Image Generation Evaluation

Overview

Image generation evaluation asks whether generated images look realistic, match prompts and references, preserve identities, and satisfy constraints such as spatial layout or readable text. Common approaches combine distributional metrics such as Fréchet Inception Distance and precision–recall, vision-language and feature-based scores, human judgments, and benchmarks designed for specific tasks. Recent work expands evaluation to fine-grained capabilities—including multi-subject identity and attribute binding, editing consistency, world plausibility, artistic style, and medical-image utility—and uses multimodal models to provide scalable judgments or explanations. A central challenge is making automated scores reliable across datasets and domains: a single metric can miss important failures or favor one quality dimension, while human and expert assessments are costly and difficult to standardize.

Latest papers

CardsList

127 papers19 papers in the last four weeks, up 27% on the four weeks before. 0.1% of all new papers.

  1. Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?

    Feb 26, 2026Hongyu Li, Kuan Liu, Yuan Chen +6Image GenerationImage Generation Evaluation

  2. MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models

    Feb 23, 2026Mingrui Wu, Hang Liu, Jiayi Ji +2Image GenerationUnified Multimodal Models

  3. PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks

    Feb 6, 2026Junxian Li, Kai Liu, Leyang Chen +7Image Generation EvaluationImage Editing Evaluation

  4. OpenVTON-Bench: A Large-Scale High-Resolution Benchmark for Controllable Virtual Try-On Evaluation

    Jan 30, 2026Jin Li, Tao Chen, Kai Wen +5Virtual Try-OnImage Generation Evaluation

  5. MedGEN-Bench: A Contextually Entangled Benchmark for Open-ended Multimodal Medical Generation

    Nov 17, 2025Junjie Yang, Yuhao Yan, Gang Wu +12HealthcareMultimodal Generation