SIGGRAPH 2022 论文列表

Generating the texture map for a 3D human mesh from a single image is challenging. To generate a plausible texture map, the invisible parts of the texture need to be synthesized with relevance to the visible part and the texture should semantically align to the UV space of the template mesh. To overcome such challenges, we propose a novel method that incorporates SamplerNet and RefineNet. SamplerNet predicts a sampling grid that enables sampling from the given visible texture information, and RefineNet refines the sampled texture to maintain spatial alignment.

This paper describes the use of Generative Adversarial Network (GAN) applied to the Wave Function Collapse (WFC) algorithm for procedural content generation. The goal of this system is to enable level designers to generate coherent 3D worlds with brand new meshes generated by the GAN.

This work introduces DynaPix, a Krita extension that automatically generates pixelated images and surface normals from an input image. DynaPix is a tool that aids pixel artists and game developers more efficiently develop 8-bit style games and bring them to life with dynamic lighting through normal maps that can be used in modern game engines such as Unity. The extension offers artists a degree of flexibility as well as allows for further refinements to generated artwork. Powered by out of the box solutions, DynaPix is a tool that seamlessly integrates in the artistic workflow.

We propose a new light source representation to intuitively model complicated lighting effects with simple user interactions. Our representation uses two layers; an emissive layer which is a traditional diffuse area light source with a constant emission, and a lighting gel layer which introduces variations to the emission. The lighting gel layer is mapped with a texture for colored shadows without modeling a 3D scene. The two layers are transformed independently to cast the texture with different effects. To cast lighting on a planar canvas in 2D design, the proposed light source can be created and edited in the 2D canvas directly, without switching to 3D world space.

An increased interest in public motion capture data has allowed for the use of data-driven animation algorithms through neural networks. While motion capture data is increasingly accessible, data sets have become too large to sort through manually. Similarity metrics quantify how different two motions are and can be used to search databases much faster when compared to manual searches as well as to train neural networks. However, the most popular similarity metrics are not informed by human perception, resulting in the potential for data that is not perceptually similar being labeled as such by these metrics. We conducted an experiment with hand motions to identify how large the differences between human perception and common similarity metrics are. In this study, participants watched two animations of hand motions, one altered and the other unaltered, and scored their similarity on a 7-point Likert scale. In our comparisons, we found that none of the tested similarity metrics correlated with human judged scores of similarity.

In this study, we proposed an exergame to reduce resistance to exercise and maintain motivation in adolescents with orthostatic dysregulation. We created a 2D side-scrolling action game in Unity to be played on smartphones. The game is synchronized with exercises that can be done in a lying posture. We analyzed the effect of the game on the feelings of the participants. Our experiments showed that the use of the exergame has a positive effect on the participants’ emotions during exercise.

Inside-out optical 2D tracking of tangible objects on a surface oftentimes uses a high-resolution pattern printed on the surface. While De-Bruijn-torus patterns offer maximum information density, their orientation must be known to decode them. Determining the orientation is challenging for patterns with very fine details; traditional algorithms, such as Hough Lines, do not work reliably. We show that a convolutional neural network can reliably determine the orientation of quasi-random bitmaps with 6 × 6 pixels per block within 36 × 36 pixel images taken by a mouse sensor. Mean error rate is below 2°. Furthermore, our model outperformed Hough Lines in a test with arbitrarily rotated low-resolution rectangles. This implies that CNN-based rotation-detection might also be applicable for more general use cases.

Monte Carlo path tracing generates renderings by estimating the rendering equation using the Monte Carlo method. Studies focus on rendering a noisy image at the original resolution with a low sample per pixel count to decrease the rendering time. Image-space denoising is then applied to produce a visually appealing output. However, denoising process cannot handle the high variance of the noisy image accurately if the sample count is reduced harshly to finish the rendering in a shorter time. We propose a framework that renders the image at a reduced resolution to cast more samples than the harshly lowered sample count in the same time budget. The image is then robustly denoised, and the denoised result is upsampled using original resolution G-buffer of the scene as guidance.

Using smartphones while walking is becoming a social problem. Recent works try to support this issue by different warning systems. However, most only focus on detecting obstacles, without considering the risk to the user. In this paper, we propose a deep learning-based context-aware risk prediction system using a built-in camera on smartphones, aiming to notify ”smombies” by a risk-degree based algorithm. The proposed system both estimates the risk degree of a potential obstacle and the user’s status, which can also be used for distracted driving or visually impaired people.

We present a compressed volumetric data structure and traversal algorithm that interactively visualizes complete terabyte-scale scientific data. Previous methods rely on heavy approximation and do not provide individual sample-level representation when going beyond gigabytes. We develop an extensible pipeline that makes the data streamable on GPU using compact pointers and a compression algorithm based on wavelet transform. The resulting approach renders high-resolution captures under varying sampling characteristics in real-time.

ACM Reference Format: Mikihito Matsuura, Koya Narumi, Toshiki Aoki, Yuta Noma, Kazutaka Nakashima, Yoshihiro Kawahara, and Takeo Igarashi. 2022. Blow-up Print: Rapidly 3D Printing Inflatable Objects in the Compressed State. In Special Interest Group on Computer Graphics and Interactive Techniques Conference Posters (SIGGRAPH ’22 Posters), August 07-11, 2022. ACM, New York, NY, USA, 2 pages. https://doi.org/10.1145/3532719.3543230

Figure 1: Spatiotemporal layout of the presented experiment. (a) Spatial layout of the experiments. There were three possible locations of the visual targets (which subtended a visual angle of one degree) inside the participant’s field of view (FoV). Auditory stimuli were spatially located outside the FoV. Both the visual targets and the auditory stimuli moved in solidarity with the participant’s head. One possible combination for an audiovisual stimuli is highlighted in blue. (b) Temporal layout. Visual targets were shown 100 ms after the sound started, for a duration of 24 ms. The auditory stimulus lasted 400 ms in order for the more complex sounds to be played completely. (c) Representative close-up view of the virtual environment. The inset shows five different visual targets (a 3.2x scale is used here for visualization purposes). Participants could freely move in a physical space of 4x1.5m. Scene by Barking Dog for Unity 3D. Six different sounds were used: white noise, pink noise, brown noise, pure frequencies, train horn and human voice.

This paper presents an audio-to-animation synthesis method for violin performance. This new approach provides a fine-grained violin performance animation using information on playing procedure consisting of played string, finger number, position, and bow direction. We demonstrate that our method is capable of synthesizing natural violin performance animation with fine fingering and bowing through extensive evaluation.