Properties on n-dimensional convolution for image deconvolution
원문 초록
Convolution system is linear and time invariant, and can describe the optical imaging process. Based on convolution system, many deconvolution techniques have been developed for optical image analysis, such as boosting the space resolution of optical images, image denoising, image enhancement and so on. Here, we gave properties on N-dimensional convolution. By using these properties, we proposed image deconvolution method. This method uses a series of convolution operations to deconvolute image. We demonstrated that the method has the similar deconvolution results to the state-of-art method. The core calculation of the proposed method is image convolution, and thus our method can easily be integrated into GPU mode for large-scale image deconvolution.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Energy-Based Transformers are Scalable Learners and Thinkers
Learning to See in the Extremely Dark
Plug-and-Play Linear Attention for Pre-trained Image and Video Restoration Models
Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models
TDiR: Transformer based Diffusion for Image Restoration Tasks
Learning Multi-scale Spatial-frequency Features for Image Denoising
토론
이 논문과 연결된 포럼 글이 아직 없습니다.