Inst-Inpaint: Instructing to Remove Objects with Diffusion Models

Abstract

Abstract Image inpainting task refers to erasing unwanted pixels from images and filling them in a semantically consistent and realistic way. Traditionally, the pixels that are wished to be erased are defined with binary masks. From the application point of view, a user needs to generate the masks for the objects they would like to remove which can be time-consuming and prone to errors. In this work, we are interested in an image inpainting algorithm that estimates which object to be removed based on natural language input and removes it, simultaneously. For this purpose, first, we construct a dataset named GQA-Inpaint for this task. Second, we present an inpainting framework, Inst-Inpaint , that can remove objects from images based on the instructions given as text prompts. We set various GAN and diffusion-based baselines and run experiments on synthetic and real-world image datasets. We compare methods with different evaluation metrics that measure the quality and accuracy of the models and show significant quantitative and qualitative improvements. Please refer to the web page of the project for the released code and dataset: http://instinpaint.abyildirim.com/

The authors' abstract, as published at the source. International Journal of Computer Vision, 2026 · DOI ↗