Single Image Deblurring Using Motion Density Functions

Gupta, Ankit; Joshi, Neel; Zitnick, C. Lawrence; Cohen, Michael F.; Curless, Brian

doi:10.1007/978-3-642-15549-9_13

Cited by 281 publications

(318 citation statements)

References 23 publications

Supporting

Mentioning

308

Contrasting

Unclassified

Order By: Relevance

“…It is also possible to remove spatially varying blur by estimating a general camera motion function. A similar model has been used to model three degrees of camera motion (with in-plane translation and rotation) in [9]. In [11], a method that employs an efficient filter flow algorithm to speed up the optimization step is developed.…”

Section: Related Workmentioning

confidence: 99%

“…In this section, we describe the non-uniform blur model caused by camera shake for the scene with constant depth that can be modeled in a way similar to [9]. The geometric model we use is based on [21] which formulates the blurry image B as the integration of the transformed copies of latent image L,…”

Section: Non-uniform Blur Model For Camera Shakementioning

confidence: 99%

“…The blurry image can be viewed as a combination of the images the camera captures with observation noise n. Similar to [9], we address this problem in a discrete space with…”

Section: Non-uniform Blur Model For Camera Shakementioning

confidence: 99%

“…In [9], it is shown that the out-of-plane rotation can be well approximated by x, y translation when the focal length is sufficiently long, which is usually the case for camera settings. In this work, we approximate the camera motion with a three-dimensional pose space as [9] (x, y translation and z rotation) and focus on estimation of pose weights.…”

Section: Non-uniform Blur Model For Camera Shakementioning

confidence: 99%

See 3 more Smart Citations

Fast Non-uniform Deblurring using Constrained Camera Pose Subspace

Yang

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

Camera shake during exposure time often results in non-uniform blur across the entire image. Recent algorithms model the non-uniform blurry image as a linear combination of images observed by the camera at discretized poses, and focus on estimating the time fraction positioned at each pose. While these algorithms show promising results, they nevertheless entail heavy computational loads. In this work, we propose a novel single image deblurring algorithm to remove non-uniform blur. We estimate the local blur kernels at different image regions and obtain an initial guess of possible camera poses using backprojection. By restraining the possible camera poses in a low-dimensional subspace, we iteratively estimate the weight for each pose in the camera pose space. Experimental validations with the state-of-the-art methods demonstrate the efficiency and effectiveness of our algorithm for non-uniform deblurring.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Non-uniform Blur Model For Camera Shakementioning

confidence: 99%

“…The blurry image can be viewed as a combination of the images the camera captures with observation noise n. Similar to [9], we address this problem in a discrete space with…”

Section: Non-uniform Blur Model For Camera Shakementioning

confidence: 99%

Section: Non-uniform Blur Model For Camera Shakementioning

confidence: 99%

See 2 more Smart Citations

Fast Non-uniform Deblurring using Constrained Camera Pose Subspace

Yang

2012

Procedings of the British Machine Vision Conference 2012

View full text Add to dashboard Cite

show abstract

“…Although these methods deal with an unknown and general blur pattern, they assume that blur is not changing across the image domain. More recently, the space-varying case has been studied [30,31,32] albeit with some restrictions on the type of motion or the scene depth structure.…”

Section: Motion Deblurring and Blind Deconvolutionmentioning

confidence: 99%

Single Image Blind Deconvolution with Higher-Order Texture Statistics

Martinello

Favaro

2011

Video Processing and Computational Video

View full text Add to dashboard Cite

Abstract. We present a novel method for solving blind deconvolution, i.e., the task of recovering a sharp image given a blurry one. We focus on blurry images obtained from a coded aperture camera, where both the camera and the scene are static, and allow blur to vary across the image domain. As most methods for blind deconvolution, we solve the problem in two steps: First, we estimate the coded blur scale at each pixel; second, we deconvolve the blurry image given the estimated blur. Our approach is to use linear high-order priors for texture and second-order priors for the blur scale map, i.e., constraints involving two pixels at a time. We show that by incorporating the texture priors in a least-squares energy minimization we can transform the initial blind deconvolution task in a simpler optimization problem. One of the striking features of the simplified optimization problem is that the parameters that define the functional can be learned offline directly from natural images via singular value decomposition. We also show a geometrical interpretation of image blurring and explain our method from this viewpoint. In doing so we devise a novel technique to design optimally coded apertures. Finally, our coded blur identification results in computing convolutions, rather than deconvolutions, which are stable operations. We will demonstrate in several experiments that this additional stability allows the method to deal with large blur. We also compare our method to existing algorithms in the literature and show that we achieve state-of-the-art performance with both synthetic and real data.

show abstract