Jiabin Liang

I am a fulltime researcher at Sea AI Lab and a PHD student in NUS, supervised by Gim Hee Lee. I work on computer graphic and machine learning. Previously, I was the leader of DJI Terra, the best and fastest photogrammetry software in the world. I got my Bachelor degrees from Shanghai Jiao Tong University and Master from ENSAM, Arts et Métiers ParisTech.

I am looking for PhD, Master, and Undergraduate students join my project. Please drop me an email if you are interested.

Email / Google Scholar

Selected Work

	TreeMeshGPT: Artistic Mesh Generation with Autoregressive Tree Sequencing Stefan Lionar, Jiabin Liang, Gim Hee Lee Computer Vision and Pattern Recognition (CVPR), 2025 Paper \| Code \| Demo TreeMeshGPT is an autoregressive Transformer designed to generate high-quality artistic meshes from input point clouds with a 22% compression rate.
	InfNeRF: Towards Infinite Scale NeRF Rendering with O(log n) Space Complexity Jiabin Liang, Lanqing Zhang, Zuoran Zhao, Xiangyu Xu SIGGRAPH Asia 2024 Conference Papers. 2024 Paper \| Code We apply the HLoD technique on NeRF to extend its capabilities towards infinity.
	Towards Garment Sewing Pattern Reconstruction from a Single Image Lijuan Liu, Xiangyu Xu, Zhijie Lin, Jiabin Liang*, Shuicheng Yan ACM Transactions on Graphics (SIGGRAPH Asia)*, 2023 Paper \| Code \| New Scientist We present the first solution for sewing pattern reconstruction from a single image.
	DJI Terra: the best and fastest photogrammetry software in the world Jiabin Liang, et al. 1st Prize of 2022 Shenzhen Scientific and Technological Progress Award 2rd Prize of 2021 Science and Technology progress award of CSGPC

Website template from here