We present a technique for jointly denoising bursts of images taken from a handheld camera. In particular, we propose a convolutional neural network architecture for predicting spatially varying kernels that can both align and denoise frames, a synthetic data generation approach based on a realistic noise formation model, and an optimization guided by an annealed loss function to avoid undesirable local minima. Our model matches or outperforms the state-of-the-art across a wide range of noise levels on both real and synthetic data.

Shallow depth-of-field is commonly used by photographers to isolate a subject from a distracting background. However, standard cell phone cameras cannot produce such images optically, as their short focal lengths and small apertures capture nearly all-in-focus images. We present a system to computationally synthesize shallow depth-of-field images with a single mobile camera and a single button press. If the image is of a person, we use a person segmentation network to separate the person and their accessories from the background. If available, we also use dense dual-pixel auto-focus hardware, effectively a 2-sample light field with an approximately 1 millimeter baseline, to compute a dense depth map. These two signals are combined and used to render a defocused image. Our system can process a 5.4 megapixel image in 4 seconds on a mobile phone, is fully automatic, and is robust enough to be used by non-experts. The modular nature of our system allows it to degrade naturally in the absence of a dual-pixel sensor or a human subject.

Neuromorphic computing offers an attractive means for processing and learning complex real-world data. With the emergence of the memristor, the physical realization of cost-effective artificial neural networks is becoming viable, due to reduced area and increased performance metrics than strictly CMOS implementations. In the work presented here, memristors are utilized as synapses in the realization of a multi-purpose heterogeneous 3D neuromorphic fabric. This paper details our in-house memristor and 3D technologies in the design of a fabric that can perform real-world signal processing (i.e., image/video etc.) as well as everyday Boolean logic applications. The applicability of this fabric is therefore diverse with applications ranging from general-purpose and high performance logic computing to power-conservative image detection for mobile and defense applications. The proposed system is an area-effective heterogeneous 3D integration of memristive neural networks, that consumes significantly less power and allows for high speeds (3D ultra-high bandwidth connectivity) in comparison to a purely CMOS 2D implementation. Images and results provided will illustrate our state of the art 3D and memristor technology capabilities for the realization of the proposed 3D memristive neural fabric. Simulation results also show the results for mapping Boolean logic functions and images onto perceptron based neural networks. Results demonstrate the proof of concept of this system, which is the first step in the physical realization of the multi-purpose heterogeneous 3D memristive neuromorphic fabric.

Changing the color of an object is a basic image editing operation, but a high quality result must also preserve natural shading. A common approach is to first compute reflectance and illumination intrinsic images. Reflectances can then be edited independently, and recomposed with the illumination. However, manipulating only the reflectance color does not account for diffuse interreflections, and can result in inconsistent shading in the edited image. We propose an approach for further decomposing illumination into direct lighting, and indirect diffuse illumination from each material. This decomposition allows us to change indirect illumination from an individual material independently, so it matches the modified reflectance color. To address the underconstrained problem of decomposing illumination into multiple components, we take advantage of its smooth nature, as well as user-provided constraints. We demonstrate our approach on a number of examples, where we consistently edit material colors and the associated interreflections.

Painters and illustrators commonly sketch vanishing points and lines to guide the construction of perspective images. We present a tool that gives users the ability to manipulate perspective in photographs using image space controls similar to those used by artists. Our approach computes a 2D warp guided by constraints based on projective geometry. A user annotates an image by marking a number of image space constraints including planar regions of the scene, straight lines, and associated vanishing points. The user can then use the lines, vanishing points, and other point constraints as handles to control the warp. Our system optimizes the warp such that straight lines remain straight, planar regions transform according to a homography, and the entire mapping is as shape-preserving as possible. While the result of this warp is not necessarily an accurate perspective projection of the scene, it is often visually plausible. We demonstrate how this approach can be used to produce a variety of effects, such as changing the perspective composition of a scene, exploring artistic perspectives not realizable with a camera, and matching perspectives of objects from different images so that they appear consistent for compositing.

Any projection of a 3D scene into a wide-angle image unavoidably results in distortion. Current projection methods either bend straight lines in the scene, or locally distort the shapes of scene objects. We present a method that minimizes this distortion by adapting the projection to content in the scene, such as salient scene regions and lines, in order to preserve their shape. Our optimization technique computes a spatially-varying projection that respects user-specified constraints while minimizing a set of energy terms that measure wide-angle image distortion. We demonstrate the effectiveness of our approach by showing results on a variety of wide-angle photographs, as well as comparisons to standard projections.

This article presents a new dimensionally-reduced linear image space that allows a number of recent image manipulation techniques to be performed efficiently and robustly. The basis vectors spanning this space are constructed from a scale-adaptive image decomposition, based on kernels of the bilateral filter. Each of these vectors locally binds together pixels in smooth regions and leaves pixels across edges independent. Despite the drastic reduction in the number of degrees of freedom, this representation can be used to perform a number of recent gradient-based tonemapping techniques. In addition to reducing computation time, this space can prevent the bleeding artifacts which are common to Poisson-based integration methods. In addition, we show that this reduced representation is useful for energy-minimization methods in achieving efficient processing and providing better matrix conditioning at a minimal quality sacrifice.