Diffusion models for eye-gaze trajectory generation using position and velocity representations

• URL: http://arxiv.org/abs/2609.05522v1
• Date: Tue, 01 Sep 2026 07:53:11 GMT
• Title: Diffusion models for eye-gaze trajectory generation using position and velocity representations
• Abstract summary: Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of privacy constraints.<n>We address this using two complementary denoising diffusion probabilistic models (DDPMs) for unconditional generation of eye-gaze dynamics from visual-search data.
• Score: 39.577682622066256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share because of privacy constraints. We address this using two complementary denoising diffusion probabilistic models (DDPMs) for unconditional generation of eye-gaze dynamics from visual-search data. Both use an identical FiLM-conditioned one-dimensional U-Net with self-attention (19.35,M parameters), trained on 8,s sliding-window sequences from 28 participants. One model generates raw two-dimensional gaze-position sequences, while the other generates two-component velocity sequences; each uses representation-specific preprocessing, training settings, data partitions, and evaluation protocols. Both are evaluated across three independent training seeds, with aggregated metrics reported as mean,$\pm$,SD. The position-space model achieves a mean Jensen-Shannon (JS) divergence of $0.016\pm0.004$ across nine kinematic features, with the highest feature-wise mean below $0.030$, fixation duration within 2% of real data, and a Fr'echet Gaze Distance more than an order of magnitude below statistical and Markovian baselines. Under a Train-on-Synthetic-Test-on-Real protocol, synthetic-only training achieves $R^2=0.66\pm0.02$, or 82.7% of the real-data $R^2$ point estimate. The velocity-space model achieves a mean JS divergence of $0.0065$ across velocity components, speed, log-speed, and turning angle, with a maximum of $0.015\pm0.005$. Reconstructed path length is less accurate ($0.21\pm0.02$ versus $0.03\pm0.01$ in position space), although the protocols differ. Overall, unconditional diffusion captures local gaze kinematics and short-range temporal and directional structure, while long-range properties such as saccade counts and cumulative path geometry remain targets for future conditioned models.

Related papers

• Inductive Biases in Field-Level Cosmological Inference from Galaxy Catalogs [0.0]
  We perform field-level likelihood-free inference of the matter density parameter $_m$ from simulated galaxy catalogs.<n>We consider galaxy positions and line-of-sight peculiar velocities, separately and jointly, and compare permutation-invariant Deep Sets and graph neural networks.
  arXiv  Detail & Related papers  (2026-09-08T22:38:38Z)
• Event-Based Motion Estimation via Oriented Distance Fields [55.23416502666468]
  Event-based motion estimation is central to tasks that demand high temporal resolution and robustness to fast motion.<n>We propose Oriented Distance Field Motion Estimation (ODF Motion Estimation), which replaces this optimization with a single averaging step over a precomputed field of event distance vectors.<n>On public and self-collected datasets, ODF motion estimation reaches sub-pixel accuracy at the lowest latency among compared methods.
  arXiv  Detail & Related papers  (2026-08-25T08:27:42Z)
• Interpretable Fuzzy Inference for UAV Target Tracking Using Bounding-Box Geometry [0.528933036850801]
  We present an interpretable fuzzy-inference framework that generates continuous yaw commands from low-dimensional features extracted from YOLO boxes.<n>Results show that the framework is transparent, data-efficient, computationally lightweight, and suitable for real-time vision-based UAV guidance toward mobile ground targets.
  arXiv  Detail & Related papers  (2026-08-04T18:18:29Z)
• Inferring Missing Trajectory Data with Temporal Convolutional Networks [0.0]
  We propose a Temporal Convolutional Network (TCN) with symmetric dilation that relaxes the standard causality constraint.<n>The model is trained with a composite loss that combines weighted mean squared error, boundary--continuity penalties, and a smoothness regularizer.<n>Trained on a synthetic dataset of $1,000$ (train), $200$ (validation), and $300$ (test) two-dimensional trajectories with randomly placed 20% masked segments, the model achieves good R$2$, MSE and MAE metrics.
  arXiv  Detail & Related papers  (2026-07-27T23:46:15Z)
• From Distances to Trajectories: Real-Time Signed Distance Function Mapping and Distance-Accelerated Motion Planning for UAVs [8.393016378205752]
  We argue that mapping and planning should be co-designed around a single representation: a signed distance function (SDF)<n>In tandem, we develop Bubble$star$, a search-based planner that exploits the distance information to grow maximal collision-free balls.<n>We demonstrate the integrated OREN-Bubble$star$ approach onboard a quadrotor, navigating unseen indoor environments in real time under tight compute constraints.
  arXiv  Detail & Related papers  (2026-07-21T17:18:46Z)
• Three-Body Scattering for Generative Modeling [17.851305398372794]
  We show that a proper distributional energy can induce sample-level motion and provide direct regression supervision for a one-step generator.<n>Three-Body Scattering Modeling for generation turns the energy distance into a constant-size per-projectile interaction.<n>We provide a design map relating diffusion-related supervision, Drift-like dynamics, and GAN-like objectives.
  arXiv  Detail & Related papers  (2026-07-20T17:38:12Z)
• EventShiftFlow: Towards Hardware-efficient FPGA-based Flow Estimation [43.77587889970362]
  Event-based vision sensors offer asynchronous, high-temporal-resolution measurements.<n>Many event-based motion estimation methods are computationally intensive and difficult to map to FPGA hardware.<n>We present a streaming velocity estimator that discretizes asynchronous events into fixed-duration time bins, constructs a 1-bit spatial occupancy grid, and evaluates multiple velocity hypotheses in parallel.
  arXiv  Detail & Related papers  (2026-05-27T11:13:58Z)
• Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization [58.14514930760722]
  We consider a decentralized setup in which the participants collaboratively train and serve a large neural network.<n>In this setup, we explore the possibility of unmaterializable weights, where a full weight set is never available to any one participant.<n>We introduce Unextractable Protocol Models (UPMs): a training and inference framework that leverages the sharded model setup.
  arXiv  Detail & Related papers  (2026-05-22T10:24:57Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)
• MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video [75.23812405203778]
  Recent solutions have been introduced to estimate 3D human pose from 2D keypoint sequence by considering body joints among all frames globally to learn-temporal correlation. We propose Mix Mix, which has temporal transformer block to separately model the temporal motion of each joint and a transformer block inter-joint spatial correlation. In addition, the network output is extended from the central frame to entire frames of input video, improving the coherence between the input and output benchmarks.
  arXiv  Detail & Related papers  (2022-03-02T04:20:59Z)
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining [58.10436813430554]
  Mini-batch training of graph neural networks (GNNs) requires a lot of computation and data movement. We argue in favor of performing mini-batch training with neighborhood sampling in a distributed multi-GPU environment. We present a sequence of improvements to mitigate these bottlenecks, including a performance-engineered neighborhood sampler. We also conduct an empirical analysis that supports the use of sampling for inference, showing that test accuracies are not materially compromised.
  arXiv  Detail & Related papers  (2021-10-16T02:41:35Z)

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.