Biography
I am currently a Ph.D. candidate at the Wangxuan Institute of Computer Technology, Peking University, China, under the supervision of Prof. Zhouhui Lian. I received my master’s degree from Peking University, China, in 2022. I received my bachelor’s degree from Xidian University, Xi’an, China, in 2019. My research interests include computer graphics and computer vision, and I am currently focusing on 3D AIGC and 3D scene reconstruction.
News
-Jul. 30, 2024: I have 1 paper conditionally accepted to SIGGRAPH Asia 2024.
-Aug. 04, 2023: I have 1 paper conditionally accepted to SIGGRAPH Asia 2023.
Publications
Total of 4 CCF-A, 2 SCI一区, 200+ Citations
Pano2Room: Novel View Synthesis from a Single Indoor Panorama | |
SinMPI: Novel View Synthesis from a Single Image with Expanded Multiplane Images | |
Controllable Image Synthesis with Attribute-Decomposed GAN | |
Aesthetic Text Logo Synthesis via Content-aware Layout Inferring | |
SSC-OCSVM: A Hybrid Unsupervised Clustering-based Anomaly Detection Method | |
Dynamic Texture Transfer using PatchMatch and Transformers |
Academic Services
Conference & Journal Reviewer: Pattern Recognition (PR) (CCF-B, SCI一区), Computers & Graphics (CCF-C, SCI四区).
Patents
连宙辉,蒲果,徐诗瑶,一种基于样例的动态纹理迁移方法及系统,202111582171.6 ,2022 年 1 月 17 日(专利,已授权)
Competitions
Jittor AI competition (Scenery Image generation track) 3rd prize (10000 RMB prize) [第二届计图人工智能竞赛,三等奖]
Peking University “Challenger Cup” 3rd prize [北京大学挑战杯2020,三等奖]
Awards
Excellent student (in Academic Performance) of Wangxuan Institute of Computer Technology, Peking University. (2023)
Excellent student (in Academic Performance) of Wangxuan Institute of Computer Technology, Peking University. (2022)
Excellent Student of Peking University. (2020)
First-class Scholarship of Xidian University. (2018)
Teaching
Teaching assistant in the “AI Introduction” course of Peking University, 2022-2023 and 2023-2024.
Coding
My code has gained more than 3.9k stars on GitHub.
My papers’ source codes are available on GitHub.
My tensorflow2.0 tutorial Dive-into-DL-TensorFlow2.0 has gained more than 3.8k stars on GitHub.