InstructBrush: Learning Attention-based Instruction Optimization for Image Editing

• URL: http://arxiv.org/abs/2403.18660v1
• Date: Wed, 27 Mar 2024 15:03:38 GMT
• Title: InstructBrush: Learning Attention-based Instruction Optimization for Image Editing
• Authors: Ruoyu Zhao, Qingnan Fan, Fei Kou, Shuai Qin, Hong Gu, Wei Wu, Pengcheng Xu, Mingrui Zhu, Nannan Wang, Xinbo Gao,
• Abstract summary: InstructBrush is an inversion method for instruction-based image editing methods. It extracts editing effects from image pairs as editing instructions, which are further applied for image editing. Our approach achieves superior performance in editing and is more semantically consistent with the target editing effects.
• Score: 54.07526261513434
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, instruction-based image editing methods have garnered significant attention in image editing. However, despite encompassing a wide range of editing priors, these methods are helpless when handling editing tasks that are challenging to accurately describe through language. We propose InstructBrush, an inversion method for instruction-based image editing methods to bridge this gap. It extracts editing effects from exemplar image pairs as editing instructions, which are further applied for image editing. Two key techniques are introduced into InstructBrush, Attention-based Instruction Optimization and Transformation-oriented Instruction Initialization, to address the limitations of the previous method in terms of inversion effects and instruction generalization. To explore the ability of instruction inversion methods to guide image editing in open scenarios, we establish a TransformationOriented Paired Benchmark (TOP-Bench), which contains a rich set of scenes and editing types. The creation of this benchmark paves the way for further exploration of instruction inversion. Quantitatively and qualitatively, our approach achieves superior performance in editing and is more semantically consistent with the target editing effects.

Related papers

• EditWorld: Simulating World Dynamics for Instruction-Following Image Editing [68.6224340373457]
  Diffusion models have significantly improved the performance of image editing. We introduce world-instructed image editing, which defines and categorizes the instructions grounded by various world scenarios. Our method significantly outperforms existing editing methods in this new task.
  arXiv  Detail & Related papers  (2024-05-23T16:54:17Z)
• AdapEdit: Spatio-Temporal Guided Adaptive Editing Algorithm for Text-Based Continuity-Sensitive Image Editing [24.9487669818162]
  We propose atemporal guided adaptive editing algorithm AdapEdit, which realizes adaptive image editing. Our approach has a significant advantage in preserving model priors and does not require model training, fine-tuning extra data, or optimization. We present our results over a wide variety of raw images and editing instructions, demonstrating competitive performance and showing it significantly outperforms the previous approaches.
  arXiv  Detail & Related papers  (2023-12-13T09:45:58Z)
• Optimisation-Based Multi-Modal Semantic Image Editing [58.496064583110694]
  We propose an inference-time editing optimisation to accommodate multiple editing instruction types. 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.
  arXiv  Detail & Related papers  (2023-11-28T15:31:11Z)
• Emu Edit: Precise Image Editing via Recognition and Generation Tasks [62.95717180730946]
  We present Emu Edit, a multi-task image editing model which sets state-of-the-art results in instruction-based image editing. We train it to multi-task across an unprecedented range of tasks, such as region-based editing, free-form editing, and Computer Vision tasks. We show that Emu Edit can generalize to new tasks, such as image inpainting, super-resolution, and compositions of editing tasks, with just a few labeled examples.
  arXiv  Detail & Related papers  (2023-11-16T18:55:58Z)
• Object-aware Inversion and Reassembly for Image Editing [61.19822563737121]
  We propose Object-aware Inversion and Reassembly (OIR) to enable object-level fine-grained editing. We use our search metric to find the optimal inversion step for each editing pair when editing an image. Our method achieves superior performance in editing object shapes, colors, materials, categories, etc., especially in multi-object editing scenarios.
  arXiv  Detail & Related papers  (2023-10-18T17:59:02Z)
• Visual Instruction Inversion: Image Editing via Visual Prompting [34.96778567507126]
  We present a method for image editing via visual prompting. We leverage the rich, pretrained editing capabilities of text-to-image diffusion models by inverting visual prompts into editing instructions.
  arXiv  Detail & Related papers  (2023-07-26T17:50:10Z)
• Fine-grained Image Editing by Pixel-wise Guidance Using Diffusion Models [4.855820180160146]
  We propose a novel diffusion-based image editing framework with pixel-wise guidance. We demonstrate that our proposal outperforms the GAN-based method for editing quality and speed.
  arXiv  Detail & Related papers  (2022-12-05T04:39:08Z)
• A Benchmark and Baseline for Language-Driven Image Editing [81.74863590492663]
  We first present a new language-driven image editing dataset that supports both local and global editing. Our new method treats each editing operation as a sub-module and can automatically predict operation parameters. We believe our work, including both the benchmark and the baseline, will advance the image editing area towards a more general and free-form level.
  arXiv  Detail & Related papers  (2020-10-05T20:51:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.