Fei Wang

Fei Wang

Auto-generated profile, based on publicly available information

Fei Wang

Guangdong-Hong Kong-Macao Joint Laboratory of Human-Machine Intelligence-Synergy Systems, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
24 September 2021 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
JCJun Cheng
Jun Cheng
PLPenglei Liu
Penglei Liu
Qieshi ZhangQieshi Zhang
Qieshi Zhang
HMHui Ma
Hui Ma
FWFei Wang
Fei Wang
JZJin Zhang
Jin Zhang
6-D pose estimation is an important branch in the field of vision measurement and is widely used in the fields of robotics, autonomous driving, and reality augmentation. The latest research trend in 6-D pose estimation is to train a deep neural network to directly predict the 2-D projection position of the 3-D keypoint from the image, establish the corresponding relationship, and, finally, use the perspective-n-point (PnP) algorithm to perform pose estimation. The current challenge of pose estimation is that, when objects are textureless, occluded, or scene-cluttered, the detection accuracy is reduced, and most of the existing algorithm models are large and cannot accommodate real-time requirements. In this article, we introduce a densely connected feature pyramid network (DFPN) that can efficiently integrate and utilize features. We combine the cross-stage partial network (CSPNet) with DFPN to design a new network for 6-D pose estimation, DFPN-6-D, a new approach for 6-D object pose estimation. DFPN-6-D can efficiently and accurately handle objects with textureless, occluded, and scene clutter and estimate their full 6-D poses in a single shot. Furthermore, we propose a new confidence calculation method and loss function for object pose estimation, which can fully consider spatial information. Finally, we propose a novel augmentation method for direct 6-D pose estimation approaches to improve performance and generalization ability in the case of occlusion, which is called 6-D augmentation. Our approach achieves a new state-of-the-art accuracy of 98.06 and 87.09 in terms of the ADD(-S) metric on the Linemod dataset and the Occluded-Linemod dataset, and our method also achieves the best result in terms of the different metric on the MULT-I dataset, the BIN-P dataset, and the T-LESS dataset, respectively, while still running end-to-end at over 65 frames/s. The experimental results demonstrate that our algorithm is robust to textureless materials and occlusion while running more efficiently than other methods. We also deploy our proposed method to a real robot to grasp and manipulate objects based on the estimated pose.

7 September 2023 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
FWFei Wang
Fei Wang
JCJun Cheng
Jun Cheng
Decoders play significant roles in recovering scene depths. However, the decoders used in previous works ignore the propagation of multilevel lossless fine-grained information, cannot adaptively capture local and global information in parallel, and cannot perform sufficient global statistical analyses on the final output disparities. In addition, the process of mapping from a low-resolution (LR) feature space to a high-resolution (HR) feature space is a one-to-many problem that may have multiple solutions. Therefore, the quality of the recovered depth map is low. To this end, we propose a high-quality decoder (HQDec), with which multilevel near-lossless fine-grained information, obtained by the proposed adaptive axial-normalized position-embedded channel attention sampling module (AdaAxialNPCAS), can be adaptively incorporated into a LR feature map with high-level semantics utilizing the proposed adaptive information exchange scheme. In the HQDec, we leverage the proposed adaptive refinement module (AdaRM) to model the local and global dependencies between pixels in parallel and utilize the proposed disparity attention module to model the distribution characteristics of disparity values from a global perspective. To recover fine-grained HR features with maximal accuracy, we adaptively fuse the high-frequency information obtained by constraining the upsampled solution space utilizing the local and global dependencies between pixels into the HR feature map generated from the nonlearning method. Extensive experiments demonstrate that each proposed component improves the quality of the depth estimation results over the baseline results, and the developed approach achieves state-of-the-art results on the KITTI and DDAD datasets. The code and models will be publicly available at HQDec.

14 March 2023 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
FWFei Wang
Fei Wang
JCJun Cheng
Jun Cheng
PLPenglei Liu
Penglei Liu
Photometric differences are widely used as supervision signals to train neural networks for estimating depth and camera pose from unlabeled monocular videos. However, this approach is detrimental for model optimization because occlusions and moving objects in a scene violate the underlying static scenario assumption. In addition, pixels in textureless regions or less discriminative pixels hinder model training. To address these problems, in this paper, we deal with moving objects and occlusions by utilizing the differences between the flow fields, and the differences between the depth structure generated by affine transformation and view synthesis, respectively. Secondly, we mitigate the effect of textureless regions on model optimization by measuring the differences between features with more semantic and contextual information without requiring additional networks. In addition, although the bidirectionality component is used in each sub-objective function, a pair of images is reasoned about only once, which helps reduce overhead. Extensive experiments and visual analysis demonstrate the effectiveness of the proposed method, which outperforms existing state-of-the-art self-supervised methods under the same conditions and without introducing additional auxiliary information.

9 February 2026 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
PLPenglei Liu
Penglei Liu
FWFei Wang
Fei Wang
YLYu Liu
Yu Liu
JCJun Cheng
Jun Cheng
6D pose estimation is a crucial subfield of visual measurement, extensively applied in robotics, autonomous driving, and augmented reality. Existing instance-level and category-level 6D pose estimation methods typically rely on prior object models or category labels, limiting their generalization and scalability in complex and dynamic environments. To address this limitation, we propose GCM-Pose, a general 6D pose estimation framework that performs inference using object-specific reference data. Specifically, a sparse Structure-from-Motion (SfM) model is first constructed from a set of RGB images or a short video. Then, GCM-Pose estimates the object’s 6D pose by establishing 2D-3D correspondences between the query image and the SfM model. This approach can be applied to novel objects without any CAD models. To handle cross-modal discrepancies and multi-scale variations in the 2D–3D feature matching process, we introduce a Cross-Modal Multi-Scale Deformable Attention (CMMDA) network trained with a triplet loss learning strategy. CMMDA addresses these issues by aligning feature descriptors from different modalities within a multi-scale latent high-dimensional space, enabling the establishment of precise and robust 2D-3D correspondences. We also construct a large-scale dataset consisting of 200 objects under various real-world conditions, including lighting variation, occlusion, and transparent objects. Experimental results on LineMOD, OnePose-LowTexture, and real-world scenes demonstrate that GCM-Pose achieves SOTA performance, highlighting its effectiveness and wide applicability in 6D pose estimation tasks.