12 papers
ProjFormer: Point Cloud Completion via Geometric-Projective Transformer and Cross-Modal Semantic Constraints
Sheng Liu, Meng Wang, Ruihui Li +3
Point cloud completion is inherently ill-posed due to severe sparsity and ambiguity in partial observations. Existing multi-view methods alleviate this by incorporating 2D semantic…
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
Existing point-based generative methods for outdoor scenes primarily focus on LiDAR-conditioned completion. During training, noisy point clouds are constructed by perturbing comple…
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…
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…
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…
Self-Supervised Point Cloud Completion based on Multi-View Augmentations of Single Partial Point Cloud
Jingjing Lu, Huilong Pi, Yunchuan Qin +2
Point cloud completion aims to reconstruct complete shapes from partial observations. Although current methods have achieved remarkable performance, they still have some limitation…
VLScene: Vision-Language Guidance Distillation for Camera-Based 3D Semantic Scene Completion
Meng Wang, Huilong Pi, Ruihui Li +3
Camera-based 3D semantic scene completion (SSC) provides dense geometric and semantic perception for autonomous driving. However, images provide limited information making the mode…
Vision-based 3D Semantic Scene Completion via Capture Dynamic Representations
Meng Wang, Fan Wu, Yunchuan Qin +3
The vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, the presence of dynamic objects in th…
Learning Temporal 3D Semantic Scene Completion via Optical Flow Guidance
Meng Wang, Fan Wu, Ruihui Li +3
3D Semantic Scene Completion (SSC) provides comprehensive scene geometry and semantics for autonomous driving perception, which is crucial for enabling accurate and reliable decisi…
PAR: Prompt-Aware Token Reduction Method for Efficient Large Multimodal Models
Yingen Liu, Fan Wu, Ruihui Li +2
Multimodal large language models (MLLMs) demonstrate strong performance across visual tasks, but their efficiency is hindered by significant computational and memory demands from p…