Oflib: Facilitating Operations with and on Optical Flow Fields in Python

• URL: http://arxiv.org/abs/2210.05635v1
• Date: Tue, 11 Oct 2022 17:28:10 GMT
• Title: Oflib: Facilitating Operations with and on Optical Flow Fields in Python
• Authors: Claudio Ravasio, Lyndon Da Cruz, Christos Bergeles
• Abstract summary: We present a theoretical framework for the characterisation and manipulation of optical flow, i.e. 2D vector fields, in the context of their use in motion estimation algorithms and beyond. This structured approach is then used as the foundation for an implementation in Python 3, with the fully differentiable PyTorch version oflibpytorch supporting back-propagation as required for deep learning. We verify the flow composition method empirically and provide a working example for its application to optical flow ground truth in synthetic training data creation.
• Score: 5.936095386978232
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present a robust theoretical framework for the characterisation and manipulation of optical flow, i.e 2D vector fields, in the context of their use in motion estimation algorithms and beyond. The definition of two frames of reference guides the mathematical derivation of flow field application, inversion, evaluation, and composition operations. This structured approach is then used as the foundation for an implementation in Python 3, with the fully differentiable PyTorch version oflibpytorch supporting back-propagation as required for deep learning. We verify the flow composition method empirically and provide a working example for its application to optical flow ground truth in synthetic training data creation. All code is publicly available.

Related papers

• TDAvec: Computing Vector Summaries of Persistence Diagrams for Topological Data Analysis in R and Python [0.6445605125467574]
  We introduce a new software package designed to streamline the vectorization of persistence diagrams (PDs) The non-Hilbert nature of the space of PDs poses challenges for their direct use in machine learning applications.
  arXiv  Detail & Related papers  (2024-11-26T11:34:12Z)
• PointFlowHop: Green and Interpretable Scene Flow Estimation from Consecutive Point Clouds [49.7285297470392]
  An efficient 3D scene flow estimation method called PointFlowHop is proposed in this work. PointFlowHop takes two consecutive point clouds and determines the 3D flow vectors for every point in the first point cloud. It decomposes the scene flow estimation task into a set of subtasks, including ego-motion compensation, object association and object-wise motion estimation.
  arXiv  Detail & Related papers  (2023-02-27T23:06:01Z)
• Efficient algorithms for implementing incremental proximal-point methods [0.3263412255491401]
  In machine learning, model training algorithms observe a small portion of the training set in each computational step. Several streams of research attempt to exploit more information about the cost functions than just their gradients via the well-known proximal operators. We devise a novel algorithmic framework, which exploits convex duality theory to achieve both algorithmic efficiency and software modularity of proximal operator.
  arXiv  Detail & Related papers  (2022-05-03T12:43:26Z)
• pygrank: A Python Package for Graph Node Ranking [13.492381728793612]
  We introduce pygrank, an open source Python package to define, run and evaluate node ranking algorithms. We provide object-oriented and extensively unit-tested algorithm components, such as graph filters, post-processors, measures, benchmarks and online tuning.
  arXiv  Detail & Related papers  (2021-10-18T13:13:21Z)
• FlowStep3D: Model Unrolling for Self-Supervised Scene Flow Estimation [87.74617110803189]
  Estimating the 3D motion of points in a scene, known as scene flow, is a core problem in computer vision. We present a recurrent architecture that learns a single step of an unrolled iterative alignment procedure for refining scene flow predictions.
  arXiv  Detail & Related papers  (2020-11-19T23:23:48Z)
• Deep Learning Framework From Scratch Using Numpy [0.0]
  This work is a rigorous development of a complete and general-purpose deep learning framework from the ground up. The fundamental components of deep learning are developed from elementary calculus and implemented in a sensible object-oriented approach using only Python and the Numpy library. Demonstrations of solved problems using the framework, named ArrayFlow, include a computer vision classification task, solving for the shape of a catenary, and a 2nd order differential equation.
  arXiv  Detail & Related papers  (2020-11-17T06:28:05Z)
• Self Normalizing Flows [65.73510214694987]
  We propose a flexible framework for training normalizing flows by replacing expensive terms in the gradient by learned approximate inverses at each layer. This reduces the computational complexity of each layer's exact update from $mathcalO(D3)$ to $mathcalO(D2)$. We show experimentally that such models are remarkably stable and optimize to similar data likelihood values as their exact gradient counterparts.
  arXiv  Detail & Related papers  (2020-11-14T09:51:51Z)
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport [52.646396621449]
  We propose a novel unsupervised learning approach to 3D shape correspondence. We show that the proposed method significantly improves over the state-of-the-art on multiple datasets.
  arXiv  Detail & Related papers  (2020-10-28T22:24:07Z)
• LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation [99.19322851246972]
  We introduce LiteFlowNet3, a deep network consisting of two specialized modules to address the problem of optical flow estimation. LiteFlowNet3 not only achieves promising results on public benchmarks but also has a small model size and a fast runtime.
  arXiv  Detail & Related papers  (2020-07-18T03:30:39Z)
• stream-learn -- open-source Python library for difficult data stream batch analysis [0.0]
  stream-learn is compatible with scikit-learn and developed for the drifting and imbalanced data stream analysis. Main component is a stream generator, which allows to produce a synthetic data stream. In addition, estimators adapted for data stream classification have been implemented.
  arXiv  Detail & Related papers  (2020-01-29T20:15:09Z)
• OPFython: A Python-Inspired Optimum-Path Forest Classifier [68.8204255655161]
  This paper proposes a Python-based Optimum-Path Forest framework, denoted as OPFython. As OPFython is a Python-based library, it provides a more friendly environment and a faster prototyping workspace than the C language.
  arXiv  Detail & Related papers  (2020-01-28T15:46:19Z)

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.