# Understanding SSIM

arXiv: https://arxiv.org/abs/2006.13846 · HTML: https://mlsanity.com/paper/2006.13846/

## Key facts

- Cited by 77 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Jun 2020.

## Built on by (most cited first, 30 of 77)

- [Multiscale Structure Guided Diffusion for Image Deblurring](https://mlsanity.com/paper/2212.01789/) (2022)
- [Neural Strands: Learning Hair Geometry and Appearance from Multi-View Images](https://mlsanity.com/paper/2207.14067/) (2022)
- [SlideCoder: Layout-aware RAG-enhanced Hierarchical Slide Generation from Design](https://mlsanity.com/paper/2506.07964/) (2025)
- [Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations](https://mlsanity.com/paper/2211.12486/) (2022)
- [Deciphering Oracle Bone Language with Diffusion Models](https://mlsanity.com/paper/2406.00684/) (2024)
- [An Optimal Transport Perspective on Unpaired Image Super-Resolution](https://mlsanity.com/paper/2202.01116/) (2022)
- [Q-space Conditioned Translation Networks for Directional Synthesis of Diffusion Weighted Images from Multi-modal Structural MRI](https://mlsanity.com/paper/2106.13188/) (2021)
- [DSSIM: a structural similarity index for floating-point data](https://mlsanity.com/paper/2202.02616/) (2022)
- [Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape](https://mlsanity.com/paper/2505.22918/) (2025)
- [Deep Perceptual Image Quality Assessment for Compression](https://mlsanity.com/paper/2103.01114/) (2021)
- [Sanity Checks Revisited: An Exploration to Repair the Model Parameter Randomisation Test](https://mlsanity.com/paper/2401.06465/) (2024)
- [Attention-Based Generative Neural Image Compression on Solar Dynamics Observatory](https://mlsanity.com/paper/2210.06478/) (2022)
- [A Fresh Look at Sanity Checks for Saliency Maps](https://mlsanity.com/paper/2405.02383/) (2024)
- [Augmenting Perceptual Super-Resolution via Image Quality Predictors](https://mlsanity.com/paper/2504.18524/) (2025)
- [Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution](https://mlsanity.com/paper/2103.02940/) (2021)
- [ClusIR: Towards Cluster-Guided All-in-One Image Restoration](https://mlsanity.com/paper/2512.10948/) (2025)
- [When Visible-to-Thermal Facial GAN Beats Conditional Diffusion](https://mlsanity.com/paper/2302.09395/) (2023)
- [Evaluation in Neural Style Transfer: A Review](https://mlsanity.com/paper/2401.17109/) (2024)
- [Reflections Unlock: Geometry-Aware Reflection Disentanglement in 3D Gaussian Splatting for Photorealistic Scenes Rendering](https://mlsanity.com/paper/2507.06103/) (2025)
- [Hessian-Free Second-Order Adversarial Examples for Adversarial Learning](https://mlsanity.com/paper/2207.01396/) (2022)
- [Video super-resolution for single-photon LIDAR](https://mlsanity.com/paper/2210.10474/) (2022)
- [FCR: Investigating Generative AI models for Forensic Craniofacial Reconstruction](https://mlsanity.com/paper/2508.18031/) (2025)
- [Confidence-Based Mesh Extraction from 3D Gaussians](https://mlsanity.com/paper/2603.24725/) (2026)
- [FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views](https://mlsanity.com/paper/2604.09862/) (2026)
- [Image-to-Video Diffusion: From Foundations to Open Frontiers](https://mlsanity.com/paper/2605.17248/) (2026)
- [Automatic Testing and Validation of Level of Detail Reductions Through Supervised Learning](https://mlsanity.com/paper/2208.12674/) (2022)
- [Continual learning autoencoder training for a particle-in-cell simulation via streaming](https://mlsanity.com/paper/2211.04770/) (2022)
- [A Practical Framework for Unsupervised Structure Preservation Medical Image Enhancement](https://mlsanity.com/paper/2304.01864/) (2023)
- [Convolutional variational autoencoders for secure lossy image compression in remote sensing](https://mlsanity.com/paper/2404.03696/) (2024)
- [Competitive Learning for Achieving Content-specific Filters in Video Coding for Machines](https://mlsanity.com/paper/2406.12367/) (2024)

## Abstract (arXiv)

The use of the structural similarity index (SSIM) is widespread. For almost two decades, it has played a major role in image quality assessment in many different research disciplines. Clearly, its merits are indisputable in the research community. However, little deep scrutiny of this index has been performed. Contrary to popular belief, there are some interesting properties of SSIM that merit such scrutiny. In this paper, we analyze the mathematical factors of SSIM and show that it can generate results, in both synthetic and realistic use cases, that are unexpected, sometimes undefined, and nonintuitive. As a consequence, assessing image quality based on SSIM can lead to incorrect conclusions and using SSIM as a loss function for deep learning can guide neural network training in the wrong direction.