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 12	97.89 3	96.53 91	98.41 77	91.73 118	98.01 60	99.02 1	96.37 8	99.30 3	98.92 18	92.39 41	99.79 37	99.16 9	99.46 41	98.08 184

PGM-MVS		96.81 49	96.53 60	97.65 43	99.35 20	93.53 61	97.65 116	98.98 2	92.22 147	97.14 66	98.44 54	91.17 67	99.85 18	94.35 132	99.46 41	99.57 29

MVS_111021_HR		96.68 60	96.58 59	96.99 77	98.46 73	92.31 100	96.20 263	98.90 3	94.30 75	95.86 119	97.74 117	92.33 42	99.38 124	96.04 82	99.42 51	99.28 69

test_fmvsmconf_n		97.49 16	97.56 10	97.29 59	97.44 153	92.37 97	97.91 77	98.88 4	95.83 12	98.92 18	99.05 10	91.45 57	99.80 34	99.12 11	99.46 41	99.69 12

ACMMP		96.27 76	95.93 79	97.28 61	99.24 28	92.62 88	98.25 35	98.81 5	92.99 124	94.56 150	98.39 58	88.96 96	99.85 18	94.57 130	97.63 149	99.36 64
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 77	96.19 76	96.39 108	98.23 94	91.35 139	96.24 261	98.79 6	93.99 82	95.80 121	97.65 124	89.92 86	99.24 136	95.87 86	99.20 79	98.58 139

patch_mono-2		96.83 48	97.44 17	95.01 189	99.05 39	85.39 316	96.98 194	98.77 7	94.70 55	97.99 41	98.66 37	93.61 19	99.91 1	97.67 32	99.50 35	99.72 11

fmvsm_s_conf0.5_n		96.85 45	97.13 22	96.04 132	98.07 109	90.28 181	97.97 69	98.76 8	94.93 39	98.84 23	99.06 9	88.80 100	99.65 69	99.06 13	98.63 112	98.18 172

fmvsm_l_conf0.5_n		97.65 7	97.75 6	97.34 56	98.21 95	92.75 84	97.83 89	98.73 9	95.04 37	99.30 3	98.84 30	93.34 22	99.78 40	99.32 3	99.13 87	99.50 44

fmvsm_s_conf0.5_n_a		96.75 53	96.93 37	96.20 124	97.64 139	90.72 167	98.00 61	98.73 9	94.55 62	98.91 19	99.08 5	88.22 110	99.63 78	98.91 16	98.37 125	98.25 167

FC-MVSNet-test		93.94 147	93.57 140	95.04 187	95.48 271	91.45 136	98.12 50	98.71 11	93.37 107	90.23 253	96.70 178	87.66 120	97.85 305	91.49 190	90.39 293	95.83 276

UniMVSNet (Re)		93.31 168	92.55 180	95.61 160	95.39 276	93.34 67	97.39 154	98.71 11	93.14 120	90.10 262	94.83 278	87.71 119	98.03 279	91.67 188	83.99 364	95.46 295

fmvsm_l_conf0.5_n_a		97.63 9	97.76 5	97.26 63	98.25 89	92.59 90	97.81 93	98.68 13	94.93 39	99.24 6	98.87 25	93.52 20	99.79 37	99.32 3	99.21 76	99.40 58

FIs		94.09 141	93.70 136	95.27 177	95.70 261	92.03 111	98.10 51	98.68 13	93.36 109	90.39 250	96.70 178	87.63 123	97.94 296	92.25 170	90.50 292	95.84 275

WR-MVS_H		92.00 223	91.35 220	93.95 250	95.09 303	89.47 208	98.04 58	98.68 13	91.46 172	88.34 312	94.68 285	85.86 153	97.56 333	85.77 306	84.24 362	94.82 339

fmvsm_s_conf0.5_n_4		96.75 53	97.07 25	95.79 147	97.76 130	89.57 202	97.66 115	98.66 16	95.36 23	99.03 11	98.90 20	88.39 107	99.73 51	99.17 8	98.66 110	98.08 184

VPA-MVSNet		93.24 170	92.48 185	95.51 166	95.70 261	92.39 96	97.86 82	98.66 16	92.30 145	92.09 211	95.37 254	80.49 248	98.40 233	93.95 138	85.86 335	95.75 284

fmvsm_l_conf0.5_n_3		97.64 8	97.60 9	97.79 30	98.14 102	93.94 52	97.93 75	98.65 18	96.70 3	99.38 1	99.07 8	89.92 86	99.81 30	99.16 9	99.43 48	99.61 23

fmvsm_s_conf0.5_n_3		97.15 27	97.36 19	96.52 92	97.98 115	91.19 147	97.84 86	98.65 18	97.08 2	99.25 5	99.10 3	87.88 117	99.79 37	99.32 3	99.18 81	98.59 138

fmvsm_s_conf0.5_n_2		96.62 61	96.82 46	96.02 134	97.98 115	90.43 177	97.50 137	98.59 20	96.59 5	99.31 2	99.08 5	84.47 170	99.75 48	99.37 2	98.45 122	97.88 196

UniMVSNet_NR-MVSNet		93.37 166	92.67 175	95.47 171	95.34 282	92.83 82	97.17 178	98.58 21	92.98 129	90.13 258	95.80 230	88.37 109	97.85 305	91.71 185	83.93 365	95.73 286

CSCG		96.05 80	95.91 80	96.46 102	99.24 28	90.47 174	98.30 28	98.57 22	89.01 257	93.97 166	97.57 132	92.62 37	99.76 44	94.66 125	99.27 69	99.15 79

fmvsm_s_conf0.5_n_6		97.08 30	97.17 21	96.81 79	97.28 158	91.73 118	97.75 98	98.50 23	94.86 43	99.22 7	98.78 34	89.75 89	99.76 44	99.10 12	99.29 67	98.94 102

MSLP-MVS++		96.94 39	97.06 26	96.59 88	98.72 58	91.86 116	97.67 112	98.49 24	94.66 58	97.24 62	98.41 57	92.31 44	98.94 180	96.61 59	99.46 41	98.96 99

HyFIR lowres test		93.66 157	92.92 163	95.87 142	98.24 90	89.88 194	94.58 333	98.49 24	85.06 353	93.78 169	95.78 234	82.86 204	98.67 211	91.77 183	95.71 196	99.07 90

CHOSEN 1792x2688		94.15 136	93.51 146	96.06 130	98.27 86	89.38 213	95.18 319	98.48 26	85.60 343	93.76 170	97.11 158	83.15 195	99.61 80	91.33 193	98.72 108	99.19 75

fmvsm_s_conf0.5_n_7		96.45 68	96.80 48	95.37 174	97.29 157	88.38 245	97.23 172	98.47 27	95.14 31	98.43 32	99.09 4	87.58 124	99.72 55	98.80 20	99.21 76	98.02 188

fmvsm_s_conf0.5_n_5		97.00 36	96.97 34	97.09 72	97.58 149	92.56 91	97.68 111	98.47 27	94.02 80	98.90 20	98.89 22	88.94 97	99.78 40	99.18 7	99.03 96	98.93 106

PHI-MVS		96.77 51	96.46 67	97.71 41	98.40 78	94.07 48	98.21 42	98.45 29	89.86 229	97.11 68	98.01 94	92.52 39	99.69 63	96.03 83	99.53 29	99.36 64

fmvsm_s_conf0.1_n		96.58 64	96.77 51	96.01 137	96.67 202	90.25 182	97.91 77	98.38 30	94.48 66	98.84 23	99.14 1	88.06 112	99.62 79	98.82 18	98.60 114	98.15 176

PVSNet_BlendedMVS		94.06 142	93.92 132	94.47 220	98.27 86	89.46 210	96.73 214	98.36 31	90.17 221	94.36 155	95.24 262	88.02 113	99.58 88	93.44 149	90.72 288	94.36 359

PVSNet_Blended		94.87 118	94.56 116	95.81 146	98.27 86	89.46 210	95.47 302	98.36 31	88.84 265	94.36 155	96.09 219	88.02 113	99.58 88	93.44 149	98.18 133	98.40 159

3Dnovator	91.36 5	95.19 108	94.44 124	97.44 53	96.56 211	93.36 66	98.65 11	98.36 31	94.12 77	89.25 291	98.06 88	82.20 220	99.77 43	93.41 151	99.32 65	99.18 76

FOURS1					99.55 1	93.34 67	99.29 1	98.35 34	94.98 38	98.49 30

DPE-MVS		97.86 4	97.65 8	98.47 5	99.17 32	95.78 7	97.21 175	98.35 34	95.16 30	98.71 27	98.80 32	95.05 10	99.89 3	96.70 57	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 70	96.47 64	96.16 126	95.48 271	90.69 168	97.91 77	98.33 36	94.07 78	98.93 15	99.14 1	87.44 131	99.61 80	98.63 21	98.32 127	98.18 172

HFP-MVS		97.14 28	96.92 38	97.83 26	99.42 7	94.12 46	98.52 15	98.32 37	93.21 112	97.18 63	98.29 74	92.08 46	99.83 26	95.63 99	99.59 19	99.54 37

ACMMPR		97.07 32	96.84 42	97.79 30	99.44 6	93.88 53	98.52 15	98.31 38	93.21 112	97.15 65	98.33 68	91.35 61	99.86 9	95.63 99	99.59 19	99.62 20

test_fmvsmvis_n_1920		96.70 56	96.84 42	96.31 113	96.62 204	91.73 118	97.98 63	98.30 39	96.19 9	96.10 110	98.95 16	89.42 90	99.76 44	98.90 17	99.08 91	97.43 223

APDe-MVS		97.82 5	97.73 7	98.08 18	99.15 33	94.82 28	98.81 7	98.30 39	94.76 53	98.30 34	98.90 20	93.77 17	99.68 65	97.93 24	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 41	94.92 41	98.99 13	98.92 18	95.08 8

MSP-MVS		97.59 11	97.54 11	97.73 38	99.40 11	93.77 57	98.53 14	98.29 41	95.55 20	98.56 29	97.81 112	93.90 15	99.65 69	96.62 58	99.21 76	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 43	94.78 51	98.93 15	98.87 25	96.04 2	99.86 9	97.45 40	99.58 23	99.59 25

test_0728_SECOND				98.51 4	99.45 3	95.93 5	98.21 42	98.28 43					99.86 9	97.52 36	99.67 6	99.75 6

CP-MVS		97.02 34	96.81 47	97.64 45	99.33 21	93.54 60	98.80 8	98.28 43	92.99 124	96.45 97	98.30 73	91.90 49	99.85 18	95.61 101	99.68 4	99.54 37

test_fmvsmconf0.1_n		97.09 29	97.06 26	97.19 68	95.67 263	92.21 104	97.95 72	98.27 46	95.78 16	98.40 33	99.00 12	89.99 84	99.78 40	99.06 13	99.41 54	99.59 25

SED-MVS		98.05 2	97.99 1	98.24 10	99.42 7	95.30 17	98.25 35	98.27 46	95.13 32	99.19 8	98.89 22	95.54 5	99.85 18	97.52 36	99.66 10	99.56 32

test_241102_TWO								98.27 46	95.13 32	98.93 15	98.89 22	94.99 11	99.85 18	97.52 36	99.65 13	99.74 8

test_241102_ONE					99.42 7	95.30 17		98.27 46	95.09 35	99.19 8	98.81 31	95.54 5	99.65 69

SF-MVS		97.39 19	97.13 22	98.17 15	99.02 42	95.28 19	98.23 39	98.27 46	92.37 144	98.27 35	98.65 39	93.33 23	99.72 55	96.49 63	99.52 30	99.51 41

SteuartSystems-ACMMP		97.62 10	97.53 12	97.87 24	98.39 80	94.25 40	98.43 22	98.27 46	95.34 25	98.11 37	98.56 41	94.53 12	99.71 57	96.57 61	99.62 17	99.65 17
Skip Steuart: Steuart Systems R&D Blog.
test_one_0601					99.32 22	95.20 20		98.25 52	95.13 32	98.48 31	98.87 25	95.16 7

PVSNet_Blended_VisFu		95.27 103	94.91 107	96.38 109	98.20 96	90.86 161	97.27 166	98.25 52	90.21 220	94.18 160	97.27 149	87.48 130	99.73 51	93.53 146	97.77 147	98.55 140

region2R		97.07 32	96.84 42	97.77 34	99.46 2	93.79 55	98.52 15	98.24 54	93.19 115	97.14 66	98.34 65	91.59 56	99.87 7	95.46 105	99.59 19	99.64 18

PS-CasMVS		91.55 243	90.84 244	93.69 266	94.96 307	88.28 248	97.84 86	98.24 54	91.46 172	88.04 322	95.80 230	79.67 264	97.48 341	87.02 286	84.54 359	95.31 308

DU-MVS		92.90 188	92.04 196	95.49 168	94.95 308	92.83 82	97.16 179	98.24 54	93.02 123	90.13 258	95.71 237	83.47 187	97.85 305	91.71 185	83.93 365	95.78 280

9.14			96.75 52		98.93 50		97.73 102	98.23 57	91.28 181	97.88 45	98.44 54	93.00 26	99.65 69	95.76 92	99.47 40

reproduce_model		97.51 15	97.51 14	97.50 50	98.99 46	93.01 78	97.79 95	98.21 58	95.73 17	97.99 41	99.03 11	92.63 36	99.82 28	97.80 26	99.42 51	99.67 13

D2MVS		91.30 260	90.95 238	92.35 312	94.71 323	85.52 312	96.18 264	98.21 58	88.89 263	86.60 351	93.82 333	79.92 260	97.95 295	89.29 235	90.95 285	93.56 372

reproduce-ours		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 107	98.20 60	95.80 14	97.88 45	98.98 14	92.91 27	99.81 30	97.68 28	99.43 48	99.67 13

our_new_method		97.53 13	97.51 14	97.60 47	98.97 47	93.31 69	97.71 107	98.20 60	95.80 14	97.88 45	98.98 14	92.91 27	99.81 30	97.68 28	99.43 48	99.67 13

SDMVSNet		94.17 134	93.61 139	95.86 144	98.09 105	91.37 138	97.35 158	98.20 60	93.18 117	91.79 219	97.28 147	79.13 272	98.93 181	94.61 128	92.84 251	97.28 231

XVS		97.18 25	96.96 36	97.81 28	99.38 14	94.03 50	98.59 12	98.20 60	94.85 44	96.59 89	98.29 74	91.70 52	99.80 34	95.66 94	99.40 56	99.62 20

X-MVStestdata		91.71 232	89.67 297	97.81 28	99.38 14	94.03 50	98.59 12	98.20 60	94.85 44	96.59 89	32.69 432	91.70 52	99.80 34	95.66 94	99.40 56	99.62 20

ACMMP_NAP		97.20 24	96.86 40	98.23 11	99.09 34	95.16 22	97.60 125	98.19 65	92.82 135	97.93 44	98.74 36	91.60 55	99.86 9	96.26 66	99.52 30	99.67 13

CP-MVSNet		91.89 228	91.24 227	93.82 258	95.05 304	88.57 238	97.82 91	98.19 65	91.70 165	88.21 318	95.76 235	81.96 224	97.52 339	87.86 261	84.65 353	95.37 304

ZNCC-MVS		96.96 37	96.67 55	97.85 25	99.37 16	94.12 46	98.49 19	98.18 67	92.64 140	96.39 99	98.18 81	91.61 54	99.88 4	95.59 104	99.55 26	99.57 29

SMA-MVS		97.35 20	97.03 31	98.30 8	99.06 38	95.42 10	97.94 73	98.18 67	90.57 212	98.85 22	98.94 17	93.33 23	99.83 26	96.72 56	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		91.20 265	90.44 261	93.48 275	94.49 331	87.91 262	97.76 97	98.18 67	91.29 178	87.78 326	95.74 236	80.35 251	97.33 352	85.46 310	82.96 375	95.19 319

DELS-MVS		96.61 62	96.38 71	97.30 58	97.79 128	93.19 74	95.96 274	98.18 67	95.23 27	95.87 118	97.65 124	91.45 57	99.70 62	95.87 86	99.44 47	99.00 97
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		89.70 316	88.40 322	93.60 269	95.15 299	90.10 184	97.56 129	98.16 71	87.28 316	86.16 355	94.63 289	77.57 300	98.05 275	74.48 393	84.59 357	92.65 385

VNet		95.89 87	95.45 90	97.21 66	98.07 109	92.94 81	97.50 137	98.15 72	93.87 86	97.52 52	97.61 130	85.29 159	99.53 102	95.81 91	95.27 205	99.16 77

DeepPCF-MVS	93.97 1	96.61 62	97.09 24	95.15 181	98.09 105	86.63 292	96.00 272	98.15 72	95.43 21	97.95 43	98.56 41	93.40 21	99.36 125	96.77 53	99.48 39	99.45 51

SD-MVS		97.41 18	97.53 12	97.06 75	98.57 72	94.46 34	97.92 76	98.14 74	94.82 48	99.01 12	98.55 43	94.18 14	97.41 348	96.94 49	99.64 14	99.32 66
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 45	96.52 61	97.82 27	99.36 18	94.14 45	98.29 29	98.13 75	92.72 137	96.70 81	98.06 88	91.35 61	99.86 9	94.83 119	99.28 68	99.47 50

UA-Net		95.95 85	95.53 86	97.20 67	97.67 135	92.98 80	97.65 116	98.13 75	94.81 49	96.61 87	98.35 62	88.87 98	99.51 107	90.36 210	97.35 159	99.11 85

QAPM		93.45 164	92.27 190	96.98 78	96.77 197	92.62 88	98.39 24	98.12 77	84.50 361	88.27 316	97.77 115	82.39 217	99.81 30	85.40 311	98.81 104	98.51 145

Vis-MVSNet		95.23 105	94.81 108	96.51 96	97.18 163	91.58 129	98.26 34	98.12 77	94.38 73	94.90 142	98.15 83	82.28 218	98.92 182	91.45 192	98.58 116	99.01 94
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
OpenMVS	89.19 12	92.86 190	91.68 210	96.40 106	95.34 282	92.73 86	98.27 32	98.12 77	84.86 356	85.78 357	97.75 116	78.89 282	99.74 49	87.50 276	98.65 111	96.73 247

TranMVSNet+NR-MVSNet		92.50 199	91.63 211	95.14 182	94.76 319	92.07 109	97.53 134	98.11 80	92.90 133	89.56 279	96.12 214	83.16 194	97.60 331	89.30 234	83.20 374	95.75 284

CPTT-MVS		95.57 97	95.19 100	96.70 81	99.27 26	91.48 133	98.33 26	98.11 80	87.79 301	95.17 138	98.03 91	87.09 137	99.61 80	93.51 147	99.42 51	99.02 91

APD-MVS		96.95 38	96.60 57	98.01 20	99.03 41	94.93 27	97.72 105	98.10 82	91.50 170	98.01 40	98.32 70	92.33 42	99.58 88	94.85 117	99.51 33	99.53 40
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
mPP-MVS		96.86 43	96.60 57	97.64 45	99.40 11	93.44 62	98.50 18	98.09 83	93.27 111	95.95 117	98.33 68	91.04 69	99.88 4	95.20 108	99.57 25	99.60 24

ZD-MVS					99.05 39	94.59 32		98.08 84	89.22 250	97.03 71	98.10 84	92.52 39	99.65 69	94.58 129	99.31 66

MTGPA								98.08 84

MTAPA		97.08 30	96.78 50	97.97 23	99.37 16	94.42 36	97.24 168	98.08 84	95.07 36	96.11 109	98.59 40	90.88 74	99.90 2	96.18 78	99.50 35	99.58 28

CNVR-MVS		97.68 6	97.44 17	98.37 7	98.90 53	95.86 6	97.27 166	98.08 84	95.81 13	97.87 48	98.31 71	94.26 13	99.68 65	97.02 48	99.49 38	99.57 29

DP-MVS Recon		95.68 92	95.12 104	97.37 55	99.19 31	94.19 42	97.03 186	98.08 84	88.35 283	95.09 140	97.65 124	89.97 85	99.48 112	92.08 177	98.59 115	98.44 156

SR-MVS		97.01 35	96.86 40	97.47 52	99.09 34	93.27 71	97.98 63	98.07 89	93.75 89	97.45 54	98.48 51	91.43 59	99.59 85	96.22 69	99.27 69	99.54 37

MCST-MVS		97.18 25	96.84 42	98.20 14	99.30 24	95.35 15	97.12 182	98.07 89	93.54 99	96.08 111	97.69 119	93.86 16	99.71 57	96.50 62	99.39 58	99.55 35

NR-MVSNet		92.34 207	91.27 226	95.53 165	94.95 308	93.05 77	97.39 154	98.07 89	92.65 139	84.46 368	95.71 237	85.00 163	97.77 316	89.71 222	83.52 371	95.78 280

MP-MVS-pluss		96.70 56	96.27 74	97.98 22	99.23 30	94.71 29	96.96 196	98.06 92	90.67 203	95.55 130	98.78 34	91.07 68	99.86 9	96.58 60	99.55 26	99.38 62
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
APD-MVS_3200maxsize		96.81 49	96.71 54	97.12 70	99.01 45	92.31 100	97.98 63	98.06 92	93.11 121	97.44 55	98.55 43	90.93 72	99.55 98	96.06 79	99.25 73	99.51 41

MP-MVS		96.77 51	96.45 68	97.72 39	99.39 13	93.80 54	98.41 23	98.06 92	93.37 107	95.54 132	98.34 65	90.59 78	99.88 4	94.83 119	99.54 28	99.49 46
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
HPM-MVS_fast		96.51 65	96.27 74	97.22 65	99.32 22	92.74 85	98.74 9	98.06 92	90.57 212	96.77 78	98.35 62	90.21 81	99.53 102	94.80 122	99.63 16	99.38 62

HPM-MVS		96.69 58	96.45 68	97.40 54	99.36 18	93.11 76	98.87 6	98.06 92	91.17 186	96.40 98	97.99 95	90.99 70	99.58 88	95.61 101	99.61 18	99.49 46
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
sss		94.51 126	93.80 134	96.64 83	97.07 169	91.97 113	96.32 253	98.06 92	88.94 261	94.50 152	96.78 173	84.60 167	99.27 134	91.90 178	96.02 187	98.68 132

DeepC-MVS	93.07 3	96.06 79	95.66 84	97.29 59	97.96 117	93.17 75	97.30 164	98.06 92	93.92 84	93.38 179	98.66 37	86.83 139	99.73 51	95.60 103	99.22 75	98.96 99
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 22	97.03 31	98.11 17	98.77 56	95.06 25	97.34 159	98.04 99	95.96 10	97.09 69	97.88 103	93.18 25	99.71 57	95.84 90	99.17 82	99.56 32

DeepC-MVS_fast	93.89 2	96.93 40	96.64 56	97.78 32	98.64 67	94.30 37	97.41 149	98.04 99	94.81 49	96.59 89	98.37 60	91.24 64	99.64 77	95.16 110	99.52 30	99.42 57
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 42	96.80 48	97.11 71	99.02 42	92.34 98	97.98 63	98.03 101	93.52 102	97.43 57	98.51 46	91.40 60	99.56 96	96.05 80	99.26 71	99.43 55

RE-MVS-def			96.72 53		99.02 42	92.34 98	97.98 63	98.03 101	93.52 102	97.43 57	98.51 46	90.71 76		96.05 80	99.26 71	99.43 55

RPMNet		88.98 322	87.05 336	94.77 207	94.45 333	87.19 277	90.23 407	98.03 101	77.87 408	92.40 197	87.55 412	80.17 255	99.51 107	68.84 412	93.95 238	97.60 216

save fliter					98.91 52	94.28 38	97.02 188	98.02 104	95.35 24

TEST9					98.70 59	94.19 42	96.41 242	98.02 104	88.17 287	96.03 112	97.56 134	92.74 33	99.59 85

train_agg		96.30 75	95.83 83	97.72 39	98.70 59	94.19 42	96.41 242	98.02 104	88.58 274	96.03 112	97.56 134	92.73 34	99.59 85	95.04 112	99.37 62	99.39 60

test_8					98.67 61	94.06 49	96.37 249	98.01 107	88.58 274	95.98 116	97.55 136	92.73 34	99.58 88

agg_prior					98.67 61	93.79 55		98.00 108		95.68 126			99.57 95

test_prior				97.23 64	98.67 61	92.99 79		98.00 108					99.41 120			99.29 67

WR-MVS		92.34 207	91.53 215	94.77 207	95.13 301	90.83 162	96.40 246	97.98 110	91.88 160	89.29 288	95.54 248	82.50 213	97.80 312	89.79 221	85.27 344	95.69 287

HPM-MVS++		97.34 21	96.97 34	98.47 5	99.08 36	96.16 4	97.55 133	97.97 111	95.59 18	96.61 87	97.89 101	92.57 38	99.84 23	95.95 85	99.51 33	99.40 58

CANet		96.39 71	96.02 78	97.50 50	97.62 142	93.38 64	97.02 188	97.96 112	95.42 22	94.86 143	97.81 112	87.38 133	99.82 28	96.88 51	99.20 79	99.29 67

114514_t		93.95 146	93.06 159	96.63 85	99.07 37	91.61 126	97.46 146	97.96 112	77.99 406	93.00 188	97.57 132	86.14 151	99.33 126	89.22 238	99.15 85	98.94 102

IU-MVS					99.42 7	95.39 11		97.94 114	90.40 218	98.94 14				97.41 43	99.66 10	99.74 8

MSC_two_6792asdad				98.86 1	98.67 61	96.94 1		97.93 115					99.86 9	97.68 28	99.67 6	99.77 2

No_MVS				98.86 1	98.67 61	96.94 1		97.93 115					99.86 9	97.68 28	99.67 6	99.77 2

fmvsm_s_conf0.1_n_2		96.33 74	96.44 70	96.00 138	97.30 156	90.37 180	97.53 134	97.92 117	96.52 6	99.14 10	99.08 5	83.21 192	99.74 49	99.22 6	98.06 138	97.88 196

Anonymous20231211		90.63 289	89.42 304	94.27 234	98.24 90	89.19 225	98.05 57	97.89 118	79.95 398	88.25 317	94.96 270	72.56 338	98.13 258	89.70 223	85.14 346	95.49 291

原ACMM1				96.38 109	98.59 69	91.09 154		97.89 118	87.41 312	95.22 137	97.68 120	90.25 80	99.54 100	87.95 260	99.12 89	98.49 148

CDPH-MVS		95.97 84	95.38 95	97.77 34	98.93 50	94.44 35	96.35 250	97.88 120	86.98 320	96.65 85	97.89 101	91.99 48	99.47 113	92.26 168	99.46 41	99.39 60

test11								97.88 120

EIA-MVS		95.53 98	95.47 89	95.71 155	97.06 172	89.63 198	97.82 91	97.87 122	93.57 95	93.92 167	95.04 268	90.61 77	98.95 178	94.62 127	98.68 109	98.54 141

CS-MVS		96.86 43	97.06 26	96.26 119	98.16 101	91.16 152	99.09 3	97.87 122	95.30 26	97.06 70	98.03 91	91.72 50	98.71 208	97.10 46	99.17 82	98.90 111

无先验							95.79 284	97.87 122	83.87 369				99.65 69	87.68 270		98.89 115

3Dnovator+	91.43 4	95.40 99	94.48 122	98.16 16	96.90 183	95.34 16	98.48 20	97.87 122	94.65 59	88.53 308	98.02 93	83.69 183	99.71 57	93.18 155	98.96 99	99.44 53

VPNet		92.23 215	91.31 223	94.99 190	95.56 267	90.96 157	97.22 174	97.86 126	92.96 130	90.96 241	96.62 190	75.06 320	98.20 252	91.90 178	83.65 370	95.80 278

test_vis1_n_1920		94.17 134	94.58 115	92.91 296	97.42 154	82.02 363	97.83 89	97.85 127	94.68 56	98.10 38	98.49 48	70.15 357	99.32 128	97.91 25	98.82 103	97.40 225

DVP-MVS		97.91 3	97.81 4	98.22 13	99.45 3	95.36 13	98.21 42	97.85 127	94.92 41	98.73 25	98.87 25	95.08 8	99.84 23	97.52 36	99.67 6	99.48 48
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 17	97.33 20	97.69 42	99.25 27	94.24 41	98.07 55	97.85 127	93.72 90	98.57 28	98.35 62	93.69 18	99.40 121	97.06 47	99.46 41	99.44 53
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 41	97.04 30	96.45 103	98.29 85	91.66 125	99.03 4	97.85 127	95.84 11	96.90 73	97.97 97	91.24 64	98.75 201	96.92 50	99.33 64	98.94 102

test_fmvsmconf0.01_n		96.15 78	95.85 82	97.03 76	92.66 381	91.83 117	97.97 69	97.84 131	95.57 19	97.53 51	99.00 12	84.20 176	99.76 44	98.82 18	99.08 91	99.48 48

GDP-MVS		95.62 94	95.13 102	97.09 72	96.79 194	93.26 72	97.89 80	97.83 132	93.58 94	96.80 75	97.82 111	83.06 199	99.16 148	94.40 131	97.95 142	98.87 117

balanced_conf03		96.84 47	96.89 39	96.68 82	97.63 141	92.22 103	98.17 48	97.82 133	94.44 68	98.23 36	97.36 144	90.97 71	99.22 138	97.74 27	99.66 10	98.61 135

AdaColmap		94.34 130	93.68 137	96.31 113	98.59 69	91.68 124	96.59 233	97.81 134	89.87 228	92.15 207	97.06 161	83.62 186	99.54 100	89.34 233	98.07 137	97.70 209

MVSMamba_PlusPlus		96.51 65	96.48 63	96.59 88	98.07 109	91.97 113	98.14 49	97.79 135	90.43 216	97.34 60	97.52 137	91.29 63	99.19 141	98.12 23	99.64 14	98.60 136

mamv4		94.66 124	96.10 77	90.37 363	98.01 112	73.41 412	96.82 207	97.78 136	89.95 227	94.52 151	97.43 141	92.91 27	99.09 161	98.28 22	99.16 84	98.60 136

ETV-MVS		96.02 81	95.89 81	96.40 106	97.16 164	92.44 95	97.47 144	97.77 137	94.55 62	96.48 94	94.51 295	91.23 66	98.92 182	95.65 97	98.19 132	97.82 204

新几何1				97.32 57	98.60 68	93.59 59		97.75 138	81.58 389	95.75 123	97.85 107	90.04 83	99.67 67	86.50 292	99.13 87	98.69 131

旧先验1					98.38 81	93.38 64		97.75 138			98.09 86	92.30 45			99.01 97	99.16 77

EC-MVSNet		96.42 69	96.47 64	96.26 119	97.01 178	91.52 131	98.89 5	97.75 138	94.42 69	96.64 86	97.68 120	89.32 91	98.60 218	97.45 40	99.11 90	98.67 133

EI-MVSNet-Vis-set		96.51 65	96.47 64	96.63 85	98.24 90	91.20 146	96.89 200	97.73 141	94.74 54	96.49 93	98.49 48	90.88 74	99.58 88	96.44 64	98.32 127	99.13 81

PAPM_NR		95.01 110	94.59 114	96.26 119	98.89 54	90.68 169	97.24 168	97.73 141	91.80 161	92.93 193	96.62 190	89.13 94	99.14 153	89.21 239	97.78 146	98.97 98

Anonymous20240529		91.98 224	90.73 251	95.73 153	98.14 102	89.40 212	97.99 62	97.72 143	79.63 400	93.54 174	97.41 142	69.94 359	99.56 96	91.04 200	91.11 281	98.22 169

CHOSEN 280x420		93.12 176	92.72 174	94.34 228	96.71 201	87.27 273	90.29 406	97.72 143	86.61 327	91.34 230	95.29 256	84.29 175	98.41 232	93.25 153	98.94 100	97.35 228

EI-MVSNet-UG-set		96.34 73	96.30 73	96.47 100	98.20 96	90.93 159	96.86 202	97.72 143	94.67 57	96.16 108	98.46 52	90.43 79	99.58 88	96.23 68	97.96 141	98.90 111

LS3D		93.57 160	92.61 178	96.47 100	97.59 145	91.61 126	97.67 112	97.72 143	85.17 351	90.29 252	98.34 65	84.60 167	99.73 51	83.85 333	98.27 129	98.06 186

PAPR		94.18 133	93.42 152	96.48 99	97.64 139	91.42 137	95.55 297	97.71 147	88.99 258	92.34 203	95.82 229	89.19 92	99.11 156	86.14 298	97.38 157	98.90 111

UGNet		94.04 144	93.28 155	96.31 113	96.85 186	91.19 147	97.88 81	97.68 148	94.40 71	93.00 188	96.18 209	73.39 335	99.61 80	91.72 184	98.46 121	98.13 177
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				95.46 172	98.18 100	88.90 231		97.66 149	82.73 380	97.03 71	98.07 87	90.06 82	98.85 189	89.67 224	98.98 98	98.64 134

test12				97.65 43	98.46 73	94.26 39		97.66 149		95.52 133		90.89 73	99.46 114		99.25 73	99.22 74

DTE-MVSNet		90.56 290	89.75 295	93.01 292	93.95 346	87.25 274	97.64 120	97.65 151	90.74 198	87.12 339	95.68 240	79.97 259	97.00 364	83.33 334	81.66 381	94.78 346

TAPA-MVS	90.10 7	92.30 210	91.22 229	95.56 162	98.33 83	89.60 200	96.79 209	97.65 151	81.83 386	91.52 225	97.23 152	87.94 115	98.91 184	71.31 407	98.37 125	98.17 175
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
sd_testset		93.10 177	92.45 186	95.05 186	98.09 105	89.21 222	96.89 200	97.64 153	93.18 117	91.79 219	97.28 147	75.35 319	98.65 213	88.99 244	92.84 251	97.28 231

test_cas_vis1_n_1920		94.48 128	94.55 119	94.28 233	96.78 195	86.45 297	97.63 122	97.64 153	93.32 110	97.68 50	98.36 61	73.75 333	99.08 164	96.73 55	99.05 93	97.31 230

cdsmvs_eth3d_5k		23.24 402	30.99 404	0.00 420	0.00 443	0.00 445	0.00 431	97.63 155	0.00 438	0.00 439	96.88 170	84.38 172	0.00 439	0.00 438	0.00 437	0.00 435

DPM-MVS		95.69 91	94.92 106	98.01 20	98.08 108	95.71 9	95.27 313	97.62 156	90.43 216	95.55 130	97.07 160	91.72 50	99.50 110	89.62 226	98.94 100	98.82 123

sasdasda		96.02 81	95.45 90	97.75 36	97.59 145	95.15 23	98.28 30	97.60 157	94.52 64	96.27 103	96.12 214	87.65 121	99.18 144	96.20 74	94.82 214	98.91 108

canonicalmvs		96.02 81	95.45 90	97.75 36	97.59 145	95.15 23	98.28 30	97.60 157	94.52 64	96.27 103	96.12 214	87.65 121	99.18 144	96.20 74	94.82 214	98.91 108

test222					98.24 90	92.21 104	95.33 308	97.60 157	79.22 402	95.25 135	97.84 109	88.80 100			99.15 85	98.72 128

cascas		91.20 265	90.08 278	94.58 216	94.97 306	89.16 226	93.65 371	97.59 160	79.90 399	89.40 283	92.92 359	75.36 318	98.36 240	92.14 173	94.75 217	96.23 257

h-mvs33		94.15 136	93.52 145	96.04 132	97.81 127	90.22 183	97.62 124	97.58 161	95.19 28	96.74 79	97.45 138	83.67 184	99.61 80	95.85 88	79.73 388	98.29 166

MGCFI-Net		95.94 86	95.40 94	97.56 49	97.59 145	94.62 31	98.21 42	97.57 162	94.41 70	96.17 107	96.16 212	87.54 126	99.17 146	96.19 76	94.73 219	98.91 108

MVSFormer		95.37 100	95.16 101	95.99 139	96.34 232	91.21 144	98.22 40	97.57 162	91.42 174	96.22 105	97.32 145	86.20 149	97.92 299	94.07 135	99.05 93	98.85 119

test_djsdf		93.07 179	92.76 169	94.00 245	93.49 362	88.70 235	98.22 40	97.57 162	91.42 174	90.08 264	95.55 247	82.85 205	97.92 299	94.07 135	91.58 272	95.40 301

OMC-MVS		95.09 109	94.70 112	96.25 122	98.46 73	91.28 140	96.43 240	97.57 162	92.04 156	94.77 146	97.96 98	87.01 138	99.09 161	91.31 194	96.77 174	98.36 163

PS-MVSNAJss		93.74 155	93.51 146	94.44 222	93.91 348	89.28 220	97.75 98	97.56 166	92.50 141	89.94 266	96.54 193	88.65 103	98.18 255	93.83 144	90.90 286	95.86 272

casdiffmvs_mvg		95.81 90	95.57 85	96.51 96	96.87 184	91.49 132	97.50 137	97.56 166	93.99 82	95.13 139	97.92 100	87.89 116	98.78 196	95.97 84	97.33 160	99.26 71
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		92.42 203	91.89 203	94.03 244	93.33 368	88.50 242	97.73 102	97.53 168	92.00 158	88.85 300	96.50 195	75.62 317	98.11 262	93.88 142	91.56 273	95.48 292

mvs_tets		92.31 209	91.76 206	93.94 252	93.41 365	88.29 247	97.63 122	97.53 168	92.04 156	88.76 303	96.45 197	74.62 325	98.09 267	93.91 140	91.48 274	95.45 296

dcpmvs_2		96.37 72	97.05 29	94.31 231	98.96 49	84.11 337	97.56 129	97.51 170	93.92 84	97.43 57	98.52 45	92.75 32	99.32 128	97.32 45	99.50 35	99.51 41

HQP_MVS		93.78 154	93.43 150	94.82 200	96.21 236	89.99 188	97.74 100	97.51 170	94.85 44	91.34 230	96.64 183	81.32 234	98.60 218	93.02 161	92.23 260	95.86 272

plane_prior5								97.51 170					98.60 218	93.02 161	92.23 260	95.86 272

reproduce_monomvs		91.30 260	91.10 233	91.92 324	96.82 191	82.48 357	97.01 191	97.49 173	94.64 60	88.35 311	95.27 259	70.53 352	98.10 263	95.20 108	84.60 356	95.19 319

PS-MVSNAJ		95.37 100	95.33 97	95.49 168	97.35 155	90.66 170	95.31 310	97.48 174	93.85 87	96.51 92	95.70 239	88.65 103	99.65 69	94.80 122	98.27 129	96.17 261

API-MVS		94.84 119	94.49 121	95.90 141	97.90 123	92.00 112	97.80 94	97.48 174	89.19 251	94.81 144	96.71 176	88.84 99	99.17 146	88.91 246	98.76 107	96.53 250

MG-MVS		95.61 95	95.38 95	96.31 113	98.42 76	90.53 172	96.04 269	97.48 174	93.47 104	95.67 127	98.10 84	89.17 93	99.25 135	91.27 195	98.77 106	99.13 81

MAR-MVS		94.22 132	93.46 148	96.51 96	98.00 114	92.19 107	97.67 112	97.47 177	88.13 291	93.00 188	95.84 227	84.86 165	99.51 107	87.99 259	98.17 134	97.83 203
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		92.98 183	92.53 182	94.32 229	96.12 246	89.20 223	95.28 311	97.47 177	92.66 138	89.90 267	95.62 243	80.58 246	98.40 233	92.73 166	92.40 258	95.38 303
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
UniMVSNet_ETH3D		91.34 258	90.22 274	94.68 210	94.86 315	87.86 263	97.23 172	97.46 179	87.99 292	89.90 267	96.92 168	66.35 387	98.23 249	90.30 211	90.99 284	97.96 191

nrg030		94.05 143	93.31 154	96.27 118	95.22 293	94.59 32	98.34 25	97.46 179	92.93 131	91.21 239	96.64 183	87.23 136	98.22 250	94.99 115	85.80 336	95.98 271

XVG-OURS		93.72 156	93.35 153	94.80 205	97.07 169	88.61 236	94.79 328	97.46 179	91.97 159	93.99 164	97.86 106	81.74 229	98.88 186	92.64 167	92.67 256	96.92 242

LPG-MVS_test		92.94 186	92.56 179	94.10 239	96.16 241	88.26 249	97.65 116	97.46 179	91.29 178	90.12 260	97.16 155	79.05 275	98.73 204	92.25 170	91.89 268	95.31 308

LGP-MVS_train				94.10 239	96.16 241	88.26 249		97.46 179	91.29 178	90.12 260	97.16 155	79.05 275	98.73 204	92.25 170	91.89 268	95.31 308

MVS		91.71 232	90.44 261	95.51 166	95.20 295	91.59 128	96.04 269	97.45 184	73.44 416	87.36 335	95.60 244	85.42 158	99.10 158	85.97 303	97.46 152	95.83 276

XVG-OURS-SEG-HR		93.86 151	93.55 141	94.81 202	97.06 172	88.53 241	95.28 311	97.45 184	91.68 166	94.08 163	97.68 120	82.41 216	98.90 185	93.84 143	92.47 257	96.98 238

baseline		95.58 96	95.42 93	96.08 128	96.78 195	90.41 178	97.16 179	97.45 184	93.69 93	95.65 128	97.85 107	87.29 134	98.68 210	95.66 94	97.25 165	99.13 81

ab-mvs		93.57 160	92.55 180	96.64 83	97.28 158	91.96 115	95.40 304	97.45 184	89.81 233	93.22 185	96.28 205	79.62 266	99.46 114	90.74 204	93.11 248	98.50 146

xiu_mvs_v2_base		95.32 102	95.29 98	95.40 173	97.22 160	90.50 173	95.44 303	97.44 188	93.70 92	96.46 96	96.18 209	88.59 106	99.53 102	94.79 124	97.81 145	96.17 261

1314		92.81 194	92.03 197	95.14 182	95.33 285	89.52 207	96.04 269	97.44 188	87.72 305	86.25 354	95.33 255	83.84 181	98.79 195	89.26 236	97.05 170	97.11 236

casdiffmvs		95.64 93	95.49 87	96.08 128	96.76 200	90.45 175	97.29 165	97.44 188	94.00 81	95.46 134	97.98 96	87.52 129	98.73 204	95.64 98	97.33 160	99.08 88
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		92.16 217	91.23 228	94.95 196	94.75 320	90.94 158	97.47 144	97.43 191	89.14 252	88.90 296	96.43 198	79.71 263	98.24 248	89.56 227	87.68 317	95.67 288

anonymousdsp		92.16 217	91.55 214	93.97 248	92.58 383	89.55 204	97.51 136	97.42 192	89.42 245	88.40 310	94.84 277	80.66 245	97.88 304	91.87 180	91.28 278	94.48 354

Effi-MVS+		94.93 115	94.45 123	96.36 111	96.61 205	91.47 134	96.41 242	97.41 193	91.02 192	94.50 152	95.92 223	87.53 127	98.78 196	93.89 141	96.81 173	98.84 122

RRT-MVS		94.51 126	94.35 126	94.98 192	96.40 228	86.55 295	97.56 129	97.41 193	93.19 115	94.93 141	97.04 162	79.12 273	99.30 132	96.19 76	97.32 162	99.09 87

HQP3-MVS								97.39 195							92.10 265

HQP-MVS		93.19 173	92.74 172	94.54 218	95.86 253	89.33 216	96.65 224	97.39 195	93.55 96	90.14 254	95.87 225	80.95 238	98.50 226	92.13 174	92.10 265	95.78 280

PLC	91.00 6	94.11 140	93.43 150	96.13 127	98.58 71	91.15 153	96.69 220	97.39 195	87.29 315	91.37 229	96.71 176	88.39 107	99.52 106	87.33 279	97.13 169	97.73 207
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
v7n		90.76 282	89.86 288	93.45 277	93.54 359	87.60 269	97.70 110	97.37 198	88.85 264	87.65 328	94.08 324	81.08 237	98.10 263	84.68 320	83.79 369	94.66 351

UnsupCasMVSNet_eth		85.99 357	84.45 362	90.62 359	89.97 401	82.40 360	93.62 372	97.37 198	89.86 229	78.59 403	92.37 369	65.25 395	95.35 394	82.27 347	70.75 411	94.10 365

ACMM	89.79 8	92.96 184	92.50 184	94.35 226	96.30 234	88.71 234	97.58 126	97.36 200	91.40 176	90.53 247	96.65 182	79.77 262	98.75 201	91.24 196	91.64 270	95.59 290
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
xiu_mvs_v1_base_debu		95.01 110	94.76 109	95.75 150	96.58 208	91.71 121	96.25 258	97.35 201	92.99 124	96.70 81	96.63 187	82.67 208	99.44 117	96.22 69	97.46 152	96.11 267

xiu_mvs_v1_base		95.01 110	94.76 109	95.75 150	96.58 208	91.71 121	96.25 258	97.35 201	92.99 124	96.70 81	96.63 187	82.67 208	99.44 117	96.22 69	97.46 152	96.11 267

xiu_mvs_v1_base_debi		95.01 110	94.76 109	95.75 150	96.58 208	91.71 121	96.25 258	97.35 201	92.99 124	96.70 81	96.63 187	82.67 208	99.44 117	96.22 69	97.46 152	96.11 267

diffmvs		95.25 104	95.13 102	95.63 158	96.43 227	89.34 215	95.99 273	97.35 201	92.83 134	96.31 101	97.37 143	86.44 144	98.67 211	96.26 66	97.19 167	98.87 117
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		94.71 123	94.02 130	96.79 80	97.71 133	92.05 110	96.59 233	97.35 201	90.61 209	94.64 148	96.93 165	86.41 145	99.39 122	91.20 197	94.71 220	98.94 102

F-COLMAP		93.58 159	92.98 161	95.37 174	98.40 78	88.98 229	97.18 177	97.29 206	87.75 304	90.49 248	97.10 159	85.21 160	99.50 110	86.70 289	96.72 177	97.63 211

XVG-ACMP-BASELINE		90.93 278	90.21 275	93.09 290	94.31 339	85.89 307	95.33 308	97.26 207	91.06 191	89.38 284	95.44 253	68.61 370	98.60 218	89.46 229	91.05 282	94.79 344

PCF-MVS	89.48 11	91.56 242	89.95 285	96.36 111	96.60 206	92.52 93	92.51 391	97.26 207	79.41 401	88.90 296	96.56 192	84.04 180	99.55 98	77.01 384	97.30 163	97.01 237
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
ACMP	89.59 10	92.62 198	92.14 193	94.05 242	96.40 228	88.20 252	97.36 157	97.25 209	91.52 169	88.30 314	96.64 183	78.46 287	98.72 207	91.86 181	91.48 274	95.23 315
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
OPM-MVS		93.28 169	92.76 169	94.82 200	94.63 326	90.77 165	96.65 224	97.18 210	93.72 90	91.68 223	97.26 150	79.33 270	98.63 215	92.13 174	92.28 259	95.07 322
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
PatchMatch-RL		92.90 188	92.02 198	95.56 162	98.19 98	90.80 163	95.27 313	97.18 210	87.96 293	91.86 218	95.68 240	80.44 249	98.99 176	84.01 328	97.54 151	96.89 243

alignmvs		95.87 89	95.23 99	97.78 32	97.56 151	95.19 21	97.86 82	97.17 212	94.39 72	96.47 95	96.40 200	85.89 152	99.20 140	96.21 73	95.11 210	98.95 101

MVS_Test		94.89 117	94.62 113	95.68 156	96.83 189	89.55 204	96.70 218	97.17 212	91.17 186	95.60 129	96.11 218	87.87 118	98.76 200	93.01 163	97.17 168	98.72 128

Fast-Effi-MVS+		93.46 163	92.75 171	95.59 161	96.77 197	90.03 185	96.81 208	97.13 214	88.19 286	91.30 233	94.27 312	86.21 148	98.63 215	87.66 271	96.46 184	98.12 179

EI-MVSNet		93.03 181	92.88 165	93.48 275	95.77 259	86.98 282	96.44 238	97.12 215	90.66 205	91.30 233	97.64 127	86.56 141	98.05 275	89.91 217	90.55 290	95.41 298

MVSTER		93.20 172	92.81 168	94.37 225	96.56 211	89.59 201	97.06 185	97.12 215	91.24 182	91.30 233	95.96 221	82.02 223	98.05 275	93.48 148	90.55 290	95.47 294

test_yl		94.78 121	94.23 127	96.43 104	97.74 131	91.22 142	96.85 203	97.10 217	91.23 183	95.71 124	96.93 165	84.30 173	99.31 130	93.10 156	95.12 208	98.75 125

DCV-MVSNet		94.78 121	94.23 127	96.43 104	97.74 131	91.22 142	96.85 203	97.10 217	91.23 183	95.71 124	96.93 165	84.30 173	99.31 130	93.10 156	95.12 208	98.75 125

LTVRE_ROB	88.41 13	90.99 274	89.92 287	94.19 235	96.18 239	89.55 204	96.31 254	97.09 219	87.88 296	85.67 358	95.91 224	78.79 283	98.57 222	81.50 350	89.98 295	94.44 357
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		92.73 196	92.88 165	92.29 315	96.08 249	81.05 371	97.98 63	97.08 220	90.72 200	96.79 77	98.18 81	63.07 399	98.45 230	97.62 34	98.42 124	97.36 226

v10		91.04 272	90.23 272	93.49 274	94.12 342	88.16 255	97.32 162	97.08 220	88.26 285	88.29 315	94.22 317	82.17 221	97.97 287	86.45 293	84.12 363	94.33 360

v144192		91.06 271	90.28 268	93.39 278	93.66 357	87.23 276	96.83 206	97.07 222	87.43 311	89.69 274	94.28 311	81.48 232	98.00 282	87.18 283	84.92 352	94.93 330

v1192		91.07 270	90.23 272	93.58 271	93.70 354	87.82 265	96.73 214	97.07 222	87.77 302	89.58 277	94.32 309	80.90 242	97.97 287	86.52 291	85.48 339	94.95 326

v8		91.29 262	90.53 260	93.57 272	94.15 341	88.12 256	97.34 159	97.06 224	88.99 258	88.32 313	94.26 314	83.08 197	98.01 281	87.62 273	83.92 367	94.57 353

mvs_anonymous		93.82 152	93.74 135	94.06 241	96.44 226	85.41 314	95.81 282	97.05 225	89.85 231	90.09 263	96.36 202	87.44 131	97.75 318	93.97 137	96.69 178	99.02 91

IterMVS-LS		92.29 211	91.94 201	93.34 280	96.25 235	86.97 283	96.57 236	97.05 225	90.67 203	89.50 282	94.80 280	86.59 140	97.64 326	89.91 217	86.11 334	95.40 301
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
v1921920		90.85 280	90.03 283	93.29 282	93.55 358	86.96 284	96.74 213	97.04 227	87.36 313	89.52 281	94.34 306	80.23 254	97.97 287	86.27 294	85.21 345	94.94 328

CDS-MVSNet		94.14 139	93.54 142	95.93 140	96.18 239	91.46 135	96.33 252	97.04 227	88.97 260	93.56 172	96.51 194	87.55 125	97.89 303	89.80 220	95.95 189	98.44 156
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
SSC-MVS3.2		89.74 315	89.26 308	91.19 348	95.16 296	80.29 382	94.53 335	97.03 229	91.79 162	88.86 299	94.10 321	69.94 359	97.82 309	85.29 312	86.66 330	95.45 296

v1144		91.37 255	90.60 256	93.68 267	93.89 349	88.23 251	96.84 205	97.03 229	88.37 282	89.69 274	94.39 302	82.04 222	97.98 284	87.80 263	85.37 341	94.84 336

v1240		90.70 286	89.85 289	93.23 284	93.51 361	86.80 285	96.61 230	97.02 231	87.16 318	89.58 277	94.31 310	79.55 267	97.98 284	85.52 309	85.44 340	94.90 333

EPP-MVSNet		95.22 106	95.04 105	95.76 148	97.49 152	89.56 203	98.67 10	97.00 232	90.69 201	94.24 158	97.62 129	89.79 88	98.81 193	93.39 152	96.49 182	98.92 107

V42		91.58 241	90.87 240	93.73 262	94.05 345	88.50 242	97.32 162	96.97 233	88.80 270	89.71 272	94.33 307	82.54 212	98.05 275	89.01 243	85.07 348	94.64 352

test_fmvs1		93.21 171	93.53 143	92.25 318	96.55 213	81.20 370	97.40 153	96.96 234	90.68 202	96.80 75	98.04 90	69.25 365	98.40 233	97.58 35	98.50 117	97.16 235

FMVSNet2		91.31 259	90.08 278	94.99 190	96.51 219	92.21 104	97.41 149	96.95 235	88.82 267	88.62 305	94.75 282	73.87 329	97.42 347	85.20 315	88.55 310	95.35 305

ACMH	87.59 16	90.53 291	89.42 304	93.87 256	96.21 236	87.92 260	97.24 168	96.94 236	88.45 280	83.91 378	96.27 206	71.92 341	98.62 217	84.43 323	89.43 301	95.05 324
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
GBi-Net		91.35 256	90.27 269	94.59 212	96.51 219	91.18 149	97.50 137	96.93 237	88.82 267	89.35 285	94.51 295	73.87 329	97.29 354	86.12 299	88.82 305	95.31 308

test1		91.35 256	90.27 269	94.59 212	96.51 219	91.18 149	97.50 137	96.93 237	88.82 267	89.35 285	94.51 295	73.87 329	97.29 354	86.12 299	88.82 305	95.31 308

FMVSNet3		91.78 230	90.69 254	95.03 188	96.53 216	92.27 102	97.02 188	96.93 237	89.79 234	89.35 285	94.65 288	77.01 303	97.47 342	86.12 299	88.82 305	95.35 305

FMVSNet1		89.88 310	88.31 323	94.59 212	95.41 275	91.18 149	97.50 137	96.93 237	86.62 326	87.41 333	94.51 295	65.94 392	97.29 354	83.04 337	87.43 320	95.31 308

GeoE		93.89 149	93.28 155	95.72 154	96.96 181	89.75 197	98.24 38	96.92 241	89.47 242	92.12 209	97.21 153	84.42 171	98.39 238	87.71 266	96.50 181	99.01 94

miper_enhance_ethall		91.54 245	91.01 236	93.15 288	95.35 281	87.07 281	93.97 357	96.90 242	86.79 324	89.17 292	93.43 353	86.55 142	97.64 326	89.97 216	86.93 325	94.74 348

eth_miper_zixun_eth		91.02 273	90.59 257	92.34 314	95.33 285	84.35 333	94.10 354	96.90 242	88.56 276	88.84 301	94.33 307	84.08 178	97.60 331	88.77 249	84.37 361	95.06 323

TAMVS		94.01 145	93.46 148	95.64 157	96.16 241	90.45 175	96.71 217	96.89 244	89.27 249	93.46 177	96.92 168	87.29 134	97.94 296	88.70 251	95.74 194	98.53 142

miper_ehance_all_eth		91.59 239	91.13 232	92.97 294	95.55 268	86.57 293	94.47 338	96.88 245	87.77 302	88.88 298	94.01 326	86.22 147	97.54 335	89.49 228	86.93 325	94.79 344

v2v482		91.59 239	90.85 243	93.80 259	93.87 350	88.17 254	96.94 197	96.88 245	89.54 239	89.53 280	94.90 274	81.70 230	98.02 280	89.25 237	85.04 350	95.20 316

CNLPA		94.28 131	93.53 143	96.52 92	98.38 81	92.55 92	96.59 233	96.88 245	90.13 224	91.91 215	97.24 151	85.21 160	99.09 161	87.64 272	97.83 144	97.92 193

PAPM		91.52 246	90.30 267	95.20 179	95.30 288	89.83 195	93.38 377	96.85 248	86.26 334	88.59 306	95.80 230	84.88 164	98.15 257	75.67 389	95.93 190	97.63 211

c3_l		91.38 253	90.89 239	92.88 298	95.58 266	86.30 300	94.68 330	96.84 249	88.17 287	88.83 302	94.23 315	85.65 156	97.47 342	89.36 232	84.63 354	94.89 334

pm-mvs1		90.72 285	89.65 299	93.96 249	94.29 340	89.63 198	97.79 95	96.82 250	89.07 254	86.12 356	95.48 252	78.61 285	97.78 314	86.97 287	81.67 380	94.46 355

test_vis1_n		92.37 206	92.26 191	92.72 304	94.75 320	82.64 353	98.02 59	96.80 251	91.18 185	97.77 49	97.93 99	58.02 408	98.29 246	97.63 33	98.21 131	97.23 234

CMPMVS	62.92 21	85.62 362	84.92 358	87.74 384	89.14 406	73.12 414	94.17 352	96.80 251	73.98 413	73.65 412	94.93 272	66.36 386	97.61 330	83.95 330	91.28 278	92.48 390
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
MS-PatchMatch		90.27 298	89.77 293	91.78 333	94.33 337	84.72 330	95.55 297	96.73 253	86.17 336	86.36 353	95.28 258	71.28 346	97.80 312	84.09 327	98.14 135	92.81 382

Effi-MVS+-dtu		93.08 178	93.21 157	92.68 307	96.02 250	83.25 347	97.14 181	96.72 254	93.85 87	91.20 240	93.44 350	83.08 197	98.30 245	91.69 187	95.73 195	96.50 252

TSAR-MVS + GP.		96.69 58	96.49 62	97.27 62	98.31 84	93.39 63	96.79 209	96.72 254	94.17 76	97.44 55	97.66 123	92.76 31	99.33 126	96.86 52	97.76 148	99.08 88

1112_ss		93.37 166	92.42 187	96.21 123	97.05 174	90.99 155	96.31 254	96.72 254	86.87 323	89.83 270	96.69 180	86.51 143	99.14 153	88.12 256	93.67 242	98.50 146

PVSNet	86.66 18	92.24 214	91.74 209	93.73 262	97.77 129	83.69 344	92.88 386	96.72 254	87.91 295	93.00 188	94.86 276	78.51 286	99.05 171	86.53 290	97.45 156	98.47 151

miper_lstm_enhance		90.50 294	90.06 282	91.83 329	95.33 285	83.74 341	93.86 363	96.70 258	87.56 309	87.79 325	93.81 334	83.45 189	96.92 366	87.39 277	84.62 355	94.82 339

v148		90.99 274	90.38 263	92.81 301	93.83 351	85.80 308	96.78 211	96.68 259	89.45 244	88.75 304	93.93 330	82.96 203	97.82 309	87.83 262	83.25 372	94.80 342

ACMH+	87.92 14	90.20 302	89.18 310	93.25 283	96.48 222	86.45 297	96.99 193	96.68 259	88.83 266	84.79 367	96.22 208	70.16 356	98.53 224	84.42 324	88.04 313	94.77 347

CANet_DTU		94.37 129	93.65 138	96.55 90	96.46 225	92.13 108	96.21 262	96.67 261	94.38 73	93.53 175	97.03 163	79.34 269	99.71 57	90.76 203	98.45 122	97.82 204

cl____		90.96 277	90.32 265	92.89 297	95.37 279	86.21 303	94.46 340	96.64 262	87.82 298	88.15 320	94.18 318	82.98 201	97.54 335	87.70 267	85.59 337	94.92 332

HY-MVS	89.66 9	93.87 150	92.95 162	96.63 85	97.10 168	92.49 94	95.64 294	96.64 262	89.05 256	93.00 188	95.79 233	85.77 155	99.45 116	89.16 242	94.35 222	97.96 191

Test_1112_low_res		92.84 192	91.84 204	95.85 145	97.04 175	89.97 191	95.53 299	96.64 262	85.38 346	89.65 276	95.18 263	85.86 153	99.10 158	87.70 267	93.58 247	98.49 148

DIV-MVS_self_test		90.97 276	90.33 264	92.88 298	95.36 280	86.19 304	94.46 340	96.63 265	87.82 298	88.18 319	94.23 315	82.99 200	97.53 337	87.72 264	85.57 338	94.93 330

Fast-Effi-MVS+-dtu		92.29 211	91.99 199	93.21 286	95.27 289	85.52 312	97.03 186	96.63 265	92.09 154	89.11 294	95.14 265	80.33 252	98.08 268	87.54 275	94.74 218	96.03 270

UnsupCasMVSNet_bld		82.13 376	79.46 381	90.14 366	88.00 414	82.47 358	90.89 404	96.62 267	78.94 403	75.61 407	84.40 418	56.63 411	96.31 376	77.30 381	66.77 419	91.63 400

cl22		91.21 264	90.56 259	93.14 289	96.09 248	86.80 285	94.41 342	96.58 268	87.80 300	88.58 307	93.99 328	80.85 243	97.62 329	89.87 219	86.93 325	94.99 325

jason		94.84 119	94.39 125	96.18 125	95.52 269	90.93 159	96.09 267	96.52 269	89.28 248	96.01 115	97.32 145	84.70 166	98.77 199	95.15 111	98.91 102	98.85 119
jason: jason.
tt0805		91.09 269	90.07 281	94.16 237	95.61 264	88.31 246	97.56 129	96.51 270	89.56 238	89.17 292	95.64 242	67.08 384	98.38 239	91.07 199	88.44 311	95.80 278

AUN-MVS		91.76 231	90.75 249	94.81 202	97.00 179	88.57 238	96.65 224	96.49 271	89.63 236	92.15 207	96.12 214	78.66 284	98.50 226	90.83 201	79.18 391	97.36 226

hse-mvs2		93.45 164	92.99 160	94.81 202	97.02 177	88.59 237	96.69 220	96.47 272	95.19 28	96.74 79	96.16 212	83.67 184	98.48 229	95.85 88	79.13 392	97.35 228

EG-PatchMatch MVS		87.02 345	85.44 350	91.76 335	92.67 380	85.00 324	96.08 268	96.45 273	83.41 376	79.52 399	93.49 347	57.10 410	97.72 320	79.34 372	90.87 287	92.56 387

KD-MVS_self_test		85.95 358	84.95 357	88.96 378	89.55 405	79.11 397	95.13 320	96.42 274	85.91 339	84.07 376	90.48 390	70.03 358	94.82 397	80.04 364	72.94 408	92.94 380

pmmvs6		87.81 337	86.19 345	92.69 306	91.32 393	86.30 300	97.34 159	96.41 275	80.59 397	84.05 377	94.37 304	67.37 379	97.67 323	84.75 319	79.51 390	94.09 367

PMMVS		92.86 190	92.34 188	94.42 224	94.92 311	86.73 288	94.53 335	96.38 276	84.78 358	94.27 157	95.12 267	83.13 196	98.40 233	91.47 191	96.49 182	98.12 179

RPSCF		90.75 283	90.86 241	90.42 362	96.84 187	76.29 405	95.61 295	96.34 277	83.89 367	91.38 228	97.87 104	76.45 308	98.78 196	87.16 284	92.23 260	96.20 259

BP-MVS1		95.89 87	95.49 87	97.08 74	96.67 202	93.20 73	98.08 53	96.32 278	94.56 61	96.32 100	97.84 109	84.07 179	99.15 150	96.75 54	98.78 105	98.90 111

MSDG		91.42 251	90.24 271	94.96 195	97.15 166	88.91 230	93.69 369	96.32 278	85.72 342	86.93 348	96.47 196	80.24 253	98.98 177	80.57 361	95.05 211	96.98 238

WBMVS		90.69 288	89.99 284	92.81 301	96.48 222	85.00 324	95.21 318	96.30 280	89.46 243	89.04 295	94.05 325	72.45 339	97.82 309	89.46 229	87.41 322	95.61 289

OurMVSNet-221017-0		90.51 293	90.19 276	91.44 341	93.41 365	81.25 368	96.98 194	96.28 281	91.68 166	86.55 352	96.30 204	74.20 328	97.98 284	88.96 245	87.40 323	95.09 321

MVP-Stereo		90.74 284	90.08 278	92.71 305	93.19 370	88.20 252	95.86 279	96.27 282	86.07 337	84.86 366	94.76 281	77.84 298	97.75 318	83.88 332	98.01 139	92.17 397
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
lupinMVS		94.99 114	94.56 116	96.29 117	96.34 232	91.21 144	95.83 281	96.27 282	88.93 262	96.22 105	96.88 170	86.20 149	98.85 189	95.27 107	99.05 93	98.82 123

BH-untuned		92.94 186	92.62 177	93.92 255	97.22 160	86.16 305	96.40 246	96.25 284	90.06 225	89.79 271	96.17 211	83.19 193	98.35 241	87.19 282	97.27 164	97.24 233

CL-MVSNet_self_test		86.31 353	85.15 354	89.80 370	88.83 409	81.74 366	93.93 360	96.22 285	86.67 325	85.03 364	90.80 388	78.09 294	94.50 398	74.92 392	71.86 410	93.15 378

IS-MVSNet		94.90 116	94.52 120	96.05 131	97.67 135	90.56 171	98.44 21	96.22 285	93.21 112	93.99 164	97.74 117	85.55 157	98.45 230	89.98 215	97.86 143	99.14 80

FA-MVS(test-final)		93.52 162	92.92 163	95.31 176	96.77 197	88.54 240	94.82 327	96.21 287	89.61 237	94.20 159	95.25 261	83.24 191	99.14 153	90.01 214	96.16 186	98.25 167

GA-MVS		91.38 253	90.31 266	94.59 212	94.65 325	87.62 268	94.34 345	96.19 288	90.73 199	90.35 251	93.83 331	71.84 342	97.96 291	87.22 281	93.61 245	98.21 170

IterMVS-SCA-FT		90.31 296	89.81 291	91.82 330	95.52 269	84.20 336	94.30 348	96.15 289	90.61 209	87.39 334	94.27 312	75.80 314	96.44 374	87.34 278	86.88 329	94.82 339

IterMVS		90.15 304	89.67 297	91.61 337	95.48 271	83.72 342	94.33 346	96.12 290	89.99 226	87.31 337	94.15 320	75.78 316	96.27 377	86.97 287	86.89 328	94.83 337
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
DP-MVS		92.76 195	91.51 218	96.52 92	98.77 56	90.99 155	97.38 156	96.08 291	82.38 382	89.29 288	97.87 104	83.77 182	99.69 63	81.37 355	96.69 178	98.89 115

pmmvs4		90.93 278	89.85 289	94.17 236	93.34 367	90.79 164	94.60 332	96.02 292	84.62 359	87.45 331	95.15 264	81.88 227	97.45 344	87.70 267	87.87 315	94.27 364

ppachtmachnet_test		88.35 332	87.29 331	91.53 338	92.45 386	83.57 345	93.75 366	95.97 293	84.28 362	85.32 363	94.18 318	79.00 281	96.93 365	75.71 388	84.99 351	94.10 365

Anonymous20240521		86.42 351	85.44 350	89.34 376	90.33 398	79.79 388	96.73 214	95.92 294	83.71 372	83.25 382	91.36 385	63.92 397	96.01 378	78.39 376	85.36 342	92.22 395

ITE_SJBPF				92.43 310	95.34 282	85.37 317		95.92 294	91.47 171	87.75 327	96.39 201	71.00 348	97.96 291	82.36 346	89.86 297	93.97 368

test_fmvs2		89.77 314	89.93 286	89.31 377	93.68 356	76.37 404	97.64 120	95.90 296	89.84 232	91.49 226	96.26 207	58.77 407	97.10 358	94.65 126	91.13 280	94.46 355

USDC		88.94 323	87.83 328	92.27 316	94.66 324	84.96 326	93.86 363	95.90 296	87.34 314	83.40 380	95.56 246	67.43 378	98.19 254	82.64 345	89.67 299	93.66 371

COLMAP_ROB	87.81 15	90.40 295	89.28 307	93.79 260	97.95 118	87.13 280	96.92 198	95.89 298	82.83 379	86.88 350	97.18 154	73.77 332	99.29 133	78.44 375	93.62 244	94.95 326
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
VDD-MVS		93.82 152	93.08 158	96.02 134	97.88 124	89.96 192	97.72 105	95.85 299	92.43 142	95.86 119	98.44 54	68.42 374	99.39 122	96.31 65	94.85 212	98.71 130

VDDNet		93.05 180	92.07 194	96.02 134	96.84 187	90.39 179	98.08 53	95.85 299	86.22 335	95.79 122	98.46 52	67.59 377	99.19 141	94.92 116	94.85 212	98.47 151

mvsmamba		94.57 125	94.14 129	95.87 142	97.03 176	89.93 193	97.84 86	95.85 299	91.34 177	94.79 145	96.80 172	80.67 244	98.81 193	94.85 117	98.12 136	98.85 119

Vis-MVSNet (Re-imp)		94.15 136	93.88 133	94.95 196	97.61 143	87.92 260	98.10 51	95.80 302	92.22 147	93.02 187	97.45 138	84.53 169	97.91 302	88.24 255	97.97 140	99.02 91

MM		97.29 23	96.98 33	98.23 11	98.01 112	95.03 26	98.07 55	95.76 303	97.78 1	97.52 52	98.80 32	88.09 111	99.86 9	99.44 1	99.37 62	99.80 1

KD-MVS_2432*1600		84.81 366	82.64 370	91.31 343	91.07 395	85.34 318	91.22 399	95.75 304	85.56 344	83.09 383	90.21 393	67.21 380	95.89 380	77.18 382	62.48 423	92.69 383

miper_refine_blended		84.81 366	82.64 370	91.31 343	91.07 395	85.34 318	91.22 399	95.75 304	85.56 344	83.09 383	90.21 393	67.21 380	95.89 380	77.18 382	62.48 423	92.69 383

FE-MVS		92.05 222	91.05 234	95.08 185	96.83 189	87.93 259	93.91 362	95.70 306	86.30 332	94.15 161	94.97 269	76.59 306	99.21 139	84.10 326	96.86 171	98.09 183

tpm cat1		88.36 331	87.21 334	91.81 331	95.13 301	80.55 377	92.58 390	95.70 306	74.97 412	87.45 331	91.96 379	78.01 297	98.17 256	80.39 363	88.74 308	96.72 248

our_test_3		88.78 327	87.98 327	91.20 347	92.45 386	82.53 355	93.61 373	95.69 308	85.77 341	84.88 365	93.71 336	79.99 258	96.78 371	79.47 369	86.24 331	94.28 363

BH-w/o		92.14 219	91.75 207	93.31 281	96.99 180	85.73 309	95.67 289	95.69 308	88.73 272	89.26 290	94.82 279	82.97 202	98.07 272	85.26 314	96.32 185	96.13 266

CR-MVSNet		90.82 281	89.77 293	93.95 250	94.45 333	87.19 277	90.23 407	95.68 310	86.89 322	92.40 197	92.36 372	80.91 240	97.05 360	81.09 359	93.95 238	97.60 216

Patchmtry		88.64 329	87.25 332	92.78 303	94.09 343	86.64 289	89.82 411	95.68 310	80.81 394	87.63 329	92.36 372	80.91 240	97.03 361	78.86 373	85.12 347	94.67 350

testing91		91.90 227	91.02 235	94.53 219	96.54 214	86.55 295	95.86 279	95.64 312	91.77 163	91.89 216	93.47 349	69.94 359	98.86 187	90.23 213	93.86 240	98.18 172

BH-RMVSNet		92.72 197	91.97 200	94.97 194	97.16 164	87.99 258	96.15 265	95.60 313	90.62 208	91.87 217	97.15 157	78.41 288	98.57 222	83.16 335	97.60 150	98.36 163

PVSNet_0	82.17 19	85.46 363	83.64 366	90.92 351	95.27 289	79.49 393	90.55 405	95.60 313	83.76 371	83.00 385	89.95 395	71.09 347	97.97 287	82.75 343	60.79 425	95.31 308

SCA		91.84 229	91.18 231	93.83 257	95.59 265	84.95 327	94.72 329	95.58 315	90.82 195	92.25 205	93.69 338	75.80 314	98.10 263	86.20 296	95.98 188	98.45 153

MonoMVSNet		91.92 225	91.77 205	92.37 311	92.94 374	83.11 349	97.09 184	95.55 316	92.91 132	90.85 243	94.55 292	81.27 236	96.52 373	93.01 163	87.76 316	97.47 222

AllTest		90.23 300	88.98 313	93.98 246	97.94 119	86.64 289	96.51 237	95.54 317	85.38 346	85.49 360	96.77 174	70.28 354	99.15 150	80.02 365	92.87 249	96.15 264

TestCases				93.98 246	97.94 119	86.64 289		95.54 317	85.38 346	85.49 360	96.77 174	70.28 354	99.15 150	80.02 365	92.87 249	96.15 264

mmtdpeth		89.70 316	88.96 314	91.90 326	95.84 258	84.42 332	97.46 146	95.53 319	90.27 219	94.46 154	90.50 389	69.74 363	98.95 178	97.39 44	69.48 414	92.34 391

tpmvs		89.83 313	89.15 311	91.89 327	94.92 311	80.30 381	93.11 382	95.46 320	86.28 333	88.08 321	92.65 362	80.44 249	98.52 225	81.47 351	89.92 296	96.84 244

pmmvs5		89.86 312	88.87 317	92.82 300	92.86 376	86.23 302	96.26 257	95.39 321	84.24 363	87.12 339	94.51 295	74.27 327	97.36 351	87.61 274	87.57 318	94.86 335

PatchmatchNet		91.91 226	91.35 220	93.59 270	95.38 277	84.11 337	93.15 381	95.39 321	89.54 239	92.10 210	93.68 340	82.82 206	98.13 258	84.81 318	95.32 204	98.52 143
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
tpmrst		91.44 250	91.32 222	91.79 332	95.15 299	79.20 396	93.42 376	95.37 323	88.55 277	93.49 176	93.67 341	82.49 214	98.27 247	90.41 208	89.34 302	97.90 194

Anonymous20231206		87.09 344	86.14 346	89.93 369	91.22 394	80.35 379	96.11 266	95.35 324	83.57 374	84.16 372	93.02 357	73.54 334	95.61 388	72.16 404	86.14 333	93.84 370

MIMVSNet1		84.93 365	83.05 367	90.56 360	89.56 404	84.84 329	95.40 304	95.35 324	83.91 366	80.38 395	92.21 376	57.23 409	93.34 410	70.69 410	82.75 378	93.50 373

TDRefinement		86.53 348	84.76 360	91.85 328	82.23 426	84.25 334	96.38 248	95.35 324	84.97 355	84.09 375	94.94 271	65.76 393	98.34 244	84.60 322	74.52 404	92.97 379

TR-MVS		91.48 249	90.59 257	94.16 237	96.40 228	87.33 270	95.67 289	95.34 327	87.68 306	91.46 227	95.52 249	76.77 305	98.35 241	82.85 340	93.61 245	96.79 246

EPNet_dtu		91.71 232	91.28 225	92.99 293	93.76 353	83.71 343	96.69 220	95.28 328	93.15 119	87.02 344	95.95 222	83.37 190	97.38 350	79.46 370	96.84 172	97.88 196
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
FMVSNet5		87.29 341	85.79 348	91.78 333	94.80 318	87.28 272	95.49 301	95.28 328	84.09 365	83.85 379	91.82 380	62.95 400	94.17 402	78.48 374	85.34 343	93.91 369

MDTV_nov1_ep13			90.76 247		95.22 293	80.33 380	93.03 384	95.28 328	88.14 290	92.84 194	93.83 331	81.34 233	98.08 268	82.86 338	94.34 223

LF4IMVS		87.94 335	87.25 332	89.98 368	92.38 388	80.05 387	94.38 343	95.25 331	87.59 308	84.34 369	94.74 283	64.31 396	97.66 325	84.83 317	87.45 319	92.23 394

TransMVSNet (Re)		88.94 323	87.56 329	93.08 291	94.35 336	88.45 244	97.73 102	95.23 332	87.47 310	84.26 371	95.29 256	79.86 261	97.33 352	79.44 371	74.44 405	93.45 375

test20.03		86.14 356	85.40 352	88.35 379	90.12 399	80.06 386	95.90 278	95.20 333	88.59 273	81.29 390	93.62 343	71.43 345	92.65 414	71.26 408	81.17 383	92.34 391

new-patchmatchnet		83.18 372	81.87 375	87.11 387	86.88 417	75.99 406	93.70 367	95.18 334	85.02 354	77.30 406	88.40 405	65.99 391	93.88 407	74.19 397	70.18 412	91.47 404

MDA-MVSNet_test_wron		85.87 360	84.23 364	90.80 357	92.38 388	82.57 354	93.17 379	95.15 335	82.15 383	67.65 418	92.33 375	78.20 290	95.51 391	77.33 379	79.74 387	94.31 362

YYNet1		85.87 360	84.23 364	90.78 358	92.38 388	82.46 359	93.17 379	95.14 336	82.12 384	67.69 416	92.36 372	78.16 293	95.50 392	77.31 380	79.73 388	94.39 358

Baseline_NR-MVSNet		91.20 265	90.62 255	92.95 295	93.83 351	88.03 257	97.01 191	95.12 337	88.42 281	89.70 273	95.13 266	83.47 187	97.44 345	89.66 225	83.24 373	93.37 376

thres200		92.23 215	91.39 219	94.75 209	97.61 143	89.03 228	96.60 232	95.09 338	92.08 155	93.28 182	94.00 327	78.39 289	99.04 174	81.26 358	94.18 229	96.19 260

ADS-MVSNet		89.89 309	88.68 319	93.53 273	95.86 253	84.89 328	90.93 402	95.07 339	83.23 377	91.28 236	91.81 381	79.01 279	97.85 305	79.52 367	91.39 276	97.84 201

pmmvs-eth3d		86.22 354	84.45 362	91.53 338	88.34 413	87.25 274	94.47 338	95.01 340	83.47 375	79.51 400	89.61 398	69.75 362	95.71 385	83.13 336	76.73 399	91.64 399

Anonymous202405211		92.07 221	90.83 245	95.76 148	98.19 98	88.75 233	97.58 126	95.00 341	86.00 338	93.64 171	97.45 138	66.24 389	99.53 102	90.68 206	92.71 254	99.01 94

MDA-MVSNet-bldmvs		85.00 364	82.95 369	91.17 349	93.13 372	83.33 346	94.56 334	95.00 341	84.57 360	65.13 422	92.65 362	70.45 353	95.85 382	73.57 400	77.49 395	94.33 360

ambc				86.56 390	83.60 423	70.00 417	85.69 421	94.97 343		80.60 394	88.45 404	37.42 425	96.84 369	82.69 344	75.44 403	92.86 381

testgi		87.97 334	87.21 334	90.24 365	92.86 376	80.76 372	96.67 223	94.97 343	91.74 164	85.52 359	95.83 228	62.66 402	94.47 400	76.25 386	88.36 312	95.48 292

myMVS_eth3d28		91.52 246	90.97 237	93.17 287	96.91 182	83.24 348	95.61 295	94.96 345	92.24 146	91.98 213	93.28 354	69.31 364	98.40 233	88.71 250	95.68 197	97.88 196

dp		88.90 325	88.26 325	90.81 355	94.58 329	76.62 403	92.85 387	94.93 346	85.12 352	90.07 265	93.07 356	75.81 313	98.12 261	80.53 362	87.42 321	97.71 208

test_fmvs3		83.21 371	83.02 368	83.78 394	86.77 418	68.34 420	96.76 212	94.91 347	86.49 328	84.14 374	89.48 399	36.04 426	91.73 416	91.86 181	80.77 385	91.26 406

test_0402		86.46 350	84.79 359	91.45 340	95.02 305	85.55 311	96.29 256	94.89 348	80.90 391	82.21 387	93.97 329	68.21 375	97.29 354	62.98 417	88.68 309	91.51 402

tfpn200view9		92.38 205	91.52 216	94.95 196	97.85 125	89.29 218	97.41 149	94.88 349	92.19 151	93.27 183	94.46 300	78.17 291	99.08 164	81.40 352	94.08 233	96.48 253

CVMVSNet		91.23 263	91.75 207	89.67 371	95.77 259	74.69 407	96.44 238	94.88 349	85.81 340	92.18 206	97.64 127	79.07 274	95.58 390	88.06 258	95.86 192	98.74 127

thres400		92.42 203	91.52 216	95.12 184	97.85 125	89.29 218	97.41 149	94.88 349	92.19 151	93.27 183	94.46 300	78.17 291	99.08 164	81.40 352	94.08 233	96.98 238

EPNet		95.20 107	94.56 116	97.14 69	92.80 378	92.68 87	97.85 85	94.87 352	96.64 4	92.46 196	97.80 114	86.23 146	99.65 69	93.72 145	98.62 113	99.10 86
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
testing99		91.62 237	90.72 252	94.32 229	96.48 222	86.11 306	95.81 282	94.76 353	91.55 168	91.75 221	93.44 350	68.55 372	98.82 191	90.43 207	93.69 241	98.04 187

SixPastTwentyTwo		89.15 321	88.54 321	90.98 350	93.49 362	80.28 383	96.70 218	94.70 354	90.78 196	84.15 373	95.57 245	71.78 343	97.71 321	84.63 321	85.07 348	94.94 328

thres100view900		92.43 202	91.58 213	94.98 192	97.92 121	89.37 214	97.71 107	94.66 355	92.20 149	93.31 181	94.90 274	78.06 295	99.08 164	81.40 352	94.08 233	96.48 253

thres600view7		92.49 201	91.60 212	95.18 180	97.91 122	89.47 208	97.65 116	94.66 355	92.18 153	93.33 180	94.91 273	78.06 295	99.10 158	81.61 349	94.06 237	96.98 238

PatchT		88.87 326	87.42 330	93.22 285	94.08 344	85.10 322	89.51 412	94.64 357	81.92 385	92.36 200	88.15 408	80.05 257	97.01 363	72.43 403	93.65 243	97.54 219

baseline1		92.82 193	91.90 202	95.55 164	97.20 162	90.77 165	97.19 176	94.58 358	92.20 149	92.36 200	96.34 203	84.16 177	98.21 251	89.20 240	83.90 368	97.68 210

UBG		91.55 243	90.76 247	93.94 252	96.52 218	85.06 323	95.22 316	94.54 359	90.47 215	91.98 213	92.71 361	72.02 340	98.74 203	88.10 257	95.26 206	98.01 189

Gipuma		67.86 392	65.41 394	75.18 407	92.66 381	73.45 411	66.50 428	94.52 360	53.33 427	57.80 428	66.07 428	30.81 428	89.20 420	48.15 426	78.88 394	62.90 428
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testing11		91.68 235	90.75 249	94.47 220	96.53 216	86.56 294	95.76 286	94.51 361	91.10 190	91.24 238	93.59 344	68.59 371	98.86 187	91.10 198	94.29 225	98.00 190

CostFormer		91.18 268	90.70 253	92.62 308	94.84 316	81.76 365	94.09 355	94.43 362	84.15 364	92.72 195	93.77 335	79.43 268	98.20 252	90.70 205	92.18 263	97.90 194

tpm2		89.96 306	89.21 309	92.23 319	94.91 313	81.25 368	93.78 365	94.42 363	80.62 396	91.56 224	93.44 350	76.44 309	97.94 296	85.60 308	92.08 267	97.49 220

testing3-2		92.10 220	92.05 195	92.27 316	97.71 133	79.56 390	97.42 148	94.41 364	93.53 100	93.22 185	95.49 250	69.16 366	99.11 156	93.25 153	94.22 227	98.13 177

MVS_0304		96.74 55	96.31 72	98.02 19	96.87 184	94.65 30	97.58 126	94.39 365	96.47 7	97.16 64	98.39 58	87.53 127	99.87 7	98.97 15	99.41 54	99.55 35

JIA-IIPM		88.26 333	87.04 337	91.91 325	93.52 360	81.42 367	89.38 413	94.38 366	80.84 393	90.93 242	80.74 420	79.22 271	97.92 299	82.76 342	91.62 271	96.38 256

dmvs_re		90.21 301	89.50 302	92.35 312	95.47 274	85.15 320	95.70 288	94.37 367	90.94 194	88.42 309	93.57 345	74.63 324	95.67 387	82.80 341	89.57 300	96.22 258

Patchmatch-test		89.42 319	87.99 326	93.70 265	95.27 289	85.11 321	88.98 414	94.37 367	81.11 390	87.10 342	93.69 338	82.28 218	97.50 340	74.37 395	94.76 216	98.48 150

LCM-MVSNet		72.55 385	69.39 389	82.03 396	70.81 436	65.42 425	90.12 409	94.36 369	55.02 426	65.88 420	81.72 419	24.16 434	89.96 417	74.32 396	68.10 417	90.71 409

ADS-MVSNet2		89.45 318	88.59 320	92.03 322	95.86 253	82.26 361	90.93 402	94.32 370	83.23 377	91.28 236	91.81 381	79.01 279	95.99 379	79.52 367	91.39 276	97.84 201

mvs5depth		86.53 348	85.08 355	90.87 352	88.74 411	82.52 356	91.91 395	94.23 371	86.35 331	87.11 341	93.70 337	66.52 385	97.76 317	81.37 355	75.80 401	92.31 393

EU-MVSNet		88.72 328	88.90 316	88.20 381	93.15 371	74.21 409	96.63 229	94.22 372	85.18 350	87.32 336	95.97 220	76.16 311	94.98 396	85.27 313	86.17 332	95.41 298

MIMVSNet		88.50 330	86.76 340	93.72 264	94.84 316	87.77 266	91.39 397	94.05 373	86.41 330	87.99 323	92.59 365	63.27 398	95.82 384	77.44 378	92.84 251	97.57 218

OpenMVS_ROB	81.14 20	84.42 368	82.28 374	90.83 353	90.06 400	84.05 339	95.73 287	94.04 374	73.89 415	80.17 398	91.53 384	59.15 406	97.64 326	66.92 415	89.05 304	90.80 408

TinyColmap		86.82 346	85.35 353	91.21 345	94.91 313	82.99 351	93.94 359	94.02 375	83.58 373	81.56 389	94.68 285	62.34 403	98.13 258	75.78 387	87.35 324	92.52 389

ETVMVS		90.52 292	89.14 312	94.67 211	96.81 193	87.85 264	95.91 277	93.97 376	89.71 235	92.34 203	92.48 367	65.41 394	97.96 291	81.37 355	94.27 226	98.21 170

IB-MVS	87.33 17	89.91 307	88.28 324	94.79 206	95.26 292	87.70 267	95.12 321	93.95 377	89.35 247	87.03 343	92.49 366	70.74 351	99.19 141	89.18 241	81.37 382	97.49 220
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		87.13 343	87.02 338	87.47 385	95.16 296	73.21 413	95.00 323	93.93 378	88.55 277	86.96 345	91.99 377	75.90 312	94.00 404	61.59 419	94.11 230	95.20 316

myMVS_eth3d		87.18 342	86.38 343	89.58 372	95.16 296	79.53 391	95.00 323	93.93 378	88.55 277	86.96 345	91.99 377	56.23 412	94.00 404	75.47 391	94.11 230	95.20 316

testing222		90.31 296	88.96 314	94.35 226	96.54 214	87.29 271	95.50 300	93.84 380	90.97 193	91.75 221	92.96 358	62.18 404	98.00 282	82.86 338	94.08 233	97.76 206

test_f		80.57 378	79.62 380	83.41 395	83.38 424	67.80 422	93.57 374	93.72 381	80.80 395	77.91 405	87.63 411	33.40 427	92.08 415	87.14 285	79.04 393	90.34 410

LCM-MVSNet-Re		92.50 199	92.52 183	92.44 309	96.82 191	81.89 364	96.92 198	93.71 382	92.41 143	84.30 370	94.60 290	85.08 162	97.03 361	91.51 189	97.36 158	98.40 159

tpm		90.25 299	89.74 296	91.76 335	93.92 347	79.73 389	93.98 356	93.54 383	88.28 284	91.99 212	93.25 355	77.51 301	97.44 345	87.30 280	87.94 314	98.12 179

ET-MVSNet_ETH3D		91.49 248	90.11 277	95.63 158	96.40 228	91.57 130	95.34 307	93.48 384	90.60 211	75.58 408	95.49 250	80.08 256	96.79 370	94.25 133	89.76 298	98.52 143

LFMVS		93.60 158	92.63 176	96.52 92	98.13 104	91.27 141	97.94 73	93.39 385	90.57 212	96.29 102	98.31 71	69.00 367	99.16 148	94.18 134	95.87 191	99.12 84

MVStest1		82.38 375	80.04 379	89.37 374	87.63 416	82.83 352	95.03 322	93.37 386	73.90 414	73.50 413	94.35 305	62.89 401	93.25 412	73.80 398	65.92 420	92.04 398

Patchmatch-RL test		87.38 340	86.24 344	90.81 355	88.74 411	78.40 400	88.12 419	93.17 387	87.11 319	82.17 388	89.29 400	81.95 225	95.60 389	88.64 252	77.02 396	98.41 158

ttmdpeth		85.91 359	84.76 360	89.36 375	89.14 406	80.25 384	95.66 292	93.16 388	83.77 370	83.39 381	95.26 260	66.24 389	95.26 395	80.65 360	75.57 402	92.57 386

test-LLR		91.42 251	91.19 230	92.12 320	94.59 327	80.66 374	94.29 349	92.98 389	91.11 188	90.76 245	92.37 369	79.02 277	98.07 272	88.81 247	96.74 175	97.63 211

test-mter		90.19 303	89.54 301	92.12 320	94.59 327	80.66 374	94.29 349	92.98 389	87.68 306	90.76 245	92.37 369	67.67 376	98.07 272	88.81 247	96.74 175	97.63 211

WB-MVSnew		89.88 310	89.56 300	90.82 354	94.57 330	83.06 350	95.65 293	92.85 391	87.86 297	90.83 244	94.10 321	79.66 265	96.88 367	76.34 385	94.19 228	92.54 388

testing3		87.67 338	86.88 339	90.05 367	96.14 244	80.71 373	97.10 183	92.85 391	90.15 223	87.54 330	94.55 292	55.70 413	94.10 403	73.77 399	94.10 232	95.35 305

test_method		66.11 393	64.89 395	69.79 410	72.62 434	35.23 442	65.19 429	92.83 393	20.35 432	65.20 421	88.08 409	43.14 423	82.70 427	73.12 402	63.46 422	91.45 405

test0.0.03 1		89.37 320	88.70 318	91.41 342	92.47 385	85.63 310	95.22 316	92.70 394	91.11 188	86.91 349	93.65 342	79.02 277	93.19 413	78.00 377	89.18 303	95.41 298

new_pmnet		82.89 373	81.12 378	88.18 382	89.63 403	80.18 385	91.77 396	92.57 395	76.79 410	75.56 409	88.23 407	61.22 405	94.48 399	71.43 406	82.92 376	89.87 411

mvsany_test1		93.93 148	93.98 131	93.78 261	94.94 310	86.80 285	94.62 331	92.55 396	88.77 271	96.85 74	98.49 48	88.98 95	98.08 268	95.03 113	95.62 199	96.46 255

thisisatest0515		92.29 211	91.30 224	95.25 178	96.60 206	88.90 231	94.36 344	92.32 397	87.92 294	93.43 178	94.57 291	77.28 302	99.00 175	89.42 231	95.86 192	97.86 200

thisisatest0530		93.03 181	92.21 192	95.49 168	97.07 169	89.11 227	97.49 143	92.19 398	90.16 222	94.09 162	96.41 199	76.43 310	99.05 171	90.38 209	95.68 197	98.31 165

tttt0517		92.96 184	92.33 189	94.87 199	97.11 167	87.16 279	97.97 69	92.09 399	90.63 207	93.88 168	97.01 164	76.50 307	99.06 170	90.29 212	95.45 202	98.38 161

K. test v3		87.64 339	86.75 341	90.32 364	93.02 373	79.48 394	96.61 230	92.08 400	90.66 205	80.25 397	94.09 323	67.21 380	96.65 372	85.96 304	80.83 384	94.83 337

TESTMET0.1,1		90.06 305	89.42 304	91.97 323	94.41 335	80.62 376	94.29 349	91.97 401	87.28 316	90.44 249	92.47 368	68.79 368	97.67 323	88.50 254	96.60 180	97.61 215

PM-MVS		83.48 370	81.86 376	88.31 380	87.83 415	77.59 402	93.43 375	91.75 402	86.91 321	80.63 393	89.91 396	44.42 422	95.84 383	85.17 316	76.73 399	91.50 403

baseline2		91.63 236	90.86 241	93.94 252	94.33 337	86.32 299	95.92 276	91.64 403	89.37 246	86.94 347	94.69 284	81.62 231	98.69 209	88.64 252	94.57 221	96.81 245

APD_test1		79.31 380	77.70 383	84.14 393	89.11 408	69.07 419	92.36 394	91.50 404	69.07 418	73.87 411	92.63 364	39.93 424	94.32 401	70.54 411	80.25 386	89.02 413

FPMVS		71.27 386	69.85 388	75.50 406	74.64 431	59.03 431	91.30 398	91.50 404	58.80 423	57.92 427	88.28 406	29.98 430	85.53 426	53.43 424	82.84 377	81.95 419

door								91.13 406

door-mid								91.06 407

EGC-MVSNET		68.77 391	63.01 397	86.07 392	92.49 384	82.24 362	93.96 358	90.96 408	0.71 437	2.62 438	90.89 387	53.66 414	93.46 408	57.25 422	84.55 358	82.51 418

mvsany_test3		83.59 369	82.44 373	87.03 388	83.80 421	73.82 410	93.70 367	90.92 409	86.42 329	82.51 386	90.26 392	46.76 421	95.71 385	90.82 202	76.76 398	91.57 401

pmmvs3		79.97 379	77.50 384	87.39 386	82.80 425	79.38 395	92.70 389	90.75 410	70.69 417	78.66 402	87.47 413	51.34 417	93.40 409	73.39 401	69.65 413	89.38 412

UWE-MVS		89.91 307	89.48 303	91.21 345	95.88 252	78.23 401	94.91 326	90.26 411	89.11 253	92.35 202	94.52 294	68.76 369	97.96 291	83.95 330	95.59 200	97.42 224

DSMNet-mixed		86.34 352	86.12 347	87.00 389	89.88 402	70.43 415	94.93 325	90.08 412	77.97 407	85.42 362	92.78 360	74.44 326	93.96 406	74.43 394	95.14 207	96.62 249

MVS-HIRNet		82.47 374	81.21 377	86.26 391	95.38 277	69.21 418	88.96 415	89.49 413	66.28 420	80.79 392	74.08 425	68.48 373	97.39 349	71.93 405	95.47 201	92.18 396

WB-MVS		76.77 382	76.63 385	77.18 401	85.32 419	56.82 433	94.53 335	89.39 414	82.66 381	71.35 414	89.18 401	75.03 321	88.88 421	35.42 430	66.79 418	85.84 415

test1111		93.19 173	92.82 167	94.30 232	97.58 149	84.56 331	98.21 42	89.02 415	93.53 100	94.58 149	98.21 78	72.69 336	99.05 171	93.06 159	98.48 120	99.28 69

SSC-MVS		76.05 383	75.83 386	76.72 405	84.77 420	56.22 434	94.32 347	88.96 416	81.82 387	70.52 415	88.91 402	74.79 323	88.71 422	33.69 431	64.71 421	85.23 416

ECVR-MVS		93.19 173	92.73 173	94.57 217	97.66 137	85.41 314	98.21 42	88.23 417	93.43 105	94.70 147	98.21 78	72.57 337	99.07 168	93.05 160	98.49 118	99.25 72

EPMVS		90.70 286	89.81 291	93.37 279	94.73 322	84.21 335	93.67 370	88.02 418	89.50 241	92.38 199	93.49 347	77.82 299	97.78 314	86.03 302	92.68 255	98.11 182

ANet_high		63.94 395	59.58 398	77.02 402	61.24 438	66.06 423	85.66 422	87.93 419	78.53 405	42.94 430	71.04 427	25.42 433	80.71 429	52.60 425	30.83 431	84.28 417

PMMVS2		70.19 387	66.92 391	80.01 397	76.35 430	65.67 424	86.22 420	87.58 420	64.83 422	62.38 423	80.29 422	26.78 432	88.49 424	63.79 416	54.07 427	85.88 414

lessismore_v0				90.45 361	91.96 391	79.09 398		87.19 421		80.32 396	94.39 302	66.31 388	97.55 334	84.00 329	76.84 397	94.70 349

PMVS	53.92 22	58.58 396	55.40 399	68.12 411	51.00 439	48.64 436	78.86 425	87.10 422	46.77 428	35.84 434	74.28 424	8.76 438	86.34 425	42.07 428	73.91 406	69.38 425
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
UWE-MVS-28		86.81 347	86.41 342	88.02 383	92.87 375	74.60 408	95.38 306	86.70 423	88.17 287	87.28 338	94.67 287	70.83 350	93.30 411	67.45 413	94.31 224	96.17 261

test_vis1_rt		86.16 355	85.06 356	89.46 373	93.47 364	80.46 378	96.41 242	86.61 424	85.22 349	79.15 401	88.64 403	52.41 416	97.06 359	93.08 158	90.57 289	90.87 407

testf1		69.31 389	66.76 392	76.94 403	78.61 428	61.93 427	88.27 417	86.11 425	55.62 424	59.69 424	85.31 416	20.19 436	89.32 418	57.62 420	69.44 415	79.58 420

APD_test2		69.31 389	66.76 392	76.94 403	78.61 428	61.93 427	88.27 417	86.11 425	55.62 424	59.69 424	85.31 416	20.19 436	89.32 418	57.62 420	69.44 415	79.58 420

gg-mvs-nofinetune		87.82 336	85.61 349	94.44 222	94.46 332	89.27 221	91.21 401	84.61 427	80.88 392	89.89 269	74.98 423	71.50 344	97.53 337	85.75 307	97.21 166	96.51 251

dmvs_testset		81.38 377	82.60 372	77.73 400	91.74 392	51.49 435	93.03 384	84.21 428	89.07 254	78.28 404	91.25 386	76.97 304	88.53 423	56.57 423	82.24 379	93.16 377

GG-mvs-BLEND				93.62 268	93.69 355	89.20 223	92.39 393	83.33 429		87.98 324	89.84 397	71.00 348	96.87 368	82.08 348	95.40 203	94.80 342

MTMP							97.86 82	82.03 430

DeepMVS_CX				74.68 408	90.84 397	64.34 426		81.61 431	65.34 421	67.47 419	88.01 410	48.60 420	80.13 430	62.33 418	73.68 407	79.58 420

E-PMN		53.28 397	52.56 401	55.43 414	74.43 432	47.13 437	83.63 424	76.30 432	42.23 429	42.59 431	62.22 430	28.57 431	74.40 431	31.53 432	31.51 430	44.78 429

test2506		91.60 238	90.78 246	94.04 243	97.66 137	83.81 340	98.27 32	75.53 433	93.43 105	95.23 136	98.21 78	67.21 380	99.07 168	93.01 163	98.49 118	99.25 72

EMVS		52.08 399	51.31 402	54.39 415	72.62 434	45.39 439	83.84 423	75.51 434	41.13 430	40.77 432	59.65 431	30.08 429	73.60 432	28.31 434	29.90 432	44.18 430

test_vis3_rt		72.73 384	70.55 387	79.27 398	80.02 427	68.13 421	93.92 361	74.30 435	76.90 409	58.99 426	73.58 426	20.29 435	95.37 393	84.16 325	72.80 409	74.31 423

MVE	50.73 23	53.25 398	48.81 403	66.58 413	65.34 437	57.50 432	72.49 427	70.94 436	40.15 431	39.28 433	63.51 429	6.89 440	73.48 433	38.29 429	42.38 429	68.76 427
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		51.94 400	53.82 400	46.29 416	33.73 440	45.30 440	78.32 426	67.24 437	18.02 433	50.93 429	87.05 414	52.99 415	53.11 435	70.76 409	25.29 433	40.46 431

kuosan		65.27 394	64.66 396	67.11 412	83.80 421	61.32 430	88.53 416	60.77 438	68.22 419	67.67 417	80.52 421	49.12 419	70.76 434	29.67 433	53.64 428	69.26 426

dongtai		69.99 388	69.33 390	71.98 409	88.78 410	61.64 429	89.86 410	59.93 439	75.67 411	74.96 410	85.45 415	50.19 418	81.66 428	43.86 427	55.27 426	72.63 424

N_pmnet		78.73 381	78.71 382	78.79 399	92.80 378	46.50 438	94.14 353	43.71 440	78.61 404	80.83 391	91.66 383	74.94 322	96.36 375	67.24 414	84.45 360	93.50 373

wuyk23d		25.11 401	24.57 405	26.74 417	73.98 433	39.89 441	57.88 430	9.80 441	12.27 434	10.39 435	6.97 437	7.03 439	36.44 436	25.43 435	17.39 434	3.89 434

testmvs		13.36 403	16.33 406	4.48 419	5.04 441	2.26 444	93.18 378	3.28 442	2.70 435	8.24 436	21.66 433	2.29 442	2.19 437	7.58 436	2.96 435	9.00 433

test123		13.04 404	15.66 407	5.18 418	4.51 442	3.45 443	92.50 392	1.81 443	2.50 436	7.58 437	20.15 434	3.67 441	2.18 438	7.13 437	1.07 436	9.90 432

mmdepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

monomultidepth		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

test_blank		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet_test		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

DCPMVS		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

pcd_1.5k_mvsjas		7.39 406	9.85 409	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	88.65 103	0.00 439	0.00 438	0.00 437	0.00 435

sosnet-low-res		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

sosnet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uncertanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

Regformer		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

n2								0.00 444

nn								0.00 444

ab-mvs-re		8.06 405	10.74 408	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	96.69 180	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

uanet		0.00 407	0.00 410	0.00 420	0.00 443	0.00 445	0.00 431	0.00 444	0.00 438	0.00 439	0.00 438	0.00 443	0.00 439	0.00 438	0.00 437	0.00 435

WAC-MVS						79.53 391								75.56 390

PC_three_1452									90.77 197	98.89 21	98.28 76	96.24 1	98.35 241	95.76 92	99.58 23	99.59 25

eth-test2					0.00 443

eth-test					0.00 443

OPU-MVS				98.55 3	98.82 55	96.86 3	98.25 35				98.26 77	96.04 2	99.24 136	95.36 106	99.59 19	99.56 32

test_0728_THIRD									94.78 51	98.73 25	98.87 25	95.87 4	99.84 23	97.45 40	99.72 2	99.77 2

GSMVS																98.45 153

test_part2					99.28 25	95.74 8				98.10 38

sam_mvs1												82.76 207				98.45 153

sam_mvs												81.94 226

test_post1							92.81 388				16.58 436	80.53 247	97.68 322	86.20 296

test_post											17.58 435	81.76 228	98.08 268

patchmatchnet-post											90.45 391	82.65 211	98.10 263

gm-plane-assit					93.22 369	78.89 399			84.82 357		93.52 346		98.64 214	87.72 264

test9_res														94.81 121	99.38 59	99.45 51

agg_prior2														93.94 139	99.38 59	99.50 44

test_prior4						93.66 58	96.42 241

test_prior2							96.35 250		92.80 136	96.03 112	97.59 131	92.01 47		95.01 114	99.38 59

旧先验2							95.94 275		81.66 388	97.34 60			98.82 191	92.26 168

新几何2							95.79 284

原ACMM2							95.67 289

testdata2													99.67 67	85.96 304

segment_acmp												92.89 30

testdata1							95.26 315		93.10 122

plane_prior7					96.21 236	89.98 190

plane_prior6					96.10 247	90.00 186						81.32 234

plane_prior4											96.64 183

plane_prior3						90.00 186			94.46 67	91.34 230

plane_prior2							97.74 100		94.85 44

plane_prior1					96.14 244

plane_prior						89.99 188	97.24 168		94.06 79						92.16 264

HQP5-MVS						89.33 216

HQP-NCC					95.86 253		96.65 224		93.55 96	90.14 254

ACMP_Plane					95.86 253		96.65 224		93.55 96	90.14 254

BP-MVS														92.13 174

HQP4-MVS										90.14 254			98.50 226			95.78 280

HQP2-MVS												80.95 238

NP-MVS					95.99 251	89.81 196					95.87 225

MDTV_nov1_ep13_2view						70.35 416	93.10 383		83.88 368	93.55 173		82.47 215		86.25 295		98.38 161

ACMMP++_ref															90.30 294

ACMMP++															91.02 283

Test By Simon												88.73 102

High-resolution multi-view benchmark