Search papers, labs, and topics across Lattice.
This paper introduces GPOcc++, a novel framework that integrates visual geometry priors into sparse Gaussian representations for enhanced 3D occupancy prediction. By addressing the limitations of traditional surface-centric outputs, GPOcc++ effectively models both multi-view observations and temporal sequences, enabling comprehensive scene understanding in both indoor and outdoor environments. Experimental results show that GPOcc++ achieves superior performance, efficiency, and generalization across various benchmarks, marking a significant advancement in volumetric scene modeling for autonomous systems.
Bridging the gap between surface-centric visual geometry priors and volumetric occupancy prediction, GPOcc++ sets a new standard for 3D scene understanding in dynamic environments.
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.
