SIGGRAPH 2021 Papers

Figure 1: (a) Schematic diagram and (b) cross-section view of a unit cell FDTD simulation 20-nm-thick silver nanohole array of coated on glass substrate. (c) Spectral reflectance and (d) transmittance of 20-nm-thick silver nanohole array with a smooth profile and 5 distinct surface roughness profiles (colored lines). (e) Rendered images of smooth and rough silver nanohole arrays coated on spherical substrate in reflectance (second row) and transmittance (third row). The associated color difference, ∆E00, as shown in reflectance (first row) and transmittance (last row). Click the link to preview the plasmonic structural color coated on 3D objects: Link.

Glanceable interfaces are Augmented Reality (AR) User Interfaces (UIs) for information retrieval ”at a glance” relying on eye gaze for implicit input. While they provide rapid information retrieval, they often occlude a large part of the real-world. This is compounded as the amount of virtual information increases. Interacting with complex glanceable interfaces often results in unintentional eye gaze interaction and selections due to the Midas Touch problem. In this work, we present Holo-box, an innovative AR UI design that combines 2D compact glanceable interfaces with 3D virtual ”Holo-boxes”. We can utilize the glanceable 2D interface to provide compact information at a glance while using Holo-box for explicit input such as hand tracking activated when necessary, surpassing the Midas Touch problem and resulting in Level-of-Detail(LOD) for AR glanceable UIs. We test our proposed system inside a real-world machine shop to provide on-demand virtual information while minimizing unintentional real-world occlusion.

Our aim is to convert an object’s appearance to an arbitrary color considering the light scattering in the entire scene, which is often called the global illumination. Existing stylization methods convert the color of an object with a 1-dimensional texture for 3-dimensional computer graphics to reproduce a typical style used in illustrations and cel animations. However, they cannot express global illumination effects such as color bleedings and soft shadows. We propose a method to compute the global illumination and convert the shading to an arbitrary color. It consists of subpath tracing from the eye to the object, and radiance estimation on the object. The radiance is stored and used later to convert its color. The method reproduces reflections in other objects with the converted color. As a result, we can convert the color of illumination effects such as soft shadows and refractions.

In this work, we propose a temporally-stable denoising system that is capable of reconstructing MC renderings in a foveated manner. We develop a multi-scale convolutional neural network that starts at a base (downsampled) resolution and denoises progressively higher resolutions. Our network learns to use the lower resolutions and the previous frames to denoise each foveal layer. We demonstrate how this architecture produces accurate denoised results at a much lower computational cost.

In our previous study, we proposed a telepresence system that can transfer the riding sensation of a vehicle (Segway) for assisting collaborative task. The system could provide a local expert who remotely attend the task not only the view of a remote environment that is captured by a camera but also the vestibular perception during the movement of the camera. In this study, we examined the rotation feedback by the rotary seat when the camera is rotated. The measured intensity adjustment showed that the angular acceleration of the rotary seat was about half that of the camera rotation. Further, the result of the simulator sickness questionnaire scores showed that the inphase rotation of the seat with the camera is appropriate for suppressing virtual reality sickness, indicating that the requirement of vestibular intensity is quite low compared with the visual cue showed on the head mounted display, which allows a designer to develop a sensation feedback device that has an actuator of low strength.

1 INTRIDUCTION Recently, there has been an increasing number of examples of dynamic projection mapping (DPM) applied to plants and animals. However, objects such as animals and plants are deformable, and it is difficult to obtain their shape or attach markers in advance; thus, these objects present a problem for DPM. Here, we propose an automatic generation method of DPM specially designed for silkworms. In addition, the system automatically generates visualeffect animations based on the shape of the projected object. Using this system, we conducted an experiment of projection on a real silkworm. Projections in the Forest [Schoor and Mawad 2014] is one example of a work in which PM is applied to plants and animals. In this previous work, static projection mapping was performed for plants and animals of the forest. Image registration for the mapping was performed manually by the artists, which required a substantial amount of time. For plant leaves with individual motion, a method of DPM that considers the occlusion of the projection area by the viewer has been proposed [Sueyoshi and Morimoto 2019]. This method automatically generates effects that match the shape of the plant. However, leaves exhibit small deformations, and it is difficult

We present a novel method to segment CAD models into developable patches by detecting curve-like features on Gauss images of the corresponding patches. A region-growing approach is employed to detect planar and curved developable patches. The Gauss image of each segmented patch is constrained to be curve-like via principal component analysis and Pearson correlation analysis. Experimental results demonstrate that our approach generates nice results on CAD models with all kinds of developable surfaces.

Recently attention network finding similarity in non-local area within a 2D image has shown outstanding improvement in multi-class generation task in GAN. However it frequently shows unstable training state sometimes falling in mode collapse. We propose cross sample similarity loss to penalize similar features of fake samples that are rarely observed in reals. Proposed method shows improved FID score compared to baseline methods on CelebA, LSUN, and decreased mode collapse on Cifar10[Krizhevsky 2009].

Crowd simulations are a popular narrative tool in the entertainment industry and rely heavily on crowd characters for their effectiveness. The traditional processes employed for modeling characters are expensive and impractical for creating crowd character models, leading to the development and use of combinatorial methods. While combinatorial methods are effective at creating large numbers of unique character variations, they lack the flexibility to create characters outside the range of possible variations. This limitation is particularly troublesome in production circumstances that entail frequent fluctuations in character asset requests and in real-time interactive experiences. This is primarily because it is difficult to predetermine the various states in which crowd characters will be rendered. This thesis explores a procedural, parametrically driven system for creating crowd characters that allows for greater flexibility in changing scenarios. This system uses craniofacial anthropometric data - sourced from existing literature - to create a multidimensional parametric structure from which procedurally randomized values can be generated and selected. Once new parametric values are generated, a base craniofacial model is deformed accordingly, resulting in a unique model that represents the parameter values assigned. The results of this method demonstrate the ability of a procedurally driven, craniofacial anthropometric facial deformation system to rapidly and efficiently create a large set of unique crowd character facial models that share a single UV map and polygonal topology. The results of this research indicate such a procedurally driven crowd character creation system would provide artists with the flexibility to quickly iterate and produce desirable results in scenarios such as interactive games.

Caricature is an art form of exaggeration of features [Akleman 1997; Akleman et al. 2000; Akleman and Reisch 2004; Brennan 1985; Klare et al. 2012; Liang et al. 2002]. An important property of feature exaggeration is that it is not deformation. By deforming features we can obtain funny looking portraits, however the resulting features will not look exaggerated. In this work, we present an approach for extreme exaggeration of facial features to obtain caricature effect. Our approach is based on the well-known conformal property of maps in complex domains. Namely, any map in a complex domain is angle preserving, which is crucial for caricature generation. Without angle preservation, the maps can result in deformations that look funny or grotesque, but not caricature. We have developed a particular mapping in a complex domain and show that we can obtain a wide variety of faces starting from any illustration (or photograph) of a human face.

This paper presents a deep learning based method that generates body motion for string instrument performance from raw audio. In contrast to prior methods which aim to predict joint position from audio, we first estimate information that dictates the bowing dynamics, such as the bow direction and the played string. The final body motion is then determined from this information following a conversion rule. By adopting the bowing information as the target domain, not only is learning the mapping more feasible, but also the produced results have bowing dynamics that are consistent with the given audio. We confirmed that our results are superior to existing methods through extensive experiments.

We apply virtual reality headsets with eye tracking capabilities to evaluate new training methods for patients living with loss of peripheral vision (“tunnel vision”). It can be shown that systematic gaze patterns, taught in a virtual reality environment, are able to significantly increase the effectively perceived visual area of the participants as well as reduce the number of obstacle collisions in navigation tasks.