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

Publications

MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation

MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation

SIGGRAPH, 2025

A model that integrates user-driven controls into image-to-video (I2V) generation models

Seurat: From Moving Points to Depth

Seurat: From Moving Points to Depth

CVPR, 2025

Inferring depth from point trajectories

Exploring Temporally-Aware Features for Point Tracking

Exploring Temporally-Aware Features for Point Tracking

CVPR, 2025

A feature backbone for point tracking with built-in temporal awareness

LocoTrack: Local All-Pair Correspondence for Point Tracking
FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking

FlowTrack: Revisiting Optical Flow for Long-Range Dense Tracking

CVPR, 2024

Dense point tracking on long-range videos.

INVE: Interactive Neural Video Editing

INVE: Interactive Neural Video Editing

CGI, 2023

A real-time video editing pipeline via edits propagation.

Layered Controllable Video Generation

Layered Controllable Video Generation

ECCV, 2022 Oral

Using masks to control the generation of videos.

Single Image Video Prediction with Auto-Regressive GANs

Sensors, Volume 22

Animating facial expressions using GANs in an auto-regressive fashion.

Deep Anchored Convolutional Neural Networks

Jiahui Huang, Kshitij Dwivedi, Gemma Roig
CVPR Workshops, 2019 Oral

A highly efficitn neural network architecture that reuses weights from different layres.

Highlight Projects