3 papers
cs.RO2026
Monocular 3D Occupancy Perception for Robots on Sidewalks via Hybrid 2D-3D Learning
Yukai Ma, Joe Lin, Liu Liu +5
Sidewalks in the real world are crowded, cluttered, and less structured than roads, making 3D occupancy prediction a key ingredient for the safe navigation of mobile robots such as…
cs.CV2025
Joint Optimization for 4D Human-Scene Reconstruction in the Wild
Zhizheng Liu, Joe Lin, Wayne Wu +1
Reconstructing human motion and its surrounding environment is crucial for understanding human-scene interaction and predicting human movements in the scene. While much progress ha…
cs.CV2024
Learning to Generate Diverse Pedestrian Movements from Web Videos with Noisy Labels
Zhizheng Liu, Joe Lin, Wayne Wu +1
Understanding and modeling pedestrian movements in the real world is crucial for applications like motion forecasting and scene simulation. Many factors influence pedestrian moveme…