arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.21487cs.ROcs.LG
收藏

GaussianSSC:基于三平面的定向高斯场用于3D语义补全

GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completion

Ruiqi Xian, Jing Liang, He Yin, Xuewei Qi, Dinesh Manocha

AI总结:

本文提出GaussianSSC,一种两阶段、基于网格和三平面引导的语义场景补全方法,通过高斯场提升语义补全效果,改进单目占用估计并提升三平面特征精度。

摘要:

我们提出了GaussianSSC,一种两阶段、基于网格和三平面引导的语义场景补全方法,该方法在不替换体素网格或维护独立高斯集的情况下注入高斯场的优势。我们引入了Gaussian Anchoring,一种亚像素、基于融合FPN特征的高斯加权图像聚合方法,紧贴体素-图像对齐并提升单目占用估计。我们进一步将点状体素特征转换为学习的每体素高斯场,并通过三平面对齐的Gaussian-Triplane Refinement模块进行改进,该模块结合局部聚集(目标中心)和全局聚合(源中心)。这种方向性、各向异性支持能够捕捉表面切线、尺度和遮挡感知的不对称性,同时保持三平面表示的效率。在SemanticKITTI数据集上,GaussianSSC在第一阶段占用估计上比最先进基线提升了1.0%的召回率、2.0%的精确率和1.8%的IoU,第二阶段语义预测上提升了1.8%的IoU和0.8%的mIoU。

英文摘要:

We present \emph{GaussianSSC}, a two-stage, grid-native and triplane-guided approach to semantic scene completion (SSC) that injects the benefits of Gaussians without replacing the voxel grid or maintaining a separate Gaussian set. We introduce \emph{Gaussian Anchoring}, a sub-pixel, Gaussian-weighted image aggregation over fused FPN features that tightens voxel--image alignment and improves monocular occupancy estimation. We further convert point-like voxel features into a learned per-voxel Gaussian field and refine triplane features via a triplane-aligned \emph{Gaussian--Triplane Refinement} module that combines \emph{local gathering} (target-centric) and \emph{global aggregation} (source-centric). This directional, anisotropic support captures surface tangency, scale, and occlusion-aware asymmetry while preserving the efficiency of triplane representations. On SemanticKITTI~\cite{behley2019semantickitti}, GaussianSSC improves Stage~1 occupancy by +1.0\% Recall, +2.0\% Precision, and +1.8\% IoU over state-of-the-art baselines, and improves Stage~2 semantic prediction by +1.8\% IoU and +0.8\% mIoU.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑