|
Dehazing using Non-Local Regularization with Iso-Depth Neighbor-Fields
Incheol Kim
MS Thesis in Computer Science
2017, KAIST, Deajeon, Korea
|
[PDF][BibTeX][Project] |
|
Removing haze from a single image is a severely ill-posed problem due to the lack of scene information. General dehazing algorithms estimate airlight initially using natural image statistics and then propagate the incompletely estimated airlight to build a dense transmission map, yielding a haze-free image. Propagating haze is different from other regularization problems, as haze is strongly correlated with depth according to the physics of light transport in participating media. However, since there is no depth information available in single-image dehazing, traditional regularization methods with a common grid random eld often su er from haze isolation artifacts caused by abrupt changes in scene depths. In this paper, to overcome the haze isolation problem, we propose a non-local regularization method by combining Markov random fields (MRFs) with nearest-neighbor fields (NNFs), based on our insightful observation that the NNFs searched in a hazy image associate patches at the similar depth, as local haze in the atmosphere is proportional to its depth. We validate that the proposed method can regularize haze effectively to restore a variety of natural landscape images. This proposed regularization method can be used separately with any other dehazing algorithms to enhance haze regularization.
|
|
|
Multisampling Compressive Video Spectroscopy
Daniel S. Jeon
MS Thesis in Computer Science
2016, KAIST, Deajeon, Korea
|
[PDF][BibTeX][Project] |
|
The coded aperture snapshot spectral imaging (CASSI) architecture has been employed widely for cap- turing hyperspectral video. Despite allowing concurrent capture of hyperspectral video, spatial mod- ulation in CASSI sacrifices image resolution significantly while reconstructing spectral projection via sparse sampling. Several multiview alternatives have been proposed to handle this low spatial resolution problem and improve measurement accuracy, for instance, by adding a translation stage for the coded aperture or changing the static coded aperture with a digital micromirror device for dynamic modulation. State-of-the-art solutions enhance spatial resolution significantly but are incapable of capturing video using CASSI. In this paper, we present a novel compressive coded aperture imaging design that increases spatial resolution while capturing 4D hyperspectral video of dynamic scenes. We revise the traditional CASSI design to allow for multiple sampling of the randomness of spatial modulation in a single frame. We demonstrate that our compressive video spectroscopy approach yields enhanced spatial resolution and consistent measurements, compared with the traditional CASSI design.
|
|
|
Building a Two-Way Hyperspectral Imaging System with Liquid Crystal Tunable Filters
Haebom Lee
MS Thesis in Computer Science
2015, KAIST, Deajeon, Korea
|
[PDF][BibTeX][Project] |
|
Liquid crystal tunable filters can provide rapid and vibrationless section of any wavelength in transmitting spectrum so that they have been broadly used in building multispectral or hyperspectral imaging systems. However, the spectral range of the filters is limited to a certain range, such as visible or near-infrared spectrum. In general hyperspectral imaging applications, we are therefore forced to choose a certain range of target spectrum, either visible or near-infrared for instance. Owing to the nature of polarizing optical elements, imaging systems combined with multiple tunable filters have been rarely practiced. In this paper, we therefore present our experience of building a two-way hyperspectral imaging system with liquid crystal tunable filters. The system allows us to capture hyperspectral radiance continuously from visible to near-infrared spectrum (400--1100nm at 7nm intervals), which is 2.3 times wider and 34 times more channels compared to a common RGB camera. We report how we handle the multiple polarizing elements to extend the spectral range of the imager with the multiple tunable filters and propose an affine-based method to register the hyperspectral image channels of each wavelength.
|
|
|
Stereo Fusion using a Refractive Medium on a Binocular Base
Seung-Hwan Baek
MS Thesis in Computer Science
2015, KAIST, Deajeon, Korea
|
[PDF][BibTeX][Project] |
|
The performance of depth reconstruction in binocular stereo relies on how adequate the predefined baseline for a target scene is. Wide-baseline stereo is capable of discriminating depth better than the narrow one, but it often suffers from spatial artifacts. Narrow-baseline stereo can provide a more elaborate depth map with less artifacts, while its depth resolution tends to be biased or coarse due to the short disparity. In this thesis, we propose a novel optical design of heterogeneous stereo fusion on a binocular imaging system with a refractive medium, where the binocular stereo part operates as wide-baseline stereo; the refractive stereo module works as narrow-baseline stereo. We then introduce a stereo fusion workflow that combines the refractive and binocular stereo algorithms to estimate fine depth information through this fusion design. The quantitative and qualitative results validate the performance of our stereo fusion system in measuring depth, compared with homogeneous stereo approaches.
|
|
|
Multispectral Photometric Stereo for Acquiring High-Fidelity Surface Normals
Giljoo Nam
MS Thesis in Computer Science
2014, KAIST, Deajeon, Korea
|
[PDF][BibTeX][Project] |
|
Multispectral imaging has become more accessible as an advanced imaging technique for a physically- meaningful imaging spectroscopy, and photometric stereo has been commonly practiced for digitizing a 3D shape with simplicity for more than three decades. However, these two imaging techniques have rarely been combined as 3D imaging applications yet. Reconstructing the shape of a 3D object using photometric stereo is still challenging due to optical phenomena such as global illumination, specular reflection and self shadow. In addition, removing interreflection in photometric stereo is a traditional chicken-and-egg problem as we need to account for interreflection without knowing geometry. In this thesis, we present a novel multispectral photometric stereo method that allows us to remove interreflection on diffuse materials using multispectral reflectance information. We demonstrate several benefits of our multispectral photometric stereo method such as removing interreflection and reconstructing the 3D shapes of objects to a high accuracy.
|
|
|
Locally Adaptive Products for Genuine Spherical Harmonic Lighting
Joo Ho Lee
MS Thesis in Computer Science
2014, KAIST, Deajeon, Korea
|
[PDF][BibTeX][Project] |
|
Precomputed radiance transfer techniques have been broadly used for supporting complex illumination effects on diffuse and glossy objects. Although working with the wavelet domain is efficient in handling all-frequency illumination, the spherical harmonics domain is more convenient for interactively changing lights and views on the fly due to the rotational invariant nature of the spherical harmonic domain. For interactive lighting, however, the number of coefficients must be limited and the high orders of coefficients have to be eliminated. Therefore, spherical harmonic lighting has been preferred and practiced only for interactive soft-diffuse lighting. In this thesis, we propose a simple but practical filtering solution using locally adaptive products of high-order harmonic coefficients within the genuine spherical harmonic lighting framework. Our approach works out on the fly in two folds. We first conduct multi-level filtering on vertices in order to determine regions of interests, where the high orders of harmonics are necessary for high-frequency lighting. The initially determined regions of interests are then refined through filling in the incomplete regions by traveling the neighboring vertices. Even not relying on graphics hardware, the proposed method allows to compute high order products of spherical harmonic lighting for both diffuse and specular lighting.
|
|
|
|
|
© Visual Computing Laboratory, School of Computing, KAIST.
All rights reserved.
|
|
|