5 papers
ReLumix: Extending Image Relighting to Video via Video Diffusion Models
Lezhong Wang, Shutong Jin, Ruiqi Cui +3
Controlling illumination during video post-production is a crucial yet elusive goal in computational photography. Existing methods often lack flexibility, restricting users to cert…
Physically-based Lighting Generation for Robotic Manipulation
Shutong Jin, Lezhong Wang, Ben Temming +1
In this paper, we propose the first framework that leverages physically-based inverse rendering for novel lighting generation on existing real-world human demonstrations of robotic…
R900: Understanding the Cost-Effectiveness of Random Exploration from 900 Hours of Robotic Data Collection
Shutong Jin, Axel Kaliff, Ruiyu Wang +2
Data scarcity presents a key bottleneck for imitation learning in robotic manipulation. In this paper, we focus on random exploration data-actions and video sequences produced auto…
One-Shot Federated Learning with Classifier-Free Diffusion Models
Obaidullah Zaland, Shutong Jin, Florian T. Pokorny +1
Federated learning (FL) enables collaborative learning without data centralization but introduces significant communication costs due to multiple communication rounds between clien…
PACA: Perspective-Aware Cross-Attention Representation for Zero-Shot Scene Rearrangement
Shutong Jin, Ruiyu Wang, Kuangyi Chen +1
Scene rearrangement, like table tidying, is a challenging task in robotic manipulation due to the complexity of predicting diverse object arrangements. Web-scale trained generative…