Learning Upright and Forward-Facing Object Poses using Category-level Canonical Representations

Constructing a unified canonical pose representation for 3D object categories is crucial for pose estimation and robotic scene understanding. Previous unified pose representations often relied on manual alignment, such as in ShapeNet and ModelNet. Recently, self-supervised canonicalization methods have been proposed, However, they are sensitive to intra-class shape variations, and their canonical pose representations cannot be aligned to a coordinate system centered on the object. In this paper, we propose a category-level canonicalization method that alleviates the impact of shape variation and extends the canonical pose representation to an upright and forward-facing state. First, we design a Siamese Vector Neurons Module (SVNM) that achieves SE(3) equivariance modeling and self-supervised disentangling of 3D shape and pose attributes. Next, we introduce a Siamese equivariant constraint that addresses the pose alignment bias caused by shape deformation. Finally, we propose a method to generate upright surface labels from pose-unknown in-the-wild data and use upright and symmetry losses to correct the canonical pose. Experimental results show that our method not only achieves SOTA consistency performance but also aligns with the object-centered coordinate system. Project page: https://anon-mity.github.io/upright-facing/

Authors

• Bing Han
• Ruitao Pan
• Xinyu Zhang
• Chenxi Wang 0004
• Zhi Zhai
• Zhibin Zhao 0002
• Xuefeng Chen 0002

Keywords

• Solid modeling
• Three-dimensional displays
• Shape
• Robot kinematics
• Pose estimation
• Neurons
• Manuals
• Robot sensing systems
• Vectors
• Intelligent robots
• Object Pose
• Canonical Representation
• Coordinate System
• Impact Of Variables
• Shape Variation
• Intra-class Variance
• Surface Labeling
• Point Cloud
• Multilayer Perceptron
• Singular Value Decomposition
• Airplane
• Forward Direction
• Binding Pose
• Gradient Separation
• Angular Deviation
• Point Cloud Data
• Shape Representation
• Human Pose Estimation
• Gradient Loss
• Chamfer Distance
• Aligned Dataset