Polarimetric Information for Multi-Modal 6D Pose Estimation of Photometrically Challenging Objects with Limited Data
This addresses pose estimation limitations for objects with difficult visual properties, offering a novel multi-modal solution that is incremental in its extension to self-supervision.
The paper tackles 6D pose estimation for photometrically challenging objects like textureless or reflective surfaces by proposing a supervised method using polarimetric information and extending it to a self-supervised approach, achieving significant advancements without annotated real data.
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 complementary polarisation information as input modality is proposed to overcome such limitations. This supervised approach is then extended to a self-supervised paradigm by leveraging physical characteristics of polarised light, thus eliminating the need for annotated real data. The methods achieve significant advancements in pose estimation by leveraging geometric information from polarised light and incorporating shape priors and invertible physical constraints.