SIGGRAPH 2022 论文列表

In this article, we present TightCap, a data-driven scheme to capture both the human shape and dressed garments accurately with only a single three-dimensional (3D) human scan, which enables numerous applications such as virtual try-on, biometrics, and body evaluation. To break the severe variations of the human poses and garments, we propose to model the clothing tightness field—the displacements from the garments to the human shape implicitly in the global UV texturing domain. To this end, we utilize an enhanced statistical human template and an effective multi-stage alignment scheme to map the 3D scan into a hybrid 2D geometry image. Based on this 2D representation, we propose a novel framework to predict clothing tightness field via a novel tightness formulation, as well as an effective optimization scheme to further reconstruct multi-layer human shape and garments under various clothing categories and human postures. We further propose a new clothing tightness dataset of human scans with a large variety of clothing styles, poses, and corresponding ground-truth human shapes to stimulate further research. Extensive experiments demonstrate the effectiveness of our TightCap to achieve the high-quality human shape and dressed garments reconstruction, as well as the further applications for clothing segmentation, retargeting, and animation.

This paper introduces a new weighting scheme for particle-grid transfers that generates hybrid Lagrangian/Eulerian fluid simulations with uniform particle distributions and precise volume control. At its core, our approach reformulates the construction of Power Particles [de Goes et al. 2015] by computing volume-constrained density kernels. We employ these optimized kernels as particle domains within the Generalized Interpolation Material Point method (GIMP) in order to incorporate Power Particles into the Particle-In-Cell framework, hence the name the Power Particle-In-Cell method. We address the construction of volume-constrained density kernels as a regularized optimal transportation problem and describe an iterative solver based on localized Gaussian convolutions that leads to a significant performance speedup compared to [de Goes et al. 2015]. We also present novel extensions for handling free surfaces and solid obstacles that bypass the need for cell clipping and ghost particles. We demonstrate the advantages of our transfer weights by improving hybrid schemes for fluid simulation such as the Fluid Implicit Particle (FLIP) method and the Affine Particle-In-Cell (APIC) method with volume preservation and robustness to varying particle-per-cell ratio, while retaining low numerical dissipation, conserving linear and angular momenta, and avoiding particle reseeding or post-process relaxations.

Three-dimensional (3D) reconstruction using an RGB-D camera has been widely adopted for realistic content creation. However, high-quality texture mapping onto the reconstructed geometry is often treated as an offline step that should run after geometric reconstruction. In this article, we propose TextureMe, a novel approach that jointly recovers 3D surface geometry and high-quality texture in real time. The key idea is to create triangular texture patches that correspond to zero-crossing triangles of truncated signed distance function (TSDF) progressively in a global texture atlas. Our approach integrates color details into the texture patches in parallel with the depth map integration to a TSDF. It also actively updates a pool of texture patches to adapt TSDF changes and minimizes misalignment artifacts that occur due to camera drift and image distortion. Our global texture atlas representation is fully compatible with conventional texture mapping. As a result, our approach produces high-quality textures without utilizing additional texture map optimization, mesh parameterization, or heavy post-processing. High-quality scenes produced by our real-time approach are even comparable to the results from state-of-the-art methods that run offline.

In virtual reality (VR), the virtual scenes are pre-designed by creators. Our physical surroundings, however, comprise significantly varied sizes, layouts, and components. To bridge the gap and further enable natural navigation, recent solutions have been proposed to redirect users or recreate the virtual content. However, they suffer from either interrupted experience or distorted appearances. We present a novel VR-oriented algorithm that automatically restructures a given virtual scene for a user’s physical environment. Different from the previous methods, we introduce neither interrupted walking experience nor curved appearances. Instead, a perception-aware function optimizes our retargeting technique to preserve the fidelity of the virtual scene that appears in VR head-mounted displays. Besides geometric and topological properties, it emphasizes the unique first-person view perceptual factors in VR, such as dynamic visibility and objectwise relationships. We conduct both analytical experiments and subjective studies. The results demonstrate our system’s versatile capability and practicability for natural navigation in VR: It reduces the virtual space by 40% without statistical loss of perceptual identicality.

Vector image representation methods that can faithfully reconstruct objects and color variations in a raster image are desired in many practical applications. This article presents triangular configuration B-spline (referred to as TCB-spline)-based vector graphics for raster image vectorization. Based on this new representation, an automatic raster image vectorization paradigm is proposed. The proposed framework first detects sharp curvilinear features in the image and constructs knot meshes based on the detected feature lines. It iteratively optimizes color and position of control points and updates the knot meshes. By using collinear knots at feature lines, both smooth and discontinuous color variations can be efficiently modeled by the same set of quadratic TCB-splines. A variational knot mesh generation method is designed to adaptively introduce knots and update their connectivity to satisfy the local reconstruction quality. Experiments and comparisons show that our framework outperforms the existing state-of-the-art methods in providing more faithful reconstruction results. In particular, our method is able to model undetected features and subtle or complicated color variations in-between features, which the previous methods cannot handle efficiently. Our vectorization representation also facilitates a variety of editing operations performed directly over vector images.

In the field of topology optimization, the homogenization approach has been revived as an important alternative to the established, density-based methods. Homogenization can represent microstructures at length scales decoupled from the resolution of the computational grid. The optimal microstructure for a single load case is an orthogonal rank-3 laminate. Initially, we investigate where singularities occur in orthogonal rank-3 laminates and show that the laminar parts of the structures we seek are unaffected by the singularities. Based on this observation, we propose a method for generating multi-laminar structures from frame fields that describe rank-3 laminates. Rather than establishing a parametrization of the domain, we compute stream surfaces that align with the frame fields and solve an optimization problem to find a well-spaced collection of such stream surfaces. Since our method does not rely on a parametrization, we also do not need a combing of the frame fields to generate this collection. Finally, we provide a method for synthesizing multi-laminar structures from a stream surface collection. This method produces a volumetric solid for each surface and combines these to form the output. We demonstrate our method on several frame fields produced by the homogenization approach to topology optimization.

When learning a dexterous skill such as playing the piano, people commonly watch videos of a teacher. However, this conventional way has some downsides such as limited information to be retrieved and less intuitive instructions. We propose a virtual training system by visualizing differences between hands to provide intuitive feedback for skill acquisition. After synchronizing the data, two visual cues are proposed including a hand-overlay manner and a two-keyboards visualization. A pilot study confirm the superiority of the proposed methods over conventional video-viewing.

Concept sketches, ubiquitously used in industrial design, are inherently imprecise yet highly effective at communicating 3D shape to human observers. We present a new symmetry-driven algorithm for recovering designer-intended 3D geometry from concept sketches. We observe that most concept sketches of human-made shapes are structured around locally symmetric building blocks, defined by triplets of orthogonal symmetry planes. We identify potential building blocks using a combination of 2D symmetries and drawing order. We reconstruct each such building block by leveraging a combination of perceptual cues and observations about designer drawing choices. We cast this reconstruction as an integer programming problem where we seek to identify, among the large set of candidate symmetry correspondences formed by approximate pen strokes, the subset that results in the most symmetric and well-connected shape. We demonstrate the robustness of our approach by reconstructing 82 sketches, which exhibit significant over-sketching, inaccurate perspective, partial symmetry, and other imperfections. In a comparative study, participants judged our results as superior to the state-of-the-art by a ratio of 2:1.

Computer graphics has experienced a recent surge of data-centric approaches for photorealistic and controllable content creation. StyleGAN in particular sets new standards for generative modeling regarding image quality and controllability. However, StyleGAN’s performance severely degrades on large unstructured datasets such as ImageNet. StyleGAN was designed for controllability; hence, prior works suspect its restrictive design to be unsuitable for diverse datasets. In contrast, we find the main limiting factor to be the current training strategy. Following the recently introduced Projected GAN paradigm, we leverage powerful neural network priors and a progressive growing strategy to successfully train the latest StyleGAN3 generator on ImageNet. Our final model, StyleGAN-XL, sets a new state-of-the-art on large-scale image synthesis and is the first to generate images at a resolution of 10242 at such a dataset scale. We demonstrate that this model can invert and edit images beyond the narrow domain of portraits or specific object classes. Code, models, and supplementary videos can be found at https://sites.google.com/view/stylegan-xl/ .

Can a generative model be trained to produce images from a specific domain, guided only by a text prompt, without seeing any image? In other words: can an image generator be trained "blindly"? Leveraging the semantic power of large scale Contrastive-Language-Image-Pre-training (CLIP) models, we present a text-driven method that allows shifting a generative model to new domains, without having to collect even a single image. We show that through natural language prompts and a few minutes of training, our method can adapt a generator across a multitude of domains characterized by diverse styles and shapes. Notably, many of these modifications would be difficult or infeasible to reach with existing methods. We conduct an extensive set of experiments across a wide range of domains. These demonstrate the effectiveness of our approach, and show that our models preserve the latent-space structure that makes generative models appealing for downstream tasks. Code and videos available at: stylegan-nada.github.io/

We present StyleFusion, a new mapping architecture for StyleGAN, which takes as input a number of latent codes and fuses them into a single style code. Inserting the resulting style code into a pre-trained StyleGAN generator results in a single harmonized image in which each semantic region is controlled by one of the input latent codes. Effectively, StyleFusion yields a disentangled representation of the image, providing fine-grained control over each region of the generated image. Moreover, to help facilitate global control over the generated image, a special input latent code is incorporated into the fused representation. StyleFusion operates in a hierarchical manner, where each level is tasked with learning to disentangle a pair of image regions (e.g., the car body and wheels). The resulting learned disentanglement allows one to modify both local, fine-grained semantics (e.g., facial features) as well as more global features (e.g., pose and background), providing improved flexibility in the synthesis process. As a natural extension, StyleFusion allows one to perform semantically-aware cross-image mixing of regions that are not necessarily aligned. Finally, we demonstrate how StyleFusion can be paired with existing editing techniques to more faithfully constrain the edit to the user’s region of interest. Code is available at: https://github.com/OmerKafri/StyleFusion.

We develop a method to automatically segment a font’s glyphs into a set of overlapping and intersecting strokes with the aim of generating artistic stylizations. The segmentation method relies on a geometric analysis of the glyph’s outline, its interior, and the surrounding areas and is grounded in perceptually informed principles and measures. Our method does not require training data or templates and applies to glyphs in a large variety of input languages, writing systems, and styles. It uses the medial axis, curvilinear shape features that specify convex and concave outline parts, links that connect concavities, and seven junction types. We show that the resulting decomposition in strokes can be used to create variations, stylizations, and animations in different artistic or design-oriented styles while remaining recognizably similar to the input font.

We present stroke transfer, an example-based synthesis method of brushstrokes for animated scenes under changes in viewpoint, lighting conditions, and object shapes. We introduce stroke field for guiding the generation of strokes, consisting of spatially varying attributes of strokes, namely, their orientations, lengths, widths, and colors. Strokes are synthesized as the integral curves of the stroke field. In essence, we separate elements that constitute the artistic stroke into style-specific transferable elements and instance-intrinsic ones. To generate the stroke field, we first compute a set of vector fields that reflect the instance-intrinsic elements and then combine them using style-specific weight functions learned from exemplars, with the weights computed in a proxy feature space shared among a variety of objects. The rendered animation using our method captures time-varying viewpoint, lighting conditions, and object shapes, as well as the artistic style given in the form of exemplars.

In this study, we propose a stereoscopic transparent display that can be viewed with the naked eye. Existing methods for generating realistic high-quality stereoscopic images require wearable devices and the presence of a display, which degrades the sense of presence. Our method increases the sense of presence by making the stereoscopic images blend into the surrounding environment.

Designing curve networks for fabrication requires simultaneous consideration of structural stability, cost effectiveness, and visual appeal—complex, interrelated objectives that make manual design a difficult and tedious task. We present a novel method for fabrication-aware simplification of curve networks, algorithmically selecting a stable subset of given 3D curves. While traditionally stability is measured as magnitude of deformation induced by a set of pre-defined loads, predicting applied forces for common day objects can be challenging. Instead, we directly optimize for minimal deformation under the worst-case load. Our technical contribution is a novel formulation of 3D curve network simplification for worst-case stability, leading to a mixed-integer semi-definite programming problem (MI-SDP). We show that while solving MI-SDP directly is infeasible, a physical insight suggests an efficient greedy approximation algorithm. We demonstrate the potential of our approach on a variety of curve network designs and validate its effectiveness compared to simpler alternatives using numerical experiments.