8 papers
3D Point World Models: Point Completion Enables More Accurate Dynamics Learning
Skand Peri, Hung Nguyen, Chanho Kim +2
Learning predictive models of the world enables robotic control through planning, potentially allowing robots to improvise solutions on new tasks. However, large video-based dynami…
Learning a Particle Dynamics Model with Real-world Videos
Chanho Kim, Suhas V. Sumukh, Li Fuxin
Data-driven learning approaches for physics simulation, sometimes referred to as world models, have emerged as promising alternatives to traditional physics simulators due to their…
GS4: Generalizable Sparse Splatting Semantic SLAM
Mingqi Jiang, Chanho Kim, Chen Ziwen +1
Traditional SLAM algorithms excel at camera tracking, but typically produce incomplete and low-resolution maps that are not tightly integrated with semantics prediction. Recent wor…
Long-Term 3D Point Tracking By Cost Volume Fusion
Hung Nguyen, Chanho Kim, Rigved Naukarkar +1
Long-term point tracking is essential to understand non-rigid motion in the physical world better. Deep learning approaches have recently been incorporated into long-term point tra…
Point Cloud Models Improve Visual Robustness in Robotic Learners
Skand Peri, Iain Lee, Chanho Kim +3
Visual control policies can encounter significant performance degradation when visual conditions like lighting or camera position differ from those seen during training -- often ex…
Object Dynamics Modeling with Hierarchical Point Cloud-based Representations
Chanho Kim, Li Fuxin
Modeling object dynamics with a neural network is an important problem with numerous applications. Most recent work has been based on graph neural networks. However, physics happen…
Out of Sight, Still in Mind: Reasoning and Planning about Unobserved Objects with Video Tracking Enabled Memory Models
Yixuan Huang, Jialin Yuan, Chanho Kim +4
Robots need to have a memory of previously observed, but currently occluded objects to work reliably in realistic environments. We investigate the problem of encoding object-orient…
Space Time Recurrent Memory Network
Hung Nguyen, Chanho Kim, Fuxin Li
Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the featur…