66 citations · 103 across the 6 of their papers we have counts for
6 papers
Quant-Trim in Practice: Improved Cross-Platform Low-Bit Deployment on Edge NPUs
Rayen Dhahri, Steffen Urban
Specialized edge accelerators rely on low-bit quantization, but vendor compilers differ in scaling, clipping, and kernel support, often as black boxes. The same floating-point (FP)…
On the Issues of TrueDepth Sensor Data for Computer Vision Tasks Across Different iPad Generations
Steffen Urban, Thomas Lindemeier, David Dobbelstein +1
In 2017 Apple introduced the TrueDepth sensor with the iPhone X release. Although its primary use case is biometric face recognition, the exploitation of accurate depth data for ot…
Point Cloud Upsampling and Normal Estimation using Deep Learning for Robust Surface Reconstruction
Rajat Sharma, Tobias Schwandt, Christian Kunert +2
The reconstruction of real-world surfaces is on high demand in various applications. Most existing reconstruction approaches apply 3D scanners for creating point clouds which are g…
mdBrief - A Fast Online Adaptable, Distorted Binary Descriptor for Real-Time Applications Using Calibrated Wide-Angle Or Fisheye Cameras
Steffen Urban, Stefan Hinz
Fast binary descriptors build the core for many vision based applications with real-time demands like object detection, Visual Odometry or SLAM. Commonly it is assumed, that the ac…
MultiCol-SLAM - A Modular Real-Time Multi-Camera SLAM System
Steffen Urban, Stefan Hinz
The basis for most vision based applications like robotics, self-driving cars and potentially augmented and virtual reality is a robust, continuous estimation of the position and o…
MLPnP - A Real-Time Maximum Likelihood Solution to the Perspective-n-Point Problem
Steffen Urban, Jens Leitloff, Stefan Hinz
In this paper, a statistically optimal solution to the Perspective-n-Point (PnP) problem is presented. Many solutions to the PnP problem are geometrically optimal, but do not consi…