HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in
Low-Resolution Face Images
- URL: http://arxiv.org/abs/2209.10167v1
- Date: Wed, 21 Sep 2022 07:57:07 GMT
- Title: HAZE-Net: High-Frequency Attentive Super-Resolved Gaze Estimation in
Low-Resolution Face Images
- Authors: Jun-Seok Yun, Youngju Na, Hee Hyeon Kim, Hyung-Il Kim, Seok Bong Yoo
- Abstract summary: We propose a high-frequency attentive gaze estimation network, i.e., HAZE-Net.
Our network improves the resolution of the input image and enhances the eye features and those boundaries.
The experimental results indicate that the proposed method exhibits robust gaze estimation performance even in low-resolution face images with 28x28 pixels.
- Score: 2.951890686127008
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Although gaze estimation methods have been developed with deep learning
techniques, there has been no such approach as aim to attain accurate
performance in low-resolution face images with a pixel width of 50 pixels or
less. To solve a limitation under the challenging low-resolution conditions, we
propose a high-frequency attentive super-resolved gaze estimation network,
i.e., HAZE-Net. Our network improves the resolution of the input image and
enhances the eye features and those boundaries via a proposed super-resolution
module based on a high-frequency attention block. In addition, our gaze
estimation module utilizes high-frequency components of the eye as well as the
global appearance map. We also utilize the structural location information of
faces to approximate head pose. The experimental results indicate that the
proposed method exhibits robust gaze estimation performance even in
low-resolution face images with 28x28 pixels. The source code of this work is
available at https://github.com/dbseorms16/HAZE_Net/.
Related papers
- Decoupling Fine Detail and Global Geometry for Compressed Depth Map Super-Resolution [55.9977636042469]
Bit-depth compression produces a uniform depth representation in regions with subtle variations, hindering the recovery of detailed information.
densely distributed random noise reduces the accuracy of estimating the global geometric structure of the scene.
We propose a novel framework, termed geometry-decoupled network (GDNet), for compressed depth map super-resolution.
arXiv Detail & Related papers (2024-11-05T16:37:30Z) - SaccadeDet: A Novel Dual-Stage Architecture for Rapid and Accurate Detection in Gigapixel Images [50.742420049839474]
'SaccadeDet' is an innovative architecture for gigapixel-level object detection, inspired by the human eye saccadic movement.
Our approach, evaluated on the PANDA dataset, achieves an 8x speed increase over the state-of-the-art methods.
It also demonstrates significant potential in gigapixel-level pathology analysis through its application to Whole Slide Imaging.
arXiv Detail & Related papers (2024-07-25T11:22:54Z) - Super-Resolving Face Image by Facial Parsing Information [52.1267613768555]
Face super-resolution is a technology that transforms a low-resolution face image into the corresponding high-resolution one.
We build a novel parsing map guided face super-resolution network which extracts the face prior from low-resolution face image.
High-resolution features contain more precise spatial information while low-resolution features provide strong contextual information.
arXiv Detail & Related papers (2023-04-06T08:19:03Z) - LSwinSR: UAV Imagery Super-Resolution based on Linear Swin Transformer [7.3817359680010615]
Super-resolution technology is especially beneficial for Unmanned Aerial Vehicles (UAV)
In this paper, for the super-resolution of UAV images, a novel network based on the state-of-the-art Swin Transformer is proposed with better efficiency and competitive accuracy.
arXiv Detail & Related papers (2023-03-17T20:14:10Z) - Deep Posterior Distribution-based Embedding for Hyperspectral Image
Super-resolution [75.24345439401166]
This paper focuses on how to embed the high-dimensional spatial-spectral information of hyperspectral (HS) images efficiently and effectively.
We formulate HS embedding as an approximation of the posterior distribution of a set of carefully-defined HS embedding events.
Then, we incorporate the proposed feature embedding scheme into a source-consistent super-resolution framework that is physically-interpretable.
Experiments over three common benchmark datasets demonstrate that PDE-Net achieves superior performance over state-of-the-art methods.
arXiv Detail & Related papers (2022-05-30T06:59:01Z) - High Quality Segmentation for Ultra High-resolution Images [72.97958314291648]
We propose the Continuous Refinement Model for the ultra high-resolution segmentation refinement task.
Our proposed method is fast and effective on image segmentation refinement.
arXiv Detail & Related papers (2021-11-29T11:53:06Z) - Enhanced Hyperspectral Image Super-Resolution via RGB Fusion and TV-TV
Minimization [9.584717030078245]
Hyperspectral (HS) images contain detailed spectral information that has proven crucial in applications like remote sensing, surveillance, and astronomy.
Because of hardware limitations of HS cameras, the captured images have low spatial resolution.
To improve them, the low-resolution hyperspectral images are fused with conventional high-resolution RGB images via a technique known as fusion based HS image super-resolution.
arXiv Detail & Related papers (2021-06-13T18:52:47Z) - Analysis and evaluation of Deep Learning based Super-Resolution
algorithms to improve performance in Low-Resolution Face Recognition [0.0]
Super-resolution algorithms may be able to recover the discriminant properties of the subjects involved.
This project aimed at evaluating and adapting different deep neural network architectures for the task of face super-resolution.
Experiments showed that general super-resolution architectures might enhance face verification performance of deep neural networks trained on high-resolution faces.
arXiv Detail & Related papers (2021-01-19T02:41:57Z) - Hyperspectral Image Super-resolution via Deep Progressive Zero-centric
Residual Learning [62.52242684874278]
Cross-modality distribution of spatial and spectral information makes the problem challenging.
We propose a novel textitlightweight deep neural network-based framework, namely PZRes-Net.
Our framework learns a high resolution and textitzero-centric residual image, which contains high-frequency spatial details of the scene.
arXiv Detail & Related papers (2020-06-18T06:32:11Z) - Hyperspectral Image Super-resolution via Deep Spatio-spectral
Convolutional Neural Networks [32.10057746890683]
We propose a simple and efficient architecture for deep convolutional neural networks to fuse a low-resolution hyperspectral image and a high-resolution multispectral image.
The proposed network architecture achieves best performance compared with recent state-of-the-art hyperspectral image super-resolution approaches.
arXiv Detail & Related papers (2020-05-29T05:56:50Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.