{"ID":2892488,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.16095","arxiv_id":"2507.16095","title":"Improving Personalized Image Generation through Social Context Feedback","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 $\u003c$man, pushing, motorcycle$\u003e$ 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.","short_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 $\u003c$man, pushing, motorcyc...","url_abs":"https://arxiv.org/abs/2507.16095","url_pdf":"https://arxiv.org/pdf/2507.16095v1","authors":"[\"Parul Gupta\",\"Abhinav Dhall\",\"Thanh-Toan Do\"]","published":"2025-07-21T22:36:30Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\"]","has_code":false}