CARVIEW

MOTORHOMES

Select Language

HTTP/2 200 server: GitHub.com content-type: text/html; charset=utf-8 last-modified: Thu, 13 Feb 2025 11:31:51 GMT access-control-allow-origin: * etag: W/"67add827-959c" expires: Sun, 28 Dec 2025 21:23:22 GMT cache-control: max-age=600 content-encoding: gzip x-proxy-cache: MISS x-github-request-id: 4D46:1F53DD:802E81:8FD3E5:69519D72 accept-ranges: bytes age: 0 date: Sun, 28 Dec 2025 21:13:22 GMT via: 1.1 varnish x-served-by: cache-bom-vanm7210078-BOM x-cache: MISS x-cache-hits: 0 x-timer: S1766956403.680169,VS0,VE206 vary: Accept-Encoding x-fastly-request-id: 3830e4d6e2d977253bd17a747ef810e8dc355a11 content-length: 5850 Hao Ouyang

Hao Ouyang (欧阳豪)

I am a passionate researcher specializing in Generative AI, with a focus on advancing image and video editing. I completed my PhD at HKUST under the inspiring supervision of Prof. Qifeng Chen and had the honor of collaborating with Prof. Jiaya Jia on my final-year project during my Bachelor’s at CUHK. My journey has also taken me through internships at Google Research, Microsoft Research Asia, Ant Research, Tencent, and Sensetime. Currently, I work as a research scientist at Ant Group. I welcome opportunities for collaboration—please feel free to reach out.

Email Google Scholar Github

Publications

MagicQuill: An Intelligent Interactive Image Editing System

Zichen Liu*, Yue Yu*, Hao Ouyang, Qiuyu Wang, Ka Leong Cheng, Wen Wang, Zhiheng Liu, Qifeng Chen, Yujun Shen

Hao Ouyang (欧阳豪)

Publications

MagicQuill: An Intelligent Interactive Image Editing System

AniDoc: Animation Creation Made Easier

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Framer: Interactive frame interpolation

Edicho: Consistent Image Editing in the Wild

DepthLab: From Partial to Complete

MangaNinja: Line Art Colorization with Precise Reference Following

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

Internal Video Inpainting by Implicit Long-range Propagation

MagicQuill: An Intelligent Interactive Image Editing System

Real-time 3d-aware portrait editing from a single image

AniDoc: Animation Creation Made Easier

LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis

Framer: Interactive frame interpolation

Edicho: Consistent Image Editing in the Wild

DepthLab: From Partial to Complete

MangaNinja: Line Art Colorization with Precise Reference Following

Text2Immersion: Generative Immersive Scene with 3D Gaussians

CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior

Dynamic Typography: Bringing Text to Life via Video Diffusion Prior

High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization

Learning Naturally Aggregated Appearance for Efficient 3D Editing

Pretraining is All You Need for Image-to-Image Translation

Restorable Image Operators with Quasi-Invertible Networks

Real-Time Neural Character Rendering with Pose-Guided Multiplane Images

Internal Video Inpainting by Implicit Long-range Propagation

Neural Camera Simulators

Deep Video Prior for Video Consistency and Propagation

Neural Camera Simulators

Image Inpainting with External-internal Learning and Monochromic Bottleneck

Hiding Video in Audio via Reversible Generative Models

Human pose estimation with spatial contextual information

Affiliations