Image editing method enables precise control of multiple subjects separately
LOCI: Localized Continuous Control for Multi-Subject Image Editing
Computer Vision and Pattern Recognition
Summary
Editing pictures with multiple people can be tricky because it's hard to change one person without affecting others nearby. The authors developed a new method called LOCI that lets you control exactly where and how much each person in a photo is changed, like making one older and adding a beard to another at the same time. This approach avoids mixing up changes between people and lets you adjust the strength of each edit smoothly. Their experiments show LOCI is better at keeping these changes separate and accurate compared to previous methods.
What this means in practice
- •For photo editing software developers: Implement precise, independently adjustable edits on different people in group photos to improve user control and output quality.$Commercial implications: Enables the creation of advanced photo editing features for commercial apps that allow users fine control over multiple subjects, enhancing product appeal.
- •For visual effects artists: Apply nuanced changes to individual actors or subjects in multi-person scenes while minimizing unintended changes to others.
Authors
Sai Vidyaranya Nuthalapati, Shlok Kumar Mishra
Abstract
Recent instruction-following image editors such as Flux.1-Kontext enable text-driven editing but lack fine-grained control over where and how much an edit is applied. Existing approaches provide either continuous but global control or spatially localized editing at a fixed strength. To our knowledge, none jointly supports explicit spatial localization, continuous per-region strength, and independent simultaneous control of multiple subjects. We present LOCI (LOcalized Continuous control for multi- subject Image editing). Given a multi-subject image with per-subject regions and instructions, LOCI edits each subject at an independently chosen, continuously adjustable strength, for instance gradually aging one person while adding a beard to another with minimal cross-region leakage. LOCI pairs subject-level attention binding for spatial isolation with a Regional LoRA layer that replaces the LoRA's scalar coefficient with a per-token scaling vector aligned to the spatial layout. A single adapter is trained at one suppression point, and continuous edit strengths follow by rescaling its regional residual at inference. Experiments on multi-subject scenes demonstrate that LOCI achieves strong edit fidelity with significantly reduced cross-region interference compared to baselines, while maintaining continuous control over edit strength