SinIR : efficient general image manipulation with single image reconstruction
SinIR : efficient general image manipulation with single image reconstruction
We propose SinIR, an efficient reconstructionbased framework trained on a single natural image for general image manipulation, including super-resolution, editing, harmonization, paint-toimage, photo-realistic style transfer, and artistic style transfer.We train our model on a single image with cascaded multi-scale learning, where each network at each scale is responsible for image …