1 code implementation • 16 Jun 2022 • Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia, Shubhankar Borse, Fatih Porikli, Amirhossein Habibian, Tijmen Blankevoort
Though the state-of-the architectures for semantic segmentation, such as HRNet, demonstrate impressive accuracy, the complexity arising from their salient design choices hinders a range of model acceleration tools, and further they make use of operations that are inefficient on current hardware.
no code implementations • 13 Feb 2021 • Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta, Lingjie Liu, Hans-Peter Seidel, Gerard Pons-Moll, Mohamed Elgharib, Christian Theobalt
We propose the first approach to automatically and jointly synthesize both the synchronous 3D conversational body and hand gestures, as well as 3D face and head animations, of a virtual character from speech input.
Ranked #5 on
3D Face Animation
on BEAT2
no code implementations • ECCV 2020 • Kripasindhu Sarkar, Dushyant Mehta, Weipeng Xu, Vladislav Golyanik, Christian Theobalt
Human re-rendering from a single image is a starkly under-constrained problem, and state-of-the-art algorithms often exhibit undesired artefacts, such as over-smoothing, unrealistic distortions of the body parts and garments, or implausible changes of the texture.
no code implementations • ICCV 2021 • Bert Moons, Parham Noorzad, Andrii Skliar, Giovanni Mariani, Dushyant Mehta, Chris Lott, Tijmen Blankevoort
Second, a rapid evolutionary search finds a set of pareto-optimal architectures for any scenario using the accuracy predictor and on-device measurements.
4 code implementations • 1 Jul 2019 • Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Mohamed Elgharib, Pascal Fua, Hans-Peter Seidel, Helge Rhodin, Gerard Pons-Moll, Christian Theobalt
The first stage is a convolutional neural network (CNN) that estimates 2D and 3D pose features along with identity assignments for all visible joints of all individuals. We contribute a new architecture for this CNN, called SelecSLS Net, that uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy.
Ranked #7 on
3D Multi-Person Pose Estimation
on MuPoTS-3D
3D Multi-Person Human Pose Estimation
3D Multi-Person Pose Estimation
+1
no code implementations • ICML Workshop Deep_Phenomen 2019 • Dushyant Mehta, Kwang In Kim, Christian Theobalt
We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained using adaptive gradient descent techniques with L2 regularization or weight decay.
no code implementations • 13 May 2019 • Dushyant Mehta, Kwang In Kim, Christian Theobalt
We show implicit filter level sparsity manifests in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay.
no code implementations • CVPR 2019 • Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta, Gerard Pons-Moll, Christian Theobalt
Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations.
no code implementations • CVPR 2019 • Dushyant Mehta, Kwang In Kim, Christian Theobalt
We investigate filter level sparsity that emerges in convolutional neural networks (CNNs) which employ Batch Normalization and ReLU activation, and are trained with adaptive gradient descent techniques and L2 regularization or weight decay.
5 code implementations • 9 Dec 2017 • Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller, Weipeng Xu, Srinath Sridhar, Gerard Pons-Moll, Christian Theobalt
Our approach uses novel occlusion-robust pose-maps (ORPM) which enable full body pose inference even under strong partial occlusions by other people and objects in the scene.
Ranked #3 on
3D Multi-Person Pose Estimation (root-relative)
on MuPoTS-3D
(MPJPE metric)
3D Human Pose Estimation
3D Multi-Person Pose Estimation (absolute)
+2
no code implementations • CVPR 2018 • Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko, Dushyant Mehta, Srinath Sridhar, Dan Casas, Christian Theobalt
We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence.
no code implementations • 7 Aug 2017 • Weipeng Xu, Avishek Chatterjee, Michael Zollhöfer, Helge Rhodin, Dushyant Mehta, Hans-Peter Seidel, Christian Theobalt
Reconstruction from monocular video alone is drastically more challenging, since strong occlusions and the inherent depth ambiguity lead to a highly ill-posed reconstruction problem.
1 code implementation • 3 May 2017 • Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko, Helge Rhodin, Mohammad Shafiei, Hans-Peter Seidel, Weipeng Xu, Dan Casas, Christian Theobalt
A real-time kinematic skeleton fitting method uses the CNN output to yield temporally stable 3D global pose reconstructions on the basis of a coherent kinematic skeleton.
Ranked #16 on
Pose Estimation
on Leeds Sports Poses
no code implementations • ICCV 2017 • Franziska Mueller, Dushyant Mehta, Oleksandr Sotnychenko, Srinath Sridhar, Dan Casas, Christian Theobalt
We present an approach for real-time, robust and accurate hand pose estimation from moving egocentric RGB-D cameras in cluttered real environments.
no code implementations • 29 Nov 2016 • Dushyant Mehta, Helge Rhodin, Dan Casas, Pascal Fua, Oleksandr Sotnychenko, Weipeng Xu, Christian Theobalt
We propose a CNN-based approach for 3D human body pose estimation from single RGB images that addresses the issue of limited generalizability of models trained solely on the starkly limited publicly available 3D pose data.
Ranked #17 on
Pose Estimation
on Leeds Sports Poses
no code implementations • 19 Mar 2016 • Oliver Nalbach, Elena Arabadzhiyska, Dushyant Mehta, Hans-Peter Seidel, Tobias Ritschel
In computer vision, convolutional neural networks (CNNs) have recently achieved new levels of performance for several inverse problems where RGB pixel appearance is mapped to attributes such as positions, normals or reflectance.