Patrick Ruhkamp
YOU?
Author Swipe
S$$^{2}$$P$$^{3}$$: Self-Supervised Polarimetric Pose Prediction Open
This paper proposes the first self-supervised 6D object pose prediction from multimodal RGB + polarimetric images. The novel training paradigm comprises (1) a physical model to extract geometric information of polarized light, (2) a teache…
S2P3: Self-Supervised Polarimetric Pose Prediction Open
This paper proposes the first self-supervised 6D object pose prediction from multimodal RGB+polarimetric images. The novel training paradigm comprises 1) a physical model to extract geometric information of polarized light, 2) a teacher-st…
Multi-Modal Dataset Acquisition for Photometrically Challenging Object Open
This paper addresses the limitations of current datasets for 3D vision tasks in terms of accuracy, size, realism, and suitable imaging modalities for photometrically challenging objects. We propose a novel annotation and acquisition pipeli…
Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Data Open
6D pose estimation pipelines that rely on RGB-only or RGB-D data show limitations for photometrically challenging objects with e.g. textureless surfaces, reflections or transparency. A supervised learning-based method utilising complementa…
On the Importance of Accurate Geometry Data for Dense 3D Vision Tasks Open
Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data. The respectively used principle of measuring distances provides advantages and drawbacks. These are typically not compared nor discussed in the lit…
HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios Open
Estimating 6D object poses is a major challenge in 3D computer vision. Building on successful instance-level approaches, research is shifting towards category-level pose estimation for practical applications. Current category-level dataset…
Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression Open
Depth estimation is a core task in 3D computer vision. Recent methods investigate the task of monocular depth trained with various depth sensor modalities. Every sensor has its advantages and drawbacks caused by the nature of estimates. In…
Robotic Framework for Autonomous Assembly: a Report from the Robothon 2021 Grand Challenge Open
Up to now, many repetitive industrial processes, like welding in automotive, have been automated. However, robust solutions for assembly operations that, besides precise robot positioning, also require precise tactile interaction are not a…
Towards Remote Robotic Competitions: An Internet-Connected Task Board and Dashboard Open
In this work we present a platform to assess robot platform skills using an internet-of-things (IoT) task board device to aggregate performances across remote sites. We demonstrate a concept for a modular, scale-able device and web dashboa…
Looking Beyond Corners: Contrastive Learning of Visual Representations for Keypoint Detection and Description Extraction Open
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods. Recent studies on self-supervised learning of visual representations have driven the increasing performance of lear…
Polarimetric Pose Prediction Open
Light has many properties that vision sensors can passively measure. Colour-band separated wavelength and intensity are arguably the most commonly used for monocular 6D object pose estimation. This paper explores how complementary polarisa…
Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for Consistent Self-Supervised Monocular Depth Estimation Open
Inferring geometrically consistent dense 3D scenes across a tuple of temporally consecutive images remains challenging for self-supervised monocular depth prediction pipelines. This paper explores how the increasingly popular transformer a…
Attention meets Geometry: Geometry Guided Spatial-Temporal Attention for\n Consistent Self-Supervised Monocular Depth Estimation Open
Inferring geometrically consistent dense 3D scenes across a tuple of\ntemporally consecutive images remains challenging for self-supervised monocular\ndepth prediction pipelines. This paper explores how the increasingly popular\ntransforme…
DynaMiTe: A Dynamic Local Motion Model with Temporal Constraints for Robust Real-Time Feature Matching Open
Feature based visual odometry and SLAM methods require accurate and fast correspondence matching between consecutive image frames for precise camera pose estimation in real-time. Current feature matching pipelines either rely solely on the…
Markerless Inside-Out Tracking for Interventional Applications Open
Tracking of rotation and translation of medical instruments plays a substantial role in many modern interventions. Traditional external optical tracking systems are often subject to line-of-sight issues, in particular when the region of in…