On Object Symmetries and 6D Pose Estimation from Images
Objects with symmetries are common in our daily life and in industrial contexts, but are often ignored in the recent literature on 6D pose estimation from images. In this paper, we study in an analytical way the link between the symmetries of a 3D object and its appearance in images. We explain why symmetrical objects can be a challenge when training machine learning algorithms that aim at estimating their 6D pose from images. We propose an efficient and simple solution that relies on the normalization of the pose rotation. Our approach is general and can be used with any 6D pose estimation algorithm. Moreover, our method is also beneficial for objects that are 'almost symmetrical', i.e. objects for which only a detail breaks the symmetry. We validate our approach within a Faster-RCNN framework on a synthetic dataset made with objects from the T-Less dataset, which exhibit various types of symmetries, as well as real sequences from T-Less.
Code (1)
Tasks
6D Pose EstimationObjectPose EstimationSimilar Papers 제목 키워드 기반
Symmetry Aware Evaluation of 3D Object Detection and Pose Estimation in Scenes of Many Parts in Bulk
While 3D object detection and pose estimation has been studied for a long time, its evaluation is not yet completely satisfactory. Indeed, existing datasets typically consist in numerous acquisitions of only a few scenes…
3D Object DetectionObjectobject-detectionObject Detection+1Learning Implicit Probability Distribution Functions for Symmetric Orientation Estimation from RGB Images Without Pose Labels
Object pose estimation is a necessary prerequisite for autonomous robotic manipulation, but the presence of symmetry increases the complexity of the pose estimation task. Existing methods for object pose estimation outpu…
ObjectPoint Cloud RegistrationPose EstimationRelPose++: Recovering 6D Poses from Sparse-view Observations
We address the task of estimating 6D camera poses from sparse-view image sets (2-8 images). This task is a vital pre-processing stage for nearly all contemporary (neural) reconstruction algorithms but remains challenging…
3D ReconstructionPose EstimationPose PredictionModelling and unsupervised learning of symmetric deformable object categories
We propose a new approach to model and learn, without manual supervision, the symmetries of natural objects, such as faces or flowers, given only images as input. It is well known that objects that have a symmetric struc…
ObjectSymmetryNet: Learning to Predict Reflectional and Rotational Symmetries of 3D Shapes from Single-View RGB-D Images
We study the problem of symmetry detection of 3D shapes from single-view RGB-D images, where severely missing data renders geometric detection approach infeasible. We propose an end-to-end deep neural network which is ab…
Multi-Task LearningSymmetry Detection