Publications (8)
DepthSynth: Real-Time Realistic Synthetic Data Generation from CAD Models for 2.5D Recognition
Benjamin Planche, Ziyan Wu, Kai Ma +7
Recent progress in computer vision has been dominated by deep neural networks trained over large amounts of labeled data. Collecting such datasets is however a tedious, often impos…
Smart sensors network for accurate indirect heat accounting in apartment buildings
Yves Stauffer, Fabio Saba, Rafael E. Carrillo +3
A new method for accurate indirect heat accounting in apartment buildings has been recently developed by the Centre Suisse d'Electronique et de Microtechnique (CSEM). It is based o…
Seeing Beyond Appearance - Mapping Real Images into Geometrical Domains for Unsupervised CAD-based Recognition
Benjamin Planche, Sergey Zakharov, Ziyan Wu +3
While convolutional neural networks are dominating the field of computer vision, one usually does not have access to the large amount of domain-relevant data needed for their train…
A hybrid learning method for system identification and optimal control
Baptiste Schubnel, Rafael E. Carrillo, Pierre-Jean Alet +1
We present a three-step method to perform system identification and optimal control of non-linear systems. Our approach is mainly data driven and does not require active excitation…
3D Object Instance Recognition and Pose Estimation Using Triplet Loss with Dynamic Margin
Sergey Zakharov, Wadim Kehl, Benjamin Planche +2
In this paper, we address the problem of 3D object instance recognition and pose estimation of localized objects in cluttered environments using convolutional neural networks. Insp…
Keep it Unreal: Bridging the Realism Gap for 2.5D Recognition with Geometry Priors Only
Sergey Zakharov, Benjamin Planche, Ziyan Wu +3
With the increasing availability of large databases of 3D CAD models, depth-based recognition methods can be trained on an uncountable number of synthetically rendered images. Howe…
Incremental Scene Synthesis
Benjamin Planche, Xuejian Rong, Ziyan Wu +5
We present a method to incrementally generate complete 2D or 3D scenes with the following properties: (a) it is globally consistent at each step according to a learned scene prior,…
NeRF-Feat: 6D Object Pose Estimation using Feature Rendering
Shishir Reddy Vutukur, Heike Brock, Benjamin Busam +3
Object Pose Estimation is a crucial component in robotic grasping and augmented reality. Learning based approaches typically require training data from a highly accurate CAD model…