Lihua Hu
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
Lihua Hu has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
- Jifu Zhang
Taiyuan University of Science and Technology
10 shared publications - Sulan Zhang
Taiyuan University of Science and Technology
7 shared publications Jifu Zhang
School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China
2 shared publications- Ping Guo
Beijing Normal University
2 shared publications Shuntang Zhang
Shangdong Institute of Business and Technology, Yantai, China, --- Select a Country --
2 shared publicationsXiaoling Yao
School of Computer Science and Technology, Taiyuan University of Science and Technology, Taiyuan, China
2 shared publications
Latest Publications
- 28 January 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 337
Multimodal interpretable image recognition network via language-guided global-local collaboratively alignment
- 28 January 2026
- Published by Elsevier in Knowledge-Based Systems
- Vol. 337
Multimodal interpretable image recognition network via language-guided global-local collaboratively alignment
- 17 January 2026
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (1) , 28
CFG-NeRF: coordinate-feature-gate collaborative optimization for sparse-view ancient architecture reconstruction
- 17 January 2026
- Published by Springer Nature in Pattern Analysis and Applications
- Vol. 29 (1) , 28
CFG-NeRF: coordinate-feature-gate collaborative optimization for sparse-view ancient architecture reconstruction
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12255-12266
Hyperbolic Concept Bottleneck Model for Interpretable Fine-Grained Image Classification
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 28, 12255-12266
Hyperbolic Concept Bottleneck Model for Interpretable Fine-Grained Image Classification
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
LrpcSIDE: Unsupervised Depth Estimation Powered by Left–Right Point Cloud Consistency
As one of the most studied topics in 3D reconstruction, single image-based depth estimation (SIDE) has achieved good performance in some scenes. However, SIDE methods suffer from distortions in the in-planar regions of reconstructed 3D point clouds due to the lack of consideration for directly using geometric information to impose constraints in 3D space, especially when repeated textural and complex structural patterns are abundant. In the work, we proposed an unsupervised SIDE method (LrpcSIDE) by using the left-right point cloud consistency constraint. First, we guided the dense-encoder features toward the desired depth prediction across multiple scales of the encoder-decoder structure and strengthened the perception of the estimation network in both detail and global perspective. Second, we designed a novel training loss function based on the left-right point cloud consistency constraint which enforced a consistency between the disparities produced relative to both the left and right point cloud, thus the distortion in the point cloud plane is curbed. Third, an unsupervised network was devised by using binocular image pairs, eliminating any potential adverse effects caused by unknown scale or pose estimation errors. Forth, the disparity map was transformed into a depth map by leveraging the relationship between the camera baseline distance and focal length, achieving end-to-end single-image depth estimation effectively. In the end, extensive experimental results on the KITTI and ancient architecture datasets verify that our method could accurately recover the 3D structure of scenes with high depth prediction and minimal depth estimation errors, and exhibit good depth estimation performance for application scenes with complex structures and repetitive textures. Source code is available at https://github.com/yaozz1110/LrpcSIDE.
- 27 February 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-11
LrpcSIDE: Unsupervised Depth Estimation Powered by Left–Right Point Cloud Consistency
As one of the most studied topics in 3D reconstruction, single image-based depth estimation (SIDE) has achieved good performance in some scenes. However, SIDE methods suffer from distortions in the in-planar regions of reconstructed 3D point clouds due to the lack of consideration for directly using geometric information to impose constraints in 3D space, especially when repeated textural and complex structural patterns are abundant. In the work, we proposed an unsupervised SIDE method (LrpcSIDE) by using the left-right point cloud consistency constraint. First, we guided the dense-encoder features toward the desired depth prediction across multiple scales of the encoder-decoder structure and strengthened the perception of the estimation network in both detail and global perspective. Second, we designed a novel training loss function based on the left-right point cloud consistency constraint which enforced a consistency between the disparities produced relative to both the left and right point cloud, thus the distortion in the point cloud plane is curbed. Third, an unsupervised network was devised by using binocular image pairs, eliminating any potential adverse effects caused by unknown scale or pose estimation errors. Forth, the disparity map was transformed into a depth map by leveraging the relationship between the camera baseline distance and focal length, achieving end-to-end single-image depth estimation effectively. In the end, extensive experimental results on the KITTI and ancient architecture datasets verify that our method could accurately recover the 3D structure of scenes with high depth prediction and minimal depth estimation errors, and exhibit good depth estimation performance for application scenes with complex structures and repetitive textures. Source code is available at https://github.com/yaozz1110/LrpcSIDE.
- 7 December 2024
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 22 (1) , 1-14
Towards real-time accurate dense pedestrian detection via large-kernel perception module and multi-level feature fusion
- 7 December 2024
- Published by Springer Nature in Journal of Real-Time Image Processing
- Vol. 22 (1) , 1-14
Towards real-time accurate dense pedestrian detection via large-kernel perception module and multi-level feature fusion
- 3 October 2024
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (4) , 2487-2502
An incomplete multi-view clustering approach using subspace alignment constraint
- 3 October 2024
- Published by Springer Nature in International Journal of Machine Learning and Cybernetics
- Vol. 16 (4) , 2487-2502
An incomplete multi-view clustering approach using subspace alignment constraint
- Open Access
- 30 August 2024
- Published by Springer Nature in Heritage Science
- Vol. 12 (1) , 1-13
Reconstructing the local structures of Chinese ancient architecture using unsupervised depth estimation
Digitalization of ancient architectures is one of the effective means for the preservation of heritage structures, with 3D reconstruction based on computer vision being a key component of such digitalization techniques. However, Chinese ancient architectures are located in mountainous areas, and existing 3D reconstruction methods fall short in restoring the local structures of these architectures. This paper proposes a self-attention-guided unsupervised single image-based depth estimation method, providing innovative technical support for the reconstruction of local structures in Chinese ancient architectures. First, an attention module is constructed based on features extracted from architectural images learned by the encoder, and then embedded into the encoder-decoder to capture the interdependencies across local features. Second, a disparity map is generated using the loss constraint network, including reconstruction matching, smoothness of the disparity, and left-right disparity consistency. Third, an unsupervised architecture based on binocular image pairs is constructed to remove any potential adverse effects due to unknown scale or estimated pose errors. Finally, with the known baseline distance and camera focal length, the disparity map is converted into the depth map to perform the end-to-end depth estimation from a single image. Experiments on the our architecture dataset validates our method, and it performs well also well on KITTI.
- 30 August 2024
- Published by Springer Nature in Heritage Science
- Vol. 12 (1) , 1-13
Open AccessReconstructing the local structures of Chinese ancient architecture using unsupervised depth estimation
Digitalization of ancient architectures is one of the effective means for the preservation of heritage structures, with 3D reconstruction based on computer vision being a key component of such digitalization techniques. However, Chinese ancient architectures are located in mountainous areas, and existing 3D reconstruction methods fall short in restoring the local structures of these architectures. This paper proposes a self-attention-guided unsupervised single image-based depth estimation method, providing innovative technical support for the reconstruction of local structures in Chinese ancient architectures. First, an attention module is constructed based on features extracted from architectural images learned by the encoder, and then embedded into the encoder-decoder to capture the interdependencies across local features. Second, a disparity map is generated using the loss constraint network, including reconstruction matching, smoothness of the disparity, and left-right disparity consistency. Third, an unsupervised architecture based on binocular image pairs is constructed to remove any potential adverse effects due to unknown scale or estimated pose errors. Finally, with the known baseline distance and camera focal length, the disparity map is converted into the depth map to perform the end-to-end depth estimation from a single image. Experiments on the our architecture dataset validates our method, and it performs well also well on KITTI.
- Open Access
Weakly Supervised Pose Estimation of Surgical Instrument from a Single Endoscopic Image
Instrument pose estimation is a key demand in computer-aided surgery, and its main challenges lie in two aspects: Firstly, the difficulty of obtaining stable corresponding image feature points due to the instruments’ high refraction and complicated background, and secondly, the lack of labeled pose data. This study aims to tackle the pose estimation problem of surgical instruments in the current endoscope system using a single endoscopic image. More specifically, a weakly supervised method based on the instrument’s image segmentation contour is proposed, with the effective assistance of synthesized endoscopic images. Our method consists of the following three modules: a segmentation module to automatically detect the instrument in the input image, followed by a point inference module to predict the image locations of the implicit feature points of the instrument, and a point back-propagatable Perspective-n-Point module to estimate the pose from the tentative 2D–3D corresponding points. To alleviate the over-reliance on point correspondence accuracy, the local errors of feature point matching and the global inconsistency of the corresponding contours are simultaneously minimized. Our proposed method is validated with both real and synthetic images in comparison with the current state-of-the-art methods.
Open AccessWeakly Supervised Pose Estimation of Surgical Instrument from a Single Endoscopic Image
Instrument pose estimation is a key demand in computer-aided surgery, and its main challenges lie in two aspects: Firstly, the difficulty of obtaining stable corresponding image feature points due to the instruments’ high refraction and complicated background, and secondly, the lack of labeled pose data. This study aims to tackle the pose estimation problem of surgical instruments in the current endoscope system using a single endoscopic image. More specifically, a weakly supervised method based on the instrument’s image segmentation contour is proposed, with the effective assistance of synthesized endoscopic images. Our method consists of the following three modules: a segmentation module to automatically detect the instrument in the input image, followed by a point inference module to predict the image locations of the implicit feature points of the instrument, and a point back-propagatable Perspective-n-Point module to estimate the pose from the tentative 2D–3D corresponding points. To alleviate the over-reliance on point correspondence accuracy, the local errors of feature point matching and the global inconsistency of the corresponding contours are simultaneously minimized. Our proposed method is validated with both real and synthetic images in comparison with the current state-of-the-art methods.
- Open Access
- 11 May 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (4) , 5569-5583
EMC+GD_C: circle-based enhanced motion consistency and guided diffusion feature matching for 3D reconstruction
Robust matching, especially the number, precision and distribution of feature point matching, directly affects the effect of 3D reconstruction. However, the existing methods rarely consider these three aspects comprehensively to improve the quality of feature matching, which in turn affects the effect of 3D reconstruction. Therefore, to effectively improve the quality of 3D reconstruction, we propose a circle-based enhanced motion consistency and guided diffusion feature matching algorithm for 3D reconstruction named EMC+GD_C. Firstly, a circle-based neighborhood division method is proposed, which increases the number of initial matching points. Secondly, to improve the precision of feature point matching, on the one hand, we put forward the idea of enhancing motion consistency, reducing the mismatch of high similarity feature points by enhancing the judgment conditions of true and false matching points; on the other hand, we combine the RANSAC optimization method to filter out the outliers and further improve the precision of feature point matching. Finally, a novel guided diffusion idea combining guided matching and motion consistency is proposed, which expands the distribution range of feature point matching and improves the stability of 3D models. Experiments on 8 sets of 908 pairs of images in the public 3D reconstruction datasets demonstrate that our method can achieve better matching performance and show stronger stability in 3D reconstruction. Specifically, EMC+GD_C achieves an average improvement of 24.07% compared to SIFT-based ratio test, 9.18% to GMS and 1.94% to EMC+GD_G in feature matching precision.
- 11 May 2024
- Published by Springer Nature in Complex & Intelligent Systems
- Vol. 10 (4) , 5569-5583
Open AccessEMC+GD_C: circle-based enhanced motion consistency and guided diffusion feature matching for 3D reconstruction
Robust matching, especially the number, precision and distribution of feature point matching, directly affects the effect of 3D reconstruction. However, the existing methods rarely consider these three aspects comprehensively to improve the quality of feature matching, which in turn affects the effect of 3D reconstruction. Therefore, to effectively improve the quality of 3D reconstruction, we propose a circle-based enhanced motion consistency and guided diffusion feature matching algorithm for 3D reconstruction named EMC+GD_C. Firstly, a circle-based neighborhood division method is proposed, which increases the number of initial matching points. Secondly, to improve the precision of feature point matching, on the one hand, we put forward the idea of enhancing motion consistency, reducing the mismatch of high similarity feature points by enhancing the judgment conditions of true and false matching points; on the other hand, we combine the RANSAC optimization method to filter out the outliers and further improve the precision of feature point matching. Finally, a novel guided diffusion idea combining guided matching and motion consistency is proposed, which expands the distribution range of feature point matching and improves the stability of 3D models. Experiments on 8 sets of 908 pairs of images in the public 3D reconstruction datasets demonstrate that our method can achieve better matching performance and show stronger stability in 3D reconstruction. Specifically, EMC+GD_C achieves an average improvement of 24.07% compared to SIFT-based ratio test, 9.18% to GMS and 1.94% to EMC+GD_G in feature matching precision.
- 16 March 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (8) , 4093-4113
Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes
- 16 March 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 84 (8) , 4093-4113
Context feature fusion and enhanced non-maximum suppression for pedestrian detection in crowded scenes