Guofeng Zhang

Dr. Guofeng Zhang


Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 November 2024 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
DCDanpeng Chen
Danpeng Chen
HLHai Li
Hai Li
WYWeicai Ye
Weicai Ye
YWYifan Wang
Yifan Wang
WXWeijian Xie
Weijian Xie
GZGuofeng Zhang
Guofeng Zhang
Recently, 3D Gaussian Splatting (3DGS) has attracted widespread attention due to its high-quality rendering, and ultra-fast training and rendering speed. However, due to the unstructured and irregular nature of Gaussian point clouds, it is difficult to guarantee geometric reconstruction accuracy and multi-view consistency simply by relying on image reconstruction loss. Although many studies on surface reconstruction based on 3DGS have emerged recently, the quality of their meshes is generally unsatisfactory. To address this problem, we propose a fast planar-based Gaussian splatting reconstruction representation (PGSR) to achieve high-fidelity surface reconstruction while ensuring high-quality rendering. Specifically, we first introduce an unbiased depth rendering method, which directly renders the distance from the camera origin to the Gaussian plane and the corresponding normal map based on the Gaussian distribution of the point cloud, and divides the two to obtain the unbiased depth. We then introduce single-view geometric, multi-view photometric, and geometric regularization to preserve global geometric accuracy. We also propose a camera exposure compensation model to cope with scenes with large illumination variations. Experiments on indoor and outdoor scenes show that the proposed method achieves fast training and rendering while maintaining high-fidelity rendering and geometric reconstruction, outperforming 3DGS-based and NeRF-based methods. Our code will be made publicly available, and more information can be found on our project page (https://zju3dv.github.io/pgsr/).

6 March 2009 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
GZGuofeng Zhang
Guofeng Zhang
JJJiaya Jia
Jiaya Jia
TWTien-Tsin Wong
Tien-Tsin Wong
HBHujun Bao
Hujun Bao
This paper presents a novel method for recovering consistent depth maps from a video sequence. We propose a bundle optimization framework to address the major difficulties in stereo reconstruction, such as dealing with image noise, occlusions, and outliers. Different from the typical multi-view stereo methods, our approach not only imposes the photo-consistency constraint, but also explicitly associates the geometric coherence with multiple frames in a statistical way. It thus can naturally maintain the temporal coherence of the recovered dense depth maps without over-smoothing. To make the inference tractable, we introduce an iterative optimization scheme by first initializing the disparity maps using a segmentation prior and then refining the disparities by means of bundle optimization. Instead of defining the visibility parameters, our method implicitly models the reconstruction noise as well as the probabilistic visibility. After bundle optimization, we introduce an efficient space-time fusion algorithm to further reduce the reconstruction noise. Our automatic depth recovery is evaluated using a variety of challenging video examples.

3 December 2010 in IEEE Transactions on Automatic Control
Verified
Journal Article
Closed access
GZGuofeng Zhang
Guofeng Zhang
MJMatthew R. James
Matthew R. James
The purpose of this paper is to study and design direct and indirect couplings for use in coherent feedback control of a class of linear quantum stochastic systems. A general physical model for a nominal linear quantum system coupled directly and indirectly to external systems is presented. Fundamental properties of stability, dissipation, passivity, and gain for this class of linear quantum models are presented and characterized using complex Lyapunov equations and linear matrix inequalities (LMIs). Coherent H ∞ and LQG synthesis methods are extended to accommodate direct couplings using multistep optimization. Examples are given to illustrate the results.

21 October 2022
Verified
Book Chapter
Closed access
PDF file
BYBangbang Yang
Bangbang Yang
CBChong Bao
Chong Bao
JZJunyi Zeng
Junyi Zeng
HBHujun Bao
Hujun Bao
YZYinda Zhang
Yinda Zhang
GZGuofeng Zhang
Guofeng Zhang

3 May 2012 in Chinese Science Bulletin
Verified
Journal Article
Open access
PDF file
GZGuofeng Zhang
Guofeng Zhang
MJMatthew R. James
Matthew R. James
The purpose of this paper is to provide a brief review of some recent developments in quantum feedback networks and control. A quantum feedback network (QFN) is an interconnected system consisting of open quantum systems linked by free fields and/or direct physical couplings. Basic network constructs, including series connections as well as feedback loops, are discussed. The quantum feedback network theory provides a natural framework for analysis and design. Basic properties such as dissipation, stability, passivity and gain of open quantum systems are discussed. Control system design is also discussed, primarily in the context of open linear quantum stochastic systems. The issue of physical realizability is discussed, and explicit criteria for stability, positive real lemma, and bounded real lemma are presented. Finally for linear quantum systems, coherent H ∞ and LQG control are described.

2 December 2022 in IEEE Transactions on Visualization and Computer Graphics
Verified
Journal Article
Closed access
HLHai Li
Hai Li
XYXingrui Yang
Xingrui Yang
HZHongjia Zhai
Hongjia Zhai
YLYuqian Liu
Yuqian Liu
HBHujun Bao
Hujun Bao
GZGuofeng Zhang
Guofeng Zhang
Virtual content creation and interaction play an important role in modern 3D applications. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for decades in the computer vision and computer graphics community. In this work, we propose Vox-Surf, a voxel-based implicit surface representation. Our Vox-Surf divides the space into finite sparse voxels, where each voxel is a basic geometry unit that stores geometry and appearance information on its corner vertices. Due to the sparsity inherited from the voxel representation, Vox-Surf is suitable for almost any scene and can be easily trained end-to-end from multiple view images. We utilize a progressive training process to gradually cull out empty voxels and keep only valid voxels for further optimization, which greatly reduces the number of sample points and improves inference speed. Experiments show that our Vox-Surf representation can learn fine surface details and accurate colors with less memory and faster rendering than previous methods. The resulting fine voxels can also be considered as the bounding volumes for collision detection, which is useful in 3D interactions. We also show the potential application of Vox-Surf in scene editing and augmented reality. The source code is publicly available at https://github.com/zju3dv/Vox-Surf .