postPerspective

You are here

Technical Papers

Perception of Shapes and People

Tuesday, 26 July, 9:00 am - 10:30 am, Anaheim Convention Center, Ballroom D
Session Chair: Michiel van de Panne, The University of British Columbia

Tactile Mesh Saliency

This paper introduces the problem of tactile mesh saliency and develops a deep metric learning framework to solve this problem. Applications for the computed saliency metrics include material suggestion for rendering and fabrication.

Manfred Lau
Lancaster University

Kapil Dev
Lancaster University

Weiqi Shi
Yale University

Julie Dorsey
Yale University

Holly Rushmeier
Yale University

Perceptual Effect of Shoulder Motions on Crowd Animations

Crowd simulators typically do not account for influences between characters at the animation level. This paper presents a set of experiments demonstrating that secondary shoulder motions are beneficial to prevent spectators from perceiving slight residual collisions and to globally increase the perceived level of animation naturalness.

Ludovic Hoyet
Inria

Anne-Hélène Olivier
Université Rennes 2

Richard Kulpa
Université Rennes 2

Julien Pettré
Inria

Body Talk: Crowd Shaping Realistic 3D Avatars With Words

This paper estimates perceptually and metrically accurate 3D human avatars from crowd-sourced ratings of images using linguistic shape descriptions. Words convey significant metric information, suggesting that humans share a shape representation mediating language and vision. Crowd shaping uses the "perception of crowds" to create body shapes without a scanner and enable novel applications.

Stephan Streuber
Max-Planck-Institut für Intelligente Systeme

M. Alejandra Quiros-Ramirez
Max-Planck-Institut für Intelligente Systeme

Matthew Q. Hill
University of Texas at Dallas

Carina A. Hahn
University of Texas at Dallas

Silvia Zuffi
Istituto per le tecnologie della costruzione

Alice O'Toole
University of Texas at Dallas

Michael Black
Max-Planck-Institut für Intelligente Systeme

An Interaction-Aware Perceptual Model for Non-Linear Elastic Objects

A model for evaluating similarity of elastic objects by building a perceptual space of compliance and providing a computational model for it. Applications range from object-similarity prediction, through speeding of computational time of elastic material assignment, to saving material costs by using cheaper materials and/or printers.

Michal Piovarči
Univerzita Komenského, Universität des Saarlandes

David Levin
Disney Research

Jason Rebello
Harvard University

Desai Chen
Massachusetts Institute of Technology

Roman Ďurikovič
Univerzita Komenského

Hanspeter Pfister
Harvard University

Wojciech Matusik
Massachusetts Institute of Technology

Piotr Didyk
Max-Planck-Institut für Informatik and Universität des Saarlandes, MMCI