SIGGRAPH 2016 Papers

People often take a series of nearly redundant pictures to capture a moment or scene. However, selecting photos to keep or share from a large collection is a painful chore. To address this problem, we seek a relative quality measure within a series of photos taken of the same scene, which can be used for automatic photo triage. Towards this end, we gather a large dataset comprised of photo series distilled from personal photo albums. The dataset contains 15, 545 unedited photos organized in 5,953 series. By augmenting this dataset with ground truth human preferences among photos within each series, we establish a benchmark for measuring the effectiveness of algorithmic models of how people select photos. We introduce several new approaches for modeling human preference based on machine learning. We also describe applications for the dataset and predictor, including a smart album viewer, automatic photo enhancement, and providing overviews of video clips.

Photo retouching enables photographers to invoke dramatic visual impressions by artistically enhancing their photos through stylistic color and tone adjustments. However, it is also a time-consuming and challenging task that requires advanced skills beyond the abilities of casual photographers. Using an automated algorithm is an appealing alternative to manual work, but such an algorithm faces many hurdles. Many photographic styles rely on subtle adjustments that depend on the image content and even its semantics. Further, these adjustments are often spatially varying. Existing automatic algorithms are still limited and cover only a subset of these challenges. Recently, deep learning has shown unique abilities to address hard problems. This motivated us to explore the use of deep neural networks (DNNs) in the context of photo editing. In this article, we formulate automatic photo adjustment in a manner suitable for this approach. We also introduce an image descriptor accounting for the local semantics of an image. Our experiments demonstrate that training DNNs using these descriptors successfully capture sophisticated photographic styles. In particular and unlike previous techniques, it can model local adjustments that depend on image semantics. We show that this yields results that are qualitatively and quantitatively better than previous work.

We introduceAutoHair, the first fully automatic method for 3D hair modeling from a single portrait image, with no user interaction or parameter tuning. Our method efficiently generates complete and high-quality hair geometries, which are comparable to those generated by the state-of-the-art methods, where user interaction is required. The core components of our method are: a novel hierarchical deep neural network for automatic hair segmentation and hair growth direction estimation, trained over an annotated hair image database; and an efficient and automatic data-driven hair matching and modeling algorithm, based on a large set of 3D hair exemplars. We demonstrate the efficacy and robustness of our method on Internet photos, resulting in a database of around 50K 3D hair models and a corresponding hairstyle space that covers a wide variety of real-world hairstyles. We also show novel applications enabled by our method, including 3D hairstyle space navigation and hair-aware image retrieval.

Animation artists enjoy the benefits of simulation but do not want to be held back by its constraints. Artist-directed dynamics seeks to resolve this need with a unified method that combines simulation with classical keyframing techniques. The combination of these approaches improves upon both extremes: simulation becomes more customizable and keyframing becomes more automatic. Examining our system in the context of the twelve fundamental animation principles reveals that it stands out for its treatment of exaggeration and appeal. Our system accommodates abrupt jumps, large plastic deformations, and makes it easy to reuse carefully crafted animations.

We introduce approximate translational building blocks for unsupervised image decomposition. Such building blocks are frequently appearing copies of image patches that are mapped coherently under translations. We exploit the coherency assumption to find approximate building blocks in noisy and ambiguous image data, using a spectral embedding of re-occurrence patterns. We quantitatively evaluate our method on a large benchmark dataset and obtain clear improvements over state-of-the-art methods. We apply our method to texture synthesis by integrating building block constraints and their offset statistics into a conventional Markov random field model. A user study shows improved retargeting results even if the images are only partially described by a few classes of building blocks.

Performance capture systems are used to acquire high-quality animated 3D surfaces, usually in form of a dense 3D triangle mesh. Extracting a more compact yet faithful representation is often desirable, but existing solutions for animated sequences are surface based, which leads to a limited approximation power in the case of extreme simplification. We introduce animated sphere-meshes, which are meshes indexing a set of animated spheres. Our solution is the first to output an animated volumetric structure to approximate animated 3D surfaces and optimizes for the sphere approximation, connectivity, and temporal coherence. As a result, our algorithm produces a multiresolution structure from which a level of simplification can be selected in real time, preserving a faithful approximation of the input, even at the coarsest levels. We demonstrate the use of animated sphere-meshes for low-cost approximate collision detection. Additionally, we propose a skinning decomposition, which automatically rigs the input mesh to the chosen level of detail. The resulting set of weights are smooth, compress the animation, and enable easy edits.

In this paper, we propose a new adaptive rendering method to improve the performance of Monte Carlo ray tracing, by reducing noise contained in rendered images while preserving high-frequency edges. Our method locally approximates an image with polynomial functions and the optimal order of each polynomial function is estimated so that our reconstruction error can be minimized. To robustly estimate the optimal order, we propose a multi-stage error estimation process that iteratively estimates our reconstruction error. In addition, we present an energy-preserving outlier removal technique to remove spike noise without causing noticeable energy loss in our reconstruction result. Also, we adaptively allocate additional ray samples to high error regions guided by our error estimation. We demonstrate that our approach outperforms state-of-the-art methods by controlling the tradeoff between reconstruction bias and variance through locally defining our polynomial order, even without need for filtering bandwidth optimization, the common approach of other recent methods.

Acoustic filters have a wide range of applications, yet customizing them with desired properties is difficult. Motivated by recent progress in additive manufacturing that allows for fast prototyping of complex shapes, we present a computational approach that automates the design of acoustic filters with complex geometries. In our approach, we construct an acoustic filter comprised of a set of parameterized shape primitives, whose transmission matrices can be precomputed. Using an efficient method of simulating the transmission matrix of an assembly built from these underlying primitives, our method is able to optimize both the arrangement and the parameters of the acoustic shape primitives in order to satisfy target acoustic properties of the filter. We validate our results against industrial laboratory measurements and high-quality off-line simulations. We demonstrate that our method enables a wide range of applications including muffler design, musical wind instrument prototyping, and encoding imperceptible acoustic information into everyday objects.

We present the Accelerated Quadratic Proxy (AQP) - a simple first-order algorithm for the optimization of geometric energies defined over triangular and tetrahedral meshes. The main stumbling block of current optimization techniques used to minimize geometric energies over meshes is slow convergence due to ill-conditioning of the energies at their minima. We observe that this ill-conditioning is in large part due to a Laplacian-like term existing in these energies. Consequently, we suggest to locally use a quadratic polynomial proxy, whose Hessian is taken to be the Laplacian, in order to achieve a preconditioning effect. This already improves stability and convergence, but more importantly allows incorporating acceleration in an almost universal way, that is independent of mesh size and of the specific energy considered. Experiments with AQP show it is rather insensitive to mesh resolution and requires a nearly constant number of iterations to converge; this is in strong contrast to other popular optimization techniques used today such as Accelerated Gradient Descent and Quasi-Newton methods, e.g. , L-BFGS. We have tested AQP for mesh deformation in 2D and 3D as well as for surface parameterization, and found it to provide a considerable speedup over common baseline techniques.

We present Spire, a shading language and compiler framework that facilitates rapid exploration of shader optimization choices (such as frequency reduction and algorithmic approximation) afforded by modern real-time graphics engines. Our design combines ideas from rate-based shader programming with new language features that expand the scope of shader execution beyond traditional GPU hardware pipelines, and enable a diverse set of shader optimizations to be described by a single mechanism: overloading shader terms at various spatio-temporal computation rates provided by the pipeline. In contrast to prior work, neither the shading language's design, nor our compiler framework's implementation, is specific to the capabilities of any one rendering pipeline, thus Spire establishes architectural separation between the shading system and the implementation of modern rendering engines (allowing different rendering pipelines to utilize its services). We demonstrate use of Spire to author complex shaders that are portable across different rendering pipelines and to rapidly explore shader optimization decisions that span multiple compute and graphics passes and even offline asset preprocessing. We further demonstrate the utility of Spire by developing a shader level-of-detail library and shader auto-tuning system on top of its abstractions, and demonstrate rapid, automatic re-optimization of shaders for different target hardware platforms.

We propose a new framework to model the exterior of residential buildings. The main goal of our work is to design a model that can be learned from data that is observable from the outside of a building and that can be trained with widely available data such as aerial images and street-view images. First, we propose a parametric model to describe the exterior of a building (with a varying number of parameters) and propose a set of attributes as a building representation with fixed dimensionality. Second, we propose a hierarchical graphical model with hidden variables to encode the relationships between building attributes and learn both the structure and parameters of the model from the database. Third, we propose optimization algorithms to generate three-dimensional models based on building attributes sampled from the graphical model. Finally, we demonstrate our framework by synthesizing new building models and completing partially observed building models from photographs.

We present a framework to synthesize character movements based on high level parameters, such that the produced movements respect the manifold of human motion, trained on a large motion capture dataset. The learned motion manifold, which is represented by the hidden units of a convolutional autoencoder, represents motion data in sparse components which can be combined to produce a wide range of complex movements. To map from high level parameters to the motion manifold, we stack a deep feedforward neural network on top of the trained autoencoder. This network is trained to produce realistic motion sequences from parameters such as a curve over the terrain that the character should follow, or a target location for punching and kicking. The feedforward control network and the motion manifold are trained independently, allowing the user to easily switch between feedforward networks according to the desired interface, without re-training the motion manifold. Once motion is generated it can be edited by performing optimization in the space of the motion manifold. This allows for imposing kinematic constraints, or transforming the style of the motion, while ensuring the edited motion remains natural. As a result, the system can produce smooth, high quality motion sequences without any manual pre-processing of the training data.