Abstract: Image editing techniques are disclosed that support a number of physically-based image editing tasks, including object insertion and relighting. The techniques can be implemented, for example in an image editing application that is executable on a computing system. In one such embodiment, the editing application is configured to compute a scene from a single image, by automatically estimating dense depth and diffuse reflectance, which respectively form the geometry and surface materials of the scene. Sources of illumination are then inferred, conditioned on the estimated scene geometry and surface materials and without any user input, to form a complete 3D physical scene model corresponding to the image. The scene model may include estimates of the geometry, illumination, and material properties represented in the scene, and various camera parameters. Using this scene model, objects can be readily inserted and composited into the input image with realistic lighting, shadowing, and perspective.

Abstract: Paintbrush and liquid simulation techniques are described. In one or more implementations, input is received to perform brush strokes with a virtual paintbrush on a virtual canvas. For virtual paint on the virtual canvas, lifelike paint qualities are simulated. However, the lifelike paint qualities are simulated solely for the virtual paint that is within a region of the canvas. The lifelike paint qualities are not simulated for virtual paint located outside the region. As part of simulating the interaction between the virtual paint, the virtual paintbrush, and the virtual canvas, various parts of the simulation may be performed by different processing units. For example, bristles of the virtual paintbrush may be simulated utilizing a first processing device such as a central processing unit (CPU). A second processing unit, such as a graphics processing unit (GPU), may be employed to simulate the lifelike effects of the virtual paint.

Abstract: Image editing techniques are disclosed that support a number of physically-based image editing tasks, including object insertion and relighting. The techniques can be implemented, for example in an image editing application that is executable on a computing system. In one such embodiment, the editing application is configured to compute a scene from a single image, by automatically estimating dense depth and diffuse reflectance, which respectively form the geometry and surface materials of the scene. Sources of illumination are then inferred, conditioned on the estimated scene geometry and surface materials and without any user input, to form a complete 3D physical scene model corresponding to the image. The scene model may include estimates of the geometry, illumination, and material properties represented in the scene, and various camera parameters. Using this scene model, objects can be readily inserted and composited into the input image with realistic lighting, shadowing, and perspective.

Abstract: Alignment techniques are described that automatically align multiple scans of an object obtained from different perspectives. Instead of relying solely on errors in local feature matching between a pair of scans to identify a best possible alignment, additional alignment possibilities may be considered. Grouped keypoint features of the pair of scans may be compared to keypoint features of an additional scan to determine an error between the respective keypoint features. Various alignment techniques may utilize the error to determine an optimal alignment for the scans.

Abstract: Dynamic motion path blur techniques are described. In one or more implementations, paths may be specified to constrain a motion blur effect to be applied to a single image. A variety of different techniques may be employed as part of the motion blur effects, including use of curved blur kernel shapes, use of a mesh representation of blur kernel parameter fields to support real time output of the motion blur effect to an image, use of flash effects, blur kernel positioning to support centered or directional blurring, tapered exposure modeling, and null paths.

Abstract: Dynamic motion path blur techniques are described. In one or more implementations, paths may be specified to constrain a motion blur effect to be applied to a single image. A variety of different techniques may be employed as part of the motion blur effects, including use of curved blur kernel shapes, use of a mesh representation of blur kernel parameter fields to support real time output of the motion blur effect to an image, use of flash effects, blur kernel positioning to support centered or directional blurring, tapered exposure modeling, and null paths.

Abstract: Dynamic motion path blur techniques are described. In one or more implementations, paths may be specified to constrain a motion blur effect to be applied to a single image. A variety of different techniques may be employed as part of the motion blur effects, including use of curved blur kernel shapes, use of a mesh representation of blur kernel parameter fields to support real time output of the motion blur effect to an image, use of flash effects, blur kernel positioning to support centered or directional blurring, tapered exposure modeling, and null paths.

Abstract: Blending techniques for curve fitting are described. In one or more implementations, an indication is received of three or more data points. A blending factor is computed based on a spatial relationship of the three or more data points to each other. A curve is fit to the three or more data points by blending a plurality or curve fitting techniques using the computed blending factor.

Abstract: This document describes techniques and apparatuses for 3D printing with small geometric offsets to affect surface characteristics. These techniques are capable of enabling fused-deposition printers to create 3D objects having desired surface characteristics, such as particular colors, images and image resolutions, textures, and luminosities. In some cases, the techniques do so using a single filament head with a single filament material. In some other cases, the techniques do so using multiple heads each with different filaments, though the techniques can forgo many switches between these heads. Each printing layer may use even a single filament from one head, thereby enabling surface characteristics while reducing starts and stops for filaments heads, which enables fewer artifacts or increases printing speed.

Abstract: Example systems and methods of providing a user interface are presented. In one example, a graphical object is displayed on an opaque display component on a user-facing side of a computing device. Using a sensing component of the computing device, movement of a physical pointer controlled by a user is sensed. The physical pointer may be located opposite the user-facing side of the computing device. On the opaque display component, a representation of the physical pointer is displayed during the movement of the physical pointer. The graphical object, as displayed on the opaque display component, is modified based on the sensed movement of the physical pointer during the movement of the physical pointer.

Abstract: Texture modeling techniques for image data are described. In one or more implementations, texels in image data are discovered by one or more computing devices, each texel representing an element that repeats to form a texture pattern in the image data. Regularity of the texels in the image data is modeled by the one or more computing devices to define translations and at least one other transformation of texels in relation to each other.

Abstract: Methods and apparatus for interactive curve-based freeform deformation of three-dimensional (3-D) models may provide a user interface that allows a user to interactively deform 3-D models based on simple and intuitive manipulations of a curve drawn on the model (i.e., freeform deformation). The user may apply freeform deformations using touch and/or multitouch gestures to specify and manipulate a deformation curve. The deformations may be applied by deforming the space around a curve/sweep path and deforming the 3-D model accordingly. The freeform deformation methods are not dependent on manipulation of a fixed set of parameters to perform deformations, and may provide for both local and global deformation. One or more weights and user interface elements for controlling those weights may be provided that allow the user to control the extent (region of influence) of the freeform deformations along the curve and/or perpendicular to the curve.

Abstract: Parametric curve fitting using maximum curvature techniques are described. In one or more implementations, a parametric curve is fit to a segment of a plurality of data points that includes a first data point disposed between second and third data points by setting a point of maximum curvature for the segment of the curve at the first data point. A result of the fitting is output by the computing device.

Abstract: Image editing techniques are disclosed that support a number of physically-based image editing tasks, including object insertion and relighting. The techniques can be implemented, for example in an image editing application that is executable on a computing system. In one such embodiment, the editing application is configured to compute a scene from a single image, by automatically estimating dense depth and diffuse reflectance, which respectively form the geometry and surface materials of the scene. Sources of illumination are then inferred, conditioned on the estimated scene geometry and surface materials and without any user input, to form a complete 3D physical scene model corresponding to the image. The scene model may include estimates of the geometry, illumination, and material properties represented in the scene, and various camera parameters. Using this scene model, objects can be readily inserted and composited into the input image with realistic lighting, shadowing, and perspective.

Abstract: A method, system, and computer-readable storage medium are disclosed for adaptive sampling guided by multilateral filtering. A plurality of versions of a first image are generated. Each of the plurality of versions of the first image has a respective different resolution. A respective priority map is generated for each of the plurality of versions of the first image. Each respective priority map identifies a plurality of high-priority regions in a corresponding one of the plurality of versions of the first image. A second image is rendered based on the priority maps. The rendering comprises performing a ray-tracing process having a greater number of samples per pixel for the high-priority regions of the second image than for other regions of the second image.

Abstract: Methods and apparatus for providing Sobolev pre-conditioning for optimizing ill-conditioned functionals. A power n is initialized to a maximum power (e.g., 8). For k (e.g., 10) iterations of an optimization pipeline, a matrix M is built by considering all powers of the Laplacian matrix up to the power indicated by n, the Sobolev gradient is computed from the standard gradient, and the computed Sobolev gradient is passed to a numerical optimizer. After the k iterations are complete, if n is at a minimum power (e.g., 1), then the algorithm resets n to the maximum power. Otherwise, n is decremented. For the next k iterations, the matrix M is again built by considering all powers of the Laplacian matrix up to the power indicated by the current value of n. This method is continued until all iterations have completed or until some other terminating condition is reached.

Abstract: Methods and apparatus for generating an n-sided patch by sketching on a three-dimensional reference surface. A user draws a closed curve on a 3D surface; the drawn outline is taken as a boundary for an N-sided patch. If the user does not close the curve, the system may automatically close the curve, as a closed outer boundary curve may be required to produce an N-sided patch. The boundary conditions, the positions, and the surface normals at the boundary are inferred automatically from the 3D surface that the user has drawn the curve on. In addition, boundary curves for the same patch may be drawn on different 3D shapes; multiple 3D shapes may be used as the template or canvas on which the user draws curves from which a patch is to be generated.

Abstract: Various embodiments of a method and apparatus for creating editable feature curves for a multi-dimensional model represented by a tessellated mesh are described. A mesh representation of a multi-dimensional model may not support intuitive modification of the model. The mesh representing the multi-dimensional model may be analyzed to extract feature curves that define the characteristics of the multi-dimensional model. Such feature curves may provide an intuitive mechanism for modifying the multi-dimensional model. The model may be modified by changing the constraints of the feature curves defining the model's characteristics. For example, a constraint may be modified to change the angle of the surface on either side of a location on a feature curve. A compressed representation of a multi-dimensional model may include the feature curves that define the shape of multi-dimensional model and a set of boundary curves that represent disjoint regions of the multi-dimensional model.

Abstract: Methods and apparatus for deactivating internal constraint curves when inflating an N-Sided patch. Given a patch representation, the methods simplify the construction of 3D models from 2D sketches. At least some interior constraint curves may be deactivated when inflating an N-sided patch generated from a 2D sketch, or when performing other surface deformation tasks. An inactive constraint is a passive curve that stays on the surface and that gets modified along with the surface when the surface is inflated, but that does not affect the surface itself. By changing parameters stored at the active constraints, embodiments may modify the surface and turn the inactive constraints from flat 2D curves into 3D space curves. The inactive constraints can be activated at any time when their 3D shape meets the user's expectations.

Abstract: Methods and apparatus for hidden surface removal with soft occlusion. Soft occlusion methods are described that treat surfaces as having a degree of uncertainty in depth. The soft occlusion methods may, for example, be used to remove artifacts from rendered images due to nearly coplanar surfaces or to render novel effects such as soft intersections between objects including consistent shadows and other global illumination effects. The soft occlusion methods may compute the ‘expected’ or average image given depth probability density functions. This has the effect of visually blending together surfaces that are close together in depth, leading to soft intersections. The computation of soft occlusion may be achieved analytically, for certain probability density functions, or stochastically. The stochastic soft occlusion methods extend the approach to a probability distribution of models, which allows for the effects of shadows and other global illumination effects to be included.