FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing

• URL: http://arxiv.org/abs/2408.12429v1
• Date: Thu, 22 Aug 2024 14:22:07 GMT
• Title: FlexEdit: Marrying Free-Shape Masks to VLLM for Flexible Image Editing
• Authors: Jue Wang, Yuxiang Lin, Tianshuo Yuan, Zhi-Qi Cheng, Xiaolong Wang, Jiao GH, Wei Chen, Xiaojiang Peng,
• Abstract summary: We propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing. Our method achieves state-of-the-art (SOTA) performance in LLM-based image editing, and our simple prompting technique stands out in its effectiveness.
• Score: 25.18320863976491
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Combining Vision Large Language Models (VLLMs) with diffusion models offers a powerful method for executing image editing tasks based on human language instructions. However, language instructions alone often fall short in accurately conveying user requirements, particularly when users want to add, replace elements in specific areas of an image. Luckily, masks can effectively indicate the exact locations or elements to be edited, while they require users to precisely draw the shapes at the desired locations, which is highly user-unfriendly. To address this, we propose FlexEdit, an end-to-end image editing method that leverages both free-shape masks and language instructions for Flexible Editing. Our approach employs a VLLM in comprehending the image content, mask, and user instructions. Additionally, we introduce the Mask Enhance Adapter (MEA) that fuses the embeddings of the VLLM with the image data, ensuring a seamless integration of mask information and model output embeddings. Furthermore, we construct FSMI-Edit, a benchmark specifically tailored for free-shape mask, including 8 types of free-shape mask. Extensive experiments show that our method achieves state-of-the-art (SOTA) performance in LLM-based image editing, and our simple prompting technique stands out in its effectiveness. The code and data can be found at https://github.com/A-new-b/flex_edit.

Related papers

• FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model [54.693572837423226]
  FireEdit is an innovative Fine-grained Instruction-based image editing framework that exploits a REgion-aware VLM. FireEdit is designed to accurately comprehend user instructions and ensure effective control over the editing process. Our approach surpasses the state-of-the-art instruction-based image editing methods.
  arXiv  Detail & Related papers  (2025-03-25T16:59:42Z)
• High-Quality Mask Tuning Matters for Open-Vocabulary Segmentation [109.19165503929992]
  We present MaskCLIP++, which uses ground-truth masks instead of generated masks to enhance the mask classification capability of CLIP. After low-cost fine-tuning, MaskCLIP++ significantly improves the mask classification performance on multi-domain datasets. We achieve performance improvements of +1.7, +2.3, +2.1, +3.1, and +0.3 mIoU on the A-847, PC-459, A-150, PC-59, and PAS-20 datasets.
  arXiv  Detail & Related papers  (2024-12-16T05:44:45Z)
• BrushEdit: All-In-One Image Inpainting and Editing [79.55816192146762]
  BrushEdit is a novel inpainting-based instruction-guided image editing paradigm. We devise a system enabling free-form instruction editing by integrating MLLMs and a dual-branch image inpainting model. Our framework effectively combines MLLMs and inpainting models, achieving superior performance across seven metrics.
  arXiv  Detail & Related papers  (2024-12-13T17:58:06Z)
• SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing [42.23117201457898]
  We introduce a new framework that integrates large language model (LLM) with Text2 generative model for graph-based image editing. Our framework significantly outperforms existing image editing methods in terms of editing precision and scene aesthetics.
  arXiv  Detail & Related papers  (2024-10-15T17:40:48Z)
• Click2Mask: Local Editing with Dynamic Mask Generation [23.89536337989824]
  Click2Mask is a novel approach that simplifies the local editing process by requiring only a single point of reference. Our experiments demonstrate that Click2Mask not only minimizes user effort but also delivers competitive or superior local image manipulation results.
  arXiv  Detail & Related papers  (2024-09-12T17:59:04Z)
• MTA-CLIP: Language-Guided Semantic Segmentation with Mask-Text Alignment [53.235290505274676]
  Large-scale vision-language models such as CLIP can improve semantic segmentation performance. We introduce MTA-CLIP, a novel framework employing mask-level vision-language alignment. MTA-CLIP achieves state-of-the-art, surpassing prior works by an average of 2.8% and 1.3% on benchmark datasets.
  arXiv  Detail & Related papers  (2024-07-31T14:56:42Z)
• An Item is Worth a Prompt: Versatile Image Editing with Disentangled Control [21.624984690721842]
  D-Edit is a framework to disentangle the comprehensive image-prompt interaction into several item-prompt interactions. It is based on pretrained diffusion models with cross-attention layers disentangled and adopts a two-step optimization to build item-prompt associations. We demonstrate state-of-the-art results in four types of editing operations including image-based, text-based, mask-based editing, and item removal.
  arXiv  Detail & Related papers  (2024-03-07T20:06:29Z)
• Text-Driven Image Editing via Learnable Regions [74.45313434129005]
  We introduce a method for region-based image editing driven by textual prompts, without the need for user-provided masks or sketches. We show that this simple approach enables flexible editing that is compatible with current image generation models. Experiments demonstrate the competitive performance of our method in manipulating images with high fidelity and realism that correspond to the provided language descriptions.
  arXiv  Detail & Related papers  (2023-11-28T02:27:31Z)
• InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions [46.88926203020054]
  We propose a framework termed InstructEdit that can do fine-grained editing based on user instructions. Our method outperforms previous editing methods in fine-grained editing applications.
  arXiv  Detail & Related papers  (2023-05-29T12:24:58Z)
• DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models [68.21154597227165]
  We show that it is possible to automatically obtain accurate semantic masks of synthetic images generated by the Off-the-shelf Stable Diffusion model. Our approach, called DiffuMask, exploits the potential of the cross-attention map between text and image.
  arXiv  Detail & Related papers  (2023-03-21T08:43:15Z)
• DiffEdit: Diffusion-based semantic image editing with mask guidance [64.555930158319]
  DiffEdit is a method to take advantage of text-conditioned diffusion models for the task of semantic image editing. Our main contribution is able to automatically generate a mask highlighting regions of the input image that need to be edited.
  arXiv  Detail & Related papers  (2022-10-20T17:16:37Z)
• FlexIT: Towards Flexible Semantic Image Translation [59.09398209706869]
  We propose FlexIT, a novel method which can take any input image and a user-defined text instruction for editing. First, FlexIT combines the input image and text into a single target point in the CLIP multimodal embedding space. We iteratively transform the input image toward the target point, ensuring coherence and quality with a variety of novel regularization terms.
  arXiv  Detail & Related papers  (2022-03-09T13:34:38Z)
• SketchEdit: Mask-Free Local Image Manipulation with Partial Sketches [95.45728042499836]
  We propose a new paradigm of sketch-based image manipulation: mask-free local image manipulation. Our model automatically predicts the target modification region and encodes it into a structure style vector. A generator then synthesizes the new image content based on the style vector and sketch.
  arXiv  Detail & Related papers  (2021-11-30T02:42:31Z)

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.