CVNov 5, 2020

Hyperrealistic Image Inpainting with Hypergraphs

arXiv:2011.02904v138 citations
Originality Highly original
AI Analysis

This addresses the problem of blurry inpainting results in computer vision, offering a novel method for improved image completion.

The paper tackles image inpainting by using hypergraph convolution on spatial features to capture complex global relationships, achieving state-of-the-art results on datasets like Places2 and CelebA-HQ.

Image inpainting is a non-trivial task in computer vision due to multiple possibilities for filling the missing data, which may be dependent on the global information of the image. Most of the existing approaches use the attention mechanism to learn the global context of the image. This attention mechanism produces semantically plausible but blurry results because of incapability to capture the global context. In this paper, we introduce hypergraph convolution on spatial features to learn the complex relationship among the data. We introduce a trainable mechanism to connect nodes using hyperedges for hypergraph convolution. To the best of our knowledge, hypergraph convolution have never been used on spatial features for any image-to-image tasks in computer vision. Further, we introduce gated convolution in the discriminator to enforce local consistency in the predicted image. The experiments on Places2, CelebA-HQ, Paris Street View, and Facades datasets, show that our approach achieves state-of-the-art results.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes