P
Peter R. Florence
Researcher at Massachusetts Institute of Technology
Publications - 47
Citations - 4539
Peter R. Florence is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Computer science & Reinforcement learning. The author has an hindex of 16, co-authored 31 publications receiving 1625 citations. Previous affiliations of Peter R. Florence include Princeton University & Google.
Papers
More filters
Proceedings ArticleDOI
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation
TL;DR: DeepSDF as mentioned in this paper represents a shape's surface by a continuous volumetric field: the magnitude of a point in the field represents the distance to the surface boundary and the sign indicates whether the region is inside (-) or outside (+) of the shape.
Posted Content
iNeRF: Inverting Neural Radiance Fields for Pose Estimation
Lin Yen-Chen,Peter R. Florence,Jonathan T. Barron,Alberto Rodriguez,Phillip Isola,Tsung-Yi Lin +5 more
TL;DR: iNeRF can perform categorylevel object pose estimation, including object instances not seen during training, with RGB images by inverting a NeRF model inferred from a single view.
Dense Object Nets: Learning Dense Visual Object Descriptors By and For Robotic Manipulation
TL;DR: In this article, a self-supervised dense object representation for visual understanding and manipulation is proposed, which can be trained in approximately 20 minutes for a wide variety of previously unseen and potentially non-rigid objects.
Posted Content
kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation.
TL;DR: A novel formulation of category-level manipulation that uses semantic 3D keypoints as the object representation enables a simple and interpretable specification of the manipulation target as geometric costs and constraints on the keypoints, which flexibly generalizes existing pose-based manipulation methods.
Proceedings ArticleDOI
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Andy Zeng,Adrian S. Wong,Stefan Welker,Krzysztof Choromanski,Federico Tombari,Aveek R. Purohit,Michael S. Ryoo,Vikas Sindhwani,Johnny Lee,Vincent Vanhoucke,Peter R. Florence +10 more
TL;DR: This work shows that model diversity is symbiotic, and can be leveraged to build AI systems with structured Socratic dialogue – in which new multimodal tasks are formulated as a guided language- based exchange between different pre-existing foundation models, without additional language-based exchange.