← Back to all news
arXiv AI By Jinwoo Chung, Sangho An, Hyunsung Park, Jangho Kim

Sparse Recovery Bird's-Eye View Model Soup for Robust Camera-Based 3D Object Detection

Read the original on arXiv AI →

The paper introduces SR‑BEVS, a sparse recovery learning technique that enhances both clean accuracy and robustness to real‑world corruptions for camera‑based bird’s‑eye view (BEV) 3D object detection models. By pruning weights based on magnitude, generating diverse sparse models, retraining them with varied learning rates, and averaging the recovered models into a single dense model, the method achieves up to 33.8% improvement in corruption robustness and a 1.8% gain in clean accuracy over the Fast‑BEV baseline on the nuScenes dataset. The approach adds no inference overhead and preserves a connected low‑loss basin, suggesting applicability to other BEV models.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv AI
Sep 7

Post Fusion Bird's Eye View Feature Stabilization for Robust Multimodal 3D Detection

The paper introduces Post Fusion Stabilizer (PFS), a lightweight module that refines intermediate bird’s‑eye view (BEV) feature maps in existing camera‑LiDAR fusion detectors. PFS stabilizes feature statistics under domain shift, suppresses regions affected by sensor degradation, and adaptively restores weakened cues via residual correction, acting as a near‑identity transformation. On the nuScenes benchmark, PFS achieves state‑of‑the‑art robustness, notably improving camera dropout robustness by +1.2% and low‑light performance by +4.4% mAP while adding only 3.3 M parameters.

By Trung Tien Dong, Dev Thakkar, Arman Sargolzaei, Xiaomin Lin
agentscomputer-visionroboticsmultimodalbenchmarks
More like this →
arXiv Computer Vision
Oct 21

Provisioning Robust and Efficient LiDAR Perception for Autonomous Driving

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.

By Tingxu Han, Zijie Shen, An Guo, Lyuke Wang, Chunrong Fang, Zhenyu Chen, Wei Song
agentscomputer-visionroboticsefficiency
More like this →
arXiv AI
Sep 7

Mitigating Performance Discrepancy in Cross-Domain 3D Class-Incremental Learning

The paper addresses performance discrepancy in cross-domain 3D class‑incremental learning, where 3D point clouds from heterogeneous sources cause varying degrees of performance loss beyond catastrophic forgetting. The authors introduce the Domain3D‑CIL protocol and adapt existing CIL methods to 3D, showing consistent discrepancy across baselines. They propose PolyMem, an exemplar‑free approach that models high‑order feature statistics to improve cross‑domain robustness and reduce performance discrepancy.

By Jinge Ma, Gautham Vinod, Bruce Coburn, Jui-Feng Chi, Siddeshwar Raghavan, Fengqing Zhu
agentsrobotics
More like this →