Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fréchet Distance

• URL: http://arxiv.org/abs/2503.21721v2
• Date: Tue, 26 Aug 2025 20:28:06 GMT
• Title: Evaluating Text-to-Image and Text-to-Video Synthesis with a Conditional Fréchet Distance
• Authors: Jaywon Koo, Jefferson Hernandez, Moayed Haji-Ali, Ziyan Yang, Vicente Ordonez,
• Abstract summary: We propose cFreD, a metric that unifies the assessment of visual fidelity and text-prompt consistency into a single score.<n>Our findings validate cFreD as a robust, future-proof metric for the systematic evaluation of text conditioned models.
• Score: 13.599366291595672
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Evaluating text-to-image and text-to-video models is challenging due to a fundamental disconnect: established metrics fail to jointly measure visual quality and semantic alignment with text, leading to a poor correlation with human judgments. To address this critical issue, we propose cFreD, a general metric based on a Conditional Fr\'echet Distance that unifies the assessment of visual fidelity and text-prompt consistency into a single score. Existing metrics such as Fr\'echet Inception Distance (FID) capture image quality but ignore text conditioning while alignment scores such as CLIPScore are insensitive to visual quality. Furthermore, learned preference models require constant retraining and are unlikely to generalize to novel architectures or out-of-distribution prompts. Through extensive experiments across multiple recently proposed text-to-image models and diverse prompt datasets, cFreD exhibits a higher correlation with human judgments compared to statistical metrics , including metrics trained with human preferences. Our findings validate cFreD as a robust, future-proof metric for the systematic evaluation of text conditioned models, standardizing benchmarking in this rapidly evolving field. We release our evaluation toolkit and benchmark.

Related papers

• PoSh: Using Scene Graphs To Guide LLMs-as-a-Judge For Detailed Image Descriptions [55.95282725491425]
  PoSh is a metric for detailed image description that uses scene graphs as structured rubrics to guide LLMs-as-a-Judge.<n>PoSh is replicable, interpretable and a better proxy for human raters than existing metrics.<n>We show that PoSh achieves stronger correlations with the human judgments in DOCENT than the best open-weight alternatives.
  arXiv  Detail & Related papers  (2025-10-21T20:30:20Z)
• Text-Visual Semantic Constrained AI-Generated Image Quality Assessment [47.575342788480505]
  We propose a unified framework to enhance the comprehensive evaluation of both text-image consistency and perceptual distortion in AI-generated images.<n>Our approach integrates key capabilities from multiple models and tackles the aforementioned challenges by introducing two core modules.<n>Tests conducted on multiple benchmark datasets demonstrate that SC-AGIQA outperforms existing state-of-the-art methods.
  arXiv  Detail & Related papers  (2025-07-14T16:21:05Z)
• TypeScore: A Text Fidelity Metric for Text-to-Image Generative Models [39.06617653124486]
  We introduce a new evaluation framework called TypeScore to assess a model's ability to generate images with high-fidelity embedded text. Our proposed metric demonstrates greater resolution than CLIPScore to differentiate popular image generation models.
  arXiv  Detail & Related papers  (2024-11-02T07:56:54Z)
• Holistic Evaluation for Interleaved Text-and-Image Generation [19.041251355695973]
  We introduce InterleavedBench, the first benchmark carefully curated for the evaluation of interleaved text-and-image generation. In addition, we present InterleavedEval, a strong reference-free metric powered by GPT-4o to deliver accurate and explainable evaluation.
  arXiv  Detail & Related papers  (2024-06-20T18:07:19Z)
• FINEMATCH: Aspect-based Fine-grained Image and Text Mismatch Detection and Correction [66.98008357232428]
  We propose FineMatch, a new aspect-based fine-grained text and image matching benchmark. FineMatch focuses on text and image mismatch detection and correction. We show that models trained on FineMatch demonstrate enhanced proficiency in detecting fine-grained text and image mismatches.
  arXiv  Detail & Related papers  (2024-04-23T03:42:14Z)
• A Survey on Quality Metrics for Text-to-Image Generation [9.753473063305503]
  AI-based text-to-image models do not only excel at generating realistic images, they also give designers more and more fine-grained control over the image content.<n>These approaches have gathered increased attention within the computer graphics research community.<n>We provide a comprehensive overview of such text-to-image quality metrics, and propose a taxonomy to categorize these metrics.
  arXiv  Detail & Related papers  (2024-03-18T14:24:20Z)
• Cobra Effect in Reference-Free Image Captioning Metrics [58.438648377314436]
  A proliferation of reference-free methods, leveraging visual-language pre-trained models (VLMs), has emerged. In this paper, we study if there are any deficiencies in reference-free metrics. We employ GPT-4V as an evaluative tool to assess generated sentences and the result reveals that our approach achieves state-of-the-art (SOTA) performance.
  arXiv  Detail & Related papers  (2024-02-18T12:36:23Z)
• Looking at words and points with attention: a benchmark for text-to-shape coherence [17.340484439401894]
  The evaluation of coherence between generated 3D shapes and input textual descriptions lacks a clear benchmark. We employ large language models to automatically refine descriptions associated with shapes. To validate our approach, we conduct a user study and compare quantitatively our metric with existing ones. The refined dataset, the new metric and a set of text-shape pairs validated by the user study comprise a novel, fine-grained benchmark.
  arXiv  Detail & Related papers  (2023-09-14T17:59:48Z)
• Evaluation of Faithfulness Using the Longest Supported Subsequence [52.27522262537075]
  We introduce a novel approach to evaluate faithfulness of machine-generated text by computing the longest noncontinuous of the claim that is supported by the context. Using a new human-annotated dataset, we finetune a model to generate Longest Supported Subsequence (LSS) Our proposed metric demonstrates an 18% enhancement over the prevailing state-of-the-art metric for faithfulness on our dataset.
  arXiv  Detail & Related papers  (2023-08-23T14:18:44Z)
• Likelihood-Based Text-to-Image Evaluation with Patch-Level Perceptual and Semantic Credit Assignment [48.835298314274254]
  We propose to evaluate text-to-image generation performance by directly estimating the likelihood of the generated images. A higher likelihood indicates better perceptual quality and better text-image alignment. It can successfully assess the generation ability of these models with as few as a hundred samples.
  arXiv  Detail & Related papers  (2023-08-16T17:26:47Z)
• FigCaps-HF: A Figure-to-Caption Generative Framework and Benchmark with Human Feedback [69.4639239117551]
  FigCaps-HF is a new framework for figure-caption generation that incorporates domain expert feedback in generating captions optimized for reader preferences.<n>Our framework comprises of 1) an automatic method for evaluating quality of figure-caption pairs, 2) a novel reinforcement learning with human feedback (RLHF) method to optimize a generative figure-to-caption model for reader preferences.
  arXiv  Detail & Related papers  (2023-07-20T13:40:22Z)
• X-Mesh: Towards Fast and Accurate Text-driven 3D Stylization via Dynamic Textual Guidance [70.08635216710967]
  X-Mesh is a text-driven 3D stylization framework that incorporates a novel Text-guided Dynamic Attention Module. We introduce a new standard text-mesh benchmark, MIT-30, and two automated metrics, which will enable future research to achieve fair and objective comparisons.
  arXiv  Detail & Related papers  (2023-03-28T06:45:31Z)
• Aligning Text-to-Image Models using Human Feedback [104.76638092169604]
  Current text-to-image models often generate images that are inadequately aligned with text prompts. We propose a fine-tuning method for aligning such models using human feedback. Our results demonstrate the potential for learning from human feedback to significantly improve text-to-image models.
  arXiv  Detail & Related papers  (2023-02-23T17:34:53Z)
• TeTIm-Eval: a novel curated evaluation data set for comparing text-to-image models [1.1252184947601962]
  evaluating and comparing text-to-image models is a challenging problem. In this paper a novel evaluation approach is experimented, on the basis of: (i) a curated data set, divided into ten categories; (ii) a quantitative metric, the CLIP-score, (iii) a human evaluation task to distinguish, for a given text, the real and the generated images. Early experimental results show that the accuracy of the human judgement is fully coherent with the CLIP-score.
  arXiv  Detail & Related papers  (2022-12-15T13:52:03Z)
• Transparent Human Evaluation for Image Captioning [70.03979566548823]
  We develop a rubric-based human evaluation protocol for image captioning models. We show that human-generated captions show substantially higher quality than machine-generated ones. We hope that this work will promote a more transparent evaluation protocol for image captioning.
  arXiv  Detail & Related papers  (2021-11-17T07:09:59Z)
• COSMic: A Coherence-Aware Generation Metric for Image Descriptions [27.41088864449921]
  Image metrics have struggled to give accurate learned estimates of the semantic and pragmatic success of text evaluation models. We present the first learned generation metric for evaluating output captions. We demonstrate a higher out-efficient for our proposed metric the human judgments for the results of a number of state-of-the-art caption models when compared to several other metrics such as BLEURT and BERT.
  arXiv  Detail & Related papers  (2021-09-11T13:43:36Z)
• Contrastive Semantic Similarity Learning for Image Captioning Evaluation with Intrinsic Auto-encoder [52.42057181754076]
  Motivated by the auto-encoder mechanism and contrastive representation learning advances, we propose a learning-based metric for image captioning. We develop three progressive model structures to learn the sentence level representations. Experiment results show that our proposed method can align well with the scores generated from other contemporary metrics.
  arXiv  Detail & Related papers  (2021-06-29T12:27:05Z)
• Intrinsic Image Captioning Evaluation [53.51379676690971]
  We propose a learning based metrics for image captioning, which we call Intrinsic Image Captioning Evaluation(I2CE) Experiment results show that our proposed method can keep robust performance and give more flexible scores to candidate captions when encountered with semantic similar expression or less aligned semantics.
  arXiv  Detail & Related papers  (2020-12-14T08:36:05Z)
• Improving Text Generation Evaluation with Batch Centering and Tempered Word Mover Distance [24.49032191669509]
  We present two techniques for improving encoding representations for similarity metrics. We show results over various BERT-backbone learned metrics and achieving state of the art correlation with human ratings on several benchmarks.
  arXiv  Detail & Related papers  (2020-10-13T03:46:25Z)
• Evaluating Text Coherence at Sentence and Paragraph Levels [17.99797111176988]
  We investigate the adaptation of existing sentence ordering methods to a paragraph ordering task. We also compare the learnability and robustness of existing models by artificially creating mini datasets and noisy datasets. We conclude that the recurrent graph neural network-based model is an optimal choice for coherence modeling.
  arXiv  Detail & Related papers  (2020-06-05T03:31:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.