Results 11 to 20 of about 16,807,593 (396)
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow [PDF]
International Conference on Learning Representations, 2022 We present rectified flow, a surprisingly simple approach to learning (neural) ordinary differential equation (ODE) models to transport between two empirically observed distributions \pi_0 and \pi_1, hence providing a unified solution to generative ...
Xingchao Liu, Chengyue Gong, Qiang Liu
semanticscholar +1 more source
FlowNet: Learning Optical Flow with Convolutional Networks [PDF]
IEEE International Conference on Computer Vision, 2015 Convolutional neural networks (CNNs) have recently been very successful in a variety of computer vision tasks, especially on those linked to recognition. Optical flow estimation has not been among the tasks CNNs succeeded at.
Alexey Dosovitskiy +8 more
semanticscholar +1 more source
Resolvent analysis of a finite wing in transonic flow
Flow, 2023 Shock waves interacting with turbulent boundary layers on wings can result first in self-sustained flow unsteadiness and eventually in structural vibration.
Jelle Houtman +2 more
doaj +1 more source
medRxiv, 2021 Background Reporting standards, such as PRISMA aim to ensure that the methods and results of systematic reviews are described in sufficient detail to allow full transparency.
N. Haddaway +3 more
semanticscholar +1 more source
Investigating cohesive sediment dynamics in open waters via grain-resolved simulations
Flow, 2023 Cohesive particulate flows play an important role in environmental fluid dynamics, as well as in a wide variety of civil and process engineering applications.
Bernhard Vowinckel +3 more
doaj +1 more source
Numerical study of the effect of sidewalls on shock train behaviour
Flow, 2023 Strongly coupled sequences of shock waves, known as shock trains, are present in high-speed propulsion systems, where the presence of sidewalls substantially modifies the boundary layer thickness, skin friction and streamwise pressure distribution.
Alexander Gillespie, Neil D. Sandham
doaj +1 more source
Flow, 2023 Ionic fluids subjected to externally applied electric fields experience Joule heating, which increases with the increased electric field and ionic conductivity of the medium. Temperature gradients induced by Joule heating can create buoyancy-driven flows
Mohammad K. D. Manshadi, Ali Beskok
doaj +1 more source
Flow, 2023 Proper orthogonal decomposition (POD) is applied to three-dimensional (3-D) velocity fields collected from large-eddy simulations (LES) of a baffled stirred tank.
Arturo A. Arosemena, Jannike Solsvik
doaj +1 more source
Stability of schooling patterns of a fish pair swimming against a flow
Flow, 2023 Fish often swim in crystallized group formations (schooling) and orient themselves against the incoming flow (rheotaxis). At the intersection of these two phenomena, we investigate the emergence of unique schooling patterns through passive hydrodynamic ...
Rishita Das +2 more
doaj +1 more source
FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks [PDF]
Computer Vision and Pattern Recognition, 2016 The FlowNet demonstrated that optical flow estimation can be cast as a learning problem. However, the state of the art with regard to the quality of the flow has still been defined by traditional methods.
Eddy Ilg +5 more
semanticscholar +1 more source