EdiVal-Agent: An Object-Centric Framework for Automated, Scalable, Fine-Grained Evaluation of Multi-Turn Editing
By: Tianyu Chen , Yasi Zhang , Zhi Zhang and more
Potential Business Impact:
Checks if computer edits pictures correctly.
Instruction-based image editing has advanced rapidly, yet reliable and interpretable evaluation remains a bottleneck. Current protocols either (i) depend on paired reference images -- resulting in limited coverage and inheriting biases from prior generative models -- or (ii) rely solely on zero-shot vision-language models (VLMs), whose prompt-based assessments of instruction following, content consistency, and visual quality are often imprecise. To address this, we introduce EdiVal-Agent, an automated, scalable, and fine-grained evaluation framework for multi-turn instruction-based editing from an object-centric perspective, supported by a suite of expert tools. Given an image, EdiVal-Agent first decomposes it into semantically meaningful objects, then synthesizes diverse, context-aware editing instructions. For evaluation, it integrates VLMs with open-vocabulary object detectors to assess instruction following, uses semantic-level feature extractors to evaluate content consistency, and leverages human preference models to judge visual quality. We show that combining VLMs with object detectors yields stronger agreement with human judgments in instruction-following evaluation compared to using VLMs alone and CLIP-based metrics. Furthermore, the pipeline's modular design allows future tools to be seamlessly integrated, enhancing evaluation accuracy over time. Instantiating this pipeline, we build EdiVal-Bench, a multi-turn editing benchmark covering 9 instruction types and 11 state-of-the-art editing models spanning autoregressive (AR) (including Nano Banana, GPT-Image-1), flow-matching, and diffusion paradigms. We demonstrate that EdiVal-Agent can be used to identify existing failure modes, thereby informing the development of the next generation of editing models. Project page: https://tianyucodings.github.io/EdiVAL-page/.
Similar Papers
An LLM-LVLM Driven Agent for Iterative and Fine-Grained Image Editing
CV and Pattern Recognition
Lets you change pictures by talking to them.
JarvisEvo: Towards a Self-Evolving Photo Editing Agent with Synergistic Editor-Evaluator Optimization
CV and Pattern Recognition
Makes AI image editing smarter and more creative.
EditInspector: A Benchmark for Evaluation of Text-Guided Image Edits
CV and Pattern Recognition
Checks if AI image edits are good.