FLLIC: Functionally Lossless Image Compression

2024-01-24

arXiv.org

AI Summary

Conventional lossless image compression methods, such as PNG, suffer from low coding efficiency on real-world noisy images (e.g., captured by smartphones or digital cameras), as they preserve sensor noise unnecessarily. Method: This paper proposes Functionally Lossless Image Compression (FLLIC), a novel paradigm that abandons strict mathematical losslessness and instead defines “functional losslessness” as preserving downstream visual task performance (e.g., classification, detection) while actively removing acquisition noise through joint denoising and compression. We design an end-to-end deep neural network integrating learnable rate-distortion optimization with task-aware fidelity constraints. Results: FLLIC achieves state-of-the-art joint denoising-compression performance across diverse noise levels, significantly reducing bitrates compared to mathematical lossless codecs (e.g., PNG) while incurring lower inference latency—demonstrating both high efficiency and practical deployability.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Learning & Optimization for CV
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

Recently, DNN models for lossless image coding have surpassed their traditional counterparts in compression performance, reducing the previous lossless bit rate by about ten percent for natural color images. But even with these advances, mathematically lossless image compression (MLLIC) ratios for natural images still fall short of the bandwidth and cost-effectiveness requirements of most practical imaging and vision systems at present and beyond. To overcome the performance barrier of MLLIC, we question the very necessity of MLLIC. Considering that all digital imaging sensors suffer from acquisition noises, why should we insist on mathematically lossless coding, i.e., wasting bits to preserve noises? Instead, we propose a new paradigm of joint denoising and compression called functionally lossless image compression (FLLIC), which performs lossless compression of optimally denoised images (the optimality may be task-specific). Although not literally lossless with respect to the noisy input, FLLIC aims to achieve the best possible reconstruction of the latent noise-free original image. Extensive experiments show that FLLIC achieves state-of-the-art performance in joint denoising and compression of noisy images and does so at a lower computational cost.

Problem

• Image compression
• Noise reduction
• Efficiency improvement

Innovation

• FLLIC
• Noise Reduction
• Energy Efficiency