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 11	97.89 3	96.53 81	98.41 74	91.73 111	98.01 59	99.02 1	96.37 4	99.30 1	98.92 10	92.39 37	99.79 33	99.16 5	99.46 42	98.08 172

PGM-MVS		96.81 42	96.53 50	97.65 42	99.35 20	93.53 60	97.65 106	98.98 2	92.22 133	97.14 53	98.44 44	91.17 62	99.85 18	94.35 118	99.46 42	99.57 26

MVS_111021_HR		96.68 51	96.58 49	96.99 70	98.46 70	92.31 93	96.20 246	98.90 3	94.30 62	95.86 107	97.74 104	92.33 38	99.38 113	96.04 69	99.42 49	99.28 65

test_fmvsmconf_n		97.49 12	97.56 9	97.29 55	97.44 144	92.37 90	97.91 76	98.88 4	95.83 8	98.92 12	99.05 5	91.45 53	99.80 30	99.12 6	99.46 42	99.69 12

ACMMP		96.27 63	95.93 66	97.28 57	99.24 28	92.62 82	98.25 36	98.81 5	92.99 108	94.56 136	98.39 48	88.96 90	99.85 18	94.57 117	97.63 136	99.36 60
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 64	96.19 63	96.39 99	98.23 91	91.35 131	96.24 244	98.79 6	93.99 69	95.80 109	97.65 111	89.92 80	99.24 124	95.87 73	99.20 74	98.58 127

patch_mono-2		96.83 41	97.44 13	95.01 177	99.05 39	85.39 305	96.98 178	98.77 7	94.70 45	97.99 32	98.66 27	93.61 19	99.91 1	97.67 18	99.50 36	99.72 11

fmvsm_s_conf0.5_n		96.85 39	97.13 16	96.04 124	98.07 105	90.28 173	97.97 69	98.76 8	94.93 30	98.84 16	99.06 4	88.80 93	99.65 58	99.06 7	98.63 103	98.18 161

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 52	98.21 92	92.75 78	97.83 85	98.73 9	95.04 28	99.30 1	98.84 20	93.34 22	99.78 35	99.32 3	99.13 80	99.50 40

fmvsm_s_conf0.5_n_a		96.75 46	96.93 29	96.20 116	97.64 129	90.72 161	98.00 61	98.73 9	94.55 50	98.91 13	99.08 3	88.22 106	99.63 67	98.91 9	98.37 115	98.25 156

FC-MVSNet-test		93.94 134	93.57 127	95.04 175	95.48 251	91.45 128	98.12 50	98.71 11	93.37 92	90.23 236	96.70 166	87.66 115	97.85 288	91.49 174	90.39 277	95.83 257

UniMVSNet (Re)		93.31 156	92.55 168	95.61 149	95.39 256	93.34 66	97.39 138	98.71 11	93.14 104	90.10 245	94.83 263	87.71 114	98.03 262	91.67 172	83.99 344	95.46 277

fmvsm_l_conf0.5_n_a		97.63 8	97.76 5	97.26 59	98.25 86	92.59 84	97.81 89	98.68 13	94.93 30	99.24 3	98.87 15	93.52 20	99.79 33	99.32 3	99.21 72	99.40 54

FIs		94.09 127	93.70 123	95.27 165	95.70 241	92.03 103	98.10 51	98.68 13	93.36 94	90.39 233	96.70 166	87.63 118	97.94 279	92.25 154	90.50 276	95.84 256

WR-MVS_H		92.00 210	91.35 206	93.95 239	95.09 282	89.47 198	98.04 57	98.68 13	91.46 157	88.34 292	94.68 270	85.86 146	97.56 313	85.77 287	84.24 342	94.82 319

VPA-MVSNet		93.24 158	92.48 173	95.51 155	95.70 241	92.39 89	97.86 80	98.66 16	92.30 132	92.09 195	95.37 241	80.49 236	98.40 216	93.95 124	85.86 316	95.75 266

UniMVSNet_NR-MVSNet		93.37 154	92.67 163	95.47 160	95.34 262	92.83 76	97.17 164	98.58 17	92.98 113	90.13 241	95.80 218	88.37 105	97.85 288	91.71 169	83.93 345	95.73 268

CSCG		96.05 69	95.91 68	96.46 93	99.24 28	90.47 168	98.30 29	98.57 18	89.01 236	93.97 150	97.57 119	92.62 33	99.76 38	94.66 112	99.27 65	99.15 75

MSLP-MVS++		96.94 33	97.06 19	96.59 79	98.72 55	91.86 108	97.67 103	98.49 19	94.66 48	97.24 50	98.41 47	92.31 40	98.94 165	96.61 43	99.46 42	98.96 94

HyFIR lowres test		93.66 145	92.92 151	95.87 132	98.24 87	89.88 185	94.58 311	98.49 19	85.06 330	93.78 153	95.78 222	82.86 194	98.67 194	91.77 167	95.71 182	99.07 85

CHOSEN 1792x2688		94.15 122	93.51 133	96.06 122	98.27 83	89.38 203	95.18 297	98.48 21	85.60 320	93.76 154	97.11 145	83.15 185	99.61 69	91.33 177	98.72 100	99.19 71

PHI-MVS		96.77 44	96.46 56	97.71 40	98.40 75	94.07 48	98.21 43	98.45 22	89.86 209	97.11 55	98.01 83	92.52 35	99.69 52	96.03 70	99.53 30	99.36 60

fmvsm_s_conf0.1_n		96.58 54	96.77 40	96.01 128	96.67 187	90.25 174	97.91 76	98.38 23	94.48 54	98.84 16	99.14 1	88.06 108	99.62 68	98.82 11	98.60 105	98.15 165

PVSNet_BlendedMVS		94.06 128	93.92 118	94.47 208	98.27 83	89.46 200	96.73 197	98.36 24	90.17 202	94.36 139	95.24 247	88.02 109	99.58 77	93.44 135	90.72 272	94.36 339

PVSNet_Blended		94.87 106	94.56 103	95.81 135	98.27 83	89.46 200	95.47 283	98.36 24	88.84 244	94.36 139	96.09 207	88.02 109	99.58 77	93.44 135	98.18 123	98.40 148

3Dnovator	91.36 5	95.19 96	94.44 111	97.44 49	96.56 195	93.36 65	98.65 11	98.36 24	94.12 65	89.25 274	98.06 77	82.20 210	99.77 37	93.41 137	99.32 62	99.18 72

FOURS1					99.55 1	93.34 66	99.29 1	98.35 27	94.98 29	98.49 23

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 161	98.35 27	95.16 22	98.71 20	98.80 22	95.05 10	99.89 3	96.70 41	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 58	96.47 53	96.16 118	95.48 251	90.69 162	97.91 76	98.33 29	94.07 66	98.93 9	99.14 1	87.44 124	99.61 69	98.63 13	98.32 117	98.18 161

HFP-MVS		97.14 23	96.92 30	97.83 26	99.42 7	94.12 46	98.52 16	98.32 30	93.21 97	97.18 51	98.29 63	92.08 42	99.83 26	95.63 86	99.59 20	99.54 33

ACMMPR		97.07 26	96.84 33	97.79 30	99.44 6	93.88 52	98.52 16	98.31 31	93.21 97	97.15 52	98.33 57	91.35 57	99.86 8	95.63 86	99.59 20	99.62 18

test_fmvsmvis_n_1920		96.70 47	96.84 33	96.31 104	96.62 188	91.73 111	97.98 63	98.30 32	96.19 5	96.10 98	98.95 8	89.42 83	99.76 38	98.90 10	99.08 84	97.43 204

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 32	94.76 43	98.30 26	98.90 12	93.77 17	99.68 54	97.93 14	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 28	98.29 34	94.92 32	98.99 7	98.92 10	95.08 8

MSP-MVS		97.59 10	97.54 10	97.73 37	99.40 11	93.77 56	98.53 15	98.29 34	95.55 13	98.56 22	97.81 99	93.90 15	99.65 58	96.62 42	99.21 72	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 36	94.78 41	98.93 9	98.87 15	96.04 2	99.86 8	97.45 26	99.58 24	99.59 22

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 43	98.28 36					99.86 8	97.52 22	99.67 6	99.75 6

CP-MVS		97.02 29	96.81 37	97.64 44	99.33 21	93.54 59	98.80 8	98.28 36	92.99 108	96.45 85	98.30 62	91.90 45	99.85 18	95.61 88	99.68 4	99.54 33

test_fmvsmconf0.1_n		97.09 24	97.06 19	97.19 64	95.67 243	92.21 96	97.95 72	98.27 39	95.78 10	98.40 25	99.00 6	89.99 78	99.78 35	99.06 7	99.41 52	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 39	95.13 23	99.19 4	98.89 13	95.54 5	99.85 18	97.52 22	99.66 11	99.56 29

test_241102_TWO								98.27 39	95.13 23	98.93 9	98.89 13	94.99 11	99.85 18	97.52 22	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 39	95.09 26	99.19 4	98.81 21	95.54 5	99.65 58

SF-MVS		97.39 15	97.13 16	98.17 15	99.02 42	95.28 19	98.23 40	98.27 39	92.37 129	98.27 27	98.65 29	93.33 23	99.72 45	96.49 48	99.52 31	99.51 37

SteuartSystems-ACMMP		97.62 9	97.53 11	97.87 24	98.39 77	94.25 40	98.43 23	98.27 39	95.34 17	98.11 28	98.56 31	94.53 12	99.71 46	96.57 45	99.62 18	99.65 15
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 45	95.13 23	98.48 24	98.87 15	95.16 7

PVSNet_Blended_VisFu		95.27 91	94.91 94	96.38 100	98.20 93	90.86 153	97.27 152	98.25 45	90.21 201	94.18 144	97.27 134	87.48 123	99.73 42	93.53 132	97.77 134	98.55 129

region2R		97.07 26	96.84 33	97.77 33	99.46 2	93.79 54	98.52 16	98.24 47	93.19 100	97.14 53	98.34 54	91.59 52	99.87 7	95.46 93	99.59 20	99.64 16

PS-CasMVS		91.55 229	90.84 228	93.69 254	94.96 287	88.28 238	97.84 84	98.24 47	91.46 157	88.04 302	95.80 218	79.67 252	97.48 321	87.02 267	84.54 339	95.31 289

DU-MVS		92.90 176	92.04 183	95.49 157	94.95 288	92.83 76	97.16 165	98.24 47	93.02 107	90.13 241	95.71 225	83.47 178	97.85 288	91.71 169	83.93 345	95.78 261

9.14			96.75 41		98.93 47		97.73 96	98.23 50	91.28 165	97.88 35	98.44 44	93.00 26	99.65 58	95.76 79	99.47 41

D2MVS		91.30 244	90.95 222	92.35 297	94.71 304	85.52 301	96.18 247	98.21 51	88.89 242	86.60 329	93.82 313	79.92 248	97.95 278	89.29 218	90.95 269	93.56 352

SDMVSNet		94.17 120	93.61 126	95.86 133	98.09 101	91.37 130	97.35 142	98.20 52	93.18 101	91.79 201	97.28 132	79.13 260	98.93 166	94.61 115	92.84 233	97.28 212

XVS		97.18 21	96.96 28	97.81 28	99.38 14	94.03 50	98.59 12	98.20 52	94.85 34	96.59 76	98.29 63	91.70 48	99.80 30	95.66 81	99.40 53	99.62 18

X-MVStestdata		91.71 218	89.67 279	97.81 28	99.38 14	94.03 50	98.59 12	98.20 52	94.85 34	96.59 76	32.69 408	91.70 48	99.80 30	95.66 81	99.40 53	99.62 18

ACMMP_NAP		97.20 20	96.86 31	98.23 11	99.09 34	95.16 22	97.60 115	98.19 55	92.82 118	97.93 34	98.74 26	91.60 51	99.86 8	96.26 54	99.52 31	99.67 13

CP-MVSNet		91.89 214	91.24 213	93.82 246	95.05 284	88.57 228	97.82 87	98.19 55	91.70 150	88.21 298	95.76 223	81.96 214	97.52 319	87.86 242	84.65 334	95.37 285

ZNCC-MVS		96.96 31	96.67 45	97.85 25	99.37 16	94.12 46	98.49 20	98.18 57	92.64 124	96.39 87	98.18 70	91.61 50	99.88 4	95.59 91	99.55 27	99.57 26

SMA-MVS		97.35 16	97.03 24	98.30 8	99.06 38	95.42 10	97.94 73	98.18 57	90.57 196	98.85 15	98.94 9	93.33 23	99.83 26	96.72 40	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		91.20 248	90.44 244	93.48 263	94.49 312	87.91 252	97.76 92	98.18 57	91.29 162	87.78 306	95.74 224	80.35 239	97.33 332	85.46 291	82.96 355	95.19 300

DELS-MVS		96.61 52	96.38 59	97.30 54	97.79 120	93.19 69	95.96 257	98.18 57	95.23 19	95.87 106	97.65 111	91.45 53	99.70 51	95.87 73	99.44 48	99.00 92
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		89.70 297	88.40 302	93.60 257	95.15 278	90.10 176	97.56 118	98.16 61	87.28 294	86.16 333	94.63 273	77.57 287	98.05 258	74.48 371	84.59 337	92.65 365

VNet		95.89 77	95.45 78	97.21 62	98.07 105	92.94 75	97.50 124	98.15 62	93.87 73	97.52 40	97.61 117	85.29 152	99.53 91	95.81 78	95.27 190	99.16 73

DeepPCF-MVS	93.97 1	96.61 52	97.09 18	95.15 169	98.09 101	86.63 282	96.00 255	98.15 62	95.43 14	97.95 33	98.56 31	93.40 21	99.36 114	96.77 38	99.48 40	99.45 47

SD-MVS		97.41 14	97.53 11	97.06 68	98.57 69	94.46 33	97.92 75	98.14 64	94.82 38	99.01 6	98.55 33	94.18 14	97.41 328	96.94 34	99.64 14	99.32 62
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 39	96.52 51	97.82 27	99.36 18	94.14 45	98.29 30	98.13 65	92.72 121	96.70 68	98.06 77	91.35 57	99.86 8	94.83 106	99.28 64	99.47 46

UA-Net		95.95 75	95.53 75	97.20 63	97.67 125	92.98 74	97.65 106	98.13 65	94.81 39	96.61 74	98.35 51	88.87 91	99.51 96	90.36 194	97.35 146	99.11 81

QAPM		93.45 152	92.27 178	96.98 71	96.77 182	92.62 82	98.39 25	98.12 67	84.50 338	88.27 296	97.77 102	82.39 207	99.81 29	85.40 292	98.81 97	98.51 134

Vis-MVSNet		95.23 93	94.81 95	96.51 86	97.18 151	91.58 121	98.26 35	98.12 67	94.38 60	94.90 129	98.15 72	82.28 208	98.92 167	91.45 176	98.58 107	99.01 89
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 178	91.68 196	96.40 97	95.34 262	92.73 80	98.27 33	98.12 67	84.86 333	85.78 335	97.75 103	78.89 269	99.74 41	87.50 257	98.65 102	96.73 229

TranMVSNet+NR-MVSNet		92.50 187	91.63 197	95.14 170	94.76 300	92.07 101	97.53 122	98.11 70	92.90 116	89.56 262	96.12 202	83.16 184	97.60 311	89.30 217	83.20 354	95.75 266

CPTT-MVS		95.57 85	95.19 88	96.70 73	99.27 26	91.48 125	98.33 27	98.11 70	87.79 279	95.17 126	98.03 80	87.09 130	99.61 69	93.51 133	99.42 49	99.02 86

APD-MVS		96.95 32	96.60 47	98.01 19	99.03 41	94.93 27	97.72 99	98.10 72	91.50 155	98.01 31	98.32 59	92.33 38	99.58 77	94.85 105	99.51 34	99.53 36
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 37	96.60 47	97.64 44	99.40 11	93.44 61	98.50 19	98.09 73	93.27 96	95.95 105	98.33 57	91.04 64	99.88 4	95.20 96	99.57 26	99.60 21

ZD-MVS					99.05 39	94.59 31		98.08 74	89.22 229	97.03 58	98.10 73	92.52 35	99.65 58	94.58 116	99.31 63

MTGPA								98.08 74

MTAPA		97.08 25	96.78 39	97.97 22	99.37 16	94.42 35	97.24 155	98.08 74	95.07 27	96.11 97	98.59 30	90.88 68	99.90 2	96.18 65	99.50 36	99.58 25

CNVR-MVS		97.68 6	97.44 13	98.37 7	98.90 50	95.86 6	97.27 152	98.08 74	95.81 9	97.87 36	98.31 60	94.26 13	99.68 54	97.02 33	99.49 39	99.57 26

DP-MVS Recon		95.68 81	95.12 91	97.37 51	99.19 31	94.19 42	97.03 171	98.08 74	88.35 262	95.09 128	97.65 111	89.97 79	99.48 101	92.08 161	98.59 106	98.44 145

SR-MVS		97.01 30	96.86 31	97.47 48	99.09 34	93.27 68	97.98 63	98.07 79	93.75 76	97.45 42	98.48 41	91.43 55	99.59 74	96.22 57	99.27 65	99.54 33

MCST-MVS		97.18 21	96.84 33	98.20 14	99.30 24	95.35 15	97.12 168	98.07 79	93.54 85	96.08 99	97.69 106	93.86 16	99.71 46	96.50 47	99.39 55	99.55 32

NR-MVSNet		92.34 195	91.27 212	95.53 154	94.95 288	93.05 72	97.39 138	98.07 79	92.65 123	84.46 346	95.71 225	85.00 156	97.77 297	89.71 206	83.52 351	95.78 261

MP-MVS-pluss		96.70 47	96.27 61	97.98 21	99.23 30	94.71 29	96.96 180	98.06 82	90.67 187	95.55 118	98.78 25	91.07 63	99.86 8	96.58 44	99.55 27	99.38 58
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 42	96.71 44	97.12 66	99.01 45	92.31 93	97.98 63	98.06 82	93.11 105	97.44 43	98.55 33	90.93 66	99.55 87	96.06 66	99.25 69	99.51 37

MP-MVS		96.77 44	96.45 57	97.72 38	99.39 13	93.80 53	98.41 24	98.06 82	93.37 92	95.54 120	98.34 54	90.59 72	99.88 4	94.83 106	99.54 29	99.49 42
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 55	96.27 61	97.22 61	99.32 22	92.74 79	98.74 9	98.06 82	90.57 196	96.77 65	98.35 51	90.21 75	99.53 91	94.80 109	99.63 17	99.38 58

HPM-MVS		96.69 49	96.45 57	97.40 50	99.36 18	93.11 71	98.87 6	98.06 82	91.17 170	96.40 86	97.99 84	90.99 65	99.58 77	95.61 88	99.61 19	99.49 42
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 112	93.80 121	96.64 74	97.07 157	91.97 105	96.32 236	98.06 82	88.94 240	94.50 137	96.78 161	84.60 160	99.27 122	91.90 162	96.02 173	98.68 123

DeepC-MVS	93.07 3	96.06 67	95.66 73	97.29 55	97.96 109	93.17 70	97.30 149	98.06 82	93.92 71	93.38 163	98.66 27	86.83 132	99.73 42	95.60 90	99.22 71	98.96 94
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 18	97.03 24	98.11 17	98.77 53	95.06 25	97.34 143	98.04 89	95.96 6	97.09 56	97.88 92	93.18 25	99.71 46	95.84 77	99.17 76	99.56 29

DeepC-MVS_fast	93.89 2	96.93 34	96.64 46	97.78 31	98.64 64	94.30 37	97.41 133	98.04 89	94.81 39	96.59 76	98.37 49	91.24 59	99.64 66	95.16 97	99.52 31	99.42 53
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 36	96.80 38	97.11 67	99.02 42	92.34 91	97.98 63	98.03 91	93.52 87	97.43 45	98.51 36	91.40 56	99.56 85	96.05 67	99.26 67	99.43 51

RE-MVS-def			96.72 43		99.02 42	92.34 91	97.98 63	98.03 91	93.52 87	97.43 45	98.51 36	90.71 70		96.05 67	99.26 67	99.43 51

RPMNet		88.98 302	87.05 316	94.77 195	94.45 314	87.19 267	90.23 383	98.03 91	77.87 385	92.40 180	87.55 388	80.17 243	99.51 96	68.84 389	93.95 220	97.60 198

save fliter					98.91 49	94.28 38	97.02 173	98.02 94	95.35 16

TEST9					98.70 56	94.19 42	96.41 225	98.02 94	88.17 266	96.03 100	97.56 121	92.74 30	99.59 74

train_agg		96.30 62	95.83 72	97.72 38	98.70 56	94.19 42	96.41 225	98.02 94	88.58 253	96.03 100	97.56 121	92.73 31	99.59 74	95.04 100	99.37 59	99.39 56

test_8					98.67 58	94.06 49	96.37 232	98.01 97	88.58 253	95.98 104	97.55 123	92.73 31	99.58 77

agg_prior					98.67 58	93.79 54		98.00 98		95.68 114			99.57 84

test_prior				97.23 60	98.67 58	92.99 73		98.00 98					99.41 109			99.29 63

WR-MVS		92.34 195	91.53 201	94.77 195	95.13 280	90.83 155	96.40 229	97.98 100	91.88 146	89.29 271	95.54 236	82.50 203	97.80 293	89.79 205	85.27 325	95.69 269

HPM-MVS++		97.34 17	96.97 27	98.47 5	99.08 36	96.16 4	97.55 121	97.97 101	95.59 11	96.61 74	97.89 90	92.57 34	99.84 23	95.95 72	99.51 34	99.40 54

CANet		96.39 59	96.02 65	97.50 47	97.62 132	93.38 63	97.02 173	97.96 102	95.42 15	94.86 130	97.81 99	87.38 126	99.82 28	96.88 36	99.20 74	99.29 63

114514_t		93.95 133	93.06 147	96.63 76	99.07 37	91.61 118	97.46 132	97.96 102	77.99 383	93.00 171	97.57 119	86.14 144	99.33 115	89.22 221	99.15 78	98.94 97

IU-MVS					99.42 7	95.39 11		97.94 104	90.40 200	98.94 8				97.41 29	99.66 11	99.74 8

MSC_two_6792asdad				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

No_MVS				98.86 1	98.67 58	96.94 1		97.93 105					99.86 8	97.68 16	99.67 6	99.77 2

Anonymous20231211		90.63 271	89.42 286	94.27 222	98.24 87	89.19 215	98.05 56	97.89 107	79.95 375	88.25 297	94.96 255	72.56 325	98.13 241	89.70 207	85.14 327	95.49 273

原ACMM1				96.38 100	98.59 66	91.09 145		97.89 107	87.41 290	95.22 125	97.68 107	90.25 74	99.54 89	87.95 241	99.12 82	98.49 137

CDPH-MVS		95.97 74	95.38 83	97.77 33	98.93 47	94.44 34	96.35 233	97.88 109	86.98 298	96.65 72	97.89 90	91.99 44	99.47 102	92.26 152	99.46 42	99.39 56

test11								97.88 109

EIA-MVS		95.53 86	95.47 77	95.71 143	97.06 160	89.63 189	97.82 87	97.87 111	93.57 81	93.92 151	95.04 253	90.61 71	98.95 164	94.62 114	98.68 101	98.54 130

CS-MVS		96.86 37	97.06 19	96.26 110	98.16 98	91.16 143	99.09 3	97.87 111	95.30 18	97.06 57	98.03 80	91.72 46	98.71 191	97.10 31	99.17 76	98.90 104

无先验							95.79 267	97.87 111	83.87 346				99.65 58	87.68 251		98.89 107

3Dnovator+	91.43 4	95.40 87	94.48 109	98.16 16	96.90 171	95.34 16	98.48 21	97.87 111	94.65 49	88.53 289	98.02 82	83.69 174	99.71 46	93.18 140	98.96 92	99.44 49

VPNet		92.23 203	91.31 209	94.99 178	95.56 247	90.96 148	97.22 160	97.86 115	92.96 114	90.96 225	96.62 178	75.06 307	98.20 234	91.90 162	83.65 350	95.80 259

test_vis1_n_1920		94.17 120	94.58 102	92.91 283	97.42 145	82.02 344	97.83 85	97.85 116	94.68 46	98.10 29	98.49 38	70.15 340	99.32 117	97.91 15	98.82 96	97.40 206

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 43	97.85 116	94.92 32	98.73 18	98.87 15	95.08 8	99.84 23	97.52 22	99.67 6	99.48 44
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 13	97.33 15	97.69 41	99.25 27	94.24 41	98.07 54	97.85 116	93.72 77	98.57 21	98.35 51	93.69 18	99.40 110	97.06 32	99.46 42	99.44 49
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 35	97.04 23	96.45 94	98.29 82	91.66 117	99.03 4	97.85 116	95.84 7	96.90 60	97.97 86	91.24 59	98.75 185	96.92 35	99.33 61	98.94 97

test_fmvsmconf0.01_n		96.15 66	95.85 70	97.03 69	92.66 360	91.83 109	97.97 69	97.84 120	95.57 12	97.53 39	99.00 6	84.20 168	99.76 38	98.82 11	99.08 84	99.48 44

AdaColmap		94.34 115	93.68 124	96.31 104	98.59 66	91.68 116	96.59 216	97.81 121	89.87 208	92.15 191	97.06 149	83.62 177	99.54 89	89.34 216	98.07 126	97.70 191

iter_conf05_11		96.17 65	96.16 64	96.21 114	97.48 143	90.74 160	98.14 49	97.80 122	92.80 119	97.34 48	97.29 131	88.54 100	99.10 141	96.40 50	99.64 14	98.80 115

mamv4		96.02 70	95.84 71	96.53 81	97.05 162	91.97 105	97.30 149	97.79 123	92.32 130	96.58 79	97.14 144	88.51 102	99.06 154	96.27 52	99.64 14	98.57 128

MVSMamba_pp		96.06 67	95.92 67	96.50 89	97.00 167	91.81 110	97.33 146	97.77 124	92.49 126	96.78 64	97.19 139	88.50 103	99.07 151	96.54 46	99.67 6	98.60 126

ETV-MVS		96.02 70	95.89 69	96.40 97	97.16 152	92.44 88	97.47 130	97.77 124	94.55 50	96.48 82	94.51 278	91.23 61	98.92 167	95.65 84	98.19 122	97.82 186

新几何1				97.32 53	98.60 65	93.59 58		97.75 126	81.58 366	95.75 111	97.85 96	90.04 77	99.67 56	86.50 273	99.13 80	98.69 122

旧先验1					98.38 78	93.38 63		97.75 126			98.09 75	92.30 41			99.01 89	99.16 73

EC-MVSNet		96.42 57	96.47 53	96.26 110	97.01 166	91.52 123	98.89 5	97.75 126	94.42 56	96.64 73	97.68 107	89.32 84	98.60 201	97.45 26	99.11 83	98.67 124

EI-MVSNet-Vis-set		96.51 55	96.47 53	96.63 76	98.24 87	91.20 138	96.89 184	97.73 129	94.74 44	96.49 81	98.49 38	90.88 68	99.58 77	96.44 49	98.32 117	99.13 77

PAPM_NR		95.01 98	94.59 101	96.26 110	98.89 51	90.68 163	97.24 155	97.73 129	91.80 147	92.93 176	96.62 178	89.13 87	99.14 137	89.21 222	97.78 133	98.97 93

Anonymous20240529		91.98 211	90.73 234	95.73 141	98.14 99	89.40 202	97.99 62	97.72 131	79.63 377	93.54 158	97.41 127	69.94 342	99.56 85	91.04 184	91.11 265	98.22 158

CHOSEN 280x420		93.12 164	92.72 162	94.34 216	96.71 186	87.27 263	90.29 382	97.72 131	86.61 305	91.34 212	95.29 243	84.29 167	98.41 215	93.25 139	98.94 93	97.35 209

EI-MVSNet-UG-set		96.34 61	96.30 60	96.47 91	98.20 93	90.93 151	96.86 186	97.72 131	94.67 47	96.16 96	98.46 42	90.43 73	99.58 77	96.23 56	97.96 129	98.90 104

LS3D		93.57 148	92.61 166	96.47 91	97.59 136	91.61 118	97.67 103	97.72 131	85.17 328	90.29 235	98.34 54	84.60 160	99.73 42	83.85 313	98.27 119	98.06 173

PAPR		94.18 119	93.42 140	96.48 90	97.64 129	91.42 129	95.55 278	97.71 135	88.99 237	92.34 186	95.82 217	89.19 85	99.11 140	86.14 279	97.38 144	98.90 104

UGNet		94.04 130	93.28 143	96.31 104	96.85 173	91.19 139	97.88 79	97.68 136	94.40 58	93.00 171	96.18 197	73.39 322	99.61 69	91.72 168	98.46 112	98.13 166
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				95.46 161	98.18 97	88.90 221		97.66 137	82.73 356	97.03 58	98.07 76	90.06 76	98.85 174	89.67 208	98.98 91	98.64 125

test12				97.65 42	98.46 70	94.26 39		97.66 137		95.52 121		90.89 67	99.46 103		99.25 69	99.22 70

DTE-MVSNet		90.56 272	89.75 277	93.01 279	93.95 327	87.25 264	97.64 110	97.65 139	90.74 182	87.12 318	95.68 228	79.97 247	97.00 344	83.33 314	81.66 361	94.78 326

TAPA-MVS	90.10 7	92.30 198	91.22 215	95.56 151	98.33 80	89.60 191	96.79 192	97.65 139	81.83 363	91.52 207	97.23 137	87.94 111	98.91 169	71.31 384	98.37 115	98.17 164
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 165	92.45 174	95.05 174	98.09 101	89.21 212	96.89 184	97.64 141	93.18 101	91.79 201	97.28 132	75.35 306	98.65 196	88.99 227	92.84 233	97.28 212

test_cas_vis1_n_1920		94.48 113	94.55 106	94.28 221	96.78 180	86.45 286	97.63 112	97.64 141	93.32 95	97.68 38	98.36 50	73.75 320	99.08 147	96.73 39	99.05 86	97.31 211

cdsmvs_eth3d_5k		23.24 378	30.99 380	0.00 396	0.00 419	0.00 421	0.00 407	97.63 143	0.00 414	0.00 415	96.88 158	84.38 164	0.00 415	0.00 414	0.00 413	0.00 411

DPM-MVS		95.69 80	94.92 93	98.01 19	98.08 104	95.71 9	95.27 293	97.62 144	90.43 199	95.55 118	97.07 148	91.72 46	99.50 99	89.62 210	98.94 93	98.82 113

sasdasda		96.02 70	95.45 78	97.75 35	97.59 136	95.15 23	98.28 31	97.60 145	94.52 52	96.27 91	96.12 202	87.65 116	99.18 130	96.20 62	94.82 198	98.91 101

canonicalmvs		96.02 70	95.45 78	97.75 35	97.59 136	95.15 23	98.28 31	97.60 145	94.52 52	96.27 91	96.12 202	87.65 116	99.18 130	96.20 62	94.82 198	98.91 101

test222					98.24 87	92.21 96	95.33 288	97.60 145	79.22 379	95.25 123	97.84 98	88.80 93			99.15 78	98.72 119

cascas		91.20 248	90.08 261	94.58 204	94.97 286	89.16 216	93.65 348	97.59 148	79.90 376	89.40 266	92.92 337	75.36 305	98.36 222	92.14 157	94.75 201	96.23 239

h-mvs33		94.15 122	93.52 132	96.04 124	97.81 119	90.22 175	97.62 114	97.58 149	95.19 20	96.74 66	97.45 124	83.67 175	99.61 69	95.85 75	79.73 368	98.29 155

MGCFI-Net		95.94 76	95.40 82	97.56 46	97.59 136	94.62 30	98.21 43	97.57 150	94.41 57	96.17 95	96.16 200	87.54 120	99.17 132	96.19 64	94.73 203	98.91 101

MVSFormer		95.37 88	95.16 89	95.99 129	96.34 213	91.21 136	98.22 41	97.57 150	91.42 159	96.22 93	97.32 129	86.20 142	97.92 282	94.07 121	99.05 86	98.85 110

test_djsdf		93.07 167	92.76 157	94.00 234	93.49 343	88.70 225	98.22 41	97.57 150	91.42 159	90.08 247	95.55 235	82.85 195	97.92 282	94.07 121	91.58 255	95.40 282

OMC-MVS		95.09 97	94.70 99	96.25 113	98.46 70	91.28 132	96.43 223	97.57 150	92.04 142	94.77 132	97.96 87	87.01 131	99.09 145	91.31 178	96.77 160	98.36 152

PS-MVSNAJss		93.74 143	93.51 133	94.44 210	93.91 329	89.28 210	97.75 93	97.56 154	92.50 125	89.94 249	96.54 181	88.65 96	98.18 237	93.83 130	90.90 270	95.86 253

casdiffmvs_mvg		95.81 79	95.57 74	96.51 86	96.87 172	91.49 124	97.50 124	97.56 154	93.99 69	95.13 127	97.92 89	87.89 112	98.78 180	95.97 71	97.33 147	99.26 67
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		92.42 191	91.89 190	94.03 233	93.33 349	88.50 232	97.73 96	97.53 156	92.00 144	88.85 281	96.50 183	75.62 304	98.11 245	93.88 128	91.56 256	95.48 274

mvs_tets		92.31 197	91.76 192	93.94 241	93.41 346	88.29 237	97.63 112	97.53 156	92.04 142	88.76 284	96.45 185	74.62 312	98.09 250	93.91 126	91.48 257	95.45 278

dcpmvs_2		96.37 60	97.05 22	94.31 219	98.96 46	84.11 323	97.56 118	97.51 158	93.92 71	97.43 45	98.52 35	92.75 29	99.32 117	97.32 30	99.50 36	99.51 37

HQP_MVS		93.78 142	93.43 138	94.82 188	96.21 217	89.99 180	97.74 94	97.51 158	94.85 34	91.34 212	96.64 171	81.32 224	98.60 201	93.02 146	92.23 242	95.86 253

plane_prior5								97.51 158					98.60 201	93.02 146	92.23 242	95.86 253

PS-MVSNAJ		95.37 88	95.33 85	95.49 157	97.35 146	90.66 164	95.31 290	97.48 161	93.85 74	96.51 80	95.70 227	88.65 96	99.65 58	94.80 109	98.27 119	96.17 243

API-MVS		94.84 107	94.49 108	95.90 131	97.90 115	92.00 104	97.80 90	97.48 161	89.19 230	94.81 131	96.71 164	88.84 92	99.17 132	88.91 229	98.76 99	96.53 232

MG-MVS		95.61 83	95.38 83	96.31 104	98.42 73	90.53 166	96.04 252	97.48 161	93.47 89	95.67 115	98.10 73	89.17 86	99.25 123	91.27 179	98.77 98	99.13 77

bld_raw_dy_0_64		94.33 116	93.90 119	95.62 148	97.64 129	90.95 149	95.17 298	97.47 164	82.34 359	91.28 219	96.84 160	89.10 88	99.04 159	96.27 52	99.00 90	96.85 225

MAR-MVS		94.22 118	93.46 135	96.51 86	98.00 108	92.19 99	97.67 103	97.47 164	88.13 269	93.00 171	95.84 215	84.86 158	99.51 96	87.99 240	98.17 124	97.83 185
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		92.98 171	92.53 170	94.32 217	96.12 227	89.20 213	95.28 291	97.47 164	92.66 122	89.90 250	95.62 231	80.58 234	98.40 216	92.73 150	92.40 240	95.38 284
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 242	90.22 257	94.68 198	94.86 296	87.86 253	97.23 159	97.46 167	87.99 270	89.90 250	96.92 156	66.35 365	98.23 231	90.30 195	90.99 268	97.96 176

nrg030		94.05 129	93.31 142	96.27 109	95.22 273	94.59 31	98.34 26	97.46 167	92.93 115	91.21 223	96.64 171	87.23 129	98.22 232	94.99 103	85.80 317	95.98 252

XVG-OURS		93.72 144	93.35 141	94.80 193	97.07 157	88.61 226	94.79 306	97.46 167	91.97 145	93.99 148	97.86 95	81.74 219	98.88 171	92.64 151	92.67 238	96.92 223

LPG-MVS_test		92.94 174	92.56 167	94.10 227	96.16 222	88.26 239	97.65 106	97.46 167	91.29 162	90.12 243	97.16 141	79.05 262	98.73 187	92.25 154	91.89 250	95.31 289

LGP-MVS_train				94.10 227	96.16 222	88.26 239		97.46 167	91.29 162	90.12 243	97.16 141	79.05 262	98.73 187	92.25 154	91.89 250	95.31 289

MVS		91.71 218	90.44 244	95.51 155	95.20 275	91.59 120	96.04 252	97.45 172	73.44 392	87.36 315	95.60 232	85.42 151	99.10 141	85.97 284	97.46 139	95.83 257

XVG-OURS-SEG-HR		93.86 138	93.55 128	94.81 190	97.06 160	88.53 231	95.28 291	97.45 172	91.68 151	94.08 147	97.68 107	82.41 206	98.90 170	93.84 129	92.47 239	96.98 219

baseline		95.58 84	95.42 81	96.08 120	96.78 180	90.41 171	97.16 165	97.45 172	93.69 80	95.65 116	97.85 96	87.29 127	98.68 193	95.66 81	97.25 151	99.13 77

ab-mvs		93.57 148	92.55 168	96.64 74	97.28 147	91.96 107	95.40 285	97.45 172	89.81 213	93.22 169	96.28 193	79.62 254	99.46 103	90.74 188	93.11 230	98.50 135

xiu_mvs_v2_base		95.32 90	95.29 86	95.40 162	97.22 148	90.50 167	95.44 284	97.44 176	93.70 79	96.46 84	96.18 197	88.59 99	99.53 91	94.79 111	97.81 132	96.17 243

1314		92.81 182	92.03 184	95.14 170	95.33 265	89.52 197	96.04 252	97.44 176	87.72 283	86.25 332	95.33 242	83.84 172	98.79 179	89.26 219	97.05 156	97.11 217

casdiffmvs		95.64 82	95.49 76	96.08 120	96.76 185	90.45 169	97.29 151	97.44 176	94.00 68	95.46 122	97.98 85	87.52 122	98.73 187	95.64 85	97.33 147	99.08 83
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		92.16 205	91.23 214	94.95 183	94.75 301	90.94 150	97.47 130	97.43 179	89.14 231	88.90 278	96.43 186	79.71 251	98.24 230	89.56 211	87.68 300	95.67 270

anonymousdsp		92.16 205	91.55 200	93.97 237	92.58 362	89.55 194	97.51 123	97.42 180	89.42 224	88.40 291	94.84 262	80.66 233	97.88 287	91.87 164	91.28 261	94.48 334

Effi-MVS+		94.93 103	94.45 110	96.36 102	96.61 189	91.47 126	96.41 225	97.41 181	91.02 176	94.50 137	95.92 211	87.53 121	98.78 180	93.89 127	96.81 159	98.84 112

HQP3-MVS								97.39 182							92.10 247

HQP-MVS		93.19 161	92.74 160	94.54 206	95.86 234	89.33 206	96.65 207	97.39 182	93.55 82	90.14 237	95.87 213	80.95 227	98.50 209	92.13 158	92.10 247	95.78 261

PLC	91.00 6	94.11 126	93.43 138	96.13 119	98.58 68	91.15 144	96.69 203	97.39 182	87.29 293	91.37 211	96.71 164	88.39 104	99.52 95	87.33 260	97.13 155	97.73 189
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 265	89.86 270	93.45 265	93.54 340	87.60 259	97.70 102	97.37 185	88.85 243	87.65 308	94.08 305	81.08 226	98.10 246	84.68 300	83.79 349	94.66 331

UnsupCasMVSNet_eth		85.99 335	84.45 339	90.62 339	89.97 380	82.40 341	93.62 349	97.37 185	89.86 209	78.59 380	92.37 346	65.25 372	95.35 373	82.27 327	70.75 389	94.10 345

ACMM	89.79 8	92.96 172	92.50 172	94.35 214	96.30 215	88.71 224	97.58 116	97.36 187	91.40 161	90.53 230	96.65 170	79.77 250	98.75 185	91.24 180	91.64 253	95.59 271
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 98	94.76 96	95.75 138	96.58 192	91.71 113	96.25 241	97.35 188	92.99 108	96.70 68	96.63 175	82.67 198	99.44 106	96.22 57	97.46 139	96.11 248

xiu_mvs_v1_base		95.01 98	94.76 96	95.75 138	96.58 192	91.71 113	96.25 241	97.35 188	92.99 108	96.70 68	96.63 175	82.67 198	99.44 106	96.22 57	97.46 139	96.11 248

xiu_mvs_v1_base_debi		95.01 98	94.76 96	95.75 138	96.58 192	91.71 113	96.25 241	97.35 188	92.99 108	96.70 68	96.63 175	82.67 198	99.44 106	96.22 57	97.46 139	96.11 248

diffmvs		95.25 92	95.13 90	95.63 146	96.43 209	89.34 205	95.99 256	97.35 188	92.83 117	96.31 88	97.37 128	86.44 137	98.67 194	96.26 54	97.19 153	98.87 109
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		94.71 111	94.02 115	96.79 72	97.71 124	92.05 102	96.59 216	97.35 188	90.61 193	94.64 134	96.93 153	86.41 138	99.39 111	91.20 181	94.71 204	98.94 97

F-COLMAP		93.58 147	92.98 149	95.37 163	98.40 75	88.98 219	97.18 163	97.29 193	87.75 282	90.49 231	97.10 146	85.21 153	99.50 99	86.70 270	96.72 163	97.63 193

XVG-ACMP-BASELINE		90.93 261	90.21 258	93.09 277	94.31 320	85.89 296	95.33 288	97.26 194	91.06 175	89.38 267	95.44 240	68.61 349	98.60 201	89.46 213	91.05 266	94.79 324

PCF-MVS	89.48 11	91.56 228	89.95 267	96.36 102	96.60 190	92.52 86	92.51 368	97.26 194	79.41 378	88.90 278	96.56 180	84.04 171	99.55 87	77.01 362	97.30 149	97.01 218
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 186	92.14 181	94.05 230	96.40 210	88.20 242	97.36 141	97.25 196	91.52 154	88.30 294	96.64 171	78.46 274	98.72 190	91.86 165	91.48 257	95.23 296
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 157	92.76 157	94.82 188	94.63 307	90.77 158	96.65 207	97.18 197	93.72 77	91.68 205	97.26 135	79.33 258	98.63 198	92.13 158	92.28 241	95.07 302
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 176	92.02 185	95.56 151	98.19 95	90.80 156	95.27 293	97.18 197	87.96 271	91.86 200	95.68 228	80.44 237	98.99 162	84.01 308	97.54 138	96.89 224

alignmvs		95.87 78	95.23 87	97.78 31	97.56 141	95.19 21	97.86 80	97.17 199	94.39 59	96.47 83	96.40 188	85.89 145	99.20 127	96.21 61	95.11 194	98.95 96

MVS_Test		94.89 105	94.62 100	95.68 144	96.83 176	89.55 194	96.70 201	97.17 199	91.17 170	95.60 117	96.11 206	87.87 113	98.76 184	93.01 148	97.17 154	98.72 119

Fast-Effi-MVS+		93.46 151	92.75 159	95.59 150	96.77 182	90.03 177	96.81 191	97.13 201	88.19 265	91.30 215	94.27 294	86.21 141	98.63 198	87.66 252	96.46 170	98.12 167

EI-MVSNet		93.03 169	92.88 153	93.48 263	95.77 239	86.98 272	96.44 221	97.12 202	90.66 189	91.30 215	97.64 114	86.56 134	98.05 258	89.91 201	90.55 274	95.41 279

MVSTER		93.20 160	92.81 156	94.37 213	96.56 195	89.59 192	97.06 170	97.12 202	91.24 166	91.30 215	95.96 209	82.02 213	98.05 258	93.48 134	90.55 274	95.47 276

test_yl		94.78 109	94.23 113	96.43 95	97.74 122	91.22 134	96.85 187	97.10 204	91.23 167	95.71 112	96.93 153	84.30 165	99.31 119	93.10 141	95.12 192	98.75 116

DCV-MVSNet		94.78 109	94.23 113	96.43 95	97.74 122	91.22 134	96.85 187	97.10 204	91.23 167	95.71 112	96.93 153	84.30 165	99.31 119	93.10 141	95.12 192	98.75 116

LTVRE_ROB	88.41 13	90.99 257	89.92 269	94.19 223	96.18 220	89.55 194	96.31 237	97.09 206	87.88 274	85.67 336	95.91 212	78.79 270	98.57 205	81.50 330	89.98 279	94.44 337
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		92.73 184	92.88 153	92.29 300	96.08 230	81.05 352	97.98 63	97.08 207	90.72 184	96.79 63	98.18 70	63.07 376	98.45 213	97.62 20	98.42 114	97.36 207

v10		91.04 255	90.23 255	93.49 262	94.12 323	88.16 245	97.32 147	97.08 207	88.26 264	88.29 295	94.22 299	82.17 211	97.97 270	86.45 274	84.12 343	94.33 340

v144192		91.06 254	90.28 251	93.39 266	93.66 338	87.23 266	96.83 190	97.07 209	87.43 289	89.69 257	94.28 293	81.48 222	98.00 265	87.18 264	84.92 333	94.93 310

v1192		91.07 253	90.23 255	93.58 259	93.70 335	87.82 255	96.73 197	97.07 209	87.77 280	89.58 260	94.32 291	80.90 231	97.97 270	86.52 272	85.48 320	94.95 306

v8		91.29 245	90.53 243	93.57 260	94.15 322	88.12 246	97.34 143	97.06 211	88.99 237	88.32 293	94.26 296	83.08 187	98.01 264	87.62 254	83.92 347	94.57 333

mvs_anonymous		93.82 140	93.74 122	94.06 229	96.44 208	85.41 303	95.81 265	97.05 212	89.85 211	90.09 246	96.36 190	87.44 124	97.75 298	93.97 123	96.69 164	99.02 86

IterMVS-LS		92.29 199	91.94 188	93.34 268	96.25 216	86.97 273	96.57 219	97.05 212	90.67 187	89.50 265	94.80 265	86.59 133	97.64 306	89.91 201	86.11 315	95.40 282
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 263	90.03 266	93.29 270	93.55 339	86.96 274	96.74 196	97.04 214	87.36 291	89.52 264	94.34 288	80.23 242	97.97 270	86.27 275	85.21 326	94.94 308

CDS-MVSNet		94.14 125	93.54 129	95.93 130	96.18 220	91.46 127	96.33 235	97.04 214	88.97 239	93.56 156	96.51 182	87.55 119	97.89 286	89.80 204	95.95 175	98.44 145
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 239	90.60 239	93.68 255	93.89 330	88.23 241	96.84 189	97.03 216	88.37 261	89.69 257	94.39 285	82.04 212	97.98 267	87.80 244	85.37 322	94.84 316

v1240		90.70 269	89.85 271	93.23 272	93.51 342	86.80 275	96.61 213	97.02 217	87.16 296	89.58 260	94.31 292	79.55 255	97.98 267	85.52 290	85.44 321	94.90 313

EPP-MVSNet		95.22 94	95.04 92	95.76 136	97.49 142	89.56 193	98.67 10	97.00 218	90.69 185	94.24 142	97.62 116	89.79 81	98.81 178	93.39 138	96.49 168	98.92 100

V42		91.58 227	90.87 224	93.73 250	94.05 326	88.50 232	97.32 147	96.97 219	88.80 249	89.71 255	94.33 289	82.54 202	98.05 258	89.01 226	85.07 329	94.64 332

test_fmvs1		93.21 159	93.53 130	92.25 302	96.55 197	81.20 351	97.40 137	96.96 220	90.68 186	96.80 62	98.04 79	69.25 345	98.40 216	97.58 21	98.50 108	97.16 216

FMVSNet2		91.31 243	90.08 261	94.99 178	96.51 202	92.21 96	97.41 133	96.95 221	88.82 246	88.62 286	94.75 267	73.87 316	97.42 327	85.20 295	88.55 294	95.35 286

ACMH	87.59 16	90.53 273	89.42 286	93.87 244	96.21 217	87.92 250	97.24 155	96.94 222	88.45 259	83.91 356	96.27 194	71.92 326	98.62 200	84.43 303	89.43 285	95.05 304
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 240	90.27 252	94.59 200	96.51 202	91.18 140	97.50 124	96.93 223	88.82 246	89.35 268	94.51 278	73.87 316	97.29 334	86.12 280	88.82 289	95.31 289

test1		91.35 240	90.27 252	94.59 200	96.51 202	91.18 140	97.50 124	96.93 223	88.82 246	89.35 268	94.51 278	73.87 316	97.29 334	86.12 280	88.82 289	95.31 289

FMVSNet3		91.78 216	90.69 237	95.03 176	96.53 200	92.27 95	97.02 173	96.93 223	89.79 214	89.35 268	94.65 272	77.01 290	97.47 322	86.12 280	88.82 289	95.35 286

FMVSNet1		89.88 292	88.31 303	94.59 200	95.41 255	91.18 140	97.50 124	96.93 223	86.62 304	87.41 313	94.51 278	65.94 369	97.29 334	83.04 317	87.43 303	95.31 289

GeoE		93.89 136	93.28 143	95.72 142	96.96 170	89.75 188	98.24 39	96.92 227	89.47 222	92.12 193	97.21 138	84.42 163	98.39 220	87.71 247	96.50 167	99.01 89

miper_enhance_ethall		91.54 230	91.01 221	93.15 275	95.35 261	87.07 271	93.97 334	96.90 228	86.79 302	89.17 275	93.43 332	86.55 135	97.64 306	89.97 200	86.93 307	94.74 328

eth_miper_zixun_eth		91.02 256	90.59 240	92.34 299	95.33 265	84.35 319	94.10 331	96.90 228	88.56 255	88.84 282	94.33 289	84.08 170	97.60 311	88.77 232	84.37 341	95.06 303

TAMVS		94.01 131	93.46 135	95.64 145	96.16 222	90.45 169	96.71 200	96.89 230	89.27 228	93.46 161	96.92 156	87.29 127	97.94 279	88.70 233	95.74 180	98.53 131

miper_ehance_all_eth		91.59 225	91.13 218	92.97 281	95.55 248	86.57 283	94.47 315	96.88 231	87.77 280	88.88 280	94.01 306	86.22 140	97.54 315	89.49 212	86.93 307	94.79 324

v2v482		91.59 225	90.85 227	93.80 247	93.87 331	88.17 244	96.94 181	96.88 231	89.54 219	89.53 263	94.90 259	81.70 220	98.02 263	89.25 220	85.04 331	95.20 297

CNLPA		94.28 117	93.53 130	96.52 83	98.38 78	92.55 85	96.59 216	96.88 231	90.13 205	91.91 197	97.24 136	85.21 153	99.09 145	87.64 253	97.83 131	97.92 178

PAPM		91.52 231	90.30 250	95.20 167	95.30 268	89.83 186	93.38 354	96.85 234	86.26 311	88.59 287	95.80 218	84.88 157	98.15 239	75.67 367	95.93 176	97.63 193

c3_l		91.38 237	90.89 223	92.88 285	95.58 246	86.30 289	94.68 308	96.84 235	88.17 266	88.83 283	94.23 297	85.65 149	97.47 322	89.36 215	84.63 335	94.89 314

pm-mvs1		90.72 268	89.65 281	93.96 238	94.29 321	89.63 189	97.79 91	96.82 236	89.07 233	86.12 334	95.48 239	78.61 272	97.78 295	86.97 268	81.67 360	94.46 335

test_vis1_n		92.37 194	92.26 179	92.72 290	94.75 301	82.64 336	98.02 58	96.80 237	91.18 169	97.77 37	97.93 88	58.02 384	98.29 228	97.63 19	98.21 121	97.23 215

CMPMVS	62.92 21	85.62 339	84.92 336	87.74 360	89.14 385	73.12 390	94.17 329	96.80 237	73.98 390	73.65 389	94.93 257	66.36 364	97.61 310	83.95 310	91.28 261	92.48 369
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 280	89.77 275	91.78 315	94.33 318	84.72 317	95.55 278	96.73 239	86.17 313	86.36 331	95.28 245	71.28 331	97.80 293	84.09 307	98.14 125	92.81 362

Effi-MVS+-dtu		93.08 166	93.21 145	92.68 293	96.02 231	83.25 333	97.14 167	96.72 240	93.85 74	91.20 224	93.44 329	83.08 187	98.30 227	91.69 171	95.73 181	96.50 234

TSAR-MVS + GP.		96.69 49	96.49 52	97.27 58	98.31 81	93.39 62	96.79 192	96.72 240	94.17 64	97.44 43	97.66 110	92.76 28	99.33 115	96.86 37	97.76 135	99.08 83

1112_ss		93.37 154	92.42 175	96.21 114	97.05 162	90.99 146	96.31 237	96.72 240	86.87 301	89.83 253	96.69 168	86.51 136	99.14 137	88.12 238	93.67 224	98.50 135

PVSNet	86.66 18	92.24 202	91.74 195	93.73 250	97.77 121	83.69 330	92.88 363	96.72 240	87.91 273	93.00 171	94.86 261	78.51 273	99.05 156	86.53 271	97.45 143	98.47 140

miper_lstm_enhance		90.50 276	90.06 265	91.83 311	95.33 265	83.74 327	93.86 340	96.70 244	87.56 287	87.79 305	93.81 314	83.45 180	96.92 346	87.39 258	84.62 336	94.82 319

v148		90.99 257	90.38 246	92.81 288	93.83 332	85.80 297	96.78 194	96.68 245	89.45 223	88.75 285	93.93 310	82.96 193	97.82 292	87.83 243	83.25 352	94.80 322

ACMH+	87.92 14	90.20 284	89.18 291	93.25 271	96.48 205	86.45 286	96.99 177	96.68 245	88.83 245	84.79 345	96.22 196	70.16 339	98.53 207	84.42 304	88.04 297	94.77 327

CANet_DTU		94.37 114	93.65 125	96.55 80	96.46 207	92.13 100	96.21 245	96.67 247	94.38 60	93.53 159	97.03 150	79.34 257	99.71 46	90.76 187	98.45 113	97.82 186

cl____		90.96 260	90.32 248	92.89 284	95.37 259	86.21 292	94.46 317	96.64 248	87.82 276	88.15 300	94.18 300	82.98 191	97.54 315	87.70 248	85.59 318	94.92 312

HY-MVS	89.66 9	93.87 137	92.95 150	96.63 76	97.10 156	92.49 87	95.64 276	96.64 248	89.05 235	93.00 171	95.79 221	85.77 148	99.45 105	89.16 225	94.35 206	97.96 176

Test_1112_low_res		92.84 180	91.84 191	95.85 134	97.04 164	89.97 183	95.53 280	96.64 248	85.38 323	89.65 259	95.18 248	85.86 146	99.10 141	87.70 248	93.58 229	98.49 137

DIV-MVS_self_test		90.97 259	90.33 247	92.88 285	95.36 260	86.19 293	94.46 317	96.63 251	87.82 276	88.18 299	94.23 297	82.99 190	97.53 317	87.72 245	85.57 319	94.93 310

Fast-Effi-MVS+-dtu		92.29 199	91.99 186	93.21 274	95.27 269	85.52 301	97.03 171	96.63 251	92.09 140	89.11 277	95.14 250	80.33 240	98.08 251	87.54 256	94.74 202	96.03 251

UnsupCasMVSNet_bld		82.13 352	79.46 357	90.14 345	88.00 391	82.47 339	90.89 380	96.62 253	78.94 380	75.61 384	84.40 394	56.63 387	96.31 355	77.30 359	66.77 396	91.63 376

cl22		91.21 247	90.56 242	93.14 276	96.09 229	86.80 275	94.41 319	96.58 254	87.80 278	88.58 288	93.99 308	80.85 232	97.62 309	89.87 203	86.93 307	94.99 305

iter_conf05		94.01 131	94.00 116	94.04 231	95.06 283	88.46 234	97.27 152	96.57 255	92.32 130	92.26 188	97.10 146	88.54 100	98.10 246	95.10 99	91.82 252	95.57 272

jason		94.84 107	94.39 112	96.18 117	95.52 249	90.93 151	96.09 250	96.52 256	89.28 227	96.01 103	97.32 129	84.70 159	98.77 183	95.15 98	98.91 95	98.85 110
jason: jason.
tt0805		91.09 252	90.07 264	94.16 225	95.61 244	88.31 236	97.56 118	96.51 257	89.56 218	89.17 275	95.64 230	67.08 363	98.38 221	91.07 183	88.44 295	95.80 259

AUN-MVS		91.76 217	90.75 232	94.81 190	97.00 167	88.57 228	96.65 207	96.49 258	89.63 216	92.15 191	96.12 202	78.66 271	98.50 209	90.83 185	79.18 371	97.36 207

hse-mvs2		93.45 152	92.99 148	94.81 190	97.02 165	88.59 227	96.69 203	96.47 259	95.19 20	96.74 66	96.16 200	83.67 175	98.48 212	95.85 75	79.13 372	97.35 209

EG-PatchMatch MVS		87.02 325	85.44 329	91.76 317	92.67 359	85.00 312	96.08 251	96.45 260	83.41 352	79.52 376	93.49 326	57.10 386	97.72 300	79.34 350	90.87 271	92.56 366

KD-MVS_self_test		85.95 336	84.95 335	88.96 355	89.55 384	79.11 375	95.13 299	96.42 261	85.91 316	84.07 354	90.48 366	70.03 341	94.82 375	80.04 342	72.94 386	92.94 360

pmmvs6		87.81 317	86.19 324	92.69 292	91.32 372	86.30 289	97.34 143	96.41 262	80.59 374	84.05 355	94.37 287	67.37 358	97.67 303	84.75 299	79.51 370	94.09 347

PMMVS		92.86 178	92.34 176	94.42 212	94.92 291	86.73 278	94.53 313	96.38 263	84.78 335	94.27 141	95.12 252	83.13 186	98.40 216	91.47 175	96.49 168	98.12 167

RPSCF		90.75 266	90.86 225	90.42 342	96.84 174	76.29 383	95.61 277	96.34 264	83.89 344	91.38 210	97.87 93	76.45 295	98.78 180	87.16 265	92.23 242	96.20 241

MSDG		91.42 235	90.24 254	94.96 182	97.15 154	88.91 220	93.69 346	96.32 265	85.72 319	86.93 326	96.47 184	80.24 241	98.98 163	80.57 339	95.05 195	96.98 219

OurMVSNet-221017-0		90.51 275	90.19 259	91.44 323	93.41 346	81.25 349	96.98 178	96.28 266	91.68 151	86.55 330	96.30 192	74.20 315	97.98 267	88.96 228	87.40 305	95.09 301

MVP-Stereo		90.74 267	90.08 261	92.71 291	93.19 351	88.20 242	95.86 262	96.27 267	86.07 314	84.86 344	94.76 266	77.84 285	97.75 298	83.88 312	98.01 127	92.17 374
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 102	94.56 103	96.29 108	96.34 213	91.21 136	95.83 264	96.27 267	88.93 241	96.22 93	96.88 158	86.20 142	98.85 174	95.27 95	99.05 86	98.82 113

BH-untuned		92.94 174	92.62 165	93.92 243	97.22 148	86.16 294	96.40 229	96.25 269	90.06 206	89.79 254	96.17 199	83.19 183	98.35 223	87.19 263	97.27 150	97.24 214

CL-MVSNet_self_test		86.31 331	85.15 333	89.80 349	88.83 387	81.74 347	93.93 337	96.22 270	86.67 303	85.03 342	90.80 365	78.09 281	94.50 376	74.92 370	71.86 388	93.15 358

IS-MVSNet		94.90 104	94.52 107	96.05 123	97.67 125	90.56 165	98.44 22	96.22 270	93.21 97	93.99 148	97.74 104	85.55 150	98.45 213	89.98 199	97.86 130	99.14 76

FA-MVS(test-final)		93.52 150	92.92 151	95.31 164	96.77 182	88.54 230	94.82 305	96.21 272	89.61 217	94.20 143	95.25 246	83.24 182	99.14 137	90.01 198	96.16 172	98.25 156

GA-MVS		91.38 237	90.31 249	94.59 200	94.65 306	87.62 258	94.34 322	96.19 273	90.73 183	90.35 234	93.83 311	71.84 327	97.96 274	87.22 262	93.61 227	98.21 159

IterMVS-SCA-FT		90.31 278	89.81 273	91.82 312	95.52 249	84.20 322	94.30 325	96.15 274	90.61 193	87.39 314	94.27 294	75.80 301	96.44 353	87.34 259	86.88 311	94.82 319

IterMVS		90.15 286	89.67 279	91.61 319	95.48 251	83.72 328	94.33 323	96.12 275	89.99 207	87.31 317	94.15 302	75.78 303	96.27 356	86.97 268	86.89 310	94.83 317
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 183	91.51 204	96.52 83	98.77 53	90.99 146	97.38 140	96.08 276	82.38 358	89.29 271	97.87 93	83.77 173	99.69 52	81.37 335	96.69 164	98.89 107

pmmvs4		90.93 261	89.85 271	94.17 224	93.34 348	90.79 157	94.60 310	96.02 277	84.62 336	87.45 311	95.15 249	81.88 217	97.45 324	87.70 248	87.87 299	94.27 344

ppachtmachnet_test		88.35 312	87.29 311	91.53 320	92.45 365	83.57 331	93.75 343	95.97 278	84.28 339	85.32 341	94.18 300	79.00 268	96.93 345	75.71 366	84.99 332	94.10 345

Anonymous20240521		86.42 329	85.44 329	89.34 353	90.33 377	79.79 367	96.73 197	95.92 279	83.71 348	83.25 359	91.36 362	63.92 374	96.01 357	78.39 354	85.36 323	92.22 372

ITE_SJBPF				92.43 296	95.34 262	85.37 306		95.92 279	91.47 156	87.75 307	96.39 189	71.00 333	97.96 274	82.36 326	89.86 281	93.97 348

test_fmvs2		89.77 296	89.93 268	89.31 354	93.68 337	76.37 382	97.64 110	95.90 281	89.84 212	91.49 208	96.26 195	58.77 383	97.10 338	94.65 113	91.13 264	94.46 335

USDC		88.94 303	87.83 308	92.27 301	94.66 305	84.96 313	93.86 340	95.90 281	87.34 292	83.40 358	95.56 234	67.43 357	98.19 236	82.64 325	89.67 283	93.66 351

COLMAP_ROB	87.81 15	90.40 277	89.28 289	93.79 248	97.95 110	87.13 270	96.92 182	95.89 283	82.83 355	86.88 328	97.18 140	73.77 319	99.29 121	78.44 353	93.62 226	94.95 306
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 140	93.08 146	96.02 126	97.88 116	89.96 184	97.72 99	95.85 284	92.43 127	95.86 107	98.44 44	68.42 353	99.39 111	96.31 51	94.85 196	98.71 121

VDDNet		93.05 168	92.07 182	96.02 126	96.84 174	90.39 172	98.08 53	95.85 284	86.22 312	95.79 110	98.46 42	67.59 356	99.19 128	94.92 104	94.85 196	98.47 140

Vis-MVSNet (Re-imp)		94.15 122	93.88 120	94.95 183	97.61 133	87.92 250	98.10 51	95.80 286	92.22 133	93.02 170	97.45 124	84.53 162	97.91 285	88.24 237	97.97 128	99.02 86

MM		97.29 19	96.98 26	98.23 11	98.01 107	95.03 26	98.07 54	95.76 287	97.78 1	97.52 40	98.80 22	88.09 107	99.86 8	99.44 1	99.37 59	99.80 1

KD-MVS_2432*1600		84.81 343	82.64 347	91.31 325	91.07 374	85.34 307	91.22 375	95.75 288	85.56 321	83.09 360	90.21 369	67.21 359	95.89 359	77.18 360	62.48 399	92.69 363

miper_refine_blended		84.81 343	82.64 347	91.31 325	91.07 374	85.34 307	91.22 375	95.75 288	85.56 321	83.09 360	90.21 369	67.21 359	95.89 359	77.18 360	62.48 399	92.69 363

FE-MVS		92.05 209	91.05 219	95.08 173	96.83 176	87.93 249	93.91 339	95.70 290	86.30 309	94.15 145	94.97 254	76.59 293	99.21 126	84.10 306	96.86 157	98.09 171

tpm cat1		88.36 311	87.21 314	91.81 313	95.13 280	80.55 358	92.58 367	95.70 290	74.97 389	87.45 311	91.96 356	78.01 284	98.17 238	80.39 341	88.74 292	96.72 230

our_test_3		88.78 307	87.98 307	91.20 329	92.45 365	82.53 338	93.61 350	95.69 292	85.77 318	84.88 343	93.71 316	79.99 246	96.78 351	79.47 347	86.24 312	94.28 343

BH-w/o		92.14 207	91.75 193	93.31 269	96.99 169	85.73 298	95.67 272	95.69 292	88.73 251	89.26 273	94.82 264	82.97 192	98.07 255	85.26 294	96.32 171	96.13 247

CR-MVSNet		90.82 264	89.77 275	93.95 239	94.45 314	87.19 267	90.23 383	95.68 294	86.89 300	92.40 180	92.36 349	80.91 229	97.05 340	81.09 338	93.95 220	97.60 198

Patchmtry		88.64 309	87.25 312	92.78 289	94.09 324	86.64 279	89.82 387	95.68 294	80.81 371	87.63 309	92.36 349	80.91 229	97.03 341	78.86 351	85.12 328	94.67 330

testing91		91.90 213	91.02 220	94.53 207	96.54 198	86.55 285	95.86 262	95.64 296	91.77 148	91.89 198	93.47 328	69.94 342	98.86 172	90.23 197	93.86 222	98.18 161

BH-RMVSNet		92.72 185	91.97 187	94.97 181	97.16 152	87.99 248	96.15 248	95.60 297	90.62 192	91.87 199	97.15 143	78.41 275	98.57 205	83.16 315	97.60 137	98.36 152

PVSNet_0	82.17 19	85.46 340	83.64 343	90.92 332	95.27 269	79.49 371	90.55 381	95.60 297	83.76 347	83.00 362	89.95 371	71.09 332	97.97 270	82.75 323	60.79 401	95.31 289

SCA		91.84 215	91.18 217	93.83 245	95.59 245	84.95 314	94.72 307	95.58 299	90.82 179	92.25 189	93.69 317	75.80 301	98.10 246	86.20 277	95.98 174	98.45 142

AllTest		90.23 282	88.98 294	93.98 235	97.94 111	86.64 279	96.51 220	95.54 300	85.38 323	85.49 338	96.77 162	70.28 337	99.15 135	80.02 343	92.87 231	96.15 245

TestCases				93.98 235	97.94 111	86.64 279		95.54 300	85.38 323	85.49 338	96.77 162	70.28 337	99.15 135	80.02 343	92.87 231	96.15 245

mvsmamba		93.83 139	93.46 135	94.93 186	94.88 295	90.85 154	98.55 14	95.49 302	94.24 63	91.29 218	96.97 152	83.04 189	98.14 240	95.56 92	91.17 263	95.78 261

tpmvs		89.83 295	89.15 292	91.89 309	94.92 291	80.30 362	93.11 359	95.46 303	86.28 310	88.08 301	92.65 339	80.44 237	98.52 208	81.47 331	89.92 280	96.84 226

pmmvs5		89.86 294	88.87 297	92.82 287	92.86 355	86.23 291	96.26 240	95.39 304	84.24 340	87.12 318	94.51 278	74.27 314	97.36 331	87.61 255	87.57 301	94.86 315

PatchmatchNet		91.91 212	91.35 206	93.59 258	95.38 257	84.11 323	93.15 358	95.39 304	89.54 219	92.10 194	93.68 319	82.82 196	98.13 241	84.81 298	95.32 189	98.52 132
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 234	91.32 208	91.79 314	95.15 278	79.20 374	93.42 353	95.37 306	88.55 256	93.49 160	93.67 320	82.49 204	98.27 229	90.41 192	89.34 286	97.90 179

Anonymous20231206		87.09 324	86.14 325	89.93 348	91.22 373	80.35 360	96.11 249	95.35 307	83.57 350	84.16 350	93.02 335	73.54 321	95.61 367	72.16 381	86.14 314	93.84 350

MIMVSNet1		84.93 342	83.05 344	90.56 340	89.56 383	84.84 316	95.40 285	95.35 307	83.91 343	80.38 372	92.21 353	57.23 385	93.34 388	70.69 387	82.75 358	93.50 353

TDRefinement		86.53 327	84.76 338	91.85 310	82.23 402	84.25 320	96.38 231	95.35 307	84.97 332	84.09 353	94.94 256	65.76 370	98.34 226	84.60 302	74.52 382	92.97 359

TR-MVS		91.48 233	90.59 240	94.16 225	96.40 210	87.33 260	95.67 272	95.34 310	87.68 284	91.46 209	95.52 237	76.77 292	98.35 223	82.85 320	93.61 227	96.79 228

EPNet_dtu		91.71 218	91.28 211	92.99 280	93.76 334	83.71 329	96.69 203	95.28 311	93.15 103	87.02 322	95.95 210	83.37 181	97.38 330	79.46 348	96.84 158	97.88 181
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 321	85.79 327	91.78 315	94.80 299	87.28 262	95.49 282	95.28 311	84.09 342	83.85 357	91.82 357	62.95 377	94.17 380	78.48 352	85.34 324	93.91 349

MDTV_nov1_ep13			90.76 231		95.22 273	80.33 361	93.03 361	95.28 311	88.14 268	92.84 177	93.83 311	81.34 223	98.08 251	82.86 318	94.34 207

LF4IMVS		87.94 315	87.25 312	89.98 347	92.38 367	80.05 366	94.38 320	95.25 314	87.59 286	84.34 347	94.74 268	64.31 373	97.66 305	84.83 297	87.45 302	92.23 371

TransMVSNet (Re)		88.94 303	87.56 309	93.08 278	94.35 317	88.45 235	97.73 96	95.23 315	87.47 288	84.26 349	95.29 243	79.86 249	97.33 332	79.44 349	74.44 383	93.45 355

test20.03		86.14 334	85.40 331	88.35 356	90.12 378	80.06 365	95.90 261	95.20 316	88.59 252	81.29 367	93.62 322	71.43 330	92.65 390	71.26 385	81.17 363	92.34 370

new-patchmatchnet		83.18 349	81.87 352	87.11 363	86.88 393	75.99 384	93.70 344	95.18 317	85.02 331	77.30 383	88.40 381	65.99 368	93.88 385	74.19 375	70.18 390	91.47 380

MDA-MVSNet_test_wron		85.87 337	84.23 341	90.80 337	92.38 367	82.57 337	93.17 356	95.15 318	82.15 360	67.65 394	92.33 352	78.20 277	95.51 370	77.33 357	79.74 367	94.31 342

YYNet1		85.87 337	84.23 341	90.78 338	92.38 367	82.46 340	93.17 356	95.14 319	82.12 361	67.69 392	92.36 349	78.16 280	95.50 371	77.31 358	79.73 368	94.39 338

Baseline_NR-MVSNet		91.20 248	90.62 238	92.95 282	93.83 332	88.03 247	97.01 176	95.12 320	88.42 260	89.70 256	95.13 251	83.47 178	97.44 325	89.66 209	83.24 353	93.37 356

thres200		92.23 203	91.39 205	94.75 197	97.61 133	89.03 218	96.60 215	95.09 321	92.08 141	93.28 166	94.00 307	78.39 276	99.04 159	81.26 337	94.18 211	96.19 242

ADS-MVSNet		89.89 291	88.68 299	93.53 261	95.86 234	84.89 315	90.93 378	95.07 322	83.23 353	91.28 219	91.81 358	79.01 266	97.85 288	79.52 345	91.39 259	97.84 183

pmmvs-eth3d		86.22 332	84.45 339	91.53 320	88.34 390	87.25 264	94.47 315	95.01 323	83.47 351	79.51 377	89.61 374	69.75 344	95.71 364	83.13 316	76.73 379	91.64 375

Anonymous202405211		92.07 208	90.83 229	95.76 136	98.19 95	88.75 223	97.58 116	95.00 324	86.00 315	93.64 155	97.45 124	66.24 367	99.53 91	90.68 190	92.71 236	99.01 89

MDA-MVSNet-bldmvs		85.00 341	82.95 346	91.17 330	93.13 353	83.33 332	94.56 312	95.00 324	84.57 337	65.13 398	92.65 339	70.45 336	95.85 361	73.57 377	77.49 375	94.33 340

ambc				86.56 366	83.60 399	70.00 393	85.69 397	94.97 326		80.60 371	88.45 380	37.42 401	96.84 349	82.69 324	75.44 381	92.86 361

testgi		87.97 314	87.21 314	90.24 344	92.86 355	80.76 353	96.67 206	94.97 326	91.74 149	85.52 337	95.83 216	62.66 378	94.47 378	76.25 364	88.36 296	95.48 274

dp		88.90 305	88.26 305	90.81 335	94.58 310	76.62 381	92.85 364	94.93 328	85.12 329	90.07 248	93.07 334	75.81 300	98.12 244	80.53 340	87.42 304	97.71 190

test_fmvs3		83.21 348	83.02 345	83.78 370	86.77 394	68.34 396	96.76 195	94.91 329	86.49 306	84.14 352	89.48 375	36.04 402	91.73 392	91.86 165	80.77 365	91.26 382

test_0402		86.46 328	84.79 337	91.45 322	95.02 285	85.55 300	96.29 239	94.89 330	80.90 368	82.21 364	93.97 309	68.21 354	97.29 334	62.98 393	88.68 293	91.51 378

tfpn200view9		92.38 193	91.52 202	94.95 183	97.85 117	89.29 208	97.41 133	94.88 331	92.19 137	93.27 167	94.46 283	78.17 278	99.08 147	81.40 332	94.08 215	96.48 235

CVMVSNet		91.23 246	91.75 193	89.67 350	95.77 239	74.69 385	96.44 221	94.88 331	85.81 317	92.18 190	97.64 114	79.07 261	95.58 369	88.06 239	95.86 178	98.74 118

thres400		92.42 191	91.52 202	95.12 172	97.85 117	89.29 208	97.41 133	94.88 331	92.19 137	93.27 167	94.46 283	78.17 278	99.08 147	81.40 332	94.08 215	96.98 219

EPNet		95.20 95	94.56 103	97.14 65	92.80 357	92.68 81	97.85 83	94.87 334	96.64 3	92.46 179	97.80 101	86.23 139	99.65 58	93.72 131	98.62 104	99.10 82
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 223	90.72 235	94.32 217	96.48 205	86.11 295	95.81 265	94.76 335	91.55 153	91.75 203	93.44 329	68.55 351	98.82 176	90.43 191	93.69 223	98.04 174

SixPastTwentyTwo		89.15 301	88.54 301	90.98 331	93.49 343	80.28 363	96.70 201	94.70 336	90.78 180	84.15 351	95.57 233	71.78 328	97.71 301	84.63 301	85.07 329	94.94 308

thres100view900		92.43 190	91.58 199	94.98 180	97.92 113	89.37 204	97.71 101	94.66 337	92.20 135	93.31 165	94.90 259	78.06 282	99.08 147	81.40 332	94.08 215	96.48 235

thres600view7		92.49 189	91.60 198	95.18 168	97.91 114	89.47 198	97.65 106	94.66 337	92.18 139	93.33 164	94.91 258	78.06 282	99.10 141	81.61 329	94.06 219	96.98 219

PatchT		88.87 306	87.42 310	93.22 273	94.08 325	85.10 311	89.51 388	94.64 339	81.92 362	92.36 183	88.15 384	80.05 245	97.01 343	72.43 380	93.65 225	97.54 201

baseline1		92.82 181	91.90 189	95.55 153	97.20 150	90.77 158	97.19 162	94.58 340	92.20 135	92.36 183	96.34 191	84.16 169	98.21 233	89.20 223	83.90 348	97.68 192

Gipuma		67.86 368	65.41 370	75.18 383	92.66 360	73.45 388	66.50 404	94.52 341	53.33 403	57.80 404	66.07 404	30.81 404	89.20 396	48.15 402	78.88 374	62.90 404
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 221	90.75 232	94.47 208	96.53 200	86.56 284	95.76 269	94.51 342	91.10 174	91.24 222	93.59 323	68.59 350	98.86 172	91.10 182	94.29 208	98.00 175

CostFormer		91.18 251	90.70 236	92.62 294	94.84 297	81.76 346	94.09 332	94.43 343	84.15 341	92.72 178	93.77 315	79.43 256	98.20 234	90.70 189	92.18 245	97.90 179

tpm2		89.96 288	89.21 290	92.23 303	94.91 293	81.25 349	93.78 342	94.42 344	80.62 373	91.56 206	93.44 329	76.44 296	97.94 279	85.60 289	92.08 249	97.49 202

JIA-IIPM		88.26 313	87.04 317	91.91 308	93.52 341	81.42 348	89.38 389	94.38 345	80.84 370	90.93 226	80.74 396	79.22 259	97.92 282	82.76 322	91.62 254	96.38 238

dmvs_re		90.21 283	89.50 284	92.35 297	95.47 254	85.15 309	95.70 271	94.37 346	90.94 178	88.42 290	93.57 324	74.63 311	95.67 366	82.80 321	89.57 284	96.22 240

Patchmatch-test		89.42 299	87.99 306	93.70 253	95.27 269	85.11 310	88.98 390	94.37 346	81.11 367	87.10 320	93.69 317	82.28 208	97.50 320	74.37 373	94.76 200	98.48 139

LCM-MVSNet		72.55 361	69.39 365	82.03 372	70.81 412	65.42 401	90.12 385	94.36 348	55.02 402	65.88 396	81.72 395	24.16 410	89.96 393	74.32 374	68.10 394	90.71 385

ADS-MVSNet2		89.45 298	88.59 300	92.03 306	95.86 234	82.26 342	90.93 378	94.32 349	83.23 353	91.28 219	91.81 358	79.01 266	95.99 358	79.52 345	91.39 259	97.84 183

EU-MVSNet		88.72 308	88.90 296	88.20 358	93.15 352	74.21 386	96.63 212	94.22 350	85.18 327	87.32 316	95.97 208	76.16 298	94.98 374	85.27 293	86.17 313	95.41 279

MVS_0304		97.04 28	96.73 42	97.96 23	97.60 135	94.36 36	98.01 59	94.09 351	97.33 2	96.29 89	98.79 24	89.73 82	99.86 8	99.36 2	99.42 49	99.67 13

MIMVSNet		88.50 310	86.76 320	93.72 252	94.84 297	87.77 256	91.39 373	94.05 352	86.41 308	87.99 303	92.59 342	63.27 375	95.82 363	77.44 356	92.84 233	97.57 200

OpenMVS_ROB	81.14 20	84.42 345	82.28 351	90.83 333	90.06 379	84.05 325	95.73 270	94.04 353	73.89 391	80.17 375	91.53 361	59.15 382	97.64 306	66.92 391	89.05 288	90.80 384

TinyColmap		86.82 326	85.35 332	91.21 327	94.91 293	82.99 335	93.94 336	94.02 354	83.58 349	81.56 366	94.68 270	62.34 379	98.13 241	75.78 365	87.35 306	92.52 368

ETVMVS		90.52 274	89.14 293	94.67 199	96.81 179	87.85 254	95.91 260	93.97 355	89.71 215	92.34 186	92.48 344	65.41 371	97.96 274	81.37 335	94.27 209	98.21 159

IB-MVS	87.33 17	89.91 289	88.28 304	94.79 194	95.26 272	87.70 257	95.12 300	93.95 356	89.35 226	87.03 321	92.49 343	70.74 335	99.19 128	89.18 224	81.37 362	97.49 202
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		87.13 323	87.02 318	87.47 361	95.16 276	73.21 389	95.00 301	93.93 357	88.55 256	86.96 323	91.99 354	75.90 299	94.00 382	61.59 395	94.11 212	95.20 297

myMVS_eth3d		87.18 322	86.38 322	89.58 351	95.16 276	79.53 369	95.00 301	93.93 357	88.55 256	86.96 323	91.99 354	56.23 388	94.00 382	75.47 369	94.11 212	95.20 297

testing222		90.31 278	88.96 295	94.35 214	96.54 198	87.29 261	95.50 281	93.84 359	90.97 177	91.75 203	92.96 336	62.18 380	98.00 265	82.86 318	94.08 215	97.76 188

test_f		80.57 354	79.62 356	83.41 371	83.38 400	67.80 398	93.57 351	93.72 360	80.80 372	77.91 382	87.63 387	33.40 403	92.08 391	87.14 266	79.04 373	90.34 386

LCM-MVSNet-Re		92.50 187	92.52 171	92.44 295	96.82 178	81.89 345	96.92 182	93.71 361	92.41 128	84.30 348	94.60 274	85.08 155	97.03 341	91.51 173	97.36 145	98.40 148

tpm		90.25 281	89.74 278	91.76 317	93.92 328	79.73 368	93.98 333	93.54 362	88.28 263	91.99 196	93.25 333	77.51 288	97.44 325	87.30 261	87.94 298	98.12 167

ET-MVSNet_ETH3D		91.49 232	90.11 260	95.63 146	96.40 210	91.57 122	95.34 287	93.48 363	90.60 195	75.58 385	95.49 238	80.08 244	96.79 350	94.25 119	89.76 282	98.52 132

LFMVS		93.60 146	92.63 164	96.52 83	98.13 100	91.27 133	97.94 73	93.39 364	90.57 196	96.29 89	98.31 60	69.00 346	99.16 134	94.18 120	95.87 177	99.12 80

Patchmatch-RL test		87.38 320	86.24 323	90.81 335	88.74 389	78.40 378	88.12 395	93.17 365	87.11 297	82.17 365	89.29 376	81.95 215	95.60 368	88.64 234	77.02 376	98.41 147

test-LLR		91.42 235	91.19 216	92.12 304	94.59 308	80.66 355	94.29 326	92.98 366	91.11 172	90.76 228	92.37 346	79.02 264	98.07 255	88.81 230	96.74 161	97.63 193

test-mter		90.19 285	89.54 283	92.12 304	94.59 308	80.66 355	94.29 326	92.98 366	87.68 284	90.76 228	92.37 346	67.67 355	98.07 255	88.81 230	96.74 161	97.63 193

WB-MVSnew		89.88 292	89.56 282	90.82 334	94.57 311	83.06 334	95.65 275	92.85 368	87.86 275	90.83 227	94.10 303	79.66 253	96.88 347	76.34 363	94.19 210	92.54 367

testing3		87.67 318	86.88 319	90.05 346	96.14 225	80.71 354	97.10 169	92.85 368	90.15 204	87.54 310	94.55 276	55.70 389	94.10 381	73.77 376	94.10 214	95.35 286

test_method		66.11 369	64.89 371	69.79 386	72.62 410	35.23 418	65.19 405	92.83 370	20.35 408	65.20 397	88.08 385	43.14 399	82.70 403	73.12 379	63.46 398	91.45 381

test0.0.03 1		89.37 300	88.70 298	91.41 324	92.47 364	85.63 299	95.22 296	92.70 371	91.11 172	86.91 327	93.65 321	79.02 264	93.19 389	78.00 355	89.18 287	95.41 279

new_pmnet		82.89 350	81.12 355	88.18 359	89.63 382	80.18 364	91.77 372	92.57 372	76.79 387	75.56 386	88.23 383	61.22 381	94.48 377	71.43 383	82.92 356	89.87 387

mvsany_test1		93.93 135	93.98 117	93.78 249	94.94 290	86.80 275	94.62 309	92.55 373	88.77 250	96.85 61	98.49 38	88.98 89	98.08 251	95.03 101	95.62 184	96.46 237

thisisatest0515		92.29 199	91.30 210	95.25 166	96.60 190	88.90 221	94.36 321	92.32 374	87.92 272	93.43 162	94.57 275	77.28 289	99.00 161	89.42 214	95.86 178	97.86 182

thisisatest0530		93.03 169	92.21 180	95.49 157	97.07 157	89.11 217	97.49 129	92.19 375	90.16 203	94.09 146	96.41 187	76.43 297	99.05 156	90.38 193	95.68 183	98.31 154

tttt0517		92.96 172	92.33 177	94.87 187	97.11 155	87.16 269	97.97 69	92.09 376	90.63 191	93.88 152	97.01 151	76.50 294	99.06 154	90.29 196	95.45 187	98.38 150

K. test v3		87.64 319	86.75 321	90.32 343	93.02 354	79.48 372	96.61 213	92.08 377	90.66 189	80.25 374	94.09 304	67.21 359	96.65 352	85.96 285	80.83 364	94.83 317

TESTMET0.1,1		90.06 287	89.42 286	91.97 307	94.41 316	80.62 357	94.29 326	91.97 378	87.28 294	90.44 232	92.47 345	68.79 347	97.67 303	88.50 236	96.60 166	97.61 197

PM-MVS		83.48 347	81.86 353	88.31 357	87.83 392	77.59 380	93.43 352	91.75 379	86.91 299	80.63 370	89.91 372	44.42 398	95.84 362	85.17 296	76.73 379	91.50 379

baseline2		91.63 222	90.86 225	93.94 241	94.33 318	86.32 288	95.92 259	91.64 380	89.37 225	86.94 325	94.69 269	81.62 221	98.69 192	88.64 234	94.57 205	96.81 227

APD_test1		79.31 356	77.70 359	84.14 369	89.11 386	69.07 395	92.36 371	91.50 381	69.07 394	73.87 388	92.63 341	39.93 400	94.32 379	70.54 388	80.25 366	89.02 389

FPMVS		71.27 362	69.85 364	75.50 382	74.64 407	59.03 407	91.30 374	91.50 381	58.80 399	57.92 403	88.28 382	29.98 406	85.53 402	53.43 400	82.84 357	81.95 395

door								91.13 383

door-mid								91.06 384

EGC-MVSNET		68.77 367	63.01 373	86.07 368	92.49 363	82.24 343	93.96 335	90.96 385	0.71 413	2.62 414	90.89 364	53.66 390	93.46 386	57.25 398	84.55 338	82.51 394

mvsany_test3		83.59 346	82.44 350	87.03 364	83.80 397	73.82 387	93.70 344	90.92 386	86.42 307	82.51 363	90.26 368	46.76 397	95.71 364	90.82 186	76.76 378	91.57 377

pmmvs3		79.97 355	77.50 360	87.39 362	82.80 401	79.38 373	92.70 366	90.75 387	70.69 393	78.66 379	87.47 389	51.34 393	93.40 387	73.39 378	69.65 391	89.38 388

UWE-MVS		89.91 289	89.48 285	91.21 327	95.88 233	78.23 379	94.91 304	90.26 388	89.11 232	92.35 185	94.52 277	68.76 348	97.96 274	83.95 310	95.59 185	97.42 205

DSMNet-mixed		86.34 330	86.12 326	87.00 365	89.88 381	70.43 391	94.93 303	90.08 389	77.97 384	85.42 340	92.78 338	74.44 313	93.96 384	74.43 372	95.14 191	96.62 231

MVS-HIRNet		82.47 351	81.21 354	86.26 367	95.38 257	69.21 394	88.96 391	89.49 390	66.28 396	80.79 369	74.08 401	68.48 352	97.39 329	71.93 382	95.47 186	92.18 373

WB-MVS		76.77 358	76.63 361	77.18 377	85.32 395	56.82 409	94.53 313	89.39 391	82.66 357	71.35 390	89.18 377	75.03 308	88.88 397	35.42 406	66.79 395	85.84 391

test1111		93.19 161	92.82 155	94.30 220	97.58 140	84.56 318	98.21 43	89.02 392	93.53 86	94.58 135	98.21 67	72.69 323	99.05 156	93.06 144	98.48 111	99.28 65

SSC-MVS		76.05 359	75.83 362	76.72 381	84.77 396	56.22 410	94.32 324	88.96 393	81.82 364	70.52 391	88.91 378	74.79 310	88.71 398	33.69 407	64.71 397	85.23 392

ECVR-MVS		93.19 161	92.73 161	94.57 205	97.66 127	85.41 303	98.21 43	88.23 394	93.43 90	94.70 133	98.21 67	72.57 324	99.07 151	93.05 145	98.49 109	99.25 68

EPMVS		90.70 269	89.81 273	93.37 267	94.73 303	84.21 321	93.67 347	88.02 395	89.50 221	92.38 182	93.49 326	77.82 286	97.78 295	86.03 283	92.68 237	98.11 170

ANet_high		63.94 371	59.58 374	77.02 378	61.24 414	66.06 399	85.66 398	87.93 396	78.53 382	42.94 406	71.04 403	25.42 409	80.71 405	52.60 401	30.83 407	84.28 393

PMMVS2		70.19 363	66.92 367	80.01 373	76.35 406	65.67 400	86.22 396	87.58 397	64.83 398	62.38 399	80.29 398	26.78 408	88.49 400	63.79 392	54.07 403	85.88 390

lessismore_v0				90.45 341	91.96 370	79.09 376		87.19 398		80.32 373	94.39 285	66.31 366	97.55 314	84.00 309	76.84 377	94.70 329

PMVS	53.92 22	58.58 372	55.40 375	68.12 387	51.00 415	48.64 412	78.86 401	87.10 399	46.77 404	35.84 410	74.28 400	8.76 414	86.34 401	42.07 404	73.91 384	69.38 401
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		86.16 333	85.06 334	89.46 352	93.47 345	80.46 359	96.41 225	86.61 400	85.22 326	79.15 378	88.64 379	52.41 392	97.06 339	93.08 143	90.57 273	90.87 383

testf1		69.31 365	66.76 368	76.94 379	78.61 404	61.93 403	88.27 393	86.11 401	55.62 400	59.69 400	85.31 392	20.19 412	89.32 394	57.62 396	69.44 392	79.58 396

APD_test2		69.31 365	66.76 368	76.94 379	78.61 404	61.93 403	88.27 393	86.11 401	55.62 400	59.69 400	85.31 392	20.19 412	89.32 394	57.62 396	69.44 392	79.58 396

gg-mvs-nofinetune		87.82 316	85.61 328	94.44 210	94.46 313	89.27 211	91.21 377	84.61 403	80.88 369	89.89 252	74.98 399	71.50 329	97.53 317	85.75 288	97.21 152	96.51 233

dmvs_testset		81.38 353	82.60 349	77.73 376	91.74 371	51.49 411	93.03 361	84.21 404	89.07 233	78.28 381	91.25 363	76.97 291	88.53 399	56.57 399	82.24 359	93.16 357

GG-mvs-BLEND				93.62 256	93.69 336	89.20 213	92.39 370	83.33 405		87.98 304	89.84 373	71.00 333	96.87 348	82.08 328	95.40 188	94.80 322

MTMP							97.86 80	82.03 406

DeepMVS_CX				74.68 384	90.84 376	64.34 402		81.61 407	65.34 397	67.47 395	88.01 386	48.60 396	80.13 406	62.33 394	73.68 385	79.58 396

E-PMN		53.28 373	52.56 377	55.43 390	74.43 408	47.13 413	83.63 400	76.30 408	42.23 405	42.59 407	62.22 406	28.57 407	74.40 407	31.53 408	31.51 406	44.78 405

test2506		91.60 224	90.78 230	94.04 231	97.66 127	83.81 326	98.27 33	75.53 409	93.43 90	95.23 124	98.21 67	67.21 359	99.07 151	93.01 148	98.49 109	99.25 68

EMVS		52.08 375	51.31 378	54.39 391	72.62 410	45.39 415	83.84 399	75.51 410	41.13 406	40.77 408	59.65 407	30.08 405	73.60 408	28.31 410	29.90 408	44.18 406

test_vis3_rt		72.73 360	70.55 363	79.27 374	80.02 403	68.13 397	93.92 338	74.30 411	76.90 386	58.99 402	73.58 402	20.29 411	95.37 372	84.16 305	72.80 387	74.31 399

MVE	50.73 23	53.25 374	48.81 379	66.58 389	65.34 413	57.50 408	72.49 403	70.94 412	40.15 407	39.28 409	63.51 405	6.89 416	73.48 409	38.29 405	42.38 405	68.76 403
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 376	53.82 376	46.29 392	33.73 416	45.30 416	78.32 402	67.24 413	18.02 409	50.93 405	87.05 390	52.99 391	53.11 411	70.76 386	25.29 409	40.46 407

kuosan		65.27 370	64.66 372	67.11 388	83.80 397	61.32 406	88.53 392	60.77 414	68.22 395	67.67 393	80.52 397	49.12 395	70.76 410	29.67 409	53.64 404	69.26 402

dongtai		69.99 364	69.33 366	71.98 385	88.78 388	61.64 405	89.86 386	59.93 415	75.67 388	74.96 387	85.45 391	50.19 394	81.66 404	43.86 403	55.27 402	72.63 400

N_pmnet		78.73 357	78.71 358	78.79 375	92.80 357	46.50 414	94.14 330	43.71 416	78.61 381	80.83 368	91.66 360	74.94 309	96.36 354	67.24 390	84.45 340	93.50 353

wuyk23d		25.11 377	24.57 381	26.74 393	73.98 409	39.89 417	57.88 406	9.80 417	12.27 410	10.39 411	6.97 413	7.03 415	36.44 412	25.43 411	17.39 410	3.89 410

testmvs		13.36 379	16.33 382	4.48 395	5.04 417	2.26 420	93.18 355	3.28 418	2.70 411	8.24 412	21.66 409	2.29 418	2.19 413	7.58 412	2.96 411	9.00 409

test123		13.04 380	15.66 383	5.18 394	4.51 418	3.45 419	92.50 369	1.81 419	2.50 412	7.58 413	20.15 410	3.67 417	2.18 414	7.13 413	1.07 412	9.90 408

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

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

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

pcd_1.5k_mvsjas		7.39 382	9.85 385	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	0.00 414	88.65 96	0.00 415	0.00 414	0.00 413	0.00 411

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

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

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

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

n2								0.00 420

nn								0.00 420

ab-mvs-re		8.06 381	10.74 384	0.00 396	0.00 419	0.00 421	0.00 407	0.00 420	0.00 414	0.00 415	96.69 168	0.00 419	0.00 415	0.00 414	0.00 413	0.00 411

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

WAC-MVS						79.53 369								75.56 368

PC_three_1452									90.77 181	98.89 14	98.28 65	96.24 1	98.35 223	95.76 79	99.58 24	99.59 22

eth-test2					0.00 419

eth-test					0.00 419

OPU-MVS				98.55 3	98.82 52	96.86 3	98.25 36				98.26 66	96.04 2	99.24 124	95.36 94	99.59 20	99.56 29

test_0728_THIRD									94.78 41	98.73 18	98.87 15	95.87 4	99.84 23	97.45 26	99.72 2	99.77 2

GSMVS																98.45 142

test_part2					99.28 25	95.74 8				98.10 29

sam_mvs1												82.76 197				98.45 142

sam_mvs												81.94 216

test_post1							92.81 365				16.58 412	80.53 235	97.68 302	86.20 277

test_post											17.58 411	81.76 218	98.08 251

patchmatchnet-post											90.45 367	82.65 201	98.10 246

gm-plane-assit					93.22 350	78.89 377			84.82 334		93.52 325		98.64 197	87.72 245

test9_res														94.81 108	99.38 56	99.45 47

agg_prior2														93.94 125	99.38 56	99.50 40

test_prior4						93.66 57	96.42 224

test_prior2							96.35 233		92.80 119	96.03 100	97.59 118	92.01 43		95.01 102	99.38 56

旧先验2							95.94 258		81.66 365	97.34 48			98.82 176	92.26 152

新几何2							95.79 267

原ACMM2							95.67 272

testdata2													99.67 56	85.96 285

segment_acmp												92.89 27

testdata1							95.26 295		93.10 106

plane_prior7					96.21 217	89.98 182

plane_prior6					96.10 228	90.00 178						81.32 224

plane_prior4											96.64 171

plane_prior3						90.00 178			94.46 55	91.34 212

plane_prior2							97.74 94		94.85 34

plane_prior1					96.14 225

plane_prior						89.99 180	97.24 155		94.06 67						92.16 246

HQP5-MVS						89.33 206

HQP-NCC					95.86 234		96.65 207		93.55 82	90.14 237

ACMP_Plane					95.86 234		96.65 207		93.55 82	90.14 237

BP-MVS														92.13 158

HQP4-MVS										90.14 237			98.50 209			95.78 261

HQP2-MVS												80.95 227

NP-MVS					95.99 232	89.81 187					95.87 213

MDTV_nov1_ep13_2view						70.35 392	93.10 360		83.88 345	93.55 157		82.47 205		86.25 276		98.38 150

ACMMP++_ref															90.30 278

ACMMP++															91.02 267

Test By Simon												88.73 95

High-resolution multi-view benchmark