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 77	98.41 74	91.73 105	98.01 57	99.02 1	96.37 4	99.30 1	98.92 10	92.39 35	99.79 33	99.16 3	99.46 39	98.08 163

PGM-MVS		96.81 39	96.53 47	97.65 41	99.35 20	93.53 58	97.65 104	98.98 2	92.22 129	97.14 50	98.44 42	91.17 60	99.85 18	94.35 111	99.46 39	99.57 26

MVS_111021_HR		96.68 48	96.58 46	96.99 66	98.46 70	92.31 89	96.20 242	98.90 3	94.30 58	95.86 100	97.74 102	92.33 36	99.38 111	96.04 61	99.42 46	99.28 63

test_fmvsmconf_n		97.49 10	97.56 7	97.29 52	97.44 137	92.37 86	97.91 75	98.88 4	95.83 8	98.92 10	99.05 5	91.45 51	99.80 30	99.12 4	99.46 39	99.69 12

ACMMP		96.27 60	95.93 62	97.28 54	99.24 28	92.62 79	98.25 36	98.81 5	92.99 105	94.56 129	98.39 46	88.96 87	99.85 18	94.57 110	97.63 130	99.36 58
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 61	96.19 60	96.39 93	98.23 90	91.35 125	96.24 240	98.79 6	93.99 65	95.80 102	97.65 109	89.92 78	99.24 122	95.87 65	99.20 70	98.58 121

patch_mono-2		96.83 38	97.44 11	95.01 170	99.05 39	85.39 295	96.98 174	98.77 7	94.70 43	97.99 30	98.66 25	93.61 19	99.91 1	97.67 16	99.50 33	99.72 11

fmvsm_s_conf0.5_n		96.85 36	97.13 14	96.04 117	98.07 103	90.28 167	97.97 67	98.76 8	94.93 29	98.84 14	99.06 4	88.80 90	99.65 56	99.06 5	98.63 97	98.18 153

fmvsm_s_conf0.5_n_a		96.75 43	96.93 26	96.20 109	97.64 126	90.72 154	98.00 59	98.73 9	94.55 48	98.91 11	99.08 3	88.22 99	99.63 65	98.91 7	98.37 109	98.25 149

FC-MVSNet-test		93.94 124	93.57 117	95.04 167	95.48 238	91.45 122	98.12 48	98.71 10	93.37 89	90.23 223	96.70 160	87.66 108	97.85 277	91.49 169	90.39 264	95.83 243

UniMVSNet (Re)		93.31 147	92.55 161	95.61 141	95.39 243	93.34 64	97.39 137	98.71 10	93.14 101	90.10 232	94.83 258	87.71 107	98.03 252	91.67 167	83.99 332	95.46 266

FIs		94.09 118	93.70 113	95.27 157	95.70 228	92.03 99	98.10 49	98.68 12	93.36 91	90.39 220	96.70 160	87.63 110	97.94 267	92.25 149	90.50 263	95.84 242

WR-MVS_H		92.00 204	91.35 200	93.95 228	95.09 269	89.47 193	98.04 55	98.68 12	91.46 151	88.34 280	94.68 265	85.86 137	97.56 302	85.77 279	84.24 330	94.82 308

VPA-MVSNet		93.24 149	92.48 166	95.51 147	95.70 228	92.39 85	97.86 79	98.66 14	92.30 128	92.09 185	95.37 236	80.49 228	98.40 205	93.95 118	85.86 304	95.75 253

UniMVSNet_NR-MVSNet		93.37 145	92.67 155	95.47 152	95.34 249	92.83 74	97.17 160	98.58 15	92.98 110	90.13 228	95.80 213	88.37 98	97.85 277	91.71 164	83.93 333	95.73 255

CSCG		96.05 64	95.91 63	96.46 87	99.24 28	90.47 162	98.30 30	98.57 16	89.01 226	93.97 143	97.57 117	92.62 31	99.76 36	94.66 105	99.27 62	99.15 73

MSLP-MVS++		96.94 30	97.06 17	96.59 75	98.72 55	91.86 103	97.67 101	98.49 17	94.66 46	97.24 47	98.41 45	92.31 38	98.94 157	96.61 41	99.46 39	98.96 92

HyFIR lowres test		93.66 135	92.92 142	95.87 125	98.24 86	89.88 179	94.58 299	98.49 17	85.06 319	93.78 146	95.78 217	82.86 185	98.67 183	91.77 162	95.71 176	99.07 83

CHOSEN 1792x2688		94.15 113	93.51 123	96.06 115	98.27 83	89.38 198	95.18 287	98.48 19	85.60 309	93.76 147	97.11 140	83.15 176	99.61 67	91.33 172	98.72 94	99.19 69

PHI-MVS		96.77 41	96.46 53	97.71 39	98.40 75	94.07 46	98.21 43	98.45 20	89.86 201	97.11 52	98.01 81	92.52 33	99.69 50	96.03 62	99.53 27	99.36 58

fmvsm_s_conf0.1_n		96.58 51	96.77 37	96.01 121	96.67 178	90.25 168	97.91 75	98.38 21	94.48 51	98.84 14	99.14 1	88.06 101	99.62 66	98.82 9	98.60 99	98.15 156

PVSNet_BlendedMVS		94.06 119	93.92 109	94.47 200	98.27 83	89.46 195	96.73 193	98.36 22	90.17 194	94.36 132	95.24 242	88.02 102	99.58 75	93.44 129	90.72 259	94.36 328

PVSNet_Blended		94.87 98	94.56 95	95.81 128	98.27 83	89.46 195	95.47 273	98.36 22	88.84 234	94.36 132	96.09 202	88.02 102	99.58 75	93.44 129	98.18 117	98.40 141

3Dnovator	91.36 5	95.19 88	94.44 103	97.44 47	96.56 187	93.36 63	98.65 11	98.36 22	94.12 61	89.25 262	98.06 75	82.20 201	99.77 35	93.41 131	99.32 59	99.18 70

FOURS1					99.55 1	93.34 64	99.29 1	98.35 25	94.98 28	98.49 21

DPE-MVS		97.86 4	97.65 6	98.47 5	99.17 32	95.78 7	97.21 157	98.35 25	95.16 22	98.71 18	98.80 20	95.05 10	99.89 3	96.70 39	99.73 1	99.73 10
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
fmvsm_s_conf0.1_n_a		96.40 55	96.47 50	96.16 111	95.48 238	90.69 155	97.91 75	98.33 27	94.07 62	98.93 7	99.14 1	87.44 115	99.61 67	98.63 11	98.32 111	98.18 153

HFP-MVS		97.14 20	96.92 27	97.83 26	99.42 7	94.12 44	98.52 16	98.32 28	93.21 94	97.18 48	98.29 61	92.08 40	99.83 26	95.63 78	99.59 17	99.54 33

ACMMPR		97.07 23	96.84 30	97.79 30	99.44 6	93.88 50	98.52 16	98.31 29	93.21 94	97.15 49	98.33 55	91.35 55	99.86 8	95.63 78	99.59 17	99.62 18

test_fmvsmvis_n_1920		96.70 44	96.84 30	96.31 98	96.62 180	91.73 105	97.98 61	98.30 30	96.19 5	96.10 91	98.95 8	89.42 81	99.76 36	98.90 8	99.08 79	97.43 192

APDe-MVS		97.82 5	97.73 5	98.08 18	99.15 33	94.82 27	98.81 7	98.30 30	94.76 41	98.30 24	98.90 12	93.77 17	99.68 52	97.93 12	99.69 3	99.75 6
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
test0726					99.45 3	95.36 13	98.31 29	98.29 32	94.92 30	98.99 5	98.92 10	95.08 8

MSP-MVS		97.59 8	97.54 8	97.73 36	99.40 11	93.77 54	98.53 15	98.29 32	95.55 13	98.56 20	97.81 97	93.90 15	99.65 56	96.62 40	99.21 69	99.77 2
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 34	94.78 39	98.93 7	98.87 15	96.04 2	99.86 8	97.45 24	99.58 21	99.59 22

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 34					99.86 8	97.52 20	99.67 6	99.75 6

CP-MVS		97.02 26	96.81 34	97.64 43	99.33 21	93.54 57	98.80 8	98.28 34	92.99 105	96.45 80	98.30 60	91.90 43	99.85 18	95.61 80	99.68 4	99.54 33

test_fmvsmconf0.1_n		97.09 21	97.06 17	97.19 60	95.67 230	92.21 92	97.95 70	98.27 37	95.78 10	98.40 23	99.00 6	89.99 76	99.78 34	99.06 5	99.41 49	99.59 22

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 36	98.27 37	95.13 23	99.19 2	98.89 13	95.54 5	99.85 18	97.52 20	99.66 10	99.56 29

test_241102_TWO								98.27 37	95.13 23	98.93 7	98.89 13	94.99 11	99.85 18	97.52 20	99.65 12	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 37	95.09 26	99.19 2	98.81 19	95.54 5	99.65 56

SF-MVS		97.39 13	97.13 14	98.17 15	99.02 42	95.28 19	98.23 40	98.27 37	92.37 127	98.27 25	98.65 27	93.33 21	99.72 43	96.49 45	99.52 28	99.51 37

SteuartSystems-ACMMP		97.62 7	97.53 9	97.87 24	98.39 77	94.25 38	98.43 24	98.27 37	95.34 17	98.11 26	98.56 29	94.53 12	99.71 44	96.57 43	99.62 15	99.65 15
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 43	95.13 23	98.48 22	98.87 15	95.16 7

PVSNet_Blended_VisFu		95.27 83	94.91 86	96.38 94	98.20 91	90.86 147	97.27 149	98.25 43	90.21 193	94.18 137	97.27 131	87.48 114	99.73 40	93.53 126	97.77 128	98.55 122

region2R		97.07 23	96.84 30	97.77 33	99.46 2	93.79 52	98.52 16	98.24 45	93.19 97	97.14 50	98.34 52	91.59 50	99.87 7	95.46 85	99.59 17	99.64 16

PS-CasMVS		91.55 220	90.84 221	93.69 244	94.96 273	88.28 232	97.84 83	98.24 45	91.46 151	88.04 290	95.80 213	79.67 244	97.48 310	87.02 259	84.54 327	95.31 278

DU-MVS		92.90 169	92.04 176	95.49 149	94.95 274	92.83 74	97.16 161	98.24 45	93.02 104	90.13 228	95.71 220	83.47 169	97.85 277	91.71 164	83.93 333	95.78 248

9.14			96.75 38		98.93 47		97.73 93	98.23 48	91.28 159	97.88 33	98.44 42	93.00 24	99.65 56	95.76 71	99.47 38

D2MVS		91.30 235	90.95 215	92.35 287	94.71 291	85.52 291	96.18 243	98.21 49	88.89 232	86.60 317	93.82 306	79.92 240	97.95 266	89.29 210	90.95 255	93.56 341

SDMVSNet		94.17 111	93.61 116	95.86 126	98.09 99	91.37 124	97.35 141	98.20 50	93.18 98	91.79 190	97.28 129	79.13 252	98.93 158	94.61 108	92.84 218	97.28 199

XVS		97.18 18	96.96 25	97.81 28	99.38 14	94.03 48	98.59 12	98.20 50	94.85 32	96.59 72	98.29 61	91.70 46	99.80 30	95.66 73	99.40 50	99.62 18

X-MVStestdata		91.71 211	89.67 270	97.81 28	99.38 14	94.03 48	98.59 12	98.20 50	94.85 32	96.59 72	32.69 394	91.70 46	99.80 30	95.66 73	99.40 50	99.62 18

ACMMP_NAP		97.20 17	96.86 28	98.23 11	99.09 34	95.16 22	97.60 113	98.19 53	92.82 116	97.93 32	98.74 24	91.60 49	99.86 8	96.26 48	99.52 28	99.67 13

CP-MVSNet		91.89 207	91.24 207	93.82 236	95.05 270	88.57 223	97.82 85	98.19 53	91.70 145	88.21 286	95.76 218	81.96 205	97.52 308	87.86 234	84.65 322	95.37 274

ZNCC-MVS		96.96 28	96.67 42	97.85 25	99.37 16	94.12 44	98.49 20	98.18 55	92.64 122	96.39 82	98.18 68	91.61 48	99.88 4	95.59 83	99.55 24	99.57 26

SMA-MVS		97.35 14	97.03 22	98.30 8	99.06 38	95.42 10	97.94 71	98.18 55	90.57 188	98.85 13	98.94 9	93.33 21	99.83 26	96.72 38	99.68 4	99.63 17
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		91.20 239	90.44 235	93.48 253	94.49 298	87.91 247	97.76 89	98.18 55	91.29 156	87.78 294	95.74 219	80.35 231	97.33 321	85.46 283	82.96 343	95.19 289

DELS-MVS		96.61 49	96.38 56	97.30 51	97.79 117	93.19 67	95.96 253	98.18 55	95.23 19	95.87 99	97.65 109	91.45 51	99.70 49	95.87 65	99.44 45	99.00 90
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		89.70 284	88.40 289	93.60 247	95.15 265	90.10 170	97.56 117	98.16 59	87.28 283	86.16 321	94.63 268	77.57 279	98.05 248	74.48 359	84.59 325	92.65 354

VNet		95.89 69	95.45 72	97.21 58	98.07 103	92.94 73	97.50 123	98.15 60	93.87 69	97.52 38	97.61 115	85.29 143	99.53 89	95.81 70	95.27 183	99.16 71

DeepPCF-MVS	93.97 1	96.61 49	97.09 16	95.15 161	98.09 99	86.63 275	96.00 251	98.15 60	95.43 14	97.95 31	98.56 29	93.40 20	99.36 112	96.77 36	99.48 37	99.45 46

SD-MVS		97.41 12	97.53 9	97.06 64	98.57 69	94.46 31	97.92 73	98.14 62	94.82 36	99.01 4	98.55 31	94.18 14	97.41 317	96.94 32	99.64 13	99.32 60
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 36	96.52 48	97.82 27	99.36 18	94.14 43	98.29 31	98.13 63	92.72 119	96.70 64	98.06 75	91.35 55	99.86 8	94.83 99	99.28 61	99.47 45

UA-Net		95.95 68	95.53 69	97.20 59	97.67 122	92.98 72	97.65 104	98.13 63	94.81 37	96.61 70	98.35 49	88.87 88	99.51 94	90.36 187	97.35 140	99.11 79

QAPM		93.45 143	92.27 171	96.98 67	96.77 173	92.62 79	98.39 26	98.12 65	84.50 327	88.27 284	97.77 100	82.39 198	99.81 29	85.40 284	98.81 91	98.51 127

Vis-MVSNet		95.23 85	94.81 87	96.51 81	97.18 144	91.58 115	98.26 35	98.12 65	94.38 56	94.90 122	98.15 70	82.28 199	98.92 159	91.45 171	98.58 101	99.01 87
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 171	91.68 190	96.40 91	95.34 249	92.73 77	98.27 33	98.12 65	84.86 322	85.78 323	97.75 101	78.89 261	99.74 39	87.50 249	98.65 96	96.73 215

TranMVSNet+NR-MVSNet		92.50 180	91.63 191	95.14 162	94.76 286	92.07 97	97.53 121	98.11 68	92.90 114	89.56 250	96.12 198	83.16 175	97.60 300	89.30 209	83.20 342	95.75 253

CPTT-MVS		95.57 77	95.19 80	96.70 69	99.27 26	91.48 119	98.33 28	98.11 68	87.79 268	95.17 119	98.03 78	87.09 121	99.61 67	93.51 127	99.42 46	99.02 84

APD-MVS		96.95 29	96.60 44	98.01 19	99.03 41	94.93 26	97.72 96	98.10 70	91.50 149	98.01 29	98.32 57	92.33 36	99.58 75	94.85 98	99.51 31	99.53 36
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 34	96.60 44	97.64 43	99.40 11	93.44 59	98.50 19	98.09 71	93.27 93	95.95 98	98.33 55	91.04 62	99.88 4	95.20 90	99.57 23	99.60 21

ZD-MVS					99.05 39	94.59 29		98.08 72	89.22 220	97.03 55	98.10 71	92.52 33	99.65 56	94.58 109	99.31 60

MTGPA								98.08 72

MTAPA		97.08 22	96.78 36	97.97 22	99.37 16	94.42 33	97.24 151	98.08 72	95.07 27	96.11 90	98.59 28	90.88 66	99.90 2	96.18 57	99.50 33	99.58 25

CNVR-MVS		97.68 6	97.44 11	98.37 7	98.90 50	95.86 6	97.27 149	98.08 72	95.81 9	97.87 34	98.31 58	94.26 13	99.68 52	97.02 31	99.49 36	99.57 26

DP-MVS Recon		95.68 73	95.12 83	97.37 49	99.19 31	94.19 40	97.03 167	98.08 72	88.35 252	95.09 121	97.65 109	89.97 77	99.48 99	92.08 156	98.59 100	98.44 138

SR-MVS		97.01 27	96.86 28	97.47 46	99.09 34	93.27 66	97.98 61	98.07 77	93.75 72	97.45 40	98.48 39	91.43 53	99.59 72	96.22 51	99.27 62	99.54 33

MCST-MVS		97.18 18	96.84 30	98.20 14	99.30 24	95.35 15	97.12 164	98.07 77	93.54 81	96.08 92	97.69 104	93.86 16	99.71 44	96.50 44	99.39 52	99.55 32

NR-MVSNet		92.34 189	91.27 206	95.53 146	94.95 274	93.05 70	97.39 137	98.07 77	92.65 121	84.46 334	95.71 220	85.00 147	97.77 286	89.71 198	83.52 339	95.78 248

MP-MVS-pluss		96.70 44	96.27 58	97.98 21	99.23 30	94.71 28	96.96 176	98.06 80	90.67 179	95.55 111	98.78 23	91.07 61	99.86 8	96.58 42	99.55 24	99.38 56
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 39	96.71 41	97.12 62	99.01 45	92.31 89	97.98 61	98.06 80	93.11 102	97.44 41	98.55 31	90.93 64	99.55 85	96.06 58	99.25 66	99.51 37

MP-MVS		96.77 41	96.45 54	97.72 37	99.39 13	93.80 51	98.41 25	98.06 80	93.37 89	95.54 113	98.34 52	90.59 70	99.88 4	94.83 99	99.54 26	99.49 41
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 52	96.27 58	97.22 57	99.32 22	92.74 76	98.74 9	98.06 80	90.57 188	96.77 61	98.35 49	90.21 73	99.53 89	94.80 102	99.63 14	99.38 56

HPM-MVS		96.69 46	96.45 54	97.40 48	99.36 18	93.11 69	98.87 6	98.06 80	91.17 164	96.40 81	97.99 82	90.99 63	99.58 75	95.61 80	99.61 16	99.49 41
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 104	93.80 111	96.64 70	97.07 151	91.97 101	96.32 232	98.06 80	88.94 230	94.50 130	96.78 155	84.60 151	99.27 120	91.90 157	96.02 167	98.68 118

DeepC-MVS	93.07 3	96.06 63	95.66 67	97.29 52	97.96 106	93.17 68	97.30 147	98.06 80	93.92 67	93.38 156	98.66 25	86.83 123	99.73 40	95.60 82	99.22 68	98.96 92
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 16	97.03 22	98.11 17	98.77 53	95.06 24	97.34 142	98.04 87	95.96 6	97.09 53	97.88 90	93.18 23	99.71 44	95.84 69	99.17 72	99.56 29

DeepC-MVS_fast	93.89 2	96.93 31	96.64 43	97.78 31	98.64 64	94.30 35	97.41 132	98.04 87	94.81 37	96.59 72	98.37 47	91.24 57	99.64 64	95.16 91	99.52 28	99.42 52
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 33	96.80 35	97.11 63	99.02 42	92.34 87	97.98 61	98.03 89	93.52 83	97.43 43	98.51 34	91.40 54	99.56 83	96.05 59	99.26 64	99.43 50

RE-MVS-def			96.72 40		99.02 42	92.34 87	97.98 61	98.03 89	93.52 83	97.43 43	98.51 34	90.71 68		96.05 59	99.26 64	99.43 50

RPMNet		88.98 289	87.05 303	94.77 189	94.45 300	87.19 260	90.23 371	98.03 89	77.87 373	92.40 173	87.55 376	80.17 235	99.51 94	68.84 377	93.95 207	97.60 186

save fliter					98.91 49	94.28 36	97.02 169	98.02 92	95.35 16

TEST9					98.70 56	94.19 40	96.41 221	98.02 92	88.17 256	96.03 93	97.56 119	92.74 28	99.59 72

train_agg		96.30 59	95.83 66	97.72 37	98.70 56	94.19 40	96.41 221	98.02 92	88.58 243	96.03 93	97.56 119	92.73 29	99.59 72	95.04 93	99.37 56	99.39 54

test_8					98.67 58	94.06 47	96.37 228	98.01 95	88.58 243	95.98 97	97.55 121	92.73 29	99.58 75

agg_prior					98.67 58	93.79 52		98.00 96		95.68 107			99.57 82

test_prior				97.23 56	98.67 58	92.99 71		98.00 96					99.41 107			99.29 61

WR-MVS		92.34 189	91.53 195	94.77 189	95.13 267	90.83 149	96.40 225	97.98 98	91.88 142	89.29 259	95.54 231	82.50 194	97.80 282	89.79 197	85.27 313	95.69 257

HPM-MVS++		97.34 15	96.97 24	98.47 5	99.08 36	96.16 4	97.55 120	97.97 99	95.59 11	96.61 70	97.89 88	92.57 32	99.84 23	95.95 64	99.51 31	99.40 53

CANet		96.39 56	96.02 61	97.50 45	97.62 128	93.38 61	97.02 169	97.96 100	95.42 15	94.86 123	97.81 97	87.38 117	99.82 28	96.88 34	99.20 70	99.29 61

114514_t		93.95 123	93.06 138	96.63 72	99.07 37	91.61 112	97.46 131	97.96 100	77.99 371	93.00 164	97.57 117	86.14 135	99.33 113	89.22 213	99.15 74	98.94 95

IU-MVS					99.42 7	95.39 11		97.94 102	90.40 192	98.94 6				97.41 27	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 103					99.86 8	97.68 14	99.67 6	99.77 2

No_MVS				98.86 1	98.67 58	96.94 1		97.93 103					99.86 8	97.68 14	99.67 6	99.77 2

Anonymous20231211		90.63 262	89.42 275	94.27 212	98.24 86	89.19 210	98.05 54	97.89 105	79.95 363	88.25 285	94.96 250	72.56 319	98.13 230	89.70 199	85.14 315	95.49 261

原ACMM1				96.38 94	98.59 66	91.09 140		97.89 105	87.41 279	95.22 118	97.68 105	90.25 72	99.54 87	87.95 233	99.12 77	98.49 130

CDPH-MVS		95.97 67	95.38 75	97.77 33	98.93 47	94.44 32	96.35 229	97.88 107	86.98 287	96.65 68	97.89 88	91.99 42	99.47 100	92.26 147	99.46 39	99.39 54

test11								97.88 107

EIA-MVS		95.53 78	95.47 71	95.71 136	97.06 154	89.63 184	97.82 85	97.87 109	93.57 77	93.92 144	95.04 248	90.61 69	98.95 156	94.62 107	98.68 95	98.54 123

CS-MVS		96.86 34	97.06 17	96.26 104	98.16 96	91.16 138	99.09 3	97.87 109	95.30 18	97.06 54	98.03 78	91.72 44	98.71 180	97.10 29	99.17 72	98.90 100

无先验							95.79 260	97.87 109	83.87 335				99.65 56	87.68 243		98.89 103

3Dnovator+	91.43 4	95.40 79	94.48 101	98.16 16	96.90 163	95.34 16	98.48 21	97.87 109	94.65 47	88.53 277	98.02 80	83.69 165	99.71 44	93.18 134	98.96 86	99.44 48

VPNet		92.23 197	91.31 203	94.99 171	95.56 234	90.96 143	97.22 156	97.86 113	92.96 112	90.96 212	96.62 175	75.06 301	98.20 223	91.90 157	83.65 338	95.80 246

test_vis1_n_1920		94.17 111	94.58 94	92.91 273	97.42 138	82.02 333	97.83 84	97.85 114	94.68 44	98.10 27	98.49 36	70.15 334	99.32 115	97.91 13	98.82 90	97.40 193

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 114	94.92 30	98.73 16	98.87 15	95.08 8	99.84 23	97.52 20	99.67 6	99.48 43
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 11	97.33 13	97.69 40	99.25 27	94.24 39	98.07 52	97.85 114	93.72 73	98.57 19	98.35 49	93.69 18	99.40 108	97.06 30	99.46 39	99.44 48
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 32	97.04 21	96.45 88	98.29 82	91.66 111	99.03 4	97.85 114	95.84 7	96.90 57	97.97 84	91.24 57	98.75 174	96.92 33	99.33 58	98.94 95

test_fmvsmconf0.01_n		96.15 62	95.85 65	97.03 65	92.66 347	91.83 104	97.97 67	97.84 118	95.57 12	97.53 37	99.00 6	84.20 159	99.76 36	98.82 9	99.08 79	99.48 43

AdaColmap		94.34 107	93.68 114	96.31 98	98.59 66	91.68 110	96.59 212	97.81 119	89.87 200	92.15 181	97.06 143	83.62 168	99.54 87	89.34 208	98.07 120	97.70 179

ETV-MVS		96.02 65	95.89 64	96.40 91	97.16 145	92.44 84	97.47 129	97.77 120	94.55 48	96.48 77	94.51 272	91.23 59	98.92 159	95.65 76	98.19 116	97.82 175

新几何1				97.32 50	98.60 65	93.59 56		97.75 121	81.58 354	95.75 104	97.85 94	90.04 75	99.67 54	86.50 265	99.13 76	98.69 117

旧先验1					98.38 78	93.38 61		97.75 121			98.09 73	92.30 39			99.01 84	99.16 71

EC-MVSNet		96.42 54	96.47 50	96.26 104	97.01 159	91.52 117	98.89 5	97.75 121	94.42 53	96.64 69	97.68 105	89.32 82	98.60 190	97.45 24	99.11 78	98.67 119

EI-MVSNet-Vis-set		96.51 52	96.47 50	96.63 72	98.24 86	91.20 133	96.89 180	97.73 124	94.74 42	96.49 76	98.49 36	90.88 66	99.58 75	96.44 46	98.32 111	99.13 75

PAPM_NR		95.01 90	94.59 93	96.26 104	98.89 51	90.68 157	97.24 151	97.73 124	91.80 143	92.93 169	96.62 175	89.13 85	99.14 133	89.21 214	97.78 127	98.97 91

Anonymous20240529		91.98 205	90.73 226	95.73 134	98.14 97	89.40 197	97.99 60	97.72 126	79.63 365	93.54 151	97.41 125	69.94 336	99.56 83	91.04 178	91.11 251	98.22 151

CHOSEN 280x420		93.12 156	92.72 154	94.34 207	96.71 177	87.27 256	90.29 370	97.72 126	86.61 294	91.34 201	95.29 238	84.29 158	98.41 204	93.25 133	98.94 87	97.35 196

EI-MVSNet-UG-set		96.34 58	96.30 57	96.47 85	98.20 91	90.93 145	96.86 182	97.72 126	94.67 45	96.16 89	98.46 40	90.43 71	99.58 75	96.23 50	97.96 123	98.90 100

LS3D		93.57 139	92.61 159	96.47 85	97.59 132	91.61 112	97.67 101	97.72 126	85.17 317	90.29 222	98.34 52	84.60 151	99.73 40	83.85 304	98.27 113	98.06 164

PAPR		94.18 110	93.42 130	96.48 84	97.64 126	91.42 123	95.55 269	97.71 130	88.99 227	92.34 178	95.82 212	89.19 83	99.11 136	86.14 271	97.38 138	98.90 100

UGNet		94.04 121	93.28 133	96.31 98	96.85 165	91.19 134	97.88 78	97.68 131	94.40 54	93.00 164	96.18 194	73.39 316	99.61 67	91.72 163	98.46 106	98.13 157
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				95.46 153	98.18 95	88.90 216		97.66 132	82.73 345	97.03 55	98.07 74	90.06 74	98.85 164	89.67 200	98.98 85	98.64 120

test12				97.65 41	98.46 70	94.26 37		97.66 132		95.52 114		90.89 65	99.46 101		99.25 66	99.22 68

DTE-MVSNet		90.56 263	89.75 268	93.01 269	93.95 314	87.25 257	97.64 108	97.65 134	90.74 174	87.12 306	95.68 223	79.97 239	97.00 333	83.33 305	81.66 349	94.78 315

TAPA-MVS	90.10 7	92.30 192	91.22 209	95.56 143	98.33 80	89.60 186	96.79 188	97.65 134	81.83 351	91.52 196	97.23 134	87.94 104	98.91 161	71.31 372	98.37 109	98.17 155
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 157	92.45 167	95.05 166	98.09 99	89.21 207	96.89 180	97.64 136	93.18 98	91.79 190	97.28 129	75.35 300	98.65 185	88.99 219	92.84 218	97.28 199

test_cas_vis1_n_1920		94.48 105	94.55 98	94.28 211	96.78 171	86.45 277	97.63 110	97.64 136	93.32 92	97.68 36	98.36 48	73.75 314	99.08 142	96.73 37	99.05 81	97.31 198

cdsmvs_eth3d_5k		23.24 363	30.99 365	0.00 382	0.00 404	0.00 407	0.00 393	97.63 138	0.00 400	0.00 401	96.88 153	84.38 155	0.00 401	0.00 400	0.00 399	0.00 397

DPM-MVS		95.69 72	94.92 85	98.01 19	98.08 102	95.71 9	95.27 283	97.62 139	90.43 191	95.55 111	97.07 142	91.72 44	99.50 97	89.62 202	98.94 87	98.82 109

canonicalmvs		96.02 65	95.45 72	97.75 35	97.59 132	95.15 23	98.28 32	97.60 140	94.52 50	96.27 86	96.12 198	87.65 109	99.18 128	96.20 56	94.82 191	98.91 99

test222					98.24 86	92.21 92	95.33 278	97.60 140	79.22 367	95.25 116	97.84 96	88.80 90			99.15 74	98.72 114

cascas		91.20 239	90.08 252	94.58 197	94.97 272	89.16 211	93.65 336	97.59 142	79.90 364	89.40 254	92.92 326	75.36 299	98.36 211	92.14 152	94.75 193	96.23 225

h-mvs33		94.15 113	93.52 122	96.04 117	97.81 116	90.22 169	97.62 112	97.58 143	95.19 20	96.74 62	97.45 122	83.67 166	99.61 67	95.85 67	79.73 356	98.29 148

MVSFormer		95.37 80	95.16 81	95.99 122	96.34 201	91.21 131	98.22 41	97.57 144	91.42 153	96.22 87	97.32 127	86.20 133	97.92 271	94.07 115	99.05 81	98.85 106

test_djsdf		93.07 160	92.76 149	94.00 223	93.49 330	88.70 220	98.22 41	97.57 144	91.42 153	90.08 234	95.55 230	82.85 186	97.92 271	94.07 115	91.58 239	95.40 271

OMC-MVS		95.09 89	94.70 91	96.25 107	98.46 70	91.28 127	96.43 219	97.57 144	92.04 138	94.77 125	97.96 85	87.01 122	99.09 140	91.31 173	96.77 154	98.36 145

PS-MVSNAJss		93.74 133	93.51 123	94.44 201	93.91 316	89.28 205	97.75 90	97.56 147	92.50 124	89.94 237	96.54 178	88.65 93	98.18 226	93.83 124	90.90 256	95.86 239

casdiffmvs_mvg		95.81 71	95.57 68	96.51 81	96.87 164	91.49 118	97.50 123	97.56 147	93.99 65	95.13 120	97.92 87	87.89 105	98.78 169	95.97 63	97.33 141	99.26 65
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
jajsoiax		92.42 184	91.89 183	94.03 222	93.33 336	88.50 227	97.73 93	97.53 149	92.00 140	88.85 269	96.50 180	75.62 298	98.11 236	93.88 122	91.56 240	95.48 262

mvs_tets		92.31 191	91.76 185	93.94 230	93.41 333	88.29 231	97.63 110	97.53 149	92.04 138	88.76 272	96.45 182	74.62 306	98.09 240	93.91 120	91.48 242	95.45 267

dcpmvs_2		96.37 57	97.05 20	94.31 209	98.96 46	84.11 313	97.56 117	97.51 151	93.92 67	97.43 43	98.52 33	92.75 27	99.32 115	97.32 28	99.50 33	99.51 37

HQP_MVS		93.78 132	93.43 128	94.82 182	96.21 205	89.99 174	97.74 91	97.51 151	94.85 32	91.34 201	96.64 166	81.32 215	98.60 190	93.02 140	92.23 227	95.86 239

plane_prior5								97.51 151					98.60 190	93.02 140	92.23 227	95.86 239

PS-MVSNAJ		95.37 80	95.33 77	95.49 149	97.35 139	90.66 158	95.31 280	97.48 154	93.85 70	96.51 75	95.70 222	88.65 93	99.65 56	94.80 102	98.27 113	96.17 229

API-MVS		94.84 99	94.49 100	95.90 124	97.90 112	92.00 100	97.80 87	97.48 154	89.19 221	94.81 124	96.71 158	88.84 89	99.17 129	88.91 221	98.76 93	96.53 218

MG-MVS		95.61 75	95.38 75	96.31 98	98.42 73	90.53 160	96.04 248	97.48 154	93.47 85	95.67 108	98.10 71	89.17 84	99.25 121	91.27 174	98.77 92	99.13 75

MAR-MVS		94.22 109	93.46 125	96.51 81	98.00 105	92.19 95	97.67 101	97.47 157	88.13 259	93.00 164	95.84 210	84.86 149	99.51 94	87.99 232	98.17 118	97.83 174
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		92.98 164	92.53 163	94.32 208	96.12 215	89.20 208	95.28 281	97.47 157	92.66 120	89.90 238	95.62 226	80.58 226	98.40 205	92.73 145	92.40 225	95.38 273
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 233	90.22 248	94.68 192	94.86 282	87.86 248	97.23 155	97.46 159	87.99 260	89.90 238	96.92 151	66.35 355	98.23 220	90.30 188	90.99 254	97.96 165

nrg030		94.05 120	93.31 132	96.27 103	95.22 260	94.59 29	98.34 27	97.46 159	92.93 113	91.21 210	96.64 166	87.23 120	98.22 221	94.99 96	85.80 305	95.98 238

XVG-OURS		93.72 134	93.35 131	94.80 187	97.07 151	88.61 221	94.79 294	97.46 159	91.97 141	93.99 141	97.86 93	81.74 210	98.88 163	92.64 146	92.67 223	96.92 210

LPG-MVS_test		92.94 167	92.56 160	94.10 217	96.16 210	88.26 233	97.65 104	97.46 159	91.29 156	90.12 230	97.16 137	79.05 254	98.73 176	92.25 149	91.89 235	95.31 278

LGP-MVS_train				94.10 217	96.16 210	88.26 233		97.46 159	91.29 156	90.12 230	97.16 137	79.05 254	98.73 176	92.25 149	91.89 235	95.31 278

MVS		91.71 211	90.44 235	95.51 147	95.20 262	91.59 114	96.04 248	97.45 164	73.44 379	87.36 303	95.60 227	85.42 142	99.10 137	85.97 276	97.46 133	95.83 243

XVG-OURS-SEG-HR		93.86 128	93.55 118	94.81 184	97.06 154	88.53 226	95.28 281	97.45 164	91.68 146	94.08 140	97.68 105	82.41 197	98.90 162	93.84 123	92.47 224	96.98 206

baseline		95.58 76	95.42 74	96.08 113	96.78 171	90.41 165	97.16 161	97.45 164	93.69 76	95.65 109	97.85 94	87.29 118	98.68 182	95.66 73	97.25 145	99.13 75

ab-mvs		93.57 139	92.55 161	96.64 70	97.28 140	91.96 102	95.40 275	97.45 164	89.81 205	93.22 162	96.28 190	79.62 245	99.46 101	90.74 182	93.11 215	98.50 128

xiu_mvs_v2_base		95.32 82	95.29 78	95.40 154	97.22 141	90.50 161	95.44 274	97.44 168	93.70 75	96.46 79	96.18 194	88.59 96	99.53 89	94.79 104	97.81 126	96.17 229

1314		92.81 175	92.03 177	95.14 162	95.33 252	89.52 192	96.04 248	97.44 168	87.72 272	86.25 320	95.33 237	83.84 163	98.79 168	89.26 211	97.05 150	97.11 204

casdiffmvs		95.64 74	95.49 70	96.08 113	96.76 176	90.45 163	97.29 148	97.44 168	94.00 64	95.46 115	97.98 83	87.52 113	98.73 176	95.64 77	97.33 141	99.08 81
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		92.16 199	91.23 208	94.95 176	94.75 288	90.94 144	97.47 129	97.43 171	89.14 222	88.90 266	96.43 183	79.71 243	98.24 219	89.56 203	87.68 288	95.67 259

anonymousdsp		92.16 199	91.55 194	93.97 226	92.58 349	89.55 189	97.51 122	97.42 172	89.42 215	88.40 279	94.84 257	80.66 224	97.88 276	91.87 159	91.28 247	94.48 323

Effi-MVS+		94.93 95	94.45 102	96.36 96	96.61 181	91.47 120	96.41 221	97.41 173	91.02 169	94.50 130	95.92 206	87.53 112	98.78 169	93.89 121	96.81 153	98.84 108

HQP3-MVS								97.39 174							92.10 232

HQP-MVS		93.19 152	92.74 152	94.54 199	95.86 221	89.33 201	96.65 203	97.39 174	93.55 78	90.14 224	95.87 208	80.95 218	98.50 198	92.13 153	92.10 232	95.78 248

PLC	91.00 6	94.11 117	93.43 128	96.13 112	98.58 68	91.15 139	96.69 199	97.39 174	87.29 282	91.37 200	96.71 158	88.39 97	99.52 93	87.33 252	97.13 149	97.73 177
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 256	89.86 261	93.45 255	93.54 327	87.60 253	97.70 100	97.37 177	88.85 233	87.65 296	94.08 298	81.08 217	98.10 237	84.68 292	83.79 337	94.66 320

UnsupCasMVSNet_eth		85.99 322	84.45 326	90.62 327	89.97 367	82.40 330	93.62 337	97.37 177	89.86 201	78.59 368	92.37 334	65.25 361	95.35 361	82.27 317	70.75 377	94.10 334

ACMM	89.79 8	92.96 165	92.50 165	94.35 206	96.30 203	88.71 219	97.58 115	97.36 179	91.40 155	90.53 216	96.65 165	79.77 242	98.75 174	91.24 175	91.64 237	95.59 260
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 90	94.76 88	95.75 131	96.58 184	91.71 107	96.25 237	97.35 180	92.99 105	96.70 64	96.63 172	82.67 189	99.44 104	96.22 51	97.46 133	96.11 234

xiu_mvs_v1_base		95.01 90	94.76 88	95.75 131	96.58 184	91.71 107	96.25 237	97.35 180	92.99 105	96.70 64	96.63 172	82.67 189	99.44 104	96.22 51	97.46 133	96.11 234

xiu_mvs_v1_base_debi		95.01 90	94.76 88	95.75 131	96.58 184	91.71 107	96.25 237	97.35 180	92.99 105	96.70 64	96.63 172	82.67 189	99.44 104	96.22 51	97.46 133	96.11 234

diffmvs		95.25 84	95.13 82	95.63 139	96.43 197	89.34 200	95.99 252	97.35 180	92.83 115	96.31 83	97.37 126	86.44 128	98.67 183	96.26 48	97.19 147	98.87 105
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		94.71 103	94.02 107	96.79 68	97.71 121	92.05 98	96.59 212	97.35 180	90.61 185	94.64 127	96.93 148	86.41 129	99.39 109	91.20 176	94.71 195	98.94 95

F-COLMAP		93.58 138	92.98 140	95.37 155	98.40 75	88.98 214	97.18 159	97.29 185	87.75 271	90.49 217	97.10 141	85.21 144	99.50 97	86.70 262	96.72 157	97.63 181

XVG-ACMP-BASELINE		90.93 252	90.21 249	93.09 267	94.31 306	85.89 286	95.33 278	97.26 186	91.06 168	89.38 255	95.44 235	68.61 341	98.60 190	89.46 205	91.05 252	94.79 313

PCF-MVS	89.48 11	91.56 219	89.95 258	96.36 96	96.60 182	92.52 82	92.51 356	97.26 186	79.41 366	88.90 266	96.56 177	84.04 162	99.55 85	77.01 351	97.30 143	97.01 205
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 179	92.14 174	94.05 220	96.40 198	88.20 236	97.36 140	97.25 188	91.52 148	88.30 282	96.64 166	78.46 266	98.72 179	91.86 160	91.48 242	95.23 285
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 148	92.76 149	94.82 182	94.63 294	90.77 152	96.65 203	97.18 189	93.72 73	91.68 192	97.26 132	79.33 249	98.63 187	92.13 153	92.28 226	95.07 291
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 169	92.02 178	95.56 143	98.19 93	90.80 150	95.27 283	97.18 189	87.96 261	91.86 189	95.68 223	80.44 229	98.99 154	84.01 300	97.54 132	96.89 211

alignmvs		95.87 70	95.23 79	97.78 31	97.56 135	95.19 21	97.86 79	97.17 191	94.39 55	96.47 78	96.40 185	85.89 136	99.20 125	96.21 55	95.11 187	98.95 94

MVS_Test		94.89 97	94.62 92	95.68 137	96.83 168	89.55 189	96.70 197	97.17 191	91.17 164	95.60 110	96.11 201	87.87 106	98.76 173	93.01 142	97.17 148	98.72 114

Fast-Effi-MVS+		93.46 142	92.75 151	95.59 142	96.77 173	90.03 171	96.81 187	97.13 193	88.19 255	91.30 204	94.27 288	86.21 132	98.63 187	87.66 244	96.46 164	98.12 158

EI-MVSNet		93.03 162	92.88 144	93.48 253	95.77 226	86.98 265	96.44 217	97.12 194	90.66 181	91.30 204	97.64 112	86.56 125	98.05 248	89.91 193	90.55 261	95.41 268

MVSTER		93.20 151	92.81 148	94.37 205	96.56 187	89.59 187	97.06 166	97.12 194	91.24 160	91.30 204	95.96 204	82.02 204	98.05 248	93.48 128	90.55 261	95.47 265

test_yl		94.78 101	94.23 105	96.43 89	97.74 119	91.22 129	96.85 183	97.10 196	91.23 161	95.71 105	96.93 148	84.30 156	99.31 117	93.10 135	95.12 185	98.75 111

DCV-MVSNet		94.78 101	94.23 105	96.43 89	97.74 119	91.22 129	96.85 183	97.10 196	91.23 161	95.71 105	96.93 148	84.30 156	99.31 117	93.10 135	95.12 185	98.75 111

LTVRE_ROB	88.41 13	90.99 248	89.92 260	94.19 213	96.18 208	89.55 189	96.31 233	97.09 198	87.88 264	85.67 324	95.91 207	78.79 262	98.57 194	81.50 320	89.98 267	94.44 326
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		92.73 177	92.88 144	92.29 290	96.08 218	81.05 341	97.98 61	97.08 199	90.72 176	96.79 60	98.18 68	63.07 365	98.45 202	97.62 18	98.42 108	97.36 194

v10		91.04 246	90.23 246	93.49 252	94.12 310	88.16 239	97.32 145	97.08 199	88.26 254	88.29 283	94.22 293	82.17 202	97.97 259	86.45 266	84.12 331	94.33 329

v144192		91.06 245	90.28 242	93.39 256	93.66 325	87.23 259	96.83 186	97.07 201	87.43 278	89.69 245	94.28 287	81.48 213	98.00 255	87.18 256	84.92 321	94.93 299

v1192		91.07 244	90.23 246	93.58 249	93.70 322	87.82 249	96.73 193	97.07 201	87.77 269	89.58 248	94.32 285	80.90 222	97.97 259	86.52 264	85.48 308	94.95 295

v8		91.29 236	90.53 234	93.57 250	94.15 309	88.12 240	97.34 142	97.06 203	88.99 227	88.32 281	94.26 290	83.08 178	98.01 254	87.62 246	83.92 335	94.57 322

mvs_anonymous		93.82 130	93.74 112	94.06 219	96.44 196	85.41 293	95.81 259	97.05 204	89.85 203	90.09 233	96.36 187	87.44 115	97.75 287	93.97 117	96.69 158	99.02 84

IterMVS-LS		92.29 193	91.94 181	93.34 258	96.25 204	86.97 266	96.57 215	97.05 204	90.67 179	89.50 253	94.80 260	86.59 124	97.64 295	89.91 193	86.11 303	95.40 271
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 254	90.03 257	93.29 260	93.55 326	86.96 267	96.74 192	97.04 206	87.36 280	89.52 252	94.34 282	80.23 234	97.97 259	86.27 267	85.21 314	94.94 297

CDS-MVSNet		94.14 116	93.54 119	95.93 123	96.18 208	91.46 121	96.33 231	97.04 206	88.97 229	93.56 149	96.51 179	87.55 111	97.89 275	89.80 196	95.95 169	98.44 138
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 230	90.60 230	93.68 245	93.89 317	88.23 235	96.84 185	97.03 208	88.37 251	89.69 245	94.39 279	82.04 203	97.98 256	87.80 236	85.37 310	94.84 305

v1240		90.70 260	89.85 262	93.23 262	93.51 329	86.80 268	96.61 209	97.02 209	87.16 285	89.58 248	94.31 286	79.55 246	97.98 256	85.52 282	85.44 309	94.90 302

EPP-MVSNet		95.22 86	95.04 84	95.76 129	97.49 136	89.56 188	98.67 10	97.00 210	90.69 177	94.24 135	97.62 114	89.79 79	98.81 167	93.39 132	96.49 162	98.92 98

V42		91.58 218	90.87 217	93.73 240	94.05 313	88.50 227	97.32 145	96.97 211	88.80 239	89.71 243	94.33 283	82.54 193	98.05 248	89.01 218	85.07 317	94.64 321

test_fmvs1		93.21 150	93.53 120	92.25 292	96.55 189	81.20 340	97.40 136	96.96 212	90.68 178	96.80 59	98.04 77	69.25 338	98.40 205	97.58 19	98.50 102	97.16 203

FMVSNet2		91.31 234	90.08 252	94.99 171	96.51 191	92.21 92	97.41 132	96.95 213	88.82 236	88.62 274	94.75 262	73.87 310	97.42 316	85.20 287	88.55 282	95.35 275

ACMH	87.59 16	90.53 264	89.42 275	93.87 234	96.21 205	87.92 245	97.24 151	96.94 214	88.45 249	83.91 344	96.27 191	71.92 320	98.62 189	84.43 295	89.43 273	95.05 293
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 231	90.27 243	94.59 193	96.51 191	91.18 135	97.50 123	96.93 215	88.82 236	89.35 256	94.51 272	73.87 310	97.29 323	86.12 272	88.82 277	95.31 278

test1		91.35 231	90.27 243	94.59 193	96.51 191	91.18 135	97.50 123	96.93 215	88.82 236	89.35 256	94.51 272	73.87 310	97.29 323	86.12 272	88.82 277	95.31 278

FMVSNet3		91.78 209	90.69 228	95.03 169	96.53 190	92.27 91	97.02 169	96.93 215	89.79 206	89.35 256	94.65 267	77.01 282	97.47 311	86.12 272	88.82 277	95.35 275

FMVSNet1		89.88 280	88.31 290	94.59 193	95.41 242	91.18 135	97.50 123	96.93 215	86.62 293	87.41 301	94.51 272	65.94 359	97.29 323	83.04 308	87.43 291	95.31 278

GeoE		93.89 126	93.28 133	95.72 135	96.96 162	89.75 182	98.24 39	96.92 219	89.47 213	92.12 183	97.21 135	84.42 154	98.39 209	87.71 239	96.50 161	99.01 87

miper_enhance_ethall		91.54 221	91.01 214	93.15 265	95.35 248	87.07 264	93.97 322	96.90 220	86.79 291	89.17 263	93.43 322	86.55 126	97.64 295	89.97 192	86.93 295	94.74 317

eth_miper_zixun_eth		91.02 247	90.59 231	92.34 289	95.33 252	84.35 309	94.10 319	96.90 220	88.56 245	88.84 270	94.33 283	84.08 161	97.60 300	88.77 224	84.37 329	95.06 292

TAMVS		94.01 122	93.46 125	95.64 138	96.16 210	90.45 163	96.71 196	96.89 222	89.27 219	93.46 154	96.92 151	87.29 118	97.94 267	88.70 225	95.74 174	98.53 124

miper_ehance_all_eth		91.59 216	91.13 212	92.97 271	95.55 235	86.57 276	94.47 303	96.88 223	87.77 269	88.88 268	94.01 299	86.22 131	97.54 304	89.49 204	86.93 295	94.79 313

v2v482		91.59 216	90.85 220	93.80 237	93.87 318	88.17 238	96.94 177	96.88 223	89.54 210	89.53 251	94.90 254	81.70 211	98.02 253	89.25 212	85.04 319	95.20 286

CNLPA		94.28 108	93.53 120	96.52 78	98.38 78	92.55 81	96.59 212	96.88 223	90.13 197	91.91 187	97.24 133	85.21 144	99.09 140	87.64 245	97.83 125	97.92 167

PAPM		91.52 222	90.30 241	95.20 159	95.30 255	89.83 180	93.38 342	96.85 226	86.26 300	88.59 275	95.80 213	84.88 148	98.15 228	75.67 355	95.93 170	97.63 181

c3_l		91.38 228	90.89 216	92.88 275	95.58 233	86.30 280	94.68 296	96.84 227	88.17 256	88.83 271	94.23 291	85.65 140	97.47 311	89.36 207	84.63 323	94.89 303

pm-mvs1		90.72 259	89.65 272	93.96 227	94.29 307	89.63 184	97.79 88	96.82 228	89.07 223	86.12 322	95.48 234	78.61 264	97.78 284	86.97 260	81.67 348	94.46 324

test_vis1_n		92.37 187	92.26 172	92.72 280	94.75 288	82.64 325	98.02 56	96.80 229	91.18 163	97.77 35	97.93 86	58.02 372	98.29 217	97.63 17	98.21 115	97.23 202

CMPMVS	62.92 21	85.62 326	84.92 323	87.74 348	89.14 372	73.12 378	94.17 317	96.80 229	73.98 377	73.65 376	94.93 252	66.36 354	97.61 299	83.95 302	91.28 247	92.48 357
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 269	89.77 266	91.78 305	94.33 304	84.72 307	95.55 269	96.73 231	86.17 302	86.36 319	95.28 240	71.28 325	97.80 282	84.09 299	98.14 119	92.81 351

Effi-MVS+-dtu		93.08 159	93.21 135	92.68 283	96.02 219	83.25 323	97.14 163	96.72 232	93.85 70	91.20 211	93.44 320	83.08 178	98.30 216	91.69 166	95.73 175	96.50 220

TSAR-MVS + GP.		96.69 46	96.49 49	97.27 55	98.31 81	93.39 60	96.79 188	96.72 232	94.17 60	97.44 41	97.66 108	92.76 26	99.33 113	96.86 35	97.76 129	99.08 81

1112_ss		93.37 145	92.42 168	96.21 108	97.05 156	90.99 141	96.31 233	96.72 232	86.87 290	89.83 241	96.69 162	86.51 127	99.14 133	88.12 230	93.67 209	98.50 128

PVSNet	86.66 18	92.24 196	91.74 188	93.73 240	97.77 118	83.69 320	92.88 351	96.72 232	87.91 263	93.00 164	94.86 256	78.51 265	99.05 149	86.53 263	97.45 137	98.47 133

miper_lstm_enhance		90.50 266	90.06 256	91.83 301	95.33 252	83.74 317	93.86 328	96.70 236	87.56 276	87.79 293	93.81 307	83.45 171	96.92 335	87.39 250	84.62 324	94.82 308

v148		90.99 248	90.38 237	92.81 278	93.83 319	85.80 287	96.78 190	96.68 237	89.45 214	88.75 273	93.93 303	82.96 184	97.82 281	87.83 235	83.25 340	94.80 311

ACMH+	87.92 14	90.20 273	89.18 280	93.25 261	96.48 194	86.45 277	96.99 173	96.68 237	88.83 235	84.79 333	96.22 193	70.16 333	98.53 196	84.42 296	88.04 285	94.77 316

CANet_DTU		94.37 106	93.65 115	96.55 76	96.46 195	92.13 96	96.21 241	96.67 239	94.38 56	93.53 152	97.03 145	79.34 248	99.71 44	90.76 181	98.45 107	97.82 175

cl____		90.96 251	90.32 239	92.89 274	95.37 246	86.21 283	94.46 305	96.64 240	87.82 265	88.15 288	94.18 294	82.98 182	97.54 304	87.70 240	85.59 306	94.92 301

HY-MVS	89.66 9	93.87 127	92.95 141	96.63 72	97.10 150	92.49 83	95.64 267	96.64 240	89.05 225	93.00 164	95.79 216	85.77 139	99.45 103	89.16 217	94.35 197	97.96 165

Test_1112_low_res		92.84 173	91.84 184	95.85 127	97.04 157	89.97 177	95.53 271	96.64 240	85.38 312	89.65 247	95.18 243	85.86 137	99.10 137	87.70 240	93.58 214	98.49 130

DIV-MVS_self_test		90.97 250	90.33 238	92.88 275	95.36 247	86.19 284	94.46 305	96.63 243	87.82 265	88.18 287	94.23 291	82.99 181	97.53 306	87.72 237	85.57 307	94.93 299

Fast-Effi-MVS+-dtu		92.29 193	91.99 179	93.21 264	95.27 256	85.52 291	97.03 167	96.63 243	92.09 136	89.11 265	95.14 245	80.33 232	98.08 241	87.54 248	94.74 194	96.03 237

UnsupCasMVSNet_bld		82.13 339	79.46 344	90.14 333	88.00 377	82.47 328	90.89 368	96.62 245	78.94 368	75.61 372	84.40 381	56.63 375	96.31 343	77.30 348	66.77 384	91.63 364

cl22		91.21 238	90.56 233	93.14 266	96.09 217	86.80 268	94.41 307	96.58 246	87.80 267	88.58 276	93.99 301	80.85 223	97.62 298	89.87 195	86.93 295	94.99 294

RRT_MVS		93.10 157	92.83 146	93.93 232	94.76 286	88.04 241	98.47 22	96.55 247	93.44 86	90.01 236	97.04 144	80.64 225	97.93 270	94.33 112	90.21 266	95.83 243

jason		94.84 99	94.39 104	96.18 110	95.52 236	90.93 145	96.09 246	96.52 248	89.28 218	96.01 96	97.32 127	84.70 150	98.77 172	95.15 92	98.91 89	98.85 106
jason: jason.
tt0805		91.09 243	90.07 255	94.16 215	95.61 231	88.31 230	97.56 117	96.51 249	89.56 209	89.17 263	95.64 225	67.08 353	98.38 210	91.07 177	88.44 283	95.80 246

AUN-MVS		91.76 210	90.75 225	94.81 184	97.00 160	88.57 223	96.65 203	96.49 250	89.63 207	92.15 181	96.12 198	78.66 263	98.50 198	90.83 179	79.18 359	97.36 194

hse-mvs2		93.45 143	92.99 139	94.81 184	97.02 158	88.59 222	96.69 199	96.47 251	95.19 20	96.74 62	96.16 197	83.67 166	98.48 201	95.85 67	79.13 360	97.35 196

EG-PatchMatch MVS		87.02 312	85.44 316	91.76 307	92.67 346	85.00 302	96.08 247	96.45 252	83.41 341	79.52 364	93.49 318	57.10 374	97.72 289	79.34 339	90.87 258	92.56 355

KD-MVS_self_test		85.95 323	84.95 322	88.96 343	89.55 371	79.11 364	95.13 288	96.42 253	85.91 305	84.07 342	90.48 354	70.03 335	94.82 363	80.04 331	72.94 374	92.94 349

pmmvs6		87.81 304	86.19 311	92.69 282	91.32 359	86.30 280	97.34 142	96.41 254	80.59 362	84.05 343	94.37 281	67.37 348	97.67 292	84.75 291	79.51 358	94.09 336

PMMVS		92.86 171	92.34 169	94.42 203	94.92 277	86.73 271	94.53 301	96.38 255	84.78 324	94.27 134	95.12 247	83.13 177	98.40 205	91.47 170	96.49 162	98.12 158

RPSCF		90.75 257	90.86 218	90.42 330	96.84 166	76.29 371	95.61 268	96.34 256	83.89 333	91.38 199	97.87 91	76.45 287	98.78 169	87.16 257	92.23 227	96.20 227

MSDG		91.42 226	90.24 245	94.96 175	97.15 147	88.91 215	93.69 334	96.32 257	85.72 308	86.93 314	96.47 181	80.24 233	98.98 155	80.57 328	95.05 188	96.98 206

OurMVSNet-221017-0		90.51 265	90.19 250	91.44 313	93.41 333	81.25 338	96.98 174	96.28 258	91.68 146	86.55 318	96.30 189	74.20 309	97.98 256	88.96 220	87.40 293	95.09 290

MVP-Stereo		90.74 258	90.08 252	92.71 281	93.19 338	88.20 236	95.86 257	96.27 259	86.07 303	84.86 332	94.76 261	77.84 277	97.75 287	83.88 303	98.01 121	92.17 362
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 94	94.56 95	96.29 102	96.34 201	91.21 131	95.83 258	96.27 259	88.93 231	96.22 87	96.88 153	86.20 133	98.85 164	95.27 89	99.05 81	98.82 109

BH-untuned		92.94 167	92.62 158	93.92 233	97.22 141	86.16 285	96.40 225	96.25 261	90.06 198	89.79 242	96.17 196	83.19 174	98.35 212	87.19 255	97.27 144	97.24 201

CL-MVSNet_self_test		86.31 318	85.15 320	89.80 337	88.83 374	81.74 336	93.93 325	96.22 262	86.67 292	85.03 330	90.80 353	78.09 273	94.50 364	74.92 358	71.86 376	93.15 347

IS-MVSNet		94.90 96	94.52 99	96.05 116	97.67 122	90.56 159	98.44 23	96.22 262	93.21 94	93.99 141	97.74 102	85.55 141	98.45 202	89.98 191	97.86 124	99.14 74

FA-MVS(test-final)		93.52 141	92.92 142	95.31 156	96.77 173	88.54 225	94.82 293	96.21 264	89.61 208	94.20 136	95.25 241	83.24 173	99.14 133	90.01 190	96.16 166	98.25 149

GA-MVS		91.38 228	90.31 240	94.59 193	94.65 293	87.62 252	94.34 310	96.19 265	90.73 175	90.35 221	93.83 304	71.84 321	97.96 264	87.22 254	93.61 212	98.21 152

IterMVS-SCA-FT		90.31 268	89.81 264	91.82 302	95.52 236	84.20 312	94.30 313	96.15 266	90.61 185	87.39 302	94.27 288	75.80 295	96.44 341	87.34 251	86.88 299	94.82 308

IterMVS		90.15 275	89.67 270	91.61 309	95.48 238	83.72 318	94.33 311	96.12 267	89.99 199	87.31 305	94.15 296	75.78 297	96.27 344	86.97 260	86.89 298	94.83 306
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 176	91.51 198	96.52 78	98.77 53	90.99 141	97.38 139	96.08 268	82.38 347	89.29 259	97.87 91	83.77 164	99.69 50	81.37 325	96.69 158	98.89 103

pmmvs4		90.93 252	89.85 262	94.17 214	93.34 335	90.79 151	94.60 298	96.02 269	84.62 325	87.45 299	95.15 244	81.88 208	97.45 313	87.70 240	87.87 287	94.27 333

ppachtmachnet_test		88.35 299	87.29 298	91.53 310	92.45 352	83.57 321	93.75 331	95.97 270	84.28 328	85.32 329	94.18 294	79.00 260	96.93 334	75.71 354	84.99 320	94.10 334

Anonymous20240521		86.42 316	85.44 316	89.34 341	90.33 364	79.79 356	96.73 193	95.92 271	83.71 337	83.25 347	91.36 350	63.92 363	96.01 345	78.39 343	85.36 311	92.22 360

ITE_SJBPF				92.43 286	95.34 249	85.37 296		95.92 271	91.47 150	87.75 295	96.39 186	71.00 327	97.96 264	82.36 316	89.86 269	93.97 337

test_fmvs2		89.77 283	89.93 259	89.31 342	93.68 324	76.37 370	97.64 108	95.90 273	89.84 204	91.49 197	96.26 192	58.77 371	97.10 327	94.65 106	91.13 250	94.46 324

USDC		88.94 290	87.83 295	92.27 291	94.66 292	84.96 303	93.86 328	95.90 273	87.34 281	83.40 346	95.56 229	67.43 347	98.19 225	82.64 315	89.67 271	93.66 340

COLMAP_ROB	87.81 15	90.40 267	89.28 278	93.79 238	97.95 107	87.13 263	96.92 178	95.89 275	82.83 344	86.88 316	97.18 136	73.77 313	99.29 119	78.44 342	93.62 211	94.95 295
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 130	93.08 137	96.02 119	97.88 113	89.96 178	97.72 96	95.85 276	92.43 125	95.86 100	98.44 42	68.42 343	99.39 109	96.31 47	94.85 189	98.71 116

VDDNet		93.05 161	92.07 175	96.02 119	96.84 166	90.39 166	98.08 51	95.85 276	86.22 301	95.79 103	98.46 40	67.59 346	99.19 126	94.92 97	94.85 189	98.47 133

Vis-MVSNet (Re-imp)		94.15 113	93.88 110	94.95 176	97.61 129	87.92 245	98.10 49	95.80 278	92.22 129	93.02 163	97.45 122	84.53 153	97.91 274	88.24 229	97.97 122	99.02 84

MM				98.23 11		95.03 25	98.07 52	95.76 279	97.78 1	97.52 38	98.80 20	88.09 100	99.86 8	99.44 1	99.37 56	99.80 1

KD-MVS_2432*1600		84.81 330	82.64 334	91.31 315	91.07 361	85.34 297	91.22 363	95.75 280	85.56 310	83.09 348	90.21 357	67.21 349	95.89 347	77.18 349	62.48 387	92.69 352

miper_refine_blended		84.81 330	82.64 334	91.31 315	91.07 361	85.34 297	91.22 363	95.75 280	85.56 310	83.09 348	90.21 357	67.21 349	95.89 347	77.18 349	62.48 387	92.69 352

FE-MVS		92.05 203	91.05 213	95.08 165	96.83 168	87.93 244	93.91 327	95.70 282	86.30 298	94.15 138	94.97 249	76.59 285	99.21 124	84.10 298	96.86 151	98.09 162

tpm cat1		88.36 298	87.21 301	91.81 303	95.13 267	80.55 347	92.58 355	95.70 282	74.97 376	87.45 299	91.96 344	78.01 276	98.17 227	80.39 330	88.74 280	96.72 216

our_test_3		88.78 294	87.98 294	91.20 318	92.45 352	82.53 327	93.61 338	95.69 284	85.77 307	84.88 331	93.71 309	79.99 238	96.78 339	79.47 336	86.24 300	94.28 332

BH-w/o		92.14 201	91.75 186	93.31 259	96.99 161	85.73 288	95.67 264	95.69 284	88.73 241	89.26 261	94.82 259	82.97 183	98.07 245	85.26 286	96.32 165	96.13 233

CR-MVSNet		90.82 255	89.77 266	93.95 228	94.45 300	87.19 260	90.23 371	95.68 286	86.89 289	92.40 173	92.36 337	80.91 220	97.05 329	81.09 327	93.95 207	97.60 186

Patchmtry		88.64 296	87.25 299	92.78 279	94.09 311	86.64 272	89.82 374	95.68 286	80.81 359	87.63 297	92.36 337	80.91 220	97.03 330	78.86 340	85.12 316	94.67 319

iter_conf_final		93.60 136	93.11 136	95.04 167	97.13 148	91.30 126	97.92 73	95.65 288	92.98 110	91.60 193	96.64 166	79.28 250	98.13 230	95.34 88	91.49 241	95.70 256

BH-RMVSNet		92.72 178	91.97 180	94.97 174	97.16 145	87.99 243	96.15 244	95.60 289	90.62 184	91.87 188	97.15 139	78.41 267	98.57 194	83.16 306	97.60 131	98.36 145

PVSNet_0	82.17 19	85.46 327	83.64 330	90.92 321	95.27 256	79.49 360	90.55 369	95.60 289	83.76 336	83.00 350	89.95 359	71.09 326	97.97 259	82.75 313	60.79 389	95.31 278

SCA		91.84 208	91.18 211	93.83 235	95.59 232	84.95 304	94.72 295	95.58 291	90.82 171	92.25 179	93.69 310	75.80 295	98.10 237	86.20 269	95.98 168	98.45 135

AllTest		90.23 271	88.98 282	93.98 224	97.94 108	86.64 272	96.51 216	95.54 292	85.38 312	85.49 326	96.77 156	70.28 331	99.15 131	80.02 332	92.87 216	96.15 231

TestCases				93.98 224	97.94 108	86.64 272		95.54 292	85.38 312	85.49 326	96.77 156	70.28 331	99.15 131	80.02 332	92.87 216	96.15 231

iter_conf05		93.18 155	92.63 156	94.83 181	96.64 179	90.69 155	97.60 113	95.53 294	92.52 123	91.58 194	96.64 166	76.35 290	98.13 230	95.43 86	91.42 244	95.68 258

mvsmamba		93.83 129	93.46 125	94.93 179	94.88 281	90.85 148	98.55 14	95.49 295	94.24 59	91.29 207	96.97 147	83.04 180	98.14 229	95.56 84	91.17 249	95.78 248

tpmvs		89.83 282	89.15 281	91.89 299	94.92 277	80.30 351	93.11 347	95.46 296	86.28 299	88.08 289	92.65 328	80.44 229	98.52 197	81.47 321	89.92 268	96.84 212

pmmvs5		89.86 281	88.87 284	92.82 277	92.86 342	86.23 282	96.26 236	95.39 297	84.24 329	87.12 306	94.51 272	74.27 308	97.36 320	87.61 247	87.57 289	94.86 304

PatchmatchNet		91.91 206	91.35 200	93.59 248	95.38 244	84.11 313	93.15 346	95.39 297	89.54 210	92.10 184	93.68 312	82.82 187	98.13 230	84.81 290	95.32 182	98.52 125
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 225	91.32 202	91.79 304	95.15 265	79.20 363	93.42 341	95.37 299	88.55 246	93.49 153	93.67 313	82.49 195	98.27 218	90.41 185	89.34 274	97.90 168

Anonymous20231206		87.09 311	86.14 312	89.93 336	91.22 360	80.35 349	96.11 245	95.35 300	83.57 339	84.16 338	93.02 325	73.54 315	95.61 355	72.16 369	86.14 302	93.84 339

MIMVSNet1		84.93 329	83.05 331	90.56 328	89.56 370	84.84 306	95.40 275	95.35 300	83.91 332	80.38 360	92.21 341	57.23 373	93.34 376	70.69 375	82.75 346	93.50 342

TDRefinement		86.53 314	84.76 325	91.85 300	82.23 387	84.25 310	96.38 227	95.35 300	84.97 321	84.09 341	94.94 251	65.76 360	98.34 215	84.60 294	74.52 370	92.97 348

TR-MVS		91.48 224	90.59 231	94.16 215	96.40 198	87.33 254	95.67 264	95.34 303	87.68 273	91.46 198	95.52 232	76.77 284	98.35 212	82.85 310	93.61 212	96.79 214

EPNet_dtu		91.71 211	91.28 205	92.99 270	93.76 321	83.71 319	96.69 199	95.28 304	93.15 100	87.02 310	95.95 205	83.37 172	97.38 319	79.46 337	96.84 152	97.88 170
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 308	85.79 314	91.78 305	94.80 285	87.28 255	95.49 272	95.28 304	84.09 331	83.85 345	91.82 345	62.95 366	94.17 368	78.48 341	85.34 312	93.91 338

MDTV_nov1_ep13			90.76 224		95.22 260	80.33 350	93.03 349	95.28 304	88.14 258	92.84 170	93.83 304	81.34 214	98.08 241	82.86 309	94.34 198

LF4IMVS		87.94 302	87.25 299	89.98 335	92.38 354	80.05 355	94.38 308	95.25 307	87.59 275	84.34 335	94.74 263	64.31 362	97.66 294	84.83 289	87.45 290	92.23 359

TransMVSNet (Re)		88.94 290	87.56 296	93.08 268	94.35 303	88.45 229	97.73 93	95.23 308	87.47 277	84.26 337	95.29 238	79.86 241	97.33 321	79.44 338	74.44 371	93.45 344

test20.03		86.14 321	85.40 318	88.35 344	90.12 365	80.06 354	95.90 256	95.20 309	88.59 242	81.29 355	93.62 315	71.43 324	92.65 378	71.26 373	81.17 351	92.34 358

new-patchmatchnet		83.18 336	81.87 339	87.11 351	86.88 379	75.99 372	93.70 332	95.18 310	85.02 320	77.30 371	88.40 369	65.99 358	93.88 373	74.19 363	70.18 378	91.47 368

MDA-MVSNet_test_wron		85.87 324	84.23 328	90.80 325	92.38 354	82.57 326	93.17 344	95.15 311	82.15 348	67.65 380	92.33 340	78.20 269	95.51 358	77.33 346	79.74 355	94.31 331

YYNet1		85.87 324	84.23 328	90.78 326	92.38 354	82.46 329	93.17 344	95.14 312	82.12 349	67.69 379	92.36 337	78.16 272	95.50 359	77.31 347	79.73 356	94.39 327

Baseline_NR-MVSNet		91.20 239	90.62 229	92.95 272	93.83 319	88.03 242	97.01 172	95.12 313	88.42 250	89.70 244	95.13 246	83.47 169	97.44 314	89.66 201	83.24 341	93.37 345

thres200		92.23 197	91.39 199	94.75 191	97.61 129	89.03 213	96.60 211	95.09 314	92.08 137	93.28 159	94.00 300	78.39 268	99.04 152	81.26 326	94.18 199	96.19 228

ADS-MVSNet		89.89 279	88.68 286	93.53 251	95.86 221	84.89 305	90.93 366	95.07 315	83.23 342	91.28 208	91.81 346	79.01 258	97.85 277	79.52 334	91.39 245	97.84 172

pmmvs-eth3d		86.22 319	84.45 326	91.53 310	88.34 376	87.25 257	94.47 303	95.01 316	83.47 340	79.51 365	89.61 362	69.75 337	95.71 352	83.13 307	76.73 367	91.64 363

Anonymous202405211		92.07 202	90.83 222	95.76 129	98.19 93	88.75 218	97.58 115	95.00 317	86.00 304	93.64 148	97.45 122	66.24 357	99.53 89	90.68 184	92.71 221	99.01 87

MDA-MVSNet-bldmvs		85.00 328	82.95 333	91.17 319	93.13 340	83.33 322	94.56 300	95.00 317	84.57 326	65.13 384	92.65 328	70.45 330	95.85 349	73.57 365	77.49 363	94.33 329

ambc				86.56 354	83.60 384	70.00 381	85.69 383	94.97 319		80.60 359	88.45 368	37.42 387	96.84 337	82.69 314	75.44 369	92.86 350

testgi		87.97 301	87.21 301	90.24 332	92.86 342	80.76 342	96.67 202	94.97 319	91.74 144	85.52 325	95.83 211	62.66 367	94.47 366	76.25 352	88.36 284	95.48 262

dp		88.90 292	88.26 292	90.81 323	94.58 297	76.62 369	92.85 352	94.93 321	85.12 318	90.07 235	93.07 324	75.81 294	98.12 235	80.53 329	87.42 292	97.71 178

test_fmvs3		83.21 335	83.02 332	83.78 358	86.77 380	68.34 384	96.76 191	94.91 322	86.49 295	84.14 340	89.48 363	36.04 388	91.73 380	91.86 160	80.77 353	91.26 370

test_0402		86.46 315	84.79 324	91.45 312	95.02 271	85.55 290	96.29 235	94.89 323	80.90 356	82.21 352	93.97 302	68.21 344	97.29 323	62.98 381	88.68 281	91.51 366

tfpn200view9		92.38 186	91.52 196	94.95 176	97.85 114	89.29 203	97.41 132	94.88 324	92.19 133	93.27 160	94.46 277	78.17 270	99.08 142	81.40 322	94.08 203	96.48 221

CVMVSNet		91.23 237	91.75 186	89.67 338	95.77 226	74.69 373	96.44 217	94.88 324	85.81 306	92.18 180	97.64 112	79.07 253	95.58 357	88.06 231	95.86 172	98.74 113

thres400		92.42 184	91.52 196	95.12 164	97.85 114	89.29 203	97.41 132	94.88 324	92.19 133	93.27 160	94.46 277	78.17 270	99.08 142	81.40 322	94.08 203	96.98 206

EPNet		95.20 87	94.56 95	97.14 61	92.80 344	92.68 78	97.85 82	94.87 327	96.64 3	92.46 172	97.80 99	86.23 130	99.65 56	93.72 125	98.62 98	99.10 80
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
SixPastTwentyTwo		89.15 288	88.54 288	90.98 320	93.49 330	80.28 352	96.70 197	94.70 328	90.78 172	84.15 339	95.57 228	71.78 322	97.71 290	84.63 293	85.07 317	94.94 297

thres100view900		92.43 183	91.58 193	94.98 173	97.92 110	89.37 199	97.71 98	94.66 329	92.20 131	93.31 158	94.90 254	78.06 274	99.08 142	81.40 322	94.08 203	96.48 221

thres600view7		92.49 182	91.60 192	95.18 160	97.91 111	89.47 193	97.65 104	94.66 329	92.18 135	93.33 157	94.91 253	78.06 274	99.10 137	81.61 319	94.06 206	96.98 206

PatchT		88.87 293	87.42 297	93.22 263	94.08 312	85.10 301	89.51 375	94.64 331	81.92 350	92.36 176	88.15 372	80.05 237	97.01 332	72.43 368	93.65 210	97.54 189

baseline1		92.82 174	91.90 182	95.55 145	97.20 143	90.77 152	97.19 158	94.58 332	92.20 131	92.36 176	96.34 188	84.16 160	98.21 222	89.20 215	83.90 336	97.68 180

Gipuma		67.86 354	65.41 356	75.18 371	92.66 347	73.45 376	66.50 390	94.52 333	53.33 389	57.80 390	66.07 390	30.81 390	89.20 384	48.15 390	78.88 362	62.90 390
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
CostFormer		91.18 242	90.70 227	92.62 284	94.84 283	81.76 335	94.09 320	94.43 334	84.15 330	92.72 171	93.77 308	79.43 247	98.20 223	90.70 183	92.18 230	97.90 168

tpm2		89.96 277	89.21 279	92.23 293	94.91 279	81.25 338	93.78 330	94.42 335	80.62 361	91.56 195	93.44 320	76.44 288	97.94 267	85.60 281	92.08 234	97.49 190

JIA-IIPM		88.26 300	87.04 304	91.91 298	93.52 328	81.42 337	89.38 376	94.38 336	80.84 358	90.93 213	80.74 383	79.22 251	97.92 271	82.76 312	91.62 238	96.38 224

dmvs_re		90.21 272	89.50 274	92.35 287	95.47 241	85.15 299	95.70 263	94.37 337	90.94 170	88.42 278	93.57 316	74.63 305	95.67 354	82.80 311	89.57 272	96.22 226

Patchmatch-test		89.42 286	87.99 293	93.70 243	95.27 256	85.11 300	88.98 377	94.37 337	81.11 355	87.10 308	93.69 310	82.28 199	97.50 309	74.37 361	94.76 192	98.48 132

LCM-MVSNet		72.55 348	69.39 352	82.03 360	70.81 397	65.42 389	90.12 373	94.36 339	55.02 388	65.88 382	81.72 382	24.16 396	89.96 381	74.32 362	68.10 382	90.71 373

ADS-MVSNet2		89.45 285	88.59 287	92.03 296	95.86 221	82.26 331	90.93 366	94.32 340	83.23 342	91.28 208	91.81 346	79.01 258	95.99 346	79.52 334	91.39 245	97.84 172

EU-MVSNet		88.72 295	88.90 283	88.20 346	93.15 339	74.21 374	96.63 208	94.22 341	85.18 316	87.32 304	95.97 203	76.16 291	94.98 362	85.27 285	86.17 301	95.41 268

MVS_0304		97.04 25	96.73 39	97.96 23	97.60 131	94.36 34	98.01 57	94.09 342	97.33 2	96.29 84	98.79 22	89.73 80	99.86 8	99.36 2	99.42 46	99.67 13

MIMVSNet		88.50 297	86.76 307	93.72 242	94.84 283	87.77 250	91.39 361	94.05 343	86.41 297	87.99 291	92.59 331	63.27 364	95.82 351	77.44 345	92.84 218	97.57 188

OpenMVS_ROB	81.14 20	84.42 332	82.28 338	90.83 322	90.06 366	84.05 315	95.73 262	94.04 344	73.89 378	80.17 363	91.53 349	59.15 370	97.64 295	66.92 379	89.05 276	90.80 372

TinyColmap		86.82 313	85.35 319	91.21 317	94.91 279	82.99 324	93.94 324	94.02 345	83.58 338	81.56 354	94.68 265	62.34 368	98.13 230	75.78 353	87.35 294	92.52 356

IB-MVS	87.33 17	89.91 278	88.28 291	94.79 188	95.26 259	87.70 251	95.12 289	93.95 346	89.35 217	87.03 309	92.49 332	70.74 329	99.19 126	89.18 216	81.37 350	97.49 190
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
Syy-MVS		87.13 310	87.02 305	87.47 349	95.16 263	73.21 377	95.00 290	93.93 347	88.55 246	86.96 311	91.99 342	75.90 292	94.00 370	61.59 383	94.11 200	95.20 286

myMVS_eth3d		87.18 309	86.38 309	89.58 339	95.16 263	79.53 358	95.00 290	93.93 347	88.55 246	86.96 311	91.99 342	56.23 376	94.00 370	75.47 357	94.11 200	95.20 286

test_f		80.57 341	79.62 343	83.41 359	83.38 385	67.80 386	93.57 339	93.72 349	80.80 360	77.91 370	87.63 375	33.40 389	92.08 379	87.14 258	79.04 361	90.34 374

LCM-MVSNet-Re		92.50 180	92.52 164	92.44 285	96.82 170	81.89 334	96.92 178	93.71 350	92.41 126	84.30 336	94.60 269	85.08 146	97.03 330	91.51 168	97.36 139	98.40 141

bld_raw_dy_0_64		92.37 187	91.69 189	94.39 204	94.28 308	89.73 183	97.71 98	93.65 351	92.78 118	90.46 218	96.67 164	75.88 293	97.97 259	92.92 144	90.89 257	95.48 262

tpm		90.25 270	89.74 269	91.76 307	93.92 315	79.73 357	93.98 321	93.54 352	88.28 253	91.99 186	93.25 323	77.51 280	97.44 314	87.30 253	87.94 286	98.12 158

ET-MVSNet_ETH3D		91.49 223	90.11 251	95.63 139	96.40 198	91.57 116	95.34 277	93.48 353	90.60 187	75.58 373	95.49 233	80.08 236	96.79 338	94.25 113	89.76 270	98.52 125

LFMVS		93.60 136	92.63 156	96.52 78	98.13 98	91.27 128	97.94 71	93.39 354	90.57 188	96.29 84	98.31 58	69.00 339	99.16 130	94.18 114	95.87 171	99.12 78

Patchmatch-RL test		87.38 307	86.24 310	90.81 323	88.74 375	78.40 367	88.12 381	93.17 355	87.11 286	82.17 353	89.29 364	81.95 206	95.60 356	88.64 226	77.02 364	98.41 140

test-LLR		91.42 226	91.19 210	92.12 294	94.59 295	80.66 344	94.29 314	92.98 356	91.11 166	90.76 214	92.37 334	79.02 256	98.07 245	88.81 222	96.74 155	97.63 181

test-mter		90.19 274	89.54 273	92.12 294	94.59 295	80.66 344	94.29 314	92.98 356	87.68 273	90.76 214	92.37 334	67.67 345	98.07 245	88.81 222	96.74 155	97.63 181

testing3		87.67 305	86.88 306	90.05 334	96.14 213	80.71 343	97.10 165	92.85 358	90.15 196	87.54 298	94.55 271	55.70 377	94.10 369	73.77 364	94.10 202	95.35 275

test_method		66.11 355	64.89 357	69.79 373	72.62 395	35.23 404	65.19 391	92.83 359	20.35 394	65.20 383	88.08 373	43.14 385	82.70 391	73.12 367	63.46 386	91.45 369

test0.0.03 1		89.37 287	88.70 285	91.41 314	92.47 351	85.63 289	95.22 286	92.70 360	91.11 166	86.91 315	93.65 314	79.02 256	93.19 377	78.00 344	89.18 275	95.41 268

new_pmnet		82.89 337	81.12 342	88.18 347	89.63 369	80.18 353	91.77 360	92.57 361	76.79 375	75.56 374	88.23 371	61.22 369	94.48 365	71.43 371	82.92 344	89.87 375

mvsany_test1		93.93 125	93.98 108	93.78 239	94.94 276	86.80 268	94.62 297	92.55 362	88.77 240	96.85 58	98.49 36	88.98 86	98.08 241	95.03 94	95.62 178	96.46 223

thisisatest0515		92.29 193	91.30 204	95.25 158	96.60 182	88.90 216	94.36 309	92.32 363	87.92 262	93.43 155	94.57 270	77.28 281	99.00 153	89.42 206	95.86 172	97.86 171

thisisatest0530		93.03 162	92.21 173	95.49 149	97.07 151	89.11 212	97.49 128	92.19 364	90.16 195	94.09 139	96.41 184	76.43 289	99.05 149	90.38 186	95.68 177	98.31 147

tttt0517		92.96 165	92.33 170	94.87 180	97.11 149	87.16 262	97.97 67	92.09 365	90.63 183	93.88 145	97.01 146	76.50 286	99.06 148	90.29 189	95.45 180	98.38 143

K. test v3		87.64 306	86.75 308	90.32 331	93.02 341	79.48 361	96.61 209	92.08 366	90.66 181	80.25 362	94.09 297	67.21 349	96.65 340	85.96 277	80.83 352	94.83 306

TESTMET0.1,1		90.06 276	89.42 275	91.97 297	94.41 302	80.62 346	94.29 314	91.97 367	87.28 283	90.44 219	92.47 333	68.79 340	97.67 292	88.50 228	96.60 160	97.61 185

PM-MVS		83.48 334	81.86 340	88.31 345	87.83 378	77.59 368	93.43 340	91.75 368	86.91 288	80.63 358	89.91 360	44.42 384	95.84 350	85.17 288	76.73 367	91.50 367

baseline2		91.63 214	90.86 218	93.94 230	94.33 304	86.32 279	95.92 255	91.64 369	89.37 216	86.94 313	94.69 264	81.62 212	98.69 181	88.64 226	94.57 196	96.81 213

APD_test1		79.31 343	77.70 346	84.14 357	89.11 373	69.07 383	92.36 359	91.50 370	69.07 381	73.87 375	92.63 330	39.93 386	94.32 367	70.54 376	80.25 354	89.02 377

FPMVS		71.27 349	69.85 351	75.50 370	74.64 392	59.03 393	91.30 362	91.50 370	58.80 385	57.92 389	88.28 370	29.98 392	85.53 390	53.43 388	82.84 345	81.95 383

door								91.13 372

door-mid								91.06 373

EGC-MVSNET		68.77 353	63.01 358	86.07 356	92.49 350	82.24 332	93.96 323	90.96 374	0.71 399	2.62 400	90.89 352	53.66 378	93.46 374	57.25 386	84.55 326	82.51 382

mvsany_test3		83.59 333	82.44 337	87.03 352	83.80 383	73.82 375	93.70 332	90.92 375	86.42 296	82.51 351	90.26 356	46.76 383	95.71 352	90.82 180	76.76 366	91.57 365

pmmvs3		79.97 342	77.50 347	87.39 350	82.80 386	79.38 362	92.70 354	90.75 376	70.69 380	78.66 367	87.47 377	51.34 381	93.40 375	73.39 366	69.65 379	89.38 376

DSMNet-mixed		86.34 317	86.12 313	87.00 353	89.88 368	70.43 379	94.93 292	90.08 377	77.97 372	85.42 328	92.78 327	74.44 307	93.96 372	74.43 360	95.14 184	96.62 217

MVS-HIRNet		82.47 338	81.21 341	86.26 355	95.38 244	69.21 382	88.96 378	89.49 378	66.28 382	80.79 357	74.08 387	68.48 342	97.39 318	71.93 370	95.47 179	92.18 361

WB-MVS		76.77 345	76.63 348	77.18 365	85.32 381	56.82 395	94.53 301	89.39 379	82.66 346	71.35 377	89.18 365	75.03 302	88.88 385	35.42 393	66.79 383	85.84 379

test1111		93.19 152	92.82 147	94.30 210	97.58 134	84.56 308	98.21 43	89.02 380	93.53 82	94.58 128	98.21 65	72.69 317	99.05 149	93.06 138	98.48 105	99.28 63

SSC-MVS		76.05 346	75.83 349	76.72 369	84.77 382	56.22 396	94.32 312	88.96 381	81.82 352	70.52 378	88.91 366	74.79 304	88.71 386	33.69 394	64.71 385	85.23 380

ECVR-MVS		93.19 152	92.73 153	94.57 198	97.66 124	85.41 293	98.21 43	88.23 382	93.43 87	94.70 126	98.21 65	72.57 318	99.07 146	93.05 139	98.49 103	99.25 66

EPMVS		90.70 260	89.81 264	93.37 257	94.73 290	84.21 311	93.67 335	88.02 383	89.50 212	92.38 175	93.49 318	77.82 278	97.78 284	86.03 275	92.68 222	98.11 161

ANet_high		63.94 356	59.58 359	77.02 366	61.24 399	66.06 387	85.66 384	87.93 384	78.53 370	42.94 392	71.04 389	25.42 395	80.71 392	52.60 389	30.83 393	84.28 381

PMMVS2		70.19 350	66.92 353	80.01 361	76.35 391	65.67 388	86.22 382	87.58 385	64.83 384	62.38 385	80.29 384	26.78 394	88.49 388	63.79 380	54.07 390	85.88 378

lessismore_v0				90.45 329	91.96 357	79.09 365		87.19 386		80.32 361	94.39 279	66.31 356	97.55 303	84.00 301	76.84 365	94.70 318

PMVS	53.92 22	58.58 357	55.40 360	68.12 374	51.00 400	48.64 398	78.86 387	87.10 387	46.77 390	35.84 396	74.28 386	8.76 400	86.34 389	42.07 391	73.91 372	69.38 388
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		86.16 320	85.06 321	89.46 340	93.47 332	80.46 348	96.41 221	86.61 388	85.22 315	79.15 366	88.64 367	52.41 380	97.06 328	93.08 137	90.57 260	90.87 371

testf1		69.31 351	66.76 354	76.94 367	78.61 389	61.93 391	88.27 379	86.11 389	55.62 386	59.69 386	85.31 379	20.19 398	89.32 382	57.62 384	69.44 380	79.58 384

APD_test2		69.31 351	66.76 354	76.94 367	78.61 389	61.93 391	88.27 379	86.11 389	55.62 386	59.69 386	85.31 379	20.19 398	89.32 382	57.62 384	69.44 380	79.58 384

gg-mvs-nofinetune		87.82 303	85.61 315	94.44 201	94.46 299	89.27 206	91.21 365	84.61 391	80.88 357	89.89 240	74.98 385	71.50 323	97.53 306	85.75 280	97.21 146	96.51 219

dmvs_testset		81.38 340	82.60 336	77.73 364	91.74 358	51.49 397	93.03 349	84.21 392	89.07 223	78.28 369	91.25 351	76.97 283	88.53 387	56.57 387	82.24 347	93.16 346

GG-mvs-BLEND				93.62 246	93.69 323	89.20 208	92.39 358	83.33 393		87.98 292	89.84 361	71.00 327	96.87 336	82.08 318	95.40 181	94.80 311

MTMP							97.86 79	82.03 394

DeepMVS_CX				74.68 372	90.84 363	64.34 390		81.61 395	65.34 383	67.47 381	88.01 374	48.60 382	80.13 393	62.33 382	73.68 373	79.58 384

E-PMN		53.28 358	52.56 362	55.43 376	74.43 393	47.13 399	83.63 386	76.30 396	42.23 391	42.59 393	62.22 392	28.57 393	74.40 394	31.53 395	31.51 392	44.78 391

test2506		91.60 215	90.78 223	94.04 221	97.66 124	83.81 316	98.27 33	75.53 397	93.43 87	95.23 117	98.21 65	67.21 349	99.07 146	93.01 142	98.49 103	99.25 66

EMVS		52.08 360	51.31 363	54.39 377	72.62 395	45.39 401	83.84 385	75.51 398	41.13 392	40.77 394	59.65 393	30.08 391	73.60 395	28.31 396	29.90 394	44.18 392

test_vis3_rt		72.73 347	70.55 350	79.27 362	80.02 388	68.13 385	93.92 326	74.30 399	76.90 374	58.99 388	73.58 388	20.29 397	95.37 360	84.16 297	72.80 375	74.31 387

MVE	50.73 23	53.25 359	48.81 364	66.58 375	65.34 398	57.50 394	72.49 389	70.94 400	40.15 393	39.28 395	63.51 391	6.89 402	73.48 396	38.29 392	42.38 391	68.76 389
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 361	53.82 361	46.29 378	33.73 401	45.30 402	78.32 388	67.24 401	18.02 395	50.93 391	87.05 378	52.99 379	53.11 397	70.76 374	25.29 395	40.46 393

N_pmnet		78.73 344	78.71 345	78.79 363	92.80 344	46.50 400	94.14 318	43.71 402	78.61 369	80.83 356	91.66 348	74.94 303	96.36 342	67.24 378	84.45 328	93.50 342

wuyk23d		25.11 362	24.57 366	26.74 379	73.98 394	39.89 403	57.88 392	9.80 403	12.27 396	10.39 397	6.97 399	7.03 401	36.44 398	25.43 397	17.39 396	3.89 396

testmvs		13.36 364	16.33 367	4.48 381	5.04 402	2.26 406	93.18 343	3.28 404	2.70 397	8.24 398	21.66 395	2.29 404	2.19 399	7.58 398	2.96 397	9.00 395

test123		13.04 365	15.66 368	5.18 380	4.51 403	3.45 405	92.50 357	1.81 405	2.50 398	7.58 399	20.15 396	3.67 403	2.18 400	7.13 399	1.07 398	9.90 394

test_blank		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet_test		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

DCPMVS		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

pcd_1.5k_mvsjas		7.39 367	9.85 370	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	88.65 93	0.00 401	0.00 400	0.00 399	0.00 397

sosnet-low-res		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

sosnet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uncertanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

Regformer		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

n2								0.00 406

nn								0.00 406

ab-mvs-re		8.06 366	10.74 369	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	96.69 162	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

uanet		0.00 368	0.00 371	0.00 382	0.00 404	0.00 407	0.00 393	0.00 406	0.00 400	0.00 401	0.00 400	0.00 405	0.00 401	0.00 400	0.00 399	0.00 397

WAC-MVS						79.53 358								75.56 356

PC_three_1452									90.77 173	98.89 12	98.28 63	96.24 1	98.35 212	95.76 71	99.58 21	99.59 22

eth-test2					0.00 404

eth-test					0.00 404

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 64	96.04 2	99.24 122	95.36 87	99.59 17	99.56 29

test_0728_THIRD									94.78 39	98.73 16	98.87 15	95.87 4	99.84 23	97.45 24	99.72 2	99.77 2

GSMVS																98.45 135

test_part2					99.28 25	95.74 8				98.10 27

sam_mvs1												82.76 188				98.45 135

sam_mvs												81.94 207

test_post1							92.81 353				16.58 398	80.53 227	97.68 291	86.20 269

test_post											17.58 397	81.76 209	98.08 241

patchmatchnet-post											90.45 355	82.65 192	98.10 237

gm-plane-assit					93.22 337	78.89 366			84.82 323		93.52 317		98.64 186	87.72 237

test9_res														94.81 101	99.38 53	99.45 46

agg_prior2														93.94 119	99.38 53	99.50 40

test_prior4						93.66 55	96.42 220

test_prior2							96.35 229		92.80 117	96.03 93	97.59 116	92.01 41		95.01 95	99.38 53

旧先验2							95.94 254		81.66 353	97.34 46			98.82 166	92.26 147

新几何2							95.79 260

原ACMM2							95.67 264

testdata2													99.67 54	85.96 277

segment_acmp												92.89 25

testdata1							95.26 285		93.10 103

plane_prior7					96.21 205	89.98 176

plane_prior6					96.10 216	90.00 172						81.32 215

plane_prior4											96.64 166

plane_prior3						90.00 172			94.46 52	91.34 201

plane_prior2							97.74 91		94.85 32

plane_prior1					96.14 213

plane_prior						89.99 174	97.24 151		94.06 63						92.16 231

HQP5-MVS						89.33 201

HQP-NCC					95.86 221		96.65 203		93.55 78	90.14 224

ACMP_Plane					95.86 221		96.65 203		93.55 78	90.14 224

BP-MVS														92.13 153

HQP4-MVS										90.14 224			98.50 198			95.78 248

HQP2-MVS												80.95 218

NP-MVS					95.99 220	89.81 181					95.87 208

MDTV_nov1_ep13_2view						70.35 380	93.10 348		83.88 334	93.55 150		82.47 196		86.25 268		98.38 143

ACMMP++_ref															90.30 265

ACMMP++															91.02 253

Test By Simon												88.73 92

High-resolution multi-view benchmark