no code implementations • 2 Dec 2023 • Patrick Ruhkamp, Daoyi Gao, Nassir Navab, Benjamin Busam
The novel training paradigm comprises 1) a physical model to extract geometric information of polarized light, 2) a teacher-student knowledge distillation scheme and 3) a self-supervised loss formulation through differentiable rendering and an invertible physical constraint.
no code implementations • 21 Aug 2023 • Patrick Ruhkamp, Daoyi Gao, HyunJun Jung, Nassir Navab, Benjamin Busam
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.
no code implementations • 21 Aug 2023 • HyunJun Jung, Patrick Ruhkamp, Nassir Navab, Benjamin Busam
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.
1 code implementation • CVPR 2023 • HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai, Nikolas Brasch, Yitong Li, Yannick Verdie, Jifei Song, Yiren Zhou, Anil Armagan, Slobodan Ilic, Ales Leonardis, Nassir Navab, Benjamin Busam
Learning-based methods to solve dense 3D vision problems typically train on 3D sensor data.
1 code implementation • 20 Dec 2022 • HyunJun Jung, Guangyao Zhai, Shun-Cheng Wu, Patrick Ruhkamp, Hannah Schieber, Giulia Rizzoli, Pengyuan Wang, Hongcheng Zhao, Lorenzo Garattoni, Sven Meier, Daniel Roth, Nassir Navab, Benjamin Busam
Estimating 6D object poses is a major challenge in 3D computer vision.
no code implementations • 9 May 2022 • HyunJun Jung, Patrick Ruhkamp, Guangyao Zhai, Nikolas Brasch, Yitong Li, Yannick Verdie, Jifei Song, Yiren Zhou, Anil Armagan, Slobodan Ilic, Ales Leonardis, Benjamin Busam
Depth estimation is a core task in 3D computer vision.
1 code implementation • 22 Dec 2021 • Henrique Siqueira, Patrick Ruhkamp, Ibrahim Halfaoui, Markus Karmann, Onay Urfalioglu
Learnable keypoint detectors and descriptors are beginning to outperform classical hand-crafted feature extraction methods.
no code implementations • 7 Dec 2021 • Daoyi Gao, Yitong Li, Patrick Ruhkamp, Iuliia Skobleva, Magdalena Wysock, HyunJun Jung, Pengyuan Wang, Arturo Guridi, Benjamin Busam
Light has many properties that vision sensors can passively measure.
no code implementations • 15 Oct 2021 • Patrick Ruhkamp, Daoyi Gao, Hanzhi Chen, Nassir Navab, Benjamin Busam
A novel temporal attention mechanism further processes the local geometric information in a global context across consecutive images.
no code implementations • 31 Jul 2020 • Patrick Ruhkamp, Ruiqi Gong, Nassir Navab, Benjamin Busam
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.
no code implementations • 5 Apr 2018 • Benjamin Busam, Patrick Ruhkamp, Salvatore Virga, Beatrice Lentes, Julia Rackerseder, Nassir Navab, Christoph Hennersperger
Tracking of rotation and translation of medical instruments plays a substantial role in many modern interventions.