FC3DNet: A Fully Connected Encoder-Decoder for Efficient Demoir'eing

TL;DR

FC3DNet is an efficient demoiréing neural network that balances high-quality results with fast processing by using multi-scale features and a novel feature fusion module, achieving state-of-the-art performance with fewer resources.

Contribution

The paper introduces FC3DNet, a fully connected encoder-decoder architecture with a multi-feature attention fusion module, significantly reducing computational cost while maintaining high demoiréing performance.

Findings

Achieves comparable results to SOTA methods on real-world datasets.

Uses fewer parameters, FLOPs, and runtime than existing methods.

Effectively captures long-range and local moiré patterns.

Abstract

Moir\'e patterns are commonly seen when taking photos of screens. Camera devices usually have limited hardware performance but take high-resolution photos. However, users are sensitive to the photo processing time, which presents a hardly considered challenge of efficiency for demoir\'eing methods. To balance the network speed and quality of results, we propose a \textbf{F}ully \textbf{C}onnected en\textbf{C}oder-de\textbf{C}oder based \textbf{D}emoir\'eing \textbf{Net}work (FC3DNet). FC3DNet utilizes features with multiple scales in each stage of the decoder for comprehensive information, which contains long-range patterns as well as various local moir\'e styles that both are crucial aspects in demoir\'eing. Besides, to make full use of multiple features, we design a Multi-Feature Multi-Attention Fusion (MFMAF) module to weigh the importance of each feature and compress them for efficiency. These designs enable our network to achieve performance comparable to state-of-the-art (SOTA) methods in real-world datasets while utilizing only a fraction of parameters, FLOPs, and runtime.