Towards Motion Aware Light Field Video for Dynamic Scenes

Tambe, Salil; Veeraraghavan, Ashok; Agrawal, Amit

doi:10.1109/iccv.2013.129

Cited by 28 publications

(13 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Our work is closely related to the problem of projection matrix design in compressed sensing, where sparsity is used as a signal prior, and matrices are optimized in terms of properties such as incoherence or RIP [8,6]. Both sparsity [20,26] and PCA [2] signal priors have been used to design multiplexing matrices for compressive light field acquisition. Works such as this have demonstrated that data driven design can bring improvements to CI.…”

Section: Our Main Contributionmentioning

confidence: 99%

Can we beat Hadamard multiplexing? Data driven design and analysis for computational imaging systems

Mitra

Cossairt

Veeraraghavan

2014

2014 IEEE International Conference on Computational Photography (ICCP)

Self Cite

View full text Add to dashboard Cite

Computational Imaging (CI) systems that exploit optical multiplexing and algorithmic demultiplexing have been shown to improve imaging performance in tasks such as motion deblurring, extended depth of field, light field and hyper-spectral imaging. Design and performance analysis of many of these approaches tend to ignore the role of image priors. It is well known that utilizing statistical image priors significantly improves demultiplexing performance. In this paper, we extend the Gaussian Mixture Model as a data-driven image prior (proposed by Mitra et. al [21]) to under-determined linear systems and study compressive CI methods such as light-field and hyper-spectral imaging. Further, we derive a novel algorithm for optimizing multiplexing matrices that simultaneously accounts for (a) sensor noise (b) image priors and (c) CI design constraints. We use our algorithm to design data-optimal multiplexing matrices for a variety of existing CI designs, and we use these matrices to analyze the performance of CI systems as a function of noise level. Our analysis gives new insight into the optimal performance of CI systems, and how this relates to the performance of classical multiplexing designs such as Hadamard matrices.

show abstract

Section: Our Main Contributionmentioning

confidence: 99%

Can we beat Hadamard multiplexing? Data driven design and analysis for computational imaging systems

Mitra

Cossairt

Veeraraghavan

2014

2014 IEEE International Conference on Computational Photography (ICCP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…CS relies on low-dimensional representations for the sensed signal such as sparsity under a transform or a dictionary. There is a rich body of work on applying CS to imaging of visual signals including images [25], [26] videos [10], [27], [28] and light fields [11], [29]. Most relevant to our paper is the video CS work of Hitomi et al [10] where a sparsifying dictionary is used on video patches to recover high-speed videos from low-frame rate sensors.…”

Section: G Compressive Sensing (Cs)mentioning

confidence: 99%

Cross-Scale Predictive Dictionaries

Saragadam

Sankaranarayanan

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Sparse representations using data dictionaries provide an efficient model particularly for signals that do not enjoy alternate analytic sparsifying transformations. However, solving inverse problems with sparsifying dictionaries can be computationally expensive, especially when the dictionary under consideration has a large number of atoms. In this paper, we incorporate additional structure on to dictionary-based sparse representations for visual signals to enable speedups when solving sparse approximation problems. The specific structure that we endow onto sparse models is that of a multi-scale modeling where the sparse representation at each scale is constrained by the sparse representation at coarser scales. We show that this cross-scale predictive model delivers significant speedups, often in the range of , with little loss in accuracy for linear inverse problems associated with images, videos, and light fields.

show abstract

“…A second subset of such methods is programmable aperture imaging [6]. Compressive sensing and dictionary learning have also been applied to reduce the number of images required by exploiting the self-similarity among light field images [2], [21]. The Pelican imaging camera array [22] is a portable, practical light field capture system that can be implemented in a cellphone but has a limited angular range.…”

Section: Related Workmentioning

confidence: 99%

The Light Field Attachment: Turning a DSLR into a Light Field Camera Using a Low Budget Camera Ring

Wang

Liu

Heidrich

et al. 2017

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Towards Motion Aware Light Field Video for Dynamic Scenes

Abstract: Current Light Field (LF) cameras offer fixed resolution in space, time and angle which is decided a-priori and is independent of the scene. These cameras either trade-off spatial resolution to capture single-shot LF [20,27,12]

Cited by 28 publications

References 29 publications

Can we beat Hadamard multiplexing? Data driven design and analysis for computational imaging systems

Can we beat Hadamard multiplexing? Data driven design and analysis for computational imaging systems

Cross-Scale Predictive Dictionaries

The Light Field Attachment: Turning a DSLR into a Light Field Camera Using a Low Budget Camera Ring

Contact Info

Product

Resources

About