Lejia Ye
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Lejia Ye has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Xiaohu Zhang
School of Aeronautics and Astronautics, Sun Yat-Sen University, Shenzhen, Guangdong, China
3 shared publications - Guangsheng Xu
School of Aeronautics and Astronautics, Sun Yat-Sen University, Shenzhen, Guangdong, China
2 shared publications - Guoyi Zhang
School of Aeronautics and Astronautics, Sun Yat-Sen University, Shenzhen, Guangdong, China
2 shared publications - Bin Wu1 shared publication
- Jingjing Gao1 shared publication
- Lian Xu
The University of Western Australia
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by Elsevier in SSRN Electronic Journal
Robust Non-Contact Vision-Based Measurement of Astronaut Body Keypoint Locations
In crewed space missions, accurate acquisition of astronauts’ body motion states is important for intravehicular and extravehicular operation monitoring, task performance assessment, and mission safety assurance. As fundamental image-based measurements for subsequent three-dimensional pose reconstruction, accurate 2D body keypoint locations are critical to the reliability of downstream 3D motion estimation. However, non-contact keypoint measurement from images remains challenging in spacesuit environments because bulky suit structures, weak joint appearance, limited texture, strong reflectance, occlusion, and large viewpoint variations substantially degrade localization accuracy. In addition, existing spacesuit datasets are limited in scale and mainly cover relatively simple scenarios, restricting systematic evaluation under challenging conditions. To address these limitations, we construct CSPose, a challenging spacesuit keypoint dataset containing over 1,000 images from diverse astronaut task scenarios. We further propose MFRNet, a robust vision-based keypoint measurement framework based on Segment Anything Model 2 (SAM2). MFRNet employs lightweight task adaptation to capture spacesuit-specific visual characteristics and introduces multi-level feature fusion and multi-resolution refinement to preserve spatial details, strengthen structural representation, and improve fine-grained keypoint localization. Experimental results show that MFRNet outperforms representative methods on both CSPose and the public CrowdPose benchmark. With the Hiera-L backbone, MFRNet achieves 85.9 AP on CSPose and 70.5 AP on CrowdPose, demonstrating strong robustness and generalization for non-contact astronaut body keypoint measurement.
- 30 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessRobust Non-Contact Vision-Based Measurement of Astronaut Body Keypoint Locations
In crewed space missions, accurate acquisition of astronauts’ body motion states is important for intravehicular and extravehicular operation monitoring, task performance assessment, and mission safety assurance. As fundamental image-based measurements for subsequent three-dimensional pose reconstruction, accurate 2D body keypoint locations are critical to the reliability of downstream 3D motion estimation. However, non-contact keypoint measurement from images remains challenging in spacesuit environments because bulky suit structures, weak joint appearance, limited texture, strong reflectance, occlusion, and large viewpoint variations substantially degrade localization accuracy. In addition, existing spacesuit datasets are limited in scale and mainly cover relatively simple scenarios, restricting systematic evaluation under challenging conditions. To address these limitations, we construct CSPose, a challenging spacesuit keypoint dataset containing over 1,000 images from diverse astronaut task scenarios. We further propose MFRNet, a robust vision-based keypoint measurement framework based on Segment Anything Model 2 (SAM2). MFRNet employs lightweight task adaptation to capture spacesuit-specific visual characteristics and introduces multi-level feature fusion and multi-resolution refinement to preserve spatial details, strengthen structural representation, and improve fine-grained keypoint localization. Experimental results show that MFRNet outperforms representative methods on both CSPose and the public CrowdPose benchmark. With the Hiera-L backbone, MFRNet achieves 85.9 AP on CSPose and 70.5 AP on CrowdPose, demonstrating strong robustness and generalization for non-contact astronaut body keypoint measurement.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4106-4121
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces, which pose distinct modeling demands. Existing methods often treat these surface types separately, limiting their generalizability and physical plausibility. To bridge this gap, we propose MicroSDF, a novel neural implicit framework that facilitates geometry and reflectance modeling through microfacet theory. Our approach incorporates three core innovations: (i) a microfacet-guided geometry model that extracts multi-scale surface normals (macroscopic and microfacet) from a signed distance field (SDF), regularized by a proposed microfacet normal consistency loss to enforce physically plausible surface orientations; (ii) an enhanced dual-branch color model, where the specular branch leverages the microfacet normals to model high-frequency reflectance, and the vanilla branch, unlike prior works, uses reflection direction (instead of viewing direction) to better model diffuse and low-frequency specular components; and (iii) a detection-guided color blending strategy that adaptively fuses the color outputs based on reflection priors, providing more physically intuitive blending than implicitly learned blending weights. Combined with a tailored multi-stage optimization scheme, the proposed MicroSDF achieves robust and high-fidelity reconstruction across reflective and non-reflective surfaces. Extensive experiments on DTU, Shiny Blender, Ref-NeRF, and DeepVoxels datasets demonstrate state-of-the-art performance, establishing a new direction for physically grounded neural reconstruction.
- 1 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35 (10577149) , 4106-4121
MicroSDF: Microfacet-Driven Hybrid Neural SDFs for Mixed-Reflectance Surface Reconstruction
Accurate 3D reconstruction in real-world environments remains a significant challenge due to the coexistence of reflective and non-reflective surfaces, which pose distinct modeling demands. Existing methods often treat these surface types separately, limiting their generalizability and physical plausibility. To bridge this gap, we propose MicroSDF, a novel neural implicit framework that facilitates geometry and reflectance modeling through microfacet theory. Our approach incorporates three core innovations: (i) a microfacet-guided geometry model that extracts multi-scale surface normals (macroscopic and microfacet) from a signed distance field (SDF), regularized by a proposed microfacet normal consistency loss to enforce physically plausible surface orientations; (ii) an enhanced dual-branch color model, where the specular branch leverages the microfacet normals to model high-frequency reflectance, and the vanilla branch, unlike prior works, uses reflection direction (instead of viewing direction) to better model diffuse and low-frequency specular components; and (iii) a detection-guided color blending strategy that adaptively fuses the color outputs based on reflection priors, providing more physically intuitive blending than implicitly learned blending weights. Combined with a tailored multi-stage optimization scheme, the proposed MicroSDF achieves robust and high-fidelity reconstruction across reflective and non-reflective surfaces. Extensive experiments on DTU, Shiny Blender, Ref-NeRF, and DeepVoxels datasets demonstrate state-of-the-art performance, establishing a new direction for physically grounded neural reconstruction.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (12) , 12306-12316
Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation
Transformer-based methods have recently achieved significant success in 3D human pose estimation, owing to their strong ability to model long-range dependencies. However, relying solely on the global attention mechanism is insufficient for capturing the fine-grained local details, which are crucial for accurate pose estimation. Existing local feature extraction networks, such as Graph Convolutional Networks, often suffer from over-smoothing, while small-kernel CNNs have limited receptive fields and are highly sensitive to 2D pose errors. These limitations constrain the full potential of data-driven approaches. To address this, we propose SSR-STF, a dual-stream model that effectively integrates local features with global dependencies to enhance 3D human pose estimation. Specifically, we introduce SSRFormer, a simple yet effective module that employs the skeleton selective refine attention (SSRA) mechanism, leveraging large kernels to capture fine-grained local dependencies in human pose sequences. This complements the global dependencies modeled by the Transformer, enabling a more comprehensive understanding of human motion. By adaptively fusing these two feature streams, SSR-STF can better learn the underlying structure of human poses, overcoming the limitations of traditional methods in local feature extraction. To the best of our knowledge, this is the first work to explore the application of large kernels in skeleton-based 3D human pose estimation. Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that SSR-STF achieves state-of-the-art performance. Furthermore, the motion representations learned by our model prove effective in downstream tasks such as human mesh recovery. Codes are available at SSR-STF.
- 3 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (12) , 12306-12316
Optimizing Local-Global Dependencies for Accurate 3D Human Pose Estimation
Transformer-based methods have recently achieved significant success in 3D human pose estimation, owing to their strong ability to model long-range dependencies. However, relying solely on the global attention mechanism is insufficient for capturing the fine-grained local details, which are crucial for accurate pose estimation. Existing local feature extraction networks, such as Graph Convolutional Networks, often suffer from over-smoothing, while small-kernel CNNs have limited receptive fields and are highly sensitive to 2D pose errors. These limitations constrain the full potential of data-driven approaches. To address this, we propose SSR-STF, a dual-stream model that effectively integrates local features with global dependencies to enhance 3D human pose estimation. Specifically, we introduce SSRFormer, a simple yet effective module that employs the skeleton selective refine attention (SSRA) mechanism, leveraging large kernels to capture fine-grained local dependencies in human pose sequences. This complements the global dependencies modeled by the Transformer, enabling a more comprehensive understanding of human motion. By adaptively fusing these two feature streams, SSR-STF can better learn the underlying structure of human poses, overcoming the limitations of traditional methods in local feature extraction. To the best of our knowledge, this is the first work to explore the application of large kernels in skeleton-based 3D human pose estimation. Extensive experiments on the Human3.6M and MPI-INF-3DHP datasets demonstrate that SSR-STF achieves state-of-the-art performance. Furthermore, the motion representations learned by our model prove effective in downstream tasks such as human mesh recovery. Codes are available at SSR-STF.