Vector-quantized Image Modeling with Improved VQGAN
2021 · arXiv (Cornell University) · 92 citations
https://doi.org/10.48550/arxiv.2110.04627
X
Xin Li
Claim or correct this author profile
Claim this profile or suggest corrections to the name, affiliation, bio, photo, or paper titles. Approved changes appear as verified CitedEvidence overlays.
124
Papers
2.2K
Citations
21
h-index
36
i10-index
Xin Li is an academic researcher from Beijing Language and Culture University. The author has contributed to research in topics: Advanced Image Processing Techniques & Image and Signal Denoising Methods & Advanced Vision and Imaging. The author has an h-index of 21, co-authored 106 publications.
ORCID: 0000-0002-6352-6523Papers by this author
worksLearned Block-Based Hybrid Image Compression
2021 · IEEE Transactions on Circuits and Systems for Video Technology · 63 citations
https://doi.org/10.1109/tcsvt.2021.3119660
Task-Driven Semantic Coding via Reinforcement Learning
2021 · IEEE Transactions on Image Processing · 53 citations
https://doi.org/10.1109/tip.2021.3091909
MoE-DiffIR: Task-Customized Diffusion Priors for Universal Compressed Image Restoration
2024 · Lecture notes in computer science · 6 citations
https://doi.org/10.1007/978-3-031-72673-6_7
Research topics
topicsChat about Author
Papers
Chat
Click to start Chat