Hao Wei
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
Hao Wei has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- Chenyang Ge
State Key Laboratory of Human–Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China
6 shared publications - Xin Qiao
State Key Laboratory of Human–Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University, Xi’an, China
4 shared publications - Pengchao Deng
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, Xian, China
3 shared publications - Yanhui Zhou
School of Information and telecommunication Xi'an Jiaotong University China
3 shared publications - Zhiyuan Li
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xian Jiaotong University, Xian, China
3 shared publications - Ajmal Mian
The University of Western Australia
2 shared publications
Latest Publications
- Open Access
- 17 June 2026
- Published by Elsevier in SSRN Electronic Journal
Geometric Mamba with Local Differential Refinement for Perceptual Video Compression
Although perceptual video compression methods have exhibited outstandingperformance, most of them typically follow a hybrid coding paradigm thatrequires explicit motion estimation and compensation, resulting in a complexsolution for video compression. In contrast, we introduce a streamlinedyet effective video compression framework founded on a direct transformstrategy, i.e., nonlinear transform, quantization, and entropy coding. Wefirst develop a cascaded Mamba module (CMM) with different embeddedgeometric transformations to effectively explore both long-range spatial andtemporal dependencies. To improve local spatial representation, we introducea locality refinement feed-forward network (LRFFN) that incorporatesa hybrid convolution block based on difference convolutions. Moreover, we present a conditional channel-wise entropy model that effectively utilizes conditional temporal priors to accurately estimate the probability distributions of current latent features. Extensive experiments demonstrate that our method outperforms state-of-the-art videocompression approaches in terms of perceptual quality and temporal consistencyunder low bitrate constraints.
- 17 June 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessGeometric Mamba with Local Differential Refinement for Perceptual Video Compression
Although perceptual video compression methods have exhibited outstandingperformance, most of them typically follow a hybrid coding paradigm thatrequires explicit motion estimation and compensation, resulting in a complexsolution for video compression. In contrast, we introduce a streamlinedyet effective video compression framework founded on a direct transformstrategy, i.e., nonlinear transform, quantization, and entropy coding. Wefirst develop a cascaded Mamba module (CMM) with different embeddedgeometric transformations to effectively explore both long-range spatial andtemporal dependencies. To improve local spatial representation, we introducea locality refinement feed-forward network (LRFFN) that incorporatesa hybrid convolution block based on difference convolutions. Moreover, we present a conditional channel-wise entropy model that effectively utilizes conditional temporal priors to accurately estimate the probability distributions of current latent features. Extensive experiments demonstrate that our method outperforms state-of-the-art videocompression approaches in terms of perceptual quality and temporal consistencyunder low bitrate constraints.
- 3 November 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108279
A lightweight model for perceptual image compression via implicit priors
- 3 November 2025
- Published by Elsevier in Neural Networks
- Vol. 195, 108279
A lightweight model for perceptual image compression via implicit priors
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (11) , 11540-11552
RDEIC: Accelerating Diffusion-Based Extreme Image Compression With Relay Residual Diffusion
Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we directly derive a novel residual diffusion equation from Stable Diffusion’s original diffusion equation that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. In this way, we effectively combine the efficiency of residual diffusion with the powerful generative capability of Stable Diffusion. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, thereby further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code and pre-trained models are available at https://github.com/huai-chang/RDEIC.
- 9 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (11) , 11540-11552
RDEIC: Accelerating Diffusion-Based Extreme Image Compression With Relay Residual Diffusion
Diffusion-based extreme image compression methods have achieved impressive performance at extremely low bitrates. However, constrained by the iterative denoising process that starts from pure noise, these methods are limited in both fidelity and efficiency. To address these two issues, we present Relay Residual Diffusion Extreme Image Compression (RDEIC), which leverages compressed feature initialization and residual diffusion. Specifically, we first use the compressed latent features of the image with added noise, instead of pure noise, as the starting point to eliminate the unnecessary initial stages of the denoising process. Second, we directly derive a novel residual diffusion equation from Stable Diffusion’s original diffusion equation that reconstructs the raw image by iteratively removing the added noise and the residual between the compressed and target latent features. In this way, we effectively combine the efficiency of residual diffusion with the powerful generative capability of Stable Diffusion. Third, we propose a fixed-step fine-tuning strategy to eliminate the discrepancy between the training and inference phases, thereby further improving the reconstruction quality. Extensive experiments demonstrate that the proposed RDEIC achieves state-of-the-art visual quality and outperforms existing diffusion-based extreme image compression methods in both fidelity and efficiency. The source code and pre-trained models are available at https://github.com/huai-chang/RDEIC.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 888-899
Toward Extreme Image Compression With Latent Feature Guidance and Diffusion Prior
Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the powerful generative capability of pre-trained diffusion models to achieve realistic image reconstruction at extremely low bitrates. In the first stage, we treat the latent representation of images in the diffusion space as guidance, employing a VAE-based compression approach to compress images and initially decode the compressed information into content variables. The second stage leverages pre-trained stable diffusion to reconstruct images under the guidance of content variables. Specifically, we introduce a small control module to inject content information while keeping the stable diffusion model fixed to maintain its generative capability. Furthermore, we design a space alignment loss to force the content variables to align with the diffusion space and provide the necessary constraints for optimization. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in terms of visual performance at extremely low bitrates. The source code and trained models are available at https://github.com/huai-chang/DiffEIC.
- 6 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 35 (1) , 888-899
Toward Extreme Image Compression With Latent Feature Guidance and Diffusion Prior
Image compression at extremely low bitrates (below 0.1 bits per pixel (bpp)) is a significant challenge due to substantial information loss. In this work, we propose a novel two-stage extreme image compression framework that exploits the powerful generative capability of pre-trained diffusion models to achieve realistic image reconstruction at extremely low bitrates. In the first stage, we treat the latent representation of images in the diffusion space as guidance, employing a VAE-based compression approach to compress images and initially decode the compressed information into content variables. The second stage leverages pre-trained stable diffusion to reconstruct images under the guidance of content variables. Specifically, we introduce a small control module to inject content information while keeping the stable diffusion model fixed to maintain its generative capability. Furthermore, we design a space alignment loss to force the content variables to align with the diffusion space and provide the necessary constraints for optimization. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art approaches in terms of visual performance at extremely low bitrates. The source code and trained models are available at https://github.com/huai-chang/DiffEIC.
- Open Access
- 11 January 2024
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 18 (5) , 1328-1343
Real‐world image deblurring using data synthesis and feature complementary network
Many learning‐based approaches to image deblurring have received increasing attention in recent years. However, the models trained on existing synthetic datasets do not generalize well to real‐world blur, resulting in undesirable artifacts and residual blur. This work attempts to address this problem from two aspects: training data synthesis and network architecture. To narrow the domain gap between synthetic and real domains, a realistic blur synthesis pipeline to generate high‐quality blurred data is proposed. Since the blur is non‐uniform and has different scales and degrees, a parallel feature complementary module to fully exploit the local and non‐local information, which improves the feature representation and helps the network to perceive the non‐uniform blur, is developed. In addition, a spatial Fourier reconstruction block to facilitate correct detail recovery in the spatial and Fourier domains is introduced. Based on these two designs, an effective encoder–decoder network for deblurring is designed. Extensive experiments demonstrate the validity and superiority of the proposed blur synthesis method and deblurring network. In particular, the proposed deblurring network can achieve superior or comparable performance to Restormer, while saving 70% of network parameters and 53% of floating point operations (FLOPs).
- 11 January 2024
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 18 (5) , 1328-1343
Open AccessReal‐world image deblurring using data synthesis and feature complementary network
Many learning‐based approaches to image deblurring have received increasing attention in recent years. However, the models trained on existing synthetic datasets do not generalize well to real‐world blur, resulting in undesirable artifacts and residual blur. This work attempts to address this problem from two aspects: training data synthesis and network architecture. To narrow the domain gap between synthetic and real domains, a realistic blur synthesis pipeline to generate high‐quality blurred data is proposed. Since the blur is non‐uniform and has different scales and degrees, a parallel feature complementary module to fully exploit the local and non‐local information, which improves the feature representation and helps the network to perceive the non‐uniform blur, is developed. In addition, a spatial Fourier reconstruction block to facilitate correct detail recovery in the spatial and Fourier domains is introduced. Based on these two designs, an effective encoder–decoder network for deblurring is designed. Extensive experiments demonstrate the validity and superiority of the proposed blur synthesis method and deblurring network. In particular, the proposed deblurring network can achieve superior or comparable performance to Restormer, while saving 70% of network parameters and 53% of floating point operations (FLOPs).
- 2 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6181-6193
Toward Extreme Image Rescaling With Generative Prior and Invertible Prior
The goal of image rescaling is to embed the information from high-resolution images into low-resolution images and then reconstruct the high-resolution images in reverse. Existing methods either focus on small scaling factors or do not generalize well to natural images with diverse content in extreme settings, i.e., using extreme scaling factors (e.g., 16× and 32×). When performing extreme rescaling, previous methods often fail to produce plausible high-quality results due to insufficient cues in low-resolution images. In this work, we propose an extreme natural image rescaling framework that exploits the rich generative prior integrated into the GAN model trained on large-scale natural images to reduce the ambiguity of extreme upscaling. Considering the invertible bijective transformation between quantized features and low-resolution image, we develop an invertible feature recovery module that generates semantically sound low-resolution image while maximizing the preservation of useful features for the subsequent upscaling. Furthermore, we propose a multi-scale refinement module that explicitly introduces the supervised ground truth information to mitigate unpleasant artifacts and distortions. Extensive experiments show that the proposed rescaling framework formulated by the above components achieves significantly better visual performance than state-of-the-art methods.
- 2 January 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 34 (7) , 6181-6193
Toward Extreme Image Rescaling With Generative Prior and Invertible Prior
The goal of image rescaling is to embed the information from high-resolution images into low-resolution images and then reconstruct the high-resolution images in reverse. Existing methods either focus on small scaling factors or do not generalize well to natural images with diverse content in extreme settings, i.e., using extreme scaling factors (e.g., 16× and 32×). When performing extreme rescaling, previous methods often fail to produce plausible high-quality results due to insufficient cues in low-resolution images. In this work, we propose an extreme natural image rescaling framework that exploits the rich generative prior integrated into the GAN model trained on large-scale natural images to reduce the ambiguity of extreme upscaling. Considering the invertible bijective transformation between quantized features and low-resolution image, we develop an invertible feature recovery module that generates semantically sound low-resolution image while maximizing the preservation of useful features for the subsequent upscaling. Furthermore, we propose a multi-scale refinement module that explicitly introduces the supervised ground truth information to mitigate unpleasant artifacts and distortions. Extensive experiments show that the proposed rescaling framework formulated by the above components achieves significantly better visual performance than state-of-the-art methods.
- 27 November 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 129, 107600
Multimodal contrastive learning for face anti-spoofing
- 27 November 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 129, 107600
Multimodal contrastive learning for face anti-spoofing
- 7 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 4258-4271
Attention-Aware Dual-Stream Network for Multimodal Face Anti-Spoofing
Since the rapid development of face recognition systems using 3D cameras, the public has demanded great safety regulations for these devices. As a closely related topic, multimodal face anti-spoofing (FAS) has become an indispensable part of face recognition systems. However, existing multimodal FAS tools suffer from performance degradation under external low-lighting conditions and insufficient representation capabilities of fusion features. To address these issues, we present an attention-aware dual-stream fusion method using 3D cameras (i.e., IR+Depth) and considering both fine-grained and global features. Specifically, we introduce a surface normal generator using depth maps to obtain robust and discriminative representations. Then, we leverage the attention mechanism to split each stream into two branches. The first branch explores complementary global information between different modalities, while the second branch captures subtle and local features from each modality. The system regards multimodal FAS as a fine-grained classification problem. Moreover, to ensure that local areas in the image do not overlap and belong to the same class, a joint loss function is developed and proven to further boost the performance of FAS. We extensively evaluate our proposed strategies on various multimodal databases, and the results show that when compared with current state-of-the-art multimodal methods, our framework achieves superior performance.
- 7 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 18 (15566013) , 4258-4271
Attention-Aware Dual-Stream Network for Multimodal Face Anti-Spoofing
Since the rapid development of face recognition systems using 3D cameras, the public has demanded great safety regulations for these devices. As a closely related topic, multimodal face anti-spoofing (FAS) has become an indispensable part of face recognition systems. However, existing multimodal FAS tools suffer from performance degradation under external low-lighting conditions and insufficient representation capabilities of fusion features. To address these issues, we present an attention-aware dual-stream fusion method using 3D cameras (i.e., IR+Depth) and considering both fine-grained and global features. Specifically, we introduce a surface normal generator using depth maps to obtain robust and discriminative representations. Then, we leverage the attention mechanism to split each stream into two branches. The first branch explores complementary global information between different modalities, while the second branch captures subtle and local features from each modality. The system regards multimodal FAS as a fine-grained classification problem. Moreover, to ensure that local areas in the image do not overlap and belong to the same class, a joint loss function is developed and proven to further boost the performance of FAS. We extensively evaluate our proposed strategies on various multimodal databases, and the results show that when compared with current state-of-the-art multimodal methods, our framework achieves superior performance.
- Open Access
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh
Open AccessNTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with focus on proposed solutions and results. In this challenge, the new Large-scale Diverse Video (LDV) dataset is employed. The challenge has three tracks. Tracks 1 and 2 aim at enhancing the videos compressed by HEVC at a fixed QP, while Track 3 is designed for enhancing the videos compressed by x265 at a fixed bit-rate. Besides, the quality enhancement of Tracks 1 and 3 targets at improving the fidelity (PSNR), and Track 2 targets at enhancing the perceptual quality. The three tracks totally attract 482 registrations. In the test phase, 12 teams, 8 teams and 11 teams submitted the final results of Tracks 1, 2 and 3, respectively. The proposed methods and solutions gauge the state-of-the-art of video quality enhancement. The homepage of the challenge: https://github.com/RenYang-home/NTIRE21_VEnh
- 1 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 2681-2684
New digital camera sensor architecture for low light imaging
In this paper, a novel digital camera sensor architecture to acquire images with high fidelity under low light conditions is proposed. Today, almost all digital cameras have only red, green, and blue color pixels. Due to their limited sensitivity to the wavelengths of visible light, the images captured using these color pixels under low light conditions are noisy. A new sensor architecture that has panchromatic pixels sensitive to all visible wavelengths along with the red, green, and blue pixels is proposed. Panchromatic pixels allow luminance information to be detected with higher sensitivity whereas red, green, and blue pixels produce the color information. Real images captured using the proposed sensor design are compared with the corresponding images obtained using a traditional digital camera having only red, green, and blue pixels. The results clearly show the feasibility of the proposed approach.
- 1 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15224880,p. 2681-2684
New digital camera sensor architecture for low light imaging
In this paper, a novel digital camera sensor architecture to acquire images with high fidelity under low light conditions is proposed. Today, almost all digital cameras have only red, green, and blue color pixels. Due to their limited sensitivity to the wavelengths of visible light, the images captured using these color pixels under low light conditions are noisy. A new sensor architecture that has panchromatic pixels sensitive to all visible wavelengths along with the red, green, and blue pixels is proposed. Panchromatic pixels allow luminance information to be detected with higher sensitivity whereas red, green, and blue pixels produce the color information. Real images captured using the proposed sensor design are compared with the corresponding images obtained using a traditional digital camera having only red, green, and blue pixels. The results clearly show the feasibility of the proposed approach.