I am a Research Scientist at Google.
I received my Ph.D. in Computer Science and Engineering from the University of Minnesota, Twin Cities, advised by Prof. Hyun Soo Park.
My research is in computer vision and computer graphics with a focus on Generative AI. I specifically focus on obtaining human and garment geometry, and their 3D deformation across various shapes and poses from images and videos. My goal is to use in-the-wild images and videos, without the need for ground truth information, to train computational models by employing geometry-aware self-supervision signals.
[Email | Google Scholar | LinkedIn | GitHub | CV]
Publications
Learning Geometric Representation of Dressed Humans
Yasamin Jafarian
PhD Thesis, Computer Science and Engineering, University of Minnesota 2023
[Pdf]
Normal-guided Garment UV Prediction for Human Re-texturing
Yasamin Jafarian, Tuanfeng Yang Wang, Duygu Ceylan, Jimei Yang, Nathan Carr, Yi Zhou, Hyun Soo Park
IEEE Computer Vision and Pattern Recognition (CVPR 2023),
[Highlight (10% of accepted papers, 2.5% of submissions)]
[Pdf | Video | Project Website | BibTeX]
Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos
Yasamin Jafarian, Hyun Soo Park
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI 2022), [Journal]
Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos
Yasamin Jafarian, Hyun Soo Park
IEEE Computer Vision and Pattern Recognition (CVPR 2021),
[Oral presentation] [Best Paper Honorable Mention Award]
Dataset
340 dance videos from TikTok mobile social networking application
Short videos (10-15 seconds) of diverse dance challenges
In total, more than 100K images along with high fidelity Segmentation, and UV coordinates from DensePose.
We provide the dance names and raw videos as well for motion detection tasks.
Internship
Research Intern
[Remote] Mountain View, CA | (Nov 2022 - March 2023.)
With Dr. Ahmed Gawish and Dr. Rohit Kumar Pandey
Intern - Research Scientist
[Remote] San Jose, USA | 2022 (March - June.)
With Dr. Duygu Ceylan and Dr. Tuanfeng Y. Wang
Honors & Awards
CVPR 2023 Outstanding Reviewer | 2023
I was chosen as an outstanding reviewer in CVPR 2023 (Out of 7,000 reviewers, 232 exceptional reviewers (3.3% of the reviewers) were selected as outstanding reviewers based on nominations and ratings provided by the Area Chairs).
CVPR 2023 Highlight paper | 2023
The paper "Normal-guided Garment UV Prediction for Human Re-texturing" is accepted as a highlight paper at CVPR 2023 (10% of accepted papers, 2.5% of submissions).
CVPR 2023 Doctoral Consortium | 2023
Accepted in the CVPR 2023 Doctoral Consortium (13% of the applications).
UMII-MnDRIVE PhD Graduate Assistantship | 2022
Received the UMII-MnDRIVE PhD Graduate Assistantship Award from the University of Minnesota Informatics Institute (UMII) ($54,946.00).
Best Paper Honorable Mention Award at CVPR 2021 | 2021
Received the Best Paper Honorable Mention Award at CVPR 2021 for my paper "Learning High-Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos"
FOE Prize | 2013
Ranked first in GPA among the hardware computer engineering class of 2013 at the University of Tehran.
News
Aug 2024: I am invited to to serve as Program Committee in AAAI 2025.
Feb 2024: I am invited to be a reviewer at ECCV 2024.
Oct 2023: I started as a Research Scientist at Google.
Sep 2023: I defended my Ph.D. thesis in "Learning Geometric Representation of Dressed Humans".
May 2023: I was chosen as an outstanding reviewer at CVPR 2023 (Out of 7,000 reviewers, 232 exceptional reviewers (3.3% of the reviewers) were selected as outstanding reviewers based on nominations and ratings provided by the Area Chairs).
March 2023: The paper "Normal-guided Garment UV Prediction for Human Re-texturing" is selected as a highlight at CVPR 2023 (10% of accepted papers, 2.5% of submissions).
March 2023: I was accepted into the CVPR 2023 Doctoral Consortium (13% of the applications).
March 2023: The paper "Normal-guided Garment UV Prediction for Human Re-texturing" is accepted in CVPR 2023.
Feb 2023: I am invited to be a reviewer at ICCV 2023.
Dec 2022: The paper "Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos" is accepted to TPAMI.
Nov 2022: I am invited to be a reviewer at CVPR 2023.
Nov 2022: I started as a research intern at Google Research.
March 2022: I started as a research intern at Adobe Research.
Jan 2022: I received the "UMII-MnDRIVE PhD Graduate Assistantship" from the University of Minnesota Informatics Institute (UMII)
June 2021: The paper "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos" won the Best Paper Honorable Mention.
June 2021: The TikTok dataset is published in the Kaggle.
June 2021: The paper "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos" is chosen as a CVPR best paper candidate.
Mar 2021: The paper "Learning High Fidelity Depths of Dressed Humans by Watching Social Media Dance Videos" is accepted for oral presentation in CVPR 2021.
Jul 2019: The paper "MONET: Multiview Semi-supervised Keypoint via Epipolar Divergence" Is accepted to ICCV 2019.