910 citations · 1.4k across the 13 of their papers we have counts for
14 papers
NOVIS: A Case for End-to-End Near-Online Video Instance Segmentation
Tim Meinhardt, Matt Feiszli, Yuchen Fan +2
Until recently, the Video Instance Segmentation (VIS) community operated under the common belief that offline methods are generally superior to a frame by frame online processing.…
Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis
Maxim Maximov, Tim Meinhardt, Ismail Elezi +4
The advent of data-driven technology solutions is accompanied by an increasing concern with data privacy. This is of particular importance for human-centered image recognition task…
HOLISMOKES -- XI. Evaluation of supervised neural networks for strong-lens searches in ground-based imaging surveys
R. Canameras, S. Schuldt, Y. Shu +10
While supervised neural networks have become state of the art for identifying the rare strong gravitational lenses from large imaging data sets, their selection remains significant…
DeVIS: Making Deformable Transformers Work for Video Instance Segmentation
Adrià Caelles, Tim Meinhardt, Guillem Brasó +1
Video Instance Segmentation (VIS) jointly tackles multi-object detection, tracking, and segmentation in video sequences. In the past, VIS methods mirrored the fragmentation of thes…
HOLISMOKES -- IX. Neural network inference of strong-lens parameters and uncertainties from ground-based images
S. Schuldt, R. Cañameras, Y. Shu +4
Modeling of strong gravitational lenses is a necessity for further applications in astrophysics and cosmology. Especially with the large number of detections in current and upcomin…
HOLISMOKES. VI. New galaxy-scale strong lens candidates from the HSC-SSP imaging survey
R. Canameras, S. Schuldt, Y. Shu +8
We have carried out a systematic search for galaxy-scale strong lenses in multiband imaging from the Hyper Suprime-Cam (HSC) survey. Our automated pipeline, based on realistic stro…
TrackFormer: Multi-Object Tracking with Transformers
Tim Meinhardt, Alexander Kirillov, Laura Leal-Taixe +1
The challenging task of multi-object tracking (MOT) requires simultaneous reasoning about track initialization, identity, and spatio-temporal trajectories. We formulate this task a…
Make One-Shot Video Object Segmentation Efficient Again
Tim Meinhardt, Laura Leal-Taixe
Video object segmentation (VOS) describes the task of segmenting a set of objects in each frame of a video. In the semi-supervised setting, the first mask of each object is provide…
Photometric Redshift Estimation with a Convolutional Neural Network: NetZ
S. Schuldt, S. H. Suyu, R. Cañameras +4
The redshifts of galaxies are a key attribute that is needed for nearly all extragalactic studies. Since spectroscopic redshifts require additional telescope and human resources, m…
HOLISMOKES -- IV. Efficient mass modeling of strong lenses through deep learning
S. Schuldt, S. H. Suyu, T. Meinhardt +4
Modelling the mass distributions of strong gravitational lenses is often necessary to use them as astrophysical and cosmological probes. With the high number of lens systems ($>10^…
HOLISMOKES -- II. Identifying galaxy-scale strong gravitational lenses in Pan-STARRS using convolutional neural networks
R. Canameras, S. Schuldt, S. H. Suyu +6
We present a systematic search for wide-separation (Einstein radius >1.5"), galaxy-scale strong lenses in the 30 000 sq.deg of the Pan-STARRS 3pi survey on the Northern sky. With l…
Tracking without bells and whistles
Philipp Bergmann, Tim Meinhardt, Laura Leal-Taixe
The problem of tracking multiple objects in a video sequence poses several challenging tasks. For tracking-by-detection, these include object re-identification, motion prediction a…
Lifting Layers: Analysis and Applications
Peter Ochs, Tim Meinhardt, Laura Leal-Taixe +1
The great advances of learning-based approaches in image processing and computer vision are largely based on deeply nested networks that compose linear transfer functions with suit…
Learning Proximal Operators: Using Denoising Networks for Regularizing Inverse Imaging Problems
Tim Meinhardt, Michael Moeller, Caner Hazirbas +1
While variational methods have been among the most powerful tools for solving linear inverse problems in imaging, deep (convolutional) neural networks have recently taken the lead…