Yihui Liang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Yihui Liang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Han Huang
Sun Yat-sen University
7 shared publications - Fujian Feng
Guizhou Minzu University
4 shared publications - Hongshan Gou
School of Big Data and Information Engineering, Guiyang Institute of Humanities and Technology, Guiyang 550025, China
2 shared publications - Mian Tan
Guizhou Key Laboratory of Pattern Recognition and Intelligent System, College of Data Science and Information Engineering, Guizhou Minzu University, Guiyang 550025, China
2 shared publications - Yi Xiang
South China University of Technology
2 shared publications Zhaoquan Cai
2 shared publications
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 534-550
BoundMamba: Boundary-Aware State Space Modeling for Remote Sensing Change Detection
- 2 September 2026
- Published by Springer Nature
- p. 534-550
BoundMamba: Boundary-Aware State Space Modeling for Remote Sensing Change Detection
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (2) , 1726-1737
Microscale-Searching Evolutionary Optimization for Image Matting
Image matting is a fundamental computer vision task. It is a large-scale optimization problem involving the selection of pixel pairs from pixel-pair sets of an image. Less prior, such as the trimaps of images, is required for evolutionary algorithms (EAs) to solve the image matting problem compared to deep learning-based methods. However, it is challenging for EAs to solve the image matting problem efficiently due to the large size of the decision set. This paper proposes a framework to guide EAs to search in a microscale subset of the decision set. The subset is estimated by collecting best-so-far solutions during EAs solve similar subproblems. Experimental results demonstrated that by integrating the proposed framework, EAs require fewer FEs to achieve competitive results compared to their original versions. Additionally, the results also indicate that the proposed strategy enhance the performance of EAs in terms of mean squared error and connectivity metrics compared to other EAs-based methods in most cases. The contribution of our work is to make EAs efficient algorithms to solving the image matting problem in scenarios with weak prior.
- 24 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computational Intelligence
- Vol. 10 (2) , 1726-1737
Microscale-Searching Evolutionary Optimization for Image Matting
Image matting is a fundamental computer vision task. It is a large-scale optimization problem involving the selection of pixel pairs from pixel-pair sets of an image. Less prior, such as the trimaps of images, is required for evolutionary algorithms (EAs) to solve the image matting problem compared to deep learning-based methods. However, it is challenging for EAs to solve the image matting problem efficiently due to the large size of the decision set. This paper proposes a framework to guide EAs to search in a microscale subset of the decision set. The subset is estimated by collecting best-so-far solutions during EAs solve similar subproblems. Experimental results demonstrated that by integrating the proposed framework, EAs require fewer FEs to achieve competitive results compared to their original versions. Additionally, the results also indicate that the proposed strategy enhance the performance of EAs in terms of mean squared error and connectivity metrics compared to other EAs-based methods in most cases. The contribution of our work is to make EAs efficient algorithms to solving the image matting problem in scenarios with weak prior.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 3323-3335
High-Resolution Natural Image Matting by Refining Low-Resolution Alpha Mattes
High-resolution natural image matting plays an important role in image editing, film-making and remote sensing due to its ability of accurately extract the foreground from a natural background. However, due to the complexity brought about by the proliferation of resolution, the existing image matting methods cannot obtain high-quality alpha mattes on high-resolution images in reasonable time. To overcome this challenge, we introduce a high-resolution image matting framework based on alpha matte refinement from low-resolution to high-resolution (HRIMF-AMR). The proposed framework transforms the complex high-resolution image matting problem into low-resolution image matting problem and high-resolution alpha matte refinement problem. While the first problem is solved by adopting an existing image matting method, the latter is addressed by applying the Detail Difference Feature Extractor (DDFE) designed as a part of our work. The DDFE extracts detail difference features from high-resolution images by measuring the image feature difference between high-resolution images and low-resolution images. The low-resolution alpha matte is refined according to the extracted detail difference feature, providing the high-resolution alpha matte. In addition, the Matte Detail Resolution Difference (MDRD) loss is introduced to train the DDFE, which imposes an additional constraint on the extraction of detail difference features with mattes. Experimental results show that integrating HRIMF-AMR significantly enhances the performance of existing matting methods on high-resolution images of Transparent-460 and Alphamatting. Project page: https://github.com/yexianmin/HRAMR-Matting.
- 2 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 3323-3335
High-Resolution Natural Image Matting by Refining Low-Resolution Alpha Mattes
High-resolution natural image matting plays an important role in image editing, film-making and remote sensing due to its ability of accurately extract the foreground from a natural background. However, due to the complexity brought about by the proliferation of resolution, the existing image matting methods cannot obtain high-quality alpha mattes on high-resolution images in reasonable time. To overcome this challenge, we introduce a high-resolution image matting framework based on alpha matte refinement from low-resolution to high-resolution (HRIMF-AMR). The proposed framework transforms the complex high-resolution image matting problem into low-resolution image matting problem and high-resolution alpha matte refinement problem. While the first problem is solved by adopting an existing image matting method, the latter is addressed by applying the Detail Difference Feature Extractor (DDFE) designed as a part of our work. The DDFE extracts detail difference features from high-resolution images by measuring the image feature difference between high-resolution images and low-resolution images. The low-resolution alpha matte is refined according to the extracted detail difference feature, providing the high-resolution alpha matte. In addition, the Matte Detail Resolution Difference (MDRD) loss is introduced to train the DDFE, which imposes an additional constraint on the extraction of detail difference features with mattes. Experimental results show that integrating HRIMF-AMR significantly enhances the performance of existing matting methods on high-resolution images of Transparent-460 and Alphamatting. Project page: https://github.com/yexianmin/HRAMR-Matting.
- 22 December 2024
- Published by Springer Nature
- p. 81-94
Adaptive Pixel Pair Generation Strategy for Image Matting Methods Based on Pixel Pair Optimization
- 22 December 2024
- Published by Springer Nature
- p. 81-94
Adaptive Pixel Pair Generation Strategy for Image Matting Methods Based on Pixel Pair Optimization
- 30 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 62-74
Enhancing Transparent Object Matting Using Predicted Definite Foreground and Background
Natural image matting is a widely used image processing technique that extracts foreground by predicting the alpha values of the unknown region based on the alpha values of the known foreground and background regions. However, existing image matting methods may not yield the most optimal results when applied to images containing transparent objects because the known foreground region is small or even absent. To address this shortcoming, in this paper, we propose a novel method named Transparent Object Matting using Predicted Definite Foreground and Background (TOM-PDFB), which can explore and utilize the definite foreground and background in the unknown region. For this purpose, a newly developed foreground-background confidence estimator is applied to predict the confidence level of the definite foreground and the definite background, thus providing the priors required for transparent object matting. Next, foreground-background guided progressive refinement network developed as a part of this work is adopted to incorporate the estimated definite foreground and background into the alpha matte refinement process. Extensive experimental results demonstrate that the TOM-PDFB outperforms state-of-the-art methods when applied to transparent objects. Project page: https://github.com/fuqian95/TOM-PDFB.
- 30 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 62-74
Enhancing Transparent Object Matting Using Predicted Definite Foreground and Background
Natural image matting is a widely used image processing technique that extracts foreground by predicting the alpha values of the unknown region based on the alpha values of the known foreground and background regions. However, existing image matting methods may not yield the most optimal results when applied to images containing transparent objects because the known foreground region is small or even absent. To address this shortcoming, in this paper, we propose a novel method named Transparent Object Matting using Predicted Definite Foreground and Background (TOM-PDFB), which can explore and utilize the definite foreground and background in the unknown region. For this purpose, a newly developed foreground-background confidence estimator is applied to predict the confidence level of the definite foreground and the definite background, thus providing the priors required for transparent object matting. Next, foreground-background guided progressive refinement network developed as a part of this work is adopted to incorporate the estimated definite foreground and background into the alpha matte refinement process. Extensive experimental results demonstrate that the TOM-PDFB outperforms state-of-the-art methods when applied to transparent objects. Project page: https://github.com/fuqian95/TOM-PDFB.
- Open Access
- 10 July 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (3) , 301
Multi-Criterion Sampling Matting Algorithm via Gaussian Process
Natural image matting is an essential technique for image processing that enables various applications, such as image synthesis, video editing, and target tracking. However, the existing image matting methods may fail to produce satisfactory results when computing resources are limited. Sampling-based methods can reduce the dimensionality of the decision space and, therefore, reduce computational resources by employing different sampling strategies. While these approaches reduce computational consumption, they may miss an optimal pixel pair when the number of available high-quality pixel pairs is limited. To address this shortcoming, we propose a novel multi-criterion sampling strategy that avoids missing high-quality pixel pairs by incorporating multi-range pixel pair sampling and a high-quality sample selection method. This strategy is employed to develop a multi-criterion matting algorithm via Gaussian process, which searches for the optimal pixel pair by using the Gaussian process fitting model instead of solving the original pixel pair objective function. The experimental results demonstrate that our proposed algorithm outperformed other methods, even with 1% computing resources, and achieved alpha matte results comparable to those yielded by the state-of-the-art optimization algorithms.
- 10 July 2023
- Published by MDPI AG in Biomimetics
- Vol. 8 (3) , 301
Open AccessMulti-Criterion Sampling Matting Algorithm via Gaussian Process
Natural image matting is an essential technique for image processing that enables various applications, such as image synthesis, video editing, and target tracking. However, the existing image matting methods may fail to produce satisfactory results when computing resources are limited. Sampling-based methods can reduce the dimensionality of the decision space and, therefore, reduce computational resources by employing different sampling strategies. While these approaches reduce computational consumption, they may miss an optimal pixel pair when the number of available high-quality pixel pairs is limited. To address this shortcoming, we propose a novel multi-criterion sampling strategy that avoids missing high-quality pixel pairs by incorporating multi-range pixel pair sampling and a high-quality sample selection method. This strategy is employed to develop a multi-criterion matting algorithm via Gaussian process, which searches for the optimal pixel pair by using the Gaussian process fitting model instead of solving the original pixel pair objective function. The experimental results demonstrate that our proposed algorithm outperformed other methods, even with 1% computing resources, and achieved alpha matte results comparable to those yielded by the state-of-the-art optimization algorithms.
- Open Access
- 5 June 2023
- Published by MDPI AG in Preprints.org
Multi-criterion Sampling Matting Algorithm via Gaussian Process
Natural image matting is an essential technique for image processing that enables various applications, such as image synthesis, video editing, and target tracking. However, the existing image matting methods may fail to produce satisfactory results when computing resources are limited. Sampling-based methods can reduce the dimensionality of the decision space and therefore reduce computational resources by employing different sampling strategies. While these approaches reduce computational consumption, they may miss an optimal pixel pair when the number of available high-quality pixel pairs is limited. To address this shortcoming, we propose a novel multi-criterion sampling strategy that avoids missing high-quality pixel pairs by incorporating multi-range pixel pair sampling and high-quality samples selection method. This strategy is employed to develop a multi-criterion matting algorithm via Gaussian process, which searches for the optimal pixel pair by using the Gaussian process fitting model instead of solving the original pixel pair objective function. Experimental results demonstrate that our proposed algorithm outperforms other methods even with 1% computing resources, and achieves alpha matte results comparable to those yielded by the state-of-the-art optimization algorithms.
- 5 June 2023
- Published by MDPI AG in Preprints.org
Open AccessMulti-criterion Sampling Matting Algorithm via Gaussian Process
Natural image matting is an essential technique for image processing that enables various applications, such as image synthesis, video editing, and target tracking. However, the existing image matting methods may fail to produce satisfactory results when computing resources are limited. Sampling-based methods can reduce the dimensionality of the decision space and therefore reduce computational resources by employing different sampling strategies. While these approaches reduce computational consumption, they may miss an optimal pixel pair when the number of available high-quality pixel pairs is limited. To address this shortcoming, we propose a novel multi-criterion sampling strategy that avoids missing high-quality pixel pairs by incorporating multi-range pixel pair sampling and high-quality samples selection method. This strategy is employed to develop a multi-criterion matting algorithm via Gaussian process, which searches for the optimal pixel pair by using the Gaussian process fitting model instead of solving the original pixel pair objective function. Experimental results demonstrate that our proposed algorithm outperforms other methods even with 1% computing resources, and achieves alpha matte results comparable to those yielded by the state-of-the-art optimization algorithms.
- Open Access
- 18 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 93487-93498
Pyramid Matting: A Resource-Adaptive Multi-Scale Pixel Pair Optimization Framework for Image Matting
Image matting is an important problem in computer vision with significant theoretical interest and diverse practical applications, including image/video editing, target tracking, and object recognition. Pixel-pair-optimization-based image matting approaches have been shown very successful in estimating the opacity of the foreground by searching for the best pair of foreground and background pixels for each unknown pixel. However, extant approaches encounter difficulties in adapting to the changes of available computing resources, which limits the application of image matting. This drawback has motivated the present study, as a part of which a multi-scale evolutionary pixel pair optimization framework named pyramid matting framework (PMF) was developed. In this framework, the large-scale pixel pair optimization problem is transformed to multiple pixel pair optimization problems of different scales using image pyramid. The resulting problems are solved level by level, starting from the problem at the small scale. Pixel pair heuristic information obtained from solving low-scale problems are iteratively propagated to the spatially-related pixel pairs in the larger-scale problem. PMF can adapt to changes in available computing resources due to its capability of transforming a small-scale problem solution to the large-scale problem solution through the heuristic information propagation. Experimental results show that the PMF-based image matting approach not only provides high-quality alpha mattes with sufficient computing resources, but also works well when computing resources are scarce.
- 18 May 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 93487-93498
Open AccessPyramid Matting: A Resource-Adaptive Multi-Scale Pixel Pair Optimization Framework for Image Matting
Image matting is an important problem in computer vision with significant theoretical interest and diverse practical applications, including image/video editing, target tracking, and object recognition. Pixel-pair-optimization-based image matting approaches have been shown very successful in estimating the opacity of the foreground by searching for the best pair of foreground and background pixels for each unknown pixel. However, extant approaches encounter difficulties in adapting to the changes of available computing resources, which limits the application of image matting. This drawback has motivated the present study, as a part of which a multi-scale evolutionary pixel pair optimization framework named pyramid matting framework (PMF) was developed. In this framework, the large-scale pixel pair optimization problem is transformed to multiple pixel pair optimization problems of different scales using image pyramid. The resulting problems are solved level by level, starting from the problem at the small scale. Pixel pair heuristic information obtained from solving low-scale problems are iteratively propagated to the spatially-related pixel pairs in the larger-scale problem. PMF can adapt to changes in available computing resources due to its capability of transforming a small-scale problem solution to the large-scale problem solution through the heuristic information propagation. Experimental results show that the PMF-based image matting approach not only provides high-quality alpha mattes with sufficient computing resources, but also works well when computing resources are scarce.
- 1 April 2019
- Published by Elsevier in Applied Soft Computing
- Vol. 77, 484-496
Deep infrared pedestrian classification based on automatic image matting
- 1 April 2019
- Published by Elsevier in Applied Soft Computing
- Vol. 77, 484-496
Deep infrared pedestrian classification based on automatic image matting
- 5 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 28 (8) , 3739-3751
Pixel-Level Discrete Multiobjective Sampling for Image Matting
In sampling-based matting methods, the alpha is estimated by choosing the best pair of foreground and background color samples. Lack of true samples is the major obstacle to obtaining high-quality alpha mattes. Regrettably, several proposed approaches did not address the conflicts among multiple sampling criteria and the effects of incomplete sample spaces. To address this issue, we propose a pixel-level discrete multiobjective sampling method (PDMS). The color sampling process at each unknown pixel is formalized as a multiobjective optimization problem (MOP). The strength of PDMS includes its ability to minimize both color difference and spatial distance between unknown and known pixels, and its capacity of adaptively making trade-offs among conflicting sampling criteria. To mitigate the effects of incomplete sample spaces, the sample space is extended to complete known regions in PDMS, which means that the colors of all known pixels can be sampled, instead of mean colors of superpixels. Our experimental results show that PDMS collects a small set of samples while achieving smaller minimum absolute difference in alpha estimation. Moreover, PDMS implements pixel-level sampling by using the proposed multiobjective optimization algorithm to efficiently solve sampling MOPs. The PDMS-based matting method provides high-quality alpha mattes with sharp boundaries and thus outperforms those prior image matting methods in terms of gradient error.
- 5 March 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 28 (8) , 3739-3751
Pixel-Level Discrete Multiobjective Sampling for Image Matting
In sampling-based matting methods, the alpha is estimated by choosing the best pair of foreground and background color samples. Lack of true samples is the major obstacle to obtaining high-quality alpha mattes. Regrettably, several proposed approaches did not address the conflicts among multiple sampling criteria and the effects of incomplete sample spaces. To address this issue, we propose a pixel-level discrete multiobjective sampling method (PDMS). The color sampling process at each unknown pixel is formalized as a multiobjective optimization problem (MOP). The strength of PDMS includes its ability to minimize both color difference and spatial distance between unknown and known pixels, and its capacity of adaptively making trade-offs among conflicting sampling criteria. To mitigate the effects of incomplete sample spaces, the sample space is extended to complete known regions in PDMS, which means that the colors of all known pixels can be sampled, instead of mean colors of superpixels. Our experimental results show that PDMS collects a small set of samples while achieving smaller minimum absolute difference in alpha estimation. Moreover, PDMS implements pixel-level sampling by using the proposed multiobjective optimization algorithm to efficiently solve sampling MOPs. The PDMS-based matting method provides high-quality alpha mattes with sharp boundaries and thus outperforms those prior image matting methods in terms of gradient error.