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 • 30 Nov 2023 • Daoyi Gao, Dávid Rozenberszki, Stefan Leutenegger, Angela Dai
We formulate this as a conditional generative task, leveraging diffusion to learn implicit probabilistic models capturing the shape, pose, and scale of CAD objects in an image.
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 • 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.