PIV-FlowDiffuser:Transfer-learning-based denoising diffusion models for PIV

• URL: http://arxiv.org/abs/2504.14952v1
• Date: Mon, 21 Apr 2025 08:22:58 GMT
• Title: PIV-FlowDiffuser:Transfer-learning-based denoising diffusion models for PIV
• Authors: Qianyu Zhu, Junjie Wang, Jeremiah Hu, Jia Ai, Yong Lee,
• Abstract summary: In this study, we employ a denoising diffusion model(FlowDiffuser) for PIV analysis.<n>And the data-hungry iterative denoising diffusion model is trained via a transfer learning strategy, resulting in our PIV-FlowDiffuser method.<n>The visualized results indicate that our PIV-FlowDiffuser effectively suppresses the noise patterns.
• Score: 4.174753106884832
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning algorithms have significantly reduced the computational time and improved the spatial resolution of particle image velocimetry~(PIV). However, the models trained on synthetic datasets might have a degraded performance on practical particle images due to domain gaps. As a result, special residual patterns are often observed for the vector fields of deep learning-based estimators. To reduce the special noise step-by-step, we employ a denoising diffusion model~(FlowDiffuser) for PIV analysis. And the data-hungry iterative denoising diffusion model is trained via a transfer learning strategy, resulting in our PIV-FlowDiffuser method. Specifically, (1) pre-training a FlowDiffuser model with multiple optical flow datasets of the computer vision community, such as Sintel, KITTI, etc; (2) fine-tuning the pre-trained model on synthetic PIV datasets. Note that the PIV images are upsampled by a factor of two to resolve the small-scale turbulent flow structures. The visualized results indicate that our PIV-FlowDiffuser effectively suppresses the noise patterns. Therefore, the denoising diffusion model reduces the average end-point error~($AEE$) by 59.4% over RAFT256-PIV baseline on the classic Cai's dataset. Besides, PIV-FlowDiffuser exhibits enhanced generalization performance on unseen particle images due to transfer learning. Overall, this study highlights the transfer-learning-based denoising diffusion models for PIV. And a detailed implementation is recommended for interested readers in the repository https://github.com/Zhu-Qianyu/PIV-FlowDiffuser.

Related papers

• Noise Conditional Variational Score Distillation [60.38982038894823]
  Noise Conditional Variational Score Distillation (NCVSD) is a novel method for distilling pretrained diffusion models into generative denoisers.<n>By integrating this insight into the Variational Score Distillation framework, we enable scalable learning of generative denoisers.
  arXiv  Detail & Related papers  (2025-06-11T06:01:39Z)
• Optimizing for the Shortest Path in Denoising Diffusion Model [8.884907787678731]
  Shortest Path Diffusion Model (ShortDF) treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error.<n>Experiments on multiple standard benchmarks demonstrate that ShortDF significantly reduces diffusion time (or steps)<n>This work, we suppose, paves the way for interactive diffusion-based applications and establishes a foundation for rapid data generation.
  arXiv  Detail & Related papers  (2025-03-05T08:47:36Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training.<n>It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models.<n>While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement [118.83316133601319]
  Current deep learning methods for low-light image enhancement (LLIE) typically rely on pixel-wise mapping learned from paired data. We propose a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process.
  arXiv  Detail & Related papers  (2023-07-27T07:22:51Z)
• Interpreting and Improving Diffusion Models from an Optimization Perspective [4.5993996573872185]
  We use this observation to interpret denoising diffusion models as approximate gradient descent applied to the Euclidean distance function. We propose a new gradient-estimation sampler, generalizing DDIM using insights from our theoretical results.
  arXiv  Detail & Related papers  (2023-06-08T00:56:33Z)
• The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation [42.48819460873482]
  Denoising diffusion probabilistic models have transformed image generation with their impressive fidelity and diversity. We show that they also excel in estimating optical flow and monocular depth, surprisingly, without task-specific architectures and loss functions.
  arXiv  Detail & Related papers  (2023-06-02T21:26:20Z)
• Low-Light Image Enhancement with Wavelet-based Diffusion Models [50.632343822790006]
  Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. We propose a robust and efficient Diffusion-based Low-Light image enhancement approach, dubbed DiffLL.
  arXiv  Detail & Related papers  (2023-06-01T03:08:28Z)
• Reflected Diffusion Models [93.26107023470979]
  We present Reflected Diffusion Models, which reverse a reflected differential equation evolving on the support of the data. Our approach learns the score function through a generalized score matching loss and extends key components of standard diffusion models.
  arXiv  Detail & Related papers  (2023-04-10T17:54:38Z)
• MANet: Improving Video Denoising with a Multi-Alignment Network [72.93429911044903]
  We present a multi-alignment network, which generates multiple flow proposals followed by attention-based averaging. Experiments on a large-scale video dataset demonstrate that our method improves the denoising baseline model by 0.2dB.
  arXiv  Detail & Related papers  (2022-02-20T00:52:07Z)
• DeFlow: Learning Complex Image Degradations from Unpaired Data with Conditional Flows [145.83812019515818]
  We propose DeFlow, a method for learning image degradations from unpaired data. We model the degradation process in the latent space of a shared flow-decoder network. We validate our DeFlow formulation on the task of joint image restoration and super-resolution.
  arXiv  Detail & Related papers  (2021-01-14T18:58:01Z)
• IV-SLAM: Introspective Vision for Simultaneous Localization and Mapping [13.249453757295083]
  IV-SLAM explicitly models the noise process of reprojection errors from visual features to be context-dependent. IV-SLAM guides feature extraction to select more features from parts of the image that are likely to result in lower noise.
  arXiv  Detail & Related papers  (2020-08-06T17:01:39Z)
• Unsupervised Learning of Particle Image Velocimetry [6.69579674554491]
  Deep learning has inspired new approaches to tackle the Particle Image Velocimetry problem. It is difficult to collect reliable ground truth data in large-scale, real-world scenarios. We present here what we believe to be the first work which takes an unsupervised learning based approach to tackle PIV problems.
  arXiv  Detail & Related papers  (2020-07-28T21:08:37Z)

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.