91 citations · 235 across the 20 of their papers we have counts for
8 papers · 1 filter
Zero-shot CAD Program Re-Parameterization for Interactive Manipulation
Milin Kodnongbua, Benjamin T. Jones, Maaz Bin Safeer Ahmad +2
Parametric CAD models encode entire families of shapes that should, in principle, be easy for designers to explore. However, in practice, parametric CAD models can be difficult to…
Neural Subdivision
Hsueh-Ti Derek Liu, Vladimir G. Kim, Siddhartha Chaudhuri +2
This paper introduces Neural Subdivision, a novel framework for data-driven coarse-to-fine geometry modeling. During inference, our method takes a coarse triangle mesh as input and…
Neural Cages for Detail-Preserving 3D Deformations
Wang Yifan, Noam Aigerman, Vladimir G. Kim +2
We propose a novel learnable representation for detail-preserving shape deformation. The goal of our method is to warp a source shape to match the general structure of a target sha…
Deep Parametric Shape Predictions using Distance Fields
Dmitriy Smirnov, Matthew Fisher, Vladimir G. Kim +2
Many tasks in graphics and vision demand machinery for converting shapes into consistent representations with sparse sets of parameters; these representations facilitate rendering,…
Learning Fuzzy Set Representations of Partial Shapes on Dual Embedding Spaces
Minhyuk Sung, Anastasia Dubrovina, Vladimir G. Kim +1
Modeling relations between components of 3D objects is essential for many geometry editing tasks. Existing techniques commonly rely on labeled components, which requires substantia…
ComplementMe: Weakly-Supervised Component Suggestions for 3D Modeling
Minhyuk Sung, Hao Su, Vladimir G. Kim +2
Assembly-based tools provide a powerful modeling paradigm for non-expert shape designers. However, choosing a component from a large shape repository and aligning it to a partial a…
Learning Hierarchical Shape Segmentation and Labeling from Online Repositories
Li Yi, Leonidas Guibas, Aaron Hertzmann +3
We propose a method for converting geometric shapes into hierarchically segmented parts with part labels. Our key idea is to train category-specific models from the scene graphs an…
Data-Driven Shape Analysis and Processing
Kai Xu, Vladimir G. Kim, Qixing Huang +1
Data-driven methods play an increasingly important role in discovering geometric, structural, and semantic relationships between 3D shapes in collections, and applying this analysi…