Image deblurring based on lightweight multi-information fusion network
원문 초록
Recently, deep learning based image deblurring has been well developed. However, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from high computational burden. To solve this problem, we propose a lightweight multiinformation fusion network (LMFN) for image deblurring. The proposed LMFN is designed as an encoder-decoder architecture. In the encoding stage, the image feature is reduced to various smallscale spaces for multi-scale information extraction and fusion without a large amount of information loss. Then, a distillation network is used in the decoding stage, which allows the network benefit the most from residual learning while remaining sufficiently lightweight. Meanwhile, an information fusion strategy between distillation modules and feature channels is also carried out by attention mechanism. Through fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring result with smaller number of parameters and outperforms existing methods in model complexity.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Revitalizing Convolutional Network for Image Restoration
Single Stage Adaptive Multi-Attention Network for Image Restoration
A Fast Blind Deblurring Algorithm Using Local Gradient Product Prior
Image Restoration via Frequency Selection
Dark and Bright Channel Prior Embedded Network for Dynamic Scene Deblurring
Image Deblurring with a Class-Specific Prior
토론
이 논문과 연결된 포럼 글이 아직 없습니다.