IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection

arXiv:2403.15241v1 Announce Type: new
Abstract: Bird's eye view (BEV) representation has emerged as a dominant solution for describing 3D space in autonomous driving scenarios. However, objects in the BEV representation typically exhibit small sizes, and the associated point cloud context is inherently sparse, which leads to great challenges for reliable 3D perception. In this paper, we propose IS-Fusion, an innovative multimodal fusion framework that jointly captures the Instance- and Scene-level contextual information. IS-Fusion essentially differs from existing approaches that only …

3d object 3d object detection arxiv collaborative cs.cv detection fusion instance multimodal object type