GraphFill: Deep Image Inpainting Using Graphs

Shashikant Verma, Aman Sharma, Roopa Sheshadri, Shanmuganathan Raman; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2024, pp. 4996-5006

We present a novel coarser-to-finer approach for deep graphical image inpainting that utilizes GraphFill, a graph neural network-based deep learning framework, and a lightweight generative baseline network. We construct a pyramidal graph for the input-masked image by reducing it into superpixels, each representing a node in the graph. The proposed pyramidal approach facilitates the transfer of global context from coarser to finer pyramid levels, enabling GraphFill to estimate plausible information for unknown node values in the graph. The estimated information is used to fill in the masked region, which a Refine Network then refines. Furthermore, we propose a resolution-robust pyramidal graph construction method, allowing for efficient inpainting of high-resolution images with relatively fewer computations. Our proposed network, trained on Places and CelebA-HQ datasets, demonstrates competitive performance compared to existing methods while using fewer learning parameters. We conduct thorough ablation studies to evaluate the effectiveness of each component in the GraphFill Network for improved performance. Our proposed lightweight model for image inpainting is efficient in real-world scenarios, as it can be easily deployed on mobile devices with limited resources.