EchoIR: Advancing Image Restoration with Echo Upsampling and Bi-Level Optimization
This work addresses a specific bottleneck in image restoration for low-level vision applications, representing an incremental improvement over existing transformer-based methods.
The paper tackles the problem of feature degradation during upsampling in image restoration, introducing EchoIR with Echo-Upsampler and AS-BLO to achieve state-of-the-art performance in reconstruction tasks.
Image restoration represents a fundamental challenge in low-level vision, focusing on reconstructing high-quality images from their degraded counterparts. With the rapid advancement of deep learning technologies, transformer-based methods with pyramid structures have advanced the field by capturing long-range cross-scale spatial interaction. Despite its popularity, the degradation of essential features during the upsampling process notably compromised the restoration performance, resulting in suboptimal reconstruction outcomes. We introduce the EchoIR, an UNet-like image restoration network with a bilateral learnable upsampling mechanism to bridge this gap. Specifically, we proposed the Echo-Upsampler that optimizes the upsampling process by learning from the bilateral intermediate features of U-Net, the "Echo", aiming for a more refined restoration by minimizing the degradation during upsampling. In pursuit of modeling a hierarchical model of image restoration and upsampling tasks, we propose the Approximated Sequential Bi-level Optimization (AS-BLO), an advanced bi-level optimization model establishing a relationship between upsampling learning and image restoration tasks. Extensive experiments against the state-of-the-art (SOTA) methods demonstrate the proposed EchoIR surpasses the existing methods, achieving SOTA performance in image restoration tasks.