Zhi Li
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
Research Subjects
Research Interests
Zhi Li has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Yiguang Liu
Sichuan University
3 shared publications - Zhenming Peng
University of Electronic Science and Technology of China
3 shared publications - Christos George Bampis
Netflix Inc., Los Gatos, CA, USA
2 shared publications Jie Yang
Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Shanghai, China
2 shared publicationsJoel Sole
2 shared publications- Nikola Kasabov
Institute of Information and Communication Technologies, Bulgarian Academy of Sciences, Sofia, Bulgaria, Bulgaria
2 shared publications
Latest Publications
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 689-701
Physics-Consistent Imaging Inverse Problem Solving Framework for Heterogeneous Systems via Latent Space Optimization
Modern imaging systems face diverse degradation artifacts arising from complex sensing mechanisms and noise environments. Existing methods often require extensive parame-ter tuning or retraining across different systems and degradation levels. Although recent generative-prior based approaches par-tially alleviate this issue, they typically assume that target scenes lie within the pretrained model's manifold; otherwise, optimiza-tion may yield degenerate solutions lacking target features and structural integrity. We propose a physics-guided framework for solving imaging inverse problems in heterogeneous systems. The framework reconstructs scenes progressively, from coarse struc-tures to fine details, through a three-phase procedure involving latent-vector optimization and latent-space fine-tuning, thereby relaxing the manifold constraint on target scenes. Furthermore, we design a prior module based on a local linearity assumption in the latent space, which improves reconstruction speed and quali-ty for image pairs with structural similarity through warm start initialization. Comprehensive experiments on CMOS sensors, single-photon avalanche diode (SPAD) arrays, and single-pixel imaging systems (SPIS) demonstrate that the proposed frame-work consistently delivers competitive performance under ex-treme environmental conditions, ultra-low-bandwidth constraints, and out-of-distribution scenarios.
- 18 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computational Imaging
- Vol. 12 (25730436) , 689-701
Physics-Consistent Imaging Inverse Problem Solving Framework for Heterogeneous Systems via Latent Space Optimization
Modern imaging systems face diverse degradation artifacts arising from complex sensing mechanisms and noise environments. Existing methods often require extensive parame-ter tuning or retraining across different systems and degradation levels. Although recent generative-prior based approaches par-tially alleviate this issue, they typically assume that target scenes lie within the pretrained model's manifold; otherwise, optimiza-tion may yield degenerate solutions lacking target features and structural integrity. We propose a physics-guided framework for solving imaging inverse problems in heterogeneous systems. The framework reconstructs scenes progressively, from coarse struc-tures to fine details, through a three-phase procedure involving latent-vector optimization and latent-space fine-tuning, thereby relaxing the manifold constraint on target scenes. Furthermore, we design a prior module based on a local linearity assumption in the latent space, which improves reconstruction speed and quali-ty for image pairs with structural similarity through warm start initialization. Comprehensive experiments on CMOS sensors, single-photon avalanche diode (SPAD) arrays, and single-pixel imaging systems (SPIS) demonstrate that the proposed frame-work consistently delivers competitive performance under ex-treme environmental conditions, ultra-low-bandwidth constraints, and out-of-distribution scenarios.
- Top Cited Papers
- 20 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-17
STADE-CDNet: Spatial–Temporal Attention With Difference Enhancement-Based Network for Remote Sensing Image Change Detection
High-resolution remote sensing image change detection focuses on ground surface changes. It has wide applications, including territorial spatial planning, urban region detection, and military operations. However, class imbalance and pseudo-changes are caused by the unchanged areas far outnumbering the changed areas and lighting changes. To address these problems, we propose spatial-temporal attention with a difference enhancement-based network (STADE-CDNet). In STADE-CDNet, a change detection difference enhancement module (CDDM) is proposed to extract important features from the difference map to detect changed regions. This module enhances the network with differential feature attributes through the training layer, improving the network’s learning ability and reducing the imbalance problem. A temporal memory module (TMM) is designed to extract temporal and spatial information. Inspired by the self-attention mechanism of the transformer, we propose a transformer and TMM (TTMM). Four encoding layers are designed to detect the semantic information from high to low levels of the multitemporal image pairs. The fusion and parallelism of multivariate data are achieved through collaborative modeling of deep learning and change detection, compensating for the need for excessive human intervention in traditional algorithms. We evaluate our approach in two different datasets (LEVIR-CD and DSIFN-CD). Promising quantitative and qualitative results show that STADE-CDNet can improve accuracy. In particular, the proposed CDDM significantly reduces false positive detection, with F1 scores at least 1.97% and 2.1% higher than other methods in the case of the LEVIR-CD and DSIFN-CD datasets, respectively. Our code is available at https://github.com/LiLisaZhi/STADE-CDNet.
- 20 February 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 62 (01962892) , 1-17
Top Cited PapersSTADE-CDNet: Spatial–Temporal Attention With Difference Enhancement-Based Network for Remote Sensing Image Change Detection
High-resolution remote sensing image change detection focuses on ground surface changes. It has wide applications, including territorial spatial planning, urban region detection, and military operations. However, class imbalance and pseudo-changes are caused by the unchanged areas far outnumbering the changed areas and lighting changes. To address these problems, we propose spatial-temporal attention with a difference enhancement-based network (STADE-CDNet). In STADE-CDNet, a change detection difference enhancement module (CDDM) is proposed to extract important features from the difference map to detect changed regions. This module enhances the network with differential feature attributes through the training layer, improving the network’s learning ability and reducing the imbalance problem. A temporal memory module (TMM) is designed to extract temporal and spatial information. Inspired by the self-attention mechanism of the transformer, we propose a transformer and TMM (TTMM). Four encoding layers are designed to detect the semantic information from high to low levels of the multitemporal image pairs. The fusion and parallelism of multivariate data are achieved through collaborative modeling of deep learning and change detection, compensating for the need for excessive human intervention in traditional algorithms. We evaluate our approach in two different datasets (LEVIR-CD and DSIFN-CD). Promising quantitative and qualitative results show that STADE-CDNet can improve accuracy. In particular, the proposed CDDM significantly reduces false positive detection, with F1 scores at least 1.97% and 2.1% higher than other methods in the case of the LEVIR-CD and DSIFN-CD datasets, respectively. Our code is available at https://github.com/LiLisaZhi/STADE-CDNet.
- 5 August 2023
- Published by Elsevier in Statistics & Probability Letters
- Vol. 202, 109913
The calculation of alias pattern in three-level regular designs
- 5 August 2023
- Published by Elsevier in Statistics & Probability Letters
- Vol. 202, 109913
The calculation of alias pattern in three-level regular designs
- 30 July 2023
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 53 (16) , 5954-5971
Optimal confounding measures for two-level regular designs
- 30 July 2023
- Published by Taylor & Francis in Communications in Statistics - Theory and Methods
- Vol. 53 (16) , 5954-5971
Optimal confounding measures for two-level regular designs
- Open Access
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 7423-7425
QoEVMA'22: 2nd Workshop on Quality of Experience (QoE) in Visual Multimedia Applications
Nowadays, people spend dramatically more time on watching videos through different devices. The advanced hardware technology and network allow for the increasing demands of users viewing experience. Thus, enhancing the Quality of Experience of end-users in advanced multimedia is the ultimate goal of service providers, as good services would attract more consumers. Quality assessment is thus important. The second workshop on "Quality of Experience (QoE) in visual multimedia applications" (QoEVMA'22) focuses on the QoE assessment of any visual multimedia applications both subjectively and objectively. The topics include 1) QoE assessment on different visual multimedia applications, including VoD for movies, dramas, variety shows, UGC on social networks, live streaming videos for gaming/shopping/social, etc. 2) QoE assessment for different video formats in multimedia services, including 2D, stereoscopic 3D, High Dynamic Range (HDR), Augmented Reality (AR), Virtual Reality (VR), 360, Free-Viewpoint Video(FVV), etc. 3) Key performance indicators (KPI) analysis for QoE. This summary gives a brief overview of the workshop, which took place on October 14, 2022 in Lisbon, Portugal, as a half-day workshop. The complete QOEVMA'22 workshop proceedings are available at: https://dl.acm.org/doi/proceedings/10.1145/3552469
- 10 October 2022
- Published by Association for Computing Machinery (ACM)
- p. 7423-7425
Open AccessQoEVMA'22: 2nd Workshop on Quality of Experience (QoE) in Visual Multimedia Applications
Nowadays, people spend dramatically more time on watching videos through different devices. The advanced hardware technology and network allow for the increasing demands of users viewing experience. Thus, enhancing the Quality of Experience of end-users in advanced multimedia is the ultimate goal of service providers, as good services would attract more consumers. Quality assessment is thus important. The second workshop on "Quality of Experience (QoE) in visual multimedia applications" (QoEVMA'22) focuses on the QoE assessment of any visual multimedia applications both subjectively and objectively. The topics include 1) QoE assessment on different visual multimedia applications, including VoD for movies, dramas, variety shows, UGC on social networks, live streaming videos for gaming/shopping/social, etc. 2) QoE assessment for different video formats in multimedia services, including 2D, stereoscopic 3D, High Dynamic Range (HDR), Augmented Reality (AR), Virtual Reality (VR), 360, Free-Viewpoint Video(FVV), etc. 3) Key performance indicators (KPI) analysis for QoE. This summary gives a brief overview of the workshop, which took place on October 14, 2022 in Lisbon, Portugal, as a half-day workshop. The complete QOEVMA'22 workshop proceedings are available at: https://dl.acm.org/doi/proceedings/10.1145/3552469
- Open Access
Banding vs. Quality: Perceptual Impact and Objective Assessment
Staircase-like contours introduced to a video by quantization in flat areas, commonly known as banding, have been a long-standing problem in both video processing and quality assessment communities. The fact that even a relatively small change of the original pixel values can result in a strong impact on perceived quality makes banding especially difficult to be detected by objective quality metrics. In this paper, we study how banding annoyance compares to more commonly studied scaling and compression artifacts with respect to the overall perceptual quality. We further propose a simple combination of VMAF and the recently developed banding index, CAMBI, into a banding-aware video quality metric showing improved correlation with overall perceived quality.
Open AccessBanding vs. Quality: Perceptual Impact and Objective Assessment
Staircase-like contours introduced to a video by quantization in flat areas, commonly known as banding, have been a long-standing problem in both video processing and quality assessment communities. The fact that even a relatively small change of the original pixel values can result in a strong impact on perceived quality makes banding especially difficult to be detected by objective quality metrics. In this paper, we study how banding annoyance compares to more commonly studied scaling and compression artifacts with respect to the overall perceptual quality. We further propose a simple combination of VMAF and the recently developed banding index, CAMBI, into a banding-aware video quality metric showing improved correlation with overall perceived quality.
- Open Access
- 17 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 1408-1422
Perceptual Video Quality Prediction Emphasizing Chroma Distortions
Measuring the quality of digital videos viewed by human observers has become a common practice in numerous multimedia applications, such as adaptive video streaming, quality monitoring, and other digital TV applications. Here we explore a significant, yet relatively unexplored problem: measuring perceptual quality on videos arising from both luma and chroma distortions from compression. Toward investigating this problem, it is important to understand the kinds of chroma distortions that arise, how they relate to luma compression distortions, and how they can affect perceived quality. We designed and carried out a subjective experiment to measure subjective video quality on both luma and chroma distortions, introduced both in isolation as well as together. Specifically, the new subjective dataset comprises a total of 210 videos afflicted by distortions caused by varying levels of luma quantization commingled with different amounts of chroma quantization. The subjective scores were evaluated by 34 subjects in a controlled environmental setting. Using the newly collected subjective data, we were able to demonstrate important shortcomings of existing video quality models, especially in regards to chroma distortions. Further, we designed an objective video quality model which builds on existing video quality algorithms, by considering the fidelity of chroma channels in a principled way. We also found that this quality analysis implies that there is room for reducing bitrate consumption in modern video codecs by creatively increasing the compression factor on chroma channels. We believe that this work will both encourage further research in this direction, as well as advance progress on the ultimate goal of jointly optimizing luma and chroma compression in modern video encoders.
- 17 December 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 30 (10577149) , 1408-1422
Open AccessPerceptual Video Quality Prediction Emphasizing Chroma Distortions
Measuring the quality of digital videos viewed by human observers has become a common practice in numerous multimedia applications, such as adaptive video streaming, quality monitoring, and other digital TV applications. Here we explore a significant, yet relatively unexplored problem: measuring perceptual quality on videos arising from both luma and chroma distortions from compression. Toward investigating this problem, it is important to understand the kinds of chroma distortions that arise, how they relate to luma compression distortions, and how they can affect perceived quality. We designed and carried out a subjective experiment to measure subjective video quality on both luma and chroma distortions, introduced both in isolation as well as together. Specifically, the new subjective dataset comprises a total of 210 videos afflicted by distortions caused by varying levels of luma quantization commingled with different amounts of chroma quantization. The subjective scores were evaluated by 34 subjects in a controlled environmental setting. Using the newly collected subjective data, we were able to demonstrate important shortcomings of existing video quality models, especially in regards to chroma distortions. Further, we designed an objective video quality model which builds on existing video quality algorithms, by considering the fidelity of chroma channels in a principled way. We also found that this quality analysis implies that there is room for reducing bitrate consumption in modern video codecs by creatively increasing the compression factor on chroma channels. We believe that this work will both encourage further research in this direction, as well as advance progress on the ultimate goal of jointly optimizing luma and chroma compression in modern video encoders.
- Open Access
- 21 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 12 (4) , 1-13
Low Illumination Video Image Enhancement
Due to weather conditions, brightness conditions, capture equipment and other factors, leads to video unclear or even abnormally confused, which is not conducive to monitoring, and can not meet the needs of applications. Based on the actual data of night video surveillance, this paper proposes a new low illumination video image enhancement algorithm, which overcomes the existing problems. We analyze the characteristics of low illumination video image, and use HSV color space instead of traditional RGB space to enhance the robustness of video contrast and color distortion. At the same time, we use wavelet image fusion to highlight the details of video image, so the enhanced video has higher clarity and visual effect. Compared with other four algorithms, the proposed algorithm outperforms the above algorithms in subjective evaluation and objective evaluation. At the same time, compared with other algorithms, the proposed algorithm has faster processing time for each frame. Experiments show that the algorithm can effectively improve the overall brightness and contrast of video images, and avoid the over-enhancement of bright areas near the light source, which can meet the practical application requirements of video surveillance.
- 21 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Photonics Journal
- Vol. 12 (4) , 1-13
Open AccessLow Illumination Video Image Enhancement
Due to weather conditions, brightness conditions, capture equipment and other factors, leads to video unclear or even abnormally confused, which is not conducive to monitoring, and can not meet the needs of applications. Based on the actual data of night video surveillance, this paper proposes a new low illumination video image enhancement algorithm, which overcomes the existing problems. We analyze the characteristics of low illumination video image, and use HSV color space instead of traditional RGB space to enhance the robustness of video contrast and color distortion. At the same time, we use wavelet image fusion to highlight the details of video image, so the enhanced video has higher clarity and visual effect. Compared with other four algorithms, the proposed algorithm outperforms the above algorithms in subjective evaluation and objective evaluation. At the same time, compared with other algorithms, the proposed algorithm has faster processing time for each frame. Experiments show that the algorithm can effectively improve the overall brightness and contrast of video images, and avoid the over-enhancement of bright areas near the light source, which can meet the practical application requirements of video surveillance.