Výsledky vyhledávání - "Kiran Varanasi"

Face It!: A Pipeline for Real-Time Performance-Driven Facial Animation

Autor: Jilliam Maria Diaz Barros, Kiran Varanasi, Vladislav Golyanik, Didier Stricker

Publikováno v: ICIP

This paper presents a new lightweight approach for real-time performance-driven facial animation from monocular videos. We transfer facial expressions from 2D images to a 3D virtual character, by estimating the rigid head pose and non-rigid face defo

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::5a64da109a421f738e64a0546dfa08f6
https://doi.org/10.1109/icip.2019.8803330

Zobrazit plný text záznamu

Real-Time Head Pose Estimation by Tracking and Detection of Keypoints and Facial Landmarks

Autor: Frederic Garcia, Bruno Mirbach, Didier Stricker, Jilliam Maria Diaz Barros, Kiran Varanasi

Publikováno v: Communications in Computer and Information Science ISBN: 9783030267551
VISIGRAPP (Revised Selected Papers)

We introduce a novel fusion framework for real-time head pose estimation using a tailored Kalman Filter. This approach estimates the pose from intensity images in monocular video data. The method is robust to extreme head rotations and varying illumi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::cff53022527f1d089d2fa6888f675654
https://doi.org/10.1007/978-3-030-26756-8_16

Zobrazit plný text záznamu

Reconstruction of Personalized 3D Face Rigs from Monocular Video

Autor: Michael Zollhöfer, Christian Theobalt, Pablo Garrido, Levi Valgaerts, Dan Casas, Patrick Pérez, Kiran Varanasi

Publikováno v: ACM Transactions on Graphics. 35:1-15

We present a novel approach for the automatic creation of a personalized high-quality 3D face rig of an actor from just monocular video data (e.g., vintage movies). Our rig is based on three distinct layers that allow us to model the actor’s facial

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::c83558aab80fcfb727a9c5340cbd6ca0
https://doi.org/10.1145/2890493

Zobrazit plný text záznamu

DeepHPS: End-to-end Estimation of 3D Hand Pose and Shape by Learning from Synthetic Depth

Autor: Ahmed Elhayek, Jameel Malik, Kiran Varanasi, Alexis Heloir, Fabrizio Nunnari, Kiarash Tamaddon, Didier Stricker

Publikováno v: 2018 International Conference on 3D Vision (3DV)
2018 International Conference on 3D Vision (3DV), Sep 2018, Verona, Italy. pp.110-119, ⟨10.1109/3DV.2018.00023⟩
3DV

Articulated hand pose and shape estimation is an important problem for vision-based applications such as augmented reality and animation. In contrast to the existing methods which optimize only for joint positions, we propose a fully supervised deep

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8c7d64d0b4a52291aa786241a1ad982c
https://hal-uphf.archives-ouvertes.fr/hal-03383020

Zobrazit plný text záznamu

Structured Low-Rank Matrix Factorization for Point-Cloud Denoising

Autor: Florian Bernard, Christian Theobalt, Kripasindhu Sarkar, Kiran Varanasi, Didier Stricker

Publikováno v: 3DV

In this work we address the problem of point-cloud denoising where we assume that a given point-cloud comprises (noisy) points that were sampled from an underlying surface that is to be denoised. We phrase the point-cloud denoising problem in terms o

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::d3ede5c4948d70d170c95d2eb802ee15
https://doi.org/10.1109/3dv.2018.00058

Zobrazit plný text záznamu

3D Shape Processing by Convolutional Denoising Autoencoders on Local Patches

Autor: Didier Stricker, Kripasindhu Sarkar, Kiran Varanasi

Publikováno v: WACV

We propose a system for surface completion and inpainting of 3D shapes using denoising autoencoders with convolutional layers, learnt on local patches. Our method uses height map based local patches parameterized using 3D mesh quadrangulation of the

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::0873eb66c5df92d74bc2df3dd749b796
https://doi.org/10.1109/wacv.2018.00213

Zobrazit plný text záznamu

Fusion of Keypoint Tracking and Facial Landmark Detection for Real-Time Head Pose Estimation

Autor: Jilliam Maria Diaz Barros, Frederic Garcia, Bruno Mirbach, Didier Stricker, Kiran Varanasi

Publikováno v: WACV

In this paper, we address the problem of extreme head pose estimation from intensity images, in a monocular setup. We introduce a novel fusion pipeline to integrate into a dedicated Kalman Filter the pose estimated from a tracking scheme in the predi

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e7f8f898092b4863ddbd1476c1b68e4f
https://doi.org/10.1109/wacv.2018.00224

Zobrazit plný text záznamu

Human Shape Capture and Tracking at Home

Autor: Saurabh Saini, P. J. Narayanan, Kiran Varanasi, Gaurav Mishra

Publikováno v: WACV

Human body tracking typically requires specialized capture set-ups. Although pose tracking is available in consumer devices like Microsoft Kinect, it is restricted to stick figures visualizing body part detection. In this paper, we propose a method f

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::f662137b444aeaa28669e5e8bc818667
https://doi.org/10.1109/wacv.2018.00049

Zobrazit plný text záznamu

HDM-Net: Monocular Non-rigid 3D Reconstruction with Learned Deformation Model

Autor: Didier Stricker, Kiran Varanasi, Vladislav Golyanik, Soshi Shimada

Publikováno v: Virtual Reality and Augmented Reality ISBN: 9783030017897
EuroVR

Monocular dense 3D reconstruction of deformable objects is a hard ill-posed problem in computer vision. Current techniques either require dense correspondences and rely on motion and deformation cues, or assume a highly accurate reconstruction (refer

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::e25499df85252ec88fb4e2c6dd40f989
https://doi.org/10.1007/978-3-030-01790-3_4

Zobrazit plný text záznamu

Vyhledávací nástroje:

Upřesnit hledání