Data-driven suggestions for creativity support in 3D modeling

By Siddhartha Chaudhuri, Vladlen Koltun. 2010

188 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Control and Systems Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Graphics and Computer-Aided Design

In Control and Systems Engineering

Citations in the corpus

Volumetric and Multi-view CNNs for Object Classification on 3D Data (2016, methodology): “Alternatives include models based on distances, angles, triangle areas, or tetrahedra volumes [23], local shape diameters measured at densely-sampled surface points [3], Heat kernel signatures [1, 17], or extensions of SIFT and SURF feature descriptors to 3D voxel grids [16].”
Multi-view Convolutional Neural Networks for 3D Shape Recognition (2015, background): “For example, shapes can be represented with histograms or bag-of-features models constructed out of surface normals and curvatures [15], distances, angles, triangle areas or tetrahedra volumes gathered at sampled surface points [25], properties of spherical functions defined in volumetric grids [16]”
SCORES (2018, background): “Publication date: November 2018. model 3D shapes with detailed geometry and complex structure, and facilitates design space exploration [Chaudhuri and Koltun 2010; Cohen-Or and Zhang 2016; Ritchie et al. 2018; Xu et al. 2012].”
A probabilistic model for component-based shape synthesis (2012, methodology): “Chaudhuri and Koltun [2010] describe an approach to retrieving compatible components for incomplete shapes during assembly-based modeling. Xu et al. [2011] describe a system that fits components from a retrieved database shape to the silhouette of an object extracted from a photograph.”
MVTN: Multi-View Transformation Network for 3D Shape Recognition (2020, background): “distances, angles, areas, or volumes) to measure the similarity between shapes [1, 9, 7].”
Mapping the Landscape of Creativity Support Tools in HCI (2019, unknown): “2018 [29, 30, 62, 73, 90, 111, 126, 162, 165, 171, 175, 184] 2017 [3, 7, 36, 43, 64, 82, 94, 98, 102, 118, 130, 134, 150, 158, 176, 183, 192] 2016 [9, 25, 35, 39, 57, 63, 66, 79, 81, 87, 101, 114, 117, 127, 129, 159, 167, 187] 2015 [38, 54, 89, 100, 123, 137, 160, 166, 168, 186] 2014 [14, 37, 55, 71”
GVCNN: Group-View Convolutional Neural Networks for 3D Shape Recognition (2018, methodology): “The shape-based descriptor was designed based on the native 3D representations of objects, such as voxel grid [26], polygon mesh [2, 10], local shape diameters measured at densely sampled surface points [3], or extensions of the SIFT and SURF descriptors to 3D voxel grids [13].”
Probabilistic reasoning for assembly-based 3D modeling (2011, methodology): “This is less appropriate for open-ended 3D modeling, when the composition of the model is not specified in advance and the user can benefit from a variety of suggestions [Chaudhuri and Koltun 2010].”