Xianpeng Liu

I'm a final-year Ph.D. student in the Laboratory for interpretable Visual Modeling, Computing and Learning (iVMCL) at North Carolina State University (NCSU) advised by Prof. Tianfu Wu.

Github  /  LinkedIn  /  Google Scholar  /  Resume

Email: xliu59 [at] ncsu.edu

I am looking for full-time positions starting from Jan. 2024. I'd appreciate it if you can share the hiring info.

2023-07      One paper was accepted by ICCV 2023.

2023-05      I passed my oral exam and proposal.

2023-02      One paper was accepted by CVPR 2023.

2022-05      I started my research internship at Innopeak Tech.

2022-01      One paper was accepted by AAAI 2022.

Focus on 3D Detection from a single image.

I have a broad interest in 2D and 3D computer vision. My current research focuses on 3D Object Detection, 3D Reconstruction, Human Pose Estimation, etc. Below is a selected list of my works. Full publication can be found at my google scholar page.

A monocular 3D object detection method with a novel 3D space top-down bounding box denoising paradigm.

A lightweight pure transformer architecture named POoling aTtention TransformER (POTTER) for the HMR task from single images.

Leverage Monocular Contexts (MonoCon) to achieve rapid and precise 3D object detection from a single image.

Design a quality-aware semantic data annotation system to achieve high annotation quality for crowdsourcing.

Perform Likelihood-ratio test to achieve precise wetting detection from videos.