793 citations
- ETH ZurichCH5 papers
- Max Planck Institute for Intelligent SystemsDE5 papers
- University of AmsterdamNL5 papers
- University of PittsburghUS5 papers
- Max Planck SocietyDE4 papers
- Deakin UniversityAU3 papers
- École Polytechnique Fédérale de LausanneCH3 papers
- Imperial College LondonGB3 papers
- Intelligent Health (United Kingdom)GB3 papers
- Massachusetts Institute of TechnologyUS3 papers
- Seoul National UniversityKR3 papers
- Tsinghua UniversityCN3 papers
19 papers · 1 filter
Neural Rendering for Sensor Adaptation in 3D Object Detection
Felix Embacher, David Holtz, Jonas Uhrig +2
Autonomous vehicles often have varying camera sensor setups, which is inevitable due to restricted placement options for different vehicle types. Training a perception model on one…
ESMStereo: Enhanced ShuffleMixer Disparity Upsampling for Real-Time and Accurate Stereo Matching
Mahmoud Tahmasebi, Saif Huq, Kevin Meehan +1
Stereo matching has become an increasingly important component of modern autonomous systems. Developing deep learning-based stereo matching models that deliver high accuracy while…
Feature-Preserving Mesh Decimation for Normal Integration
Moritz Heep, Sven Behnke, Eduard Zell
Normal integration reconstructs 3D surfaces from normal maps obtained e.g. by photometric stereo. These normal maps capture surface details down to the pixel level but require larg…
Establishing Reality-Virtuality Interconnections in Urban Digital Twins for Superior Intelligent Road Inspection and Simulation
Yikang Zhang, Chuang-Wei Liu, Jiahang Li +3
Road inspection is crucial for maintaining road serviceability and ensuring traffic safety, as road defects gradually develop and compromise functionality. Traditional inspection m…
DCVSMNet: Double Cost Volume Stereo Matching Network
Mahmoud Tahmasebi, Saif Huq, Kevin Meehan +1
We introduce Double Cost Volume Stereo Matching Network(DCVSMNet) which is a novel architecture characterised by by two small upper (group-wise) and lower (norm correlation) cost v…
Hypernymization of named entity-rich captions for grounding-based multi-modal pretraining
Giacomo Nebbia, Adriana Kovashka
Named entities are ubiquitous in text that naturally accompanies images, especially in domains such as news or Wikipedia articles. In previous work, named entities have been identi…