Scale-arbitrary Invertible Image Downscaling

TL;DR

This paper introduces AIDN, a novel invertible image downscaling network capable of handling arbitrary scale factors, preserving high-resolution details and enabling accurate restoration of original images, thus addressing limitations of fixed-scale methods.

Contribution

The proposed AIDN is the first to support scale-arbitrary invertible image downscaling, embedding HR information in LR images for flexible resolution control.

Findings

Achieves top performance on invertible downscaling tasks.

Supports both integer and non-integer scale factors.

Maintains nearly imperceptible HR information in LR images.

Abstract

Conventional social media platforms usually downscale the HR images to restrict their resolution to a specific size for saving transmission/storage cost, which leads to the super-resolution (SR) being highly ill-posed. Recent invertible image downscaling methods jointly model the downscaling/upscaling problems and achieve significant improvements. However, they only consider fixed integer scale factors that cannot downscale HR images with various resolutions to meet the resolution restriction of social media platforms. In this paper, we propose a scale-Arbitrary Invertible image Downscaling Network (AIDN), to natively downscale HR images with arbitrary scale factors. Meanwhile, the HR information is embedded in the downscaled low-resolution (LR) counterparts in a nearly imperceptible form such that our AIDN can also restore the original HR images solely from the LR images. The key to supporting arbitrary scale factors is our proposed Conditional Resampling Module (CRM) that conditions the downscaling/upscaling kernels and sampling locations on both scale factors and image content. Extensive experimental results demonstrate that our AIDN achieves top performance for invertible downscaling with both arbitrary integer and non-integer scale factors. Code will be released upon publication.