Guiding Vector Field Generation via Score-based Diffusion Model

• URL: http://arxiv.org/abs/2604.24487v1
• Date: Mon, 27 Apr 2026 13:55:42 GMT
• Title: Guiding Vector Field Generation via Score-based Diffusion Model
• Abstract summary: We propose a unified framework, termed the Score-Induced Guiding Vector Field (SGVF)<n>We learn vector fields from point clouds with unit-normity, directional-consistency losses, and geometric fidelity.<n>This approach removes the reliance on ad-hoc path segmentation and enables guidance along complex topologies such as branching and pseudo-manifolds.
• Score: 14.390715666696174
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Guiding Vector Fields (GVFs) are a powerful tool for robotic path following. However, classical methods assume smooth, ordered curves and fail when paths are unordered, multi-branch, or generated by probabilistic models. We propose a unified framework, termed the Score-Induced Guiding Vector Field (SGVF), which leverages score-based generative modeling to construct vector fields directly from data distributions. SGVF learns tangent fields from point clouds with unit-norm, orthogonality, and directional-consistency losses, ensuring geometric fidelity and control feasibility. This approach removes the reliance on ad-hoc path segmentation and enables guidance along complex topologies such as branching and pseudo-manifolds. The study establishes a correspondence between score vanishing in diffusion models and GVF singularities and highlights representational capacity near sharp path curvatures. Experiments on robotic navigation in planar environments demonstrate that SGVF achieves reliable path following in scenarios where classical GVFs fail, underscoring its potential as a bridge between generative modeling and geometric control. Code and experiment video are available at https://github.com/czr-gif/Guiding-Vector-Field-Generation-via-Score-based-Diffusion-Model.

Related papers

• Parameter-Efficient Generative Modeling with Controlled Vector Fields [1.370633147306388]
  We introduce a continuous-time generative modeling framework that builds expressive flows from a small set of fixed vector fields.<n>We train the resulting model using a continuous-normalizing-flow likelihood objective and present proof-of-concept experiments on synthetic distributions.
  arXiv  Detail & Related papers  (2026-05-27T10:14:29Z)
• Inverting Self-Organizing Maps: A Unified Activation-Based Framework [39.146761527401424]
  We show that the activation pattern of a SOM can be inverted to recover the exact input under mild geometric conditions.<n>We introduce the Manifold-Aware Unified SOM Inversion and Control (MUSIC) update rule.<n>We validate the approach using synthetic Gaussian mixtures, the MNIST and the Faces in the Wild dataset.
  arXiv  Detail & Related papers  (2026-01-20T11:02:54Z)
• Source-Guided Flow Matching [7.888172595458005]
  We propose the Source-Guided Flow Matching framework.<n>It modifies the source distribution directly while keeping the pre-trained vector field intact.<n>This reduces the guidance problem to a well-defined problem of sampling from the source distribution.
  arXiv  Detail & Related papers  (2025-08-20T15:56:25Z)
• Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching [59.97254029720877]
  Flow Matching (FM) is an effective framework for training a model to learn a vector field that transports samples from a source distribution to a target distribution.<n>We propose Model- Coupling Coupling (MAC), an effective method that matches training couplings based on geometric distance.<n>Experiments show that MAC significantly improves generation quality and efficiency in few-step settings compared to existing methods.
  arXiv  Detail & Related papers  (2025-05-29T11:10:41Z)
• Topology Guidance: Controlling the Outputs of Generative Models via Vector Field Topology [25.30645421862573]
  We propose a method for guiding the sampling process of a generative model, specifically a diffusion model.<n>We show how to use topologically-relevant signals provided by the coordinate-based network to help guide the denoising process of a diffusion model.
  arXiv  Detail & Related papers  (2025-05-11T01:02:01Z)
• Visual Generation Without Guidance [54.556375372833685]
  We propose to build visual models that are free from sampling guided.<n>The resulting algorithm, Guidance-Free Training (GFT), matches the performance of CFG while reducing sampling to a single model, halving the cost.
  arXiv  Detail & Related papers  (2025-01-26T06:48:05Z)
• TFG-Flow: Training-free Guidance in Multimodal Generative Flow [73.93071065307782]
  We introduce TFG-Flow, a training-free guidance method for multimodal generative flow.<n>TFG-Flow addresses the curse-of-dimensionality while maintaining the property of unbiased sampling in guiding discrete variables.<n>We show that TFG-Flow has great potential in drug design by generating molecules with desired properties.
  arXiv  Detail & Related papers  (2025-01-24T03:44:16Z)
• A Geometry-Aware Message Passing Neural Network for Modeling Aerodynamics over Airfoils [61.60175086194333]
  aerodynamics is a key problem in aerospace engineering, often involving flows interacting with solid objects such as airfoils.<n>Here, we consider modeling of incompressible flows over solid objects, wherein geometric structures are a key factor in determining aerodynamics.<n>To effectively incorporate geometries, we propose a message passing scheme that efficiently and expressively integrates the airfoil shape with the mesh representation.<n>These design choices lead to a purely data-driven machine learning framework known as GeoMPNN, which won the Best Student Submission award at the NeurIPS 2024 ML4CFD Competition, placing 4th overall.
  arXiv  Detail & Related papers  (2024-12-12T16:05:39Z)
• MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction [72.70572835589158]
  We propose constructing a mixed Gaussian prior for a normalizing flow model for trajectory prediction.<n>Our method achieves state-of-the-art performance in the evaluation of both trajectory alignment and diversity on the popular UCY/ETH and SDD datasets.
  arXiv  Detail & Related papers  (2024-02-19T15:48:55Z)
• Bayesian Structure Learning with Generative Flow Networks [85.84396514570373]
  In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) from data. Recently, a class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling. We show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs.
  arXiv  Detail & Related papers  (2022-02-28T15:53:10Z)
• Generation Drawing/Grinding Trajectoy Based on Hierarchical CVAE [4.817429789586127]
  We propose a method to model the local and global features of the drawing/grinding trajectory with hierarchical Variational Autoencoders (VAEs) The hierarchical generation network enables the generation of higher-order trajectories with a relatively small amount of training data. It is possible to generate new trajectories, which have never been learned in the past, by changing the combination of the learned models.
  arXiv  Detail & Related papers  (2021-11-22T02:40:06Z)
• Haar Wavelet based Block Autoregressive Flows for Trajectories [129.37479472754083]
  Prediction of trajectories such as that of pedestrians is crucial to the performance of autonomous agents. We introduce a novel Haar wavelet based block autoregressive model leveraging split couplings. We illustrate the advantages of our approach for generating diverse and accurate trajectories on two real-world datasets.
  arXiv  Detail & Related papers  (2020-09-21T13:57:10Z)

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.