PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation with Photometrically Challenging Objects

TL;DR

PhoCaL is a comprehensive multi-modal dataset designed for category-level object pose estimation, featuring photometrically challenging objects like reflective and transparent items, with high-precision annotations to advance robotic and AR applications.

Contribution

The paper introduces PhoCaL, a novel dataset with high-quality annotations for category-level pose estimation of challenging objects, supported by a new multi-modal data collection and annotation process.

Findings

State-of-the-art methods perform variably on PhoCaL

Photometrically challenging objects remain difficult for current algorithms

PhoCaL provides a new benchmark for future research

Abstract

Object pose estimation is crucial for robotic applications and augmented reality. Beyond instance level 6D object pose estimation methods, estimating category-level pose and shape has become a promising trend. As such, a new research field needs to be supported by well-designed datasets. To provide a benchmark with high-quality ground truth annotations to the community, we introduce a multimodal dataset for category-level object pose estimation with photometrically challenging objects termed PhoCaL. PhoCaL comprises 60 high quality 3D models of household objects over 8 categories including highly reflective, transparent and symmetric objects. We developed a novel robot-supported multi-modal (RGB, depth, polarisation) data acquisition and annotation process. It ensures sub-millimeter accuracy of the pose for opaque textured, shiny and transparent objects, no motion blur and perfect camera synchronisation. To set a benchmark for our dataset, state-of-the-art RGB-D and monocular RGB methods are evaluated on the challenging scenes of PhoCaL.