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 88	98.41 77	91.73 116	98.01 60	99.02 1	96.37 6	99.30 2	98.92 15	92.39 41	99.79 36	99.16 6	99.46 41	98.08 179

PGM-MVS		96.81 45	96.53 54	97.65 42	99.35 20	93.53 60	97.65 111	98.98 2	92.22 139	97.14 60	98.44 48	91.17 67	99.85 18	94.35 126	99.46 41	99.57 28

MVS_111021_HR		96.68 55	96.58 53	96.99 75	98.46 73	92.31 98	96.20 256	98.90 3	94.30 70	95.86 113	97.74 111	92.33 42	99.38 118	96.04 76	99.42 50	99.28 68

test_fmvsmconf_n		97.49 15	97.56 9	97.29 58	97.44 148	92.37 95	97.91 76	98.88 4	95.83 10	98.92 14	99.05 7	91.45 57	99.80 33	99.12 7	99.46 41	99.69 12

ACMMP		96.27 70	95.93 73	97.28 60	99.24 28	92.62 87	98.25 35	98.81 5	92.99 117	94.56 144	98.39 52	88.96 94	99.85 18	94.57 124	97.63 143	99.36 63
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 71	96.19 70	96.39 104	98.23 94	91.35 136	96.24 254	98.79 6	93.99 76	95.80 115	97.65 118	89.92 86	99.24 130	95.87 80	99.20 76	98.58 135

patch_mono-2		96.83 44	97.44 16	95.01 183	99.05 39	85.39 310	96.98 187	98.77 7	94.70 50	97.99 35	98.66 31	93.61 19	99.91 1	97.67 26	99.50 35	99.72 11

fmvsm_s_conf0.5_n		96.85 41	97.13 19	96.04 128	98.07 108	90.28 177	97.97 69	98.76 8	94.93 35	98.84 18	99.06 6	88.80 97	99.65 63	99.06 8	98.63 106	98.18 168

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 55	98.21 95	92.75 83	97.83 87	98.73 9	95.04 33	99.30 2	98.84 25	93.34 22	99.78 38	99.32 3	99.13 83	99.50 43

fmvsm_s_conf0.5_n_a		96.75 49	96.93 32	96.20 120	97.64 135	90.72 163	98.00 61	98.73 9	94.55 57	98.91 15	99.08 3	88.22 106	99.63 72	98.91 11	98.37 119	98.25 163

FC-MVSNet-test		93.94 141	93.57 134	95.04 181	95.48 263	91.45 133	98.12 50	98.71 11	93.37 100	90.23 245	96.70 172	87.66 115	97.85 297	91.49 183	90.39 284	95.83 267

UniMVSNet (Re)		93.31 162	92.55 174	95.61 155	95.39 268	93.34 66	97.39 148	98.71 11	93.14 113	90.10 254	94.83 271	87.71 114	98.03 271	91.67 181	83.99 354	95.46 286

fmvsm_l_conf0.5_n_a		97.63 8	97.76 5	97.26 62	98.25 89	92.59 89	97.81 91	98.68 13	94.93 35	99.24 4	98.87 20	93.52 20	99.79 36	99.32 3	99.21 74	99.40 57

FIs		94.09 135	93.70 130	95.27 171	95.70 253	92.03 109	98.10 51	98.68 13	93.36 102	90.39 242	96.70 172	87.63 118	97.94 288	92.25 163	90.50 283	95.84 266

WR-MVS_H		92.00 216	91.35 213	93.95 244	95.09 294	89.47 203	98.04 58	98.68 13	91.46 163	88.34 303	94.68 278	85.86 147	97.56 324	85.77 298	84.24 352	94.82 329

VPA-MVSNet		93.24 164	92.48 179	95.51 161	95.70 253	92.39 94	97.86 81	98.66 16	92.30 138	92.09 204	95.37 247	80.49 242	98.40 226	93.95 132	85.86 325	95.75 275

fmvsm_s_conf0.5_n_2		96.62 56	96.82 41	96.02 130	97.98 114	90.43 173	97.50 132	98.59 17	96.59 3	99.31 1	99.08 3	84.47 164	99.75 44	99.37 2	98.45 116	97.88 189

UniMVSNet_NR-MVSNet		93.37 160	92.67 169	95.47 166	95.34 274	92.83 81	97.17 171	98.58 18	92.98 122	90.13 250	95.80 224	88.37 105	97.85 297	91.71 178	83.93 355	95.73 277

CSCG		96.05 74	95.91 74	96.46 98	99.24 28	90.47 170	98.30 28	98.57 19	89.01 248	93.97 160	97.57 126	92.62 37	99.76 41	94.66 119	99.27 67	99.15 78

MSLP-MVS++		96.94 35	97.06 22	96.59 85	98.72 58	91.86 114	97.67 108	98.49 20	94.66 53	97.24 56	98.41 51	92.31 44	98.94 173	96.61 53	99.46 41	98.96 98

HyFIR lowres test		93.66 151	92.92 157	95.87 138	98.24 90	89.88 190	94.58 324	98.49 20	85.06 343	93.78 163	95.78 228	82.86 198	98.67 204	91.77 176	95.71 190	99.07 89

CHOSEN 1792x2688		94.15 130	93.51 140	96.06 126	98.27 86	89.38 208	95.18 310	98.48 22	85.60 333	93.76 164	97.11 152	83.15 189	99.61 74	91.33 186	98.72 103	99.19 74

PHI-MVS		96.77 47	96.46 61	97.71 40	98.40 78	94.07 48	98.21 42	98.45 23	89.86 220	97.11 62	98.01 88	92.52 39	99.69 57	96.03 77	99.53 29	99.36 63

fmvsm_s_conf0.1_n		96.58 59	96.77 45	96.01 133	96.67 194	90.25 178	97.91 76	98.38 24	94.48 61	98.84 18	99.14 1	88.06 108	99.62 73	98.82 13	98.60 108	98.15 172

PVSNet_BlendedMVS		94.06 136	93.92 126	94.47 214	98.27 86	89.46 205	96.73 207	98.36 25	90.17 212	94.36 149	95.24 255	88.02 109	99.58 82	93.44 143	90.72 279	94.36 349

PVSNet_Blended		94.87 112	94.56 110	95.81 142	98.27 86	89.46 205	95.47 294	98.36 25	88.84 256	94.36 149	96.09 213	88.02 109	99.58 82	93.44 143	98.18 127	98.40 155

3Dnovator	91.36 5	95.19 102	94.44 118	97.44 52	96.56 203	93.36 65	98.65 11	98.36 25	94.12 72	89.25 283	98.06 82	82.20 214	99.77 40	93.41 145	99.32 64	99.18 75

FOURS1					99.55 1	93.34 66	99.29 1	98.35 28	94.98 34	98.49 25

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 168	98.35 28	95.16 27	98.71 22	98.80 27	95.05 10	99.89 3	96.70 51	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 64	96.47 58	96.16 122	95.48 263	90.69 164	97.91 76	98.33 30	94.07 73	98.93 11	99.14 1	87.44 125	99.61 74	98.63 15	98.32 121	98.18 168

HFP-MVS		97.14 26	96.92 33	97.83 26	99.42 7	94.12 46	98.52 15	98.32 31	93.21 105	97.18 57	98.29 68	92.08 46	99.83 26	95.63 93	99.59 19	99.54 36

ACMMPR		97.07 29	96.84 37	97.79 30	99.44 6	93.88 52	98.52 15	98.31 32	93.21 105	97.15 59	98.33 62	91.35 61	99.86 9	95.63 93	99.59 19	99.62 20

test_fmvsmvis_n_1920		96.70 51	96.84 37	96.31 109	96.62 196	91.73 116	97.98 63	98.30 33	96.19 7	96.10 104	98.95 13	89.42 88	99.76 41	98.90 12	99.08 87	97.43 215

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 33	94.76 48	98.30 28	98.90 17	93.77 17	99.68 59	97.93 18	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 27	98.29 35	94.92 37	98.99 9	98.92 15	95.08 8

MSP-MVS		97.59 10	97.54 10	97.73 37	99.40 11	93.77 56	98.53 14	98.29 35	95.55 18	98.56 24	97.81 106	93.90 15	99.65 63	96.62 52	99.21 74	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 61	95.39 11	99.29 1	98.28 37	94.78 46	98.93 11	98.87 20	96.04 2	99.86 9	97.45 34	99.58 23	99.59 24

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 37					99.86 9	97.52 30	99.67 6	99.75 6

CP-MVS		97.02 31	96.81 42	97.64 44	99.33 21	93.54 59	98.80 8	98.28 37	92.99 117	96.45 91	98.30 67	91.90 49	99.85 18	95.61 95	99.68 4	99.54 36

test_fmvsmconf0.1_n		97.09 27	97.06 22	97.19 67	95.67 255	92.21 102	97.95 72	98.27 40	95.78 14	98.40 27	99.00 9	89.99 84	99.78 38	99.06 8	99.41 53	99.59 24

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 40	95.13 28	99.19 5	98.89 18	95.54 5	99.85 18	97.52 30	99.66 10	99.56 31

test_241102_TWO								98.27 40	95.13 28	98.93 11	98.89 18	94.99 11	99.85 18	97.52 30	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 40	95.09 31	99.19 5	98.81 26	95.54 5	99.65 63

SF-MVS		97.39 18	97.13 19	98.17 15	99.02 42	95.28 19	98.23 39	98.27 40	92.37 137	98.27 29	98.65 33	93.33 23	99.72 50	96.49 57	99.52 30	99.51 40

SteuartSystems-ACMMP		97.62 9	97.53 11	97.87 24	98.39 80	94.25 40	98.43 22	98.27 40	95.34 22	98.11 31	98.56 35	94.53 12	99.71 51	96.57 55	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 46	95.13 28	98.48 26	98.87 20	95.16 7

PVSNet_Blended_VisFu		95.27 97	94.91 101	96.38 105	98.20 96	90.86 157	97.27 160	98.25 46	90.21 211	94.18 154	97.27 143	87.48 124	99.73 47	93.53 140	97.77 141	98.55 136

region2R		97.07 29	96.84 37	97.77 33	99.46 2	93.79 54	98.52 15	98.24 48	93.19 108	97.14 60	98.34 59	91.59 56	99.87 7	95.46 99	99.59 19	99.64 18

PS-CasMVS		91.55 236	90.84 236	93.69 260	94.96 298	88.28 242	97.84 85	98.24 48	91.46 163	88.04 313	95.80 224	79.67 258	97.48 332	87.02 278	84.54 349	95.31 298

DU-MVS		92.90 182	92.04 189	95.49 163	94.95 299	92.83 81	97.16 172	98.24 48	93.02 116	90.13 250	95.71 231	83.47 181	97.85 297	91.71 178	83.93 355	95.78 271

9.14			96.75 46		98.93 50		97.73 99	98.23 51	91.28 172	97.88 39	98.44 48	93.00 26	99.65 63	95.76 86	99.47 40

reproduce_model		97.51 14	97.51 13	97.50 49	98.99 46	93.01 77	97.79 93	98.21 52	95.73 15	97.99 35	99.03 8	92.63 36	99.82 28	97.80 20	99.42 50	99.67 13

D2MVS		91.30 252	90.95 230	92.35 305	94.71 314	85.52 306	96.18 257	98.21 52	88.89 254	86.60 341	93.82 324	79.92 254	97.95 287	89.29 228	90.95 276	93.56 362

reproduce-ours		97.53 12	97.51 13	97.60 46	98.97 47	93.31 68	97.71 104	98.20 54	95.80 12	97.88 39	98.98 11	92.91 27	99.81 30	97.68 22	99.43 48	99.67 13

our_new_method		97.53 12	97.51 13	97.60 46	98.97 47	93.31 68	97.71 104	98.20 54	95.80 12	97.88 39	98.98 11	92.91 27	99.81 30	97.68 22	99.43 48	99.67 13

SDMVSNet		94.17 128	93.61 133	95.86 140	98.09 104	91.37 135	97.35 152	98.20 54	93.18 110	91.79 211	97.28 141	79.13 266	98.93 174	94.61 122	92.84 242	97.28 223

XVS		97.18 24	96.96 31	97.81 28	99.38 14	94.03 50	98.59 12	98.20 54	94.85 39	96.59 83	98.29 68	91.70 52	99.80 33	95.66 88	99.40 55	99.62 20

X-MVStestdata		91.71 225	89.67 289	97.81 28	99.38 14	94.03 50	98.59 12	98.20 54	94.85 39	96.59 83	32.69 422	91.70 52	99.80 33	95.66 88	99.40 55	99.62 20

ACMMP_NAP		97.20 23	96.86 35	98.23 11	99.09 34	95.16 22	97.60 120	98.19 59	92.82 128	97.93 38	98.74 30	91.60 55	99.86 9	96.26 60	99.52 30	99.67 13

CP-MVSNet		91.89 221	91.24 220	93.82 252	95.05 295	88.57 233	97.82 89	98.19 59	91.70 156	88.21 309	95.76 229	81.96 218	97.52 330	87.86 253	84.65 343	95.37 294

ZNCC-MVS		96.96 33	96.67 49	97.85 25	99.37 16	94.12 46	98.49 19	98.18 61	92.64 133	96.39 93	98.18 75	91.61 54	99.88 4	95.59 98	99.55 26	99.57 28

SMA-MVS		97.35 19	97.03 27	98.30 8	99.06 38	95.42 10	97.94 73	98.18 61	90.57 203	98.85 17	98.94 14	93.33 23	99.83 26	96.72 50	99.68 4	99.63 19
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		91.20 257	90.44 253	93.48 269	94.49 322	87.91 256	97.76 95	98.18 61	91.29 169	87.78 317	95.74 230	80.35 245	97.33 343	85.46 302	82.96 365	95.19 309

DELS-MVS		96.61 57	96.38 65	97.30 57	97.79 126	93.19 73	95.96 267	98.18 61	95.23 24	95.87 112	97.65 118	91.45 57	99.70 56	95.87 80	99.44 47	99.00 96
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		89.70 307	88.40 313	93.60 263	95.15 290	90.10 180	97.56 124	98.16 65	87.28 306	86.16 345	94.63 281	77.57 294	98.05 267	74.48 384	84.59 347	92.65 375

VNet		95.89 81	95.45 84	97.21 65	98.07 108	92.94 80	97.50 132	98.15 66	93.87 80	97.52 46	97.61 124	85.29 153	99.53 96	95.81 85	95.27 198	99.16 76

DeepPCF-MVS	93.97 1	96.61 57	97.09 21	95.15 175	98.09 104	86.63 286	96.00 265	98.15 66	95.43 19	97.95 37	98.56 35	93.40 21	99.36 119	96.77 47	99.48 39	99.45 50

SD-MVS		97.41 17	97.53 11	97.06 73	98.57 72	94.46 34	97.92 75	98.14 68	94.82 43	99.01 8	98.55 37	94.18 14	97.41 339	96.94 43	99.64 14	99.32 65
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 41	96.52 55	97.82 27	99.36 18	94.14 45	98.29 29	98.13 69	92.72 130	96.70 75	98.06 82	91.35 61	99.86 9	94.83 113	99.28 66	99.47 49

UA-Net		95.95 79	95.53 80	97.20 66	97.67 131	92.98 79	97.65 111	98.13 69	94.81 44	96.61 81	98.35 56	88.87 95	99.51 101	90.36 203	97.35 153	99.11 84

QAPM		93.45 158	92.27 184	96.98 76	96.77 189	92.62 87	98.39 24	98.12 71	84.50 351	88.27 307	97.77 109	82.39 211	99.81 30	85.40 303	98.81 99	98.51 141

Vis-MVSNet		95.23 99	94.81 102	96.51 92	97.18 156	91.58 126	98.26 34	98.12 71	94.38 68	94.90 136	98.15 77	82.28 212	98.92 175	91.45 185	98.58 110	99.01 93
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 184	91.68 203	96.40 102	95.34 274	92.73 85	98.27 32	98.12 71	84.86 346	85.78 347	97.75 110	78.89 276	99.74 45	87.50 268	98.65 105	96.73 239

TranMVSNet+NR-MVSNet		92.50 193	91.63 204	95.14 176	94.76 310	92.07 107	97.53 129	98.11 74	92.90 126	89.56 271	96.12 208	83.16 188	97.60 322	89.30 227	83.20 364	95.75 275

CPTT-MVS		95.57 91	95.19 94	96.70 78	99.27 26	91.48 130	98.33 26	98.11 74	87.79 291	95.17 132	98.03 85	87.09 131	99.61 74	93.51 141	99.42 50	99.02 90

APD-MVS		96.95 34	96.60 51	98.01 20	99.03 41	94.93 27	97.72 102	98.10 76	91.50 161	98.01 34	98.32 64	92.33 42	99.58 82	94.85 111	99.51 33	99.53 39
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 39	96.60 51	97.64 44	99.40 11	93.44 61	98.50 18	98.09 77	93.27 104	95.95 111	98.33 62	91.04 69	99.88 4	95.20 102	99.57 25	99.60 23

ZD-MVS					99.05 39	94.59 32		98.08 78	89.22 241	97.03 65	98.10 78	92.52 39	99.65 63	94.58 123	99.31 65

MTGPA								98.08 78

MTAPA		97.08 28	96.78 44	97.97 23	99.37 16	94.42 36	97.24 162	98.08 78	95.07 32	96.11 103	98.59 34	90.88 74	99.90 2	96.18 72	99.50 35	99.58 27

CNVR-MVS		97.68 6	97.44 16	98.37 7	98.90 53	95.86 6	97.27 160	98.08 78	95.81 11	97.87 42	98.31 65	94.26 13	99.68 59	97.02 42	99.49 38	99.57 28

DP-MVS Recon		95.68 86	95.12 98	97.37 54	99.19 31	94.19 42	97.03 179	98.08 78	88.35 274	95.09 134	97.65 118	89.97 85	99.48 106	92.08 170	98.59 109	98.44 152

SR-MVS		97.01 32	96.86 35	97.47 51	99.09 34	93.27 70	97.98 63	98.07 83	93.75 83	97.45 48	98.48 45	91.43 59	99.59 79	96.22 63	99.27 67	99.54 36

MCST-MVS		97.18 24	96.84 37	98.20 14	99.30 24	95.35 15	97.12 175	98.07 83	93.54 93	96.08 105	97.69 113	93.86 16	99.71 51	96.50 56	99.39 57	99.55 34

NR-MVSNet		92.34 201	91.27 219	95.53 160	94.95 299	93.05 76	97.39 148	98.07 83	92.65 132	84.46 358	95.71 231	85.00 157	97.77 307	89.71 215	83.52 361	95.78 271

MP-MVS-pluss		96.70 51	96.27 68	97.98 22	99.23 30	94.71 29	96.96 189	98.06 86	90.67 194	95.55 124	98.78 29	91.07 68	99.86 9	96.58 54	99.55 26	99.38 61
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 45	96.71 48	97.12 69	99.01 45	92.31 98	97.98 63	98.06 86	93.11 114	97.44 49	98.55 37	90.93 72	99.55 92	96.06 73	99.25 71	99.51 40

MP-MVS		96.77 47	96.45 62	97.72 38	99.39 13	93.80 53	98.41 23	98.06 86	93.37 100	95.54 126	98.34 59	90.59 78	99.88 4	94.83 113	99.54 28	99.49 45
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 60	96.27 68	97.22 64	99.32 22	92.74 84	98.74 9	98.06 86	90.57 203	96.77 72	98.35 56	90.21 81	99.53 96	94.80 116	99.63 16	99.38 61

HPM-MVS		96.69 53	96.45 62	97.40 53	99.36 18	93.11 75	98.87 6	98.06 86	91.17 177	96.40 92	97.99 89	90.99 70	99.58 82	95.61 95	99.61 18	99.49 45
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 120	93.80 128	96.64 80	97.07 162	91.97 111	96.32 246	98.06 86	88.94 252	94.50 146	96.78 167	84.60 161	99.27 128	91.90 171	96.02 181	98.68 129

DeepC-MVS	93.07 3	96.06 73	95.66 78	97.29 58	97.96 115	93.17 74	97.30 158	98.06 86	93.92 78	93.38 173	98.66 31	86.83 133	99.73 47	95.60 97	99.22 73	98.96 98
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 21	97.03 27	98.11 17	98.77 56	95.06 25	97.34 153	98.04 93	95.96 8	97.09 63	97.88 97	93.18 25	99.71 51	95.84 84	99.17 78	99.56 31

DeepC-MVS_fast	93.89 2	96.93 36	96.64 50	97.78 31	98.64 67	94.30 37	97.41 143	98.04 93	94.81 44	96.59 83	98.37 54	91.24 64	99.64 71	95.16 104	99.52 30	99.42 56
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 38	96.80 43	97.11 70	99.02 42	92.34 96	97.98 63	98.03 95	93.52 95	97.43 51	98.51 40	91.40 60	99.56 90	96.05 74	99.26 69	99.43 54

RE-MVS-def			96.72 47		99.02 42	92.34 96	97.98 63	98.03 95	93.52 95	97.43 51	98.51 40	90.71 76		96.05 74	99.26 69	99.43 54

RPMNet		88.98 313	87.05 327	94.77 201	94.45 324	87.19 271	90.23 397	98.03 95	77.87 398	92.40 190	87.55 402	80.17 249	99.51 101	68.84 403	93.95 229	97.60 208

save fliter					98.91 52	94.28 38	97.02 181	98.02 98	95.35 21

TEST9					98.70 59	94.19 42	96.41 235	98.02 98	88.17 278	96.03 106	97.56 128	92.74 33	99.59 79

train_agg		96.30 69	95.83 77	97.72 38	98.70 59	94.19 42	96.41 235	98.02 98	88.58 265	96.03 106	97.56 128	92.73 34	99.59 79	95.04 106	99.37 61	99.39 59

test_8					98.67 61	94.06 49	96.37 242	98.01 101	88.58 265	95.98 110	97.55 130	92.73 34	99.58 82

agg_prior					98.67 61	93.79 54		98.00 102		95.68 120			99.57 89

test_prior				97.23 63	98.67 61	92.99 78		98.00 102					99.41 114			99.29 66

WR-MVS		92.34 201	91.53 208	94.77 201	95.13 292	90.83 158	96.40 239	97.98 104	91.88 152	89.29 280	95.54 242	82.50 207	97.80 303	89.79 214	85.27 334	95.69 278

HPM-MVS++		97.34 20	96.97 30	98.47 5	99.08 36	96.16 4	97.55 128	97.97 105	95.59 16	96.61 81	97.89 95	92.57 38	99.84 23	95.95 79	99.51 33	99.40 57

CANet		96.39 65	96.02 72	97.50 49	97.62 138	93.38 63	97.02 181	97.96 106	95.42 20	94.86 137	97.81 106	87.38 127	99.82 28	96.88 45	99.20 76	99.29 66

114514_t		93.95 140	93.06 153	96.63 82	99.07 37	91.61 123	97.46 141	97.96 106	77.99 396	93.00 181	97.57 126	86.14 145	99.33 120	89.22 231	99.15 81	98.94 101

IU-MVS					99.42 7	95.39 11		97.94 108	90.40 209	98.94 10				97.41 37	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 109					99.86 9	97.68 22	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 109					99.86 9	97.68 22	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 68	96.44 64	96.00 134	97.30 151	90.37 176	97.53 129	97.92 111	96.52 4	99.14 7	99.08 3	83.21 186	99.74 45	99.22 5	98.06 132	97.88 189

Anonymous20231211		90.63 281	89.42 296	94.27 228	98.24 90	89.19 220	98.05 57	97.89 112	79.95 388	88.25 308	94.96 263	72.56 332	98.13 250	89.70 216	85.14 336	95.49 282

原ACMM1				96.38 105	98.59 69	91.09 150		97.89 112	87.41 302	95.22 131	97.68 114	90.25 80	99.54 94	87.95 252	99.12 85	98.49 144

CDPH-MVS		95.97 78	95.38 89	97.77 33	98.93 50	94.44 35	96.35 243	97.88 114	86.98 310	96.65 79	97.89 95	91.99 48	99.47 107	92.26 161	99.46 41	99.39 59

test11								97.88 114

EIA-MVS		95.53 92	95.47 83	95.71 150	97.06 165	89.63 194	97.82 89	97.87 116	93.57 89	93.92 161	95.04 261	90.61 77	98.95 171	94.62 121	98.68 104	98.54 137

CS-MVS		96.86 39	97.06 22	96.26 115	98.16 101	91.16 148	99.09 3	97.87 116	95.30 23	97.06 64	98.03 85	91.72 50	98.71 201	97.10 40	99.17 78	98.90 108

无先验							95.79 277	97.87 116	83.87 359				99.65 63	87.68 262		98.89 112

3Dnovator+	91.43 4	95.40 93	94.48 116	98.16 16	96.90 175	95.34 16	98.48 20	97.87 116	94.65 54	88.53 299	98.02 87	83.69 177	99.71 51	93.18 148	98.96 94	99.44 52

VPNet		92.23 209	91.31 216	94.99 184	95.56 259	90.96 153	97.22 167	97.86 120	92.96 123	90.96 233	96.62 184	75.06 314	98.20 244	91.90 171	83.65 360	95.80 269

test_vis1_n_1920		94.17 128	94.58 109	92.91 289	97.42 149	82.02 356	97.83 87	97.85 121	94.68 51	98.10 32	98.49 42	70.15 350	99.32 122	97.91 19	98.82 98	97.40 217

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 121	94.92 37	98.73 20	98.87 20	95.08 8	99.84 23	97.52 30	99.67 6	99.48 47
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 16	97.33 18	97.69 41	99.25 27	94.24 41	98.07 55	97.85 121	93.72 84	98.57 23	98.35 56	93.69 18	99.40 115	97.06 41	99.46 41	99.44 52
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
SPE-MVS-test		96.89 37	97.04 26	96.45 99	98.29 85	91.66 122	99.03 4	97.85 121	95.84 9	96.90 67	97.97 91	91.24 64	98.75 194	96.92 44	99.33 63	98.94 101

test_fmvsmconf0.01_n		96.15 72	95.85 76	97.03 74	92.66 371	91.83 115	97.97 69	97.84 125	95.57 17	97.53 45	99.00 9	84.20 170	99.76 41	98.82 13	99.08 87	99.48 47

GDP-MVS		95.62 88	95.13 96	97.09 71	96.79 186	93.26 71	97.89 79	97.83 126	93.58 88	96.80 69	97.82 105	83.06 193	99.16 142	94.40 125	97.95 136	98.87 114

balanced_conf03		96.84 43	96.89 34	96.68 79	97.63 137	92.22 101	98.17 48	97.82 127	94.44 63	98.23 30	97.36 138	90.97 71	99.22 132	97.74 21	99.66 10	98.61 132

AdaColmap		94.34 124	93.68 131	96.31 109	98.59 69	91.68 121	96.59 226	97.81 128	89.87 219	92.15 200	97.06 155	83.62 180	99.54 94	89.34 226	98.07 131	97.70 201

MVSMamba_PlusPlus		96.51 60	96.48 57	96.59 85	98.07 108	91.97 111	98.14 49	97.79 129	90.43 207	97.34 54	97.52 131	91.29 63	99.19 135	98.12 17	99.64 14	98.60 133

mamv4		94.66 118	96.10 71	90.37 354	98.01 111	73.41 402	96.82 200	97.78 130	89.95 218	94.52 145	97.43 135	92.91 27	99.09 154	98.28 16	99.16 80	98.60 133

ETV-MVS		96.02 75	95.89 75	96.40 102	97.16 157	92.44 93	97.47 139	97.77 131	94.55 57	96.48 88	94.51 287	91.23 66	98.92 175	95.65 91	98.19 126	97.82 196

新几何1				97.32 56	98.60 68	93.59 58		97.75 132	81.58 379	95.75 117	97.85 101	90.04 83	99.67 61	86.50 284	99.13 83	98.69 128

旧先验1					98.38 81	93.38 63		97.75 132			98.09 80	92.30 45			99.01 92	99.16 76

EC-MVSNet		96.42 63	96.47 58	96.26 115	97.01 171	91.52 128	98.89 5	97.75 132	94.42 64	96.64 80	97.68 114	89.32 89	98.60 211	97.45 34	99.11 86	98.67 130

EI-MVSNet-Vis-set		96.51 60	96.47 58	96.63 82	98.24 90	91.20 143	96.89 193	97.73 135	94.74 49	96.49 87	98.49 42	90.88 74	99.58 82	96.44 58	98.32 121	99.13 80

PAPM_NR		95.01 104	94.59 108	96.26 115	98.89 54	90.68 165	97.24 162	97.73 135	91.80 153	92.93 186	96.62 184	89.13 92	99.14 147	89.21 232	97.78 140	98.97 97

Anonymous20240529		91.98 217	90.73 243	95.73 148	98.14 102	89.40 207	97.99 62	97.72 137	79.63 390	93.54 168	97.41 136	69.94 352	99.56 90	91.04 193	91.11 272	98.22 165

CHOSEN 280x420		93.12 170	92.72 168	94.34 222	96.71 193	87.27 267	90.29 396	97.72 137	86.61 317	91.34 222	95.29 249	84.29 169	98.41 225	93.25 147	98.94 95	97.35 220

EI-MVSNet-UG-set		96.34 67	96.30 67	96.47 96	98.20 96	90.93 155	96.86 195	97.72 137	94.67 52	96.16 102	98.46 46	90.43 79	99.58 82	96.23 62	97.96 135	98.90 108

LS3D		93.57 154	92.61 172	96.47 96	97.59 141	91.61 123	97.67 108	97.72 137	85.17 341	90.29 244	98.34 59	84.60 161	99.73 47	83.85 324	98.27 123	98.06 180

PAPR		94.18 127	93.42 146	96.48 95	97.64 135	91.42 134	95.55 289	97.71 141	88.99 249	92.34 196	95.82 223	89.19 90	99.11 150	86.14 290	97.38 151	98.90 108

UGNet		94.04 138	93.28 149	96.31 109	96.85 178	91.19 144	97.88 80	97.68 142	94.40 66	93.00 181	96.18 203	73.39 329	99.61 74	91.72 177	98.46 115	98.13 173
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				95.46 167	98.18 100	88.90 226		97.66 143	82.73 370	97.03 65	98.07 81	90.06 82	98.85 182	89.67 217	98.98 93	98.64 131

test12				97.65 42	98.46 73	94.26 39		97.66 143		95.52 127		90.89 73	99.46 108		99.25 71	99.22 73

DTE-MVSNet		90.56 282	89.75 287	93.01 285	93.95 337	87.25 268	97.64 115	97.65 145	90.74 189	87.12 329	95.68 234	79.97 253	97.00 355	83.33 325	81.66 371	94.78 336

TAPA-MVS	90.10 7	92.30 204	91.22 222	95.56 157	98.33 83	89.60 196	96.79 202	97.65 145	81.83 376	91.52 217	97.23 146	87.94 111	98.91 177	71.31 398	98.37 119	98.17 171
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 171	92.45 180	95.05 180	98.09 104	89.21 217	96.89 193	97.64 147	93.18 110	91.79 211	97.28 141	75.35 313	98.65 206	88.99 237	92.84 242	97.28 223

test_cas_vis1_n_1920		94.48 122	94.55 113	94.28 227	96.78 187	86.45 291	97.63 117	97.64 147	93.32 103	97.68 44	98.36 55	73.75 327	99.08 157	96.73 49	99.05 89	97.31 222

cdsmvs_eth3d_5k		23.24 392	30.99 394	0.00 410	0.00 433	0.00 435	0.00 421	97.63 149	0.00 428	0.00 429	96.88 164	84.38 166	0.00 429	0.00 428	0.00 427	0.00 425

DPM-MVS		95.69 85	94.92 100	98.01 20	98.08 107	95.71 9	95.27 304	97.62 150	90.43 207	95.55 124	97.07 154	91.72 50	99.50 104	89.62 219	98.94 95	98.82 120

sasdasda		96.02 75	95.45 84	97.75 35	97.59 141	95.15 23	98.28 30	97.60 151	94.52 59	96.27 97	96.12 208	87.65 116	99.18 138	96.20 68	94.82 207	98.91 105

canonicalmvs		96.02 75	95.45 84	97.75 35	97.59 141	95.15 23	98.28 30	97.60 151	94.52 59	96.27 97	96.12 208	87.65 116	99.18 138	96.20 68	94.82 207	98.91 105

test222					98.24 90	92.21 102	95.33 299	97.60 151	79.22 392	95.25 129	97.84 103	88.80 97			99.15 81	98.72 125

cascas		91.20 257	90.08 270	94.58 210	94.97 297	89.16 221	93.65 361	97.59 154	79.90 389	89.40 275	92.92 349	75.36 312	98.36 232	92.14 166	94.75 210	96.23 249

h-mvs33		94.15 130	93.52 139	96.04 128	97.81 125	90.22 179	97.62 119	97.58 155	95.19 25	96.74 73	97.45 132	83.67 178	99.61 74	95.85 82	79.73 378	98.29 162

MGCFI-Net		95.94 80	95.40 88	97.56 48	97.59 141	94.62 31	98.21 42	97.57 156	94.41 65	96.17 101	96.16 206	87.54 120	99.17 140	96.19 70	94.73 212	98.91 105

MVSFormer		95.37 94	95.16 95	95.99 135	96.34 224	91.21 141	98.22 40	97.57 156	91.42 165	96.22 99	97.32 139	86.20 143	97.92 291	94.07 129	99.05 89	98.85 116

test_djsdf		93.07 173	92.76 163	94.00 239	93.49 353	88.70 230	98.22 40	97.57 156	91.42 165	90.08 256	95.55 241	82.85 199	97.92 291	94.07 129	91.58 263	95.40 291

OMC-MVS		95.09 103	94.70 106	96.25 118	98.46 73	91.28 137	96.43 233	97.57 156	92.04 148	94.77 140	97.96 92	87.01 132	99.09 154	91.31 187	96.77 168	98.36 159

PS-MVSNAJss		93.74 149	93.51 140	94.44 216	93.91 339	89.28 215	97.75 96	97.56 160	92.50 134	89.94 258	96.54 187	88.65 100	98.18 247	93.83 138	90.90 277	95.86 263

casdiffmvs_mvg		95.81 84	95.57 79	96.51 92	96.87 176	91.49 129	97.50 132	97.56 160	93.99 76	95.13 133	97.92 94	87.89 112	98.78 189	95.97 78	97.33 154	99.26 70
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		92.42 197	91.89 196	94.03 238	93.33 359	88.50 237	97.73 99	97.53 162	92.00 150	88.85 291	96.50 189	75.62 311	98.11 254	93.88 136	91.56 264	95.48 283

mvs_tets		92.31 203	91.76 199	93.94 246	93.41 356	88.29 241	97.63 117	97.53 162	92.04 148	88.76 294	96.45 191	74.62 319	98.09 259	93.91 134	91.48 265	95.45 287

dcpmvs_2		96.37 66	97.05 25	94.31 225	98.96 49	84.11 331	97.56 124	97.51 164	93.92 78	97.43 51	98.52 39	92.75 32	99.32 122	97.32 39	99.50 35	99.51 40

HQP_MVS		93.78 148	93.43 144	94.82 194	96.21 228	89.99 184	97.74 97	97.51 164	94.85 39	91.34 222	96.64 177	81.32 228	98.60 211	93.02 154	92.23 251	95.86 263

plane_prior5								97.51 164					98.60 211	93.02 154	92.23 251	95.86 263

reproduce_monomvs		91.30 252	91.10 226	91.92 316	96.82 183	82.48 350	97.01 184	97.49 167	94.64 55	88.35 302	95.27 252	70.53 345	98.10 255	95.20 102	84.60 346	95.19 309

PS-MVSNAJ		95.37 94	95.33 91	95.49 163	97.35 150	90.66 166	95.31 301	97.48 168	93.85 81	96.51 86	95.70 233	88.65 100	99.65 63	94.80 116	98.27 123	96.17 253

API-MVS		94.84 113	94.49 115	95.90 137	97.90 121	92.00 110	97.80 92	97.48 168	89.19 242	94.81 138	96.71 170	88.84 96	99.17 140	88.91 239	98.76 102	96.53 242

MG-MVS		95.61 89	95.38 89	96.31 109	98.42 76	90.53 168	96.04 262	97.48 168	93.47 97	95.67 121	98.10 78	89.17 91	99.25 129	91.27 188	98.77 101	99.13 80

MAR-MVS		94.22 126	93.46 142	96.51 92	98.00 113	92.19 105	97.67 108	97.47 171	88.13 281	93.00 181	95.84 221	84.86 159	99.51 101	87.99 251	98.17 128	97.83 195
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		92.98 177	92.53 176	94.32 223	96.12 238	89.20 218	95.28 302	97.47 171	92.66 131	89.90 259	95.62 237	80.58 240	98.40 226	92.73 159	92.40 249	95.38 293
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 250	90.22 266	94.68 204	94.86 306	87.86 257	97.23 166	97.46 173	87.99 282	89.90 259	96.92 162	66.35 377	98.23 241	90.30 204	90.99 275	97.96 184

nrg030		94.05 137	93.31 148	96.27 114	95.22 285	94.59 32	98.34 25	97.46 173	92.93 124	91.21 231	96.64 177	87.23 130	98.22 242	94.99 109	85.80 326	95.98 262

XVG-OURS		93.72 150	93.35 147	94.80 199	97.07 162	88.61 231	94.79 319	97.46 173	91.97 151	93.99 158	97.86 100	81.74 223	98.88 179	92.64 160	92.67 247	96.92 234

LPG-MVS_test		92.94 180	92.56 173	94.10 233	96.16 233	88.26 243	97.65 111	97.46 173	91.29 169	90.12 252	97.16 149	79.05 269	98.73 197	92.25 163	91.89 259	95.31 298

LGP-MVS_train				94.10 233	96.16 233	88.26 243		97.46 173	91.29 169	90.12 252	97.16 149	79.05 269	98.73 197	92.25 163	91.89 259	95.31 298

MVS		91.71 225	90.44 253	95.51 161	95.20 287	91.59 125	96.04 262	97.45 178	73.44 406	87.36 326	95.60 238	85.42 152	99.10 151	85.97 295	97.46 146	95.83 267

XVG-OURS-SEG-HR		93.86 145	93.55 135	94.81 196	97.06 165	88.53 236	95.28 302	97.45 178	91.68 157	94.08 157	97.68 114	82.41 210	98.90 178	93.84 137	92.47 248	96.98 230

baseline		95.58 90	95.42 87	96.08 124	96.78 187	90.41 174	97.16 172	97.45 178	93.69 87	95.65 122	97.85 101	87.29 128	98.68 203	95.66 88	97.25 159	99.13 80

ab-mvs		93.57 154	92.55 174	96.64 80	97.28 152	91.96 113	95.40 296	97.45 178	89.81 224	93.22 179	96.28 199	79.62 260	99.46 108	90.74 197	93.11 239	98.50 142

xiu_mvs_v2_base		95.32 96	95.29 92	95.40 168	97.22 153	90.50 169	95.44 295	97.44 182	93.70 86	96.46 90	96.18 203	88.59 103	99.53 96	94.79 118	97.81 139	96.17 253

1314		92.81 188	92.03 190	95.14 176	95.33 277	89.52 202	96.04 262	97.44 182	87.72 295	86.25 344	95.33 248	83.84 175	98.79 188	89.26 229	97.05 164	97.11 228

casdiffmvs		95.64 87	95.49 81	96.08 124	96.76 192	90.45 171	97.29 159	97.44 182	94.00 75	95.46 128	97.98 90	87.52 123	98.73 197	95.64 92	97.33 154	99.08 87
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		92.16 211	91.23 221	94.95 190	94.75 311	90.94 154	97.47 139	97.43 185	89.14 243	88.90 288	96.43 192	79.71 257	98.24 240	89.56 220	87.68 308	95.67 279

anonymousdsp		92.16 211	91.55 207	93.97 242	92.58 373	89.55 199	97.51 131	97.42 186	89.42 236	88.40 301	94.84 270	80.66 239	97.88 296	91.87 173	91.28 269	94.48 344

Effi-MVS+		94.93 109	94.45 117	96.36 107	96.61 197	91.47 131	96.41 235	97.41 187	91.02 183	94.50 146	95.92 217	87.53 121	98.78 189	93.89 135	96.81 167	98.84 119

RRT-MVS		94.51 120	94.35 120	94.98 186	96.40 220	86.55 289	97.56 124	97.41 187	93.19 108	94.93 135	97.04 156	79.12 267	99.30 126	96.19 70	97.32 156	99.09 86

HQP3-MVS								97.39 189							92.10 256

HQP-MVS		93.19 167	92.74 166	94.54 212	95.86 245	89.33 211	96.65 217	97.39 189	93.55 90	90.14 246	95.87 219	80.95 232	98.50 219	92.13 167	92.10 256	95.78 271

PLC	91.00 6	94.11 134	93.43 144	96.13 123	98.58 71	91.15 149	96.69 213	97.39 189	87.29 305	91.37 221	96.71 170	88.39 104	99.52 100	87.33 271	97.13 163	97.73 199
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 274	89.86 280	93.45 271	93.54 350	87.60 263	97.70 107	97.37 192	88.85 255	87.65 319	94.08 315	81.08 231	98.10 255	84.68 311	83.79 359	94.66 341

UnsupCasMVSNet_eth		85.99 347	84.45 352	90.62 350	89.97 391	82.40 353	93.62 362	97.37 192	89.86 220	78.59 393	92.37 359	65.25 385	95.35 385	82.27 338	70.75 401	94.10 355

ACMM	89.79 8	92.96 178	92.50 178	94.35 220	96.30 226	88.71 229	97.58 121	97.36 194	91.40 167	90.53 239	96.65 176	79.77 256	98.75 194	91.24 189	91.64 261	95.59 281
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 104	94.76 103	95.75 145	96.58 200	91.71 118	96.25 251	97.35 195	92.99 117	96.70 75	96.63 181	82.67 202	99.44 111	96.22 63	97.46 146	96.11 258

xiu_mvs_v1_base		95.01 104	94.76 103	95.75 145	96.58 200	91.71 118	96.25 251	97.35 195	92.99 117	96.70 75	96.63 181	82.67 202	99.44 111	96.22 63	97.46 146	96.11 258

xiu_mvs_v1_base_debi		95.01 104	94.76 103	95.75 145	96.58 200	91.71 118	96.25 251	97.35 195	92.99 117	96.70 75	96.63 181	82.67 202	99.44 111	96.22 63	97.46 146	96.11 258

diffmvs		95.25 98	95.13 96	95.63 153	96.43 219	89.34 210	95.99 266	97.35 195	92.83 127	96.31 95	97.37 137	86.44 138	98.67 204	96.26 60	97.19 161	98.87 114
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		94.71 117	94.02 124	96.79 77	97.71 130	92.05 108	96.59 226	97.35 195	90.61 200	94.64 142	96.93 159	86.41 139	99.39 116	91.20 190	94.71 213	98.94 101

F-COLMAP		93.58 153	92.98 155	95.37 169	98.40 78	88.98 224	97.18 170	97.29 200	87.75 294	90.49 240	97.10 153	85.21 154	99.50 104	86.70 281	96.72 171	97.63 203

XVG-ACMP-BASELINE		90.93 270	90.21 267	93.09 283	94.31 330	85.89 301	95.33 299	97.26 201	91.06 182	89.38 276	95.44 246	68.61 360	98.60 211	89.46 222	91.05 273	94.79 334

PCF-MVS	89.48 11	91.56 235	89.95 277	96.36 107	96.60 198	92.52 91	92.51 381	97.26 201	79.41 391	88.90 288	96.56 186	84.04 174	99.55 92	77.01 375	97.30 157	97.01 229
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 192	92.14 187	94.05 236	96.40 220	88.20 246	97.36 151	97.25 203	91.52 160	88.30 305	96.64 177	78.46 281	98.72 200	91.86 174	91.48 265	95.23 305
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 163	92.76 163	94.82 194	94.63 317	90.77 161	96.65 217	97.18 204	93.72 84	91.68 215	97.26 144	79.33 264	98.63 208	92.13 167	92.28 250	95.07 312
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 182	92.02 191	95.56 157	98.19 98	90.80 159	95.27 304	97.18 204	87.96 283	91.86 210	95.68 234	80.44 243	98.99 169	84.01 319	97.54 145	96.89 235

alignmvs		95.87 83	95.23 93	97.78 31	97.56 146	95.19 21	97.86 81	97.17 206	94.39 67	96.47 89	96.40 194	85.89 146	99.20 134	96.21 67	95.11 203	98.95 100

MVS_Test		94.89 111	94.62 107	95.68 151	96.83 181	89.55 199	96.70 211	97.17 206	91.17 177	95.60 123	96.11 212	87.87 113	98.76 193	93.01 156	97.17 162	98.72 125

Fast-Effi-MVS+		93.46 157	92.75 165	95.59 156	96.77 189	90.03 181	96.81 201	97.13 208	88.19 277	91.30 225	94.27 304	86.21 142	98.63 208	87.66 263	96.46 178	98.12 174

EI-MVSNet		93.03 175	92.88 159	93.48 269	95.77 251	86.98 276	96.44 231	97.12 209	90.66 196	91.30 225	97.64 121	86.56 135	98.05 267	89.91 210	90.55 281	95.41 288

MVSTER		93.20 166	92.81 162	94.37 219	96.56 203	89.59 197	97.06 178	97.12 209	91.24 173	91.30 225	95.96 215	82.02 217	98.05 267	93.48 142	90.55 281	95.47 285

test_yl		94.78 115	94.23 121	96.43 100	97.74 128	91.22 139	96.85 196	97.10 211	91.23 174	95.71 118	96.93 159	84.30 167	99.31 124	93.10 149	95.12 201	98.75 122

DCV-MVSNet		94.78 115	94.23 121	96.43 100	97.74 128	91.22 139	96.85 196	97.10 211	91.23 174	95.71 118	96.93 159	84.30 167	99.31 124	93.10 149	95.12 201	98.75 122

LTVRE_ROB	88.41 13	90.99 266	89.92 279	94.19 229	96.18 231	89.55 199	96.31 247	97.09 213	87.88 286	85.67 348	95.91 218	78.79 277	98.57 215	81.50 341	89.98 286	94.44 347
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		92.73 190	92.88 159	92.29 308	96.08 241	81.05 364	97.98 63	97.08 214	90.72 191	96.79 71	98.18 75	63.07 389	98.45 223	97.62 28	98.42 118	97.36 218

v10		91.04 264	90.23 264	93.49 268	94.12 333	88.16 249	97.32 156	97.08 214	88.26 276	88.29 306	94.22 309	82.17 215	97.97 279	86.45 285	84.12 353	94.33 350

v144192		91.06 263	90.28 260	93.39 272	93.66 348	87.23 270	96.83 199	97.07 216	87.43 301	89.69 266	94.28 303	81.48 226	98.00 274	87.18 275	84.92 342	94.93 320

v1192		91.07 262	90.23 264	93.58 265	93.70 345	87.82 259	96.73 207	97.07 216	87.77 292	89.58 269	94.32 301	80.90 236	97.97 279	86.52 283	85.48 329	94.95 316

v8		91.29 254	90.53 252	93.57 266	94.15 332	88.12 250	97.34 153	97.06 218	88.99 249	88.32 304	94.26 306	83.08 191	98.01 273	87.62 265	83.92 357	94.57 343

mvs_anonymous		93.82 146	93.74 129	94.06 235	96.44 218	85.41 308	95.81 275	97.05 219	89.85 222	90.09 255	96.36 196	87.44 125	97.75 309	93.97 131	96.69 172	99.02 90

IterMVS-LS		92.29 205	91.94 194	93.34 274	96.25 227	86.97 277	96.57 229	97.05 219	90.67 194	89.50 274	94.80 273	86.59 134	97.64 317	89.91 210	86.11 324	95.40 291
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 272	90.03 275	93.29 276	93.55 349	86.96 278	96.74 206	97.04 221	87.36 303	89.52 273	94.34 298	80.23 248	97.97 279	86.27 286	85.21 335	94.94 318

CDS-MVSNet		94.14 133	93.54 136	95.93 136	96.18 231	91.46 132	96.33 245	97.04 221	88.97 251	93.56 166	96.51 188	87.55 119	97.89 295	89.80 213	95.95 183	98.44 152
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
v1144		91.37 247	90.60 248	93.68 261	93.89 340	88.23 245	96.84 198	97.03 223	88.37 273	89.69 266	94.39 294	82.04 216	97.98 276	87.80 255	85.37 331	94.84 326

v1240		90.70 278	89.85 281	93.23 278	93.51 352	86.80 279	96.61 223	97.02 224	87.16 308	89.58 269	94.31 302	79.55 261	97.98 276	85.52 301	85.44 330	94.90 323

EPP-MVSNet		95.22 100	95.04 99	95.76 143	97.49 147	89.56 198	98.67 10	97.00 225	90.69 192	94.24 152	97.62 123	89.79 87	98.81 186	93.39 146	96.49 176	98.92 104

V42		91.58 234	90.87 232	93.73 256	94.05 336	88.50 237	97.32 156	96.97 226	88.80 261	89.71 264	94.33 299	82.54 206	98.05 267	89.01 236	85.07 338	94.64 342

test_fmvs1		93.21 165	93.53 137	92.25 310	96.55 205	81.20 363	97.40 147	96.96 227	90.68 193	96.80 69	98.04 84	69.25 356	98.40 226	97.58 29	98.50 111	97.16 227

FMVSNet2		91.31 251	90.08 270	94.99 184	96.51 211	92.21 102	97.41 143	96.95 228	88.82 258	88.62 296	94.75 275	73.87 323	97.42 338	85.20 306	88.55 301	95.35 295

ACMH	87.59 16	90.53 283	89.42 296	93.87 250	96.21 228	87.92 254	97.24 162	96.94 229	88.45 271	83.91 368	96.27 200	71.92 335	98.62 210	84.43 314	89.43 292	95.05 314
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 248	90.27 261	94.59 206	96.51 211	91.18 145	97.50 132	96.93 230	88.82 258	89.35 277	94.51 287	73.87 323	97.29 345	86.12 291	88.82 296	95.31 298

test1		91.35 248	90.27 261	94.59 206	96.51 211	91.18 145	97.50 132	96.93 230	88.82 258	89.35 277	94.51 287	73.87 323	97.29 345	86.12 291	88.82 296	95.31 298

FMVSNet3		91.78 223	90.69 246	95.03 182	96.53 208	92.27 100	97.02 181	96.93 230	89.79 225	89.35 277	94.65 280	77.01 297	97.47 333	86.12 291	88.82 296	95.35 295

FMVSNet1		89.88 302	88.31 314	94.59 206	95.41 267	91.18 145	97.50 132	96.93 230	86.62 316	87.41 324	94.51 287	65.94 382	97.29 345	83.04 328	87.43 311	95.31 298

GeoE		93.89 143	93.28 149	95.72 149	96.96 174	89.75 193	98.24 38	96.92 234	89.47 233	92.12 202	97.21 147	84.42 165	98.39 230	87.71 258	96.50 175	99.01 93

miper_enhance_ethall		91.54 238	91.01 229	93.15 281	95.35 273	87.07 275	93.97 347	96.90 235	86.79 314	89.17 284	93.43 344	86.55 136	97.64 317	89.97 209	86.93 316	94.74 338

eth_miper_zixun_eth		91.02 265	90.59 249	92.34 307	95.33 277	84.35 327	94.10 344	96.90 235	88.56 267	88.84 292	94.33 299	84.08 172	97.60 322	88.77 242	84.37 351	95.06 313

TAMVS		94.01 139	93.46 142	95.64 152	96.16 233	90.45 171	96.71 210	96.89 237	89.27 240	93.46 171	96.92 162	87.29 128	97.94 288	88.70 243	95.74 188	98.53 138

miper_ehance_all_eth		91.59 232	91.13 225	92.97 287	95.55 260	86.57 287	94.47 328	96.88 238	87.77 292	88.88 290	94.01 317	86.22 141	97.54 326	89.49 221	86.93 316	94.79 334

v2v482		91.59 232	90.85 235	93.80 253	93.87 341	88.17 248	96.94 190	96.88 238	89.54 230	89.53 272	94.90 267	81.70 224	98.02 272	89.25 230	85.04 340	95.20 306

CNLPA		94.28 125	93.53 137	96.52 89	98.38 81	92.55 90	96.59 226	96.88 238	90.13 215	91.91 207	97.24 145	85.21 154	99.09 154	87.64 264	97.83 138	97.92 186

PAPM		91.52 239	90.30 259	95.20 173	95.30 280	89.83 191	93.38 367	96.85 241	86.26 324	88.59 297	95.80 224	84.88 158	98.15 249	75.67 380	95.93 184	97.63 203

c3_l		91.38 245	90.89 231	92.88 291	95.58 258	86.30 294	94.68 321	96.84 242	88.17 278	88.83 293	94.23 307	85.65 150	97.47 333	89.36 225	84.63 344	94.89 324

pm-mvs1		90.72 277	89.65 291	93.96 243	94.29 331	89.63 194	97.79 93	96.82 243	89.07 245	86.12 346	95.48 245	78.61 279	97.78 305	86.97 279	81.67 370	94.46 345

test_vis1_n		92.37 200	92.26 185	92.72 297	94.75 311	82.64 346	98.02 59	96.80 244	91.18 176	97.77 43	97.93 93	58.02 398	98.29 238	97.63 27	98.21 125	97.23 226

CMPMVS	62.92 21	85.62 352	84.92 348	87.74 374	89.14 396	73.12 404	94.17 342	96.80 244	73.98 403	73.65 402	94.93 265	66.36 376	97.61 321	83.95 321	91.28 269	92.48 380
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 290	89.77 285	91.78 325	94.33 328	84.72 324	95.55 289	96.73 246	86.17 326	86.36 343	95.28 251	71.28 340	97.80 303	84.09 318	98.14 129	92.81 372

Effi-MVS+-dtu		93.08 172	93.21 151	92.68 300	96.02 242	83.25 341	97.14 174	96.72 247	93.85 81	91.20 232	93.44 341	83.08 191	98.30 237	91.69 180	95.73 189	96.50 244

TSAR-MVS + GP.		96.69 53	96.49 56	97.27 61	98.31 84	93.39 62	96.79 202	96.72 247	94.17 71	97.44 49	97.66 117	92.76 31	99.33 120	96.86 46	97.76 142	99.08 87

1112_ss		93.37 160	92.42 181	96.21 119	97.05 167	90.99 151	96.31 247	96.72 247	86.87 313	89.83 262	96.69 174	86.51 137	99.14 147	88.12 248	93.67 233	98.50 142

PVSNet	86.66 18	92.24 208	91.74 202	93.73 256	97.77 127	83.69 338	92.88 376	96.72 247	87.91 285	93.00 181	94.86 269	78.51 280	99.05 164	86.53 282	97.45 150	98.47 147

miper_lstm_enhance		90.50 286	90.06 274	91.83 321	95.33 277	83.74 335	93.86 353	96.70 251	87.56 299	87.79 316	93.81 325	83.45 183	96.92 357	87.39 269	84.62 345	94.82 329

v148		90.99 266	90.38 255	92.81 294	93.83 342	85.80 302	96.78 204	96.68 252	89.45 235	88.75 295	93.93 321	82.96 197	97.82 301	87.83 254	83.25 362	94.80 332

ACMH+	87.92 14	90.20 294	89.18 301	93.25 277	96.48 214	86.45 291	96.99 186	96.68 252	88.83 257	84.79 357	96.22 202	70.16 349	98.53 217	84.42 315	88.04 304	94.77 337

CANet_DTU		94.37 123	93.65 132	96.55 87	96.46 217	92.13 106	96.21 255	96.67 254	94.38 68	93.53 169	97.03 157	79.34 263	99.71 51	90.76 196	98.45 116	97.82 196

cl____		90.96 269	90.32 257	92.89 290	95.37 271	86.21 297	94.46 330	96.64 255	87.82 288	88.15 311	94.18 310	82.98 195	97.54 326	87.70 259	85.59 327	94.92 322

HY-MVS	89.66 9	93.87 144	92.95 156	96.63 82	97.10 161	92.49 92	95.64 287	96.64 255	89.05 247	93.00 181	95.79 227	85.77 149	99.45 110	89.16 235	94.35 215	97.96 184

Test_1112_low_res		92.84 186	91.84 197	95.85 141	97.04 168	89.97 187	95.53 291	96.64 255	85.38 336	89.65 268	95.18 256	85.86 147	99.10 151	87.70 259	93.58 238	98.49 144

DIV-MVS_self_test		90.97 268	90.33 256	92.88 291	95.36 272	86.19 298	94.46 330	96.63 258	87.82 288	88.18 310	94.23 307	82.99 194	97.53 328	87.72 256	85.57 328	94.93 320

Fast-Effi-MVS+-dtu		92.29 205	91.99 192	93.21 280	95.27 281	85.52 306	97.03 179	96.63 258	92.09 146	89.11 286	95.14 258	80.33 246	98.08 260	87.54 267	94.74 211	96.03 261

UnsupCasMVSNet_bld		82.13 366	79.46 371	90.14 357	88.00 404	82.47 351	90.89 394	96.62 260	78.94 393	75.61 397	84.40 408	56.63 401	96.31 367	77.30 372	66.77 409	91.63 390

cl22		91.21 256	90.56 251	93.14 282	96.09 240	86.80 279	94.41 332	96.58 261	87.80 290	88.58 298	93.99 319	80.85 237	97.62 320	89.87 212	86.93 316	94.99 315

jason		94.84 113	94.39 119	96.18 121	95.52 261	90.93 155	96.09 260	96.52 262	89.28 239	96.01 109	97.32 139	84.70 160	98.77 192	95.15 105	98.91 97	98.85 116
jason: jason.
tt0805		91.09 261	90.07 273	94.16 231	95.61 256	88.31 240	97.56 124	96.51 263	89.56 229	89.17 284	95.64 236	67.08 374	98.38 231	91.07 192	88.44 302	95.80 269

AUN-MVS		91.76 224	90.75 241	94.81 196	97.00 172	88.57 233	96.65 217	96.49 264	89.63 227	92.15 200	96.12 208	78.66 278	98.50 219	90.83 194	79.18 381	97.36 218

hse-mvs2		93.45 158	92.99 154	94.81 196	97.02 170	88.59 232	96.69 213	96.47 265	95.19 25	96.74 73	96.16 206	83.67 178	98.48 222	95.85 82	79.13 382	97.35 220

EG-PatchMatch MVS		87.02 336	85.44 340	91.76 327	92.67 370	85.00 318	96.08 261	96.45 266	83.41 366	79.52 389	93.49 338	57.10 400	97.72 311	79.34 363	90.87 278	92.56 377

KD-MVS_self_test		85.95 348	84.95 347	88.96 369	89.55 395	79.11 388	95.13 311	96.42 267	85.91 329	84.07 366	90.48 380	70.03 351	94.82 388	80.04 355	72.94 398	92.94 370

pmmvs6		87.81 328	86.19 335	92.69 299	91.32 383	86.30 294	97.34 153	96.41 268	80.59 387	84.05 367	94.37 296	67.37 369	97.67 314	84.75 310	79.51 380	94.09 357

PMMVS		92.86 184	92.34 182	94.42 218	94.92 302	86.73 282	94.53 326	96.38 269	84.78 348	94.27 151	95.12 260	83.13 190	98.40 226	91.47 184	96.49 176	98.12 174

RPSCF		90.75 275	90.86 233	90.42 353	96.84 179	76.29 396	95.61 288	96.34 270	83.89 357	91.38 220	97.87 98	76.45 302	98.78 189	87.16 276	92.23 251	96.20 251

BP-MVS1		95.89 81	95.49 81	97.08 72	96.67 194	93.20 72	98.08 53	96.32 271	94.56 56	96.32 94	97.84 103	84.07 173	99.15 144	96.75 48	98.78 100	98.90 108

MSDG		91.42 243	90.24 263	94.96 189	97.15 159	88.91 225	93.69 359	96.32 271	85.72 332	86.93 338	96.47 190	80.24 247	98.98 170	80.57 352	95.05 204	96.98 230

WBMVS		90.69 280	89.99 276	92.81 294	96.48 214	85.00 318	95.21 309	96.30 273	89.46 234	89.04 287	94.05 316	72.45 333	97.82 301	89.46 222	87.41 313	95.61 280

OurMVSNet-221017-0		90.51 285	90.19 268	91.44 333	93.41 356	81.25 361	96.98 187	96.28 274	91.68 157	86.55 342	96.30 198	74.20 322	97.98 276	88.96 238	87.40 314	95.09 311

MVP-Stereo		90.74 276	90.08 270	92.71 298	93.19 361	88.20 246	95.86 272	96.27 275	86.07 327	84.86 356	94.76 274	77.84 292	97.75 309	83.88 323	98.01 133	92.17 387
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 108	94.56 110	96.29 113	96.34 224	91.21 141	95.83 274	96.27 275	88.93 253	96.22 99	96.88 164	86.20 143	98.85 182	95.27 101	99.05 89	98.82 120

BH-untuned		92.94 180	92.62 171	93.92 249	97.22 153	86.16 299	96.40 239	96.25 277	90.06 216	89.79 263	96.17 205	83.19 187	98.35 233	87.19 274	97.27 158	97.24 225

CL-MVSNet_self_test		86.31 343	85.15 344	89.80 361	88.83 399	81.74 359	93.93 350	96.22 278	86.67 315	85.03 354	90.80 378	78.09 288	94.50 389	74.92 383	71.86 400	93.15 368

IS-MVSNet		94.90 110	94.52 114	96.05 127	97.67 131	90.56 167	98.44 21	96.22 278	93.21 105	93.99 158	97.74 111	85.55 151	98.45 223	89.98 208	97.86 137	99.14 79

FA-MVS(test-final)		93.52 156	92.92 157	95.31 170	96.77 189	88.54 235	94.82 318	96.21 280	89.61 228	94.20 153	95.25 254	83.24 185	99.14 147	90.01 207	96.16 180	98.25 163

GA-MVS		91.38 245	90.31 258	94.59 206	94.65 316	87.62 262	94.34 335	96.19 281	90.73 190	90.35 243	93.83 322	71.84 336	97.96 283	87.22 273	93.61 236	98.21 166

IterMVS-SCA-FT		90.31 288	89.81 283	91.82 322	95.52 261	84.20 330	94.30 338	96.15 282	90.61 200	87.39 325	94.27 304	75.80 308	96.44 365	87.34 270	86.88 320	94.82 329

IterMVS		90.15 296	89.67 289	91.61 329	95.48 263	83.72 336	94.33 336	96.12 283	89.99 217	87.31 328	94.15 312	75.78 310	96.27 368	86.97 279	86.89 319	94.83 327
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 189	91.51 211	96.52 89	98.77 56	90.99 151	97.38 150	96.08 284	82.38 372	89.29 280	97.87 98	83.77 176	99.69 57	81.37 346	96.69 172	98.89 112

pmmvs4		90.93 270	89.85 281	94.17 230	93.34 358	90.79 160	94.60 323	96.02 285	84.62 349	87.45 322	95.15 257	81.88 221	97.45 335	87.70 259	87.87 306	94.27 354

ppachtmachnet_test		88.35 323	87.29 322	91.53 330	92.45 376	83.57 339	93.75 356	95.97 286	84.28 352	85.32 353	94.18 310	79.00 275	96.93 356	75.71 379	84.99 341	94.10 355

Anonymous20240521		86.42 341	85.44 340	89.34 367	90.33 388	79.79 380	96.73 207	95.92 287	83.71 362	83.25 372	91.36 375	63.92 387	96.01 369	78.39 367	85.36 332	92.22 385

ITE_SJBPF				92.43 303	95.34 274	85.37 311		95.92 287	91.47 162	87.75 318	96.39 195	71.00 342	97.96 283	82.36 337	89.86 288	93.97 358

test_fmvs2		89.77 306	89.93 278	89.31 368	93.68 347	76.37 395	97.64 115	95.90 289	89.84 223	91.49 218	96.26 201	58.77 397	97.10 349	94.65 120	91.13 271	94.46 345

USDC		88.94 314	87.83 319	92.27 309	94.66 315	84.96 320	93.86 353	95.90 289	87.34 304	83.40 370	95.56 240	67.43 368	98.19 246	82.64 336	89.67 290	93.66 361

COLMAP_ROB	87.81 15	90.40 287	89.28 299	93.79 254	97.95 116	87.13 274	96.92 191	95.89 291	82.83 369	86.88 340	97.18 148	73.77 326	99.29 127	78.44 366	93.62 235	94.95 316
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 146	93.08 152	96.02 130	97.88 122	89.96 188	97.72 102	95.85 292	92.43 135	95.86 113	98.44 48	68.42 364	99.39 116	96.31 59	94.85 205	98.71 127

VDDNet		93.05 174	92.07 188	96.02 130	96.84 179	90.39 175	98.08 53	95.85 292	86.22 325	95.79 116	98.46 46	67.59 367	99.19 135	94.92 110	94.85 205	98.47 147

mvsmamba		94.57 119	94.14 123	95.87 138	97.03 169	89.93 189	97.84 85	95.85 292	91.34 168	94.79 139	96.80 166	80.67 238	98.81 186	94.85 111	98.12 130	98.85 116

Vis-MVSNet (Re-imp)		94.15 130	93.88 127	94.95 190	97.61 139	87.92 254	98.10 51	95.80 295	92.22 139	93.02 180	97.45 132	84.53 163	97.91 294	88.24 247	97.97 134	99.02 90

MM		97.29 22	96.98 29	98.23 11	98.01 111	95.03 26	98.07 55	95.76 296	97.78 1	97.52 46	98.80 27	88.09 107	99.86 9	99.44 1	99.37 61	99.80 1

KD-MVS_2432*1600		84.81 356	82.64 360	91.31 335	91.07 385	85.34 312	91.22 389	95.75 297	85.56 334	83.09 373	90.21 383	67.21 370	95.89 371	77.18 373	62.48 413	92.69 373

miper_refine_blended		84.81 356	82.64 360	91.31 335	91.07 385	85.34 312	91.22 389	95.75 297	85.56 334	83.09 373	90.21 383	67.21 370	95.89 371	77.18 373	62.48 413	92.69 373

FE-MVS		92.05 215	91.05 227	95.08 179	96.83 181	87.93 253	93.91 352	95.70 299	86.30 322	94.15 155	94.97 262	76.59 300	99.21 133	84.10 317	96.86 165	98.09 178

tpm cat1		88.36 322	87.21 325	91.81 323	95.13 292	80.55 370	92.58 380	95.70 299	74.97 402	87.45 322	91.96 369	78.01 291	98.17 248	80.39 354	88.74 299	96.72 240

our_test_3		88.78 318	87.98 318	91.20 339	92.45 376	82.53 348	93.61 363	95.69 301	85.77 331	84.88 355	93.71 327	79.99 252	96.78 362	79.47 360	86.24 321	94.28 353

BH-w/o		92.14 213	91.75 200	93.31 275	96.99 173	85.73 303	95.67 282	95.69 301	88.73 263	89.26 282	94.82 272	82.97 196	98.07 264	85.26 305	96.32 179	96.13 257

CR-MVSNet		90.82 273	89.77 285	93.95 244	94.45 324	87.19 271	90.23 397	95.68 303	86.89 312	92.40 190	92.36 362	80.91 234	97.05 351	81.09 350	93.95 229	97.60 208

Patchmtry		88.64 320	87.25 323	92.78 296	94.09 334	86.64 283	89.82 401	95.68 303	80.81 384	87.63 320	92.36 362	80.91 234	97.03 352	78.86 364	85.12 337	94.67 340

testing91		91.90 220	91.02 228	94.53 213	96.54 206	86.55 289	95.86 272	95.64 305	91.77 154	91.89 208	93.47 340	69.94 352	98.86 180	90.23 206	93.86 231	98.18 168

BH-RMVSNet		92.72 191	91.97 193	94.97 188	97.16 157	87.99 252	96.15 258	95.60 306	90.62 199	91.87 209	97.15 151	78.41 282	98.57 215	83.16 326	97.60 144	98.36 159

PVSNet_0	82.17 19	85.46 353	83.64 356	90.92 342	95.27 281	79.49 384	90.55 395	95.60 306	83.76 361	83.00 375	89.95 385	71.09 341	97.97 279	82.75 334	60.79 415	95.31 298

SCA		91.84 222	91.18 224	93.83 251	95.59 257	84.95 321	94.72 320	95.58 308	90.82 186	92.25 198	93.69 329	75.80 308	98.10 255	86.20 288	95.98 182	98.45 149

MonoMVSNet		91.92 218	91.77 198	92.37 304	92.94 365	83.11 342	97.09 177	95.55 309	92.91 125	90.85 235	94.55 284	81.27 230	96.52 364	93.01 156	87.76 307	97.47 214

AllTest		90.23 292	88.98 304	93.98 240	97.94 117	86.64 283	96.51 230	95.54 310	85.38 336	85.49 350	96.77 168	70.28 347	99.15 144	80.02 356	92.87 240	96.15 255

TestCases				93.98 240	97.94 117	86.64 283		95.54 310	85.38 336	85.49 350	96.77 168	70.28 347	99.15 144	80.02 356	92.87 240	96.15 255

mmtdpeth		89.70 307	88.96 305	91.90 318	95.84 250	84.42 326	97.46 141	95.53 312	90.27 210	94.46 148	90.50 379	69.74 355	98.95 171	97.39 38	69.48 404	92.34 381

tpmvs		89.83 305	89.15 302	91.89 319	94.92 302	80.30 374	93.11 372	95.46 313	86.28 323	88.08 312	92.65 352	80.44 243	98.52 218	81.47 342	89.92 287	96.84 236

pmmvs5		89.86 304	88.87 308	92.82 293	92.86 366	86.23 296	96.26 250	95.39 314	84.24 353	87.12 329	94.51 287	74.27 321	97.36 342	87.61 266	87.57 309	94.86 325

PatchmatchNet		91.91 219	91.35 213	93.59 264	95.38 269	84.11 331	93.15 371	95.39 314	89.54 230	92.10 203	93.68 331	82.82 200	98.13 250	84.81 309	95.32 197	98.52 139
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 242	91.32 215	91.79 324	95.15 290	79.20 387	93.42 366	95.37 316	88.55 268	93.49 170	93.67 332	82.49 208	98.27 239	90.41 201	89.34 293	97.90 187

Anonymous20231206		87.09 335	86.14 336	89.93 360	91.22 384	80.35 372	96.11 259	95.35 317	83.57 364	84.16 362	93.02 347	73.54 328	95.61 379	72.16 395	86.14 323	93.84 360

MIMVSNet1		84.93 355	83.05 357	90.56 351	89.56 394	84.84 323	95.40 296	95.35 317	83.91 356	80.38 385	92.21 366	57.23 399	93.34 401	70.69 401	82.75 368	93.50 363

TDRefinement		86.53 338	84.76 350	91.85 320	82.23 416	84.25 328	96.38 241	95.35 317	84.97 345	84.09 365	94.94 264	65.76 383	98.34 236	84.60 313	74.52 394	92.97 369

TR-MVS		91.48 241	90.59 249	94.16 231	96.40 220	87.33 264	95.67 282	95.34 320	87.68 296	91.46 219	95.52 243	76.77 299	98.35 233	82.85 331	93.61 236	96.79 238

EPNet_dtu		91.71 225	91.28 218	92.99 286	93.76 344	83.71 337	96.69 213	95.28 321	93.15 112	87.02 334	95.95 216	83.37 184	97.38 341	79.46 361	96.84 166	97.88 189
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 332	85.79 338	91.78 325	94.80 309	87.28 266	95.49 293	95.28 321	84.09 355	83.85 369	91.82 370	62.95 390	94.17 393	78.48 365	85.34 333	93.91 359

MDTV_nov1_ep13			90.76 239		95.22 285	80.33 373	93.03 374	95.28 321	88.14 280	92.84 187	93.83 322	81.34 227	98.08 260	82.86 329	94.34 216

LF4IMVS		87.94 326	87.25 323	89.98 359	92.38 378	80.05 379	94.38 333	95.25 324	87.59 298	84.34 359	94.74 276	64.31 386	97.66 316	84.83 308	87.45 310	92.23 384

TransMVSNet (Re)		88.94 314	87.56 320	93.08 284	94.35 327	88.45 239	97.73 99	95.23 325	87.47 300	84.26 361	95.29 249	79.86 255	97.33 343	79.44 362	74.44 395	93.45 365

test20.03		86.14 346	85.40 342	88.35 370	90.12 389	80.06 378	95.90 271	95.20 326	88.59 264	81.29 380	93.62 334	71.43 339	92.65 404	71.26 399	81.17 373	92.34 381

new-patchmatchnet		83.18 362	81.87 365	87.11 377	86.88 407	75.99 397	93.70 357	95.18 327	85.02 344	77.30 396	88.40 395	65.99 381	93.88 398	74.19 388	70.18 402	91.47 394

MDA-MVSNet_test_wron		85.87 350	84.23 354	90.80 348	92.38 378	82.57 347	93.17 369	95.15 328	82.15 373	67.65 408	92.33 365	78.20 284	95.51 382	77.33 370	79.74 377	94.31 352

YYNet1		85.87 350	84.23 354	90.78 349	92.38 378	82.46 352	93.17 369	95.14 329	82.12 374	67.69 406	92.36 362	78.16 287	95.50 383	77.31 371	79.73 378	94.39 348

Baseline_NR-MVSNet		91.20 257	90.62 247	92.95 288	93.83 342	88.03 251	97.01 184	95.12 330	88.42 272	89.70 265	95.13 259	83.47 181	97.44 336	89.66 218	83.24 363	93.37 366

thres200		92.23 209	91.39 212	94.75 203	97.61 139	89.03 223	96.60 225	95.09 331	92.08 147	93.28 176	94.00 318	78.39 283	99.04 167	81.26 349	94.18 220	96.19 252

ADS-MVSNet		89.89 301	88.68 310	93.53 267	95.86 245	84.89 322	90.93 392	95.07 332	83.23 367	91.28 228	91.81 371	79.01 273	97.85 297	79.52 358	91.39 267	97.84 193

pmmvs-eth3d		86.22 344	84.45 352	91.53 330	88.34 403	87.25 268	94.47 328	95.01 333	83.47 365	79.51 390	89.61 388	69.75 354	95.71 376	83.13 327	76.73 389	91.64 389

Anonymous202405211		92.07 214	90.83 237	95.76 143	98.19 98	88.75 228	97.58 121	95.00 334	86.00 328	93.64 165	97.45 132	66.24 379	99.53 96	90.68 199	92.71 245	99.01 93

MDA-MVSNet-bldmvs		85.00 354	82.95 359	91.17 340	93.13 363	83.33 340	94.56 325	95.00 334	84.57 350	65.13 412	92.65 352	70.45 346	95.85 373	73.57 391	77.49 385	94.33 350

ambc				86.56 380	83.60 413	70.00 407	85.69 411	94.97 336		80.60 384	88.45 394	37.42 415	96.84 360	82.69 335	75.44 393	92.86 371

testgi		87.97 325	87.21 325	90.24 356	92.86 366	80.76 365	96.67 216	94.97 336	91.74 155	85.52 349	95.83 222	62.66 392	94.47 391	76.25 377	88.36 303	95.48 283

dp		88.90 316	88.26 316	90.81 346	94.58 320	76.62 394	92.85 377	94.93 338	85.12 342	90.07 257	93.07 346	75.81 307	98.12 253	80.53 353	87.42 312	97.71 200

test_fmvs3		83.21 361	83.02 358	83.78 384	86.77 408	68.34 410	96.76 205	94.91 339	86.49 318	84.14 364	89.48 389	36.04 416	91.73 406	91.86 174	80.77 375	91.26 396

test_0402		86.46 340	84.79 349	91.45 332	95.02 296	85.55 305	96.29 249	94.89 340	80.90 381	82.21 377	93.97 320	68.21 365	97.29 345	62.98 407	88.68 300	91.51 392

tfpn200view9		92.38 199	91.52 209	94.95 190	97.85 123	89.29 213	97.41 143	94.88 341	92.19 143	93.27 177	94.46 292	78.17 285	99.08 157	81.40 343	94.08 224	96.48 245

CVMVSNet		91.23 255	91.75 200	89.67 362	95.77 251	74.69 398	96.44 231	94.88 341	85.81 330	92.18 199	97.64 121	79.07 268	95.58 381	88.06 250	95.86 186	98.74 124

thres400		92.42 197	91.52 209	95.12 178	97.85 123	89.29 213	97.41 143	94.88 341	92.19 143	93.27 177	94.46 292	78.17 285	99.08 157	81.40 343	94.08 224	96.98 230

EPNet		95.20 101	94.56 110	97.14 68	92.80 368	92.68 86	97.85 84	94.87 344	96.64 2	92.46 189	97.80 108	86.23 140	99.65 63	93.72 139	98.62 107	99.10 85
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 230	90.72 244	94.32 223	96.48 214	86.11 300	95.81 275	94.76 345	91.55 159	91.75 213	93.44 341	68.55 362	98.82 184	90.43 200	93.69 232	98.04 181

SixPastTwentyTwo		89.15 312	88.54 312	90.98 341	93.49 353	80.28 375	96.70 211	94.70 346	90.78 187	84.15 363	95.57 239	71.78 337	97.71 312	84.63 312	85.07 338	94.94 318

thres100view900		92.43 196	91.58 206	94.98 186	97.92 119	89.37 209	97.71 104	94.66 347	92.20 141	93.31 175	94.90 267	78.06 289	99.08 157	81.40 343	94.08 224	96.48 245

thres600view7		92.49 195	91.60 205	95.18 174	97.91 120	89.47 203	97.65 111	94.66 347	92.18 145	93.33 174	94.91 266	78.06 289	99.10 151	81.61 340	94.06 228	96.98 230

PatchT		88.87 317	87.42 321	93.22 279	94.08 335	85.10 316	89.51 402	94.64 349	81.92 375	92.36 193	88.15 398	80.05 251	97.01 354	72.43 394	93.65 234	97.54 211

baseline1		92.82 187	91.90 195	95.55 159	97.20 155	90.77 161	97.19 169	94.58 350	92.20 141	92.36 193	96.34 197	84.16 171	98.21 243	89.20 233	83.90 358	97.68 202

UBG		91.55 236	90.76 239	93.94 246	96.52 210	85.06 317	95.22 307	94.54 351	90.47 206	91.98 206	92.71 351	72.02 334	98.74 196	88.10 249	95.26 199	98.01 182

Gipuma		67.86 382	65.41 384	75.18 397	92.66 371	73.45 401	66.50 418	94.52 352	53.33 417	57.80 418	66.07 418	30.81 418	89.20 410	48.15 416	78.88 384	62.90 418
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 228	90.75 241	94.47 214	96.53 208	86.56 288	95.76 279	94.51 353	91.10 181	91.24 230	93.59 335	68.59 361	98.86 180	91.10 191	94.29 217	98.00 183

CostFormer		91.18 260	90.70 245	92.62 301	94.84 307	81.76 358	94.09 345	94.43 354	84.15 354	92.72 188	93.77 326	79.43 262	98.20 244	90.70 198	92.18 254	97.90 187

tpm2		89.96 298	89.21 300	92.23 311	94.91 304	81.25 361	93.78 355	94.42 355	80.62 386	91.56 216	93.44 341	76.44 303	97.94 288	85.60 300	92.08 258	97.49 212

MVS_0304		96.74 50	96.31 66	98.02 19	96.87 176	94.65 30	97.58 121	94.39 356	96.47 5	97.16 58	98.39 52	87.53 121	99.87 7	98.97 10	99.41 53	99.55 34

JIA-IIPM		88.26 324	87.04 328	91.91 317	93.52 351	81.42 360	89.38 403	94.38 357	80.84 383	90.93 234	80.74 410	79.22 265	97.92 291	82.76 333	91.62 262	96.38 248

dmvs_re		90.21 293	89.50 294	92.35 305	95.47 266	85.15 314	95.70 281	94.37 358	90.94 185	88.42 300	93.57 336	74.63 318	95.67 378	82.80 332	89.57 291	96.22 250

Patchmatch-test		89.42 310	87.99 317	93.70 259	95.27 281	85.11 315	88.98 404	94.37 358	81.11 380	87.10 332	93.69 329	82.28 212	97.50 331	74.37 386	94.76 209	98.48 146

LCM-MVSNet		72.55 375	69.39 379	82.03 386	70.81 426	65.42 415	90.12 399	94.36 360	55.02 416	65.88 410	81.72 409	24.16 424	89.96 407	74.32 387	68.10 407	90.71 399

ADS-MVSNet2		89.45 309	88.59 311	92.03 314	95.86 245	82.26 354	90.93 392	94.32 361	83.23 367	91.28 228	91.81 371	79.01 273	95.99 370	79.52 358	91.39 267	97.84 193

mvs5depth		86.53 338	85.08 345	90.87 343	88.74 401	82.52 349	91.91 385	94.23 362	86.35 321	87.11 331	93.70 328	66.52 375	97.76 308	81.37 346	75.80 391	92.31 383

EU-MVSNet		88.72 319	88.90 307	88.20 372	93.15 362	74.21 399	96.63 222	94.22 363	85.18 340	87.32 327	95.97 214	76.16 305	94.98 387	85.27 304	86.17 322	95.41 288

MIMVSNet		88.50 321	86.76 331	93.72 258	94.84 307	87.77 260	91.39 387	94.05 364	86.41 320	87.99 314	92.59 355	63.27 388	95.82 375	77.44 369	92.84 242	97.57 210

OpenMVS_ROB	81.14 20	84.42 358	82.28 364	90.83 344	90.06 390	84.05 333	95.73 280	94.04 365	73.89 405	80.17 388	91.53 374	59.15 396	97.64 317	66.92 405	89.05 295	90.80 398

TinyColmap		86.82 337	85.35 343	91.21 337	94.91 304	82.99 344	93.94 349	94.02 366	83.58 363	81.56 379	94.68 278	62.34 393	98.13 250	75.78 378	87.35 315	92.52 379

ETVMVS		90.52 284	89.14 303	94.67 205	96.81 185	87.85 258	95.91 270	93.97 367	89.71 226	92.34 196	92.48 357	65.41 384	97.96 283	81.37 346	94.27 218	98.21 166

IB-MVS	87.33 17	89.91 299	88.28 315	94.79 200	95.26 284	87.70 261	95.12 312	93.95 368	89.35 238	87.03 333	92.49 356	70.74 344	99.19 135	89.18 234	81.37 372	97.49 212
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		87.13 334	87.02 329	87.47 375	95.16 288	73.21 403	95.00 314	93.93 369	88.55 268	86.96 335	91.99 367	75.90 306	94.00 395	61.59 409	94.11 221	95.20 306

myMVS_eth3d		87.18 333	86.38 333	89.58 363	95.16 288	79.53 382	95.00 314	93.93 369	88.55 268	86.96 335	91.99 367	56.23 402	94.00 395	75.47 382	94.11 221	95.20 306

testing222		90.31 288	88.96 305	94.35 220	96.54 206	87.29 265	95.50 292	93.84 371	90.97 184	91.75 213	92.96 348	62.18 394	98.00 274	82.86 329	94.08 224	97.76 198

test_f		80.57 368	79.62 370	83.41 385	83.38 414	67.80 412	93.57 364	93.72 372	80.80 385	77.91 395	87.63 401	33.40 417	92.08 405	87.14 277	79.04 383	90.34 400

LCM-MVSNet-Re		92.50 193	92.52 177	92.44 302	96.82 183	81.89 357	96.92 191	93.71 373	92.41 136	84.30 360	94.60 282	85.08 156	97.03 352	91.51 182	97.36 152	98.40 155

tpm		90.25 291	89.74 288	91.76 327	93.92 338	79.73 381	93.98 346	93.54 374	88.28 275	91.99 205	93.25 345	77.51 295	97.44 336	87.30 272	87.94 305	98.12 174

ET-MVSNet_ETH3D		91.49 240	90.11 269	95.63 153	96.40 220	91.57 127	95.34 298	93.48 375	90.60 202	75.58 398	95.49 244	80.08 250	96.79 361	94.25 127	89.76 289	98.52 139

LFMVS		93.60 152	92.63 170	96.52 89	98.13 103	91.27 138	97.94 73	93.39 376	90.57 203	96.29 96	98.31 65	69.00 357	99.16 142	94.18 128	95.87 185	99.12 83

MVStest1		82.38 365	80.04 369	89.37 365	87.63 406	82.83 345	95.03 313	93.37 377	73.90 404	73.50 403	94.35 297	62.89 391	93.25 402	73.80 389	65.92 410	92.04 388

Patchmatch-RL test		87.38 331	86.24 334	90.81 346	88.74 401	78.40 391	88.12 409	93.17 378	87.11 309	82.17 378	89.29 390	81.95 219	95.60 380	88.64 244	77.02 386	98.41 154

ttmdpeth		85.91 349	84.76 350	89.36 366	89.14 396	80.25 376	95.66 285	93.16 379	83.77 360	83.39 371	95.26 253	66.24 379	95.26 386	80.65 351	75.57 392	92.57 376

test-LLR		91.42 243	91.19 223	92.12 312	94.59 318	80.66 367	94.29 339	92.98 380	91.11 179	90.76 237	92.37 359	79.02 271	98.07 264	88.81 240	96.74 169	97.63 203

test-mter		90.19 295	89.54 293	92.12 312	94.59 318	80.66 367	94.29 339	92.98 380	87.68 296	90.76 237	92.37 359	67.67 366	98.07 264	88.81 240	96.74 169	97.63 203

WB-MVSnew		89.88 302	89.56 292	90.82 345	94.57 321	83.06 343	95.65 286	92.85 382	87.86 287	90.83 236	94.10 313	79.66 259	96.88 358	76.34 376	94.19 219	92.54 378

testing3		87.67 329	86.88 330	90.05 358	96.14 236	80.71 366	97.10 176	92.85 382	90.15 214	87.54 321	94.55 284	55.70 403	94.10 394	73.77 390	94.10 223	95.35 295

test_method		66.11 383	64.89 385	69.79 400	72.62 424	35.23 432	65.19 419	92.83 384	20.35 422	65.20 411	88.08 399	43.14 413	82.70 417	73.12 393	63.46 412	91.45 395

test0.0.03 1		89.37 311	88.70 309	91.41 334	92.47 375	85.63 304	95.22 307	92.70 385	91.11 179	86.91 339	93.65 333	79.02 271	93.19 403	78.00 368	89.18 294	95.41 288

new_pmnet		82.89 363	81.12 368	88.18 373	89.63 393	80.18 377	91.77 386	92.57 386	76.79 400	75.56 399	88.23 397	61.22 395	94.48 390	71.43 397	82.92 366	89.87 401

mvsany_test1		93.93 142	93.98 125	93.78 255	94.94 301	86.80 279	94.62 322	92.55 387	88.77 262	96.85 68	98.49 42	88.98 93	98.08 260	95.03 107	95.62 192	96.46 247

thisisatest0515		92.29 205	91.30 217	95.25 172	96.60 198	88.90 226	94.36 334	92.32 388	87.92 284	93.43 172	94.57 283	77.28 296	99.00 168	89.42 224	95.86 186	97.86 192

thisisatest0530		93.03 175	92.21 186	95.49 163	97.07 162	89.11 222	97.49 138	92.19 389	90.16 213	94.09 156	96.41 193	76.43 304	99.05 164	90.38 202	95.68 191	98.31 161

tttt0517		92.96 178	92.33 183	94.87 193	97.11 160	87.16 273	97.97 69	92.09 390	90.63 198	93.88 162	97.01 158	76.50 301	99.06 163	90.29 205	95.45 195	98.38 157

K. test v3		87.64 330	86.75 332	90.32 355	93.02 364	79.48 385	96.61 223	92.08 391	90.66 196	80.25 387	94.09 314	67.21 370	96.65 363	85.96 296	80.83 374	94.83 327

TESTMET0.1,1		90.06 297	89.42 296	91.97 315	94.41 326	80.62 369	94.29 339	91.97 392	87.28 306	90.44 241	92.47 358	68.79 358	97.67 314	88.50 246	96.60 174	97.61 207

PM-MVS		83.48 360	81.86 366	88.31 371	87.83 405	77.59 393	93.43 365	91.75 393	86.91 311	80.63 383	89.91 386	44.42 412	95.84 374	85.17 307	76.73 389	91.50 393

baseline2		91.63 229	90.86 233	93.94 246	94.33 328	86.32 293	95.92 269	91.64 394	89.37 237	86.94 337	94.69 277	81.62 225	98.69 202	88.64 244	94.57 214	96.81 237

APD_test1		79.31 370	77.70 373	84.14 383	89.11 398	69.07 409	92.36 384	91.50 395	69.07 408	73.87 401	92.63 354	39.93 414	94.32 392	70.54 402	80.25 376	89.02 403

FPMVS		71.27 376	69.85 378	75.50 396	74.64 421	59.03 421	91.30 388	91.50 395	58.80 413	57.92 417	88.28 396	29.98 420	85.53 416	53.43 414	82.84 367	81.95 409

door								91.13 397

door-mid								91.06 398

EGC-MVSNET		68.77 381	63.01 387	86.07 382	92.49 374	82.24 355	93.96 348	90.96 399	0.71 427	2.62 428	90.89 377	53.66 404	93.46 399	57.25 412	84.55 348	82.51 408

mvsany_test3		83.59 359	82.44 363	87.03 378	83.80 411	73.82 400	93.70 357	90.92 400	86.42 319	82.51 376	90.26 382	46.76 411	95.71 376	90.82 195	76.76 388	91.57 391

pmmvs3		79.97 369	77.50 374	87.39 376	82.80 415	79.38 386	92.70 379	90.75 401	70.69 407	78.66 392	87.47 403	51.34 407	93.40 400	73.39 392	69.65 403	89.38 402

UWE-MVS		89.91 299	89.48 295	91.21 337	95.88 244	78.23 392	94.91 317	90.26 402	89.11 244	92.35 195	94.52 286	68.76 359	97.96 283	83.95 321	95.59 193	97.42 216

DSMNet-mixed		86.34 342	86.12 337	87.00 379	89.88 392	70.43 405	94.93 316	90.08 403	77.97 397	85.42 352	92.78 350	74.44 320	93.96 397	74.43 385	95.14 200	96.62 241

MVS-HIRNet		82.47 364	81.21 367	86.26 381	95.38 269	69.21 408	88.96 405	89.49 404	66.28 410	80.79 382	74.08 415	68.48 363	97.39 340	71.93 396	95.47 194	92.18 386

WB-MVS		76.77 372	76.63 375	77.18 391	85.32 409	56.82 423	94.53 326	89.39 405	82.66 371	71.35 404	89.18 391	75.03 315	88.88 411	35.42 420	66.79 408	85.84 405

test1111		93.19 167	92.82 161	94.30 226	97.58 145	84.56 325	98.21 42	89.02 406	93.53 94	94.58 143	98.21 72	72.69 330	99.05 164	93.06 152	98.48 114	99.28 68

SSC-MVS		76.05 373	75.83 376	76.72 395	84.77 410	56.22 424	94.32 337	88.96 407	81.82 377	70.52 405	88.91 392	74.79 317	88.71 412	33.69 421	64.71 411	85.23 406

ECVR-MVS		93.19 167	92.73 167	94.57 211	97.66 133	85.41 308	98.21 42	88.23 408	93.43 98	94.70 141	98.21 72	72.57 331	99.07 161	93.05 153	98.49 112	99.25 71

EPMVS		90.70 278	89.81 283	93.37 273	94.73 313	84.21 329	93.67 360	88.02 409	89.50 232	92.38 192	93.49 338	77.82 293	97.78 305	86.03 294	92.68 246	98.11 177

ANet_high		63.94 385	59.58 388	77.02 392	61.24 428	66.06 413	85.66 412	87.93 410	78.53 395	42.94 420	71.04 417	25.42 423	80.71 419	52.60 415	30.83 421	84.28 407

PMMVS2		70.19 377	66.92 381	80.01 387	76.35 420	65.67 414	86.22 410	87.58 411	64.83 412	62.38 413	80.29 412	26.78 422	88.49 414	63.79 406	54.07 417	85.88 404

lessismore_v0				90.45 352	91.96 381	79.09 389		87.19 412		80.32 386	94.39 294	66.31 378	97.55 325	84.00 320	76.84 387	94.70 339

PMVS	53.92 22	58.58 386	55.40 389	68.12 401	51.00 429	48.64 426	78.86 415	87.10 413	46.77 418	35.84 424	74.28 414	8.76 428	86.34 415	42.07 418	73.91 396	69.38 415
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
test_vis1_rt		86.16 345	85.06 346	89.46 364	93.47 355	80.46 371	96.41 235	86.61 414	85.22 339	79.15 391	88.64 393	52.41 406	97.06 350	93.08 151	90.57 280	90.87 397

testf1		69.31 379	66.76 382	76.94 393	78.61 418	61.93 417	88.27 407	86.11 415	55.62 414	59.69 414	85.31 406	20.19 426	89.32 408	57.62 410	69.44 405	79.58 410

APD_test2		69.31 379	66.76 382	76.94 393	78.61 418	61.93 417	88.27 407	86.11 415	55.62 414	59.69 414	85.31 406	20.19 426	89.32 408	57.62 410	69.44 405	79.58 410

gg-mvs-nofinetune		87.82 327	85.61 339	94.44 216	94.46 323	89.27 216	91.21 391	84.61 417	80.88 382	89.89 261	74.98 413	71.50 338	97.53 328	85.75 299	97.21 160	96.51 243

dmvs_testset		81.38 367	82.60 362	77.73 390	91.74 382	51.49 425	93.03 374	84.21 418	89.07 245	78.28 394	91.25 376	76.97 298	88.53 413	56.57 413	82.24 369	93.16 367

GG-mvs-BLEND				93.62 262	93.69 346	89.20 218	92.39 383	83.33 419		87.98 315	89.84 387	71.00 342	96.87 359	82.08 339	95.40 196	94.80 332

MTMP							97.86 81	82.03 420

DeepMVS_CX				74.68 398	90.84 387	64.34 416		81.61 421	65.34 411	67.47 409	88.01 400	48.60 410	80.13 420	62.33 408	73.68 397	79.58 410

E-PMN		53.28 387	52.56 391	55.43 404	74.43 422	47.13 427	83.63 414	76.30 422	42.23 419	42.59 421	62.22 420	28.57 421	74.40 421	31.53 422	31.51 420	44.78 419

test2506		91.60 231	90.78 238	94.04 237	97.66 133	83.81 334	98.27 32	75.53 423	93.43 98	95.23 130	98.21 72	67.21 370	99.07 161	93.01 156	98.49 112	99.25 71

EMVS		52.08 389	51.31 392	54.39 405	72.62 424	45.39 429	83.84 413	75.51 424	41.13 420	40.77 422	59.65 421	30.08 419	73.60 422	28.31 424	29.90 422	44.18 420

test_vis3_rt		72.73 374	70.55 377	79.27 388	80.02 417	68.13 411	93.92 351	74.30 425	76.90 399	58.99 416	73.58 416	20.29 425	95.37 384	84.16 316	72.80 399	74.31 413

MVE	50.73 23	53.25 388	48.81 393	66.58 403	65.34 427	57.50 422	72.49 417	70.94 426	40.15 421	39.28 423	63.51 419	6.89 430	73.48 423	38.29 419	42.38 419	68.76 417
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 390	53.82 390	46.29 406	33.73 430	45.30 430	78.32 416	67.24 427	18.02 423	50.93 419	87.05 404	52.99 405	53.11 425	70.76 400	25.29 423	40.46 421

kuosan		65.27 384	64.66 386	67.11 402	83.80 411	61.32 420	88.53 406	60.77 428	68.22 409	67.67 407	80.52 411	49.12 409	70.76 424	29.67 423	53.64 418	69.26 416

dongtai		69.99 378	69.33 380	71.98 399	88.78 400	61.64 419	89.86 400	59.93 429	75.67 401	74.96 400	85.45 405	50.19 408	81.66 418	43.86 417	55.27 416	72.63 414

N_pmnet		78.73 371	78.71 372	78.79 389	92.80 368	46.50 428	94.14 343	43.71 430	78.61 394	80.83 381	91.66 373	74.94 316	96.36 366	67.24 404	84.45 350	93.50 363

wuyk23d		25.11 391	24.57 395	26.74 407	73.98 423	39.89 431	57.88 420	9.80 431	12.27 424	10.39 425	6.97 427	7.03 429	36.44 426	25.43 425	17.39 424	3.89 424

testmvs		13.36 393	16.33 396	4.48 409	5.04 431	2.26 434	93.18 368	3.28 432	2.70 425	8.24 426	21.66 423	2.29 432	2.19 427	7.58 426	2.96 425	9.00 423

test123		13.04 394	15.66 397	5.18 408	4.51 432	3.45 433	92.50 382	1.81 433	2.50 426	7.58 427	20.15 424	3.67 431	2.18 428	7.13 427	1.07 426	9.90 422

mmdepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

monomultidepth		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

test_blank		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet_test		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

DCPMVS		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

pcd_1.5k_mvsjas		7.39 396	9.85 399	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	88.65 100	0.00 429	0.00 428	0.00 427	0.00 425

sosnet-low-res		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

sosnet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uncertanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

Regformer		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

n2								0.00 434

nn								0.00 434

ab-mvs-re		8.06 395	10.74 398	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	96.69 174	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

uanet		0.00 397	0.00 400	0.00 410	0.00 433	0.00 435	0.00 421	0.00 434	0.00 428	0.00 429	0.00 428	0.00 433	0.00 429	0.00 428	0.00 427	0.00 425

WAC-MVS						79.53 382								75.56 381

PC_three_1452									90.77 188	98.89 16	98.28 70	96.24 1	98.35 233	95.76 86	99.58 23	99.59 24

eth-test2					0.00 433

eth-test					0.00 433

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 71	96.04 2	99.24 130	95.36 100	99.59 19	99.56 31

test_0728_THIRD									94.78 46	98.73 20	98.87 20	95.87 4	99.84 23	97.45 34	99.72 2	99.77 2

GSMVS																98.45 149

test_part2					99.28 25	95.74 8				98.10 32

sam_mvs1												82.76 201				98.45 149

sam_mvs												81.94 220

test_post1							92.81 378				16.58 426	80.53 241	97.68 313	86.20 288

test_post											17.58 425	81.76 222	98.08 260

patchmatchnet-post											90.45 381	82.65 205	98.10 255

gm-plane-assit					93.22 360	78.89 390			84.82 347		93.52 337		98.64 207	87.72 256

test9_res														94.81 115	99.38 58	99.45 50

agg_prior2														93.94 133	99.38 58	99.50 43

test_prior4						93.66 57	96.42 234

test_prior2							96.35 243		92.80 129	96.03 106	97.59 125	92.01 47		95.01 108	99.38 58

旧先验2							95.94 268		81.66 378	97.34 54			98.82 184	92.26 161

新几何2							95.79 277

原ACMM2							95.67 282

testdata2													99.67 61	85.96 296

segment_acmp												92.89 30

testdata1							95.26 306		93.10 115

plane_prior7					96.21 228	89.98 186

plane_prior6					96.10 239	90.00 182						81.32 228

plane_prior4											96.64 177

plane_prior3						90.00 182			94.46 62	91.34 222

plane_prior2							97.74 97		94.85 39

plane_prior1					96.14 236

plane_prior						89.99 184	97.24 162		94.06 74						92.16 255

HQP5-MVS						89.33 211

HQP-NCC					95.86 245		96.65 217		93.55 90	90.14 246

ACMP_Plane					95.86 245		96.65 217		93.55 90	90.14 246

BP-MVS														92.13 167

HQP4-MVS										90.14 246			98.50 219			95.78 271

HQP2-MVS												80.95 232

NP-MVS					95.99 243	89.81 192					95.87 219

MDTV_nov1_ep13_2view						70.35 406	93.10 373		83.88 358	93.55 167		82.47 209		86.25 287		98.38 157

ACMMP++_ref															90.30 285

ACMMP++															91.02 274

Test By Simon												88.73 99

High-resolution multi-view benchmark