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.

MM		95.85 6	95.74 11	96.15 9	96.34 110	89.50 10	99.18 9	98.10 8	95.68 1	96.64 34	97.92 80	80.72 76	99.80 32	99.16 2	97.96 61	99.15 28

DeepPCF-MVS	89.82 1	94.61 25	96.17 5	89.91 270	97.09 101	70.21 419	98.99 29	96.69 85	95.57 2	95.08 59	99.23 2	86.40 33	99.87 12	97.84 33	98.66 32	99.65 7

fmvsm_s_conf0.5_n_8		94.52 29	95.04 23	92.96 108	95.15 159	81.14 188	99.09 20	96.66 90	95.53 3	97.84 10	98.71 22	76.33 159	99.81 28	99.24 1	96.85 107	97.92 111

fmvsm_l_conf0.5_n_9		94.91 16	95.60 12	92.84 116	95.20 154	80.55 216	99.45 1	96.36 138	95.17 4	98.48 4	98.55 28	80.53 79	99.78 39	98.87 7	97.79 68	98.19 85

MCST-MVS		96.17 3	96.12 6	96.32 8	99.42 3	89.36 11	98.94 31	97.10 37	95.17 4	92.11 107	98.46 40	87.33 27	99.97 3	97.21 46	99.31 4	99.63 8

fmvsm_l_conf0.5_n_3		94.61 25	94.92 26	93.68 72	94.52 179	82.80 130	99.33 2	96.37 136	95.08 6	97.59 20	98.48 38	77.40 132	99.79 36	98.28 16	97.21 88	98.44 68

fmvsm_s_conf0.5_n_11		94.41 32	95.19 21	92.09 168	95.65 137	80.91 203	99.23 7	94.85 246	94.92 7	97.68 16	98.82 12	79.31 95	99.78 39	98.83 9	97.38 82	95.60 257

fmvsm_s_conf0.5_n_9		94.52 29	95.22 20	92.41 144	95.79 133	78.61 287	98.73 38	96.00 168	94.91 8	97.73 13	98.73 21	79.09 101	99.79 36	99.14 4	96.86 105	98.83 44

MGCNet		95.58 9	95.44 17	96.01 11	97.63 77	89.26 13	99.27 5	96.59 101	94.71 9	97.08 25	97.99 74	78.69 109	99.86 14	99.15 3	97.85 65	98.91 41

CNVR-MVS		96.30 1	96.54 1	95.55 16	99.31 6	87.69 25	99.06 23	97.12 35	94.66 10	96.79 30	98.78 15	86.42 32	99.95 6	97.59 39	99.18 7	99.00 33

EPNet		94.06 43	94.15 44	93.76 63	97.27 98	84.35 92	98.29 63	97.64 14	94.57 11	95.36 51	96.88 137	79.96 90	99.12 121	91.30 127	96.11 124	97.82 122
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
fmvsm_s_conf0.5_n_3		93.95 45	94.53 32	92.20 162	94.41 188	80.04 239	98.90 33	95.96 173	94.53 12	97.63 19	98.58 27	75.95 169	99.79 36	98.25 18	96.60 113	96.77 217

test_fmvsm_n_1920		94.81 22	95.60 12	92.45 139	95.29 150	80.96 200	99.29 4	97.21 26	94.50 13	97.29 23	98.44 41	82.15 68	99.78 39	98.56 12	97.68 71	96.61 224

DELS-MVS		94.98 15	94.49 34	96.44 7	96.42 108	90.59 8	99.21 8	97.02 43	94.40 14	91.46 116	97.08 129	83.32 60	99.69 65	92.83 107	98.70 31	99.04 31
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
NCCC		95.63 7	95.94 9	94.69 33	99.21 7	85.15 76	99.16 11	96.96 50	94.11 15	95.59 50	98.64 25	85.07 38	99.91 7	95.61 63	99.10 9	99.00 33

fmvsm_s_conf0.5_n_2		92.97 63	93.38 61	91.73 195	94.10 200	80.64 211	98.96 30	95.89 182	94.09 16	97.05 26	98.40 45	68.92 277	99.80 32	98.53 13	94.50 149	94.74 284

CANet		94.89 18	94.64 31	95.63 14	97.55 83	88.12 19	99.06 23	96.39 131	94.07 17	95.34 52	97.80 89	76.83 148	99.87 12	97.08 48	97.64 72	98.89 42

fmvsm_s_conf0.5_n_10		94.36 33	94.73 28	93.23 94	95.19 155	82.87 128	99.18 9	96.39 131	93.97 18	97.91 8	98.53 32	75.88 172	99.82 24	98.58 11	96.95 100	97.00 201

test_vis1_n_1920		89.95 159	90.59 125	88.03 320	92.36 268	68.98 428	99.12 16	94.34 292	93.86 19	93.64 81	97.01 133	51.54 412	99.59 77	96.76 52	96.71 112	95.53 261

fmvsm_s_conf0.1_n_2		92.26 96	92.48 82	91.60 203	92.29 278	80.55 216	98.73 38	94.33 295	93.80 20	96.18 41	98.11 65	66.93 296	99.75 50	98.19 21	93.74 163	94.50 291

DeepC-MVS_fast	89.06 2	94.48 31	94.30 40	95.02 23	98.86 26	85.68 55	98.06 77	96.64 94	93.64 21	91.74 114	98.54 30	80.17 85	99.90 8	92.28 114	98.75 29	99.49 9
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
test_fmvsmconf_n		93.99 44	94.36 38	92.86 113	92.82 252	81.12 189	99.26 6	96.37 136	93.47 22	95.16 55	98.21 56	79.00 102	99.64 71	98.21 20	96.73 111	97.83 120

DPM-MVS		96.21 2	95.53 15	98.26 1	96.26 113	95.09 1	99.15 12	96.98 46	93.39 23	96.45 38	98.79 14	90.17 10	99.99 1	89.33 171	99.25 6	99.70 4

test_fmvsmconf0.1_n		93.08 61	93.22 64	92.65 126	88.45 382	80.81 206	99.00 28	95.11 231	93.21 24	94.00 76	97.91 82	76.84 146	99.59 77	97.91 29	96.55 115	97.54 149

CANet_DTU		90.98 131	90.04 146	93.83 60	94.76 172	86.23 42	96.32 228	93.12 383	93.11 25	93.71 79	96.82 141	63.08 327	99.48 90	84.29 227	95.12 140	95.77 252

test_cas_vis1_n_1920		89.90 160	90.02 147	89.54 280	90.14 350	74.63 372	98.71 40	94.43 284	93.04 26	92.40 99	96.35 153	53.41 408	99.08 124	95.59 64	96.16 121	94.90 278

fmvsm_s_conf0.5_n_4		93.59 50	94.32 39	91.41 212	93.89 206	79.24 261	98.89 34	96.53 112	92.82 27	97.37 22	98.47 39	77.21 140	99.78 39	98.11 25	95.59 136	95.21 272

test_fmvsmvis_n_1920		92.12 98	92.10 95	92.17 164	90.87 330	81.04 192	98.34 61	93.90 328	92.71 28	87.24 192	97.90 83	74.83 197	99.72 58	96.96 49	96.20 120	95.76 253

patch_mono-2		95.14 14	96.08 7	92.33 150	98.44 48	77.84 316	98.43 52	97.21 26	92.58 29	97.68 16	97.65 98	86.88 29	99.83 22	98.25 18	97.60 73	99.33 19

HPM-MVS++		95.32 12	95.48 16	94.85 27	98.62 39	86.04 44	97.81 94	96.93 53	92.45 30	95.69 48	98.50 35	85.38 36	99.85 16	94.75 76	99.18 7	98.65 57

PS-MVSNAJ		94.17 39	93.52 56	96.10 10	95.65 137	92.35 2	98.21 66	95.79 189	92.42 31	96.24 40	98.18 58	71.04 254	99.17 116	96.77 51	97.39 81	96.79 215

NormalMVS		92.88 67	92.97 69	92.59 132	97.80 70	82.02 153	97.94 84	94.70 254	92.34 32	92.15 105	96.53 150	77.03 141	98.57 148	91.13 131	97.12 93	97.19 187

SymmetryMVS		92.45 89	92.33 86	92.82 117	95.19 155	82.02 153	97.94 84	97.43 17	92.34 32	92.15 105	96.53 150	77.03 141	98.57 148	91.13 131	91.19 200	97.87 115

fmvsm_s_conf0.5_n_7		92.88 67	93.82 47	90.08 261	92.79 255	76.45 347	98.54 48	96.74 77	92.28 34	95.22 54	98.49 36	74.91 196	98.15 176	98.28 16	97.13 92	95.63 255

fmvsm_s_conf0.5_n_6		94.17 39	94.70 29	92.58 133	93.50 222	81.20 186	99.08 21	96.48 120	92.24 35	98.62 3	98.39 46	78.58 111	99.72 58	98.08 26	97.36 83	96.81 214

MSP-MVS		95.62 8	96.54 1	92.86 113	98.31 53	80.10 237	97.42 130	96.78 66	92.20 36	97.11 24	98.29 53	93.46 1	99.10 122	96.01 56	99.30 5	99.38 15
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
fmvsm_s_conf0.5_n		93.69 48	94.13 45	92.34 148	94.56 176	82.01 155	99.07 22	97.13 33	92.09 37	96.25 39	98.53 32	76.47 154	99.80 32	98.39 14	94.71 145	95.22 271

test_fmvsmconf0.01_n		91.08 128	90.68 124	92.29 153	82.43 446	80.12 236	97.94 84	93.93 324	92.07 38	91.97 109	97.60 101	67.56 287	99.53 85	97.09 47	95.56 137	97.21 184

fmvsm_l_conf0.5_n		94.89 18	95.24 19	93.86 59	94.42 187	84.61 88	99.13 15	96.15 156	92.06 39	97.92 6	98.52 34	84.52 44	99.74 53	98.76 10	95.67 134	97.22 181

xiu_mvs_v2_base		93.92 46	93.26 62	95.91 12	95.07 162	92.02 6	98.19 67	95.68 195	92.06 39	96.01 45	98.14 63	70.83 259	98.96 130	96.74 53	96.57 114	96.76 219

IU-MVS					99.03 20	85.34 65		96.86 60	92.05 41	98.74 2				98.15 22	98.97 17	99.42 14

fmvsm_l_conf0.5_n_a		94.91 16	95.30 18	93.72 68	94.50 184	84.30 95	99.14 14	96.00 168	91.94 42	97.91 8	98.60 26	84.78 41	99.77 43	98.84 8	96.03 127	97.08 198

fmvsm_s_conf0.5_n_a		93.34 56	93.71 50	92.22 159	93.38 225	81.71 174	98.86 35	96.98 46	91.64 43	96.85 29	98.55 28	75.58 178	99.77 43	97.88 32	93.68 164	95.18 273

TSAR-MVS + GP.		94.35 34	94.50 33	93.89 58	97.38 95	83.04 124	98.10 73	95.29 225	91.57 44	93.81 78	97.45 107	86.64 30	99.43 93	96.28 54	94.01 155	99.20 26

reproduce_monomvs		87.80 224	87.60 206	88.40 302	96.56 105	80.26 229	95.80 274	96.32 142	91.56 45	73.60 370	88.36 348	88.53 18	96.25 311	90.47 147	67.23 416	88.67 384

CLD-MVS		87.97 220	87.48 210	89.44 281	92.16 288	80.54 220	98.14 68	94.92 240	91.41 46	79.43 306	95.40 183	62.34 330	97.27 252	90.60 145	82.90 303	90.50 330
Zhaoxin Li, Wangmeng Zuo, Zhaoqi Wang, Lei Zhang: Confidence-based Large-scale Dense Multi-view Stereo. IEEE Transaction on Image Processing, 2020
save fliter					98.24 56	83.34 117	98.61 46	96.57 104	91.32 47

TSAR-MVS + MP.		94.79 23	95.17 22	93.64 74	97.66 76	84.10 98	95.85 271	96.42 126	91.26 48	97.49 21	96.80 142	86.50 31	98.49 155	95.54 65	99.03 13	98.33 73
Zhenlong Yuan, Jiakai Cao, Zhaoqi Wang, Zhaoxin Li: TSAR-MVS: Textureless-aware Segmentation and Correlative Refinement Guided Multi-View Stereo. Pattern Recognition
fmvsm_s_conf0.1_n		92.93 65	93.16 65	92.24 156	90.52 338	81.92 161	98.42 54	96.24 148	91.17 49	96.02 44	98.35 51	75.34 189	99.74 53	97.84 33	94.58 147	95.05 276

BridgeMVS		94.60 27	94.30 40	95.48 17	96.45 107	88.82 15	96.33 227	95.58 200	91.12 50	95.84 47	93.87 255	83.47 59	98.37 165	97.26 44	98.81 24	99.24 24

PC_three_1452									91.12 50	98.33 5	98.42 44	92.51 2	99.81 28	98.96 6	99.37 1	99.70 4

PAPM		92.87 69	92.40 83	94.30 42	92.25 282	87.85 22	96.40 220	96.38 133	91.07 52	88.72 165	96.90 135	82.11 69	97.37 246	90.05 158	97.70 70	97.67 135

lupinMVS		93.87 47	93.58 54	94.75 31	93.00 239	88.08 20	99.15 12	95.50 207	91.03 53	94.90 62	97.66 94	78.84 105	97.56 212	94.64 79	97.46 76	98.62 59

PVSNet_Blended		93.13 58	92.98 68	93.57 79	97.47 84	83.86 101	99.32 3	96.73 79	91.02 54	89.53 148	96.21 155	76.42 156	99.57 81	94.29 82	95.81 133	97.29 179

fmvsm_s_conf0.5_n_5		93.57 52	93.75 48	93.01 105	92.87 251	82.73 131	98.93 32	95.90 181	90.96 55	95.61 49	98.39 46	76.57 152	99.63 73	98.32 15	96.24 119	96.68 223

DeepC-MVS	86.58 3	91.53 115	91.06 117	92.94 110	94.52 179	81.89 164	95.95 254	95.98 171	90.76 56	83.76 252	96.76 143	73.24 221	99.71 61	91.67 125	96.96 99	97.22 181
Andreas Kuhn, Christian Sormann, Mattia Rossi, Oliver Erdler, Friedrich Fraundorfer: DeepC-MVS: Deep Confidence Prediction for Multi-View Stereo Reconstruction. 3DV 2020
MSLP-MVS++		94.28 35	94.39 37	93.97 56	98.30 54	84.06 99	98.64 44	96.93 53	90.71 57	93.08 89	98.70 23	79.98 89	99.21 108	94.12 85	99.07 11	98.63 58

fmvsm_s_conf0.1_n_a		92.38 92	92.49 81	92.06 172	88.08 387	81.62 179	97.97 83	96.01 167	90.62 58	96.58 35	98.33 52	74.09 209	99.71 61	97.23 45	93.46 169	94.86 280

jason		92.73 73	92.23 90	94.21 47	90.50 339	87.30 31	98.65 43	95.09 232	90.61 59	92.76 95	97.13 125	75.28 190	97.30 249	93.32 97	96.75 110	98.02 98
jason: jason.
HQP-NCC					92.08 293		97.63 107		90.52 60	82.30 271

ACMP_Plane					92.08 293		97.63 107		90.52 60	82.30 271

HQP-MVS		87.91 222	87.55 208	88.98 290	92.08 293	78.48 289	97.63 107	94.80 249	90.52 60	82.30 271	94.56 228	65.40 308	97.32 247	87.67 200	83.01 300	91.13 322

h-mvs33		89.30 179	88.95 172	90.36 253	95.07 162	76.04 354	96.96 173	97.11 36	90.39 63	92.22 103	95.10 203	74.70 199	98.86 137	93.14 102	65.89 427	96.16 237

hse-mvs2		88.22 212	88.21 190	88.25 310	93.54 216	73.41 381	95.41 293	95.89 182	90.39 63	92.22 103	94.22 240	74.70 199	96.66 297	93.14 102	64.37 432	94.69 289

SPE-MVS-test		92.98 62	93.67 51	90.90 234	96.52 106	76.87 339	98.68 41	94.73 253	90.36 65	94.84 64	97.89 84	77.94 121	97.15 263	94.28 84	97.80 67	98.70 55

plane_prior						77.96 310	97.52 121		90.36 65						82.96 302

plane_prior3						77.75 323			90.17 67	81.33 284

MG-MVS		94.25 37	93.72 49	95.85 13	99.38 4	89.35 12	97.98 81	98.09 9	89.99 68	92.34 101	96.97 134	81.30 74	98.99 128	88.54 186	98.88 20	99.20 26

AstraMVS		88.99 186	88.35 187	90.92 232	90.81 334	78.29 296	96.73 192	94.24 301	89.96 69	86.13 214	95.04 205	62.12 336	97.41 237	92.54 112	87.57 262	97.06 200

HQP_MVS		87.50 236	87.09 220	88.74 295	91.86 305	77.96 310	97.18 146	94.69 258	89.89 70	81.33 284	94.15 245	64.77 315	97.30 249	87.08 204	82.82 304	90.96 324

plane_prior2							97.18 146		89.89 70

ETV-MVS		92.72 75	92.87 71	92.28 154	94.54 178	81.89 164	97.98 81	95.21 229	89.77 72	93.11 88	96.83 139	77.23 138	97.50 225	95.74 61	95.38 138	97.44 166

guyue		89.85 162	89.33 162	91.40 213	92.53 266	80.15 235	96.82 184	95.68 195	89.66 73	86.43 209	94.23 239	67.00 294	97.16 259	91.96 122	89.65 218	96.89 209

SD-MVS		94.84 20	95.02 25	94.29 43	97.87 69	84.61 88	97.76 99	96.19 154	89.59 74	96.66 33	98.17 61	84.33 46	99.60 76	96.09 55	98.50 41	98.66 56
Zhenlong Yuan, Jiakai Cao, Zhaoxin Li, Hao Jiang and Zhaoqi Wang: SD-MVS: Segmentation-driven Deformation Multi-View Stereo with Spherical Refinement and EM optimization. AAAI2024
BP-MVS1		93.55 53	93.50 57	93.71 69	92.64 261	85.39 64	97.78 96	96.84 61	89.52 75	92.00 108	97.06 131	88.21 22	98.03 180	91.45 126	96.00 129	97.70 133

SteuartSystems-ACMMP		94.13 42	94.44 36	93.20 96	95.41 145	81.35 184	99.02 27	96.59 101	89.50 76	94.18 74	98.36 50	83.68 58	99.45 92	94.77 75	98.45 44	98.81 46
Skip Steuart: Steuart Systems R&D Blog.
CS-MVS		92.73 73	93.48 58	90.48 247	96.27 112	75.93 360	98.55 47	94.93 239	89.32 77	94.54 70	97.67 93	78.91 104	97.02 268	93.80 88	97.32 85	98.49 64

ET-MVSNet_ETH3D		90.01 157	89.03 166	92.95 109	94.38 189	86.77 35	98.14 68	96.31 143	89.30 78	63.33 443	96.72 146	90.09 11	93.63 418	90.70 144	82.29 311	98.46 66

EIA-MVS		91.73 108	92.05 96	90.78 239	94.52 179	76.40 349	98.06 77	95.34 221	89.19 79	88.90 160	97.28 119	77.56 129	97.73 199	90.77 141	96.86 105	98.20 84

MVS_111021_HR		93.41 55	93.39 60	93.47 87	97.34 96	82.83 129	97.56 115	98.27 6	89.16 80	89.71 143	97.14 124	79.77 91	99.56 83	93.65 91	97.94 62	98.02 98

CHOSEN 1792x2688		91.07 129	90.21 139	93.64 74	95.18 157	83.53 113	96.26 232	96.13 157	88.92 81	84.90 229	93.10 271	72.86 224	99.62 75	88.86 176	95.67 134	97.79 124

DVP-MVS		95.58 9	95.91 10	94.57 36	99.05 14	85.18 71	99.06 23	96.46 121	88.75 82	96.69 31	98.76 18	87.69 25	99.76 45	97.90 30	98.85 21	98.77 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
test0726					99.05 14	85.18 71	99.11 19	96.78 66	88.75 82	97.65 18	98.91 3	87.69 25

SED-MVS		95.88 5	96.22 4	94.87 26	99.03 20	85.03 80	99.12 16	96.78 66	88.72 84	97.79 11	98.91 3	88.48 19	99.82 24	98.15 22	98.97 17	99.74 1

test_241102_TWO								96.78 66	88.72 84	97.70 14	98.91 3	87.86 24	99.82 24	98.15 22	99.00 15	99.47 10

test_241102_ONE					99.03 20	85.03 80		96.78 66	88.72 84	97.79 11	98.90 6	88.48 19	99.82 24

WTY-MVS		92.65 83	91.68 102	95.56 15	96.00 121	88.90 14	98.23 65	97.65 13	88.57 87	89.82 142	97.22 122	79.29 96	99.06 125	89.57 166	88.73 235	98.73 53

EPNet_dtu		87.65 232	87.89 196	86.93 348	94.57 175	71.37 411	96.72 193	96.50 116	88.56 88	87.12 196	95.02 207	75.91 171	94.01 410	66.62 397	90.00 214	95.42 264
Wanjuan Su, Wenbing Tao: Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation. AAAI 2023
sasdasda		92.27 94	91.22 111	95.41 18	95.80 131	88.31 16	97.09 160	94.64 265	88.49 89	92.99 91	97.31 114	72.68 227	98.57 148	93.38 95	88.58 241	99.36 17

canonicalmvs		92.27 94	91.22 111	95.41 18	95.80 131	88.31 16	97.09 160	94.64 265	88.49 89	92.99 91	97.31 114	72.68 227	98.57 148	93.38 95	88.58 241	99.36 17

MVS_111021_LR		91.60 114	91.64 104	91.47 210	95.74 134	78.79 282	96.15 244	96.77 72	88.49 89	88.64 166	97.07 130	72.33 233	99.19 114	93.13 104	96.48 117	96.43 229

DVP-MVS++		96.05 4	96.41 3	94.96 25	99.05 14	85.34 65	98.13 71	96.77 72	88.38 92	97.70 14	98.77 16	92.06 3	99.84 18	97.47 40	99.37 1	99.70 4

test_0728_THIRD									88.38 92	96.69 31	98.76 18	89.64 14	99.76 45	97.47 40	98.84 23	99.38 15

GDP-MVS		92.85 70	92.55 80	93.75 64	92.82 252	85.76 51	97.63 107	95.05 235	88.34 94	93.15 87	97.10 128	86.92 28	98.01 183	87.95 194	94.00 156	97.47 160

HY-MVS	84.06 6	91.63 112	90.37 134	95.39 20	96.12 118	88.25 18	90.22 410	97.58 15	88.33 95	90.50 133	91.96 292	79.26 97	99.06 125	90.29 155	89.07 229	98.88 43

PVSNet_Blended_VisFu		91.24 123	90.77 122	92.66 125	95.09 160	82.40 143	97.77 97	95.87 186	88.26 96	86.39 210	93.94 253	76.77 149	99.27 102	88.80 182	94.00 156	96.31 235

MGCFI-Net		91.95 102	91.03 118	94.72 32	95.68 136	86.38 38	96.93 176	94.48 275	88.25 97	92.78 94	97.24 120	72.34 232	98.46 158	93.13 104	88.43 249	99.32 20

mvsmamba		90.53 147	90.08 143	91.88 182	94.81 170	80.93 201	93.94 348	94.45 281	88.24 98	87.02 198	92.35 282	68.04 280	95.80 331	94.86 74	97.03 97	98.92 40

EI-MVSNet-Vis-set		91.84 107	91.77 101	92.04 174	97.60 79	81.17 187	96.61 200	96.87 58	88.20 99	89.19 153	97.55 106	78.69 109	99.14 118	90.29 155	90.94 205	95.80 247

UGNet		87.73 227	86.55 234	91.27 218	95.16 158	79.11 267	96.35 225	96.23 149	88.14 100	87.83 184	90.48 314	50.65 417	99.09 123	80.13 276	94.03 153	95.60 257
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
myMVS_eth3d28		92.72 75	92.23 90	94.21 47	96.16 116	87.46 30	97.37 134	96.99 45	88.13 101	88.18 176	95.47 181	84.12 51	98.04 179	92.46 113	91.17 202	97.14 190

test_one_0601					98.91 23	84.56 90		96.70 83	88.06 102	96.57 36	98.77 16	88.04 23

alignmvs		92.97 63	92.26 89	95.12 22	95.54 142	87.77 23	98.67 42	96.38 133	88.04 103	93.01 90	97.45 107	79.20 99	98.60 146	93.25 99	88.76 234	98.99 35

PVSNet_BlendedMVS		90.05 156	89.96 149	90.33 254	97.47 84	83.86 101	98.02 80	96.73 79	87.98 104	89.53 148	89.61 329	76.42 156	99.57 81	94.29 82	79.59 324	87.57 409

test_fmvs1		87.79 225	88.52 184	85.62 371	92.98 243	64.31 449	97.88 89	92.42 394	87.95 105	92.24 102	95.82 163	47.94 430	98.44 162	95.31 70	94.09 152	94.09 298

UBG		92.68 82	92.35 84	93.70 70	95.61 139	85.65 58	97.25 140	97.06 40	87.92 106	89.28 152	95.03 206	86.06 35	98.07 177	92.24 115	90.69 209	97.37 172

MTAPA		92.45 89	92.31 87	92.86 113	97.90 66	80.85 205	92.88 377	96.33 140	87.92 106	90.20 138	98.18 58	76.71 151	99.76 45	92.57 111	98.09 56	97.96 110

EI-MVSNet-UG-set		91.35 121	91.22 111	91.73 195	97.39 93	80.68 209	96.47 212	96.83 62	87.92 106	88.30 173	97.36 113	77.84 124	99.13 120	89.43 170	89.45 220	95.37 265

OPM-MVS		85.84 263	85.10 261	88.06 318	88.34 384	77.83 317	95.72 276	94.20 309	87.89 109	80.45 294	94.05 247	58.57 361	97.26 253	83.88 231	82.76 306	89.09 364
Ray L. Khuboni, Hongjun Xu: Octagram Propagation Matching for Multi-Scale View Stereopsis (OPM-MVS).
diffmvs		91.17 125	90.74 123	92.44 141	93.11 237	82.50 140	96.25 233	93.62 359	87.79 110	90.40 136	95.93 160	73.44 219	97.42 235	93.62 92	92.55 179	97.41 168
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
PVSNet	82.34 9	89.02 185	87.79 199	92.71 123	95.49 143	81.50 181	97.70 103	97.29 20	87.76 111	85.47 222	95.12 202	56.90 385	98.90 136	80.33 271	94.02 154	97.71 132

PAPR		92.74 72	92.17 93	94.45 38	98.89 25	84.87 85	97.20 144	96.20 152	87.73 112	88.40 170	98.12 64	78.71 108	99.76 45	87.99 193	96.28 118	98.74 49

casdiffmvs		90.95 133	90.39 132	92.63 129	92.82 252	82.53 135	96.83 182	94.47 278	87.69 113	88.47 168	95.56 178	74.04 210	97.54 219	90.90 136	92.74 177	97.83 120
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
casdiffmvs_mvg		91.13 126	90.45 130	93.17 98	92.99 242	83.58 112	97.46 125	94.56 271	87.69 113	87.19 194	94.98 211	74.50 204	97.60 206	91.88 124	92.79 176	98.34 72
Fangjinhua Wang, Qingshan Xu, Yew-Soon Ong, Marc Pollefeys: Lightweight and Accurate Multi-View Stereo With Confidence-Aware Diffusion Model. IEEE T-PAMI 2025
baseline		90.76 138	90.10 142	92.74 121	92.90 250	82.56 134	94.60 327	94.56 271	87.69 113	89.06 157	95.67 170	73.76 214	97.51 224	90.43 150	92.23 189	98.16 88

MED-MVS		95.58 9	96.03 8	94.21 47	99.06 11	83.70 107	98.35 57	97.14 31	87.65 116	97.03 27	98.83 10	89.87 13	99.96 4	97.78 35	98.60 34	98.97 36

TestfortrainingZip a		94.24 38	94.19 43	94.40 40	99.06 11	84.33 93	98.35 57	96.81 65	87.65 116	95.97 46	98.83 10	84.06 52	99.89 10	91.98 121	95.03 141	98.97 36

balanced_ft_v1		92.00 101	91.12 116	94.64 34	96.35 109	86.78 34	94.96 317	94.70 254	87.65 116	90.20 138	93.01 273	69.71 268	98.02 181	97.40 42	96.13 123	99.11 29

Vis-MVSNet		88.67 197	87.82 198	91.24 220	92.68 256	78.82 275	96.95 174	93.85 332	87.55 119	87.07 197	95.13 201	63.43 324	97.21 256	77.58 308	96.15 122	97.70 133
Jingyang Zhang, Yao Yao, Shiwei Li, Zixin Luo, Tian Fang: Visibility-aware Multiview Stereo Network. BMVC 2020
testing11		92.48 88	92.04 97	93.78 62	95.94 125	86.00 45	97.56 115	97.08 38	87.52 120	89.32 151	95.40 183	84.60 42	98.02 181	91.93 123	89.04 230	97.32 175

test_fmvs1_n		86.34 255	86.72 230	85.17 379	87.54 394	63.64 454	96.91 178	92.37 396	87.49 121	91.33 120	95.58 177	40.81 459	98.46 158	95.00 73	93.49 167	93.41 312

MED-MVS test				94.20 50	99.06 11	83.70 107	98.35 57	97.14 31	87.45 122	97.03 27	98.90 6		99.96 4	97.78 35	98.60 34	98.94 38

testdata1							95.57 287		87.44 123

EC-MVSNet		91.73 108	92.11 94	90.58 243	93.54 216	77.77 320	98.07 76	94.40 287	87.44 123	92.99 91	97.11 127	74.59 203	96.87 285	93.75 89	97.08 95	97.11 191

UA-Net		88.92 189	88.48 185	90.24 257	94.06 202	77.18 335	93.04 373	94.66 262	87.39 125	91.09 124	93.89 254	74.92 195	98.18 174	75.83 330	91.43 198	95.35 266

test_vis1_n		85.60 271	85.70 245	85.33 376	84.79 427	64.98 447	96.83 182	91.61 412	87.36 126	91.00 127	94.84 220	36.14 466	97.18 258	95.66 62	93.03 174	93.82 303

baseline1		88.85 192	87.49 209	92.93 111	95.21 153	86.85 33	95.47 290	94.61 268	87.29 127	83.11 264	94.99 210	80.70 77	96.89 282	82.28 255	73.72 361	95.05 276

diffmvs_AUTHOR		90.86 137	90.41 131	92.24 156	92.01 299	82.22 149	96.18 241	93.64 357	87.28 128	90.46 135	95.64 172	72.82 225	97.39 241	93.17 101	92.46 182	97.11 191

MonoMVSNet		85.68 267	84.22 275	90.03 263	88.43 383	77.83 317	92.95 376	91.46 413	87.28 128	78.11 318	85.96 392	66.31 303	94.81 390	90.71 143	76.81 344	97.46 161

PMMVS		89.46 172	89.92 151	88.06 318	94.64 173	69.57 425	96.22 237	94.95 238	87.27 130	91.37 119	96.54 149	65.88 304	97.39 241	88.54 186	93.89 160	97.23 180

xiu_mvs_v1_base_debu		90.54 144	89.54 157	93.55 80	92.31 270	87.58 27	96.99 166	94.87 243	87.23 131	93.27 83	97.56 103	57.43 379	98.32 167	92.72 108	93.46 169	94.74 284

xiu_mvs_v1_base		90.54 144	89.54 157	93.55 80	92.31 270	87.58 27	96.99 166	94.87 243	87.23 131	93.27 83	97.56 103	57.43 379	98.32 167	92.72 108	93.46 169	94.74 284

xiu_mvs_v1_base_debi		90.54 144	89.54 157	93.55 80	92.31 270	87.58 27	96.99 166	94.87 243	87.23 131	93.27 83	97.56 103	57.43 379	98.32 167	92.72 108	93.46 169	94.74 284

MVSTER		89.25 181	88.92 173	90.24 257	95.98 123	84.66 87	96.79 187	95.36 218	87.19 134	80.33 296	90.61 313	90.02 12	95.97 320	85.38 220	78.64 333	90.09 340

IB-MVS	85.34 4	88.67 197	87.14 219	93.26 92	93.12 236	84.32 94	98.76 37	97.27 22	87.19 134	79.36 307	90.45 315	83.92 56	98.53 153	84.41 226	69.79 390	96.93 206
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
VortexMVS		85.45 275	84.40 271	88.63 297	93.25 228	81.66 176	95.39 295	94.34 292	87.15 136	75.10 362	87.65 360	66.58 301	95.19 367	86.89 208	73.21 367	89.03 372

viewmanbaseed2359cas		90.74 139	90.07 144	92.76 119	92.98 243	82.93 127	96.53 207	94.28 298	87.08 137	88.96 158	95.64 172	72.03 242	97.58 210	90.85 138	92.26 187	97.76 126

E3new		90.90 135	90.35 135	92.55 134	93.63 212	82.40 143	96.79 187	94.49 274	87.07 138	88.54 167	95.70 167	73.85 212	97.60 206	91.23 129	91.86 193	97.64 138

XVS		92.69 80	92.71 74	92.63 129	98.52 42	80.29 226	97.37 134	96.44 123	87.04 139	91.38 117	97.83 88	77.24 136	99.59 77	90.46 148	98.07 57	98.02 98

X-MVStestdata		86.26 257	84.14 278	92.63 129	98.52 42	80.29 226	97.37 134	96.44 123	87.04 139	91.38 117	20.73 500	77.24 136	99.59 77	90.46 148	98.07 57	98.02 98

viewcassd2359sk11		90.66 141	90.06 145	92.47 137	93.22 229	82.21 150	96.70 197	94.47 278	86.94 141	88.22 175	95.50 180	73.15 222	97.59 208	90.86 137	91.48 197	97.60 144

dcpmvs_2		93.10 60	93.46 59	92.02 175	97.77 72	79.73 249	94.82 322	93.86 331	86.91 142	91.33 120	96.76 143	85.20 37	98.06 178	96.90 50	97.60 73	98.27 80

testing3-2		91.37 119	91.01 119	92.44 141	95.93 126	83.77 104	98.83 36	97.45 16	86.88 143	86.63 206	94.69 226	84.57 43	97.75 198	89.65 164	84.44 289	95.80 247

test1111		88.11 214	87.04 221	91.35 214	93.15 233	78.79 282	96.57 204	90.78 428	86.88 143	85.04 226	95.20 195	57.23 384	97.39 241	83.88 231	94.59 146	97.87 115

testing99		91.91 104	91.35 108	93.60 77	95.98 123	85.70 53	97.31 138	96.92 55	86.82 145	88.91 159	95.25 188	84.26 50	97.89 193	88.80 182	87.94 255	97.21 184

OMC-MVS		88.80 194	88.16 192	90.72 240	95.30 149	77.92 313	94.81 323	94.51 273	86.80 146	84.97 228	96.85 138	67.53 288	98.60 146	85.08 221	87.62 259	95.63 255

test2506		90.96 132	90.39 132	92.65 126	93.54 216	82.46 141	96.37 221	97.35 19	86.78 147	87.55 185	95.25 188	77.83 125	97.50 225	84.07 229	94.80 143	97.98 106

ECVR-MVS		88.35 208	87.25 215	91.65 199	93.54 216	79.40 257	96.56 206	90.78 428	86.78 147	85.57 220	95.25 188	57.25 383	97.56 212	84.73 225	94.80 143	97.98 106

testing91		91.90 105	91.31 110	93.66 73	95.99 122	85.68 55	97.39 133	96.89 56	86.75 149	88.85 161	95.23 192	83.93 55	97.90 192	88.91 175	87.89 256	97.41 168

3Dnovator	82.32 10	89.33 178	87.64 202	94.42 39	93.73 211	85.70 53	97.73 101	96.75 76	86.73 150	76.21 347	95.93 160	62.17 331	99.68 67	81.67 259	97.81 66	97.88 113

E2		90.33 151	89.65 155	92.37 146	92.66 257	81.99 156	96.58 202	94.39 288	86.71 151	87.88 181	95.25 188	72.18 236	97.56 212	90.37 153	90.88 206	97.57 146

E3		90.33 151	89.65 155	92.37 146	92.64 261	81.99 156	96.58 202	94.39 288	86.71 151	87.87 182	95.27 187	72.17 237	97.56 212	90.37 153	90.88 206	97.57 146

lecture		93.17 57	93.57 55	91.96 177	97.80 70	78.79 282	98.50 50	96.98 46	86.61 153	94.75 67	98.16 62	78.36 115	99.35 100	93.89 87	97.12 93	97.75 127

KinetiMVS		89.13 182	87.95 195	92.65 126	92.16 288	82.39 145	97.04 164	96.05 164	86.59 154	88.08 179	94.85 219	61.54 343	98.38 164	81.28 265	93.99 158	97.19 187

viewmacassd2359aftdt		89.89 161	89.01 169	92.52 136	91.56 312	82.46 141	96.32 228	94.06 319	86.41 155	88.11 178	95.01 208	69.68 269	97.47 228	88.73 185	91.19 200	97.63 140

VNet		92.11 99	91.22 111	94.79 29	96.91 102	86.98 32	97.91 87	97.96 10	86.38 156	93.65 80	95.74 165	70.16 265	98.95 132	93.39 93	88.87 233	98.43 69

viewdifsd2359ckpt09		90.00 158	89.28 163	92.15 166	93.31 227	81.38 182	96.37 221	93.64 357	86.34 157	86.62 207	95.64 172	71.58 248	97.52 222	88.93 174	91.06 203	97.54 149

E4		89.85 162	89.06 165	92.22 159	91.88 304	81.63 178	96.43 217	94.27 299	86.32 158	87.29 190	94.97 212	70.81 260	97.52 222	89.57 166	90.00 214	97.51 156

ACMMP_NAP		93.46 54	93.23 63	94.17 51	97.16 99	84.28 96	96.82 184	96.65 91	86.24 159	94.27 72	97.99 74	77.94 121	99.83 22	93.39 93	98.57 37	98.39 71

viewdifsd2359ckpt13		90.08 155	89.36 160	92.26 155	93.03 238	81.90 163	96.37 221	94.34 292	86.16 160	87.44 186	95.30 186	70.93 258	97.55 216	89.05 173	91.59 196	97.35 174

TESTMET0.1,1		89.83 164	89.34 161	91.31 215	92.54 265	80.19 233	97.11 156	96.57 104	86.15 161	86.85 205	91.83 297	79.32 94	96.95 276	81.30 264	92.35 186	96.77 217

DPE-MVS		95.32 12	95.55 14	94.64 34	98.79 28	84.87 85	97.77 97	96.74 77	86.11 162	96.54 37	98.89 9	88.39 21	99.74 53	97.67 38	99.05 12	99.31 21
Kehua Chen, Zhenlong Yuan, Tianlu Mao, Zhaoqi Wang: Dual-Level Precision Edges Guided Multi-View Stereo with Accurate Planarization. AAAI2025
3Dnovator+	82.88 8	89.63 169	87.85 197	94.99 24	94.49 185	86.76 36	97.84 91	95.74 192	86.10 163	75.47 358	96.02 159	65.00 312	99.51 88	82.91 249	97.07 96	98.72 54

test_prior2							98.37 56		86.08 164	94.57 69	98.02 73	83.14 61		95.05 72	98.79 27

testing222		91.09 127	90.49 129	92.87 112	95.82 129	85.04 79	96.51 210	97.28 21	86.05 165	89.13 154	95.34 185	80.16 86	96.62 298	85.82 215	88.31 251	96.96 204

RRT-MVS		89.67 167	88.67 176	92.67 124	94.44 186	81.08 191	94.34 334	94.45 281	86.05 165	85.79 217	92.39 281	63.39 325	98.16 175	93.22 100	93.95 159	98.76 48

E5new		89.38 173	88.55 180	91.85 185	91.77 308	80.97 195	95.90 262	94.22 304	86.03 167	86.88 200	94.90 215	69.05 273	97.47 228	88.86 176	89.35 221	97.10 193

E6new		89.37 175	88.55 180	91.85 185	91.75 310	80.97 195	95.90 262	94.22 304	86.03 167	86.88 200	94.91 213	69.05 273	97.47 228	88.86 176	89.34 223	97.10 193

E6		89.37 175	88.55 180	91.85 185	91.75 310	80.97 195	95.90 262	94.22 304	86.03 167	86.88 200	94.91 213	69.05 273	97.47 228	88.86 176	89.34 223	97.10 193

E5		89.38 173	88.55 180	91.85 185	91.77 308	80.97 195	95.90 262	94.22 304	86.03 167	86.88 200	94.90 215	69.05 273	97.47 228	88.86 176	89.35 221	97.10 193

baseline2		90.39 148	90.21 139	90.93 231	90.86 331	80.99 194	95.20 304	97.41 18	86.03 167	80.07 301	94.61 227	90.58 7	97.47 228	87.29 203	89.86 217	94.35 292

CHOSEN 280x420		91.71 111	91.85 98	91.29 217	94.94 166	82.69 132	87.89 434	96.17 155	85.94 172	87.27 191	94.31 236	90.27 9	95.65 343	94.04 86	95.86 131	95.53 261

sss		90.87 136	89.96 149	93.60 77	94.15 196	83.84 103	97.14 153	98.13 7	85.93 173	89.68 144	96.09 158	71.67 245	99.30 101	87.69 199	89.16 228	97.66 136

EPMVS		87.47 237	85.90 242	92.18 163	95.41 145	82.26 148	87.00 441	96.28 144	85.88 174	84.23 241	85.57 397	75.07 194	96.26 309	71.14 374	92.50 180	98.03 97

ME-MVS		94.82 21	95.04 23	94.17 51	99.17 9	83.70 107	97.66 106	97.22 25	85.79 175	95.34 52	98.90 6	84.89 39	99.86 14	97.78 35	98.60 34	98.94 38

APDe-MVS		94.56 28	94.75 27	93.96 57	98.84 27	83.40 116	98.04 79	96.41 127	85.79 175	95.00 61	98.28 54	84.32 49	99.18 115	97.35 43	98.77 28	99.28 22
Zhaojie Zeng, Yuesong Wang, Tao Guan: Matching Ambiguity-Resilient Multi-View Stereo via Adaptive Patch Deformation. Pattern Recognition
VPNet		84.69 290	82.92 302	90.01 264	89.01 372	83.45 115	96.71 195	95.46 210	85.71 177	79.65 303	92.18 287	56.66 388	96.01 319	83.05 248	67.84 410	90.56 329

MP-MVS		92.61 84	92.67 76	92.42 143	98.13 61	79.73 249	97.33 137	96.20 152	85.63 178	90.53 132	97.66 94	78.14 119	99.70 64	92.12 117	98.30 53	97.85 118
Rongxuan Tan, Qing Wang, et al.: MP-MVS: Multi-Scale Windows PatchMatch and Planar Prior Multi-View Stereo.
TestfortrainingZip				97.22 3	99.48 2	91.93 7	98.35 57	97.26 24	85.61 179	99.54 1	99.26 1	91.36 5	99.98 2		96.55 115	99.73 3

Effi-MVS+-dtu		84.61 293	84.90 265	83.72 401	91.96 301	63.14 457	94.95 318	93.34 373	85.57 180	79.79 302	87.12 370	61.99 339	95.61 347	83.55 240	85.83 280	92.41 317

GA-MVS		85.79 265	84.04 279	91.02 230	89.47 368	80.27 228	96.90 179	94.84 247	85.57 180	80.88 288	89.08 333	56.56 389	96.47 302	77.72 304	85.35 285	96.34 232

FIs		86.73 249	86.10 239	88.61 298	90.05 351	80.21 231	96.14 245	96.95 51	85.56 182	78.37 315	92.30 283	76.73 150	95.28 361	79.51 281	79.27 327	90.35 332

viewdifsd2359ckpt11		86.38 252	85.29 253	89.66 279	90.42 341	75.65 364	95.27 299	92.45 392	85.54 183	84.27 240	94.73 222	62.16 332	97.39 241	87.78 196	74.97 355	95.96 240

viewmsd2359difaftdt		86.38 252	85.29 253	89.67 278	90.42 341	75.65 364	95.27 299	92.45 392	85.54 183	84.28 239	94.73 222	62.16 332	97.39 241	87.78 196	74.97 355	95.96 240

ETVMVS		90.99 130	90.26 136	93.19 97	95.81 130	85.64 59	96.97 171	97.18 29	85.43 185	88.77 164	94.86 218	82.00 70	96.37 305	82.70 250	88.60 240	97.57 146

DU-MVS		84.57 294	83.33 294	88.28 307	88.76 373	79.36 258	96.43 217	95.41 217	85.42 186	78.11 318	90.82 309	67.61 285	95.14 373	79.14 289	68.30 404	90.33 333

UniMVSNet (Re)		85.31 279	84.23 274	88.55 299	89.75 358	80.55 216	96.72 193	96.89 56	85.42 186	78.40 314	88.93 336	75.38 185	95.52 351	78.58 294	68.02 407	89.57 349

SMA-MVS		94.70 24	94.68 30	94.76 30	98.02 64	85.94 48	97.47 123	96.77 72	85.32 188	97.92 6	98.70 23	83.09 63	99.84 18	95.79 60	99.08 10	98.49 64
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
test-mter		88.95 187	88.60 178	89.98 266	92.26 280	77.23 333	97.11 156	95.96 173	85.32 188	86.30 212	91.38 300	76.37 158	96.78 292	80.82 267	91.92 191	95.94 243

tpmrst		88.36 207	87.38 213	91.31 215	94.36 190	79.92 241	87.32 438	95.26 227	85.32 188	88.34 171	86.13 390	80.60 78	96.70 294	83.78 233	85.34 286	97.30 178

region2R		92.72 75	92.70 75	92.79 118	98.68 31	80.53 221	97.53 118	96.51 114	85.22 191	91.94 111	97.98 77	77.26 134	99.67 69	90.83 140	98.37 49	98.18 86

UniMVSNet_NR-MVSNet		85.49 273	84.59 266	88.21 314	89.44 369	79.36 258	96.71 195	96.41 127	85.22 191	78.11 318	90.98 308	76.97 145	95.14 373	79.14 289	68.30 404	90.12 338

HFP-MVS		92.89 66	92.86 73	92.98 107	98.71 30	81.12 189	97.58 113	96.70 83	85.20 193	91.75 113	97.97 79	78.47 112	99.71 61	90.95 133	98.41 46	98.12 93

ACMMPR		92.69 80	92.67 76	92.75 120	98.66 33	80.57 215	97.58 113	96.69 85	85.20 193	91.57 115	97.92 80	77.01 143	99.67 69	90.95 133	98.41 46	98.00 104

icg_test_0407_2		87.55 234	86.59 233	90.43 248	92.30 273	78.81 277	92.17 386	93.84 333	85.14 195	83.68 253	94.49 231	67.75 283	95.02 384	81.33 260	88.61 236	97.46 161

IMVS_0407		87.82 223	86.72 230	91.14 225	92.30 273	78.81 277	93.34 364	93.84 333	85.14 195	83.68 253	94.49 231	67.75 283	97.14 264	81.33 260	88.61 236	97.46 161

IMVS_0404		85.34 277	83.69 281	90.29 255	92.30 273	78.81 277	90.62 407	93.84 333	85.14 195	72.51 387	94.49 231	54.36 404	94.61 397	81.33 260	88.61 236	97.46 161

IMVS_0403		88.07 215	87.02 222	91.24 220	92.30 273	78.81 277	93.62 356	93.84 333	85.14 195	84.36 238	94.49 231	69.49 270	97.46 234	81.33 260	88.61 236	97.46 161

FC-MVSNet-test		85.96 261	85.39 251	87.66 328	89.38 370	78.02 307	95.65 282	96.87 58	85.12 199	77.34 324	91.94 295	76.28 161	94.74 393	77.09 313	78.82 331	90.21 335

mPP-MVS		91.88 106	91.82 99	92.07 171	98.38 49	78.63 286	97.29 139	96.09 160	85.12 199	88.45 169	97.66 94	75.53 179	99.68 67	89.83 159	98.02 60	97.88 113

dmvs_re		84.10 301	82.90 303	87.70 325	91.41 318	73.28 385	90.59 408	93.19 377	85.02 201	77.96 321	93.68 260	57.92 372	96.18 314	75.50 336	80.87 316	93.63 306

PVSNet_0	77.72 15	81.70 341	78.95 360	89.94 269	90.77 335	76.72 343	95.96 253	96.95 51	85.01 202	70.24 410	88.53 343	52.32 409	98.20 172	86.68 212	44.08 485	94.89 279

ZNCC-MVS		92.75 71	92.60 78	93.23 94	98.24 56	81.82 169	97.63 107	96.50 116	85.00 203	91.05 125	97.74 91	78.38 113	99.80 32	90.48 146	98.34 51	98.07 95

UWE-MVS		88.56 202	88.91 174	87.50 335	94.17 195	72.19 396	95.82 273	97.05 41	84.96 204	84.78 231	93.51 265	81.33 72	94.75 392	79.43 283	89.17 227	95.57 259

SCA		85.63 268	83.64 287	91.60 203	92.30 273	81.86 166	92.88 377	95.56 202	84.85 205	82.52 267	85.12 407	58.04 367	95.39 354	73.89 352	87.58 261	97.54 149

tpm		85.55 272	84.47 270	88.80 294	90.19 347	75.39 367	88.79 424	94.69 258	84.83 206	83.96 248	85.21 403	78.22 117	94.68 396	76.32 326	78.02 341	96.34 232

CP-MVS		92.54 86	92.60 78	92.34 148	98.50 45	79.90 242	98.40 55	96.40 129	84.75 207	90.48 134	98.09 67	77.40 132	99.21 108	91.15 130	98.23 55	97.92 111

9.14			94.26 42		98.10 62		98.14 68	96.52 113	84.74 208	94.83 65	98.80 13	82.80 66	99.37 97	95.95 58	98.42 45

ACMMP		90.39 148	89.97 148	91.64 200	97.58 81	78.21 303	96.78 189	96.72 81	84.73 209	84.72 233	97.23 121	71.22 251	99.63 73	88.37 191	92.41 185	97.08 198
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
GST-MVS		92.43 91	92.22 92	93.04 104	98.17 59	81.64 177	97.40 132	96.38 133	84.71 210	90.90 128	97.40 112	77.55 130	99.76 45	89.75 163	97.74 69	97.72 130

MP-MVS-pluss		92.58 85	92.35 84	93.29 91	97.30 97	82.53 135	96.44 215	96.04 166	84.68 211	89.12 155	98.37 49	77.48 131	99.74 53	93.31 98	98.38 48	97.59 145
MP-MVS-pluss: MP-MVS-pluss. MP-MVS-pluss
NR-MVSNet		83.35 312	81.52 325	88.84 292	88.76 373	81.31 185	94.45 329	95.16 230	84.65 212	67.81 420	90.82 309	70.36 263	94.87 387	74.75 343	66.89 420	90.33 333

PAPM_NR		91.46 116	90.82 121	93.37 90	98.50 45	81.81 170	95.03 316	96.13 157	84.65 212	86.10 215	97.65 98	79.24 98	99.75 50	83.20 245	96.88 103	98.56 61

PatchmatchNet		86.83 246	85.12 260	91.95 178	94.12 199	82.27 147	86.55 445	95.64 198	84.59 214	82.98 266	84.99 409	77.26 134	95.96 323	68.61 387	91.34 199	97.64 138
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Pablo Speciale, Marc Pollefeys: PatchmatchNet: Learned Multi-View Patchmatch Stereo.
casdiffseed414692147		88.22 212	86.93 226	92.08 169	92.04 297	81.84 167	96.08 249	94.08 317	84.56 215	85.59 219	93.98 252	67.37 290	97.42 235	80.12 277	88.52 245	96.99 202

usedtu_dtu_shiyan1		85.03 283	83.24 295	90.37 251	86.62 401	86.24 40	96.23 235	95.30 223	84.55 216	77.22 327	88.47 345	67.85 281	95.27 362	76.59 319	76.35 345	89.61 347

FE-MVSNET3		85.03 283	83.24 295	90.37 251	86.62 401	86.24 40	96.23 235	95.30 223	84.55 216	77.22 327	88.47 345	67.85 281	95.27 362	76.59 319	76.35 345	89.61 347

TranMVSNet+NR-MVSNet		83.24 316	81.71 321	87.83 322	87.71 391	78.81 277	96.13 247	94.82 248	84.52 218	76.18 348	90.78 311	64.07 320	94.60 398	74.60 347	66.59 423	90.09 340

train_agg		94.28 35	94.45 35	93.74 65	98.64 36	83.71 105	97.82 92	96.65 91	84.50 219	95.16 55	98.09 67	84.33 46	99.36 98	95.91 59	98.96 19	98.16 88

test_8					98.63 38	83.64 111	97.81 94	96.63 96	84.50 219	95.10 58	98.11 65	84.33 46	99.23 106

viewdifsd2359ckpt07		89.04 184	88.30 188	91.27 218	92.32 269	78.90 272	95.89 266	93.77 345	84.48 221	85.18 224	95.16 198	69.83 266	97.70 200	88.75 184	89.29 226	97.22 181

gm-plane-assit					92.27 279	79.64 252			84.47 222		95.15 200		97.93 186	85.81 216

Vis-MVSNet (Re-imp)		88.88 191	88.87 175	88.91 291	93.89 206	74.43 375	96.93 176	94.19 310	84.39 223	83.22 262	95.67 170	78.24 116	94.70 394	78.88 292	94.40 151	97.61 143

thres200		88.92 189	87.65 201	92.73 122	96.30 111	85.62 60	97.85 90	98.86 1	84.38 224	84.82 230	93.99 251	75.12 193	98.01 183	70.86 376	86.67 267	94.56 290

nrg030		86.79 247	85.43 250	90.87 236	88.76 373	85.34 65	97.06 163	94.33 295	84.31 225	80.45 294	91.98 291	72.36 231	96.36 306	88.48 189	71.13 377	90.93 326

MVS_Test		90.29 153	89.18 164	93.62 76	95.23 151	84.93 83	94.41 330	94.66 262	84.31 225	90.37 137	91.02 306	75.13 192	97.82 195	83.11 247	94.42 150	98.12 93

SDMVSNet		87.02 241	85.61 247	91.24 220	94.14 197	83.30 118	93.88 350	95.98 171	84.30 227	79.63 304	92.01 288	58.23 364	97.68 202	90.28 157	82.02 312	92.75 313

sd_testset		84.62 292	83.11 298	89.17 285	94.14 197	77.78 319	91.54 398	94.38 290	84.30 227	79.63 304	92.01 288	52.28 410	96.98 274	77.67 306	82.02 312	92.75 313

TEST9					98.64 36	83.71 105	97.82 92	96.65 91	84.29 229	95.16 55	98.09 67	84.39 45	99.36 98

CDS-MVSNet		89.50 171	88.96 171	91.14 225	91.94 303	80.93 201	97.09 160	95.81 188	84.26 230	84.72 233	94.20 242	80.31 81	95.64 344	83.37 244	88.96 232	96.85 213
Khang Truong Giang, Soohwan Song, Sungho Jo: Curvature-guided dynamic scale networks for Multi-view Stereo. ICLR 2022
CR-MVSNet		83.53 310	81.36 327	90.06 262	90.16 348	79.75 246	79.02 473	91.12 420	84.24 231	82.27 275	80.35 447	75.45 181	93.67 417	63.37 417	86.25 272	96.75 220

reproduce-ours		92.70 78	93.02 66	91.75 192	97.45 86	77.77 320	96.16 242	95.94 177	84.12 232	92.45 96	98.43 42	80.06 87	99.24 104	95.35 68	97.18 89	98.24 82

our_new_method		92.70 78	93.02 66	91.75 192	97.45 86	77.77 320	96.16 242	95.94 177	84.12 232	92.45 96	98.43 42	80.06 87	99.24 104	95.35 68	97.18 89	98.24 82

BH-w/o		88.24 211	87.47 211	90.54 246	95.03 165	78.54 288	97.41 131	93.82 337	84.08 234	78.23 317	94.51 230	69.34 272	97.21 256	80.21 275	94.58 147	95.87 246

USDC		78.65 378	76.25 379	85.85 363	87.58 392	74.60 373	89.58 416	90.58 431	84.05 235	63.13 444	88.23 351	40.69 460	96.86 287	66.57 399	75.81 350	86.09 431

SF-MVS		94.17 39	94.05 46	94.55 37	97.56 82	85.95 46	97.73 101	96.43 125	84.02 236	95.07 60	98.74 20	82.93 64	99.38 95	95.42 67	98.51 39	98.32 74

IS-MVSNet		88.67 197	88.16 192	90.20 259	93.61 213	76.86 340	96.77 191	93.07 384	84.02 236	83.62 255	95.60 176	74.69 202	96.24 312	78.43 296	93.66 166	97.49 158

WR-MVS		84.32 298	82.96 301	88.41 301	89.38 370	80.32 225	96.59 201	96.25 147	83.97 238	76.63 336	90.36 317	67.53 288	94.86 388	75.82 331	70.09 388	90.06 342

mvsany_test1		87.58 233	88.22 189	85.67 369	89.78 356	67.18 436	95.25 301	87.93 450	83.96 239	88.79 162	97.06 131	72.52 229	94.53 400	92.21 116	86.45 270	95.30 268

AUN-MVS		86.25 258	85.57 248	88.26 308	93.57 215	73.38 382	95.45 291	95.88 184	83.94 240	85.47 222	94.21 241	73.70 217	96.67 296	83.54 241	64.41 431	94.73 288

PS-MVSNAJss		84.91 287	84.30 273	86.74 349	85.89 415	74.40 376	94.95 318	94.16 312	83.93 241	76.45 340	90.11 323	71.04 254	95.77 334	83.16 246	79.02 330	90.06 342

LCM-MVSNet-Re		83.75 307	83.54 290	84.39 394	93.54 216	64.14 451	92.51 380	84.03 473	83.90 242	66.14 431	86.59 378	67.36 291	92.68 425	84.89 224	92.87 175	96.35 231

SD_0403		81.29 347	81.13 331	81.78 422	90.20 346	60.43 466	89.97 412	91.31 419	83.87 243	71.78 391	93.08 272	63.86 321	89.61 456	60.00 430	86.07 277	95.30 268

MAR-MVS		90.63 142	90.22 138	91.86 183	98.47 47	78.20 304	97.18 146	96.61 97	83.87 243	88.18 176	98.18 58	68.71 278	99.75 50	83.66 239	97.15 91	97.63 140
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
UWE-MVS-28		85.41 276	86.36 235	82.59 414	91.12 324	66.81 441	93.88 350	97.03 42	83.86 245	78.55 312	93.84 256	77.76 127	88.55 461	73.47 357	87.69 258	92.41 317

PGM-MVS		91.93 103	91.80 100	92.32 152	98.27 55	79.74 248	95.28 296	97.27 22	83.83 246	90.89 129	97.78 90	76.12 166	99.56 83	88.82 181	97.93 64	97.66 136

MDTV_nov1_ep13			83.69 281		94.09 201	81.01 193	86.78 443	96.09 160	83.81 247	84.75 232	84.32 414	74.44 205	96.54 299	63.88 413	85.07 287

WBMVS		87.73 227	86.79 228	90.56 244	95.61 139	85.68 55	97.63 107	95.52 205	83.77 248	78.30 316	88.44 347	86.14 34	95.78 333	82.54 251	73.15 368	90.21 335

SSC-MVS3.2		81.06 351	79.49 355	85.75 367	89.78 356	73.00 390	94.40 333	95.23 228	83.76 249	76.61 338	87.82 358	49.48 424	94.88 386	66.80 394	71.56 375	89.38 352

test-LLR		88.48 203	87.98 194	89.98 266	92.26 280	77.23 333	97.11 156	95.96 173	83.76 249	86.30 212	91.38 300	72.30 234	96.78 292	80.82 267	91.92 191	95.94 243

test0.0.03 1		82.79 324	82.48 310	83.74 400	86.81 399	72.22 394	96.52 208	95.03 236	83.76 249	73.00 380	93.20 267	72.30 234	88.88 459	64.15 412	77.52 342	90.12 338

ACMP	81.66 11	84.00 303	83.22 297	86.33 355	91.53 316	72.95 392	95.91 261	93.79 341	83.70 252	73.79 369	92.22 284	54.31 406	96.89 282	83.98 230	79.74 322	89.16 362
Qingshan Xu and Wenbing Tao: Planar Prior Assisted PatchMatch Multi-View Stereo. AAAI 2020
LuminaMVS		88.02 218	86.89 227	91.43 211	88.65 380	83.16 121	94.84 321	94.41 286	83.67 253	86.56 208	91.95 294	62.04 337	96.88 284	89.78 161	90.06 213	94.24 293

reproduce_model		92.53 87	92.87 71	91.50 208	97.41 90	77.14 337	96.02 250	95.91 180	83.65 254	92.45 96	98.39 46	79.75 92	99.21 108	95.27 71	96.98 98	98.14 90

1112_ss		88.60 200	87.47 211	92.00 176	93.21 230	80.97 195	96.47 212	92.46 391	83.64 255	80.86 289	97.30 117	80.24 83	97.62 205	77.60 307	85.49 283	97.40 170

TAMVS		88.48 203	87.79 199	90.56 244	91.09 325	79.18 264	96.45 214	95.88 184	83.64 255	83.12 263	93.33 266	75.94 170	95.74 339	82.40 252	88.27 252	96.75 220

Test_1112_low_res		88.03 217	86.73 229	91.94 180	93.15 233	80.88 204	96.44 215	92.41 395	83.59 257	80.74 291	91.16 304	80.18 84	97.59 208	77.48 310	85.40 284	97.36 173

tfpn200view9		88.48 203	87.15 217	92.47 137	96.21 114	85.30 69	97.44 126	98.85 2	83.37 258	83.99 246	93.82 257	75.36 186	97.93 186	69.04 384	86.24 274	94.17 294

thres400		88.42 206	87.15 217	92.23 158	96.21 114	85.30 69	97.44 126	98.85 2	83.37 258	83.99 246	93.82 257	75.36 186	97.93 186	69.04 384	86.24 274	93.45 310

Effi-MVS+		90.70 140	89.90 152	93.09 102	93.61 213	83.48 114	95.20 304	92.79 388	83.22 260	91.82 112	95.70 167	71.82 244	97.48 227	91.25 128	93.67 165	98.32 74

thisisatest0515		90.95 133	90.26 136	93.01 105	94.03 205	84.27 97	97.91 87	96.67 87	83.18 261	86.87 204	95.51 179	88.66 17	97.85 194	80.46 270	89.01 231	96.92 208

CostFormer		89.08 183	88.39 186	91.15 224	93.13 235	79.15 266	88.61 426	96.11 159	83.14 262	89.58 147	86.93 373	83.83 57	96.87 285	88.22 192	85.92 278	97.42 167

VDD-MVS		88.28 210	87.02 222	92.06 172	95.09 160	80.18 234	97.55 117	94.45 281	83.09 263	89.10 156	95.92 162	47.97 429	98.49 155	93.08 106	86.91 266	97.52 155

jajsoiax		82.12 335	81.15 330	85.03 381	84.19 434	70.70 414	94.22 342	93.95 323	83.07 264	73.48 372	89.75 325	49.66 423	95.37 356	82.24 256	79.76 320	89.02 374

viewmambaseed2359dif		89.52 170	89.02 167	91.03 228	92.24 283	78.83 274	95.89 266	93.77 345	83.04 265	88.28 174	95.80 164	72.08 240	97.40 239	89.76 162	90.32 211	96.87 212

FOURS1					98.51 44	78.01 308	98.13 71	96.21 151	83.04 265	94.39 71

VPA-MVSNet		85.32 278	83.83 280	89.77 276	90.25 344	82.63 133	96.36 224	97.07 39	83.03 267	81.21 286	89.02 335	61.58 342	96.31 308	85.02 223	70.95 379	90.36 331

CDPH-MVS		93.12 59	92.91 70	93.74 65	98.65 35	83.88 100	97.67 105	96.26 146	83.00 268	93.22 86	98.24 55	81.31 73	99.21 108	89.12 172	98.74 30	98.14 90

miper_enhance_ethall		85.95 262	85.20 256	88.19 315	94.85 169	79.76 245	96.00 251	94.06 319	82.98 269	77.74 322	88.76 338	79.42 93	95.46 353	80.58 269	72.42 370	89.36 356

1314		88.94 188	87.20 216	94.17 51	93.21 230	85.73 52	93.33 365	96.64 94	82.89 270	75.98 350	96.36 152	66.83 298	99.39 94	83.52 243	96.02 128	97.39 171

ZD-MVS					99.09 10	83.22 120		96.60 100	82.88 271	93.61 82	98.06 72	82.93 64	99.14 118	95.51 66	98.49 42

BH-RMVSNet		86.84 245	85.28 255	91.49 209	95.35 148	80.26 229	96.95 174	92.21 399	82.86 272	81.77 283	95.46 182	59.34 356	97.64 204	69.79 382	93.81 162	96.57 226

dmvs_testset		72.00 424	73.36 407	67.91 462	83.83 439	31.90 502	85.30 454	77.12 487	82.80 273	63.05 446	92.46 280	61.54 343	82.55 484	42.22 482	71.89 374	89.29 357

mvs_tets		81.74 340	80.71 336	84.84 382	84.22 433	70.29 418	93.91 349	93.78 342	82.77 274	73.37 375	89.46 331	47.36 434	95.31 360	81.99 257	79.55 326	88.92 381

thres600view7		88.06 216	86.70 232	92.15 166	96.10 119	85.17 75	97.14 153	98.85 2	82.70 275	83.41 259	93.66 261	75.43 183	97.82 195	67.13 393	85.88 279	93.45 310

thres100view900		88.30 209	86.95 224	92.33 150	96.10 119	84.90 84	97.14 153	98.85 2	82.69 276	83.41 259	93.66 261	75.43 183	97.93 186	69.04 384	86.24 274	94.17 294

D2MVS		82.67 326	81.55 323	86.04 362	87.77 390	76.47 345	95.21 303	96.58 103	82.66 277	70.26 408	85.46 400	60.39 348	95.80 331	76.40 324	79.18 328	85.83 437

PHI-MVS		93.59 50	93.63 52	93.48 85	98.05 63	81.76 171	98.64 44	97.13 33	82.60 278	94.09 75	98.49 36	80.35 80	99.85 16	94.74 77	98.62 33	98.83 44

HyFIR lowres test		89.36 177	88.60 178	91.63 202	94.91 168	80.76 208	95.60 285	95.53 203	82.56 279	84.03 245	91.24 303	78.03 120	96.81 289	87.07 206	88.41 250	97.32 175

Syy-MVS		77.97 385	78.05 365	77.74 444	92.13 290	56.85 475	93.97 346	94.23 302	82.43 280	73.39 373	93.57 263	57.95 370	87.86 466	32.40 487	82.34 309	88.51 387

myMVS_eth3d		81.93 337	82.18 313	81.18 425	92.13 290	67.18 436	93.97 346	94.23 302	82.43 280	73.39 373	93.57 263	76.98 144	87.86 466	50.53 465	82.34 309	88.51 387

APD-MVS		93.61 49	93.59 53	93.69 71	98.76 29	83.26 119	97.21 142	96.09 160	82.41 282	94.65 68	98.21 56	81.96 71	98.81 140	94.65 78	98.36 50	99.01 32
Yuesong Wang, Zhaojie Zeng and etc.: Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo. CVPR2023
Fast-Effi-MVS+-dtu		83.33 313	82.60 309	85.50 373	89.55 366	69.38 426	96.09 248	91.38 414	82.30 283	75.96 351	91.41 299	56.71 386	95.58 349	75.13 341	84.90 288	91.54 320

LPG-MVS_test		84.20 300	83.49 292	86.33 355	90.88 328	73.06 388	95.28 296	94.13 313	82.20 284	76.31 342	93.20 267	54.83 402	96.95 276	83.72 236	80.83 317	88.98 377

LGP-MVS_train				86.33 355	90.88 328	73.06 388		94.13 313	82.20 284	76.31 342	93.20 267	54.83 402	96.95 276	83.72 236	80.83 317	88.98 377

SR-MVS		92.16 97	92.27 88	91.83 190	98.37 50	78.41 293	96.67 199	95.76 190	82.19 286	91.97 109	98.07 71	76.44 155	98.64 144	93.71 90	97.27 86	98.45 67

FA-MVS(test-final)		87.71 230	86.23 238	92.17 164	94.19 194	80.55 216	87.16 440	96.07 163	82.12 287	85.98 216	88.35 349	72.04 241	98.49 155	80.26 273	89.87 216	97.48 159

HPM-MVS		91.62 113	91.53 106	91.89 181	97.88 68	79.22 263	96.99 166	95.73 193	82.07 288	89.50 150	97.19 123	75.59 177	98.93 135	90.91 135	97.94 62	97.54 149
Chunlin Ren, Qingshan Xu, Shikun Zhang, Jiaqi Yang: Hierarchical Prior Mining for Non-local Multi-View Stereo. ICCV 2023
mvs_anonymous		88.68 196	87.62 204	91.86 183	94.80 171	81.69 175	93.53 360	94.92 240	82.03 289	78.87 311	90.43 316	75.77 173	95.34 357	85.04 222	93.16 173	98.55 63

XVG-OURS		85.18 281	84.38 272	87.59 331	90.42 341	71.73 406	91.06 403	94.07 318	82.00 290	83.29 261	95.08 204	56.42 390	97.55 216	83.70 238	83.42 296	93.49 309

BH-untuned		86.95 243	85.94 240	89.99 265	94.52 179	77.46 328	96.78 189	93.37 372	81.80 291	76.62 337	93.81 259	66.64 299	97.02 268	76.06 327	93.88 161	95.48 263

WB-MVSnew		84.08 302	83.51 291	85.80 364	91.34 319	76.69 344	95.62 284	96.27 145	81.77 292	81.81 282	92.81 275	58.23 364	94.70 394	66.66 396	87.06 264	85.99 434

FMVSNet3		84.71 289	82.71 307	90.70 241	94.55 177	87.71 24	95.92 257	94.67 261	81.73 293	75.82 353	88.08 354	66.99 295	94.47 401	71.23 371	75.38 352	89.91 344

thisisatest0530		89.65 168	89.02 167	91.53 205	93.46 223	80.78 207	96.52 208	96.67 87	81.69 294	83.79 251	94.90 215	88.85 16	97.68 202	77.80 301	87.49 263	96.14 238

v2v482		83.46 311	81.86 319	88.25 310	86.19 409	79.65 251	96.34 226	94.02 322	81.56 295	77.32 325	88.23 351	65.62 305	96.03 317	77.77 302	69.72 392	89.09 364

XVG-OURS-SEG-HR		85.74 266	85.16 259	87.49 337	90.22 345	71.45 409	91.29 399	94.09 316	81.37 296	83.90 250	95.22 193	60.30 349	97.53 221	85.58 218	84.42 291	93.50 308

Fast-Effi-MVS+		87.93 221	86.94 225	90.92 232	94.04 203	79.16 265	98.26 64	93.72 352	81.29 297	83.94 249	92.90 274	69.83 266	96.68 295	76.70 318	91.74 194	96.93 206

0.4-1-1-0.2		87.73 227	85.82 244	93.46 88	89.97 353	85.31 68	98.49 51	96.55 107	81.24 298	87.14 195	89.63 328	76.16 164	97.02 268	86.84 210	66.38 424	98.05 96

ab-mvs		87.08 240	84.94 263	93.48 85	93.34 226	83.67 110	88.82 423	95.70 194	81.18 299	84.55 237	90.14 322	62.72 328	98.94 134	85.49 219	82.54 308	97.85 118

0.3-1-1-0.015		87.79 225	85.93 241	93.38 89	89.87 354	85.09 78	98.43 52	96.55 107	81.13 300	87.21 193	89.75 325	77.23 138	97.02 268	86.87 209	66.38 424	98.02 98

test_fmvs2		79.59 365	79.90 350	78.67 440	82.86 445	55.82 479	95.20 304	89.55 437	81.09 301	80.12 300	89.80 324	34.31 471	93.51 420	87.82 195	78.36 338	86.69 422

原ACMM1				91.22 223	97.77 72	78.10 306		96.61 97	81.05 302	91.28 122	97.42 111	77.92 123	98.98 129	79.85 280	98.51 39	96.59 225

test_yl		91.46 116	90.53 127	94.24 45	97.41 90	85.18 71	98.08 74	97.72 11	80.94 303	89.85 140	96.14 156	75.61 175	98.81 140	90.42 151	88.56 243	98.74 49

DCV-MVSNet		91.46 116	90.53 127	94.24 45	97.41 90	85.18 71	98.08 74	97.72 11	80.94 303	89.85 140	96.14 156	75.61 175	98.81 140	90.42 151	88.56 243	98.74 49

0.4-1-1-0.1		87.53 235	85.67 246	93.13 99	89.70 361	84.41 91	98.30 62	96.55 107	80.85 305	86.94 199	89.53 330	76.18 162	96.99 273	86.62 213	66.36 426	97.98 106

testing3		80.74 356	81.17 329	79.44 435	91.15 323	63.48 455	97.16 150	95.76 190	80.83 306	71.36 395	93.15 270	78.22 117	87.30 471	43.19 479	79.67 323	87.55 412

CP-MVSNet		81.01 353	80.08 345	83.79 398	87.91 389	70.51 415	94.29 341	95.65 197	80.83 306	72.54 386	88.84 337	63.71 322	92.32 431	68.58 388	68.36 403	88.55 386

tttt0517		88.57 201	88.19 191	89.71 277	93.00 239	75.99 358	95.67 280	96.67 87	80.78 308	81.82 281	94.40 235	88.97 15	97.58 210	76.05 328	86.31 271	95.57 259

MVSFormer		91.36 120	90.57 126	93.73 67	93.00 239	88.08 20	94.80 324	94.48 275	80.74 309	94.90 62	97.13 125	78.84 105	95.10 376	83.77 234	97.46 76	98.02 98

test_djsdf		83.00 322	82.45 311	84.64 387	84.07 436	69.78 422	94.80 324	94.48 275	80.74 309	75.41 359	87.70 359	61.32 346	95.10 376	83.77 234	79.76 320	89.04 370

MDTV_nov1_ep13_2view						81.74 172	86.80 442		80.65 311	85.65 218		74.26 206		76.52 322		96.98 203

CVMVSNet		84.83 288	85.57 248	82.63 413	91.55 314	60.38 467	95.13 310	95.03 236	80.60 312	82.10 277	94.71 224	66.40 302	90.19 454	74.30 349	90.32 211	97.31 177

DP-MVS Recon		91.72 110	90.85 120	94.34 41	99.50 1	85.00 82	98.51 49	95.96 173	80.57 313	88.08 179	97.63 100	76.84 146	99.89 10	85.67 217	94.88 142	98.13 92

SR-MVS-dyc-post		91.29 122	91.45 107	90.80 237	97.76 74	76.03 355	96.20 239	95.44 212	80.56 314	90.72 130	97.84 86	75.76 174	98.61 145	91.99 119	96.79 108	97.75 127

RE-MVS-def			91.18 115		97.76 74	76.03 355	96.20 239	95.44 212	80.56 314	90.72 130	97.84 86	73.36 220		91.99 119	96.79 108	97.75 127

v148		82.41 332	80.89 332	86.99 347	86.18 410	76.81 341	96.27 231	93.82 337	80.49 316	75.28 360	86.11 391	67.32 292	95.75 336	75.48 337	67.03 419	88.42 393

IterMVS-LS		83.93 304	82.80 306	87.31 341	91.46 317	77.39 330	95.66 281	93.43 367	80.44 317	75.51 357	87.26 367	73.72 215	95.16 370	76.99 314	70.72 381	89.39 350
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
ACMM	80.70 13	83.72 308	82.85 305	86.31 358	91.19 321	72.12 398	95.88 268	94.29 297	80.44 317	77.02 331	91.96 292	55.24 398	97.14 264	79.30 287	80.38 319	89.67 346
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
EI-MVSNet		85.80 264	85.20 256	87.59 331	91.55 314	77.41 329	95.13 310	95.36 218	80.43 319	80.33 296	94.71 224	73.72 215	95.97 320	76.96 316	78.64 333	89.39 350

UnsupCasMVSNet_eth		73.25 415	70.57 420	81.30 423	77.53 468	66.33 443	87.24 439	93.89 329	80.38 320	57.90 468	81.59 439	42.91 448	90.56 450	65.18 406	48.51 476	87.01 419

mamba_0408		85.26 280	83.10 299	91.74 194	92.94 245	82.53 135	72.52 486	91.77 406	80.36 321	83.50 256	94.01 248	64.97 313	96.90 280	79.37 284	88.51 246	95.79 249

SSM_04072		84.64 291	83.10 299	89.25 284	92.94 245	82.53 135	72.52 486	91.77 406	80.36 321	83.50 256	94.01 248	64.97 313	89.41 457	79.37 284	88.51 246	95.79 249

V42		83.04 320	81.53 324	87.57 333	86.27 408	79.09 269	95.87 269	94.11 315	80.35 323	77.22 327	86.79 376	65.32 310	96.02 318	77.74 303	70.14 384	87.61 408

TR-MVS		86.30 256	84.93 264	90.42 249	94.63 174	77.58 326	96.57 204	93.82 337	80.30 324	82.42 270	95.16 198	58.74 360	97.55 216	74.88 342	87.82 257	96.13 239

IterMVS		80.67 357	79.16 357	85.20 378	89.79 355	76.08 353	92.97 375	91.86 403	80.28 325	71.20 397	85.14 406	57.93 371	91.34 443	72.52 363	70.74 380	88.18 398
Fangjinhua Wang, Silvano Galliani, Christoph Vogel, Marc Pollefeys: IterMVS: Iterative Probability Estimation for Efficient Multi-View Stereo.
PS-CasMVS		80.27 360	79.18 356	83.52 404	87.56 393	69.88 421	94.08 344	95.29 225	80.27 326	72.08 389	88.51 344	59.22 358	92.23 433	67.49 390	68.15 406	88.45 392

XVG-ACMP-BASELINE		79.38 369	77.90 367	83.81 397	84.98 426	67.14 440	89.03 422	93.18 379	80.26 327	72.87 382	88.15 353	38.55 461	96.26 309	76.05 328	78.05 340	88.02 400

XXY-MVS		83.84 305	82.00 317	89.35 282	87.13 396	81.38 182	95.72 276	94.26 300	80.15 328	75.92 352	90.63 312	61.96 340	96.52 300	78.98 291	73.28 366	90.14 337

SSM_0407		87.33 239	85.87 243	91.71 198	92.94 245	82.53 135	94.30 337	92.33 397	80.11 329	83.50 256	94.18 243	64.68 317	96.80 291	82.34 253	88.51 246	95.79 249

SSM_0404		87.69 231	86.26 236	91.95 178	92.94 245	83.02 125	94.69 326	92.33 397	80.11 329	84.65 235	94.18 243	64.68 317	96.90 280	82.34 253	90.44 210	95.94 243

WR-MVS_H		81.02 352	80.09 344	83.79 398	88.08 387	71.26 412	94.46 328	96.54 110	80.08 331	72.81 383	86.82 374	70.36 263	92.65 426	64.18 411	67.50 413	87.46 414

IterMVS-SCA-FT		80.51 359	79.10 358	84.73 384	89.63 364	74.66 371	92.98 374	91.81 405	80.05 332	71.06 400	85.18 404	58.04 367	91.40 442	72.48 364	70.70 382	88.12 399

v1144		82.90 323	81.27 328	87.78 324	86.29 407	79.07 270	96.14 245	93.93 324	80.05 332	77.38 323	86.80 375	65.50 306	95.93 325	75.21 340	70.13 385	88.33 395

ITE_SJBPF				82.38 416	87.00 397	65.59 445		89.55 437	79.99 334	69.37 415	91.30 302	41.60 453	95.33 358	62.86 419	74.63 359	86.24 428

dp		84.30 299	82.31 312	90.28 256	94.24 193	77.97 309	86.57 444	95.53 203	79.94 335	80.75 290	85.16 405	71.49 250	96.39 304	63.73 414	83.36 297	96.48 228

APD-MVS_3200maxsize		91.23 124	91.35 108	90.89 235	97.89 67	76.35 350	96.30 230	95.52 205	79.82 336	91.03 126	97.88 85	74.70 199	98.54 152	92.11 118	96.89 102	97.77 125

PEN-MVS		79.47 368	78.26 364	83.08 407	86.36 405	68.58 429	93.85 352	94.77 252	79.76 337	71.37 394	88.55 341	59.79 350	92.46 427	64.50 409	65.40 428	88.19 397

cl22		85.11 282	84.17 276	87.92 321	95.06 164	78.82 275	95.51 288	94.22 304	79.74 338	76.77 334	87.92 356	75.96 168	95.68 340	79.93 279	72.42 370	89.27 358

MS-PatchMatch		83.05 319	81.82 320	86.72 353	89.64 363	79.10 268	94.88 320	94.59 270	79.70 339	70.67 402	89.65 327	50.43 419	96.82 288	70.82 378	95.99 130	84.25 449

PCF-MVS	84.09 5	86.77 248	85.00 262	92.08 169	92.06 296	83.07 123	92.14 387	94.47 278	79.63 340	76.90 333	94.78 221	71.15 252	99.20 113	72.87 360	91.05 204	93.98 300
Andreas Kuhn, Shan Lin, Oliver Erdler: Plane Completion and Filtering for Multi-View Stereo Reconstruction. GCPR 2019
GeoE		86.36 254	85.20 256	89.83 273	93.17 232	76.13 352	97.53 118	92.11 400	79.58 341	80.99 287	94.01 248	66.60 300	96.17 315	73.48 356	89.30 225	97.20 186

HPM-MVS_fast		90.38 150	90.17 141	91.03 228	97.61 78	77.35 331	97.15 152	95.48 208	79.51 342	88.79 162	96.90 135	71.64 247	98.81 140	87.01 207	97.44 78	96.94 205

testgi		74.88 406	73.40 406	79.32 436	80.13 454	61.75 461	93.21 370	86.64 460	79.49 343	66.56 430	91.06 305	35.51 469	88.67 460	56.79 446	71.25 376	87.56 410

EPP-MVSNet		89.76 165	89.72 154	89.87 271	93.78 208	76.02 357	97.22 141	96.51 114	79.35 344	85.11 225	95.01 208	84.82 40	97.10 266	87.46 202	88.21 253	96.50 227

v1192		82.31 333	80.55 339	87.60 330	85.94 413	78.47 292	95.85 271	93.80 340	79.33 345	76.97 332	86.51 379	63.33 326	95.87 327	73.11 359	70.13 385	88.46 391

tpm2		87.35 238	86.26 236	90.62 242	92.93 249	78.67 285	88.06 433	95.99 170	79.33 345	87.40 187	86.43 384	80.28 82	96.40 303	80.23 274	85.73 282	96.79 215

PatchMatch-RL		85.00 286	83.66 284	89.02 289	95.86 128	74.55 374	92.49 381	93.60 360	79.30 347	79.29 308	91.47 298	58.53 362	98.45 160	70.22 380	92.17 190	94.07 299

miper_ehance_all_eth		84.57 294	83.60 289	87.50 335	92.64 261	78.25 299	95.40 294	93.47 364	79.28 348	76.41 341	87.64 361	76.53 153	95.24 365	78.58 294	72.42 370	89.01 376

PLC	83.97 7	88.00 219	87.38 213	89.83 273	98.02 64	76.46 346	97.16 150	94.43 284	79.26 349	81.98 278	96.28 154	69.36 271	99.27 102	77.71 305	92.25 188	93.77 304
Jie Liao, Yanping Fu, Qingan Yan, Chunxia xiao: Pyramid Multi-View Stereo with Local Consistency. Pacific Graphics 2019
LFMVS		89.27 180	87.64 202	94.16 54	97.16 99	85.52 62	97.18 146	94.66 262	79.17 350	89.63 146	96.57 148	55.35 397	98.22 171	89.52 169	89.54 219	98.74 49

eth_miper_zixun_eth		83.12 318	82.01 316	86.47 354	91.85 307	74.80 370	94.33 335	93.18 379	79.11 351	75.74 356	87.25 368	72.71 226	95.32 359	76.78 317	67.13 417	89.27 358

v144192		82.43 329	80.73 335	87.54 334	85.81 416	78.22 300	95.98 252	93.78 342	79.09 352	77.11 330	86.49 380	64.66 319	95.91 326	74.20 350	69.42 393	88.49 389

GBi-Net		82.42 330	80.43 341	88.39 303	92.66 257	81.95 158	94.30 337	93.38 369	79.06 353	75.82 353	85.66 393	56.38 391	93.84 413	71.23 371	75.38 352	89.38 352

test1		82.42 330	80.43 341	88.39 303	92.66 257	81.95 158	94.30 337	93.38 369	79.06 353	75.82 353	85.66 393	56.38 391	93.84 413	71.23 371	75.38 352	89.38 352

FMVSNet2		82.79 324	80.44 340	89.83 273	92.66 257	85.43 63	95.42 292	94.35 291	79.06 353	74.46 366	87.28 365	56.38 391	94.31 405	69.72 383	74.68 358	89.76 345

v1921920		82.02 336	80.23 343	87.41 338	85.62 417	77.92 313	95.79 275	93.69 354	78.86 356	76.67 335	86.44 382	62.50 329	95.83 329	72.69 361	69.77 391	88.47 390

v8		81.88 338	80.06 347	87.32 340	86.63 400	79.04 271	94.41 330	93.65 356	78.77 357	73.19 379	85.57 397	66.87 297	95.81 330	73.84 354	67.61 412	87.11 417

DTE-MVSNet		78.37 379	77.06 373	82.32 418	85.22 424	67.17 439	93.40 361	93.66 355	78.71 358	70.53 403	88.29 350	59.06 359	92.23 433	61.38 424	63.28 437	87.56 410

c3_l		83.80 306	82.65 308	87.25 343	92.10 292	77.74 324	95.25 301	93.04 385	78.58 359	76.01 349	87.21 369	75.25 191	95.11 375	77.54 309	68.89 398	88.91 382

Patchmatch-RL test		76.65 397	74.01 403	84.55 389	77.37 470	64.23 450	78.49 475	82.84 478	78.48 360	64.63 438	73.40 473	76.05 167	91.70 441	76.99 314	57.84 446	97.72 130

v1240		81.70 341	79.83 351	87.30 342	85.50 418	77.70 325	95.48 289	93.44 365	78.46 361	76.53 339	86.44 382	60.85 347	95.84 328	71.59 368	70.17 383	88.35 394

cl____		83.27 314	82.12 314	86.74 349	92.20 284	75.95 359	95.11 312	93.27 375	78.44 362	74.82 364	87.02 372	74.19 207	95.19 367	74.67 345	69.32 394	89.09 364

DIV-MVS_self_test		83.27 314	82.12 314	86.74 349	92.19 285	75.92 361	95.11 312	93.26 376	78.44 362	74.81 365	87.08 371	74.19 207	95.19 367	74.66 346	69.30 395	89.11 363

SixPastTwentyTwo		76.04 399	74.32 399	81.22 424	84.54 429	61.43 464	91.16 401	89.30 441	77.89 364	64.04 439	86.31 386	48.23 426	94.29 406	63.54 416	63.84 435	87.93 402

v10		81.43 345	79.53 354	87.11 345	86.38 404	78.87 273	94.31 336	93.43 367	77.88 365	73.24 378	85.26 401	65.44 307	95.75 336	72.14 365	67.71 411	86.72 421

miper_lstm_enhance		81.66 343	80.66 337	84.67 386	91.19 321	71.97 401	91.94 389	93.19 377	77.86 366	72.27 388	85.26 401	73.46 218	93.42 421	73.71 355	67.05 418	88.61 385

MVP-Stereo		82.65 327	81.67 322	85.59 372	86.10 412	78.29 296	93.33 365	92.82 387	77.75 367	69.17 417	87.98 355	59.28 357	95.76 335	71.77 366	96.88 103	82.73 458
Qingsong Yan: MVP-Stereo: A Parallel Multi-View Patchmatch Stereo Method with Dilation Matching for Photogrammetric Application.
pmmvs5		81.34 346	79.54 353	86.73 352	85.02 425	76.91 338	96.22 237	91.65 410	77.65 368	73.55 371	88.61 340	55.70 395	94.43 403	74.12 351	73.35 365	88.86 383

MVS		90.60 143	88.64 177	96.50 6	94.25 192	90.53 9	93.33 365	97.21 26	77.59 369	78.88 310	97.31 114	71.52 249	99.69 65	89.60 165	98.03 59	99.27 23

AdaColmap		88.81 193	87.61 205	92.39 145	99.33 5	79.95 240	96.70 197	95.58 200	77.51 370	83.05 265	96.69 147	61.90 341	99.72 58	84.29 227	93.47 168	97.50 157

无先验							96.87 180	96.78 66	77.39 371				99.52 86	79.95 278		98.43 69

MIMVSNet		79.18 371	75.99 381	88.72 296	87.37 395	80.66 210	79.96 467	91.82 404	77.38 372	74.33 367	81.87 438	41.78 451	90.74 449	66.36 402	83.10 299	94.76 283

pmmvs4		82.54 328	80.79 333	87.79 323	86.11 411	80.49 224	93.55 359	93.18 379	77.29 373	73.35 376	89.40 332	65.26 311	95.05 383	75.32 339	73.61 362	87.83 403

CL-MVSNet_self_test		75.81 401	74.14 402	80.83 428	78.33 466	67.79 433	94.22 342	93.52 363	77.28 374	69.82 412	81.54 441	61.47 345	89.22 458	57.59 441	53.51 464	85.48 439

pm-mvs1		80.05 361	78.02 366	86.15 360	85.42 419	75.81 362	95.11 312	92.69 390	77.13 375	70.36 404	87.43 363	58.44 363	95.27 362	71.36 370	64.25 433	87.36 415

K. test v3		73.62 410	71.59 415	79.69 433	82.98 444	59.85 470	90.85 405	88.83 444	77.13 375	58.90 463	82.11 434	43.62 442	91.72 440	65.83 403	54.10 457	87.50 413

anonymousdsp		80.98 354	79.97 348	84.01 395	81.73 448	70.44 417	92.49 381	93.58 362	77.10 377	72.98 381	86.31 386	57.58 378	94.90 385	79.32 286	78.63 335	86.69 422

CSCG		92.02 100	91.65 103	93.12 100	98.53 41	80.59 212	97.47 123	97.18 29	77.06 378	84.64 236	97.98 77	83.98 54	99.52 86	90.72 142	97.33 84	99.23 25

OurMVSNet-221017-0		77.18 394	76.06 380	80.55 429	83.78 440	60.00 469	90.35 409	91.05 423	77.01 379	66.62 429	87.92 356	47.73 432	94.03 409	71.63 367	68.44 402	87.62 407

Elysia		85.62 269	83.66 284	91.51 206	88.76 373	82.21 150	95.15 308	94.70 254	76.96 380	84.13 242	92.20 285	50.81 415	97.26 253	77.81 299	92.42 183	95.06 274

StellarMVS		85.62 269	83.66 284	91.51 206	88.76 373	82.21 150	95.15 308	94.70 254	76.96 380	84.13 242	92.20 285	50.81 415	97.26 253	77.81 299	92.42 183	95.06 274

mmtdpeth		78.04 382	76.76 376	81.86 421	89.60 365	66.12 444	92.34 385	87.18 454	76.83 382	85.55 221	76.49 465	46.77 435	97.02 268	90.85 138	45.24 482	82.43 462

FE-MVSNET2		73.72 409	70.80 418	82.46 415	74.97 479	73.81 380	91.88 391	91.73 408	76.70 383	59.74 462	77.41 459	42.26 450	90.52 451	64.75 408	57.79 447	83.06 454

FE-MVS		86.06 260	84.15 277	91.78 191	94.33 191	79.81 243	84.58 458	96.61 97	76.69 384	85.00 227	87.38 364	70.71 261	98.37 165	70.39 379	91.70 195	97.17 189

test_vis1_rt		73.96 408	72.40 411	78.64 441	83.91 438	61.16 465	95.63 283	68.18 495	76.32 385	60.09 460	74.77 468	29.01 482	97.54 219	87.74 198	75.94 348	77.22 478

KD-MVS_2432*1600		77.63 388	74.92 393	85.77 365	90.86 331	79.44 255	88.08 431	93.92 326	76.26 386	67.05 424	82.78 427	72.15 238	91.92 436	61.53 421	41.62 488	85.94 435

miper_refine_blended		77.63 388	74.92 393	85.77 365	90.86 331	79.44 255	88.08 431	93.92 326	76.26 386	67.05 424	82.78 427	72.15 238	91.92 436	61.53 421	41.62 488	85.94 435

Baseline_NR-MVSNet		81.22 349	80.07 346	84.68 385	85.32 423	75.12 369	96.48 211	88.80 445	76.24 388	77.28 326	86.40 385	67.61 285	94.39 404	75.73 332	66.73 421	84.54 446

F-COLMAP		84.50 296	83.44 293	87.67 327	95.22 152	72.22 394	95.95 254	93.78 342	75.74 389	76.30 344	95.18 197	59.50 354	98.45 160	72.67 362	86.59 269	92.35 319

CPTT-MVS		89.72 166	89.87 153	89.29 283	98.33 52	73.30 384	97.70 103	95.35 220	75.68 390	87.40 187	97.44 110	70.43 262	98.25 170	89.56 168	96.90 101	96.33 234

OpenMVS	79.58 14	86.09 259	83.62 288	93.50 83	90.95 327	86.71 37	97.44 126	95.83 187	75.35 391	72.64 384	95.72 166	57.42 382	99.64 71	71.41 369	95.85 132	94.13 297

cascas		86.50 250	84.48 269	92.55 134	92.64 261	85.95 46	97.04 164	95.07 234	75.32 392	80.50 292	91.02 306	54.33 405	97.98 185	86.79 211	87.62 259	93.71 305

tpmvs		83.04 320	80.77 334	89.84 272	95.43 144	77.96 310	85.59 451	95.32 222	75.31 393	76.27 345	83.70 420	73.89 211	97.41 237	59.53 431	81.93 314	94.14 296

114514_t		88.79 195	87.57 207	92.45 139	98.21 58	81.74 172	96.99 166	95.45 211	75.16 394	82.48 268	95.69 169	68.59 279	98.50 154	80.33 271	95.18 139	97.10 193

API-MVS		90.18 154	88.97 170	93.80 61	98.66 33	82.95 126	97.50 122	95.63 199	75.16 394	86.31 211	97.69 92	72.49 230	99.90 8	81.26 266	96.07 125	98.56 61

v7n		79.32 370	77.34 370	85.28 377	84.05 437	72.89 393	93.38 362	93.87 330	75.02 396	70.68 401	84.37 413	59.58 353	95.62 346	67.60 389	67.50 413	87.32 416

TAPA-MVS	81.61 12	85.02 285	83.67 283	89.06 287	96.79 103	73.27 387	95.92 257	94.79 251	74.81 397	80.47 293	96.83 139	71.07 253	98.19 173	49.82 467	92.57 178	95.71 254
Andrea Romanoni, Matteo Matteucci: TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereo. ICCV 2019
PM-MVS		69.32 435	66.93 434	76.49 451	73.60 482	55.84 478	85.91 449	79.32 485	74.72 398	61.09 456	78.18 455	21.76 486	91.10 446	70.86 376	56.90 449	82.51 459

MVSMamba_PlusPlus		92.37 93	91.55 105	94.83 28	95.37 147	87.69 25	95.60 285	95.42 216	74.65 399	93.95 77	92.81 275	83.11 62	97.70 200	94.49 80	98.53 38	99.11 29

新几何1				93.12 100	97.44 88	81.60 180		96.71 82	74.54 400	91.22 123	97.57 102	79.13 100	99.51 88	77.40 312	98.46 43	98.26 81

CNLPA		86.96 242	85.37 252	91.72 197	97.59 80	79.34 260	97.21 142	91.05 423	74.22 401	78.90 309	96.75 145	67.21 293	98.95 132	74.68 344	90.77 208	96.88 211

tt0805		81.20 350	79.06 359	87.61 329	86.50 403	72.97 391	93.66 354	95.48 208	74.11 402	76.23 346	91.99 290	41.36 455	97.40 239	77.44 311	74.78 357	92.45 316

test20.03		72.36 421	71.15 416	75.98 454	77.79 467	59.16 471	92.40 383	89.35 440	74.09 403	61.50 454	84.32 414	48.09 427	85.54 477	50.63 464	62.15 440	83.24 453

旧先验2							96.97 171		74.06 404	96.10 42			97.76 197	88.38 190

TransMVSNet (Re)		76.94 395	74.38 398	84.62 388	85.92 414	75.25 368	95.28 296	89.18 442	73.88 405	67.22 421	86.46 381	59.64 351	94.10 408	59.24 435	52.57 468	84.50 447

QAPM		86.88 244	84.51 267	93.98 55	94.04 203	85.89 49	97.19 145	96.05 164	73.62 406	75.12 361	95.62 175	62.02 338	99.74 53	70.88 375	96.06 126	96.30 236

UniMVSNet_ETH3D		80.86 355	78.75 361	87.22 344	86.31 406	72.02 399	91.95 388	93.76 347	73.51 407	75.06 363	90.16 321	43.04 447	95.66 341	76.37 325	78.55 336	93.98 300

tfpnnormal		78.14 381	75.42 389	86.31 358	88.33 385	79.24 261	94.41 330	96.22 150	73.51 407	69.81 413	85.52 399	55.43 396	95.75 336	47.65 472	67.86 409	83.95 452

testdata				90.13 260	95.92 127	74.17 377		96.49 119	73.49 409	94.82 66	97.99 74	78.80 107	97.93 186	83.53 242	97.52 75	98.29 78

our_test_3		77.90 386	75.37 390	85.48 374	85.39 420	76.74 342	93.63 355	91.67 409	73.39 410	65.72 433	84.65 412	58.20 366	93.13 424	57.82 439	67.87 408	86.57 424

FMVSNet1		79.50 367	76.54 378	88.39 303	88.47 381	81.95 158	94.30 337	93.38 369	73.14 411	72.04 390	85.66 393	43.86 441	93.84 413	65.48 404	72.53 369	89.38 352

Anonymous20231206		75.29 404	73.64 405	80.22 431	80.75 449	63.38 456	93.36 363	90.71 430	73.09 412	67.12 422	83.70 420	50.33 420	90.85 448	53.63 456	70.10 387	86.44 425

ADS-MVSNet2		79.57 366	77.53 369	85.71 368	93.78 208	72.13 397	79.48 469	86.11 462	73.09 412	80.14 298	79.99 450	62.15 334	90.14 455	59.49 432	83.52 294	94.85 281

ADS-MVSNet		81.26 348	78.36 362	89.96 268	93.78 208	79.78 244	79.48 469	93.60 360	73.09 412	80.14 298	79.99 450	62.15 334	95.24 365	59.49 432	83.52 294	94.85 281

EU-MVSNet		76.92 396	76.95 374	76.83 450	84.10 435	54.73 482	91.77 393	92.71 389	72.74 415	69.57 414	88.69 339	58.03 369	87.43 470	64.91 407	70.00 389	88.33 395

pmmvs-eth3d		73.59 411	70.66 419	82.38 416	76.40 474	73.38 382	89.39 420	89.43 439	72.69 416	60.34 459	77.79 456	46.43 437	91.26 445	66.42 401	57.06 448	82.51 459

wanda-best-256-512		78.87 373	75.75 383	88.22 312	79.74 456	80.51 222	95.92 257	93.75 348	72.60 417	70.34 405	82.14 430	57.91 373	95.09 378	75.61 333	53.77 459	89.05 367

FE-blended-shiyan7		78.87 373	75.75 383	88.22 312	79.74 456	80.51 222	95.92 257	93.75 348	72.60 417	70.34 405	82.14 430	57.91 373	95.09 378	75.61 333	53.77 459	89.05 367

LTVRE_ROB	73.68 18	77.99 383	75.74 385	84.74 383	90.45 340	72.02 399	86.41 446	91.12 420	72.57 419	66.63 428	87.27 366	54.95 401	96.98 274	56.29 447	75.98 347	85.21 441
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
gbinet_0.2-2-1-0.02		78.67 377	75.67 386	87.70 325	80.38 453	79.60 253	96.25 233	94.03 321	72.51 420	71.41 393	83.33 424	55.97 394	94.45 402	73.37 358	53.73 463	89.04 370

ACMH	75.40 17	77.99 383	74.96 391	87.10 346	90.67 336	76.41 348	93.19 372	91.64 411	72.47 421	63.44 442	87.61 362	43.34 444	97.16 259	58.34 437	73.94 360	87.72 404
Qingshan Xu and Wenbing Tao: Multi-Scale Geometric Consistency Guided Multi-View Stereo. CVPR 2019
blended_shiyan8		78.76 375	75.65 387	88.10 316	79.58 461	80.20 232	95.70 279	93.71 353	72.43 422	70.26 408	82.12 433	57.66 377	95.08 380	75.57 335	53.80 458	89.02 374

blended_shiyan6		78.74 376	75.63 388	88.07 317	79.63 460	80.10 237	95.72 276	93.73 350	72.43 422	70.17 411	82.09 435	57.69 376	95.07 381	75.47 338	53.77 459	89.03 372

blend_shiyan4		81.76 339	79.58 352	88.31 306	80.00 455	80.59 212	95.95 254	93.73 350	72.26 424	71.14 398	82.52 429	76.13 165	95.15 371	77.83 297	66.62 422	89.19 360

mvsany_test3		67.19 440	65.34 441	72.72 458	63.08 492	48.57 485	83.12 463	78.09 486	72.07 425	61.21 455	77.11 462	22.94 485	87.78 468	78.59 293	51.88 469	81.80 467

test222					96.15 117	78.41 293	95.87 269	96.46 121	71.97 426	89.66 145	97.45 107	76.33 159			98.24 54	98.30 77

ACMH+	76.62 16	77.47 391	74.94 392	85.05 380	91.07 326	71.58 408	93.26 369	90.01 433	71.80 427	64.76 437	88.55 341	41.62 452	96.48 301	62.35 420	71.00 378	87.09 418

ppachtmachnet_test		77.19 393	74.22 400	86.13 361	85.39 420	78.22 300	93.98 345	91.36 416	71.74 428	67.11 423	84.87 410	56.67 387	93.37 423	52.21 458	64.59 430	86.80 420

new-patchmatchnet		68.85 438	65.93 439	77.61 445	73.57 483	63.94 453	90.11 411	88.73 447	71.62 429	55.08 474	73.60 472	40.84 458	87.22 472	51.35 462	48.49 477	81.67 470

FMVSNet5		76.46 398	74.16 401	83.35 406	90.05 351	76.17 351	89.58 416	89.85 434	71.39 430	65.29 436	80.42 446	50.61 418	87.70 469	61.05 426	69.24 396	86.18 429

test_fmvs3		69.56 432	69.19 427	70.67 460	69.01 485	47.05 486	90.87 404	86.81 457	71.31 431	66.79 427	77.15 461	16.40 490	83.17 482	81.84 258	62.51 439	81.79 468

tpm cat1		83.63 309	81.38 326	90.39 250	93.53 221	78.19 305	85.56 452	95.09 232	70.78 432	78.51 313	83.28 425	74.80 198	97.03 267	66.77 395	84.05 292	95.95 242

MDA-MVSNet-bldmvs		71.45 425	67.94 432	81.98 420	85.33 422	68.50 430	92.35 384	88.76 446	70.40 433	42.99 485	81.96 437	46.57 436	91.31 444	48.75 471	54.39 456	86.11 430

Anonymous202405211		84.41 297	81.93 318	91.85 185	96.78 104	78.41 293	97.44 126	91.34 417	70.29 434	84.06 244	94.26 238	41.09 456	98.96 130	79.46 282	82.65 307	98.17 87

FE-MVSNET		69.26 436	66.03 438	78.93 438	73.82 481	68.33 431	89.65 413	84.06 472	70.21 435	57.79 469	76.94 464	41.48 454	86.98 473	45.85 475	54.51 455	81.48 471

KD-MVS_self_test		70.97 428	69.31 426	75.95 455	76.24 476	55.39 481	87.45 436	90.94 426	70.20 436	62.96 447	77.48 458	44.01 440	88.09 464	61.25 425	53.26 465	84.37 448

DeepMVS_CX				64.06 468	78.53 465	43.26 493		68.11 497	69.94 437	38.55 487	76.14 466	18.53 488	79.34 485	43.72 478	41.62 488	69.57 483

MSDG		80.62 358	77.77 368	89.14 286	93.43 224	77.24 332	91.89 390	90.18 432	69.86 438	68.02 419	91.94 295	52.21 411	98.84 138	59.32 434	83.12 298	91.35 321

VDDNet		86.44 251	84.51 267	92.22 159	91.56 312	81.83 168	97.10 159	94.64 265	69.50 439	87.84 183	95.19 196	48.01 428	97.92 191	89.82 160	86.92 265	96.89 209

LF4IMVS		72.36 421	70.82 417	76.95 449	79.18 462	56.33 476	86.12 448	86.11 462	69.30 440	63.06 445	86.66 377	33.03 474	92.25 432	65.33 405	68.64 400	82.28 463

mvs5depth		71.40 426	68.36 430	80.54 430	75.31 478	65.56 446	79.94 468	85.14 465	69.11 441	71.75 392	81.59 439	41.02 457	93.94 411	60.90 427	50.46 471	82.10 464

EG-PatchMatch MVS		74.92 405	72.02 413	83.62 402	83.76 442	73.28 385	93.62 356	92.04 402	68.57 442	58.88 464	83.80 419	31.87 476	95.57 350	56.97 445	78.67 332	82.00 466

kuosan		73.55 412	72.39 412	77.01 448	89.68 362	66.72 442	85.24 455	93.44 365	67.76 443	60.04 461	83.40 423	71.90 243	84.25 479	45.34 476	54.75 452	80.06 474

AllTest		75.92 400	73.06 408	84.47 390	92.18 286	67.29 434	91.07 402	84.43 468	67.63 444	63.48 440	90.18 319	38.20 462	97.16 259	57.04 443	73.37 363	88.97 379

TestCases				84.47 390	92.18 286	67.29 434		84.43 468	67.63 444	63.48 440	90.18 319	38.20 462	97.16 259	57.04 443	73.37 363	88.97 379

YYNet1		73.53 414	70.43 421	82.85 410	84.52 430	71.73 406	91.69 395	91.37 415	67.63 444	46.79 481	81.21 443	55.04 400	90.43 452	55.93 448	59.70 444	86.38 426

MDA-MVSNet_test_wron		73.54 413	70.43 421	82.86 409	84.55 428	71.85 403	91.74 394	91.32 418	67.63 444	46.73 482	81.09 444	55.11 399	90.42 453	55.91 449	59.76 443	86.31 427

DSMNet-mixed		73.13 416	72.45 410	75.19 456	77.51 469	46.82 487	85.09 456	82.01 480	67.61 448	69.27 416	81.33 442	50.89 414	86.28 474	54.54 453	83.80 293	92.46 315

MIMVSNet1		69.44 434	66.65 436	77.84 443	76.48 473	62.84 458	87.42 437	88.97 443	66.96 449	57.75 470	79.72 452	32.77 475	85.83 476	46.32 473	63.42 436	84.85 443

TinyColmap		72.41 419	68.99 428	82.68 411	88.11 386	69.59 424	88.41 427	85.20 464	65.55 450	57.91 467	84.82 411	30.80 478	95.94 324	51.38 460	68.70 399	82.49 461

Anonymous20240521		72.06 423	69.91 423	78.50 442	77.11 471	61.67 463	91.62 397	90.97 425	65.52 451	62.37 449	79.05 453	36.32 465	90.96 447	57.75 440	68.52 401	82.87 455

UnsupCasMVSNet_bld		68.60 439	64.50 443	80.92 427	74.63 480	67.80 432	83.97 460	92.94 386	65.12 452	54.63 475	68.23 483	35.97 467	92.17 435	60.13 429	44.83 483	82.78 457

RPSCF		77.73 387	76.63 377	81.06 426	88.66 379	55.76 480	87.77 435	87.88 451	64.82 453	74.14 368	92.79 277	49.22 425	96.81 289	67.47 391	76.88 343	90.62 328

dongtai		69.47 433	68.98 429	70.93 459	86.87 398	58.45 472	88.19 429	93.18 379	63.98 454	56.04 472	80.17 449	70.97 257	79.24 486	33.46 486	47.94 478	75.09 480

usedtu_blend_shiyan5		77.51 390	73.93 404	88.26 308	79.74 456	80.59 212	90.76 406	89.69 435	63.21 455	70.34 405	82.14 430	57.91 373	95.15 371	77.83 297	53.77 459	89.05 367

PatchT		79.75 363	76.85 375	88.42 300	89.55 366	75.49 366	77.37 477	94.61 268	63.07 456	82.46 269	73.32 474	75.52 180	93.41 422	51.36 461	84.43 290	96.36 230

TDRefinement		69.20 437	65.78 440	79.48 434	66.04 490	62.21 460	88.21 428	86.12 461	62.92 457	61.03 457	85.61 396	33.23 473	94.16 407	55.82 450	53.02 466	82.08 465

ttmdpeth		69.58 431	66.92 435	77.54 446	75.95 477	62.40 459	88.09 430	84.32 470	62.87 458	65.70 434	86.25 388	36.53 464	88.53 462	55.65 451	46.96 481	81.70 469

OpenMVS_ROB	68.52 20	73.02 417	69.57 424	83.37 405	80.54 452	71.82 404	93.60 358	88.22 449	62.37 459	61.98 451	83.15 426	35.31 470	95.47 352	45.08 477	75.88 349	82.82 456

JIA-IIPM		79.00 372	77.20 371	84.40 393	89.74 360	64.06 452	75.30 481	95.44 212	62.15 460	81.90 279	59.08 487	78.92 103	95.59 348	66.51 400	85.78 281	93.54 307

LS3D		82.22 334	79.94 349	89.06 287	97.43 89	74.06 379	93.20 371	92.05 401	61.90 461	73.33 377	95.21 194	59.35 355	99.21 108	54.54 453	92.48 181	93.90 302

N_pmnet		61.30 446	60.20 449	64.60 467	84.32 432	17.00 508	91.67 396	10.98 506	61.77 462	58.45 466	78.55 454	49.89 422	91.83 439	42.27 481	63.94 434	84.97 442

test_0402		72.68 418	69.54 425	82.09 419	88.67 378	71.81 405	92.72 379	86.77 459	61.52 463	62.21 450	83.91 418	43.22 445	93.76 416	34.60 485	72.23 373	80.72 473

COLMAP_ROB	73.24 19	75.74 402	73.00 409	83.94 396	92.38 267	69.08 427	91.85 392	86.93 456	61.48 464	65.32 435	90.27 318	42.27 449	96.93 279	50.91 463	75.63 351	85.80 438
Johannes L. SchÃ¶nberger, Enliang Zheng, Marc Pollefeys, Jan-Michael Frahm: Pixelwise View Selection for Unstructured Multi-View Stereo. ECCV 2016
test_f		64.01 445	62.13 447	69.65 461	63.00 493	45.30 492	83.66 462	80.68 482	61.30 465	55.70 473	72.62 476	14.23 492	84.64 478	69.84 381	58.11 445	79.00 475

gg-mvs-nofinetune		85.48 274	82.90 303	93.24 93	94.51 183	85.82 50	79.22 471	96.97 49	61.19 466	87.33 189	53.01 489	90.58 7	96.07 316	86.07 214	97.23 87	97.81 123

DP-MVS		81.47 344	78.28 363	91.04 227	98.14 60	78.48 289	95.09 315	86.97 455	61.14 467	71.12 399	92.78 278	59.59 352	99.38 95	53.11 457	86.61 268	95.27 270

pmmvs6		74.65 407	71.67 414	83.60 403	79.13 463	69.94 420	93.31 368	90.88 427	61.05 468	65.83 432	84.15 416	43.43 443	94.83 389	66.62 397	60.63 442	86.02 433

Patchmtry		77.36 392	74.59 396	85.67 369	89.75 358	75.75 363	77.85 476	91.12 420	60.28 469	71.23 396	80.35 447	75.45 181	93.56 419	57.94 438	67.34 415	87.68 406

CMPMVS	54.94 21	75.71 403	74.56 397	79.17 437	79.69 459	55.98 477	89.59 415	93.30 374	60.28 469	53.85 476	89.07 334	47.68 433	96.33 307	76.55 321	81.02 315	85.22 440
M. Jancosek, T. Pajdla: Multi-View Reconstruction Preserving Weakly-Supported Surfaces. CVPR 2011
Anonymous20240529		83.15 317	80.60 338	90.80 237	95.74 134	78.27 298	96.81 186	94.92 240	60.10 471	81.89 280	92.54 279	45.82 438	98.82 139	79.25 288	78.32 339	95.31 267

Patchmatch-test		78.25 380	74.72 395	88.83 293	91.20 320	74.10 378	73.91 484	88.70 448	59.89 472	66.82 426	85.12 407	78.38 113	94.54 399	48.84 470	79.58 325	97.86 117

WB-MVS		57.26 447	56.22 450	60.39 473	69.29 484	35.91 500	86.39 447	70.06 493	59.84 473	46.46 483	72.71 475	51.18 413	78.11 487	15.19 496	34.89 492	67.14 486

Anonymous20231211		79.72 364	77.19 372	87.33 339	95.59 141	77.16 336	95.18 307	94.18 311	59.31 474	72.57 385	86.20 389	47.89 431	95.66 341	74.53 348	69.24 396	89.18 361

ANet_high		46.22 456	41.28 463	61.04 472	39.91 504	46.25 490	70.59 488	76.18 488	58.87 475	23.09 496	48.00 493	12.58 495	66.54 496	28.65 490	13.62 497	70.35 482

RPMNet		79.85 362	75.92 382	91.64 200	90.16 348	79.75 246	79.02 473	95.44 212	58.43 476	82.27 275	72.55 477	73.03 223	98.41 163	46.10 474	86.25 272	96.75 220

SSC-MVS		56.01 450	54.96 451	59.17 474	68.42 486	34.13 501	84.98 457	69.23 494	58.08 477	45.36 484	71.67 481	50.30 421	77.46 488	14.28 497	32.33 493	65.91 487

new_pmnet		66.18 442	63.18 444	75.18 457	76.27 475	61.74 462	83.79 461	84.66 467	56.64 478	51.57 478	71.85 480	31.29 477	87.93 465	49.98 466	62.55 438	75.86 479

test_vis3_rt		54.10 452	51.04 455	63.27 470	58.16 494	46.08 491	84.17 459	49.32 505	56.48 479	36.56 489	49.48 492	8.03 500	91.91 438	67.29 392	49.87 472	51.82 491

pmmvs3		65.75 443	62.18 446	76.45 452	67.12 489	64.54 448	88.68 425	85.05 466	54.77 480	57.54 471	73.79 471	29.40 481	86.21 475	55.49 452	47.77 479	78.62 476

usedtu_dtu_shiyan2		64.65 444	60.40 448	77.38 447	64.24 491	57.84 474	89.16 421	87.60 453	52.95 481	53.43 477	71.31 482	23.41 484	88.27 463	51.95 459	49.58 473	86.03 432

sc_t1		72.37 420	68.03 431	85.39 375	83.78 440	70.51 415	91.27 400	83.70 475	52.46 482	68.29 418	82.02 436	30.58 479	94.81 390	64.50 409	55.69 450	90.85 327

tt0320-xc		69.70 430	65.27 442	82.99 408	84.33 431	71.92 402	89.56 418	82.08 479	50.11 483	61.87 453	77.50 457	30.48 480	92.34 430	60.30 428	51.20 470	84.71 444

MVStest1		66.93 441	63.01 445	78.69 439	78.56 464	71.43 410	85.51 453	86.81 457	49.79 484	48.57 480	84.15 416	53.46 407	83.31 480	43.14 480	37.15 491	81.34 472

tt0320		70.21 429	66.07 437	82.64 412	83.42 443	70.82 413	89.63 414	84.10 471	49.75 485	62.71 448	77.28 460	33.35 472	92.45 429	58.78 436	55.62 451	84.64 445

MVS-HIRNet		71.36 427	67.00 433	84.46 392	90.58 337	69.74 423	79.15 472	87.74 452	46.09 486	61.96 452	50.50 490	45.14 439	95.64 344	53.74 455	88.11 254	88.00 401

PMMVS2		50.90 455	46.31 458	64.67 466	55.53 496	46.67 488	77.30 478	71.02 492	40.89 487	34.16 491	59.32 486	9.83 498	76.14 492	40.09 484	28.63 494	71.21 481

APD_test1		56.56 449	53.58 453	65.50 464	67.93 488	46.51 489	77.24 479	72.95 490	38.09 488	42.75 486	75.17 467	13.38 493	82.78 483	40.19 483	54.53 454	67.23 485

FPMVS		55.09 451	52.93 454	61.57 471	55.98 495	40.51 496	83.11 464	83.41 477	37.61 489	34.95 490	71.95 478	14.40 491	76.95 489	29.81 488	65.16 429	67.25 484

LCM-MVSNet		52.52 453	48.24 456	65.35 465	47.63 502	41.45 494	72.55 485	83.62 476	31.75 490	37.66 488	57.92 488	9.19 499	76.76 490	49.26 468	44.60 484	77.84 477

Gipuma		45.11 459	42.05 461	54.30 477	80.69 450	51.30 484	35.80 495	83.81 474	28.13 491	27.94 495	34.53 495	11.41 497	76.70 491	21.45 493	54.65 453	34.90 495
S. Galliani, K. Lasinger, K. Schindler: Massively Parallel Multiview Stereopsis by Surface Normal Diffusion. ICCV 2015
testf1		45.70 457	42.41 459	55.58 475	53.29 499	40.02 497	68.96 489	62.67 499	27.45 492	29.85 492	61.58 484	5.98 501	73.83 494	28.49 491	43.46 486	52.90 489

APD_test2		45.70 457	42.41 459	55.58 475	53.29 499	40.02 497	68.96 489	62.67 499	27.45 492	29.85 492	61.58 484	5.98 501	73.83 494	28.49 491	43.46 486	52.90 489

PMVS	34.80 23	39.19 461	35.53 464	50.18 478	29.72 505	30.30 503	59.60 493	66.20 498	26.06 494	17.91 498	49.53 491	3.12 503	74.09 493	18.19 495	49.40 474	46.14 492
Y. Furukawa, J. Ponce: Accurate, dense, and robust multiview stereopsis. PAMI (2010)
E-PMN		32.70 463	32.39 465	33.65 481	53.35 498	25.70 505	74.07 483	53.33 503	21.08 495	17.17 499	33.63 497	11.85 496	54.84 499	12.98 498	14.04 496	20.42 496

EMVS		31.70 464	31.45 466	32.48 482	50.72 501	23.95 506	74.78 482	52.30 504	20.36 496	16.08 500	31.48 498	12.80 494	53.60 500	11.39 499	13.10 499	19.88 497

test_method		56.77 448	54.53 452	63.49 469	76.49 472	40.70 495	75.68 480	74.24 489	19.47 497	48.73 479	71.89 479	19.31 487	65.80 497	57.46 442	47.51 480	83.97 451

MVE	35.65 22	33.85 462	29.49 467	46.92 479	41.86 503	36.28 499	50.45 494	56.52 502	18.75 498	18.28 497	37.84 494	2.41 504	58.41 498	18.71 494	20.62 495	46.06 493
Simon Fuhrmann, Fabian Langguth, Michael Goesele: MVE - A Multi-View Reconstruction Environment. EUROGRAPHICS Workshops on Graphics and Cultural Heritage (2014)
tmp_tt		41.54 460	41.93 462	40.38 480	20.10 506	26.84 504	61.93 492	59.09 501	14.81 499	28.51 494	80.58 445	35.53 468	48.33 501	63.70 415	13.11 498	45.96 494

wuyk23d		14.10 466	13.89 469	14.72 483	55.23 497	22.91 507	33.83 496	3.56 507	4.94 500	4.11 501	2.28 503	2.06 505	19.66 502	10.23 500	8.74 500	1.59 500

testmvs		9.92 467	12.94 470	0.84 485	0.65 507	0.29 510	93.78 353	0.39 508	0.42 501	2.85 502	15.84 501	0.17 507	0.30 504	2.18 501	0.21 501	1.91 499

test123		9.07 468	11.73 471	1.11 484	0.50 508	0.77 509	89.44 419	0.20 509	0.34 502	2.15 503	10.72 502	0.34 506	0.32 503	1.79 502	0.08 502	2.23 498

EGC-MVSNET		52.46 454	47.56 457	67.15 463	81.98 447	60.11 468	82.54 465	72.44 491	0.11 503	0.70 504	74.59 469	25.11 483	83.26 481	29.04 489	61.51 441	58.09 488

mmdepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

monomultidepth		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

test_blank		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet_test		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

DCPMVS		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

cdsmvs_eth3d_5k		21.43 465	28.57 468	0.00 486	0.00 509	0.00 511	0.00 497	95.93 179	0.00 504	0.00 505	97.66 94	63.57 323	0.00 505	0.00 503	0.00 503	0.00 501

pcd_1.5k_mvsjas		5.92 470	7.89 473	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	71.04 254	0.00 505	0.00 503	0.00 503	0.00 501

sosnet-low-res		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

sosnet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uncertanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

Regformer		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

ab-mvs-re		8.11 469	10.81 472	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	97.30 117	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

uanet		0.00 471	0.00 474	0.00 486	0.00 509	0.00 511	0.00 497	0.00 510	0.00 504	0.00 505	0.00 504	0.00 508	0.00 505	0.00 503	0.00 503	0.00 501

WAC-MVS						67.18 436								49.00 469

MSC_two_6792asdad				97.14 4	99.05 14	92.19 4		96.83 62					99.81 28	98.08 26	98.81 24	99.43 12

No_MVS				97.14 4	99.05 14	92.19 4		96.83 62					99.81 28	98.08 26	98.81 24	99.43 12

eth-test2					0.00 509

eth-test					0.00 509

OPU-MVS				97.30 2	99.19 8	92.31 3	99.12 16				98.54 30	92.06 3	99.84 18	99.11 5	99.37 1	99.74 1

test_0728_SECOND				95.14 21	99.04 19	86.14 43	99.06 23	96.77 72					99.84 18	97.90 30	98.85 21	99.45 11

GSMVS																97.54 149

test_part2					98.90 24	85.14 77				96.07 43

sam_mvs1												77.59 128				97.54 149

sam_mvs												75.35 188

ambc				76.02 453	68.11 487	51.43 483	64.97 491	89.59 436		60.49 458	74.49 470	17.17 489	92.46 427	61.50 423	52.85 467	84.17 450

MTGPA								96.33 140

test_post1							85.88 450				30.24 499	73.77 213	95.07 381	73.89 352

test_post											33.80 496	76.17 163	95.97 320

patchmatchnet-post											77.09 463	77.78 126	95.39 354

GG-mvs-BLEND				93.49 84	94.94 166	86.26 39	81.62 466	97.00 44		88.32 172	94.30 237	91.23 6	96.21 313	88.49 188	97.43 79	98.00 104

MTMP							97.53 118	68.16 496

test9_res														96.00 57	99.03 13	98.31 76

agg_prior2														94.30 81	99.00 15	98.57 60

agg_prior					98.59 40	83.13 122		96.56 106		94.19 73			99.16 117

test_prior4						82.34 146	97.75 100

test_prior				93.09 102	98.68 31	81.91 162		96.40 129					99.06 125			98.29 78

新几何2							96.42 219

旧先验1					97.39 93	79.58 254		96.54 110			98.08 70	84.00 53			97.42 80	97.62 142

原ACMM2							96.84 181

testdata2													99.48 90	76.45 323

segment_acmp												82.69 67

test12				94.25 44	98.34 51	85.55 61		96.35 139		92.36 100		80.84 75	99.22 107		98.31 52	97.98 106

plane_prior7					91.86 305	77.55 327

plane_prior6					91.98 300	77.92 313						64.77 315

plane_prior5								94.69 258					97.30 249	87.08 204	82.82 304	90.96 324

plane_prior4											94.15 245

plane_prior1					91.95 302

n2								0.00 510

nn								0.00 510

door-mid								79.75 484

lessismore_v0				79.98 432	80.59 451	58.34 473		80.87 481		58.49 465	83.46 422	43.10 446	93.89 412	63.11 418	48.68 475	87.72 404

test11								96.50 116

door								80.13 483

HQP5-MVS						78.48 289

BP-MVS														87.67 200

HQP4-MVS										82.30 271			97.32 247			91.13 322

HQP3-MVS								94.80 249							83.01 300

HQP2-MVS												65.40 308

NP-MVS					92.04 297	78.22 300					94.56 228

ACMMP++_ref															78.45 337

ACMMP++															79.05 329

Test By Simon												71.65 246

High-resolution multi-view benchmark