More Like this

1. PartDistillation: Learning Parts from Instance Segmentation

   https://doi.org/10.1109/CVPR52729.2023.00691  

   Cho, Jang Hyun; Krähenbühl, Philipp; Ramanathan, Vignesh (June 2023, IEEE)
2. Virtual Inspection of Additively Manufactured Parts

   https://doi.org/10.1109/PacificVis53943.2022.00017  

   Klacansky, Pavol; Miao, Haichao; Gyulassy, Attila; Townsend, Andrew; Champley, Kyle; Tringe, Joseph; Pascucci, Valerio; Bremer, Peer-Timo (April 2022, 2022 IEEE 15th Pacific Visualization Symposium (PacificVis))
3. Megahertz Light Steering Without Moving Parts

   https://doi.org/10.1109/CVPR52729.2023.00009  

   Pediredla, Adithya; Narasimhan, Srinivasa G.; Chamanzar, Maysamreza; Gkioulekas, Ioannis (June 2023, IEEE)
4. Pricing Analytics for Rotable Spare Parts

   https://doi.org/10.1287/inte.2020.1033  

   Besbes, Omar; Elmachtoub, Adam N.; Sun, Yunjie (September 2020, INFORMS Journal on Applied Analytics)

   null (Ed.)

   In this paper, we describe a comprehensive approach to pricing analytics for reusable resources in the context of rotable spare parts, which are parts that can be repeatedly repaired and resold. Working in collaboration with a major aircraft manufacturer, we aim to instill a new pricing culture and develop a scalable new pricing methodology. Pricing rotable spare parts presents unique challenges ranging from complex inventory dynamics and minimal demand information to limited data availability. We develop a novel pricing analytics approach that tackles all of these challenges and that can be applied across all rotable spare parts. We then describe a large-scale implementation of our approach with our industrial partner, which led to an improvement in profits of over 3.9% over a 10-month period. 

   more » « less
5. Visual Identification of Articulated Object Parts

   Zeng, V.; Lee, T.; Liang, J.; Kroemer, O. (October 2021, Proceedings of the IEEERSJ International Conference on Intelligent Robots and Systems)

   null (Ed.)

   As autonomous robots interact and navigate around real-world environments such as homes, it is useful to reliably identify and manipulate articulated objects, such as doors and cabinets. Many prior works in object articulation identification require manipulation of the object, either by the robot or a human. While recent works have addressed predicting articulation types from visual observations alone, they often assume prior knowledge of category-level kinematic motion models or sequence of observations where the articulated parts are moving according to their kinematic constraints. In this work, we propose FormNet, a neural network that identifies the articulation mechanisms between pairs of object parts from a single frame of an RGB-D image and segmentation masks. The network is trained on 100k synthetic images of 149 articulated objects from 6 categories. Synthetic images are rendered via a photorealistic simulator with domain randomization. Our proposed model predicts motion residual flows of object parts, and these flows are used to determine the articulation type and parameters. The network achieves an articulation type classification accuracy of 82.5% on novel object instances in trained categories. Experiments also show how this method enables generalization to novel categories and can be applied to real-world images without fine-tuning. 

   more » « less