GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priors
This work addresses the challenge of volumetric occupancy prediction from visual observations for autonomous driving and embodied intelligence, offering a unified framework that handles multi-view and temporal inputs.
GPOcc++ introduces a unified sparse Gaussian representation that transforms visual geometry priors into occupancy-aware features for 3D scene understanding, achieving strong performance on both indoor and outdoor benchmarks with favorable efficiency and generalization.
Accurate 3D scene understanding is fundamental to embodied intelligence and autonomous driving, where 3D occupancy provides a unified representation of objects, structures, and free space. However, recovering such a complete volumetric representation from visual observations remains challenging, particularly in occluded and unobserved regions. Visual geometry priors offer strong and generalizable geometric cues for addressing this challenge, but their outputs are inherently surface-centric, whereas occupancy prediction requires reasoning about volumetric interiors and free space. To bridge this gap, we introduce GPOcc, which transforms visual geometry priors into occupancy-aware sparse Gaussian representations for efficient and expressive volumetric scene modeling. Building on GPOcc, GPOcc++ models multi-view observations and temporal sequences within a unified framework, allowing spatial and temporal evidence to be handled through the same representation. We further extend GPOcc++ from indoor scenes to outdoor occupancy prediction. Extensive experiments on both indoor and outdoor benchmarks demonstrate consistently strong performance across both multi-view and temporal settings, together with favorable efficiency and generalization. Code will be released at https://github.com/JuIvyy/GPOcc.