← Search

Mingqian Ji

2 accepted papers

2026

Revisiting Token Compression for Accelerating ViT-based Sparse Multi-View 3D Object Detectors

CVPR 2026

Vision Transformer (ViT)-based sparse multi-view 3D object detectors have achieved remarkable accuracy but still suffer from high inference latency due to heavy token processing. To accelerate these models, token compression has been widely explored. However, our revisit of existing strategies, such

Cited by 0SourcecodeScholar
2025

OcRFDet: Object-Centric Radiance Fields for Multi-View 3D Object Detection in Autonomous Driving

ICCV 2025poster

Current multi-view 3D object detection methods typically transfer 2D features into 3D space using depth estimation or 3D position encoder, but in a fully data-driven and implicit manner, which limits the detection performance. Inspired by the success of radiance fields on 3D reconstruction, we assum…