Dilip Krishnan

Blind deconvolution using a normalized sparsity measure

Blind image deconvolution is an ill-posed problem that requires regularization to solve. However, many common forms of image prior used in this setting have a major drawback in that the minimum of the resulting cost function does not correspond to the true sharp solution. Accordingly, a range of additional methods are needed to yield good results (Bayesian methods, adaptive cost functions, alpha-matte extraction and edge localization). In this paper we introduce a new type of image regularization which gives lowest cost for the true sharp image. This allows a very simple cost formulation to be used for the blind deconvolution model, obviating the need for additional methods. Due to its simplicity the algorithm is fast and very robust. We demonstrate our method on real images with both spatially invariant and spatially varying blur.

Restoring an Image Taken through a Window Covered with Dirt or Rain

Photographs taken through a window are often compromised by dirt or rain present on the window surface. Common cases of this include pictures taken from inside a vehicle, or outdoor security cameras mounted inside a protective enclosure. At capture time, defocus can be used to remove the artifacts, but this relies on achieving a shallow depth-of-field and placement of the camera close to the window. Instead, we present a post-capture image processing solution that can remove localized rain and dirt artifacts from a single image. We collect a dataset of clean/corrupted image pairs which are then used to train a specialized form of convolutional neural network. This learns how to map corrupted image patches to clean ones, implicitly capturing the characteristic appearance of dirt and water droplets in natural images. Our models demonstrate effective removal of dirt and rain in outdoor test conditions.

Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks

Collecting well-annotated image datasets to train modern machine learning algorithms is prohibitively expensive for many tasks. One appealing alternative is rendering synthetic data where ground-truth annotations are generated automatically. Unfortunately, models trained purely on rendered images fail to generalize to real images. To address this shortcoming, prior work introduced unsupervised domain adaptation algorithms that have tried to either map representations between the two domains, or learn to extract features that are domain-invariant. In this work, we approach the problem in a new light by learning in an unsupervised manner a transformation in the pixel space from one domain to the other. Our generative adversarial network (GAN)-based method adapts source-domain images to appear as if drawn from the target domain. Our approach not only produces plausible samples, but also outperforms the state-of-the-art on a number of unsupervised domain adaptation scenarios by large margins. Finally, we demonstrate that the adaptation process generalizes to object classes unseen during training.

Crisp Boundary Detection Using Pointwise Mutual Information

Detecting boundaries between semantically meaningful objects in visual scenes is an important component of many vision algorithms. In this paper, we propose a novel method for detecting such boundaries based on a simple underlying principle: pixels belonging to the same object exhibit higher statistical dependencies than pixels belonging to different objects. We show how to derive an affinity measure based on this principle using pointwise mutual information, and we show that this measure is indeed a good predictor of whether or not two pixels reside on the same object. Using this affinity with spectral clustering, we can find object boundaries in the image – achieving state-of-the-art results on the BSDS500 dataset. Our method produces pixel-level accurate boundaries while requiring minimal feature engineering.

Efficient preconditioning of laplacian matrices for computer graphics

We present a new multi-level preconditioning scheme for discrete Poisson equations that arise in various computer graphics applications such as colorization, edge-preserving decomposition for two-dimensional images, and geodesic distances and diffusion on three-dimensional meshes. Our approach interleaves the selection of fine-and coarse-level variables with the removal of weak connections between potential fine-level variables (sparsification) and the compensation for these changes by strengthening nearby connections. By applying these operations before each elimination step and repeating the procedure recursively on the resulting smaller systems, we obtain a highly efficient multi-level preconditioning scheme with linear time and memory requirements. Our experiments demonstrate that our new scheme outperforms or is comparable with other state-of-the-art methods, both in terms of operation count and wall-clock time. This speedup is achieved by the new methods ability to reduce the condition number of irregular Laplacian matrices as well as homogeneous systems. It can therefore be used for a wide variety of computational photography problems, as well as several 3D mesh processing tasks, without the need to carefully match the algorithm to the problem characteristics.

Learning Ordinal Relationships for Mid-Level Vision

We propose a framework that infers mid-level visual properties of an image by learning about ordinal relationships. Instead of estimating metric quantities directly, the system proposes pairwise relationship estimates for points in the input image. These sparse probabilistic ordinal measurements are globalized to create a dense output map of continuous metric measurements. Estimating order relationships between pairs of points has several advantages over metric estimation: it solves a simpler problem than metric regression, humans are better at relative judgements, so data collection is easier, ordinal relationships are invariant to monotonic transformations of the data, thereby increasing the robustness of the system and providing qualitatively different information. We demonstrate that this frame-work works well on two important mid-level vision tasks: intrinsic image decomposition and depth from an RGB image. We train two systems with the same architecture on data from these two modalities. We provide an analysis of the resulting models, showing that they learn a number of simple rules to make ordinal decisions. We apply our algorithm to depth estimation, with good results, and intrinsic image decomposition, with state-of-the-art results.

Reflection removal using ghosting cues

Photographs taken through glass windows often contain both the desired scene and undesired reflections. Separating the reflection and transmission layers is an important but ill-posed problem that has both aesthetic and practical applications. In this work, we introduce the use of ghosting cues that exploit asymmetry between the layers, thereby helping to reduce the ill-posedness of the problem. These cues arise from shifted double reflections of the reflected scene off the glass surface. In double-pane windows, each pane reflects shifted and attenuated versions of objects on the same side of the glass as the camera. For single-pane windows, ghosting cues arise from shifted reflections on the two surfaces of the glass pane. Even though the ghosting is sometimes barely perceptible by humans, we can still exploit the cue for layer separation. In this work, we model the ghosted reflection using a double-impulse convolution kernel, and automatically estimate the spatial separation and relative attenuation of the ghosted reflection components. To separate the layers, we propose an algorithm that uses a Gaussian Mixture Model for regularization. Our method is automatic and requires only a single input image. We demonstrate that our approach removes a large fraction of reflections on both synthetic and real-world inputs.

Multigrid and multilevel preconditioners for computational photography

This paper unifies multigrid and multilevel (hierarchical) preconditioners, two widely-used approaches for solving computational photography and other computer graphics simulation problems. It provides detailed experimental comparisons of these techniques and their variants, including an analysis of relative computational costs and how these impact practical algorithm performance. We derive both theoretical convergence rates based on the condition numbers of the systems and their preconditioners, and empirical convergence rates drawn from real-world problems. We also develop new techniques for sparsifying higher connectivity problems, and compare our techniques to existing and newly developed variants such as algebraic and combinatorial multigrid. Our experimental results demonstrate that, except for highly irregular problems, adaptive hierarchical basis function preconditioners generally outperform alternative multigrid techniques, especially when computational complexity is taken into account.

Visualizing Dataflow Graphs of Deep Learning Models in TensorFlow

We present a design study of the TensorFlow Graph Visualizer, part of the TensorFlow machine intelligence platform. This tool helps users understand complex machine learning architectures by visualizing their underlying dataflow graphs. The tool works by applying a series of graph transformations that enable standard layout techniques to produce a legible interactive diagram. To declutter the graph, we decouple non-critical nodes from the layout. To provide an overview, we build a clustered graph using the hierarchical structure annotated in the source code. To support exploration of nested structure on demand, we perform edge bundling to enable stable and responsive cluster expansion. Finally, we detect and highlight repeated structures to emphasize a models modular composition. To demonstrate the utility of the visualizer, we describe example usage scenarios and report user feedback. Overall, users find the visualizer useful for understanding, debugging, and sharing the structures of their models.

Synthesizing Normalized Faces from Facial Identity Features

We present a method for synthesizing a frontal, neutral-expression image of a persons face, given an input face photograph. This is achieved by learning to generate facial landmarks and textures from features extracted from a facial-recognition network. Unlike previous generative approaches, our encoding feature vector is largely invariant to lighting, pose, and facial expression. Exploiting this invariance, we train our decoder network using only frontal, neutral-expression photographs. Since these photographs are well aligned, we can decompose them into a sparse set of landmark points and aligned texture maps. The decoder then predicts landmarks and textures independently and combines them using a differentiable image warping operation. The resulting images can be used for a number of applications, such as analyzing facial attributes, exposure and white balance adjustment, or creating a 3-D avatar.