10 papers
RayLift: Lifting Complementary Ray-Wise Evidence with 3D Geometry Priors for Semantic Scene Completion
Meng Wang, Hongxia Yu, Wenzhe He +4
Camera-based 3D semantic scene completion (SSC) provides comprehensive scene understanding for autonomous driving and robotics. However, existing methods often treat stereo depth e…
Geospatial-Prior Guidance for 3D Semantic Scene Completion
Meng Wang, Shougao Zhang, Wenzhe He +4
Inferring complete 3D geometry and semantics from onboard images remains challenging because occlusions and restricted fields of view leave large scene regions underconstrained. Al…
FPSGen: Flexible Point Cloud Scene Generation with BEV-Supported Transport Flows
Wenzhe He, Meng Wang, JiaWei Qian +3
FPSGen is a framework that generates outdoor point‑cloud scenes by first predicting a bird’s‑eye‑view prior and then using a transport‑flow model to create points, supporting both…
RoomPilot: Controllable Indoor Scene Synthesis via Multimodal Semantic Parsing
Wentang Chen, Shougao Zhang, Yiman Zhang +2
Generating controllable indoor scenes is fundamental to applications in game development, architectural visualization, and embodied AI. However, existing approaches either support…
All Cities are Equal: A Unified Human Mobility Generation Model Enabled by LLMs
Bo Liu, Tong Li, Zhu Xiao +4
Synthetic human mobility generation is gaining traction as an ethical and practical approach to supporting the data needs of intelligent urban systems. Existing methods perform wel…
LiNeXt: Revisiting LiDAR Completion with Efficient Non-Diffusion Architectures
Wenzhe He, Xiaojun Chen, Ruiqi Wang +5
3D LiDAR scene completion from point clouds is a fundamental component of perception systems in autonomous vehicles. Previous methods have predominantly employed diffusion models f…