GazeFusion: Saliency-guided Image Generation

Abstract

Diffusion models offer unprecedented image generation power given just a text prompt. While emerging approaches for controlling diffusion models have enabled users to specify the desired spatial layouts of the generated content, they cannot predict or control where viewers will pay more attention due to the complexity of human vision. Recognizing the significance of attention-controllable image generation in practical applications, we present a saliency-guided framework to incorporate the data priors of human visual attention mechanisms into the generation process. Given a user-specified viewer attention distribution, our control module conditions a diffusion model to generate images that attract viewers’ attention toward the desired regions. To assess the efficacy of our approach, we performed an eye-tracked user study and a large-scale model-based saliency analysis. The results evidence that both the cross-user eye gaze distributions and the saliency models’ predictions align with the desired attention distributions. Lastly, we outline several applications, including interactive design of saliency guidance, attention suppression in unwanted regions, and adaptive generation for varied display/viewing conditions.

Acknowledgement

This research is partially supported by the National Science Foundation grant #2232817 and a gift from Google. We would like to thank Saining Xie, Anyi Rao, and Zoya Bylinskii for fruitful early discussion, and the authors of Stable Diffusion, ControlNet, BLIP-2, EML-Net, and Text2Video-Zero for their great work, based on which GazeFusion was developed.

Bibtex

@article{zhang2024gazefusion,
author = {Zhang, Yunxiang and Wu, Nan and Lin, Connor Z. and Wetzstein, Gordon and Sun, Qi},
title = {GazeFusion: Saliency-guided Image Generation},
year = {2024},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
issn = {1544-3558},
url = {https://doi.org/10.1145/3694969},
doi = {10.1145/3694969},
journal = {ACM Trans. Appl. Percept.},
month = {sep},
keywords = {Human Visual Attention, Perceptual Computer Graphics, Controllable Image Generation}
}