FreqPDE: Rethinking Positional Depth Embedding for Multi-View 3D Object Detection Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Haisheng, Zhang, Junjie, Song, Feixiang, Zhou, Sanping, Wu, Wei, Zheng, Nanning, Yan, Junchi
Format:	Preprint
Published:	2025
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2510.15385