# Learned Image Downscaling for Upscaling using Content Adaptive Resampler

## TL;DR

This paper introduces a content adaptive resampling method for image downscaling that, when combined with deep super-resolution models, significantly improves the quality of upscaled images by preserving essential details.

## Contribution

It proposes a novel learned downscaling approach using content adaptive resampler networks that enhance super-resolution performance.

## Key findings

- Achieves state-of-the-art super-resolution results.
- Generated LR images are comparable to traditional interpolation methods.
- Joint training of downscaling and super-resolution models improves detail preservation.

## Abstract

Deep convolutional neural network based image super-resolution (SR) models have shown superior performance in recovering the underlying high resolution (HR) images from low resolution (LR) images obtained from the predefined downscaling methods. In this paper we propose a learned image downscaling method based on content adaptive resampler (CAR) with consideration on the upscaling process. The proposed resampler network generates content adaptive image resampling kernels that are applied to the original HR input to generate pixels on the downscaled image. Moreover, a differentiable upscaling (SR) module is employed to upscale the LR result into its underlying HR counterpart. By back-propagating the reconstruction error down to the original HR input across the entire framework to adjust model parameters, the proposed framework achieves a new state-of-the-art SR performance through upscaling guided image resamplers which adaptively preserve detailed information that is essential to the upscaling. Experimental results indicate that the quality of the generated LR image is comparable to that of the traditional interpolation based method, but the significant SR performance gain is achieved by deep SR models trained jointly with the CAR model. The code is publicly available on: URL https://github.com/sunwj/CAR.