Entity · paper

Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications

paperactiveprovisionalinstruction-based-image-editing-a-survey-on-data-models-evaluation-and-applications-59364dfe·1 events·first seen 3d ago

Aliases: Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications

Co-occurring entities

CDD-IIE Bench

More like this (12)

image manipulation detection image manipulation localization Subject-driven Image Generation Masked Image Modeling text-to-image models ImageNet Data Selection Through Iterative Self-Filtering for Vision-Language Settings Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges NAMESAKES: Probing Identity Memorization in Text-to-Image Models A Multi-Domain Benchmark for Detecting AI-Generated Text-Rich Images from GPT-Image-2 Semantic Browsing: Controllable Diversity for Image Generation Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization

Recent events (1)

4arXiv · cs.CL·3d ago·source ↗

Survey on instruction-based image editing: taxonomy, benchmarks, and CDD-IIE Bench

A new arXiv survey systematically reviews instruction-based image editing (IIE) research across five dimensions: task taxonomy, training data construction, architectural evolution (GAN to diffusion to autoregressive), evaluation metrics, and commercial solutions. The authors introduce CDD-IIE Bench, a new diagnostic benchmark designed to rigorously assess multiple aspects of IIE model performance. The survey covers the role of LLMs and VLMs in enabling practical one-sentence image editing systems and compares open-source solutions empirically.

Evaluation and Benchmarking Multimodal Progress CDD-IIE Bench Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications