Search Results for author:
Found 2 papers, 2 papers with code
Controlling Rate, Distortion, and Realism: Towards a Single Comprehensive Neural Image Compression Model
A critical obstacle of these generative NIC methods is that each model is optimized for a single bit rate.
Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networks
To address both of the drawbacks, our method adopts two-stage training and network interpolation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
