Image Super-Resolution Using Deep Convolutional Networks

Chao Dong1, Chen Change Loy1, Kaiming He2, Xiaoou Tang1
1Department of Information Engineering, The Chinese University of Hong Kong, Hong Kong, China
2Microsoft Research Asia, Beijing, China

Tóm tắt

Từ khóa


Tài liệu tham khảo

10.1109/ICCV.2013.241

sun, 0, Deep learning face representation by joint identification-verification, Proc Adv Neural Inf Process Syst, 1988

ouyang, 0, Deepid-net: Deformable deep convolutional neural networks for object detection

nair, 0, Rectified linear units improve restricted Boltzmann machines, Proc Int Conf Mach Learn, 807

10.1109/ICCV.2001.937655

mamalet, 0, Simplifying convNets for fast learning, Proc Int Conf Artif Neural Netw, 58

10.1109/TIP.2005.859389

10.1109/CVPR.2015.7299003

10.1109/CVPR.2013.142

10.1109/ICCV.2013.257

lee, 0, Efficient sparse coding algorithms, Proc Adv Neural Inf Process Syst, 801

10.1109/5.726791

10.1007/s11263-006-0029-5

bevilacqua, 0, Proc Brit Mach Vis Conf, 1

aharon, 2006, K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation, IEEE Trans Signal Process, 54, 4311, 10.1109/TSP.2006.881199

10.1016/1049-9652(91)90045-L

10.1109/TPAMI.2012.95

jain, 0, Natural image denoising with convolutional networks, Proc Adv Neural Inf Process Syst, 769

kim, 0, Single-image super-resolution using sparse regression and natural image prior, IEEE Trans Pattern Anal Mach Intell, 32, 1127

10.1145/2647868.2654889

10.1162/neco.1989.1.4.541

krizhevsky, 0, ImageNet classification with deep convolutional neural networks, Proc Adv Neural Inf Process Syst, 1097

zhang, 0, Part-based R-CNNs for fine-grained category detection, Proc Eur Conf Comput Vis, 834

denton, 0, Exploiting linear structure within convolutional networks for efficient evaluation, Proc Adv Neural Inf Process Syst, 1269

dong, 0, Learning a deep convolutional network for image super-resolution, Proc Eur Conf Comput Vis, 184

timofte, 0, A+: Adjusted anchored neighborhood regression for fast super-resolution, Proc Asian Conf Comput Vis, 111

10.1109/ICCV.2013.84

freedman, 2011, Image and video upscaling from local self-examples, ACM Trans Graph, 30, 12, 10.1145/1944846.1944852

10.1109/38.988747

10.1023/A:1026501619075

10.1109/ICCV.2009.5459271

he, 0, Convolutional neural networks at constrained time cost

he, 0, Spatial pyramid pooling in deep convolutional networks for visual recognition, Proc Eur Conf Comput Vis, 346

b, 0, Single image super-resolution from transformed self-exemplars, Proc IEEE Conf Comput Vis Pattern Recog, 5197

10.1109/CVPR.2004.1315043

10.1109/CVPR.2012.6247952

10.1111/cgf.12544

cui, 0, Deep network cascade for image super-resolution, Proc Eur Conf Comput Vis

10.1109/83.841940

dai, 0, Softcuts: A soft edge smoothness prior for color image super-resolution, IEEE Trans Image Process, 18, 969

zeyde, 0, On single image scale-up using sparse-representations, Proc 7th Int Conf Curves Surfaces, 711

deng, 0, ImageNet: A large-scale hierarchical image database, Proc IEEE Conf Comput Vis Pattern Recog, 248

10.1109/TIP.2012.2192127

10.1109/CVPR.2013.141

10.1109/TIP.2010.2050625

yang, 0, Image super-resolution as sparse representation of raw image patches, Proc IEEE Conf Comput Vis Pattern Recog, 1

10.1109/ACSSC.2003.1292216

10.1109/TIP.2003.819861

yang, 0, Single-image super-resolution: A benchmark, Proc Eur Conf Comput Vis, 372

yang, 0, Exploiting self-similarities for single frame super-resolution, Proc Asian Conf Comput Vis, 497