Bowei Chen

Bowei Chen （陈柏维）

I am a Ph.D. student at University of Washington, working with Prof. Steve Seitz, Prof. Brian Curless, and Prof. Ira Kemelmacher-Shlizerman.

Previously, I was a master student in Robotics Institute at Carnegie Mellon University, supervised by Prof. Srinivasa Narasimhan. I also worked with Prof. Martial Hebert, Dr. Sing Bing Kang, and Dr. Tiancheng Zhi.

I did my bachelors at Northeastern University , where I worked with Prof. Jean-François Lalonde, Prof. Guibing Guo, and Dr. Fajie Yuan.

I will be graduating in 2026 and am actively seeking industry positions starting in Summer (or potentially Spring) 2026. Please feel free to contact me if you have any opportunities.

Email / Linkedin / CV / Google Scholar / Github

Research

I am broadly interested in visual generative models, with a particular focus on image and video generation. My work explores visual tokenizers and develops novel methods as well as creative applications for generative models.

News

June 2025: Starting my summer internship at Adobe, mentored by Kai Zhang, working on visual tokenization and generative models.
July 2024: Our paper Inverse Painting was accepted to SIGGRAPH Asia 2024!
April 2024: Our paper Total Selfie was accepted to CVPR 2024 and selected as a Highlight!
June 2023: Started my summer internship at TikTok, mentored by Tiancheng Zhi, working on portrait image editing.
September 2022: Graduated from CMU and began my PhD at the University of Washington.
July 2022: Our paper NPP-Net was accepted to ECCV 2022!
March 2022: Our paper Semantically Supervised Appearance Decomposition was accepted to SIGGRAPH 2022!

Selected Publications

* indicates equal contribution

	Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models Bowei Chen, Sai Bi, Hao Tan, He Zhang, Tianyuan Zhang, Zhengqi Li, Yuanjun Xiong, Jianming Zhang, Kai Zhang. Preprint 2025 (New!) [Website] [Arxiv] We propose aligning pretrained visual encoders to serve as tokenizers for latent diffusion models in image generation. This introduces a new tokenizer training paradigm that produces a semantically rich latent space, improving diffusion model performance.
	Generating Fit Check Videos with a Handheld Camera Bowei Chen, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz. Preprint 2025 [Arxiv] [Code] Our approach takes as input two static photos (front and back) of you in a mirror, along with an IMU motion reference that you perform while holding your mobile phone, and synthesizes a realistic video of you performing a similar target motion.
	Inverse Painting: Reconstructing The Painting Process Bowei Chen, Yifan Wang, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz. SIGGRAPH Asia 2024 [Website] [Video] [Code] Given an input painting, we reconstruct a time-lapse video of how it may be painted.
	Total Selfie: Generating Full Body Images from Selfies Bowei Chen, Brian Curless, Ira Kemelmacher-Shlizerman, Steven M. Seitz. CVPR 2024 (Highlight) [Website] [Video] [Code] Take an image of your face, legs, shoes, and body with your phone and we'll generate a full body selfie for you.
	Learning Feature-Preserving Portrait Editing from Generated Pairs Bowei Chen, Tiancheng Zhi, Peihao Zhu, Shen Sang, Jing Liu, Linjie Luo, Preprint 2024 [Arxiv] [Code] Given a portrait image, we applies advanced editing effects by training on automatically generated training pairs.
	Learning Continuous Implicit Representation for Near-Periodic Patterns Bowei Chen, Tiancheng Zhi, Martial Hebert, Srinivasa Narasimhan. ECCV 2022 [Arxiv] [Paper] [Website] [Video] [Poster] [Supp] [Code] Present a periodicity-aware framework to learn Near-Periodic Patterns (NPP) representation, which enables various applications including NPP completion, resolution-enhanced remapping, and segmentation.
	Semantically Supervised Appearance Decomposition for Virtual Staging from a Single Panorama Tiancheng Zhi, Bowei Chen, Ivaylo Boyadzhiev, Sing Bing Kang, Martial Hebert, Srinivasa Narasimhan. SIGGRAPH 2022 [Paper] [Website] [Code] Present a weakly supervised appearance decomposition for a single indoor panorama. The applications include furniture insertion, sunlight direction changing, and floor material changing.
	Leveraging Title-Abstract Attentive Semantics for Paper Recommendation Guibing Guo, Bowei Chen, Xiaoyan Zhang, Zhirong Liu, Zhenhua Dong, Xiuqiang He. AAAI 2020 [paper] Propose a two-level attentive neural network to capture title-abstract semantics relationships for paper recommendation.

The website's style is borrowed from this amazing guy.