April 9, 2024, 4:46 a.m. | Duy-Tho Le, Hengcan Shi, Jianfei Cai, Hamid Rezatofighi

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.04629v1 Announce Type: new
Abstract: Diffusion models have recently gained prominence as powerful deep generative models, demonstrating unmatched performance across various domains. However, their potential in multi-sensor fusion remains largely unexplored. In this work, we introduce DifFUSER, a novel approach that leverages diffusion models for multi-modal fusion in 3D object detection and BEV map segmentation. Benefiting from the inherent denoising property of diffusion, DifFUSER is able to refine or even synthesize sensor features in case of sensor malfunction, thereby improving …

3d object 3d object detection abstract arxiv cs.cv deep generative models detection diffusion diffusion model diffusion models domains fusion generative generative models however modal multi-modal novel object performance robust segmentation sensor type work

Founding AI Engineer, Agents

@ Occam AI | New York

AI Engineer Intern, Agents

@ Occam AI | US

AI Research Scientist

@ Vara | Berlin, Germany and Remote

Data Architect

@ University of Texas at Austin | Austin, TX

Data ETL Engineer

@ University of Texas at Austin | Austin, TX

Consultant - Artificial Intelligence & Data (Google Cloud Data Engineer) - MY / TH

@ Deloitte | Kuala Lumpur, MY