TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (12) · 10279-10287
DOI: 10.1609/aaai.v40i12.37997 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Yiwen Wang und 2 weiteren Autor:innen.
Abstract (Originalsprache)
3D Gaussian Splatting (3DGS) has become a powerful technique for real-time novel view synthesis, using explicit, end-to-end optimized 3D Gaussians to represent scenes. However, its training objective is primarily based on pixel-wise photometric loss, and its densification strategy fails to account for structural consistency and localized perceptual priorities. As a result, 3DGS struggles to capture fine textures and boundary details in underconstrained areas, leading to inefficient use of representational capacity and degraded rendering quality in critical regions. To overcome this limitation, we introduce TileGS, a tile-wise, perceptually guided framework designed to refine scene representation based on local rendering quality. Our method features a tile-guided densification approach that performs per-tile perceptual analysis between rendered and ground-truth tiles to identify areas and Gaussians requiring refinement. Additionally, we incorporate a tile-level structural loss to enforce localized consistency during training. TileGS is designed to be a plug-and-play framework, seamlessly integrating into existing 3DGS pipelines with minimal adjustments. Experiments across multiple datasets demonstrate that TileGS improves rendering quality while maintaining an efficient representation, showcasing its versatility and effectiveness in diverse rendering scenarios.
Zitieren
APA
Wang, Y., Yi, R., & Ma, L. (2026). TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis. Proceedings of the AAAI Conference on Artificial Intelligence, 40(12), 10279-10287. https://doi.org/10.1609/aaai.v40i12.37997
Vancouver
Wang Y, Yi R, Ma L. TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(12):10279-10287. doi:10.1609/aaai.v40i12.37997
BibTeX
@article{Wang2026,
author = {Wang, Yiwen and Yi, Ran and Ma, Lizhuang},
title = {TileGS: Adaptive Gaussian Densification Through Tile-Guided Perceptual Analysis},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {12},
pages = {10279--10287},
doi = {10.1609/aaai.v40i12.37997}
}
EUVIMED