Understanding the Robustness of 3D Object Detection with Bird’s-Eye-View Representations in Autonomous Driving. (arXiv:2303.17297v2 [cs.CV] UPDATED)

Abstract:3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In

Read more

Related Posts

• ApproxABFT: Approximate Algorithm-Based Fault Tolerance for Vision Transformers. (arXiv:2302.10469v2 [cs.CR] UPDATED)a
• Why Don’t You Clean Your Glasses? Perception Attacks with Dynamic Optical Perturbations. (arXiv:2307.13131v1 [cs.CR])a
• SHIFT3D: Synthesizing Hard Inputs For Tricking 3D Detectors. (arXiv:2309.05810v1 [cs.CV])a
• REAP: A Large-Scale Realistic Adversarial Patch Benchmark. (arXiv:2212.05680v2 [cs.CV] UPDATED)a
• What Can Human Sketches Do for Object Detection? Insights On Sketch-based Image Retrievala