ArpitsinhVaghela

PhD Student

Active Perception Group, Arizona State University

Advised by Dr. Yezhou Yang, I work on 3D scene representation and generation, and on how Gaussian splatting and diffusion models can reconstruct and edit dynamic scenes from imperfect real-world capture.

From pictures to worlds.

Google Scholar Resume GitHub Email

Research

Publications

Event-Guided Dynamic Reconstruction under Extreme Motion Blur

Workshop on Physical World AI, Conference on Neural Information Processing Systems (NeurIPS), 2026

Arpitsinh Vaghela, Aayush Atul Verma, Kaustav Chanda, Chi-Yao Huang, Duo Lu, Bharatesh Chakravarthi, Yezhou Yang

Project page PDF Code

eTraM: Event-based Traffic Monitoring Dataset

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024Highlight

Aayush Atul Verma, Bharatesh Chakravarthi, Arpitsinh Vaghela, Hua Wei, Yezhou Yang

Project page PDF arXiv

SEVD: Synthetic Event-based Vision Dataset for Ego and Fixed Traffic Perception

IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2024

Manideep Reddy Alimati, Bharatesh Chakravarthi, Aayush Atul Verma, Arpitsinh Vaghela, Hua Wei, Xuesong Zhou, Yezhou Yang

Project page PDF arXiv

et al.

SynTraC: A Synthetic Dataset for Traffic Signal Control from Traffic Monitoring Cameras

IEEE International Conference on Intelligent Transportation Systems (ITSC), 2024

Tiejin Chen, Prithvi Shirke, Bharatesh Chakravarthi, Arpitsinh Vaghela, Longchao Da, Duo Lu, Yezhou Yang, Hua Wei

PDF arXiv Code