用各向异性高斯点云增强扩散模型，提升大区域图像修复的结构连贯性。
Diffusion Models with Anisotropic Gaussian Splatting for Image Inpainting
- 用自适应梯度的各向异性高斯点表示缺失区域结构
- 在多个基准上优于现有方法，结构完整性与纹理真实感显著提升
- 适合需要高质量大块修复的视觉重建任务
图像修复是计算机视觉中的基础任务，旨在真实还原图像中缺失或损坏的区域。尽管深度学习方法已大幅推进该领域进展，但在保持结构连续性和生成一致纹理方面仍面临挑战，尤其在大范围缺失区域。扩散模型虽能生成高保真图像，但缺乏必要的结构引导。本文提出一种新修复方法，将扩散模型与各向异性高斯点云结合，有效捕捉局部结构与全局上下文。通过使用随局部图像梯度自适应的各向异性高斯函数建模缺失区域，本方法为基于扩散的修复网络提供结构引导。高斯点云图被嵌入扩散过程，显著提升模型生成高保真、结构一致修复结果的能力。大量实验表明，该方法超越现有最先进水平，在视觉可接受性、结构完整性和纹理真实性方面均有明显改善。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。