Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

Chen, Qifeng; Koltun, Vladlen

doi:10.1109/cvpr.2016.509

Cited by 145 publications

(118 citation statements)

References 49 publications

Supporting

Mentioning

117

Contrasting

Unclassified

Order By: Relevance

“…However, BCA turns out to not work well for noisy data, and recent work prefers patch-based data terms from the stereo matching literature, e.g. [7,36,37]. The weakness of BCA is aggravated by the low density of the evidence in PIV data (in our case ≈0.0003 particles per voxel).…”

Section: Volumetric Flowmentioning

confidence: 78%

“…Recently, 2D optical flow benchmarks have been dominated by label-based methods [7,24], propagation methods [4,18], neural regression networks [10] and models that exploit scene-specific properties like semantics [35,3]. Most of these models do not scale well to the volumetric domain and struggle heavily with memory consumption.…”

Section: Related Workmentioning

confidence: 99%

“…G denotes the discretized version of the data term from (3) and F one of the investigated regularizers from (4,7,8). In case of QR or TV, the linear mapping D implements the finite differences to approximate the spatial gradient of the flow in each coordinate direction, which leads to Y :=Y…”

Section: Volumetric Flowmentioning

confidence: 99%

“…Here, we prefer a variational approach and first-order methods [5], because these methods have a manageable memory foot- print and offer the possibility to include the aforementioned physical constraints. As in the 2D case, [7,36,37], we prefer to use window-based data terms rather than per-pixel brightness constancy. For our (soft, probabilistic) particle volumes, where all particles look the same, we posit that matching information can still be found in the local patterns of the particles.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations

Lasinger

Vogel

Schindler

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

In experimental fluid dynamics, the flow in a volume of fluid is observed by injecting high-contrast tracer particles and tracking them in multi-view video. Fluid dynamics researchers have developed variants of space-carving to reconstruct the 3D particle distribution at a given time-step, and then use relatively simple local matching to recover the motion over time. On the contrary, estimating the optical flow between two consecutive images is a long-standing standard problem in computer vision, but only little work exists about volumetric 3D flow. Here, we propose a variational method for 3D fluid flow estimation from multi-view data. We start from a 3D version of the standard variational flow model, and investigate different regularization schemes that ensure divergence-free flow fields, to account for the physics of incompressible fluids. Moreover, we propose a semi-dense formulation, to cope with the computational demands of large volumetric datasets. Flow is estimated and regularized at a lower spatial resolution, while the data term is evaluated at full resolution to preserve the discriminative power and geometric precision of the local particle distribution. Extensive experiments reveal that a simple sum of squared differences (SSD) is the most suitable data term for our application. For regularization, an energy whose Euler-Lagrange equations correspond to the stationary Stokes equations leads to the best results. This strictly enforces a divergence-free flow and additionally penalizes the squared gradient of the flow.

show abstract

Section: Volumetric Flowmentioning

confidence: 78%

Section: Related Workmentioning

confidence: 99%

Section: Volumetric Flowmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations

Lasinger

Vogel

Schindler

2017

2017 IEEE International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

show abstract

“…The most recently proposed Fullflow method [12] also adopts EpicFlow. But the overall performance of optical flow estimation of our method is much better than that of Fullflow method as shown in Figure 7.…”

Section: Optimization Of Deep Estimation Based On Epicflowmentioning

confidence: 99%

Light Field Flow Estimation Based on Occlusion Detection

Zhang¹,

Lin²

2017

JCC

View full text Add to dashboard Cite

Light field cameras have a wide area of applications, such as digital refocusing, scene depth information extraction and 3-D image reconstruction. By recording the energy and direction information of light field, they can well solve many technical problems that cannot be done by conventional cameras. An important feature of light field cameras is that a microlens array is inserted between the sensor and main lens, through which a series of sub-aperture images of different perspectives are formed. Based on this feature and the full-focus image acquisition technique, we propose a light-field optical flow calculation algorithm, which involves both the depth estimation and the occlusion detection and guarantees the edge-preserving property. This algorithm consists of three steps: 1) Computing the dense optical flow field among a group of sub-aperture images; 2) Obtaining a robust depth-estimation by initializing the light-filed optical flow using the linear regression approach and detecting occluded areas using the consistency; 3) Computing an improved light-field depth map by using the edge-preserving algorithm to realize interpolation optimization. The reliability and high accuracy of the proposed approach is validated by experimental results.

show abstract

Neural network‐based optical flow versus traditional optical flow techniques with thermal aerial imaging in real‐world settings

Nguyen

Rosser

Perera

et al. 2023

Journal of Field Robotics

View full text Add to dashboard Cite

The study explores the feasibility of optical flow‐based neural network from real‐world thermal aerial imagery. While traditional optical flow techniques have shown adequate performance, sparse techniques do not work well during cold‐soaked low‐contrast conditions, and dense algorithms are more accurate in low‐contrast conditions but suffer from the aperture problem in some scenes. On the other hand, optical flow from convolutional neural networks has demonstrated good performance with strong generalization from several synthetic public data set benchmarks. Ground truth was generated from real‐world thermal data estimated with traditional dense optical flow techniques. The state‐of‐the‐art Recurrent All‐Pairs Field Transform for the Optical Flow model was trained with both color synthetic data and the captured real‐world thermal data across various thermal contrast conditions. The results showed strong performance of the deep‐learning network against established sparse and dense optical flow techniques in various environments and weather conditions, at the cost of higher computational demand.

show abstract

Full Flow: Optical Flow Estimation By Global Optimization over Regular Grids

Cited by 145 publications

References 49 publications

Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations

Volumetric Flow Estimation for Incompressible Fluids Using the Stationary Stokes Equations

Light Field Flow Estimation Based on Occlusion Detection

Neural network‐based optical flow versus traditional optical flow techniques with thermal aerial imaging in real‐world settings

Contact Info

Product

Resources

About