Closing the Visual Sim-to-Real Gap with Object-Composable NeRFs

N Mishra, M Sieb, P Abbeel, X Chen - arXiv preprint arXiv:2403.04114, 2024 - arxiv.org
Deep learning methods for perception are the cornerstone of many robotic systems. Despite
their potential for impressive performance, obtaining real-world training data is expensive …

Learning Polynomial Representations of Physical Objects with Application to Certifying Correct Packing Configurations

M Jones - arXiv preprint arXiv:2312.06791, 2023 - arxiv.org
This paper introduces a novel approach for learning polynomial representations of physical
objects. Given a point cloud data set associated with a physical object, we solve a one-class …