paper-with-me

홈 › Papers

WAYLA - Generating Images from Eye Movements

2017-11-21 · Bingqing Yu, James J. Clark

We present a method for reconstructing images viewed by observers based only on their eye movements. By exploring the relationships between gaze patterns and image stimuli, the "What Are You Looking At?" (WAYLA) system learns to synthesize photo-realistic images that are similar to the original pictures being viewed. The WAYLA approach is based on the Conditional Generative Adversarial Network (Conditional GAN) image-to-image translation technique of Isola et al. We consider two specific applications - the first, of reconstructing newspaper images from gaze heat maps, and the second, of detailed reconstruction of images containing only text. The newspaper image reconstruction process is divided into two image-to-image translation operations, the first mapping gaze heat maps into image segmentations, and the second mapping the generated segmentation into a newspaper image. We validate the performance of our approach using various evaluation metrics, along with human visual inspection. All results confirm the ability of our network to perform image generation tasks using eye tracking data.

📄 PDF Abstract BibTeX arXiv:1711.07974

Code (0)

등록된 구현이 없습니다.

Tasks

Generative Adversarial NetworkImage GenerationImage ReconstructionImage-to-Image TranslationTranslation

Similar Papers 제목 키워드 기반

Motion Transfer-Enhanced StyleGAN for Generating Diverse Macaque Facial Expressions

2025-11-20 · Takuya Igaue, Catia Correia-Caeiro, Akito Yoshida, Takako Miyabe-Nishiwaki 외 arxiv

Generating animal faces using generative AI techniques is challenging because the available training images are limited both in quantity and variation, particularly for facial expressions across individuals. In this stud…

Data AugmentationImage Editing

Lip Movements Generation at a Glance

2018-03-28 · ECCV 2018 9 · Lele Chen, Zhiheng Li, Ross K. Maddox, Zhiyao Duan 외

Cross-modality generation is an emerging topic that aims to synthesize data in one modality based on information in a different modality. In this paper, we consider a task of such: given an arbitrary audio speech and one…

DFA-NeRF: Personalized Talking Head Generation via Disentangled Face Attributes Neural Rendering

2022-01-03 · Shunyu Yao, RuiZhe Zhong, Yichao Yan, Guangtao Zhai 외

While recent advances in deep neural networks have made it possible to render high-quality images, generating photo-realistic and personalized talking head remains challenging. With given audio, the key to tackling this …

NeRFNeural RenderingTalking Head Generation

Versatile Multimodal Controls for Expressive Talking Human Animation

2025-03-10 · Zheng Qin, Ruobing Zheng, Yabing Wang, Tianqi Li 외

In filmmaking, directors typically allow actors to perform freely based on the script before providing specific guidance on how to present key actions. AI-generated content faces similar requirements, where users not onl…

Human Animation

StyleFaceV: Face Video Generation via Decomposing and Recomposing Pretrained StyleGAN3

2022-08-16 · Haonan Qiu, Yuming Jiang, Hang Zhou, Wayne Wu 외

Realistic generative face video synthesis has long been a pursuit in both computer vision and graphics community. However, existing face video generation methods tend to produce low-quality frames with drifted facial ide…

Image GenerationVideo Generation