Search Results for author:
Found 9 papers, 4 papers with code
LEGO-Net: Learning Regular Rearrangements of Objects in Rooms
Humans universally dislike the task of cleaning up a messy room.
Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields
We present Canonical Field Network (CaFi-Net), a self-supervised method to canonicalize the 3D pose of instances from an object category represented as neural fields, specifically neural radiance fields (NeRFs).
Equivalence Between SE(3) Equivariant Networks via Steerable Kernels and Group Convolution
Most approaches for equivariance under the Euclidean group $\mathrm{SE}(3)$ of rotations and translations fall within one of the two major categories.
Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
We present OAVNN: Orientation Aware Vector Neuron Network, an extension of the Vector Neuron Network.
ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
ConDor is a self-supervised method that learns to Canonicalize the 3D orientation and position for full and partial 3D point clouds.
A Functional Approach to Rotation Equivariant Non-Linearities for Tensor Field Networks.
A fundamental problem in equivariant deep learning is to design activation functions which are both informative and preserve equivariance.
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds.
Effective Rotation-invariant Point CNN with Spherical Harmonics kernels
We present a novel rotation invariant architecture operating directly on point cloud data.
Multi-directional Geodesic Neural Networks via Equivariant Convolution
Our construction, which we call multi-directional geodesic convolution, or directional convolution for short, allows, in particular, to propagate and relate directional information across layers and thus different regions on the shape.
