DHECA-SuperGaze: Dual Head-Eye Cross-Attention and Super-Resolution for Unconstrained Gaze Estimation

• URL: http://arxiv.org/abs/2505.08426v1
• Date: Tue, 13 May 2025 10:45:08 GMT
• Title: DHECA-SuperGaze: Dual Head-Eye Cross-Attention and Super-Resolution for Unconstrained Gaze Estimation
• Authors: Franko Šikić, Donik Vršnak, Sven Lončarić,
• Abstract summary: This paper introduces DHECA-SuperGaze, a deep learning-based method that advances gaze prediction through super-resolution (SR) and a dual head-eye cross-attention (DHECA) module.<n>Performance evaluation on Gaze360 and GFIE datasets demonstrates superior within-dataset performance of the proposed method.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Unconstrained gaze estimation is the process of determining where a subject is directing their visual attention in uncontrolled environments. Gaze estimation systems are important for a myriad of tasks such as driver distraction monitoring, exam proctoring, accessibility features in modern software, etc. However, these systems face challenges in real-world scenarios, partially due to the low resolution of in-the-wild images and partially due to insufficient modeling of head-eye interactions in current state-of-the-art (SOTA) methods. This paper introduces DHECA-SuperGaze, a deep learning-based method that advances gaze prediction through super-resolution (SR) and a dual head-eye cross-attention (DHECA) module. Our dual-branch convolutional backbone processes eye and multiscale SR head images, while the proposed DHECA module enables bidirectional feature refinement between the extracted visual features through cross-attention mechanisms. Furthermore, we identified critical annotation errors in one of the most diverse and widely used gaze estimation datasets, Gaze360, and rectified the mislabeled data. Performance evaluation on Gaze360 and GFIE datasets demonstrates superior within-dataset performance of the proposed method, reducing angular error (AE) by 0.48{\deg} (Gaze360) and 2.95{\deg} (GFIE) in static configurations, and 0.59{\deg} (Gaze360) and 3.00{\deg} (GFIE) in temporal settings compared to prior SOTA methods. Cross-dataset testing shows improvements in AE of more than 1.53{\deg} (Gaze360) and 3.99{\deg} (GFIE) in both static and temporal settings, validating the robust generalization properties of our approach.

Related papers

• MAGE: A Multi-task Architecture for Gaze Estimation with an Efficient Calibration Module [5.559268969773661]
  MAGE is a Multi-task Architecture for Gaze Estimation with an efficient calibration module.<n>Our basic model encodes both the directional and positional features from facial images.<n>Our method achieves state-of-the-art performance on the public MPIIFaceGaze, EYEDIAP, and our built IMRGaze datasets.
  arXiv  Detail & Related papers  (2025-05-22T08:36:58Z)
• Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels [10.827081942898506]
  We introduce a novel Self-Training Weakly-Supervised Gaze Estimation framework (ST-WSGE)<n>We propose the Gaze Transformer (GaT), a modality-agnostic architecture capable of simultaneously learning static and dynamic gaze information from both image and video datasets.<n>By combining 3D video datasets with 2D gaze target labels from gaze following tasks, our approach achieves the following key contributions.
  arXiv  Detail & Related papers  (2025-02-27T16:35:25Z)
• Spectrum-oriented Point-supervised Saliency Detector for Hyperspectral Images [13.79887292039637]
  We introduce point supervision into Hyperspectral salient object detection (HSOD)<n>We incorporate Spectral Saliency, derived from conventional HSOD methods, as a pivotal spectral representation within the framework.<n>We propose a novel pipeline, specifically designed for HSIs, to generate pseudo-labels, effectively mitigating the performance decline associated with point supervision strategy.
  arXiv  Detail & Related papers  (2024-12-24T02:52:43Z)
• S^2Former-OR: Single-Stage Bi-Modal Transformer for Scene Graph Generation in OR [50.435592120607815]
  Scene graph generation (SGG) of surgical procedures is crucial in enhancing holistically cognitive intelligence in the operating room (OR) Previous works have primarily relied on multi-stage learning, where the generated semantic scene graphs depend on intermediate processes with pose estimation and object detection. In this study, we introduce a novel single-stage bi-modal transformer framework for SGG in the OR, termed S2Former-OR.
  arXiv  Detail & Related papers  (2024-02-22T11:40:49Z)
• GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning [50.7702397913573]
  The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology. We propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection.
  arXiv  Detail & Related papers  (2024-02-03T03:13:50Z)
• Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection [59.41026558455904]
  We focus on multi-modal anomaly detection. Specifically, we investigate early multi-modal approaches that attempted to utilize models pre-trained on large-scale visual datasets. We propose a Local-to-global Self-supervised Feature Adaptation (LSFA) method to finetune the adaptors and learn task-oriented representation toward anomaly detection.
  arXiv  Detail & Related papers  (2024-01-06T07:30:41Z)
• Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation [29.154335016375367]
  We show that tuning a few simple parameters of a ResNet architecture can outperform most of the existing state-of-the-art methods for the gaze estimation task. We obtain the state-of-the-art performances on three datasets with 3.64 on ETH-XGaze, 4.50 on MPIIFaceGaze, and 9.13 on Gaze360 degrees gaze estimation error.
  arXiv  Detail & Related papers  (2023-08-18T14:41:51Z)
• NeRF-Gaze: A Head-Eye Redirection Parametric Model for Gaze Estimation [37.977032771941715]
  We propose a novel Head-Eye redirection parametric model based on Neural Radiance Field. Our model can decouple the face and eyes for separate neural rendering. It can achieve the purpose of separately controlling the attributes of the face, identity, illumination, and eye gaze direction.
  arXiv  Detail & Related papers  (2022-12-30T13:52:28Z)
• Detecting Rotated Objects as Gaussian Distributions and Its 3-D Generalization [81.29406957201458]
  Existing detection methods commonly use a parameterized bounding box (BBox) to model and detect (horizontal) objects. We argue that such a mechanism has fundamental limitations in building an effective regression loss for rotation detection. We propose to model the rotated objects as Gaussian distributions. We extend our approach from 2-D to 3-D with a tailored algorithm design to handle the heading estimation.
  arXiv  Detail & Related papers  (2022-09-22T07:50:48Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)
• MTGLS: Multi-Task Gaze Estimation with Limited Supervision [27.57636769596276]
  MTGLS: a Multi-Task Gaze estimation framework with Limited Supervision. We propose MTGLS: a Multi-Task Gaze estimation framework with Limited Supervision. Our proposed framework outperforms the unsupervised state-of-the-art on CAVE (by 6.43%) and even supervised state-of-the-art methods on Gaze360 (by 6.59%)
  arXiv  Detail & Related papers  (2021-10-23T00:20:23Z)
• EHSOD: CAM-Guided End-to-end Hybrid-Supervised Object Detection with Cascade Refinement [53.69674636044927]
  We present EHSOD, an end-to-end hybrid-supervised object detection system. It can be trained in one shot on both fully and weakly-annotated data. It achieves comparable results on multiple object detection benchmarks with only 30% fully-annotated data.
  arXiv  Detail & Related papers  (2020-02-18T08:04:58Z)

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.