Puntawat Ponglertnapakorn

I am a Ph.D. candidate under the supervision of Prof. Supasorn Suwajanakorn in the Vision and Learning Lab (VLL) at VISTEC, Thailand. My research focuses on applying deep learning and generative models to face relighting, human motion generation for football players, and computer vision for sports virtual replay and reconstruction. I’m passionate about exploring how these approaches can be applied to the football domain, including modeling player movements and recreating virtual replay experiences.

Selected Publications

Where Is The Ball: 3D Ball Trajectory Estimation From 2D Monocular Tracking

"An approach for 3D ball trajectory estimation from a 2D tracking sequence that generalizes to real-world trajectories, despite being trained solely on simulation."

Puntawat Ponglertnapakorn, Supasorn Suwajanakorn

I sincerely thank Dr. Konstantinos Rematas for his valuable guidance and support.

11th CVsports @ CVPR 2025

Project Page · Paper

DiFaReli++: Diffusion Face Relighting With Consistent Cast Shadows

"An extension to DiFaReli that improves cast shadows by enabling removal or alteration of hard cast shadows with temporal consistency, and achieves faster relighting in a single network pass."

Puntawat Ponglertnapakorn, Nontawat Tritrong, Supasorn Suwajanakorn

Arxiv Preprint 2025

Project Page · Paper

DiFaReli: Diffusion Face Relighting

"A novel approach to single-view face relighting in the wild leveraging a conditional diffusion implicit model (DDIM) without any need for light stage data, multi-view images, or lighting ground truth."

Puntawat Ponglertnapakorn, Nontawat Tritrong, Supasorn Suwajanakorn

ICCV 2023

Project Page · Paper

Other Publications

Revealing Preference in Popular music Through Familiarity and Brain Response

"A music preference study, factorized by familiarity score and brain responses (EEG) while listening to music with and without lyrics."

Soravitt Sangnark, Phairot Autthasan, Puntawat Ponglertnapakorn, Phudit Chalekarn, Thapanun Sudhawiyangkul, Manatsanan Trakulruangroj, Sarita Songsermsawad, Rawin Assabumrungrat, Supalak Amplod, Kajornvut Ounjai, Theerawit Wilaiprasitporn

IEEE Sensor Journal 2021

Dataset · Paper

Improving Heart Rate Estimation on Consumer Grade Wrist-Worn Device Using Post-Calibration Approach

"A method to improve heart rate estimation from various consumer-grade wrist-worn devices toward medical-grade accuracy."

Tanut Choksatchawathi, Puntawat Ponglertnapakorn, Apiwat Ditthapron, Pitshaporn Leelaarporn, Thayakorn Wisutthisen, Maytus Piriyajitakonkij, Theerawit Wilaiprasitporn

IEEE Sensor Journal 2020

Paper