I am a first-year Ph.D. student at the Department of Computer Science and Engineering, HKUST advised by Prof. Qifeng Chen.
Before joining HUKST. I spend two wonderful years in Huya as a computer vision engineer led by Xintong Han and Jia Xu.
I was an intern at Tencent AI Lab advised by Yibing Song and Wei Liu.
Meanwhile, I have cooperated many times with my good friend Ziyu Wan.
My research interest includes 2D/3D Generation, digital human, neural rendering and contrastive learning.
I love fishing very much, and my dream is to go fishing all over China!
🔥 News
- 2023.06: 🎉🎉 GOAE is accepted to ICCV2023.
- 2023.05: 🎉🎉 I will join Ant Research as an intern, which is supervised by XuanWang. And I will focus on 3D Generation.
- 2023.05: 🎉🎉 XFormer is accepted to IJCAI2023.
- 2023.03: 🎉🎉 My new home page is online.
📝 Selected Publications
Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding.
Ziyang Yuan, Yiming Zhu1, Yu Li, Hongyu Liu and Chun Yuan.
XFormer: Fast and Accurate Monocular 3D Body Capture.
Lihui Qian, Xintong Han, Faqiang Wang, Hongyu Liu, Huawei Wei, Zhe Lin, Haoye Dong, Haoye Dong, Zhiwen Li, Huawei Wei, Zhe Lin and Chengbin Jin.
Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint.
Hongyu Liu, Yibing Song and Qifeng Chen.
Human MotionFormer: Transferring Human Motions with Vision Transformers.
Hongyu Liu, Xintong Han, Chenbin Jin, Lihui Qian, Huawei Wei, Zhe Lin, Faqiang Wang, Haoye Dong, Yibing Song, Jia Xu and Qifeng Chen.
One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations.
Yiming Zhu *, Hongyu Liu *, Yibing Song, Xintong Han, Chun Yuan, Qifeng Chen and Jue Wang (* denotes equal contribution).
Pd-gan: Probabilistic diverse gan for image inpainting.
Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han and Jing Liao.
DeFLOCNet: Deep Image Editing via Flexible Low-level Controls.
Hongyu Liu, Ziyu Wan, Wei Huang, Yibing Song, Xintong Han, Jing Liao, Bin Jiang and Wei Liu.
Rethinking image inpainting via a mutual encoder-decoder with feature equalizations.
Hongyu Liu, Bing Jiang, Yibing Song, Wei Huang and Chao Yang.
Coherent semantic attention for image inpainting.
Hongyu Liu, Bin Jiang, Yi Xiao and Chao Yang.
🙈 Projects
Anime talking heads. Control anime avatar with your expression in real time. We also bulid SDK, which only occupy 9% I7 CPU’s performance (No GPU!).
Paper man. I can drive a 2D image with your skeleton.
Consumer Digital Human. Given a single image(T pose), we can create an avatar and drive this avatar with target motion.
🎖 Honors and Awards
- 2022 HuNan outstanding master graduation thesis.
- 2020 CCF outstanding master graduation thesis.
- 2020 School-level outstanding graduation thesis of HuNan University.
- 2019 National Scholarship.
- 2020 Provincial outstanding graduates of HuNan.
- 2020 School-level outstanding graduates of HuNan University.
- 2018 CCF BIG DATA 2018 best application paper award.
- 2018 Third place out of 390 teams, Few-Shot Classification in AI FUTURELAB 2018.
💬 Invited Talks
- 2021 Combining Deep Neural Networks for Efficient Image Restoration and Editing. Link
✏ Academic Reviewer
- Conference CVPR, ECCV, ICCV, ICLR, NeurIPS, ICML.
- Journal TNNCL, TVCG, TMM, TCSVT
- Outstanding reviewer NeurIPS, 2022
💻 Work Experience
- 2022.9 - 2023.5, Tencent AI Lab, Intern.
- 2020.07 - 2022.07, Huya Inc, Computer vision engineer
- 2020.2 - 2020.7, Tencent AI Lab, Intern.
- 2019.10 - 2019.11, Sense Time, Intern.
- 2018.7 - 2018.9, Hua Wei, Intern.