Image Inpainting via Generative Multi-column Convolutional Neural Networks

Abstract

In this paper, we propose a generative multi-column network for image inpainting. This network synthesizes different image components in a parallel manner within one stage. To better characterize global structures, we design a confidence-driven reconstruction loss while an implicit diversified MRF regularization is adopted to enhance local details. The multi-column network combined with the reconstruction and MRF loss propagates local and global information derived from context to the target inpainting regions. Extensive experiments on challenging street view, face, natural objects and scenes manifest that our method produces visual compelling results even without previously common post-processing.

Accepted in NIPS 2018

References in corpus (3)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Generative Image Inpainting with Contextual Attention

Cited by in corpus (25)

• PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting
• PEPSI++: Fast and Lightweight Network for Image Inpainting
• Image Fine-grained Inpainting
• Boundless: Generative Adversarial Networks for Image Extension
• Generative Adversarial Networks for Image and Video Synthesis: Algorithms and Applications
• Interpreting Black Box Models via Hypothesis Testing
• Image Inpainting with Learnable Bidirectional Attention Maps
• Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
• Examining Autocompletion as a Basic Concept for Interaction with Generative AI
• Context-Aware Mutual Learning for Blind Image Inpainting and Beyond
• Squeezed Deep 6DoF Object Detection Using Knowledge Distillation
• Domain Embedded Multi-model Generative Adversarial Networks for Image-based Face Inpainting
• Bi-level Feature Alignment for Versatile Image Translation and Manipulation
• Learning Oracle Attention for High-fidelity Face Completion
• SwapText: Image Based Texts Transfer in Scenes
• Vision-Infused Deep Audio Inpainting
• PD-GAN: Probabilistic Diverse GAN for Image Inpainting
• VCNet: A Robust Approach to Blind Image Inpainting
• SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches
• A nonlocal feature-driven exemplar-based approach for image inpainting
• Semantic Editing On Segmentation Map Via Multi-Expansion Loss
• Conditional Generative Modeling via Learning the Latent Space
• Open-World Entity Segmentation
• Generative Image Inpainting with Submanifold Alignment
• Synthesizing Photorealistic Images with Deep Generative Learning