Chong Xia | 夏冲

I'm a second-year PhD student in the Department of Electronic Engineering at Tsinghua University , advised by Prof. Yueqi Duan. In 2024, I obtained my B.Eng. in the Department of Automation, Tsinghua University.

My research interest lies in 3D Vision and Embodied AI. If you are interested in working with me, please feel free to drop me an email.

Email  /  CV  /  Github

Preprints

*Equal contribution    ^†Project leader

We propose ReplicateAnyScene, a framework for fully automated and zero-shot compositional 3D reconstruction from casually captured videos. Our method extracts and aligns cross-modal priors from vision foundation models to generate semantically coherent and physically plausible 3D scenes.

Selected Publications

*Equal contribution    ^†Project leader

In this paper, we propose a novel compositional scene reconstruction framework, coined SimRecon, that implements a "Perception-Generation-Simulation" pipeline with specialized bridging modules to ensure high visual fidelity and physical plausibility.

To enable online 3D reconstruction from streaming images, we propose OnlineX, a framework that jointly models visual appearance and language fields through a novel decoupled memory state evolution.

In this paper, we introduce a novel world generation framework, coined ScenePainter, to direct the iterative scene generation process with semantically consistent scene concepts and relations.

We propose a model and task-agnostic plug-and-play module, which converts offline 3D scene perception models (receive reconstructed point clouds) to online perception models (receive streaming RGB-D videos).

Website Template