LogicIR: Logic Gate Networks for Image Restoration
Quick Answer
LogicIR introduces a novel Logic Gate Network for image restoration, achieving strong performance with reduced computational costs.
Quick Take
LogicIR introduces a novel Logic Gate Network for image restoration, achieving strong performance with reduced computational costs. This UNet-inspired architecture utilizes logic gates and includes a differentiable bit decoding layer, enhancing information propagation. Experimental results show its effectiveness across multiple benchmarks, making it a promising alternative in the field.
Key Points
- LogicIR is the first Logic Gate Network designed specifically for image restoration tasks.
- The architecture is inspired by UNet and consists entirely of logic gates.
- A differentiable bit decoding layer improves information propagation across gates.
- LogicIR demonstrates strong performance on multiple image restoration benchmarks.
- The model significantly reduces computational costs compared to traditional methods.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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 this https URL
| Comments: | ECCV 2026 |
| Subjects: | Computer Vision and Pattern Recognition (cs.CV) |
| Cite as: | arXiv:2606.26609 [cs.CV] |
| (or arXiv:2606.26609v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2606.26609 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hongjae Lee [view email]
[v1]
Thu, 25 Jun 2026 05:11:28 UTC (36,537 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →LLM-Guided ANN Index Optimization for Human-Object Interaction Retrieval
A phase-aware LLM agent optimizes human-object interaction retrieval, outperforming Optuna TPE by 33.3% and VDTuner by 34.2% on the HICO-DET benchmark. This method enhances throughput by 15.3x over UniIR and demonstrates strong transferability across vector database management systems.