Talking Papers Podcast
Talking Papers Podcast: deep dives into research papers in computer vision, 3D, machine learning, and AI, with the authors who wrote them. Where research meets conversation. By researchers, for researchers.
Each episode is structured like the paper itself: a TL;DR / abstract to set the stage, then related work, approach, results, conclusions, and future work. We close with a bonus segment called "What did Reviewer 2 say?", where the authors share the candid peer-review story behind the publication.
Hosted by Itzik Ben-Shabat. Guests are PhD students, postdocs, and faculty from leading labs across academia and industry. Aimed at fellow researchers and graduate students who want the candid version of the work, not a polished press release.
Talking Papers Podcast
Despoina Paschalidou - Neural Parts
Use Left/Right to seek, Home/End to jump to start or end. Hold shift to jump forward or backward.
PAPER TITLE
Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks
AUTHORS
Despoina Paschalidou , Angelos Katharopoulos, Andreas Geiger, Sanja Fidler
ABSTRACT
Impressive progress in 3D shape extraction led to representations that can capture object geometries with high fidelity. In parallel, primitive-based methods seek to represent objects as semantically consistent part arrangements. However, due to the simplicity of existing primitive representations, these methods fail to accurately reconstruct 3D shapes using a small number of primitives/parts. We address the trade-off between reconstruction quality and number of parts with Neural Parts, a novel 3D primitive representation that defines primitives using an Invertible Neural Network (INN) which implements homeomorphic mappings between a sphere and the target object. The INN allows us to compute the inverse mapping of the homomorphism, which in turn, enables the efficient computation of both the implicit surface function of a primitive and its mesh, without any additional post-processing. Our model learns to parse 3D objects into semantically consistent part arrangements without any part-level supervision. Evaluations on ShapeNet, D-FAUST and FreiHAND demonstrate that our primitives can capture complex geometries and thus simultaneously achieve geometrically accurate as well as interpretable reconstructions using an order of magnitude fewer primitives than state-of-the-art shape abstraction methods.
RELATED PAPERS
📚 "KeypointDeformer: Unsupervised 3D Keypoint Discovery for Shape Control"
📚 "Learning Shape Abstractions by Assembling Volumetric Primitives": Volumetric primitives"
📚 "Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids"
📚 "CvxNet: Learnable Convex Decomposition"
📚 "Neural Star Domain as Primitive Representation"
LINKS AND RESOURCES
💻 Project Page: https://paschalidoud.github.io/neural_parts
💻 CODE: https://github.com/paschalidoud/neural_parts
CONTACT
If you would like to be a guest, sponsor or just share your thoughts, feel free to reach out via email: talking.papers.podcast@gmail.com
SUBSCRIBE AND FOLLOW
🎧Subscribe on your favourite podcast app: https://talking.papers.podcast.itzikbs.com
📧Subscribe to our mailing list: http://eepurl.com/hRznqb
🐦Follow us on Twitter: https://twitter.com/talking_papers
🎥YouTube Channel: https://bit.ly/3eQOgwP
This episode was recorded on April, 25th 2021.
🎧Subscribe on your favourite podcast app: https://talking.papers.podcast.itzikbs.com
📧Subscribe to our mailing list: http://eepurl.com/hRznqb
🐦Follow us on Twitter: https://twitter.com/talking_papers
🎥YouTube Channel: https://bit.ly/3eQOgwP
