Blur robust optical flow using motion channel

Li, Wenbin; Chen, Yang; Lee, Jeehang; Ren, Gang; Cosker, Darren

doi:10.1016/j.neucom.2016.03.105

Cited by 8 publications

(16 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their approach is supposed to improve the flow regularization at motion boundaries. Li et al [57] embed an additional camera motion channel into a hybrid framework in order to obtain the deblurring result and motion estimation result iteratively. Their method requires a physical motion tracker to obtain the ground truth motion accompanied with the moving camera.…”

Section: Optical Flowmentioning

confidence: 99%

See 1 more Smart Citation

Learn to model blurry motion via directional similarity and filtering

Chen

et al. 2018

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

It is difficult to recover the motion field from a real-world footage given a mixture of camera shake and other photometric effects. In this paper we propose a hybrid framework by interleaving a Convolutional Neural Network (CNN) and a traditional optical flow energy. We first conduct a CNN architecture using a novel learnable directional filtering layer. Such layer encodes the angle and distance similarity matrix between blur and camera motion, which is able to enhance the blur features of the camera-shake footages. The proposed CNNs are then integrated into an iterative optical flow framework, which enable the capability of modeling and solving both the blind deconvolution and the optical flow estimation problems simultaneously. Our framework is trained end-to-end on a synthetic dataset and yields competitive precision and performance against the state-of-the-art approaches

show abstract

Section: Optical Flowmentioning

confidence: 99%

“…The deblurring process may sharpen the images but still permanently change the pixel intensity and further bring unpredictable artifacts. The alternative is to match un-uniform blur [57,52] between the input images:…”

Section: Recover Motion Field From Blurred Footagementioning

confidence: 99%

Learn to model blurry motion via directional similarity and filtering

Chen

et al. 2018

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Freehand motion tracking enabled by a remote 3D camera is very different from handheld input devices or fiducial markers. The former may involve expensive computer vision tracking task [48,49,50] and real-time accuracy request [51,52]. For example, low cost 3D camera can only track hand motion robustly, but not always accurately track small motions of wrists or fingers from a distance.…”

Section: Freehand Gestural Design Challengesmentioning

confidence: 99%

Towards the design of effective freehand gestural interaction for interactive TV

Ren

O’Neill

2016

IFS

Self Cite

View full text Add to dashboard Cite

As interactive devices become pervasive, people are beginning to look for more advanced interaction with televisions in the living room. Interactive television has the potential to offer a very engaging experience. But most common user tasks are still challenging with such systems, such as menu selection or text input, and little work has been done on understanding and supporting the effective design of freehand interaction with a TV in the domestic environment. In this paper, we report two studies investigating freehand gestural interaction with a consumer level sensor that is suitable for TV use scenarios. In the first study, we investigate a range of design factors for tiled layout menu selection, including wearable feedback, push gesture depth, target size and position in motor space. The results show that tactile and audio feedback have no significant effect on user performance and preference, and these results inform potential designs for high selection performance. In the second study, we investigate using freehand gestures for the common TV user task of text input. We design and evaluate two virtual keyboard layouts and three freehand selection methods. Results show that ease of use and error tolerance can both be achieved using a text entry method utilizing a dual circle layout and an expanding target selection technique. Finally, we propose design guidelines for effective, usable and comfortable freehand gestural interaction for interactive TV based on the findings

show abstract

“…Where α 1 , α 2 and α 3 are weights for controlling the contribution of each pixel in the 3 × 3 area. Using this 3 × 3 kernel is supposed to give extra robustness against the subpixel accuracy and illumination changes [16,17,14,18]. In our experiments, all these weights are set as α 1 = 1, α 2 = 0.25 and α 3 = 0.125 which refer to the distance from the centre pixel x of the area.…”

Section: Step One: Computing Optical Flow Fieldsmentioning

confidence: 99%

Drift robust non-rigid optical flow enhancement for long sequences

Cosker

Brown

2016

IFS

Self Cite

View full text Add to dashboard Cite

It is hard to densely track a nonrigid object in long term, which is a fundamental research issue in the computer vision community. This task often relies on estimating pairwise correspondences between images over time where the error is accumulated and leads to a drift. In this paper, we introduce a novel optimisation framework with an Anchor Patch constraint. It is supposed to significantly reduce overall errors given long sequences containing nonrigidly deformable objects. Our framework can be applied to any dense tracking algorithm, e.g. optical flow. We demonstrate the success of our approach by showing significant error reduction on 6 popular optical flow algorithms applied to a range of realworld nonrigid benchmarks. We also provide quantitative analysis of our approach given synthetic occlusions and image noise

show abstract

Blur robust optical flow using motion channel

Cited by 8 publications

References 27 publications

Learn to model blurry motion via directional similarity and filtering

Learn to model blurry motion via directional similarity and filtering

Towards the design of effective freehand gestural interaction for interactive TV

Drift robust non-rigid optical flow enhancement for long sequences

Contact Info

Product

Resources

About