Timezone: »
Autonomous part assembly is a challenging yet crucial task in 3D computer vision and robotics. Analogous to buying an IKEA furniture, given a set of 3D parts that can assemble a single shape, an intelligent agent needs to perceive the 3D part geometry, reason to propose pose estimations for the input parts, and finally call robotic planning and control routines for actuation. In this paper, we focus on the pose estimation subproblem from the vision side involving geometric and relational reasoning over the input part geometry. Essentially, the task of generative 3D part assembly is to predict a 6-DoF part pose, including a rigid rotation and translation, for each input part that assembles a single 3D shape as the final output. To tackle this problem, we propose an assembly-oriented dynamic graph learning framework that leverages an iterative graph neural network as a backbone. It explicitly conducts sequential part assembly refinements in a coarse-to-fine manner, exploits a pair of part relation reasoning module and part aggregation module for dynamically adjusting both part features and their relations in the part graph. We conduct extensive experiments and quantitative comparisons to three strong baseline methods, demonstrating the effectiveness of the proposed approach.
Author Information
jialei huang (Peking University)
Guanqi Zhan (Peking University)
Qingnan Fan (Stanford University)
Kaichun Mo (Stanford University)
I am currently a fifth-year CS Ph.D. student advised by Prof. Leonidas J. Guibas. My research interests include 3D vision and graphics, deep learning, geometry processing, reinforcement learning and robotics.
Lin Shao (Stanford University)
Baoquan Chen (Shandong University)
Leonidas Guibas (stanford.edu)
Hao Dong (Peking University)
More from the Same Authors
-
2020 Poster: CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations »
Davis Rempe · Tolga Birdal · Yongheng Zhao · Zan Gojcic · Srinath Sridhar · Leonidas Guibas -
2020 Poster: ShapeFlow: Learnable Deformation Flows Among 3D Shapes »
Chiyu Jiang · Jingwei Huang · Andrea Tagliasacchi · Leonidas Guibas -
2020 Spotlight: ShapeFlow: Learnable Deformation Flows Among 3D Shapes »
Chiyu Jiang · Jingwei Huang · Andrea Tagliasacchi · Leonidas Guibas -
2020 Spotlight: CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations »
Davis Rempe · Tolga Birdal · Yongheng Zhao · Zan Gojcic · Srinath Sridhar · Leonidas Guibas -
2019 Poster: Multiview Aggregation for Learning Category-Specific Shape Reconstruction »
Srinath Sridhar · Davis Rempe · Julien Valentin · Bouaziz Sofien · Leonidas Guibas -
2019 Poster: A Condition Number for Joint Optimization of Cycle-Consistent Networks »
Leonidas Guibas · Qixing Huang · Zhenxiao Liang -
2019 Spotlight: A Condition Number for Joint Optimization of Cycle-Consistent Networks »
Leonidas Guibas · Qixing Huang · Zhenxiao Liang -
2018 Poster: Deep Functional Dictionaries: Learning Consistent Semantic Structures on 3D Models from Functions »
Minhyuk Sung · Hao Su · Ronald Yu · Leonidas Guibas -
2018 Poster: DifNet: Semantic Segmentation by Diffusion Networks »
Peng Jiang · Fanglin Gu · Yunhai Wang · Changhe Tu · Baoquan Chen -
2018 Poster: PointCNN: Convolution On X-Transformed Points »
Yangyan Li · Rui Bu · Mingchao Sun · Wei Wu · Xinhan Di · Baoquan Chen -
2017 Poster: PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space »
Charles Ruizhongtai Qi · Li Yi · Hao Su · Leonidas Guibas -
2016 Poster: FPNN: Field Probing Neural Networks for 3D Data »
Yangyan Li · Soeren Pirk · Hao Su · Charles R Qi · Leonidas Guibas -
2015 Poster: Deep Knowledge Tracing »
Chris Piech · Jonathan Bassen · Jonathan Huang · Surya Ganguli · Mehran Sahami · Leonidas Guibas · Jascha Sohl-Dickstein -
2013 Poster: Wavelets on Graphs via Deep Learning »
Raif Rustamov · Leonidas Guibas -
2013 Demonstration: Codewebs: a Pedagogical Search Engine for Code Submissions to a MOOC »
Jonathan Huang · Chris Piech · Andy Nguyen · Leonidas Guibas -
2007 Oral: Efficient Inference forDistributions on Permutations »
Jonathan Huang · Carlos Guestrin · Leonidas Guibas -
2007 Poster: Efficient Inference forDistributions on Permutations »
Jonathan Huang · Carlos Guestrin · Leonidas Guibas