# T2I-FineEval: Fine-Grained Compositional Metric for Text-to-Image Evaluation

arXiv: https://arxiv.org/abs/2503.11481 · HTML: https://mlsanity.com/paper/2503.11481/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 19 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 17 of 17)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [SPICE: Semantic Propositional Image Caption Evaluation](https://mlsanity.com/paper/1607.08822/) (2016)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [FILIP: Fine-grained Interactive Language-Image Pre-Training](https://mlsanity.com/paper/2111.07783/) (2021)
- [Compositional Visual Generation with Composable Diffusion Models](https://mlsanity.com/paper/2206.01714/) (2022)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections](https://mlsanity.com/paper/2205.12005/) (2022)
- [Simple multi-dataset detection](https://mlsanity.com/paper/2102.13086/) (2021)
- [Human Evaluation of Text-to-Image Models on a Multi-Task Benchmark](https://mlsanity.com/paper/2211.12112/) (2022)
- [Transparent Human Evaluation for Image Captioning](https://mlsanity.com/paper/2111.08940/) (2021)
- [Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback](https://mlsanity.com/paper/2307.04749/) (2023)

## Built on by (most cited first, 4 of 4)

- [Beyond the Pixels: VLM-based Evaluation of Identity Preservation in Reference-Guided Synthesis](https://mlsanity.com/paper/2511.08087/) (2025)
- [Efficient Adversarial Attacks on High-dimensional Offline Bandits](https://mlsanity.com/paper/2602.01658/) (2026)
- [WeGenBench: A Multidimensional Diagnostic Benchmark towards Text-to-Image Model Optimization](https://mlsanity.com/paper/2606.20100/) (2026)
- [VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric](https://mlsanity.com/paper/2610.16441/) (2026)

## Abstract (arXiv)

Although recent text-to-image generative models have achieved impressive performance, they still often struggle with capturing the compositional complexities of prompts including attribute binding, and spatial relationships between different entities. This misalignment is not revealed by common evaluation metrics such as CLIPScore. Recent works have proposed evaluation metrics that utilize Visual Question Answering (VQA) by decomposing prompts into questions about the generated image for more robust compositional evaluation. Although these methods align better with human evaluations, they still fail to fully cover the compositionality within the image. To address this, we propose a novel metric that breaks down images into components, and texts into fine-grained questions about the generated image for evaluation. Our method outperforms previous state-of-the-art metrics, demonstrating its effectiveness in evaluating text-to-image generative models. Code is available at https://github.com/hadi-hosseini/ T2I-FineEval.