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_fmvsm_n_1920		97.55 9	97.89 3	96.53 73	98.41 74	91.73 101	98.01 56	99.02 1	96.37 3	99.30 1	98.92 3	92.39 35	99.79 31	99.16 2	99.46 39	98.08 155

PGM-MVS		96.81 36	96.53 42	97.65 40	99.35 20	93.53 57	97.65 96	98.98 2	92.22 121	97.14 42	98.44 34	91.17 59	99.85 17	94.35 103	99.46 39	99.57 23

MVS_111021_HR		96.68 44	96.58 41	96.99 62	98.46 70	92.31 87	96.20 233	98.90 3	94.30 51	95.86 92	97.74 94	92.33 36	99.38 103	96.04 53	99.42 45	99.28 59

ACMMP		96.27 54	95.93 56	97.28 52	99.24 28	92.62 78	98.25 36	98.81 4	92.99 97	94.56 121	98.39 38	88.96 85	99.85 17	94.57 102	97.63 122	99.36 54
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
MVS_111021_LR		96.24 55	96.19 54	96.39 89	98.23 90	91.35 121	96.24 231	98.79 5	93.99 57	95.80 94	97.65 101	89.92 76	99.24 114	95.87 57	99.20 67	98.58 117

patch_mono-2		96.83 35	97.44 10	95.01 162	99.05 39	85.39 287	96.98 165	98.77 6	94.70 38	97.99 24	98.66 17	93.61 19	99.91 1	97.67 8	99.50 33	99.72 10

FC-MVSNet-test		93.94 117	93.57 110	95.04 159	95.48 232	91.45 118	98.12 48	98.71 7	93.37 81	90.23 215	96.70 152	87.66 102	97.85 269	91.49 161	90.39 253	95.83 235

UniMVSNet (Re)		93.31 140	92.55 154	95.61 133	95.39 236	93.34 63	97.39 129	98.71 7	93.14 93	90.10 224	94.83 250	87.71 101	98.03 244	91.67 159	83.99 321	95.46 258

FIs		94.09 111	93.70 106	95.27 149	95.70 223	92.03 96	98.10 49	98.68 9	93.36 83	90.39 212	96.70 152	87.63 104	97.94 259	92.25 141	90.50 252	95.84 234

WR-MVS_H		92.00 197	91.35 193	93.95 220	95.09 260	89.47 185	98.04 54	98.68 9	91.46 143	88.34 272	94.68 257	85.86 130	97.56 294	85.77 271	84.24 319	94.82 297

VPA-MVSNet		93.24 142	92.48 159	95.51 139	95.70 223	92.39 84	97.86 71	98.66 11	92.30 120	92.09 177	95.37 228	80.49 220	98.40 197	93.95 110	85.86 293	95.75 245

UniMVSNet_NR-MVSNet		93.37 138	92.67 148	95.47 144	95.34 242	92.83 73	97.17 152	98.58 12	92.98 102	90.13 220	95.80 205	88.37 95	97.85 269	91.71 156	83.93 322	95.73 247

CSCG		96.05 57	95.91 57	96.46 83	99.24 28	90.47 156	98.30 30	98.57 13	89.01 217	93.97 135	97.57 109	92.62 31	99.76 33	94.66 97	99.27 59	99.15 69

MSLP-MVS++		96.94 28	97.06 15	96.59 71	98.72 55	91.86 100	97.67 93	98.49 14	94.66 41	97.24 39	98.41 37	92.31 38	98.94 149	96.61 33	99.46 39	98.96 88

HyFIR lowres test		93.66 128	92.92 135	95.87 117	98.24 86	89.88 171	94.58 288	98.49 14	85.06 308	93.78 138	95.78 209	82.86 177	98.67 175	91.77 154	95.71 168	99.07 79

CHOSEN 1792x2688		94.15 106	93.51 116	96.06 109	98.27 83	89.38 190	95.18 278	98.48 16	85.60 298	93.76 139	97.11 132	83.15 168	99.61 60	91.33 164	98.72 90	99.19 65

PHI-MVS		96.77 38	96.46 47	97.71 38	98.40 75	94.07 45	98.21 43	98.45 17	89.86 192	97.11 44	98.01 73	92.52 33	99.69 46	96.03 54	99.53 27	99.36 54

PVSNet_BlendedMVS		94.06 112	93.92 102	94.47 192	98.27 83	89.46 187	96.73 184	98.36 18	90.17 186	94.36 124	95.24 234	88.02 96	99.58 67	93.44 121	90.72 248	94.36 317

PVSNet_Blended		94.87 91	94.56 88	95.81 120	98.27 83	89.46 187	95.47 264	98.36 18	88.84 225	94.36 124	96.09 194	88.02 96	99.58 67	93.44 121	98.18 109	98.40 137

3Dnovator	91.36 5	95.19 81	94.44 96	97.44 46	96.56 183	93.36 62	98.65 11	98.36 18	94.12 54	89.25 254	98.06 67	82.20 193	99.77 32	93.41 123	99.32 56	99.18 66

FOURS1					99.55 1	93.34 63	99.29 1	98.35 21	94.98 24	98.49 16

DPE-MVS		97.86 4	97.65 6	98.47 5	99.17 32	95.78 7	97.21 149	98.35 21	95.16 18	98.71 13	98.80 13	95.05 10	99.89 3	96.70 31	99.73 1	99.73 9
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
HFP-MVS		97.14 19	96.92 23	97.83 25	99.42 7	94.12 43	98.52 16	98.32 23	93.21 86	97.18 40	98.29 53	92.08 40	99.83 25	95.63 70	99.59 17	99.54 30

ACMMPR		97.07 21	96.84 26	97.79 29	99.44 6	93.88 49	98.52 16	98.31 24	93.21 86	97.15 41	98.33 47	91.35 54	99.86 8	95.63 70	99.59 17	99.62 16

test_fmvsmvis_n_1920		96.70 40	96.84 26	96.31 94	96.62 176	91.73 101	97.98 59	98.30 25	96.19 4	96.10 83	98.95 1	89.42 79	99.76 33	98.90 3	99.08 76	97.43 184

APDe-MVS		97.82 5	97.73 5	98.08 17	99.15 33	94.82 26	98.81 7	98.30 25	94.76 36	98.30 18	98.90 5	93.77 17	99.68 48	97.93 4	99.69 3	99.75 5

test0726					99.45 3	95.36 13	98.31 29	98.29 27	94.92 25	98.99 5	98.92 3	95.08 8

MSP-MVS		97.59 8	97.54 7	97.73 35	99.40 11	93.77 53	98.53 15	98.29 27	95.55 9	98.56 15	97.81 89	93.90 15	99.65 52	96.62 32	99.21 66	99.77 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
DVP-MVS++		98.06 1	97.99 1	98.28 9	98.67 58	95.39 11	99.29 1	98.28 29	94.78 34	98.93 7	98.87 8	96.04 2	99.86 8	97.45 16	99.58 21	99.59 20

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 29					99.86 8	97.52 12	99.67 6	99.75 5

CP-MVS		97.02 24	96.81 30	97.64 42	99.33 21	93.54 56	98.80 8	98.28 29	92.99 97	96.45 72	98.30 52	91.90 43	99.85 17	95.61 72	99.68 4	99.54 30

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 32	95.13 19	99.19 2	98.89 6	95.54 5	99.85 17	97.52 12	99.66 10	99.56 26

test_241102_TWO								98.27 32	95.13 19	98.93 7	98.89 6	94.99 11	99.85 17	97.52 12	99.65 12	99.74 7

test_241102_ONE					99.42 7	95.30 17		98.27 32	95.09 22	99.19 2	98.81 12	95.54 5	99.65 52

SF-MVS		97.39 12	97.13 13	98.17 14	99.02 42	95.28 19	98.23 40	98.27 32	92.37 119	98.27 19	98.65 19	93.33 21	99.72 39	96.49 37	99.52 28	99.51 34

SteuartSystems-ACMMP		97.62 7	97.53 8	97.87 23	98.39 77	94.25 37	98.43 24	98.27 32	95.34 13	98.11 20	98.56 21	94.53 12	99.71 40	96.57 35	99.62 15	99.65 13
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 37	95.13 19	98.48 17	98.87 8	95.16 7

PVSNet_Blended_VisFu		95.27 76	94.91 79	96.38 90	98.20 91	90.86 143	97.27 141	98.25 37	90.21 185	94.18 129	97.27 123	87.48 108	99.73 36	93.53 118	97.77 120	98.55 118

region2R		97.07 21	96.84 26	97.77 32	99.46 2	93.79 51	98.52 16	98.24 39	93.19 89	97.14 42	98.34 44	91.59 50	99.87 7	95.46 77	99.59 17	99.64 14

PS-CasMVS		91.55 213	90.84 214	93.69 236	94.96 264	88.28 224	97.84 75	98.24 39	91.46 143	88.04 282	95.80 205	79.67 236	97.48 302	87.02 251	84.54 316	95.31 269

DU-MVS		92.90 162	92.04 169	95.49 141	94.95 265	92.83 73	97.16 153	98.24 39	93.02 96	90.13 220	95.71 212	83.47 161	97.85 269	91.71 156	83.93 322	95.78 240

9.14			96.75 33		98.93 47		97.73 85	98.23 42	91.28 151	97.88 27	98.44 34	93.00 24	99.65 52	95.76 63	99.47 38

D2MVS		91.30 228	90.95 208	92.35 279	94.71 282	85.52 283	96.18 234	98.21 43	88.89 223	86.60 306	93.82 297	79.92 232	97.95 258	89.29 202	90.95 244	93.56 330

SDMVSNet		94.17 104	93.61 109	95.86 118	98.09 99	91.37 120	97.35 133	98.20 44	93.18 90	91.79 182	97.28 121	79.13 244	98.93 150	94.61 100	92.84 207	97.28 191

XVS		97.18 17	96.96 22	97.81 27	99.38 14	94.03 47	98.59 12	98.20 44	94.85 27	96.59 64	98.29 53	91.70 46	99.80 29	95.66 65	99.40 48	99.62 16

X-MVStestdata		91.71 204	89.67 263	97.81 27	99.38 14	94.03 47	98.59 12	98.20 44	94.85 27	96.59 64	32.69 381	91.70 46	99.80 29	95.66 65	99.40 48	99.62 16

ACMMP_NAP		97.20 16	96.86 24	98.23 11	99.09 34	95.16 22	97.60 105	98.19 47	92.82 108	97.93 26	98.74 16	91.60 49	99.86 8	96.26 40	99.52 28	99.67 11

CP-MVSNet		91.89 200	91.24 200	93.82 228	95.05 261	88.57 215	97.82 77	98.19 47	91.70 137	88.21 278	95.76 210	81.96 197	97.52 300	87.86 226	84.65 311	95.37 266

ZNCC-MVS		96.96 26	96.67 37	97.85 24	99.37 16	94.12 43	98.49 20	98.18 49	92.64 114	96.39 74	98.18 60	91.61 48	99.88 4	95.59 75	99.55 24	99.57 23

SMA-MVS		97.35 13	97.03 19	98.30 8	99.06 38	95.42 10	97.94 66	98.18 49	90.57 180	98.85 10	98.94 2	93.33 21	99.83 25	96.72 30	99.68 4	99.63 15
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
PEN-MVS		91.20 232	90.44 228	93.48 245	94.49 289	87.91 239	97.76 81	98.18 49	91.29 148	87.78 286	95.74 211	80.35 223	97.33 313	85.46 275	82.96 332	95.19 278

DELS-MVS		96.61 45	96.38 50	97.30 50	97.79 116	93.19 66	95.96 244	98.18 49	95.23 15	95.87 91	97.65 101	91.45 51	99.70 45	95.87 57	99.44 44	99.00 86
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
tfpnnormal		89.70 277	88.40 282	93.60 239	95.15 256	90.10 162	97.56 109	98.16 53	87.28 272	86.16 310	94.63 260	77.57 271	98.05 240	74.48 349	84.59 314	92.65 343

VNet		95.89 62	95.45 65	97.21 56	98.07 103	92.94 72	97.50 115	98.15 54	93.87 61	97.52 31	97.61 107	85.29 136	99.53 81	95.81 62	95.27 175	99.16 67

DeepPCF-MVS	93.97 1	96.61 45	97.09 14	95.15 153	98.09 99	86.63 267	96.00 242	98.15 54	95.43 10	97.95 25	98.56 21	93.40 20	99.36 104	96.77 28	99.48 37	99.45 42

SD-MVS		97.41 11	97.53 8	97.06 61	98.57 69	94.46 30	97.92 68	98.14 56	94.82 31	99.01 4	98.55 23	94.18 14	97.41 309	96.94 24	99.64 13	99.32 56
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
GST-MVS		96.85 34	96.52 43	97.82 26	99.36 18	94.14 42	98.29 31	98.13 57	92.72 111	96.70 56	98.06 67	91.35 54	99.86 8	94.83 91	99.28 58	99.47 41

UA-Net		95.95 61	95.53 62	97.20 57	97.67 121	92.98 71	97.65 96	98.13 57	94.81 32	96.61 62	98.35 41	88.87 86	99.51 86	90.36 179	97.35 132	99.11 75

QAPM		93.45 136	92.27 164	96.98 63	96.77 170	92.62 78	98.39 26	98.12 59	84.50 316	88.27 276	97.77 92	82.39 190	99.81 28	85.40 276	98.81 87	98.51 123

Vis-MVSNet		95.23 78	94.81 80	96.51 77	97.18 141	91.58 111	98.26 35	98.12 59	94.38 49	94.90 114	98.15 62	82.28 191	98.92 151	91.45 163	98.58 95	99.01 83
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 164	91.68 183	96.40 87	95.34 242	92.73 76	98.27 33	98.12 59	84.86 311	85.78 312	97.75 93	78.89 253	99.74 35	87.50 241	98.65 92	96.73 207

TranMVSNet+NR-MVSNet		92.50 173	91.63 184	95.14 154	94.76 277	92.07 94	97.53 113	98.11 62	92.90 106	89.56 242	96.12 190	83.16 167	97.60 292	89.30 201	83.20 331	95.75 245

CPTT-MVS		95.57 70	95.19 73	96.70 65	99.27 26	91.48 115	98.33 28	98.11 62	87.79 257	95.17 111	98.03 70	87.09 114	99.61 60	93.51 119	99.42 45	99.02 80

APD-MVS		96.95 27	96.60 39	98.01 18	99.03 41	94.93 25	97.72 88	98.10 64	91.50 141	98.01 23	98.32 49	92.33 36	99.58 67	94.85 90	99.51 31	99.53 33
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 32	96.60 39	97.64 42	99.40 11	93.44 58	98.50 19	98.09 65	93.27 85	95.95 90	98.33 47	91.04 61	99.88 4	95.20 82	99.57 23	99.60 19

ZD-MVS					99.05 39	94.59 28		98.08 66	89.22 211	97.03 47	98.10 63	92.52 33	99.65 52	94.58 101	99.31 57

MTGPA								98.08 66

MTAPA		97.08 20	96.78 32	97.97 21	99.37 16	94.42 32	97.24 143	98.08 66	95.07 23	96.11 82	98.59 20	90.88 65	99.90 2	96.18 49	99.50 33	99.58 22

CNVR-MVS		97.68 6	97.44 10	98.37 7	98.90 50	95.86 6	97.27 141	98.08 66	95.81 7	97.87 28	98.31 50	94.26 13	99.68 48	97.02 23	99.49 36	99.57 23

DP-MVS Recon		95.68 66	95.12 76	97.37 48	99.19 31	94.19 39	97.03 158	98.08 66	88.35 241	95.09 113	97.65 101	89.97 75	99.48 91	92.08 148	98.59 94	98.44 134

SR-MVS		97.01 25	96.86 24	97.47 45	99.09 34	93.27 65	97.98 59	98.07 71	93.75 64	97.45 32	98.48 31	91.43 52	99.59 64	96.22 43	99.27 59	99.54 30

MCST-MVS		97.18 17	96.84 26	98.20 13	99.30 24	95.35 15	97.12 156	98.07 71	93.54 73	96.08 84	97.69 96	93.86 16	99.71 40	96.50 36	99.39 50	99.55 29

NR-MVSNet		92.34 182	91.27 199	95.53 138	94.95 265	93.05 69	97.39 129	98.07 71	92.65 113	84.46 323	95.71 212	85.00 140	97.77 278	89.71 190	83.52 328	95.78 240

MP-MVS-pluss		96.70 40	96.27 52	97.98 20	99.23 30	94.71 27	96.96 167	98.06 74	90.67 171	95.55 103	98.78 15	91.07 60	99.86 8	96.58 34	99.55 24	99.38 52
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 36	96.71 36	97.12 59	99.01 45	92.31 87	97.98 59	98.06 74	93.11 94	97.44 33	98.55 23	90.93 63	99.55 77	96.06 50	99.25 63	99.51 34

MP-MVS		96.77 38	96.45 48	97.72 36	99.39 13	93.80 50	98.41 25	98.06 74	93.37 81	95.54 105	98.34 44	90.59 69	99.88 4	94.83 91	99.54 26	99.49 38
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 47	96.27 52	97.22 55	99.32 22	92.74 75	98.74 9	98.06 74	90.57 180	96.77 53	98.35 41	90.21 72	99.53 81	94.80 94	99.63 14	99.38 52

HPM-MVS		96.69 42	96.45 48	97.40 47	99.36 18	93.11 68	98.87 6	98.06 74	91.17 156	96.40 73	97.99 74	90.99 62	99.58 67	95.61 72	99.61 16	99.49 38
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 97	93.80 104	96.64 66	97.07 148	91.97 98	96.32 223	98.06 74	88.94 221	94.50 122	96.78 147	84.60 144	99.27 112	91.90 149	96.02 159	98.68 114

DeepC-MVS	93.07 3	96.06 56	95.66 60	97.29 51	97.96 105	93.17 67	97.30 139	98.06 74	93.92 59	93.38 148	98.66 17	86.83 116	99.73 36	95.60 74	99.22 65	98.96 88
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
NCCC		97.30 15	97.03 19	98.11 16	98.77 53	95.06 24	97.34 134	98.04 81	95.96 5	97.09 45	97.88 82	93.18 23	99.71 40	95.84 61	99.17 69	99.56 26

DeepC-MVS_fast	93.89 2	96.93 29	96.64 38	97.78 30	98.64 64	94.30 34	97.41 124	98.04 81	94.81 32	96.59 64	98.37 39	91.24 56	99.64 59	95.16 83	99.52 28	99.42 48
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
SR-MVS-dyc-post		96.88 31	96.80 31	97.11 60	99.02 42	92.34 85	97.98 59	98.03 83	93.52 75	97.43 35	98.51 26	91.40 53	99.56 75	96.05 51	99.26 61	99.43 46

RE-MVS-def			96.72 35		99.02 42	92.34 85	97.98 59	98.03 83	93.52 75	97.43 35	98.51 26	90.71 67		96.05 51	99.26 61	99.43 46

RPMNet		88.98 282	87.05 296	94.77 181	94.45 291	87.19 252	90.23 358	98.03 83	77.87 360	92.40 165	87.55 363	80.17 227	99.51 86	68.84 366	93.95 196	97.60 178

save fliter					98.91 49	94.28 35	97.02 160	98.02 86	95.35 12

TEST9					98.70 56	94.19 39	96.41 212	98.02 86	88.17 245	96.03 85	97.56 111	92.74 28	99.59 64

train_agg		96.30 53	95.83 59	97.72 36	98.70 56	94.19 39	96.41 212	98.02 86	88.58 234	96.03 85	97.56 111	92.73 29	99.59 64	95.04 85	99.37 54	99.39 50

test_8					98.67 58	94.06 46	96.37 219	98.01 89	88.58 234	95.98 89	97.55 113	92.73 29	99.58 67

agg_prior					98.67 58	93.79 51		98.00 90		95.68 99			99.57 74

test_prior				97.23 54	98.67 58	92.99 70		98.00 90					99.41 99			99.29 57

WR-MVS		92.34 182	91.53 188	94.77 181	95.13 258	90.83 145	96.40 216	97.98 92	91.88 134	89.29 251	95.54 223	82.50 186	97.80 274	89.79 189	85.27 302	95.69 249

HPM-MVS++		97.34 14	96.97 21	98.47 5	99.08 36	96.16 4	97.55 112	97.97 93	95.59 8	96.61 62	97.89 80	92.57 32	99.84 22	95.95 56	99.51 31	99.40 49

CANet		96.39 50	96.02 55	97.50 44	97.62 126	93.38 60	97.02 160	97.96 94	95.42 11	94.86 115	97.81 89	87.38 110	99.82 27	96.88 26	99.20 67	99.29 57

114514_t		93.95 116	93.06 131	96.63 68	99.07 37	91.61 108	97.46 123	97.96 94	77.99 358	93.00 156	97.57 109	86.14 128	99.33 105	89.22 205	99.15 71	98.94 91

IU-MVS					99.42 7	95.39 11		97.94 96	90.40 184	98.94 6				97.41 19	99.66 10	99.74 7

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 97					99.86 8	97.68 6	99.67 6	99.77 1

No_MVS				98.86 1	98.67 58	96.94 1		97.93 97					99.86 8	97.68 6	99.67 6	99.77 1

Anonymous20231211		90.63 255	89.42 268	94.27 204	98.24 86	89.19 202	98.05 53	97.89 99	79.95 350	88.25 277	94.96 242	72.56 308	98.13 222	89.70 191	85.14 304	95.49 253

原ACMM1				96.38 90	98.59 66	91.09 136		97.89 99	87.41 268	95.22 110	97.68 97	90.25 71	99.54 79	87.95 225	99.12 74	98.49 126

CDPH-MVS		95.97 60	95.38 68	97.77 32	98.93 47	94.44 31	96.35 220	97.88 101	86.98 276	96.65 60	97.89 80	91.99 42	99.47 92	92.26 139	99.46 39	99.39 50

test11								97.88 101

EIA-MVS		95.53 71	95.47 64	95.71 128	97.06 151	89.63 176	97.82 77	97.87 103	93.57 69	93.92 136	95.04 240	90.61 68	98.95 148	94.62 99	98.68 91	98.54 119

CS-MVS		96.86 32	97.06 15	96.26 100	98.16 96	91.16 134	99.09 3	97.87 103	95.30 14	97.06 46	98.03 70	91.72 44	98.71 172	97.10 21	99.17 69	98.90 96

无先验							95.79 251	97.87 103	83.87 324				99.65 52	87.68 235		98.89 99

3Dnovator+	91.43 4	95.40 72	94.48 94	98.16 15	96.90 160	95.34 16	98.48 21	97.87 103	94.65 42	88.53 269	98.02 72	83.69 157	99.71 40	93.18 126	98.96 82	99.44 44

VPNet		92.23 190	91.31 196	94.99 163	95.56 228	90.96 139	97.22 148	97.86 107	92.96 104	90.96 204	96.62 167	75.06 292	98.20 215	91.90 149	83.65 327	95.80 238

test_vis1_n_1920		94.17 104	94.58 87	92.91 265	97.42 135	82.02 325	97.83 76	97.85 108	94.68 39	98.10 21	98.49 28	70.15 323	99.32 107	97.91 5	98.82 86	97.40 185

DVP-MVS		97.91 3	97.81 4	98.22 12	99.45 3	95.36 13	98.21 43	97.85 108	94.92 25	98.73 11	98.87 8	95.08 8	99.84 22	97.52 12	99.67 6	99.48 40
Zhenlong Yuan, Jinguo Luo, Fei Shen, Zhaoxin Li, Cong Liu, Tianlu Mao, Zhaoqi Wang: DVP-MVS: Synergize Depth-Edge and Visibility Prior for Multi-View Stereo. AAAI2025
TSAR-MVS + MP.		97.42 10	97.33 12	97.69 39	99.25 27	94.24 38	98.07 52	97.85 108	93.72 65	98.57 14	98.35 41	93.69 18	99.40 100	97.06 22	99.46 39	99.44 44
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
CS-MVS-test		96.89 30	97.04 18	96.45 84	98.29 82	91.66 107	99.03 4	97.85 108	95.84 6	96.90 49	97.97 76	91.24 56	98.75 166	96.92 25	99.33 55	98.94 91

AdaColmap		94.34 100	93.68 107	96.31 94	98.59 66	91.68 106	96.59 203	97.81 112	89.87 191	92.15 173	97.06 135	83.62 160	99.54 79	89.34 200	98.07 112	97.70 171

ETV-MVS		96.02 58	95.89 58	96.40 87	97.16 142	92.44 83	97.47 121	97.77 113	94.55 43	96.48 69	94.51 263	91.23 58	98.92 151	95.65 68	98.19 108	97.82 167

新几何1				97.32 49	98.60 65	93.59 55		97.75 114	81.58 341	95.75 96	97.85 86	90.04 74	99.67 50	86.50 257	99.13 73	98.69 113

旧先验1					98.38 78	93.38 60		97.75 114			98.09 65	92.30 39			99.01 80	99.16 67

EC-MVSNet		96.42 49	96.47 45	96.26 100	97.01 156	91.52 113	98.89 5	97.75 114	94.42 46	96.64 61	97.68 97	89.32 80	98.60 182	97.45 16	99.11 75	98.67 115

EI-MVSNet-Vis-set		96.51 47	96.47 45	96.63 68	98.24 86	91.20 129	96.89 171	97.73 117	94.74 37	96.49 68	98.49 28	90.88 65	99.58 67	96.44 38	98.32 104	99.13 71

PAPM_NR		95.01 83	94.59 86	96.26 100	98.89 51	90.68 151	97.24 143	97.73 117	91.80 135	92.93 161	96.62 167	89.13 83	99.14 125	89.21 206	97.78 119	98.97 87

Anonymous20240529		91.98 198	90.73 219	95.73 126	98.14 97	89.40 189	97.99 58	97.72 119	79.63 352	93.54 143	97.41 117	69.94 325	99.56 75	91.04 170	91.11 240	98.22 146

CHOSEN 280x420		93.12 149	92.72 147	94.34 199	96.71 174	87.27 248	90.29 357	97.72 119	86.61 283	91.34 193	95.29 230	84.29 151	98.41 196	93.25 125	98.94 83	97.35 188

EI-MVSNet-UG-set		96.34 52	96.30 51	96.47 81	98.20 91	90.93 141	96.86 173	97.72 119	94.67 40	96.16 81	98.46 32	90.43 70	99.58 67	96.23 42	97.96 115	98.90 96

LS3D		93.57 132	92.61 152	96.47 81	97.59 130	91.61 108	97.67 93	97.72 119	85.17 306	90.29 214	98.34 44	84.60 144	99.73 36	83.85 296	98.27 105	98.06 156

PAPR		94.18 103	93.42 123	96.48 80	97.64 125	91.42 119	95.55 260	97.71 123	88.99 218	92.34 170	95.82 204	89.19 81	99.11 128	86.14 263	97.38 130	98.90 96

UGNet		94.04 114	93.28 126	96.31 94	96.85 162	91.19 130	97.88 70	97.68 124	94.40 47	93.00 156	96.18 186	73.39 305	99.61 60	91.72 155	98.46 100	98.13 149
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
testdata				95.46 145	98.18 95	88.90 208		97.66 125	82.73 334	97.03 47	98.07 66	90.06 73	98.85 156	89.67 192	98.98 81	98.64 116

test12				97.65 40	98.46 70	94.26 36		97.66 125		95.52 106		90.89 64	99.46 93		99.25 63	99.22 64

DTE-MVSNet		90.56 256	89.75 261	93.01 261	93.95 305	87.25 249	97.64 100	97.65 127	90.74 166	87.12 297	95.68 215	79.97 231	97.00 325	83.33 297	81.66 338	94.78 304

TAPA-MVS	90.10 7	92.30 185	91.22 202	95.56 135	98.33 80	89.60 178	96.79 179	97.65 127	81.83 339	91.52 188	97.23 126	87.94 98	98.91 153	71.31 361	98.37 103	98.17 148
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 150	92.45 160	95.05 158	98.09 99	89.21 199	96.89 171	97.64 129	93.18 90	91.79 182	97.28 121	75.35 291	98.65 177	88.99 211	92.84 207	97.28 191

test_cas_vis1_n_1920		94.48 98	94.55 91	94.28 203	96.78 168	86.45 269	97.63 102	97.64 129	93.32 84	97.68 30	98.36 40	73.75 303	99.08 134	96.73 29	99.05 77	97.31 190

cdsmvs_eth3d_5k		23.24 351	30.99 353	0.00 369	0.00 392	0.00 393	0.00 380	97.63 131	0.00 387	0.00 388	96.88 145	84.38 148	0.00 388	0.00 386	0.00 386	0.00 384

DPM-MVS		95.69 65	94.92 78	98.01 18	98.08 102	95.71 9	95.27 274	97.62 132	90.43 183	95.55 103	97.07 134	91.72 44	99.50 89	89.62 194	98.94 83	98.82 105

canonicalmvs		96.02 58	95.45 65	97.75 34	97.59 130	95.15 23	98.28 32	97.60 133	94.52 44	96.27 78	96.12 190	87.65 103	99.18 120	96.20 48	94.82 183	98.91 95

test222					98.24 86	92.21 90	95.33 269	97.60 133	79.22 354	95.25 108	97.84 88	88.80 88			99.15 71	98.72 110

cascas		91.20 232	90.08 245	94.58 189	94.97 263	89.16 203	93.65 323	97.59 135	79.90 351	89.40 246	92.92 317	75.36 290	98.36 203	92.14 144	94.75 185	96.23 217

h-mvs33		94.15 106	93.52 115	96.04 111	97.81 115	90.22 161	97.62 104	97.58 136	95.19 16	96.74 54	97.45 114	83.67 158	99.61 60	95.85 59	79.73 345	98.29 144

MVSFormer		95.37 73	95.16 74	95.99 114	96.34 197	91.21 127	98.22 41	97.57 137	91.42 145	96.22 79	97.32 119	86.20 126	97.92 263	94.07 107	99.05 77	98.85 102

test_djsdf		93.07 153	92.76 142	94.00 215	93.49 321	88.70 212	98.22 41	97.57 137	91.42 145	90.08 226	95.55 222	82.85 178	97.92 263	94.07 107	91.58 228	95.40 263

OMC-MVS		95.09 82	94.70 84	96.25 103	98.46 70	91.28 123	96.43 210	97.57 137	92.04 130	94.77 117	97.96 77	87.01 115	99.09 132	91.31 165	96.77 146	98.36 141

PS-MVSNAJss		93.74 126	93.51 116	94.44 193	93.91 307	89.28 197	97.75 82	97.56 140	92.50 116	89.94 229	96.54 170	88.65 90	98.18 218	93.83 116	90.90 245	95.86 231

casdiffmvs_mvg		95.81 64	95.57 61	96.51 77	96.87 161	91.49 114	97.50 115	97.56 140	93.99 57	95.13 112	97.92 79	87.89 99	98.78 161	95.97 55	97.33 133	99.26 61
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 177	91.89 176	94.03 214	93.33 327	88.50 219	97.73 85	97.53 142	92.00 132	88.85 261	96.50 172	75.62 289	98.11 228	93.88 114	91.56 229	95.48 254

mvs_tets		92.31 184	91.76 178	93.94 222	93.41 324	88.29 223	97.63 102	97.53 142	92.04 130	88.76 264	96.45 174	74.62 295	98.09 232	93.91 112	91.48 231	95.45 259

dcpmvs_2		96.37 51	97.05 17	94.31 201	98.96 46	84.11 305	97.56 109	97.51 144	93.92 59	97.43 35	98.52 25	92.75 27	99.32 107	97.32 20	99.50 33	99.51 34

HQP_MVS		93.78 125	93.43 121	94.82 174	96.21 201	89.99 166	97.74 83	97.51 144	94.85 27	91.34 193	96.64 158	81.32 207	98.60 182	93.02 132	92.23 216	95.86 231

plane_prior5								97.51 144					98.60 182	93.02 132	92.23 216	95.86 231

PS-MVSNAJ		95.37 73	95.33 70	95.49 141	97.35 136	90.66 152	95.31 271	97.48 147	93.85 62	96.51 67	95.70 214	88.65 90	99.65 52	94.80 94	98.27 105	96.17 221

API-MVS		94.84 92	94.49 93	95.90 116	97.90 111	92.00 97	97.80 79	97.48 147	89.19 212	94.81 116	96.71 150	88.84 87	99.17 121	88.91 213	98.76 89	96.53 210

MG-MVS		95.61 68	95.38 68	96.31 94	98.42 73	90.53 154	96.04 239	97.48 147	93.47 77	95.67 100	98.10 63	89.17 82	99.25 113	91.27 166	98.77 88	99.13 71

MAR-MVS		94.22 102	93.46 118	96.51 77	98.00 104	92.19 92	97.67 93	97.47 150	88.13 248	93.00 156	95.84 202	84.86 142	99.51 86	87.99 224	98.17 110	97.83 166
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
CLD-MVS		92.98 157	92.53 156	94.32 200	96.12 210	89.20 200	95.28 272	97.47 150	92.66 112	89.90 230	95.62 218	80.58 218	98.40 197	92.73 137	92.40 214	95.38 265
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 226	90.22 241	94.68 184	94.86 273	87.86 240	97.23 147	97.46 152	87.99 249	89.90 230	96.92 143	66.35 344	98.23 212	90.30 180	90.99 243	97.96 157

nrg030		94.05 113	93.31 125	96.27 99	95.22 253	94.59 28	98.34 27	97.46 152	92.93 105	91.21 202	96.64 158	87.23 113	98.22 213	94.99 88	85.80 294	95.98 230

XVG-OURS		93.72 127	93.35 124	94.80 179	97.07 148	88.61 213	94.79 283	97.46 152	91.97 133	93.99 133	97.86 85	81.74 202	98.88 155	92.64 138	92.67 212	96.92 202

LPG-MVS_test		92.94 160	92.56 153	94.10 209	96.16 206	88.26 225	97.65 96	97.46 152	91.29 148	90.12 222	97.16 129	79.05 246	98.73 168	92.25 141	91.89 224	95.31 269

LGP-MVS_train				94.10 209	96.16 206	88.26 225		97.46 152	91.29 148	90.12 222	97.16 129	79.05 246	98.73 168	92.25 141	91.89 224	95.31 269

MVS		91.71 204	90.44 228	95.51 139	95.20 255	91.59 110	96.04 239	97.45 157	73.44 366	87.36 294	95.60 219	85.42 135	99.10 129	85.97 268	97.46 125	95.83 235

XVG-OURS-SEG-HR		93.86 121	93.55 111	94.81 176	97.06 151	88.53 218	95.28 272	97.45 157	91.68 138	94.08 132	97.68 97	82.41 189	98.90 154	93.84 115	92.47 213	96.98 198

baseline		95.58 69	95.42 67	96.08 107	96.78 168	90.41 159	97.16 153	97.45 157	93.69 68	95.65 101	97.85 86	87.29 111	98.68 174	95.66 65	97.25 137	99.13 71

ab-mvs		93.57 132	92.55 154	96.64 66	97.28 137	91.96 99	95.40 266	97.45 157	89.81 196	93.22 154	96.28 182	79.62 237	99.46 93	90.74 174	93.11 204	98.50 124

xiu_mvs_v2_base		95.32 75	95.29 71	95.40 146	97.22 138	90.50 155	95.44 265	97.44 161	93.70 67	96.46 71	96.18 186	88.59 93	99.53 81	94.79 96	97.81 118	96.17 221

1314		92.81 168	92.03 170	95.14 154	95.33 245	89.52 184	96.04 239	97.44 161	87.72 261	86.25 309	95.33 229	83.84 155	98.79 160	89.26 203	97.05 142	97.11 196

casdiffmvs		95.64 67	95.49 63	96.08 107	96.76 173	90.45 157	97.29 140	97.44 161	94.00 56	95.46 107	97.98 75	87.52 107	98.73 168	95.64 69	97.33 133	99.08 77
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
XXY-MVS		92.16 192	91.23 201	94.95 168	94.75 279	90.94 140	97.47 121	97.43 164	89.14 213	88.90 258	96.43 175	79.71 235	98.24 211	89.56 195	87.68 277	95.67 251

anonymousdsp		92.16 192	91.55 187	93.97 218	92.58 339	89.55 181	97.51 114	97.42 165	89.42 206	88.40 271	94.84 249	80.66 216	97.88 268	91.87 151	91.28 236	94.48 312

Effi-MVS+		94.93 88	94.45 95	96.36 92	96.61 177	91.47 116	96.41 212	97.41 166	91.02 161	94.50 122	95.92 198	87.53 106	98.78 161	93.89 113	96.81 145	98.84 104

HQP3-MVS								97.39 167							92.10 221

HQP-MVS		93.19 145	92.74 145	94.54 191	95.86 216	89.33 193	96.65 194	97.39 167	93.55 70	90.14 216	95.87 200	80.95 210	98.50 190	92.13 145	92.10 221	95.78 240

PLC	91.00 6	94.11 110	93.43 121	96.13 106	98.58 68	91.15 135	96.69 190	97.39 167	87.29 271	91.37 192	96.71 150	88.39 94	99.52 85	87.33 244	97.13 141	97.73 169
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 249	89.86 254	93.45 247	93.54 318	87.60 245	97.70 92	97.37 170	88.85 224	87.65 288	94.08 289	81.08 209	98.10 229	84.68 284	83.79 326	94.66 309

UnsupCasMVSNet_eth		85.99 312	84.45 316	90.62 319	89.97 357	82.40 322	93.62 324	97.37 170	89.86 192	78.59 357	92.37 325	65.25 350	95.35 353	82.27 309	70.75 366	94.10 323

ACMM	89.79 8	92.96 158	92.50 158	94.35 198	96.30 199	88.71 211	97.58 107	97.36 172	91.40 147	90.53 208	96.65 157	79.77 234	98.75 166	91.24 167	91.64 226	95.59 252
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 83	94.76 81	95.75 123	96.58 180	91.71 103	96.25 228	97.35 173	92.99 97	96.70 56	96.63 164	82.67 181	99.44 96	96.22 43	97.46 125	96.11 226

xiu_mvs_v1_base		95.01 83	94.76 81	95.75 123	96.58 180	91.71 103	96.25 228	97.35 173	92.99 97	96.70 56	96.63 164	82.67 181	99.44 96	96.22 43	97.46 125	96.11 226

xiu_mvs_v1_base_debi		95.01 83	94.76 81	95.75 123	96.58 180	91.71 103	96.25 228	97.35 173	92.99 97	96.70 56	96.63 164	82.67 181	99.44 96	96.22 43	97.46 125	96.11 226

diffmvs		95.25 77	95.13 75	95.63 131	96.43 193	89.34 192	95.99 243	97.35 173	92.83 107	96.31 75	97.37 118	86.44 121	98.67 175	96.26 40	97.19 139	98.87 101
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
WTY-MVS		94.71 96	94.02 100	96.79 64	97.71 120	92.05 95	96.59 203	97.35 173	90.61 177	94.64 119	96.93 140	86.41 122	99.39 101	91.20 168	94.71 187	98.94 91

F-COLMAP		93.58 131	92.98 133	95.37 147	98.40 75	88.98 206	97.18 151	97.29 178	87.75 260	90.49 209	97.10 133	85.21 137	99.50 89	86.70 254	96.72 149	97.63 173

XVG-ACMP-BASELINE		90.93 245	90.21 242	93.09 259	94.31 297	85.89 278	95.33 269	97.26 179	91.06 160	89.38 247	95.44 227	68.61 330	98.60 182	89.46 197	91.05 241	94.79 302

PCF-MVS	89.48 11	91.56 212	89.95 251	96.36 92	96.60 178	92.52 81	92.51 343	97.26 179	79.41 353	88.90 258	96.56 169	84.04 154	99.55 77	77.01 343	97.30 135	97.01 197
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 172	92.14 167	94.05 212	96.40 194	88.20 228	97.36 132	97.25 181	91.52 140	88.30 274	96.64 158	78.46 258	98.72 171	91.86 152	91.48 231	95.23 276
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 141	92.76 142	94.82 174	94.63 285	90.77 148	96.65 194	97.18 182	93.72 65	91.68 184	97.26 124	79.33 241	98.63 179	92.13 145	92.28 215	95.07 280
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 162	92.02 171	95.56 135	98.19 93	90.80 146	95.27 274	97.18 182	87.96 250	91.86 181	95.68 215	80.44 221	98.99 146	84.01 292	97.54 124	96.89 203

alignmvs		95.87 63	95.23 72	97.78 30	97.56 133	95.19 21	97.86 71	97.17 184	94.39 48	96.47 70	96.40 177	85.89 129	99.20 117	96.21 47	95.11 179	98.95 90

MVS_Test		94.89 90	94.62 85	95.68 129	96.83 165	89.55 181	96.70 188	97.17 184	91.17 156	95.60 102	96.11 193	87.87 100	98.76 165	93.01 134	97.17 140	98.72 110

Fast-Effi-MVS+		93.46 135	92.75 144	95.59 134	96.77 170	90.03 163	96.81 178	97.13 186	88.19 244	91.30 196	94.27 279	86.21 125	98.63 179	87.66 236	96.46 156	98.12 150

EI-MVSNet		93.03 155	92.88 137	93.48 245	95.77 221	86.98 257	96.44 208	97.12 187	90.66 173	91.30 196	97.64 104	86.56 118	98.05 240	89.91 185	90.55 250	95.41 260

MVSTER		93.20 144	92.81 141	94.37 197	96.56 183	89.59 179	97.06 157	97.12 187	91.24 152	91.30 196	95.96 196	82.02 196	98.05 240	93.48 120	90.55 250	95.47 257

test_yl		94.78 94	94.23 98	96.43 85	97.74 118	91.22 125	96.85 174	97.10 189	91.23 153	95.71 97	96.93 140	84.30 149	99.31 109	93.10 127	95.12 177	98.75 107

DCV-MVSNet		94.78 94	94.23 98	96.43 85	97.74 118	91.22 125	96.85 174	97.10 189	91.23 153	95.71 97	96.93 140	84.30 149	99.31 109	93.10 127	95.12 177	98.75 107

LTVRE_ROB	88.41 13	90.99 241	89.92 253	94.19 205	96.18 204	89.55 181	96.31 224	97.09 191	87.88 253	85.67 313	95.91 199	78.79 254	98.57 186	81.50 312	89.98 256	94.44 315
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_fmvs1_n		92.73 170	92.88 137	92.29 282	96.08 213	81.05 333	97.98 59	97.08 192	90.72 168	96.79 52	98.18 60	63.07 354	98.45 194	97.62 10	98.42 102	97.36 186

v10		91.04 239	90.23 239	93.49 244	94.12 301	88.16 231	97.32 137	97.08 192	88.26 243	88.29 275	94.22 284	82.17 194	97.97 251	86.45 258	84.12 320	94.33 318

v144192		91.06 238	90.28 235	93.39 248	93.66 316	87.23 251	96.83 177	97.07 194	87.43 267	89.69 237	94.28 278	81.48 205	98.00 247	87.18 248	84.92 310	94.93 288

v1192		91.07 237	90.23 239	93.58 241	93.70 313	87.82 241	96.73 184	97.07 194	87.77 258	89.58 240	94.32 276	80.90 214	97.97 251	86.52 256	85.48 297	94.95 284

v8		91.29 229	90.53 227	93.57 242	94.15 300	88.12 232	97.34 134	97.06 196	88.99 218	88.32 273	94.26 281	83.08 170	98.01 246	87.62 238	83.92 324	94.57 311

mvs_anonymous		93.82 123	93.74 105	94.06 211	96.44 192	85.41 285	95.81 250	97.05 197	89.85 194	90.09 225	96.36 179	87.44 109	97.75 279	93.97 109	96.69 150	99.02 80

IterMVS-LS		92.29 186	91.94 174	93.34 250	96.25 200	86.97 258	96.57 206	97.05 197	90.67 171	89.50 245	94.80 252	86.59 117	97.64 287	89.91 185	86.11 292	95.40 263
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 247	90.03 250	93.29 252	93.55 317	86.96 259	96.74 183	97.04 199	87.36 269	89.52 244	94.34 273	80.23 226	97.97 251	86.27 259	85.21 303	94.94 286

CDS-MVSNet		94.14 109	93.54 112	95.93 115	96.18 204	91.46 117	96.33 222	97.04 199	88.97 220	93.56 141	96.51 171	87.55 105	97.89 267	89.80 188	95.95 161	98.44 134
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 223	90.60 223	93.68 237	93.89 308	88.23 227	96.84 176	97.03 201	88.37 240	89.69 237	94.39 270	82.04 195	97.98 248	87.80 228	85.37 299	94.84 294

v1240		90.70 253	89.85 255	93.23 254	93.51 320	86.80 260	96.61 200	97.02 202	87.16 274	89.58 240	94.31 277	79.55 238	97.98 248	85.52 274	85.44 298	94.90 291

EPP-MVSNet		95.22 79	95.04 77	95.76 121	97.49 134	89.56 180	98.67 10	97.00 203	90.69 169	94.24 127	97.62 106	89.79 77	98.81 159	93.39 124	96.49 154	98.92 94

V42		91.58 211	90.87 210	93.73 232	94.05 304	88.50 219	97.32 137	96.97 204	88.80 230	89.71 235	94.33 274	82.54 185	98.05 240	89.01 210	85.07 306	94.64 310

test_fmvs1		93.21 143	93.53 113	92.25 284	96.55 185	81.20 332	97.40 128	96.96 205	90.68 170	96.80 51	98.04 69	69.25 327	98.40 197	97.58 11	98.50 96	97.16 195

FMVSNet2		91.31 227	90.08 245	94.99 163	96.51 187	92.21 90	97.41 124	96.95 206	88.82 227	88.62 266	94.75 254	73.87 299	97.42 308	85.20 279	88.55 271	95.35 267

ACMH	87.59 16	90.53 257	89.42 268	93.87 226	96.21 201	87.92 237	97.24 143	96.94 207	88.45 238	83.91 333	96.27 183	71.92 309	98.62 181	84.43 287	89.43 262	95.05 282
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 224	90.27 236	94.59 185	96.51 187	91.18 131	97.50 115	96.93 208	88.82 227	89.35 248	94.51 263	73.87 299	97.29 315	86.12 264	88.82 266	95.31 269

test1		91.35 224	90.27 236	94.59 185	96.51 187	91.18 131	97.50 115	96.93 208	88.82 227	89.35 248	94.51 263	73.87 299	97.29 315	86.12 264	88.82 266	95.31 269

FMVSNet3		91.78 202	90.69 221	95.03 161	96.53 186	92.27 89	97.02 160	96.93 208	89.79 197	89.35 248	94.65 259	77.01 274	97.47 303	86.12 264	88.82 266	95.35 267

FMVSNet1		89.88 273	88.31 283	94.59 185	95.41 235	91.18 131	97.50 115	96.93 208	86.62 282	87.41 292	94.51 263	65.94 348	97.29 315	83.04 300	87.43 280	95.31 269

GeoE		93.89 119	93.28 126	95.72 127	96.96 159	89.75 174	98.24 39	96.92 212	89.47 204	92.12 175	97.21 127	84.42 147	98.39 201	87.71 231	96.50 153	99.01 83

miper_enhance_ethall		91.54 214	91.01 207	93.15 257	95.35 241	87.07 256	93.97 309	96.90 213	86.79 280	89.17 255	93.43 313	86.55 119	97.64 287	89.97 184	86.93 284	94.74 306

eth_miper_zixun_eth		91.02 240	90.59 224	92.34 281	95.33 245	84.35 301	94.10 306	96.90 213	88.56 236	88.84 262	94.33 274	84.08 153	97.60 292	88.77 216	84.37 318	95.06 281

TAMVS		94.01 115	93.46 118	95.64 130	96.16 206	90.45 157	96.71 187	96.89 215	89.27 210	93.46 146	96.92 143	87.29 111	97.94 259	88.70 217	95.74 166	98.53 120

miper_ehance_all_eth		91.59 209	91.13 205	92.97 263	95.55 229	86.57 268	94.47 291	96.88 216	87.77 258	88.88 260	94.01 290	86.22 124	97.54 296	89.49 196	86.93 284	94.79 302

v2v482		91.59 209	90.85 213	93.80 229	93.87 309	88.17 230	96.94 168	96.88 216	89.54 201	89.53 243	94.90 246	81.70 203	98.02 245	89.25 204	85.04 308	95.20 277

CNLPA		94.28 101	93.53 113	96.52 74	98.38 78	92.55 80	96.59 203	96.88 216	90.13 188	91.91 179	97.24 125	85.21 137	99.09 132	87.64 237	97.83 117	97.92 159

PAPM		91.52 215	90.30 234	95.20 151	95.30 248	89.83 172	93.38 329	96.85 219	86.26 289	88.59 267	95.80 205	84.88 141	98.15 220	75.67 347	95.93 162	97.63 173

c3_l		91.38 221	90.89 209	92.88 267	95.58 227	86.30 272	94.68 285	96.84 220	88.17 245	88.83 263	94.23 282	85.65 133	97.47 303	89.36 199	84.63 312	94.89 292

pm-mvs1		90.72 252	89.65 265	93.96 219	94.29 298	89.63 176	97.79 80	96.82 221	89.07 214	86.12 311	95.48 226	78.61 256	97.78 276	86.97 252	81.67 337	94.46 313

test_vis1_n		92.37 180	92.26 165	92.72 272	94.75 279	82.64 317	98.02 55	96.80 222	91.18 155	97.77 29	97.93 78	58.02 361	98.29 209	97.63 9	98.21 107	97.23 194

CMPMVS	62.92 21	85.62 316	84.92 313	87.74 338	89.14 362	73.12 366	94.17 304	96.80 222	73.98 364	73.65 365	94.93 244	66.36 343	97.61 291	83.95 294	91.28 236	92.48 346
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 262	89.77 259	91.78 297	94.33 295	84.72 299	95.55 260	96.73 224	86.17 291	86.36 308	95.28 232	71.28 314	97.80 274	84.09 291	98.14 111	92.81 340

Effi-MVS+-dtu		93.08 152	93.21 128	92.68 275	96.02 214	83.25 315	97.14 155	96.72 225	93.85 62	91.20 203	93.44 311	83.08 170	98.30 208	91.69 158	95.73 167	96.50 212

TSAR-MVS + GP.		96.69 42	96.49 44	97.27 53	98.31 81	93.39 59	96.79 179	96.72 225	94.17 53	97.44 33	97.66 100	92.76 26	99.33 105	96.86 27	97.76 121	99.08 77

1112_ss		93.37 138	92.42 161	96.21 104	97.05 153	90.99 137	96.31 224	96.72 225	86.87 279	89.83 233	96.69 154	86.51 120	99.14 125	88.12 222	93.67 198	98.50 124

PVSNet	86.66 18	92.24 189	91.74 181	93.73 232	97.77 117	83.69 312	92.88 338	96.72 225	87.91 252	93.00 156	94.86 248	78.51 257	99.05 141	86.53 255	97.45 129	98.47 129

miper_lstm_enhance		90.50 259	90.06 249	91.83 293	95.33 245	83.74 309	93.86 315	96.70 229	87.56 265	87.79 285	93.81 298	83.45 163	96.92 327	87.39 242	84.62 313	94.82 297

v148		90.99 241	90.38 230	92.81 270	93.83 310	85.80 279	96.78 181	96.68 230	89.45 205	88.75 265	93.93 294	82.96 176	97.82 273	87.83 227	83.25 329	94.80 300

ACMH+	87.92 14	90.20 266	89.18 273	93.25 253	96.48 190	86.45 269	96.99 164	96.68 230	88.83 226	84.79 322	96.22 185	70.16 322	98.53 188	84.42 288	88.04 274	94.77 305

CANet_DTU		94.37 99	93.65 108	96.55 72	96.46 191	92.13 93	96.21 232	96.67 232	94.38 49	93.53 144	97.03 137	79.34 240	99.71 40	90.76 173	98.45 101	97.82 167

cl____		90.96 244	90.32 232	92.89 266	95.37 239	86.21 275	94.46 293	96.64 233	87.82 254	88.15 280	94.18 285	82.98 174	97.54 296	87.70 232	85.59 295	94.92 290

HY-MVS	89.66 9	93.87 120	92.95 134	96.63 68	97.10 147	92.49 82	95.64 258	96.64 233	89.05 216	93.00 156	95.79 208	85.77 132	99.45 95	89.16 209	94.35 189	97.96 157

Test_1112_low_res		92.84 166	91.84 177	95.85 119	97.04 154	89.97 169	95.53 262	96.64 233	85.38 301	89.65 239	95.18 235	85.86 130	99.10 129	87.70 232	93.58 203	98.49 126

DIV-MVS_self_test		90.97 243	90.33 231	92.88 267	95.36 240	86.19 276	94.46 293	96.63 236	87.82 254	88.18 279	94.23 282	82.99 173	97.53 298	87.72 229	85.57 296	94.93 288

Fast-Effi-MVS+-dtu		92.29 186	91.99 172	93.21 256	95.27 249	85.52 283	97.03 158	96.63 236	92.09 128	89.11 257	95.14 237	80.33 224	98.08 233	87.54 240	94.74 186	96.03 229

UnsupCasMVSNet_bld		82.13 329	79.46 334	90.14 325	88.00 367	82.47 320	90.89 355	96.62 238	78.94 355	75.61 361	84.40 368	56.63 364	96.31 335	77.30 340	66.77 372	91.63 353

cl22		91.21 231	90.56 226	93.14 258	96.09 212	86.80 260	94.41 295	96.58 239	87.80 256	88.58 268	93.99 292	80.85 215	97.62 290	89.87 187	86.93 284	94.99 283

RRT_MVS		93.10 150	92.83 139	93.93 224	94.76 277	88.04 233	98.47 22	96.55 240	93.44 78	90.01 228	97.04 136	80.64 217	97.93 262	94.33 104	90.21 255	95.83 235

jason		94.84 92	94.39 97	96.18 105	95.52 230	90.93 141	96.09 237	96.52 241	89.28 209	96.01 88	97.32 119	84.70 143	98.77 164	95.15 84	98.91 85	98.85 102
jason: jason.
tt0805		91.09 236	90.07 248	94.16 207	95.61 225	88.31 222	97.56 109	96.51 242	89.56 200	89.17 255	95.64 217	67.08 342	98.38 202	91.07 169	88.44 272	95.80 238

AUN-MVS		91.76 203	90.75 218	94.81 176	97.00 157	88.57 215	96.65 194	96.49 243	89.63 198	92.15 173	96.12 190	78.66 255	98.50 190	90.83 171	79.18 348	97.36 186

hse-mvs2		93.45 136	92.99 132	94.81 176	97.02 155	88.59 214	96.69 190	96.47 244	95.19 16	96.74 54	96.16 189	83.67 158	98.48 193	95.85 59	79.13 349	97.35 188

EG-PatchMatch MVS		87.02 302	85.44 306	91.76 299	92.67 337	85.00 294	96.08 238	96.45 245	83.41 330	79.52 353	93.49 309	57.10 363	97.72 281	79.34 331	90.87 247	92.56 344

KD-MVS_self_test		85.95 313	84.95 312	88.96 333	89.55 361	79.11 353	95.13 279	96.42 246	85.91 294	84.07 331	90.48 343	70.03 324	94.82 355	80.04 323	72.94 363	92.94 338

pmmvs6		87.81 297	86.19 301	92.69 274	91.32 349	86.30 272	97.34 134	96.41 247	80.59 349	84.05 332	94.37 272	67.37 337	97.67 284	84.75 283	79.51 347	94.09 325

PMMVS		92.86 164	92.34 162	94.42 195	94.92 268	86.73 263	94.53 290	96.38 248	84.78 313	94.27 126	95.12 239	83.13 169	98.40 197	91.47 162	96.49 154	98.12 150

RPSCF		90.75 250	90.86 211	90.42 322	96.84 163	76.29 360	95.61 259	96.34 249	83.89 322	91.38 191	97.87 83	76.45 279	98.78 161	87.16 249	92.23 216	96.20 219

MSDG		91.42 219	90.24 238	94.96 167	97.15 144	88.91 207	93.69 321	96.32 250	85.72 297	86.93 303	96.47 173	80.24 225	98.98 147	80.57 320	95.05 180	96.98 198

OurMVSNet-221017-0		90.51 258	90.19 243	91.44 305	93.41 324	81.25 330	96.98 165	96.28 251	91.68 138	86.55 307	96.30 181	74.20 298	97.98 248	88.96 212	87.40 282	95.09 279

MVP-Stereo		90.74 251	90.08 245	92.71 273	93.19 329	88.20 228	95.86 248	96.27 252	86.07 292	84.86 321	94.76 253	77.84 269	97.75 279	83.88 295	98.01 113	92.17 351
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 87	94.56 88	96.29 98	96.34 197	91.21 127	95.83 249	96.27 252	88.93 222	96.22 79	96.88 145	86.20 126	98.85 156	95.27 81	99.05 77	98.82 105

BH-untuned		92.94 160	92.62 151	93.92 225	97.22 138	86.16 277	96.40 216	96.25 254	90.06 189	89.79 234	96.17 188	83.19 166	98.35 204	87.19 247	97.27 136	97.24 193

CL-MVSNet_self_test		86.31 308	85.15 310	89.80 328	88.83 364	81.74 328	93.93 312	96.22 255	86.67 281	85.03 319	90.80 342	78.09 265	94.50 356	74.92 348	71.86 365	93.15 336

IS-MVSNet		94.90 89	94.52 92	96.05 110	97.67 121	90.56 153	98.44 23	96.22 255	93.21 86	93.99 133	97.74 94	85.55 134	98.45 194	89.98 183	97.86 116	99.14 70

FA-MVS(test-final)		93.52 134	92.92 135	95.31 148	96.77 170	88.54 217	94.82 282	96.21 257	89.61 199	94.20 128	95.25 233	83.24 165	99.14 125	90.01 182	96.16 158	98.25 145

GA-MVS		91.38 221	90.31 233	94.59 185	94.65 284	87.62 244	94.34 298	96.19 258	90.73 167	90.35 213	93.83 295	71.84 310	97.96 256	87.22 246	93.61 201	98.21 147

IterMVS-SCA-FT		90.31 261	89.81 257	91.82 294	95.52 230	84.20 304	94.30 300	96.15 259	90.61 177	87.39 293	94.27 279	75.80 286	96.44 333	87.34 243	86.88 288	94.82 297

IterMVS		90.15 268	89.67 263	91.61 301	95.48 232	83.72 310	94.33 299	96.12 260	89.99 190	87.31 296	94.15 287	75.78 288	96.27 336	86.97 252	86.89 287	94.83 295
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 169	91.51 191	96.52 74	98.77 53	90.99 137	97.38 131	96.08 261	82.38 335	89.29 251	97.87 83	83.77 156	99.69 46	81.37 317	96.69 150	98.89 99

pmmvs4		90.93 245	89.85 255	94.17 206	93.34 326	90.79 147	94.60 287	96.02 262	84.62 314	87.45 290	95.15 236	81.88 200	97.45 305	87.70 232	87.87 276	94.27 322

ppachtmachnet_test		88.35 292	87.29 291	91.53 302	92.45 342	83.57 313	93.75 318	95.97 263	84.28 317	85.32 318	94.18 285	79.00 252	96.93 326	75.71 346	84.99 309	94.10 323

Anonymous20240521		86.42 306	85.44 306	89.34 331	90.33 354	79.79 347	96.73 184	95.92 264	83.71 326	83.25 336	91.36 339	63.92 352	96.01 337	78.39 335	85.36 300	92.22 349

ITE_SJBPF				92.43 278	95.34 242	85.37 288		95.92 264	91.47 142	87.75 287	96.39 178	71.00 316	97.96 256	82.36 308	89.86 258	93.97 326

test_fmvs2		89.77 276	89.93 252	89.31 332	93.68 315	76.37 359	97.64 100	95.90 266	89.84 195	91.49 189	96.26 184	58.77 360	97.10 319	94.65 98	91.13 239	94.46 313

USDC		88.94 283	87.83 288	92.27 283	94.66 283	84.96 295	93.86 315	95.90 266	87.34 270	83.40 335	95.56 221	67.43 336	98.19 217	82.64 307	89.67 260	93.66 329

COLMAP_ROB	87.81 15	90.40 260	89.28 271	93.79 230	97.95 106	87.13 255	96.92 169	95.89 268	82.83 333	86.88 305	97.18 128	73.77 302	99.29 111	78.44 334	93.62 200	94.95 284
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 123	93.08 130	96.02 112	97.88 112	89.96 170	97.72 88	95.85 269	92.43 117	95.86 92	98.44 34	68.42 332	99.39 101	96.31 39	94.85 181	98.71 112

VDDNet		93.05 154	92.07 168	96.02 112	96.84 163	90.39 160	98.08 51	95.85 269	86.22 290	95.79 95	98.46 32	67.59 335	99.19 118	94.92 89	94.85 181	98.47 129

Vis-MVSNet (Re-imp)		94.15 106	93.88 103	94.95 168	97.61 127	87.92 237	98.10 49	95.80 271	92.22 121	93.02 155	97.45 114	84.53 146	97.91 266	88.24 221	97.97 114	99.02 80

KD-MVS_2432*1600		84.81 320	82.64 324	91.31 307	91.07 351	85.34 289	91.22 350	95.75 272	85.56 299	83.09 337	90.21 346	67.21 338	95.89 339	77.18 341	62.48 374	92.69 341

miper_refine_blended		84.81 320	82.64 324	91.31 307	91.07 351	85.34 289	91.22 350	95.75 272	85.56 299	83.09 337	90.21 346	67.21 338	95.89 339	77.18 341	62.48 374	92.69 341

FE-MVS		92.05 196	91.05 206	95.08 157	96.83 165	87.93 236	93.91 314	95.70 274	86.30 287	94.15 130	94.97 241	76.59 277	99.21 116	84.10 290	96.86 143	98.09 154

tpm cat1		88.36 291	87.21 294	91.81 295	95.13 258	80.55 338	92.58 342	95.70 274	74.97 363	87.45 290	91.96 333	78.01 268	98.17 219	80.39 322	88.74 269	96.72 208

our_test_3		88.78 287	87.98 287	91.20 310	92.45 342	82.53 319	93.61 325	95.69 276	85.77 296	84.88 320	93.71 300	79.99 230	96.78 331	79.47 328	86.24 289	94.28 321

BH-w/o		92.14 194	91.75 179	93.31 251	96.99 158	85.73 280	95.67 255	95.69 276	88.73 232	89.26 253	94.82 251	82.97 175	98.07 237	85.26 278	96.32 157	96.13 225

CR-MVSNet		90.82 248	89.77 259	93.95 220	94.45 291	87.19 252	90.23 358	95.68 278	86.89 278	92.40 165	92.36 328	80.91 212	97.05 321	81.09 319	93.95 196	97.60 178

Patchmtry		88.64 289	87.25 292	92.78 271	94.09 302	86.64 264	89.82 361	95.68 278	80.81 346	87.63 289	92.36 328	80.91 212	97.03 322	78.86 332	85.12 305	94.67 308

iter_conf_final		93.60 129	93.11 129	95.04 159	97.13 145	91.30 122	97.92 68	95.65 280	92.98 102	91.60 185	96.64 158	79.28 242	98.13 222	95.34 80	91.49 230	95.70 248

BH-RMVSNet		92.72 171	91.97 173	94.97 166	97.16 142	87.99 235	96.15 235	95.60 281	90.62 176	91.87 180	97.15 131	78.41 259	98.57 186	83.16 298	97.60 123	98.36 141

PVSNet_0	82.17 19	85.46 317	83.64 320	90.92 313	95.27 249	79.49 349	90.55 356	95.60 281	83.76 325	83.00 339	89.95 348	71.09 315	97.97 251	82.75 305	60.79 376	95.31 269

SCA		91.84 201	91.18 204	93.83 227	95.59 226	84.95 296	94.72 284	95.58 283	90.82 163	92.25 171	93.69 301	75.80 286	98.10 229	86.20 261	95.98 160	98.45 131

AllTest		90.23 264	88.98 275	93.98 216	97.94 107	86.64 264	96.51 207	95.54 284	85.38 301	85.49 315	96.77 148	70.28 320	99.15 123	80.02 324	92.87 205	96.15 223

TestCases				93.98 216	97.94 107	86.64 264		95.54 284	85.38 301	85.49 315	96.77 148	70.28 320	99.15 123	80.02 324	92.87 205	96.15 223

iter_conf05		93.18 148	92.63 149	94.83 173	96.64 175	90.69 150	97.60 105	95.53 286	92.52 115	91.58 186	96.64 158	76.35 282	98.13 222	95.43 78	91.42 233	95.68 250

mvsmamba		93.83 122	93.46 118	94.93 171	94.88 272	90.85 144	98.55 14	95.49 287	94.24 52	91.29 199	96.97 139	83.04 172	98.14 221	95.56 76	91.17 238	95.78 240

tpmvs		89.83 275	89.15 274	91.89 291	94.92 268	80.30 342	93.11 334	95.46 288	86.28 288	88.08 281	92.65 319	80.44 221	98.52 189	81.47 313	89.92 257	96.84 204

pmmvs5		89.86 274	88.87 277	92.82 269	92.86 333	86.23 274	96.26 227	95.39 289	84.24 318	87.12 297	94.51 263	74.27 297	97.36 312	87.61 239	87.57 278	94.86 293

PatchmatchNet		91.91 199	91.35 193	93.59 240	95.38 237	84.11 305	93.15 333	95.39 289	89.54 201	92.10 176	93.68 303	82.82 179	98.13 222	84.81 282	95.32 174	98.52 121
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 218	91.32 195	91.79 296	95.15 256	79.20 352	93.42 328	95.37 291	88.55 237	93.49 145	93.67 304	82.49 187	98.27 210	90.41 177	89.34 263	97.90 160

Anonymous20231206		87.09 301	86.14 302	89.93 327	91.22 350	80.35 340	96.11 236	95.35 292	83.57 328	84.16 327	93.02 316	73.54 304	95.61 347	72.16 358	86.14 291	93.84 328

MIMVSNet1		84.93 319	83.05 321	90.56 320	89.56 360	84.84 298	95.40 266	95.35 292	83.91 321	80.38 349	92.21 332	57.23 362	93.34 365	70.69 364	82.75 335	93.50 331

TDRefinement		86.53 304	84.76 315	91.85 292	82.23 375	84.25 302	96.38 218	95.35 292	84.97 310	84.09 330	94.94 243	65.76 349	98.34 207	84.60 286	74.52 359	92.97 337

TR-MVS		91.48 217	90.59 224	94.16 207	96.40 194	87.33 246	95.67 255	95.34 295	87.68 262	91.46 190	95.52 224	76.77 276	98.35 204	82.85 302	93.61 201	96.79 206

EPNet_dtu		91.71 204	91.28 198	92.99 262	93.76 312	83.71 311	96.69 190	95.28 296	93.15 92	87.02 301	95.95 197	83.37 164	97.38 311	79.46 329	96.84 144	97.88 162
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 300	85.79 304	91.78 297	94.80 276	87.28 247	95.49 263	95.28 296	84.09 320	83.85 334	91.82 334	62.95 355	94.17 360	78.48 333	85.34 301	93.91 327

MDTV_nov1_ep13			90.76 217		95.22 253	80.33 341	93.03 336	95.28 296	88.14 247	92.84 162	93.83 295	81.34 206	98.08 233	82.86 301	94.34 190

LF4IMVS		87.94 295	87.25 292	89.98 326	92.38 344	80.05 346	94.38 296	95.25 299	87.59 264	84.34 324	94.74 255	64.31 351	97.66 286	84.83 281	87.45 279	92.23 348

TransMVSNet (Re)		88.94 283	87.56 289	93.08 260	94.35 294	88.45 221	97.73 85	95.23 300	87.47 266	84.26 326	95.29 230	79.86 233	97.33 313	79.44 330	74.44 360	93.45 333

test20.03		86.14 311	85.40 308	88.35 334	90.12 355	80.06 345	95.90 247	95.20 301	88.59 233	81.29 344	93.62 306	71.43 313	92.65 367	71.26 362	81.17 340	92.34 347

new-patchmatchnet		83.18 326	81.87 329	87.11 340	86.88 369	75.99 361	93.70 319	95.18 302	85.02 309	77.30 360	88.40 356	65.99 347	93.88 362	74.19 353	70.18 367	91.47 357

MDA-MVSNet_test_wron		85.87 314	84.23 318	90.80 317	92.38 344	82.57 318	93.17 331	95.15 303	82.15 336	67.65 367	92.33 331	78.20 261	95.51 350	77.33 338	79.74 344	94.31 320

YYNet1		85.87 314	84.23 318	90.78 318	92.38 344	82.46 321	93.17 331	95.14 304	82.12 337	67.69 366	92.36 328	78.16 264	95.50 351	77.31 339	79.73 345	94.39 316

Baseline_NR-MVSNet		91.20 232	90.62 222	92.95 264	93.83 310	88.03 234	97.01 163	95.12 305	88.42 239	89.70 236	95.13 238	83.47 161	97.44 306	89.66 193	83.24 330	93.37 334

thres200		92.23 190	91.39 192	94.75 183	97.61 127	89.03 205	96.60 202	95.09 306	92.08 129	93.28 151	94.00 291	78.39 260	99.04 144	81.26 318	94.18 191	96.19 220

ADS-MVSNet		89.89 272	88.68 279	93.53 243	95.86 216	84.89 297	90.93 353	95.07 307	83.23 331	91.28 200	91.81 335	79.01 250	97.85 269	79.52 326	91.39 234	97.84 164

pmmvs-eth3d		86.22 309	84.45 316	91.53 302	88.34 366	87.25 249	94.47 291	95.01 308	83.47 329	79.51 354	89.61 351	69.75 326	95.71 344	83.13 299	76.73 356	91.64 352

Anonymous202405211		92.07 195	90.83 215	95.76 121	98.19 93	88.75 210	97.58 107	95.00 309	86.00 293	93.64 140	97.45 114	66.24 346	99.53 81	90.68 176	92.71 210	99.01 83

MDA-MVSNet-bldmvs		85.00 318	82.95 323	91.17 311	93.13 331	83.33 314	94.56 289	95.00 309	84.57 315	65.13 371	92.65 319	70.45 319	95.85 341	73.57 354	77.49 352	94.33 318

ambc				86.56 343	83.60 372	70.00 369	85.69 370	94.97 311		80.60 348	88.45 355	37.42 374	96.84 329	82.69 306	75.44 358	92.86 339

testgi		87.97 294	87.21 294	90.24 324	92.86 333	80.76 334	96.67 193	94.97 311	91.74 136	85.52 314	95.83 203	62.66 356	94.47 358	76.25 344	88.36 273	95.48 254

dp		88.90 285	88.26 285	90.81 315	94.58 288	76.62 358	92.85 339	94.93 313	85.12 307	90.07 227	93.07 315	75.81 285	98.12 227	80.53 321	87.42 281	97.71 170

test_fmvs3		83.21 325	83.02 322	83.78 347	86.77 370	68.34 372	96.76 182	94.91 314	86.49 284	84.14 329	89.48 352	36.04 375	91.73 369	91.86 152	80.77 342	91.26 359

test_0402		86.46 305	84.79 314	91.45 304	95.02 262	85.55 282	96.29 226	94.89 315	80.90 343	82.21 341	93.97 293	68.21 333	97.29 315	62.98 370	88.68 270	91.51 355

tfpn200view9		92.38 179	91.52 189	94.95 168	97.85 113	89.29 195	97.41 124	94.88 316	92.19 125	93.27 152	94.46 268	78.17 262	99.08 134	81.40 314	94.08 192	96.48 213

CVMVSNet		91.23 230	91.75 179	89.67 329	95.77 221	74.69 362	96.44 208	94.88 316	85.81 295	92.18 172	97.64 104	79.07 245	95.58 349	88.06 223	95.86 164	98.74 109

thres400		92.42 177	91.52 189	95.12 156	97.85 113	89.29 195	97.41 124	94.88 316	92.19 125	93.27 152	94.46 268	78.17 262	99.08 134	81.40 314	94.08 192	96.98 198

EPNet		95.20 80	94.56 88	97.14 58	92.80 335	92.68 77	97.85 74	94.87 319	96.64 2	92.46 164	97.80 91	86.23 123	99.65 52	93.72 117	98.62 93	99.10 76
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SixPastTwentyTwo		89.15 281	88.54 281	90.98 312	93.49 321	80.28 343	96.70 188	94.70 320	90.78 164	84.15 328	95.57 220	71.78 311	97.71 282	84.63 285	85.07 306	94.94 286

thres100view900		92.43 176	91.58 186	94.98 165	97.92 109	89.37 191	97.71 90	94.66 321	92.20 123	93.31 150	94.90 246	78.06 266	99.08 134	81.40 314	94.08 192	96.48 213

thres600view7		92.49 175	91.60 185	95.18 152	97.91 110	89.47 185	97.65 96	94.66 321	92.18 127	93.33 149	94.91 245	78.06 266	99.10 129	81.61 311	94.06 195	96.98 198

PatchT		88.87 286	87.42 290	93.22 255	94.08 303	85.10 293	89.51 362	94.64 323	81.92 338	92.36 168	88.15 359	80.05 229	97.01 324	72.43 357	93.65 199	97.54 181

baseline1		92.82 167	91.90 175	95.55 137	97.20 140	90.77 148	97.19 150	94.58 324	92.20 123	92.36 168	96.34 180	84.16 152	98.21 214	89.20 207	83.90 325	97.68 172

Gipuma		67.86 342	65.41 344	75.18 358	92.66 338	73.45 365	66.50 377	94.52 325	53.33 376	57.80 377	66.07 377	30.81 377	89.20 373	48.15 378	78.88 351	62.90 377
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CostFormer		91.18 235	90.70 220	92.62 276	94.84 274	81.76 327	94.09 307	94.43 326	84.15 319	92.72 163	93.77 299	79.43 239	98.20 215	90.70 175	92.18 219	97.90 160

tpm2		89.96 270	89.21 272	92.23 285	94.91 270	81.25 330	93.78 317	94.42 327	80.62 348	91.56 187	93.44 311	76.44 280	97.94 259	85.60 273	92.08 223	97.49 182

JIA-IIPM		88.26 293	87.04 297	91.91 290	93.52 319	81.42 329	89.38 363	94.38 328	80.84 345	90.93 205	80.74 370	79.22 243	97.92 263	82.76 304	91.62 227	96.38 216

dmvs_re		90.21 265	89.50 267	92.35 279	95.47 234	85.15 291	95.70 254	94.37 329	90.94 162	88.42 270	93.57 307	74.63 294	95.67 346	82.80 303	89.57 261	96.22 218

Patchmatch-test		89.42 279	87.99 286	93.70 235	95.27 249	85.11 292	88.98 364	94.37 329	81.11 342	87.10 299	93.69 301	82.28 191	97.50 301	74.37 351	94.76 184	98.48 128

LCM-MVSNet		72.55 336	69.39 340	82.03 349	70.81 385	65.42 377	90.12 360	94.36 331	55.02 375	65.88 369	81.72 369	24.16 383	89.96 370	74.32 352	68.10 371	90.71 362

ADS-MVSNet2		89.45 278	88.59 280	92.03 288	95.86 216	82.26 323	90.93 353	94.32 332	83.23 331	91.28 200	91.81 335	79.01 250	95.99 338	79.52 326	91.39 234	97.84 164

EU-MVSNet		88.72 288	88.90 276	88.20 336	93.15 330	74.21 363	96.63 199	94.22 333	85.18 305	87.32 295	95.97 195	76.16 283	94.98 354	85.27 277	86.17 290	95.41 260

MVS_0304		97.04 23	96.73 34	97.96 22	97.60 129	94.36 33	98.01 56	94.09 334	97.33 1	96.29 76	98.79 14	89.73 78	99.86 8	99.36 1	99.42 45	99.67 11

MIMVSNet		88.50 290	86.76 298	93.72 234	94.84 274	87.77 242	91.39 348	94.05 335	86.41 286	87.99 283	92.59 322	63.27 353	95.82 343	77.44 337	92.84 207	97.57 180

OpenMVS_ROB	81.14 20	84.42 322	82.28 328	90.83 314	90.06 356	84.05 307	95.73 253	94.04 336	73.89 365	80.17 352	91.53 338	59.15 359	97.64 287	66.92 368	89.05 265	90.80 361

TinyColmap		86.82 303	85.35 309	91.21 309	94.91 270	82.99 316	93.94 311	94.02 337	83.58 327	81.56 343	94.68 257	62.34 357	98.13 222	75.78 345	87.35 283	92.52 345

IB-MVS	87.33 17	89.91 271	88.28 284	94.79 180	95.26 252	87.70 243	95.12 280	93.95 338	89.35 208	87.03 300	92.49 323	70.74 318	99.19 118	89.18 208	81.37 339	97.49 182
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
test_f		80.57 331	79.62 333	83.41 348	83.38 373	67.80 374	93.57 326	93.72 339	80.80 347	77.91 359	87.63 362	33.40 376	92.08 368	87.14 250	79.04 350	90.34 363

LCM-MVSNet-Re		92.50 173	92.52 157	92.44 277	96.82 167	81.89 326	96.92 169	93.71 340	92.41 118	84.30 325	94.60 261	85.08 139	97.03 322	91.51 160	97.36 131	98.40 137

bld_raw_dy_0_64		92.37 180	91.69 182	94.39 196	94.28 299	89.73 175	97.71 90	93.65 341	92.78 110	90.46 210	96.67 156	75.88 284	97.97 251	92.92 136	90.89 246	95.48 254

tpm		90.25 263	89.74 262	91.76 299	93.92 306	79.73 348	93.98 308	93.54 342	88.28 242	91.99 178	93.25 314	77.51 272	97.44 306	87.30 245	87.94 275	98.12 150

ET-MVSNet_ETH3D		91.49 216	90.11 244	95.63 131	96.40 194	91.57 112	95.34 268	93.48 343	90.60 179	75.58 362	95.49 225	80.08 228	96.79 330	94.25 105	89.76 259	98.52 121

LFMVS		93.60 129	92.63 149	96.52 74	98.13 98	91.27 124	97.94 66	93.39 344	90.57 180	96.29 76	98.31 50	69.00 328	99.16 122	94.18 106	95.87 163	99.12 74

Patchmatch-RL test		87.38 299	86.24 300	90.81 315	88.74 365	78.40 356	88.12 368	93.17 345	87.11 275	82.17 342	89.29 353	81.95 198	95.60 348	88.64 218	77.02 353	98.41 136

test-LLR		91.42 219	91.19 203	92.12 286	94.59 286	80.66 335	94.29 301	92.98 346	91.11 158	90.76 206	92.37 325	79.02 248	98.07 237	88.81 214	96.74 147	97.63 173

test-mter		90.19 267	89.54 266	92.12 286	94.59 286	80.66 335	94.29 301	92.98 346	87.68 262	90.76 206	92.37 325	67.67 334	98.07 237	88.81 214	96.74 147	97.63 173

test_method		66.11 343	64.89 345	69.79 360	72.62 383	35.23 390	65.19 378	92.83 348	20.35 381	65.20 370	88.08 360	43.14 372	82.70 378	73.12 356	63.46 373	91.45 358

test0.0.03 1		89.37 280	88.70 278	91.41 306	92.47 341	85.63 281	95.22 277	92.70 349	91.11 158	86.91 304	93.65 305	79.02 248	93.19 366	78.00 336	89.18 264	95.41 260

new_pmnet		82.89 327	81.12 332	88.18 337	89.63 359	80.18 344	91.77 347	92.57 350	76.79 362	75.56 363	88.23 358	61.22 358	94.48 357	71.43 360	82.92 333	89.87 364

mvsany_test1		93.93 118	93.98 101	93.78 231	94.94 267	86.80 260	94.62 286	92.55 351	88.77 231	96.85 50	98.49 28	88.98 84	98.08 233	95.03 86	95.62 170	96.46 215

thisisatest0515		92.29 186	91.30 197	95.25 150	96.60 178	88.90 208	94.36 297	92.32 352	87.92 251	93.43 147	94.57 262	77.28 273	99.00 145	89.42 198	95.86 164	97.86 163

thisisatest0530		93.03 155	92.21 166	95.49 141	97.07 148	89.11 204	97.49 120	92.19 353	90.16 187	94.09 131	96.41 176	76.43 281	99.05 141	90.38 178	95.68 169	98.31 143

tttt0517		92.96 158	92.33 163	94.87 172	97.11 146	87.16 254	97.97 65	92.09 354	90.63 175	93.88 137	97.01 138	76.50 278	99.06 140	90.29 181	95.45 172	98.38 139

K. test v3		87.64 298	86.75 299	90.32 323	93.02 332	79.48 350	96.61 200	92.08 355	90.66 173	80.25 351	94.09 288	67.21 338	96.65 332	85.96 269	80.83 341	94.83 295

TESTMET0.1,1		90.06 269	89.42 268	91.97 289	94.41 293	80.62 337	94.29 301	91.97 356	87.28 272	90.44 211	92.47 324	68.79 329	97.67 284	88.50 220	96.60 152	97.61 177

PM-MVS		83.48 324	81.86 330	88.31 335	87.83 368	77.59 357	93.43 327	91.75 357	86.91 277	80.63 347	89.91 349	44.42 371	95.84 342	85.17 280	76.73 356	91.50 356

baseline2		91.63 207	90.86 211	93.94 222	94.33 295	86.32 271	95.92 246	91.64 358	89.37 207	86.94 302	94.69 256	81.62 204	98.69 173	88.64 218	94.57 188	96.81 205

APD_test1		79.31 333	77.70 336	84.14 346	89.11 363	69.07 371	92.36 346	91.50 359	69.07 368	73.87 364	92.63 321	39.93 373	94.32 359	70.54 365	80.25 343	89.02 366

FPMVS		71.27 337	69.85 339	75.50 357	74.64 380	59.03 381	91.30 349	91.50 359	58.80 372	57.92 376	88.28 357	29.98 379	85.53 377	53.43 376	82.84 334	81.95 370

door								91.13 361

door-mid								91.06 362

EGC-MVSNET		68.77 341	63.01 346	86.07 345	92.49 340	82.24 324	93.96 310	90.96 363	0.71 386	2.62 387	90.89 341	53.66 365	93.46 363	57.25 374	84.55 315	82.51 369

mvsany_test3		83.59 323	82.44 327	87.03 341	83.80 371	73.82 364	93.70 319	90.92 364	86.42 285	82.51 340	90.26 345	46.76 370	95.71 344	90.82 172	76.76 355	91.57 354

pmmvs3		79.97 332	77.50 337	87.39 339	82.80 374	79.38 351	92.70 341	90.75 365	70.69 367	78.66 356	87.47 364	51.34 368	93.40 364	73.39 355	69.65 368	89.38 365

DSMNet-mixed		86.34 307	86.12 303	87.00 342	89.88 358	70.43 367	94.93 281	90.08 366	77.97 359	85.42 317	92.78 318	74.44 296	93.96 361	74.43 350	95.14 176	96.62 209

MVS-HIRNet		82.47 328	81.21 331	86.26 344	95.38 237	69.21 370	88.96 365	89.49 367	66.28 369	80.79 346	74.08 374	68.48 331	97.39 310	71.93 359	95.47 171	92.18 350

test1111		93.19 145	92.82 140	94.30 202	97.58 132	84.56 300	98.21 43	89.02 368	93.53 74	94.58 120	98.21 57	72.69 306	99.05 141	93.06 130	98.48 99	99.28 59

ECVR-MVS		93.19 145	92.73 146	94.57 190	97.66 123	85.41 285	98.21 43	88.23 369	93.43 79	94.70 118	98.21 57	72.57 307	99.07 138	93.05 131	98.49 97	99.25 62

EPMVS		90.70 253	89.81 257	93.37 249	94.73 281	84.21 303	93.67 322	88.02 370	89.50 203	92.38 167	93.49 309	77.82 270	97.78 276	86.03 267	92.68 211	98.11 153

ANet_high		63.94 344	59.58 347	77.02 354	61.24 387	66.06 375	85.66 371	87.93 371	78.53 357	42.94 379	71.04 376	25.42 382	80.71 379	52.60 377	30.83 380	84.28 368

PMMVS2		70.19 338	66.92 341	80.01 350	76.35 379	65.67 376	86.22 369	87.58 372	64.83 371	62.38 372	80.29 371	26.78 381	88.49 375	63.79 369	54.07 377	85.88 367

lessismore_v0				90.45 321	91.96 347	79.09 354		87.19 373		80.32 350	94.39 270	66.31 345	97.55 295	84.00 293	76.84 354	94.70 307

PMVS	53.92 22	58.58 345	55.40 348	68.12 361	51.00 388	48.64 384	78.86 374	87.10 374	46.77 377	35.84 383	74.28 373	8.76 387	86.34 376	42.07 379	73.91 361	69.38 375
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		86.16 310	85.06 311	89.46 330	93.47 323	80.46 339	96.41 212	86.61 375	85.22 304	79.15 355	88.64 354	52.41 367	97.06 320	93.08 129	90.57 249	90.87 360

testf1		69.31 339	66.76 342	76.94 355	78.61 377	61.93 379	88.27 366	86.11 376	55.62 373	59.69 373	85.31 366	20.19 385	89.32 371	57.62 372	69.44 369	79.58 371

APD_test2		69.31 339	66.76 342	76.94 355	78.61 377	61.93 379	88.27 366	86.11 376	55.62 373	59.69 373	85.31 366	20.19 385	89.32 371	57.62 372	69.44 369	79.58 371

gg-mvs-nofinetune		87.82 296	85.61 305	94.44 193	94.46 290	89.27 198	91.21 352	84.61 378	80.88 344	89.89 232	74.98 372	71.50 312	97.53 298	85.75 272	97.21 138	96.51 211

dmvs_testset		81.38 330	82.60 326	77.73 353	91.74 348	51.49 383	93.03 336	84.21 379	89.07 214	78.28 358	91.25 340	76.97 275	88.53 374	56.57 375	82.24 336	93.16 335

GG-mvs-BLEND				93.62 238	93.69 314	89.20 200	92.39 345	83.33 380		87.98 284	89.84 350	71.00 316	96.87 328	82.08 310	95.40 173	94.80 300

MTMP							97.86 71	82.03 381

DeepMVS_CX				74.68 359	90.84 353	64.34 378		81.61 382	65.34 370	67.47 368	88.01 361	48.60 369	80.13 380	62.33 371	73.68 362	79.58 371

E-PMN		53.28 346	52.56 350	55.43 363	74.43 381	47.13 385	83.63 373	76.30 383	42.23 378	42.59 380	62.22 379	28.57 380	74.40 381	31.53 381	31.51 379	44.78 378

test2506		91.60 208	90.78 216	94.04 213	97.66 123	83.81 308	98.27 33	75.53 384	93.43 79	95.23 109	98.21 57	67.21 338	99.07 138	93.01 134	98.49 97	99.25 62

EMVS		52.08 348	51.31 351	54.39 364	72.62 383	45.39 387	83.84 372	75.51 385	41.13 379	40.77 381	59.65 380	30.08 378	73.60 382	28.31 382	29.90 381	44.18 379

test_vis3_rt		72.73 335	70.55 338	79.27 351	80.02 376	68.13 373	93.92 313	74.30 386	76.90 361	58.99 375	73.58 375	20.29 384	95.37 352	84.16 289	72.80 364	74.31 374

MVE	50.73 23	53.25 347	48.81 352	66.58 362	65.34 386	57.50 382	72.49 376	70.94 387	40.15 380	39.28 382	63.51 378	6.89 389	73.48 383	38.29 380	42.38 378	68.76 376
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 349	53.82 349	46.29 365	33.73 389	45.30 388	78.32 375	67.24 388	18.02 382	50.93 378	87.05 365	52.99 366	53.11 384	70.76 363	25.29 382	40.46 380

N_pmnet		78.73 334	78.71 335	78.79 352	92.80 335	46.50 386	94.14 305	43.71 389	78.61 356	80.83 345	91.66 337	74.94 293	96.36 334	67.24 367	84.45 317	93.50 331

wuyk23d		25.11 350	24.57 354	26.74 366	73.98 382	39.89 389	57.88 379	9.80 390	12.27 383	10.39 384	6.97 386	7.03 388	36.44 385	25.43 383	17.39 383	3.89 383

testmvs		13.36 352	16.33 355	4.48 368	5.04 390	2.26 392	93.18 330	3.28 391	2.70 384	8.24 385	21.66 382	2.29 391	2.19 386	7.58 384	2.96 384	9.00 382

test123		13.04 353	15.66 356	5.18 367	4.51 391	3.45 391	92.50 344	1.81 392	2.50 385	7.58 386	20.15 383	3.67 390	2.18 387	7.13 385	1.07 385	9.90 381

test_blank		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet_test		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

DCPMVS		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

pcd_1.5k_mvsjas		7.39 355	9.85 358	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	88.65 90	0.00 388	0.00 386	0.00 386	0.00 384

sosnet-low-res		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

sosnet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uncertanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

Regformer		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

n2								0.00 393

nn								0.00 393

ab-mvs-re		8.06 354	10.74 357	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	96.69 154	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

uanet		0.00 356	0.00 359	0.00 369	0.00 392	0.00 393	0.00 380	0.00 393	0.00 387	0.00 388	0.00 387	0.00 392	0.00 388	0.00 386	0.00 386	0.00 384

PC_three_1452									90.77 165	98.89 9	98.28 55	96.24 1	98.35 204	95.76 63	99.58 21	99.59 20

eth-test2					0.00 392

eth-test					0.00 392

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 56	96.04 2	99.24 114	95.36 79	99.59 17	99.56 26

test_0728_THIRD									94.78 34	98.73 11	98.87 8	95.87 4	99.84 22	97.45 16	99.72 2	99.77 1

GSMVS																98.45 131

test_part2					99.28 25	95.74 8				98.10 21

sam_mvs1												82.76 180				98.45 131

sam_mvs												81.94 199

test_post1							92.81 340				16.58 385	80.53 219	97.68 283	86.20 261

test_post											17.58 384	81.76 201	98.08 233

patchmatchnet-post											90.45 344	82.65 184	98.10 229

gm-plane-assit					93.22 328	78.89 355			84.82 312		93.52 308		98.64 178	87.72 229

test9_res														94.81 93	99.38 51	99.45 42

agg_prior2														93.94 111	99.38 51	99.50 37

test_prior4						93.66 54	96.42 211

test_prior2							96.35 220		92.80 109	96.03 85	97.59 108	92.01 41		95.01 87	99.38 51

旧先验2							95.94 245		81.66 340	97.34 38			98.82 158	92.26 139

新几何2							95.79 251

原ACMM2							95.67 255

testdata2													99.67 50	85.96 269

segment_acmp												92.89 25

testdata1							95.26 276		93.10 95

plane_prior7					96.21 201	89.98 168

plane_prior6					96.10 211	90.00 164						81.32 207

plane_prior4											96.64 158

plane_prior3						90.00 164			94.46 45	91.34 193

plane_prior2							97.74 83		94.85 27

plane_prior1					96.14 209

plane_prior						89.99 166	97.24 143		94.06 55						92.16 220

HQP5-MVS						89.33 193

HQP-NCC					95.86 216		96.65 194		93.55 70	90.14 216

ACMP_Plane					95.86 216		96.65 194		93.55 70	90.14 216

BP-MVS														92.13 145

HQP4-MVS										90.14 216			98.50 190			95.78 240

HQP2-MVS												80.95 210

NP-MVS					95.99 215	89.81 173					95.87 200

MDTV_nov1_ep13_2view						70.35 368	93.10 335		83.88 323	93.55 142		82.47 188		86.25 260		98.38 139

ACMMP++_ref															90.30 254

ACMMP++															91.02 242

Test By Simon												88.73 89

High-resolution multi-view benchmark