Search Results for author: Jan Eric Lenssen

Found 17 papers, 9 papers with code

latentSplat: Autoencoding Variational Gaussians for Fast Generalizable 3D Reconstruction

no code implementations24 Mar 2024 Christopher Wewer, Kevin Raj, Eddy Ilg, Bernt Schiele, Jan Eric Lenssen

We present latentSplat, a method to predict semantic Gaussians in a 3D latent space that can be splatted and decoded by a light-weight generative 2D architecture.

3D Reconstruction

Recent Trends in 3D Reconstruction of General Non-Rigid Scenes

no code implementations22 Mar 2024 Raza Yunus, Jan Eric Lenssen, Michael Niemeyer, Yiyi Liao, Christian Rupprecht, Christian Theobalt, Gerard Pons-Moll, Jia-Bin Huang, Vladislav Golyanik, Eddy Ilg

Reconstructing models of the real world, including 3D geometry, appearance, and motion of real scenes, is essential for computer graphics and computer vision.

3D Reconstruction Navigate

NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

no code implementations5 Mar 2024 Yannan He, Garvita Tiwari, Tolga Birdal, Jan Eric Lenssen, Gerard Pons-Moll

Faithfully modeling the space of articulations is a crucial task that allows recovery and generation of realistic poses, and remains a notorious challenge.

Pose Estimation

Neural Point Cloud Diffusion for Disentangled 3D Shape and Appearance Generation

1 code implementation21 Dec 2023 Philipp Schröppel, Christopher Wewer, Jan Eric Lenssen, Eddy Ilg, Thomas Brox

However, none of the existing models enable disentangled generation to control the shape and appearance separately.

Disentanglement

Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation

no code implementations12 Dec 2023 Xianghui Xie, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll

We generate 1M+ human-object interaction pairs in 3D and leverage this large-scale data to train our HDM (Hierarchical Diffusion Model), a novel method to reconstruct interacting human and unseen objects, without any templates.

Human-Object Interaction Detection Object

Relational Deep Learning: Graph Representation Learning on Relational Databases

no code implementations7 Dec 2023 Matthias Fey, Weihua Hu, Kexin Huang, Jan Eric Lenssen, Rishabh Ranjan, Joshua Robinson, Rex Ying, Jiaxuan You, Jure Leskovec

The core idea is to view relational databases as a temporal, heterogeneous graph, with a node for each row in each table, and edges specified by primary-foreign key links.

Feature Engineering Graph Representation Learning

Neural Parametric Gaussians for Monocular Non-Rigid Object Reconstruction

no code implementations2 Dec 2023 Devikalyan Das, Christopher Wewer, Raza Yunus, Eddy Ilg, Jan Eric Lenssen

In this work, we introduce Neural Parametric Gaussians (NPGs) to take on this challenge by imposing a two-stage approach: first, we fit a low-rank neural deformation model, which then is used as regularization for non-rigid reconstruction in the second stage.

Object Object Reconstruction

SimNP: Learning Self-Similarity Priors Between Neural Points

no code implementations ICCV 2023 Christopher Wewer, Eddy Ilg, Bernt Schiele, Jan Eric Lenssen

(1) We design the first neural point representation on a category level by utilizing the concept of coherent point clouds.

3D Object Reconstruction Object

Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields

1 code implementation27 Jul 2022 Garvita Tiwari, Dimitrije Antic, Jan Eric Lenssen, Nikolaos Sarafianos, Tony Tung, Gerard Pons-Moll

The resulting high-dimensional implicit function can be differentiated with respect to the input poses and thus can be used to project arbitrary poses onto the manifold by using gradient descent on the set of 3-dimensional hyperspheres.

Denoising

TOCH: Spatio-Temporal Object-to-Hand Correspondence for Motion Refinement

no code implementations16 May 2022 Keyang Zhou, Bharat Lal Bhatnagar, Jan Eric Lenssen, Gerard Pons-Moll

The core of our method are TOCH fields, a novel spatio-temporal representation for modeling correspondences between hands and objects during interaction.

Denoising Object +1

Quaternion Equivariant Capsule Networks for 3D Point Clouds

2 code implementations ECCV 2020 Yongheng Zhao, Tolga Birdal, Jan Eric Lenssen, Emanuele Menegatti, Leonidas Guibas, Federico Tombari

We present a 3D capsule module for processing point clouds that is equivariant to 3D rotations and translations, as well as invariant to permutations of the input points.

Pose Estimation

Deep Iterative Surface Normal Estimation

2 code implementations CVPR 2020 Jan Eric Lenssen, Christian Osendorfer, Jonathan Masci

This results in a state-of-the-art surface normal estimator that is robust to noise, outliers and point density variation, preserves sharp features through anisotropic kernels and equivariance through a local quaternion-based spatial transformer.

Surface Normal Estimation Surface Normals Estimation

Fast Graph Representation Learning with PyTorch Geometric

4 code implementations6 Mar 2019 Matthias Fey, Jan Eric Lenssen

We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch.

Graph Classification Graph Representation Learning +2

Group Equivariant Capsule Networks

1 code implementation NeurIPS 2018 Jan Eric Lenssen, Matthias Fey, Pascal Libuschewski

We present group equivariant capsule networks, a framework to introduce guaranteed equivariance and invariance properties to the capsule network idea.

SplineCNN: Fast Geometric Deep Learning with Continuous B-Spline Kernels

5 code implementations CVPR 2018 Matthias Fey, Jan Eric Lenssen, Frank Weichert, Heinrich Müller

We present Spline-based Convolutional Neural Networks (SplineCNNs), a variant of deep neural networks for irregular structured and geometric input, e. g., graphs or meshes.

General Classification Graph Classification +2

Cannot find the paper you are looking for? You can Submit a new open access paper.