AI RESEARCH
Efficient Multi-View 3D Object Detection by Dynamic Token Selection and Fine-Tuning
arXiv CS.CV
•
ArXi:2604.13586v1 Announce Type: new Existing multi-view three-dimensional (3D) object detection approaches widely adopt large-scale pre-trained vision transformer (ViT)-based foundation models as backbones, being computationally complex. To address this problem, current state-of-the-art (SOTA) \texttt{ToC3D} for efficient multi-view ViT-based 3D object detection employs ego-motion-based relevant token selection. However, there are two key limitations: (1) The fixed layer-individual token selection ratios limit computational efficiency during both