Xuelin Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xuelin Shen has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Wenhan Yang
Pengcheng Laboratory, Shenzhen, China
6 shared publications - Shiqi Wang
City University of Hong Kong, Hong Kong, China
4 shared publications - Kang Xiao
School of Data Science, Lingnan University, Hong Kong, China
3 shared publications - Sam Kwong
Lingnan University
3 shared publications - Silin Zheng
College of Computer Science and Software Engineering, Shenzhen University
3 shared publications - Xu Wang
Shenzhen University
3 shared publications
Latest Publications
- 9 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 177
Towards Generalized Image Coding for Machine Through Meta Adversarial Adaptation
- 9 March 2026
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 134 (4) , 177
Towards Generalized Image Coding for Machine Through Meta Adversarial Adaptation
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 8199-8211
Transferring From Distortion to Perception-Oriented Optimization: Just-Noticeable-Distortion-Based Domain Adaptation
The perception-distortion- tradeoff reveals the limitation of current low-level deep learning paradigms, i.e., minimizing reconstruction distortion does not guarantee improved perceptual quality. Acknowledging the lack of a reliable perception-oriented optimization function, we are motivated to explore a flexible approach for enhancing perceptual quality by steering the tradeoff to prioritize perception. To this end, we reconsider the perception-distortion function by incorporating the Just-Noticeable-Distortion (JND) mechanism. We mathematically demonstrate that in the common image restoration process, altering the optimization target from natural images to distorted images—where the distortion intensity is constrained by the JND threshold and the distortion type aligns with that arising from the restorer itself—effectively obtained improved perception indices without any changes to the restorer or optimization function. Accordingly, to facilitate various low-level learning models, we are motivated to construct the first large-scale CNN-oriented JND image dataset. Our dataset comprises 500 natural images and 4,500 degraded versions generated by a series of autoencoders, as well as the actual JND judgment results collected through rigorous subjective testing from twenty volunteers. Finally, a learning-based JND inference model is established on the proposed dataset and employed in the proposed JND-based adaptation scheme, where the inferred JND images serve as pseudo-ground truth for the training or fine-tuning processes of low-level vision models. Extensive experiments on image super-resolution and end-to-end image compression across multiple models have shown encouraging improvements in perceptual quality, demonstrating the effectiveness of the proposed scheme. Our dataset is available at: https://github.com/ohq17/CNN-Oriented-JND-Dataset.
- 2 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 27 (15209210) , 8199-8211
Transferring From Distortion to Perception-Oriented Optimization: Just-Noticeable-Distortion-Based Domain Adaptation
The perception-distortion- tradeoff reveals the limitation of current low-level deep learning paradigms, i.e., minimizing reconstruction distortion does not guarantee improved perceptual quality. Acknowledging the lack of a reliable perception-oriented optimization function, we are motivated to explore a flexible approach for enhancing perceptual quality by steering the tradeoff to prioritize perception. To this end, we reconsider the perception-distortion function by incorporating the Just-Noticeable-Distortion (JND) mechanism. We mathematically demonstrate that in the common image restoration process, altering the optimization target from natural images to distorted images—where the distortion intensity is constrained by the JND threshold and the distortion type aligns with that arising from the restorer itself—effectively obtained improved perception indices without any changes to the restorer or optimization function. Accordingly, to facilitate various low-level learning models, we are motivated to construct the first large-scale CNN-oriented JND image dataset. Our dataset comprises 500 natural images and 4,500 degraded versions generated by a series of autoencoders, as well as the actual JND judgment results collected through rigorous subjective testing from twenty volunteers. Finally, a learning-based JND inference model is established on the proposed dataset and employed in the proposed JND-based adaptation scheme, where the inferred JND images serve as pseudo-ground truth for the training or fine-tuning processes of low-level vision models. Extensive experiments on image super-resolution and end-to-end image compression across multiple models have shown encouraging improvements in perceptual quality, demonstrating the effectiveness of the proposed scheme. Our dataset is available at: https://github.com/ohq17/CNN-Oriented-JND-Dataset.
- 18 August 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 7924-7945
Monotonic and Invertible Network: A General Framework for Learning IQA Model from Mixed Datasets
- 18 August 2025
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 133 (11) , 7924-7945
Monotonic and Invertible Network: A General Framework for Learning IQA Model from Mixed Datasets
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (7) , 6833-6841
Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
In the context of Omni-Directional Image (ODI) Super-Resolution (SR), the unique challenge arises from the non-uniform oversampling characteristics caused by EquiRectangular Projection (ERP). Considerable efforts in designing complex spherical convolutions or polyhedron reprojection offer significant performance improvements but at the expense of cumbersome processing procedures and slower inference speeds. Under these circumstances, this paper proposes a new ODI-SR model characterized by its capacity to perform Fast and Arbitrary-scale ODI-SR processes, denoted as FAOR. The key innovation lies in adapting the implicit image function from the planar image domain to the ERP image domain by incorporating spherical geometric priors at both the latent representation and image reconstruction stages, in a low-overhead manner. Specifically, at the latent representation stage, we adopt a pair of pixel-wise and semantic-wise sphere-to-planar distortion maps to perform affine transformations on the latent representation, thereby incorporating it with spherical properties. Moreover, during the image reconstruction stage, we introduce a geodesic-based resampling strategy, aligning the implicit image function with spherical geometrics without introducing additional parameters. As a result, the proposed FAOR outperforms the state-of-the-art ODI-SR models with a much faster inference speed. Extensive experimental results and ablation studies have demonstrated the effectiveness of our design.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (7) , 6833-6841
Open AccessFast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
In the context of Omni-Directional Image (ODI) Super-Resolution (SR), the unique challenge arises from the non-uniform oversampling characteristics caused by EquiRectangular Projection (ERP). Considerable efforts in designing complex spherical convolutions or polyhedron reprojection offer significant performance improvements but at the expense of cumbersome processing procedures and slower inference speeds. Under these circumstances, this paper proposes a new ODI-SR model characterized by its capacity to perform Fast and Arbitrary-scale ODI-SR processes, denoted as FAOR. The key innovation lies in adapting the implicit image function from the planar image domain to the ERP image domain by incorporating spherical geometric priors at both the latent representation and image reconstruction stages, in a low-overhead manner. Specifically, at the latent representation stage, we adopt a pair of pixel-wise and semantic-wise sphere-to-planar distortion maps to perform affine transformations on the latent representation, thereby incorporating it with spherical properties. Moreover, during the image reconstruction stage, we introduce a geodesic-based resampling strategy, aligning the implicit image function with spherical geometrics without introducing additional parameters. As a result, the proposed FAOR outperforms the state-of-the-art ODI-SR models with a much faster inference speed. Extensive experimental results and ablation studies have demonstrated the effectiveness of our design.
- Open Access
Fast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
In the context of Omni-Directional Image (ODI) Super-Resolution (SR), the unique challenge arises from the non-uniform oversampling characteristics caused by EquiRectangular Projection (ERP). Considerable efforts in designing complex spherical convolutions or polyhedron reprojection offer significant performance improvements but at the expense of cumbersome processing procedures and slower inference speeds. Under these circumstances, this paper proposes a new ODI-SR model characterized by its capacity to perform Fast and Arbitrary-scale ODI-SR processes, denoted as FAOR. The key innovation lies in adapting the implicit image function from the planar image domain to the ERP image domain by incorporating spherical geometric priors at both the latent representation and image reconstruction stages, in a low-overhead manner. Specifically, at the latent representation stage, we adopt a pair of pixel-wise and semantic-wise sphere-to-planar distortion maps to perform affine transformations on the latent representation, thereby incorporating it with spherical properties. Moreover, during the image reconstruction stage, we introduce a geodesic-based resampling strategy, aligning the implicit image function with spherical geometrics without introducing additional parameters. As a result, the proposed FAOR outperforms the state-of-the-art ODI-SR models with a much faster inference speed. Extensive experimental results and ablation studies have demonstrated the effectiveness of our design.
Open AccessFast Omni-Directional Image Super-Resolution: Adapting the Implicit Image Function with Pixel and Semantic-Wise Spherical Geometric Priors
In the context of Omni-Directional Image (ODI) Super-Resolution (SR), the unique challenge arises from the non-uniform oversampling characteristics caused by EquiRectangular Projection (ERP). Considerable efforts in designing complex spherical convolutions or polyhedron reprojection offer significant performance improvements but at the expense of cumbersome processing procedures and slower inference speeds. Under these circumstances, this paper proposes a new ODI-SR model characterized by its capacity to perform Fast and Arbitrary-scale ODI-SR processes, denoted as FAOR. The key innovation lies in adapting the implicit image function from the planar image domain to the ERP image domain by incorporating spherical geometric priors at both the latent representation and image reconstruction stages, in a low-overhead manner. Specifically, at the latent representation stage, we adopt a pair of pixel-wise and semantic-wise sphere-to-planar distortion maps to perform affine transformations on the latent representation, thereby incorporating it with spherical properties. Moreover, during the image reconstruction stage, we introduce a geodesic-based resampling strategy, aligning the implicit image function with spherical geometrics without introducing additional parameters. As a result, the proposed FAOR outperforms the state-of-the-art ODI-SR models with a much faster inference speed. Extensive experimental results and ablation studies have demonstrated the effectiveness of our design.
- 14 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 510-521
Breaking Boundaries: Unifying Imaging and Compression for HDR Image Compression
High Dynamic Range (HDR) images present unique challenges for Learned Image Compression (LIC) due to their complex domain distribution compared to Low Dynamic Range (LDR) images. In coding practice, HDR-oriented LIC typically adopts preprocessing steps (e.g., perceptual quantization and tone mapping operation) to align the distributions between LDR and HDR images, which inevitably comes at the expense of perceptual quality. To address this challenge, we rethink the HDR imaging process which involves fusing multiple exposure LDR images to create an HDR image and propose a novel HDR image compression paradigm, Unifying Imaging and Compression (HDR-UIC). The key innovation lies in establishing a seamless pipeline from image capture to delivery and enabling end-to-end training and optimization. Specifically, a Mixture-ATtention (MAT)-based compression backbone merges LDR features while simultaneously generating a compact representation. Meanwhile, the Reference-guided Misalignment-aware feature Enhancement (RME) module mitigates ghosting artifacts caused by misalignment in the LDR branches, maintaining fidelity without introducing additional information. Furthermore, we introduce an Appearance Redundancy Removal (ARR) module to optimize coding resource allocation among LDR features, thereby enhancing the final HDR compression performance. Extensive experimental results demonstrate the efficacy of our approach, showing significant improvements over existing state-of-the-art HDR compression schemes. Our code is available at: https://github.com/plf1999/HDR-UIC.
- 14 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 34 (10577149) , 510-521
Breaking Boundaries: Unifying Imaging and Compression for HDR Image Compression
High Dynamic Range (HDR) images present unique challenges for Learned Image Compression (LIC) due to their complex domain distribution compared to Low Dynamic Range (LDR) images. In coding practice, HDR-oriented LIC typically adopts preprocessing steps (e.g., perceptual quantization and tone mapping operation) to align the distributions between LDR and HDR images, which inevitably comes at the expense of perceptual quality. To address this challenge, we rethink the HDR imaging process which involves fusing multiple exposure LDR images to create an HDR image and propose a novel HDR image compression paradigm, Unifying Imaging and Compression (HDR-UIC). The key innovation lies in establishing a seamless pipeline from image capture to delivery and enabling end-to-end training and optimization. Specifically, a Mixture-ATtention (MAT)-based compression backbone merges LDR features while simultaneously generating a compact representation. Meanwhile, the Reference-guided Misalignment-aware feature Enhancement (RME) module mitigates ghosting artifacts caused by misalignment in the LDR branches, maintaining fidelity without introducing additional information. Furthermore, we introduce an Appearance Redundancy Removal (ARR) module to optimize coding resource allocation among LDR features, thereby enhancing the final HDR compression performance. Extensive experimental results demonstrate the efficacy of our approach, showing significant improvements over existing state-of-the-art HDR compression schemes. Our code is available at: https://github.com/plf1999/HDR-UIC.
- Open Access
Sliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference. However, existing FR-IQA models including both the classical ones (eg, PSNR and SSIM) and deep-learning based measures (eg, LPIPS and DISTS) still exhibit limitations in capturing the full perception characteristics of the human visual system (HVS). In this paper, instead of designing a new FR-IQA measure, we aim to explore a generalized human visual attention estimation strategy to mimic the process of human quality rating and enhance existing IQA models. In particular, we model human attention generation by measuring the statistical dependency between the degraded image and the reference image. The dependency is captured in a training-free manner by our proposed sliced maximal information coefficient and exhibits surprising generalization in different IQA measures. Experimental results verify the performance of existing IQA models can be consistently improved when our attention module is incorporated. The source code is available at https://github.com/KANGX99/SMIC.
Open AccessSliced Maximal Information Coefficient: A Training-Free Approach for Image Quality Assessment Enhancement
Full-reference image quality assessment (FR-IQA) models generally operate by measuring the visual differences between a degraded image and its reference. However, existing FR-IQA models including both the classical ones (eg, PSNR and SSIM) and deep-learning based measures (eg, LPIPS and DISTS) still exhibit limitations in capturing the full perception characteristics of the human visual system (HVS). In this paper, instead of designing a new FR-IQA measure, we aim to explore a generalized human visual attention estimation strategy to mimic the process of human quality rating and enhance existing IQA models. In particular, we model human attention generation by measuring the statistical dependency between the degraded image and the reference image. The dependency is captured in a training-free manner by our proposed sliced maximal information coefficient and exhibits surprising generalization in different IQA measures. Experimental results verify the performance of existing IQA models can be consistently improved when our attention module is incorporated. The source code is available at https://github.com/KANGX99/SMIC.
- 1 May 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (42) , 90271-90288
Towards 360$^{\circ }$ image compression for machines via modulating pixel significance- 1 May 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (42) , 90271-90288
Towards 360$^{\circ }$ image compression for machines via modulating pixel significance- 3 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 26-38
Just Noticeable Distortion Profile Inference: A Patch-Level Structural Visibility Learning Approach
In this paper, we propose an effective approach to infer the just noticeable distortion (JND) profile based on patchlevel structural visibility learning. Instead of pixel-level JND profile estimation, the image patch, which is regarded as the basic processing unit to better correlate with the human perception, can be further decomposed into three conceptually independent components for visibility estimation. In particular, to incorporate the structural degradation into the patch-level JND model, a deep learning-based structural degradation estimation model is trained to approximate the masking of structural visibility. In order to facilitate the learning process, a JND dataset is further established, including 202 pristine images and 7878 distorted images generated by advanced compression algorithms based on the upcoming Versatile Video Coding (VVC) standard. Extensive experimental results further show the superiority of the proposed approach over the state-of-the-art.
- 3 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 26-38
Just Noticeable Distortion Profile Inference: A Patch-Level Structural Visibility Learning Approach
In this paper, we propose an effective approach to infer the just noticeable distortion (JND) profile based on patchlevel structural visibility learning. Instead of pixel-level JND profile estimation, the image patch, which is regarded as the basic processing unit to better correlate with the human perception, can be further decomposed into three conceptually independent components for visibility estimation. In particular, to incorporate the structural degradation into the patch-level JND model, a deep learning-based structural degradation estimation model is trained to approximate the masking of structural visibility. In order to facilitate the learning process, a JND dataset is further established, including 202 pristine images and 7878 distorted images generated by advanced compression algorithms based on the upcoming Versatile Video Coding (VVC) standard. Extensive experimental results further show the superiority of the proposed approach over the state-of-the-art.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Feature based inter prediction optimization for non-translational video coding in cloud
Visual features of images and video frames have become pervasive and maturely developed in extensive research fields such as computer vision and visual search. In more and more cases, the visual feature becomes necessary information which needs to be transmitted and stored at server side in cloud. Among visual features, the local feature descriptors extracted by SIFT can represent both translational and non-translational motion, such as orientation and zooming. On the other hand, only translational motion can be represented by the Motion Vector (MV) in current MV based block video coding standard. Inspired by these properties, a method that utilizes the available feature to optimize inter prediction video coding is proposed in this paper. In this method, the localization, orientation and scale parameters of matching features extracted by SIFT are delivered to inter prediction to provide non-translational motion estimation (ME) and optimized merge mode. Experimental results have shown that the proposed method can efficiently improve the coding performance according to the accurate feature-matching.
- 1 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Feature based inter prediction optimization for non-translational video coding in cloud
Visual features of images and video frames have become pervasive and maturely developed in extensive research fields such as computer vision and visual search. In more and more cases, the visual feature becomes necessary information which needs to be transmitted and stored at server side in cloud. Among visual features, the local feature descriptors extracted by SIFT can represent both translational and non-translational motion, such as orientation and zooming. On the other hand, only translational motion can be represented by the Motion Vector (MV) in current MV based block video coding standard. Inspired by these properties, a method that utilizes the available feature to optimize inter prediction video coding is proposed in this paper. In this method, the localization, orientation and scale parameters of matching features extracted by SIFT are delivered to inter prediction to provide non-translational motion estimation (ME) and optimized merge mode. Experimental results have shown that the proposed method can efficiently improve the coding performance according to the accurate feature-matching.