MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization

ACM Transactions on Graphics (TOG), 2025

MILO illustration

Uğur Çoğalan1     Mojtaba Bemana1     Karol Myszkowski1     Hans-Peter Seidel1     Colin Groth1    

1 MPI Informatik

Abstract

We present MILO (Metric for Image- and Latent-space Optimization), a lightweight, multiscale, perceptual metric for full-reference image quality assessment (FR-IQA). MILO is trained using pseudo-MOS (Mean Opinion Score) supervision, in which reproducible distortions are applied to diverse images and scored via an ensemble of recent quality metrics that account for visual masking effects. This approach enables accurate learning without requiring large-scale human-labeled datasets. Despite its compact architecture, MILO outperforms existing metrics across standard FR-IQA benchmarks and offers fast inference suitable for real-time applications. Beyond quality prediction, we demonstrate the utility of MILO as a perceptual loss in both image and latent domains. In particular, we show that spatial masking modeled by MILO, when applied to latent representations from a VAE encoder within Stable Diffusion, enables efficient and perceptually aligned optimization. By combining spatial masking with a curriculum learning strategy, we first process perceptually less relevant regions before progressively shifting the optimization to more visually distorted areas. This strategy leads to significantly improved performance in tasks like denoising, super-resolution, and face restoration, while also reducing computational overhead. MILO thus functions as both a state-of-the-art image quality metric and as a practical tool for perceptual optimization in generative pipelines.

Citation and Materials

@article{Cogalan2025MILO,
  author    = {Ugur {\c{C}}o{\u{g}}alan and Mojtaba Bemana and 
			   Karol Myszkowski and Hans-Peter Seidel and Colin Groth},
  title     = {MILO: A Lightweight Perceptual Quality Metric for Image and Latent-Space Optimization},
  journal   = {ACM Transactions on Graphics (TOG)},
  year      = {2025},
  volume    = {44},
  number    = {6},
  publisher = {ACM},
  doi       = {10.1145/3763340}
}
📄 Paper (Full Author's Copy) 📄 Supplementary GitHub View on GitHub

Interactive Quality Comparison

Latent Space Optimization