G
Guofeng Zhang
Researcher at Zhejiang University
Publications - 177
Citations - 3740
Guofeng Zhang is an academic researcher from Zhejiang University. The author has contributed to research in topics: Computer science & Amorphous metal. The author has an hindex of 30, co-authored 128 publications receiving 2803 citations. Previous affiliations of Guofeng Zhang include Huawei & Samsung.
Papers
More filters
Journal ArticleDOI
Consistent Depth Maps Recovery from a Video Sequence
TL;DR: This paper presents a novel method for recovering consistent depth maps from a video sequence that not only imposes the photo-consistency constraint, but also explicitly associates the geometric coherence with multiple frames in a statistical way and can naturally maintain the temporal coherence of the recovered dense depth maps without over-smoothing.
Proceedings ArticleDOI
Robust monocular SLAM in dynamic environments
TL;DR: A novel prior-based adaptive RANSAC algorithm (PARSAC) is proposed to efficiently remove outliers even when the inlier ratio is rather low, so that the camera pose can be reliably estimated even in very challenging situations.
Journal ArticleDOI
High conductivity of isotropic conductive adhesives filled with silver nanowires
Huayue Wu,Jinfang Liu,Xiaoxin Wu,Mingyuan Ge,Y.W. Wang,Guofeng Zhang,Guofeng Zhang,Jianzhong Jiang +7 more
TL;DR: In this article, an isotropic conductive adhesive (ICA) has been developed by adding Ag nanowires as conductive filler, which has been characterized by X-ray diffraction and transmission electron microscopy.
Proceedings ArticleDOI
Depth Completion From Sparse LiDAR Data With Depth-Normal Constraints
TL;DR: Zhang et al. as discussed by the authors proposed a unified CNN framework that models the geometric constraints between depth and surface normal in a diffusion module and predicts the confidence of sparse LiDAR measurements to mitigate the impact of noise.
Proceedings ArticleDOI
Keyframe-based dense planar SLAM
TL;DR: A novel keyframe-based dense planar SLAM (KDP-SLAM) system, based on CPU only, to reconstruct large indoor environments in real-time using a hand-held RGB-D sensor, and explicitly modeling plane landmarks in the fully probabilistic global optimization significantly reduces the drift that plagues other dense SLAM algorithms.