Optical Flow from Motion Blurred Color Images

Schoueri, Yasmina; Scaccia, Milena; Rekleitis, Ioannis

doi:10.1109/crv.2009.15

Cited by 5 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We refer the reader to extensive surveys on this topic [KLY21, ZRL * 22], and we focus our discussion on deblurring solutions that explicitly recover intra‐frame optical flow from motion blur that we employ in this work. Earlier works [Rek95, SSR09] assume global motion models that lead to spatially‐invariant deblurring kernels. More advanced solutions support spatially‐varying kernels that are approximated by linear motion [HKML14, DW08].…”

Section: Previous Workmentioning

confidence: 99%

Video frame interpolation for high dynamic range sequences captured with dual‐exposure sensors

Cogalan

Bemana

Seidel

2023

Computer Graphics Forum

View full text Add to dashboard Cite

Video frame interpolation (VFI) enables many important applications such as slow motion playback and frame rate conversion. However, one major challenge in using VFI is accurately handling high dynamic range (HDR) scenes with complex motion. To this end, we explore the possible advantages of dual‐exposure sensors that readily provide sharp short and blurry long exposures that are spatially registered and whose ends are temporally aligned. This way, motion blur registers temporally continuous information on the scene motion that, combined with the sharp reference, enables more precise motion sampling within a single camera shot. We demonstrate that this facilitates a more complex motion reconstruction in the VFI task, as well as HDR frame reconstruction that so far has been considered only for the originally captured frames, not in‐between interpolated frames. We design a neural network trained in these tasks that clearly outperforms existing solutions. We also propose a metric for scene motion complexity that provides important insights into the performance of VFI methods at test time.

show abstract

Section: Previous Workmentioning

confidence: 99%

Video frame interpolation for high dynamic range sequences captured with dual‐exposure sensors

Cogalan

Bemana

Seidel

2023

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…However, flow approaches that can perform well given blurred scenes -where the Brightness Constancy is usually violated -are less common. Of the approaches that do exist, Schoueri et al [19] perform a linear deblurring filter before optical flow estimation while Portz et al [1] attempt to match un-uniform camera motion between neighbouring input images. Whereas the former approach may be limited given nonlinear blur in realworld scenes; the latter requires two extra frames to parameterise the motioninduced blur.…”

Section: Related Workmentioning

confidence: 99%

“…Because of the nonlinearity in terms of φ , b i+1 * , the system (Eqs. 18,19) is difficult to solve by linear numerical methods. We apply the first order Taylor expansions to remove these nonlinearity in b i+1 * , which results in:…”

Section: Optical Flow Energy Optimisationmentioning

confidence: 99%

Blur robust optical flow using motion channel

Chen

Lee

et al. 2017

Neurocomputing

View full text Add to dashboard Cite

It is hard to estimate optical flow given a realworld video sequence with camera shake and other motion blur. In this paper, we first investigate the blur parameterization for video footage using near linear motion elements. We then combine a commercial 3D pose sensor with an RGB camera, in order to film video footage of interest together with the camera motion. We illustrates that this additional camera motion/trajectory channel can be embedded into a hybrid framework by interleaving an iterative blind deconvolution and warping based optical flow scheme. Our method yields improved accuracy within three other state-of-the-art baselines given our proposed ground truth blurry sequences; and several other realworld sequences filmed by our imaging system.

show abstract

“…Our work is also related to motion from blur [7,15,23], where the motion blur in a single image is used to estimate the motion. These algorithms only provide the direction and speed of motion at the time the image was captured, which is unlikely to provide accurate correspondences between image pairs with arbitrary motion.…”

Section: Related Workmentioning

confidence: 99%

Optical flow in the presence of spatially-varying motion blur

Portz

Zhang

Jiang

2012

2012 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

This paper extends the classical warping-based optical flow method to achieve accurate flow in the presence of spatially-varying motion blur. Our idea is to parameterize the appearance of each frame as a function of both the pixel motion and the motion-induced blur. We search for the flows that best match two consecutive frames, which amounts to finding the derivative of a blurred frame with respect to both the motion and the blur, where the blur itself is a function of the motion. We propose an efficient technique to calculate the derivatives using pre-filtering. Our technique avoids performing spatially-varying filtering (which can be computationally expensive) during the optimization iterations. In the end, our derivative calculation technique can be easily incorporated with classical flow code to handle video with non-uniform motion blur with little performance penalty. Our method is evaluated on both synthetic and real videos and outperforms conventional flow methods in the presence of motion blur.

show abstract

Optical Flow from Motion Blurred Color Images

Cited by 5 publications

References 9 publications

Video frame interpolation for high dynamic range sequences captured with dual‐exposure sensors

Video frame interpolation for high dynamic range sequences captured with dual‐exposure sensors

Blur robust optical flow using motion channel

Optical flow in the presence of spatially-varying motion blur

Contact Info

Product

Resources

About