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

• URL: http://arxiv.org/abs/2603.17408v1
• Date: Wed, 18 Mar 2026 06:35:53 GMT
• Title: Joint Degradation-Aware Arbitrary-Scale Super-Resolution for Variable-Rate Extreme Image Compression
• Abstract summary: ASSR-EIC is a novel image compression framework that supports variable-rate extreme image compression.<n>We exploit the compression- and rescaling-aware diffusion prior to guide the reconstruction, yielding high fidelity and high realism restoration.
• Score: 28.21479870337623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compression [46.54433210034761]
  SPRDiff is a diffusion-based compression method that fully leverages both semantic and pixel representations.<n>We develop a triple-encoder architecture that utilizes high-fidelity features from the pretrained distortion-oriented and semantic-oriented encoders.<n>Experiments on benchmark datasets demonstrate that our method outperforms state-of-the-art approaches in the rate-distortion-perception tradeoff.
  arXiv  Detail & Related papers  (2026-06-01T02:59:31Z)
• Rethinking Autoregressive Models for Lossless Image Compression via Hierarchical Parallelism and Progressive Adaptation [75.58269386927076]
  Autoregressive (AR) models are often dismissed as impractical due to prohibitive computational cost.<n>This work re-thinks this paradigm, introducing a framework built on hierarchical parallelism and progressive adaptation.<n> Experiments on diverse datasets (natural, satellite, medical) validate that our method achieves new state-of-the-art compression.
  arXiv  Detail & Related papers  (2025-11-14T06:27:58Z)
• SANR: Scene-Aware Neural Representation for Light Field Image Compression with Rate-Distortion Optimization [54.184486302645716]
  We propose a Scene-Aware Neural Representation framework for light field image compression with end-to-end rate-distortion optimization.<n>For scene awareness, SANR introduces a hierarchical scene modeling block that leverages multi-scale latent codes to capture intrinsic scene structures.<n>Experiment results demonstrate that SANR significantly outperforms state-of-the-art techniques regarding rate-distortion performance with a 65.62% BD-rate saving against HEVC.
  arXiv  Detail & Related papers  (2025-10-17T16:00:43Z)
• COLI: A Hierarchical Efficient Compressor for Large Images [18.697445453003983]
  Implicit Neural Representations (INRs) present a promising alternative by learning continuous mappings from spatial coordinates to pixel intensities for individual images.<n>We introduce COLI (Compressor for Large Images), a novel framework leveraging Neural Representations for Videos (NeRV)<n>We show that COLI consistently achieves competitive or superior PSNR and SSIM metrics at significantly reduced bits per pixel (bpp) while accelerating NeRV training by up to 4 times.
  arXiv  Detail & Related papers  (2025-07-15T16:07:07Z)
• Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model [55.2480439325792]
  We propose a hybrid compression scheme optimized for perceptual quality, extending the approach of the CDC model with a decoder network.<n>We achieve up to +2dB PSNR fidelity improvements while maintaining comparable LPIPS and FID perceptual scores when compared with CDC.
  arXiv  Detail & Related papers  (2025-05-19T14:13:14Z)
• Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusion [28.61304513668606]
  ResULIC is a residual-guided ultra lowrate image compression system.<n>It incorporates residual signals into both semantic retrieval and the diffusion-based generation process.<n>It achieves superior objective and subjective performance compared to state-of-the-art diffusion-based methods.
  arXiv  Detail & Related papers  (2025-05-13T06:51:23Z)
• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations.<n> Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations.<n> Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptation [52.82508784748278]
  This paper proposes a Control Generative Image Compression framework, termed Control-GIC.<n>Control-GIC is capable of fine-grained adaption across a broad spectrum while ensuring high-fidelity and generality compression.<n>Our experiments show that Control-GIC allows highly flexible and controllable adaption where the results demonstrate its superior performance over recent state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-06-02T14:22:09Z)
• Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion [24.812267280543693]
  We propose an adaptive downsampled dual-layer (ADDL) image compression system. In the ADDL compression system, an image is reduced in resolution by learned content-adaptive downsampling kernels and compressed to form a coded base layer. For decompression the base layer is decoded and upconverted to the original resolution using a deep upsampling neural network.
  arXiv  Detail & Related papers  (2023-02-13T04:36:13Z)
• Improving Multi-generation Robustness of Learned Image Compression [16.86614420872084]
  We show that LIC can achieve comparable performance to the first compression of BPG even after 50 times reencoding without any change of the network structure.
  arXiv  Detail & Related papers  (2022-10-31T03:26:11Z)
• Learned Image Compression with Generalized Octave Convolution and Cross-Resolution Parameter Estimation [5.238765582868391]
  We propose a learned multi-resolution image compression framework, which exploits octave convolutions to factorize the latent representations into the high-resolution (HR) and low-resolution (LR) parts. Experimental results show that our method separately reduces the decoding time by approximately 73.35 % and 93.44 % compared with that of state-of-the-art learned image compression methods.
  arXiv  Detail & Related papers  (2022-09-07T08:21:52Z)
• Learned Video Compression via Heterogeneous Deformable Compensation Network [78.72508633457392]
  We propose a learned video compression framework via heterogeneous deformable compensation strategy (HDCVC) to tackle the problems of unstable compression performance. More specifically, the proposed algorithm extracts features from the two adjacent frames to estimate content-Neighborhood heterogeneous deformable (HetDeform) kernel offsets. Experimental results indicate that HDCVC achieves superior performance than the recent state-of-the-art learned video compression approaches.
  arXiv  Detail & Related papers  (2022-07-11T02:31:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.