Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Swedish, Tristan"'
Autor:
Sundar, Varun, Ardelean, Andrei, Swedish, Tristan, Bruschini, Claudio, Charbon, Edoardo, Gupta, Mohit
Reinterpretable cameras are defined by their post-processing capabilities that exceed traditional imaging. We present "SoDaCam" that provides reinterpretable cameras at the granularity of photons, from photon-cubes acquired by single-photon devices.
Externí odkaz:
http://arxiv.org/abs/2309.00066
Autor:
Sadhu, Subhash Chandra, Singh, Abhishek, Maeda, Tomohiro, Swedish, Tristan, Kim, Ryan, Sinha, Lagnojita, Raskar, Ramesh
Time of flight based Non-line-of-sight (NLOS) imaging approaches require precise calibration of illumination and detector positions on the visible scene to produce reasonable results. If this calibration error is sufficiently high, reconstruction can
Externí odkaz:
http://arxiv.org/abs/2105.10603
Seeing around corners, also known as non-line-of-sight (NLOS) imaging is a computational method to resolve or recover objects hidden around corners. Recent advances in imaging around corners have gained significant interest. This paper reviews differ
Externí odkaz:
http://arxiv.org/abs/1910.05613
Autor:
Sharma, Vivek, Vepakomma, Praneeth, Swedish, Tristan, Chang, Ken, Kalpathy-Cramer, Jayashree, Raskar, Ramesh
Recently, there has been the development of Split Learning, a framework for distributed computation where model components are split between the client and server (Vepakomma et al., 2018b). As Split Learning scales to include many different model com
Externí odkaz:
http://arxiv.org/abs/1910.03731
Autor:
Sharma, Vivek, Vepakomma, Praneeth, Swedish, Tristan, Chang, Ken, Kalpathy-Cramer, Jayashree, Raskar, Ramesh
In this work we introduce ExpertMatcher, a method for automating deep learning model selection using autoencoders. Specifically, we are interested in performing inference on data sources that are distributed across many clients using pretrained exper
Externí odkaz:
http://arxiv.org/abs/1910.02312
We discuss a data market technique based on intrinsic (relevance and uniqueness) as well as extrinsic value (influenced by supply and demand) of data. For intrinsic value, we explain how to perform valuation of data in absolute terms (i.e just by its
Externí odkaz:
http://arxiv.org/abs/1905.06462
We survey distributed deep learning models for training or inference without accessing raw data from clients. These methods aim to protect confidential patterns in data while still allowing servers to train models. The distributed deep learning metho
Externí odkaz:
http://arxiv.org/abs/1812.03288
Can health entities collaboratively train deep learning models without sharing sensitive raw data? This paper proposes several configurations of a distributed deep learning method called SplitNN to facilitate such collaborations. SplitNN does not sha
Externí odkaz:
http://arxiv.org/abs/1812.00564
Over the recent years, there has been an explosion of studies on autonomous vehicles. Many collected large amount of data from human drivers. However, compared to the tedious data collection approach, building a virtual simulation of traffic makes th
Externí odkaz:
http://arxiv.org/abs/1810.12552
Autor:
Swedish, Tristan
Images of everyday scenes often contain hidden information that can be extracted to localize objects outside the view of the camera and to see around corners. For example, we show that it is possible to look at shadows cast by an object on a table, s
Externí odkaz:
https://hdl.handle.net/1721.1/151975