paper-with-me

홈 › Papers

EditScribe: Non-Visual Image Editing with Natural Language Verification Loops

2024-08-13 · Ruei-Che Chang, Yuxuan Liu, Lotus Zhang, Anhong Guo

Image editing is an iterative process that requires precise visual evaluation and manipulation for the output to match the editing intent. However, current image editing tools do not provide accessible interaction nor sufficient feedback for blind and low vision individuals to achieve this level of control. To address this, we developed EditScribe, a prototype system that makes image editing accessible using natural language verification loops powered by large multimodal models. Using EditScribe, the user first comprehends the image content through initial general and object descriptions, then specifies edit actions using open-ended natural language prompts. EditScribe performs the image edit, and provides four types of verification feedback for the user to verify the performed edit, including a summary of visual changes, AI judgement, and updated general and object descriptions. The user can ask follow-up questions to clarify and probe into the edits or verification feedback, before performing another edit. In a study with ten blind or low-vision users, we found that EditScribe supported participants to perform and verify image edit actions non-visually. We observed different prompting strategies from participants, and their perceptions on the various types of verification feedback. Finally, we discuss the implications of leveraging natural language verification loops to make visual authoring non-visually accessible.

📄 PDF Abstract BibTeX arXiv:2408.06632

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ChartReformer: Natural Language-Driven Chart Image Editing

2024-03-01 · Pengyu Yan, Mahesh Bhosale, Jay Lal, Bikhyat Adhikari 외

Chart visualizations are essential for data interpretation and communication; however, most charts are only accessible in image format and lack the corresponding data tables and supplementary information, making it diffi…

PlotEdit: Natural Language-Driven Accessible Chart Editing in PDFs via Multimodal LLM Agents

2025-01-20 · Kanika Goswami, Puneet Mathur, Ryan Rossi, Franck Dernoncourt

Chart visualizations, while essential for data interpretation and communication, are predominantly accessible only as images in PDFs, lacking source data tables and stylistic information. To enable effective editing of c…

AttributeTable Extraction

Guiding Instruction-based Image Editing via Multimodal Large Language Models

2023-09-29 · Tsu-Jui Fu, Wenze Hu, Xianzhi Du, William Yang Wang 외

Instruction-based image editing improves the controllability and flexibility of image manipulation via natural commands without elaborate descriptions or regional masks. However, human instructions are sometimes too brie…

Image ManipulationResponse Generation

Let RGB Be the Language of Vision

2026-07-14 · Timing Yang, Jinrui Yang, Xinlong Li, Yuhan Wang 외 arxiv

This work introduces a unified formulation for vision models, where diverse forms of visual information beyond natural images, such as masks, depth maps, and other structured visual signals, are all represented as RGB im…

Depth EstimationImage GenerationImage Editing

InstructRL4Pix: Training Diffusion for Image Editing by Reinforcement Learning

2024-06-14 · Tiancheng Li, Jinxiu Liu, Huajun Chen, Qi Liu

Instruction-based image editing has made a great process in using natural human language to manipulate the visual content of images. However, existing models are limited by the quality of the dataset and cannot accuratel…

Objectreinforcement-learningReinforcement Learning