# The Art of Deception: Color Visual Illusions and Diffusion Models arXiv: https://arxiv.org/abs/2412.10122 ยท HTML: https://mlsanity.com/paper/2412.10122/ ## Key facts - Cited by 9 papers in the map (data through 14 Oct 2026). - Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. - Builds on 30 of its 73 references that are in the map. - First posted on arXiv 13 Dec 2024. ## Placed in - Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/) ## Builds on (most cited first, 30 of 30) - [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021) - [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020) - [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022) - [Variational Inference with Normalizing Flows](https://mlsanity.com/paper/1505.05770/) (2015) - [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021) - [Null-text Inversion for Editing Real Images using Guided Diffusion Models](https://mlsanity.com/paper/2211.09794/) (2022) - [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023) - [HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models](https://mlsanity.com/paper/2310.14566/) (2023) - [DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models](https://mlsanity.com/paper/2210.14896/) (2022) - [Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment](https://mlsanity.com/paper/2306.08877/) (2023) - [Diffusion-based Image Translation using Disentangled Style and Content Representation](https://mlsanity.com/paper/2209.15264/) (2022) - [Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing](https://mlsanity.com/paper/2309.15664/) (2023) - [StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing](https://mlsanity.com/paper/2303.15649/) (2023) - [Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models](https://mlsanity.com/paper/2311.17919/) (2023) - [TokenCompose: Text-to-Image Diffusion with Token-level Supervision](https://mlsanity.com/paper/2312.03626/) (2023) - [Interpolating between Images with Diffusion Models](https://mlsanity.com/paper/2307.12560/) (2023) - [Does enhanced shape bias improve neural network robustness to common corruptions?](https://mlsanity.com/paper/2104.09789/) (2021) - [Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?](https://mlsanity.com/paper/2311.00047/) (2023) - [IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models](https://mlsanity.com/paper/2403.15952/) (2024) - [Enhancing Semantic Fidelity in Text-to-Image Synthesis: Attention Regulation in Diffusion Models](https://mlsanity.com/paper/2403.06381/) (2024) - [Iterative Gaussianization: from ICA to Random Rotations](https://mlsanity.com/paper/1602.00229/) (2016) - [Diffusion Illusions: Hiding Images in Plain Sight](https://mlsanity.com/paper/2312.03817/) (2023) - [Factorized Diffusion: Perceptual Illusions by Noise Decomposition](https://mlsanity.com/paper/2404.11615/) (2024) - [Contrast Sensitivity Functions in Autoencoders](https://mlsanity.com/paper/2103.00481/) (2021) - [Nonlinearities and Adaptation of Color Vision from Sequential Principal Curves Analysis](https://mlsanity.com/paper/1602.00236/) (2016) - [IterInv: Iterative Inversion for Pixel-Level T2I Models](https://mlsanity.com/paper/2310.19540/) (2023) - [Neural Networks Trained on Natural Scenes Exhibit Gestalt Closure](https://mlsanity.com/paper/1903.01069/) (2019) - [Optical Illusions Images Dataset](https://mlsanity.com/paper/1810.00415/) (2018) - [BRI3L: A Brightness Illusion Image Dataset for Identification and Localization of Regions of Illusory Perception](https://mlsanity.com/paper/2402.04541/) (2024) - [Investigating Color Illusions from the Perspective of Computational Color Constancy](https://mlsanity.com/paper/2312.13114/) (2023) ## Built on by (most cited first, 9 of 9) - [Anchor Token Matching: Implicit Structure Locking for Training-free AR Image Editing](https://mlsanity.com/paper/2504.10434/) (2025) - [Seeing Is Believing? A Benchmark for Multimodal Large Language Models on Visual Illusions and Anomalies](https://mlsanity.com/paper/2602.01816/) (2026) - [Leveraging Semantic Attribute Binding for Free-Lunch Color Control in Diffusion Models](https://mlsanity.com/paper/2503.09864/) (2025) - [Color encoding in Latent Space of Stable Diffusion Models](https://mlsanity.com/paper/2512.09477/) (2025) - [Contrast Sensitivity in Multimodal Large Language Models: A Psychophysics-Inspired Evaluation](https://mlsanity.com/paper/2508.10367/) (2025) - [Do Vision Encoders Exhibit Human-like Color Thresholds?](https://mlsanity.com/paper/2607.16540/) (2026) - [Style-Aware Gloss Control for Generative Non-Photorealistic Rendering](https://mlsanity.com/paper/2602.16611/) (2026) - [Denoising Models Develop Human-Like Perceptual Illusion Representations Across Architectures](https://mlsanity.com/paper/2607.17138/) (2026) - [(How) Do MLLMs Report Bistable Images Like Humans?](https://mlsanity.com/paper/2609.13254/) (2026) ## Abstract (arXiv) Visual illusions in humans arise when interpreting out-of-distribution stimuli: if the observer is adapted to certain statistics, perception of outliers deviates from reality. Recent studies have shown that artificial neural networks (ANNs) can also be deceived by visual illusions. This revelation raises profound questions about the nature of visual information. Why are two independent systems, both human brains and ANNs, susceptible to the same illusions? Should any ANN be capable of perceiving visual illusions? Are these perceptions a feature or a flaw? In this work, we study how visual illusions are encoded in diffusion models. Remarkably, we show that they present human-like brightness/color shifts in their latent space. We use this fact to demonstrate that diffusion models can predict visual illusions. Furthermore, we also show how to generate new unseen visual illusions in realistic images using text-to-image diffusion models. We validate this ability through psychophysical experiments that show how our model-generated illusions also fool humans.