Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression

2026-03-18

AI Summary

This work proposes ASSR-EIC, a novel framework for extreme image compression that integrates arbitrary-scale super-resolution with diffusion models to address the limitations of existing methods, which require separate models for each target bitrate and struggle with severe information loss under fixed-scale reconstruction. ASSR-EIC introduces a joint degradation-aware diffusion-based super-resolution decoder within a single model, enabling variable bitrate compression and adaptive reconstruction. The framework incorporates a global compression-rescaling adapter and a local modulator to facilitate bitrate-adaptive detail recovery, along with a dual semantic enhancement mechanism to improve reconstruction fidelity. Experimental results demonstrate that ASSR-EIC achieves state-of-the-art performance in extreme compression tasks while supporting flexible bitrate control and highly realistic image reconstruction.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Recent diffusion-based extreme image compression methods have demonstrated remarkable performance at ultra-low bitrates. However, most approaches require training separate diffusion models for each target bitrate, resulting in substantial computational overhead and hindering practical deployment. Meanwhile, recent studies have shown that joint super-resolution can serve as an effective approach for enhancing low-bitrate reconstruction. However, when moving toward ultra-low bitrate regimes, these methods struggle due to severe information loss, and their reliance on fixed super-resolution scales prevents flexible adaptation across diverse bitrates. To address these limitations, we propose ASSR-EIC, a novel image compression framework that leverages arbitrary-scale super-resolution (ASSR) to support variable-rate extreme image compression (EIC). An arbitrary-scale downsampling module is introduced at the encoder side to provide controllable rate reduction, while a diffusion-based, joint degradation-aware ASSR decoder enables rate-adaptive reconstruction within a single model. We exploit the compression- and rescaling-aware diffusion prior to guide the reconstruction, yielding high fidelity and high realism restoration across diverse compression and rescaling settings. Specifically, we design a global compression-rescaling adaptor that offers holistic guidance for rate adaptation, and a local compression-rescaling modulator that dynamically balances generative and fidelity-oriented behaviors to achieve fine-grained, bitrate-adaptive detail restoration. To further enhance reconstruction quality, we introduce a dual semantic-enhanced design. Extensive experiments demonstrate that ASSR-EIC delivers state-of-the-art performance in extreme image compression while simultaneously supporting flexible bitrate control and adaptive rate-dependent reconstruction.

Problem

• extreme image compression
• variable-rate compression
• arbitrary-scale super-resolution
• joint degradation-aware reconstruction
• ultra-low bitrate

Innovation

• arbitrary-scale super-resolution
• extreme image compression
• diffusion-based reconstruction
• joint degradation-aware
• variable-rate adaptation