Removing camera motion blur from a single light field is a challenging task since it is highly ill-posed inverse problem. The problem becomes even worse when blur kernel varies spatially due to scene depth variation and high-order camera motion. In this paper, we propose a novel algorithm to estimate all blur model variables jointly, including latent sub-aperture image, camera motion, and scene...

In this paper, we propose a discriminative learning-based method for recovering the depth of a scene from multiple defocused images. The proposed method consists of a discriminative learning phase and a depth estimation phase. In the discriminative learning phase, we formalize depth from defocus (DFD) as a multi-class classification problem which can be solved by learning the discriminative met...

Three-dimensional content (3D) creation has received a lot of attention due to numerous successes of 3D entertainment. Accurate estimation of depth information is necessary for efficient 3D content creation. In this paper, we propose a disparity map estimation method based on stereo correspondence. The proposed system utilizes depth and stereo camera sets. While the stereo set carries out dispa...

In this paper, we propose a scheme for multiview depth map estimation to enhance temporal consistency. After we divide the center image into several segments, we estimate one depth value for each segment using 3-D warping and segment-based matching techniques. In the refinement process, we apply a segment-based belief propagation algorithm. In order to enhance temporal consistency and reliabili...

We focus on the challenging problem of efficient mouse 3D pose estimation based on static images, and especially single depth images. We introduce an approach to discriminatively train the split nodes of trees in random forest to improve their performance on estimation of 3D joint positions of mouse. Our algorithm is capable of working with different types of rodents and with different types of...

Most of the existing deep learning-based methods for 3D hand and human pose estimation from a single depth map are based on a common framework that takes a 2D depth map and directly regresses the 3D coordinates of keypoints, such as hand or human body joints, via 2D convolutional neural networks (CNNs). The first weakness of this approach is the presence of perspective distortion in the 2D dept...

Depth information is essential for depth image-based rendering (DIBR), which is one of the rendering processes for the virtual view using a color image and its corresponding depth map. Although there are several depth estimation methods, more accurate depth estimation is still required. Since inaccurate depth information along object boundaries causes serious rendering errors, depth boundary in...

Previous monocular depth estimation methods take a single view and directly regress the expected results. Though recent advances are made by applying geometrically inspired loss functions during training, the inference procedure does not explicitly impose any geometrical constraint. Therefore these models purely rely on the quality of data and the effectiveness of learning to generalize. This e...

In this paper, we propose a new algorithm to estimate temporally consistent depth sequence. Our algorithm first calculates the matching cost using left and right views. In order to enhance the temporal consistency, we modify the matching function by adding the temporal weighting function and we perform the motion estimation technique to refer to the previous depths of moving objects. Experiment...