About Me

• I obtained my CS Ph.D. degree from City University of Hong Kong (2020~2024) under the supervision of Prof. Junhui Hou, during which I also collaborated closely with Prof. Wenping Wang and Prof. Ying He. Previously, I worked as a short-term research intern guided by Prof. Runmin Cong. I received my B.Sc. degree from Beijing Normal University in 2019.

• Since August 2024, I joined Tencent as a senior AI researcher, leading an effort to 3D mesh generation and geometry processing.

News

• [2023.09] Two papers, NeuroGF for geodesics learning, UPIDet for cross-modal 3D detection, got accepted by NeurIPS-2023.
• [2023.12] One paper, Cross-PCC for image-assisted 3D point cloud completion, got accepted by TMM.
• [2023.12] One paper, PointVST for self-supervised 3D point cloud backbone pre-training, got accepted by TVCG.
• [2024.06] One paper, SPCV for spatio-temporal structurization of dynamic 3D point cloud sequences, got accepted by TPAMI.
• [2024.09] One paper, Flatten Anything Model for surface parameterization (UV unwrapping), got accepted by NeurIPS-2024.
• [2025.03] One paper, Human as Points for single-image 3D human reconstruction, got accepted by TPAMI.
• [2025.10] One paper, HuGDiffusion for 3D human Gaussian diffusion, got accepted by TVCG.
• [2025.10] One paper, FlexPara for flexible multi-chart surface parameterization, got accepted by TPAMI.

Research

In general, I have broad interests in developing deep learning models and neural optimization algorithms to solve various geometry, vision, and graphics problems.

My Ph.D. research primarily focused on the scope of 3D Spatial Intelligence, encompassing the following specific topics:

• Geometry Modeling and Surface Computing: Regular Representation (Flattening-Net, RegGeoNet); Mesh Parameterization (FAM); 4D Spatio-Temporal Structurization (SPCV); Neural Geodesics (NeuroGF).

• Point Cloud Processing and Reconstruction: Sampling (MOPS-Net); Completion (Cross-PCC); Generation (WarpingGAN); 4D Sequence Interpolation (IDEA-Net).

• Visual-Geometric Joint Learning: Image-to-3D Distillation (PointMCD); Image-Assisted 3D Pre-training (PointVST); 3D Perception (GLENet, UPIDet); Image Recogtition (CoADNet, DAFNet).

• Digital Human: 3D Human Reconstruction (HaP); Human-Centered 3D Gaussian Splatting (HuGDiffusion).

Current Focuses: Despite recent breakthroughs in 3D generative models, their applicability in professional asset creation workflows remains limited. I am currently concentrating my research efforts on Production-Ready 3D AIGC and its integration into real-world game industry pipelines. My ongoing R&D projects include:

• Ultra-Realistic Mesh Geometry Detailization. (See our earlier results in SuperCarver.)

• Controllable Mesh Texture Repainting and Editing.

• Practical Mesh UV Unwrapping. (See our earlier results in FAM, FlexPara.)

Services

• Conference Reviewer: NeurIPS, ICLR, ICML, CVPR, ICCV, ECCV, ACM MM, IJCAI, CVM, etc.

• Journal Reviewer: TIP, TVCG, TMM, TCSVT, TITS, TGRS, JSTARS, etc.

Selected Publications

	Joint Geometry–Appearance Human Reconstruction in a Unified Latent Space via Bridge Diffusion Yingzhi Tang, Qijian Zhang, Junhui Hou Pre-print
	SuperCarver: Texture-Consistent 3D Geometry Super-Resolution for High-Fidelity Surface Detail Generation Qijian Zhang, Xiaozheng Jian, Xuan Zhang, Wenping Wang, Junhui Hou Pre-print

	FlexPara: Flexible Neural Surface Parameterization Yuming Zhao, Qijian Zhang, Junhui Hou, Jiazhi Xia, Wenping Wang, Ying He TPAMI 2025
	HuGDiffusion: Generalizable Single-Image Human Rendering via 3D Gaussian Diffusion Yingzhi Tang, Qijian Zhang, Junhui Hou TVCG 2025
	Human as Points: Explicit Point-based 3D Human Reconstruction from Single-view RGB Images Yingzhi Tang, Qijian Zhang, Junhui Hou, Yebin Liu TPAMI 2025
	Flatten Anything: Unsupervised Neural Surface Parameterization Qijian Zhang, Junhui Hou, Wenping Wang, Ying He NeurIPS 2024
	Dynamic 3D Point Cloud Sequences as 2D Videos Yiming Zeng, Junhui Hou, Qijian Zhang, Siyu Ren, Wenping Wang TPAMI 2024
	PointVST: Self-Supervised Pre-training for 3D Point Clouds via View-Specific Point-to-Image Translation Qijian Zhang, Junhui Hou TVCG 2023
	Leveraging Single-View Images for Unsupervised 3D Point Cloud Completion Lintai Wu, Qijian Zhang, Junhui Hou, Yong Xu TMM 2023
	NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries Qijian Zhang, Junhui Hou, Yohanes Yudhi Adikusuma, Wenping Wang, Ying He NeurIPS 2023
	Unleash the Potential of Image Branch for Cross-modal 3D Object Detection Yifan Zhang, Qijian Zhang, Junhui Hou, Yixuan Yuan, Guoliang Xing NeurIPS 2023
	PointMCD: Boosting Deep Point Cloud Encoders via Multi-view Cross-modal Distillation for 3D Shape Recognition Qijian Zhang, Junhui Hou, Yue Qian TMM 2023
	GLENet: Boosting 3D Object Detectors with Generative Label Uncertainty Estimation Yifan Zhang, Qijian Zhang, Zhiyu Zhu, Junhui Hou, Yixuan Yuan IJCV 2023
	Task-Oriented Compact Representation of 3D Point Clouds via A Matrix Optimization-Driven Network Yue Qian, Junhui Hou, Qijian Zhang, Yiming Zeng, Sam Kwong, Ying He TCSVT 2023
	Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis Qijian Zhang, Junhui Hou, Yue Qian, Yiming Zeng, Juyong Zhang, Ying He TPAMI 2023
	RegGeoNet: Learning Regular Representations for Large-Scale 3D Point Clouds Qijian Zhang, Junhui Hou, Yue Qian, Antoni B. Chan, Juyong Zhang, Ying He IJCV 2022
	WarpingGAN: Warping Multiple Uniform Priors for Adversarial 3D Point Cloud Generation Yingzhi Tang, Yue Qian, Qijian Zhang, Yiming Zeng, Junhui Hou, Xuefei Zhe CVPR 2022
	IDEA-Net: Dynamic 3D Point Cloud Interpolation via Deep Embedding Alignment Yiming Zeng, Yue Qian, Qijian Zhang, Junhui Hou, Yixuan Yuan, Ying He CVPR 2022
	Dense Attention Fluid Network for Salient Object Detection in Optical Remote Sensing Images Qijian Zhang, Runmin Cong, Chongyi Li, Ming-Ming Cheng, Yuming Fang, Xiaochun Cao, Yao Zhao, Sam Kwong TIP 2021
	CoADNet: Collaborative Aggregation-and-Distribution Networks for Co-Salient Object Detection Qijian Zhang*, Runmin Cong* , Junhui Hou, Chongyi Li, Yao Zhao NeurIPS 2020