Jiwen Yu

I am a third year master student at Peking University, VILLA, advised by Prof.Jian Zhang. My research interests are focused on images/videos generation, editing, and restoration.

Currently, I am interning at Tencent AI Lab, where my research focuses on video editing, working closely with Xiaodong Cun.

Email  /  Google Scholar  /  Github  /  CV

profile photo
Research

In the past, my research primarily focused on image restoration problems, which can be considered as conditional image generation tasks where the conditions are degraded images. Recently, I have expanded my research interests to broader areas, including image generation/editing and video editing, utilizing cutting-edge diffusion-based technologies. Moving forward, I plan to continue my research in the field of AIGC-related image/video generation, editing, and restoration.

I am currently seeking a PhD position starting in fall 2024, focusing on research related to AIGC applications in the domains of images, videos, and 3D. If you have any openings or recommendations, please don't hesitate to contact me via email.

AnimateZero: Video Diffusion Models are Zero-Shot Image Animators
Jiwen Yu, Xiaodong Cun, Chenyang Qi, Yong Zhang, Xintao Wang, Ying Shan, Jian Zhang
ArXiv, 2023
code / arXiv / paper / project page

We propose AnimateZero, a zero-shot approach for image animation on generated images. AnimateZero also supports various applications, such as video editing, frame interpolation, real image animation, and more.

CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography
Jiwen Yu, Xuanyu Zhang, Youmin Xu, Jian Zhang
NeurIPS, 2023
code / arXiv

We propose a novel diffusion-based image steganography framework named Controllable, Robust, and Secure Image Steganography (CRoSS). This framework offers significant advantages in controllability, robustness, and security compared to cover-based image steganography methods. Importantly, these benefits are achieved without requiring additional training.

FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
Jiwen Yu, Yinhuai Wang, Chen Zhao, Bernard Ghanem, Jian Zhang
ICCV, 2023
code / arXiv

FreeDoM is a simple but effective training-free method generating results under control from various conditions using unconditional diffusion models.

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Yinhuai Wang*, Jiwen Yu*, Jian Zhang (*denotes equal contribution)
ICLR, 2023   (Oral Presentation)
project page / arXiv / code

We bring Range-Null space Decomposition (RND) into diffusion models, enabling diverse image restoration tasks in a zero-shot manner, without extra training or optimization.

Experience
Research Intern, Tencent AI Lab
April, 2023 - Present

This cool template is stolen from Jon Barron!