
MetaPose: Fast 3D Pose from Multiple Views without 3D Supervision
Recently, huge strides were made in monocular and multiview pose estima...
read it

Deep Medial Fields
Implicit representations of geometry, such as occupancy fields or signed...
read it

Vector Neurons: A General Framework for SO(3)Equivariant Networks
Invariance and equivariance to the rotation group have been widely discu...
read it

COTR: Correspondence Transformer for Matching Across Images
We propose a novel framework for finding correspondences in images based...
read it

Human 3D keypoints via spatial uncertainty modeling
We introduce a technique for 3D human keypoint estimation that directly ...
read it

Canonical Capsules: Unsupervised Capsules in Canonical Pose
We propose an unsupervised capsule architecture for 3D point clouds. We ...
read it

Unsupervised part representation by Flow Capsules
Capsule networks are designed to parse an image into a hierarchy of obje...
read it

DeRF: Decomposed Radiance Fields
With the advent of Neural Radiance Fields (NeRF), neural networks can no...
read it

Voronoi Convolutional Neural Networks
In this technical report, we investigate extending convolutional neural ...
read it

LSMAT Least Squares Medial Axis Transform
The medial axis transform has applications in numerous fields including ...
read it

CoSE: Compositional Stroke Embeddings
We present a generative model for strokebased drawing tasks which is ab...
read it

ShapeFlow: Learnable Deformations Among 3D Shapes
We present ShapeFlow, a flowbased model for learning a deformation spac...
read it

Deep Implicit Volume Compression
We describe a novel approach for compressing truncated signed distance f...
read it

NiLBS: Neural Inverse Linear Blend Skinning
In this technical report, we investigate efficient representations of ar...
read it

VoronoiNet: General Functional Approximators with Local Support
Voronoi diagrams are highly compact representations that are used in var...
read it

NASA: Neural Articulated Shape Approximation
Efficient representation of articulated objects such as human bodies is ...
read it

CvxNets: Learnable Convex Decomposition
Any solid object can be decomposed into a collection of convex polytopes...
read it

CvxNet: Learnable Convex Decomposition
Any solid object can be decomposed into a collection of convex polytopes...
read it

Attentive Context Normalization for Robust PermutationEquivariant Learning
Many problems in computer vision require dealing with sparse, unstructur...
read it

VIPER: Volume Invariant Positionbased Elastic Rods
We extend the formulation of positionbased rods to include elastic volu...
read it

Volumetric Capture of Humans with a Single RGBD Camera via SemiParametric Learning
Volumetric (4D) performance capture is fundamental for AR/VR content gen...
read it

Linearized MultiSampling for Differentiable Image Transformation
We propose a novel image sampling method for differentiable image transf...
read it

MIST: Multiple Instance Spatial Transformer Network
We propose a deep network that can be trained to tackle image reconstruc...
read it

HandSeg: A Dataset for Hand Segmentation from Depth Images
We introduce a largescale RGBD hand segmentation dataset, with detailed...
read it

Espresso: Efficient Forward Propagation for BCNNs
There are many applications scenarios for which the computational perfor...
read it

Skeletal Representations and Applications
When representing a solid object there are alternatives to the use of tr...
read it
Andrea Tagliasacchi
is this you? claim profile