Computing Visual Scene Understanding 3D and 4D Reconstruction Multi-modal Reconstruction and Synthesis Free-viewpoint and 3D Video Marker-less Motion and Performance Capture 3D Image Analysis and Synthesis Inverse [...] phase is entered. Postdocs / Group Leaders Current Openings (Neural) Modeling, Capture and Rendering, 3D/4D Reconstruction, Geometric Deep Learning Virtual Human Modeling and Animation General Information The [...] Theobalt via Email. General Openings: PhD (student) positions The Visual Computing and Artificial Intelligence department at MPI is continuously looking for PhD students (wiss. Mitarbeiter) that are fascinated
Articulated People Detection and Pose Estimation Leveraging 3D Body Model for Training Data Generation Multi-view Pictorial Structures for 3D Human Pose Estimation Learning People Detectors for Tracking [...] upper body attributes, as described in the paper, we finetune on the PETA database of pedestrians [3] with five long term attributes: Age1: personalLess30 Age2: personalLess45 Gender: personalMale Short [...] R. Fergus and L. Bourdev, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [3] Pedestrian Attribute Recognition at Far Distance , Y. Deng, P. Luo, C. C. Loy, X. Tang, In Proceedings
game industries. Virtual actors (avatars) are fundamental components of special effects and virtual 3D worlds. With respect to commercially-available motion capture methods, marker- based optical methods [...] reconstruction, can be integrated in the new method. In this way, in addition to the skeletal movement, a 3D surface reconstruction of the person can be captured (so-called performance capture). Here a complex [...] 9325-4004 Email stoll@mpi-inf.mpg.de EpiExplorer and RnBeads: Integrative Analysis of Epigenomic Data RDF-3X – Fast Searches for Semantic Data Markerless Performance Capture
Research Departments Computer Vision and Machine Learning Research 3D Reconstruction and Perception of People Non-rigid Tracking from Depth and Video Non-rigid Tracking from Depth and RGB Video Non-Rigid [...] non-rigid motion from RGB videos alone. We have shown real-time non-rigid tracking of general objects [3], and humans in clothing [4]. References [1] DoubleFusion: Real-time Capture of Human Performances with [...] Pons-Moll, Yebin Liu in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) , 2019. [3] NRST: Non-rigid Surface Tracking from Monocular Video M. Habermann, W. Xu, H. Rohdin, M. Zollhöfer
movements are analyzed and converted into a precise, controllable skeletal representation. Next, a 3D reconstruction is generated that realistically captures both body shape and fine details of clothing [...] the avatars reconstructed from a single-camera feed were systematically compared with high-precision 3D reference models captured by a 120-camera setup. The results demonstrate that EgoAvatar produces more [...] Computer Graphics and Interactive Techniques in Asia (SIGGRAPH ASIA), which took place from December 3 to 6, 2024, in Tokyo, Japan. SIGGRAPH ASIA is one of the world’s leading conferences in computer graphics
(Virtual), 2021. 2019 3 Conference paper D2 V. Lazova, E. Insafutdinov, and G. Pons-Moll “360-Degree Textures of People in Clothing from a Single Image,” in International Conference on 3D Vision, Québec City [...] Research Departments Computer Vision and Machine Learning People Verica Lazova Verica Lazova (PhD Student) MSc Verica Lazova Address Max-Planck-Institut für Informatik Saarland Informatics Campus Campus [...] Interests Human modeling from images Generative models Computer vision Machine learning Education Ph.D. student, Perceiving and modelling people from video and images, Max-Planck-Institute for Informatics
and novel approach to fabricating embedded user interfaces. Digital fabrication techniques, such as 3D printing and laser cutting, are already successful in commercial applications, for they enable the [...] Photography Calibrated Display Management Recognizing Human Activity Correspondences and Symmetry in 3D Scenes Flow Analysis Optimizing User Interfaces for Human Performance
consider streaming approaches that fi t best to modern graphics hardware and human perception. First, 3D information is en- coded on the server side with human perception in mind, e.g., by faithfully encoding [...] Photography Calibrated Display Management Recognizing Human Activity Correspondences and Symmetry in 3D Scenes Flow Analysis Optimizing User Interfaces for Human Performance
Photography Calibrated Display Management Recognizing Human Activity Correspondences and Symmetry in 3D Scenes Flow Analysis Optimizing User Interfaces for Human Performance
handle.net/21.11116/0000-0007-D8BB-3 %R 10.22028/D291-32992 %U nbn:de:bsz:291--ds-329923 %F OTHER: 20.500.11880/30503 %I Universität des Saarlandes %C Saarbrücken %D 2020 %P 224 p. %V phd %9 phd [...] Adaptation for {3D} Human Pose Estimation}, AUTHOR = {Amin, Sikandar and M{\"u}ller, Philipp and Bulling, Andreas and Andriluka, Mykhaylo}, LANGUAGE = {eng}, ISBN = {978-3-319-11751-5; 978-3-319-11752-2} [...] Planck Society %T Test-time Adaptation for 3D Human Pose Estimation : %G eng %U http://hdl.handle.net/11858/00-001M-0000-0024-3736-5 %R 10.1007/978-3-319-11752-2_20 %D 2014 %B 36th German Conference on Pattern
