eess.IVNov 6, 2026

Noise-Regularized Training for Learned Image Compression

Authors: Renjie Zou, Zhiwei Huang, Dong Jiang

Organizations: Malanshan Audio & Video Laboratory

Abstract

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% on a reproduced ELIC and -0.85% / -1.05% / -2.38% on the Base/Medium/Large scales of a variable-rate DMCI codec, with DMCI-Large reaching -22.02% against VTM-22.0. A second-order expansion of the noisy RD loss accounts for these gains: because the noise enters upstream of the analysis transform, it converts the clean RD objective into a structured O(σ2)O(σ^{2}) regularizer comprising an information-weighted encoder-Jacobian penalty (rate side) and a Frobenius contractive penalty on the end-to-end reconstruction map (distortion side). A finite-difference Lipschitz analysis shows corresponding sensitivity reductions of ~12% for the encoder and ~8% for the end-to-end codec, while an exact-JVP test further shows preferential contraction of high-information directions. Code and trained models are available at https://github.com/Googolxx/NoiseRegu-LIC.

Figures & tables

Appendix figures & tables7 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Efficient Learned Image Compression without Entropy Coding

    May 22, 2026Hao Cao, Wenqi Guo, Zhijin Qin +1Learned Image CompressionVector Quantization

  2. Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression

    May 9, 2026Jiaming Liang, Chi-Man Pun, Weisi Lin +1Learned Image CompressionAdversarial Attacks

  3. Channel-Level Mask Guidance for Slimmable Image Compression

    Oct 19, 2026Chen Chen, Chenggang Wu, Yongbiao Chen +3Channel PruningLearned Image Compression