ROLGMar 23

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

arXiv:2603.2148771.9h-index: 8
AI Analysis

This work addresses 3D scene understanding for autonomous driving by providing incremental improvements in semantic completion accuracy.

The paper tackles 3D semantic scene completion by introducing GaussianSSC, a two-stage method that uses Gaussian fields and triplane guidance to enhance voxel-image alignment and feature refinement, resulting in improved occupancy estimation and semantic prediction on SemanticKITTI with gains such as +1.8% IoU in Stage 2.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes