activity
20152022
most citedFlowNet: Learning Optical Flow with Convolutional Networks

604 citations · 1k across the 30 of their papers we have counts for

collaborators
Showing cs.CVShow all

43 papers · 1 filter

cs.CV20221 cited

SF2SE3: Clustering Scene Flow into SE(3)-Motions via Proposal and Selection

Leonhard Sommer, Philipp Schröppel, Thomas Brox

We propose SF2SE3, a novel approach to estimate scene dynamics in form of a segmentation into independently moving rigid objects and their SE(3)-motions. SF2SE3 operates on two con…

cs.CV20221 cited

A Benchmark and a Baseline for Robust Multi-view Depth Estimation

Philipp Schröppel, Jan Bechtold, Artemij Amiranashvili +1

Recent deep learning approaches for multi-view depth estimation are employed either in a depth-from-video or a multi-view stereo setting. Despite different settings, these approach…

cs.CV20222 cited

Neural Architecture Search for Dense Prediction Tasks in Computer Vision

Thomas Elsken, Arber Zela, Jan Hendrik Metzen +4

The success of deep learning in recent years has lead to a rising demand for neural network architecture engineering. As a consequence, neural architecture search (NAS), which aims…

cs.CV20223 cited

Ranking Info Noise Contrastive Estimation: Boosting Contrastive Learning via Ranked Positives

David T. Hoffmann, Nadine Behrmann, Juergen Gall +2

This paper introduces Ranking Info Noise Contrastive Estimation (RINCE), a new member in the family of InfoNCE losses that preserves a ranked ordering of positive samples. In contr…

cs.CV2021

CrossCLR: Cross-modal Contrastive Learning For Multi-modal Video Representations

Mohammadreza Zolfaghari, Yi Zhu, Peter Gehler +1

Contrastive learning allows us to flexibly define powerful losses by contrasting positive pairs from sets of negative samples. Recently, the principle has also been used to learn c…

cs.CV2021

Contrastive Representation Learning for Hand Shape Estimation

Christian Zimmermann, Max Argus, Thomas Brox

This work presents improvements in monocular hand shape estimation by building on top of recent advances in unsupervised learning. We extend momentum contrastive learning and contr…