Ph.D. Student · 3D Computer Vision

Rongkun
Yang

I am pursuing my Ph.D. in Electronics and Communication Engineering at Sun Yat-sen University, advised by Prof. Yulan Guo. Before starting my doctoral journey, I received my B.E. degree from Central South University.

My research focuses on 3D computer vision, especially 3D scene understanding, segmentation, and reconstruction.

Email me GitHub

3D VisionScene UnderstandingReconstruction

Sun Yat-sen University
Guangzhou, China

Selected work

Publications

Research on open-world 3D scene understanding and controllable scene generation.

Featured · Underreview 2026

Underreview · 2026

Beyond Context Bias: Adaptive Instance Placement for Robust 3D Instance Segmentation

Rongkun Yang, Ye Zhang, Longguang Wang, Zhiheng Fu, Ziru Yu, Yulan Guo

ACGP decouples instances from their source scenes and adaptively relocates them into diverse yet geometrically plausible target contexts, thereby enriching object--scene contexts beyond dataset-specific layout priors.

Project page Paper Code

Featured · TIP 2026

IEEE Transactions on Image Processing · 2026

POSITION: Open World 3D Scene CAD Recomposition

Rongkun Yang, Hongda Liu, Yijun Chen, Sheng Ao, Yongjian Zhang, Longguang Wang, Kaiwen Xue, Shunbo Zhou, Yulan Guo

We reconstruct synthetic scenes using CAD models retrieved from scalable databases, preserving the geometry and spatial arrangement of the original environment.

Project page Paper Code

IROS 2025

IEEE/RSJ International Conference on Intelligent Robots and Systems · 2025

Graph2Scene: Versatile 3D Indoor Scene Generation with Interaction-aware Scene Graph

Minglin Chen, Rongkun Yang, Qibin Hu, Kaiwen Xue, Shunbo Zhou, Yulan Guo

An interaction-aware scene graph method for efficiently generating diverse 3D indoor environments with fine-grained control.

Project pagePaperCode