ChatsYapsForumsTopicsWatchFeedsDecksChartsChatsYapsForumsTopicsWatchFeedsDecksCharts
Log inRegister

Log in to follow channels.

Log in to follow topics.

Log in to see your friends.

software

Forum post

Noise-Regularized Training for Learned Image Compression

·1w

arXiv.org

Noise-Regularized Training for Learned Image Compression

Learned image compression (LIC) is trained almost exclusively on clean images: the only stochastic perturbation in the loop is an additive uniform proxy injected in the latent domain to keep the entropy model differentiable. Outside compression, by contrast, a long line of work---from Tikhonov regularization and contractive autoencoders through denoising score matching and modern diffusion models---has established that Gaussian noise at the input of a network with a clean target acts as a structured probe of the data manifold rather than as data augmentation. Building on this view, we introduce noise-regularized training for LIC: at every training step we add Gaussian noise to the encoder input while keeping the distortion target, the latent uniform proxy, the hyperprior, and the entropy coding pipeline unchanged. The recipe is architecture-agnostic and adds essentially no training or inference overhead. Across backbones and operating regimes it yields consistent BD-Rate gains: -2.60%

1

0 comments