# Block-Based Multi-Scale Image Rescaling

arXiv: https://arxiv.org/abs/2412.11468 · HTML: https://mlsanity.com/paper/2412.11468/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 16 Dec 2024.

## Builds on (most cited first, 13 of 13)

- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Activating More Pixels in Image Super-Resolution Transformer](https://mlsanity.com/paper/2205.04437/) (2022)
- [ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting](https://mlsanity.com/paper/2307.12348/) (2023)
- [Implicit Diffusion Models for Continuous Super-Resolution](https://mlsanity.com/paper/2303.16491/) (2023)
- [ClassSR: A General Framework to Accelerate Super-Resolution Networks by Data Characteristic](https://mlsanity.com/paper/2103.04039/) (2021)
- [Learned Image Downscaling for Upscaling using Content Adaptive Resampler](https://mlsanity.com/paper/1907.12904/) (2019)
- [Multi-Channel Deep Networks for Block-Based Image Compressive Sensing](https://mlsanity.com/paper/1908.11221/) (2019)
- [Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images](https://mlsanity.com/paper/2211.10643/) (2022)
- [Global Sensing and Measurements Reuse for Image Compressed Sensing](https://mlsanity.com/paper/2206.11629/) (2022)
- [Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting](https://mlsanity.com/paper/2303.08331/) (2023)
- [Transformer-based Selective Super-Resolution for Efficient Image Refinement](https://mlsanity.com/paper/2312.05803/) (2023)
- [Dual-layer Image Compression via Adaptive Downsampling and Spatially Varying Upconversion](https://mlsanity.com/paper/2302.06096/) (2023)

## Abstract (arXiv)

Image rescaling (IR) seeks to determine the optimal low-resolution (LR) representation of a high-resolution (HR) image to reconstruct a high-quality super-resolution (SR) image. Typically, HR images with resolutions exceeding 2K possess rich information that is unevenly distributed across the image. Traditional image rescaling methods often fall short because they focus solely on the overall scaling rate, ignoring the varying amounts of information in different parts of the image. To address this limitation, we propose a Block-Based Multi-Scale Image Rescaling Framework (BBMR), tailored for IR tasks involving HR images of 2K resolution and higher. BBMR consists of two main components: the Downscaling Module and the Upscaling Module. In the Downscaling Module, the HR image is segmented into sub-blocks of equal size, with each sub-block receiving a dynamically allocated scaling rate while maintaining a constant overall scaling rate. For the Upscaling Module, we introduce the Joint Super-Resolution method (JointSR), which performs SR on these sub-blocks with varying scaling rates and effectively eliminates blocking artifacts. Experimental results demonstrate that BBMR significantly enhances the SR image quality on the of 2K and 4K test dataset compared to initial network image rescaling methods.