 231	99.60 146

VNet		99.11 104	98.90 116	99.73 64	99.52 171	99.56 77	99.41 211	99.39 227	99.01 40	99.74 64	99.78 124	95.56 190	99.92 98	99.52 38	98.18 240	99.72 103

XVG-OURS-SEG-HR		98.69 158	98.62 153	98.89 215	99.71 96	97.74 257	99.12 302	99.54 87	98.44 102	99.42 149	99.71 155	94.20 249	99.92 98	98.54 166	98.90 196	99.00 249

mvsmamba		99.06 112	98.96 109	99.36 141	99.47 193	98.64 199	99.70 54	99.05 321	97.61 205	99.65 94	99.83 70	96.54 154	99.92 98	99.19 74	99.62 139	99.51 177

HPM-MVS_fast		99.51 18	99.40 27	99.85 28	99.91 1	99.79 30	99.76 36	99.56 71	97.72 192	99.76 60	99.75 139	99.13 12	99.92 98	99.07 86	99.92 29	99.85 35

HY-MVS	97.30 7	98.85 142	98.64 147	99.47 126	99.42 204	99.08 144	99.62 91	99.36 244	97.39 234	99.28 183	99.68 175	96.44 160	99.92 98	98.37 180	98.22 235	99.40 207

DP-MVS		99.16 87	98.95 111	99.78 52	99.77 62	99.53 84	99.41 211	99.50 137	97.03 269	99.04 237	99.88 37	97.39 120	99.92 98	98.66 143	99.90 44	99.87 30

IB-MVS	95.67 18	96.22 329	95.44 343	98.57 255	99.21 263	96.70 313	98.65 373	97.74 392	96.71 288	97.27 358	98.54 369	86.03 375	99.92 98	98.47 172	86.30 397	99.10 233
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
DeepC-MVS_fast	98.69 1	99.49 22	99.39 30	99.77 55	99.63 133	99.59 71	99.36 235	99.46 188	99.07 35	99.79 46	99.82 79	98.85 39	99.92 98	98.68 141	99.87 59	99.82 54
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
balanced_conf03		99.46 32	99.39 30	99.67 70	99.55 162	99.58 76	99.74 45	99.51 117	98.42 103	99.87 27	99.84 65	98.05 105	99.91 109	99.58 30	99.94 25	99.52 170

9.14			99.10 80		99.72 91		99.40 219	99.51 117	97.53 216	99.64 99	99.78 124	98.84 41	99.91 109	97.63 247	99.82 95

SMA-MVS		99.44 40	99.30 53	99.85 28	99.73 87	99.83 16	99.56 125	99.47 179	97.45 225	99.78 51	99.82 79	99.18 10	99.91 109	98.79 127	99.89 53	99.81 61
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
TEST9					99.67 112	99.65 57	99.05 317	99.41 218	96.22 326	98.95 251	99.49 249	98.77 51	99.91 109

train_agg		99.02 118	98.77 134	99.77 55	99.67 112	99.65 57	99.05 317	99.41 218	96.28 320	98.95 251	99.49 249	98.76 52	99.91 109	97.63 247	99.72 123	99.75 88

test_8					99.67 112	99.61 67	99.03 322	99.41 218	96.28 320	98.93 254	99.48 254	98.76 52	99.91 109

agg_prior					99.67 112	99.62 65		99.40 224		98.87 264			99.91 109

原ACMM1				99.65 75	99.73 87	99.33 108		99.47 179	97.46 222	99.12 219	99.66 186	98.67 66	99.91 109	97.70 244	99.69 128	99.71 112

LFMVS		97.90 237	97.35 284	99.54 101	99.52 171	99.01 153	99.39 223	98.24 382	97.10 261	99.65 94	99.79 118	84.79 384	99.91 109	99.28 66	98.38 224	99.69 115

XVG-OURS		98.73 156	98.68 142	98.88 217	99.70 101	97.73 258	98.92 347	99.55 79	98.52 94	99.45 140	99.84 65	95.27 200	99.91 109	98.08 206	98.84 200	99.00 249

PLC	97.94 4	99.02 118	98.85 125	99.53 109	99.66 122	99.01 153	99.24 279	99.52 103	96.85 281	99.27 188	99.48 254	98.25 94	99.91 109	97.76 235	99.62 139	99.65 129
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
PCF-MVS	97.08 14	97.66 281	97.06 306	99.47 126	99.61 143	99.09 141	98.04 399	99.25 292	91.24 390	98.51 310	99.70 159	94.55 237	99.91 109	92.76 378	99.85 74	99.42 202
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
UWE-MVS		97.58 287	97.29 294	98.48 266	99.09 295	96.25 332	99.01 330	96.61 403	97.86 173	99.19 208	99.01 341	88.72 354	99.90 121	97.38 272	98.69 208	99.28 222

test_vis1_rt		95.81 339	95.65 338	96.32 365	99.67 112	91.35 392	99.49 176	96.74 401	98.25 123	95.24 380	98.10 386	74.96 401	99.90 121	99.53 36	98.85 199	97.70 386

FA-MVS(test-final)		98.75 153	98.53 164	99.41 135	99.55 162	99.05 149	99.80 24	99.01 325	96.59 302	99.58 116	99.59 213	95.39 195	99.90 121	97.78 231	99.49 149	99.28 222

bld_raw_conf03		99.39 54	99.32 44	99.62 86	99.53 166	99.50 89	99.75 40	99.50 137	98.13 141	99.87 27	99.85 54	97.89 108	99.90 121	99.39 52	99.95 18	99.47 189

MCST-MVS		99.43 43	99.30 53	99.82 41	99.79 54	99.74 41	99.29 256	99.40 224	98.79 70	99.52 129	99.62 204	98.91 34	99.90 121	98.64 145	99.75 117	99.82 54

CDPH-MVS		99.13 94	98.91 115	99.80 46	99.75 73	99.71 44	99.15 296	99.41 218	96.60 300	99.60 112	99.55 228	98.83 42	99.90 121	97.48 263	99.83 91	99.78 80

NCCC		99.34 60	99.19 72	99.79 49	99.61 143	99.65 57	99.30 251	99.48 159	98.86 60	99.21 202	99.63 199	98.72 61	99.90 121	98.25 191	99.63 138	99.80 70

114514_t		98.93 128	98.67 143	99.72 66	99.85 26	99.53 84	99.62 91	99.59 58	92.65 385	99.71 72	99.78 124	98.06 104	99.90 121	98.84 119	99.91 36	99.74 92

1112_ss		98.98 124	98.77 134	99.59 91	99.68 109	99.02 151	99.25 277	99.48 159	97.23 248	99.13 217	99.58 217	96.93 141	99.90 121	98.87 109	98.78 205	99.84 39

PHI-MVS		99.30 65	99.17 74	99.70 68	99.56 158	99.52 87	99.58 112	99.80 8	97.12 257	99.62 106	99.73 150	98.58 72	99.90 121	98.61 150	99.91 36	99.68 119

AdaColmap		99.01 122	98.80 130	99.66 71	99.56 158	99.54 81	99.18 291	99.70 15	98.18 135	99.35 170	99.63 199	96.32 163	99.90 121	97.48 263	99.77 112	99.55 161

COLMAP_ROB	97.56 6	98.86 135	98.75 136	99.17 174	99.88 11	98.53 208	99.34 243	99.59 58	97.55 212	98.70 288	99.89 32	95.83 181	99.90 121	98.10 201	99.90 44	99.08 238
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
thisisatest0530		98.35 181	98.03 201	99.31 150	99.63 133	98.56 205	99.54 142	96.75 400	97.53 216	99.73 66	99.65 187	91.25 328	99.89 133	98.62 147	99.56 144	99.48 183

tttt0517		98.42 173	98.14 186	99.28 162	99.66 122	98.38 225	99.74 45	96.85 398	97.68 198	99.79 46	99.74 144	91.39 325	99.89 133	98.83 122	99.56 144	99.57 158

test12				99.75 58	99.64 130	99.61 67		99.29 285		99.21 202		98.38 88	99.89 133		99.74 120	99.74 92

Test_1112_low_res		98.89 130	98.66 146	99.57 96	99.69 105	98.95 165	99.03 322	99.47 179	96.98 271	99.15 215	99.23 317	96.77 145	99.89 133	98.83 122	98.78 205	99.86 32

CNLPA		99.14 92	98.99 101	99.59 91	99.58 152	99.41 102	99.16 293	99.44 207	98.45 99	99.19 208	99.49 249	98.08 103	99.89 133	97.73 239	99.75 117	99.48 183

sd_testset		98.75 153	98.57 160	99.29 158	99.81 46	98.26 229	99.56 125	99.62 41	98.78 73	99.64 99	99.88 37	92.02 308	99.88 138	99.54 34	98.26 233	99.72 103

APD_test1		95.87 337	96.49 320	94.00 372	99.53 166	84.01 401	99.54 142	99.32 273	95.91 343	97.99 339	99.85 54	85.49 379	99.88 138	91.96 381	98.84 200	98.12 366

diffmvs		99.14 92	99.02 95	99.51 117	99.61 143	98.96 162	99.28 261	99.49 147	98.46 98	99.72 71	99.71 155	96.50 156	99.88 138	99.31 62	99.11 177	99.67 122
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_BlendedMVS		98.86 135	98.80 130	99.03 189	99.76 65	98.79 187	99.28 261	99.91 3	97.42 231	99.67 82	99.37 285	97.53 117	99.88 138	98.98 93	97.29 290	98.42 349

PVSNet_Blended		99.08 110	98.97 105	99.42 134	99.76 65	98.79 187	98.78 361	99.91 3	96.74 286	99.67 82	99.49 249	97.53 117	99.88 138	98.98 93	99.85 74	99.60 146

MVS		97.28 306	96.55 318	99.48 123	98.78 340	98.95 165	99.27 266	99.39 227	83.53 403	98.08 334	99.54 233	96.97 139	99.87 143	94.23 360	99.16 171	99.63 140

MG-MVS		99.13 94	99.02 95	99.45 129	99.57 154	98.63 200	99.07 312	99.34 256	98.99 45	99.61 109	99.82 79	97.98 107	99.87 143	97.00 293	99.80 102	99.85 35

MSDG		98.98 124	98.80 130	99.53 109	99.76 65	99.19 126	98.75 364	99.55 79	97.25 245	99.47 137	99.77 132	97.82 111	99.87 143	96.93 300	99.90 44	99.54 163

ETV-MVS		99.26 73	99.21 70	99.40 136	99.46 195	99.30 115	99.56 125	99.52 103	98.52 94	99.44 145	99.27 312	98.41 87	99.86 146	99.10 83	99.59 142	99.04 245

thisisatest0515		98.14 199	97.79 224	99.19 172	99.50 183	98.50 215	98.61 375	96.82 399	96.95 275	99.54 125	99.43 266	91.66 320	99.86 146	98.08 206	99.51 148	99.22 227

thres600view7		97.86 242	97.51 258	98.92 206	99.72 91	97.95 248	99.59 104	98.74 361	97.94 166	99.27 188	98.62 366	91.75 314	99.86 146	93.73 365	98.19 239	98.96 255

lupinMVS		99.13 94	99.01 99	99.46 128	99.51 174	98.94 168	99.05 317	99.16 306	97.86 173	99.80 44	99.56 225	97.39 120	99.86 146	98.94 97	99.85 74	99.58 154

PVSNet	96.02 17	98.85 142	98.84 127	98.89 215	99.73 87	97.28 276	98.32 391	99.60 54	97.86 173	99.50 132	99.57 222	96.75 146	99.86 146	98.56 162	99.70 127	99.54 163

MAR-MVS		98.86 135	98.63 148	99.54 101	99.37 222	99.66 53	99.45 191	99.54 87	96.61 298	99.01 240	99.40 276	97.09 132	99.86 146	97.68 246	99.53 147	99.10 233
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
testing91		97.44 300	97.02 307	98.71 243	99.18 271	96.89 307	99.19 289	99.04 322	97.78 186	98.31 321	98.29 378	85.41 380	99.85 152	98.01 212	97.95 249	99.39 208

test2506		96.81 320	96.65 316	97.29 346	99.74 80	92.21 389	99.60 98	85.06 420	99.13 22	99.77 55	99.93 9	87.82 370	99.85 152	99.38 53	99.38 155	99.80 70

AllTest		98.87 132	98.72 137	99.31 150	99.86 20	98.48 218	99.56 125	99.61 48	97.85 176	99.36 167	99.85 54	95.95 174	99.85 152	96.66 313	99.83 91	99.59 150

TestCases				99.31 150	99.86 20	98.48 218		99.61 48	97.85 176	99.36 167	99.85 54	95.95 174	99.85 152	96.66 313	99.83 91	99.59 150

jason		99.13 94	99.03 91	99.45 129	99.46 195	98.87 175	99.12 302	99.26 290	98.03 161	99.79 46	99.65 187	97.02 137	99.85 152	99.02 90	99.90 44	99.65 129
jason: jason.
CNVR-MVS		99.42 45	99.30 53	99.78 52	99.62 139	99.71 44	99.26 275	99.52 103	98.82 65	99.39 160	99.71 155	98.96 24	99.85 152	98.59 155	99.80 102	99.77 82

PAPM_NR		99.04 115	98.84 127	99.66 71	99.74 80	99.44 98	99.39 223	99.38 235	97.70 196	99.28 183	99.28 309	98.34 90	99.85 152	96.96 297	99.45 151	99.69 115

testing99		97.36 303	96.94 310	98.63 248	99.18 271	96.70 313	99.30 251	98.93 333	97.71 193	98.23 326	98.26 379	84.92 383	99.84 159	98.04 211	97.85 256	99.35 214

testing222		97.16 311	96.50 319	99.16 175	99.16 281	98.47 220	99.27 266	98.66 371	97.71 193	98.23 326	98.15 382	82.28 396	99.84 159	97.36 273	97.66 262	99.18 229

test1111		98.04 214	98.11 190	97.83 326	99.74 80	93.82 374	99.58 112	95.40 407	99.12 25	99.65 94	99.93 9	90.73 333	99.84 159	99.43 50	99.38 155	99.82 54

ECVR-MVS		98.04 214	98.05 199	98.00 314	99.74 80	94.37 369	99.59 104	94.98 408	99.13 22	99.66 87	99.93 9	90.67 334	99.84 159	99.40 51	99.38 155	99.80 70

test_yl		98.86 135	98.63 148	99.54 101	99.49 185	99.18 128	99.50 165	99.07 318	98.22 128	99.61 109	99.51 243	95.37 196	99.84 159	98.60 153	98.33 227	99.59 150

DCV-MVSNet		98.86 135	98.63 148	99.54 101	99.49 185	99.18 128	99.50 165	99.07 318	98.22 128	99.61 109	99.51 243	95.37 196	99.84 159	98.60 153	98.33 227	99.59 150

Fast-Effi-MVS+		98.70 157	98.43 167	99.51 117	99.51 174	99.28 117	99.52 151	99.47 179	96.11 336	99.01 240	99.34 295	96.20 167	99.84 159	97.88 220	98.82 202	99.39 208

TSAR-MVS + GP.		99.36 58	99.36 36	99.36 141	99.67 112	98.61 203	99.07 312	99.33 263	99.00 43	99.82 40	99.81 93	99.06 16	99.84 159	99.09 84	99.42 153	99.65 129

tpmrst		98.33 182	98.48 166	97.90 320	99.16 281	94.78 362	99.31 249	99.11 311	97.27 243	99.45 140	99.59 213	95.33 198	99.84 159	98.48 169	98.61 210	99.09 237

Vis-MVSNet		99.12 100	98.97 105	99.56 98	99.78 56	99.10 140	99.68 64	99.66 28	98.49 96	99.86 32	99.87 45	94.77 222	99.84 159	99.19 74	99.41 154	99.74 92
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
PAPR		98.63 164	98.34 173	99.51 117	99.40 214	99.03 150	98.80 359	99.36 244	96.33 317	99.00 244	99.12 331	98.46 81	99.84 159	95.23 346	99.37 162	99.66 125

PatchMatch-RL		98.84 145	98.62 153	99.52 115	99.71 96	99.28 117	99.06 315	99.77 9	97.74 191	99.50 132	99.53 237	95.41 194	99.84 159	97.17 287	99.64 136	99.44 200

EPP-MVSNet		99.13 94	98.99 101	99.53 109	99.65 128	99.06 147	99.81 19	99.33 263	97.43 229	99.60 112	99.88 37	97.14 130	99.84 159	99.13 80	98.94 191	99.69 115

testing11		97.50 293	97.10 304	98.71 243	99.20 265	96.91 305	99.29 256	98.82 352	97.89 171	98.21 329	98.40 373	85.63 378	99.83 172	98.45 174	98.04 247	99.37 212

thres100view900		97.76 260	97.45 267	98.69 245	99.72 91	97.86 254	99.59 104	98.74 361	97.93 167	99.26 192	98.62 366	91.75 314	99.83 172	93.22 370	98.18 240	98.37 355

tfpn200view9		97.72 270	97.38 280	98.72 241	99.69 105	97.96 246	99.50 165	98.73 367	97.83 179	99.17 213	98.45 371	91.67 318	99.83 172	93.22 370	98.18 240	98.37 355

test_prior				99.68 69	99.67 112	99.48 93		99.56 71					99.83 172			99.74 92

1314		98.68 159	98.54 163	99.11 181	98.89 325	98.65 197	99.27 266	99.49 147	96.89 279	97.99 339	99.56 225	97.72 115	99.83 172	97.74 238	99.27 166	98.84 261

thres400		97.77 259	97.38 280	98.92 206	99.69 105	97.96 246	99.50 165	98.73 367	97.83 179	99.17 213	98.45 371	91.67 318	99.83 172	93.22 370	98.18 240	98.96 255

casdiffmvs		99.13 94	98.98 104	99.56 98	99.65 128	99.16 131	99.56 125	99.50 137	98.33 114	99.41 153	99.86 49	95.92 177	99.83 172	99.45 49	99.16 171	99.70 113
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
CS-MVS-test		99.49 22	99.48 15	99.54 101	99.78 56	99.30 115	99.89 2	99.58 62	98.56 90	99.73 66	99.69 169	98.55 75	99.82 179	99.69 20	99.85 74	99.48 183

MVS_Test		99.10 108	98.97 105	99.48 123	99.49 185	99.14 136	99.67 67	99.34 256	97.31 240	99.58 116	99.76 136	97.65 116	99.82 179	98.87 109	99.07 183	99.46 195

dp		97.75 264	97.80 223	97.59 338	99.10 292	93.71 377	99.32 246	98.88 345	96.48 309	99.08 228	99.55 228	92.67 292	99.82 179	96.52 316	98.58 213	99.24 226

RPSCF		98.22 189	98.62 153	96.99 352	99.82 42	91.58 391	99.72 51	99.44 207	96.61 298	99.66 87	99.89 32	95.92 177	99.82 179	97.46 266	99.10 180	99.57 158

PMMVS		98.80 149	98.62 153	99.34 143	99.27 248	98.70 193	98.76 363	99.31 277	97.34 237	99.21 202	99.07 333	97.20 129	99.82 179	98.56 162	98.87 197	99.52 170

UBG		97.85 243	97.48 261	98.95 200	99.25 254	97.64 265	99.24 279	98.74 361	97.90 170	98.64 298	98.20 381	88.65 358	99.81 184	98.27 190	98.40 223	99.42 202

EIA-MVS		99.18 83	99.09 83	99.45 129	99.49 185	99.18 128	99.67 67	99.53 98	97.66 201	99.40 158	99.44 264	98.10 100	99.81 184	98.94 97	99.62 139	99.35 214

Effi-MVS+		98.81 146	98.59 159	99.48 123	99.46 195	99.12 139	98.08 398	99.50 137	97.50 220	99.38 162	99.41 272	96.37 162	99.81 184	99.11 82	98.54 218	99.51 177

thres200		97.61 285	97.28 295	98.62 249	99.64 130	98.03 240	99.26 275	98.74 361	97.68 198	99.09 227	98.32 377	91.66 320	99.81 184	92.88 375	98.22 235	98.03 372

tpmvs		97.98 225	98.02 203	97.84 325	99.04 305	94.73 363	99.31 249	99.20 301	96.10 340	98.76 278	99.42 268	94.94 208	99.81 184	96.97 296	98.45 222	98.97 253

casdiffmvs_mvg		99.15 89	99.02 95	99.55 100	99.66 122	99.09 141	99.64 81	99.56 71	98.26 122	99.45 140	99.87 45	96.03 171	99.81 184	99.54 34	99.15 174	99.73 97
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
DeepPCF-MVS	98.18 3	98.81 146	99.37 34	97.12 350	99.60 148	91.75 390	98.61 375	99.44 207	99.35 12	99.83 39	99.85 54	98.70 63	99.81 184	99.02 90	99.91 36	99.81 61

DPM-MVS		98.95 127	98.71 139	99.66 71	99.63 133	99.55 79	98.64 374	99.10 312	97.93 167	99.42 149	99.55 228	98.67 66	99.80 191	95.80 331	99.68 131	99.61 144

DP-MVS Recon		99.12 100	98.95 111	99.65 75	99.74 80	99.70 46	99.27 266	99.57 66	96.40 316	99.42 149	99.68 175	98.75 55	99.80 191	97.98 214	99.72 123	99.44 200

MVS_111021_LR		99.41 49	99.33 42	99.65 75	99.77 62	99.51 88	98.94 345	99.85 6	98.82 65	99.65 94	99.74 144	98.51 78	99.80 191	98.83 122	99.89 53	99.64 136

CS-MVS		99.50 20	99.48 15	99.54 101	99.76 65	99.42 100	99.90 1	99.55 79	98.56 90	99.78 51	99.70 159	98.65 68	99.79 194	99.65 24	99.78 109	99.41 205

Fast-Effi-MVS+-dtu		98.77 152	98.83 129	98.60 250	99.41 209	96.99 299	99.52 151	99.49 147	98.11 145	99.24 194	99.34 295	96.96 140	99.79 194	97.95 216	99.45 151	99.02 248

baseline1		98.31 183	97.95 210	99.38 140	99.50 183	98.74 190	99.59 104	98.93 333	98.41 104	99.14 216	99.60 211	94.59 233	99.79 194	98.48 169	93.29 369	99.61 144

baseline		99.15 89	99.02 95	99.53 109	99.66 122	99.14 136	99.72 51	99.48 159	98.35 111	99.42 149	99.84 65	96.07 169	99.79 194	99.51 39	99.14 175	99.67 122

PVSNet_0	94.43 19	96.09 334	95.47 341	97.94 317	99.31 238	94.34 371	97.81 400	99.70 15	97.12 257	97.46 352	98.75 363	89.71 345	99.79 194	97.69 245	81.69 403	99.68 119

API-MVS		99.04 115	99.03 91	99.06 185	99.40 214	99.31 113	99.55 138	99.56 71	98.54 92	99.33 174	99.39 280	98.76 52	99.78 199	96.98 295	99.78 109	98.07 369

OMC-MVS		99.08 110	99.04 89	99.20 171	99.67 112	98.22 231	99.28 261	99.52 103	98.07 153	99.66 87	99.81 93	97.79 112	99.78 199	97.79 230	99.81 98	99.60 146

GeoE		98.85 142	98.62 153	99.53 109	99.61 143	99.08 144	99.80 24	99.51 117	97.10 261	99.31 176	99.78 124	95.23 204	99.77 201	98.21 193	99.03 186	99.75 88

alignmvs		98.81 146	98.56 162	99.58 94	99.43 202	99.42 100	99.51 158	98.96 331	98.61 86	99.35 170	98.92 353	94.78 219	99.77 201	99.35 55	98.11 245	99.54 163

tpm cat1		97.39 302	97.36 282	97.50 341	99.17 279	93.73 376	99.43 201	99.31 277	91.27 389	98.71 282	99.08 332	94.31 247	99.77 201	96.41 320	98.50 220	99.00 249

CostFormer		97.72 270	97.73 236	97.71 333	99.15 285	94.02 373	99.54 142	99.02 324	94.67 364	99.04 237	99.35 291	92.35 304	99.77 201	98.50 168	97.94 250	99.34 217

MGCFI-Net		99.01 122	98.85 125	99.50 122	99.42 204	99.26 120	99.82 15	99.48 159	98.60 87	99.28 183	98.81 358	97.04 136	99.76 205	99.29 65	97.87 254	99.47 189

test_241102_ONE					99.84 32	99.90 2		99.48 159	99.07 35	99.91 18	99.74 144	99.20 7	99.76 205

MDTV_nov1_ep13			98.32 175		99.11 289	94.44 368	99.27 266	98.74 361	97.51 219	99.40 158	99.62 204	94.78 219	99.76 205	97.59 250	98.81 204

sasdasda		99.02 118	98.86 123	99.51 117	99.42 204	99.32 109	99.80 24	99.48 159	98.63 83	99.31 176	98.81 358	97.09 132	99.75 208	99.27 68	97.90 251	99.47 189

canonicalmvs		99.02 118	98.86 123	99.51 117	99.42 204	99.32 109	99.80 24	99.48 159	98.63 83	99.31 176	98.81 358	97.09 132	99.75 208	99.27 68	97.90 251	99.47 189

Effi-MVS+-dtu		98.78 150	98.89 119	98.47 271	99.33 231	96.91 305	99.57 119	99.30 281	98.47 97	99.41 153	98.99 343	96.78 144	99.74 210	98.73 133	99.38 155	98.74 274

patchmatchnet-post											98.70 364	94.79 218	99.74 210

SCA		98.19 193	98.16 183	98.27 297	99.30 239	95.55 345	99.07 312	98.97 329	97.57 209	99.43 146	99.57 222	92.72 287	99.74 210	97.58 251	99.20 169	99.52 170

BH-untuned		98.42 173	98.36 171	98.59 251	99.49 185	96.70 313	99.27 266	99.13 310	97.24 247	98.80 273	99.38 282	95.75 184	99.74 210	97.07 291	99.16 171	99.33 218

BH-RMVSNet		98.41 175	98.08 195	99.40 136	99.41 209	98.83 183	99.30 251	98.77 357	97.70 196	98.94 253	99.65 187	92.91 282	99.74 210	96.52 316	99.55 146	99.64 136

MVS_111021_HR		99.41 49	99.32 44	99.66 71	99.72 91	99.47 95	98.95 343	99.85 6	98.82 65	99.54 125	99.73 150	98.51 78	99.74 210	98.91 103	99.88 56	99.77 82

test_post											65.99 414	94.65 232	99.73 216

XVG-ACMP-BASELINE		97.83 249	97.71 238	98.20 299	99.11 289	96.33 329	99.41 211	99.52 103	98.06 157	99.05 236	99.50 246	89.64 347	99.73 216	97.73 239	97.38 288	98.53 337

HyFIR lowres test		99.11 104	98.92 113	99.65 75	99.90 4	99.37 104	99.02 325	99.91 3	97.67 200	99.59 115	99.75 139	95.90 179	99.73 216	99.53 36	99.02 188	99.86 32

DeepMVS_CX				93.34 375	99.29 243	82.27 404		99.22 297	85.15 401	96.33 372	99.05 336	90.97 331	99.73 216	93.57 367	97.77 259	98.01 373

Patchmatch-test		97.93 231	97.65 243	98.77 238	99.18 271	97.07 290	99.03 322	99.14 309	96.16 331	98.74 279	99.57 222	94.56 235	99.72 220	93.36 369	99.11 177	99.52 170

LPG-MVS_test		98.22 189	98.13 188	98.49 264	99.33 231	97.05 292	99.58 112	99.55 79	97.46 222	99.24 194	99.83 70	92.58 294	99.72 220	98.09 202	97.51 274	98.68 292

LGP-MVS_train				98.49 264	99.33 231	97.05 292		99.55 79	97.46 222	99.24 194	99.83 70	92.58 294	99.72 220	98.09 202	97.51 274	98.68 292

BH-w/o		98.00 223	97.89 219	98.32 289	99.35 226	96.20 334	99.01 330	98.90 342	96.42 314	98.38 317	99.00 342	95.26 202	99.72 220	96.06 324	98.61 210	99.03 246

ACMP	97.20 11	98.06 208	97.94 212	98.45 274	99.37 222	97.01 297	99.44 197	99.49 147	97.54 215	98.45 314	99.79 118	91.95 310	99.72 220	97.91 218	97.49 279	98.62 320
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LTVRE_ROB	97.16 12	98.02 218	97.90 215	98.40 282	99.23 258	96.80 311	99.70 54	99.60 54	97.12 257	98.18 331	99.70 159	91.73 316	99.72 220	98.39 177	97.45 281	98.68 292
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
test_post1							99.23 281				65.14 415	94.18 252	99.71 226	97.58 251

ADS-MVSNet		98.20 192	98.08 195	98.56 258	99.33 231	96.48 324	99.23 281	99.15 307	96.24 324	99.10 224	99.67 181	94.11 253	99.71 226	96.81 305	99.05 184	99.48 183

JIA-IIPM		97.50 293	97.02 307	98.93 204	98.73 349	97.80 256	99.30 251	98.97 329	91.73 388	98.91 256	94.86 403	95.10 206	99.71 226	97.58 251	97.98 248	99.28 222

EPMVS		97.82 252	97.65 243	98.35 286	98.88 326	95.98 337	99.49 176	94.71 410	97.57 209	99.26 192	99.48 254	92.46 301	99.71 226	97.87 222	99.08 182	99.35 214

TDRefinement		95.42 343	94.57 350	97.97 316	89.83 413	96.11 336	99.48 181	98.75 358	96.74 286	96.68 369	99.88 37	88.65 358	99.71 226	98.37 180	82.74 402	98.09 368

ACMM	97.58 5	98.37 180	98.34 173	98.48 266	99.41 209	97.10 286	99.56 125	99.45 199	98.53 93	99.04 237	99.85 54	93.00 278	99.71 226	98.74 131	97.45 281	98.64 311
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
tt0805		97.97 228	97.77 229	98.57 255	99.59 150	96.61 320	99.45 191	99.08 315	98.21 130	98.88 261	99.80 106	88.66 357	99.70 232	98.58 156	97.72 260	99.39 208

CHOSEN 280x420		99.12 100	99.13 77	99.08 182	99.66 122	97.89 251	98.43 385	99.71 13	98.88 59	99.62 106	99.76 136	96.63 150	99.70 232	99.46 48	99.99 1	99.66 125

EC-MVSNet		99.44 40	99.39 30	99.58 94	99.56 158	99.49 91	99.88 3	99.58 62	98.38 106	99.73 66	99.69 169	98.20 96	99.70 232	99.64 27	99.82 95	99.54 163

PatchmatchNet		98.31 183	98.36 171	98.19 300	99.16 281	95.32 353	99.27 266	98.92 336	97.37 235	99.37 164	99.58 217	94.90 212	99.70 232	97.43 269	99.21 168	99.54 163
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
ACMH	97.28 8	98.10 203	97.99 205	98.44 277	99.41 209	96.96 303	99.60 98	99.56 71	98.09 148	98.15 332	99.91 21	90.87 332	99.70 232	98.88 106	97.45 281	98.67 299
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
ETVMVS		97.50 293	96.90 311	99.29 158	99.23 258	98.78 189	99.32 246	98.90 342	97.52 218	98.56 307	98.09 387	84.72 385	99.69 237	97.86 223	97.88 253	99.39 208

HQP_MVS		98.27 188	98.22 181	98.44 277	99.29 243	96.97 301	99.39 223	99.47 179	98.97 51	99.11 221	99.61 208	92.71 289	99.69 237	97.78 231	97.63 263	98.67 299

plane_prior5								99.47 179					99.69 237	97.78 231	97.63 263	98.67 299

D2MVS		98.41 175	98.50 165	98.15 305	99.26 250	96.62 319	99.40 219	99.61 48	97.71 193	98.98 246	99.36 288	96.04 170	99.67 240	98.70 136	97.41 286	98.15 365

IS-MVSNet		99.05 114	98.87 121	99.57 96	99.73 87	99.32 109	99.75 40	99.20 301	98.02 162	99.56 120	99.86 49	96.54 154	99.67 240	98.09 202	99.13 176	99.73 97

CLD-MVS		98.16 197	98.10 191	98.33 287	99.29 243	96.82 310	98.75 364	99.44 207	97.83 179	99.13 217	99.55 228	92.92 280	99.67 240	98.32 187	97.69 261	98.48 341
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
test_fmvs2		97.25 308	97.30 292	97.09 351	99.43 202	93.31 382	99.73 49	98.87 347	98.83 64	99.28 183	99.80 106	84.45 386	99.66 243	97.88 220	97.45 281	98.30 357

AUN-MVS		96.88 318	96.31 324	98.59 251	99.48 192	97.04 295	99.27 266	99.22 297	97.44 228	98.51 310	99.41 272	91.97 309	99.66 243	97.71 242	83.83 400	99.07 243

UniMVSNet_ETH3D		97.32 305	96.81 313	98.87 221	99.40 214	97.46 270	99.51 158	99.53 98	95.86 344	98.54 309	99.77 132	82.44 394	99.66 243	98.68 141	97.52 273	99.50 181

OPM-MVS		98.19 193	98.10 191	98.45 274	98.88 326	97.07 290	99.28 261	99.38 235	98.57 89	99.22 199	99.81 93	92.12 306	99.66 243	98.08 206	97.54 272	98.61 329
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
ACMH+	97.24 10	97.92 234	97.78 227	98.32 289	99.46 195	96.68 317	99.56 125	99.54 87	98.41 104	97.79 348	99.87 45	90.18 341	99.66 243	98.05 210	97.18 295	98.62 320

hse-mvs2		97.50 293	97.14 301	98.59 251	99.49 185	97.05 292	99.28 261	99.22 297	98.94 54	99.66 87	99.42 268	94.93 209	99.65 248	99.48 45	83.80 401	99.08 238

VPA-MVSNet		98.29 186	97.95 210	99.30 155	99.16 281	99.54 81	99.50 165	99.58 62	98.27 119	99.35 170	99.37 285	92.53 296	99.65 248	99.35 55	94.46 352	98.72 276

TR-MVS		97.76 260	97.41 278	98.82 230	99.06 301	97.87 252	98.87 353	98.56 374	96.63 297	98.68 290	99.22 318	92.49 297	99.65 248	95.40 342	97.79 258	98.95 257

gm-plane-assit					98.54 368	92.96 384			94.65 365		99.15 326		99.64 251	97.56 256

HQP4-MVS										98.66 291			99.64 251			98.64 311

HQP-MVS		98.02 218	97.90 215	98.37 285	99.19 268	96.83 308	98.98 336	99.39 227	98.24 124	98.66 291	99.40 276	92.47 298	99.64 251	97.19 284	97.58 268	98.64 311

PAPM		97.59 286	97.09 305	99.07 183	99.06 301	98.26 229	98.30 392	99.10 312	94.88 359	98.08 334	99.34 295	96.27 165	99.64 251	89.87 389	98.92 194	99.31 220

TAPA-MVS	97.07 15	97.74 266	97.34 287	98.94 202	99.70 101	97.53 268	99.25 277	99.51 117	91.90 387	99.30 179	99.63 199	98.78 48	99.64 251	88.09 396	99.87 59	99.65 129
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
XXY-MVS		98.38 179	98.09 194	99.24 167	99.26 250	99.32 109	99.56 125	99.55 79	97.45 225	98.71 282	99.83 70	93.23 273	99.63 256	98.88 106	96.32 310	98.76 269

ITE_SJBPF				98.08 307	99.29 243	96.37 327		98.92 336	98.34 112	98.83 269	99.75 139	91.09 329	99.62 257	95.82 329	97.40 287	98.25 361

LF4IMVS		97.52 290	97.46 266	97.70 334	98.98 315	95.55 345	99.29 256	98.82 352	98.07 153	98.66 291	99.64 193	89.97 342	99.61 258	97.01 292	96.68 300	97.94 380

tpm		97.67 280	97.55 252	98.03 309	99.02 307	95.01 359	99.43 201	98.54 376	96.44 312	99.12 219	99.34 295	91.83 313	99.60 259	97.75 237	96.46 306	99.48 183

tpm2		97.44 300	97.34 287	97.74 332	99.15 285	94.36 370	99.45 191	98.94 332	93.45 378	98.90 258	99.44 264	91.35 326	99.59 260	97.31 275	98.07 246	99.29 221

baseline2		97.87 240	97.55 252	98.82 230	99.18 271	98.02 241	99.41 211	96.58 404	96.97 272	96.51 370	99.17 323	93.43 270	99.57 261	97.71 242	99.03 186	98.86 259

MS-PatchMatch		97.24 310	97.32 290	96.99 352	98.45 371	93.51 381	98.82 357	99.32 273	97.41 232	98.13 333	99.30 305	88.99 351	99.56 262	95.68 335	99.80 102	97.90 383

TinyColmap		97.12 313	96.89 312	97.83 326	99.07 299	95.52 348	98.57 378	98.74 361	97.58 208	97.81 347	99.79 118	88.16 365	99.56 262	95.10 347	97.21 293	98.39 353

USDC		97.34 304	97.20 299	97.75 331	99.07 299	95.20 355	98.51 382	99.04 322	97.99 163	98.31 321	99.86 49	89.02 350	99.55 264	95.67 336	97.36 289	98.49 340

MSLP-MVS++		99.46 32	99.47 17	99.44 133	99.60 148	99.16 131	99.41 211	99.71 13	98.98 48	99.45 140	99.78 124	99.19 9	99.54 265	99.28 66	99.84 82	99.63 140

TAMVS		99.12 100	99.08 84	99.24 167	99.46 195	98.55 206	99.51 158	99.46 188	98.09 148	99.45 140	99.82 79	98.34 90	99.51 266	98.70 136	98.93 192	99.67 122

EPNet_dtu		98.03 216	97.96 208	98.23 298	98.27 374	95.54 347	99.23 281	98.75 358	99.02 38	97.82 346	99.71 155	96.11 168	99.48 267	93.04 373	99.65 135	99.69 115
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
EG-PatchMatch MVS		95.97 336	95.69 337	96.81 359	97.78 381	92.79 385	99.16 293	98.93 333	96.16 331	94.08 388	99.22 318	82.72 392	99.47 268	95.67 336	97.50 276	98.17 364

MVP-Stereo		97.81 254	97.75 234	97.99 315	97.53 385	96.60 321	98.96 340	98.85 349	97.22 249	97.23 359	99.36 288	95.28 199	99.46 269	95.51 338	99.78 109	97.92 382
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
CVMVSNet		98.57 166	98.67 143	98.30 291	99.35 226	95.59 344	99.50 165	99.55 79	98.60 87	99.39 160	99.83 70	94.48 240	99.45 270	98.75 130	98.56 216	99.85 35

test-LLR		98.06 208	97.90 215	98.55 260	98.79 337	97.10 286	98.67 370	97.75 390	97.34 237	98.61 303	98.85 355	94.45 242	99.45 270	97.25 278	99.38 155	99.10 233

TESTMET0.1,1		97.55 288	97.27 298	98.40 282	98.93 320	96.53 322	98.67 370	97.61 393	96.96 273	98.64 298	99.28 309	88.63 360	99.45 270	97.30 276	99.38 155	99.21 228

test-mter		97.49 298	97.13 303	98.55 260	98.79 337	97.10 286	98.67 370	97.75 390	96.65 293	98.61 303	98.85 355	88.23 364	99.45 270	97.25 278	99.38 155	99.10 233

mvs_anonymous		99.03 117	98.99 101	99.16 175	99.38 219	98.52 212	99.51 158	99.38 235	97.79 184	99.38 162	99.81 93	97.30 126	99.45 270	99.35 55	98.99 189	99.51 177

tfpnnormal		97.84 247	97.47 264	98.98 195	99.20 265	99.22 125	99.64 81	99.61 48	96.32 318	98.27 325	99.70 159	93.35 272	99.44 275	95.69 334	95.40 335	98.27 359

v7n		97.87 240	97.52 256	98.92 206	98.76 347	98.58 204	99.84 11	99.46 188	96.20 327	98.91 256	99.70 159	94.89 213	99.44 275	96.03 325	93.89 363	98.75 271

jajsoiax		98.43 172	98.28 178	98.88 217	98.60 364	98.43 222	99.82 15	99.53 98	98.19 132	98.63 300	99.80 106	93.22 275	99.44 275	99.22 72	97.50 276	98.77 267

mvs_tets		98.40 178	98.23 180	98.91 210	98.67 357	98.51 214	99.66 72	99.53 98	98.19 132	98.65 297	99.81 93	92.75 284	99.44 275	99.31 62	97.48 280	98.77 267

Vis-MVSNet (Re-imp)		98.87 132	98.72 137	99.31 150	99.71 96	98.88 174	99.80 24	99.44 207	97.91 169	99.36 167	99.78 124	95.49 193	99.43 279	97.91 218	99.11 177	99.62 142

OPU-MVS				99.64 80	99.56 158	99.72 42	99.60 98				99.70 159	99.27 5	99.42 280	98.24 192	99.80 102	99.79 74

Anonymous20231211		97.88 238	97.54 255	98.90 212	99.71 96	98.53 208	99.48 181	99.57 66	94.16 369	98.81 271	99.68 175	93.23 273	99.42 280	98.84 119	94.42 354	98.76 269

m2depth		97.80 256	97.63 247	98.29 292	98.77 345	97.38 273	99.64 81	99.36 244	98.78 73	96.30 373	99.58 217	92.34 305	99.39 282	98.36 182	95.58 330	98.10 367

VPNet		97.84 247	97.44 272	99.01 191	99.21 263	98.94 168	99.48 181	99.57 66	98.38 106	99.28 183	99.73 150	88.89 352	99.39 282	99.19 74	93.27 370	98.71 278

nrg030		98.64 163	98.42 168	99.28 162	99.05 304	99.69 47	99.81 19	99.46 188	98.04 159	99.01 240	99.82 79	96.69 148	99.38 284	99.34 59	94.59 351	98.78 264

GA-MVS		97.85 243	97.47 264	99.00 193	99.38 219	97.99 243	98.57 378	99.15 307	97.04 268	98.90 258	99.30 305	89.83 344	99.38 284	96.70 310	98.33 227	99.62 142

UniMVSNet (Re)		98.29 186	98.00 204	99.13 180	99.00 309	99.36 107	99.49 176	99.51 117	97.95 165	98.97 248	99.13 328	96.30 164	99.38 284	98.36 182	93.34 368	98.66 307

FIs		98.78 150	98.63 148	99.23 169	99.18 271	99.54 81	99.83 14	99.59 58	98.28 117	98.79 275	99.81 93	96.75 146	99.37 287	99.08 85	96.38 308	98.78 264

PS-MVSNAJss		98.92 129	98.92 113	98.90 212	98.78 340	98.53 208	99.78 31	99.54 87	98.07 153	99.00 244	99.76 136	99.01 18	99.37 287	99.13 80	97.23 292	98.81 262

CDS-MVSNet		99.09 109	99.03 91	99.25 165	99.42 204	98.73 191	99.45 191	99.46 188	98.11 145	99.46 139	99.77 132	98.01 106	99.37 287	98.70 136	98.92 194	99.66 125
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
MVS-HIRNet		95.75 340	95.16 345	97.51 340	99.30 239	93.69 378	98.88 351	95.78 405	85.09 402	98.78 276	92.65 405	91.29 327	99.37 287	94.85 352	99.85 74	99.46 195

v1192		97.81 254	97.44 272	98.91 210	98.88 326	98.68 194	99.51 158	99.34 256	96.18 329	99.20 205	99.34 295	94.03 256	99.36 291	95.32 344	95.18 339	98.69 287

EI-MVSNet		98.67 160	98.67 143	98.68 246	99.35 226	97.97 244	99.50 165	99.38 235	96.93 278	99.20 205	99.83 70	97.87 109	99.36 291	98.38 178	97.56 270	98.71 278

MVSTER		98.49 167	98.32 175	99.00 193	99.35 226	99.02 151	99.54 142	99.38 235	97.41 232	99.20 205	99.73 150	93.86 263	99.36 291	98.87 109	97.56 270	98.62 320

gg-mvs-nofinetune		96.17 332	95.32 344	98.73 240	98.79 337	98.14 235	99.38 228	94.09 411	91.07 392	98.07 337	91.04 409	89.62 348	99.35 294	96.75 307	99.09 181	98.68 292

pm-mvs1		97.68 277	97.28 295	98.88 217	99.06 301	98.62 201	99.50 165	99.45 199	96.32 318	97.87 344	99.79 118	92.47 298	99.35 294	97.54 258	93.54 367	98.67 299

OurMVSNet-221017-0		97.88 238	97.77 229	98.19 300	98.71 353	96.53 322	99.88 3	99.00 326	97.79 184	98.78 276	99.94 6	91.68 317	99.35 294	97.21 280	96.99 299	98.69 287

EGC-MVSNET		82.80 374	77.86 380	97.62 336	97.91 378	96.12 335	99.33 245	99.28 287	8.40 417	25.05 418	99.27 312	84.11 387	99.33 297	89.20 391	98.22 235	97.42 391

pmmvs6		96.53 324	96.09 329	97.82 328	98.69 355	95.47 349	99.37 230	99.47 179	93.46 377	97.41 353	99.78 124	87.06 373	99.33 297	96.92 302	92.70 377	98.65 309

V42		98.06 208	97.79 224	98.86 224	98.98 315	98.84 180	99.69 58	99.34 256	96.53 304	99.30 179	99.37 285	94.67 230	99.32 299	97.57 255	94.66 349	98.42 349

lessismore_v0				97.79 330	98.69 355	95.44 351		94.75 409		95.71 379	99.87 45	88.69 356	99.32 299	95.89 328	94.93 346	98.62 320

OpenMVS_ROB	92.34 20	94.38 354	93.70 360	96.41 364	97.38 387	93.17 383	99.06 315	98.75 358	86.58 400	94.84 386	98.26 379	81.53 397	99.32 299	89.01 392	97.87 254	96.76 394

v8		97.95 230	97.63 247	98.93 204	98.95 319	98.81 186	99.80 24	99.41 218	96.03 341	99.10 224	99.42 268	94.92 211	99.30 302	96.94 299	94.08 360	98.66 307

v1921920		97.80 256	97.45 267	98.84 228	98.80 336	98.53 208	99.52 151	99.34 256	96.15 333	99.24 194	99.47 257	93.98 258	99.29 303	95.40 342	95.13 341	98.69 287

anonymousdsp		98.44 171	98.28 178	98.94 202	98.50 369	98.96 162	99.77 33	99.50 137	97.07 263	98.87 264	99.77 132	94.76 223	99.28 304	98.66 143	97.60 266	98.57 335

MVSFormer		99.17 85	99.12 78	99.29 158	99.51 174	98.94 168	99.88 3	99.46 188	97.55 212	99.80 44	99.65 187	97.39 120	99.28 304	99.03 88	99.85 74	99.65 129

test_djsdf		98.67 160	98.57 160	98.98 195	98.70 354	98.91 172	99.88 3	99.46 188	97.55 212	99.22 199	99.88 37	95.73 185	99.28 304	99.03 88	97.62 265	98.75 271

cascas		97.69 275	97.43 276	98.48 266	98.60 364	97.30 275	98.18 396	99.39 227	92.96 381	98.41 315	98.78 362	93.77 266	99.27 307	98.16 199	98.61 210	98.86 259

v144192		97.92 234	97.60 250	98.87 221	98.83 335	98.65 197	99.55 138	99.34 256	96.20 327	99.32 175	99.40 276	94.36 244	99.26 308	96.37 321	95.03 343	98.70 283

dmvs_re		98.08 206	98.16 183	97.85 323	99.55 162	94.67 365	99.70 54	98.92 336	98.15 137	99.06 234	99.35 291	93.67 269	99.25 309	97.77 234	97.25 291	99.64 136

v2v482		98.06 208	97.77 229	98.92 206	98.90 324	98.82 184	99.57 119	99.36 244	96.65 293	99.19 208	99.35 291	94.20 249	99.25 309	97.72 241	94.97 344	98.69 287

v1240		97.69 275	97.32 290	98.79 236	98.85 333	98.43 222	99.48 181	99.36 244	96.11 336	99.27 188	99.36 288	93.76 267	99.24 311	94.46 356	95.23 338	98.70 283

WBMVS		97.74 266	97.50 259	98.46 272	99.24 256	97.43 271	99.21 287	99.42 215	97.45 225	98.96 250	99.41 272	88.83 353	99.23 312	98.94 97	96.02 315	98.71 278

v1144		97.98 225	97.69 239	98.85 227	98.87 329	98.66 196	99.54 142	99.35 251	96.27 322	99.23 198	99.35 291	94.67 230	99.23 312	96.73 308	95.16 340	98.68 292

v10		97.85 243	97.52 256	98.86 224	98.99 312	98.67 195	99.75 40	99.41 218	95.70 345	98.98 246	99.41 272	94.75 224	99.23 312	96.01 327	94.63 350	98.67 299

WR-MVS_H		98.13 200	97.87 220	98.90 212	99.02 307	98.84 180	99.70 54	99.59 58	97.27 243	98.40 316	99.19 322	95.53 191	99.23 312	98.34 184	93.78 365	98.61 329

miper_enhance_ethall		98.16 197	98.08 195	98.41 280	98.96 318	97.72 260	98.45 384	99.32 273	96.95 275	98.97 248	99.17 323	97.06 135	99.22 316	97.86 223	95.99 318	98.29 358

GG-mvs-BLEND				98.45 274	98.55 367	98.16 233	99.43 201	93.68 412		97.23 359	98.46 370	89.30 349	99.22 316	95.43 341	98.22 235	97.98 378

FC-MVSNet-test		98.75 153	98.62 153	99.15 179	99.08 298	99.45 97	99.86 10	99.60 54	98.23 127	98.70 288	99.82 79	96.80 143	99.22 316	99.07 86	96.38 308	98.79 263

UniMVSNet_NR-MVSNet		98.22 189	97.97 207	98.96 198	98.92 322	98.98 155	99.48 181	99.53 98	97.76 188	98.71 282	99.46 261	96.43 161	99.22 316	98.57 159	92.87 375	98.69 287

DU-MVS		98.08 206	97.79 224	98.96 198	98.87 329	98.98 155	99.41 211	99.45 199	97.87 172	98.71 282	99.50 246	94.82 215	99.22 316	98.57 159	92.87 375	98.68 292

cl____		98.01 221	97.84 222	98.55 260	99.25 254	97.97 244	98.71 368	99.34 256	96.47 311	98.59 306	99.54 233	95.65 188	99.21 321	97.21 280	95.77 324	98.46 346

WR-MVS		98.06 208	97.73 236	99.06 185	98.86 332	99.25 122	99.19 289	99.35 251	97.30 241	98.66 291	99.43 266	93.94 259	99.21 321	98.58 156	94.28 356	98.71 278

test_0402		96.64 322	96.24 325	97.85 323	98.85 333	96.43 326	99.44 197	99.26 290	93.52 375	96.98 366	99.52 240	88.52 361	99.20 323	92.58 380	97.50 276	97.93 381

SixPastTwentyTwo		97.50 293	97.33 289	98.03 309	98.65 358	96.23 333	99.77 33	98.68 370	97.14 254	97.90 342	99.93 9	90.45 335	99.18 324	97.00 293	96.43 307	98.67 299

cl22		97.85 243	97.64 246	98.48 266	99.09 295	97.87 252	98.60 377	99.33 263	97.11 260	98.87 264	99.22 318	92.38 303	99.17 325	98.21 193	95.99 318	98.42 349

WB-MVSnew		97.65 282	97.65 243	97.63 335	98.78 340	97.62 266	99.13 299	98.33 379	97.36 236	99.07 229	98.94 349	95.64 189	99.15 326	92.95 374	98.68 209	96.12 401

IterMVS-SCA-FT		97.82 252	97.75 234	98.06 308	99.57 154	96.36 328	99.02 325	99.49 147	97.18 251	98.71 282	99.72 154	92.72 287	99.14 327	97.44 268	95.86 323	98.67 299

pmmvs5		97.52 290	97.30 292	98.16 302	98.57 366	96.73 312	99.27 266	98.90 342	96.14 334	98.37 318	99.53 237	91.54 323	99.14 327	97.51 260	95.87 322	98.63 318

v148		97.79 258	97.55 252	98.50 263	98.74 348	97.72 260	99.54 142	99.33 263	96.26 323	98.90 258	99.51 243	94.68 229	99.14 327	97.83 227	93.15 372	98.63 318

miper_ehance_all_eth		98.18 195	98.10 191	98.41 280	99.23 258	97.72 260	98.72 367	99.31 277	96.60 300	98.88 261	99.29 307	97.29 127	99.13 330	97.60 249	95.99 318	98.38 354

NR-MVSNet		97.97 228	97.61 249	99.02 190	98.87 329	99.26 120	99.47 187	99.42 215	97.63 203	97.08 364	99.50 246	95.07 207	99.13 330	97.86 223	93.59 366	98.68 292

IterMVS		97.83 249	97.77 229	98.02 311	99.58 152	96.27 331	99.02 325	99.48 159	97.22 249	98.71 282	99.70 159	92.75 284	99.13 330	97.46 266	96.00 317	98.67 299
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
CMPMVS	69.68 23	94.13 355	94.90 347	91.84 380	97.24 391	80.01 410	98.52 381	99.48 159	89.01 397	91.99 397	99.67 181	85.67 377	99.13 330	95.44 340	97.03 298	96.39 398
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
eth_miper_zixun_eth		98.05 213	97.96 208	98.33 287	99.26 250	97.38 273	98.56 380	99.31 277	96.65 293	98.88 261	99.52 240	96.58 152	99.12 334	97.39 271	95.53 333	98.47 343

pmmvs4		98.13 200	97.90 215	98.81 233	98.61 363	98.87 175	98.99 333	99.21 300	96.44 312	99.06 234	99.58 217	95.90 179	99.11 335	97.18 286	96.11 314	98.46 346

TransMVSNet (Re)		97.15 312	96.58 317	98.86 224	99.12 287	98.85 179	99.49 176	98.91 340	95.48 348	97.16 362	99.80 106	93.38 271	99.11 335	94.16 362	91.73 381	98.62 320

ambc				93.06 378	92.68 409	82.36 403	98.47 383	98.73 367		95.09 384	97.41 392	55.55 410	99.10 337	96.42 319	91.32 382	97.71 384

Baseline_NR-MVSNet		97.76 260	97.45 267	98.68 246	99.09 295	98.29 227	99.41 211	98.85 349	95.65 346	98.63 300	99.67 181	94.82 215	99.10 337	98.07 209	92.89 374	98.64 311

test_vis3_rt		87.04 370	85.81 373	90.73 384	93.99 408	81.96 405	99.76 36	90.23 419	92.81 383	81.35 407	91.56 407	40.06 416	99.07 339	94.27 359	88.23 394	91.15 407

CP-MVSNet		98.09 204	97.78 227	99.01 191	98.97 317	99.24 123	99.67 67	99.46 188	97.25 245	98.48 313	99.64 193	93.79 265	99.06 340	98.63 146	94.10 359	98.74 274

PS-CasMVS		97.93 231	97.59 251	98.95 200	98.99 312	99.06 147	99.68 64	99.52 103	97.13 255	98.31 321	99.68 175	92.44 302	99.05 341	98.51 167	94.08 360	98.75 271

K. test v3		97.10 314	96.79 314	98.01 312	98.72 351	96.33 329	99.87 7	97.05 396	97.59 206	96.16 375	99.80 106	88.71 355	99.04 342	96.69 311	96.55 305	98.65 309

new_pmnet		96.38 328	96.03 330	97.41 342	98.13 377	95.16 358	99.05 317	99.20 301	93.94 370	97.39 356	98.79 361	91.61 322	99.04 342	90.43 387	95.77 324	98.05 371

DIV-MVS_self_test		98.01 221	97.85 221	98.48 266	99.24 256	97.95 248	98.71 368	99.35 251	96.50 305	98.60 305	99.54 233	95.72 186	99.03 344	97.21 280	95.77 324	98.46 346

IterMVS-LS		98.46 170	98.42 168	98.58 254	99.59 150	98.00 242	99.37 230	99.43 213	96.94 277	99.07 229	99.59 213	97.87 109	99.03 344	98.32 187	95.62 329	98.71 278
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
our_test_3		97.65 282	97.68 240	97.55 339	98.62 361	94.97 360	98.84 355	99.30 281	96.83 284	98.19 330	99.34 295	97.01 138	99.02 346	95.00 350	96.01 316	98.64 311

Patchmtry		97.75 264	97.40 279	98.81 233	99.10 292	98.87 175	99.11 308	99.33 263	94.83 361	98.81 271	99.38 282	94.33 245	99.02 346	96.10 323	95.57 331	98.53 337

N_pmnet		94.95 349	95.83 335	92.31 379	98.47 370	79.33 411	99.12 302	92.81 417	93.87 371	97.68 349	99.13 328	93.87 262	99.01 348	91.38 384	96.19 312	98.59 333

CR-MVSNet		98.17 196	97.93 213	98.87 221	99.18 271	98.49 216	99.22 285	99.33 263	96.96 273	99.56 120	99.38 282	94.33 245	99.00 349	94.83 353	98.58 213	99.14 230

c3_l		98.12 202	98.04 200	98.38 284	99.30 239	97.69 264	98.81 358	99.33 263	96.67 291	98.83 269	99.34 295	97.11 131	98.99 350	97.58 251	95.34 336	98.48 341

test0.0.03 1		97.71 273	97.42 277	98.56 258	98.41 373	97.82 255	98.78 361	98.63 372	97.34 237	98.05 338	98.98 345	94.45 242	98.98 351	95.04 349	97.15 296	98.89 258

PatchT		97.03 316	96.44 321	98.79 236	98.99 312	98.34 226	99.16 293	99.07 318	92.13 386	99.52 129	97.31 396	94.54 238	98.98 351	88.54 394	98.73 207	99.03 246

GBi-Net		97.68 277	97.48 261	98.29 292	99.51 174	97.26 279	99.43 201	99.48 159	96.49 306	99.07 229	99.32 302	90.26 337	98.98 351	97.10 288	96.65 301	98.62 320

test1		97.68 277	97.48 261	98.29 292	99.51 174	97.26 279	99.43 201	99.48 159	96.49 306	99.07 229	99.32 302	90.26 337	98.98 351	97.10 288	96.65 301	98.62 320

FMVSNet3		98.03 216	97.76 233	98.84 228	99.39 217	98.98 155	99.40 219	99.38 235	96.67 291	99.07 229	99.28 309	92.93 279	98.98 351	97.10 288	96.65 301	98.56 336

FMVSNet2		97.72 270	97.36 282	98.80 235	99.51 174	98.84 180	99.45 191	99.42 215	96.49 306	98.86 268	99.29 307	90.26 337	98.98 351	96.44 318	96.56 304	98.58 334

FMVSNet1		96.84 319	96.36 323	98.29 292	99.32 237	97.26 279	99.43 201	99.48 159	95.11 353	98.55 308	99.32 302	83.95 388	98.98 351	95.81 330	96.26 311	98.62 320

ppachtmachnet_test		97.49 298	97.45 267	97.61 337	98.62 361	95.24 354	98.80 359	99.46 188	96.11 336	98.22 328	99.62 204	96.45 159	98.97 358	93.77 364	95.97 321	98.61 329

TranMVSNet+NR-MVSNet		97.93 231	97.66 242	98.76 239	98.78 340	98.62 201	99.65 78	99.49 147	97.76 188	98.49 312	99.60 211	94.23 248	98.97 358	98.00 213	92.90 373	98.70 283

MVStest1		96.08 335	95.48 340	97.89 321	98.93 320	96.70 313	99.56 125	99.35 251	92.69 384	91.81 398	99.46 261	89.90 343	98.96 360	95.00 350	92.61 378	98.00 376

test_method		91.10 365	91.36 367	90.31 385	95.85 398	73.72 418	94.89 406	99.25 292	68.39 409	95.82 378	99.02 340	80.50 399	98.95 361	93.64 366	94.89 348	98.25 361

ADS-MVSNet2		98.02 218	98.07 198	97.87 322	99.33 231	95.19 356	99.23 281	99.08 315	96.24 324	99.10 224	99.67 181	94.11 253	98.93 362	96.81 305	99.05 184	99.48 183

ET-MVSNet_ETH3D		96.49 325	95.64 339	99.05 187	99.53 166	98.82 184	98.84 355	97.51 394	97.63 203	84.77 403	99.21 321	92.09 307	98.91 363	98.98 93	92.21 380	99.41 205

miper_lstm_enhance		98.00 223	97.91 214	98.28 296	99.34 230	97.43 271	98.88 351	99.36 244	96.48 309	98.80 273	99.55 228	95.98 172	98.91 363	97.27 277	95.50 334	98.51 339

PEN-MVS		97.76 260	97.44 272	98.72 241	98.77 345	98.54 207	99.78 31	99.51 117	97.06 265	98.29 324	99.64 193	92.63 293	98.89 365	98.09 202	93.16 371	98.72 276

testing3		97.28 306	96.76 315	98.82 230	99.37 222	98.07 239	99.45 191	99.36 244	97.56 211	97.89 343	98.95 348	83.70 389	98.82 366	96.03 325	98.56 216	99.58 154

testgi		97.65 282	97.50 259	98.13 306	99.36 225	96.45 325	99.42 208	99.48 159	97.76 188	97.87 344	99.45 263	91.09 329	98.81 367	94.53 355	98.52 219	99.13 232

testf1		90.42 368	90.68 369	89.65 388	97.78 381	73.97 416	99.13 299	98.81 354	89.62 394	91.80 399	98.93 350	62.23 408	98.80 368	86.61 402	91.17 383	96.19 399

APD_test2		90.42 368	90.68 369	89.65 388	97.78 381	73.97 416	99.13 299	98.81 354	89.62 394	91.80 399	98.93 350	62.23 408	98.80 368	86.61 402	91.17 383	96.19 399

MIMVSNet		97.73 268	97.45 267	98.57 255	99.45 200	97.50 269	99.02 325	98.98 328	96.11 336	99.41 153	99.14 327	90.28 336	98.74 370	95.74 332	98.93 192	99.47 189

LCM-MVSNet-Re		97.83 249	98.15 185	96.87 358	99.30 239	92.25 388	99.59 104	98.26 380	97.43 229	96.20 374	99.13 328	96.27 165	98.73 371	98.17 198	98.99 189	99.64 136

Syy-MVS		97.09 315	97.14 301	96.95 355	99.00 309	92.73 386	99.29 256	99.39 227	97.06 265	97.41 353	98.15 382	93.92 261	98.68 372	91.71 382	98.34 225	99.45 198

myMVS_eth3d		96.89 317	96.37 322	98.43 279	99.00 309	97.16 283	99.29 256	99.39 227	97.06 265	97.41 353	98.15 382	83.46 390	98.68 372	95.27 345	98.34 225	99.45 198

DTE-MVSNet		97.51 292	97.19 300	98.46 272	98.63 360	98.13 236	99.84 11	99.48 159	96.68 290	97.97 341	99.67 181	92.92 280	98.56 374	96.88 304	92.60 379	98.70 283

PC_three_1452									98.18 135	99.84 34	99.70 159	99.31 3	98.52 375	98.30 189	99.80 102	99.81 61

mvsany_test3		93.77 357	93.45 361	94.74 370	95.78 399	88.01 396	99.64 81	98.25 381	98.28 117	94.31 387	97.97 389	68.89 404	98.51 376	97.50 261	90.37 388	97.71 384

UnsupCasMVSNet_bld		93.53 358	92.51 364	96.58 363	97.38 387	93.82 374	98.24 393	99.48 159	91.10 391	93.10 392	96.66 398	74.89 402	98.37 377	94.03 363	87.71 395	97.56 389

Anonymous20240521		96.20 331	95.89 334	97.13 349	97.72 384	94.96 361	99.79 30	99.29 285	93.01 380	97.20 361	99.03 338	89.69 346	98.36 378	91.16 385	96.13 313	98.07 369

test_f		91.90 364	91.26 368	93.84 373	95.52 403	85.92 398	99.69 58	98.53 377	95.31 350	93.87 389	96.37 400	55.33 411	98.27 379	95.70 333	90.98 386	97.32 392

MDA-MVSNet_test_wron		95.45 342	94.60 349	98.01 312	98.16 376	97.21 282	99.11 308	99.24 294	93.49 376	80.73 409	98.98 345	93.02 277	98.18 380	94.22 361	94.45 353	98.64 311

UnsupCasMVSNet_eth		96.44 326	96.12 327	97.40 343	98.65 358	95.65 342	99.36 235	99.51 117	97.13 255	96.04 377	98.99 343	88.40 362	98.17 381	96.71 309	90.27 389	98.40 352

KD-MVS_2432*1600		94.62 350	93.72 358	97.31 344	97.19 393	95.82 340	98.34 388	99.20 301	95.00 357	97.57 350	98.35 375	87.95 367	98.10 382	92.87 376	77.00 407	98.01 373

miper_refine_blended		94.62 350	93.72 358	97.31 344	97.19 393	95.82 340	98.34 388	99.20 301	95.00 357	97.57 350	98.35 375	87.95 367	98.10 382	92.87 376	77.00 407	98.01 373

YYNet1		95.36 344	94.51 351	97.92 318	97.89 379	97.10 286	99.10 310	99.23 295	93.26 379	80.77 408	99.04 337	92.81 283	98.02 384	94.30 357	94.18 358	98.64 311

EU-MVSNet		97.98 225	98.03 201	97.81 329	98.72 351	96.65 318	99.66 72	99.66 28	98.09 148	98.35 319	99.82 79	95.25 203	98.01 385	97.41 270	95.30 337	98.78 264

Gipuma		90.99 366	90.15 371	93.51 374	98.73 349	90.12 394	93.98 407	99.45 199	79.32 405	92.28 395	94.91 402	69.61 403	97.98 386	87.42 398	95.67 328	92.45 405
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
pmmvs-eth3d		95.34 345	94.73 348	97.15 347	95.53 402	95.94 338	99.35 240	99.10 312	95.13 351	93.55 390	97.54 391	88.15 366	97.91 387	94.58 354	89.69 392	97.61 387

PM-MVS		92.96 361	92.23 365	95.14 369	95.61 400	89.98 395	99.37 230	98.21 383	94.80 362	95.04 385	97.69 390	65.06 405	97.90 388	94.30 357	89.98 391	97.54 390

MDA-MVSNet-bldmvs		94.96 348	93.98 355	97.92 318	98.24 375	97.27 277	99.15 296	99.33 263	93.80 372	80.09 410	99.03 338	88.31 363	97.86 389	93.49 368	94.36 355	98.62 320

Patchmatch-RL test		95.84 338	95.81 336	95.95 367	95.61 400	90.57 393	98.24 393	98.39 378	95.10 355	95.20 382	98.67 365	94.78 219	97.77 390	96.28 322	90.02 390	99.51 177

Anonymous20231206		96.22 329	96.03 330	96.79 360	97.31 390	94.14 372	99.63 86	99.08 315	96.17 330	97.04 365	99.06 335	93.94 259	97.76 391	86.96 400	95.06 342	98.47 343

SD-MVS		99.41 49	99.52 11	99.05 187	99.74 80	99.68 48	99.46 190	99.52 103	99.11 26	99.88 22	99.91 21	99.43 1	97.70 392	98.72 134	99.93 27	99.77 82
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
DSMNet-mixed		97.25 308	97.35 284	96.95 355	97.84 380	93.61 380	99.57 119	96.63 402	96.13 335	98.87 264	98.61 368	94.59 233	97.70 392	95.08 348	98.86 198	99.55 161

dongtai		93.26 359	92.93 363	94.25 371	99.39 217	85.68 399	97.68 402	93.27 413	92.87 382	96.85 368	99.39 280	82.33 395	97.48 394	76.78 407	97.80 257	99.58 154

pmmvs3		94.09 356	93.25 362	96.60 362	94.76 407	94.49 367	98.92 347	98.18 385	89.66 393	96.48 371	98.06 388	86.28 374	97.33 395	89.68 390	87.20 396	97.97 379

KD-MVS_self_test		95.00 347	94.34 352	96.96 354	97.07 395	95.39 352	99.56 125	99.44 207	95.11 353	97.13 363	97.32 395	91.86 312	97.27 396	90.35 388	81.23 404	98.23 363

FMVSNet5		96.43 327	96.19 326	97.15 347	99.11 289	95.89 339	99.32 246	99.52 103	94.47 368	98.34 320	99.07 333	87.54 371	97.07 397	92.61 379	95.72 327	98.47 343

new-patchmatchnet		94.48 353	94.08 354	95.67 368	95.08 405	92.41 387	99.18 291	99.28 287	94.55 367	93.49 391	97.37 394	87.86 369	97.01 398	91.57 383	88.36 393	97.61 387

LCM-MVSNet		86.80 372	85.22 376	91.53 382	87.81 414	80.96 408	98.23 395	98.99 327	71.05 407	90.13 402	96.51 399	48.45 415	96.88 399	90.51 386	85.30 398	96.76 394

CL-MVSNet_self_test		94.49 352	93.97 356	96.08 366	96.16 397	93.67 379	98.33 390	99.38 235	95.13 351	97.33 357	98.15 382	92.69 291	96.57 400	88.67 393	79.87 405	97.99 377

MIMVSNet1		95.51 341	95.04 346	96.92 357	97.38 387	95.60 343	99.52 151	99.50 137	93.65 374	96.97 367	99.17 323	85.28 382	96.56 401	88.36 395	95.55 332	98.60 332

test20.03		96.12 333	95.96 332	96.63 361	97.44 386	95.45 350	99.51 158	99.38 235	96.55 303	96.16 375	99.25 315	93.76 267	96.17 402	87.35 399	94.22 357	98.27 359

tmp_tt		82.80 374	81.52 377	86.66 390	66.61 420	68.44 419	92.79 409	97.92 387	68.96 408	80.04 411	99.85 54	85.77 376	96.15 403	97.86 223	43.89 413	95.39 403

test_fmvs3		92.10 363	91.77 366	93.08 377	96.19 396	86.25 397	99.82 15	98.62 373	96.65 293	95.19 383	96.90 397	55.05 412	95.93 404	96.63 315	90.92 387	97.06 393

kuosan		90.92 367	90.11 372	93.34 375	98.78 340	85.59 400	98.15 397	93.16 415	89.37 396	92.07 396	98.38 374	81.48 398	95.19 405	62.54 414	97.04 297	99.25 225

dmvs_testset		95.02 346	96.12 327	91.72 381	99.10 292	80.43 409	99.58 112	97.87 389	97.47 221	95.22 381	98.82 357	93.99 257	95.18 406	88.09 396	94.91 347	99.56 160

PMMVS2		86.87 371	85.37 375	91.35 383	90.21 412	83.80 402	98.89 350	97.45 395	83.13 404	91.67 401	95.03 401	48.49 414	94.70 407	85.86 404	77.62 406	95.54 402

PMVS	70.75 22	75.98 380	74.97 381	79.01 396	70.98 419	55.18 421	93.37 408	98.21 383	65.08 413	61.78 414	93.83 404	21.74 421	92.53 408	78.59 406	91.12 385	89.34 409
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
FPMVS		84.93 373	85.65 374	82.75 394	86.77 415	63.39 420	98.35 387	98.92 336	74.11 406	83.39 405	98.98 345	50.85 413	92.40 409	84.54 405	94.97 344	92.46 404

WB-MVS		93.10 360	94.10 353	90.12 386	95.51 404	81.88 406	99.73 49	99.27 289	95.05 356	93.09 393	98.91 354	94.70 228	91.89 410	76.62 408	94.02 362	96.58 396

SSC-MVS		92.73 362	93.73 357	89.72 387	95.02 406	81.38 407	99.76 36	99.23 295	94.87 360	92.80 394	98.93 350	94.71 227	91.37 411	74.49 410	93.80 364	96.42 397

MVE	76.82 21	76.91 379	74.31 383	84.70 391	85.38 417	76.05 415	96.88 405	93.17 414	67.39 410	71.28 412	89.01 411	21.66 422	87.69 412	71.74 411	72.29 409	90.35 408
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
E-PMN		80.61 376	79.88 378	82.81 393	90.75 411	76.38 414	97.69 401	95.76 406	66.44 411	83.52 404	92.25 406	62.54 407	87.16 413	68.53 412	61.40 410	84.89 411

EMVS		80.02 377	79.22 379	82.43 395	91.19 410	76.40 413	97.55 404	92.49 418	66.36 412	83.01 406	91.27 408	64.63 406	85.79 414	65.82 413	60.65 411	85.08 410

ANet_high		77.30 378	74.86 382	84.62 392	75.88 418	77.61 412	97.63 403	93.15 416	88.81 398	64.27 413	89.29 410	36.51 417	83.93 415	75.89 409	52.31 412	92.33 406

wuyk23d		40.18 381	41.29 386	36.84 397	86.18 416	49.12 422	79.73 410	22.81 422	27.64 414	25.46 417	28.45 417	21.98 420	48.89 416	55.80 415	23.56 416	12.51 414

test123		39.01 383	42.50 385	28.53 398	39.17 421	20.91 423	98.75 364	19.17 423	19.83 416	38.57 415	66.67 413	33.16 418	15.42 417	37.50 417	29.66 415	49.26 412

testmvs		39.17 382	43.78 384	25.37 399	36.04 422	16.84 424	98.36 386	26.56 421	20.06 415	38.51 416	67.32 412	29.64 419	15.30 418	37.59 416	39.90 414	43.98 413

test_blank		0.13 387	0.17 390	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	1.57 418	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

uanet_test		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

DCPMVS		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

cdsmvs_eth3d_5k		24.64 384	32.85 387	0.00 400	0.00 423	0.00 425	0.00 411	99.51 117	0.00 418	0.00 419	99.56 225	96.58 152	0.00 419	0.00 418	0.00 417	0.00 415

pcd_1.5k_mvsjas		8.27 386	11.03 389	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	99.01 18	0.00 419	0.00 418	0.00 417	0.00 415

sosnet-low-res		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

sosnet		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

uncertanet		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

Regformer		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

ab-mvs-re		8.30 385	11.06 388	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	99.58 217	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

uanet		0.02 388	0.03 391	0.00 400	0.00 423	0.00 425	0.00 411	0.00 424	0.00 418	0.00 419	0.27 419	0.00 423	0.00 419	0.00 418	0.00 417	0.00 415

WAC-MVS						97.16 283								95.47 339

FOURS1					99.91 1	99.93 1	99.87 7	99.56 71	99.10 27	99.81 41

test_one_0601					99.81 46	99.88 8		99.49 147	98.97 51	99.65 94	99.81 93	99.09 14

eth-test2					0.00 423

eth-test					0.00 423

RE-MVS-def			99.34 40		99.76 65	99.82 22	99.63 86	99.52 103	98.38 106	99.76 60	99.82 79	98.75 55		98.61 150	99.81 98	99.77 82

IU-MVS					99.84 32	99.88 8		99.32 273	98.30 116	99.84 34				98.86 114	99.85 74	99.89 19

save fliter					99.76 65	99.59 71	99.14 298	99.40 224	99.00 43

test0726					99.85 26	99.89 4	99.62 91	99.50 137	99.10 27	99.86 32	99.82 79	98.94 29

GSMVS																99.52 170

test_part2					99.81 46	99.83 16				99.77 55

sam_mvs1												94.86 214				99.52 170

sam_mvs												94.72 226

MTGPA								99.47 179

MTMP							99.54 142	98.88 345

test9_res														97.49 262	99.72 123	99.75 88

agg_prior2														97.21 280	99.73 122	99.75 88

test_prior4						99.56 77	98.99 333

test_prior2							98.96 340		98.34 112	99.01 240	99.52 240	98.68 64		97.96 215	99.74 120

新几何2							99.01 330

旧先验1					99.74 80	99.59 71		99.54 87			99.69 169	98.47 80			99.68 131	99.73 97

原ACMM2							98.95 343

test222					99.75 73	99.49 91	98.91 349	99.49 147	96.42 314	99.34 173	99.65 187	98.28 93			99.69 128	99.72 103

segment_acmp												98.96 24

testdata1							98.85 354		98.32 115

plane_prior7					99.29 243	97.03 296

plane_prior6					99.27 248	96.98 300						92.71 289

plane_prior4											99.61 208

plane_prior3						97.00 298			98.69 80	99.11 221

plane_prior2							99.39 223		98.97 51

plane_prior1					99.26 250

plane_prior						96.97 301	99.21 287		98.45 99						97.60 266

n2								0.00 424

nn								0.00 424

door-mid								98.05 386

test11								99.35 251

door								97.92 387

HQP5-MVS						96.83 308

HQP-NCC					99.19 268		98.98 336		98.24 124	98.66 291

ACMP_Plane					99.19 268		98.98 336		98.24 124	98.66 291

BP-MVS														97.19 284

HQP3-MVS								99.39 227							97.58 268

HQP2-MVS												92.47 298

NP-MVS					99.23 258	96.92 304					99.40 276

MDTV_nov1_ep13_2view						95.18 357	99.35 240		96.84 282	99.58 116		95.19 205		97.82 228		99.46 195

ACMMP++_ref															97.19 294

ACMMP++															97.43 285

Test By Simon												98.75 55

High-resolution multi-view benchmark