Tianhao Wu

About Me

Currently I am a Ph.D. candidate in S-Lab at Nanyang Technological University, Singapore, supervised by Prof. Tat-Jen Cham. I've had the distinct privilege of collaborating with Prof. Andrea Vedaldi and Dr. Chuanxia Zheng from Visual Geometry Group, University of Oxford. My research focus on 2D image generation/manipulation and 3D reconstruction/editing.

Education

(2022 - present) Ph.D. in Computer Science, Nanyang Technological University, Singapore

(2017 - 2021) B.S. in Computer Science, Beihang University, Beijing, China

Intership

(Expected graduation this year and actively seeking an internship, full-time job or postdoc positions worldwide! Email&CV)

(2021.2 - 2021.6) Intern at ByteDance AI Lab, Voice Activity Detection, Beijing, China

(2021.10 - 2021.12) Intern at SenseTime Autonomous Driving, Autonomous Driving Planning, Beijing, China

Publications

	Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images Tianhao Wu, Chuanxia Zheng, Frank Guan, Andrea Vedaldi, Tat-Jen Cham Preprint, 2025 arXiv / Project Page / Model / Demo A model for 3D amodal reconstruction from partially visible input.
	LTOS: Layout-controllable Text-Object Synthesis via Adaptive Cross-attention Fusions Xiaoran Zhao, Tianhao Wu, Lai yu, Zhiliang Tian, Zhen Huang, Yahui Liu, Zejiang He, Dongsheng Li ICASSP, 2025 arXiv / code A high-quality text-object fusion synthesis model via diffusion.
	ClusteringSDF: Self-Organized Neural Implicit Surfaces for 3D Decomposition Tianhao Wu, Chuanxia Zheng, Qianyi Wu, Tat-Jen Cham ECCV, 2024 project page / arXiv / code A self-organized 3D segmentation model via neural implicit surface representation.
	PanoDiffusion: 360-degree Panorama Outpainting via Diffusion Tianhao Wu, Chuanxia Zheng, Tat-Jen Cham ICLR, 2024 project page / PDF / arXiv / code An indoor panorama outpainting model using latent diffusion models with view-consistent.

Academic Services

Conference Reviewer

3DMV 2024

ECCV 2024

ACM MM 2024

ICLR 2025

CVPR 2025

Journal Reviewer

TMM