Chengliang Zhong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chengliang Zhong has a total of 32 co-authors. Here are the top co-authors by number of shared publications:
Xiangchen He
Research Center for Simulation Algorithm, Beijing Institute of Remote Sensing Technology, Beijing 100039, China
2 shared publicationsXiaodong Mu
Computer Department, Xi'an Research Institute of Hi-Tech, Xi'an 710025, China
2 shared publicationsBangjie Li
1 shared publicationBen Niu
Computer Department, Xi'an Research Institute of Hi-Tech, Xi'an 710025, China
1 shared publicationBichao Zhan
Research Center for Simulation Algorithm, Beijing Institute of Remote Sensing Technology, Beijing 100039, China
1 shared publication- Bu Jin
Institute of Automation, Chinese Academy of Sciences (CASIA), Haidian, China
1 shared publication
Latest Publications
- 17 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 1980-1994
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence
Unsupervised non-rigid point cloud shape correspondence underpins a multitude of 3D vision tasks, yet itself is non-trivial given the exponential complexity stemming from inter-point degree-of-freedom, i.e., pose transformations. Based on the assumption of local rigidity, one solution for reducing complexity is to decompose the overall shape into independent local regions using Local Reference Frames (LRFs) that are equivariant to SE(3) transformations. However, the focus solely on local structure neglects global geometric contexts, resulting in less distinctive LRFs that lack crucial semantic information necessary for effective matching. Furthermore, such complexity introduces out-of-distribution geometric contexts during inference, thus complicating generalization. To this end, we introduce 1) EquiShape, a novel structure tailored to learn pair-wise LRFs with global structural cues for both spatial and semantic consistency, and 2) LRF-Refine, an optimization strategy generally applicable to LRF-based methods, aimed at addressing the generalization challenges. Specifically, for EquiShape, we employ cross-talk within separate equivariant graph neural networks (Cross-GVP) to build long-range dependencies to compensate for the lack of semantic information in local structure modeling, deducing pair-wise independent SE(3)-equivariant LRF vectors for each point. For LRF-Refine, the optimization adjusts LRFs within specific contexts and knowledge, enhancing the geometric and semantic generalizability of point features. Our overall framework surpasses the state-of-the-art methods by a large margin on three benchmarks. Codes are available at https://github.com/2019EPWL/EquiShape.
- 17 March 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 1980-1994
Equivariant Local Reference Frames With Optimization for Robust Non-Rigid Point Cloud Correspondence
Unsupervised non-rigid point cloud shape correspondence underpins a multitude of 3D vision tasks, yet itself is non-trivial given the exponential complexity stemming from inter-point degree-of-freedom, i.e., pose transformations. Based on the assumption of local rigidity, one solution for reducing complexity is to decompose the overall shape into independent local regions using Local Reference Frames (LRFs) that are equivariant to SE(3) transformations. However, the focus solely on local structure neglects global geometric contexts, resulting in less distinctive LRFs that lack crucial semantic information necessary for effective matching. Furthermore, such complexity introduces out-of-distribution geometric contexts during inference, thus complicating generalization. To this end, we introduce 1) EquiShape, a novel structure tailored to learn pair-wise LRFs with global structural cues for both spatial and semantic consistency, and 2) LRF-Refine, an optimization strategy generally applicable to LRF-based methods, aimed at addressing the generalization challenges. Specifically, for EquiShape, we employ cross-talk within separate equivariant graph neural networks (Cross-GVP) to build long-range dependencies to compensate for the lack of semantic information in local structure modeling, deducing pair-wise independent SE(3)-equivariant LRF vectors for each point. For LRF-Refine, the optimization adjusts LRFs within specific contexts and knowledge, enhancing the geometric and semantic generalizability of point features. Our overall framework surpasses the state-of-the-art methods by a large margin on three benchmarks. Codes are available at https://github.com/2019EPWL/EquiShape.
- Top Cited Papers
- 23 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (9) , 7827-7834
GaussianGrasper: 3D Language Gaussian Splatting for Open-Vocabulary Robotic Grasping
Constructing a 3D scene capable of accommodating open-ended language queries, is a pivotal pursuit in the domain of robotics, which facilitates robots in executing object manipulations based on human language directives. To achieve this, some research efforts have been dedicated to the development of language-embedded implicit fields. However, implicit fields (e.g. NeRF) encounter limitations due to the necessity of taking images from a larger number of viewpoints for reconstruction, coupled with their inherent inefficiencies in inference. Furthermore, these methods directly distill patch-level 2D features, leading to ambiguous segmentation boundaries. Thus, we present the GaussianGrasper , which uses 3D Gaussian Splatting (3DGS) to explicitly represent the scene as a set of Gaussian primitives and is capable of real-time rendering. Our approach takes RGB-D images from limited viewpoints as input and uses an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently distill 2D language embeddings and constraint consistency of feature embeddings. With the reconstructed geometry of the Gaussian field, our method enables the pre-trained grasping model to generate collision-free grasp pose candidates. Furthermore, we propose a normal-guided grasp module to select the best grasp pose. Through comprehensive real-world experiments, we demonstrate that GaussianGrasper enables robots to accurately locate and grasp objects according to language instructions, providing a new solution for language-guided grasping tasks.
- 23 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 9 (9) , 7827-7834
Top Cited PapersGaussianGrasper: 3D Language Gaussian Splatting for Open-Vocabulary Robotic Grasping
Constructing a 3D scene capable of accommodating open-ended language queries, is a pivotal pursuit in the domain of robotics, which facilitates robots in executing object manipulations based on human language directives. To achieve this, some research efforts have been dedicated to the development of language-embedded implicit fields. However, implicit fields (e.g. NeRF) encounter limitations due to the necessity of taking images from a larger number of viewpoints for reconstruction, coupled with their inherent inefficiencies in inference. Furthermore, these methods directly distill patch-level 2D features, leading to ambiguous segmentation boundaries. Thus, we present the GaussianGrasper , which uses 3D Gaussian Splatting (3DGS) to explicitly represent the scene as a set of Gaussian primitives and is capable of real-time rendering. Our approach takes RGB-D images from limited viewpoints as input and uses an Efficient Feature Distillation (EFD) module that employs contrastive learning to efficiently distill 2D language embeddings and constraint consistency of feature embeddings. With the reconstructed geometry of the Gaussian field, our method enables the pre-trained grasping model to generate collision-free grasp pose candidates. Furthermore, we propose a normal-guided grasp module to select the best grasp pose. Through comprehensive real-world experiments, we demonstrate that GaussianGrasper enables robots to accurately locate and grasp objects according to language instructions, providing a new solution for language-guided grasping tasks.
- 2 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 16 (3) , 412-416
SAR Target Image Classification Based on Transfer Learning and Model Compression
When convolutional neural networks (CNNs) are applied to the synthetic aperture radar (SAR) image classification, they are prone to overfitting due to scarce SAR image data, and CNNs require a large amount of storage and long computing time, so it is difficult to deploy them on resource constrained devices. This letter proposes a simple and feasible approach that can effectively solve these problems. First, the convolutional layers of the pretrained model on the ImageNet data set are transferred, and a new convolutional layer and global pooling layer are added afterward. Then, fine-tuning is performed on the new network from the SAR image data set. Finally, a filter-based pruning method is used on the convolutional layers to obtain a compact network. Compared with the all-convolutional network (A-ConvNets) which is the state-of-the-art method on the moving and stationary target acquisition and recognition data set, our method achieves about 3.6x speedup during forward propagation and 3.7x compression of the parameters, with only a 1.42% decrease in the accuracy.
- 2 November 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 16 (3) , 412-416
SAR Target Image Classification Based on Transfer Learning and Model Compression
When convolutional neural networks (CNNs) are applied to the synthetic aperture radar (SAR) image classification, they are prone to overfitting due to scarce SAR image data, and CNNs require a large amount of storage and long computing time, so it is difficult to deploy them on resource constrained devices. This letter proposes a simple and feasible approach that can effectively solve these problems. First, the convolutional layers of the pretrained model on the ImageNet data set are transferred, and a new convolutional layer and global pooling layer are added afterward. Then, fine-tuning is performed on the new network from the SAR image data set. Finally, a filter-based pruning method is used on the convolutional layers to obtain a compact network. Compared with the all-convolutional network (A-ConvNets) which is the state-of-the-art method on the moving and stationary target acquisition and recognition data set, our method achieves about 3.6x speedup during forward propagation and 3.7x compression of the parameters, with only a 1.42% decrease in the accuracy.
- 18 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 15 (9) , 1377-1381
Classification for SAR Scene Matching Areas Based on Convolutional Neural Networks
The selection of scene matching areas is a difficult problem in the field of matching guidance. Compared with the traditional methods of matching feature extraction and pattern classification, this letter applies convolutional neural networks (CNN) to the extraction of synthetic aperture radar (SAR) scene matching regions for the first time. First of all, we match the SAR images of the same land taken by satellites from different angles and in different phases, and then automatically label the matching suitability of the images as the output of the network according to the matching results. Next, the digital elevation model data reflecting the elevation information and the SAR image grayscale information are fused as the input to the network. Finally, CNN is used to automatically extract the matching features and classify the suitability of the SAR images. The proposed method avoids the steps of extracting features manually and improves the classification performance of SAR scene matching area. Compared with the support vector machine method, the classification accuracy increases from 86.1% to 93.3%.
- 18 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 15 (9) , 1377-1381
Classification for SAR Scene Matching Areas Based on Convolutional Neural Networks
The selection of scene matching areas is a difficult problem in the field of matching guidance. Compared with the traditional methods of matching feature extraction and pattern classification, this letter applies convolutional neural networks (CNN) to the extraction of synthetic aperture radar (SAR) scene matching regions for the first time. First of all, we match the SAR images of the same land taken by satellites from different angles and in different phases, and then automatically label the matching suitability of the images as the output of the network according to the matching results. Next, the digital elevation model data reflecting the elevation information and the SAR image grayscale information are fused as the input to the network. Finally, CNN is used to automatically extract the matching features and classify the suitability of the SAR images. The proposed method avoids the steps of extracting features manually and improves the classification performance of SAR scene matching area. Compared with the support vector machine method, the classification accuracy increases from 86.1% to 93.3%.