arXiv Open Access 2019

Deep Residual Learning for Image Compression

Zhengxue Cheng Heming Sun Masaru Takeuchi Jiro Katto
Lihat Sumber

Abstrak

In this paper, we provide a detailed description on our approach designed for CVPR 2019 Workshop and Challenge on Learned Image Compression (CLIC). Our approach mainly consists of two proposals, i.e. deep residual learning for image compression and sub-pixel convolution as up-sampling operations. Experimental results have indicated that our approaches, Kattolab, Kattolabv2 and KattolabSSIM, achieve 0.972 in MS-SSIM at the rate constraint of 0.15bpp with moderate complexity during the validation phase.

Topik & Kata Kunci

Penulis (4)

Z

Zhengxue Cheng

H

Heming Sun

M

Masaru Takeuchi

J

Jiro Katto

Format Sitasi

Cheng, Z., Sun, H., Takeuchi, M., Katto, J. (2019). Deep Residual Learning for Image Compression. https://arxiv.org/abs/1906.09731

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2019
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓