SIGGRAPH 2015 Papers

We propose a method to design linear deformation subspaces, unifying linear blend skinning and generalized barycentric coordinates. Deformation subspaces cut down the time complexity of variational shape deformation methods and physics-based animation (reduced-order physics). Our subspaces feature many desirable properties: interpolation, smoothness, shape-awareness, locality, and both constant and linear precision. We achieve these by minimizing a quadratic deformation energy, built via a discrete Laplacian inducing linear precision on the domain boundary. Our main advantage is speed: subspace bases are solutions to a sparse linear system, computed interactively even for generously tessellated domains. Users may seamlessly switch between applying transformations at handles and editing the subspace by adding, removing or relocating control handles. The combination of fast computation and good properties means that designing the right subspace is now just as creative as manipulating handles. This paradigm shift in handle-based deformation opens new opportunities to explore the space of shape deformations.

Good icons are legible, and legible icons are scale-dependent. Experienced icon designers use a set of common strategies to create legible scale variations of icons, but executing those strategies with current tools can be challenging. In part, this is because many apparent objects, like hairlines formed by negative space, are not explicitly represented as objects in vector drawings. We present transient widgets as a mechanism for selecting and manipulating apparent objects that is independent of the underlying drawing representation. We implement transient widgets using a constraint-based editing framework; demonstrate their utility for performing the kinds of edits most common when producing scale variations of icons; and report qualitative feedback on the system from professional icon designers.

Manipulated images lose believability if the user's edits fail to account for shadows. We propose a method that makes removal and editing of soft shadows easy. Soft shadows are ubiquitous, but remain notoriously difficult to extract and manipulate. We posit that soft shadows can be segmented, and therefore edited, by learning a mapping function for image patches that generates shadow mattes. We validate this premise by removing soft shadows from photographs with only a small amount of user input. Given only broad user brush strokes that indicate the region to be processed, our new supervised regression algorithm automatically unshadows an image, removing the umbra and penumbra. The resulting lit image is frequently perceived as a believable shadow-free version of the scene. We tested the approach on a large set of soft shadow images, and performed a user study that compared our method to the state-of-the-art and to real lit scenes. Our results are more difficult to identify as being altered and are perceived as preferable compared to prior work.

Popular sites like Houzz, Pinterest, and LikeThatDecor, have communities of users helping each other answer questions about products in images. In this paper we learn an embedding for visual search in interior design. Our embedding contains two different domains of product images: products cropped from internet scenes, and products in their iconic form. With such a multi-domain embedding, we demonstrate several applications of visual search including identifying products in scenes and finding stylistically similar products. To obtain the embedding, we train a convolutional neural network on pairs of images. We explore several training architectures including re-purposing object classifiers, using siamese networks, and using multitask learning. We evaluate our search quantitatively and qualitatively and demonstrate high quality results for search across multiple visual domains, enabling new applications in interior design.

We present a method to learn and propagate shape placements in 2D polygonal scenes from a few examples provided by a user. The placement of a shape is modeled as an oriented bounding box. Simple geometric relationships between this bounding box and nearby scene polygons define a feature set for the placement. The feature sets of all example placements are then used to learn a probabilistic model over all possible placements and scenes. With this model, we can generate a new set of placements with similar geometric relationships in any given scene. We introduce extensions that enable propagation and generation of shapes in 3D scenes, as well as the application of a learned modeling session to large scenes without additional user interaction. These concepts allow us to generate complex scenes with thousands of objects with relatively little user interaction.

In this paper we present a novel approach to appearance transfer for fluid animations based on flow-guided texture synthesis. In contrast to common practice where pre-captured sets of fluid elements are combined in order to achieve desired motion and look, we bring the possibility of fine-tuning motion properties in advance using CG techniques, and then transferring the desired look from a selected appearance exemplar. We demonstrate that such a practical work-flow cannot be simply implemented using current state-of-the-art techniques, analyze what the main obstacles are, and propose a solution to resolve them. In addition, we extend the algorithm to allow for synthesis with rich boundary effects and video exemplars. Finally, we present numerous results that demonstrate the versatility of the proposed approach.

We introduce a novel approach that reconstructs 3D urban scenes in the form of levels of detail (LODs). Starting from raw datasets such as surface meshes generated by multiview stereo systems, our algorithm proceeds in three main steps: classification, abstraction, and reconstruction. From geometric attributes and a set of semantic rules combined with a Markov random field, we classify the scene into four meaningful classes. The abstraction step detects and regularizes planar structures on buildings, fits icons on trees, roofs, and facades, and performs filtering and simplification for LOD generation. The abstracted data are then provided as input to the reconstruction step which generates watertight buildings through a min-cut formulation on a set of 3D arrangements. Our experiments on complex buildings and large-scale urban scenes show that our approach generates meaningful LODs while being robust and scalable. By combining semantic segmentation and abstraction, it also outperforms general mesh approximation approaches at preserving urban structures.

Inspired by how humans learn dynamic motor skills through a progressive process of coaching and practices, we introduce an intuitive and interactive framework for developing dynamic controllers. The user only needs to provide a primitive initial controller and high-level, human-readable instructions as if s/he is coaching a human trainee, while the character has the ability to interpret the abstract instructions, accumulate the knowledge from the coach, and improve its skill iteratively. We introduce “control rigs” as an intermediate layer of control module to facilitate the mapping between high-level instructions and low-level control variables. Control rigs also utilize the human coach's knowledge to reduce the search space for control optimization. In addition, we develop a new sampling-based optimization method, Covariance Matrix Adaptation with Classification (CMA-C), to efficiently compute-control rig parameters. Based on the observation of human ability to “learn from failure”, CMA-C utilizes the failed simulation trials to approximate an infeasible region in the space of control rig parameters, resulting a faster convergence for the CMA optimization. We demonstrate the design process of complex dynamic controllers using our framework, including precision jumps, turnaround jumps, monkey vaults, drop-and-rolls, and wall-backflips.

We introduce in this paper an algorithm that generates from an input tolerance volume a surface triangle mesh guaranteed to be within the tolerance, intersection free and topologically correct. A pliant meshing algorithm is used to capture the topology and discover the anisotropy in the input tolerance volume in order to generate a concise output. We first refine a 3D Delaunay triangulation over the tolerance volume while maintaining a piecewise-linear function on this triangulation, until an isosurface of this function matches the topology sought after. We then embed the isosurface into the 3D triangulation via mutual tessellation, and simplify it while preserving the topology. Our approach extends to surfaces with boundaries and to non-manifold surfaces. We demonstrate the versatility and efficacy of our approach on a variety of data sets and tolerance volumes.

A large range of computer graphics applications such as data visualization or virtual movie production require users to position and move viewpoints in 3D scenes to effectively convey visual information or tell stories. The desired viewpoints and camera paths are required to satisfy a number of visual properties ( e.g. size, vantage angle, visibility, and on-screen position of targets). Yet, existing camera manipulation tools only provide limited interaction methods and automated techniques remain computationally expensive. In this work, we introduce the Toric space , a novel and compact representation for intuitive and efficient virtual camera control. We first show how visual properties are expressed in this Toric space and propose an efficient interval-based search technique for automated viewpoint computation. We then derive a novel screen-space manipulation technique that provides intuitive and real-time control of visual properties. Finally, we propose an effective viewpoint interpolation technique which ensures the continuity of visual properties along the generated paths. The proposed approach (i) performs better than existing automated viewpoint computation techniques in terms of speed and precision, (ii) provides a screen-space manipulation tool that is more efficient than classical manipulators and easier to use for beginners, and (iii) enables the creation of complex camera motions such as long takes in a very short time and in a controllable way. As a result, the approach should quickly find its place in a number of applications that require interactive or automated camera control such as 3D modelers, navigation tools or 3D games.

We demonstrate an interactive method to create heterogeneous continuous deformable materials on complex three-dimensional meshes. The user specifies displacements and internal elastic forces at a chosen set of mesh vertices. Our system then rapidly solves an optimization problem to compute a corresponding heterogeneous spatial distribution of material properties using the Finite Element Method (FEM) analysis. We apply our method to linear and nonlinear isotropic deformable materials. We demonstrate that solving the problem interactively in the full-dimensional space of individual tetrahedron material values is not practical. Instead, we propose a new model reduction method that projects the material space to a low-dimensional space of material modes. Our model reduction accelerates optimization by two orders of magnitude and makes the convergence much more robust, making it possible to interactively design material distributions on complex meshes. We apply our method to precise control of contact forces and control of pressure over large contact areas between rigid and deformable objects for ergonomics. Our tetrahedron-based dithering method can efficiently convert continuous material distributions into discrete ones and we demonstrate its precision via FEM simulation. We physically display our distributions using haptics, as well as demonstrate how haptics can aid in the material design. The produced heterogeneous material distributions can also be used in computer animation applications.

We introduce a contextual descriptor which aims to provide a geometric description of the functionality of a 3D object in the context of a given scene. Differently from previous works, we do not regard functionality as an abstract label or represent it implicitly through an agent. Our descriptor, called interaction context or ICON for short, explicitly represents the geometry of object-to-object interactions. Our approach to object functionality analysis is based on the key premise that functionality should mainly be derived from interactions between objects and not objects in isolation. Specifically, ICON collects geometric and structural features to encode interactions between a central object in a 3D scene and its surrounding objects. These interactions are then grouped based on feature similarity, leading to a hierarchical structure. By focusing on interactions and their organization, ICON is insensitive to the numbers of objects that appear in a scene, the specific disposition of objects around the central object, or the objects' fine-grained geometry. With a series of experiments, we demonstrate the potential of ICON in functionality-oriented shape processing, including shape retrieval (either directly or by complementing existing shape descriptors), segmentation, and synthesis.

We present a framework for designing curl-free tangent vector fields on discrete surfaces. Such vector fields are gradients of locally-defined scalar functions, and this property is beneficial for creating surface parameterizations, since the gradients of the parameterization coordinate functions are then exactly aligned with the designed fields. We introduce a novel definition for discrete curl between unordered sets of vectors (PolyVectors), and devise a curl-eliminating continuous optimization that is independent of the matchings between them. Our algorithm naturally places the singularities required to satisfy the user-provided alignment constraints, and our fields are the gradients of an inversion-free parameterization by design.

Conventional camera designs usually shun sample irregularities and lens aberrations. We demonstrate that such irregularities and aberrations, when properly applied, can improve the quality and usability of light field cameras. Examples include spherical aberrations for the mainlens, and misaligned sampling patterns for the microlens and photosensor elements. These observations are a natural consequence of a key difference between conventional and light field cameras: optimizing for a single captured 2D image versus a range of reprojected 2D images from a captured 4D light field. We propose designs in mainlens aberrations and microlens/photosensor sample patterns, and evaluate them through simulated measurements and captured results with our hardware prototype.

Humans describe images in terms of nouns and adjectives while algorithms operate on images represented as sets of pixels. Bridging this gap between how humans would like to access images versus their typical representation is the goal of image parsing, which involves assigning object and attribute labels to pixels. In this article we propose treating nouns as object labels and adjectives as visual attribute labels. This allows us to formulate the image parsing problem as one of jointly estimating per-pixel object and attribute labels from a set of training images. We propose an efficient (interactive time) solution. Using the extracted labels as handles, our system empowers a user to verbally refine the results. This enables hands-free parsing of an image into pixel-wise object/attribute labels that correspond to human semantics. Verbally selecting objects of interest enables a novel and natural interaction modality that can possibly be used to interact with new generation devices (e.g., smartphones, Google Glass, livingroom devices). We demonstrate our system on a large number of real-world images with varying complexity. To help understand the trade-offs compared to traditional mouse-based interactions, results are reported for both a large-scale quantitative evaluation and a user study.

Exploration of the hyperspectral domain offers a host of new research and application possibilities involving material appearance modeling. In this article, we address these prospects with respect to human skin, one of the most ubiquitous materials portrayed in synthetic imaging. We present the first hyperspectral model designed for the predictive rendering of skin appearance attributes in the ultraviolet, visible, and infrared domains. The proposed model incorporates the intrinsic bio-optical properties of human skin affecting light transport in these spectral regions, including the particle nature and distribution patterns of the main light attenuation agents found within the cutaneous tissues. Accordingly, it accounts for phenomena that significantly affect skin spectral signatures, both within and outside the visible domain, such as detour and sieve effects, that are overlooked by existing skin appearance models. Using a first-principles approach, the proposed model computes the surface and subsurface scattering components of skin reflectance taking into account not only the wavelength and the illumination geometry, but also the positional dependence of the reflected light. Hence, the spectral and spatial distributions of light interacting with human skin can be comprehensively represented in terms of hyperspectral reflectance and BSSRDF, respectively.