Nonlinear Evolutionary PDE-Based Refinement of Optical Flow

• URL: http://arxiv.org/abs/2102.00487v1
• Date: Sun, 31 Jan 2021 16:35:26 GMT
• Title: Nonlinear Evolutionary PDE-Based Refinement of Optical Flow
• Authors: Hirak Doshi, N. Uday Kiran
• Abstract summary: We show how the model can be adapted suitably for both rigid and fluid motion estimation. We show the results of our algorithm on different datasets.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The goal of this paper is propose a mathematical framework for optical flow refinement with non-quadratic regularization using variational techniques. We demonstrate how the model can be suitably adapted for both rigid and fluid motion estimation. We study the problem as an abstract IVP using an evolutionary PDE approach. We show that for a particular choice of constraint our model approximates the continuity model with non-quadratic regularization using augmented Lagrangian techniques. We subsequently show the results of our algorithm on different datasets.

Related papers

• Total Uncertainty Quantification in Inverse PDE Solutions Obtained with Reduced-Order Deep Learning Surrogate Models [50.90868087591973]
  We propose an approximate Bayesian method for quantifying the total uncertainty in inverse PDE solutions obtained with machine learning surrogate models. We test the proposed framework by comparing it with the iterative ensemble smoother and deep ensembling methods for a non-linear diffusion equation.
  arXiv  Detail & Related papers  (2024-08-20T19:06:02Z)
• On the Trajectory Regularity of ODE-based Diffusion Sampling [79.17334230868693]
  Diffusion-based generative models use differential equations to establish a smooth connection between a complex data distribution and a tractable prior distribution. In this paper, we identify several intriguing trajectory properties in the ODE-based sampling process of diffusion models.
  arXiv  Detail & Related papers  (2024-05-18T15:59:41Z)
• Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models [98.95988351420334]
  We present the first framework to solve linear inverse problems leveraging pre-trained latent diffusion models. We theoretically analyze our algorithm showing provable sample recovery in a linear model setting.
  arXiv  Detail & Related papers  (2023-07-02T17:21:30Z)
• A Geometric Perspective on Diffusion Models [57.27857591493788]
  We inspect the ODE-based sampling of a popular variance-exploding SDE. We establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm.
  arXiv  Detail & Related papers  (2023-05-31T15:33:16Z)
• Counting Phases and Faces Using Bayesian Thermodynamic Integration [77.34726150561087]
  We introduce a new approach to reconstruction of the thermodynamic functions and phase boundaries in two-parametric statistical mechanics systems. We use the proposed approach to accurately reconstruct the partition functions and phase diagrams of the Ising model and the exactly solvable non-equilibrium TASEP.
  arXiv  Detail & Related papers  (2022-05-18T17:11:23Z)
• Score-based Generative Modeling of Graphs via the System of Stochastic Differential Equations [57.15855198512551]
  We propose a novel score-based generative model for graphs with a continuous-time framework. We show that our method is able to generate molecules that lie close to the training distribution yet do not violate the chemical valency rule.
  arXiv  Detail & Related papers  (2022-02-05T08:21:04Z)
• An Operator-Splitting Method for the Gaussian Curvature Regularization Model with Applications in Surface Smoothing and Imaging [6.860238280163609]
  We propose an operator-splitting method for a general Gaussian curvature model. The proposed method is not sensitive to the choice of parameters, its efficiency and performances being demonstrated.
  arXiv  Detail & Related papers  (2021-08-04T08:59:41Z)
• Compositional Modeling of Nonlinear Dynamical Systems with ODE-based Random Features [0.0]
  We present a novel, domain-agnostic approach to tackling this problem. We use compositions of physics-informed random features, derived from ordinary differential equations. We find that our approach achieves comparable performance to a number of other probabilistic models on benchmark regression tasks.
  arXiv  Detail & Related papers  (2021-06-10T17:55:13Z)
• VOLDOR: Visual Odometry from Log-logistic Dense Optical flow Residuals [18.739522634776062]
  We develop a generalized-EM formulation for the joint inference of camera motion, pixel depth, and motion-track confidence. Our method achieved top-ranking results on both TUM RGB-D and KITTI odometry benchmarks. Our open-sourced implementation is inherently GPU-friendly with only linear computational and storage growth.
  arXiv  Detail & Related papers  (2021-04-14T11:39:19Z)
• A Framework for Fluid Motion Estimation using a Constraint-Based Refinement Approach [0.0]
  We formulate a general framework for fluid motion estimation using a constraint-based refinement approach. We demonstrate that for a particular choice of constraint, our results closely approximate the classical continuity equation-based method for fluid flow. We also observe a surprising connection to the Cauchy-Riemann operator that diagonalizes the system leading to a diffusive phenomenon involving the divergence and the curl of the flow.
  arXiv  Detail & Related papers  (2020-11-24T18:23:39Z)
• Spatiotemporal Imaging with Diffeomorphic Optimal Transportation [1.5464123983408111]
  We propose a variational model with diffeomorphic optimal transportation for joint image reconstruction and motion estimation. The proposed model is compared against several existing alternatives theoretically. Several important issues on the proposed model and associated algorithms are also discussed.
  arXiv  Detail & Related papers  (2020-11-24T05:55:25Z)

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.