• Publications
  • Influence
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
TLDR
This paper designs a novel type of neural network that directly consumes point clouds, which well respects the permutation invariance of points in the input and provides a unified architecture for applications ranging from object classification, part segmentation, to scene semantic parsing.
PartNet: A Large-Scale Benchmark for Fine-Grained and Hierarchical Part-Level 3D Object Understanding
TLDR
This work presents PartNet, a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information, and proposes a baseline method for part instance segmentation that is superior performance over existing methods.
SAPIEN: A SimulAted Part-Based Interactive ENvironment
TLDR
SAPIEN is a realistic and physics-rich simulated environment that hosts a large-scale set of articulated objects that enables various robotic vision and interaction tasks that require detailed part-level understanding and hopes it will open research directions yet to be explored.
StructureNet: Hierarchical Graph Networks for 3D Shape Generation
TLDR
StructureNet is introduced, a hierarchical graph network which can directly encode shapes represented as such n-ary graphs, and can be robustly trained on large and complex shape families and used to generate a great diversity of realistic structured shape geometries.
Generative 3D Part Assembly via Dynamic Graph Learning
TLDR
An assembly-oriented dynamic graph learning framework that leverages an iterative graph neural network as a backbone that conducts sequential part assembly refinements in a coarse-to-fine manner and 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.
PT2PC: Learning to Generate 3D Point Cloud Shapes from Part Tree Conditions
TLDR
A conditional GAN "part tree"-to-point cloud" model (PT2PC) that disentangles the structural and geometric factors and incorporates the part tree condition into the architecture design by passing messages top-down and bottom-up along the part Tree hierarchy.
Learning to Group: A Bottom-Up Framework for 3D Part Discovery in Unseen Categories
TLDR
A learning-based iterative grouping framework which learns a grouping policy to progressively merge small part proposals into bigger ones in a bottom-up fashion, which guarantees the generalizability to novel categories.
StructEdit: Learning Structural Shape Variations
TLDR
This work demonstrates that a separate encoding of shape deltas or differences provides a principled way to deal with inhomogeneities in the shape space due to different combinatorial part structures, while also allowing for compactness in the representation, as well as edit abstraction and transfer.
Learning 3D Part Assembly from a Single Image
TLDR
A novel problem, single-image-guided 3D part assembly, along with a learningbased solution, and proposes a two-module pipeline that leverages strong 2D-3D correspondences and assembly-oriented graph message-passing to infer part relationships.
DSM-Net: Disentangled Structured Mesh Net for Controllable Generation of Fine Geometry
TLDR
DSM-Net is introduced, a deep neural network that learns a disentangled structured mesh representation for 3D shapes, where two key aspects of shapes, geometry and structure, are encoded in a synergistic manner to ensure plausibility of the generated shapes, while also beingdisentangled as much as possible.
...
...