Saved in:
Bibliographic Details
Main Authors: Santos, Rodrigo, Branco, António, Silva, João, Rodrigues, João
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.10064
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915182242955264
author Santos, Rodrigo
Branco, António
Silva, João
Rodrigues, João
author_facet Santos, Rodrigo
Branco, António
Silva, João
Rodrigues, João
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2502_10064
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Hands-off Image Editing: Language-guided Editing without any Task-specific Labeling, Masking or even Training
Santos, Rodrigo
Branco, António
Silva, João
Rodrigues, João
Computation and Language
Computer Vision and Pattern Recognition
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.
title Hands-off Image Editing: Language-guided Editing without any Task-specific Labeling, Masking or even Training
topic Computation and Language
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2502.10064