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

• URL: http://arxiv.org/abs/2604.09853v2
• Date: Tue, 14 Apr 2026 17:35:03 GMT
• Title: Do vision models perceive illusory motion in static images like humans?
• Abstract summary: Deep neural networks (DNNs) achieve strong performance in optical flow estimation, but remain less robust than humans.<n>Visual motion illusions provide a powerful probe into these mechanisms, revealing how human and machine vision align or diverge.<n>We evaluate several representative optical flow models on Rotating Snakes and show that most fail to generate flow fields consistent with human perception.
• Score: 2.1349209400003932
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot Teaming [0.4282159812965447]
  PoseOFF is a pose-anchored optical flow representation that captures local motion information around human joints.<n>By conditioning motion feature extraction on human pose, PoseOFF encodes localised motion dynamics at semantically meaningful body locations.<n>Our results show that PoseOFF enables models to achieve comparable or improved performance while observing less of the action sequence.
  arXiv  Detail & Related papers  (2026-08-26T08:07:19Z)
• Primate vision reveals a missing principle for robust dynamic AI [9.82700229401299]
  We compare human perception and neural activity in macaque inferior temporal cortex with representations from image- and video-based neural networks.<n>We find progressive integration of motion into object representations as a principle of robust dynamic vision.
  arXiv  Detail & Related papers  (2026-08-24T19:38:54Z)
• PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation [75.96085587438279]
  Existing video rewards primarily rely on 2D perceptual signals, without explicitly modeling the 3D body state, contact, and dynamics underlying articulated human motion.<n>We propose PhyMotion, a structured, fine-grained motion reward that grounds recovered 3D human trajectories in a physics simulator and evaluates motion quality along multiple dimensions of physical feasibility.<n>Experiments show that PhyMotion achieves stronger correlation with human judgments than existing reward formulations.
  arXiv  Detail & Related papers  (2026-05-14T02:12:13Z)
• Cortical Policy: A Dual-Stream View Transformer for Robotic Manipulation [57.28703268044067]
  We propose Cortical Policy, a novel dual-stream view transformer for robotic manipulation.<n>Our framework offers a fresh perspective for robotic manipulation and holds potential for broader application in vision-based robot control.
  arXiv  Detail & Related papers  (2026-03-22T04:18:54Z)
• MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction [54.36564144414704]
  MeshMimic is an innovative framework that bridges 3D scene reconstruction and embodied intelligence to enable humanoid robots to learn coupled "motion-terrain" interactions directly from video.<n>By leveraging state-of-the-art 3D vision models, our framework precisely segments and reconstructs both human trajectories and the underlying 3D geometry of terrains and objects.
  arXiv  Detail & Related papers  (2026-02-17T17:09:45Z)
• Machine Learning Modeling for Multi-order Human Visual Motion Processing [5.043066132820344]
  This research aims to develop machines that learn to perceive visual motion as do humans.<n>Our model architecture mimics the cortical V1-MT motion processing pathway.<n>We trained our dual-pathway model on novel motion datasets with varying material properties of moving objects.
  arXiv  Detail & Related papers  (2025-01-22T11:41:41Z)
• Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli [10.978614683038758]
  We evaluate a broad range of optical flow models and a neuroscience inspired motion energy model for zero-shot figure-ground segmentation. We find that a cross section of 40 deep optical flow models trained on different datasets struggle to estimate motion patterns in random dot videos. This neuroscience-inspired model successfully addresses the lack of human-like zero-shot generalization to random dot stimuli in current computer vision models.
  arXiv  Detail & Related papers  (2024-11-03T09:59:45Z)
• Reanimating Images using Neural Representations of Dynamic Stimuli [36.04425924379253]
  BrainNRDS (Brain-Neural Representations of Dynamic Stimuli) advances our understanding of how the brain represents spatial and temporal information in dynamic visual scenes.<n>We utilize fMRI brain activity for a deeper understanding of human responses to dynamic visual stimuli.<n>Our findings demonstrate the potential of combining brain imaging with video diffusion models for developing more robust and biologically-inspired computer vision systems.
  arXiv  Detail & Related papers  (2024-06-04T17:59:49Z)
• Modelling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network [1.9458156037869137]
  We propose an image-computable model of human motion perception by bridging the gap between biological and computer vision models. This model architecture aims to capture the computations in V1-MT, the core structure for motion perception in the biological visual system. In silico neurophysiology reveals that our model's unit responses are similar to mammalian neural recordings regarding motion pooling and speed tuning.
  arXiv  Detail & Related papers  (2023-05-16T04:16:07Z)
• GIMO: Gaze-Informed Human Motion Prediction in Context [75.52839760700833]
  We propose a large-scale human motion dataset that delivers high-quality body pose sequences, scene scans, and ego-centric views with eye gaze. Our data collection is not tied to specific scenes, which further boosts the motion dynamics observed from our subjects. To realize the full potential of gaze, we propose a novel network architecture that enables bidirectional communication between the gaze and motion branches.
  arXiv  Detail & Related papers  (2022-04-20T13:17:39Z)
• Learning Motion-Dependent Appearance for High-Fidelity Rendering of Dynamic Humans from a Single Camera [49.357174195542854]
  A key challenge of learning the dynamics of the appearance lies in the requirement of a prohibitively large amount of observations. We show that our method can generate a temporally coherent video of dynamic humans for unseen body poses and novel views given a single view video.
  arXiv  Detail & Related papers  (2022-03-24T00:22:03Z)
• Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction [63.62263239934777]
  We conduct an indepth study on various pose representations with a focus on their effects on the motion prediction task. We propose a novel RNN architecture termed AHMR (Attentive Hierarchical Motion Recurrent network) for motion prediction. Our approach outperforms the state-of-the-art methods in short-term prediction and achieves much enhanced long-term prediction proficiency.
  arXiv  Detail & Related papers  (2021-12-30T10:45:22Z)
• High-Fidelity Neural Human Motion Transfer from Monocular Video [71.75576402562247]
  Video-based human motion transfer creates video animations of humans following a source motion. We present a new framework which performs high-fidelity and temporally-consistent human motion transfer with natural pose-dependent non-rigid deformations. In the experimental results, we significantly outperform the state-of-the-art in terms of video realism.
  arXiv  Detail & Related papers  (2020-12-20T16:54:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.