2025
On Disentangled Training for Nonlinear Transform in Learned Image Compression
ICLR 2025spotlight
Learned image compression (LIC) has demonstrated superior rate-distortion (R-D) performance compared to traditional codecs, but is challenged by training inefficiency that could incur more than two weeks to train a state-of-the-art model from scratch. Existing LIC methods overlook the slow convergen…