IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (6) · 4932-4940
DOI: 10.1609/aaai.v40i6.42497 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Wenhao Hu und 7 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Even multi-view observations from a single scene scan often fail to capture the full structural details. Existing approaches typically rely on multi-stage pipelines—such as segmentation, background completion, and inpainting—or require per-object dense scanning, both of which are error-prone, and not easily scalable. We propose IGFuse, a novel framework that reconstructs interactive Gaussian scene by fusing observations from multiple scans, where natural object rearrangement between captures reveal previously occluded regions. Our method constructs segmentation-aware Gaussian fields and enforces bi-directional photometric and semantic consistency across scans. To handle spatial misalignments, we introduce a pseudo-intermediate scene state for symmetric alignment, alongside collaborative co-pruning strategies to refine geometry. IGFuse enables high-fidelity rendering and object-level scene manipulation without dense observations or complex pipelines. Extensive experiments validate the framework’s strong generalization to novel scene configurations, demonstrating its effectiveness for real-world 3D reconstruction and real-to-simulation transfer.
Zitieren
APA
Hu, W., Li, Z., Zhou, H., Liu, L., Wen, X., Su, Z., Li, X., & Wang, G. (2026). IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion. Proceedings of the AAAI Conference on Artificial Intelligence, 40(6), 4932-4940. https://doi.org/10.1609/aaai.v40i6.42497
Vancouver
Hu W, Li Z, Zhou H, Liu L, Wen X, Su Z, et al. IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(6):4932-4940. doi:10.1609/aaai.v40i6.42497
BibTeX
@article{Hu2026,
author = {Hu, Wenhao and Li, Zesheng and Zhou, Haonan and Liu, Liu and Wen, Xuexiang and Su, Zhizhong and Li, Xi and Wang, Gaoang},
title = {IGFuse: Interactive 3D Gaussian Scene Reconstruction via Multi-Scans Fusion},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {6},
pages = {4932--4940},
doi = {10.1609/aaai.v40i6.42497}
}
EUVIMED