Reliability‐Aware Adaptive Gaussian Propagation for Low‐Texture Dynamic Outdoor Scenes
Computer Graphics Forum · 14.11.2026
DOI: 10.1111/cgf.70649 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Graphics Forum, online erschienen am 14.11.2026. Verfasst von Yumeng Cao und 1 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
3D Gaussian Splatting (3DGS) remains challenging in dynamic outdoor scenes where dynamic distractors are coupled with large low‐texture regions such as roads and walls. Binary mask‐based foreground removal is insufficient—dynamic boundaries corrupt static optimization, while low‐texture regions lack reliable matching cues. In our method, we propose Reliability‐Aware Adaptive Gaussian Propagation (RAGP) for low‐texture dynamic outdoor scenes. Our method adapts patch scales based on local structure and static reliability for pixel‐level propagation, and fuses dynamic probability maps with rendering residuals into continuous reliability weights to constrain supervision, propagation filtering, and densification. Unlike foreground masking, RAGP converts dynamic priors into static reliability constraints and embeds them into geometric propagation. Experiments on dynamic outdoor benchmarks demonstrate that RAGP reduces artifacts and erroneous densification while improving low‐texture reconstruction and rendering fidelity.
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Cao, Y., & Wu, X. (2026). Reliability‐Aware Adaptive Gaussian Propagation for Low‐Texture Dynamic Outdoor Scenes. Computer Graphics Forum. https://doi.org/10.1111/cgf.70649
Vancouver
Cao Y, Wu X. Reliability‐Aware Adaptive Gaussian Propagation for Low‐Texture Dynamic Outdoor Scenes. Computer Graphics Forum. 2026. doi:10.1111/cgf.70649
BibTeX
@article{Cao2026,
author = {Cao, Yumeng and Wu, Xiaoqun},
title = {Reliability‐Aware Adaptive Gaussian Propagation for Low‐Texture Dynamic Outdoor Scenes},
journal = {Computer Graphics Forum},
year = {2026},
doi = {10.1111/cgf.70649}
}
EUVIMED