Fully Convolutional Geometric Features for Category-level Object Alignment
This addresses a domain-specific challenge in computer vision for object mapping, but it is incremental as it builds on existing category-level registration methods.
The paper tackles the problem of pose registration for different object instances within the same category, which is needed for online object mapping when test instances differ from training ones, and it achieves accurate alignment by generating matching points through fully convolutional geometric features.
This paper focuses on pose registration of different object instances from the same category. This is required in online object mapping because object instances detected at test time usually differ from the training instances. Our approach transforms instances of the same category to a normalized canonical coordinate frame and uses metric learning to train fully convolutional geometric features. The resulting model is able to generate pairs of matching points between the instances, allowing category-level registration. Evaluation on both synthetic and real-world data shows that our method provides robust features, leading to accurate alignment of instances with different shapes.