Variational Rectified Flow Matching

• URL: http://arxiv.org/abs/2502.09616v1
• Date: Thu, 13 Feb 2025 18:59:15 GMT
• Title: Variational Rectified Flow Matching
• Authors: Pengsheng Guo, Alexander G. Schwing,
• Abstract summary: Variational Rectified Flow Matching enhances classic rectified flow matching by modeling multi-modal velocity vector-fields.<n>We show on synthetic data that variational rectified flow matching leads to compelling results.
• Score: 100.63726791602049
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study Variational Rectified Flow Matching, a framework that enhances classic rectified flow matching by modeling multi-modal velocity vector-fields. At inference time, classic rectified flow matching 'moves' samples from a source distribution to the target distribution by solving an ordinary differential equation via integration along a velocity vector-field. At training time, the velocity vector-field is learnt by linearly interpolating between coupled samples one drawn from the source and one drawn from the target distribution randomly. This leads to ''ground-truth'' velocity vector-fields that point in different directions at the same location, i.e., the velocity vector-fields are multi-modal/ambiguous. However, since training uses a standard mean-squared-error loss, the learnt velocity vector-field averages ''ground-truth'' directions and isn't multi-modal. In contrast, variational rectified flow matching learns and samples from multi-modal flow directions. We show on synthetic data, MNIST, CIFAR-10, and ImageNet that variational rectified flow matching leads to compelling results.

Related papers

• Bezier Distillation [5.432285843497807]
  In Rectified Flow, by obtaining the rectified flow several times, the mapping relationship between distributions can be distilled into a neural network. I intend to combine multi - teacher knowledge distillation with Bezier curves to solve the problem of error accumulation.
  arXiv  Detail & Related papers  (2025-03-20T06:48:35Z)
• FlowDPS: Flow-Driven Posterior Sampling for Inverse Problems [51.99765487172328]
  Posterior sampling for inverse problem solving can be effectively achieved using flows. Flow-Driven Posterior Sampling (FlowDPS) outperforms state-of-the-art alternatives.
  arXiv  Detail & Related papers  (2025-03-11T07:56:14Z)
• Towards Hierarchical Rectified Flow [18.976435451156824]
  We formulate a hierarchical rectified flow to model data distributions. We empirically defines a time-differentiable process that generates a data distribution from a known source distribution. We verify this on synthetic 1D and 2D data as well as MNIST, CIFAR-10, and ImageNet-32 data.
  arXiv  Detail & Related papers  (2025-02-24T18:59:55Z)
• Flow Matching: Markov Kernels, Stochastic Processes and Transport Plans [1.9766522384767222]
  Flow matching techniques can be used to solve inverse problems.<n>We show how flow matching can be used for solving inverse problems.<n>We briefly address continuous normalizing flows and score matching techniques.
  arXiv  Detail & Related papers  (2025-01-28T10:28:17Z)
• Rectified Diffusion: Straightness Is Not Your Need in Rectified Flow [65.51671121528858]
  Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation speed by straightening the ODE path. We propose Rectified Diffusion, which generalizes the design space and application scope of rectification to encompass the broader category of diffusion models.
  arXiv  Detail & Related papers  (2024-10-09T17:43:38Z)
• Unsupervised Representation Learning from Sparse Transformation Analysis [79.94858534887801]
  We propose to learn representations from sequence data by factorizing the transformations of the latent variables into sparse components. Input data are first encoded as distributions of latent activations and subsequently transformed using a probability flow model.
  arXiv  Detail & Related papers  (2024-10-07T23:53:25Z)
• Consistency Flow Matching: Defining Straight Flows with Velocity Consistency [97.28511135503176]
  We introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Preliminary experiments demonstrate that our Consistency-FM significantly improves training efficiency by converging 4.4x faster than consistency models.
  arXiv  Detail & Related papers  (2024-07-02T16:15:37Z)
• 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)
• Building Normalizing Flows with Stochastic Interpolants [11.22149158986164]
  A simple generative quadratic model based on a continuous-time normalizing flow between any pair of base and target distributions is proposed. The velocity field of this flow is inferred from the probability current of a time-dependent distribution that interpolates between the base and the target in finite time.
  arXiv  Detail & Related papers  (2022-09-30T16:30:31Z)

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.