Computer Science

Given new pairs of source and target point sets, standard point set registration methods often repeatedly conduct the independent iterative search of desired geometric transformation to align the source point set with the target one. This limits their use in applications to handle the real-time point set registration with large volume dataset. This paper presents a novel method, named coherent point drift networks (CPD-Net), for the unsupervised learning of geometric transformation towards real-time non-rigid point set registration. In contrast to previous efforts (e.g. coherent point drift), CPD-Net can learn displacement field function to estimate geometric transformation from a training dataset, consequently, to predict the desired geometric transformation for the alignment of previously unseen pairs without any additional iterative optimization process. Furthermore, CPD-Net leverages the power of deep neural networks to fit an arbitrary function, that adaptively accommodates different levels of complexity of the desired geometric transformation. Particularly, CPD-Net is proved with a theoretical guarantee to learn a continuous displacement vector function that could further avoid imposing additional parametric smoothness constraint as in previous works. Our experiments verify the impressive performance of CPD-Net for non-rigid point set registration on various 2D/3D datasets, even in the presence of significant displacement noise, outliers, and missing points. Our code will be available at this https URL.

We propose a collaborative 3D modeling system, which is based on the blockchain technology. Our approach uses the blockchain to communicate with modeling tools and to provide them a decentralized database of the mesh modification history. This approach also provides a server-less version control system: users can commit their modifications to the blockchain and checkout others' modifications from the blockchain. As a result, our system enables users to do collaborative modeling without any central server.

Most commercially available optical see-through head-mounted displays (OST-HMDs) utilize optical combiners to simultaneously visualize the physical background and virtual objects. The displayed images perceived by users are a blend of rendered pixels and background colors. Enabling high fidelity color perception in mixed reality (MR) scenarios using OST-HMDs is an important but challenging task. We propose a real-time rendering scheme to enhance the color contrast between virtual objects and the surrounding background for OST-HMDs. Inspired by the discovery of color perception in psychophysics, we first formulate the color contrast enhancement as a constrained optimization problem. We then design an end-to-end algorithm to search the optimal complementary shift in both chromaticity and luminance of the displayed color. This aims at enhancing the contrast between virtual objects and the real background as well as keeping the consistency with the original color. We assess the performance of our approach using a simulated OST-HMD environment and an off-the-shelf OST-HMD. Experimental results from objective evaluations and subjective user studies demonstrate that the proposed approach makes rendered virtual objects more distinguishable from the surrounding background, thereby bringing a better visual experience.

Human endeavor has involved making choices about color and looking for ways to color objects since the dawn of civilization. While it has been the exclusive domain of artists and craftspeople for millennia, the last century has seen the introduction of a scientific basis to color communication. The ultimate goal of this development is for color communication to happen seamlessly and in a transparent way. There are however two categories of challenges here: first, understanding and quantifying color needs and expectation and second, developing control mechanisms that deliver the desired color. In this paper a review will be presented of the color needs in end-to-end color journeys, from initial concept to final colored object and an overview of recent developments in color printing will follow. Topics like imaging pipelines (including the recently-introduced HP Pixel Control), the ease of use of color workflows (including HP Smart Color Tools), the handling of brand or corporate identity colors (via HP Professional PANTONE Emulation) and the measurement of color difference under specific viewing arrangements (i.e., the dENS metric for viewing samples without separation) will be addressed. Finally, a series of challenges for the future will be set out, so that their solution can be approached by both academic and industrial communities.

Empty space skipping can be efficiently implemented with hierarchical data structures such as k-d trees and bounding volume hierarchies. This paper compares several recently published hierarchical data structures with regard to construction and rendering performance. The papers that form our prior work have primarily focused on interactively building the data structures and only showed that rendering performance is superior to using simple acceleration data structures such as uniform grids with macro cells. In the area of surface ray tracing, there exists a trade-off between construction and rendering performance of hierarchical data structures. In this paper we present performance comparisons for several empty space skipping data structures in order to determine if such a trade-off also exists for volume rendering with uniform data topologies.

We present a novel approach to enrich arbitrary rig animations with elastodynamic secondary effects. Unlike previous methods which pit rig displacements and physical forces as adversaries against each other, we advocate that physics should complement artists intentions. We propose optimizing for elastodynamic displacements in the subspace orthogonal to displacements that can be created by the rig. This ensures that the additional dynamic motions do not undo the rig animation. The complementary space is high dimensional, algebraically constructed without manual oversight, and capable of rich high-frequency dynamics. Unlike prior tracking methods, we do not require extra painted weights, segmentation into fixed and free regions or tracking clusters. Our method is agnostic to the physical model and plugs into non-linear FEM simulations, geometric as-rigid-as-possible energies, or mass-spring models. Our method does not require a particular type of rig and adds secondary effects to skeletal animations, cage-based deformations, wire deformers, motion capture data, and rigid-body simulations.

We present a novel representation of compressed data structure for simultaneous bounding volume hierarchy (BVH) traversals like they appear for instance in collision detection & proximity query. The main idea is to compress bounding volume (BV) descriptors and cluster BVH into a smaller parts 'treelet' that fit into CPU cache while at the same time maintain random-access and automatic cache-aware data structure layouts. To do that, we quantify BV and compress 'treelet' using predictor-corrector scheme with the predictor at a specific node in the BVH based on the chain of BVs upwards.

Despite the increasing availability of personal fabrication hardware and services, the true potential of digital fabrication remains unrealized due to lack of computational techniques that can support 3D shape design by non-experts. This work develops computational methods that address two key aspects of content creation:(1) Function-driven design synthesis, (2) Design assessment. For design synthesis, a generative shape modeling algorithm that facilitates automatic geometry synthesis and user-driven modification for non-experts is introduced. A critical observation that arises from this study is that the most geometrical specifications are dictated by functional requirements. To support design by high-level functional prescriptions, a physics based shape optimization method for compliant coupling behavior design has been developed. In line with this idea, producing complex 3D surfaces from flat 2D sheets by exploiting the concept of buckling beams has also been explored. Effective design assessment, the second key aspect, becomes critical for problems in which computational solutions do not exist. For these problems, this work proposes crowdsourcing as a way to empower non-experts in esoteric design domains that traditionally require expertise and specialized knowledge.

Cold bent glass is a promising and cost-efficient method for realizing doubly curved glass façades. They are produced by attaching planar glass sheets to curved frames and require keeping the occurring stress within safe limits. However, it is very challenging to navigate the design space of cold bent glass panels due to the fragility of the material, which impedes the form-finding for practically feasible and aesthetically pleasing cold bent glass façades. We propose an interactive, data-driven approach for designing cold bent glass façades that can be seamlessly integrated into a typical architectural design pipeline. Our method allows non-expert users to interactively edit a parametric surface while providing real-time feedback on the deformed shape and maximum stress of cold bent glass panels. Designs are automatically refined to minimize several fairness criteria while maximal stresses are kept within glass limits. We achieve interactive frame rates by using a differentiable Mixture Density Network trained from more than a million simulations. Given a curved boundary, our regression model is capable of handling multistable configurations and accurately predicting the equilibrium shape of the panel and its corresponding maximal stress. We show predictions are highly accurate and validate our results with a physical realization of a cold bent glass surface.

Trusses are load-carrying light-weight structures consisting of bars connected at joints ubiquitously applied in a variety of engineering scenarios. Designing optimal trusses that satisfy functional specifications with a minimal amount of material has interested both theoreticians and practitioners for more than a century. In this paper, we introduce two main ideas to improve upon the state of the art. First, we formulate an alternating linear programming problem for geometry optimization. Second, we introduce two sets of complementary topological operations, including a novel subdivision scheme for global topology refinement inspired by Michell's famed theoretical study. Based on these two ideas, we build an efficient computational framework for the design of lightweight trusses. \AD{We illustrate our framework with a variety of functional specifications and extensions. We show that our method achieves trusses with smaller volumes and is over two orders of magnitude faster compared with recent state-of-the-art approaches.