# Do vision models perceive illusory motion in static images like humans?

arXiv: https://arxiv.org/abs/2604.09853 · HTML: https://mlsanity.com/paper/2604.09853/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 50 references that are in the map.
- First posted on arXiv 10 Apr 2026.

## Builds on (most cited first, 13 of 13)

- [RAFT: Recurrent All-Pairs Field Transforms for Optical Flow](https://mlsanity.com/paper/2003.12039/) (2020)
- [FlowNet: Learning Optical Flow with Convolutional Networks](https://mlsanity.com/paper/1504.06852/) (2015)
- [PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume](https://mlsanity.com/paper/1709.02371/) (2017)
- [Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning](https://mlsanity.com/paper/1605.08104/) (2016)
- [A Lightweight Optical Flow CNN - Revisiting Data Fidelity and Regularization](https://mlsanity.com/paper/1903.07414/) (2019)
- [Attacking Optical Flow](https://mlsanity.com/paper/1910.10053/) (2019)
- [Microsaccade-inspired Event Camera for Robotics](https://mlsanity.com/paper/2405.17769/) (2024)
- [CCMR: High Resolution Optical Flow Estimation via Coarse-to-Fine Context-Guided Motion Reasoning](https://mlsanity.com/paper/2311.02661/) (2023)
- [Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli](https://mlsanity.com/paper/2411.01505/) (2024)
- [Illusions in Humans and AI: How Visual Perception Aligns and Diverges](https://mlsanity.com/paper/2508.12422/) (2025)
- [Motion Illusion-like Patterns Extracted from Photo and Art Images Using Predictive Deep Neural Networks](https://mlsanity.com/paper/2106.12254/) (2021)
- [Motion Estimation for Large Displacements and Deformations](https://mlsanity.com/paper/2206.12464/) (2022)
- [Inconsistent illusory motion in predictive coding deep neural networks](https://mlsanity.com/paper/2301.07455/) (2023)

## Built on by (most cited first, 2 of 2)

- [Now You See the Hate: Adaptive View Retrieval for Hidden Hateful Illusions](https://mlsanity.com/paper/2607.19061/) (2026)
- [FlyHack: Stress-Testing Mechanistic Claims in a Connectome-Constrained Visual Model](https://mlsanity.com/paper/2610.13018/) (2026)

## Abstract (arXiv)

Understanding human motion processing is essential for building reliable, human-centered computer vision systems. Although deep neural networks (DNNs) achieve strong performance in optical flow estimation, they remain less robust than humans and rely on fundamentally different computational strategies. Visual motion illusions provide a powerful probe into these mechanisms, revealing how human and machine vision align or diverge. While recent DNN-based motion models can reproduce dynamic illusions such as reverse-phi, it remains unclear whether they can perceive illusory motion in static images, exemplified by the Rotating Snakes illusion. We evaluate several representative optical flow models on Rotating Snakes and show that most fail to generate flow fields consistent with human perception. Under simulated conditions mimicking saccadic eye movements, only the human-inspired Dual-Channel model exhibits the expected rotational motion, with the closest correspondence emerging during the saccade simulation. Ablation analyses further reveal that both luminance-based and higher-order color--feature--based motion signals contribute to this behavior and that a recurrent attention mechanism is critical for integrating local cues. Our results highlight a substantial gap between current optical-flow models and human visual motion processing, and offer insights for developing future motion-estimation systems with improved correspondence to human perception and human-centric AI.