QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy
This addresses the challenge of expensive 3D annotation for autonomous driving by enabling self-supervised learning with improved performance, though it is incremental as it builds on existing self-supervised methods.
The paper tackles the problem of learning 3D semantic occupancy from images without manual labels by introducing QueryOcc, a self-supervised framework that uses 4D spatio-temporal queries, resulting in a 26% improvement in semantic RayIoU on the Occ3D-nuScenes benchmark while running at 11.6 FPS.
Learning 3D scene geometry and semantics from images is a core challenge in computer vision and a key capability for autonomous driving. Since large-scale 3D annotation is prohibitively expensive, recent work explores self-supervised learning directly from sensor data without manual labels. Existing approaches either rely on 2D rendering consistency, where 3D structure emerges only implicitly, or on discretized voxel grids from accumulated lidar point clouds, limiting spatial precision and scalability. We introduce QueryOcc, a query-based self-supervised framework that learns continuous 3D semantic occupancy directly through independent 4D spatio-temporal queries sampled across adjacent frames. The framework supports supervision from either pseudo-point clouds derived from vision foundation models or raw lidar data. To enable long-range supervision and reasoning under constant memory, we introduce a contractive scene representation that preserves near-field detail while smoothly compressing distant regions. QueryOcc surpasses previous camera-based methods by 26% in semantic RayIoU on the self-supervised Occ3D-nuScenes benchmark while running at 11.6 FPS, demonstrating that direct 4D query supervision enables strong self-supervised occupancy learning. https://research.zenseact.com/publications/queryocc/