Reproduce “Image Restoration Using Very Deep Convolutional Encoder-Decoder Networks with Symmetric Skip Connections” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Xiao-Jiao Mao, Chunhua Shen, Yu-Bin Yang
RED-Net addresses image restoration with an encoder that extracts features and a decoder that reconstructs the image, adding matching encoder features directly to decoder features. The authors say these shortcuts may preserve detail and ease training. On 14 images with Gaussian noise at σ = 70, RED30 reports 25.31 dB PSNR versus WNNM’s 24.80 dB, limited to this synthetic setting.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.