Learning Semantic Deformation Flows with 3D Convolutional Networks

By Mehmet Ersin Yümer, Niloy J. Mitra. 2016

69 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

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 Computer Vision and Pattern Recognition

Citations in the corpus

Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputs (2017, methodology): “Applications include single- and multi-view 3D object reconstruction trained in supervised [14, 5, 7, 17] and unsupervised [37, 12, 19] ways, probabilistic generative modeling of 3D shapes [36, 35, 29], semantic segmentation [2, 4] and shape deformation [39].”
Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision (2016, background): “Learning from transformed sensory data has gained attention [12, 5, 15, 13, 23, 6, 24] in recent years.”
VConv-DAE: Deep Volumetric Shape Learning Without Object Labels (2016, methodology): “[25] uses a similar architecture for predicting deformed version of the input shape.”
Learning Efficient Point Cloud Generation for Dense 3D Object Reconstruction (2017, background): “Similar applications include the use of an additional encoded pose embedding to learn shape deformations (Yumer and Mitra 2016) and using adversarial training to learn more realistic shape generation (Wu et al.”
Deformation-driven shape correspondence via shape recognition (2017, background): “Developing neural nets for structured shape representations requires a significant departure from existing works on convolutional neural networks (CNNs) for volumetric [Wu et al. 2015; Girdhar et al. 2016; Yumer and Mitra 2016; Wu et al. 2016] or view-based [Su et al.”
Interactive 3D Modeling with a Generative Adversarial Network (2017, methodology): “…Wu et al. 2016], shape completion [Wu et al. 2015], shape interpolation [Brock et al. 2016; Girdhar et al. 2016; Wu et al. 2016], classification [Brock et al. 2016; Wu et al. 2016], 2D-to-3D mapping [Girdhar et al. 2016; Rezende et al. 2016; Wu et al. 2016], and deformations [Yumer and Mitra 2016].”
Transformation-Grounded Image Generation Network for Novel 3D View Synthesis (2017, unknown): “In the 3D case, flow fields are learned to transform input 3D mesh to the target shape [50] or input view to the desired output view [51].”
Deep Shape from a Low Number of Silhouettes (2016, background): “…network (3D-R2N2) is built to unify both single and multi-view 3D object reconstruction [22], Semantic deformation ﬂows are learned with 3D convolution networks for improving 3D reconstruction [23], 3D volumetric reconstruction is learned from single-view with projective transformations [24].”
Image2Mesh: A Learning Framework for Single Image 3D Reconstruction (2017, methodology): “A 3D shape editing tool has been presented in [43] and it uses a volumetric network to infer per-voxel deformation flows using Ffd.”
Shape Prior Deformation for Categorical 6D Object Pose and Size Estimation (2020, methodology): “[13,20,41] use free-form deformation in conjunction with voxel, mesh and point cloud representations, respectively.”
Text2Mesh: Text-Driven Neural Stylization for Meshes (2021, methodology): “Prior to CLIP, text-driven control for deforming 3D shapes was explored [67, 68] using specialized 3D datasets.”
Self-supervised Learning of 3D Objects from Natural Images (2019, methodology): “Instead of predicting a mesh directly, we predict shape deformations using free-form deformation [33] similar to several other object reconstruction works [21, 47].”