4 papers
Learning to Factorize and Adapt: A Versatile Approach Toward Universal Spatio-Temporal Foundation Models
Siru Zhong, Junjie Qiu, Yangyu Wu +7
Spatio-Temporal (ST) Foundation Models (STFMs) promise cross-dataset generalization, yet joint ST pretraining is computationally expensive and grapples with the heterogeneity of do…
A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene Generation
Wentao Qu, Guofeng Mei, Yang Wu +3
Text-to-LiDAR generation can customize 3D data with rich structures and diverse scenes for downstream tasks. However, the scarcity of Text-LiDAR pairs often causes insufficient tra…
Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch
Xu Cai, Yang Wu, Qianli Chen +3
We present an ultra-efficient post-training method for shortcutting large-scale pre-trained flow matching diffusion models into efficient few-step samplers, enabled by novel veloci…
Veila: Panoramic LiDAR Generation from a Monocular RGB Image
Youquan Liu, Lingdong Kong, Weidong Yang +8
Realistic and controllable panoramic LiDAR data generation is critical for scalable 3D perception in autonomous driving and robotics. Existing methods either perform unconditional…