Sorry, you need to enable JavaScript to visit this website.

We consider the task of removing the effect of camera shake during a long exposure. Technically, this is a blind deconvolution problem in which both the image and the motion blur have to be jointly inferred. Several algorithms have been proposed till date for removing camera shake that work with one or more images. However, most of these algorithms are computationally expensive and hence cannot be used in real-time.

In this paper, we propose a novel object proposal generation scheme by formulating a graph-based salient edge classification framework that utilizes the edge context. In the proposed method, we construct a Bayesian probabilistic edge map to assign a saliency value to the edgelets by exploiting low level edge features. A Conditional Random Field is then learned to effectively combine these features for edge classification with object/non-object label. We propose an objectness score for the generated windows by analyzing the salient edge density inside the bounding box.

Capturing more information, e.g. geometry and material, using optical cameras can greatly help the perception and understanding of complex scenes. This paper proposes a novel method to capture the spectral and light field information simultaneously. By using a delicately designed chromatic aberration enlarged camera, the spectral-varying slices at different depths of the scene can be easily captured.

A major drawback of JPEG 2000 is the computational complexity of its entropy coder named Embedded Block Coder with Optimized Truncation (EBCOT). This paper proposes two alterations to the original algorithm that seek to improve the trade-off between compression efficiency and throughput. Firstly, magnitude bits within a bit plane are not prioritized by their significance anymore, but instead coded in a single pass instead of three, reducing the amount of expensive memory accesses at the cost of fewer truncation points.

In this paper, we propose a principal color component extraction
method that is simply performed by linear color composition (transformation)
of R, G, B colors, but its composite coefficients are calculated
so as to obtain a noisy-texture-less principal component of
RGB color images. Our method is related to principal component
analysis (PCA) and edge preserving smoothing by total variation
(TV) minimization. The resultant image becomes a principal color
component image with the minimum total variation. We show this

Mobile cameras have come a long way since their evolution and have replaced digital still cameras. However, their lowlight photography performance needs significant improvement. Dual camera systems consisting of a monochrome sensor and a Bayer sensor offer us a way to improve the low-light photography. The existing dual camera systems use post-processing methods after Image Signal Processor (ISP) for image fusion which are computationally intensive and use two ISPs. We propose a novel architecture in which the image fusion can be done in Bayer domain prior to the ISP.

Semantic segmentation has recently witnessed major progress, but most of the previous work focused on improving single image segmentation. In this paper, we introduce a novel approach to implicitly utilize temporal data in videos for online segmentation. This design receives a sequence of consecutive video frames and outputs the segmentation of the last frame. Convolutional gated recurrent networks are used for the recurrent part to preserve spatial connectivities in the image. This architecture is tested for both binary and semantic video segmentation tasks.

Sequential dictionary learning algorithms has gained widespread acceptance in functional magnetic resonance imaging (fMRI) data analysis. However, many problems in fMRI data analysis involve the analysis of multiple-subject fMRI data sets and the existing algorithms do not extend naturally to this case. In this paper we propose an algorithm dedicated to multiple-subject fMRI data analysis. The algorithm is named SMSDL for sequential multi-subject dictionary learning and differs from existing dictionary learning algorithms in its dictionary update stage.