ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing
This addresses a bottleneck in image editing for AI applications by enhancing reasoning capabilities, though it is incremental as it builds on existing datasets and methods.
The paper tackles the problem of instruction-based image editing models lacking active reasoning for implicit or vague instructions by introducing ReasonPix2Pix, a dataset with reasoning-focused instructions and realistic images, resulting in a fine-tuned model that shows superior performance in editing tasks.
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.