mlsanityData to 14 Oct 2026

Cost Savings from Automatic Quality Assessment of Generated Images

arXiv 2510.16179 ↗First posted 17 Oct 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep generative models have shown impressive progress in recent years, making it possible to produce high quality images with a simple text prompt or a reference image. However, state of the art technology does not yet meet the quality standards offered by traditional photographic methods. For this reason, production pipelines that use generated images often include a manual stage of image quality assessment (IQA). This process is slow and expensive, especially because of the low yield of automatically generated images that pass the quality bar. The IQA workload can be reduced by introducing an automatic pre-filtering stage, that will increase the overall quality of the images sent to review and, therefore, reduce the average cost required to obtain a high quality image. We present a formula that estimates the cost savings depending on the precision and pass yield of a generic IQA engine. This formula is applied in a use case of background inpainting, showcasing a significant cost saving of 51.61% obtained with a simple AutoML solution.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 39 of its 51 references that are in the map. First posted on arXiv 17 Oct 2025.

Builds on

39 of 51 references.

References · 39

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,503
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2016Improved Techniques for Training GANscited by 2,970
  7. 2023InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuningcited by 2,876
  8. 2015VQA: Visual Question Answeringcited by 2,506
  9. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  10. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,295
  11. 2018Demystifying MMD GANscited by 1,293
  12. 2023ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generationcited by 1,045
27 more
  1. 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,023
  2. 2023Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generationcited by 977
  3. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  4. 2023Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levelscited by 503
  5. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
  6. 2023TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answeringcited by 428
  7. 2023Human Preference Score: Better Aligning Text-to-Image Models with Human Preferencecited by 287
  8. 2024Fast High-Resolution Image Synthesis with Latent Adversarial Diffusion Distillationcited by 279
  9. 2024VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generationcited by 197
  10. 2023Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generationcited by 171
  11. 2023Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Modelscited by 152
  12. 2023What You See is What You Read? Improving Text-Image Alignment Evaluationcited by 108
  13. 2024Learning Multi-dimensional Human Preference for Text-to-Image Generationcited by 106
  14. 2020Transformer for Image Quality Assessmentcited by 76
  15. 2024AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perceptioncited by 65
  16. 2022Personalized Image Aesthetics Assessment with Rich Attributescited by 58
  17. 2021Perceptual Image Quality Assessment with Transformerscited by 54
  18. 2023Towards Artistic Image Aesthetics Assessment: a Large-scale Dataset and a New Methodcited by 49
  19. 2024Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratingscited by 44
  20. 2025The Amazon Nova Family of Models: Technical Report and Model Cardcited by 41
  21. 2024Consistency-diversity-realism Pareto fronts of conditional image generative modelscited by 36
  22. 2024AutoGluon-Multimodal (AutoMM): Supercharging Multimodal AutoML with Foundation Modelscited by 30
  23. 2024Quality Assessment in the Era of Large Models: A Surveycited by 26
  24. 2024A Survey on Quality Metrics for Text-to-Image Generationcited by 18
  25. 2024What makes a good metric? Evaluating automatic metrics for text-to-image consistencycited by 12
  26. 2022MSTRIQ: No Reference Image Quality Assessment Based on Swin Transformer with Multi-Stage Fusioncited by 10
  27. 2024Quality Assured: Rethinking Annotation Strategies in Imaging AIcited by 6

Built on by

Not cited yet.