Abstract We present a kernel‐predicting neural denoising method for path‐traced deep‐Z images that facilitates their usage in animation and visual effects production. Deep‐Z images provide enhanced flexibility during compositing as they contain color, opacity, and other rendered data at multiple depth‐resolved bins within each pixel. However, they are subject to noise, and rendering until convergence is prohibitively expensive. The current state of the art in deep‐Z denoising yields objectionable artifacts, and current neural denoising methods are incapable of handling the variable number of depth bins in deep‐Z images. Our method extends kernel‐predicting convolutional neural networks to address the challenges stemming from denoising deep‐Z images. We propose a hybrid reconstruction architecture that combines the depth‐resolved reconstruction at each bin with the flattened reconstruction at the pixel level. Moreover, we propose depth‐aware neighbor indexing of the depth‐resolved inputs to the convolution and denoising kernel application operators, which reduces artifacts caused by depth misalignment present in deep‐Z images. We evaluate our method on a production‐quality deep‐Z dataset, demonstrating significant improvements in denoising quality and performance compared to the current state‐of‐the‐art deep‐Z denoiser. By addressing the significant challenge of the cost associated with rendering path‐traced deep‐Z images, we believe that our approach will pave the way for broader adoption of deep‐Z workflows in future productions.

ReLU networks have remained the default choice for models in the area of image prediction despite their well-established spectral bias towards learning low frequencies faster, and consequently their difficulty of reproducing high frequency visual details. As an alternative, sin networks showed promising results in learning implicit representations of visual data. However training these networks in practically relevant settings proved to be difficult, requiring careful initialization, dealing with issues due to inconsistent gradients, and a degeneracy in local minima. In this work, we instead propose replacing a baseline network’s existing activations with a novel ensemble function with trainable parameters. The proposed MetaSin activation can be trained reliably without requiring intricate initialization schemes, and results in consistently lower test loss compared to alternatives. We demonstrate our method in the areas of Monte-Carlo denoising and image resampling where we set new state-of-the-art through a knowledge distillation based training procedure. We present ablations on hyper-parameter settings, comparisons with alternative activation function formulations, and discuss the use of our method in other domains, such as image classification.

Abstract We study the problem of High Dynamic Range (HDR) image reconstruction from a Standard Dynamic Range (SDR) input with potential clipping artifacts. Instead of building a direct model that maps from SDR to HDR images as in previous work, we decompose an input SDR image into a base (low frequency) and detail layer (high frequency), and treat reconstructing these two layers as two separate problems. We propose a novel architecture that comprises individual components specially designed to handle both tasks. Specifically, our base layer reconstruction component recovers low frequency content and remaps the color gamut of the input SDR, whereas our detail layer reconstruction component, which builds upon prior work on image inpainting, hallucinates missing texture information. The output HDR prediction is produced by a final refinement stage. We present qualitative and quantitative comparisons with existing techniques where our method achieves state‐of‐the‐art performance.

The goal of natural image matting is the estimation of opacities of a user-defined foreground object that is essential in creating realistic composite imagery. Natural matting is a challenging process due to the high number of unknowns in the mathematical modeling of the problem, namely the opacities as well as the foreground and background layer colors, while the original image serves as the single observation. In this paper, we propose the estimation of the layer colors through the use of deep neural networks prior to the opacity estimation. The layer color estimation is a better match for the capabilities of neural networks, and the availability of these colors substantially increase the performance of opacity estimation due to the reduced number of unknowns in the compositing equation. A prominent approach to matting in parallel to ours is called sampling-based matting, which involves gathering color samples from known-opacity regions to predict the layer colors. Our approach outperforms not only the previous hand-crafted sampling algorithms, but also current data-driven methods. We hence classify our method as a hybrid sampling- and learning-based approach to matting, and demonstrate the effectiveness of our approach through detailed ablation studies using alternative network architectures.

We consider the chromaticity in high dynamic range (HDR) video coding and show the advantages of a constant luminance color space for encoding. For this, we introduce two constant luminance HDR video coding pipelines, which convert the source video to linear Yu'v'. A content dependent scaling of the chromaticity components serves as color quality parameter. This reduces perceivable color artifacts while remaining fully compatible with core High Efficiency Video Coding or other video coding standards. One of the pipelines further combines the scaling with a dedicated chromaticity transform to optimize the representation of the chromaticity components for encoding. We validate both pipelines with subjective user studies in addition to an objective comparison to the other state-of-the-art methods. The user studies show a significant improvement in perceived color quality at medium to high compression rates without sacrificing luminance quality compared with current standard coding pipelines. The objective evaluation suggests that both pipelines perform at least comparable to the current state-of-the-art methods.

We present a novel, purely affinity-based natural image matting algorithm. Our method relies on carefully defined pixel-to-pixel connections that enable effective use of information available in the image and the trimap. We control the information flow from the known-opacity regions into the unknown region, as well as within the unknown region itself, by utilizing multiple definitions of pixel affinities. This way we achieve significant improvements on matte quality near challenging regions of the foreground object. Among other forms of information flow, we introduce color-mixture flow, which builds upon local linear embedding and effectively encapsulates the relation between different pixel opacities. Our resulting novel linear system formulation can be solved in closed-form and is robust against several fundamental challenges in natural matting such as holes and remote intricate structures. While our method is primarily designed as a standalone natural matting tool, we show that it can also be used for regularizing mattes obtained by various sampling-based methods. Our evaluation using the public alpha matting benchmark suggests a significant performance improvement over the state-of-the-art.

We present a new method for decomposing an image into a set of soft color segments that are analogous to color layers with alpha channels that have been commonly utilized in modern image manipulation software. We show that the resulting decomposition serves as an effective intermediate image representation, which can be utilized for performing various, seemingly unrelated, image manipulation tasks. We identify a set of requirements that soft color segmentation methods have to fulfill, and present an in-depth theoretical analysis of prior work. We propose an energy formulation for producing compact layers of homogeneous colors and a color refinement procedure, as well as a method for automatically estimating a statistical color model from an image. This results in a novel framework for automatic and high-quality soft color segmentation that is efficient, parallelizable, and scalable. We show that our technique is superior in quality compared to previous methods through quantitative analysis as well as visually through an extensive set of examples. We demonstrate that our soft color segments can easily be exported to familiar image manipulation software packages and used to produce compelling results for numerous image manipulation applications without forcing the user to learn new tools and workflows.

Subjective studies showed that most HDR video tone mapping operators either produce disturbing temporal artifacts, or are limited in their local contrast reproduction capability. Recently, both these issues have been addressed by a novel temporally coherent local HDR tone mapping method, which has been shown, both qualitatively and through a subjective study, to be advantageous compared to previous methods. However, this method's high-quality results came at the cost of a computationally expensive workflow that could only be executed offline. In this paper, we present a modified algorithm which builds upon the previous work by redesigning key components to achieve real-time performance. We accomplish this by replacing the optical flow based per-pixel temporal coherency with a tone-curve-space alternative. This way we eliminate the main computational burden of the original method with little sacrifice in visual quality.

We introduce a constant luminance HDR video coding pipeline, which converts the source video to linear Y u'v' color space and applies a dedicated chromaticity transformation before encoding. This reduces perceivable color artifacts without modifying the core codec itself. We validate our approach by a user study that shows a significant improvement in perceived color quality at high compression rates without sacrificing luminance quality compared to current standard coding pipelines.

Due to the widespread use of compositing in contemporary feature films, green-screen keying has become an essential part of postproduction workflows. To comply with the ever-increasing quality requirements of the industry, specialized compositing artists spend countless hours using multiple commercial software tools, while eventually having to resort to manual painting because of the many shortcomings of these tools. Due to the sheer amount of manual labor involved in the process, new green-screen keying approaches that produce better keying results with less user interaction are welcome additions to the compositing artist’s arsenal. We found that—contrary to the common belief in the research community—production-quality green-screen keying is still an unresolved problem with its unique challenges. In this article, we propose a novel green-screen keying method utilizing a new energy minimization-based color unmixing algorithm. We present comprehensive comparisons with commercial software packages and relevant methods in literature, which show that the quality of our results is superior to any other currently available green-screen keying solution. It is important to note that, using the proposed method, these high-quality results can be generated using only one-tenth of the manual editing time that a professional compositing artist requires to process the same content having all previous state-of-the-art tools at one’s disposal.

Existing tone mapping operators (TMOs) provide good results in well-lit scenes, but often perform poorly on im-ages in low light conditions. In these scenes, noise is prevalent and gets amplified by TMOs, as they confuse contrast created by noise with contrast created by the scene. This paper presents a principled approach to produce tone mapped images with less visible noise. For this purpose, we leverage established models of camera noise and human contrast perception to design two new quality scores: contrast waste and contrast loss, which measure image quality as a function of contrast allocation. To produce tone mappings with less visible noise, we apply these scores in two ways: first, to automatically tune the parameters of existing TMOs to reduce the amount of noise they produce; and second, to propose a new noise-aware tone curve

High dynamic range (HDR) display prototypes have been built and used for scientific studies for nearly a decade, and they are now on the verge of entering consumer market. However, problems exist regarding the accurate color reproduction capabilities on these displays. In this paper, we first characterize the color reproduction capability of a state-of-art HDR display through a set of measurements, and present a novel calibration method that takes into account the variation of the chrominance error over HDR display's wide luminance range. Our proposed 3D octree forest data structure for representing and querying the calibration function successfully addresses the challenges in calibrating HDR displays: (i) high computational complexity due to nonlinear chromatic distortions, and (ii) huge storage space demand for a look-up table (35GB vs 100kB). We show that our method achieves high color reproduction accuracy through both objective metrics and a controlled subjective study.

We present a perceptually calibrated system for automatic aesthetic evaluation of photographic images. Our work builds upon the concepts of no-reference image quality assessment, with the main difference being our focus on rating image aesthetic attributes rather than detecting image distortions. In contrast to the recent attempts on the highly subjective aesthetic judgment problems such as binary aesthetic classification and the prediction of an image's overall aesthetics rating, our method aims on providing a reliable objective basis of comparison between aesthetic properties of different photographs. To that end our system computes perceptually calibrated ratings for a set of fundamental and meaningful aesthetic attributes, that together form an "aesthetic signature" of an image. We show that aesthetic signatures can still be used to improve upon the current state-of-the-art in automatic aesthetic judgment, but also enable interesting new photo editing applications such as automated aesthetic analysis, HDR tone mapping evaluation, and providing aesthetic feedback during multi-scale contrast manipulation.

Abstract We present a novel stereo‐to‐multiview video conversion method for glasses‐free multiview displays. Different from previous stereo‐to‐multiview approaches, our mapping algorithm utilizes the limited depth range of autostereoscopic displays optimally and strives to preserve the scene's artistic composition and perceived depth even under strong depth compression. We first present an investigation of how perceived image quality relates to spatial frequency and disparity. The outcome of this study is utilized in a two‐step mapping algorithm, where we (i) compress the scene depth using a non‐linear global function to the depth range of an autostereoscopic display and (ii) enhance the depth gradients of salient objects to restore the perceived depth and salient scene structure. Finally, an adapted image domain warping algorithm is proposed to generate the multiview output, which enables overall disparity range extension.

Recent subjective studies showed that current tone mapping operators either produce disturbing temporal artifacts, or are limited in their local contrast reproduction capability. We address both of these issues and present an HDR video tone mapping operator that can greatly reduce the input dynamic range, while at the same time preserving scene details without causing significant visual artifacts. To achieve this, we revisit the commonly usedspatialbase-detail layer decomposition and extend it to thetemporal domain. We achieve high quality spatiotemporal edge-aware filtering efficiently by using a mathematically justified iterative approach that approximates a global solution. Comparison with the state-of-the-art, both qualitatively, and quantitatively through a controlled subjective experiment, clearly shows our method's advantages over previous work. We present local tone mapping results on challenging high resolution scenes with complex motion and varying illumination. We also demonstrate our method's capability of preserving scene details at user adjustable scales, and its advantages for low light video sequences with significant camera noise.

Abstract Synthetically generating images and video frames of complex 3D scenes using some photo‐realistic rendering software is often prone to artifacts and requires expert knowledge to tune the parameters. The manual work required for detecting and preventing artifacts can be automated through objective quality evaluation of synthetic images. Most practical objective quality assessment methods of natural images rely on a ground‐truth reference, which is often not available in rendering applications. While general purpose no‐reference image quality assessment is a difficult problem, we show in a subjective study that the performance of a dedicated no‐reference metric as presented in this paper can match the state‐of‐the‐art metrics that do require a reference. This level of predictive power is achieved exploiting information about the underlying synthetic scene (e.g., 3D surfaces, textures) instead of merely considering color, and training our learning framework with typical rendering artifacts. We show that our method successfully detects various non‐trivial types of artifacts such as noise and clamping bias due to insufficient virtual point light sources, and shadow map discretization artifacts. We also briefly discuss an inpainting method for automatic correction of detected artifacts.

We present an efficient and simple method for introducing temporal consistency to a large class of optimization driven image-based computer graphics problems. Our method extends recent work in edge-aware filtering, approximating costly global regularization with a fast iterative joint filtering operation. Using this representation, we can achieve tremendous efficiency gains both in terms of memory requirements and running time. This enables us to process entire shots at once, taking advantage of supporting information that exists across far away frames, something that is difficult with existing approaches due to the computational burden of video data. Our method is able to filter along motion paths using an iterative approach that simultaneously uses and estimates per-pixel optical flow vectors. We demonstrate its utility by creating temporally consistent results for a number of applications including optical flow, disparity estimation, colorization, scribble propagation, sparse data up-sampling, and visual saliency computation.

Retargeting refers to the process by which an image or video is adapted from the display device for which it was meant (target display) to another one (retarget display). The retarget display has different features from the target one such as dynamic range, discretization levels, color gamut, multi-view, and refresh rate spatial resolution. This is a very relevant topic in graphics, given the increasing number of display devices from large, high-contrast screens to small cell phones with limited dynamic range; a lot of techniques are being published in different venues, and it's hard to keep up. For most cases retargeting can be an ill-posed problem, for example in the process of displaying Low Dynamic Range (LDR) or 8-bit content on High Dynamic Range (HDR) displays. Such a problem requires the retargeting algorithm to generate new content which is missing in the input image/frame. In this course, we will present the latest solutions and techniques for retargeting images along various dimensions such as dynamic range, colors, temporal and spatial resolutions, and for the first time offer a much-needed holistic view of the field. Moreover, we are going to show how to measure and analyze the changes applied to an image or video in terms of quality using both psychophysical experiments (subjective) and computational metrics (objective). The course should be of interest to anyone involved in graphics in a broader sense, given the almost unavoidable need to retarget results to different devices -from developers interested in implementing retargeting techniques, to users that just need an overall perspective. For researchers fully engaged in developing multi-dimensional retargeting techniques, this course will serve as a solid background for future algorithms.

Numerous image processing and computer graphics methods make use of either explicitly computed strength of image edges, or an implicit edge strength definition that is integrated into their algorithms. In both cases, the end result is highly affected by the computation of edge strength. We address several shortcomings of the widely used gradient magnitude-based edge strength model through the computation of a hypothetical Human Visual System (HVS) response at edge locations. Contrary to gradient magnitude, the resulting “visual significance” values account for various HVS mechanisms such as luminance adaptation and visual masking, and are scaled in perceptually linear units that are uniform across images. The visual significance computation is implemented in a fast multiscale second-generation wavelet framework which we use to demonstrate the differences in image retargeting, HDR image stitching, and tone mapping applications with respect to the gradient magnitude model. Our results suggest that simple perceptual models provide qualitative improvements on applications utilizing edge strength at the cost of a modest computational burden.

Numerous current Computer Graphics methods produce video sequences as their outcome. The merit of these methods is often judged by assessing the quality of a set of results through lengthy user studies. We present a full-reference video quality metric geared specifically towards the requirements of Computer Graphics applications as a faster computational alternative to subjective evaluation. Our metric can compare a video pair with arbitrary dynamic ranges, and comprises a human visual system model for a wide range of luminance levels, that predicts distortion visibility through models of luminance adaptation, spatiotemporal contrast sensitivity and visual masking. We present applications of the proposed metric to quality prediction of HDR video compression and temporal tone mapping, comparison of different rendering approaches and qualities, and assessing the impact of variable frame rate to perceived quality.

Abstract Display devices, more than ever, are finding their ways into electronic consumer goods as a result of recent trends in providing more functionality and user interaction. Combined with the new developments in display technology towards higher reproducible luminance range, the mobility and variation in capability of display devices are constantly increasing. Consequently, in real life usage it is now very likely that the display emission to be distorted by spatially and temporally varying reflections, and the observer's visual system to be not adapted to the particular display that she is viewing at that moment. The actual perception of the display content cannot be fully understood by only considering steady‐state illumination and adaptation conditions. We propose an objective method for display visibility analysis formulating the problem as a full‐reference image quality assessment problem, where the display emission under “ideal” conditions is used as the reference for real‐life conditions. Our work includes a human visual system model that accounts for maladaptation and temporal recovery of sensitivity. As an example application we integrate our method to a global illumination simulator and analyze the visibility of a car interior display under realistic lighting conditions.

The diversity of display technologies and introduction of high dynamic range imagery introduces the necessity of comparing images of radically different dynamic ranges. Current quality assessment metrics are not suitable for this task, as they assume that both reference and test images have the same dynamic range. Image fidelity measures employed by a majority of current metrics, based on the difference of pixel intensity or contrast values between test and reference images, result in meaningless predictions if this assumption does not hold. We present a novel image quality metric capable of operating on an image pair where both images have arbitrary dynamic ranges. Our metric utilizes a model of the human visual system, and its central idea is a new definition of visible distortion based on the detection and classification of visible changes in the image structure. Our metric is carefully calibrated and its performance is validated through perceptual experiments. We demonstrate possible applications of our metric to the evaluation of direct and inverse tone mapping operators as well as the analysis of the image appearance on displays with various characteristics.