AI RESEARCH

Co-Fusion4D: Spatio-temporal Collaborative Fusion for Robust 3D Object Detection

arXiv CS.CV

ArXi:2605.20301v1 Announce Type: new In autonomous driving, 3D object detection is essential for accurate perception and reliable decision-making. However, object motion and ego-motion often induce cross-frame spatiotemporal inconsistencies in BEV-based detectors, leading to temporal BEV feature misalignment and degraded spatiotemporal consistency. To address these challenges, we propose Co-Fusion4D, a unified framework that explicitly preserves cross-frame spatiotemporal consistency and suppresses temporal feature drift.