Plug-and-Play Tri-Branch Invertible Block for Image Rescaling

TL;DR

This paper introduces a plug-and-play tri-branch invertible neural network block that decomposes low-frequency information into luminance and chrominance components, improving image rescaling efficiency and reconstruction quality.

Contribution

The paper proposes a novel tri-branch invertible block that reduces redundancy by separating luminance and chrominance, and employs an all-zero high-frequency mapping strategy for better image rescaling.

Findings

Improves HR image reconstruction performance.

Enhances efficiency by reducing channel redundancy.

Achieves state-of-the-art results in image rescaling tasks.

Abstract

High-resolution (HR) images are commonly downscaled to low-resolution (LR) to reduce bandwidth, followed by upscaling to restore their original details. Recent advancements in image rescaling algorithms have employed invertible neural networks (INNs) to create a unified framework for downscaling and upscaling, ensuring a one-to-one mapping between LR and HR images. Traditional methods, utilizing dual-branch based vanilla invertible blocks, process high-frequency and low-frequency information separately, often relying on specific distributions to model high-frequency components. However, processing the low-frequency component directly in the RGB domain introduces channel redundancy, limiting the efficiency of image reconstruction. To address these challenges, we propose a plug-and-play tri-branch invertible block (T-InvBlocks) that decomposes the low-frequency branch into luminance (Y) and chrominance (CbCr) components, reducing redundancy and enhancing feature processing. Additionally, we adopt an all-zero mapping strategy for high-frequency components during upscaling, focusing essential rescaling information within the LR image. Our T-InvBlocks can be seamlessly integrated into existing rescaling models, improving performance in both general rescaling tasks and scenarios involving lossy compression. Extensive experiments confirm that our method advances the state of the art in HR image reconstruction.