Po-Hao Huang

Contour-Based Structure from Reflection

In this paper, we propose a novel contour-based algorithm for 3D object reconstruction from a single uncalibrated image acquired under the setting of two plane mirrors. With the epipolar geometry recovered from the image and the properties of mirror reflection, metric reconstruction of an arbitrary rigid object is accomplished without knowing the camera parameters and the mirror poses. For this mirror setup, the epipoles can be estimated from the correspondences between the object and its reflection, which can be established automatically from the tangent lines of their contours. By using the property of mirror reflection as well as the relationship between the mirror plane normal with the epipole and camera intrinsic, we can estimate the camera intrinsic, plane normals and the orientation of virtual cameras. The positions of the virtual cameras are determined by minimizing the distance between the object contours and the projected visual cone for a reference view. After the camera parameters are determined, the 3D object model is constructed via the image-based visual hulls (IBVH) technique. The 3D model can be refined by integrating the multiple models reconstructed from different views. The main advantage of the proposed contour-based Structure from Reflection (SfR) algorithm is that it can achieve metric reconstruction from an uncalibrated image without feature point correspondences. Experimental results on synthetic and real images are presented to show its performance.

A novel gradient attenuation Richardson-Lucy algorithm for image motion deblurring

This paper presents a novel blind image deconvolution algorithm for motion deblurring from a single blurred image. We propose a unified framework for both blur kernel estimation and non-blind image deconvolution by using bilateral filtering (BF) and a new image deconvolution algorithm, called the Gradient Attenuation Richardson-Lucy (GARL) algorithm. In the blur kernel estimation stage, we show that an initial blur kernel, which is used for starting an alternating kernel refinement process, can be obtained from the blurred image with a quadratic regularization approach. In the non-blind image deconvolution stage, we exploit the image gradients and develop the GARL algorithm to alleviate the notorious ringing problem in the Richardson-Lucy-based image restoration approach. Furthermore, the loss of image details due to the suppression of the ringing artifacts around the regions with strong edges is recovered with an incremental detail recovery procedure. The proposed framework is simple yet effective compared to previous statistical approaches. Experimental results on various real data sets are given to demonstrate superior performance of the proposed algorithm over the previous methods. A novel blind image deconvolution algorithm for motion deblurring from a single blurred image is presented.A novel GARL algorithm is proposed to alleviate the ringing problem in the classical Richardson-Lucy image deconvolution method.A unified framework for blur kernel estimation and image deconvolution based on bilateral filtering and the GARL algorithm is presented.

Image deblurring with blur kernel estimation from a reference image patch

In this paper, we propose a new approach for image deblurring from two images, non-blurred and blurred, in different poses by exploiting the co-existing planar object in both views. We focus on the problem of aligning the corresponding image patches, which are the co-existing planar object, in both images and propose an iterative two-stage algorithm for patch alignment and kernel estimation. In the first stage, we extend the intensity-based alignment method to find the geometric transformation between patches, and then the aligned image patches are used for blur kernel estimation in the second stage. These two stages are repeated until convergence. Furthermore, the proposed algorithm can also be used when the geometric relationship between the two images is a homography or an approximate homography, such as images from image mosaic. Experimental results on real images are given to demonstrate its performance.

Blind image deblurring with modified richardson-lucy deconvolution for ringing artifact suppression

In this paper, we develop a unified image deblurring framework that consists of both blur kernel estimation and non-blind image deconvolution. For blind kernel estimation, we propose a patch selection procedure and integrate it with a coarse-to-fine kernel estimation algorithm to develop a robust blur kernel estimation algorithm. For the non-blind image deconvolution, we modify the traditional Richardson-Lucy (RL) image restoration algorithm to suppress the notorious ringing artifact in the regions around strong edges. Experimental results on some real blurred images are shown to demonstrate the improved efficiency and image restoration by using the proposed algorithm.

Image deblurring by exploiting inherent bi-level regions

In this paper, we propose an image restoration framework for restoring an image degraded by unknown motion blur. Our approach takes advantage of inherent bi-level regions of an image to estimate a blur kernel. The framework contains three parts: bi-level region searching, initial blur kernel estimation and iterative maximum a posteriori (MAP) image restoration. Firstly, candidate bi-level regions are located around the detected corners. We use four image features to score each region and choose the best N regions for estimating an initial blur kernel. Finally, an alternating minimization algorithm is developed to iteratively refine both the blur kernel and the restored image. Experimental results of synthetic and real blurred images are shown to demonstrate the performance of the proposed algorithm.

Silhouette-based camera calibration from sparse views under circular motion

In this paper, we propose a new approach to camera calibration from silhouettes under circular motion with minimal data. We exploit the mirror symmetry property and derive a common homography that relates silhouettes with epipoles under circular motion. With the epipoles determined, the homography can be computed from the frontier points induced by epipolar tangencies. On the other hand, given the homography, the epipoles can be located directly from the bi-tangent lines of silhouettes. With the homography recovered, the image invariants under circular motion and camera parameters can be determined. If the epipoles are not available, camera parameters can be determined by a low-dimensional search of the optimal homography in a bounded region. In the degenerate case, when the camera optical axes intersect at one point, we derive a closed-form solution for the focal length to solve the problem. By using the proposed algorithm, we can achieve camera calibration simply from silhouettes of three images captured under circular motion. Experimental results on synthetic and real images are presented to show its performance.

Automatic Multi-Layer Red-Eye Detection

Red-eye is a frequently encountered problem caused by flash reflection bouncing back into the camera from a persons retina. In this paper, we propose a two-stage automatic red-eye detection method. At the first stage, a series of heuristic filters are used to rapidly remove impossible regions according to constraints on color, smoothness, and size. A multi-layer process is applied at this stage to prevent the influence of surrounding redness of the eye. Moreover, at each layer, the approximate size of pupil can be decided automatically without multi-scaling. At the second stage, an SVM classifier that was trained for eye detection is applied to confirm the remaining candidate regions. Some experimental results on real images show the performance of the propose algorithm.

Camera calibration from silhouettes under incomplete circular motion with a constant interval angle

In this paper, we propose an algorithm for camera calibration from silhouettes under circular motion with an unknown constant interval angle. Unlike previous silhouette-based methods based on surface of revolution, the proposed algorithm can be applied to sparse and incomplete image sequences. Under the assumption of circular motion with a constant interval angle, epipoles of successive image pairs remain constant and can be determined from silhouettes. A pair of epipoles formed by a certain interval angle can provide a constraint on the angle and focal length. With more pairs of epipoles recovered, the focal length can be determined from the one that most satisfies the constraints and determine the interval angle concurrently. The rest of camera parameters can be recovered from image invariants. Finally, the estimated parameters are optimized by minimizing the epipolar tangency constraints. Experimental results on both synthetic and real images are shown to demonstrate its performance.

Three-dimensional model reconstruction for treasures of jadeite material from uncalibrated image sequences

This paper presents several novel techniques in the proposed semi-automatic system for reconstructing three-dimensional models of jadeite material from uncalibrated image sequences. There are two major challenges for this 3D model reconstruction problem. The first is the difficult image registration problem due to the semi-diaphaneity and the highly specular property of jadeite materials. Secondly, the unknown camera information, including the intrinsic (calibration) and extrinsic (position and orientation) parameters, to be recovered from the uncalibrated image sequences makes the robust 3D reconstruction problem very challenging. The proposed 3D modeling process first recovers the camera information as well as rough 3D structure by using a robust structure from motion algorithm, and then further extracts the fine details of the model from dense correspondences between image patches of different views. We have developed three new robust techniques for this challenging task, including a robust structure from motion algorithm, a robust image registration algorithm, and a robust dense depth computation algorithm. Finally, experimental results of the three-dimensional model reconstruction from the image sequence of the Chinese treasure, Jadeite Cabbage with Insects, are given to demonstrate the performance of the developed system.

Robust 3D object model reconstruction from video

In this paper, we present a 3D object reconstruction system that recovers 3D models of general objects from video. We assume the video of the object is captured from multiple viewpoints. The proposed system is composed of the following components: feature trajectory extraction, 3D structure from motion, surface reconstruction, and texture computation. In the feature trajectory extraction, we compute dense optical flow fields between adjacent frames and aggregate them at the interest points to obtain reliable feature trajectories. In the next structure from motion stage, we develop a robust algorithm to recover the dense 3D structures from several viewpoints for uncalibrated image sequences. For the surface reconstruction from the recovered 3D data points, we develop a new cluster-based radial-basis-function (RBF) algorithm, which overcomes the extensive computational cost limit in a divide-and-conquer manner. For the last texture computation process, we combine multi-view images to form the texture map of the 3D object model. Finally, experimental results are given to show the performance or the proposed 3D reconstruction system.