Yufei Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yufei Wang has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Bihan Wen
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore, Singapore
13 shared publications - Alex Chichung Kot
Shenzhen MSU-BIT University, Shenzhen, China
11 shared publications - Lanqing Guo
The University of Texas at Austin, Austin, USA
9 shared publications - Lap-Pui Chau
The Hong Kong Polytechnic University, Hong Kong, China
7 shared publications - Wenhan Yang
Pengcheng Laboratory, Shenzhen, China
7 shared publications - Haoliang Li
City University of Hong Kong, Hong Kong, China
5 shared publications
Latest Publications
- 14 September 2026
- Published by Springer Nature
- p. 271-293
One Video, One World: Turning Monocular Video into Physical 4D Scenes
- 14 September 2026
- Published by Springer Nature
- p. 271-293
One Video, One World: Turning Monocular Video into Physical 4D Scenes
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Turning 2D Images into Production-Ready 3D Assets—In Seconds
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessTurning 2D Images into Production-Ready 3D Assets—In Seconds
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 36-40
Clean-Label Attack on Face Authentication Systems Through Rolling Shutter Mechanism
We introduce a novel clean-label black-box face presentation attack on face authentication systems, i.e., face recognition and verification systems, under mild conditions. Different from other clean-label attacks which require inserting complicated or intensity patterns after the image-capturing phase, our designed pattern can be automatically inserted during the exposure by utilizing the rolling shutter mechanism and modulating environment LEDs in a specialized waveform. This method provides a potential way to conduct backdoor attacks in the physical domain. Additionally, we propose an optimization strategy based on evolutionary computing to optimize the parameters of the stripe patterns, enhancing the attack success rate. The experimental results on several face recognition models and face verification services provided by the leading technology companies demonstrate the effectiveness of our attack method. Our study reveals a new attack applicable in the physical world, highlighting significant security concerns for existing face recognition, verification, and face anti-spoofing techniques.
- 7 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 32 (10709908) , 36-40
Clean-Label Attack on Face Authentication Systems Through Rolling Shutter Mechanism
We introduce a novel clean-label black-box face presentation attack on face authentication systems, i.e., face recognition and verification systems, under mild conditions. Different from other clean-label attacks which require inserting complicated or intensity patterns after the image-capturing phase, our designed pattern can be automatically inserted during the exposure by utilizing the rolling shutter mechanism and modulating environment LEDs in a specialized waveform. This method provides a potential way to conduct backdoor attacks in the physical domain. Additionally, we propose an optimization strategy based on evolutionary computing to optimize the parameters of the stripe patterns, enhancing the attack success rate. The experimental results on several face recognition models and face verification services provided by the leading technology companies demonstrate the effectiveness of our attack method. Our study reveals a new attack applicable in the physical world, highlighting significant security concerns for existing face recognition, verification, and face anti-spoofing techniques.
- 30 October 2024
- Published by Springer Nature
- p. 349-367
Temporal As a Plugin: Unsupervised Video Denoising with Pre-trained Image Denoisers
- 30 October 2024
- Published by Springer Nature
- p. 349-367
Temporal As a Plugin: Unsupervised Video Denoising with Pre-trained Image Denoisers
- Open Access
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3751-3760
Evolving Storytelling: Benchmarks and Methods for New Character Customization with Diffusion Models
Diffusion-based models for story visualization have shown promise in generating content-coherent images for storytelling tasks. However, how to effectively integrate new characters into existing narratives while maintaining character consistency remains an open problem, particularly with limited data. Two major limitations hinder the progress: (1) the absence of a suitable benchmark due to potential character leakage and inconsistent text labeling, and (2) the challenge of distinguishing between new and old characters, leading to ambiguous results. To address these challenges, we introduce the NewEpisode benchmark, comprising refined datasets designed to evaluate generative models' adaptability in generating new stories with fresh characters using just a single example story. The refined dataset involves refined text prompts and eliminates character leakage. Additionally, to mitigate the character confusion of generated results, we propose EpicEvo, a method that customizes a diffusion-based visual story generation model with a single story featuring the new characters seamlessly integrating them into established character dynamics. EpicEvo introduces a novel adversarial character alignment module to align the generated images progressively in the diffusive process, with exemplar images of new characters, while applying knowledge distillation to prevent forgetting of characters and background details. Our evaluation quantitatively demonstrates that EpicEvo outperforms existing baselines on the NewEpisode benchmark, and qualitative studies confirm its superior customization of visual story generation in diffusion models. In summary, EpicEvo provides an effective way to incorporate new characters using only one example story, unlocking new possibilities for applications such as serialized cartoons.
- 28 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 3751-3760
Open AccessEvolving Storytelling: Benchmarks and Methods for New Character Customization with Diffusion Models
Diffusion-based models for story visualization have shown promise in generating content-coherent images for storytelling tasks. However, how to effectively integrate new characters into existing narratives while maintaining character consistency remains an open problem, particularly with limited data. Two major limitations hinder the progress: (1) the absence of a suitable benchmark due to potential character leakage and inconsistent text labeling, and (2) the challenge of distinguishing between new and old characters, leading to ambiguous results. To address these challenges, we introduce the NewEpisode benchmark, comprising refined datasets designed to evaluate generative models' adaptability in generating new stories with fresh characters using just a single example story. The refined dataset involves refined text prompts and eliminates character leakage. Additionally, to mitigate the character confusion of generated results, we propose EpicEvo, a method that customizes a diffusion-based visual story generation model with a single story featuring the new characters seamlessly integrating them into established character dynamics. EpicEvo introduces a novel adversarial character alignment module to align the generated images progressively in the diffusive process, with exemplar images of new characters, while applying knowledge distillation to prevent forgetting of characters and background details. Our evaluation quantitatively demonstrates that EpicEvo outperforms existing baselines on the NewEpisode benchmark, and qualitative studies confirm its superior customization of visual story generation in diffusion models. In summary, EpicEvo provides an effective way to incorporate new characters using only one example story, unlocking new possibilities for applications such as serialized cartoons.
- 25 October 2024
- Published by Springer Nature
- p. 39-55
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
- 25 October 2024
- Published by Springer Nature
- p. 39-55
Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
- Open Access
Temporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers
Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision. However, the challenge of acquiring paired videos for dynamic scenes hampers the practical deployment of deep video denoising techniques. In contrast, this obstacle is less pronounced in image denoising, where paired data is more readily available. Thus, a well-trained image denoiser could serve as a reliable spatial prior for video denoising. In this paper, we propose a novel unsupervised video denoising framework, named ``Temporal As a Plugin'' (TAP), which integrates tunable temporal modules into a pre-trained image denoiser. By incorporating temporal modules, our method can harness temporal information across noisy frames, complementing its power of spatial denoising. Furthermore, we introduce a progressive fine-tuning strategy that refines each temporal module using the generated pseudo clean video frames, progressively enhancing the network's denoising performance. Compared to other unsupervised video denoising methods, our framework demonstrates superior performance on both sRGB and raw video denoising datasets.
Open AccessTemporal As a Plugin: Unsupervised Video Denoising with Pre-Trained Image Denoisers
Recent advancements in deep learning have shown impressive results in image and video denoising, leveraging extensive pairs of noisy and noise-free data for supervision. However, the challenge of acquiring paired videos for dynamic scenes hampers the practical deployment of deep video denoising techniques. In contrast, this obstacle is less pronounced in image denoising, where paired data is more readily available. Thus, a well-trained image denoiser could serve as a reliable spatial prior for video denoising. In this paper, we propose a novel unsupervised video denoising framework, named ``Temporal As a Plugin'' (TAP), which integrates tunable temporal modules into a pre-trained image denoiser. By incorporating temporal modules, our method can harness temporal information across noisy frames, complementing its power of spatial denoising. Furthermore, we introduce a progressive fine-tuning strategy that refines each temporal module using the generated pseudo clean video frames, progressively enhancing the network's denoising performance. Compared to other unsupervised video denoising methods, our framework demonstrates superior performance on both sRGB and raw video denoising datasets.
- 17 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (12) , 5514-5533
Beyond Learned Metadata-Based Raw Image Reconstruction
- 17 June 2024
- Published by Springer Nature in International Journal of Computer Vision
- Vol. 132 (12) , 5514-5533
Beyond Learned Metadata-Based Raw Image Reconstruction
- Open Access
Progressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI
Deep unfolding networks (DUN) have emerged as a popular iterative framework for accelerated magnetic resonance imaging (MRI) reconstruction. However, conventional DUN aims to reconstruct all the missing information within the entire null space in each iteration. Thus it could be challenging when dealing with highly ill-posed degradation, usually leading to unsatisfactory reconstruction. In this work, we propose a Progressive Divide-And-Conquer (PDAC) strategy, aiming to break down the subsampling process in the actual severe degradation and thus perform reconstruction sequentially. Starting from decomposing the original maximum-a-posteriori problem of accelerated MRI, we present a rigorous derivation of the proposed PDAC framework, which could be further unfolded into an end-to-end trainable network. Specifically, each iterative stage in PDAC focuses on recovering a distinct moderate degradation according to the decomposition. Furthermore, as part of the PDAC iteration, such decomposition is adaptively learned as an auxiliary task through a degradation predictor which provides an estimation of the decomposed sampling mask. Following this prediction, the sampling mask is further integrated via a severity conditioning module to ensure awareness of the degradation severity at each stage. Extensive experiments demonstrate that our proposed method achieves superior performance on the publicly available fastMRI and Stanford2D FSE datasets in both multi-coil and single-coil settings.
Open AccessProgressive Divide-and-Conquer via Subsampling Decomposition for Accelerated MRI
Deep unfolding networks (DUN) have emerged as a popular iterative framework for accelerated magnetic resonance imaging (MRI) reconstruction. However, conventional DUN aims to reconstruct all the missing information within the entire null space in each iteration. Thus it could be challenging when dealing with highly ill-posed degradation, usually leading to unsatisfactory reconstruction. In this work, we propose a Progressive Divide-And-Conquer (PDAC) strategy, aiming to break down the subsampling process in the actual severe degradation and thus perform reconstruction sequentially. Starting from decomposing the original maximum-a-posteriori problem of accelerated MRI, we present a rigorous derivation of the proposed PDAC framework, which could be further unfolded into an end-to-end trainable network. Specifically, each iterative stage in PDAC focuses on recovering a distinct moderate degradation according to the decomposition. Furthermore, as part of the PDAC iteration, such decomposition is adaptively learned as an auxiliary task through a degradation predictor which provides an estimation of the decomposed sampling mask. Following this prediction, the sampling mask is further integrated via a severity conditioning module to ensure awareness of the degradation severity at each stage. Extensive experiments demonstrate that our proposed method achieves superior performance on the publicly available fastMRI and Stanford2D FSE datasets in both multi-coil and single-coil settings.
- 14 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (5) , 2142-2150
Privacy-Preserving Constrained Domain Generalization Via Gradient Alignment
Deep neural networks (DNN) have demonstrated unprecedented success for various applications. However, due to the issue of limited dataset availability and the strict legal and ethical requirements for data privacy protection, the broad applications of DNN (e.g., medical imaging classification) with large-scale training data have been largely hindered, greatly constraining the model generalization capability. In this paper, we aim to tackle this problem by developing the privacy-preserving constrained domain generalization method, aiming to improve the generalization capability under the privacy-preserving condition. In particular, we propose to improve the information aggregation process on the centralized server side with a novel gradient alignment loss, expecting that the trained model can be better generalized to the “unseen” but related data. The rationale and effectiveness of our proposed method can be explained by connecting our proposed method with the Maximum Mean Discrepancy (MMD) which has been widely adopted as the distribution distance measure. Experimental results on three domain generalization benchmark datasets indicate that our method can achieve better cross-domain generalization capability compared to the state-of-the-art federated learning methods.
- 14 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (5) , 2142-2150
Privacy-Preserving Constrained Domain Generalization Via Gradient Alignment
Deep neural networks (DNN) have demonstrated unprecedented success for various applications. However, due to the issue of limited dataset availability and the strict legal and ethical requirements for data privacy protection, the broad applications of DNN (e.g., medical imaging classification) with large-scale training data have been largely hindered, greatly constraining the model generalization capability. In this paper, we aim to tackle this problem by developing the privacy-preserving constrained domain generalization method, aiming to improve the generalization capability under the privacy-preserving condition. In particular, we propose to improve the information aggregation process on the centralized server side with a novel gradient alignment loss, expecting that the trained model can be better generalized to the “unseen” but related data. The rationale and effectiveness of our proposed method can be explained by connecting our proposed method with the Maximum Mean Discrepancy (MMD) which has been widely adopted as the distribution distance measure. Experimental results on three domain generalization benchmark datasets indicate that our method can achieve better cross-domain generalization capability compared to the state-of-the-art federated learning methods.