paper-with-me

Papers

Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting

2022-12-13 · CVPR 2023 1 · Su Wang, Chitwan Saharia, Ceslee Montgomery, Jordi Pont-Tuset, Shai Noy, Stefano Pellegrini, Yasumasa Onoe, Sarah Laszlo, David J. Fleet, Radu Soricut, Jason Baldridge, Mohammad Norouzi, Peter Anderson, William Chan

Text-guided image editing can have a transformative impact in supporting creative applications. A key challenge is to generate edits that are faithful to input text prompts, while consistent with input images. We present Imagen Editor, a cascaded diffusion model built, by fine-tuning Imagen on text-guided image inpainting. Imagen Editor's edits are faithful to the text prompts, which is accomplished by using object detectors to propose inpainting masks during training. In addition, Imagen Editor captures fine details in the input image by conditioning the cascaded pipeline on the original high resolution image. To improve qualitative and quantitative evaluation, we introduce EditBench, a systematic benchmark for text-guided image inpainting. EditBench evaluates inpainting edits on natural and generated images exploring objects, attributes, and scenes. Through extensive human evaluation on EditBench, we find that object-masking during training leads to across-the-board improvements in text-image alignment -- such that Imagen Editor is preferred over DALL-E 2 and Stable Diffusion -- and, as a cohort, these models are better at object-rendering than text-rendering, and handle material/color/size attributes better than count/shape attributes.

📄 PDF Abstract BibTeX arXiv:2212.06909

Code (0)

등록된 구현이 없습니다.

Tasks

Image InpaintingObjecttext-guided-image-editing

Methods 이 논문이 사용한 방법론

Inpainting Train a convolutional neural network to generate the contents of an arbitrary image region conditioned on its surroundings.
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

PhysEditBench: A Protocol-Conditioned Benchmark for Dense Physical-Map Prediction with Image Editors

2026-05-13 · Jiaxin Yang, Yu Hou, Muxin Liu, Weixuan Liu 외 arxiv

Can general-purpose image editors predict physical maps from a single RGB image? General-purpose image editors differ from standard task-specific dense-prediction models: they do not directly take an image and output a p…

DreamEdit: Subject-driven Image Editing

2023-06-22 · Tianle Li, Max Ku, Cong Wei, Wenhu Chen

Subject-driven image generation aims at generating images containing customized subjects, which has recently drawn enormous attention from the research community. However, the previous works cannot precisely control the …

Image GenerationPosition

TextEditBench: Evaluating Reasoning-aware Text Editing Beyond Rendering

2025-12-18 · Rui Gui, Yang Wan, Haochen Han, Dongxing Mao 외 arxiv

Text rendering has recently emerged as one of the most challenging frontiers in visual generation, drawing significant attention from large-scale diffusion and multimodal models. However, text editing within images remai…

multimodal generationImage Editing

SAFEdit: Does Multi-Agent Decomposition Resolve the Reliability Challenges of Instructed Code Editing?

2026-04-28 · Noam Tarshish, Nofar Selouk, Daniel Hodisan, Bar Ezra Gafniel 외 arxiv

Instructed code editing is a significant challenge for large language models (LLMs). On the EditBench benchmark, 39 of 40 evaluated models obtain a task success rate (TSR) below 60 percent, highlighting a gap between gen…

Code Generation

ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models

2026-02-17 · Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik, Carolyn Rosé arxiv

While Multimodal Large Language Models (MLLMs) perform strongly on single-turn chart generation, their ability to support real-world exploratory data analysis remains underexplored. In practice, users iteratively refine …