We introduce an effective technique to enhance the images captured underwater and degraded due to the medium scattering and absorption. Our method is a single image approach that does not require specialized hardware or knowledge about the underwater conditions or scene structure. It builds on the blending of two images that are directly derived from a color-compensated and white-balanced version of the original degraded image. The two images to fusion, as well as their associated weight maps, are defined to promote the transfer of edges and color contrast to the output image. To avoid that the sharp weight map transitions create artifacts in the low frequency components of the reconstructed image, we also adapt a multiscale fusion strategy. Our extensive qualitative and quantitative evaluation reveals that our enhanced images and videos are characterized by better exposedness of the dark regions, improved global contrast, and edges sharpness. Our validation also proves that our algorithm is reasonably independent of the camera settings, and improves the accuracy of several image processing applications, such as image segmentation and keypoint matching.

Simultaneous estimation of lighting and BRDF from multi-view images is an interesting problem in computer vision. It allows for exciting applications, such as flexible relighting in post-production, without recapturing the scene. Unfortunately, the estimation problem is made difficult because lighting and BRDF have closely entangled effects in the input images. This paper presents an algorithm to support both the estimation of distant and near-field illumination. Previous techniques are limited to distant lighting. We contribute by proposing an additional factorization of the lighting, while keeping the rendering efficient and additional data compactly stored in the wavelet domain. We reduce complexity by clustering the scene geometry into a few groups of important emitters and calculate the emitting powers by alternately solving for illumination and reflectance. We demonstrate our work on a synthetic and real datasets and show that a clean separation of distant and near-field illumination leads to a more accurate estimation and separation of lighting and BRDF.

Shannon entropy has been commonly used to quantify the image informativeness. The main drawback of this measure is that it does not take into account the spatial distribution of pixels. In this paper, we analyze four information-theoretic measures that overcome this limitation. Three of them (entropy rate, excess entropy, and erasure entropy) consider the image as a stationary stochastic process, while the fourth (partitional information) is based on an information channel between image regions and histogram bins. Experimental results, applied to natural and synthetic images, show the performance of these measures to characterize several informativeness aspects of an image. We also analyze their behavior under some image effects such as blurring, contrast change, and noise.

In this paper we present a novel approach for tracking the movement of a user in a large indoor environment. Many studies show that natural walking in virtual environments increases the feeling of immersion by the users. However, most tracking systems suffer from a limited working area or are expensive to scale up to a reasonable size for navigation.

This paper describes a novel strategy to enhance underwater videos and images. Built on the fusion principles, our strategy derives the inputs and the weight measures only from the degraded version of the image. In order to overcome the limitations of the underwater medium we define two inputs that represent color corrected and contrast enhanced versions of the original underwater image/frame, but also four weight maps that aim to increase the visibility of the distant objects degraded due to the medium scattering and absorption. Our strategy is a single image approach that does not require specialized hardware or knowledge about the underwater conditions or scene structure. Our fusion framework also supports temporal coherence between adjacent frames by performing an effective edge preserving noise reduction strategy. The enhanced images and videos are characterized by reduced noise level, better exposed-ness of the dark regions, improved global contrast while the finest details and edges are enhanced significantly. In addition, the utility of our enhancing technique is proved for several challenging applications.

We present a novel method of simulating wave effects in graphics using ray-based renderers with a new function: the Wave BSDF (Bidirectional Scattering Distribution Function). Reflections from neighboring surface patches represented by local BSDFs are mutually independent. However, in many surfaces with wavelength-scale microstructures, interference and diffraction requires a joint analysis of reflected wavefronts from neighboring patches. We demonstrate a simple method to compute the BSDF for the entire microstructure, which can be used independently for each patch. This allows us to use traditional ray-based rendering pipelines to synthesize wave effects. We exploit the Wigner Distribution Function (WDF) to create transmissive, reflective, and emissive BSDFs for various diffraction phenomena in a physically accurate way. In contrast to previous methods for computing interference, we circumvent the need to explicitly keep track of the phase of the wave by using BSDFs that include positive as well as negative coefficients. We describe and compare the theory in relation to well-understood concepts in rendering and demonstrate a straightforward implementation. In conjunction with standard raytracers, such as PBRT, we demonstrate wave effects for a range of scenarios such as multibounce diffraction materials, holograms, and reflection of high-frequency surfaces.

This paper introduces an effective decolorization algorithm that preserves the appearance of the original color image. Guided by the original saliency, the method blends the luminance and the chrominance information in order to conserve the initial color disparity while enhancing the chromatic contrast. As a result, our straightforward fusing strategy generates a new spatial distribution that discriminates better the illuminated areas and color features. Since we do not employ quantization or a per-pixel optimization (computationally expensive), the algorithm has a linear runtime, and depending on the image resolution it could be used in real-time applications. Extensive experiments and a comprehensive evaluation against existing state-of-the-art methods demonstrate the potential of our grayscale operator. Furthermore, since the method accurately preserves the finest details while enhancing the chromatic contrast, the utility and versatility of our operator have been proved for several other challenging applications such as video decolorization, detail enhancement, single image dehazing and segmentation under different illuminants.

In this work we provide an introduction to the Wigner Distribution Function (WDF) using geometric optics principles. The WDF provides a useful model of wave-fields, allowing simulation of diffraction and interference effects. We attempt to explain these Fourier optics concepts to computational photography researchers by clarifying the relationship between the WDF and position-angle representations. We demonstrate how the WDF can be used to simulate diffraction effects using a light field representation and discuss its validity in the near-field, far-field, and under the paraxial approximation. Finally, we demonstrate that although the WDF representation contains negative values, any projection always yields a non-negative intensity value.

In this paper we introduce a novel strategy that effectively enhance the visibility of underwater images. Our method is build-up on the fusion strategy that takes a sequence of inputs derived from the initial image. Practically, our fusion-based method aims to yield a final image that overcomes the deficiencies existing in the degraded input images by employing several weight maps that discriminate the regions characterized by poor visibility. The extensive experiments demonstrate the utility of our solution since the visibility range of the underwater images is significantly increased by improving both the scene contrast and the color appearance.

Depth information opens up a lot of possibilities for meaningful editing of photographs. So far, it has only been possible to acquire depth information by either using additional hardware, restrictive scene assumptions or extensive manual input. We developed a novel user-assisted technique for creating adequate depth maps with an intuitive stroke-based user interface. Starting from absolute depth constraints as well as surface normal constraints, we optimize for a feasible depth map over the image. We introduce a suitable smoothness constraint that respects image edges and accounts for slanted surfaces. We illustrate the usefulness of our technique by several applications such as depth of field reduction and advanced compositing.

This paper introduces a technique that increases the spatial resolution of a given video. The method is built on the fundamentals of super-resolution techniques that aim to reconstruct high-resolution frames from a low-resolution input sequence. Different than classical super-resolution methods, besides using the information of adjacent frames, we take advantage of several reference high quality (resolution) photographs of the same scene. The method is purely imagebased, and does not require depth estimation. The additional information extracted from the reference photographs is used to construct several high resolution seed frames added with a constant step in the initial video sequence. Therefore, the seed frames but also the adjacent low-resolution frames provide important information to define priors that are considered in the probabilistic interpretation of the generative model. The estimated solution is obtained based on a standard maximum a posteriori (MAP) approach. Objective tests on real and synthetic video sequences demonstrate the utility and the benefits of the proposed technique over related methods.

Matching images taken from widely different viewpoints is still an open problem being extremely challenging. In this paper is presented a new method that manipulates effectively the color in order to improve the matching performances of the well-known SIFT operator for the wide-baseline case. Without exploiting additional information, the algorithm employs a new model that preserves efficiently the initial variations of the color and lightness. Instead of extracting feature points in the standard gray space, we take advantage of the redistributed chromatic information to increase the distinctness of the neighbor regions of the keypoints. No assumptions are made about the geometry or chromatic content of the initial images. The extensive experiments prove the utility and robustness of the new scheme that is able to find a considerable number of additional valid matches.

Even though the color contains important distinctive information, it is mostly neglected in many fundamental vision applications (such as image matching) since the standard grayscale conversion (luminance channel) is employed extensively. This paper introduces a novel image decolorization technique that besides performing a perceptually accurate color mapping as the other state-of-the-art operators did, it focuses to increase as well the local contrast by manipulating effectively the chromatic information. Additionally, we perform an extensive evaluation of the several recent SIFT-derived local operators in context of image matching when the camera viewpoint is varied and images are differently decolorized based on several recent grayscale operators. The experiments prove the effectiveness of our approach that is able to decolorize accurately images but also to improve the matching results.

This papers introduces a new single image dehazing approach. The method employs a fusion-based strategy that takes as inputs two adapted versions of the original image that are weighted by speci??c maps in order to yield accurate hazefree results. The method computes in a per-pixel fashion being straightforward to be implemented. Our effective method demonstrates to yield comparative and even better results than the more complex state-of-the-art techniques but has the advantage to be appropriate for real-time applications.

In outdoor environments, light reflected from object surfaces is commonly scattered due to the impurities of the aerosol, or the presence of atmospheric phenomena such as fog and haze. Aside from scattering, the absorption coefficient presents another important factor that attenuates the reflected light of distant objects reaching the camera lens. As a result, images taken in bad weather conditions (or similarly, underwater and aerial photographs) are characterized by poor contrast, lower saturation and additional noise.

Many vision and graphics problems such as relighting, structured light scanning and photometric stereo, need images of a scene under a number of different illumination conditions. It is typically assumed that the scene is static. To extend such methods to dynamic scenes, dense optical flow can be used to register adjacent frames. This registration becomes inaccurate if the frame rate is too low with respect to the degree of movement in the scenes. We present a general method that extends time multiplexing with color multiplexing in order to better handle dynamic scenes. Our method allows for packing more illumination information into a single frame, thereby reducing the number of required frames over which optical flow must be computed. Moreover, color-multiplexed frames lend themselves better to reliably computing optical flow. We show that our method produces better results compared to time-multiplexing alone. We demonstrate its application to relighting, structured light scanning and photometric stereo in dynamic scenes.

We present an approach for recovering the reflectance of a static scene with known geometry from a collection of images taken under distant, unknown illumination. In contrast to previous work, we allow the illumination to vary between the images, which greatly increases the applicability of the approach. Using an all-frequency relighting framework based on wavelets, we are able to simultaneously estimate the per-image incident illumination and the persurface point reflectance. The wavelet framework allows for incorporating various reflection models. We demonstrate the quality of our results for synthetic test cases as well as for several datasets captured under laboratory conditions. Combined with multi-view stereo reconstruction, we are even able to recover the geometry and reflectance of a scene solely using images collected from the Internet.

In this paper we present a novel method for 3D structure acquisition, based on structured light. Unlike classical structured light methods, in which a static projector illuminates a scene with time-varying illumination patterns, our technique makes use of a moving projector emitting a static striped illumination pattern. This projector is translated at a constant velocity, in the direction of the projector's horizontal axis. Illuminating the object in this manner allows us to perform a per pixel analysis, in which we decompose the recorded illumination sequence into a corresponding set of frequency components. The dominant frequency in this set can be directly converted into a corresponding depth value. This per pixel analysis allows us to preserve sharp edges in the depth image. Unlike classical structured light methods, the quality of our results is not limited by projector or camera resolution, but is solely dependent on the temporal sampling density of the captured image sequence. Additional benefits include a significant robustness against common problems encountered with structured light methods, such as occlusions, specular reflections, subsurface scattering, interreflections, and to a certain extent projector defocus.

In this paper, we investigate discrete finite impulse response (FIR) filtering of images, while harnessing the powerful computational resources of next-generation GPUs. These novel platforms exhibit a massive data parallel architecture with an advanced SIMT execution model and thread management, to enable designers to better cope with the infamous memory wall, i.e. the growing gap between the cost of data communication and computational processing. However, the concerning platforms still have hard constraints that prevent trivial optimization of convolution filtering. Although automatic (compiler) optimization is available, we investigate and explain the speedup potential considering manual intervention, given the context of FIR kernels. Furthermore, we present multiple convolution implementation techniques that are able to cope with the hard platform constraints in different situations, while still being able to optimize the implementation to the underlying architecture. Utilizing the acquired insights, a view is given on the impact for possible optimization when loosening these hard constraints in the near future.

Recent efforts to accurately integrate properties of human visual perception have fueled an impressive improvement not only in digital photography but also in color manipulation tools. Color is one of the main attributes that influences human visual system, being ultimately the result of our experience and perception. However, several important applications such as substitution systems for visually impaired people, computerized tomography, printed textbooks and aesthetical stylization still require a reliable grayscale representation of images. Mapping three dimensional color information onto a single dimension while still preserving the original appearance, contrast and finest details is not a trivial task. Standard monochromatic transformations, found in commercial image editing software, neglect the color distribution, being unable to conserve in many cases the discriminability of the original chromatic contrast. Consequently, isoluminant colors are mapped to similar grayscale levels increasing the ambiguity in the decolorized image version. Although luminance is a definite value, our subjective interpretation that measures apparent brightness is very important in image decolorization process.

Abstract Restoration of the photographs damaged by the camera shake is a challenging task that manifested increasing attention in the recent period. Despite of the important progress of the blind deconvolution techniques, due to the ill‐posed nature of the problem, the finest details of the kernel blur cannot be recovered entirely. Moreover, the additional constraints and prior assumptions make these approaches to be relative limited. In this paper we introduce a novel technique that removes the undesired blur artifacts from photographs taken by hand‐held digital cameras. Our approach is based on the observation that in general several consecutive photographs taken by the users share image regions that project the same scene content. Therefore, we took advantage of additional sharp photographs of the same scene. Based on several invariant local feature points, filtered from the given blurred/non‐blurred images, our approach matches the keypoints and estimates the blur kernel using additional statistical constraints. We also present a simple deconvolution technique that preserves edges while minimizing the ringing artifacts in the restored latent image. The experimental results prove that our technique is able to infer accurately the blur kernel while reducing significantly the artifacts of the spoilt images.

The shape and reflectance of complex objects, for use in computer graphics applications, cannot always be acquired using specialized equipment due to cost or pratical considerations. We want to provide an easy and cost-effective way for the approximate recovery of both shape and spatially-varying reflectance of objects using commodity hardware. In this paper, we present an image-based technique for recovering 3D shape and spatially-varying reflectance properties from a sparse set of photographs, taken under varying illumination. Our technique models the reflectance with a set of low-parameter BRDFs without knowledge of the location of the light-sources or camera. This results an a flexible and portable system that can be used in the field. We successfully apply the approach to several objects (synthetic and real), recovering shape and reflectance. The acquired information can then be used to render the object with modifications to geometry and lighting via traditional rendering methods. 1

We propose a technique for cheap and efficient acquisition of mesostructure normal maps from specularities, which only requires a simple LCD monitor and a digital camera. Coded illumination enables us to capture subtle surface details with only a handful of images. In addition, our method can deal with heterogeneous surfaces, and high albedo materials. We are able to recover highly detailed mesostructures, which was previously only possible with an expensive hardware setup.

Abstract We present a novel multi‐view, projective texture mapping technique. While previous multi‐view texturing approaches lead to blurring and ghosting artefacts if 3D geometry and/or camera calibration are imprecise, we propose a texturing algorithm that warps (“floats”) projected textures during run‐time to preserve crisp, detailed texture appearance. Our GPU implementation achieves interactive to real‐time frame rates. The method is very generally applicable and can be used in combination with many image‐based rendering methods or projective texturing applications. By using Floating Textures in conjunction with, e.g., visual hull rendering, light field rendering, or free‐viewpoint video, improved rendering results are obtained from fewer input images, less accurately calibrated cameras, and coarser 3D geometry proxies.

Abstract Many video sequences consist of a locally dynamic background containing moving foreground subjects. In this paper we propose a novel way of re‐displaying these sequences, by giving the user control over a virtual camera frame. Based on video mosaicing, we first compute a static high quality background panorama. After segmenting and removing the foreground subjects from the original video, the remaining elements are merged into a dynamic background panorama, which seamlessly extends the original video footage. We then re‐display this augmented video by warping and cropping the panorama. The virtual camera can have an enlarged field‐of‐view and a controlled camera motion. Our technique is able to process videos with complex camera motions, reconstructing high quality panoramas without parallax artefacts, visible seams or blurring, while retaining repetitive dynamic elements.

Shadow computation in dynamic scenes under complex illumination is a challenging problem. Methods based on precomputation provide accurate, real-time solutions, but are hard to extend to dynamic scenes. Specialized approaches for soft shadows can deal with dynamic objects but are not fast enough to handle more than one light source. In this paper, we present a technique for rendering dynamic objects under arbitrary environment illumination, which does not require any precomputation. The key ingredient is a fast, approximate technique for computing soft shadows, which achieves several hundred frames per second for a single light source. This allows for approximating environment illumination with a sparse collection of area light sources and yields real-time frame rates.

In this paper, we present a high speed optical motion capture method that can measure three dimensional motion, orientation, and incident illumination at tagged points in a scene. We use tracking tags that work in natural lighting conditions and can be imperceptibly embedded in attire or other objects. Our system supports an unlimited number of tags in a scene, with each tag uniquely identified to eliminate marker reacquisition issues. Our tags also provide incident illumination data which can be used to match scene lighting when inserting synthetic elements. The technique is therefore ideal for on-set motion capture or real-time broadcasting of virtual sets. Unlike previous methods that employ high speed cameras or scanning lasers, we capture the scene appearance using the simplest possible optical devices - a light-emitting diode (LED) with a passive binary mask used as the transmitter and a photosensor used as the receiver. We strategically place a set of optical transmitters to spatio-temporally encode the volume of interest. Photosensors attached to scene points demultiplex the coded optical signals from multiple transmitters, allowing us to compute not only receiver location and orientation but also their incident illumination and the reflectance of the surfaces to which the photosensors are attached. We use our untethered tag system, called Prakash, to demonstrate methods of adding special effects to captured videos that cannot be accomplished using pure vision techniques that rely on camera images.

Abstract A novel approach is presented to efficiently render local subsurface scattering effects. We introduce an importance sampling scheme for a practical subsurface scattering model. It leads to a simple and efficient rendering algorithm, which operates in image space, and which is even amenable for implementation on graphics hardware. We demonstrate the applicability of our technique to the problem of skin rendering, for which the subsurface transport of light typically remains local. Our implementation shows that plausible images can be rendered interactively using hardware acceleration.

A novel approach is presented to efficiently render local subsurface scattering effects. We introduce an important sampling scheme for a practical subsurface scattering model. It leads to a simple and efficient rendering algorithm, which operates in image-space, and which is even amenable for implementation on graphics hardware. We demonstrate the applicability of our technique to the problem of skin rendering, for which the subsurface transport of light typically remains local. Our implementation shows that plausible images can be rendered interactively using hardware acceleration.

No abstract available.

Abstract This paper presents a rendering method for translucent objects, in which viewpoint and illumination can be modified at interactive rates. In a preprocessing step, the impulse response to incoming light impinging at each surface point is computed and stored in two different ways: The local effect on close‐by surface points is modeled as a per‐texel filter kernel that is applied to a texture map representing the incident illumination. The global response (i.e. light shining through the object) is stored as vertex‐to‐vertex throughput factors for the triangle mesh of the object. During rendering, the illumination map for the object is computed according to the current lighting situation and then filtered by the precomputed kernels. The illumination map is also used to derive the incident illumination on the vertices which is distributed via the vertex‐to‐vertex throughput factors to the other vertices. The final image is obtained by combining the local and global response. We demonstrate the performance of our method for several models. ACM CSS:I.3.7 Computer Graphics—Three‐Dimensional Graphics and Realism Color Radiosity

This paper presents a rendering method for translucent objects, in which view point and illumination can be modified at interactive rates. In a preprocessing step the impulse response to incoming light impinging at each surface point is computed and stored in two different ways: The local effect on close-by surface points is modeled as a per-texel filter kernel that is applied to a texture map representing the incident illumination. The global response (i.e. light shining through the object) is stored as vertex-to-vertex throughput factors for the triangle mesh of the object. During rendering, the illumination map for the object is computed according to the current lighting situation and then filtered by the precomputed kernels. The illumination map is also used to derive the incident illumination on the vertices which is distributed via the vertex-to-vertex throughput factors to the other vertices. The final image is obtained by combining the local and global response. We demonstrate the performance of our method for several models.

In this paper we present a new framework for the analysis of scene visibility and radiosity complexity. We introduce a number of complexity measures from information theory quantifying how difficult it is to compute with accuracy the visibility and radiosity in a scene. We define the continuous mutual information as a complexity measure of a scene, independent of whatever discretisation, and discrete mutual information as the complexity of a discretised scene. Mutual information can be understood as the degree of correlation or dependence between all the points or patches of a scene. Thus, low complexity corresponds to low correlation and vice versa. Experiments illustrating that the best mesh of a given scene among a number of alternatives corresponds to the one with the highest discrete mutual information, indicate the feasibility of the approach. Unlike continuous mutual information, which is very cheap to compute, the computation of discrete mutual information can however be quite demanding. We will develop cheap complexity measure estimates and derive practical algorithms from this framework in future work.

In this paper we present a new radiosity algorithm, based on the notion of a well distributed ray set (WDRS). A WDRS is a set of rays, connecting mutually visible points and patches, that forms an approximate representation of the radiosity operator and the radiosity distribution. We propose an algorithm that constructs an optimal WDRS for a given accuracy and mesh. The construction is based on discrete importance sampling as in previously proposed stochastic radiosity algorithms, and on quasi Monte Carlo sampling. Quasi Monte Carlo sampling leads to faster convergence rates and the fact that the sampling is deterministic makes it possible to represent the well distributed ray set very efficiently in computer memory. Like previously proposed stochastic radiosity algorithms, the new algorithm is well suited for computing the radiance distribution in very complex diffuse scenes, when it is not feasible to explicitly compute and store form factors as in classical radiosity algorithms. Experiments show that the new algorithm is often more efficient than previously proposed Monte Carlo radiosity algorithms by half an order of magnitude and more.