SIGGRAPH 2019 论文列表

A procedural art-directable workflow is developed for voxel 3D printing using existing digital effects technologies. Customised for the Stratasys J750's unique materials, the system produces large-scale prosthetic eyes as a case study for film and display work.

We present Vox-Cells, a volume visualization framework designed for real-time volume investigation and exploration. We seek to treat data as a first-class citizen with a 1:1 relationship between the data and its corresponding representation. CPU-GPU transfer is minimized, and novel approaches to volume construction and lighting are explored in order to maximize performance for deployment on consumer grade Virtual Reality (VR) Head-mounted displays (HMD).

Plasmonic color generation describes structural color arising from resonant interaction between visible light and metallic nanostructures, causing selective frequencies of light to be scattered and/or absorbed [Kristensen et al. 2017; Sun and Xia 2003]. The perceived color from such metallic nanostructures is highly dependent on viewing angle and the color appearance can change with color of the viewing background. Plasmonic color generation is a rapidly emerging research area with potential advantages over conventional pigment printing technology including higher printing resolution and robustness, greater compatibility for integration and functionalization, and reduced resource requirements [Mudachathi and Tanaka 2017; Zhu et al. 2017]. Structural color from plasmonic nanostructures has already been used to improve security measures in currency notes and credit cards [Lee et al. 2018].

Visual effects (called "VFX" in this poster) have expanded the range of expression and been necessary to enhance the mood for the story in films and videos. A variety of software tools which support producing VFX has been developed.

Strokes have a wide range of occurrence among people of all races and genders. The consequences of a stroke often include significant muscle weakness on one side of the body that must be physically exercised to attempt to restore its previous strength and mobility. In traditional mirror therapy, the partially disabled hand or leg is hidden by a mirror. The patient sees a reflection of the healthy side of their body where the disabled limb should be, in order to stimulate brain to operate the partially disabled hand/leg in the proper way. The patient will interact with mirror using unaffected hand and observe its reflection.

In this work, we solve the problem of real-time transfer of geometric style from a single glyph to the entire glyph set of a vector font. In our solution, a single glyph is defined as one or more closed Bézier paths which is further broken down in primitives to define a set of segments. The modification to these segments is percolated to the entire glyph set by comparing the set of segments across glyphs using techniques like the order and direction of segments and the spatial placement of segments. Once the target segments in other glyphs is identified the transformation from style glyph is applied to the target glyph. Furthermore, we establish user-controlled policies for percolation of style like mapping line segment modification to curve segments. This extension to the algorithm enables the user to create multiple variations of a glyph.

Virtual and Augmented Reality (VR and AR) are two fast growing mediums, not only in the entertainment industry but also in health, education and engineering. A good VR or AR application seamlessly merges the real and virtual world, making the user feels fully immersed. Traditionally, a computer-generated object can be interacted with using controllers or hand gestures [HTC 2019; Microsoft 2019; Oculus 2019]. However, these motions can feel unnatural and do not accurately represent the motion of interacting with a real object. On the other hand, a physical object can be used to control the motion of a virtual object. At present, this can be done by tracking purely rigid motion using an external sensor [HTC 2019]. Alternatively, a sparse number of markers can be tracked, for example using a motion capture system, and the positions of these used to drive the motion of an underlying non-rigid model. However, this approach is sensitive to changes in marker position and occlusions and often involves costly non-standard hardware [Vicon 2019]. In addition, these approaches often require a virtual model to be manually sculpted and rigged which can be a time consuming process. Neural networks have been shown to be successful tools in computer vision, with several key methods using networks for tracking rigid and non-rigid motion in RGB images [Andrychowicz et al. 2018; Kanazawa et al. 2018; Pumarola et al. 2018]. While these methods show potential, they are limited to using multiple RGB cameras or large, costly amounts of labelled training data.

This paper proposes an innovative industry practice regarding fractal geometry generating and rendering processes. VFX Fractal Toolkit (VFT) aims to provide powerful, yet intuitive and artist-friendly workflows for exploration and generating of vast amounts of fractals. VFT allows for node-based description of fractals implemented in SideFX Houdini. VFT is built specifically for Visual Effects (VFX) pipelines and employs standard practices. It aims to provide artists with a toolset which would help them explore fractal forms of generative art directly in VFX applications.

We present an unsupervised incremental learning method for refining hand shape and pose estimation. We propose a refiner network (RefNet) that can augment a state-of-the-art hand tracking system (BaseNet) by refining its estimations on unlabeled data. At each input depth frame, the estimations from the BaseNet are iteratively refined by RefNet using a model-fitting strategy. During this process, the RefNet adapts to the input data characteristics by incremental learning. We show that our method provides more accurate hand shape and pose estimates on both a standard dataset and real data.

The ocean surface is highly dynamic. It moves rapidly and thus its shading changes rapidly as well. Usually, this doesn't pose any problems if the shading is smooth. However, for a surface that has a strong highlight or bright reflection moving rapidly, it causes an inaccurate and unnatural flickering. In the traditional rendering algorithms, each frame is rendered independently at a discrete time, resulting in serious temporal aliasing artifacts. Particularly, for a wavy water surface, reflection vectors may not hit the light source even though they actually hit for part of the frame time. Removing such aliasing in real-time is an active research area and many methods have been proposed [Jimenez et al. 2011]. They can improve the fidelity and efficiency of the rendering method. However, their focus is on spatial anti-aliasing and most of them do not address the temporal aliasing problem, particularly the one observed in rendering a reflected image of a light source on the water surface.

We propose a novel method for editing vector graphics which enables users to intuitively modify complex Bézier geometry. Our method uses a Generative Adversarial Network (GAN) to automatically predict salient points for any arbitrary geometry defined by cubic Bézier curves, which are used as handle locations for a Linear Blend Skinning transformation. Further, we bind input geometry to a triangle mesh, to decouple the complexity of input geometry from mesh topology. Finally, to reconstruct Bézier curves from the transformed mesh, we formulate a linear optimization problem and solve it in performant manner to ensure real time feedback, without increasing the number of Bézier segments.

This paper describes "Scented Graphics," our artistic experiments with a scented-printing technique that utilizes an inkjet printer. By mixing water-soluble aromatic oils with inks, an inkjet printer can be utilized to control scent mixing with high precision at almost no extra cost. Such features are hardly provided by the existing scented-printing services at the same level of flexibility and cost-effectiveness. We mimicked the Swiss graphic design in our experiment as the style to facilitate the preliminary investigation of this technique. As scent mixing is a fundamental technique in olfactory art, our experiments can be beneficial as design exemplars as a preliminary exploration of the technique.

DisplayBowl is a bowl-shaped hemispherical display for showing omnidirectional images with direction data. It provides users with a novel way of observing 360-degree video streams, which improves the awareness of the surroundings when operating a remote-controlled vehicle compared to conventional flat displays and HMDs. In this paper, we present a user study, in which we asked participants to control a remote drone using an omnidirectional video streaming, to compare the uniqueness and advantages of three displays: a flat panel display, a head-mounted display and DisplayBowl.

The Ouija board game is associated with a type of involuntary motion known as an ideomotor action. We sought to clarify the conditions under which this motion occurs by evaluating the effect that visual and haptic movement cues have on its occurrence. Using our lateral skin deformation device, we found that the simultaneous presentation of visual and tactile illusory motion and force produced larger ideomotor actions than when either modality presented alone, an effect that was further potentiated by the presence of another player (an avatar).

In computer graphics, stippling is a widely used non-photorealistic rendering technique. As the art of representing images with dots, one of the key problems is the placement of dots. In general, they should be distributed evenly, and with some randomness at the same time. Blue noise methods provide these characteristics and are used by state-of-the-art gray-scale algorithms to distribute dots. Color stippling, however, is more challenging as each channel should have even distribution at the same time. Existing approaches cast color stippling as a multi-class blue noise sampling problem and provide high quality results at the cost of a very long processing time. In this paper, we propose a real-time structure aware method for color stippling, based on samples generated from an incremental voronoi set. Our method can handle an arbitrary input color vector for stippling and produce significantly better results than previous methods, at real-time frame rate. We evaluate the perceptual quality of our stippling with a user study and its numerical performance by measuring the MSE between the reconstructed image from the stippling and the input image. As a result, the real time performance of our method makes interactive stippling editing possible, providing the artist with an effective tool to explore quickly a wide space of color image stippling.

This paper proposes an intuitive tool for users to create 3D architectural models through 2D sketch input. A user only needs to draw the outline of a frontal or oblique view of a building. Our system recognizes the parts drawn in a sketch and estimates their types. The estimated information is then used to compose the corresponding 3D model. Besides, our system provides additional assistant tools for rapid editing. The modeling process can be iterative and incremental. To accomplish a building complex, a user can gradually create their models from one view to another. Our experiment shows that the proposed interface with sketch analysis tools eases the process of 3D building modeling.

Light projection onto falling water produces distinct and impressive experience which is suitable for entertainment and advertising installations in public spaces [Barnum et al. 2010; Eitoku et al. 2006]. One of popular and classical techniques used in illuminating water for such purposes is strobe lighting, which presents optical illusion of levitating --- or slowly falling or rising --- water drops depending on the relation between water dropping and strobe lighting frequencies (e.g. [Pevnick 1981; Rosenthal 1984]).