arXiv AI
A Large-scale Evaluation of Text-guided Models for Facial Editing
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 3
Multi-Tool Image Editing Attribution in Facial Forgery
The paper introduces Multi-Tool Image Editing Attribution (MIEA), a task that identifies multiple generative AI tools used to edit facial images. It presents a new dataset, MultiEdit, with over 500,000 edited faces covering six editing tool types, including face swapping and facial enhancements. The authors propose DPEC, a method that captures tool-specific traces in spatial and frequency domains using an error-based curriculum learning strategy, outperforming nine baseline methods on images edited in up to five steps.
Hugging Face Trending Papers
Aug 3
MIEScore: Human-Aligned Evaluation for Multi-Source Image Editing
Recent advances in unified multimodal models have significantly improved text-guided image editing abilities. In particular, models such as Nano-Banana-Pro and GPT-Image-2 demonstrate emerging capabilities in multi-source image editing (MIE), including tasks such as object synthesis, person-background composition, and cross-image style fusion.
arXiv AI
Jun 2
TECCI: Tricky Edits of Collected and Curated Images
arXiv:2606. 01213v1 Announce Type: cross Abstract: Despite tremendous recent progress, current text-guided image editing methods still struggle with many aspects of editing involving instruction following, minimally editing the source image, and ensuring high visual quality.
Hugging Face Trending Papers
Jul 13
Latent-Identity Tuning in Text-to-Image Personalization Models
Generating and editing a person's face demands high precision, as even minor modifications can significantly alter a subject's perceived identity. Current personalization and editing methods built on general-purpose text-to-image models, however, often lack the precision required for fine-grained facial edits.
arXiv AI
Sep 2
EdiTikZ: Scientific Figure Editing from Revision Trajectories
arXiv:2609.01409v1 Announce Type: new Abstract: Vision-language models (VLMs) have shown strong performance in generating scientific figures from text or images. However, producing publication-ready...
arXiv AI
Jun 9
IEA: Amateur-Friendly Conversational Image Editing Agent via Three Stages of Multitask Alignment
arXiv:2606. 08016v1 Announce Type: cross Abstract: Current image editing software often hinges on fixed filters or expert tuning, leaving a gap between amateur users' intent and outcomes.