17 citations · 34 across the 8 of their papers we have counts for
10 papers
Self-supervised Shape Completion via Involution and Implicit Correspondences
Mengya Liu, Ajad Chhatkuli, Janis Postels +2
3D shape completion is traditionally solved using supervised training or by distribution learning on complete shape examples. Recently self-supervised learning approaches that do n…
3D Compression Using Neural Fields
Janis Postels, Yannick Strümpler, Klara Reichard +2
Neural Fields (NFs) have gained momentum as a tool for compressing various data modalities - e.g. images and videos. This work leverages previous advances and proposes a novel NF-b…
ManiFlow: Implicitly Representing Manifolds with Normalizing Flows
Janis Postels, Martin Danelljan, Luc Van Gool +1
Normalizing Flows (NFs) are flexible explicit generative models that have been shown to accurately model complex real-world data distributions. However, their invertibility constra…
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
Tao Sun, Mattia Segu, Janis Postels +5
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems. Existing image and video driving datasets, howeve…
Implicit Neural Representations for Image Compression
Yannick Strümpler, Janis Postels, Ren Yang +2
Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types. Thus far, prior work mostly focused on optimizing t…
On the Practicality of Deterministic Epistemic Uncertainty
Janis Postels, Mattia Segu, Tao Sun +4
A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Net…
Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction
Janis Postels, Mengya Liu, Riccardo Spezialetti +2
Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time. How…
Variational Transformer Networks for Layout Generation
Diego Martin Arroyo, Janis Postels, Federico Tombari
Generative models able to synthesize layouts of different kinds (e.g. documents, user interfaces or furniture arrangements) are a useful tool to aid design processes and as a first…
The Hidden Uncertainty in a Neural Networks Activations
Janis Postels, Hermann Blum, Yannick Strümpler +4
The distribution of a neural network's latent representations has been successfully used to detect out-of-distribution (OOD) data. This work investigates whether this distribution…
Sampling-free Epistemic Uncertainty Estimation Using Approximated Variance Propagation
Janis Postels, Francesco Ferroni, Huseyin Coskun +2
We present a sampling-free approach for computing the epistemic uncertainty of a neural network. Epistemic uncertainty is an important quantity for the deployment of deep neural ne…