Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
College of Computer Science, Beijing University of Technology, Beijing, 100124, China, Corresponding author: Cuntai Guan, Guo-Sen Xie.Yong Li is with the School of Computer Science and Engineering, and the Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications, Southeast University, Nanjing 210096, China. E-mail: mysee1989@gmail.com.Tianyi Zhang is with Key Laboratory of Child Development and Learning Science (Ministry of Education), School of Biological Sciences and Medical Engineering, Southeast University, Nanjing, China. E-mail: t.zhang@seu.edu.cn.Yi Ren, Yizhe Zhang, Wenhua Zhang and Guo-Sen Xie are with the School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China. E-mail: yi.ren@njust.edu.cn, zhangyizhe@njust.edu.cn, whzhang@njust.edu.cn, gsxiehm@gmail.com.Cuntai Guan and Muyun Jiang are with the School of Computer Science and Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore, 639798. E-mail: (ctguan, james.jiang)@ntu.edu.sg.Manuscript received April 19, 2021; revised August 16, 2021
1
0
0
1
DMFormer is introduced, an innovative multi-modal BEV perception framework that employs Transformer architecture and a diffusion denoising model to tackle key challenges, including sensor noise, efficient fusion of multi-modal data, and modeling dynamic scenes.