| CARVIEW |
Hello 👋, I'm Gabriel (Jiahui) Huang
I’m a Research Scientist/Engineer at Adobe Research, working on topics related to video processing and editing.
I live in the beautiful city of Vancouver, Canada 🇨🇦, where I previously received my Master’s degree from UBC under Leonid Sigal.
News
- Oct 2024: Presented project “Clean Machine” at Adobe Max Sneaks 2024.
- Oct 2023: Presented project “Fast Fill” at Adobe Max Sneaks 2023.
- Feb 2023: I joined Adobe Research as a research scientist/engineer.
- Oct 2022: Internship project “Instant Add” show-cased at Adobe Max Sneaks 2022.
Publications
Exploring Temporally-Aware Features for Point Tracking
A feature backbone for point tracking with built-in temporal awareness
MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation
A model that integrates user-driven controls into image-to-video (I2V) generation models
LocoTrack: Local All-Pair Correspondence for Point Tracking
A highly accurate and efficient model for point tracking.
FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking
Dense point tracking on long-range videos.
INVE: Interactive Neural Video Editing
A real-time video editing pipeline via edits propagation.
Layered Controllable Video Generation
Using masks to control the generation of videos.
Single Image Video Prediction with Auto-Regressive GANs
Animating facial expressions using GANs in an auto-regressive fashion.
Duality diagram similarity: a generic framework for initialization selection in task transfer learning
A metric that measures the similarity between neural networks.
Deep Anchored Convolutional Neural Networks
A highly efficitn neural network architecture that reuses weights from different layres.