9 citations · 16 across the 7 of their papers we have counts for
9 papers
LEGO-Net: Learning Regular Rearrangements of Objects in Rooms
Qiuhong Anna Wei, Sijie Ding, Jeong Joon Park +4
Humans universally dislike the task of cleaning up a messy room. If machines were to help us with this task, they must understand human criteria for regular arrangements, such as s…
Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields
Rohith Agaram, Shaurya Dewan, Rahul Sajnani +3
Coordinate-based implicit neural networks, or neural fields, have emerged as useful representations of shape and appearance in 3D computer vision. Despite advances, however, it rem…
Equivalence Between SE(3) Equivariant Networks via Steerable Kernels and Group Convolution
Adrien Poulenard, Maks Ovsjanikov, Leonidas J. Guibas
A wide range of techniques have been proposed in recent years for designing neural networks for 3D data that are equivariant under rotation and translation of the input. Most appro…
Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
Sidhika Balachandar, Adrien Poulenard, Congyue Deng +1
Equivariant networks have been adopted in many 3-D learning areas. Here we identify a fundamental limitation of these networks: their ambiguity to symmetries. Equivariant networks…
ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
Rahul Sajnani, Adrien Poulenard, Jivitesh Jain +3
Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it…
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Congyue Deng, Or Litany, Yueqi Duan +3
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds. Yet most proposed methods either use complex mathema…
Effective Rotation-invariant Point CNN with Spherical Harmonics kernels
Adrien Poulenard, Marie-Julie Rakotosaona, Yann Ponty +1
We present a novel rotation invariant architecture operating directly on point cloud data. We demonstrate how rotation invariance can be injected into a recently proposed point-bas…
Multi-directional Geodesic Neural Networks via Equivariant Convolution
Adrien Poulenard, Maks Ovsjanikov
We propose a novel approach for performing convolution of signals on curved surfaces and show its utility in a variety of geometric deep learning applications. Key to our construct…
Continuous and Orientation-preserving Correspondences via Functional Maps
Jing Ren, Adrien Poulenard, Peter Wonka +1
We propose a method for efficiently computing orientation-preserving and approximately continuous correspondences between non-rigid shapes, using the functional maps framework. We…