Fuxin Li
@fuxinli.bsky.social
Computer Vision, Explainable Deep Learning, Point Clouds, 3D Perception
We can usually only get partial observations of scenes, but getting complete object information could be helpful for many tasks in robotics and graphics. Our new ICLR 2025 paper extends point-based single object completion models to completing multiple objects in a scene, (1/3)🧵
February 11, 2025 at 6:59 AM
We can usually only get partial observations of scenes, but getting complete object information could be helpful for many tasks in robotics and graphics. Our new ICLR 2025 paper extends point-based single object completion models to completing multiple objects in a scene, (1/3)🧵