English

TLIC: Learned Image Compression with ROI-Weighted Distortion and Bit Allocation

Computer Vision and Pattern Recognition 2024-03-26 v3 Image and Video Processing

Abstract

This short paper describes our method for the track of image compression. To achieve better perceptual quality, we use the adversarial loss to generate realistic textures, use region of interest (ROI) mask to guide the bit allocation for different regions. Our Team name is TLIC.

Keywords

Cite

@article{arxiv.2401.08154,
  title  = {TLIC: Learned Image Compression with ROI-Weighted Distortion and Bit Allocation},
  author = {Wei Jiang and Yongqi Zhai and Hangyu Li and Ronggang Wang},
  journal= {arXiv preprint arXiv:2401.08154},
  year   = {2024}
}

Comments

2nd Place in the Image Compression Track, CLIC 2024, DCC 2024

R2 v1 2026-06-28T14:17:43.871Z