Mengya Liu

I'm now working at Beijing Institute for General Artificial Intelligence (BIGAI). I did my PhD at ETH Zurich in the Computer Vision Lab, supervised by Prof. Luc Van Gool and Dr. Federico Tombari. My research mainly focuses on 3D vision, especially 3D reconstruction, generation and pose estimation of objects. Currently, I'm interested in the research of vision, language and action models. Before that, I obtained my master and bachelor degrees from Northwestern Polytechnical University.

Mengya Liu portrait

Selected Publications

One2Any: One-Reference 6D Pose Estimation for Any Object

Mengya Liu, Siyuan Li, Ajad Chhatkuli, Prune Truong, Luc Van Gool, Federico Tombari CVPR, 2025

Self-supervised Shape Completion via Involution and Implicit Correspondences

Mengya Liu, Ajad Chhatkuli, Janis Postels, Luc Van Gool, Federico Tombari
ECCV, 2024

Unsupervised Template Warp Consistency for Implicit Surface Correspondences

Mengya Liu, Ajad Chhatkuli, Janis Postels, Luc Van Gool, Federico Tombari Eurographics, 2023

Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction

Janis Postels, Mengya Liu, Riccardo Spezialetti, Luc Van Gool, Federico Tombari 3D Vision, 2021