1.2k citations · 1.9k across the 13 of their papers we have counts for
15 papers
Simple and Efficient Architectures for Semantic Segmentation
Dushyant Mehta, Andrii Skliar, Haitam Ben Yahia +4
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…
Learning Speech-driven 3D Conversational Gestures from Video
Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta +5
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 vi…
Neural Re-Rendering of Humans from a Single Image
Kripasindhu Sarkar, Dushyant Mehta, Weipeng Xu +2
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, unrealisti…
Distilling Optimal Neural Networks: Rapid Search in Diverse Spaces
Bert Moons, Parham Noorzad, Andrii Skliar +4
Current state-of-the-art Neural Architecture Search (NAS) methods neither efficiently scale to multiple hardware platforms, nor handle diverse architectural search-spaces. To remed…
XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera
Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller +7
We present a real-time approach for multi-person 3D motion capture at over 30 fps using a single RGB camera. It operates successfully in generic scenes which may contain occlusions…
Implicit Filter Sparsification In Convolutional Neural Networks
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 gradien…
In the Wild Human Pose Estimation Using Explicit 2D Features and Intermediate 3D Representations
Ikhsanul Habibie, Weipeng Xu, Dushyant Mehta +2
Convolutional Neural Network based approaches for monocular 3D human pose estimation usually require a large amount of training images with 3D pose annotations. While it is feasibl…
On Implicit Filter Level Sparsity in Convolutional Neural Networks
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 gradie…
GANerated Hands for Real-time 3D Hand Tracking from Monocular RGB
Franziska Mueller, Florian Bernard, Oleksandr Sotnychenko +4
We address the highly challenging problem of real-time 3D hand tracking based on a monocular RGB-only sequence. Our tracking method combines a convolutional neural network with a k…
Single-Shot Multi-Person 3D Pose Estimation From Monocular RGB
Dushyant Mehta, Oleksandr Sotnychenko, Franziska Mueller +4
We propose a new single-shot method for multi-person 3D pose estimation in general scenes from a monocular RGB camera. Our approach uses novel occlusion-robust pose-maps (ORPM) whi…
MonoPerfCap: Human Performance Capture from Monocular Video
Weipeng Xu, Avishek Chatterjee, Michael Zollhöfer +4
We present the first marker-less approach for temporally coherent 3D performance capture of a human with general clothing from monocular video. Our approach reconstructs articulate…
VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera
Dushyant Mehta, Srinath Sridhar, Oleksandr Sotnychenko +6
We present the first real-time method to capture the full global 3D skeletal pose of a human in a stable, temporally consistent manner using a single RGB camera. Our method combine…
Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor
Franziska Mueller, Dushyant Mehta, Oleksandr Sotnychenko +3
We present an approach for real-time, robust and accurate hand pose estimation from moving egocentric RGB-D cameras in cluttered real environments. Existing methods typically fail…
Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision
Dushyant Mehta, Helge Rhodin, Dan Casas +4
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 starkl…
Deep Shading: Convolutional Neural Networks for Screen-Space Shading
Oliver Nalbach, Elena Arabadzhiyska, Dushyant Mehta +2
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 attri…