|
Luchao Qi I am a Ph.D. candidate at the University of North Carolina at Chapel Hill, where I work on computer vision with Roni Sengupta. I previously worked with Bardia Nezami during my time as a software engineer at ValtedSeq. Prior to that, I earned my M.S.E. in Biomedical Engineering and Data Science from Johns Hopkins University, where I was mentored by Brian Caffo. Earlier in my academic journey, I completed my B.S.E. in Biomedical Engineering at Northeastern University under the guidance of Ming Qian at the Shenzhen Institute of Advanced Technology. Opinions are my own and do not represent any affiliated organizations. |
|
|
|
PublicationsIām interested in controlling generative models + multimodalities (e.g. 3D, video, etc.). My previous research focused on personalized face generation and editing. More recently, my work has explored video generation and editing. My future research interests include combining implicit and explicit representations for generative modeling, for example, integrating data-driven approaches with inductive biases. Click here if you'd like to work with me!If you would like to collaborate, the best way to reach out is through email! Depending on the project, please indicate how exactly I can help you with your research in the email. For example,
|
|
Huaizhi Qu, Ruichen Zhang, Shuqing Luo, Luchao Qi, Zhihao Zhang, Xiaoming Liu, Roni Sengupta, Tianlong Chen Under Review arxiv Propagating edited 2D images to 3D representations through video generative models. |
|
Ana Xiong*, Prakrut Patel*, Qingyuan Fan*, Amisha Wadhwa*, Sarathy Selvam, Xiao Guo, Luchao Qi, Xiaoming Liu, Roni Sengupta Under Review project page / arxiv TalkingHeadBench is a benchmark for talking head generation and deepfake detection. |
|
Bang Gong*, Luchao Qi*, Jiaye Wu, Zhicheng Fu, Chunbo Song, David W. Jacobs, John Nicholson, Roni Sengupta SIGGRAPH Asia 2025 project page / arxiv We perform face editing in diffusion models (FLUX) via attention manipulation in a training-free manner, exploring the inversionāediting trade-off in the context of facial aging. |
|
Luchao Qi, Jiaye Wu, Bang Gong, Annie N. Wang, David W. Jacobs, Roni Sengupta SIGGRAPH 2025 (TOG Journal) project page / arxiv / š¤Paper of the Day / tweet Inspired by The Irishman, MyTimeMachine performs personalized de-aging and aging with high fidelity and identity preservation from ~50 selfies, extendable to temporally consistent video. |
|
|
Annie N. Wang, Luchao Qi, Roni Sengupta WACV 2025 project page / arxiv We introduce a continual learning problem of updating personalized 2D and 3D generative face models without forgetting past representations as new photos are regularly captured. |
|
Luchao Qi, Jiaye Wu, Annie N. Wang, Shengze Wang, Roni Sengupta WACV 2025 (Oral) project page / arxiv / tweet / code We personalize a pretrained GAN-based model (EG3D) using a few (~50) selfies of an individual without full finetuning, enabling scalable personalization in a real-world scenario. |
|
|
Luchao Qi, Qi Zhang , Yan Tan, Kwok Ho Lam, Hairong Zheng , Ming Qian IEEE Transactions on Biomedical Engineering 2019 pdf / google scholar We investigate how ultrasound microbeam stimulation affects the intracellular calcium response of human breast cancer cells. |
Miscellanea |
Academic Service |
CVPR 2025 |
|
Web template cloned from jonbarron/website |