English

Improving Personalized Image Generation through Social Context Feedback

Computer Vision and Pattern Recognition 2025-07-23 v1

Abstract

Personalized image generation, where reference images of one or more subjects are used to generate their image according to a scene description, has gathered significant interest in the community. However, such generated images suffer from three major limitations -- complex activities, such as <<man, pushing, motorcycle>> are not generated properly with incorrect human poses, reference human identities are not preserved, and generated human gaze patterns are unnatural/inconsistent with the scene description. In this work, we propose to overcome these shortcomings through feedback-based fine-tuning of existing personalized generation methods, wherein, state-of-art detectors of pose, human-object-interaction, human facial recognition and human gaze-point estimation are used to refine the diffusion model. We also propose timestep-based inculcation of different feedback modules, depending upon whether the signal is low-level (such as human pose), or high-level (such as gaze point). The images generated in this manner show an improvement in the generated interactions, facial identities and image quality over three benchmark datasets.

Keywords

Cite

@article{arxiv.2507.16095,
  title  = {Improving Personalized Image Generation through Social Context Feedback},
  author = {Parul Gupta and Abhinav Dhall and Thanh-Toan Do},
  journal= {arXiv preprint arXiv:2507.16095},
  year   = {2025}
}
R2 v1 2026-07-01T04:12:26.581Z