SIGGRAPH 2019 Papers

The materials around us usually exist as mixtures of constituents, each constituent with possibly a different elasto-viscoplastic property. How can we describe the material property of such a mixture is the core question of this paper. We propose a nonlinear blending model that can capture intriguing flowing behaviors that can differ from that of the individual constituents (Fig. 1). We used a laboratory device, rheometer, to measure the flowing properties of various fluid-like foods, and found that an elastic Herschel-Bulkley model has nice agreements with the measured data even for the mixtures of these foods. We then constructed a blending model such that it qualitatively agrees with the measurements and is closed in the parameter space of the elastic Herschel-Bulkley model. We provide validations through comparisons between the measured and estimated properties using our model, and comparisons between simulated examples and captured footages. We show the utility of our model for producing interesting behaviors of various mixtures.

Polygonal meshes provide an efficient representation for 3D shapes. They explicitly captureboth shape surface and topology, and leverage non-uniformity to represent large flat regions as well as sharp, intricate features. This non-uniformity and irregularity, however, inhibits mesh analysis efforts using neural networks that combine convolution and pooling operations. In this paper, we utilize the unique properties of the mesh for a direct analysis of 3D shapes using MeshCNN, a convolutional neural network designed specifically for triangular meshes. Analogous to classic CNNs, MeshCNN combines specialized convolution and pooling layers that operate on the mesh edges, by leveraging their intrinsic geodesic connections. Convolutions are applied on edges and the four edges of their incident triangles, and pooling is applied via an edge collapse operation that retains surface topology, thereby, generating new mesh connectivity for the subsequent convolutions. MeshCNN learns which edges to collapse, thus forming a task-driven process where the network exposes and expands the important features while discarding the redundant ones. We demonstrate the effectiveness of MeshCNN on various learning tasks applied to 3D meshes.

Meet in Rain is a serious game on Chinese poetry. While invoking various events, players must complete given tasks, which help them better appreciate the poems, by exploring imaginary sceneries that depict Chinese poems. Its visual design also mimics Chinese paintings in the era when the poems were created. As only a few serious games exist for Chinese poetry and they mostly focus on knowledge acquisition, our work provides a rare design exemplar of a serious game that is designed with the intention to foster aesthetic appreciation for a cultural subject.

We propose MagniFinger, a fingertip-worn microscopy device that augments the limited abilities of human visual and tactile sensory systems in micrometer-scale environments. MagniFinger makes use of the finger's dexterous motor skills to achieve precise and intuitive control while allowing the user to observe the desired position simply by placing a fingertip. To implement the fingertip-sized device and its tactile display, we have built a system comprising a ball lens, an image sensor, and a thin piezoelectric actuator. Vibration-based tactile feedback is displayed based on the luminance of a magnified image, providing the user with the feeling of touching the magnified world.

This study proposes a tabletop projection device that can be implemented by combining physical objects with interactive projections. Users can interact on kraft papers using daily tools, such as marker pens, toothbrushes, colored blocks, and square wooden blocks. The input of the proposed device is a multifunction sensor, and the output is a tabletop projector. Using MagicPAPER, four types of interactions are implemented, namely drawing, gesture recognition, brushing, and building blocks. The abstract and poster discuss the design motivations and system descriptions of MagicPAPER.

Current rendering techniques struggle to fulfill quality and power efficiency requirements imposed by new display devices such as virtual reality headsets. A promising solution to overcome these problems is foveated rendering, which exploits gaze information to reduce rendering quality for the peripheral vision where the requirements of the human visual system are significantly lower. Most of the current solutions model the sensitivity as a function of eccentricity, neglecting the fact that it also is strongly influenced by the displayed content. In this work, we propose a new luminance-contrast-aware foveated rendering technique which demonstrates that the computational savings of foveated rendering can be significantly improved if local luminance contrast of the image is analyzed. To this end, we first study the resolution requirements at different eccentricities as a function of luminance patterns. We later use this information to derive a low-cost predictor of the foveated rendering parameters. Its main feature is the ability to predict the parameters using only a low-resolution version of the current frame, even though the prediction holds for high-resolution rendering. This property is essential for the estimation of required quality before the full-resolution image is rendered. We demonstrate that our predictor can efficiently drive the foveated rendering technique and analyze its benefits in a series of user experiments.

We present a practical and robust deep learning solution for capturing and rendering novel views of complex real world scenes for virtual exploration. Previous approaches either require intractably dense view sampling or provide little to no guidance for how users should sample views of a scene to reliably render high-quality novel views. Instead, we propose an algorithm for view synthesis from an irregular grid of sampled views that first expands each sampled view into a local light field via a multiplane image (MPI) scene representation, then renders novel views by blending adjacent local light fields. We extend traditional plenoptic sampling theory to derive a bound that specifies precisely how densely users should sample views of a given scene when using our algorithm. In practice, we apply this bound to capture and render views of real world scenes that achieve the perceptual quality of Nyquist rate view sampling while using up to 4000X fewer views. We demonstrate our approach's practicality with an augmented reality smart-phone app that guides users to capture input images of a scene and viewers that enable realtime virtual exploration on desktop and mobile platforms.

We present the first real-time human performance capture approach that reconstructs dense, space-time coherent deforming geometry of entire humans in general everyday clothing from just a single RGB video. We propose a novel two-stage analysis-by-synthesis optimization whose formulation and implementation are designed for high performance. In the first stage, a skinned template model is jointly fitted to background subtracted input video, 2D and 3D skeleton joint positions found using a deep neural network, and a set of sparse facial landmark detections. In the second stage, dense non-rigid 3D deformations of skin and even loose apparel are captured based on a novel real-time capable algorithm for non-rigid tracking using dense photometric and silhouette constraints. Our novel energy formulation leverages automatically identified material regions on the template to model the differing non-rigid deformation behavior of skin and apparel. The two resulting non-linear optimization problems per frame are solved with specially tailored data-parallel Gauss-Newton solvers. To achieve real-time performance of over 25Hz, we design a pipelined parallel architecture using the CPU and two commodity GPUs. Our method is the first real-time monocular approach for full-body performance capture. Our method yields comparable accuracy with off-line performance capture techniques while being orders of magnitude faster.

In this article, we introduce a novel method that can generate a sequence of physical transformations between 3D models with different shape and topology. Feasible transformations are realized on a chain structure with connected components that are 3D printed. Collision-free motions are computed to transform between different configurations of the 3D printed chain structure. To realize the transformation between different 3D models, we first voxelize these input models into a similar number of voxels. The challenging part of our approach is to generate a simple path—as a chain configuration to connect most voxels. A layer-based algorithm is developed with theoretical guarantee of the existence and the path length. We find that collision-free motion sequence can always be generated when using a straight line as the intermediate configuration of transformation. The effectiveness of our method is demonstrated by both the simulation and the experimental tests taken on 3D printed chains.

We present a new algorithm to automatically schedule Halide programs for high-performance image processing and deep learning. We significantly improve upon the performance of previous methods, which considered a limited subset of schedules. We define a parameterization of possible schedules much larger than prior methods and use a variant of beam search to search over it. The search optimizes runtime predicted by a cost model based on a combination of new derived features and machine learning. We train the cost model by generating and featurizing hundreds of thousands of random programs and schedules. We show that this approach operates effectively with or without autotuning. It produces schedules which are on average almost twice as fast as the existing Halide autoscheduler without autotuning, or more than twice as fast with, and is the first automatic scheduling algorithm to significantly outperform human experts on average.

Hybrid unmanned aerial vehicles (UAV) combine advantages of multicopters and fixed-wing planes: vertical take-off, landing, and low energy use. However, hybrid UAVs are rarely used because controller design is challenging due to its complex, mixed dynamics. In this paper, we propose a method to automate this design process by training a mode-free, model-agnostic neural network controller for hybrid UAVs. We present a neural network controller design with a novel error convolution input trained by reinforcement learning. Our controller exhibits two key features: First, it does not distinguish among flying modes, and the same controller structure can be used for copters with various dynamics. Second, our controller works for real models without any additional parameter tuning process, closing the gap between virtual simulation and real fabrication. We demonstrate the efficacy of the proposed controller both in simulation and in our custom-built hybrid UAVs (Figure 1, 8). The experiments show that the controller is robust to exploit the complex dynamics when both rotors and wings are active in flight tests.

There is increasing interest in using robots in simulation to understand and improve human-robot interaction (HRI). At the same time, the use of simulated settings to gather training data promises to help address a major data bottleneck in allowing robots to take advantage of powerful machine learning approaches. In this paper, we describe a prototype system that combines the robot operating system (ROS), the simulator Gazebo, and the Unity game engine to create human-robot interaction scenarios. A person can engage with the scenario using a monitor wall, allowing simultaneous collection of realistic sensor data and traces of human actions.

Analyzing human motion is a challenging task with a wide variety of applications in computer vision and in graphics. One such application, of particular importance in computer animation, is the retargeting of motion from one performer to another. While humans move in three dimensions, the vast majority of human motions are captured using video, requiring 2D-to-3D pose and camera recovery, before existing retargeting approaches may be applied. In this paper, we present a new method for retargeting video-captured motion between different human performers, without the need to explicitly reconstruct 3D poses and/or camera parameters. In order to achieve our goal, we learn to extract, directly from a video, a high-level latent motion representation, which is invariant to the skeleton geometry and the camera view. Our key idea is to train a deep neural network to decompose temporal sequences of 2D poses into three components: motion, skeleton, and camera view-angle. Having extracted such a representation, we are able to re-combine motion with novel skeletons and camera views, and decode a retargeted temporal sequence, which we compare to a ground truth from a synthetic dataset. We demonstrate that our framework can be used to robustly extract human motion from videos, bypassing 3D reconstruction, and outperforming existing retargeting methods, when applied to videos in-the-wild. It also enables additional applications, such as performance cloning, video-driven cartoons, and motion retrieval.

Given a point set S ⊆ R2, reconstruction refers to the process of identifying a vector shape that best approximates the input. Although this field was pioneered since 1983 by Edelsbrunner [Edelsbrunner et al. 2006] and has been heavily studied since then, the general problem still remains open, ill-posed and challenging. Solving it is essential for a wide range of applications, from image processing, pattern recognition and sketching to wireless networks.

With the advance of personal and customized fabrication techniques, the capability to embed information in physical objects becomes evermore crucial. We present LayerCode, a tagging scheme that embeds a carefully designed barcode pattern in 3D printed objects as a deliberate byproduct of the 3D printing process. The LayerCode concept is inspired by the structural resemblance between the parallel black and white bars of the standard barcode and the universal layer-by-layer approach of 3D printing. We introduce an encoding algorithm that enables the 3D printing layers to carry information without altering the object geometry. We also introduce a decoding algorithm that reads the LayerCode tag of a physical object by just taking a photo. The physical deployment of LayerCode tags is realized on various types of 3D printers, including Fused Deposition Modeling printers as well as Stereolithography based printers. Each offers its own advantages and tradeoffs. We show that LayerCode tags can work on complex, nontrivial shapes, on which all previous tagging mechanisms may fail. To evaluate LayerCode thoroughly, we further stress test it with a large dataset of complex shapes using virtual rendering. Among 4,835 tested shapes, we successfully encode and decode on more than 99% of the shapes.

We introduce knittable stitch meshes for modeling complex 3D knit structures that can be fabricated via knitting. We extend the concept of stitch mesh modeling, which provides a powerful 3D design interface for knit structures but lacks the ability to produce actually knittable models. Knittable stitch meshes ensure that the final model can be knitted. Moreover, they include novel representations for handling important shaping techniques that allow modeling more complex knit structures than prior methods. In particular, we introduce shift paths that connect the yarn for neighboring rows, general solutions for properly connecting pieces of knit fabric with mismatched knitting directions without introducing seams, and a new structure for representing short rows, a shaping technique for knitting that is crucial for creating various 3D forms, within the stitch mesh modeling framework. Our new 3D modeling interface allows for designing knittable structures with complex surface shapes and topologies, and our knittable stitch mesh structure contains all information needed for fabricating these shapes via knitting. Furthermore, we present a scheduling algorithm for providing step-by-step hand knitting instructions to a knitter, so that anyone who knows how to knit can reproduce the complex models that can be designed using our approach. We show a variety of 3D knit shapes and garment examples designed and knitted using our system.

We propose a new modal sound synthesis method that rapidly estimates all acoustic transfer fields of a linear modal vibration model, and greatly reduces preprocessing costs. Instead of performing a separate frequency-domain Helmholtz radiation analysis for each mode, our method partitions vibration modes into chords using optimal mode conflation, then performs a single time-domain wave simulation for each chord. We then perform transfer deconflation on each chord's time-domain radiation field using a specialized QR solver, and thereby extract the frequency-domain transfer functions of each mode. The precomputed transfer functions are represented for fast far-field evaluation, e.g., using multipole expansions. In this paper, we propose to use a single scalar-valued Far-field Acoustic Transfer (FFAT) cube map. We describe a GPU-accelerated vector wavesolver that achieves high-throughput acoustic transfer computation at accuracy sufficient for sound synthesis. Our implementation, KleinPAT, can achieve hundred- to thousand-fold speedups compared to existing Helmholtz-based transfer solvers, thereby enabling large-scale generation of modal sound models for audio-visual applications.