14 papers
See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting
Dongyue Lu, Ao Liang, Tianxin Huang +8
Immersive applications call for synthesizing spatiotemporal 4D content from casual videos without costly 3D supervision. Existing video-to-4D methods typically rely on manually ann…
GeneMAN: Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data
Wentao Wang, Hang Ye, Fangzhou Hong +5
Given a single in-the-wild human photo, it remains a challenging task to reconstruct a high-fidelity 3D human model. Existing methods face difficulties including a) the varying bod…
Enhanced Spatiotemporal Consistency for Image-to-LiDAR Data Pretraining
Xiang Xu, Lingdong Kong, Hui Shuai +5
LiDAR representation learning has emerged as a promising approach to reducing reliance on costly and labor-intensive human annotations. While existing methods primarily focus on sp…
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
Lingdong Kong, Xiang Xu, Jiawei Ren +5
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supe…
LargeAD: Large-Scale Cross-Sensor Data Pretraining for Autonomous Driving
Lingdong Kong, Xiang Xu, Youquan Liu +6
Recent advancements in vision foundation models (VFMs) have revolutionized visual perception in 2D, yet their potential for 3D scene understanding, particularly in autonomous drivi…
DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes
Hengwei Bian, Lingdong Kong, Haozhe Xie +3
Urban scene generation has been developing rapidly recently. However, existing methods primarily focus on generating static and single-frame scenes, overlooking the inherently dyna…