Haolin Xiong

Email: xiongh@ucla.edu

I'm a student researcher at Institute for Creative Technologies, a research center affiliated to University of Southern California, in Los Angeles, where I explore 3D Computer Vision topics under Assistant Professor/Interim Director Yajie Zhao.

I am currently seeking PhD opportunities in Computer Vision/Imaging for Fall 2025. I earned my Master's degree in Electrical & Computer Engineering from UCLA, where I was jointly advised by Associate Professor Achuta Kadambi and Assistant Professor Lin Yang. Previously, I obtained a M.S. in Business Analytics and a dual B.S. in Computer & Systems Engineering/Economics from Rensselaer Polytechnic Institute."

CV / Linkedin / Twitter / Github

Research

My research interest lies broadly in 3D Computer Vision (e.g. depth sensing, scene reconstruction, generative AI, etc), recently focuses on 3D Gaussian Splatting.

SparseGS: Sparse View Synthesis with 3D Gaussian Splatting

Haolin Xiong*, Sairisheek Muttukuru*, Hanyuan Xiao, Rishi Upadhyay, Pradyumna Chari, Yajie Zhao, Achuta Kadambi
project page / arXiv

3DV, 2025
Real-world scene reconstruction using 3D Gaussian Splatting with 12 input views.

Localized Gaussian Splatting Editing with Contextual Awareness

Hanyuan Xiao, Yingshu Chen, Huajian Huang, Haolin Xiong, Jing Yang, Pratusha Prasad, Yajie Zhao
arXiv

WACV, 2025
Contextual and lighting-aware 3D editing with Gaussian Splatting.

SRVD: Sparse View Scene Reconstruction with Video Diffusion Model

Wenbin Teng, Haolin Xiong, Hanyuan Xiao, Gonglin Chen, Niluthpol C. Mithun, Qiao Wang, Supun Samarasekera, Rakesh Kumar, Yajie Zhao

CVPR, 2025 (Under Review)
Use Video Diffusion Model to generate extra views for better NVS quality.