Daniel Cremers

Daniel Cremers

Auto-generated profile, based on publicly available information

Daniel Cremers

Technical University of Munich

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 December 2020 in International Journal of Computer Vision
Verified
Journal Article
Open access
PDF file
PDPatrick Dendorfer
Patrick Dendorfer
AOAljos̆a Os̆eP
Aljos̆a Os̆eP
AMAnton Milan
Anton Milan
KSKonrad Schindler
Konrad Schindler
DCDaniel Cremers
Daniel Cremers
LLLaura Leal-Taixé
Laura Leal-Taixé
Standardized benchmarks have been crucial in pushing the performance of computer vision algorithms, especially since the advent of deep learning. Although leaderboards should not be over-claimed, they often provide the most objective measure of performance and are therefore important guides for research. We presentMOTChallenge, a benchmark for single-camera Multiple Object Tracking (MOT) launched in late 2014, to collect existing and new data and create a framework for the standardized evaluation of multiple object tracking methods. The benchmark is focused on multiple people tracking, since pedestrians are by far the most studied object in the tracking community, with applications ranging from robot navigation to self-driving cars. This paper collects the first three releases of the benchmark: (i)MOT15, along with numerous state-of-the-art results that were submitted in the last years, (ii)MOT16, which contains new challenging videos, and (iii)MOT17, that extendsMOT16sequences with more precise labels and evaluates tracking performance on three different object detectors. The second and third release not only offers a significant increase in the number of labeled boxes, but also provide labels for multiple object classes beside pedestrians, as well as the level of visibility for every single object of interest. We finally provide a categorization of state-of-the-art trackers and a broad error analysis. This will help newcomers understand the related work and research trends in the MOT community, and hopefully shed some light into potential future research directions.

23 May 2018 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
KMK.-K. Maninis
K.-K. Maninis
SCS. Caelles
S. Caelles
YCY. Chen
Y. Chen
JPJ. Pont-Tuset
J. Pont-Tuset
LLL. Leal-Taixe
L. Leal-Taixe
LGL. Van Gool
L. Van Gool
Video Object Segmentation, and video processing in general, has been historically dominated by methods that rely on the temporal consistency and redundancy in consecutive video frames. When the temporal smoothness is suddenly broken, such as when an object is occluded, or some frames are missing in a sequence, the result of these methods can deteriorate significantly. This paper explores the orthogonal approach of processing each frame independently, i.e., disregarding the temporal information. In particular, it tackles the task of semi-supervised video object segmentation: the separation of an object from the background in a video, given its mask in the first frame. We present Semantic One-Shot Video Object Segmentation (OSVOSS), based on a fully-convolutional neural network architecture that is able to successively transfer generic semantic information, learned on ImageNet, to the task of foreground segmentation, and finally to learning the appearance of a single annotated object of the test sequence (hence one shot). We show that instance-level semantic information, when combined effectively, can dramatically improve the results of our previous method, OSVOS. We perform experiments on two recent single-object video segmentation databases, which show that OSVOSS is both the fastest and most accurate method in the state of the art. Experiments on multi-object video segmentation show that OSVOSS obtains competitive results.

3 February 2016 in Computer Graphics Forum
Verified
Journal Article
Closed access
PDF file
ERE. Rodolà
E. Rodolà
LCLuca Cosmo
Luca Cosmo
MBM. M. Bronstein
M. M. Bronstein
ATAndrea Torsello
Andrea Torsello
DCD. Cremers
D. Cremers

1 November 2014 in Robotics and Autonomous Systems
Verified
Journal Article
Closed access
JEJakob Engel
Jakob Engel
JSJürgen Sturm
Jürgen Sturm
DCDaniel Cremers
Daniel Cremers

6 October 2018
Verified
Book Chapter
Closed access
PDF file
ZLZorah Lähner
Zorah Lähner
DCDaniel Cremers
Daniel Cremers
TTTony Tung
Tony Tung

30 January 2023 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
SKSimon Klenk
Simon Klenk
LKLukas Koestler
Lukas Koestler
DSDavide Scaramuzza
Davide Scaramuzza
DCDaniel Cremers
Daniel Cremers
Estimating neural radiance fields (NeRFs) from “ideal” images has been extensively studied in the computer vision community. Most approaches assume optimal illumination and slow camera motion. These assumptions are often violated in robotic applications, where images may contain motion blur, and the scene may not have suitable illumination. This can cause significant problems for downstream tasks such as navigation, inspection, or visualization of the scene. To alleviate these problems, we present E-NeRF, the first method which estimates a volumetric scene representation in the form of a NeRF from a fast-moving event camera. Our method can recover NeRFs during very fast motion and in high-dynamic-range conditions where frame-based approaches fail. We show that rendering high-quality frames is possible by only providing an event stream as input. Furthermore, by combining events and frames, we can estimate NeRFs of higher quality than state-of-the-art approaches under severe motion blur. We also show that combining events and frames can overcome failure cases of NeRF estimation in scenarios where only a few input views are available without requiring additional regularization.