Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking

Camera-based 4D panoptic occupancy tracking (4D-POT) is a promising paradigm for holistic scene understanding from multi-view imagery, enabling joint reasoning about geometry, semantics, and object identities across time. Recent mask-based pipelines achieve strong performance by propagating instance queries across frames. However, their underlying volumetric representations are typically recomputed at each timestep, limiting geometric temporal consistency, particularly under occlusion and for static scene elements. To address this limitation, we propose a streaming Gaussian encoder that maintains a persistent volumetric scene representation for 4D-POT. Our method models the scene as a fixed-size set of latent Gaussian queries that are propagated via ego-motion compensation and refreshed under a confidence-guided budget constraint. Crucially, we shape Gaussian opacities through depth-based supervision to serve as proxy for visibility, enabling confidence to accumulate as a temporally aggregated measure of persistent scene support. Together with a warmup-based multi-frame training strategy, this yields representation-level temporal coherence beyond decoder-only tracking. Extensive experiments on Occ3D-extended nuScenes and Waymo establish a new state-of-the-art for camera-based 4D-POT, improving tracking consistency with negligible computational overhead while remaining fully compatible with existing mask-based pipelines. We provide code and models at https://sge.cs.uni-freiburg.de.

Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking

Capturing 4D spatiotemporal surroundings is crucial for the safe and reliable operation of robots in dynamic environments. However, most existing methods address only one side of the problem: they either provide coarse geometric tracking via bounding boxes, or detailed 3D structures like voxel-based occupancy that lack explicit temporal association. In this work, we present Latent Gaussian Splatting for 4D Panoptic Occupancy Tracking (LaGS) that advances spatiotemporal scene understanding in a holistic direction. Our approach incorporates camera-based end-to-end tracking with mask-based multi-view panoptic occupancy prediction, and addresses the key challenge of efficiently aggregating multi-view information into 3D voxel grids via a novel latent Gaussian splatting approach. Specifically, we first fuse observations into 3D Gaussians that serve as a sparse point-centric latent representation of the 3D scene, and then splat the aggregated features onto a 3D voxel grid that is decoded by a mask-based segmentation head. We evaluate LaGS on the Occ3D nuScenes and Waymo datasets, achieving state-of-the-art performance for 4D panoptic occupancy tracking. We make our code available at https://lags.cs.uni-freiburg.de/.

Mono Video-Based AI Corridor for Model-Free Detection of Collision-Relevant Obstacles

The detection of previously unseen, unexpected obstacles on the road is a major challenge for automated driving systems. Different from the detection of ordinary objects with pre-definable classes, detecting unexpected obstacles on the road cannot be resolved by upscaling the sensor technology alone (e.g., high resolution video imagers / radar antennas, denser LiDAR scan lines). This is due to the fact, that there is a wide variety in the types of unexpected obstacles that also do not share a common appearance (e.g., lost cargo as a suitcase or bicycle, tire fragments, a tree stem). Also adding object classes or adding \enquote{all} of these objects to a common \enquote{unexpected obstacle} class does not scale. In this contribution, we study the feasibility of using a deep learning video-based lane corridor (called \enquote{AI ego-corridor}) to ease the challenge by inverting the problem: Instead of detecting a previously unseen object, the AI ego-corridor detects that the ego-lane ahead ends. A smart ground-truth definition enables an easy feature-based classification of an abrupt end of the ego-lane. We propose two neural network designs and research among other things the potential of training with synthetic data. We evaluate our approach on a test vehicle platform. It is shown that the approach is able to detect numerous previously unseen obstacles at a distance of up to 300 m with a detection rate of 95 %.