Now showing items 1-20 of 22

    • DFR: Differentiable Function Rendering for Learning 3D Generation from Images 

      Wu, Yunjie; Sun, Zhengxing (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Learning-based 3D generation is a popular research field in computer graphics. Recently, some works adapted implicit function defined by a neural network to represent 3D objects and have become the current state-of-the-art. ...
    • Poisson Surface Reconstruction with Envelope Constraints 

      Kazhdan, Misha; Chuang, Ming; Rusinkiewicz, Szymon; Hoppe, Hugues (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Reconstructing surfaces from scanned 3D points has been an important research area for several decades. One common approach that has proven efficient and robust to noise is implicit surface reconstruction, i.e. fitting to ...
    • Generating Adversarial Surfaces via Band-Limited Perturbations 

      Mariani, Giorgio; Cosmo, Luca; Bronstein, Alex M.; Rodolà, Emanuele (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Adversarial attacks have demonstrated remarkable efficacy in altering the output of a learning model by applying a minimal perturbation to the input data. While increasing attention has been placed on the image domain, ...
    • A Parametric Analysis of Discrete Hamiltonian Functional Maps 

      Postolache, Emilian; Fumero, Marco; Cosmo, Luca; Rodolà, Emanuele (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      In this paper we develop an in-depth theoretical investigation of the discrete Hamiltonian eigenbasis, which remains quite unexplored in the geometry processing community. This choice is supported by the fact that Dirichlet ...
    • A Simple Discretization of the Vector Dirichlet Energy 

      Stein, Oded; Wardetzky, Max; Jacobson, Alec; Grinspun, Eitan (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      We present a simple and concise discretization of the covariant derivative vector Dirichlet energy for triangle meshes in 3D using Crouzeix-Raviart finite elements. The discretization is based on linear discontinuous ...
    • Geometry Processing 2020 CGF 39-5: Frontmatter 

      Jacobson, Alec; Huang, Qixing (The Eurographics Association and John Wiley & Sons Ltd., 2020)
    • Topology-Aware Surface Reconstruction for Point Clouds 

      Brüel-Gabrielsson, Rickard; Ganapathi-Subramanian, Vignesh; Skraba, Primoz; Guibas, Leonidas J. (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      We present an approach to incorporate topological priors in the reconstruction of a surface from a point scan. We base the reconstruction on basis functions which are optimized to provide a good fit to the point scan while ...
    • Nonlinear Deformation Synthesis via Sparse Principal Geodesic Analysis 

      Sassen, Josua; Hildebrandt, Klaus; Rumpf, Martin (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      This paper introduces the construction of a low-dimensional nonlinear space capturing the variability of a non-rigid shape from a data set of example poses. The core of the approach is a Sparse Principal Geodesic Analysis ...
    • Anderson Acceleration for Nonconvex ADMM Based on Douglas-Rachford Splitting 

      Ouyang, Wenqing; Peng, Yue; Yao, Yuxin; Zhang, Juyong; Deng, Bailin (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      The alternating direction multiplier method (ADMM) is widely used in computer graphics for solving optimization problems that can be nonsmooth and nonconvex. It converges quickly to an approximate solution, but can take a ...
    • EGGS: Sparsity-Specific Code Generation 

      Tang, Xuan; Schneider, Teseo; Kamil, Shoaib; Panda, Aurojit; Li, Jinyang; Panozzo, Daniele (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Sparse matrix computations are among the most important computational patterns, commonly used in geometry processing, physical simulation, graph algorithms, and other situations where sparse data arises. In many cases, the ...
    • Interactive Sculpting of Digital Faces Using an Anatomical Modeling Paradigm 

      Gruber, Aurel; Fratarcangeli, Marco; Zoss, Gaspard; Cattaneo, Roman; Beeler, Thabo; Gross, Markus; Bradley, Derek (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Digitally sculpting 3D human faces is a very challenging task. It typically requires either 1) highly-skilled artists using complex software packages for high quality results, or 2) highly-constrained simple interfaces for ...
    • Medial Axis Isoperimetric Profiles 

      Zhang, Paul; DeFord, Daryl; Solomon, Justin (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Recently proposed as a stable means of evaluating geometric compactness, the isoperimetric profile of a planar domain measures the minimum perimeter needed to inscribe a shape with prescribed area varying from 0 to the ...
    • A Laplacian for Nonmanifold Triangle Meshes 

      Sharp, Nicholas; Crane, Keenan (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      We describe a discrete Laplacian suitable for any triangle mesh, including those that are nonmanifold or nonorientable (with or without boundary). Our Laplacian is a robust drop-in replacement for the usual cotan matrix, ...
    • Fabricable Unobtrusive 3D-QR-Codes with Directional Light 

      Peng, Hao; Liu, Peiqing; Lu, Lin; Sharf, Andrei; Liu, Lin; Lischinski, Dani; Chen, Baoquan (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      QR code is a 2D matrix barcode widely used for product tracking, identification, document management and general marketing. Recently, there have been various attempts to utilize QR codes in 3D manufacturing by carving QR ...
    • Interpolated Corrected Curvature Measures for Polygonal Surfaces 

      Lachaud, Jacques-Olivier; Romon, Pascal; Thibert, Boris; Coeurjolly, David (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      A consistent and yet practically accurate definition of curvature onto polyhedral meshes remains an open problem. We propose a new framework to define curvature measures, based on the Corrected Normal Current, which ...
    • Approximating Isosurfaces by Guaranteed-quality Triangular Meshes 

      Hass, Joel; Trnkova, Maria (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      We describe a new method for approximating an implicit surface F by a piecewise-flat triangulated surface whose triangles are as close as possible to equilateral. The main advantage is improved mesh quality which is ...
    • Learning Part Boundaries from 3D Point Clouds 

      Loizou, Marios; Averkiou, Melinos; Kalogerakis, Evangelos (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      We present a method that detects boundaries of parts in 3D shapes represented as point clouds. Our method is based on a graph convolutional network architecture that outputs a probability for a point to lie in an area that ...
    • Integer-Grid Sketch Simplification and Vectorization 

      Stanko, Tibor; Bessmeltsev, Mikhail; Bommes, David; Bousseau, Adrien (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      A major challenge in line drawing vectorization is segmenting the input bitmap into separate curves. This segmentation is especially problematic for rough sketches, where curves are depicted using multiple overdrawn strokes. ...
    • Cost Minimizing Local Anisotropic Quad Mesh Refinement 

      Lyon, Max; Bommes, David; Kobbelt, Leif (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      Quad meshes as a surface representation have many conceptual advantages over triangle meshes. Their edges can naturally be aligned to principal curvatures of the underlying surface and they have the flexibility to create ...
    • Consistent ZoomOut: Efficient Spectral Map Synchronization 

      Huang, Ruqi; Ren, Jing; Wonka, Peter; Ovsjanikov, Maks (The Eurographics Association and John Wiley & Sons Ltd., 2020)
      In this paper, we propose a novel method, which we call CONSISTENT ZOOMOUT, for efficiently refining correspondences among deformable 3D shape collections, while promoting the resulting map consistency. Our formulation is ...