Back to Search Start Over

ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing

Authors :
Jin, Ying
Ling, Pengyang
Dong, Xiaoyi
Zhang, Pan
Wang, Jiaqi
Lin, Dahua
Publication Year :
2024

Abstract

Instruction-based image editing focuses on equipping a generative model with the capacity to adhere to human-written instructions for editing images. Current approaches typically comprehend explicit and specific instructions. However, they often exhibit a deficiency in executing active reasoning capacities required to comprehend instructions that are implicit or insufficiently defined. To enhance active reasoning capabilities and impart intelligence to the editing model, we introduce ReasonPix2Pix, a comprehensive reasoning-attentive instruction editing dataset. The dataset is characterized by 1) reasoning instruction, 2) more realistic images from fine-grained categories, and 3) increased variances between input and edited images. When fine-tuned with our dataset under supervised conditions, the model demonstrates superior performance in instructional editing tasks, independent of whether the tasks require reasoning or not. The code will be available at https://github.com/Jin-Ying/ReasonPix2Pix.

Details

Database :
arXiv
Publication Type :
Report
Accession number :
edsarx.2405.11190
Document Type :
Working Paper