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

arXiv: https://arxiv.org/abs/2509.01411 · HTML: https://mlsanity.com/paper/2509.01411/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 57 references that are in the map.
- First posted on arXiv 1 Sep 2025.

## Builds on (most cited first, 25 of 25)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [Image Super-Resolution via Iterative Refinement](https://mlsanity.com/paper/2104.07636/) (2021)
- [Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising](https://mlsanity.com/paper/1608.03981/) (2016)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Exploring CLIP for Assessing the Look and Feel of Images](https://mlsanity.com/paper/2207.12396/) (2022)
- [Image Quality Assessment: Unifying Structure and Texture Similarity](https://mlsanity.com/paper/2004.07728/) (2020)
- [Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring](https://mlsanity.com/paper/1612.02177/) (2016)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior](https://mlsanity.com/paper/2308.15070/) (2023)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models](https://mlsanity.com/paper/2308.06160/) (2023)
- [Locally Adaptive Structure and Texture Similarity for Image Quality Assessment](https://mlsanity.com/paper/2110.08521/) (2021)
- [DeepWSD: Projecting Degradations in Perceptual Space to Wasserstein Distance in Deep Feature Space](https://mlsanity.com/paper/2208.03323/) (2022)
- [PromptIQA: Boosting the Performance and Generalization for No-Reference Image Quality Assessment via Prompts](https://mlsanity.com/paper/2403.04993/) (2024)
- [Deep Ensembling for Perceptual Image Quality Assessment](https://mlsanity.com/paper/2305.09141/) (2023)
- [IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond](https://mlsanity.com/paper/2503.09294/) (2025)
- [Wavelet-Based Fast Decoding of 360-Degree Videos](https://mlsanity.com/paper/2208.10859/) (2022)
- [Enhancing image quality prediction with self-supervised visual masking](https://mlsanity.com/paper/2305.19858/) (2023)
- [DSMix: Distortion-Induced Sensitivity Map Based Pre-training for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2407.03886/) (2024)

## Built on by (most cited first, 3 of 3)

- [MSDS: Deep Structural Similarity with Multiscale Representation](https://mlsanity.com/paper/2604.19159/) (2026)
- [Compact Neural Appearance Models for Efficient Gaussian Splatting](https://mlsanity.com/paper/2609.05255/) (2026)
- [Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment](https://mlsanity.com/paper/2609.38487/) (2026)

## Abstract (arXiv)

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.