Self-Supervised Learning

Inpainting

Introduced by Pathak et al. in Context Encoders: Feature Learning by Inpainting

Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.

Source: Context Encoders: Feature Learning by Inpainting

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Inpainting 74 30.20%
Denoising 14 5.71%
Video Inpainting 12 4.90%
Image Generation 11 4.49%
Semantic Segmentation 10 4.08%
Image Restoration 7 2.86%
Facial Inpainting 6 2.45%
Texture Synthesis 6 2.45%
Optical Flow Estimation 5 2.04%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories