REVIEW 5 cited by
RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
The recent advances in camera-based bird's eye view (BEV) representation exhibit great potential for in-vehicle 3D perception. Despite the substantial progress achieved on standard benchmarks, the robustness of BEV algorithms has not been thoroughly examined, which is critical for safe operations. To bridge this gap, we introduce RoboBEV, a comprehensive benchmark suite that encompasses eight distinct corruptions, including Bright, Dark, Fog, Snow, Motion Blur, Color Quant, Camera Crash, and Frame Lost. Based on it, we undertake extensive evaluations across a wide range of BEV-based models to understand their resilience and reliability. Our findings indicate a strong correlation between absolute performance on in-distribution and out-of-distribution datasets. Nonetheless, there are considerable variations in relative performance across different approaches. Our experiments further demonstrate that pre-training and depth-free BEV transformation has the potential to enhance out-of-distribution robustness. Additionally, utilizing long and rich temporal information largely helps with robustness. Our findings provide valuable insights for designing future BEV models that can achieve both accuracy and robustness in real-world deployments.
Forward citations
Cited by 5 Pith papers
-
Iterate or Widen? When Test-Time Refinement Helps LiDAR Scene Completion: A Controlled Study of Evidence Geometry, Training Coverage, and Compute
A controlled LiDAR scene completion study finds that fixed-depth iterative refinement beats a parameter-matched wide model only for coherent missing regions, while training augmentation dominates for scattered thinning.
-
SafeMap: Robust HD Map Construction from Incomplete Observations
SafeMap improves HD map construction accuracy under missing camera views by reconstructing the missing perspective features with Gaussian-sampled attention and correcting the BEV features through distillation.
-
SAM4D: Segment Anything in Camera and LiDAR Streams
SAM4D is a promptable model that segments and tracks objects across camera and LiDAR streams with cross-modal prompts, trained on pseudo-labels generated by an automated data engine.
-
Foundation Models for Autonomous Driving Perception: A Survey Through Core Capabilities
Foundation-model perception for autonomous driving is surveyed through four capability lenses: generalized knowledge, spatial understanding, multi-sensor robustness, and temporal understanding.
-
What Really Matters for Robust Multi-Sensor HD Map Construction?
Combining data augmentation, cross-modal attention fusion, and modality dropout training improves robustness of camera-LiDAR HD map construction under 13 synthetic sensor corruptions and raises clean nuScenes mAP to 77.0.
Discussion (0). Continue with ORCID to comment.