Gamasutra

If you missed SIGGRAPH 2017 watch a selection of recorded Live Streaming Sessions.

You are here

Technical Papers

Comparing 3D Shapes and Parts

Renderosity

Epson

Monday, 31 July, 3:45 pm - 5:35 pm, Los Angeles Convention Center, Los Angeles Convention Center - Room 153
Session Chair: Niloy Mitra, University College London

Co-Locating Style-Defining Elements on 3D Shapes

A method to translate high-level style descriptions, such as “Ming” or “European” for furniture models, into explicit and localized regions over the geometric models that characterize each style.

Ruizhen Hu
Shenzhen University

Wenchao Li
Shenzhen Institute of Advanced Technology

Oliver Van Kaick
Carleton University

Hui Huang
Shenzhen Institute of Advanced Technology

Melinos Averkiou
University of Cyprus

Daniel Cohen-Or
Tel Aviv University

Hao Zhang
Simon Fraser University

Deformation-Driven Shape Correspondence via Shape Recognition

A method for fine-grained, topology-varying part correspondence between two 3D shapes where the core evaluation mechanism only tests global, visual shape similarity.

Chenyang Zhu
Simon Fraser University, National University of Defense Technology

Renjiao Yi
Simon Fraser University, National University of Defense Technology

Wallace Lira
Simon Fraser University

Ibraheem Alhashim
Simon Fraser University

Kai Xu
National University of Defense Technology

Hao Zhang
Simon Fraser University

GRASS: Generative Recursive Autoencoders for Shape Structures

Introducing GRASS (Generative Recursive Autoencoders for Shape Structures), a novel neural network architecture for encoding and synthesis of 3D shapes, particularly their structures.

Jun Li
National University Of Defense Technology

Kai Xu
National University Of Defense Technology

Siddhartha Chaudhuri
Indian Institute of Technology Bombay

Ersin Yumer
Adobe Research

Hao (Richard) Zhang
Simon Fraser University

Leonidas Guibas
Stanford University

Retrieval on Parametric Shape Collections

This work describes a descriptor-based approach for efficient representation of parametric shapes in a collection, allowing accurate and fast shape-based matching and retrieval.

Adriana Schulz
Massachusetts Institute of Technology, Instituto Nacional de Matemática Pura e Aplicada

Ariel Shamir
Interdisciplinary Center Herzliya

Ilya Baran
Onshape Inc.

David I.W. Levin
University of Toronto

Pitchaya Sitthi-Amorn
Chulalongkorn University

Wojciech Matusik
Massachusetts Institute of Technology

Understanding and Exploiting Object Interaction Landscapes

Interactions play a key role in understanding objects and scenes for virtual and real-world agents. This paper introduces a representation for interactions among physical objects that is agnostic to the type of objects or interaction involved.

Sören Pirk
Stanford University

Vojtech Krs
Purdue University

Kaimo Hu
Purdue University

Suren Deepak Rajasekaran
Purdue University

Hao Kang
Purdue University

Bedrich Benes
Purdue University

Yusuke Yoshiyasu
Centre national de la recherche scientifique

Leonidas Guibas
Stanford University