Region-Adaptive Generative Compression with Spatially Varying Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908931471704064 |
|---|---|
| author | Relic, Lucas Azevedo, Roberto Zhang, Yang Mandt, Stephan Gross, Markus Schroers, Christopher |
| author_facet | Relic, Lucas Azevedo, Roberto Zhang, Yang Mandt, Stephan Gross, Markus Schroers, Christopher |
| contents | Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tendency to focus on particular aspects of a visual scene (e.g., salient objects) while giving less importance to other regions. An ideal perceptual codec should be able to exploit this property by allocating more representational capacity to perceptually important areas. To this end, we propose a region-adaptive diffusion-based image codec that supports non-uniform bit allocation within an image. We design a novel spatially varying diffusion model capable of denoising varying amounts of noise per pixel according to arbitrary importance maps. We further identify that these maps can serve as effective priors on the latent representation, and integrate them into our entropy model, improving rate-distortion performance. Built on these contributions, our spatially-adaptive diffusion-based codec outperforms state-of-the-art ROI-controllable baselines in both full-image and ROI-masked perceptual quality. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01122 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Region-Adaptive Generative Compression with Spatially Varying Diffusion Models Relic, Lucas Azevedo, Roberto Zhang, Yang Mandt, Stephan Gross, Markus Schroers, Christopher Image and Video Processing Generative image codecs aim to optimize perceptual quality, producing realistic and detailed reconstructions. However, they often overlook a key property of human vision: our tendency to focus on particular aspects of a visual scene (e.g., salient objects) while giving less importance to other regions. An ideal perceptual codec should be able to exploit this property by allocating more representational capacity to perceptually important areas. To this end, we propose a region-adaptive diffusion-based image codec that supports non-uniform bit allocation within an image. We design a novel spatially varying diffusion model capable of denoising varying amounts of noise per pixel according to arbitrary importance maps. We further identify that these maps can serve as effective priors on the latent representation, and integrate them into our entropy model, improving rate-distortion performance. Built on these contributions, our spatially-adaptive diffusion-based codec outperforms state-of-the-art ROI-controllable baselines in both full-image and ROI-masked perceptual quality. |
| title | Region-Adaptive Generative Compression with Spatially Varying Diffusion Models |
| topic | Image and Video Processing |
| url | https://arxiv.org/abs/2604.01122 |