Three-dimensional scene inpainting is crucial for applications from virtual reality to architectural visualization, yet existing methods struggle with view consistency and geometric accuracy in 360{\deg} unbounded scenes. We present AuraFusion360, a novel reference-based method that enables high-quality object removal and hole filling in 3D scenes represented by Gaussian Splatting. Our approach introduces (1) depth-aware unseen mask generation for accurate occlusion identification, (2) Adaptive Guided Depth Diffusion, a zero-shot method for accurate initial point placement without requiring additional training, and (3) SDEdit-based detail enhancement for multi-view coherence. We also introduce 360-USID, the first comprehensive dataset for 360{\deg} unbounded scene inpainting with ground truth. Extensive experiments demonstrate that AuraFusion360 significantly outperforms existing methods, achieving superior perceptual quality while maintaining geometric accuracy across dramatic viewpoint changes.
@article{arxiv.2502.05176,
title = {AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360{\deg} Unbounded Scene Inpainting},
author = {Chung-Ho Wu and Yang-Jung Chen and Ying-Huan Chen and Jie-Ying Lee and Bo-Hsu Ke and Chun-Wei Tuan Mu and Yi-Chuan Huang and Chin-Yang Lin and Min-Hung Chen and Yen-Yu Lin and Yu-Lun Liu},
journal= {arXiv preprint arXiv:2502.05176},
year = {2025}
}
Comments
Paper accepted to CVPR 2025. Project page: https://kkennethwu.github.io/aurafusion360/