-
[pdf]
[supp]
[bibtex]@InProceedings{Wu_2025_CVPR, author = {Wu, Chung-Ho and Chen, Yang-Jung and Chen, Ying-Huan and Lee, Jie-Ying and Ke, Bo-Hsu and Mu, Chun-Wei Tuan and Huang, Yi-Chuan and Lin, Chin-Yang and Chen, Min-Hung and Lin, Yen-Yu and Liu, Yu-Lun}, title = {AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpainting}, booktitle = {Proceedings of the Computer Vision and Pattern Recognition Conference (CVPR)}, month = {June}, year = {2025}, pages = {16366-16376} }
AuraFusion360: Augmented Unseen Region Alignment for Reference-based 360deg Unbounded Scene Inpainting
Abstract
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 360deg 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 360deg 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.
Related Material