Diffusion Models with Anisotropic Gaussian Splatting for Image Inpainting

TL;DR

This paper introduces a novel image inpainting method that combines diffusion models with anisotropic Gaussian splatting to better preserve structure and texture in missing regions, outperforming existing techniques.

Contribution

The authors propose integrating anisotropic Gaussian splatting into diffusion models to improve structural guidance and coherence in image inpainting.

Findings

Outperforms state-of-the-art inpainting methods.

Produces more structurally coherent and realistic images.

Enhances texture and detail preservation in large missing areas.

Abstract

Image inpainting is a fundamental task in computer vision, aiming to restore missing or corrupted regions in images realistically. While recent deep learning approaches have significantly advanced the state-of-the-art, challenges remain in maintaining structural continuity and generating coherent textures, particularly in large missing areas. Diffusion models have shown promise in generating high-fidelity images but often lack the structural guidance necessary for realistic inpainting. We propose a novel inpainting method that combines diffusion models with anisotropic Gaussian splatting to capture both local structures and global context effectively. By modeling missing regions using anisotropic Gaussian functions that adapt to local image gradients, our approach provides structural guidance to the diffusion-based inpainting network. The Gaussian splat maps are integrated into the diffusion process, enhancing the model's ability to generate high-fidelity and structurally coherent inpainting results. Extensive experiments demonstrate that our method outperforms state-of-the-art techniques, producing visually plausible results with enhanced structural integrity and texture realism.