Rameen Abdal
Scholar

Rameen Abdal

Google Scholar ID: kEQimk0AAAAJ
Snap Inc.
AIDeep LearningMachine LearningGenerative Modeling
Citations & Impact
All-time
Citations
4,391
 
H-index
15
 
i10-index
16
 
Publications
20
 
Co-authors
20
list available
Resume (English only)
Academic Achievements
  • - Zero-Shot Dynamic Concept Personalization with Grid-Based LoRA, SIGGRAPH Asia, 2025
  • - Dynamic Concepts Personalization from Single Videos, SIGGRAPH, 2025
  • - Improving the Diffusability of Autoencoders, ICML, 2025
  • - Interpreting the Weight Space of Customized Diffusion Models, NeurIPS, 2024
  • - Gaussian Shell Maps for Efficient 3D Human Generation, CVPR, 2024
  • - 3DAvatarGAN: Bridging Domains for Personalized Editable Avatars, CVPR, 2023
  • - Video2StyleGAN: Disentangling Local and Global Variations in a Video, ArXiv pre-print, 2022
  • - HairNet: Hairstyle Transfer with Pose Changes, ECCV, 2022
  • - CLIP2StyleGAN: Unsupervised Extraction of StyleGAN Edit Directions, ACM SIGGRAPH Conference Proceedings, 2022
  • - Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks, ICLR, 2022
  • - Barbershop: GAN-based Image Compositing using Segmentation Masks, 2021
Research Experience
  • - Research Scientist, Snap Inc. (Creative Vision Team), Palo Alto, California, USA, September 2024 - present
  • - Research Intern, Snap Research Creative Vision, Los Angeles, California, USA, June 2022 - Oct 2022
  • - Collaborator (Remote), Adobe Research, London, UK, March 2020 - May 2022
Education
  • - Postdoc, Stanford Computational Imaging Lab, Stanford University, 2023 - 2024, Advisor: Gordon Wetzstein
  • - Ph.D. in Computer Science, KAUST, Visual Computing Center, 2020 - 2023, Advisor: Peter Wonka
  • - MS in Computer Science, KAUST, Visual Computing Center, 2018 - 2020
  • - B.Tech in ECE, National Institute of Technology (NIT), Srinagar, India, 2014 - 2018
Background
  • Research interests include image and video personalization, particularly capturing unique user expressions, motions, and interactions in immersive and collaborative environments.
Miscellany
  • Looking for interns. Feel free to reach out directly.