😸 About Me

He is currently a 4^th-year Ph.D. student in the School of Computer Science and Engineering at Sun Yat-sen University (中山大学计算机学院), supervised by Prof. Xiaohua Xie (谢晓华教授), and also co-supervised by Prof. Jianhuang Lai (赖剑煌教授).

His research interests span AIGC, 3D Reconstruction, Medical Image Processing and the longstanding challenges on image and video, such as object detection and segmentation. He has published some papers at the top international CV journals and conferences, such as IJCV, IEEE TIP, IEEE TCSVT, ICCV and CVPR. He has served as a reviewer of IEEE TIP, IEEE TCSVT, CVPR, ICCV, ECCV, and ICME.

🔥 News

2024.12: 🎉 One paper (HETMM) is accepted by IJCV!
2023.07: 🎉 One paper (CuNeRF) is accepted by ICCV 2023!
2021.09: I started to pursue my PHD degree in Sun Yat-sen University .
2020.11: 🎉 One paper (CAL) is accepted by IEEE TIP!
2020.02: 🎉 One paper (ITSD) is accepted by CVPR 2020!
2019.07: I joined in Lenovo AI-LAB as a CV researcher in Shenzhen!
2019.03: 🎉 One paper (ICE) is accepted by IEEE TCSVT!

📝 Publications

🏭 Anomaly Detection

IJCV

Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection
Zixuan Chen, Xiaohua Xie, Lingxiao Yang, Jian-Huang Lai.
International Journal of Computer Vision (IJCV), 2024.

HETMM aims to address the hard mining issues in Industrial Anomaly Detection, significantly reducing the false alarms.

PDF ArXiv Code

🗿 3D Gaussian Splatting

Arxiv 2024

GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
Zixuan Chen, Guangcong Wang, Jiahao Zhu, Jian-Huang Lai, Xiaohua Xie.

GuardSplat aims to effectively protect the copyright of 3DGS assets, achieving superior capacity and fidelity to existing advances.

ArXiv Project Code Video

Arxiv 2024

VividDreamer: Towards High-Fidelity and Efficient Text-to-3D Generation
Zixuan Chen, Ruijie Su, Jiahao Zhu, Guangcong Wang, Lingxiao Yang, Jian-Huang Lai, Shisong Wu, Xiaohua Xie.

VividDreamer aims to address the inherent trade-off between optimization costs and reconstruction quality, creating high-fidelity 3D assets in a short time.

ArXiv Project Code

📷 Implicit Neural Representation

ICCV 2023

CuNeRF: Cube-Based Neural Radiance Field for Zero-Shot Medical Image Arbitrary-Scale Super Resolution
Zixuan Chen, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie.
International Conference on Computer Vision (ICCV), 2023.

CuNeRF is the first zero-shot framework for Medical Image Arbitrary-Scale Super-Resolution.

PDF ArXiv Project Code

Arxiv 2023

APRF: Anti-Aliasing Projection Representation Field for Inverse Problem in Imaging
Zixuan Chen, Lingxiao Yang, Jian-Huang Lai, Xiaohua Xie.

APRF aims to address the aliasing errors in Sparse-View Computed Tomography reconstruction.

ArXiv

💃 Salient Object Detection

IEEE TIP

Contour-aware loss: Boundary-aware learning for salient object segmentation
Zixuan Chen, Huajun Zhou, Jian-Huang Lai, Lingxiao Yang, Xiaohua Xie.
IEEE Transactions on Image Processing (IEEE TIP), 2021.

This paper aims to employ contour cues and hierarchical attention modules to locate the salient objects.

PDF

CVPR 2020

Interactive Two-Stream Decoder for Accurate and Fast Saliency Detection
Huajun Zhou, Xiaohua Xie, Jian-Huang Lai, Zixuan Chen, Lingxiao Yang.
Computer Vision and Pattern Recognition Conference (CVPR), 2020.

This paper is a streamlined salient object detector that is beyond the real-time speed!

PDF Code

📹 Video Object Segmentation

IEEE TCSVT

Motion-appearance interactive encoding for object segmentation in unconstrained videos
Zixuan Chen, Chunchao Guo, Jian-Huang Lai, Xiaohua Xie.
IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020.

This paper aims to integrate motion and appearance cues to segment the moving object in video.