GEditBench v2: A Human-Aligned Benchmark for General Image Editing

Published on Mar 30

Authors:

,

,

,

,

,

,

Abstract

A new benchmark and evaluation model for image editing are introduced to better assess visual consistency and human alignment in complex editing tasks.

AI-generated summary

Recent advances in image editing have enabled models to handle complex instructions with impressive realism. However, existing evaluation frameworks lag behind: current benchmarks suffer from narrow task coverage, while standard metrics fail to adequately capture visual consistency, i.e., the preservation of identity, structure and semantic coherence between edited and original images. To address these limitations, we introduce GEditBench v2, a comprehensive benchmark with 1,200 real-world user queries spanning 23 tasks, including a dedicated open-set category for unconstrained, out-of-distribution editing instructions beyond predefined tasks. Furthermore, we propose PVC-Judge, an open-source pairwise assessment model for visual consistency, trained via two novel region-decoupled preference data synthesis pipelines. Besides, we construct VCReward-Bench using expert-annotated preference pairs to assess the alignment of PVC-Judge with human judgments on visual consistency evaluation. Experiments show that our PVC-Judge achieves state-of-the-art evaluation performance among open-source models and even surpasses GPT-5.1 on average. Finally, by benchmarking 16 frontier editing models, we show that GEditBench v2 enables more human-aligned evaluation, revealing critical limitations of current models, and providing a reliable foundation for advancing precise image editing.

View arXiv page View PDF Project page GitHub 30 Add to collection

Get this paper in your agent:

hf papers read 2603.28547

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 1

Datasets citing this paper 3

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2603.28547 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.