Computer Science

We present a novel redirected walking controller based on alignment that allows the user to explore large and complex virtual environments, while minimizing the number of collisions with obstacles in the physical environment. Our alignment-based redirection controller, ARC, steers the user such that their proximity to obstacles in the physical environment matches the proximity to obstacles in the virtual environment as closely as possible. To quantify a controller's performance in complex environments, we introduce a new metric, Complexity Ratio (CR), to measure the relative environment complexity and characterize the difference in navigational complexity between the physical and virtual environments. Through extensive simulation-based experiments, we show that ARC significantly outperforms current state-of-the-art controllers in its ability to steer the user on a collision-free path. We also show through quantitative and qualitative measures of performance that our controller is robust in complex environments with many obstacles. Our method is applicable to arbitrary environments and operates without any user input or parameter tweaking, aside from the layout of the environments. We have implemented our algorithm on the Oculus Quest head-mounted display and evaluated its performance in environments with varying complexity. Our project website is available at this https URL.

In this paper, we propose ARCH (Animatable Reconstruction of Clothed Humans), a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image. Existing approaches to digitize 3D humans struggle to handle pose variations and recover details. Also, they do not produce models that are animation ready. In contrast, ARCH is a learned pose-aware model that produces detailed 3D rigged full-body human avatars from a single unconstrained RGB image. A Semantic Space and a Semantic Deformation Field are created using a parametric 3D body estimator. They allow the transformation of 2D/3D clothed humans into a canonical space, reducing ambiguities in geometry caused by pose variations and occlusions in training data. Detailed surface geometry and appearance are learned using an implicit function representation with spatial local features. Furthermore, we propose additional per-pixel supervision on the 3D reconstruction using opacity-aware differentiable rendering. Our experiments indicate that ARCH increases the fidelity of the reconstructed humans. We obtain more than 50% lower reconstruction errors for standard metrics compared to state-of-the-art methods on public datasets. We also show numerous qualitative examples of animated, high-quality reconstructed avatars unseen in the literature so far.

The alternating direction method of multipliers (ADMM) is a popular approach for solving optimization problems that are potentially non-smooth and with hard constraints. It has been applied to various computer graphics applications, including physical simulation, geometry processing, and image processing. However, ADMM can take a long time to converge to a solution of high accuracy. Moreover, many computer graphics tasks involve non-convex optimization, and there is often no convergence guarantee for ADMM on such problems since it was originally designed for convex optimization. In this paper, we propose a method to speed up ADMM using Anderson acceleration, an established technique for accelerating fixed-point iterations. We show that in the general case, ADMM is a fixed-point iteration of the second primal variable and the dual variable, and Anderson acceleration can be directly applied. Additionally, when the problem has a separable target function and satisfies certain conditions, ADMM becomes a fixed-point iteration of only one variable, which further reduces the computational overhead of Anderson acceleration. Moreover, we analyze a particular non-convex problem structure that is common in computer graphics, and prove the convergence of ADMM on such problems under mild assumptions. We apply our acceleration technique on a variety of optimization problems in computer graphics, with notable improvement on their convergence speed.

Extracting a Construction Tree from potentially noisy point clouds is an important aspect of Reverse Engineering tasks in Computer Aided Design. Solutions based on algorithmic geometry impose constraints on usable model representations (e.g. quadric surfaces only) and noise robustness. Re-formulating the problem as a combinatorial optimization problem and solving it with an Evolutionary Algorithm can mitigate some of these constraints at the cost of increased computational complexity. This paper proposes a graph-based search space partitioning scheme that is able to accelerate Evolutionary Construction Tree extraction while exploiting parallelization capabilities of modern CPUs. The evaluation indicates a speed-up up to a factor of 46.6 compared to the baseline approach while resulting tree sizes increased by 25.2% to 88.6% .

To be suitable for film-quality animation, rigs for character deformation must fulfill a broad set of requirements. They must be able to create highly stylized deformation, allow a wide variety of controls to permit artistic freedom, and accurately reflect the design intent. Facial deformation is especially challenging due to its nonlinearity with respect to the animation controls and its additional precision requirements, which often leads to highly complex face rigs that are not generalizable to other characters. This lack of generality creates a need for approximation methods that encode the deformation in simpler structures. We propose a rig approximation method that addresses these issues by learning localized shape information in differential coordinates and, separately, a subspace for mesh reconstruction. The use of differential coordinates produces a smooth distribution of errors in the resulting deformed surface, while the learned subspace provides constraints that reduce the low frequency error in the reconstruction. Our method can reconstruct both face and body deformations with high fidelity and does not require a set of well-posed animation examples, as we demonstrate with a variety of production characters.

We propose a novel approach to robot-operated active understanding of unknown indoor scenes, based on online RGBD reconstruction with semantic segmentation. In our method, the exploratory robot scanning is both driven by and targeting at the recognition and segmentation of semantic objects from the scene. Our algorithm is built on top of the volumetric depth fusion framework (e.g., KinectFusion) and performs real-time voxel-based semantic labeling over the online reconstructed volume. The robot is guided by an online estimated discrete viewing score field (VSF) parameterized over the 3D space of 2D location and azimuth rotation. VSF stores for each grid the score of the corresponding view, which measures how much it reduces the uncertainty (entropy) of both geometric reconstruction and semantic labeling. Based on VSF, we select the next best views (NBV) as the target for each time step. We then jointly optimize the traverse path and camera trajectory between two adjacent NBVs, through maximizing the integral viewing score (information gain) along path and trajectory. Through extensive evaluation, we show that our method achieves efficient and accurate online scene parsing during exploratory scanning.

Most ray tracing libraries allow the user to provide custom functionality that is executed when a potential ray surface interaction was encountered to determine if the interaction was valid or traversal should be continued. This is e.g. useful for alpha mask validation and allows the user to reuse existing ray object intersection routines rather than reimplementing them. Augmenting ray traversal with custom intersection logic requires some kind of callback mechanism that injects user code into existing library routines. With template libraries, this injection can happen statically since the user compiles the binary code herself. We present an implementation of this "custom intersector" approach and its integration into the C++ ray tracing template library Visionaray.

Gupta et al. [1, 2] describe a very beautiful application of algebraic geometry to lattice structures composed of quadric of revolution (quador) implicit surfaces. However, the shapes created have concave edges where the stubs meet, and such edges can be stress-raisers which can cause significant problems with, for instance, fatigue under cyclic loading. This note describes a way in which quadric fillets can be added to these models, thus relieving this problem while retaining their computational simplicity and efficiency.

Trimming is a core technique in geometric modeling. Unfortunately, the resulting objects do not take the requirements of numerical simulations into account and yield various problems. This paper outlines principal issues of trimmed models and highlights different analysis-suitable strategies to address them. It is discussed that these concepts not only provide important computational tools for isogeometric analysis, but can also improve the treatment of trimmed models in a design context.

Field-guided parametrization methods have proven effective for quad meshing of surfaces; these methods compute smooth cross fields to guide the meshing process and then integrate the fields to construct a discrete mesh. A key challenge in extending these methods to three dimensions, however, is representation of field values. Whereas cross fields can be represented by tangent vector fields that form a linear space, the 3D analog---an octahedral frame field---takes values in a nonlinear manifold. In this work, we describe the space of octahedral frames in the language of differential and algebraic geometry. With this understanding, we develop geometry-aware tools for optimization of octahedral fields, namely geodesic stepping and exact projection via semidefinite relaxation. Our algebraic approach not only provides an elegant and mathematically-sound description of the space of octahedral frames but also suggests a generalization to frames whose three axes scale independently, better capturing the singular behavior we expect to see in volumetric frame fields. These new odeco frames, so-called as they are represented by orthogonally decomposable tensors, also admit a semidefinite program--based projection operator. Our description of the spaces of octahedral and odeco frames suggests computing frame fields via manifold-based optimization algorithms; we show that these algorithms efficiently produce high-quality fields while maintaining stability and smoothness.