AsyncBEV: Cross-modal Flow Alignment in Asynchronous 3D Object Detection

arXiv:2601.12994 · cs.CV · Submitted 2026-01-19 · Read on arXiv

cs.CV

Submitted: 2026-01-19

Updated: 2026-10-18

Comments: Camera-ready version, ICLR 2026. 17 pages, 7 figures. Project page: https://tudelft-iv.github.io/AsyncBEV/

Code: https://github.com/tudelft-iv/AsyncBEV

Project page: https://tudelft-iv.github.io/AsyncBEV

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Robustness — 2× in this paper · explained in 5 episodes
• Scene Flow — 1× in this paper · explained in 2 episodes

Sources

• BEVFusion4D: Learning LiDAR-Camera Fusion Under Bird's-Eye-View via Cross-Modality Guidance and Temporal Aggregation
• BEVDet4D: Exploit Temporal Cues in Multi-camera 3D Object Detection
• BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View
• Multi-modal Sensor Fusion for Auto Driving Perception: A Survey
• Temporal Misalignment Attacks against Multimodal Perception in Autonomous Driving
• Cross Modal Transformer: Towards Fast and Robust 3D Object Detection

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models