About Me

I am currently a Ph.D. student at Australian Institute of Machine Learning (AIML), Adelaide University, where I also obtained my MPhil degree here in 2024 supervised by Prof. Lingqiao Liu, Dr. Libo Sun and Prof. Ian Reid. Before joining AIML, I received my bachelor's degree from Beijing University of Posts and Telecommunications (BUPT) in 2022.

My research focuses on 3D computer vision, spanning reconstruction, perception, and especially 3D content generation. I have developed a deep understanding of the core problems in 3D generation, including geometry, texture, and topology generation, as well as part-aware decomposition. Beyond this, I am exploring how 3D generation can be integrated into world models and real-to-sim pipelines, with a strong interest in building scalable and realistic environments for robotics research.

I'm looking for industrial internship, feel free to reach out!

Publications

Parts by Boundaries: Native Part-Aware 3D Generation with Seg-Voxel Representation

Junlin Hao^*, Jiatong Xia^*, Xibin Song, Senbo Wang, Zongming Guo, Pan Ji, Xinggong Zhang
In Submission
[Project]

Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors

Jiatong Xia^*, Zicheng Duan^*, Anton van den Hengel, Lingqiao Liu
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2026
[Paper] [Project]

Towards high-quality novel view synthesis from nonuniformly distributed input views

Libo Sun^*, Jiatong Xia^*, Lingqiao Liu
IEEE Trans. on Visualization and Computer Graphics (TVCG), 2025
[Paper]

SmartWay: enhanced waypoint prediction and backtracking for zero-shot vision-and-language navigation

Xiangyu Shi^*, Zerui Li^*, Wenqi Lyu, Jiatong Xia, Feras Dayoub, Yanyuan Qiao, Qi Wu
IEEE International Conference on Intelligent Robots and Systems (IROS), 2025
[Paper][Project]

Invited Talks

Point-cloud–centric paradigm for general 3D scene and asset generation Invited talk at DICTA2025 workshop: Visual Generative Models: Past, Present, and Future