K
Kostas Daniilidis
Researcher at University of Pennsylvania
Publications - 316
Citations - 19601
Kostas Daniilidis is an academic researcher from University of Pennsylvania. The author has contributed to research in topics: Pose & Optical flow. The author has an hindex of 64, co-authored 316 publications receiving 14950 citations. Previous affiliations of Kostas Daniilidis include University of Kiel & Karlsruhe Institute of Technology.
Papers
More filters
Journal ArticleDOI
Model-based object tracking in monocular image sequences of road traffic scenes
TL;DR: An elaborate combination of various techniques has enabled us to track vehicles under complex illumination conditions and over long monocular image sequences, and open problems as well as future work are outlined.
Proceedings ArticleDOI
Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop
TL;DR: SPIN as discussed by the authors uses a deep network to initialize an iterative optimization routine that fits the body model to 2D joints within the training loop, and the fitted estimate is subsequently used to supervise the network.
Journal ArticleDOI
Event-based Vision: A Survey
Guillermo Gallego,Tobi Delbruck,Garrick Orchard,Chiara Bartolozzi,Brian Taba,Andrea Censi,Stefan Leutenegger,Andrew J. Davison,Jörg Conradt,Kostas Daniilidis,Davide Scaramuzza +10 more
TL;DR: This paper provides a comprehensive overview of the emerging field of event-based vision, with a focus on the applications and the algorithms developed to unlock the outstanding properties of event cameras.
Proceedings ArticleDOI
Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose
TL;DR: In this paper, a fine discretization of the 3D space around the subject and train a ConvNet to predict per voxel likelihoods for each joint is proposed.
Proceedings ArticleDOI
Learning to Estimate 3D Human Pose and Shape from a Single Color Image
TL;DR: This work addresses the problem of estimating the full body 3D human pose and shape from a single color image and proposes an efficient and effective direct prediction method based on ConvNets, incorporating a parametric statistical body shape model (SMPL) within an end-to-end framework.