• Publications
  • Influence
RGBD-fusion: Real-time high precision depth recovery
TLDR
The popularity of low-cost RGB-D scanners is increasing on a daily basis. Expand
  • 92
  • 9
  • PDF
Duckietown: An open, inexpensive and flexible platform for autonomy education and research
  • L. Paull, J. Tani, +27 authors A. Censi
  • Computer Science, Engineering
  • IEEE International Conference on Robotics and…
  • 1 May 2017
TLDR
We present “Duckietown,” an open, inexpensive and flexible platform for autonomy education and research. Expand
  • 76
  • 9
  • PDF
A Mixture of Manhattan Frames: Beyond the Manhattan World
TLDR
We propose a novel probabilistic model that describes the world as a mixture of Manhattan frames: each frame defines a different orthogonal coordinate system. Expand
  • 52
  • 9
  • PDF
Artificial Intelligence in Surgery: Promises and Perils
Objective: The aim of this review was to summarize major topics in artificial intelligence (AI), including their applications and limitations in surgery. This paper reviews the key capabilities of AIExpand
  • 148
  • 4
  • PDF
Variational End-to-End Navigation and Localization
TLDR
Deep learning has revolutionized the ability to learn “end-to-end” autonomous vehicle control directly from raw sensory data. Expand
  • 46
  • 3
  • PDF
Patch‐Collaborative Spectral Point‐Cloud Denoising
TLDR
We present a new framework for point cloud denoising by patch‐collaborative spectral analysis. Expand
  • 38
  • 3
  • PDF
Uncertainty-Aware Driver Trajectory Prediction at Urban Intersections
TLDR
We show how to augment the variational predictor with a physics-based predictor, and based on their confidence estimations, improve overall system performance. Expand
  • 30
  • 3
  • PDF
DiversityGAN: Diversity-Aware Vehicle Motion Prediction via Latent Semantic Sampling
TLDR
We propose a novel approach for generating realistic and diverse vehicle trajectories. Expand
  • 11
  • 3
  • PDF
Coresets for k-Segmentation of Streaming Data
TLDR
We develop real-time algorithms for summarization and segmentation of large streams, by compressing the signals into a compact meaningful representation. Expand
  • 37
  • 2
  • PDF
The Manhattan Frame Model—Manhattan World Inference in the Space of Surface Normals
TLDR
We introduce the Manhattan Frame (MF) model which captures the notion of an MW in the surface normals space, the unit sphere, and two probabilistic MF models over this space. Expand
  • 31
  • 2
  • PDF
...
1
2
3
4
5
...