The Flow has not summarised this story yet — read it at arXiv Computer Vision.
For safety of the intended functionality (SOTIF) analysis according to ISO 21448, a machine learning object detector for light detection and ranging (LiDAR) point clouds can meet a performance target,...
The paper presents a method for creating LiDAR-based 3D object detectors that remain accurate under point‑cloud corruptions while meeting strict latency and memory constraints. It achieves robustness by generating corrupted samples that mimic extreme weather and training detectors to focus on hard samples, guided by perturbation sensitivity estimated from an ensemble of seven heterogeneous detectors. Efficiency is improved by narrowing the network and using offline neighborhood‑density measurements to reduce the number of points processed at each sampling stage, resulting in significant gains in AP under corruption and reductions in inference latency and GPU memory usage across multiple datasets and detector architectures.
LiDAR-based 3D object detection is a core perception service for autonomous driving, but deployment requires robustness to point-cloud corruption while meeting latency and memory requirements. Existin...
The paper studies how epistemic uncertainty estimates can be used in different ways—either as an additional input feature or as a per‑sample confidence weight in the loss function—to improve 3D LiDAR point cloud segmentation. Experiments on four large‑scale LiDAR benchmarks (ISPRS Vaihingen, AHN3, Paris‑Lille‑3D, and Toronto‑3D) show that uncertainty‑aware models outperform a baseline ANN in mean Intersection over Union, recover minority classes, and better align prediction error with estimated uncertainty. The results suggest that uncertainty can serve multiple roles in the segmentation pipeline beyond merely boosting accuracy.
Reliable motion classification is critical for autonomous driving, as false dynamic predictions of static objects can cascade into unnecessary planner interventions. Unstable bounding box predictions can lead to spurious velocity estimates in tracking and falsely predicted trajectories.
The paper introduces Grace-BEV, a lightweight framework that enhances the robustness of Lift‑Splat‑Shoot (LSS) based bird’s‑eye view (BEV) perception models against sensor corruptions. Grace‑BEV operates in aligned BEV space, combining a LiDAR‑guided image‑BEV expert with a LiDAR‑independent visual expert, and uses a TrustGate Router and FailSafe Fusion Block to mix and recalibrate their outputs. Experiments on nuScenes-R and nuScenes-C show that Grace‑BEV maintains strong performance under diverse corruptions, recovers up to 34.7 mAP when LiDAR is lost, and even improves clean accuracy by up to 1.4 mAP with only 1.2M additional parameters.