LogicIR: Logic Gate Networks for Image Restoration

2026-06-25

AI Summary

This work addresses the high computational cost and limited deployability of existing image restoration models by proposing LogicIR—the first fully logic-gate-based network dedicated to image restoration. Built upon fundamental Boolean operations such as NAND and XOR, LogicIR adopts a UNet-style architecture and introduces two key innovations: a differentiable bit-decoding layer and an index-shuffling mechanism, which together enhance information flow and eliminate reliance on floating-point arithmetic. Extensive experiments demonstrate that LogicIR achieves competitive performance across multiple image restoration benchmarks while substantially reducing computational overhead, thereby establishing the feasibility and promise of pure logic-gate networks for efficient image restoration.

Abstract

Image restoration aims to reconstruct high-quality images from degraded low-quality inputs. As the computational demands of image restoration models continue to rise, there is growing interest in lightweight architectures optimized for fast and efficient inference. Logic gate networks (LGNs), which operate using fundamental logic operations such as NAND and XOR, have recently emerged as a promising direction for achieving highly efficient computation. However, their potential remains largely untapped in the domain of image restoration. In this work, we introduce LogicIR, the first LGN specifically designed for image restoration tasks. LogicIR incorporates a UNet-inspired architecture composed entirely of logic gates. In addition, we propose a differentiable bit decoding layer and an index shuffling mechanism that improves information propagation across logic gates. Experimental results across multiple image restoration benchmarks demonstrate that LogicIR achieves strong performance with significantly reduced computational cost, establishing LogicIR as a viable and efficient alternative for image restoration. The source code is available at https://github.com/jimmy9704/LogicIR

Problem

• image restoration
• lightweight architecture
• logic gate networks
• efficient inference
• computational cost

Innovation

• Logic Gate Networks
• Image Restoration
• Differentiable Bit Decoding
• Index Shuffling
• Lightweight Architecture