Publications

You can also find my articles on my Google Scholar profile.

GeoReF: Geometric Alignment Across Shape Variation for Category-level Object Pose Refinement

Published in the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Object pose refinement is essential for robust object pose estimation. Previous work has made significant progress towards instance-level object pose refinement. Yet, category-level pose refinement is a more challenging problem due to large shape variations within a category and the discrepancies between the target object and the shape prior. To address these challenges, we introduce a novel architecture for category-level object pose refinement. Project page

Recommended citation: Linfang Zheng, Tze Ho Elden Tse, Chen Wang, Yinghan Sun, Hua Chen, Ales Leonardis, Wei Zhang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Multi-Resolution Planar Region Extraction for Uneven Terrains

Published in the IEEE International Conference on Robotics and Automation (ICRA), 2024

This paper studies the problem of extracting planar regions in uneven terrains from unordered point cloud measurements. Such a problem is critical in various robotic applications such as robotic perceptive locomotion. While existing approaches have shown promising results in effectively extracting planar regions from the environment, they often suffer from issues such as low computational efficiency or loss of resolution. To address these issues, we propose a multi-resolution planar region extraction strategy in this paper that balances the accuracy in boundaries and computational efficiency.

Recommended citation: Yinghan Sun, Linfang Zheng, Hua Chen, Wei Zhang, "Multi-Resolution Planar Region Extraction for Uneven Terrains," 2024 International Conference on Robotics and Automation (ICRA), Yokohama, Japan, 2024

Where Are They Looking in the 3D Space?

Published in the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023

We propose a novel depth-aware joint attention target estimation framework that estimates the attention target in 3D space. Our goal is to mimic human’s ability to understand where each person is looking in their proximity. In this work, we tackle the previously unexplored problem of utilising a depth prior along with a 3D joint FOV probability map to estimate the joint attention target of people in the scene.

Recommended citation: Nora Horanyi, Linfang Zheng, Eunji Chong, Aleš Leonardis, Hyung Jin Chang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2023, pp. 2678-2687

HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation

Published in the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023

In this paper, we focus on the problem of category-level object pose estimation, which is challenging due to the large intra-category shape variation. 3D graph convolution (3D-GC) based methods have been widely used to extract local geometric features, but they have limitations for complex shaped objects and are sensitive to noise. Moreover, the scale and translation invariant properties of 3D-GC restrict the perception of an object’s size and translation information. In this paper, we propose a simple network structure, the HS-layer, which extends 3D-GC to extract hybrid scope latent features from point cloud data for category-level object pose estimation tasks. Project page

Recommended citation: Linfang Zheng, Chen Wang, Yinghan Sun, Esha Dasgupta, Hua Chen, Aleš Leonardis, Wei Zhang, Hyung Jin Chang; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023, pp. 17163-17173

Trans6D: Transformer-Based 6D Object Pose Estimation and Refinement

Published in the European Conference on Computer Vision (ECCV) Workshops, 2023

Estimating 6D object pose from a monocular RGB image remains challenging due to factors such as texture-less and occlusion. Although convolution neural network (CNN)-based methods have made remarkable progress, they are not efficient in capturing global dependencies and often suffer from information loss due to downsampling operations. To extract robust feature representation, we propose a Transformer-based 6D object pose estimation approach (Trans6D).

Recommended citation: Zhang, Z., Chen, W., Zheng, L., Leonardis, A., Chang, H.J. (2023). Trans6D: Transformer-Based 6D Object Pose Estimation and Refinement. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds) Computer Vision – ECCV 2022 Workshops. ECCV 2022. Lecture Notes in Computer Science, vol 13808. Springer, Cham. https://doi.org/10.1007/978-3-031-25085-9_7

TP-AE: Temporally Primed 6D Object Pose Tracking with Auto-Encoders

Published in the IEEE International Conference on Robotics and Automation (ICRA), 2022

Fast and accurate tracking of an object’s motion is one of the key functionalities of a robotic system for achieving reliable interaction with the environment. This paper focuses on the instance-level 6D pose tracking problem with a symmetric and textureless object under occlusion. We propose a Temporally Primed 6D pose tracking framework with Auto-Encoders (TP-AE) to tackle the pose tracking problem. Project Page

Recommended citation: L. Zheng et al., "TP-AE: Temporally Primed 6D Object Pose Tracking with Auto-Encoders," 2022 International Conference on Robotics and Automation (ICRA), Philadelphia, PA, USA, 2022, pp. 10616-10623, doi: 10.1109/ICRA46639.2022.9811890.

Optimal Control Inspired Q-Learning for Switched Linear Systems

Published in the American Control Conference (ACC), 2020

This paper studies Q-learning for quadratic regulation problem of switched linear systems. Inspired by the analytical results from classical model-based optimal control, a structured Q-learning algorithm is developed.

Recommended citation: H. Chen, L. Zheng and W. Zhang, "Optimal Control Inspired Q-Learning for Switched Linear Systems," 2020 American Control Conference (ACC), Denver, CO, USA, 2020, pp. 4003-4010, doi: 10.23919/ACC45564.2020.9147818.

Linfang Zheng (郑林芳)