Hello! Iām Peng Zheng (éé¹ in Chinese), currently pursuing my first year of a PhD program at Jilin University, where I am also involved in joint training at the Shanghai Innovation Institute. I am a member of the Intelligent Content Learning (ICL) group within the School of Artificial Intelligence at Jilin University. My research interests lie in generative models and neural rendering.
I have the privilege of being advised by Associate Professor Rui Ma. My journey in the field of artificial intelligence has been exciting, and Iām passionate about exploring novel ways to create and understand visual content.
Feel free to connect with me or explore my work further! š
š„ News
- 2024.08: One paper is accepted by PG 2024. Thanks to Ruiqi Liu!
- 2024.07: One paper is accepted by ECCV 2024.
- 2024.03: Create my homepage.
š Publications
SemanticHuman-HD: High-Resolution Semantic Disentangled 3D Human Generation
Peng Zheng, Tao Liu, Zili Yi, Rui Ma
- We introduce SemanticHuman-HD, the first method to achieve semantic disentangled human image synthesis. Notably, SemanticHuman-HD is also the first method to achieve 3D-aware image synthesis at 10242 resolution, benefiting from our proposed 3D-aware super-resolution module.
3D-SSGAN: Lifting 2D Semantics for 3D-Aware Compositional Portrait Synthesis
Ruiqi Liu, Peng Zheng, Ye Wang, Rui Ma
- We propose 3D-SSGAN, a novel framework for 3D-aware compositional portrait image synthesis. First, a simple yet effective depth-guided 2D-to-3D lifting module maps the generated 2D part features and semantics to 3D. Then, a volume renderer with a novel 3D-aware semantic mask renderer is utilized to produce the composed face features and corresponding masks.
Renyi Mao, Qingshan Xu, Peng Zheng, Ye Wang, Tieru Wu, Rui Ma
- In this paper, we aim for both fast and high-quality implicit field learning, and propose TaylorGrid, a novel implicit field representation which can be efficiently computed via direct Taylor expansion optimization on 2D or 3D grids.
D-Aug: Enhancing Data Augmentation for Dynamic LiDAR Scenes
Jiaxing Zhao, Peng Zheng, Rui Ma
- We propose D-Aug, a LiDAR data augmentation method tailored for augmenting dynamic scenes. D-Aug extracts objects and inserts them into dynamic scenes, considering the continuity of these objects across consecutive frames.
š Honors and Awards
- 2023: Received a third prize in the Second Jittor Artificial Intelligence Competition.
š Educations
- 2022.09 - 2025.06, M.E., Jilin University, Computer Science and Technology.
- 2018.09 - 2022.06, B.E., Jilin University, Agricultural Mechanization and Automation.