Zongming Guo

Zongming Guo

Auto-generated profile, based on publicly available information

Zongming Guo

Peking University, Beijing, China

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

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

Representative Publications

View All Publications
27 January 2019 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
WYWenhan Yang
Wenhan Yang
RTRobby T. Tan
Robby T. Tan
JFJiashi Feng
Jiashi Feng
ZGZongming Guo
Zongming Guo
SYShuicheng Yan
Shuicheng Yan
JLJiaying Liu
Jiaying Liu
Rain streaks, particularly in heavy rain, not only degrade visibility but also make many computer vision algorithms fail to function properly. In this paper, we address this visibility problem by focusing on single-image rain removal, even in the presence of dense rain streaks and rain-streak accumulation, which is visually similar to mist or fog. To achieve this, we introduce a new rain model and a deep learning architecture. Our rain model incorporates a binary rain map indicating rain-streak regions, and accommodates various shapes, directions, and sizes of overlapping rain streaks, as well as rain accumulation, to model heavy rain. Based on this model, we construct a multi-task deep network, which jointly learns three targets: the binary rain-streak map, rain streak layers, and clean background, which is our ultimate output. To generate features that can be invariant to rain steaks, we introduce a contextual dilated network, which is able to exploit regional contextual information. To handle various shapes and directions of overlapping rain streaks, our strategy is to utilize a recurrent process that progressively removes rain streaks. Our binary map provides a constraint and thus additional information to train our network. Extensive evaluation on real images, particularly in heavy rain, shows the effectiveness of our model and architecture.

6 March 2020 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
WHWei Hu
Wei Hu
XGXiang Gao
Xiang Gao
GCGene Cheung
Gene Cheung
ZGZongming Guo
Zongming Guo
Identifying an appropriate underlying graph kernel that reflects pairwise similarities is critical in many recent graph spectral signal restoration schemes, including image denoising, dequantization, and contrast enhancement. Existing graph learning algorithms compute the most likely entries of a properly defined graph Laplacian matrix L, but require a large number of signal observations z's for a stable estimate. In this work, we assume instead the availability of a relevant feature vector ${f_{i}}$ per node ${i}$ , from which we compute an optimal feature graph via optimization of a feature metric. Specifically, we alternately optimize the diagonal and off-diagonal entries of a Mahalanobis distance matrix ${M}$ by minimizing the graph Laplacian regularizer (GLR) ${z^{T}Lz}$ , where edge weight is ${w_{i,j} = exp\{(-fi-fj)^{T}M(fi-fj)\}}$ , given a single observation z. We optimize diagonal entries via proximal gradient (PG), where we constrain M to be positive definite (PD) via linear inequalities derived from the Gershgorin circle theorem. To optimize off-diagonal entries, we design a block descent algorithm that iteratively optimizes one row and column of M. To keep M PD, we constrain the Schur complement of sub-matrix ${\rm{M_{2,2}}}$ of M to be PD when optimizing via PG. Our algorithm mitigates full eigen-decomposition of M, thus ensuring fast computation speed even when feature vector ${f_{i}}$ has high dimension. To validate its usefulness, we apply our feature graph learning algorithm to the problem of 3D point cloud denoising, resulting in state-of-the-art performance compared to competing schemes in extensive experiments.

11 January 2019 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
WYWenhan Yang
Wenhan Yang
JLJiaying Liu
Jiaying Liu
SYShuai Yang
Shuai Yang
ZGZongming Guo
Zongming Guo
In this paper, we address a rain removal problem from a single image, even in the presence of large rain streaks and rain streak accumulation (where individual streaks cannot be seen, and thus visually similar to mist or fog). For rain streak removal, the mismatch problem between different streak sizes in training and testing phases leads to a poor performance, especially when there are large streaks. To mitigate this problem, we embed a hierarchical representation of wavelet transform into a recurrent rain removal process: 1) rain removal on the low-frequency component; 2) recurrent detail recovery on highfrequency components under the guidance of the recovered lowfrequency component. Benefiting from the recurrent multi-scale modeling of wavelet transform-like design, the proposed network trained on streaks with one size can adapt to those with larger sizes, which significantly favors real rain streak removal. The dilated residual dense network is used as the basic model of the recurrent recovery process. The network includes multiple paths with different receptive fields, thus can make full use of multi-scale redundancy and utilize context information in large regions. Furthermore, to handle heavy rain cases where rain streak accumulation is presented, we construct a detail appearing rain accumulation removal to not only improve the visibility but also enhance the details in dark regions. The evaluation on both synthetic and real images, particularly on those containing large rain streaks and heavy accumulation, shows the effectiveness of our novel models, which significantly outperforms the state-ofthe- art methods.

3 January 2020 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
TZTong Zhang
Tong Zhang
XLXiaolong Li
Xiaolong Li
WQWenfa Qi
Wenfa Qi
ZGZongming Guo
Zongming Guo
Histogram shifting (HS) is a major approach of current reversible data hiding (RDH) studies. Recently, a method based on multiple histogram modification (MHM) is proposed, in which a sequence of prediction-error histograms are generated and two expansion bins are selected in each histogram for embedding data. However, it only chooses a single pair of expansion bins which limits the embedding capacity. On the other hand, the exhaustive expansion-bin-selection procedure in MHM takes huge computation time so that it cannot be extended for high capacity. In order to overcome the drawbacks of MHM, we propose a high capacity RDH scheme based on dynamic programming strategy in this paper. Instead of using single pair of expansion bins for each histogram of MHM, multiple pairs of expansion bins are utilized for each histogram so that the embedding capacity is significantly improved. Moreover, an algorithm based on dynamic programming is developed to optimize the embedding performance and reduce the computation time. Compared with the original MHM and some other methods, the experiment results show that the proposed scheme achieves better performance in terms of the marked image quality.

20 March 2019 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
WHWei Hu
Wei Hu
ZFZeqing Fu
Zeqing Fu
ZGZongming Guo
Zongming Guo
As 3D scanning devices and depth sensors mature, point clouds have attracted increasing attention as a format for 3D object representation, with applications in various fields such as tele-presence, navigation and heritage reconstruction. However, point clouds usually exhibit holes of missing data, mainly due to the limitation of acquisition techniques and complicated structure. Further, point clouds are defined on irregular non- Euclidean domains, which is challenging to address especially with conventional signal processing tools. Hence, leveraging on recent advances in graph signal processing, we propose an efficient point cloud inpainting method, exploiting both the local smoothness and the non-local self-similarity in point clouds. Specifically, we first propose a frequency interpretation in graph nodal domain, based on which we derive the smoothing and denoising properties of a graph-signal smoothness prior in order to describe the local smoothness of point clouds. Secondly, we explore the characteristics of non-local self-similarity, by globally searching for the most similar area to the missing region. The similarity metric between two areas is defined based on the direct component and the anisotropic graph total variation of normals in each area. Finally, we formulate the hole-filling step as an optimization problem based on the selected most similar area and regularized by the graph-signal smoothness prior. Besides, we propose voxelization and automatic hole detection methods for the point cloud prior to inpainting. Experimental results show that the proposed approach outperforms four competing methods significantly, both in objective and subjective quality.