StructEdit: Learning Structural Shape VariationsKaichun Mo*, Paul Guerrero*, Li Yi, Hao Su, Peter Wonka, Niloy Mitra and Leonidas J. GuibasWe learn local shape edits (shape deltas) space that captures both discrete structural changes and continuous variations. Our approach is based on a conditional variational autoencoder (cVAE) for encoding and decoding shape deltas, conditioned on a source shape. The learned shape delta spaces support shape edit suggestions, shape analogy, and shape edit transfer, much better than StructureNet, on the PartNet dataset. [Paper] [Project] [Bibtex] |
|
StructureNet: Hierarchical Graph Networks for 3D Shape GenerationKaichun Mo*, Paul Guerrero*, Li Yi, Hao Su, Peter Wonka, Niloy Mitra and Leonidas J. GuibasACM Transactions on Graphics (SIGGRAPH Asia 2019) We introduce a hierarchical graph network for learning structure-aware shape generation which (i) can directly encode shape parts represented as such n-ary graphs; (ii) can be robustly trained on large and complex shape families such as PartNet; and (iii) can be used to generate a great diversity of realistic structured shape geometries with both both continuous geometric and discrete structural variations. [Paper] [Project] [Bibtex] |
|
PartNet: A Large-scale Benchmark for Fine-grained and Hierarchical Part-level 3D Object UnderstandingKaichun Mo, Shilin Zhu, Angel X.Chang, Li Yi, Subarna Tripathi, Leonidas J. Guibas and Hao SuCVPR 2019 (Also be present at The Sixth Workshop on Fine-Grained Visual Categorization and the 3D Scene Generation Workshop) Featured in: The Robot Report, IEEE Spectrum, Robotics Business Review, TechCrunch, VentureBeat, Intel AI Blog, Intel Newsroom We propose a 3D object database with fine-grained and hierarchical part annotation, to assist segmentation and affordance research. We benchmark three part-level object understanding tasks: fine-grained semantic segmentation, hierarchical semantic segmentation and instance segmentation. We also propose a novel method for instance segmentation. [Paper] [Project] [Bibtex] |
|
The AdobeIndoorNav Dataset: Towards Deep Reinforcement Learning based Real-world Indoor Robot Visual NavigationKaichun Mo, Haoxiang Li, Zhe Lin and Joon-Young LeearXiv:1802.08824 [cs.RO] We propose an indoor navigation dataset for visual navigation and deep reinforcement learning research. We show that the current mapless DRL-based method suffers from the target generalization and scene generalization issues. We propose methods to improve target generalization. [Paper] [Project] [Bibtex] |
|
PointNet: Deep Learning on Point Sets for 3D Classification and SegmentationCharles R. Qi*, Hao Su*, Kaichun Mo and Leonidas J. GuibasCVPR 2017, Oral Presentation We propose novel neural networks to directly consume an unordered point cloud as input, without converting to other 3D representations such as voxel grids first. Rich theoretical and empirical analyses are provided. [Paper] [Project] [Bibtex] |
|
Accelerating Random Kaczmarz Algorithm Based on Clustering InformationYujun Li, Kaichun Mo and Haishan YeAAAI 2016 Using the property of randomly sampled data in high-dimensional space, we propose an accelerated algorithm based on clustering information to improve block Kaczmarz and Kaczmarz via Johnson-Lindenstrauss lemma. Additionally, we theoretically demonstrate convergence improvement on block Kaczmarz algorithm. [Paper] [Bibtex] |
|
(*: indicates equal contribution.) |