HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images

Yun, Jun‐Seok; Na, Youngju; Kim, Hee Hyeon; Kim, Hyung-Il; Yoo, Seok Bong

doi:10.1007/978-3-031-26348-4_9

Cited by 14 publications

(9 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although this method demonstrates strong generalization and stability in real-world environments, it still faces challenges related to low resolution and other factors. Yun et al [33] proposed a high-frequency attention-based super-resolution module to enhance eye features and boundary information for low-resolution face images detected from high-resolution images in real-world scenes. They combined facial structural location information to approximate head pose estimation and introduced HAZE-Net.…”

Section: Gaze Estimationmentioning

confidence: 99%

“…Yun et al. [33] proposed a high‐frequency attention‐based super‐resolution module to enhance eye features and boundary information for low‐resolution face images detected from high‐resolution images in real‐world scenes. They combined facial structural location information to approximate head pose estimation and introduced HAZE‐Net.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

FSKT‐GE: Feature maps similarity knowledge transfer for low‐resolution gaze estimation

Yan,

Pan,

Dai

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

The limited of texture details information in low‐resolution facial or eye images presents a challenge for gaze estimation. To address this, FSKT‐GE (feature maps similarity knowledge transfer for low‐resolution gaze estimation) is proposed, a gaze estimation framework consisting of both a high resolution (HR) network and low resolution (LR) network with the identical structure. Rather than mere feature imitation, this issue is addressed by assessing the cosine similarity of feature layers, emphasizing the distribution similarity between the HR and LR networks. This enables the LR network to acquire richer knowledge. This framework utilizes a combination loss function, incorporating cosine similarity measurement, soft loss based on probability distribution difference and gaze direction output, along with a hard loss from the LR network output layer. This approach on low‐resolution datasets derived from Gaze360 and RT‐Gene datasets is validated, demonstrating excellent performance in low‐resolution gaze estimation. Evaluations on low‐resolution images obtained through 2×, 4×, and 8× down‐sampling are conducted on two datasets. On the Gaze360 dataset, the lowest mean angular errors of 10.97°, 11.22°, and 13.61° were achieved, while on the RT‐Gene dataset, the lowest mean angular errors of 6.73°, 6.83°, and 7.75° were obtained.

show abstract

Section: Gaze Estimationmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

FSKT‐GE: Feature maps similarity knowledge transfer for low‐resolution gaze estimation

Yan,

Pan,

Dai

et al. 2024

IET Image Processing

View full text Add to dashboard Cite

show abstract

“…The SISR technique [11][12][13][14][15] is well known in computer vision and aims to generate an HR image from a single LR counterpart. Early deep learning models, such as the SR convolutional neural network (SRCNN) [16] and fast SR CNN [17], use shallow architectures to learn mappings from LR to HR images.…”

Section: Single Image Super-resoultionmentioning

confidence: 99%

Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution

Kim,

Yoo

2023

Mathematics

View full text Add to dashboard Cite

Recently, several arbitrary-scale models have been proposed for single-image super-resolution. Furthermore, the importance of arbitrary-scale single image super-resolution is emphasized for applications such as satellite image processing, HR display, and video-based surveillance. However, the baseline integer-scale model must be retrained to fit the existing network, and the learning speed is slow. This paper proposes a network to solve these problems, processing super-resolution by restoring the high-frequency information lost in the remaining arbitrary-scale while maintaining the baseline integer scale. The proposed network extends an integer-scaled image to an arbitrary-scale target in the discrete cosine transform spectral domain. We also modulate the high-frequency restoration weights of the depthwise multi-head attention to use memory efficiently. Finally, we demonstrate the performance through experiments with existing state-of-the-art models and their flexibility through integration with existing integer-scale models in terms of peak signal-to-noise ratio (PSNR) and similarity index measure (SSIM) scores. This means that the proposed network restores high-resolution (HR) images appropriately by improving the image sharpness of low-resolution (LR) images.

show abstract

“…Similarly, there is active research in the field of deepfake detection that leverages the frequency domain for various purposes [21][22][23][24][25][26][27][28][29][30][31][32]. Durall et al [21] employed the Discrete Fourier Transform (DFT) for deepfake detection.…”

Section: Deepfake Detectionmentioning

confidence: 99%

ClueCatcher: Catching Domain-Wise Independent Clues for Deepfake Detection

Lee,

Yoo

2023

Mathematics

View full text Add to dashboard Cite

Deepfake detection is a focus of extensive research to combat the proliferation of manipulated media. Existing approaches suffer from limited generalizability and struggle to detect deepfakes created using unseen techniques. This paper proposes a novel deepfake detection method to improve generalizability. We observe domain-wise independent clues in deepfake images, including inconsistencies in facial colors, detectable artifacts at synthesis boundaries, and disparities in quality between facial and nonfacial regions. This approach uses an interpatch dissimilarity estimator and a multistream convolutional neural network to capture deepfake clues unique to each feature. By exploiting these clues, we enhance the effectiveness and generalizability of deepfake detection. The experimental results demonstrate the improved performance and robustness of this method.

show abstract

HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in Low-Resolution Face Images

Cited by 14 publications

References 42 publications

FSKT‐GE: Feature maps similarity knowledge transfer for low‐resolution gaze estimation

FSKT‐GE: Feature maps similarity knowledge transfer for low‐resolution gaze estimation

Memory-Efficient Discrete Cosine Transform Domain Weight Modulation Transformer for Arbitrary-Scale Super-Resolution

ClueCatcher: Catching Domain-Wise Independent Clues for Deepfake Detection

Contact Info

Product

Resources

About