AI Paper Atlas

Research map / Point clouds / Segmentation and detection

QueryOcc: Query-based Self-Supervision for 3D Semantic Occupancy

Adam Lilja, Ji Lan, Junsheng Fu, Lars Hammarstrand

CVPR 2026 · Point clouds › Segmentation and detection · approach: Scene completion and instance segmentation · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use query-based 4D supervision instead of rendering-based supervision (ablation)QueryOcc · Occ3D-nuScenesSemantic RayIoU: 15.0 -> 23.6Improved
add VFM feature distillation (ablation)QueryOcc · Occ3D-nuScenesSemantic RayIoU: 23.6 -> 24.0Improved
add rendering losses to query-based supervision (ablation)QueryOcc · Occ3D-nuScenesSemantic RayIoU: 23.6 -> 23.3No clear effect
add log-linear bins, long supervision, contraction and point encoding to LSS (ablation)QueryOcc · Occ3D-nuScenesSemantic RayIoU: 21.7 -> 23.6Improved
use lidar supervision instead of pseudo point clouds (ablation)QueryOcc · Occ3D-nuScenesSemantic RayIoU: 23.6 -> 22.9Hurt
use lidar supervision instead of pseudo point clouds (ablation)QueryOcc · Occ3D-nuScenesOccupancy RayIoU: 45.2 -> 48.3Improved
combine pseudo and lidar supervision (ablation)QueryOcc · Occ3D-nuScenesSemantic RayIoU: 23.6 -> 24.6Improved
add Argoverse 2 training data (ablation)QueryOcc (lidar) · Occ3D-nuScenesSemantic RayIoU: 22.9 -> 26.0Improved
add Argoverse 2 training data (ablation)QueryOcc (lidar) · Occ3D-nuScenesDynamic RayIoU: 19.4 -> 23.8Improved
subsample pseudo point cloud to fewer than 100k points (ablation)QueryOcc · Occ3D-nuScenesmRayIoUNo clear effect
raise input resolution from 256x256 to 900x1600 (ablation)QueryOcc · Occ3D-nuScenesmRayIoU: +3 mRayIoU (approx.)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy