View-Consistent 3D Inpainting in Unbounded Scenes via Anti-Aliased Neural Radiance Fields
Applied Sciences · 21.07.2026 · 16 (14) · 7316
DOI: 10.3390/app16147316 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 21.07.2026. Verfasst von Zhaoxiang Guo und 9 weiteren Autor:innen. Die Arbeit nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation for Distinguished Young Scholars of China, an internal project, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Recent advances in NeRF-based inpainting have enabled the completion of masked regions across multi-view images. However, two major challenges remain: generating accurate masks efficiently in the presence of complex multi-object interference and maintaining view consistency without floating artifacts in large-scale, unbounded 360° environments. To address these challenges, we propose a 3D inpainting framework with two principal components. First, a depth-aware mask-generation pipeline produces high-quality, view-consistent masks from sparse annotations. Second, spherical parameterization is combined with a joint objective comprising smooth inter-layer and original-scene constraints to suppress floating artifacts and content drift in unbounded scenes. We also introduce IM2360, a multi-object 360° dataset for evaluating 3D inpainting methods. Experiments show that our approach outperforms existing NeRF-based inpainting methods in PSNR, LPIPS, and FID. On a single NVIDIA GeForce RTX 4090, our method requires an average of 25.21 min of training per scene, compared with 98.14 min for SPIn-NeRF, 38.71 min for OR-NeRF, and 11.29 min for InFusion. These results indicate that the proposed method provides a favorable balance between reconstruction quality and computational cost for high-fidelity restoration of complex immersive scenes.
Förderung
- National Science Foundation for Distinguished Young Scholars of China
- an internal project
- Fundamental Research Funds for the Central Universities
- 111 Project
Zitieren
APA
Guo, Z., Wu, X., Cheng, Q., Li, X., Lin, X., Sun, X., Zhu, M., Wen, Z., Liu, D., & Zhang, J. (2026). View-Consistent 3D Inpainting in Unbounded Scenes via Anti-Aliased Neural Radiance Fields. Applied Sciences, 16(14), 7316. https://doi.org/10.3390/app16147316
Vancouver
Guo Z, Wu X, Cheng Q, Li X, Lin X, Sun X, et al. View-Consistent 3D Inpainting in Unbounded Scenes via Anti-Aliased Neural Radiance Fields. Applied Sciences. 2026;16(14):7316. doi:10.3390/app16147316
BibTeX
@article{Guo2026,
author = {Guo, Zhaoxiang and Wu, Xin and Cheng, Qiang and Li, Xiang and Lin, Xiaoyan and Sun, Xue and Zhu, Mingxia and Wen, Zelin and Liu, Delian and Zhang, Jianqi},
title = {View-Consistent 3D Inpainting in Unbounded Scenes via Anti-Aliased Neural Radiance Fields},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {14},
pages = {7316},
doi = {10.3390/app16147316}
}
EUVIMED