Yanhong Zeng 曾艳纒

Yanhong Zeng is currently a researcher at Shanghai AI Laboratory. Before that, she obtained her computer science Ph.D. degree in the joint doctoral program between Sun Yat-sen University and Microsoft Research Asia (MSRA) in 2022, supervised by Prof. Hongyang Chao and Dr. Baining Guo.

Her research interests is developing high-quality and controllable generative models for open-domain multi-modality generation (e.g., image, video, and audio, etc.).

CV  /  Email  /  Google Scholar  /  Twitter  /  Github  /  Linkedin

profile photo

status: struggle with ddl

News

  • [2024.09] πŸŽ‰ HumanVid is accepted by NeurIPS 2024 (D&B Track).
  • [2024.09] πŸŽ‰ MotionBooth is accepted by NeurIPS 2024 (Spotlight).
  • [2024.07] πŸŽ‰ PowerPaint is accepted by ECCV 2024.
  • [2024.03] πŸŽ‰ PIA and Make-it-Vivid are accepted by CVPR 2024.
  • [2024.02] πŸ”₯ Our technology has been shipped in the animation series "Poems of Timeless Acclaim", which is broadcasted in over 10 languages and on more than 70 mainstream media platforms overseas. It has reached an audience of nearly 100 million worldwide viewers within two weeks.
  • [2024.01] πŸ”₯ We release MagicMaker, an AI platform that supports image generation, editing and animation!

Selected Publications

HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Zhenzhi Wang, Yixuan Li, Yanhong Zeng, Yuwei Guo, Youqing Fang, Wenran Liu, Jing Tan, Kai Chen, Tianfan Xue, Bo Dai, Dahua Lin
NeurIPS, 2024 (D&B Track)
project page / arXiv / code

HumanVid is the first large-scale high-quality dataset tailored for human image animation, which combines crafted real-world and synthetic data.

MotionBooth: Motion-Aware Customized Text-to-Video Generation
Jianzong Wu, Xiangtai Li, Yanhong Zeng, Jiangning Zhang, Qianyu Zhou, Yining Li, Yunhai Tong, Kai Chen
NeurIPS, 2024 (Spotlight)
project page / video / arXiv / code

MotionBooth is designed for animating customized subjects with precise control over both object and camera movements.

FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds
Yiming Zhang, Yicheng Gu, Yanhong Zeng ♦, Zhening Xing, Yuancheng Wang, Zhizheng Wu, Kai Chen
Arxiv, 2024
project page / video / arXiv / demo / code

FoleyCrafter is a text-based video-to-audio generation framework which can generate high-quality audios that are semantically relevant and temporally synchronized with the input videos.

Live2Diff: Live Stream Translation via Uni-directional Attention in Video Diffusion Models
Zhening Xing, Gereon Fox, Yanhong Zeng, Xingang Pan, Mohamed Elgharib, KChristian Theobalt , Kai Chen
Arxiv, 2024
project page / video / arXiv / demo / code

Live2Diff is the first attempt that enables uni-directional attention modeling to video diffusion models for live video steam processing, and achieves 16FPS on RTX 4090 GPU.

StyleShot: A SnapShot on Any Style
Junyao Guo, Yanchen Liu, Yanan Sun, Yinhao Tang, Yanhong Zeng, Kai Chen, Cairong Zhao,
Arxiv, 2024
project page / video / arXiv / demo / code

StyleShot is a style transfer model that excels in text and image-driven style transferring without test-time style-tuning.

A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting
Junhao Zhuang, Yanhong Zeng, Wenran Liu, Chun Yuan, Kai Chen
ECCV, 2024
project page / video / arXiv / demo / code

PowerPaint is the first versatile inpainting model that achieves SOTA in text-guided and shape-guided object inpainting, object removal, outpainting, etc.

PIA: Your Personalized Image Animator via Plug-and-Play Modules in Text-to-Image Models
Yiming Zhang*, Zhening Xing*, Yanhong Zeng ♦, Youqing Fang, Kai Chen
CVPR, 2024
project page / video / arXiv / demo / code

PIA can animate any images from personalized models by text while preserving high-fidelity details and unique styles.

Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text
Junshu Tang, Yanhong Zeng, Ke Fan, Xuheng Wang, Bo Dai, Lizhuang Ma, Kai Chen
CVPR, 2024
project page / video / arXiv / code

We present Make-it-Vivid, the first attempt that can create plausible and consistent texture in UV space for 3D biped cartoon characters from text input within few seconds.

Aggregated Contextual Transformations for High-Resolution Image Inpainting
Yanhong Zeng, Jianlong Fu, Hongyang Chao, Baining Guo
TVCG, 2023
project page / arXiv / video 1 / video 2 / code

In AOT-GAN, we propose aggregated contextual transformations and a novel mask-guided GAN training strategy for high-resolution image inpaining.

hdvila Advancing High-Resolution Video-Language Representation with Large-Scale Video Transcriptions
Yanhong Zeng*, Hongwei Xue*, Tiankai Hang*, Yuchong Sun*, Bei Liu, Huan Yang, Jianlong Fu, Baining Guo
CVPR, 2022
arXiv / video / code

We collect a large dataset which is the first high-resolution dataset including 371.5k hours of 720p videos and the most diversified dataset covering 15 popular YouTube categories.

Improving Visual Quality of Image Synthesis by A Token-based Generator with Transformers
Yanhong Zeng, Huan Yang, Hongyang Chao, Jianbo Wang, Jianlong Fu
NeurIPS, 2021
arXiv

We propose a token-based generator with Transformers for image synthesis. We present a new perspective by viewing this task as visual token generation, controlled by style tokens.

Learning Joint Spatial-Temporal Transformations for Video Inpainting
Yanhong Zeng, Hongyang Chao, Jianlong Fu
ECCV, 2020
project page / arXiv / video 1 / more results / code

We propose STTN, the first transformer-based model for high-quality image inpainting, setting a new state-of-the-art performance.

Learning Pyramid Context-Encoder Network for High-Quality Image Inpainting
Yanhong Zeng, Hongyang Chao, Jianlong Fu, Baining Guo
CVPR, 2019
project page / arXiv / video / code

We propose PEN-Net, the first work that is able to conduct both semantic and texture inpainting. To achieve this, we propose cross-layer attention transfer and pyramid filling strategy.

3D Human Body Reshaping with Anthropometric Modeling
Yanhong Zeng, Hongyang Chao, Jianlong Fu
ICIMCS, 2017
project page / arXiv / video / code

We design a 3D human body reshaping system. It can take as input user's anthropometric measurements (e.g., height and weight) and generate a 3D human shape for the user.

Projects

MagicMaker

Project Owner, 2023.04 ~ 2024.01

MagicMaker is a user-friendly AI platform that enables seamless image generation, editing, and animation. It empowers users to transform their imagination into captivating cinema and animations with ease.
OpenMMLab/MMagic

Lead Core Maintainer, 2022.07 ~ 2023.08

OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic πŸͺ„: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.

Working Experience

Shanghai AI Laboratory

Researcher, 2022.07 ~ Present


Microsoft Research Asia (MSRA)

Research Intern, 2018.06 ~ 2021.12

Research Intern, 2016.06 ~ 2017.06


Miscellanea


The website template was adapted from Jon Barron.