Optimisation-Based Multi-Modal Semantic Image Editing

TL;DR — We propose an inference-time optimisation editing method using diffusion models, designed to extend beyond textual edits to accommodate multiple instruction types (e.g., spatial layout-based; pose, scribbles, edge maps).

Abstract

Image editing affords increased control over the aesthetics and content of generated images. Pre-existing works focus predominantly on text-based instructions to achieve desired image modifications, which limit edit precision and accuracy. In this work, we propose an inference-time editing optimisation, designed to extend beyond textual edits to accommodate multiple editing instruction types (e.g., spatial layout-based; pose, scribbles, edge maps). We propose to disentangle the editing task into two competing subtasks: successful local image modifications and global content consistency preservation, where subtasks are guidedthrough two dedicated loss functions. By allowing to adjust the influence of each loss function, we build a flexible editing solution that can be adjusted to user preferences. We evaluate our method using text, pose and scribble edit conditions, and highlight our ability to achieve complex edits, through both qualitative and quantitative experiments.