Youngjung Kim

Depth Analogy: Data-Driven Approach for Single Image Depth Estimation Using Gradient Samples

Inferring scene depth from a single monocular image is a highly ill-posed problem in computer vision. This paper presents a new gradient-domain approach, called depth analogy, that makes use of analogy as a means for synthesizing a target depth field, when a collection of RGB-D image pairs is given as training data. Specifically, the proposed method employs a non-parametric learning process that creates an analogous depth field by sampling reliable depth gradients using visual correspondence established on training image pairs. Unlike existing data-driven approaches that directly select depth values from training data, our framework transfers depth gradients as reconstruction cues, which are then integrated by the Poisson reconstruction. The performance of most conventional approaches relies heavily on the training RGB-D data used in the process, and such a dependency severely degenerates the quality of reconstructed depth maps when the desired depth distribution of an input image is quite different from that of the training data, e.g., outdoor versus indoor scenes. Our key observation is that using depth gradients in the reconstruction is less sensitive to scene characteristics, providing better cues for depth recovery. Thus, our gradient-domain approach can support a great variety of training range datasets that involve substantial appearance and geometric variations. The experimental results demonstrate that our (depth) gradient-domain approach outperforms existing data-driven approaches directly working on depth domain, even when only uncorrelated training datasets are available.

Data-driven single image depth estimation using weighted median statistics

In this paper, a data-driven approach is proposed for automatically estimating a plausible depth map from a single monocular image based on the weighted median statistics (WMS). Instead of using complicated parametric models for learning frameworks that are typically employed in existing methods, we cast the estimation as a simple yet effective statistical approach. It assigns perceptually proper depth values to an input image in accordance with a data-driven depth prior. Based on the assumption that similar scenes are likely to have similar depth structure, the depth prior is computed from the WMS of k-nearest neighbor 3D pairs in a large 3D image repository. We show that the WMS captures the underlying depth structure of the input image very well, even though the visual appearance of nearest neighbor images are not tightly aligned. The depth map is then inferred according to the depth prior by making use of the edge-aware image filtering technique, resulting in a discontinuity-preserving smooth depth map. Experimental results demonstrate that our method outperforms state-of-the-art methods in terms of both accuracy and efficiency.

Structure Selective Depth Superresolution for RGB-D Cameras

This paper describes a method for high-quality depth superresolution. The standard formulations of image-guided depth upsampling, using simple joint filtering or quadratic optimization, lead to texture copying and depth bleeding artifacts. These artifacts are caused by inherent discrepancy of structures in data from different sensors. Although there exists some correlation between depth and intensity discontinuities, they are different in distribution and formation. To tackle this problem, we formulate an optimization model using a nonconvex regularizer. A nonlocal affinity established in a high-dimensional feature space is used to offer precisely localized depth boundaries. We show that the proposed method iteratively handles differences in structure between depth and intensity images. This property enables reducing texture copying and depth bleeding artifacts significantly on a variety of range data sets. We also propose a fast alternating direction method of multipliers algorithm to solve our optimization problem. Our solver shows a noticeable speed up compared with the conventional majorize-minimize algorithm. Extensive experiments with synthetic and real-world data sets demonstrate that the proposed method is superior to the existing methods.

Deeply Aggregated Alternating Minimization for Image Restoration

Regularization-based image restoration has remained an active research topic in image processing and computer vision. It often leverages a guidance signal captured in different fields as an additional cue. In this work, we present a general framework for image restoration, called deeply aggregated alternating minimization (DeepAM). We propose to train deep neural network to advance two of the steps in the conventional AM algorithm: proximal mapping and β-continuation. Both steps are learned from a large dataset in an end-to-end manner. The proposed framework enables the convolutional neural networks (CNNs) to operate as a regularizer in the AM algorithm. We show that our learned regularizer via deep aggregation outperforms the recent data-driven approaches as well as the nonlocal-based methods. The flexibility and effectiveness of our framework are demonstrated in several restoration tasks, including single image denoising, RGB-NIR restoration, and depth super-resolution.

A majorize-minimize approach for high-quality depth upsampling

This paper describes a non-convex model that is carefully designed for high quality depth upsampling. Modern depth sensors such as time-of-flight cameras provide a promising depth measurement with video rate, but suffer from noise and low resolution. To tackle these limitations, we formulate an optimization problem using a robust potential function. In this formulation, a nonlocal principle established in the high-dimensional feature space is used to disambiguate the up-sampling problem. We also derive a numerical algorithm based on the majorization-minimization approach for efficient optimization. The proposed model iteratively creates a new affinity space that determines the influence of neighboring pixels by jointly considering spatial distance, appearance, and current estimates. This behavior enables one to significantly reduce annoying artifacts on a variety of range dataset, including a challenging real measurement. Extensive experiments demonstrate that the proposed model achieves competitive performance with state-of-the-art methods.

Multi-Color Electrochromic Device Based on Organic Electrochromic Materials

Multi-color electrochromic (EC) device was fabricated on a patterned ITO glass. Organic electrochromic dyes were encapsulated within nano-sized porous TiO2 nanoparticles, and their relative electrochromic (EC) properties were determined using spectroelectrochemical method. Blue, green, and red colored organic dye doped TiO2 nanoparticles were coated on a patterned ITO substrate to afford multi-colored EC electrode, which was coated with a photo-curable polymer electrolyte and then covered with a bare ITO glass as a counter electrode. Upon photocuring of the electrolyte layer under UV light, an all-solid state multi-colored electrochromic device (ECD) was obtained. The resultant ECD showed reversible multi-color change within 8 sec and high optical contrast.

MEASUREMENT OF PULL‐OFF FORCES BY ATOMIC FORCE MICROSCOPE IN LIQUIDS USED FOR BIOLOGICAL APPLICATIONS

SummaryFundamental differences were observed between what the accepted theory predicts and what we were able to achieve in the laboratory. At low axial load levels, the Euler equation predicts the decrease in the fundamental natural frequency well, but the agreement decays badly as critical buckling load approaches. We attribute this disagreement to nonlinear behavior that is not accounted for in Euler’s model. It is possible that fixed end conditions would produce better agreement between theory and test results. In spite of the divergence between the analytical prediction and our test results, the Euler buckling equation is used universally (and successfully) to predict critical load of slender, axially loaded beams.

Optimal boundary smoothing for curvature estimation

Computing a curvature function on a digitized boundary is an ill-posed problem due to the discrete nature of the boundary. Thus, the boundary needs to be smoothed before computing the curvature function. The authors use a constrained regularization technique to obtain the optimal smooth boundary. The curvature function is computed from this optimal smooth boundary. This method solves a common critical problem of current curvature estimation methods in determining a unique smoothing factor. This method is used to derive a curvature function which is invariant under rotation, scale, and translation.<<ETX>>

Fast Domain Decomposition for Global Image Smoothing

Edge-preserving smoothing (EPS) can be formulated as minimizing an objective function that consists of data and regularization terms. At the price of high-computational cost, this global EPS approach is more robust and versatile than a local one that typically has a form of weighted averaging. In this paper, we introduce an efficient decomposition-based method for global EPS that minimizes the objective function of

Edge-aware image smoothing using commute time distances

{L_{2}}