31 citations · 89 across the 15 of their papers we have counts for
17 papers
Reliable Student: Addressing Noise in Semi-Supervised 3D Object Detection
Farzad Nozarian, Shashank Agarwal, Farzaneh Rezaeianaran +4
Semi-supervised 3D object detection can benefit from the promising pseudo-labeling technique when labeled data is limited. However, recent approaches have overlooked the impact of…
Expanding Synthetic Real-World Degradations for Blind Video Super Resolution
Mehran Jeelani, Sadbhawna, Noshaba Cheema +3
Video super-resolution (VSR) techniques, especially deep-learning-based algorithms, have drastically improved over the last few years and shown impressive performance on synthetic…
Edge-aware Consistent Stereo Video Depth Estimation
Elena Kosheleva, Sunil Jaiswal, Faranak Shamsafar +3
Video depth estimation is crucial in various applications, such as scene reconstruction and augmented reality. In contrast to the naive method of estimating depths from images, a m…
High-Resolution Synthetic RGB-D Datasets for Monocular Depth Estimation
Aakash Rajpal, Noshaba Cheema, Klaus Illgner-Fehns +2
Accurate depth maps are essential in various applications, such as autonomous driving, scene reconstruction, point-cloud creation, etc. However, monocular-depth estimation (MDE) al…
XEngine: Optimal Tensor Rematerialization for Neural Networks in Heterogeneous Environments
Manuela Schuler, Richard Membarth, Philipp Slusallek
Memory efficiency is crucial in training deep learning networks on resource-restricted devices. During backpropagation, forward tensors are used to calculate gradients. Despite the…
IMos: Intent-Driven Full-Body Motion Synthesis for Human-Object Interactions
Anindita Ghosh, Rishabh Dabral, Vladislav Golyanik +2
Can we make virtual characters in a scene interact with their surrounding objects through simple instructions? Is it possible to synthesize such motion plausibly with a diverse set…
FLOWER: A comprehensive dataflow compiler for high-level synthesis
Puya Amiri, Arsène Pérard-Gayot, Richard Membarth +3
FPGAs have found their way into data centers as accelerator cards, making reconfigurable computing more accessible for high-performance applications. At the same time, new high-lev…
Synthesis of Compositional Animations from Textual Descriptions
Anindita Ghosh, Noshaba Cheema, Cennet Oguz +2
"How can we animate 3D-characters from a movie script or move robots by simply telling them what we would like them to do?" "How unstructured and complex can we make a sentence and…
Parallel Multi-Hypothesis Algorithm for Criticality Estimation in Traffic and Collision Avoidance
Eduardo Sánchez Morales, Richard Membarth, Andreas Gaull +5
Due to the current developments towards autonomous driving and vehicle active safety, there is an increasing necessity for algorithms that are able to perform complex criticality p…
AnyHLS: High-Level Synthesis with Partial Evaluation
M. Akif Özkan, Arsène Pérard-Gayot, Richard Membarth +5
FPGAs excel in low power and high throughput computations, but they are challenging to program. Traditionally, developers rely on hardware description languages like Verilog or VHD…
Fine-Grained Semantic Segmentation of Motion Capture Data using Dilated Temporal Fully-Convolutional Networks
Noshaba Cheema, Somayeh Hosseini, Janis Sprenger +4
Human motion capture data has been widely used in data-driven character animation. In order to generate realistic, natural-looking motions, most data-driven approaches require cons…
Dilated Temporal Fully-Convolutional Network for Semantic Segmentation of Motion Capture Data
Noshaba Cheema, Somayeh Hosseini, Janis Sprenger +4
Semantic segmentation of motion capture sequences plays a key part in many data-driven motion synthesis frameworks. It is a preprocessing step in which long recordings of motion ca…
How should a fixed budget of dwell time be spent in scanning electron microscopy to optimize image quality?
Patrick Trampert, Faysal Bourghorbel, Pavel Potocek +4
In scanning electron microscopy, the achievable image quality is often limited by a maximum feasible acquisition time per dataset. Particularly with regard to three-dimensional or…
Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting
Tim Dahmen, Patrick Trampert, Pascal Peter +3
Exemplar-based inpainting is the process of reconstructing missing parts of an image by searching the remaining data for patches that fit seamlessly. The image is completed to a pl…
ManyDSL: A Host for Many Languages
Piotr Danilewski, Philipp Slusallek
Domain-specific languages are becoming increasingly important. Almost every application touches multiple domains. But how to define, use, and combine multiple DSLs within the same…
Building Code with Dynamic Staging
Piotr Danilewski, Philipp Slusallek
When creating a new domain-specific language (DSL) it is common to embed it as a part of a flexible host language, rather than creating it entirely from scratch. The semantics of a…
Towards a living earth simulator
M. Paolucci, D. Kossman, R. Conte +17
The Living Earth Simulator (LES) is one of the core components of the FuturICT architecture. It will work as a federation of methods, tools, techniques and facilities supporting al…