News
- Jun 2022: One paper on rPPG augmentation conditionally accepted in ICCP '22.
- Jun 2022: Our lab is going to CVPR '22 in person. Come and say hello!
- Mar 2022: One paper accepted in CVPR '22. Stay tuned!
|
Experience
Google
Student Researcher, 2023-2024
|
Selected papers
In general, I'm interested in computer vision and its application in machine autonomy and digital health. I'm passionate about problems in capture (sensing and reconstruction) & synthesis (rendering) of the physical world to all the subtleties, ranging from indoor and natural outdoor scenes to human face and body.
|
|
ALTO: Alternating Latent Topologies for Implicit 3D Reconstruction
Zhen Wang*,
Shijie Zhou*,
Jeong Joon Park,
Despoina Paschalidou, Suya You,
Gordon Wetzstein,
Leonidas Guibas,
Achuta Kadambi,
CVPR 2023,
Project website
Rethinking latent topologies for fast and detailed implicit 3D reconstructions.
|
|
Synthetic Generation of Face Videos with Plethysmograph Physiology
Zhen Wang*,
Yunhao Ba*,
Pradyumna Chari,
Oyku Deniz Bozkurt,
Gianna Brown, Parth Patwa, Niranjan Vaddi, Laleh Jalilian,
Achuta Kadambi,
CVPR 2022,
Project website
A scalable biophysical neural rendering method to generate biorealistic synthetic rPPG videos given any reference image and target blood flow.
|
|
Style Transfer with Bio-realistic Appearance Manipulation for Skin-tone Inclusive rPPG
Yunhao Ba*,
Zhen Wang*,
Kerim Doruk Karinca,
Oyku Deniz Bozkurt,
Achuta Kadambi,
ICCP 2022,
Project website
A first attempt that transfers light-skinned subjects to dark skin tones while preserving the pulse signals in the facial videos.
|
August 2022 (Pasadena, CA): IEEE International Conference on Computational Photography (ICCP) 2022 | Video
April 2022 (Caltech): Synthetic Generation of Face Videos with Plethysmograph Physiology (Host: Prof. Katie Bouman)
|
CVPR 2024, ICLR 2024, AAAI 2024, NeurIPS 2023, ICCV 2023, Neural Fields @ ICLR 2023, CVPR 2023, APSIPA Transactions on Signal and Information Processing 2023 (Editor: Prof. C.-C. Jay Kuo), SDM 2021, AAAI 2021.
|
Thanks to Jon Barron for the source code of this website.
|
|