Hands-off Image Editing: Language-guided Editing without any Task-specific Labeling, Masking or even Training
This addresses the scalability and domain adaptation challenges in image editing for users needing flexible, unsupervised solutions, though it appears incremental in its approach.
The paper tackles instruction-guided image editing without requiring task-specific supervision like labeling, masking, or training, achieving very competitive performance.
Instruction-guided image editing consists in taking an image and an instruction and deliverring that image altered according to that instruction. State-of-the-art approaches to this task suffer from the typical scaling up and domain adaptation hindrances related to supervision as they eventually resort to some kind of task-specific labelling, masking or training. We propose a novel approach that does without any such task-specific supervision and offers thus a better potential for improvement. Its assessment demonstrates that it is highly effective, achieving very competitive performance.