Learning from Ideal Edge for Image Restoration

スポンサーリンク

概要

• 論文の詳細を見る

• Considering the real existent fact of the ideal edge and the learning style of image analogy without reference parameters, a blind image recovery algorithm using a self-adaptive learning method is proposed in this paper. We show that a specific local image patch with degradation characteristic can be utilized for restoring the whole image. In the training process, a clear counterpart of the local image patch is constructed based on the ideal edge assumption so that identification of the Point Spread Function is no longer needed. Experiments demonstrate the effectiveness of the proposed method on remote sensing images.

• The Institute of Electronics, Information and Communication Engineersの論文

著者

• Chen Jian-sheng

  Department Of Electronic Engineering Tsinghua University

• Su Guang-da

  Department Of Electronic Engineering Tsinghua University

• HE Jin-Ping

  Beijing Institute of Space Mechanics & Electricity

• GAO Kun

  School of Optoelectronics, Beijing Institute of Technology

• NI Guo-Qiang

  School of Optoelectronics, Beijing Institute of Technology

• SU Guang-Da

  Department of Electronics Engineering, Tsinghua University

関連論文

• Super-Resolution for Facial Images Based on Local Similarity Preserving
• Learning from Ideal Edge for Image Restoration

スポンサーリンク