Xiaoyu Xiang
Scholar

Xiaoyu Xiang

Google Scholar ID: KTn1AoUAAAAJ
Research Scientist, Meta Reality Labs
Computer VisionDeep LearningImage Processing
Citations & Impact
All-time
Citations
1,560
 
H-index
14
 
i10-index
21
 
Publications
20
 
Co-authors
19
list available
Resume (English only)
Academic Achievements
  • Garment3DGen: 3D Garment Stylization and Texture Generation (arXiv, 2024)
  • PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar (CVPR, 2024, Oral, Best Paper Award Finalist)
  • EfficientSAM: Leveraged Masked Image Pretraining for Efficient Segment Anything (CVPR, 2024, Highlight)
  • UnSAMFlow: Unsupervised Optical Flow Guided by Segment Anything Model (CVPR, 2024)
  • CAD: Photorealistic 3D Generation via Adversarial Distillation (CVPR, 2024)
  • Customizing 360-Degree Panoramas through Text-to-Image Diffusion Models (WACV, 2024)
  • SqueezeSAM: User friendly mobile interactive segmentation (arXiv, 2023)
  • Learning Neural Duplex Radiance Fields for Real-Time View Synthesis (CVPR, 2023)
Research Experience
  • Currently a staff research scientist at Meta Reality Labs, focusing on 3D Computer Vision and Generative-AI research for AR and VR.
Education
  • Ph.D. from Purdue University, advised by Jan Allebach; Bachelor's degree from Tsinghua University.
Background
  • Research interests include Generative Model, Computational Photography, Temporal Modeling, and Novel View Synthesis. Works at Meta Reality Labs on 3D Computer Vision and Generative-AI research for AR and VR.
Miscellany
  • Personal interests and hobbies not provided